{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 93733, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 5.334300619845732e-05, "grad_norm": 4.451326304751513, "learning_rate": 4.267121826328142e-08, "loss": 0.9738, "num_tokens": 29342.0, "step": 5 }, { "epoch": 0.00010668601239691465, "grad_norm": 5.033802415471702, "learning_rate": 9.60102410923832e-08, "loss": 0.9023, "num_tokens": 63798.0, "step": 10 }, { "epoch": 0.00016002901859537197, "grad_norm": 3.1126589904250497, "learning_rate": 1.4934926392148497e-07, "loss": 0.7405, "num_tokens": 99300.0, "step": 15 }, { "epoch": 0.0002133720247938293, "grad_norm": 17.1762780803618, "learning_rate": 2.0268828675058673e-07, "loss": 1.0216, "num_tokens": 120300.0, "step": 20 }, { "epoch": 0.0002667150309922866, "grad_norm": 4.465357399257684, "learning_rate": 2.5602730957968847e-07, "loss": 0.8756, "num_tokens": 146226.0, "step": 25 }, { "epoch": 0.00032005803719074394, "grad_norm": 3.2761292547611283, "learning_rate": 3.093663324087903e-07, "loss": 0.9112, "num_tokens": 188241.0, "step": 30 }, { "epoch": 0.00037340104338920123, "grad_norm": 3.768362486208382, "learning_rate": 3.6270535523789204e-07, "loss": 0.8953, "num_tokens": 213850.0, "step": 35 }, { "epoch": 0.0004267440495876586, "grad_norm": 10.486425955742359, "learning_rate": 4.1604437806699386e-07, "loss": 0.8548, "num_tokens": 245103.0, "step": 40 }, { "epoch": 0.0004800870557861159, "grad_norm": 2.738668685615406, "learning_rate": 4.693834008960956e-07, "loss": 0.8172, "num_tokens": 287454.0, "step": 45 }, { "epoch": 0.0005334300619845732, "grad_norm": 3.0420431372562273, "learning_rate": 5.227224237251973e-07, "loss": 0.8084, "num_tokens": 303132.0, "step": 50 }, { "epoch": 0.0005867730681830305, "grad_norm": 2.5433988386079456, "learning_rate": 5.760614465542991e-07, "loss": 0.7609, "num_tokens": 336459.0, "step": 55 }, { "epoch": 0.0006401160743814879, "grad_norm": 2.7740922420700884, "learning_rate": 6.29400469383401e-07, "loss": 0.7485, "num_tokens": 378513.0, "step": 60 }, { "epoch": 0.0006934590805799452, "grad_norm": 2.8356785479782594, "learning_rate": 6.827394922125027e-07, "loss": 0.879, "num_tokens": 414758.0, "step": 65 }, { "epoch": 0.0007468020867784025, "grad_norm": 2.710215247517447, "learning_rate": 7.360785150416045e-07, "loss": 0.7396, "num_tokens": 445228.0, "step": 70 }, { "epoch": 0.0008001450929768598, "grad_norm": 4.2428371591996665, "learning_rate": 7.894175378707062e-07, "loss": 0.9078, "num_tokens": 473757.0, "step": 75 }, { "epoch": 0.0008534880991753172, "grad_norm": 2.9858054740879156, "learning_rate": 8.42756560699808e-07, "loss": 0.6662, "num_tokens": 495890.0, "step": 80 }, { "epoch": 0.0009068311053737745, "grad_norm": 2.5613175792733607, "learning_rate": 8.960955835289099e-07, "loss": 0.7762, "num_tokens": 531358.0, "step": 85 }, { "epoch": 0.0009601741115722318, "grad_norm": 3.043060525528482, "learning_rate": 9.494346063580116e-07, "loss": 0.6751, "num_tokens": 555313.0, "step": 90 }, { "epoch": 0.001013517117770689, "grad_norm": 3.671195835189716, "learning_rate": 1.0027736291871133e-06, "loss": 0.8321, "num_tokens": 578739.0, "step": 95 }, { "epoch": 0.0010668601239691464, "grad_norm": 4.222458345364644, "learning_rate": 1.056112652016215e-06, "loss": 0.781, "num_tokens": 607883.0, "step": 100 }, { "epoch": 0.0011202031301676036, "grad_norm": 4.573465459490853, "learning_rate": 1.1094516748453168e-06, "loss": 0.7248, "num_tokens": 633028.0, "step": 105 }, { "epoch": 0.001173546136366061, "grad_norm": 1.8909780498965516, "learning_rate": 1.1627906976744186e-06, "loss": 0.6974, "num_tokens": 678413.0, "step": 110 }, { "epoch": 0.0012268891425645185, "grad_norm": 2.800731135347133, "learning_rate": 1.2161297205035203e-06, "loss": 0.7657, "num_tokens": 709362.0, "step": 115 }, { "epoch": 0.0012802321487629758, "grad_norm": 4.6262569431166725, "learning_rate": 1.2694687433326223e-06, "loss": 0.7389, "num_tokens": 736808.0, "step": 120 }, { "epoch": 0.001333575154961433, "grad_norm": 2.3033926007485634, "learning_rate": 1.322807766161724e-06, "loss": 0.7836, "num_tokens": 773571.0, "step": 125 }, { "epoch": 0.0013869181611598903, "grad_norm": 3.774645507059957, "learning_rate": 1.3761467889908258e-06, "loss": 0.5705, "num_tokens": 787961.0, "step": 130 }, { "epoch": 0.0014402611673583476, "grad_norm": 2.735466193379792, "learning_rate": 1.4294858118199274e-06, "loss": 0.7091, "num_tokens": 820742.0, "step": 135 }, { "epoch": 0.001493604173556805, "grad_norm": 2.4350235147195693, "learning_rate": 1.4828248346490291e-06, "loss": 0.8115, "num_tokens": 849466.0, "step": 140 }, { "epoch": 0.0015469471797552622, "grad_norm": 2.3974674607644846, "learning_rate": 1.5361638574781311e-06, "loss": 0.7009, "num_tokens": 866917.0, "step": 145 }, { "epoch": 0.0016002901859537195, "grad_norm": 2.6932989892914696, "learning_rate": 1.589502880307233e-06, "loss": 0.7593, "num_tokens": 901511.0, "step": 150 }, { "epoch": 0.0016536331921521768, "grad_norm": 2.5642091667540314, "learning_rate": 1.6428419031363346e-06, "loss": 0.7141, "num_tokens": 930361.0, "step": 155 }, { "epoch": 0.0017069761983506343, "grad_norm": 2.978308931740302, "learning_rate": 1.6961809259654362e-06, "loss": 0.7494, "num_tokens": 949600.0, "step": 160 }, { "epoch": 0.0017603192045490916, "grad_norm": 2.626690996172547, "learning_rate": 1.7495199487945382e-06, "loss": 0.8107, "num_tokens": 970713.0, "step": 165 }, { "epoch": 0.001813662210747549, "grad_norm": 3.7660111360612345, "learning_rate": 1.80285897162364e-06, "loss": 0.7037, "num_tokens": 1007633.0, "step": 170 }, { "epoch": 0.0018670052169460062, "grad_norm": 2.206981331147623, "learning_rate": 1.856197994452742e-06, "loss": 0.7126, "num_tokens": 1042356.0, "step": 175 }, { "epoch": 0.0019203482231444635, "grad_norm": 3.870046474127697, "learning_rate": 1.9095370172818435e-06, "loss": 0.724, "num_tokens": 1066853.0, "step": 180 }, { "epoch": 0.001973691229342921, "grad_norm": 1.7549705471986983, "learning_rate": 1.9628760401109454e-06, "loss": 0.8219, "num_tokens": 1110129.0, "step": 185 }, { "epoch": 0.002027034235541378, "grad_norm": 3.165848633325654, "learning_rate": 2.016215062940047e-06, "loss": 0.7546, "num_tokens": 1143253.0, "step": 190 }, { "epoch": 0.0020803772417398356, "grad_norm": 2.468814350800813, "learning_rate": 2.0695540857691485e-06, "loss": 0.6787, "num_tokens": 1185102.0, "step": 195 }, { "epoch": 0.0021337202479382927, "grad_norm": 2.638646527012755, "learning_rate": 2.1228931085982505e-06, "loss": 0.6435, "num_tokens": 1226902.0, "step": 200 }, { "epoch": 0.00218706325413675, "grad_norm": 2.4174701871854136, "learning_rate": 2.176232131427352e-06, "loss": 0.6045, "num_tokens": 1254030.0, "step": 205 }, { "epoch": 0.0022404062603352073, "grad_norm": 2.674540954530446, "learning_rate": 2.229571154256454e-06, "loss": 0.7854, "num_tokens": 1295367.0, "step": 210 }, { "epoch": 0.002293749266533665, "grad_norm": 4.558050863599099, "learning_rate": 2.282910177085556e-06, "loss": 0.6682, "num_tokens": 1336069.0, "step": 215 }, { "epoch": 0.002347092272732122, "grad_norm": 2.777309910813694, "learning_rate": 2.336249199914658e-06, "loss": 0.6163, "num_tokens": 1363737.0, "step": 220 }, { "epoch": 0.0024004352789305794, "grad_norm": 3.070015171834906, "learning_rate": 2.3895882227437595e-06, "loss": 0.9052, "num_tokens": 1407634.0, "step": 225 }, { "epoch": 0.002453778285129037, "grad_norm": 3.4517104418542424, "learning_rate": 2.442927245572861e-06, "loss": 0.644, "num_tokens": 1429600.0, "step": 230 }, { "epoch": 0.002507121291327494, "grad_norm": 2.625873295821217, "learning_rate": 2.496266268401963e-06, "loss": 0.7192, "num_tokens": 1452470.0, "step": 235 }, { "epoch": 0.0025604642975259515, "grad_norm": 2.712178521652603, "learning_rate": 2.5496052912310646e-06, "loss": 0.6053, "num_tokens": 1480979.0, "step": 240 }, { "epoch": 0.0026138073037244086, "grad_norm": 2.1422831359138064, "learning_rate": 2.6029443140601666e-06, "loss": 0.726, "num_tokens": 1513788.0, "step": 245 }, { "epoch": 0.002667150309922866, "grad_norm": 3.0227545761453314, "learning_rate": 2.656283336889268e-06, "loss": 0.6759, "num_tokens": 1554180.0, "step": 250 }, { "epoch": 0.002720493316121323, "grad_norm": 3.0778777648689135, "learning_rate": 2.70962235971837e-06, "loss": 0.6148, "num_tokens": 1574901.0, "step": 255 }, { "epoch": 0.0027738363223197807, "grad_norm": 2.58606366612496, "learning_rate": 2.7629613825474716e-06, "loss": 0.5954, "num_tokens": 1600341.0, "step": 260 }, { "epoch": 0.0028271793285182378, "grad_norm": 2.0374668912557268, "learning_rate": 2.8163004053765736e-06, "loss": 0.7139, "num_tokens": 1641730.0, "step": 265 }, { "epoch": 0.0028805223347166953, "grad_norm": 3.780844812664666, "learning_rate": 2.8696394282056756e-06, "loss": 0.7051, "num_tokens": 1671686.0, "step": 270 }, { "epoch": 0.002933865340915153, "grad_norm": 2.2099436158525467, "learning_rate": 2.922978451034777e-06, "loss": 0.5335, "num_tokens": 1692759.0, "step": 275 }, { "epoch": 0.00298720834711361, "grad_norm": 1.9922886364841275, "learning_rate": 2.976317473863879e-06, "loss": 0.7106, "num_tokens": 1722270.0, "step": 280 }, { "epoch": 0.0030405513533120674, "grad_norm": 3.050267212786454, "learning_rate": 3.0296564966929807e-06, "loss": 0.7566, "num_tokens": 1745639.0, "step": 285 }, { "epoch": 0.0030938943595105245, "grad_norm": 2.2588089796167523, "learning_rate": 3.0829955195220826e-06, "loss": 0.5794, "num_tokens": 1778268.0, "step": 290 }, { "epoch": 0.003147237365708982, "grad_norm": 2.6179250469246726, "learning_rate": 3.1363345423511846e-06, "loss": 0.5963, "num_tokens": 1807721.0, "step": 295 }, { "epoch": 0.003200580371907439, "grad_norm": 2.6604673652510376, "learning_rate": 3.1896735651802857e-06, "loss": 0.6099, "num_tokens": 1829677.0, "step": 300 }, { "epoch": 0.0032539233781058966, "grad_norm": 2.4201213247696476, "learning_rate": 3.2430125880093877e-06, "loss": 0.6603, "num_tokens": 1860278.0, "step": 305 }, { "epoch": 0.0033072663843043536, "grad_norm": 2.5460594026040217, "learning_rate": 3.2963516108384897e-06, "loss": 0.6414, "num_tokens": 1892294.0, "step": 310 }, { "epoch": 0.003360609390502811, "grad_norm": 2.7216331685396575, "learning_rate": 3.3496906336675912e-06, "loss": 0.7021, "num_tokens": 1915601.0, "step": 315 }, { "epoch": 0.0034139523967012687, "grad_norm": 3.200151471511676, "learning_rate": 3.403029656496693e-06, "loss": 0.473, "num_tokens": 1933925.0, "step": 320 }, { "epoch": 0.0034672954028997257, "grad_norm": 3.1653524331519804, "learning_rate": 3.456368679325795e-06, "loss": 0.6723, "num_tokens": 1965851.0, "step": 325 }, { "epoch": 0.0035206384090981833, "grad_norm": 3.5318563533103675, "learning_rate": 3.509707702154897e-06, "loss": 0.6179, "num_tokens": 1980535.0, "step": 330 }, { "epoch": 0.0035739814152966403, "grad_norm": 1.927606884527476, "learning_rate": 3.5630467249839983e-06, "loss": 0.6054, "num_tokens": 2020414.0, "step": 335 }, { "epoch": 0.003627324421495098, "grad_norm": 4.359140482815659, "learning_rate": 3.6163857478131003e-06, "loss": 0.6114, "num_tokens": 2052137.0, "step": 340 }, { "epoch": 0.003680667427693555, "grad_norm": 2.260913371647579, "learning_rate": 3.6697247706422022e-06, "loss": 0.6072, "num_tokens": 2096412.0, "step": 345 }, { "epoch": 0.0037340104338920124, "grad_norm": 2.115818738979165, "learning_rate": 3.7230637934713034e-06, "loss": 0.7353, "num_tokens": 2127213.0, "step": 350 }, { "epoch": 0.0037873534400904695, "grad_norm": 3.1244399833428447, "learning_rate": 3.7764028163004053e-06, "loss": 0.567, "num_tokens": 2148182.0, "step": 355 }, { "epoch": 0.003840696446288927, "grad_norm": 2.432008723948822, "learning_rate": 3.829741839129508e-06, "loss": 0.5919, "num_tokens": 2173491.0, "step": 360 }, { "epoch": 0.0038940394524873845, "grad_norm": 2.4060938293972547, "learning_rate": 3.883080861958609e-06, "loss": 0.6194, "num_tokens": 2199803.0, "step": 365 }, { "epoch": 0.003947382458685842, "grad_norm": 2.5986061886907437, "learning_rate": 3.936419884787711e-06, "loss": 0.6032, "num_tokens": 2226865.0, "step": 370 }, { "epoch": 0.004000725464884299, "grad_norm": 2.276947510628256, "learning_rate": 3.989758907616812e-06, "loss": 0.6704, "num_tokens": 2274500.0, "step": 375 }, { "epoch": 0.004054068471082756, "grad_norm": 2.965486827838171, "learning_rate": 4.043097930445915e-06, "loss": 0.675, "num_tokens": 2303108.0, "step": 380 }, { "epoch": 0.004107411477281214, "grad_norm": 2.2773827450766153, "learning_rate": 4.0964369532750155e-06, "loss": 0.6418, "num_tokens": 2321312.0, "step": 385 }, { "epoch": 0.004160754483479671, "grad_norm": 1.8292059509758571, "learning_rate": 4.149775976104118e-06, "loss": 0.6342, "num_tokens": 2350340.0, "step": 390 }, { "epoch": 0.004214097489678128, "grad_norm": 3.9757130008231294, "learning_rate": 4.203114998933219e-06, "loss": 0.4998, "num_tokens": 2374617.0, "step": 395 }, { "epoch": 0.004267440495876585, "grad_norm": 2.914352443406278, "learning_rate": 4.256454021762322e-06, "loss": 0.6944, "num_tokens": 2403607.0, "step": 400 }, { "epoch": 0.004320783502075043, "grad_norm": 2.625548776547604, "learning_rate": 4.309793044591423e-06, "loss": 0.6452, "num_tokens": 2435971.0, "step": 405 }, { "epoch": 0.0043741265082735, "grad_norm": 2.622552203661941, "learning_rate": 4.363132067420525e-06, "loss": 0.6661, "num_tokens": 2453120.0, "step": 410 }, { "epoch": 0.004427469514471958, "grad_norm": 4.256730614197613, "learning_rate": 4.416471090249627e-06, "loss": 0.6492, "num_tokens": 2469134.0, "step": 415 }, { "epoch": 0.004480812520670415, "grad_norm": 2.7139299258239094, "learning_rate": 4.469810113078728e-06, "loss": 0.5127, "num_tokens": 2492392.0, "step": 420 }, { "epoch": 0.004534155526868872, "grad_norm": 2.719178381413541, "learning_rate": 4.52314913590783e-06, "loss": 0.6455, "num_tokens": 2517750.0, "step": 425 }, { "epoch": 0.00458749853306733, "grad_norm": 3.0856400082578324, "learning_rate": 4.576488158736932e-06, "loss": 0.6324, "num_tokens": 2538847.0, "step": 430 }, { "epoch": 0.004640841539265787, "grad_norm": 2.4180027887095537, "learning_rate": 4.629827181566034e-06, "loss": 0.6321, "num_tokens": 2561840.0, "step": 435 }, { "epoch": 0.004694184545464244, "grad_norm": 3.915955073050681, "learning_rate": 4.683166204395135e-06, "loss": 0.625, "num_tokens": 2594816.0, "step": 440 }, { "epoch": 0.004747527551662701, "grad_norm": 1.795741268611148, "learning_rate": 4.7365052272242375e-06, "loss": 0.4736, "num_tokens": 2620677.0, "step": 445 }, { "epoch": 0.004800870557861159, "grad_norm": 2.0570237005637515, "learning_rate": 4.789844250053339e-06, "loss": 0.6487, "num_tokens": 2646623.0, "step": 450 }, { "epoch": 0.004854213564059616, "grad_norm": 2.0373940285513292, "learning_rate": 4.8431832728824406e-06, "loss": 0.532, "num_tokens": 2675255.0, "step": 455 }, { "epoch": 0.004907556570258074, "grad_norm": 2.1784462821588533, "learning_rate": 4.896522295711543e-06, "loss": 0.6314, "num_tokens": 2703128.0, "step": 460 }, { "epoch": 0.0049608995764565305, "grad_norm": 2.30712982995254, "learning_rate": 4.9498613185406445e-06, "loss": 0.6596, "num_tokens": 2735724.0, "step": 465 }, { "epoch": 0.005014242582654988, "grad_norm": 4.118205852749781, "learning_rate": 5.003200341369747e-06, "loss": 0.5405, "num_tokens": 2749101.0, "step": 470 }, { "epoch": 0.0050675855888534455, "grad_norm": 2.680095832037963, "learning_rate": 5.056539364198848e-06, "loss": 0.5884, "num_tokens": 2778153.0, "step": 475 }, { "epoch": 0.005120928595051903, "grad_norm": 3.7213962299880907, "learning_rate": 5.10987838702795e-06, "loss": 0.7308, "num_tokens": 2810063.0, "step": 480 }, { "epoch": 0.00517427160125036, "grad_norm": 1.8821032463063232, "learning_rate": 5.1632174098570516e-06, "loss": 0.5641, "num_tokens": 2835907.0, "step": 485 }, { "epoch": 0.005227614607448817, "grad_norm": 1.9611533910818022, "learning_rate": 5.216556432686153e-06, "loss": 0.5722, "num_tokens": 2865331.0, "step": 490 }, { "epoch": 0.005280957613647275, "grad_norm": 2.660380570953238, "learning_rate": 5.269895455515255e-06, "loss": 0.5287, "num_tokens": 2881153.0, "step": 495 }, { "epoch": 0.005334300619845732, "grad_norm": 2.039534461895729, "learning_rate": 5.323234478344357e-06, "loss": 0.702, "num_tokens": 2912508.0, "step": 500 }, { "epoch": 0.00538764362604419, "grad_norm": 2.5514094172956705, "learning_rate": 5.376573501173459e-06, "loss": 0.7238, "num_tokens": 2934566.0, "step": 505 }, { "epoch": 0.005440986632242646, "grad_norm": 1.9647452366532636, "learning_rate": 5.42991252400256e-06, "loss": 0.5993, "num_tokens": 2955940.0, "step": 510 }, { "epoch": 0.005494329638441104, "grad_norm": 2.0195598733706004, "learning_rate": 5.4832515468316626e-06, "loss": 0.5623, "num_tokens": 2980898.0, "step": 515 }, { "epoch": 0.005547672644639561, "grad_norm": 1.8206334909410893, "learning_rate": 5.536590569660764e-06, "loss": 0.6629, "num_tokens": 3000137.0, "step": 520 }, { "epoch": 0.005601015650838019, "grad_norm": 2.798664042659382, "learning_rate": 5.5899295924898665e-06, "loss": 0.5562, "num_tokens": 3027053.0, "step": 525 }, { "epoch": 0.0056543586570364755, "grad_norm": 2.453030275284941, "learning_rate": 5.643268615318967e-06, "loss": 0.722, "num_tokens": 3048120.0, "step": 530 }, { "epoch": 0.005707701663234933, "grad_norm": 3.368432789663426, "learning_rate": 5.69660763814807e-06, "loss": 0.6595, "num_tokens": 3074745.0, "step": 535 }, { "epoch": 0.0057610446694333906, "grad_norm": 3.71065088477825, "learning_rate": 5.749946660977171e-06, "loss": 0.5544, "num_tokens": 3101765.0, "step": 540 }, { "epoch": 0.005814387675631848, "grad_norm": 2.543408805218537, "learning_rate": 5.803285683806273e-06, "loss": 0.7628, "num_tokens": 3146811.0, "step": 545 }, { "epoch": 0.005867730681830306, "grad_norm": 2.4228941284969103, "learning_rate": 5.856624706635374e-06, "loss": 0.638, "num_tokens": 3191145.0, "step": 550 }, { "epoch": 0.005921073688028762, "grad_norm": 2.8461417701955765, "learning_rate": 5.909963729464477e-06, "loss": 0.6222, "num_tokens": 3223066.0, "step": 555 }, { "epoch": 0.00597441669422722, "grad_norm": 2.10906524510095, "learning_rate": 5.963302752293578e-06, "loss": 0.54, "num_tokens": 3245647.0, "step": 560 }, { "epoch": 0.006027759700425677, "grad_norm": 2.964977967967938, "learning_rate": 6.01664177512268e-06, "loss": 0.6098, "num_tokens": 3276090.0, "step": 565 }, { "epoch": 0.006081102706624135, "grad_norm": 3.4218003629726157, "learning_rate": 6.069980797951782e-06, "loss": 0.5272, "num_tokens": 3310979.0, "step": 570 }, { "epoch": 0.006134445712822591, "grad_norm": 2.7386780983930166, "learning_rate": 6.123319820780884e-06, "loss": 0.7414, "num_tokens": 3343219.0, "step": 575 }, { "epoch": 0.006187788719021049, "grad_norm": 2.4613659709365527, "learning_rate": 6.176658843609985e-06, "loss": 0.5941, "num_tokens": 3374871.0, "step": 580 }, { "epoch": 0.006241131725219506, "grad_norm": 2.4524778420804827, "learning_rate": 6.229997866439087e-06, "loss": 0.5267, "num_tokens": 3395331.0, "step": 585 }, { "epoch": 0.006294474731417964, "grad_norm": 2.489434157763007, "learning_rate": 6.283336889268189e-06, "loss": 0.6471, "num_tokens": 3433842.0, "step": 590 }, { "epoch": 0.0063478177376164215, "grad_norm": 1.5859238038549404, "learning_rate": 6.336675912097291e-06, "loss": 0.623, "num_tokens": 3472404.0, "step": 595 }, { "epoch": 0.006401160743814878, "grad_norm": 2.9987409979947963, "learning_rate": 6.390014934926393e-06, "loss": 0.6501, "num_tokens": 3502530.0, "step": 600 }, { "epoch": 0.006454503750013336, "grad_norm": 1.578444189307962, "learning_rate": 6.443353957755494e-06, "loss": 0.6194, "num_tokens": 3547293.0, "step": 605 }, { "epoch": 0.006507846756211793, "grad_norm": 2.1398811335334456, "learning_rate": 6.496692980584595e-06, "loss": 0.662, "num_tokens": 3586453.0, "step": 610 }, { "epoch": 0.006561189762410251, "grad_norm": 4.431815126470482, "learning_rate": 6.550032003413698e-06, "loss": 0.5708, "num_tokens": 3609756.0, "step": 615 }, { "epoch": 0.006614532768608707, "grad_norm": 4.463147642476886, "learning_rate": 6.603371026242799e-06, "loss": 0.5861, "num_tokens": 3624393.0, "step": 620 }, { "epoch": 0.006667875774807165, "grad_norm": 2.1549292633840107, "learning_rate": 6.656710049071902e-06, "loss": 0.5542, "num_tokens": 3663718.0, "step": 625 }, { "epoch": 0.006721218781005622, "grad_norm": 3.437451771904971, "learning_rate": 6.710049071901003e-06, "loss": 0.6542, "num_tokens": 3692559.0, "step": 630 }, { "epoch": 0.00677456178720408, "grad_norm": 2.6310262251012833, "learning_rate": 6.763388094730106e-06, "loss": 0.5988, "num_tokens": 3722446.0, "step": 635 }, { "epoch": 0.006827904793402537, "grad_norm": 2.466520192796315, "learning_rate": 6.8167271175592055e-06, "loss": 0.6107, "num_tokens": 3759146.0, "step": 640 }, { "epoch": 0.006881247799600994, "grad_norm": 2.1834426840852266, "learning_rate": 6.870066140388308e-06, "loss": 0.562, "num_tokens": 3795871.0, "step": 645 }, { "epoch": 0.0069345908057994515, "grad_norm": 3.398247434867917, "learning_rate": 6.9234051632174095e-06, "loss": 0.5688, "num_tokens": 3813635.0, "step": 650 }, { "epoch": 0.006987933811997909, "grad_norm": 2.046848728541157, "learning_rate": 6.976744186046512e-06, "loss": 0.5105, "num_tokens": 3845613.0, "step": 655 }, { "epoch": 0.0070412768181963665, "grad_norm": 3.067314017243531, "learning_rate": 7.0300832088756134e-06, "loss": 0.5381, "num_tokens": 3861195.0, "step": 660 }, { "epoch": 0.007094619824394823, "grad_norm": 5.375047700239235, "learning_rate": 7.083422231704716e-06, "loss": 0.4823, "num_tokens": 3876808.0, "step": 665 }, { "epoch": 0.007147962830593281, "grad_norm": 2.1842928058495708, "learning_rate": 7.136761254533817e-06, "loss": 0.6601, "num_tokens": 3900845.0, "step": 670 }, { "epoch": 0.007201305836791738, "grad_norm": 4.515831040320595, "learning_rate": 7.19010027736292e-06, "loss": 0.6351, "num_tokens": 3929266.0, "step": 675 }, { "epoch": 0.007254648842990196, "grad_norm": 2.9462644825073974, "learning_rate": 7.2434393001920205e-06, "loss": 0.5316, "num_tokens": 3951559.0, "step": 680 }, { "epoch": 0.007307991849188653, "grad_norm": 1.9601035454792122, "learning_rate": 7.296778323021122e-06, "loss": 0.5522, "num_tokens": 3993048.0, "step": 685 }, { "epoch": 0.00736133485538711, "grad_norm": 1.8881525061150444, "learning_rate": 7.3501173458502244e-06, "loss": 0.6287, "num_tokens": 4021410.0, "step": 690 }, { "epoch": 0.007414677861585567, "grad_norm": 2.125865916617444, "learning_rate": 7.403456368679326e-06, "loss": 0.6666, "num_tokens": 4065733.0, "step": 695 }, { "epoch": 0.007468020867784025, "grad_norm": 3.179413272890471, "learning_rate": 7.456795391508428e-06, "loss": 0.6543, "num_tokens": 4100832.0, "step": 700 }, { "epoch": 0.007521363873982482, "grad_norm": 2.523472630639466, "learning_rate": 7.51013441433753e-06, "loss": 0.5723, "num_tokens": 4121683.0, "step": 705 }, { "epoch": 0.007574706880180939, "grad_norm": 3.570399832671642, "learning_rate": 7.563473437166632e-06, "loss": 0.5991, "num_tokens": 4149860.0, "step": 710 }, { "epoch": 0.0076280498863793966, "grad_norm": 2.725944484804011, "learning_rate": 7.616812459995733e-06, "loss": 0.6946, "num_tokens": 4172247.0, "step": 715 }, { "epoch": 0.007681392892577854, "grad_norm": 2.6488292007385703, "learning_rate": 7.670151482824835e-06, "loss": 0.6257, "num_tokens": 4202971.0, "step": 720 }, { "epoch": 0.007734735898776312, "grad_norm": 2.3768379516202174, "learning_rate": 7.723490505653937e-06, "loss": 0.6574, "num_tokens": 4227754.0, "step": 725 }, { "epoch": 0.007788078904974769, "grad_norm": 2.1907875258855047, "learning_rate": 7.776829528483039e-06, "loss": 0.6546, "num_tokens": 4267550.0, "step": 730 }, { "epoch": 0.007841421911173227, "grad_norm": 2.7829753185472375, "learning_rate": 7.83016855131214e-06, "loss": 0.8098, "num_tokens": 4309250.0, "step": 735 }, { "epoch": 0.007894764917371684, "grad_norm": 3.649749799209132, "learning_rate": 7.883507574141243e-06, "loss": 0.598, "num_tokens": 4336365.0, "step": 740 }, { "epoch": 0.00794810792357014, "grad_norm": 1.8347653572433118, "learning_rate": 7.936846596970345e-06, "loss": 0.666, "num_tokens": 4373127.0, "step": 745 }, { "epoch": 0.008001450929768597, "grad_norm": 3.0434434212163053, "learning_rate": 7.990185619799445e-06, "loss": 0.6179, "num_tokens": 4410686.0, "step": 750 }, { "epoch": 0.008054793935967055, "grad_norm": 2.888916755394829, "learning_rate": 8.043524642628546e-06, "loss": 0.6543, "num_tokens": 4442365.0, "step": 755 }, { "epoch": 0.008108136942165512, "grad_norm": 3.0909164587782785, "learning_rate": 8.09686366545765e-06, "loss": 0.571, "num_tokens": 4481940.0, "step": 760 }, { "epoch": 0.00816147994836397, "grad_norm": 2.2764445596019725, "learning_rate": 8.150202688286751e-06, "loss": 0.5598, "num_tokens": 4510914.0, "step": 765 }, { "epoch": 0.008214822954562427, "grad_norm": 2.7175792768105045, "learning_rate": 8.203541711115853e-06, "loss": 0.6158, "num_tokens": 4539216.0, "step": 770 }, { "epoch": 0.008268165960760885, "grad_norm": 2.775327532436684, "learning_rate": 8.256880733944954e-06, "loss": 0.5781, "num_tokens": 4564712.0, "step": 775 }, { "epoch": 0.008321508966959342, "grad_norm": 3.2498145280497055, "learning_rate": 8.310219756774057e-06, "loss": 0.5829, "num_tokens": 4586421.0, "step": 780 }, { "epoch": 0.0083748519731578, "grad_norm": 22.17257989031318, "learning_rate": 8.363558779603157e-06, "loss": 0.6282, "num_tokens": 4602105.0, "step": 785 }, { "epoch": 0.008428194979356256, "grad_norm": 3.154862559147727, "learning_rate": 8.416897802432259e-06, "loss": 0.5903, "num_tokens": 4629653.0, "step": 790 }, { "epoch": 0.008481537985554713, "grad_norm": 2.2457394067195406, "learning_rate": 8.470236825261362e-06, "loss": 0.6294, "num_tokens": 4679041.0, "step": 795 }, { "epoch": 0.00853488099175317, "grad_norm": 3.7961347176249025, "learning_rate": 8.523575848090464e-06, "loss": 0.474, "num_tokens": 4718430.0, "step": 800 }, { "epoch": 0.008588223997951628, "grad_norm": 4.207824349702711, "learning_rate": 8.576914870919565e-06, "loss": 0.6887, "num_tokens": 4750070.0, "step": 805 }, { "epoch": 0.008641567004150086, "grad_norm": 4.802085165247283, "learning_rate": 8.630253893748667e-06, "loss": 0.6845, "num_tokens": 4784730.0, "step": 810 }, { "epoch": 0.008694910010348543, "grad_norm": 3.712053767388168, "learning_rate": 8.68359291657777e-06, "loss": 0.65, "num_tokens": 4810063.0, "step": 815 }, { "epoch": 0.008748253016547, "grad_norm": 4.379900396580583, "learning_rate": 8.73693193940687e-06, "loss": 0.6067, "num_tokens": 4829324.0, "step": 820 }, { "epoch": 0.008801596022745458, "grad_norm": 4.1055900766966005, "learning_rate": 8.790270962235971e-06, "loss": 0.5774, "num_tokens": 4856405.0, "step": 825 }, { "epoch": 0.008854939028943916, "grad_norm": 3.6673581141683522, "learning_rate": 8.843609985065075e-06, "loss": 0.6066, "num_tokens": 4890090.0, "step": 830 }, { "epoch": 0.008908282035142372, "grad_norm": 2.42573486096563, "learning_rate": 8.896949007894176e-06, "loss": 0.5232, "num_tokens": 4911071.0, "step": 835 }, { "epoch": 0.00896162504134083, "grad_norm": 2.752884801032895, "learning_rate": 8.950288030723278e-06, "loss": 0.7688, "num_tokens": 4941763.0, "step": 840 }, { "epoch": 0.009014968047539287, "grad_norm": 2.945662635192546, "learning_rate": 9.00362705355238e-06, "loss": 0.6037, "num_tokens": 4961139.0, "step": 845 }, { "epoch": 0.009068311053737744, "grad_norm": 2.597624101453087, "learning_rate": 9.056966076381482e-06, "loss": 0.6201, "num_tokens": 4989986.0, "step": 850 }, { "epoch": 0.009121654059936202, "grad_norm": 2.1524251710751963, "learning_rate": 9.110305099210582e-06, "loss": 0.5887, "num_tokens": 5011963.0, "step": 855 }, { "epoch": 0.00917499706613466, "grad_norm": 3.4498318007172597, "learning_rate": 9.163644122039684e-06, "loss": 0.6434, "num_tokens": 5040511.0, "step": 860 }, { "epoch": 0.009228340072333117, "grad_norm": 2.900073729675512, "learning_rate": 9.216983144868785e-06, "loss": 0.6272, "num_tokens": 5067770.0, "step": 865 }, { "epoch": 0.009281683078531574, "grad_norm": 2.3797010168666106, "learning_rate": 9.270322167697889e-06, "loss": 0.7377, "num_tokens": 5099782.0, "step": 870 }, { "epoch": 0.009335026084730032, "grad_norm": 2.3721455749375284, "learning_rate": 9.32366119052699e-06, "loss": 0.6596, "num_tokens": 5130075.0, "step": 875 }, { "epoch": 0.009388369090928488, "grad_norm": 2.421492693788271, "learning_rate": 9.377000213356092e-06, "loss": 0.5913, "num_tokens": 5162362.0, "step": 880 }, { "epoch": 0.009441712097126945, "grad_norm": 2.161048536525354, "learning_rate": 9.430339236185193e-06, "loss": 0.6111, "num_tokens": 5189368.0, "step": 885 }, { "epoch": 0.009495055103325403, "grad_norm": 2.521767059351796, "learning_rate": 9.483678259014295e-06, "loss": 0.8098, "num_tokens": 5224815.0, "step": 890 }, { "epoch": 0.00954839810952386, "grad_norm": 2.3498040293386806, "learning_rate": 9.537017281843396e-06, "loss": 0.6576, "num_tokens": 5257791.0, "step": 895 }, { "epoch": 0.009601741115722318, "grad_norm": 4.091307017483774, "learning_rate": 9.590356304672498e-06, "loss": 0.5543, "num_tokens": 5276351.0, "step": 900 }, { "epoch": 0.009655084121920775, "grad_norm": 1.9191029561441557, "learning_rate": 9.643695327501601e-06, "loss": 0.5261, "num_tokens": 5319827.0, "step": 905 }, { "epoch": 0.009708427128119233, "grad_norm": 2.9034537582739897, "learning_rate": 9.697034350330703e-06, "loss": 0.8532, "num_tokens": 5354130.0, "step": 910 }, { "epoch": 0.00976177013431769, "grad_norm": 3.7257940197723856, "learning_rate": 9.750373373159804e-06, "loss": 0.6102, "num_tokens": 5395432.0, "step": 915 }, { "epoch": 0.009815113140516148, "grad_norm": 3.272040871785404, "learning_rate": 9.803712395988906e-06, "loss": 0.598, "num_tokens": 5418735.0, "step": 920 }, { "epoch": 0.009868456146714603, "grad_norm": 4.3136824280973105, "learning_rate": 9.857051418818007e-06, "loss": 0.6537, "num_tokens": 5439630.0, "step": 925 }, { "epoch": 0.009921799152913061, "grad_norm": 3.4762032400965963, "learning_rate": 9.910390441647109e-06, "loss": 0.6137, "num_tokens": 5463435.0, "step": 930 }, { "epoch": 0.009975142159111518, "grad_norm": 2.8827225694753413, "learning_rate": 9.96372946447621e-06, "loss": 0.502, "num_tokens": 5481273.0, "step": 935 }, { "epoch": 0.010028485165309976, "grad_norm": 2.6675651398914173, "learning_rate": 1.0017068487305314e-05, "loss": 0.6354, "num_tokens": 5522316.0, "step": 940 }, { "epoch": 0.010081828171508433, "grad_norm": 3.170583965634891, "learning_rate": 1.0070407510134415e-05, "loss": 0.6239, "num_tokens": 5542913.0, "step": 945 }, { "epoch": 0.010135171177706891, "grad_norm": 2.2434770108721107, "learning_rate": 1.0123746532963517e-05, "loss": 0.6372, "num_tokens": 5585203.0, "step": 950 }, { "epoch": 0.010188514183905348, "grad_norm": 2.5791768363196392, "learning_rate": 1.0177085555792618e-05, "loss": 0.7383, "num_tokens": 5619512.0, "step": 955 }, { "epoch": 0.010241857190103806, "grad_norm": 3.2130603902911457, "learning_rate": 1.023042457862172e-05, "loss": 0.6873, "num_tokens": 5644524.0, "step": 960 }, { "epoch": 0.010295200196302264, "grad_norm": 2.4942161186180507, "learning_rate": 1.0283763601450822e-05, "loss": 0.5528, "num_tokens": 5672982.0, "step": 965 }, { "epoch": 0.01034854320250072, "grad_norm": 1.9264744940113596, "learning_rate": 1.0337102624279923e-05, "loss": 0.5971, "num_tokens": 5701031.0, "step": 970 }, { "epoch": 0.010401886208699177, "grad_norm": 2.14922246032407, "learning_rate": 1.0390441647109025e-05, "loss": 0.5791, "num_tokens": 5735391.0, "step": 975 }, { "epoch": 0.010455229214897634, "grad_norm": 1.6575435614128202, "learning_rate": 1.0443780669938128e-05, "loss": 0.6274, "num_tokens": 5778417.0, "step": 980 }, { "epoch": 0.010508572221096092, "grad_norm": 2.2359364301029636, "learning_rate": 1.049711969276723e-05, "loss": 0.6834, "num_tokens": 5812926.0, "step": 985 }, { "epoch": 0.01056191522729455, "grad_norm": 2.595447268060081, "learning_rate": 1.0550458715596331e-05, "loss": 0.6632, "num_tokens": 5841665.0, "step": 990 }, { "epoch": 0.010615258233493007, "grad_norm": 3.4334157003858454, "learning_rate": 1.0603797738425433e-05, "loss": 0.6528, "num_tokens": 5876581.0, "step": 995 }, { "epoch": 0.010668601239691464, "grad_norm": 2.299220767659033, "learning_rate": 1.0657136761254534e-05, "loss": 0.6158, "num_tokens": 5908474.0, "step": 1000 }, { "epoch": 0.010721944245889922, "grad_norm": 2.3565647920820583, "learning_rate": 1.0710475784083636e-05, "loss": 0.553, "num_tokens": 5933522.0, "step": 1005 }, { "epoch": 0.01077528725208838, "grad_norm": 2.3109579983107427, "learning_rate": 1.0763814806912737e-05, "loss": 0.6949, "num_tokens": 5957938.0, "step": 1010 }, { "epoch": 0.010828630258286835, "grad_norm": 2.1530922071148053, "learning_rate": 1.081715382974184e-05, "loss": 0.7523, "num_tokens": 5996244.0, "step": 1015 }, { "epoch": 0.010881973264485293, "grad_norm": 2.5906713280118003, "learning_rate": 1.0870492852570942e-05, "loss": 0.591, "num_tokens": 6024812.0, "step": 1020 }, { "epoch": 0.01093531627068375, "grad_norm": 4.440466688148703, "learning_rate": 1.0923831875400044e-05, "loss": 0.5742, "num_tokens": 6061553.0, "step": 1025 }, { "epoch": 0.010988659276882208, "grad_norm": 4.545395054119756, "learning_rate": 1.0977170898229145e-05, "loss": 0.5273, "num_tokens": 6078296.0, "step": 1030 }, { "epoch": 0.011042002283080665, "grad_norm": 2.18770225024128, "learning_rate": 1.1030509921058247e-05, "loss": 0.6192, "num_tokens": 6121440.0, "step": 1035 }, { "epoch": 0.011095345289279123, "grad_norm": 1.8897727976309784, "learning_rate": 1.1083848943887348e-05, "loss": 0.5273, "num_tokens": 6151522.0, "step": 1040 }, { "epoch": 0.01114868829547758, "grad_norm": 3.1971438436613457, "learning_rate": 1.113718796671645e-05, "loss": 0.6636, "num_tokens": 6190109.0, "step": 1045 }, { "epoch": 0.011202031301676038, "grad_norm": 3.2617067100333057, "learning_rate": 1.1190526989545553e-05, "loss": 0.6753, "num_tokens": 6240444.0, "step": 1050 }, { "epoch": 0.011255374307874495, "grad_norm": 3.8482489258330537, "learning_rate": 1.1243866012374655e-05, "loss": 0.6798, "num_tokens": 6276465.0, "step": 1055 }, { "epoch": 0.011308717314072951, "grad_norm": 2.155939249172738, "learning_rate": 1.1297205035203756e-05, "loss": 0.6923, "num_tokens": 6328763.0, "step": 1060 }, { "epoch": 0.011362060320271409, "grad_norm": 3.8368817380654487, "learning_rate": 1.1350544058032856e-05, "loss": 0.6041, "num_tokens": 6348078.0, "step": 1065 }, { "epoch": 0.011415403326469866, "grad_norm": 3.063672452330261, "learning_rate": 1.140388308086196e-05, "loss": 0.5686, "num_tokens": 6374220.0, "step": 1070 }, { "epoch": 0.011468746332668324, "grad_norm": 2.725983198697937, "learning_rate": 1.145722210369106e-05, "loss": 0.6656, "num_tokens": 6404277.0, "step": 1075 }, { "epoch": 0.011522089338866781, "grad_norm": 2.2421618082708688, "learning_rate": 1.1510561126520162e-05, "loss": 0.7145, "num_tokens": 6433062.0, "step": 1080 }, { "epoch": 0.011575432345065239, "grad_norm": 2.874670677669139, "learning_rate": 1.1563900149349264e-05, "loss": 0.5237, "num_tokens": 6466473.0, "step": 1085 }, { "epoch": 0.011628775351263696, "grad_norm": 2.6944775219294117, "learning_rate": 1.1617239172178367e-05, "loss": 0.5993, "num_tokens": 6493001.0, "step": 1090 }, { "epoch": 0.011682118357462154, "grad_norm": 3.5601151075443536, "learning_rate": 1.1670578195007469e-05, "loss": 0.6363, "num_tokens": 6515633.0, "step": 1095 }, { "epoch": 0.011735461363660611, "grad_norm": 3.463613412464829, "learning_rate": 1.1723917217836568e-05, "loss": 0.4978, "num_tokens": 6530763.0, "step": 1100 }, { "epoch": 0.011788804369859067, "grad_norm": 2.715524638827885, "learning_rate": 1.1777256240665672e-05, "loss": 0.5884, "num_tokens": 6550698.0, "step": 1105 }, { "epoch": 0.011842147376057524, "grad_norm": 2.0532506986892383, "learning_rate": 1.1830595263494773e-05, "loss": 0.7076, "num_tokens": 6586747.0, "step": 1110 }, { "epoch": 0.011895490382255982, "grad_norm": 2.61500004835188, "learning_rate": 1.1883934286323875e-05, "loss": 0.6742, "num_tokens": 6624074.0, "step": 1115 }, { "epoch": 0.01194883338845444, "grad_norm": 1.5581508247963871, "learning_rate": 1.1937273309152976e-05, "loss": 0.6498, "num_tokens": 6674546.0, "step": 1120 }, { "epoch": 0.012002176394652897, "grad_norm": 1.7202342190495044, "learning_rate": 1.199061233198208e-05, "loss": 0.6288, "num_tokens": 6719607.0, "step": 1125 }, { "epoch": 0.012055519400851354, "grad_norm": 1.9154334623057112, "learning_rate": 1.2043951354811181e-05, "loss": 0.513, "num_tokens": 6750099.0, "step": 1130 }, { "epoch": 0.012108862407049812, "grad_norm": 2.695980281680344, "learning_rate": 1.2097290377640281e-05, "loss": 0.6776, "num_tokens": 6784095.0, "step": 1135 }, { "epoch": 0.01216220541324827, "grad_norm": 3.6192348344251406, "learning_rate": 1.2150629400469384e-05, "loss": 0.594, "num_tokens": 6800319.0, "step": 1140 }, { "epoch": 0.012215548419446727, "grad_norm": 2.734498019324087, "learning_rate": 1.2203968423298486e-05, "loss": 0.6584, "num_tokens": 6828301.0, "step": 1145 }, { "epoch": 0.012268891425645183, "grad_norm": 2.832606236351937, "learning_rate": 1.2257307446127587e-05, "loss": 0.813, "num_tokens": 6874892.0, "step": 1150 }, { "epoch": 0.01232223443184364, "grad_norm": 1.5506454392393227, "learning_rate": 1.2310646468956689e-05, "loss": 0.6147, "num_tokens": 6911127.0, "step": 1155 }, { "epoch": 0.012375577438042098, "grad_norm": 2.140012281741162, "learning_rate": 1.2363985491785792e-05, "loss": 0.6909, "num_tokens": 6942988.0, "step": 1160 }, { "epoch": 0.012428920444240555, "grad_norm": 3.3046126484934684, "learning_rate": 1.2417324514614894e-05, "loss": 0.5703, "num_tokens": 6977064.0, "step": 1165 }, { "epoch": 0.012482263450439013, "grad_norm": 1.8701856806923154, "learning_rate": 1.2470663537443994e-05, "loss": 0.6218, "num_tokens": 7011591.0, "step": 1170 }, { "epoch": 0.01253560645663747, "grad_norm": 1.6336894670172906, "learning_rate": 1.2524002560273095e-05, "loss": 0.6593, "num_tokens": 7051382.0, "step": 1175 }, { "epoch": 0.012588949462835928, "grad_norm": 2.1352439438412807, "learning_rate": 1.2577341583102198e-05, "loss": 0.5604, "num_tokens": 7073622.0, "step": 1180 }, { "epoch": 0.012642292469034385, "grad_norm": 3.7390604061410553, "learning_rate": 1.26306806059313e-05, "loss": 0.5703, "num_tokens": 7096000.0, "step": 1185 }, { "epoch": 0.012695635475232843, "grad_norm": 2.9275685097789577, "learning_rate": 1.2684019628760401e-05, "loss": 0.6229, "num_tokens": 7118223.0, "step": 1190 }, { "epoch": 0.012748978481431299, "grad_norm": 2.2709070285838115, "learning_rate": 1.2737358651589503e-05, "loss": 0.6012, "num_tokens": 7152420.0, "step": 1195 }, { "epoch": 0.012802321487629756, "grad_norm": 2.6066889578375627, "learning_rate": 1.2790697674418606e-05, "loss": 0.6255, "num_tokens": 7178713.0, "step": 1200 }, { "epoch": 0.012855664493828214, "grad_norm": 4.229350327763845, "learning_rate": 1.2844036697247708e-05, "loss": 0.5991, "num_tokens": 7201015.0, "step": 1205 }, { "epoch": 0.012909007500026671, "grad_norm": 2.612585474967952, "learning_rate": 1.289737572007681e-05, "loss": 0.6486, "num_tokens": 7229661.0, "step": 1210 }, { "epoch": 0.012962350506225129, "grad_norm": 3.281139929817161, "learning_rate": 1.2950714742905911e-05, "loss": 0.6697, "num_tokens": 7255658.0, "step": 1215 }, { "epoch": 0.013015693512423586, "grad_norm": 2.8655750108838696, "learning_rate": 1.3004053765735014e-05, "loss": 0.597, "num_tokens": 7277994.0, "step": 1220 }, { "epoch": 0.013069036518622044, "grad_norm": 2.54606616065361, "learning_rate": 1.3057392788564112e-05, "loss": 0.6647, "num_tokens": 7304532.0, "step": 1225 }, { "epoch": 0.013122379524820501, "grad_norm": 1.6855280437567548, "learning_rate": 1.3110731811393216e-05, "loss": 0.6402, "num_tokens": 7347676.0, "step": 1230 }, { "epoch": 0.013175722531018959, "grad_norm": 1.7453638045692865, "learning_rate": 1.3164070834222317e-05, "loss": 0.6373, "num_tokens": 7374541.0, "step": 1235 }, { "epoch": 0.013229065537217415, "grad_norm": 2.2212458014527146, "learning_rate": 1.3217409857051419e-05, "loss": 0.6839, "num_tokens": 7416529.0, "step": 1240 }, { "epoch": 0.013282408543415872, "grad_norm": 2.7275451226134257, "learning_rate": 1.327074887988052e-05, "loss": 0.6511, "num_tokens": 7448805.0, "step": 1245 }, { "epoch": 0.01333575154961433, "grad_norm": 2.747381464265763, "learning_rate": 1.3324087902709623e-05, "loss": 0.6431, "num_tokens": 7481071.0, "step": 1250 }, { "epoch": 0.013389094555812787, "grad_norm": 2.158383578894424, "learning_rate": 1.3377426925538725e-05, "loss": 0.5065, "num_tokens": 7504296.0, "step": 1255 }, { "epoch": 0.013442437562011245, "grad_norm": 1.9041414392882725, "learning_rate": 1.3430765948367827e-05, "loss": 0.5396, "num_tokens": 7537112.0, "step": 1260 }, { "epoch": 0.013495780568209702, "grad_norm": 2.4219910638038207, "learning_rate": 1.3484104971196928e-05, "loss": 0.6893, "num_tokens": 7574101.0, "step": 1265 }, { "epoch": 0.01354912357440816, "grad_norm": 2.5749847994055832, "learning_rate": 1.3537443994026031e-05, "loss": 0.573, "num_tokens": 7604068.0, "step": 1270 }, { "epoch": 0.013602466580606617, "grad_norm": 2.366288803338944, "learning_rate": 1.3590783016855133e-05, "loss": 0.6617, "num_tokens": 7644556.0, "step": 1275 }, { "epoch": 0.013655809586805075, "grad_norm": 3.6740149699552234, "learning_rate": 1.3644122039684234e-05, "loss": 0.5597, "num_tokens": 7668808.0, "step": 1280 }, { "epoch": 0.01370915259300353, "grad_norm": 3.3116872717756576, "learning_rate": 1.3697461062513336e-05, "loss": 0.7217, "num_tokens": 7683813.0, "step": 1285 }, { "epoch": 0.013762495599201988, "grad_norm": 1.8455614047235889, "learning_rate": 1.375080008534244e-05, "loss": 0.6584, "num_tokens": 7718703.0, "step": 1290 }, { "epoch": 0.013815838605400445, "grad_norm": 2.692813289679306, "learning_rate": 1.3804139108171537e-05, "loss": 0.5995, "num_tokens": 7737318.0, "step": 1295 }, { "epoch": 0.013869181611598903, "grad_norm": 2.5978315455313736, "learning_rate": 1.3857478131000639e-05, "loss": 0.5851, "num_tokens": 7753440.0, "step": 1300 }, { "epoch": 0.01392252461779736, "grad_norm": 1.9870036119441596, "learning_rate": 1.3910817153829742e-05, "loss": 0.6224, "num_tokens": 7785104.0, "step": 1305 }, { "epoch": 0.013975867623995818, "grad_norm": 1.9694885225156682, "learning_rate": 1.3964156176658844e-05, "loss": 0.6308, "num_tokens": 7817015.0, "step": 1310 }, { "epoch": 0.014029210630194276, "grad_norm": 2.653182922906877, "learning_rate": 1.4017495199487945e-05, "loss": 0.5433, "num_tokens": 7833650.0, "step": 1315 }, { "epoch": 0.014082553636392733, "grad_norm": 1.9320311744349559, "learning_rate": 1.4070834222317047e-05, "loss": 0.6246, "num_tokens": 7868083.0, "step": 1320 }, { "epoch": 0.01413589664259119, "grad_norm": 2.5729721928094205, "learning_rate": 1.412417324514615e-05, "loss": 0.7611, "num_tokens": 7914597.0, "step": 1325 }, { "epoch": 0.014189239648789646, "grad_norm": 2.0625191807854204, "learning_rate": 1.4177512267975252e-05, "loss": 0.691, "num_tokens": 7940975.0, "step": 1330 }, { "epoch": 0.014242582654988104, "grad_norm": 2.440208379331682, "learning_rate": 1.4230851290804353e-05, "loss": 0.5937, "num_tokens": 7978175.0, "step": 1335 }, { "epoch": 0.014295925661186561, "grad_norm": 1.7560899448251996, "learning_rate": 1.4284190313633455e-05, "loss": 0.5801, "num_tokens": 8013083.0, "step": 1340 }, { "epoch": 0.014349268667385019, "grad_norm": 1.9283227147693536, "learning_rate": 1.4337529336462558e-05, "loss": 0.6013, "num_tokens": 8036055.0, "step": 1345 }, { "epoch": 0.014402611673583476, "grad_norm": 3.602841578430121, "learning_rate": 1.439086835929166e-05, "loss": 0.6547, "num_tokens": 8068488.0, "step": 1350 }, { "epoch": 0.014455954679781934, "grad_norm": 3.7450862640105735, "learning_rate": 1.4444207382120761e-05, "loss": 0.6374, "num_tokens": 8113566.0, "step": 1355 }, { "epoch": 0.014509297685980391, "grad_norm": 3.418747742493877, "learning_rate": 1.4497546404949863e-05, "loss": 0.5372, "num_tokens": 8131699.0, "step": 1360 }, { "epoch": 0.014562640692178849, "grad_norm": 1.885200555437705, "learning_rate": 1.4550885427778962e-05, "loss": 0.5386, "num_tokens": 8176709.0, "step": 1365 }, { "epoch": 0.014615983698377306, "grad_norm": 2.943256706225416, "learning_rate": 1.4604224450608064e-05, "loss": 0.6672, "num_tokens": 8204127.0, "step": 1370 }, { "epoch": 0.014669326704575762, "grad_norm": 2.9782620463878287, "learning_rate": 1.4657563473437166e-05, "loss": 0.5589, "num_tokens": 8230422.0, "step": 1375 }, { "epoch": 0.01472266971077422, "grad_norm": 2.2203575394769235, "learning_rate": 1.4710902496266269e-05, "loss": 0.6622, "num_tokens": 8264995.0, "step": 1380 }, { "epoch": 0.014776012716972677, "grad_norm": 2.017825944283939, "learning_rate": 1.476424151909537e-05, "loss": 0.4787, "num_tokens": 8285634.0, "step": 1385 }, { "epoch": 0.014829355723171135, "grad_norm": 3.069473377956092, "learning_rate": 1.4817580541924472e-05, "loss": 0.6297, "num_tokens": 8296572.0, "step": 1390 }, { "epoch": 0.014882698729369592, "grad_norm": 2.0671212652954813, "learning_rate": 1.4870919564753573e-05, "loss": 0.5897, "num_tokens": 8323940.0, "step": 1395 }, { "epoch": 0.01493604173556805, "grad_norm": 2.3721062859408533, "learning_rate": 1.4924258587582677e-05, "loss": 0.5226, "num_tokens": 8340655.0, "step": 1400 }, { "epoch": 0.014989384741766507, "grad_norm": 2.4920720017584177, "learning_rate": 1.4977597610411778e-05, "loss": 0.7292, "num_tokens": 8360140.0, "step": 1405 }, { "epoch": 0.015042727747964965, "grad_norm": 1.9284272401700595, "learning_rate": 1.503093663324088e-05, "loss": 0.5976, "num_tokens": 8398230.0, "step": 1410 }, { "epoch": 0.015096070754163422, "grad_norm": 1.957621595479325, "learning_rate": 1.5084275656069981e-05, "loss": 0.6088, "num_tokens": 8426469.0, "step": 1415 }, { "epoch": 0.015149413760361878, "grad_norm": 3.5744019263463813, "learning_rate": 1.5137614678899085e-05, "loss": 0.6188, "num_tokens": 8447924.0, "step": 1420 }, { "epoch": 0.015202756766560336, "grad_norm": 1.8074490207068579, "learning_rate": 1.5190953701728186e-05, "loss": 0.6668, "num_tokens": 8481854.0, "step": 1425 }, { "epoch": 0.015256099772758793, "grad_norm": 2.9588795447602285, "learning_rate": 1.5244292724557288e-05, "loss": 0.5315, "num_tokens": 8506678.0, "step": 1430 }, { "epoch": 0.01530944277895725, "grad_norm": 1.8717093881601596, "learning_rate": 1.5297631747386388e-05, "loss": 0.5291, "num_tokens": 8533919.0, "step": 1435 }, { "epoch": 0.015362785785155708, "grad_norm": 2.320323477214032, "learning_rate": 1.535097077021549e-05, "loss": 0.5955, "num_tokens": 8560803.0, "step": 1440 }, { "epoch": 0.015416128791354166, "grad_norm": 2.5963701181276586, "learning_rate": 1.540430979304459e-05, "loss": 0.769, "num_tokens": 8598015.0, "step": 1445 }, { "epoch": 0.015469471797552623, "grad_norm": 3.752197454044507, "learning_rate": 1.5457648815873692e-05, "loss": 0.5691, "num_tokens": 8619859.0, "step": 1450 }, { "epoch": 0.01552281480375108, "grad_norm": 3.029254745673144, "learning_rate": 1.5510987838702794e-05, "loss": 0.6351, "num_tokens": 8661274.0, "step": 1455 }, { "epoch": 0.015576157809949538, "grad_norm": 2.9448053058695547, "learning_rate": 1.55643268615319e-05, "loss": 0.6657, "num_tokens": 8687469.0, "step": 1460 }, { "epoch": 0.015629500816147994, "grad_norm": 2.086189190691705, "learning_rate": 1.5617665884361e-05, "loss": 0.5934, "num_tokens": 8715947.0, "step": 1465 }, { "epoch": 0.015682843822346453, "grad_norm": 1.6976940513671237, "learning_rate": 1.5671004907190102e-05, "loss": 0.59, "num_tokens": 8744549.0, "step": 1470 }, { "epoch": 0.01573618682854491, "grad_norm": 2.6541042646565725, "learning_rate": 1.5724343930019203e-05, "loss": 0.7064, "num_tokens": 8774446.0, "step": 1475 }, { "epoch": 0.015789529834743368, "grad_norm": 1.751605131494007, "learning_rate": 1.5777682952848305e-05, "loss": 0.5486, "num_tokens": 8801696.0, "step": 1480 }, { "epoch": 0.015842872840941824, "grad_norm": 2.072054848600005, "learning_rate": 1.5831021975677406e-05, "loss": 0.6867, "num_tokens": 8834795.0, "step": 1485 }, { "epoch": 0.01589621584714028, "grad_norm": 1.5599611845600971, "learning_rate": 1.5884360998506508e-05, "loss": 0.609, "num_tokens": 8873725.0, "step": 1490 }, { "epoch": 0.01594955885333874, "grad_norm": 2.8793695230865657, "learning_rate": 1.593770002133561e-05, "loss": 0.639, "num_tokens": 8894349.0, "step": 1495 }, { "epoch": 0.016002901859537195, "grad_norm": 2.155851770235768, "learning_rate": 1.5991039044164714e-05, "loss": 0.6547, "num_tokens": 8917836.0, "step": 1500 }, { "epoch": 0.016056244865735654, "grad_norm": 2.7512481664770427, "learning_rate": 1.6044378066993813e-05, "loss": 0.6034, "num_tokens": 8938446.0, "step": 1505 }, { "epoch": 0.01610958787193411, "grad_norm": 2.6409358389565085, "learning_rate": 1.6097717089822914e-05, "loss": 0.761, "num_tokens": 8971378.0, "step": 1510 }, { "epoch": 0.01616293087813257, "grad_norm": 3.8059707679283865, "learning_rate": 1.6151056112652016e-05, "loss": 0.5457, "num_tokens": 8999869.0, "step": 1515 }, { "epoch": 0.016216273884331025, "grad_norm": 2.072478443614139, "learning_rate": 1.6204395135481117e-05, "loss": 0.6501, "num_tokens": 9030225.0, "step": 1520 }, { "epoch": 0.016269616890529484, "grad_norm": 2.883918444768695, "learning_rate": 1.625773415831022e-05, "loss": 0.5572, "num_tokens": 9055036.0, "step": 1525 }, { "epoch": 0.01632295989672794, "grad_norm": 1.4943007889869775, "learning_rate": 1.631107318113932e-05, "loss": 0.5209, "num_tokens": 9089299.0, "step": 1530 }, { "epoch": 0.016376302902926396, "grad_norm": 2.336241513243102, "learning_rate": 1.6364412203968425e-05, "loss": 0.6057, "num_tokens": 9120521.0, "step": 1535 }, { "epoch": 0.016429645909124855, "grad_norm": 2.9409917339719414, "learning_rate": 1.6417751226797527e-05, "loss": 0.7374, "num_tokens": 9157328.0, "step": 1540 }, { "epoch": 0.01648298891532331, "grad_norm": 7.509916857538075, "learning_rate": 1.647109024962663e-05, "loss": 0.6807, "num_tokens": 9189207.0, "step": 1545 }, { "epoch": 0.01653633192152177, "grad_norm": 2.3090666430398734, "learning_rate": 1.652442927245573e-05, "loss": 0.5681, "num_tokens": 9223008.0, "step": 1550 }, { "epoch": 0.016589674927720226, "grad_norm": 2.0715267854969746, "learning_rate": 1.657776829528483e-05, "loss": 0.4764, "num_tokens": 9241139.0, "step": 1555 }, { "epoch": 0.016643017933918685, "grad_norm": 3.164753103774762, "learning_rate": 1.6631107318113933e-05, "loss": 0.6915, "num_tokens": 9266692.0, "step": 1560 }, { "epoch": 0.01669636094011714, "grad_norm": 2.0633043570326923, "learning_rate": 1.6684446340943035e-05, "loss": 0.6188, "num_tokens": 9298017.0, "step": 1565 }, { "epoch": 0.0167497039463156, "grad_norm": 2.85652293136901, "learning_rate": 1.6737785363772136e-05, "loss": 0.5748, "num_tokens": 9325791.0, "step": 1570 }, { "epoch": 0.016803046952514056, "grad_norm": 1.8536298320550961, "learning_rate": 1.679112438660124e-05, "loss": 0.6086, "num_tokens": 9342477.0, "step": 1575 }, { "epoch": 0.01685638995871251, "grad_norm": 1.9063423444508711, "learning_rate": 1.684446340943034e-05, "loss": 0.7175, "num_tokens": 9388051.0, "step": 1580 }, { "epoch": 0.01690973296491097, "grad_norm": 4.385031875123001, "learning_rate": 1.689780243225944e-05, "loss": 0.8137, "num_tokens": 9414161.0, "step": 1585 }, { "epoch": 0.016963075971109427, "grad_norm": 2.8006910769206517, "learning_rate": 1.6951141455088542e-05, "loss": 0.5623, "num_tokens": 9442339.0, "step": 1590 }, { "epoch": 0.017016418977307886, "grad_norm": 1.8852299101751995, "learning_rate": 1.7004480477917644e-05, "loss": 0.6555, "num_tokens": 9491072.0, "step": 1595 }, { "epoch": 0.01706976198350634, "grad_norm": 2.4872876880640615, "learning_rate": 1.7057819500746745e-05, "loss": 0.6725, "num_tokens": 9513010.0, "step": 1600 }, { "epoch": 0.0171231049897048, "grad_norm": 1.983735988212786, "learning_rate": 1.7111158523575847e-05, "loss": 0.6297, "num_tokens": 9537224.0, "step": 1605 }, { "epoch": 0.017176447995903257, "grad_norm": 3.3700925434576923, "learning_rate": 1.7164497546404952e-05, "loss": 0.5006, "num_tokens": 9563705.0, "step": 1610 }, { "epoch": 0.017229791002101716, "grad_norm": 3.1429088111811203, "learning_rate": 1.7217836569234054e-05, "loss": 0.6423, "num_tokens": 9594383.0, "step": 1615 }, { "epoch": 0.01728313400830017, "grad_norm": 2.0869091609134816, "learning_rate": 1.7271175592063155e-05, "loss": 0.6101, "num_tokens": 9620347.0, "step": 1620 }, { "epoch": 0.017336477014498627, "grad_norm": 2.3543049046419147, "learning_rate": 1.7324514614892257e-05, "loss": 0.7369, "num_tokens": 9662134.0, "step": 1625 }, { "epoch": 0.017389820020697087, "grad_norm": 2.0986759968823585, "learning_rate": 1.7377853637721358e-05, "loss": 0.6158, "num_tokens": 9684210.0, "step": 1630 }, { "epoch": 0.017443163026895542, "grad_norm": 3.808103622794443, "learning_rate": 1.743119266055046e-05, "loss": 0.5585, "num_tokens": 9700916.0, "step": 1635 }, { "epoch": 0.017496506033094, "grad_norm": 2.329059181252417, "learning_rate": 1.748453168337956e-05, "loss": 0.6217, "num_tokens": 9737437.0, "step": 1640 }, { "epoch": 0.017549849039292457, "grad_norm": 2.464308175028983, "learning_rate": 1.7537870706208663e-05, "loss": 0.6522, "num_tokens": 9767949.0, "step": 1645 }, { "epoch": 0.017603192045490917, "grad_norm": 3.641459854730167, "learning_rate": 1.7591209729037764e-05, "loss": 0.5777, "num_tokens": 9785167.0, "step": 1650 }, { "epoch": 0.017656535051689373, "grad_norm": 2.2628479585068906, "learning_rate": 1.7644548751866866e-05, "loss": 0.5951, "num_tokens": 9816182.0, "step": 1655 }, { "epoch": 0.017709878057887832, "grad_norm": 1.4659129986604316, "learning_rate": 1.7697887774695967e-05, "loss": 0.585, "num_tokens": 9850316.0, "step": 1660 }, { "epoch": 0.017763221064086288, "grad_norm": 2.154651989447763, "learning_rate": 1.775122679752507e-05, "loss": 0.5959, "num_tokens": 9883228.0, "step": 1665 }, { "epoch": 0.017816564070284743, "grad_norm": 2.8075278940391364, "learning_rate": 1.780456582035417e-05, "loss": 0.5639, "num_tokens": 9904174.0, "step": 1670 }, { "epoch": 0.017869907076483203, "grad_norm": 3.734576139181317, "learning_rate": 1.7857904843183272e-05, "loss": 0.675, "num_tokens": 9929228.0, "step": 1675 }, { "epoch": 0.01792325008268166, "grad_norm": 1.567485543010393, "learning_rate": 1.7911243866012377e-05, "loss": 0.6134, "num_tokens": 9959461.0, "step": 1680 }, { "epoch": 0.017976593088880118, "grad_norm": 2.253101895047034, "learning_rate": 1.796458288884148e-05, "loss": 0.6338, "num_tokens": 9992114.0, "step": 1685 }, { "epoch": 0.018029936095078573, "grad_norm": 2.0955619574044664, "learning_rate": 1.801792191167058e-05, "loss": 0.6989, "num_tokens": 10015678.0, "step": 1690 }, { "epoch": 0.018083279101277033, "grad_norm": 7.146182432323703, "learning_rate": 1.8071260934499682e-05, "loss": 0.7098, "num_tokens": 10043012.0, "step": 1695 }, { "epoch": 0.01813662210747549, "grad_norm": 2.082137577460472, "learning_rate": 1.8124599957328783e-05, "loss": 0.7867, "num_tokens": 10082220.0, "step": 1700 }, { "epoch": 0.018189965113673948, "grad_norm": 1.8400072689736946, "learning_rate": 1.8177938980157885e-05, "loss": 0.5618, "num_tokens": 10111511.0, "step": 1705 }, { "epoch": 0.018243308119872403, "grad_norm": 1.822893417822708, "learning_rate": 1.8231278002986986e-05, "loss": 0.6573, "num_tokens": 10137963.0, "step": 1710 }, { "epoch": 0.01829665112607086, "grad_norm": 3.7665982295538227, "learning_rate": 1.8284617025816088e-05, "loss": 0.5886, "num_tokens": 10162120.0, "step": 1715 }, { "epoch": 0.01834999413226932, "grad_norm": 2.330448945028731, "learning_rate": 1.833795604864519e-05, "loss": 0.6906, "num_tokens": 10182205.0, "step": 1720 }, { "epoch": 0.018403337138467774, "grad_norm": 1.6324606190791373, "learning_rate": 1.839129507147429e-05, "loss": 0.6683, "num_tokens": 10219068.0, "step": 1725 }, { "epoch": 0.018456680144666233, "grad_norm": 2.3457288090095676, "learning_rate": 1.8444634094303393e-05, "loss": 0.5997, "num_tokens": 10252216.0, "step": 1730 }, { "epoch": 0.01851002315086469, "grad_norm": 2.545640984338592, "learning_rate": 1.8497973117132494e-05, "loss": 0.6309, "num_tokens": 10284945.0, "step": 1735 }, { "epoch": 0.01856336615706315, "grad_norm": 1.690888705671803, "learning_rate": 1.8551312139961596e-05, "loss": 0.54, "num_tokens": 10323072.0, "step": 1740 }, { "epoch": 0.018616709163261604, "grad_norm": 1.820437623779878, "learning_rate": 1.8604651162790697e-05, "loss": 0.5292, "num_tokens": 10348668.0, "step": 1745 }, { "epoch": 0.018670052169460064, "grad_norm": 2.3807761250191906, "learning_rate": 1.86579901856198e-05, "loss": 0.6232, "num_tokens": 10366384.0, "step": 1750 }, { "epoch": 0.01872339517565852, "grad_norm": 2.252789733749338, "learning_rate": 1.8711329208448904e-05, "loss": 0.5141, "num_tokens": 10387957.0, "step": 1755 }, { "epoch": 0.018776738181856975, "grad_norm": 2.4271545288151595, "learning_rate": 1.8764668231278005e-05, "loss": 0.639, "num_tokens": 10421917.0, "step": 1760 }, { "epoch": 0.018830081188055434, "grad_norm": 2.90807061218536, "learning_rate": 1.8818007254107107e-05, "loss": 0.5919, "num_tokens": 10437901.0, "step": 1765 }, { "epoch": 0.01888342419425389, "grad_norm": 2.339487219254684, "learning_rate": 1.887134627693621e-05, "loss": 0.6163, "num_tokens": 10461128.0, "step": 1770 }, { "epoch": 0.01893676720045235, "grad_norm": 2.246975281679251, "learning_rate": 1.892468529976531e-05, "loss": 0.7238, "num_tokens": 10482705.0, "step": 1775 }, { "epoch": 0.018990110206650805, "grad_norm": 3.378911296611014, "learning_rate": 1.897802432259441e-05, "loss": 0.6279, "num_tokens": 10502542.0, "step": 1780 }, { "epoch": 0.019043453212849264, "grad_norm": 2.4643489815825577, "learning_rate": 1.9031363345423513e-05, "loss": 0.6036, "num_tokens": 10516599.0, "step": 1785 }, { "epoch": 0.01909679621904772, "grad_norm": 2.6875206217064176, "learning_rate": 1.9084702368252615e-05, "loss": 0.6241, "num_tokens": 10557411.0, "step": 1790 }, { "epoch": 0.01915013922524618, "grad_norm": 3.2958780808805574, "learning_rate": 1.9138041391081716e-05, "loss": 0.6385, "num_tokens": 10587679.0, "step": 1795 }, { "epoch": 0.019203482231444635, "grad_norm": 2.09204988092485, "learning_rate": 1.9191380413910818e-05, "loss": 0.5922, "num_tokens": 10612231.0, "step": 1800 }, { "epoch": 0.01925682523764309, "grad_norm": 2.09912781873547, "learning_rate": 1.924471943673992e-05, "loss": 0.6627, "num_tokens": 10657306.0, "step": 1805 }, { "epoch": 0.01931016824384155, "grad_norm": 2.2716897251242294, "learning_rate": 1.929805845956902e-05, "loss": 0.604, "num_tokens": 10679622.0, "step": 1810 }, { "epoch": 0.019363511250040006, "grad_norm": 2.403688761177489, "learning_rate": 1.9351397482398122e-05, "loss": 0.5468, "num_tokens": 10714044.0, "step": 1815 }, { "epoch": 0.019416854256238465, "grad_norm": 2.851859075572419, "learning_rate": 1.9404736505227224e-05, "loss": 0.6657, "num_tokens": 10749092.0, "step": 1820 }, { "epoch": 0.01947019726243692, "grad_norm": 3.1660615872046285, "learning_rate": 1.9458075528056325e-05, "loss": 0.6843, "num_tokens": 10775148.0, "step": 1825 }, { "epoch": 0.01952354026863538, "grad_norm": 2.0177263141429687, "learning_rate": 1.951141455088543e-05, "loss": 0.6161, "num_tokens": 10806451.0, "step": 1830 }, { "epoch": 0.019576883274833836, "grad_norm": 2.150902254293911, "learning_rate": 1.9564753573714532e-05, "loss": 0.626, "num_tokens": 10838242.0, "step": 1835 }, { "epoch": 0.019630226281032295, "grad_norm": 2.2438345004791347, "learning_rate": 1.9618092596543633e-05, "loss": 0.6598, "num_tokens": 10871710.0, "step": 1840 }, { "epoch": 0.01968356928723075, "grad_norm": 2.2021043347557865, "learning_rate": 1.9671431619372735e-05, "loss": 0.605, "num_tokens": 10913080.0, "step": 1845 }, { "epoch": 0.019736912293429207, "grad_norm": 2.7664970947453282, "learning_rate": 1.9724770642201837e-05, "loss": 0.5851, "num_tokens": 10940745.0, "step": 1850 }, { "epoch": 0.019790255299627666, "grad_norm": 2.6865927137740906, "learning_rate": 1.9778109665030938e-05, "loss": 0.503, "num_tokens": 10968618.0, "step": 1855 }, { "epoch": 0.019843598305826122, "grad_norm": 2.287640202439088, "learning_rate": 1.983144868786004e-05, "loss": 0.5439, "num_tokens": 11020788.0, "step": 1860 }, { "epoch": 0.01989694131202458, "grad_norm": 3.357994937916931, "learning_rate": 1.988478771068914e-05, "loss": 0.5717, "num_tokens": 11053714.0, "step": 1865 }, { "epoch": 0.019950284318223037, "grad_norm": 3.3665709805199464, "learning_rate": 1.9938126733518243e-05, "loss": 0.6076, "num_tokens": 11086108.0, "step": 1870 }, { "epoch": 0.020003627324421496, "grad_norm": 1.8043046439330976, "learning_rate": 1.9991465756347344e-05, "loss": 0.5155, "num_tokens": 11124221.0, "step": 1875 }, { "epoch": 0.020056970330619952, "grad_norm": 1.7707977984876575, "learning_rate": 2.0044804779176446e-05, "loss": 0.6105, "num_tokens": 11150087.0, "step": 1880 }, { "epoch": 0.02011031333681841, "grad_norm": 2.978396434228023, "learning_rate": 2.0098143802005547e-05, "loss": 0.6975, "num_tokens": 11175616.0, "step": 1885 }, { "epoch": 0.020163656343016867, "grad_norm": 2.304726810214464, "learning_rate": 2.015148282483465e-05, "loss": 0.5607, "num_tokens": 11201867.0, "step": 1890 }, { "epoch": 0.020216999349215323, "grad_norm": 1.7687254542735695, "learning_rate": 2.020482184766375e-05, "loss": 0.5664, "num_tokens": 11237673.0, "step": 1895 }, { "epoch": 0.020270342355413782, "grad_norm": 2.0345576066174393, "learning_rate": 2.0258160870492855e-05, "loss": 0.6116, "num_tokens": 11257920.0, "step": 1900 }, { "epoch": 0.020323685361612238, "grad_norm": 2.6093216232028347, "learning_rate": 2.0311499893321957e-05, "loss": 0.6526, "num_tokens": 11284041.0, "step": 1905 }, { "epoch": 0.020377028367810697, "grad_norm": 3.950890916863815, "learning_rate": 2.036483891615106e-05, "loss": 0.6999, "num_tokens": 11314440.0, "step": 1910 }, { "epoch": 0.020430371374009153, "grad_norm": 2.486878561576986, "learning_rate": 2.041817793898016e-05, "loss": 0.6516, "num_tokens": 11342296.0, "step": 1915 }, { "epoch": 0.020483714380207612, "grad_norm": 2.953796282581275, "learning_rate": 2.047151696180926e-05, "loss": 0.685, "num_tokens": 11368873.0, "step": 1920 }, { "epoch": 0.020537057386406068, "grad_norm": 2.395418862671706, "learning_rate": 2.0524855984638363e-05, "loss": 0.5514, "num_tokens": 11388145.0, "step": 1925 }, { "epoch": 0.020590400392604527, "grad_norm": 1.9142789794190547, "learning_rate": 2.057819500746746e-05, "loss": 0.6419, "num_tokens": 11417492.0, "step": 1930 }, { "epoch": 0.020643743398802983, "grad_norm": 3.519562793833908, "learning_rate": 2.0631534030296566e-05, "loss": 0.5912, "num_tokens": 11430586.0, "step": 1935 }, { "epoch": 0.02069708640500144, "grad_norm": 1.9183402370003824, "learning_rate": 2.0684873053125668e-05, "loss": 0.6144, "num_tokens": 11453110.0, "step": 1940 }, { "epoch": 0.020750429411199898, "grad_norm": 3.0372291727452687, "learning_rate": 2.073821207595477e-05, "loss": 0.5465, "num_tokens": 11471887.0, "step": 1945 }, { "epoch": 0.020803772417398354, "grad_norm": 1.4927139951765833, "learning_rate": 2.079155109878387e-05, "loss": 0.6237, "num_tokens": 11499526.0, "step": 1950 }, { "epoch": 0.020857115423596813, "grad_norm": 2.6068015759339325, "learning_rate": 2.0844890121612972e-05, "loss": 0.6155, "num_tokens": 11532328.0, "step": 1955 }, { "epoch": 0.02091045842979527, "grad_norm": 1.9285923882902685, "learning_rate": 2.0898229144442074e-05, "loss": 0.8159, "num_tokens": 11574673.0, "step": 1960 }, { "epoch": 0.020963801435993728, "grad_norm": 3.1728152302756634, "learning_rate": 2.0951568167271176e-05, "loss": 0.7258, "num_tokens": 11605646.0, "step": 1965 }, { "epoch": 0.021017144442192184, "grad_norm": 2.4075647606125723, "learning_rate": 2.1004907190100277e-05, "loss": 0.7036, "num_tokens": 11634569.0, "step": 1970 }, { "epoch": 0.021070487448390643, "grad_norm": 1.7295532891578382, "learning_rate": 2.1058246212929382e-05, "loss": 0.5127, "num_tokens": 11651705.0, "step": 1975 }, { "epoch": 0.0211238304545891, "grad_norm": 2.6540373337288523, "learning_rate": 2.1111585235758484e-05, "loss": 0.7581, "num_tokens": 11683396.0, "step": 1980 }, { "epoch": 0.021177173460787554, "grad_norm": 2.6316292137196737, "learning_rate": 2.1164924258587585e-05, "loss": 0.6704, "num_tokens": 11702338.0, "step": 1985 }, { "epoch": 0.021230516466986014, "grad_norm": 1.9737131255164642, "learning_rate": 2.1218263281416687e-05, "loss": 0.6663, "num_tokens": 11747329.0, "step": 1990 }, { "epoch": 0.02128385947318447, "grad_norm": 1.7230344702955727, "learning_rate": 2.1271602304245788e-05, "loss": 0.7397, "num_tokens": 11784836.0, "step": 1995 }, { "epoch": 0.02133720247938293, "grad_norm": 2.900465010946832, "learning_rate": 2.1324941327074886e-05, "loss": 0.6617, "num_tokens": 11819871.0, "step": 2000 }, { "epoch": 0.021390545485581385, "grad_norm": 2.001560298877336, "learning_rate": 2.1378280349903988e-05, "loss": 0.5647, "num_tokens": 11841690.0, "step": 2005 }, { "epoch": 0.021443888491779844, "grad_norm": 2.63124245789233, "learning_rate": 2.1431619372733093e-05, "loss": 0.6198, "num_tokens": 11862011.0, "step": 2010 }, { "epoch": 0.0214972314979783, "grad_norm": 2.04778312236943, "learning_rate": 2.1484958395562194e-05, "loss": 0.5645, "num_tokens": 11880021.0, "step": 2015 }, { "epoch": 0.02155057450417676, "grad_norm": 3.5149927684619002, "learning_rate": 2.1538297418391296e-05, "loss": 0.7092, "num_tokens": 11906785.0, "step": 2020 }, { "epoch": 0.021603917510375215, "grad_norm": 2.3801631896709488, "learning_rate": 2.1591636441220398e-05, "loss": 0.5343, "num_tokens": 11923568.0, "step": 2025 }, { "epoch": 0.02165726051657367, "grad_norm": 3.323541608234014, "learning_rate": 2.16449754640495e-05, "loss": 0.606, "num_tokens": 11945133.0, "step": 2030 }, { "epoch": 0.02171060352277213, "grad_norm": 3.177245699727, "learning_rate": 2.16983144868786e-05, "loss": 0.6642, "num_tokens": 11959942.0, "step": 2035 }, { "epoch": 0.021763946528970585, "grad_norm": 2.6996711391096424, "learning_rate": 2.1751653509707702e-05, "loss": 0.6243, "num_tokens": 11973128.0, "step": 2040 }, { "epoch": 0.021817289535169045, "grad_norm": 2.4431020226906086, "learning_rate": 2.1804992532536804e-05, "loss": 0.6266, "num_tokens": 12004569.0, "step": 2045 }, { "epoch": 0.0218706325413675, "grad_norm": 1.9699790283417389, "learning_rate": 2.185833155536591e-05, "loss": 0.58, "num_tokens": 12029252.0, "step": 2050 }, { "epoch": 0.02192397554756596, "grad_norm": 1.8394364584575047, "learning_rate": 2.191167057819501e-05, "loss": 0.5625, "num_tokens": 12049414.0, "step": 2055 }, { "epoch": 0.021977318553764415, "grad_norm": 2.2546707539570523, "learning_rate": 2.1965009601024112e-05, "loss": 0.6979, "num_tokens": 12082473.0, "step": 2060 }, { "epoch": 0.022030661559962875, "grad_norm": 1.5780161828306747, "learning_rate": 2.2018348623853213e-05, "loss": 0.7081, "num_tokens": 12120379.0, "step": 2065 }, { "epoch": 0.02208400456616133, "grad_norm": 3.0767104037981676, "learning_rate": 2.207168764668231e-05, "loss": 0.5416, "num_tokens": 12137720.0, "step": 2070 }, { "epoch": 0.022137347572359786, "grad_norm": 3.3939845024553548, "learning_rate": 2.2125026669511413e-05, "loss": 0.6853, "num_tokens": 12170448.0, "step": 2075 }, { "epoch": 0.022190690578558245, "grad_norm": 1.822864136236866, "learning_rate": 2.2178365692340518e-05, "loss": 0.8117, "num_tokens": 12202952.0, "step": 2080 }, { "epoch": 0.0222440335847567, "grad_norm": 2.3990987036111777, "learning_rate": 2.223170471516962e-05, "loss": 0.6902, "num_tokens": 12235613.0, "step": 2085 }, { "epoch": 0.02229737659095516, "grad_norm": 2.436207959134093, "learning_rate": 2.228504373799872e-05, "loss": 0.607, "num_tokens": 12253242.0, "step": 2090 }, { "epoch": 0.022350719597153616, "grad_norm": 2.2131898424613583, "learning_rate": 2.2338382760827823e-05, "loss": 0.6913, "num_tokens": 12294904.0, "step": 2095 }, { "epoch": 0.022404062603352076, "grad_norm": 1.79649656938582, "learning_rate": 2.2391721783656924e-05, "loss": 0.5918, "num_tokens": 12331785.0, "step": 2100 }, { "epoch": 0.02245740560955053, "grad_norm": 2.2131031593639916, "learning_rate": 2.2445060806486026e-05, "loss": 0.6623, "num_tokens": 12363419.0, "step": 2105 }, { "epoch": 0.02251074861574899, "grad_norm": 2.4710143809061527, "learning_rate": 2.2498399829315127e-05, "loss": 0.5432, "num_tokens": 12388745.0, "step": 2110 }, { "epoch": 0.022564091621947446, "grad_norm": 2.3310533829336797, "learning_rate": 2.255173885214423e-05, "loss": 0.7459, "num_tokens": 12412146.0, "step": 2115 }, { "epoch": 0.022617434628145902, "grad_norm": 3.47977548564492, "learning_rate": 2.2605077874973334e-05, "loss": 0.718, "num_tokens": 12448984.0, "step": 2120 }, { "epoch": 0.02267077763434436, "grad_norm": 1.7536067546691398, "learning_rate": 2.2658416897802435e-05, "loss": 0.5838, "num_tokens": 12486372.0, "step": 2125 }, { "epoch": 0.022724120640542817, "grad_norm": 1.765006131660429, "learning_rate": 2.2711755920631537e-05, "loss": 0.6094, "num_tokens": 12529183.0, "step": 2130 }, { "epoch": 0.022777463646741276, "grad_norm": 2.6506303784781866, "learning_rate": 2.276509494346064e-05, "loss": 0.5927, "num_tokens": 12563786.0, "step": 2135 }, { "epoch": 0.022830806652939732, "grad_norm": 2.2635171009892603, "learning_rate": 2.2818433966289737e-05, "loss": 0.6716, "num_tokens": 12601415.0, "step": 2140 }, { "epoch": 0.02288414965913819, "grad_norm": 2.292726268295667, "learning_rate": 2.2871772989118838e-05, "loss": 0.824, "num_tokens": 12644179.0, "step": 2145 }, { "epoch": 0.022937492665336647, "grad_norm": 3.1446653140927285, "learning_rate": 2.292511201194794e-05, "loss": 0.5892, "num_tokens": 12668888.0, "step": 2150 }, { "epoch": 0.022990835671535106, "grad_norm": 1.9720239385527045, "learning_rate": 2.2978451034777045e-05, "loss": 0.571, "num_tokens": 12690623.0, "step": 2155 }, { "epoch": 0.023044178677733562, "grad_norm": 1.84673611888121, "learning_rate": 2.3031790057606146e-05, "loss": 0.7677, "num_tokens": 12733944.0, "step": 2160 }, { "epoch": 0.023097521683932018, "grad_norm": 3.9479602574106543, "learning_rate": 2.3085129080435248e-05, "loss": 0.6366, "num_tokens": 12762074.0, "step": 2165 }, { "epoch": 0.023150864690130477, "grad_norm": 2.0177725191684233, "learning_rate": 2.313846810326435e-05, "loss": 0.7368, "num_tokens": 12794147.0, "step": 2170 }, { "epoch": 0.023204207696328933, "grad_norm": 3.2492602571905405, "learning_rate": 2.319180712609345e-05, "loss": 0.7211, "num_tokens": 12843342.0, "step": 2175 }, { "epoch": 0.023257550702527392, "grad_norm": 1.9093357820826324, "learning_rate": 2.3245146148922552e-05, "loss": 0.5978, "num_tokens": 12873825.0, "step": 2180 }, { "epoch": 0.023310893708725848, "grad_norm": 1.7292804288825814, "learning_rate": 2.3298485171751654e-05, "loss": 0.5816, "num_tokens": 12905222.0, "step": 2185 }, { "epoch": 0.023364236714924307, "grad_norm": 1.576399170112194, "learning_rate": 2.3351824194580756e-05, "loss": 0.6897, "num_tokens": 12942916.0, "step": 2190 }, { "epoch": 0.023417579721122763, "grad_norm": 2.4704001872518626, "learning_rate": 2.340516321740986e-05, "loss": 0.6621, "num_tokens": 12986740.0, "step": 2195 }, { "epoch": 0.023470922727321222, "grad_norm": 2.528294656644798, "learning_rate": 2.3458502240238962e-05, "loss": 0.6015, "num_tokens": 13011707.0, "step": 2200 }, { "epoch": 0.023524265733519678, "grad_norm": 1.6877889250049822, "learning_rate": 2.3511841263068064e-05, "loss": 0.6099, "num_tokens": 13035958.0, "step": 2205 }, { "epoch": 0.023577608739718134, "grad_norm": 1.8892663347247736, "learning_rate": 2.3565180285897165e-05, "loss": 0.5844, "num_tokens": 13072665.0, "step": 2210 }, { "epoch": 0.023630951745916593, "grad_norm": 2.0211135033596603, "learning_rate": 2.3618519308726263e-05, "loss": 0.7102, "num_tokens": 13095854.0, "step": 2215 }, { "epoch": 0.02368429475211505, "grad_norm": 2.8627677544491577, "learning_rate": 2.3671858331555365e-05, "loss": 0.7058, "num_tokens": 13120773.0, "step": 2220 }, { "epoch": 0.023737637758313508, "grad_norm": 1.9909422144912647, "learning_rate": 2.3725197354384466e-05, "loss": 0.6464, "num_tokens": 13145522.0, "step": 2225 }, { "epoch": 0.023790980764511964, "grad_norm": 1.8790350694664169, "learning_rate": 2.377853637721357e-05, "loss": 0.6413, "num_tokens": 13171164.0, "step": 2230 }, { "epoch": 0.023844323770710423, "grad_norm": 2.3906719529901075, "learning_rate": 2.3831875400042673e-05, "loss": 0.5254, "num_tokens": 13202905.0, "step": 2235 }, { "epoch": 0.02389766677690888, "grad_norm": 2.2397423777937355, "learning_rate": 2.3885214422871774e-05, "loss": 0.5942, "num_tokens": 13219424.0, "step": 2240 }, { "epoch": 0.023951009783107338, "grad_norm": 2.1937894015802226, "learning_rate": 2.3938553445700876e-05, "loss": 0.5974, "num_tokens": 13243001.0, "step": 2245 }, { "epoch": 0.024004352789305794, "grad_norm": 2.6653833148150134, "learning_rate": 2.3991892468529977e-05, "loss": 0.6193, "num_tokens": 13262773.0, "step": 2250 }, { "epoch": 0.02405769579550425, "grad_norm": 1.3113612283117324, "learning_rate": 2.404523149135908e-05, "loss": 0.5423, "num_tokens": 13297441.0, "step": 2255 }, { "epoch": 0.02411103880170271, "grad_norm": 1.634379266926965, "learning_rate": 2.409857051418818e-05, "loss": 0.6688, "num_tokens": 13332269.0, "step": 2260 }, { "epoch": 0.024164381807901165, "grad_norm": 2.3281297543235193, "learning_rate": 2.4151909537017282e-05, "loss": 0.6808, "num_tokens": 13353102.0, "step": 2265 }, { "epoch": 0.024217724814099624, "grad_norm": 1.8235036309133839, "learning_rate": 2.4205248559846387e-05, "loss": 0.578, "num_tokens": 13384549.0, "step": 2270 }, { "epoch": 0.02427106782029808, "grad_norm": 2.454077811247922, "learning_rate": 2.425858758267549e-05, "loss": 0.6534, "num_tokens": 13428379.0, "step": 2275 }, { "epoch": 0.02432441082649654, "grad_norm": 2.6156504007758037, "learning_rate": 2.431192660550459e-05, "loss": 0.651, "num_tokens": 13444774.0, "step": 2280 }, { "epoch": 0.024377753832694995, "grad_norm": 1.592594759879583, "learning_rate": 2.436526562833369e-05, "loss": 0.596, "num_tokens": 13482988.0, "step": 2285 }, { "epoch": 0.024431096838893454, "grad_norm": 2.15339461723763, "learning_rate": 2.441860465116279e-05, "loss": 0.6957, "num_tokens": 13514200.0, "step": 2290 }, { "epoch": 0.02448443984509191, "grad_norm": 2.633144105820017, "learning_rate": 2.447194367399189e-05, "loss": 0.6602, "num_tokens": 13534074.0, "step": 2295 }, { "epoch": 0.024537782851290366, "grad_norm": 2.4266826855106296, "learning_rate": 2.4525282696820996e-05, "loss": 0.6457, "num_tokens": 13559209.0, "step": 2300 }, { "epoch": 0.024591125857488825, "grad_norm": 2.2814785178242687, "learning_rate": 2.4578621719650098e-05, "loss": 0.808, "num_tokens": 13596208.0, "step": 2305 }, { "epoch": 0.02464446886368728, "grad_norm": 4.314315164616263, "learning_rate": 2.46319607424792e-05, "loss": 0.6085, "num_tokens": 13617262.0, "step": 2310 }, { "epoch": 0.02469781186988574, "grad_norm": 2.574768812448507, "learning_rate": 2.46852997653083e-05, "loss": 0.6201, "num_tokens": 13646352.0, "step": 2315 }, { "epoch": 0.024751154876084196, "grad_norm": 2.5059011547226215, "learning_rate": 2.4738638788137403e-05, "loss": 0.6266, "num_tokens": 13674985.0, "step": 2320 }, { "epoch": 0.024804497882282655, "grad_norm": 2.9195730886481517, "learning_rate": 2.4791977810966504e-05, "loss": 0.5812, "num_tokens": 13708503.0, "step": 2325 }, { "epoch": 0.02485784088848111, "grad_norm": 2.1456609716903667, "learning_rate": 2.4845316833795606e-05, "loss": 0.6249, "num_tokens": 13738699.0, "step": 2330 }, { "epoch": 0.02491118389467957, "grad_norm": 2.245695159688627, "learning_rate": 2.4898655856624707e-05, "loss": 0.703, "num_tokens": 13786420.0, "step": 2335 }, { "epoch": 0.024964526900878026, "grad_norm": 2.086058043192248, "learning_rate": 2.4951994879453812e-05, "loss": 0.7208, "num_tokens": 13807860.0, "step": 2340 }, { "epoch": 0.02501786990707648, "grad_norm": 2.256833034206119, "learning_rate": 2.5005333902282914e-05, "loss": 0.6121, "num_tokens": 13834997.0, "step": 2345 }, { "epoch": 0.02507121291327494, "grad_norm": 2.873729445874082, "learning_rate": 2.5058672925112015e-05, "loss": 0.6749, "num_tokens": 13868897.0, "step": 2350 }, { "epoch": 0.025124555919473397, "grad_norm": 2.950996278417087, "learning_rate": 2.5112011947941117e-05, "loss": 0.6749, "num_tokens": 13894621.0, "step": 2355 }, { "epoch": 0.025177898925671856, "grad_norm": 2.0869960625784705, "learning_rate": 2.516535097077022e-05, "loss": 0.5659, "num_tokens": 13915145.0, "step": 2360 }, { "epoch": 0.02523124193187031, "grad_norm": 2.753624195847143, "learning_rate": 2.521868999359932e-05, "loss": 0.605, "num_tokens": 13928126.0, "step": 2365 }, { "epoch": 0.02528458493806877, "grad_norm": 1.984966842516869, "learning_rate": 2.527202901642842e-05, "loss": 0.6843, "num_tokens": 13956755.0, "step": 2370 }, { "epoch": 0.025337927944267227, "grad_norm": 1.7631905223480548, "learning_rate": 2.5325368039257523e-05, "loss": 0.6467, "num_tokens": 13989349.0, "step": 2375 }, { "epoch": 0.025391270950465686, "grad_norm": 2.8213429132999157, "learning_rate": 2.5378707062086628e-05, "loss": 0.5524, "num_tokens": 14017443.0, "step": 2380 }, { "epoch": 0.02544461395666414, "grad_norm": 1.9148015295059377, "learning_rate": 2.543204608491573e-05, "loss": 0.6248, "num_tokens": 14045269.0, "step": 2385 }, { "epoch": 0.025497956962862597, "grad_norm": 1.7660528863022933, "learning_rate": 2.5485385107744824e-05, "loss": 0.6727, "num_tokens": 14075007.0, "step": 2390 }, { "epoch": 0.025551299969061057, "grad_norm": 3.094956157669585, "learning_rate": 2.5538724130573926e-05, "loss": 0.6206, "num_tokens": 14099516.0, "step": 2395 }, { "epoch": 0.025604642975259512, "grad_norm": 2.7321590910442413, "learning_rate": 2.5592063153403027e-05, "loss": 0.6485, "num_tokens": 14130423.0, "step": 2400 }, { "epoch": 0.02565798598145797, "grad_norm": 1.8447233808454049, "learning_rate": 2.564540217623213e-05, "loss": 0.7947, "num_tokens": 14165988.0, "step": 2405 }, { "epoch": 0.025711328987656427, "grad_norm": 2.1365557737203726, "learning_rate": 2.5698741199061234e-05, "loss": 0.6477, "num_tokens": 14193928.0, "step": 2410 }, { "epoch": 0.025764671993854887, "grad_norm": 1.9913402156138427, "learning_rate": 2.5752080221890335e-05, "loss": 0.6201, "num_tokens": 14229848.0, "step": 2415 }, { "epoch": 0.025818015000053342, "grad_norm": 2.295166977580632, "learning_rate": 2.5805419244719437e-05, "loss": 0.5534, "num_tokens": 14254683.0, "step": 2420 }, { "epoch": 0.0258713580062518, "grad_norm": 1.8240834579532963, "learning_rate": 2.585875826754854e-05, "loss": 0.5914, "num_tokens": 14284573.0, "step": 2425 }, { "epoch": 0.025924701012450257, "grad_norm": 3.607040298104003, "learning_rate": 2.591209729037764e-05, "loss": 0.5827, "num_tokens": 14305829.0, "step": 2430 }, { "epoch": 0.025978044018648713, "grad_norm": 2.029923363377828, "learning_rate": 2.596543631320674e-05, "loss": 0.5072, "num_tokens": 14347298.0, "step": 2435 }, { "epoch": 0.026031387024847173, "grad_norm": 2.2783379016363376, "learning_rate": 2.6018775336035843e-05, "loss": 0.7699, "num_tokens": 14375885.0, "step": 2440 }, { "epoch": 0.02608473003104563, "grad_norm": 1.832663858457096, "learning_rate": 2.6072114358864945e-05, "loss": 0.6192, "num_tokens": 14411390.0, "step": 2445 }, { "epoch": 0.026138073037244088, "grad_norm": 2.1066599938445942, "learning_rate": 2.612545338169405e-05, "loss": 0.6463, "num_tokens": 14449311.0, "step": 2450 }, { "epoch": 0.026191416043442543, "grad_norm": 2.3442269764007317, "learning_rate": 2.617879240452315e-05, "loss": 0.6028, "num_tokens": 14481124.0, "step": 2455 }, { "epoch": 0.026244759049641003, "grad_norm": 1.362176253027795, "learning_rate": 2.6232131427352253e-05, "loss": 0.6548, "num_tokens": 14516480.0, "step": 2460 }, { "epoch": 0.02629810205583946, "grad_norm": 2.103805038062079, "learning_rate": 2.6285470450181354e-05, "loss": 0.7199, "num_tokens": 14570271.0, "step": 2465 }, { "epoch": 0.026351445062037918, "grad_norm": 2.2813040666983913, "learning_rate": 2.6338809473010456e-05, "loss": 0.6441, "num_tokens": 14595734.0, "step": 2470 }, { "epoch": 0.026404788068236373, "grad_norm": 3.053249077046309, "learning_rate": 2.6392148495839557e-05, "loss": 0.6797, "num_tokens": 14628098.0, "step": 2475 }, { "epoch": 0.02645813107443483, "grad_norm": 2.9620627213943673, "learning_rate": 2.644548751866866e-05, "loss": 0.4995, "num_tokens": 14639707.0, "step": 2480 }, { "epoch": 0.02651147408063329, "grad_norm": 1.735848733546384, "learning_rate": 2.649882654149776e-05, "loss": 0.6232, "num_tokens": 14663663.0, "step": 2485 }, { "epoch": 0.026564817086831744, "grad_norm": 2.8414168296409303, "learning_rate": 2.6552165564326865e-05, "loss": 0.595, "num_tokens": 14685392.0, "step": 2490 }, { "epoch": 0.026618160093030203, "grad_norm": 1.9415355484931285, "learning_rate": 2.6605504587155967e-05, "loss": 0.7099, "num_tokens": 14725204.0, "step": 2495 }, { "epoch": 0.02667150309922866, "grad_norm": 1.9775495694079894, "learning_rate": 2.665884360998507e-05, "loss": 0.6891, "num_tokens": 14761274.0, "step": 2500 }, { "epoch": 0.02672484610542712, "grad_norm": 1.7097193780823927, "learning_rate": 2.671218263281417e-05, "loss": 0.6573, "num_tokens": 14799491.0, "step": 2505 }, { "epoch": 0.026778189111625574, "grad_norm": 2.286720396661724, "learning_rate": 2.676552165564327e-05, "loss": 0.5984, "num_tokens": 14814241.0, "step": 2510 }, { "epoch": 0.026831532117824033, "grad_norm": 1.3580876134532884, "learning_rate": 2.6818860678472373e-05, "loss": 0.6155, "num_tokens": 14854669.0, "step": 2515 }, { "epoch": 0.02688487512402249, "grad_norm": 2.133385223877799, "learning_rate": 2.6872199701301475e-05, "loss": 0.6383, "num_tokens": 14883142.0, "step": 2520 }, { "epoch": 0.026938218130220945, "grad_norm": 2.1810173381447284, "learning_rate": 2.6925538724130576e-05, "loss": 0.7824, "num_tokens": 14923549.0, "step": 2525 }, { "epoch": 0.026991561136419404, "grad_norm": 2.161794460908731, "learning_rate": 2.6978877746959674e-05, "loss": 0.6215, "num_tokens": 14950355.0, "step": 2530 }, { "epoch": 0.02704490414261786, "grad_norm": 1.6312223990290915, "learning_rate": 2.7032216769788776e-05, "loss": 0.7243, "num_tokens": 14990759.0, "step": 2535 }, { "epoch": 0.02709824714881632, "grad_norm": 3.0997378538913822, "learning_rate": 2.7085555792617878e-05, "loss": 0.6044, "num_tokens": 15013325.0, "step": 2540 }, { "epoch": 0.027151590155014775, "grad_norm": 2.1068719526912436, "learning_rate": 2.713889481544698e-05, "loss": 0.6061, "num_tokens": 15031065.0, "step": 2545 }, { "epoch": 0.027204933161213234, "grad_norm": 2.0311837077027266, "learning_rate": 2.719223383827608e-05, "loss": 0.645, "num_tokens": 15062094.0, "step": 2550 }, { "epoch": 0.02725827616741169, "grad_norm": 3.478441306426347, "learning_rate": 2.7245572861105186e-05, "loss": 0.6567, "num_tokens": 15089995.0, "step": 2555 }, { "epoch": 0.02731161917361015, "grad_norm": 1.927585664105061, "learning_rate": 2.7298911883934287e-05, "loss": 0.6769, "num_tokens": 15118063.0, "step": 2560 }, { "epoch": 0.027364962179808605, "grad_norm": 2.4932728303096927, "learning_rate": 2.735225090676339e-05, "loss": 0.642, "num_tokens": 15149827.0, "step": 2565 }, { "epoch": 0.02741830518600706, "grad_norm": 2.092383720830385, "learning_rate": 2.740558992959249e-05, "loss": 0.6218, "num_tokens": 15176636.0, "step": 2570 }, { "epoch": 0.02747164819220552, "grad_norm": 1.4550038422387124, "learning_rate": 2.7458928952421592e-05, "loss": 0.5988, "num_tokens": 15200088.0, "step": 2575 }, { "epoch": 0.027524991198403976, "grad_norm": 2.2238856631231747, "learning_rate": 2.7512267975250693e-05, "loss": 0.6019, "num_tokens": 15227935.0, "step": 2580 }, { "epoch": 0.027578334204602435, "grad_norm": 3.1316061732807534, "learning_rate": 2.7565606998079795e-05, "loss": 0.7891, "num_tokens": 15249216.0, "step": 2585 }, { "epoch": 0.02763167721080089, "grad_norm": 2.4556753837984764, "learning_rate": 2.7618946020908896e-05, "loss": 0.5594, "num_tokens": 15263332.0, "step": 2590 }, { "epoch": 0.02768502021699935, "grad_norm": 1.9091480372271776, "learning_rate": 2.7672285043738e-05, "loss": 0.5585, "num_tokens": 15285948.0, "step": 2595 }, { "epoch": 0.027738363223197806, "grad_norm": 1.8620965603487405, "learning_rate": 2.7725624066567103e-05, "loss": 0.5978, "num_tokens": 15303667.0, "step": 2600 }, { "epoch": 0.027791706229396265, "grad_norm": 3.442971294632992, "learning_rate": 2.7778963089396204e-05, "loss": 0.7836, "num_tokens": 15330491.0, "step": 2605 }, { "epoch": 0.02784504923559472, "grad_norm": 2.536505783141569, "learning_rate": 2.7832302112225306e-05, "loss": 0.7014, "num_tokens": 15359666.0, "step": 2610 }, { "epoch": 0.027898392241793177, "grad_norm": 2.3080754584997596, "learning_rate": 2.7885641135054408e-05, "loss": 0.7201, "num_tokens": 15412308.0, "step": 2615 }, { "epoch": 0.027951735247991636, "grad_norm": 2.5775334487987505, "learning_rate": 2.793898015788351e-05, "loss": 0.6934, "num_tokens": 15438243.0, "step": 2620 }, { "epoch": 0.028005078254190092, "grad_norm": 2.5183771747448906, "learning_rate": 2.799231918071261e-05, "loss": 0.6636, "num_tokens": 15473147.0, "step": 2625 }, { "epoch": 0.02805842126038855, "grad_norm": 2.5931298732261623, "learning_rate": 2.8045658203541712e-05, "loss": 0.6738, "num_tokens": 15511814.0, "step": 2630 }, { "epoch": 0.028111764266587007, "grad_norm": 1.8956208561309094, "learning_rate": 2.8098997226370817e-05, "loss": 0.5738, "num_tokens": 15541139.0, "step": 2635 }, { "epoch": 0.028165107272785466, "grad_norm": 1.7957745196941444, "learning_rate": 2.815233624919992e-05, "loss": 0.8836, "num_tokens": 15588155.0, "step": 2640 }, { "epoch": 0.028218450278983922, "grad_norm": 6.291038789103634, "learning_rate": 2.820567527202902e-05, "loss": 0.7291, "num_tokens": 15621182.0, "step": 2645 }, { "epoch": 0.02827179328518238, "grad_norm": 2.038243726266393, "learning_rate": 2.8259014294858122e-05, "loss": 0.6591, "num_tokens": 15642192.0, "step": 2650 }, { "epoch": 0.028325136291380837, "grad_norm": 4.378149445522743, "learning_rate": 2.8312353317687223e-05, "loss": 0.7469, "num_tokens": 15672428.0, "step": 2655 }, { "epoch": 0.028378479297579293, "grad_norm": 1.6359047802743434, "learning_rate": 2.8365692340516325e-05, "loss": 0.7084, "num_tokens": 15712426.0, "step": 2660 }, { "epoch": 0.028431822303777752, "grad_norm": 1.6681185035653685, "learning_rate": 2.8419031363345426e-05, "loss": 0.7504, "num_tokens": 15753747.0, "step": 2665 }, { "epoch": 0.028485165309976208, "grad_norm": 3.9316216191794524, "learning_rate": 2.8472370386174525e-05, "loss": 0.6263, "num_tokens": 15769386.0, "step": 2670 }, { "epoch": 0.028538508316174667, "grad_norm": 1.9180208044287903, "learning_rate": 2.8525709409003626e-05, "loss": 0.7684, "num_tokens": 15824503.0, "step": 2675 }, { "epoch": 0.028591851322373123, "grad_norm": 2.592400373294601, "learning_rate": 2.8579048431832728e-05, "loss": 0.5471, "num_tokens": 15862514.0, "step": 2680 }, { "epoch": 0.028645194328571582, "grad_norm": 2.673727949505159, "learning_rate": 2.863238745466183e-05, "loss": 0.6784, "num_tokens": 15899117.0, "step": 2685 }, { "epoch": 0.028698537334770038, "grad_norm": 1.7238440671120863, "learning_rate": 2.868572647749093e-05, "loss": 0.8281, "num_tokens": 15923476.0, "step": 2690 }, { "epoch": 0.028751880340968497, "grad_norm": 1.4754236408369608, "learning_rate": 2.8739065500320032e-05, "loss": 0.6452, "num_tokens": 15959133.0, "step": 2695 }, { "epoch": 0.028805223347166953, "grad_norm": 1.8156952146894503, "learning_rate": 2.8792404523149137e-05, "loss": 0.5943, "num_tokens": 15993294.0, "step": 2700 }, { "epoch": 0.02885856635336541, "grad_norm": 1.6585322228249768, "learning_rate": 2.884574354597824e-05, "loss": 0.7567, "num_tokens": 16025954.0, "step": 2705 }, { "epoch": 0.028911909359563868, "grad_norm": 1.5630067918925759, "learning_rate": 2.889908256880734e-05, "loss": 0.5869, "num_tokens": 16057323.0, "step": 2710 }, { "epoch": 0.028965252365762324, "grad_norm": 1.6772095617608616, "learning_rate": 2.8952421591636442e-05, "loss": 0.6362, "num_tokens": 16091119.0, "step": 2715 }, { "epoch": 0.029018595371960783, "grad_norm": 1.9513105375736024, "learning_rate": 2.9005760614465544e-05, "loss": 0.6598, "num_tokens": 16120926.0, "step": 2720 }, { "epoch": 0.02907193837815924, "grad_norm": 1.6722459537276229, "learning_rate": 2.9059099637294645e-05, "loss": 0.6192, "num_tokens": 16138086.0, "step": 2725 }, { "epoch": 0.029125281384357698, "grad_norm": 2.7118327062849366, "learning_rate": 2.9112438660123747e-05, "loss": 0.6737, "num_tokens": 16181040.0, "step": 2730 }, { "epoch": 0.029178624390556154, "grad_norm": 2.3970484138806882, "learning_rate": 2.9165777682952848e-05, "loss": 0.5768, "num_tokens": 16200429.0, "step": 2735 }, { "epoch": 0.029231967396754613, "grad_norm": 1.821588082262361, "learning_rate": 2.9219116705781953e-05, "loss": 0.7609, "num_tokens": 16241699.0, "step": 2740 }, { "epoch": 0.02928531040295307, "grad_norm": 2.333223914537588, "learning_rate": 2.9272455728611055e-05, "loss": 0.6513, "num_tokens": 16276408.0, "step": 2745 }, { "epoch": 0.029338653409151524, "grad_norm": 2.830740336393341, "learning_rate": 2.9325794751440156e-05, "loss": 0.6053, "num_tokens": 16301947.0, "step": 2750 }, { "epoch": 0.029391996415349984, "grad_norm": 1.5948161562328795, "learning_rate": 2.9379133774269258e-05, "loss": 0.5535, "num_tokens": 16326396.0, "step": 2755 }, { "epoch": 0.02944533942154844, "grad_norm": 1.8835332627142598, "learning_rate": 2.943247279709836e-05, "loss": 0.6035, "num_tokens": 16343166.0, "step": 2760 }, { "epoch": 0.0294986824277469, "grad_norm": 1.7336363727114137, "learning_rate": 2.948581181992746e-05, "loss": 0.8513, "num_tokens": 16387714.0, "step": 2765 }, { "epoch": 0.029552025433945354, "grad_norm": 1.454608091096033, "learning_rate": 2.9539150842756562e-05, "loss": 0.5971, "num_tokens": 16436413.0, "step": 2770 }, { "epoch": 0.029605368440143814, "grad_norm": 2.411138929497988, "learning_rate": 2.9592489865585664e-05, "loss": 0.6124, "num_tokens": 16454542.0, "step": 2775 }, { "epoch": 0.02965871144634227, "grad_norm": 1.5864722028690297, "learning_rate": 2.964582888841477e-05, "loss": 0.8508, "num_tokens": 16492466.0, "step": 2780 }, { "epoch": 0.02971205445254073, "grad_norm": 1.956522099444423, "learning_rate": 2.969916791124387e-05, "loss": 0.7152, "num_tokens": 16522031.0, "step": 2785 }, { "epoch": 0.029765397458739185, "grad_norm": 1.9982083808077837, "learning_rate": 2.9752506934072972e-05, "loss": 0.6512, "num_tokens": 16541784.0, "step": 2790 }, { "epoch": 0.02981874046493764, "grad_norm": 2.0421925123323867, "learning_rate": 2.9805845956902074e-05, "loss": 0.7116, "num_tokens": 16579021.0, "step": 2795 }, { "epoch": 0.0298720834711361, "grad_norm": 1.9066707507604068, "learning_rate": 2.9859184979731175e-05, "loss": 0.6805, "num_tokens": 16622154.0, "step": 2800 }, { "epoch": 0.029925426477334555, "grad_norm": 2.223745521498546, "learning_rate": 2.9912524002560277e-05, "loss": 0.565, "num_tokens": 16647496.0, "step": 2805 }, { "epoch": 0.029978769483533015, "grad_norm": 2.1381814524409175, "learning_rate": 2.9965863025389378e-05, "loss": 0.5768, "num_tokens": 16674592.0, "step": 2810 }, { "epoch": 0.03003211248973147, "grad_norm": 1.7066500344187991, "learning_rate": 3.0019202048218476e-05, "loss": 0.6483, "num_tokens": 16707711.0, "step": 2815 }, { "epoch": 0.03008545549592993, "grad_norm": 1.5698020769172538, "learning_rate": 3.0072541071047578e-05, "loss": 0.6672, "num_tokens": 16730037.0, "step": 2820 }, { "epoch": 0.030138798502128385, "grad_norm": 2.087666699034186, "learning_rate": 3.012588009387668e-05, "loss": 0.5243, "num_tokens": 16747160.0, "step": 2825 }, { "epoch": 0.030192141508326845, "grad_norm": 2.728459687629893, "learning_rate": 3.017921911670578e-05, "loss": 0.5761, "num_tokens": 16769099.0, "step": 2830 }, { "epoch": 0.0302454845145253, "grad_norm": 2.320152755525634, "learning_rate": 3.0232558139534883e-05, "loss": 0.6155, "num_tokens": 16795350.0, "step": 2835 }, { "epoch": 0.030298827520723756, "grad_norm": 1.6800112643240501, "learning_rate": 3.0285897162363984e-05, "loss": 0.7337, "num_tokens": 16829752.0, "step": 2840 }, { "epoch": 0.030352170526922215, "grad_norm": 2.0582278540225474, "learning_rate": 3.0339236185193086e-05, "loss": 0.6552, "num_tokens": 16856273.0, "step": 2845 }, { "epoch": 0.03040551353312067, "grad_norm": 1.8610599167720396, "learning_rate": 3.039257520802219e-05, "loss": 0.6267, "num_tokens": 16878739.0, "step": 2850 }, { "epoch": 0.03045885653931913, "grad_norm": 2.259579135662765, "learning_rate": 3.0445914230851292e-05, "loss": 0.6043, "num_tokens": 16907302.0, "step": 2855 }, { "epoch": 0.030512199545517586, "grad_norm": 3.858942622863348, "learning_rate": 3.0499253253680394e-05, "loss": 0.7179, "num_tokens": 16930598.0, "step": 2860 }, { "epoch": 0.030565542551716045, "grad_norm": 1.729348048382547, "learning_rate": 3.0552592276509495e-05, "loss": 0.6442, "num_tokens": 16956391.0, "step": 2865 }, { "epoch": 0.0306188855579145, "grad_norm": 1.923604310775261, "learning_rate": 3.06059312993386e-05, "loss": 0.5114, "num_tokens": 16986615.0, "step": 2870 }, { "epoch": 0.03067222856411296, "grad_norm": 2.4087417912479148, "learning_rate": 3.06592703221677e-05, "loss": 0.5484, "num_tokens": 17013664.0, "step": 2875 }, { "epoch": 0.030725571570311416, "grad_norm": 1.9324253928429203, "learning_rate": 3.07126093449968e-05, "loss": 0.8028, "num_tokens": 17042190.0, "step": 2880 }, { "epoch": 0.030778914576509872, "grad_norm": 1.975676795247896, "learning_rate": 3.07659483678259e-05, "loss": 0.6336, "num_tokens": 17066579.0, "step": 2885 }, { "epoch": 0.03083225758270833, "grad_norm": 2.3301508916548994, "learning_rate": 3.0819287390655006e-05, "loss": 0.6493, "num_tokens": 17089948.0, "step": 2890 }, { "epoch": 0.030885600588906787, "grad_norm": 1.8071910188386748, "learning_rate": 3.0872626413484105e-05, "loss": 0.66, "num_tokens": 17115283.0, "step": 2895 }, { "epoch": 0.030938943595105246, "grad_norm": 3.2370164492409885, "learning_rate": 3.092596543631321e-05, "loss": 0.6552, "num_tokens": 17135416.0, "step": 2900 }, { "epoch": 0.030992286601303702, "grad_norm": 2.8182467871808763, "learning_rate": 3.097930445914231e-05, "loss": 0.6787, "num_tokens": 17155790.0, "step": 2905 }, { "epoch": 0.03104562960750216, "grad_norm": 2.19843463338732, "learning_rate": 3.103264348197141e-05, "loss": 0.6653, "num_tokens": 17182697.0, "step": 2910 }, { "epoch": 0.031098972613700617, "grad_norm": 1.6042139538146198, "learning_rate": 3.108598250480052e-05, "loss": 0.6913, "num_tokens": 17212958.0, "step": 2915 }, { "epoch": 0.031152315619899076, "grad_norm": 1.5851338740371959, "learning_rate": 3.1139321527629616e-05, "loss": 0.6776, "num_tokens": 17244533.0, "step": 2920 }, { "epoch": 0.031205658626097532, "grad_norm": 2.2199071973117284, "learning_rate": 3.119266055045872e-05, "loss": 0.5939, "num_tokens": 17269997.0, "step": 2925 }, { "epoch": 0.03125900163229599, "grad_norm": 1.5596779742211175, "learning_rate": 3.124599957328782e-05, "loss": 0.6467, "num_tokens": 17303289.0, "step": 2930 }, { "epoch": 0.031312344638494444, "grad_norm": 2.0190576612426345, "learning_rate": 3.1299338596116924e-05, "loss": 0.6711, "num_tokens": 17344194.0, "step": 2935 }, { "epoch": 0.031365687644692906, "grad_norm": 2.0229466988964218, "learning_rate": 3.135267761894602e-05, "loss": 0.5886, "num_tokens": 17381163.0, "step": 2940 }, { "epoch": 0.03141903065089136, "grad_norm": 2.2532356604853025, "learning_rate": 3.140601664177513e-05, "loss": 0.711, "num_tokens": 17406531.0, "step": 2945 }, { "epoch": 0.03147237365708982, "grad_norm": 1.9786279936770457, "learning_rate": 3.145935566460423e-05, "loss": 0.6087, "num_tokens": 17434125.0, "step": 2950 }, { "epoch": 0.031525716663288274, "grad_norm": 2.590731562341142, "learning_rate": 3.151269468743332e-05, "loss": 0.5432, "num_tokens": 17460982.0, "step": 2955 }, { "epoch": 0.031579059669486736, "grad_norm": 2.1407030131725873, "learning_rate": 3.156603371026243e-05, "loss": 0.7061, "num_tokens": 17488690.0, "step": 2960 }, { "epoch": 0.03163240267568519, "grad_norm": 3.74257939584317, "learning_rate": 3.1619372733091526e-05, "loss": 0.695, "num_tokens": 17514406.0, "step": 2965 }, { "epoch": 0.03168574568188365, "grad_norm": 3.3127180340157576, "learning_rate": 3.167271175592063e-05, "loss": 0.6501, "num_tokens": 17533131.0, "step": 2970 }, { "epoch": 0.031739088688082104, "grad_norm": 2.4645190654640525, "learning_rate": 3.1726050778749736e-05, "loss": 0.5999, "num_tokens": 17566975.0, "step": 2975 }, { "epoch": 0.03179243169428056, "grad_norm": 2.446640558117617, "learning_rate": 3.1779389801578834e-05, "loss": 0.5633, "num_tokens": 17589296.0, "step": 2980 }, { "epoch": 0.03184577470047902, "grad_norm": 1.9791635554495872, "learning_rate": 3.183272882440794e-05, "loss": 0.732, "num_tokens": 17619135.0, "step": 2985 }, { "epoch": 0.03189911770667748, "grad_norm": 2.2799095787037826, "learning_rate": 3.188606784723704e-05, "loss": 0.627, "num_tokens": 17648053.0, "step": 2990 }, { "epoch": 0.031952460712875934, "grad_norm": 1.6826456982841174, "learning_rate": 3.193940687006614e-05, "loss": 0.6445, "num_tokens": 17693667.0, "step": 2995 }, { "epoch": 0.03200580371907439, "grad_norm": 2.2292754116400273, "learning_rate": 3.199274589289524e-05, "loss": 0.6396, "num_tokens": 17714202.0, "step": 3000 }, { "epoch": 0.03205914672527285, "grad_norm": 2.072094438416018, "learning_rate": 3.2046084915724345e-05, "loss": 0.7768, "num_tokens": 17750995.0, "step": 3005 }, { "epoch": 0.03211248973147131, "grad_norm": 1.6806978656299718, "learning_rate": 3.2099423938553444e-05, "loss": 0.7228, "num_tokens": 17786574.0, "step": 3010 }, { "epoch": 0.032165832737669764, "grad_norm": 2.184545587162833, "learning_rate": 3.215276296138255e-05, "loss": 0.7294, "num_tokens": 17818259.0, "step": 3015 }, { "epoch": 0.03221917574386822, "grad_norm": 1.6651673197384327, "learning_rate": 3.2206101984211653e-05, "loss": 0.5871, "num_tokens": 17852611.0, "step": 3020 }, { "epoch": 0.032272518750066675, "grad_norm": 1.8048762714789346, "learning_rate": 3.225944100704075e-05, "loss": 0.6465, "num_tokens": 17880804.0, "step": 3025 }, { "epoch": 0.03232586175626514, "grad_norm": 3.4278216731872226, "learning_rate": 3.2312780029869857e-05, "loss": 0.6417, "num_tokens": 17909481.0, "step": 3030 }, { "epoch": 0.032379204762463594, "grad_norm": 1.4643941235645022, "learning_rate": 3.2366119052698955e-05, "loss": 0.6686, "num_tokens": 17944427.0, "step": 3035 }, { "epoch": 0.03243254776866205, "grad_norm": 1.8533955013403087, "learning_rate": 3.241945807552806e-05, "loss": 0.7513, "num_tokens": 17976522.0, "step": 3040 }, { "epoch": 0.032485890774860506, "grad_norm": 1.8115060035348223, "learning_rate": 3.247279709835716e-05, "loss": 0.7304, "num_tokens": 18004017.0, "step": 3045 }, { "epoch": 0.03253923378105897, "grad_norm": 4.629401942985889, "learning_rate": 3.252613612118626e-05, "loss": 0.6684, "num_tokens": 18021170.0, "step": 3050 }, { "epoch": 0.032592576787257424, "grad_norm": 3.6672584143104197, "learning_rate": 3.257947514401537e-05, "loss": 0.6107, "num_tokens": 18041968.0, "step": 3055 }, { "epoch": 0.03264591979345588, "grad_norm": 1.9834679104634132, "learning_rate": 3.2632814166844466e-05, "loss": 0.7269, "num_tokens": 18076125.0, "step": 3060 }, { "epoch": 0.032699262799654336, "grad_norm": 2.259312412902677, "learning_rate": 3.268615318967357e-05, "loss": 0.6947, "num_tokens": 18107145.0, "step": 3065 }, { "epoch": 0.03275260580585279, "grad_norm": 1.8560493681482417, "learning_rate": 3.273949221250267e-05, "loss": 0.7501, "num_tokens": 18152826.0, "step": 3070 }, { "epoch": 0.032805948812051254, "grad_norm": 1.4539556556259212, "learning_rate": 3.2792831235331774e-05, "loss": 0.7395, "num_tokens": 18193572.0, "step": 3075 }, { "epoch": 0.03285929181824971, "grad_norm": 1.8901362164087667, "learning_rate": 3.284617025816087e-05, "loss": 0.6629, "num_tokens": 18213131.0, "step": 3080 }, { "epoch": 0.032912634824448166, "grad_norm": 1.8958502829192299, "learning_rate": 3.289950928098998e-05, "loss": 0.6142, "num_tokens": 18235917.0, "step": 3085 }, { "epoch": 0.03296597783064662, "grad_norm": 1.4122038866595181, "learning_rate": 3.2952848303819075e-05, "loss": 0.5667, "num_tokens": 18256521.0, "step": 3090 }, { "epoch": 0.033019320836845084, "grad_norm": 1.688364641334075, "learning_rate": 3.300618732664817e-05, "loss": 0.597, "num_tokens": 18291364.0, "step": 3095 }, { "epoch": 0.03307266384304354, "grad_norm": 2.1863924255089215, "learning_rate": 3.305952634947728e-05, "loss": 0.7716, "num_tokens": 18322523.0, "step": 3100 }, { "epoch": 0.033126006849241996, "grad_norm": 1.580169062738207, "learning_rate": 3.3112865372306376e-05, "loss": 0.7337, "num_tokens": 18359246.0, "step": 3105 }, { "epoch": 0.03317934985544045, "grad_norm": 2.185873388333818, "learning_rate": 3.316620439513548e-05, "loss": 0.7328, "num_tokens": 18388496.0, "step": 3110 }, { "epoch": 0.03323269286163891, "grad_norm": 1.8178886614053638, "learning_rate": 3.321954341796458e-05, "loss": 0.6015, "num_tokens": 18429887.0, "step": 3115 }, { "epoch": 0.03328603586783737, "grad_norm": 1.6265582097137785, "learning_rate": 3.3272882440793684e-05, "loss": 0.555, "num_tokens": 18452237.0, "step": 3120 }, { "epoch": 0.033339378874035826, "grad_norm": 1.3422163492130987, "learning_rate": 3.332622146362279e-05, "loss": 0.6368, "num_tokens": 18501130.0, "step": 3125 }, { "epoch": 0.03339272188023428, "grad_norm": 2.015910522593991, "learning_rate": 3.337956048645189e-05, "loss": 0.6778, "num_tokens": 18533776.0, "step": 3130 }, { "epoch": 0.03344606488643274, "grad_norm": 2.086939778158842, "learning_rate": 3.343289950928099e-05, "loss": 0.6878, "num_tokens": 18567480.0, "step": 3135 }, { "epoch": 0.0334994078926312, "grad_norm": 1.7599724279337075, "learning_rate": 3.348623853211009e-05, "loss": 0.6468, "num_tokens": 18596353.0, "step": 3140 }, { "epoch": 0.033552750898829656, "grad_norm": 2.5634521469631073, "learning_rate": 3.3539577554939196e-05, "loss": 0.7698, "num_tokens": 18628925.0, "step": 3145 }, { "epoch": 0.03360609390502811, "grad_norm": 1.3326657520782395, "learning_rate": 3.3592916577768294e-05, "loss": 0.7199, "num_tokens": 18664339.0, "step": 3150 }, { "epoch": 0.03365943691122657, "grad_norm": 2.3907158505066977, "learning_rate": 3.36462556005974e-05, "loss": 0.7522, "num_tokens": 18686165.0, "step": 3155 }, { "epoch": 0.03371277991742502, "grad_norm": 2.6351378195075137, "learning_rate": 3.3699594623426504e-05, "loss": 0.73, "num_tokens": 18711897.0, "step": 3160 }, { "epoch": 0.033766122923623486, "grad_norm": 2.749059760692382, "learning_rate": 3.37529336462556e-05, "loss": 0.6193, "num_tokens": 18733657.0, "step": 3165 }, { "epoch": 0.03381946592982194, "grad_norm": 1.524608627295265, "learning_rate": 3.380627266908471e-05, "loss": 0.6638, "num_tokens": 18770373.0, "step": 3170 }, { "epoch": 0.0338728089360204, "grad_norm": 2.1334642269842177, "learning_rate": 3.3859611691913805e-05, "loss": 0.6482, "num_tokens": 18799879.0, "step": 3175 }, { "epoch": 0.03392615194221885, "grad_norm": 2.6703729002745975, "learning_rate": 3.391295071474291e-05, "loss": 0.6321, "num_tokens": 18819394.0, "step": 3180 }, { "epoch": 0.033979494948417316, "grad_norm": 1.7511171219880124, "learning_rate": 3.396628973757201e-05, "loss": 0.555, "num_tokens": 18846467.0, "step": 3185 }, { "epoch": 0.03403283795461577, "grad_norm": 4.596034612850974, "learning_rate": 3.401962876040111e-05, "loss": 0.689, "num_tokens": 18863268.0, "step": 3190 }, { "epoch": 0.03408618096081423, "grad_norm": 2.013274185807365, "learning_rate": 3.407296778323021e-05, "loss": 0.5881, "num_tokens": 18881972.0, "step": 3195 }, { "epoch": 0.03413952396701268, "grad_norm": 1.5185585232949748, "learning_rate": 3.4126306806059316e-05, "loss": 0.5774, "num_tokens": 18906839.0, "step": 3200 }, { "epoch": 0.03419286697321114, "grad_norm": 2.3323881104585675, "learning_rate": 3.417964582888842e-05, "loss": 0.6957, "num_tokens": 18939927.0, "step": 3205 }, { "epoch": 0.0342462099794096, "grad_norm": 2.0642491497875737, "learning_rate": 3.423298485171752e-05, "loss": 0.7074, "num_tokens": 18970627.0, "step": 3210 }, { "epoch": 0.03429955298560806, "grad_norm": 2.3693478807302872, "learning_rate": 3.4286323874546624e-05, "loss": 0.6272, "num_tokens": 18991586.0, "step": 3215 }, { "epoch": 0.03435289599180651, "grad_norm": 1.7824541558298255, "learning_rate": 3.433966289737572e-05, "loss": 0.7021, "num_tokens": 19027489.0, "step": 3220 }, { "epoch": 0.03440623899800497, "grad_norm": 2.2362449855314654, "learning_rate": 3.439300192020483e-05, "loss": 0.8535, "num_tokens": 19048046.0, "step": 3225 }, { "epoch": 0.03445958200420343, "grad_norm": 2.3908303666518385, "learning_rate": 3.4446340943033925e-05, "loss": 0.627, "num_tokens": 19085242.0, "step": 3230 }, { "epoch": 0.03451292501040189, "grad_norm": 2.191043864805889, "learning_rate": 3.4499679965863024e-05, "loss": 0.6572, "num_tokens": 19115441.0, "step": 3235 }, { "epoch": 0.03456626801660034, "grad_norm": 1.318714447761153, "learning_rate": 3.455301898869213e-05, "loss": 0.6584, "num_tokens": 19154283.0, "step": 3240 }, { "epoch": 0.0346196110227988, "grad_norm": 2.6571821221562315, "learning_rate": 3.460635801152123e-05, "loss": 0.6392, "num_tokens": 19178957.0, "step": 3245 }, { "epoch": 0.034672954028997255, "grad_norm": 2.399900301848659, "learning_rate": 3.465969703435033e-05, "loss": 0.5782, "num_tokens": 19203647.0, "step": 3250 }, { "epoch": 0.03472629703519572, "grad_norm": 1.4513280536256614, "learning_rate": 3.471303605717943e-05, "loss": 0.6812, "num_tokens": 19243541.0, "step": 3255 }, { "epoch": 0.03477964004139417, "grad_norm": 2.1943760977793056, "learning_rate": 3.4766375080008535e-05, "loss": 0.6288, "num_tokens": 19292313.0, "step": 3260 }, { "epoch": 0.03483298304759263, "grad_norm": 2.2258391882024378, "learning_rate": 3.481971410283763e-05, "loss": 0.7012, "num_tokens": 19319398.0, "step": 3265 }, { "epoch": 0.034886326053791085, "grad_norm": 2.934037350869316, "learning_rate": 3.487305312566674e-05, "loss": 0.6829, "num_tokens": 19341315.0, "step": 3270 }, { "epoch": 0.03493966905998955, "grad_norm": 2.1044471744657196, "learning_rate": 3.492639214849584e-05, "loss": 0.7324, "num_tokens": 19383322.0, "step": 3275 }, { "epoch": 0.034993012066188, "grad_norm": 5.047089792087005, "learning_rate": 3.497973117132494e-05, "loss": 0.7757, "num_tokens": 19413448.0, "step": 3280 }, { "epoch": 0.03504635507238646, "grad_norm": 1.3507953620622122, "learning_rate": 3.5033070194154046e-05, "loss": 0.6698, "num_tokens": 19444353.0, "step": 3285 }, { "epoch": 0.035099698078584915, "grad_norm": 2.682191598189692, "learning_rate": 3.5086409216983144e-05, "loss": 0.8096, "num_tokens": 19472435.0, "step": 3290 }, { "epoch": 0.03515304108478337, "grad_norm": 1.7573299343486344, "learning_rate": 3.513974823981225e-05, "loss": 0.6224, "num_tokens": 19494695.0, "step": 3295 }, { "epoch": 0.03520638409098183, "grad_norm": 1.899844522826642, "learning_rate": 3.519308726264135e-05, "loss": 0.6787, "num_tokens": 19525260.0, "step": 3300 }, { "epoch": 0.03525972709718029, "grad_norm": 1.912626883808448, "learning_rate": 3.524642628547045e-05, "loss": 0.5723, "num_tokens": 19550919.0, "step": 3305 }, { "epoch": 0.035313070103378745, "grad_norm": 1.5198088797282712, "learning_rate": 3.529976530829956e-05, "loss": 0.6258, "num_tokens": 19577406.0, "step": 3310 }, { "epoch": 0.0353664131095772, "grad_norm": 1.8433413621064432, "learning_rate": 3.5353104331128655e-05, "loss": 0.6091, "num_tokens": 19603519.0, "step": 3315 }, { "epoch": 0.035419756115775664, "grad_norm": 1.6862192361555934, "learning_rate": 3.540644335395776e-05, "loss": 0.757, "num_tokens": 19629158.0, "step": 3320 }, { "epoch": 0.03547309912197412, "grad_norm": 3.3025174148406173, "learning_rate": 3.545978237678686e-05, "loss": 0.6224, "num_tokens": 19647643.0, "step": 3325 }, { "epoch": 0.035526442128172575, "grad_norm": 1.6081254309957067, "learning_rate": 3.551312139961596e-05, "loss": 0.6924, "num_tokens": 19668997.0, "step": 3330 }, { "epoch": 0.03557978513437103, "grad_norm": 1.5169014790784359, "learning_rate": 3.556646042244506e-05, "loss": 0.7562, "num_tokens": 19712133.0, "step": 3335 }, { "epoch": 0.03563312814056949, "grad_norm": 1.3794533933617459, "learning_rate": 3.5619799445274166e-05, "loss": 0.6869, "num_tokens": 19744784.0, "step": 3340 }, { "epoch": 0.03568647114676795, "grad_norm": 2.381048593058742, "learning_rate": 3.5673138468103264e-05, "loss": 0.6356, "num_tokens": 19772106.0, "step": 3345 }, { "epoch": 0.035739814152966405, "grad_norm": 1.6412228800953126, "learning_rate": 3.572647749093237e-05, "loss": 0.6109, "num_tokens": 19812676.0, "step": 3350 }, { "epoch": 0.03579315715916486, "grad_norm": 1.2704764059362585, "learning_rate": 3.5779816513761474e-05, "loss": 0.716, "num_tokens": 19864072.0, "step": 3355 }, { "epoch": 0.03584650016536332, "grad_norm": 2.0706078317746823, "learning_rate": 3.583315553659057e-05, "loss": 0.6192, "num_tokens": 19889730.0, "step": 3360 }, { "epoch": 0.03589984317156178, "grad_norm": 1.452554333318886, "learning_rate": 3.588649455941968e-05, "loss": 0.6936, "num_tokens": 19930224.0, "step": 3365 }, { "epoch": 0.035953186177760235, "grad_norm": 2.611877894324566, "learning_rate": 3.5939833582248776e-05, "loss": 0.7322, "num_tokens": 19953052.0, "step": 3370 }, { "epoch": 0.03600652918395869, "grad_norm": 2.1228591364484846, "learning_rate": 3.599317260507788e-05, "loss": 0.6613, "num_tokens": 19985635.0, "step": 3375 }, { "epoch": 0.03605987219015715, "grad_norm": 2.467784480881711, "learning_rate": 3.604651162790698e-05, "loss": 0.7487, "num_tokens": 20014332.0, "step": 3380 }, { "epoch": 0.0361132151963556, "grad_norm": 2.096570811017284, "learning_rate": 3.609985065073608e-05, "loss": 0.6484, "num_tokens": 20044709.0, "step": 3385 }, { "epoch": 0.036166558202554065, "grad_norm": 2.0345410968778457, "learning_rate": 3.615318967356518e-05, "loss": 0.6079, "num_tokens": 20067196.0, "step": 3390 }, { "epoch": 0.03621990120875252, "grad_norm": 2.0734055928233737, "learning_rate": 3.620652869639428e-05, "loss": 0.5395, "num_tokens": 20090804.0, "step": 3395 }, { "epoch": 0.03627324421495098, "grad_norm": 1.4705943226861513, "learning_rate": 3.6259867719223385e-05, "loss": 0.7452, "num_tokens": 20116121.0, "step": 3400 }, { "epoch": 0.03632658722114943, "grad_norm": 1.351884587597583, "learning_rate": 3.631320674205248e-05, "loss": 0.5916, "num_tokens": 20153886.0, "step": 3405 }, { "epoch": 0.036379930227347895, "grad_norm": 1.6170171603401196, "learning_rate": 3.636654576488159e-05, "loss": 0.7207, "num_tokens": 20187138.0, "step": 3410 }, { "epoch": 0.03643327323354635, "grad_norm": 1.4127194931849774, "learning_rate": 3.641988478771069e-05, "loss": 0.7074, "num_tokens": 20216922.0, "step": 3415 }, { "epoch": 0.03648661623974481, "grad_norm": 2.2502884648237615, "learning_rate": 3.647322381053979e-05, "loss": 0.6634, "num_tokens": 20228396.0, "step": 3420 }, { "epoch": 0.03653995924594326, "grad_norm": 1.8977582514321316, "learning_rate": 3.6526562833368896e-05, "loss": 0.5779, "num_tokens": 20257293.0, "step": 3425 }, { "epoch": 0.03659330225214172, "grad_norm": 1.5132840343033218, "learning_rate": 3.6579901856197994e-05, "loss": 0.5801, "num_tokens": 20298769.0, "step": 3430 }, { "epoch": 0.03664664525834018, "grad_norm": 1.9469135419066608, "learning_rate": 3.66332408790271e-05, "loss": 0.6377, "num_tokens": 20325983.0, "step": 3435 }, { "epoch": 0.03669998826453864, "grad_norm": 1.9797219650348015, "learning_rate": 3.66865799018562e-05, "loss": 0.6964, "num_tokens": 20362643.0, "step": 3440 }, { "epoch": 0.03675333127073709, "grad_norm": 2.4911706024212235, "learning_rate": 3.67399189246853e-05, "loss": 0.766, "num_tokens": 20388605.0, "step": 3445 }, { "epoch": 0.03680667427693555, "grad_norm": 1.5917046797106988, "learning_rate": 3.67932579475144e-05, "loss": 0.5832, "num_tokens": 20416911.0, "step": 3450 }, { "epoch": 0.03686001728313401, "grad_norm": 1.736976130318473, "learning_rate": 3.6846596970343505e-05, "loss": 0.7053, "num_tokens": 20443329.0, "step": 3455 }, { "epoch": 0.03691336028933247, "grad_norm": 3.329261962926907, "learning_rate": 3.689993599317261e-05, "loss": 0.7218, "num_tokens": 20467341.0, "step": 3460 }, { "epoch": 0.03696670329553092, "grad_norm": 2.3506951040585338, "learning_rate": 3.695327501600171e-05, "loss": 0.7415, "num_tokens": 20493274.0, "step": 3465 }, { "epoch": 0.03702004630172938, "grad_norm": 1.571120524651512, "learning_rate": 3.700661403883081e-05, "loss": 0.7483, "num_tokens": 20525972.0, "step": 3470 }, { "epoch": 0.037073389307927834, "grad_norm": 2.166256095621117, "learning_rate": 3.705995306165991e-05, "loss": 0.5678, "num_tokens": 20553424.0, "step": 3475 }, { "epoch": 0.0371267323141263, "grad_norm": 1.6959571622247995, "learning_rate": 3.7113292084489016e-05, "loss": 0.4778, "num_tokens": 20573643.0, "step": 3480 }, { "epoch": 0.03718007532032475, "grad_norm": 1.3685144605226978, "learning_rate": 3.7166631107318115e-05, "loss": 0.6405, "num_tokens": 20612300.0, "step": 3485 }, { "epoch": 0.03723341832652321, "grad_norm": 2.2397331379741567, "learning_rate": 3.721997013014722e-05, "loss": 0.6244, "num_tokens": 20644694.0, "step": 3490 }, { "epoch": 0.037286761332721664, "grad_norm": 3.261677035640978, "learning_rate": 3.7273309152976324e-05, "loss": 0.4827, "num_tokens": 20656840.0, "step": 3495 }, { "epoch": 0.03734010433892013, "grad_norm": 1.9337709238288345, "learning_rate": 3.732664817580542e-05, "loss": 0.6718, "num_tokens": 20675331.0, "step": 3500 }, { "epoch": 0.03739344734511858, "grad_norm": 1.744700315552261, "learning_rate": 3.737998719863453e-05, "loss": 0.5456, "num_tokens": 20701269.0, "step": 3505 }, { "epoch": 0.03744679035131704, "grad_norm": 2.7634845134912998, "learning_rate": 3.7433326221463626e-05, "loss": 0.6637, "num_tokens": 20727364.0, "step": 3510 }, { "epoch": 0.037500133357515494, "grad_norm": 1.6334319573262936, "learning_rate": 3.748666524429273e-05, "loss": 0.729, "num_tokens": 20767090.0, "step": 3515 }, { "epoch": 0.03755347636371395, "grad_norm": 2.229782163854249, "learning_rate": 3.754000426712183e-05, "loss": 0.6701, "num_tokens": 20791105.0, "step": 3520 }, { "epoch": 0.03760681936991241, "grad_norm": 1.571932981331482, "learning_rate": 3.759334328995093e-05, "loss": 0.7544, "num_tokens": 20829806.0, "step": 3525 }, { "epoch": 0.03766016237611087, "grad_norm": 2.4000468736560343, "learning_rate": 3.764668231278003e-05, "loss": 0.7279, "num_tokens": 20867520.0, "step": 3530 }, { "epoch": 0.037713505382309324, "grad_norm": 1.6284174141942547, "learning_rate": 3.770002133560913e-05, "loss": 0.6534, "num_tokens": 20893736.0, "step": 3535 }, { "epoch": 0.03776684838850778, "grad_norm": 2.63530331326227, "learning_rate": 3.7753360358438235e-05, "loss": 0.6921, "num_tokens": 20908703.0, "step": 3540 }, { "epoch": 0.03782019139470624, "grad_norm": 2.164188938752187, "learning_rate": 3.780669938126733e-05, "loss": 0.6656, "num_tokens": 20931063.0, "step": 3545 }, { "epoch": 0.0378735344009047, "grad_norm": 1.6945373572596, "learning_rate": 3.786003840409644e-05, "loss": 0.6543, "num_tokens": 20959180.0, "step": 3550 }, { "epoch": 0.037926877407103154, "grad_norm": 2.6130691100033303, "learning_rate": 3.7913377426925536e-05, "loss": 0.5731, "num_tokens": 20987194.0, "step": 3555 }, { "epoch": 0.03798022041330161, "grad_norm": 1.489264659576076, "learning_rate": 3.796671644975464e-05, "loss": 0.6648, "num_tokens": 21015871.0, "step": 3560 }, { "epoch": 0.038033563419500066, "grad_norm": 1.667325120015918, "learning_rate": 3.8020055472583746e-05, "loss": 0.6606, "num_tokens": 21053323.0, "step": 3565 }, { "epoch": 0.03808690642569853, "grad_norm": 2.1023451971348988, "learning_rate": 3.8073394495412844e-05, "loss": 0.6534, "num_tokens": 21075247.0, "step": 3570 }, { "epoch": 0.038140249431896985, "grad_norm": 1.9943417497897626, "learning_rate": 3.812673351824195e-05, "loss": 0.7288, "num_tokens": 21100537.0, "step": 3575 }, { "epoch": 0.03819359243809544, "grad_norm": 2.132193915781359, "learning_rate": 3.818007254107105e-05, "loss": 0.7164, "num_tokens": 21140659.0, "step": 3580 }, { "epoch": 0.038246935444293896, "grad_norm": 1.943414598241963, "learning_rate": 3.823341156390015e-05, "loss": 0.6577, "num_tokens": 21172224.0, "step": 3585 }, { "epoch": 0.03830027845049236, "grad_norm": 1.9588672830642504, "learning_rate": 3.828675058672925e-05, "loss": 0.6455, "num_tokens": 21196735.0, "step": 3590 }, { "epoch": 0.038353621456690815, "grad_norm": 1.5281524595754694, "learning_rate": 3.8340089609558355e-05, "loss": 0.7516, "num_tokens": 21227178.0, "step": 3595 }, { "epoch": 0.03840696446288927, "grad_norm": 1.501196680999869, "learning_rate": 3.839342863238746e-05, "loss": 0.6677, "num_tokens": 21256777.0, "step": 3600 }, { "epoch": 0.038460307469087726, "grad_norm": 2.6264055195886016, "learning_rate": 3.844676765521656e-05, "loss": 0.546, "num_tokens": 21271297.0, "step": 3605 }, { "epoch": 0.03851365047528618, "grad_norm": 3.591429134696896, "learning_rate": 3.8500106678045663e-05, "loss": 0.7513, "num_tokens": 21309691.0, "step": 3610 }, { "epoch": 0.038566993481484645, "grad_norm": 3.084290252512353, "learning_rate": 3.855344570087476e-05, "loss": 0.7856, "num_tokens": 21335484.0, "step": 3615 }, { "epoch": 0.0386203364876831, "grad_norm": 2.1226598534550862, "learning_rate": 3.8606784723703867e-05, "loss": 0.5589, "num_tokens": 21347183.0, "step": 3620 }, { "epoch": 0.038673679493881556, "grad_norm": 1.9307309280996041, "learning_rate": 3.8660123746532965e-05, "loss": 0.6766, "num_tokens": 21365251.0, "step": 3625 }, { "epoch": 0.03872702250008001, "grad_norm": 1.37089510146794, "learning_rate": 3.871346276936207e-05, "loss": 0.7363, "num_tokens": 21391816.0, "step": 3630 }, { "epoch": 0.038780365506278475, "grad_norm": 2.8453173693057043, "learning_rate": 3.876680179219117e-05, "loss": 0.7052, "num_tokens": 21431320.0, "step": 3635 }, { "epoch": 0.03883370851247693, "grad_norm": 1.8924107638658278, "learning_rate": 3.882014081502027e-05, "loss": 0.7243, "num_tokens": 21457717.0, "step": 3640 }, { "epoch": 0.038887051518675386, "grad_norm": 1.6501276965729699, "learning_rate": 3.887347983784938e-05, "loss": 0.7147, "num_tokens": 21488247.0, "step": 3645 }, { "epoch": 0.03894039452487384, "grad_norm": 1.921907870828025, "learning_rate": 3.8926818860678476e-05, "loss": 0.8295, "num_tokens": 21522151.0, "step": 3650 }, { "epoch": 0.0389937375310723, "grad_norm": 1.5910344569208112, "learning_rate": 3.898015788350758e-05, "loss": 0.531, "num_tokens": 21550948.0, "step": 3655 }, { "epoch": 0.03904708053727076, "grad_norm": 1.7932735512450262, "learning_rate": 3.903349690633667e-05, "loss": 0.5972, "num_tokens": 21580167.0, "step": 3660 }, { "epoch": 0.039100423543469216, "grad_norm": 1.4696338558618733, "learning_rate": 3.908683592916578e-05, "loss": 0.665, "num_tokens": 21613566.0, "step": 3665 }, { "epoch": 0.03915376654966767, "grad_norm": 1.8143775698492113, "learning_rate": 3.914017495199488e-05, "loss": 0.6522, "num_tokens": 21638576.0, "step": 3670 }, { "epoch": 0.03920710955586613, "grad_norm": 2.416894546550053, "learning_rate": 3.919351397482398e-05, "loss": 0.5582, "num_tokens": 21664866.0, "step": 3675 }, { "epoch": 0.03926045256206459, "grad_norm": 2.8136379281723385, "learning_rate": 3.9246852997653085e-05, "loss": 0.7336, "num_tokens": 21704917.0, "step": 3680 }, { "epoch": 0.039313795568263046, "grad_norm": 1.4963224107444077, "learning_rate": 3.930019202048218e-05, "loss": 0.5777, "num_tokens": 21729806.0, "step": 3685 }, { "epoch": 0.0393671385744615, "grad_norm": 2.0406568562406173, "learning_rate": 3.935353104331129e-05, "loss": 0.6644, "num_tokens": 21754762.0, "step": 3690 }, { "epoch": 0.03942048158065996, "grad_norm": 1.7067003107382464, "learning_rate": 3.9406870066140386e-05, "loss": 0.641, "num_tokens": 21797862.0, "step": 3695 }, { "epoch": 0.039473824586858414, "grad_norm": 1.8682530354848412, "learning_rate": 3.946020908896949e-05, "loss": 0.6115, "num_tokens": 21828196.0, "step": 3700 }, { "epoch": 0.039527167593056876, "grad_norm": 2.6764188847301904, "learning_rate": 3.951354811179859e-05, "loss": 0.7245, "num_tokens": 21860681.0, "step": 3705 }, { "epoch": 0.03958051059925533, "grad_norm": 1.5680387931839446, "learning_rate": 3.9566887134627694e-05, "loss": 0.7574, "num_tokens": 21890930.0, "step": 3710 }, { "epoch": 0.03963385360545379, "grad_norm": 1.7090516434046006, "learning_rate": 3.96202261574568e-05, "loss": 0.7868, "num_tokens": 21922039.0, "step": 3715 }, { "epoch": 0.039687196611652244, "grad_norm": 1.5208398681506872, "learning_rate": 3.96735651802859e-05, "loss": 0.6409, "num_tokens": 21940405.0, "step": 3720 }, { "epoch": 0.039740539617850706, "grad_norm": 2.295622674958193, "learning_rate": 3.9726904203115e-05, "loss": 0.7219, "num_tokens": 21968421.0, "step": 3725 }, { "epoch": 0.03979388262404916, "grad_norm": 1.8890317283303357, "learning_rate": 3.97802432259441e-05, "loss": 0.738, "num_tokens": 21993314.0, "step": 3730 }, { "epoch": 0.03984722563024762, "grad_norm": 1.6056902217313016, "learning_rate": 3.9833582248773206e-05, "loss": 0.8214, "num_tokens": 22033918.0, "step": 3735 }, { "epoch": 0.039900568636446074, "grad_norm": 2.1960538185297236, "learning_rate": 3.9886921271602304e-05, "loss": 0.7717, "num_tokens": 22061290.0, "step": 3740 }, { "epoch": 0.03995391164264453, "grad_norm": 2.0308624315561947, "learning_rate": 3.994026029443141e-05, "loss": 0.7101, "num_tokens": 22093048.0, "step": 3745 }, { "epoch": 0.04000725464884299, "grad_norm": 3.6693412472025946, "learning_rate": 3.9993599317260514e-05, "loss": 0.647, "num_tokens": 22127899.0, "step": 3750 }, { "epoch": 0.04006059765504145, "grad_norm": 1.6792843633662946, "learning_rate": 4.004693834008961e-05, "loss": 0.8093, "num_tokens": 22164151.0, "step": 3755 }, { "epoch": 0.040113940661239904, "grad_norm": 1.968219194305774, "learning_rate": 4.010027736291872e-05, "loss": 0.6732, "num_tokens": 22185554.0, "step": 3760 }, { "epoch": 0.04016728366743836, "grad_norm": 2.1219178122751137, "learning_rate": 4.0153616385747815e-05, "loss": 0.7264, "num_tokens": 22210720.0, "step": 3765 }, { "epoch": 0.04022062667363682, "grad_norm": 2.7465771216129142, "learning_rate": 4.020695540857692e-05, "loss": 0.844, "num_tokens": 22241925.0, "step": 3770 }, { "epoch": 0.04027396967983528, "grad_norm": 2.552860369303941, "learning_rate": 4.026029443140602e-05, "loss": 0.7179, "num_tokens": 22269764.0, "step": 3775 }, { "epoch": 0.040327312686033734, "grad_norm": 1.6701310162805283, "learning_rate": 4.031363345423512e-05, "loss": 0.7111, "num_tokens": 22296994.0, "step": 3780 }, { "epoch": 0.04038065569223219, "grad_norm": 2.6153826647251974, "learning_rate": 4.036697247706422e-05, "loss": 0.6336, "num_tokens": 22322870.0, "step": 3785 }, { "epoch": 0.040433998698430645, "grad_norm": 1.6278470574724582, "learning_rate": 4.0420311499893326e-05, "loss": 0.5547, "num_tokens": 22351913.0, "step": 3790 }, { "epoch": 0.04048734170462911, "grad_norm": 1.498369783484821, "learning_rate": 4.047365052272243e-05, "loss": 0.7066, "num_tokens": 22384749.0, "step": 3795 }, { "epoch": 0.040540684710827564, "grad_norm": 1.9991377458713238, "learning_rate": 4.052698954555152e-05, "loss": 0.7327, "num_tokens": 22418937.0, "step": 3800 }, { "epoch": 0.04059402771702602, "grad_norm": 1.2517548068999205, "learning_rate": 4.058032856838063e-05, "loss": 0.6388, "num_tokens": 22451348.0, "step": 3805 }, { "epoch": 0.040647370723224475, "grad_norm": 2.2202736678255377, "learning_rate": 4.0633667591209725e-05, "loss": 0.6888, "num_tokens": 22477047.0, "step": 3810 }, { "epoch": 0.04070071372942294, "grad_norm": 1.845265310690191, "learning_rate": 4.068700661403883e-05, "loss": 0.672, "num_tokens": 22511973.0, "step": 3815 }, { "epoch": 0.040754056735621394, "grad_norm": 1.7635559162668013, "learning_rate": 4.0740345636867935e-05, "loss": 0.6522, "num_tokens": 22540969.0, "step": 3820 }, { "epoch": 0.04080739974181985, "grad_norm": 3.2978237202538745, "learning_rate": 4.0793684659697034e-05, "loss": 0.6353, "num_tokens": 22561474.0, "step": 3825 }, { "epoch": 0.040860742748018306, "grad_norm": 2.029295302400253, "learning_rate": 4.084702368252614e-05, "loss": 0.7356, "num_tokens": 22582371.0, "step": 3830 }, { "epoch": 0.04091408575421676, "grad_norm": 2.1117441335818596, "learning_rate": 4.090036270535524e-05, "loss": 0.6906, "num_tokens": 22613976.0, "step": 3835 }, { "epoch": 0.040967428760415224, "grad_norm": 1.8532196803177479, "learning_rate": 4.095370172818434e-05, "loss": 0.702, "num_tokens": 22641755.0, "step": 3840 }, { "epoch": 0.04102077176661368, "grad_norm": 2.197562115577898, "learning_rate": 4.100704075101344e-05, "loss": 0.5889, "num_tokens": 22662120.0, "step": 3845 }, { "epoch": 0.041074114772812136, "grad_norm": 2.334074150366558, "learning_rate": 4.1060379773842545e-05, "loss": 0.8193, "num_tokens": 22698859.0, "step": 3850 }, { "epoch": 0.04112745777901059, "grad_norm": 1.8319361534549365, "learning_rate": 4.111371879667165e-05, "loss": 0.7847, "num_tokens": 22740361.0, "step": 3855 }, { "epoch": 0.041180800785209054, "grad_norm": 1.443979142752034, "learning_rate": 4.116705781950075e-05, "loss": 0.6038, "num_tokens": 22780358.0, "step": 3860 }, { "epoch": 0.04123414379140751, "grad_norm": 2.0531210965973994, "learning_rate": 4.122039684232985e-05, "loss": 0.7183, "num_tokens": 22830752.0, "step": 3865 }, { "epoch": 0.041287486797605966, "grad_norm": 3.01702211914834, "learning_rate": 4.127373586515895e-05, "loss": 0.72, "num_tokens": 22848073.0, "step": 3870 }, { "epoch": 0.04134082980380442, "grad_norm": 2.278322526396825, "learning_rate": 4.1327074887988056e-05, "loss": 0.6688, "num_tokens": 22887542.0, "step": 3875 }, { "epoch": 0.04139417281000288, "grad_norm": 1.719385167064649, "learning_rate": 4.1380413910817154e-05, "loss": 0.6901, "num_tokens": 22910150.0, "step": 3880 }, { "epoch": 0.04144751581620134, "grad_norm": 1.8185789939318762, "learning_rate": 4.143375293364626e-05, "loss": 0.7285, "num_tokens": 22947025.0, "step": 3885 }, { "epoch": 0.041500858822399796, "grad_norm": 1.381880305405159, "learning_rate": 4.148709195647536e-05, "loss": 0.6027, "num_tokens": 22992733.0, "step": 3890 }, { "epoch": 0.04155420182859825, "grad_norm": 1.9189816987089794, "learning_rate": 4.154043097930446e-05, "loss": 0.5619, "num_tokens": 23008244.0, "step": 3895 }, { "epoch": 0.04160754483479671, "grad_norm": 1.5312727890251032, "learning_rate": 4.159377000213357e-05, "loss": 0.5902, "num_tokens": 23036714.0, "step": 3900 }, { "epoch": 0.04166088784099517, "grad_norm": 2.9396396976824795, "learning_rate": 4.1647109024962665e-05, "loss": 0.638, "num_tokens": 23067151.0, "step": 3905 }, { "epoch": 0.041714230847193626, "grad_norm": 1.200652680097142, "learning_rate": 4.170044804779177e-05, "loss": 0.6596, "num_tokens": 23098650.0, "step": 3910 }, { "epoch": 0.04176757385339208, "grad_norm": 1.6612184514432464, "learning_rate": 4.175378707062087e-05, "loss": 0.7077, "num_tokens": 23121049.0, "step": 3915 }, { "epoch": 0.04182091685959054, "grad_norm": 2.156248734572956, "learning_rate": 4.180712609344997e-05, "loss": 0.7517, "num_tokens": 23146999.0, "step": 3920 }, { "epoch": 0.04187425986578899, "grad_norm": 1.9959323006521192, "learning_rate": 4.186046511627907e-05, "loss": 0.6062, "num_tokens": 23168646.0, "step": 3925 }, { "epoch": 0.041927602871987456, "grad_norm": 1.1781379558462137, "learning_rate": 4.1913804139108176e-05, "loss": 0.7938, "num_tokens": 23215824.0, "step": 3930 }, { "epoch": 0.04198094587818591, "grad_norm": 2.491623975109907, "learning_rate": 4.196714316193728e-05, "loss": 0.5524, "num_tokens": 23239499.0, "step": 3935 }, { "epoch": 0.04203428888438437, "grad_norm": 1.5877703032854185, "learning_rate": 4.202048218476637e-05, "loss": 0.5577, "num_tokens": 23259189.0, "step": 3940 }, { "epoch": 0.04208763189058282, "grad_norm": 1.9620981893672649, "learning_rate": 4.207382120759548e-05, "loss": 0.7104, "num_tokens": 23280295.0, "step": 3945 }, { "epoch": 0.042140974896781286, "grad_norm": 2.214064378511625, "learning_rate": 4.2127160230424576e-05, "loss": 0.591, "num_tokens": 23309884.0, "step": 3950 }, { "epoch": 0.04219431790297974, "grad_norm": 1.6716634629063738, "learning_rate": 4.218049925325368e-05, "loss": 0.7208, "num_tokens": 23330556.0, "step": 3955 }, { "epoch": 0.0422476609091782, "grad_norm": 2.488000998756416, "learning_rate": 4.2233838276082786e-05, "loss": 0.7266, "num_tokens": 23346443.0, "step": 3960 }, { "epoch": 0.04230100391537665, "grad_norm": 3.241941401196035, "learning_rate": 4.2287177298911884e-05, "loss": 0.7647, "num_tokens": 23374305.0, "step": 3965 }, { "epoch": 0.04235434692157511, "grad_norm": 1.8799273948962163, "learning_rate": 4.234051632174099e-05, "loss": 0.6529, "num_tokens": 23406619.0, "step": 3970 }, { "epoch": 0.04240768992777357, "grad_norm": 1.2294110011627377, "learning_rate": 4.239385534457009e-05, "loss": 0.7097, "num_tokens": 23444681.0, "step": 3975 }, { "epoch": 0.04246103293397203, "grad_norm": 2.94868291620136, "learning_rate": 4.244719436739919e-05, "loss": 0.7174, "num_tokens": 23463812.0, "step": 3980 }, { "epoch": 0.04251437594017048, "grad_norm": 1.8985844692993825, "learning_rate": 4.250053339022829e-05, "loss": 0.8399, "num_tokens": 23516679.0, "step": 3985 }, { "epoch": 0.04256771894636894, "grad_norm": 2.3639867006907123, "learning_rate": 4.2553872413057395e-05, "loss": 0.7493, "num_tokens": 23547671.0, "step": 3990 }, { "epoch": 0.0426210619525674, "grad_norm": 1.9288906050278414, "learning_rate": 4.260721143588649e-05, "loss": 0.7915, "num_tokens": 23575779.0, "step": 3995 }, { "epoch": 0.04267440495876586, "grad_norm": 2.8502455812794874, "learning_rate": 4.26605504587156e-05, "loss": 0.5244, "num_tokens": 23595511.0, "step": 4000 }, { "epoch": 0.04272774796496431, "grad_norm": 2.29290015212519, "learning_rate": 4.27138894815447e-05, "loss": 0.8916, "num_tokens": 23634043.0, "step": 4005 }, { "epoch": 0.04278109097116277, "grad_norm": 2.5086674586638398, "learning_rate": 4.27672285043738e-05, "loss": 0.6312, "num_tokens": 23670627.0, "step": 4010 }, { "epoch": 0.042834433977361225, "grad_norm": 1.5674692506735695, "learning_rate": 4.2820567527202906e-05, "loss": 0.6428, "num_tokens": 23700567.0, "step": 4015 }, { "epoch": 0.04288777698355969, "grad_norm": 4.206159902635154, "learning_rate": 4.2873906550032004e-05, "loss": 0.8168, "num_tokens": 23742572.0, "step": 4020 }, { "epoch": 0.04294111998975814, "grad_norm": 1.2531238942142802, "learning_rate": 4.292724557286111e-05, "loss": 0.6754, "num_tokens": 23786558.0, "step": 4025 }, { "epoch": 0.0429944629959566, "grad_norm": 1.6336546843797635, "learning_rate": 4.298058459569021e-05, "loss": 0.7456, "num_tokens": 23831044.0, "step": 4030 }, { "epoch": 0.043047806002155055, "grad_norm": 2.088163155463328, "learning_rate": 4.303392361851931e-05, "loss": 0.7173, "num_tokens": 23858609.0, "step": 4035 }, { "epoch": 0.04310114900835352, "grad_norm": 2.4121555932983045, "learning_rate": 4.308726264134841e-05, "loss": 0.7665, "num_tokens": 23882112.0, "step": 4040 }, { "epoch": 0.04315449201455197, "grad_norm": 2.0758476697986907, "learning_rate": 4.3140601664177515e-05, "loss": 0.6049, "num_tokens": 23894585.0, "step": 4045 }, { "epoch": 0.04320783502075043, "grad_norm": 1.8752628384472536, "learning_rate": 4.319394068700662e-05, "loss": 0.7283, "num_tokens": 23932015.0, "step": 4050 }, { "epoch": 0.043261178026948885, "grad_norm": 2.166015966509464, "learning_rate": 4.324727970983572e-05, "loss": 0.8091, "num_tokens": 23967629.0, "step": 4055 }, { "epoch": 0.04331452103314734, "grad_norm": 2.772070036704222, "learning_rate": 4.330061873266482e-05, "loss": 0.724, "num_tokens": 23994159.0, "step": 4060 }, { "epoch": 0.0433678640393458, "grad_norm": 1.4936374348174932, "learning_rate": 4.335395775549392e-05, "loss": 0.7257, "num_tokens": 24024624.0, "step": 4065 }, { "epoch": 0.04342120704554426, "grad_norm": 1.970024826814631, "learning_rate": 4.3407296778323026e-05, "loss": 0.6897, "num_tokens": 24051204.0, "step": 4070 }, { "epoch": 0.043474550051742715, "grad_norm": 1.4475553924068294, "learning_rate": 4.3460635801152125e-05, "loss": 0.618, "num_tokens": 24073208.0, "step": 4075 }, { "epoch": 0.04352789305794117, "grad_norm": 2.5552991539423116, "learning_rate": 4.351397482398123e-05, "loss": 0.683, "num_tokens": 24118220.0, "step": 4080 }, { "epoch": 0.04358123606413963, "grad_norm": 1.2748385760259793, "learning_rate": 4.356731384681033e-05, "loss": 0.6598, "num_tokens": 24155581.0, "step": 4085 }, { "epoch": 0.04363457907033809, "grad_norm": 1.3452643262885375, "learning_rate": 4.3620652869639426e-05, "loss": 0.7187, "num_tokens": 24200474.0, "step": 4090 }, { "epoch": 0.043687922076536545, "grad_norm": 1.9805789222463734, "learning_rate": 4.367399189246853e-05, "loss": 0.7902, "num_tokens": 24229733.0, "step": 4095 }, { "epoch": 0.043741265082735, "grad_norm": 1.3556659570517255, "learning_rate": 4.372733091529763e-05, "loss": 0.6971, "num_tokens": 24260736.0, "step": 4100 }, { "epoch": 0.04379460808893346, "grad_norm": 1.697300517868266, "learning_rate": 4.3780669938126734e-05, "loss": 0.7978, "num_tokens": 24307515.0, "step": 4105 }, { "epoch": 0.04384795109513192, "grad_norm": 1.8124171424197941, "learning_rate": 4.383400896095584e-05, "loss": 0.676, "num_tokens": 24332097.0, "step": 4110 }, { "epoch": 0.043901294101330375, "grad_norm": 1.7457844441288464, "learning_rate": 4.388734798378494e-05, "loss": 0.6662, "num_tokens": 24372624.0, "step": 4115 }, { "epoch": 0.04395463710752883, "grad_norm": 1.5354614037810081, "learning_rate": 4.394068700661404e-05, "loss": 0.7292, "num_tokens": 24401171.0, "step": 4120 }, { "epoch": 0.04400798011372729, "grad_norm": 1.4364676673007752, "learning_rate": 4.399402602944314e-05, "loss": 0.5843, "num_tokens": 24425848.0, "step": 4125 }, { "epoch": 0.04406132311992575, "grad_norm": 1.704500108819304, "learning_rate": 4.4047365052272245e-05, "loss": 0.6511, "num_tokens": 24463050.0, "step": 4130 }, { "epoch": 0.044114666126124205, "grad_norm": 1.977992809867684, "learning_rate": 4.410070407510134e-05, "loss": 0.5532, "num_tokens": 24491050.0, "step": 4135 }, { "epoch": 0.04416800913232266, "grad_norm": 1.6029678715952091, "learning_rate": 4.415404309793045e-05, "loss": 0.7396, "num_tokens": 24526938.0, "step": 4140 }, { "epoch": 0.04422135213852112, "grad_norm": 1.4685066151455146, "learning_rate": 4.4207382120759546e-05, "loss": 0.727, "num_tokens": 24560185.0, "step": 4145 }, { "epoch": 0.04427469514471957, "grad_norm": 2.3471624721909436, "learning_rate": 4.426072114358865e-05, "loss": 0.5947, "num_tokens": 24574418.0, "step": 4150 }, { "epoch": 0.044328038150918035, "grad_norm": 1.692581174279793, "learning_rate": 4.4314060166417756e-05, "loss": 0.7139, "num_tokens": 24590077.0, "step": 4155 }, { "epoch": 0.04438138115711649, "grad_norm": 2.6002697242630295, "learning_rate": 4.4367399189246854e-05, "loss": 0.5913, "num_tokens": 24604914.0, "step": 4160 }, { "epoch": 0.04443472416331495, "grad_norm": 1.7203594902171038, "learning_rate": 4.442073821207596e-05, "loss": 0.762, "num_tokens": 24641266.0, "step": 4165 }, { "epoch": 0.0444880671695134, "grad_norm": 1.5932865725964294, "learning_rate": 4.447407723490506e-05, "loss": 0.8296, "num_tokens": 24675880.0, "step": 4170 }, { "epoch": 0.044541410175711865, "grad_norm": 1.3587943486111522, "learning_rate": 4.452741625773416e-05, "loss": 0.6681, "num_tokens": 24704606.0, "step": 4175 }, { "epoch": 0.04459475318191032, "grad_norm": 2.037008128011891, "learning_rate": 4.458075528056326e-05, "loss": 0.6506, "num_tokens": 24735880.0, "step": 4180 }, { "epoch": 0.04464809618810878, "grad_norm": 1.7546452431707869, "learning_rate": 4.4634094303392365e-05, "loss": 0.6548, "num_tokens": 24762613.0, "step": 4185 }, { "epoch": 0.04470143919430723, "grad_norm": 1.490786389836575, "learning_rate": 4.468743332622147e-05, "loss": 0.6511, "num_tokens": 24804631.0, "step": 4190 }, { "epoch": 0.04475478220050569, "grad_norm": 1.8470916209664971, "learning_rate": 4.474077234905057e-05, "loss": 0.7039, "num_tokens": 24833956.0, "step": 4195 }, { "epoch": 0.04480812520670415, "grad_norm": 1.3243473879609262, "learning_rate": 4.4794111371879673e-05, "loss": 0.7186, "num_tokens": 24868244.0, "step": 4200 }, { "epoch": 0.04486146821290261, "grad_norm": 1.6405098205878408, "learning_rate": 4.484745039470877e-05, "loss": 0.754, "num_tokens": 24886230.0, "step": 4205 }, { "epoch": 0.04491481121910106, "grad_norm": 1.7667548256288397, "learning_rate": 4.4900789417537877e-05, "loss": 0.7081, "num_tokens": 24918818.0, "step": 4210 }, { "epoch": 0.04496815422529952, "grad_norm": 1.2279734745885102, "learning_rate": 4.4954128440366975e-05, "loss": 0.6624, "num_tokens": 24957939.0, "step": 4215 }, { "epoch": 0.04502149723149798, "grad_norm": 3.909756995978758, "learning_rate": 4.500746746319608e-05, "loss": 0.6692, "num_tokens": 24981411.0, "step": 4220 }, { "epoch": 0.04507484023769644, "grad_norm": 2.9399675974871204, "learning_rate": 4.506080648602518e-05, "loss": 0.7515, "num_tokens": 25007457.0, "step": 4225 }, { "epoch": 0.04512818324389489, "grad_norm": 2.1393744373142605, "learning_rate": 4.5114145508854276e-05, "loss": 0.8219, "num_tokens": 25055475.0, "step": 4230 }, { "epoch": 0.04518152625009335, "grad_norm": 1.452128112721498, "learning_rate": 4.516748453168338e-05, "loss": 0.6377, "num_tokens": 25087642.0, "step": 4235 }, { "epoch": 0.045234869256291804, "grad_norm": 1.610342361883011, "learning_rate": 4.522082355451248e-05, "loss": 0.716, "num_tokens": 25123670.0, "step": 4240 }, { "epoch": 0.04528821226249027, "grad_norm": 1.6431219307579807, "learning_rate": 4.5274162577341584e-05, "loss": 0.6682, "num_tokens": 25155309.0, "step": 4245 }, { "epoch": 0.04534155526868872, "grad_norm": 2.0363108727943264, "learning_rate": 4.532750160017068e-05, "loss": 0.6694, "num_tokens": 25176965.0, "step": 4250 }, { "epoch": 0.04539489827488718, "grad_norm": 2.3484474224368097, "learning_rate": 4.538084062299979e-05, "loss": 0.7666, "num_tokens": 25195113.0, "step": 4255 }, { "epoch": 0.045448241281085634, "grad_norm": 1.4962062878444322, "learning_rate": 4.543417964582889e-05, "loss": 0.7074, "num_tokens": 25229839.0, "step": 4260 }, { "epoch": 0.0455015842872841, "grad_norm": 2.144532025376379, "learning_rate": 4.548751866865799e-05, "loss": 0.6044, "num_tokens": 25255540.0, "step": 4265 }, { "epoch": 0.04555492729348255, "grad_norm": 1.7947103734678038, "learning_rate": 4.5540857691487095e-05, "loss": 0.6545, "num_tokens": 25295713.0, "step": 4270 }, { "epoch": 0.04560827029968101, "grad_norm": 2.529944488910496, "learning_rate": 4.559419671431619e-05, "loss": 0.7725, "num_tokens": 25312477.0, "step": 4275 }, { "epoch": 0.045661613305879464, "grad_norm": 1.8177811303984277, "learning_rate": 4.56475357371453e-05, "loss": 0.7044, "num_tokens": 25342015.0, "step": 4280 }, { "epoch": 0.04571495631207792, "grad_norm": 1.861182262422305, "learning_rate": 4.5700874759974396e-05, "loss": 0.5976, "num_tokens": 25376476.0, "step": 4285 }, { "epoch": 0.04576829931827638, "grad_norm": 2.0971492425471, "learning_rate": 4.57542137828035e-05, "loss": 0.7041, "num_tokens": 25416251.0, "step": 4290 }, { "epoch": 0.04582164232447484, "grad_norm": 2.584994907401149, "learning_rate": 4.5807552805632606e-05, "loss": 0.7127, "num_tokens": 25443350.0, "step": 4295 }, { "epoch": 0.045874985330673294, "grad_norm": 1.5627931540196998, "learning_rate": 4.5860891828461704e-05, "loss": 0.7318, "num_tokens": 25487547.0, "step": 4300 }, { "epoch": 0.04592832833687175, "grad_norm": 1.8948075023557398, "learning_rate": 4.591423085129081e-05, "loss": 0.7362, "num_tokens": 25508924.0, "step": 4305 }, { "epoch": 0.04598167134307021, "grad_norm": 1.8656723138950857, "learning_rate": 4.596756987411991e-05, "loss": 0.6931, "num_tokens": 25519930.0, "step": 4310 }, { "epoch": 0.04603501434926867, "grad_norm": 1.4233374851596934, "learning_rate": 4.602090889694901e-05, "loss": 0.7091, "num_tokens": 25560875.0, "step": 4315 }, { "epoch": 0.046088357355467124, "grad_norm": 1.116948123937129, "learning_rate": 4.607424791977811e-05, "loss": 0.7583, "num_tokens": 25614380.0, "step": 4320 }, { "epoch": 0.04614170036166558, "grad_norm": 1.913290825728951, "learning_rate": 4.6127586942607216e-05, "loss": 0.7377, "num_tokens": 25634597.0, "step": 4325 }, { "epoch": 0.046195043367864036, "grad_norm": 3.0817559187766226, "learning_rate": 4.6180925965436314e-05, "loss": 0.6705, "num_tokens": 25661940.0, "step": 4330 }, { "epoch": 0.0462483863740625, "grad_norm": 1.6247329858497621, "learning_rate": 4.623426498826542e-05, "loss": 0.6069, "num_tokens": 25691675.0, "step": 4335 }, { "epoch": 0.046301729380260954, "grad_norm": 1.4504727436356915, "learning_rate": 4.6287604011094524e-05, "loss": 0.7204, "num_tokens": 25725309.0, "step": 4340 }, { "epoch": 0.04635507238645941, "grad_norm": 1.6593086214067203, "learning_rate": 4.634094303392362e-05, "loss": 0.7302, "num_tokens": 25774571.0, "step": 4345 }, { "epoch": 0.046408415392657866, "grad_norm": 1.338661693257311, "learning_rate": 4.639428205675273e-05, "loss": 0.7059, "num_tokens": 25812266.0, "step": 4350 }, { "epoch": 0.04646175839885633, "grad_norm": 1.4866720045935156, "learning_rate": 4.6447621079581825e-05, "loss": 0.8085, "num_tokens": 25844631.0, "step": 4355 }, { "epoch": 0.046515101405054785, "grad_norm": 1.7900963531870364, "learning_rate": 4.650096010241093e-05, "loss": 0.7307, "num_tokens": 25887175.0, "step": 4360 }, { "epoch": 0.04656844441125324, "grad_norm": 1.277708700410048, "learning_rate": 4.655429912524003e-05, "loss": 0.5946, "num_tokens": 25921579.0, "step": 4365 }, { "epoch": 0.046621787417451696, "grad_norm": 1.4165988872572428, "learning_rate": 4.6607638148069126e-05, "loss": 0.6949, "num_tokens": 25957719.0, "step": 4370 }, { "epoch": 0.04667513042365015, "grad_norm": 1.5700006062519576, "learning_rate": 4.666097717089823e-05, "loss": 0.771, "num_tokens": 26010429.0, "step": 4375 }, { "epoch": 0.046728473429848615, "grad_norm": 1.6929891915627002, "learning_rate": 4.671431619372733e-05, "loss": 0.6848, "num_tokens": 26045469.0, "step": 4380 }, { "epoch": 0.04678181643604707, "grad_norm": 2.1431493785847517, "learning_rate": 4.6767655216556434e-05, "loss": 0.6635, "num_tokens": 26075893.0, "step": 4385 }, { "epoch": 0.046835159442245526, "grad_norm": 1.8223226538173507, "learning_rate": 4.682099423938553e-05, "loss": 0.6415, "num_tokens": 26101046.0, "step": 4390 }, { "epoch": 0.04688850244844398, "grad_norm": 1.1371135638095247, "learning_rate": 4.687433326221464e-05, "loss": 0.6563, "num_tokens": 26134454.0, "step": 4395 }, { "epoch": 0.046941845454642445, "grad_norm": 1.1101968782703993, "learning_rate": 4.692767228504374e-05, "loss": 0.7896, "num_tokens": 26164927.0, "step": 4400 }, { "epoch": 0.0469951884608409, "grad_norm": 1.6265888299128193, "learning_rate": 4.698101130787284e-05, "loss": 0.5671, "num_tokens": 26181983.0, "step": 4405 }, { "epoch": 0.047048531467039356, "grad_norm": 1.3744136221441814, "learning_rate": 4.7034350330701945e-05, "loss": 0.7301, "num_tokens": 26219509.0, "step": 4410 }, { "epoch": 0.04710187447323781, "grad_norm": 2.278328319898999, "learning_rate": 4.7087689353531044e-05, "loss": 0.7168, "num_tokens": 26249073.0, "step": 4415 }, { "epoch": 0.04715521747943627, "grad_norm": 2.809793647383721, "learning_rate": 4.714102837636015e-05, "loss": 0.621, "num_tokens": 26277455.0, "step": 4420 }, { "epoch": 0.04720856048563473, "grad_norm": 1.5139021173392195, "learning_rate": 4.719436739918925e-05, "loss": 0.6717, "num_tokens": 26296260.0, "step": 4425 }, { "epoch": 0.047261903491833186, "grad_norm": 1.3993472911299105, "learning_rate": 4.724770642201835e-05, "loss": 0.6029, "num_tokens": 26323607.0, "step": 4430 }, { "epoch": 0.04731524649803164, "grad_norm": 1.4317913421001607, "learning_rate": 4.730104544484745e-05, "loss": 0.7368, "num_tokens": 26368544.0, "step": 4435 }, { "epoch": 0.0473685895042301, "grad_norm": 2.1083054949537767, "learning_rate": 4.7354384467676555e-05, "loss": 0.7685, "num_tokens": 26404279.0, "step": 4440 }, { "epoch": 0.04742193251042856, "grad_norm": 1.2451747551335426, "learning_rate": 4.740772349050566e-05, "loss": 0.8123, "num_tokens": 26434359.0, "step": 4445 }, { "epoch": 0.047475275516627016, "grad_norm": 1.4482777831148395, "learning_rate": 4.746106251333476e-05, "loss": 0.6653, "num_tokens": 26463467.0, "step": 4450 }, { "epoch": 0.04752861852282547, "grad_norm": 3.4214311478888138, "learning_rate": 4.751440153616386e-05, "loss": 0.7792, "num_tokens": 26489833.0, "step": 4455 }, { "epoch": 0.04758196152902393, "grad_norm": 1.8028460470231311, "learning_rate": 4.756774055899296e-05, "loss": 0.8464, "num_tokens": 26529887.0, "step": 4460 }, { "epoch": 0.047635304535222384, "grad_norm": 1.6962294270153448, "learning_rate": 4.7621079581822066e-05, "loss": 0.6005, "num_tokens": 26560653.0, "step": 4465 }, { "epoch": 0.047688647541420846, "grad_norm": 2.4442767340685627, "learning_rate": 4.7674418604651164e-05, "loss": 0.6807, "num_tokens": 26589900.0, "step": 4470 }, { "epoch": 0.0477419905476193, "grad_norm": 2.0814753539085538, "learning_rate": 4.772775762748027e-05, "loss": 0.7182, "num_tokens": 26613738.0, "step": 4475 }, { "epoch": 0.04779533355381776, "grad_norm": 1.8660283039355565, "learning_rate": 4.778109665030937e-05, "loss": 0.7655, "num_tokens": 26636629.0, "step": 4480 }, { "epoch": 0.047848676560016214, "grad_norm": 1.947522888363326, "learning_rate": 4.783443567313847e-05, "loss": 0.6141, "num_tokens": 26663340.0, "step": 4485 }, { "epoch": 0.047902019566214676, "grad_norm": 2.1707123954647907, "learning_rate": 4.788777469596758e-05, "loss": 0.6609, "num_tokens": 26692323.0, "step": 4490 }, { "epoch": 0.04795536257241313, "grad_norm": 1.9331943378516383, "learning_rate": 4.7941113718796675e-05, "loss": 0.6382, "num_tokens": 26717277.0, "step": 4495 }, { "epoch": 0.04800870557861159, "grad_norm": 2.055571952534796, "learning_rate": 4.799445274162578e-05, "loss": 0.7037, "num_tokens": 26736835.0, "step": 4500 }, { "epoch": 0.048062048584810044, "grad_norm": 1.5283679847047267, "learning_rate": 4.804779176445487e-05, "loss": 0.6463, "num_tokens": 26762060.0, "step": 4505 }, { "epoch": 0.0481153915910085, "grad_norm": 1.9342437266452726, "learning_rate": 4.8101130787283976e-05, "loss": 0.6048, "num_tokens": 26784418.0, "step": 4510 }, { "epoch": 0.04816873459720696, "grad_norm": 1.7276093259083731, "learning_rate": 4.815446981011308e-05, "loss": 0.7621, "num_tokens": 26797362.0, "step": 4515 }, { "epoch": 0.04822207760340542, "grad_norm": 1.1120243839667523, "learning_rate": 4.820780883294218e-05, "loss": 0.6759, "num_tokens": 26851911.0, "step": 4520 }, { "epoch": 0.048275420609603874, "grad_norm": 1.3654886346298443, "learning_rate": 4.8261147855771284e-05, "loss": 0.6547, "num_tokens": 26879769.0, "step": 4525 }, { "epoch": 0.04832876361580233, "grad_norm": 2.2331814971092103, "learning_rate": 4.831448687860038e-05, "loss": 0.6664, "num_tokens": 26893140.0, "step": 4530 }, { "epoch": 0.04838210662200079, "grad_norm": 1.5321547481112017, "learning_rate": 4.836782590142949e-05, "loss": 0.6618, "num_tokens": 26933294.0, "step": 4535 }, { "epoch": 0.04843544962819925, "grad_norm": 1.484880434905489, "learning_rate": 4.8421164924258586e-05, "loss": 0.6756, "num_tokens": 26975025.0, "step": 4540 }, { "epoch": 0.048488792634397704, "grad_norm": 1.77285979603319, "learning_rate": 4.847450394708769e-05, "loss": 0.7392, "num_tokens": 27005368.0, "step": 4545 }, { "epoch": 0.04854213564059616, "grad_norm": 1.9643958686471314, "learning_rate": 4.8527842969916796e-05, "loss": 0.6581, "num_tokens": 27026145.0, "step": 4550 }, { "epoch": 0.048595478646794615, "grad_norm": 2.296851515062863, "learning_rate": 4.8581181992745894e-05, "loss": 0.6518, "num_tokens": 27061206.0, "step": 4555 }, { "epoch": 0.04864882165299308, "grad_norm": 1.8587226172037787, "learning_rate": 4.8634521015575e-05, "loss": 0.6469, "num_tokens": 27092899.0, "step": 4560 }, { "epoch": 0.048702164659191534, "grad_norm": 1.5524777174231192, "learning_rate": 4.86878600384041e-05, "loss": 0.6362, "num_tokens": 27116618.0, "step": 4565 }, { "epoch": 0.04875550766538999, "grad_norm": 1.3422619966865166, "learning_rate": 4.87411990612332e-05, "loss": 0.6793, "num_tokens": 27144372.0, "step": 4570 }, { "epoch": 0.048808850671588445, "grad_norm": 1.7475031557417167, "learning_rate": 4.87945380840623e-05, "loss": 0.6274, "num_tokens": 27165460.0, "step": 4575 }, { "epoch": 0.04886219367778691, "grad_norm": 1.975956033230773, "learning_rate": 4.8847877106891405e-05, "loss": 0.6874, "num_tokens": 27188284.0, "step": 4580 }, { "epoch": 0.048915536683985364, "grad_norm": 2.38192509530893, "learning_rate": 4.89012161297205e-05, "loss": 0.7191, "num_tokens": 27208180.0, "step": 4585 }, { "epoch": 0.04896887969018382, "grad_norm": 1.6675520163186064, "learning_rate": 4.895455515254961e-05, "loss": 0.6713, "num_tokens": 27254347.0, "step": 4590 }, { "epoch": 0.049022222696382275, "grad_norm": 2.301510842760849, "learning_rate": 4.900789417537871e-05, "loss": 0.7159, "num_tokens": 27276328.0, "step": 4595 }, { "epoch": 0.04907556570258073, "grad_norm": 1.766236510707616, "learning_rate": 4.906123319820781e-05, "loss": 0.6386, "num_tokens": 27302596.0, "step": 4600 }, { "epoch": 0.049128908708779194, "grad_norm": 1.6269911948865612, "learning_rate": 4.9114572221036916e-05, "loss": 0.6297, "num_tokens": 27324137.0, "step": 4605 }, { "epoch": 0.04918225171497765, "grad_norm": 1.945373433740721, "learning_rate": 4.9167911243866014e-05, "loss": 0.7339, "num_tokens": 27356793.0, "step": 4610 }, { "epoch": 0.049235594721176106, "grad_norm": 1.9858075827396289, "learning_rate": 4.922125026669512e-05, "loss": 0.8789, "num_tokens": 27381439.0, "step": 4615 }, { "epoch": 0.04928893772737456, "grad_norm": 1.6822773361383114, "learning_rate": 4.927458928952422e-05, "loss": 0.7107, "num_tokens": 27423834.0, "step": 4620 }, { "epoch": 0.049342280733573024, "grad_norm": 2.757117980817788, "learning_rate": 4.932792831235332e-05, "loss": 0.7869, "num_tokens": 27434508.0, "step": 4625 }, { "epoch": 0.04939562373977148, "grad_norm": 1.762877805948677, "learning_rate": 4.938126733518243e-05, "loss": 0.8533, "num_tokens": 27476756.0, "step": 4630 }, { "epoch": 0.049448966745969936, "grad_norm": 2.193071275781341, "learning_rate": 4.9434606358011525e-05, "loss": 0.6875, "num_tokens": 27497823.0, "step": 4635 }, { "epoch": 0.04950230975216839, "grad_norm": 1.6186759611476347, "learning_rate": 4.948794538084063e-05, "loss": 0.7503, "num_tokens": 27513214.0, "step": 4640 }, { "epoch": 0.04955565275836685, "grad_norm": 1.7265150109475647, "learning_rate": 4.954128440366973e-05, "loss": 0.7634, "num_tokens": 27560749.0, "step": 4645 }, { "epoch": 0.04960899576456531, "grad_norm": 1.463348978271057, "learning_rate": 4.9594623426498827e-05, "loss": 0.6948, "num_tokens": 27587318.0, "step": 4650 }, { "epoch": 0.049662338770763766, "grad_norm": 2.030462587926211, "learning_rate": 4.964796244932793e-05, "loss": 0.7261, "num_tokens": 27618132.0, "step": 4655 }, { "epoch": 0.04971568177696222, "grad_norm": 2.3645834396308483, "learning_rate": 4.970130147215703e-05, "loss": 0.6445, "num_tokens": 27634238.0, "step": 4660 }, { "epoch": 0.04976902478316068, "grad_norm": 1.3836023808503948, "learning_rate": 4.9754640494986135e-05, "loss": 0.6411, "num_tokens": 27655461.0, "step": 4665 }, { "epoch": 0.04982236778935914, "grad_norm": 1.2425888874702051, "learning_rate": 4.980797951781523e-05, "loss": 0.6682, "num_tokens": 27688018.0, "step": 4670 }, { "epoch": 0.049875710795557596, "grad_norm": 2.1170183308006325, "learning_rate": 4.986131854064434e-05, "loss": 0.799, "num_tokens": 27711231.0, "step": 4675 }, { "epoch": 0.04992905380175605, "grad_norm": 2.770964244983845, "learning_rate": 4.9914657563473436e-05, "loss": 0.6843, "num_tokens": 27741368.0, "step": 4680 }, { "epoch": 0.04998239680795451, "grad_norm": 1.5192706560466058, "learning_rate": 4.996799658630254e-05, "loss": 0.6638, "num_tokens": 27774417.0, "step": 4685 }, { "epoch": 0.05003573981415296, "grad_norm": 1.6579382760176644, "learning_rate": 4.99999999439877e-05, "loss": 0.6907, "num_tokens": 27804644.0, "step": 4690 }, { "epoch": 0.050089082820351426, "grad_norm": 1.3895242741122709, "learning_rate": 4.9999999313849295e-05, "loss": 0.6728, "num_tokens": 27825203.0, "step": 4695 }, { "epoch": 0.05014242582654988, "grad_norm": 1.3490714876577492, "learning_rate": 4.999999798355713e-05, "loss": 0.5364, "num_tokens": 27865598.0, "step": 4700 }, { "epoch": 0.05019576883274834, "grad_norm": 1.7183199024299354, "learning_rate": 4.999999595311124e-05, "loss": 0.7619, "num_tokens": 27887816.0, "step": 4705 }, { "epoch": 0.05024911183894679, "grad_norm": 2.271464990879541, "learning_rate": 4.99999932225117e-05, "loss": 0.7553, "num_tokens": 27913809.0, "step": 4710 }, { "epoch": 0.050302454845145256, "grad_norm": 1.4039201165334578, "learning_rate": 4.999998979175858e-05, "loss": 0.7192, "num_tokens": 27959063.0, "step": 4715 }, { "epoch": 0.05035579785134371, "grad_norm": 1.7288606380873337, "learning_rate": 4.9999985660852e-05, "loss": 0.6961, "num_tokens": 27982873.0, "step": 4720 }, { "epoch": 0.05040914085754217, "grad_norm": 3.7501115381943966, "learning_rate": 4.999998082979208e-05, "loss": 0.754, "num_tokens": 27996530.0, "step": 4725 }, { "epoch": 0.05046248386374062, "grad_norm": 2.0164313869143196, "learning_rate": 4.9999975298578965e-05, "loss": 0.7165, "num_tokens": 28028777.0, "step": 4730 }, { "epoch": 0.05051582686993908, "grad_norm": 2.018124491619553, "learning_rate": 4.999996906721285e-05, "loss": 0.6189, "num_tokens": 28057974.0, "step": 4735 }, { "epoch": 0.05056916987613754, "grad_norm": 1.3844534380805145, "learning_rate": 4.9999962135693904e-05, "loss": 0.7057, "num_tokens": 28082609.0, "step": 4740 }, { "epoch": 0.050622512882336, "grad_norm": 1.4447106226552413, "learning_rate": 4.999995450402236e-05, "loss": 0.7728, "num_tokens": 28125926.0, "step": 4745 }, { "epoch": 0.05067585588853445, "grad_norm": 1.6603064670732341, "learning_rate": 4.999994617219844e-05, "loss": 0.6456, "num_tokens": 28158802.0, "step": 4750 }, { "epoch": 0.05072919889473291, "grad_norm": 2.362689211419395, "learning_rate": 4.999993714022241e-05, "loss": 0.7507, "num_tokens": 28203061.0, "step": 4755 }, { "epoch": 0.05078254190093137, "grad_norm": 2.933597242509425, "learning_rate": 4.9999927408094554e-05, "loss": 0.6046, "num_tokens": 28231880.0, "step": 4760 }, { "epoch": 0.05083588490712983, "grad_norm": 1.6269791617203526, "learning_rate": 4.999991697581518e-05, "loss": 0.6, "num_tokens": 28251126.0, "step": 4765 }, { "epoch": 0.05088922791332828, "grad_norm": 1.401454113344528, "learning_rate": 4.9999905843384596e-05, "loss": 0.7187, "num_tokens": 28284878.0, "step": 4770 }, { "epoch": 0.05094257091952674, "grad_norm": 1.6344944328053586, "learning_rate": 4.9999894010803166e-05, "loss": 0.7105, "num_tokens": 28312117.0, "step": 4775 }, { "epoch": 0.050995913925725195, "grad_norm": 2.2781098945703815, "learning_rate": 4.9999881478071254e-05, "loss": 0.6855, "num_tokens": 28336180.0, "step": 4780 }, { "epoch": 0.05104925693192366, "grad_norm": 3.199608409293231, "learning_rate": 4.999986824518923e-05, "loss": 0.6805, "num_tokens": 28365014.0, "step": 4785 }, { "epoch": 0.05110259993812211, "grad_norm": 1.348627249847933, "learning_rate": 4.999985431215754e-05, "loss": 0.6906, "num_tokens": 28389362.0, "step": 4790 }, { "epoch": 0.05115594294432057, "grad_norm": 1.2433832650355816, "learning_rate": 4.99998396789766e-05, "loss": 0.6427, "num_tokens": 28415397.0, "step": 4795 }, { "epoch": 0.051209285950519025, "grad_norm": 2.0859126968758797, "learning_rate": 4.999982434564685e-05, "loss": 0.6762, "num_tokens": 28441260.0, "step": 4800 }, { "epoch": 0.05126262895671749, "grad_norm": 1.7377432690685994, "learning_rate": 4.9999808312168786e-05, "loss": 0.7882, "num_tokens": 28470039.0, "step": 4805 }, { "epoch": 0.05131597196291594, "grad_norm": 2.3373837074588546, "learning_rate": 4.999979157854291e-05, "loss": 0.6776, "num_tokens": 28487586.0, "step": 4810 }, { "epoch": 0.0513693149691144, "grad_norm": 4.748348600885524, "learning_rate": 4.999977414476973e-05, "loss": 0.8193, "num_tokens": 28523219.0, "step": 4815 }, { "epoch": 0.051422657975312855, "grad_norm": 1.3624092556022795, "learning_rate": 4.99997560108498e-05, "loss": 0.7045, "num_tokens": 28561949.0, "step": 4820 }, { "epoch": 0.05147600098151131, "grad_norm": 1.6957628054103937, "learning_rate": 4.999973717678369e-05, "loss": 0.7575, "num_tokens": 28609582.0, "step": 4825 }, { "epoch": 0.05152934398770977, "grad_norm": 1.6836503392067017, "learning_rate": 4.9999717642571955e-05, "loss": 0.6608, "num_tokens": 28643556.0, "step": 4830 }, { "epoch": 0.05158268699390823, "grad_norm": 1.4566024133891633, "learning_rate": 4.9999697408215223e-05, "loss": 0.6803, "num_tokens": 28680906.0, "step": 4835 }, { "epoch": 0.051636030000106685, "grad_norm": 1.5678160956368847, "learning_rate": 4.999967647371413e-05, "loss": 0.7257, "num_tokens": 28713123.0, "step": 4840 }, { "epoch": 0.05168937300630514, "grad_norm": 1.8396481310300654, "learning_rate": 4.999965483906933e-05, "loss": 0.6544, "num_tokens": 28743263.0, "step": 4845 }, { "epoch": 0.0517427160125036, "grad_norm": 2.002714132760615, "learning_rate": 4.999963250428147e-05, "loss": 0.7506, "num_tokens": 28775749.0, "step": 4850 }, { "epoch": 0.05179605901870206, "grad_norm": 2.489994024140306, "learning_rate": 4.999960946935127e-05, "loss": 0.6021, "num_tokens": 28793960.0, "step": 4855 }, { "epoch": 0.051849402024900515, "grad_norm": 1.6633925647172367, "learning_rate": 4.999958573427944e-05, "loss": 0.7328, "num_tokens": 28826063.0, "step": 4860 }, { "epoch": 0.05190274503109897, "grad_norm": 1.2782590177845328, "learning_rate": 4.999956129906671e-05, "loss": 0.742, "num_tokens": 28866662.0, "step": 4865 }, { "epoch": 0.051956088037297427, "grad_norm": 4.9745088451856265, "learning_rate": 4.999953616371386e-05, "loss": 0.8483, "num_tokens": 28904258.0, "step": 4870 }, { "epoch": 0.05200943104349589, "grad_norm": 1.9005635315625407, "learning_rate": 4.999951032822165e-05, "loss": 0.6853, "num_tokens": 28931424.0, "step": 4875 }, { "epoch": 0.052062774049694345, "grad_norm": 2.154189893608311, "learning_rate": 4.99994837925909e-05, "loss": 0.566, "num_tokens": 28958598.0, "step": 4880 }, { "epoch": 0.0521161170558928, "grad_norm": 2.247657092899862, "learning_rate": 4.9999456556822425e-05, "loss": 0.6855, "num_tokens": 28994249.0, "step": 4885 }, { "epoch": 0.05216946006209126, "grad_norm": 1.4388213374838217, "learning_rate": 4.999942862091708e-05, "loss": 0.5634, "num_tokens": 29017627.0, "step": 4890 }, { "epoch": 0.05222280306828972, "grad_norm": 1.4807762608491408, "learning_rate": 4.999939998487573e-05, "loss": 0.686, "num_tokens": 29056823.0, "step": 4895 }, { "epoch": 0.052276146074488175, "grad_norm": 1.898249372835235, "learning_rate": 4.999937064869927e-05, "loss": 0.6651, "num_tokens": 29089325.0, "step": 4900 }, { "epoch": 0.05232948908068663, "grad_norm": 2.2949863808207502, "learning_rate": 4.999934061238861e-05, "loss": 0.7156, "num_tokens": 29123989.0, "step": 4905 }, { "epoch": 0.05238283208688509, "grad_norm": 2.288814838471049, "learning_rate": 4.999930987594468e-05, "loss": 0.6389, "num_tokens": 29151742.0, "step": 4910 }, { "epoch": 0.05243617509308354, "grad_norm": 2.0736925321071022, "learning_rate": 4.9999278439368445e-05, "loss": 0.7561, "num_tokens": 29177493.0, "step": 4915 }, { "epoch": 0.052489518099282005, "grad_norm": 1.675742539848703, "learning_rate": 4.9999246302660884e-05, "loss": 0.621, "num_tokens": 29212155.0, "step": 4920 }, { "epoch": 0.05254286110548046, "grad_norm": 1.8362528717620934, "learning_rate": 4.999921346582299e-05, "loss": 0.6712, "num_tokens": 29244500.0, "step": 4925 }, { "epoch": 0.05259620411167892, "grad_norm": 2.3521171394458764, "learning_rate": 4.9999179928855784e-05, "loss": 0.7324, "num_tokens": 29270362.0, "step": 4930 }, { "epoch": 0.05264954711787737, "grad_norm": 1.5836768216406378, "learning_rate": 4.999914569176031e-05, "loss": 0.6543, "num_tokens": 29305729.0, "step": 4935 }, { "epoch": 0.052702890124075835, "grad_norm": 1.6646150077873632, "learning_rate": 4.999911075453765e-05, "loss": 0.7059, "num_tokens": 29347301.0, "step": 4940 }, { "epoch": 0.05275623313027429, "grad_norm": 1.3998711275852715, "learning_rate": 4.9999075117188864e-05, "loss": 0.6772, "num_tokens": 29387942.0, "step": 4945 }, { "epoch": 0.05280957613647275, "grad_norm": 4.390965366350196, "learning_rate": 4.999903877971508e-05, "loss": 0.6957, "num_tokens": 29405063.0, "step": 4950 }, { "epoch": 0.0528629191426712, "grad_norm": 2.0247318183056677, "learning_rate": 4.999900174211743e-05, "loss": 0.7507, "num_tokens": 29438566.0, "step": 4955 }, { "epoch": 0.05291626214886966, "grad_norm": 2.1089181607345067, "learning_rate": 4.999896400439706e-05, "loss": 0.8805, "num_tokens": 29484984.0, "step": 4960 }, { "epoch": 0.05296960515506812, "grad_norm": 1.5787410609397101, "learning_rate": 4.999892556655513e-05, "loss": 0.6582, "num_tokens": 29511103.0, "step": 4965 }, { "epoch": 0.05302294816126658, "grad_norm": 2.441789550969793, "learning_rate": 4.999888642859286e-05, "loss": 0.7, "num_tokens": 29544954.0, "step": 4970 }, { "epoch": 0.05307629116746503, "grad_norm": 1.567999516223538, "learning_rate": 4.9998846590511464e-05, "loss": 0.6736, "num_tokens": 29572762.0, "step": 4975 }, { "epoch": 0.05312963417366349, "grad_norm": 1.2073234971712687, "learning_rate": 4.999880605231216e-05, "loss": 0.6643, "num_tokens": 29603241.0, "step": 4980 }, { "epoch": 0.05318297717986195, "grad_norm": 1.9842096753600516, "learning_rate": 4.9998764813996244e-05, "loss": 0.7937, "num_tokens": 29628275.0, "step": 4985 }, { "epoch": 0.05323632018606041, "grad_norm": 1.1419166316183345, "learning_rate": 4.999872287556497e-05, "loss": 0.6338, "num_tokens": 29668710.0, "step": 4990 }, { "epoch": 0.05328966319225886, "grad_norm": 2.2846612059504707, "learning_rate": 4.999868023701966e-05, "loss": 0.7454, "num_tokens": 29692078.0, "step": 4995 }, { "epoch": 0.05334300619845732, "grad_norm": 2.212438978690335, "learning_rate": 4.999863689836163e-05, "loss": 0.7018, "num_tokens": 29719512.0, "step": 5000 }, { "epoch": 0.053396349204655774, "grad_norm": 2.095724231575548, "learning_rate": 4.999859285959223e-05, "loss": 0.6324, "num_tokens": 29744872.0, "step": 5005 }, { "epoch": 0.05344969221085424, "grad_norm": 4.265741751613015, "learning_rate": 4.999854812071284e-05, "loss": 0.801, "num_tokens": 29770173.0, "step": 5010 }, { "epoch": 0.05350303521705269, "grad_norm": 3.8001598652630744, "learning_rate": 4.999850268172484e-05, "loss": 0.8538, "num_tokens": 29807393.0, "step": 5015 }, { "epoch": 0.05355637822325115, "grad_norm": 1.500269749858105, "learning_rate": 4.9998456542629654e-05, "loss": 0.7983, "num_tokens": 29850894.0, "step": 5020 }, { "epoch": 0.053609721229449604, "grad_norm": 1.357697124682007, "learning_rate": 4.999840970342871e-05, "loss": 0.7841, "num_tokens": 29894589.0, "step": 5025 }, { "epoch": 0.05366306423564807, "grad_norm": 1.8337480000997197, "learning_rate": 4.999836216412348e-05, "loss": 0.6357, "num_tokens": 29919768.0, "step": 5030 }, { "epoch": 0.05371640724184652, "grad_norm": 1.5676691597950136, "learning_rate": 4.9998313924715424e-05, "loss": 0.5786, "num_tokens": 29940323.0, "step": 5035 }, { "epoch": 0.05376975024804498, "grad_norm": 2.7712231379650496, "learning_rate": 4.9998264985206044e-05, "loss": 0.6776, "num_tokens": 29961915.0, "step": 5040 }, { "epoch": 0.053823093254243434, "grad_norm": 2.2447339766675625, "learning_rate": 4.999821534559688e-05, "loss": 0.6894, "num_tokens": 29981920.0, "step": 5045 }, { "epoch": 0.05387643626044189, "grad_norm": 1.4865620469040155, "learning_rate": 4.999816500588947e-05, "loss": 0.7941, "num_tokens": 30014169.0, "step": 5050 }, { "epoch": 0.05392977926664035, "grad_norm": 1.5828331393468325, "learning_rate": 4.9998113966085366e-05, "loss": 0.7009, "num_tokens": 30033310.0, "step": 5055 }, { "epoch": 0.05398312227283881, "grad_norm": 1.6604139254846664, "learning_rate": 4.9998062226186184e-05, "loss": 0.7267, "num_tokens": 30071990.0, "step": 5060 }, { "epoch": 0.054036465279037264, "grad_norm": 1.522034484463031, "learning_rate": 4.999800978619351e-05, "loss": 0.6744, "num_tokens": 30104156.0, "step": 5065 }, { "epoch": 0.05408980828523572, "grad_norm": 1.9680362737370598, "learning_rate": 4.999795664610898e-05, "loss": 0.6741, "num_tokens": 30129916.0, "step": 5070 }, { "epoch": 0.05414315129143418, "grad_norm": 1.7597521659172846, "learning_rate": 4.9997902805934255e-05, "loss": 0.7078, "num_tokens": 30171694.0, "step": 5075 }, { "epoch": 0.05419649429763264, "grad_norm": 1.2948851112244355, "learning_rate": 4.9997848265671e-05, "loss": 0.6375, "num_tokens": 30202116.0, "step": 5080 }, { "epoch": 0.054249837303831094, "grad_norm": 4.499926861143924, "learning_rate": 4.9997793025320924e-05, "loss": 0.7896, "num_tokens": 30231630.0, "step": 5085 }, { "epoch": 0.05430318031002955, "grad_norm": 1.4998811888035903, "learning_rate": 4.999773708488574e-05, "loss": 0.8372, "num_tokens": 30267475.0, "step": 5090 }, { "epoch": 0.054356523316228006, "grad_norm": 2.7733601957547003, "learning_rate": 4.9997680444367195e-05, "loss": 0.7922, "num_tokens": 30285707.0, "step": 5095 }, { "epoch": 0.05440986632242647, "grad_norm": 1.2506186641385653, "learning_rate": 4.999762310376704e-05, "loss": 0.6083, "num_tokens": 30316286.0, "step": 5100 }, { "epoch": 0.054463209328624924, "grad_norm": 0.9534027791763476, "learning_rate": 4.999756506308706e-05, "loss": 0.5155, "num_tokens": 30340640.0, "step": 5105 }, { "epoch": 0.05451655233482338, "grad_norm": 2.124934039459049, "learning_rate": 4.999750632232908e-05, "loss": 0.6754, "num_tokens": 30365046.0, "step": 5110 }, { "epoch": 0.054569895341021836, "grad_norm": 1.810277653748187, "learning_rate": 4.999744688149491e-05, "loss": 0.7686, "num_tokens": 30397054.0, "step": 5115 }, { "epoch": 0.0546232383472203, "grad_norm": 1.3065822177186772, "learning_rate": 4.9997386740586397e-05, "loss": 0.6765, "num_tokens": 30417967.0, "step": 5120 }, { "epoch": 0.054676581353418754, "grad_norm": 1.7313160696355405, "learning_rate": 4.999732589960542e-05, "loss": 0.6327, "num_tokens": 30434467.0, "step": 5125 }, { "epoch": 0.05472992435961721, "grad_norm": 1.673805059420692, "learning_rate": 4.999726435855388e-05, "loss": 0.8089, "num_tokens": 30464193.0, "step": 5130 }, { "epoch": 0.054783267365815666, "grad_norm": 1.58845529040096, "learning_rate": 4.9997202117433686e-05, "loss": 0.6916, "num_tokens": 30481335.0, "step": 5135 }, { "epoch": 0.05483661037201412, "grad_norm": 1.4964271394806834, "learning_rate": 4.999713917624677e-05, "loss": 0.6663, "num_tokens": 30515867.0, "step": 5140 }, { "epoch": 0.054889953378212585, "grad_norm": 1.4862686102078773, "learning_rate": 4.999707553499509e-05, "loss": 0.6877, "num_tokens": 30539047.0, "step": 5145 }, { "epoch": 0.05494329638441104, "grad_norm": 1.226750147426599, "learning_rate": 4.999701119368063e-05, "loss": 0.7751, "num_tokens": 30593350.0, "step": 5150 }, { "epoch": 0.054996639390609496, "grad_norm": 2.2137294375561702, "learning_rate": 4.999694615230539e-05, "loss": 0.7659, "num_tokens": 30632977.0, "step": 5155 }, { "epoch": 0.05504998239680795, "grad_norm": 1.4477044758490334, "learning_rate": 4.99968804108714e-05, "loss": 0.783, "num_tokens": 30673742.0, "step": 5160 }, { "epoch": 0.055103325403006415, "grad_norm": 1.2304539718671679, "learning_rate": 4.9996813969380695e-05, "loss": 0.7367, "num_tokens": 30700222.0, "step": 5165 }, { "epoch": 0.05515666840920487, "grad_norm": 1.7561332624903083, "learning_rate": 4.999674682783535e-05, "loss": 0.6484, "num_tokens": 30727130.0, "step": 5170 }, { "epoch": 0.055210011415403326, "grad_norm": 2.080930836156777, "learning_rate": 4.999667898623746e-05, "loss": 0.6286, "num_tokens": 30761714.0, "step": 5175 }, { "epoch": 0.05526335442160178, "grad_norm": 1.345967304019169, "learning_rate": 4.9996610444589124e-05, "loss": 0.7276, "num_tokens": 30793739.0, "step": 5180 }, { "epoch": 0.05531669742780024, "grad_norm": 1.4564276418576363, "learning_rate": 4.9996541202892486e-05, "loss": 0.6688, "num_tokens": 30816599.0, "step": 5185 }, { "epoch": 0.0553700404339987, "grad_norm": 1.8448921817007073, "learning_rate": 4.999647126114969e-05, "loss": 0.5929, "num_tokens": 30853562.0, "step": 5190 }, { "epoch": 0.055423383440197156, "grad_norm": 1.8493172093099135, "learning_rate": 4.999640061936292e-05, "loss": 0.757, "num_tokens": 30881033.0, "step": 5195 }, { "epoch": 0.05547672644639561, "grad_norm": 1.8868821297630538, "learning_rate": 4.999632927753438e-05, "loss": 0.7799, "num_tokens": 30905676.0, "step": 5200 }, { "epoch": 0.05553006945259407, "grad_norm": 1.6320794419610363, "learning_rate": 4.999625723566627e-05, "loss": 0.7249, "num_tokens": 30923585.0, "step": 5205 }, { "epoch": 0.05558341245879253, "grad_norm": 1.6141763526569155, "learning_rate": 4.999618449376084e-05, "loss": 0.6385, "num_tokens": 30950672.0, "step": 5210 }, { "epoch": 0.055636755464990986, "grad_norm": 2.0432431472004926, "learning_rate": 4.999611105182037e-05, "loss": 0.7144, "num_tokens": 30983677.0, "step": 5215 }, { "epoch": 0.05569009847118944, "grad_norm": 2.0644327721337103, "learning_rate": 4.9996036909847114e-05, "loss": 0.6833, "num_tokens": 31008739.0, "step": 5220 }, { "epoch": 0.0557434414773879, "grad_norm": 2.263036024039836, "learning_rate": 4.999596206784341e-05, "loss": 0.6025, "num_tokens": 31031638.0, "step": 5225 }, { "epoch": 0.055796784483586354, "grad_norm": 2.2123480004857967, "learning_rate": 4.9995886525811574e-05, "loss": 0.7088, "num_tokens": 31064237.0, "step": 5230 }, { "epoch": 0.055850127489784816, "grad_norm": 1.8442094833988667, "learning_rate": 4.999581028375396e-05, "loss": 0.6439, "num_tokens": 31104637.0, "step": 5235 }, { "epoch": 0.05590347049598327, "grad_norm": 3.2851163588832004, "learning_rate": 4.999573334167293e-05, "loss": 0.6698, "num_tokens": 31124693.0, "step": 5240 }, { "epoch": 0.05595681350218173, "grad_norm": 2.4199005405975553, "learning_rate": 4.9995655699570884e-05, "loss": 0.7628, "num_tokens": 31146498.0, "step": 5245 }, { "epoch": 0.056010156508380184, "grad_norm": 1.41059575982015, "learning_rate": 4.999557735745026e-05, "loss": 0.8334, "num_tokens": 31194047.0, "step": 5250 }, { "epoch": 0.056063499514578646, "grad_norm": 1.3576824309453823, "learning_rate": 4.9995498315313456e-05, "loss": 0.6094, "num_tokens": 31221247.0, "step": 5255 }, { "epoch": 0.0561168425207771, "grad_norm": 1.1424476971942, "learning_rate": 4.999541857316296e-05, "loss": 0.6209, "num_tokens": 31253343.0, "step": 5260 }, { "epoch": 0.05617018552697556, "grad_norm": 1.46412511768201, "learning_rate": 4.999533813100124e-05, "loss": 0.7262, "num_tokens": 31288326.0, "step": 5265 }, { "epoch": 0.056223528533174014, "grad_norm": 4.978913360658231, "learning_rate": 4.999525698883081e-05, "loss": 0.6887, "num_tokens": 31312726.0, "step": 5270 }, { "epoch": 0.05627687153937247, "grad_norm": 1.457291232455207, "learning_rate": 4.999517514665418e-05, "loss": 0.6436, "num_tokens": 31347163.0, "step": 5275 }, { "epoch": 0.05633021454557093, "grad_norm": 1.580180273662309, "learning_rate": 4.999509260447391e-05, "loss": 0.5986, "num_tokens": 31367061.0, "step": 5280 }, { "epoch": 0.05638355755176939, "grad_norm": 1.84619252325897, "learning_rate": 4.999500936229257e-05, "loss": 0.7039, "num_tokens": 31409817.0, "step": 5285 }, { "epoch": 0.056436900557967844, "grad_norm": 2.853128113534099, "learning_rate": 4.999492542011274e-05, "loss": 0.6829, "num_tokens": 31440363.0, "step": 5290 }, { "epoch": 0.0564902435641663, "grad_norm": 1.717137171585639, "learning_rate": 4.9994840777937035e-05, "loss": 0.6306, "num_tokens": 31469115.0, "step": 5295 }, { "epoch": 0.05654358657036476, "grad_norm": 1.4697269617101685, "learning_rate": 4.9994755435768095e-05, "loss": 0.622, "num_tokens": 31495120.0, "step": 5300 }, { "epoch": 0.05659692957656322, "grad_norm": 1.9836395590859495, "learning_rate": 4.999466939360857e-05, "loss": 0.6502, "num_tokens": 31511914.0, "step": 5305 }, { "epoch": 0.056650272582761674, "grad_norm": 2.0430930505794, "learning_rate": 4.999458265146114e-05, "loss": 0.6665, "num_tokens": 31526631.0, "step": 5310 }, { "epoch": 0.05670361558896013, "grad_norm": 1.622197777113387, "learning_rate": 4.9994495209328496e-05, "loss": 0.668, "num_tokens": 31573935.0, "step": 5315 }, { "epoch": 0.056756958595158585, "grad_norm": 1.4601804076129081, "learning_rate": 4.9994407067213375e-05, "loss": 0.6133, "num_tokens": 31597579.0, "step": 5320 }, { "epoch": 0.05681030160135705, "grad_norm": 1.875078147625055, "learning_rate": 4.999431822511851e-05, "loss": 0.7839, "num_tokens": 31643882.0, "step": 5325 }, { "epoch": 0.056863644607555504, "grad_norm": 2.441237655880425, "learning_rate": 4.9994228683046664e-05, "loss": 0.6629, "num_tokens": 31662222.0, "step": 5330 }, { "epoch": 0.05691698761375396, "grad_norm": 1.5233334239653302, "learning_rate": 4.999413844100062e-05, "loss": 0.7183, "num_tokens": 31695247.0, "step": 5335 }, { "epoch": 0.056970330619952415, "grad_norm": 1.8283943464267538, "learning_rate": 4.99940474989832e-05, "loss": 0.8391, "num_tokens": 31728595.0, "step": 5340 }, { "epoch": 0.05702367362615088, "grad_norm": 1.2223988757371729, "learning_rate": 4.9993955856997226e-05, "loss": 0.6561, "num_tokens": 31753416.0, "step": 5345 }, { "epoch": 0.057077016632349334, "grad_norm": 1.1781474900510505, "learning_rate": 4.999386351504555e-05, "loss": 0.6869, "num_tokens": 31801928.0, "step": 5350 }, { "epoch": 0.05713035963854779, "grad_norm": 1.4858755846716993, "learning_rate": 4.999377047313104e-05, "loss": 0.6539, "num_tokens": 31832733.0, "step": 5355 }, { "epoch": 0.057183702644746245, "grad_norm": 2.185437449288207, "learning_rate": 4.99936767312566e-05, "loss": 0.8381, "num_tokens": 31862251.0, "step": 5360 }, { "epoch": 0.0572370456509447, "grad_norm": 1.6768385368987366, "learning_rate": 4.999358228942514e-05, "loss": 0.6582, "num_tokens": 31884442.0, "step": 5365 }, { "epoch": 0.057290388657143164, "grad_norm": 2.198894569894685, "learning_rate": 4.9993487147639604e-05, "loss": 0.732, "num_tokens": 31904185.0, "step": 5370 }, { "epoch": 0.05734373166334162, "grad_norm": 1.3538311319407523, "learning_rate": 4.999339130590295e-05, "loss": 0.6685, "num_tokens": 31932926.0, "step": 5375 }, { "epoch": 0.057397074669540075, "grad_norm": 2.2037539256368253, "learning_rate": 4.999329476421816e-05, "loss": 0.7899, "num_tokens": 31962890.0, "step": 5380 }, { "epoch": 0.05745041767573853, "grad_norm": 1.0556262351997332, "learning_rate": 4.9993197522588245e-05, "loss": 0.7007, "num_tokens": 32000664.0, "step": 5385 }, { "epoch": 0.057503760681936994, "grad_norm": 2.6208450450492045, "learning_rate": 4.9993099581016224e-05, "loss": 0.7302, "num_tokens": 32033197.0, "step": 5390 }, { "epoch": 0.05755710368813545, "grad_norm": 1.9903173317435223, "learning_rate": 4.999300093950515e-05, "loss": 0.8039, "num_tokens": 32063923.0, "step": 5395 }, { "epoch": 0.057610446694333906, "grad_norm": 1.8494038871216065, "learning_rate": 4.9992901598058085e-05, "loss": 0.6644, "num_tokens": 32099376.0, "step": 5400 }, { "epoch": 0.05766378970053236, "grad_norm": 1.3718938092086808, "learning_rate": 4.999280155667811e-05, "loss": 0.7209, "num_tokens": 32122088.0, "step": 5405 }, { "epoch": 0.05771713270673082, "grad_norm": 1.3301373958110252, "learning_rate": 4.999270081536837e-05, "loss": 0.7602, "num_tokens": 32148540.0, "step": 5410 }, { "epoch": 0.05777047571292928, "grad_norm": 1.838718927589464, "learning_rate": 4.9992599374131976e-05, "loss": 0.7133, "num_tokens": 32175826.0, "step": 5415 }, { "epoch": 0.057823818719127736, "grad_norm": 1.2648105976590256, "learning_rate": 4.9992497232972094e-05, "loss": 0.6994, "num_tokens": 32208478.0, "step": 5420 }, { "epoch": 0.05787716172532619, "grad_norm": 1.4232476870459558, "learning_rate": 4.999239439189189e-05, "loss": 0.5612, "num_tokens": 32233957.0, "step": 5425 }, { "epoch": 0.05793050473152465, "grad_norm": 1.332568374980583, "learning_rate": 4.999229085089458e-05, "loss": 0.6832, "num_tokens": 32264977.0, "step": 5430 }, { "epoch": 0.05798384773772311, "grad_norm": 1.3311043493961023, "learning_rate": 4.9992186609983385e-05, "loss": 0.6285, "num_tokens": 32297919.0, "step": 5435 }, { "epoch": 0.058037190743921566, "grad_norm": 1.3404154992435724, "learning_rate": 4.999208166916153e-05, "loss": 0.8793, "num_tokens": 32351323.0, "step": 5440 }, { "epoch": 0.05809053375012002, "grad_norm": 1.7284032344532527, "learning_rate": 4.999197602843231e-05, "loss": 0.6483, "num_tokens": 32375773.0, "step": 5445 }, { "epoch": 0.05814387675631848, "grad_norm": 1.3044475639521635, "learning_rate": 4.999186968779898e-05, "loss": 0.593, "num_tokens": 32404176.0, "step": 5450 }, { "epoch": 0.05819721976251693, "grad_norm": 1.9642096279331467, "learning_rate": 4.9991762647264876e-05, "loss": 0.6235, "num_tokens": 32420230.0, "step": 5455 }, { "epoch": 0.058250562768715396, "grad_norm": 1.50420253262461, "learning_rate": 4.999165490683331e-05, "loss": 0.5908, "num_tokens": 32448883.0, "step": 5460 }, { "epoch": 0.05830390577491385, "grad_norm": 1.3504790861520477, "learning_rate": 4.999154646650764e-05, "loss": 0.5896, "num_tokens": 32466859.0, "step": 5465 }, { "epoch": 0.05835724878111231, "grad_norm": 1.6346290343553436, "learning_rate": 4.999143732629125e-05, "loss": 0.8132, "num_tokens": 32500826.0, "step": 5470 }, { "epoch": 0.05841059178731076, "grad_norm": 2.041220104034045, "learning_rate": 4.999132748618753e-05, "loss": 0.8962, "num_tokens": 32535711.0, "step": 5475 }, { "epoch": 0.058463934793509226, "grad_norm": 1.207859685684484, "learning_rate": 4.99912169461999e-05, "loss": 0.9278, "num_tokens": 32593742.0, "step": 5480 }, { "epoch": 0.05851727779970768, "grad_norm": 2.011354565101678, "learning_rate": 4.9991105706331786e-05, "loss": 0.6815, "num_tokens": 32621294.0, "step": 5485 }, { "epoch": 0.05857062080590614, "grad_norm": 1.7623724647995218, "learning_rate": 4.999099376658667e-05, "loss": 0.6616, "num_tokens": 32645312.0, "step": 5490 }, { "epoch": 0.05862396381210459, "grad_norm": 2.049217221809084, "learning_rate": 4.9990881126968014e-05, "loss": 0.6978, "num_tokens": 32679338.0, "step": 5495 }, { "epoch": 0.05867730681830305, "grad_norm": 1.0872384796979495, "learning_rate": 4.999076778747935e-05, "loss": 0.7026, "num_tokens": 32720413.0, "step": 5500 }, { "epoch": 0.05873064982450151, "grad_norm": 1.7108251544882274, "learning_rate": 4.9990653748124185e-05, "loss": 0.7718, "num_tokens": 32750602.0, "step": 5505 }, { "epoch": 0.05878399283069997, "grad_norm": 3.310665176944233, "learning_rate": 4.9990539008906065e-05, "loss": 0.7325, "num_tokens": 32783603.0, "step": 5510 }, { "epoch": 0.05883733583689842, "grad_norm": 1.845157823163537, "learning_rate": 4.999042356982857e-05, "loss": 0.6251, "num_tokens": 32814703.0, "step": 5515 }, { "epoch": 0.05889067884309688, "grad_norm": 1.3928144863007472, "learning_rate": 4.99903074308953e-05, "loss": 0.5886, "num_tokens": 32837613.0, "step": 5520 }, { "epoch": 0.05894402184929534, "grad_norm": 1.9490235865059418, "learning_rate": 4.999019059210985e-05, "loss": 0.6608, "num_tokens": 32855871.0, "step": 5525 }, { "epoch": 0.0589973648554938, "grad_norm": 1.546033176359639, "learning_rate": 4.999007305347587e-05, "loss": 0.652, "num_tokens": 32884133.0, "step": 5530 }, { "epoch": 0.05905070786169225, "grad_norm": 1.4110207028501676, "learning_rate": 4.9989954814997004e-05, "loss": 0.7466, "num_tokens": 32919160.0, "step": 5535 }, { "epoch": 0.05910405086789071, "grad_norm": 1.5280045534756197, "learning_rate": 4.998983587667694e-05, "loss": 0.6287, "num_tokens": 32939453.0, "step": 5540 }, { "epoch": 0.059157393874089165, "grad_norm": 1.48386129945415, "learning_rate": 4.998971623851939e-05, "loss": 0.7438, "num_tokens": 32966335.0, "step": 5545 }, { "epoch": 0.05921073688028763, "grad_norm": 1.9003685042069944, "learning_rate": 4.9989595900528065e-05, "loss": 0.8304, "num_tokens": 33003972.0, "step": 5550 }, { "epoch": 0.05926407988648608, "grad_norm": 1.947421861605184, "learning_rate": 4.99894748627067e-05, "loss": 0.617, "num_tokens": 33022348.0, "step": 5555 }, { "epoch": 0.05931742289268454, "grad_norm": 2.5476781106835573, "learning_rate": 4.998935312505907e-05, "loss": 0.8419, "num_tokens": 33050323.0, "step": 5560 }, { "epoch": 0.059370765898882995, "grad_norm": 1.3688854847117848, "learning_rate": 4.9989230687588984e-05, "loss": 0.6196, "num_tokens": 33074752.0, "step": 5565 }, { "epoch": 0.05942410890508146, "grad_norm": 2.0843574698542877, "learning_rate": 4.998910755030022e-05, "loss": 0.5837, "num_tokens": 33100113.0, "step": 5570 }, { "epoch": 0.05947745191127991, "grad_norm": 1.7301642012032956, "learning_rate": 4.9988983713196624e-05, "loss": 0.6604, "num_tokens": 33122878.0, "step": 5575 }, { "epoch": 0.05953079491747837, "grad_norm": 1.524424162706343, "learning_rate": 4.998885917628205e-05, "loss": 0.7964, "num_tokens": 33151820.0, "step": 5580 }, { "epoch": 0.059584137923676825, "grad_norm": 2.011643039623075, "learning_rate": 4.9988733939560375e-05, "loss": 0.7773, "num_tokens": 33174437.0, "step": 5585 }, { "epoch": 0.05963748092987528, "grad_norm": 1.767581859488782, "learning_rate": 4.998860800303548e-05, "loss": 0.7742, "num_tokens": 33195065.0, "step": 5590 }, { "epoch": 0.05969082393607374, "grad_norm": 1.3187432507853618, "learning_rate": 4.998848136671131e-05, "loss": 0.6535, "num_tokens": 33224793.0, "step": 5595 }, { "epoch": 0.0597441669422722, "grad_norm": 1.2607421577012354, "learning_rate": 4.9988354030591786e-05, "loss": 0.6412, "num_tokens": 33256284.0, "step": 5600 }, { "epoch": 0.059797509948470655, "grad_norm": 2.1397787395807715, "learning_rate": 4.998822599468088e-05, "loss": 0.9346, "num_tokens": 33282968.0, "step": 5605 }, { "epoch": 0.05985085295466911, "grad_norm": 1.49735621722213, "learning_rate": 4.998809725898258e-05, "loss": 0.768, "num_tokens": 33311227.0, "step": 5610 }, { "epoch": 0.05990419596086757, "grad_norm": 1.458392263828062, "learning_rate": 4.998796782350088e-05, "loss": 0.7747, "num_tokens": 33355571.0, "step": 5615 }, { "epoch": 0.05995753896706603, "grad_norm": 1.744935441707931, "learning_rate": 4.9987837688239807e-05, "loss": 0.7095, "num_tokens": 33386179.0, "step": 5620 }, { "epoch": 0.060010881973264485, "grad_norm": 1.8991763166647653, "learning_rate": 4.998770685320342e-05, "loss": 0.7987, "num_tokens": 33422001.0, "step": 5625 }, { "epoch": 0.06006422497946294, "grad_norm": 1.2757695916347125, "learning_rate": 4.998757531839579e-05, "loss": 0.7414, "num_tokens": 33479502.0, "step": 5630 }, { "epoch": 0.060117567985661396, "grad_norm": 2.129696970404362, "learning_rate": 4.9987443083821e-05, "loss": 0.6755, "num_tokens": 33504397.0, "step": 5635 }, { "epoch": 0.06017091099185986, "grad_norm": 1.153532704606043, "learning_rate": 4.998731014948318e-05, "loss": 0.789, "num_tokens": 33533619.0, "step": 5640 }, { "epoch": 0.060224253998058315, "grad_norm": 4.15532826504695, "learning_rate": 4.9987176515386456e-05, "loss": 0.7163, "num_tokens": 33553310.0, "step": 5645 }, { "epoch": 0.06027759700425677, "grad_norm": 1.794605550438959, "learning_rate": 4.998704218153498e-05, "loss": 0.7663, "num_tokens": 33577561.0, "step": 5650 }, { "epoch": 0.060330940010455227, "grad_norm": 1.441824478783946, "learning_rate": 4.9986907147932956e-05, "loss": 0.6342, "num_tokens": 33610993.0, "step": 5655 }, { "epoch": 0.06038428301665369, "grad_norm": 1.4607672788127322, "learning_rate": 4.998677141458456e-05, "loss": 0.5806, "num_tokens": 33638539.0, "step": 5660 }, { "epoch": 0.060437626022852145, "grad_norm": 2.5182136285312247, "learning_rate": 4.998663498149403e-05, "loss": 0.8419, "num_tokens": 33668393.0, "step": 5665 }, { "epoch": 0.0604909690290506, "grad_norm": 1.6700469068146093, "learning_rate": 4.998649784866561e-05, "loss": 0.648, "num_tokens": 33696074.0, "step": 5670 }, { "epoch": 0.06054431203524906, "grad_norm": 1.5473682290694324, "learning_rate": 4.9986360016103564e-05, "loss": 0.852, "num_tokens": 33740128.0, "step": 5675 }, { "epoch": 0.06059765504144751, "grad_norm": 2.2864227360835336, "learning_rate": 4.998622148381218e-05, "loss": 0.6342, "num_tokens": 33761379.0, "step": 5680 }, { "epoch": 0.060650998047645975, "grad_norm": 2.971234237718948, "learning_rate": 4.998608225179577e-05, "loss": 0.6567, "num_tokens": 33790308.0, "step": 5685 }, { "epoch": 0.06070434105384443, "grad_norm": 2.436076528247515, "learning_rate": 4.998594232005868e-05, "loss": 0.7622, "num_tokens": 33824906.0, "step": 5690 }, { "epoch": 0.06075768406004289, "grad_norm": 2.9907517350637125, "learning_rate": 4.998580168860524e-05, "loss": 0.7499, "num_tokens": 33850228.0, "step": 5695 }, { "epoch": 0.06081102706624134, "grad_norm": 1.2958749446062705, "learning_rate": 4.998566035743984e-05, "loss": 0.6069, "num_tokens": 33894862.0, "step": 5700 }, { "epoch": 0.060864370072439805, "grad_norm": 2.4110046750757816, "learning_rate": 4.9985518326566885e-05, "loss": 0.7416, "num_tokens": 33921050.0, "step": 5705 }, { "epoch": 0.06091771307863826, "grad_norm": 1.6967437475733684, "learning_rate": 4.998537559599079e-05, "loss": 0.6886, "num_tokens": 33953236.0, "step": 5710 }, { "epoch": 0.06097105608483672, "grad_norm": 1.3860451932944657, "learning_rate": 4.998523216571598e-05, "loss": 0.7538, "num_tokens": 33976196.0, "step": 5715 }, { "epoch": 0.06102439909103517, "grad_norm": 1.4393916425681619, "learning_rate": 4.998508803574692e-05, "loss": 0.601, "num_tokens": 33993662.0, "step": 5720 }, { "epoch": 0.06107774209723363, "grad_norm": 1.9316007651213989, "learning_rate": 4.998494320608813e-05, "loss": 0.5311, "num_tokens": 34010830.0, "step": 5725 }, { "epoch": 0.06113108510343209, "grad_norm": 2.240464549163988, "learning_rate": 4.998479767674408e-05, "loss": 0.5867, "num_tokens": 34032729.0, "step": 5730 }, { "epoch": 0.06118442810963055, "grad_norm": 1.4353848682430224, "learning_rate": 4.998465144771932e-05, "loss": 0.6647, "num_tokens": 34056705.0, "step": 5735 }, { "epoch": 0.061237771115829, "grad_norm": 2.2478491650430454, "learning_rate": 4.998450451901838e-05, "loss": 0.6977, "num_tokens": 34085288.0, "step": 5740 }, { "epoch": 0.06129111412202746, "grad_norm": 1.1112354982660944, "learning_rate": 4.9984356890645855e-05, "loss": 0.6847, "num_tokens": 34122723.0, "step": 5745 }, { "epoch": 0.06134445712822592, "grad_norm": 1.4802212053707566, "learning_rate": 4.998420856260632e-05, "loss": 0.7699, "num_tokens": 34159439.0, "step": 5750 }, { "epoch": 0.06139780013442438, "grad_norm": 1.5554611407114116, "learning_rate": 4.9984059534904406e-05, "loss": 0.7706, "num_tokens": 34193538.0, "step": 5755 }, { "epoch": 0.06145114314062283, "grad_norm": 1.5164626700015664, "learning_rate": 4.998390980754473e-05, "loss": 0.6859, "num_tokens": 34231333.0, "step": 5760 }, { "epoch": 0.06150448614682129, "grad_norm": 2.599070371561864, "learning_rate": 4.998375938053197e-05, "loss": 0.6579, "num_tokens": 34250300.0, "step": 5765 }, { "epoch": 0.061557829153019744, "grad_norm": 1.6835657776259645, "learning_rate": 4.998360825387081e-05, "loss": 0.6487, "num_tokens": 34284932.0, "step": 5770 }, { "epoch": 0.06161117215921821, "grad_norm": 1.3127977778392288, "learning_rate": 4.998345642756594e-05, "loss": 0.6473, "num_tokens": 34313237.0, "step": 5775 }, { "epoch": 0.06166451516541666, "grad_norm": 1.9831026205339104, "learning_rate": 4.998330390162209e-05, "loss": 0.7178, "num_tokens": 34343994.0, "step": 5780 }, { "epoch": 0.06171785817161512, "grad_norm": 1.8003284700910465, "learning_rate": 4.9983150676043995e-05, "loss": 0.63, "num_tokens": 34364275.0, "step": 5785 }, { "epoch": 0.061771201177813574, "grad_norm": 3.6341871308729123, "learning_rate": 4.998299675083644e-05, "loss": 0.889, "num_tokens": 34395839.0, "step": 5790 }, { "epoch": 0.06182454418401204, "grad_norm": 2.2339234282278713, "learning_rate": 4.99828421260042e-05, "loss": 0.6822, "num_tokens": 34433094.0, "step": 5795 }, { "epoch": 0.06187788719021049, "grad_norm": 1.3581938982254778, "learning_rate": 4.99826868015521e-05, "loss": 0.6791, "num_tokens": 34468583.0, "step": 5800 }, { "epoch": 0.06193123019640895, "grad_norm": 2.308010273934841, "learning_rate": 4.998253077748497e-05, "loss": 0.7169, "num_tokens": 34493655.0, "step": 5805 }, { "epoch": 0.061984573202607404, "grad_norm": 2.3123382306915548, "learning_rate": 4.998237405380766e-05, "loss": 0.7087, "num_tokens": 34514290.0, "step": 5810 }, { "epoch": 0.06203791620880586, "grad_norm": 1.641395565632403, "learning_rate": 4.998221663052505e-05, "loss": 0.7599, "num_tokens": 34547385.0, "step": 5815 }, { "epoch": 0.06209125921500432, "grad_norm": 4.668544908089278, "learning_rate": 4.998205850764204e-05, "loss": 0.7654, "num_tokens": 34576322.0, "step": 5820 }, { "epoch": 0.06214460222120278, "grad_norm": 2.989917616634022, "learning_rate": 4.998189968516355e-05, "loss": 0.7889, "num_tokens": 34604442.0, "step": 5825 }, { "epoch": 0.062197945227401234, "grad_norm": 2.54380807003183, "learning_rate": 4.998174016309451e-05, "loss": 0.7923, "num_tokens": 34637625.0, "step": 5830 }, { "epoch": 0.06225128823359969, "grad_norm": 2.3418358307498304, "learning_rate": 4.9981579941439904e-05, "loss": 0.8061, "num_tokens": 34669322.0, "step": 5835 }, { "epoch": 0.06230463123979815, "grad_norm": 1.8106786263965173, "learning_rate": 4.9981419020204705e-05, "loss": 0.7447, "num_tokens": 34703212.0, "step": 5840 }, { "epoch": 0.06235797424599661, "grad_norm": 1.2967066899567266, "learning_rate": 4.998125739939393e-05, "loss": 0.7936, "num_tokens": 34741773.0, "step": 5845 }, { "epoch": 0.062411317252195064, "grad_norm": 1.9720730268279372, "learning_rate": 4.9981095079012597e-05, "loss": 0.6952, "num_tokens": 34764734.0, "step": 5850 }, { "epoch": 0.06246466025839352, "grad_norm": 2.0054032026406956, "learning_rate": 4.998093205906576e-05, "loss": 0.689, "num_tokens": 34795011.0, "step": 5855 }, { "epoch": 0.06251800326459198, "grad_norm": 1.5346844869289598, "learning_rate": 4.99807683395585e-05, "loss": 0.5623, "num_tokens": 34815762.0, "step": 5860 }, { "epoch": 0.06257134627079043, "grad_norm": 1.5719057028518901, "learning_rate": 4.998060392049591e-05, "loss": 0.5811, "num_tokens": 34834548.0, "step": 5865 }, { "epoch": 0.06262468927698889, "grad_norm": 1.4981059104770114, "learning_rate": 4.9980438801883087e-05, "loss": 0.7139, "num_tokens": 34873738.0, "step": 5870 }, { "epoch": 0.06267803228318736, "grad_norm": 1.6253810232816006, "learning_rate": 4.99802729837252e-05, "loss": 0.7007, "num_tokens": 34908383.0, "step": 5875 }, { "epoch": 0.06273137528938581, "grad_norm": 2.54150456425708, "learning_rate": 4.9980106466027386e-05, "loss": 0.6978, "num_tokens": 34922037.0, "step": 5880 }, { "epoch": 0.06278471829558427, "grad_norm": 1.584055789635932, "learning_rate": 4.997993924879484e-05, "loss": 0.5471, "num_tokens": 34940893.0, "step": 5885 }, { "epoch": 0.06283806130178272, "grad_norm": 1.259039156698657, "learning_rate": 4.997977133203276e-05, "loss": 0.7576, "num_tokens": 34969480.0, "step": 5890 }, { "epoch": 0.06289140430798118, "grad_norm": 1.91413882224219, "learning_rate": 4.997960271574637e-05, "loss": 0.6715, "num_tokens": 34984692.0, "step": 5895 }, { "epoch": 0.06294474731417964, "grad_norm": 1.0790167958563763, "learning_rate": 4.997943339994091e-05, "loss": 0.7418, "num_tokens": 35031222.0, "step": 5900 }, { "epoch": 0.06299809032037809, "grad_norm": 2.406619675908307, "learning_rate": 4.997926338462166e-05, "loss": 0.644, "num_tokens": 35061193.0, "step": 5905 }, { "epoch": 0.06305143332657655, "grad_norm": 1.2415887731629742, "learning_rate": 4.9979092669793914e-05, "loss": 0.6875, "num_tokens": 35103882.0, "step": 5910 }, { "epoch": 0.063104776332775, "grad_norm": 2.1451385364415154, "learning_rate": 4.997892125546297e-05, "loss": 0.6273, "num_tokens": 35128560.0, "step": 5915 }, { "epoch": 0.06315811933897347, "grad_norm": 1.1162430081476464, "learning_rate": 4.997874914163417e-05, "loss": 0.8796, "num_tokens": 35161427.0, "step": 5920 }, { "epoch": 0.06321146234517193, "grad_norm": 2.8832143672352855, "learning_rate": 4.997857632831287e-05, "loss": 0.6432, "num_tokens": 35179356.0, "step": 5925 }, { "epoch": 0.06326480535137038, "grad_norm": 2.260325635168697, "learning_rate": 4.997840281550445e-05, "loss": 0.6055, "num_tokens": 35215477.0, "step": 5930 }, { "epoch": 0.06331814835756884, "grad_norm": 1.3409966803955955, "learning_rate": 4.997822860321431e-05, "loss": 0.6364, "num_tokens": 35241842.0, "step": 5935 }, { "epoch": 0.0633714913637673, "grad_norm": 1.4010497897563583, "learning_rate": 4.9978053691447855e-05, "loss": 0.6647, "num_tokens": 35279528.0, "step": 5940 }, { "epoch": 0.06342483436996575, "grad_norm": 4.225166260433297, "learning_rate": 4.997787808021055e-05, "loss": 0.6941, "num_tokens": 35306151.0, "step": 5945 }, { "epoch": 0.06347817737616421, "grad_norm": 1.4701169872308806, "learning_rate": 4.997770176950785e-05, "loss": 0.8106, "num_tokens": 35333929.0, "step": 5950 }, { "epoch": 0.06353152038236266, "grad_norm": 1.6570424204876362, "learning_rate": 4.997752475934524e-05, "loss": 0.6866, "num_tokens": 35357373.0, "step": 5955 }, { "epoch": 0.06358486338856112, "grad_norm": 1.4551809095098684, "learning_rate": 4.997734704972823e-05, "loss": 0.5646, "num_tokens": 35379903.0, "step": 5960 }, { "epoch": 0.06363820639475959, "grad_norm": 4.542099419573978, "learning_rate": 4.997716864066235e-05, "loss": 0.7995, "num_tokens": 35409597.0, "step": 5965 }, { "epoch": 0.06369154940095804, "grad_norm": 1.697003175530128, "learning_rate": 4.997698953215314e-05, "loss": 0.8016, "num_tokens": 35443203.0, "step": 5970 }, { "epoch": 0.0637448924071565, "grad_norm": 2.0962495337346687, "learning_rate": 4.99768097242062e-05, "loss": 0.6149, "num_tokens": 35462389.0, "step": 5975 }, { "epoch": 0.06379823541335496, "grad_norm": 1.4921542865265758, "learning_rate": 4.997662921682711e-05, "loss": 0.6551, "num_tokens": 35489252.0, "step": 5980 }, { "epoch": 0.06385157841955341, "grad_norm": 1.9294690441412081, "learning_rate": 4.997644801002147e-05, "loss": 0.7895, "num_tokens": 35504240.0, "step": 5985 }, { "epoch": 0.06390492142575187, "grad_norm": 1.2982426224401409, "learning_rate": 4.9976266103794955e-05, "loss": 0.7581, "num_tokens": 35537004.0, "step": 5990 }, { "epoch": 0.06395826443195032, "grad_norm": 1.3833320989951594, "learning_rate": 4.99760834981532e-05, "loss": 0.576, "num_tokens": 35569957.0, "step": 5995 }, { "epoch": 0.06401160743814878, "grad_norm": 1.6466207598594067, "learning_rate": 4.9975900193101886e-05, "loss": 0.8461, "num_tokens": 35595055.0, "step": 6000 }, { "epoch": 0.06406495044434724, "grad_norm": 2.8484018927009647, "learning_rate": 4.997571618864674e-05, "loss": 0.8773, "num_tokens": 35623829.0, "step": 6005 }, { "epoch": 0.0641182934505457, "grad_norm": 2.0340964923663236, "learning_rate": 4.997553148479347e-05, "loss": 0.8468, "num_tokens": 35659315.0, "step": 6010 }, { "epoch": 0.06417163645674416, "grad_norm": 1.2125736530705802, "learning_rate": 4.997534608154781e-05, "loss": 0.6002, "num_tokens": 35688023.0, "step": 6015 }, { "epoch": 0.06422497946294262, "grad_norm": 2.191908153239602, "learning_rate": 4.997515997891556e-05, "loss": 0.7218, "num_tokens": 35719807.0, "step": 6020 }, { "epoch": 0.06427832246914107, "grad_norm": 1.3059200053819706, "learning_rate": 4.997497317690249e-05, "loss": 0.7149, "num_tokens": 35766702.0, "step": 6025 }, { "epoch": 0.06433166547533953, "grad_norm": 2.2295963046708422, "learning_rate": 4.997478567551442e-05, "loss": 0.6321, "num_tokens": 35793464.0, "step": 6030 }, { "epoch": 0.06438500848153798, "grad_norm": 1.9980149252496908, "learning_rate": 4.997459747475719e-05, "loss": 0.6641, "num_tokens": 35810372.0, "step": 6035 }, { "epoch": 0.06443835148773644, "grad_norm": 1.7889946831723984, "learning_rate": 4.997440857463665e-05, "loss": 0.6918, "num_tokens": 35852211.0, "step": 6040 }, { "epoch": 0.0644916944939349, "grad_norm": 1.928256187856842, "learning_rate": 4.997421897515867e-05, "loss": 0.7522, "num_tokens": 35872356.0, "step": 6045 }, { "epoch": 0.06454503750013335, "grad_norm": 2.2238879668896088, "learning_rate": 4.997402867632917e-05, "loss": 0.7771, "num_tokens": 35899799.0, "step": 6050 }, { "epoch": 0.06459838050633182, "grad_norm": 1.945254061406933, "learning_rate": 4.997383767815405e-05, "loss": 0.6563, "num_tokens": 35939000.0, "step": 6055 }, { "epoch": 0.06465172351253028, "grad_norm": 2.0862636097905733, "learning_rate": 4.997364598063928e-05, "loss": 0.6382, "num_tokens": 35969433.0, "step": 6060 }, { "epoch": 0.06470506651872873, "grad_norm": 1.8079360796030044, "learning_rate": 4.997345358379079e-05, "loss": 0.653, "num_tokens": 36001904.0, "step": 6065 }, { "epoch": 0.06475840952492719, "grad_norm": 1.145983254981834, "learning_rate": 4.9973260487614596e-05, "loss": 0.6972, "num_tokens": 36025237.0, "step": 6070 }, { "epoch": 0.06481175253112564, "grad_norm": 1.65791728089991, "learning_rate": 4.99730666921167e-05, "loss": 0.671, "num_tokens": 36049862.0, "step": 6075 }, { "epoch": 0.0648650955373241, "grad_norm": 2.038540670297654, "learning_rate": 4.9972872197303126e-05, "loss": 0.6716, "num_tokens": 36068371.0, "step": 6080 }, { "epoch": 0.06491843854352256, "grad_norm": 1.615827821504038, "learning_rate": 4.997267700317993e-05, "loss": 0.7824, "num_tokens": 36105640.0, "step": 6085 }, { "epoch": 0.06497178154972101, "grad_norm": 1.2666633521519026, "learning_rate": 4.997248110975318e-05, "loss": 0.6929, "num_tokens": 36126033.0, "step": 6090 }, { "epoch": 0.06502512455591947, "grad_norm": 2.6300977237873098, "learning_rate": 4.9972284517028984e-05, "loss": 0.7895, "num_tokens": 36153367.0, "step": 6095 }, { "epoch": 0.06507846756211794, "grad_norm": 2.758128919428039, "learning_rate": 4.9972087225013455e-05, "loss": 0.6988, "num_tokens": 36169106.0, "step": 6100 }, { "epoch": 0.06513181056831639, "grad_norm": 1.2407398979894706, "learning_rate": 4.997188923371273e-05, "loss": 0.6668, "num_tokens": 36199428.0, "step": 6105 }, { "epoch": 0.06518515357451485, "grad_norm": 1.332876372424686, "learning_rate": 4.997169054313296e-05, "loss": 0.5945, "num_tokens": 36234372.0, "step": 6110 }, { "epoch": 0.0652384965807133, "grad_norm": 1.4642511672875698, "learning_rate": 4.997149115328036e-05, "loss": 0.7092, "num_tokens": 36263419.0, "step": 6115 }, { "epoch": 0.06529183958691176, "grad_norm": 1.5793671049465308, "learning_rate": 4.9971291064161095e-05, "loss": 0.5843, "num_tokens": 36291173.0, "step": 6120 }, { "epoch": 0.06534518259311022, "grad_norm": 1.398531133852693, "learning_rate": 4.997109027578142e-05, "loss": 0.7429, "num_tokens": 36325896.0, "step": 6125 }, { "epoch": 0.06539852559930867, "grad_norm": 1.1679792896963819, "learning_rate": 4.997088878814756e-05, "loss": 0.6033, "num_tokens": 36361647.0, "step": 6130 }, { "epoch": 0.06545186860550713, "grad_norm": 1.7615525759200106, "learning_rate": 4.997068660126581e-05, "loss": 0.849, "num_tokens": 36388345.0, "step": 6135 }, { "epoch": 0.06550521161170558, "grad_norm": 1.4526622339623405, "learning_rate": 4.997048371514244e-05, "loss": 0.7093, "num_tokens": 36405896.0, "step": 6140 }, { "epoch": 0.06555855461790405, "grad_norm": 2.0858375875886437, "learning_rate": 4.9970280129783774e-05, "loss": 0.7015, "num_tokens": 36429544.0, "step": 6145 }, { "epoch": 0.06561189762410251, "grad_norm": 1.3704246933451822, "learning_rate": 4.997007584519615e-05, "loss": 0.6814, "num_tokens": 36463588.0, "step": 6150 }, { "epoch": 0.06566524063030096, "grad_norm": 1.1567864006447799, "learning_rate": 4.996987086138592e-05, "loss": 0.7486, "num_tokens": 36506728.0, "step": 6155 }, { "epoch": 0.06571858363649942, "grad_norm": 1.321879850333185, "learning_rate": 4.9969665178359465e-05, "loss": 0.6515, "num_tokens": 36530284.0, "step": 6160 }, { "epoch": 0.06577192664269788, "grad_norm": 1.039442914094357, "learning_rate": 4.996945879612318e-05, "loss": 0.6693, "num_tokens": 36561124.0, "step": 6165 }, { "epoch": 0.06582526964889633, "grad_norm": 1.775280174153582, "learning_rate": 4.996925171468348e-05, "loss": 0.6647, "num_tokens": 36588534.0, "step": 6170 }, { "epoch": 0.06587861265509479, "grad_norm": 1.3997081934004774, "learning_rate": 4.996904393404684e-05, "loss": 0.821, "num_tokens": 36634913.0, "step": 6175 }, { "epoch": 0.06593195566129324, "grad_norm": 1.3449987597100874, "learning_rate": 4.99688354542197e-05, "loss": 0.7052, "num_tokens": 36659560.0, "step": 6180 }, { "epoch": 0.0659852986674917, "grad_norm": 1.7620332903234341, "learning_rate": 4.9968626275208546e-05, "loss": 0.7913, "num_tokens": 36696265.0, "step": 6185 }, { "epoch": 0.06603864167369017, "grad_norm": 2.0959645309789567, "learning_rate": 4.99684163970199e-05, "loss": 0.6466, "num_tokens": 36720914.0, "step": 6190 }, { "epoch": 0.06609198467988862, "grad_norm": 2.2810291533590967, "learning_rate": 4.996820581966028e-05, "loss": 0.8161, "num_tokens": 36746761.0, "step": 6195 }, { "epoch": 0.06614532768608708, "grad_norm": 1.3146615633205265, "learning_rate": 4.996799454313625e-05, "loss": 0.874, "num_tokens": 36797729.0, "step": 6200 }, { "epoch": 0.06619867069228554, "grad_norm": 1.129784839855781, "learning_rate": 4.9967782567454385e-05, "loss": 0.6377, "num_tokens": 36824233.0, "step": 6205 }, { "epoch": 0.06625201369848399, "grad_norm": 1.1989677058937238, "learning_rate": 4.996756989262127e-05, "loss": 0.7144, "num_tokens": 36855842.0, "step": 6210 }, { "epoch": 0.06630535670468245, "grad_norm": 1.2388331429954322, "learning_rate": 4.996735651864353e-05, "loss": 0.6518, "num_tokens": 36882333.0, "step": 6215 }, { "epoch": 0.0663586997108809, "grad_norm": 2.703338908107012, "learning_rate": 4.996714244552781e-05, "loss": 0.804, "num_tokens": 36911907.0, "step": 6220 }, { "epoch": 0.06641204271707936, "grad_norm": 1.673025302314824, "learning_rate": 4.996692767328076e-05, "loss": 0.8078, "num_tokens": 36936944.0, "step": 6225 }, { "epoch": 0.06646538572327781, "grad_norm": 1.2552175160834378, "learning_rate": 4.996671220190908e-05, "loss": 0.7661, "num_tokens": 36966322.0, "step": 6230 }, { "epoch": 0.06651872872947628, "grad_norm": 1.8057382561098898, "learning_rate": 4.996649603141945e-05, "loss": 0.7188, "num_tokens": 37008628.0, "step": 6235 }, { "epoch": 0.06657207173567474, "grad_norm": 1.2177876073604643, "learning_rate": 4.9966279161818616e-05, "loss": 0.7067, "num_tokens": 37049317.0, "step": 6240 }, { "epoch": 0.0666254147418732, "grad_norm": 1.2979001256813565, "learning_rate": 4.996606159311333e-05, "loss": 0.573, "num_tokens": 37073189.0, "step": 6245 }, { "epoch": 0.06667875774807165, "grad_norm": 1.7586596390797062, "learning_rate": 4.996584332531035e-05, "loss": 0.8969, "num_tokens": 37118620.0, "step": 6250 }, { "epoch": 0.06673210075427011, "grad_norm": 1.8683052675913399, "learning_rate": 4.996562435841646e-05, "loss": 0.5193, "num_tokens": 37134035.0, "step": 6255 }, { "epoch": 0.06678544376046856, "grad_norm": 2.0708862470705647, "learning_rate": 4.99654046924385e-05, "loss": 0.5949, "num_tokens": 37170010.0, "step": 6260 }, { "epoch": 0.06683878676666702, "grad_norm": 1.3866418208894573, "learning_rate": 4.996518432738328e-05, "loss": 0.6355, "num_tokens": 37202796.0, "step": 6265 }, { "epoch": 0.06689212977286547, "grad_norm": 1.2047547805513898, "learning_rate": 4.9964963263257676e-05, "loss": 0.5841, "num_tokens": 37225318.0, "step": 6270 }, { "epoch": 0.06694547277906393, "grad_norm": 1.5231237595944247, "learning_rate": 4.996474150006856e-05, "loss": 0.72, "num_tokens": 37249709.0, "step": 6275 }, { "epoch": 0.0669988157852624, "grad_norm": 1.7275407153828748, "learning_rate": 4.9964519037822824e-05, "loss": 0.6366, "num_tokens": 37273962.0, "step": 6280 }, { "epoch": 0.06705215879146086, "grad_norm": 1.7261740140283917, "learning_rate": 4.996429587652741e-05, "loss": 0.5931, "num_tokens": 37300732.0, "step": 6285 }, { "epoch": 0.06710550179765931, "grad_norm": 2.6155776038590313, "learning_rate": 4.996407201618925e-05, "loss": 0.6926, "num_tokens": 37332392.0, "step": 6290 }, { "epoch": 0.06715884480385777, "grad_norm": 1.0362191264845453, "learning_rate": 4.9963847456815303e-05, "loss": 0.6018, "num_tokens": 37375904.0, "step": 6295 }, { "epoch": 0.06721218781005622, "grad_norm": 1.900266161967473, "learning_rate": 4.996362219841257e-05, "loss": 0.8201, "num_tokens": 37404768.0, "step": 6300 }, { "epoch": 0.06726553081625468, "grad_norm": 1.724419815946038, "learning_rate": 4.9963396240988055e-05, "loss": 0.6788, "num_tokens": 37432208.0, "step": 6305 }, { "epoch": 0.06731887382245313, "grad_norm": 2.053216308201671, "learning_rate": 4.996316958454879e-05, "loss": 0.6775, "num_tokens": 37456773.0, "step": 6310 }, { "epoch": 0.06737221682865159, "grad_norm": 1.4474965056695028, "learning_rate": 4.996294222910183e-05, "loss": 0.7274, "num_tokens": 37493253.0, "step": 6315 }, { "epoch": 0.06742555983485005, "grad_norm": 1.2489909635406882, "learning_rate": 4.996271417465424e-05, "loss": 0.6525, "num_tokens": 37518919.0, "step": 6320 }, { "epoch": 0.06747890284104852, "grad_norm": 1.245397164103303, "learning_rate": 4.996248542121314e-05, "loss": 0.5822, "num_tokens": 37540068.0, "step": 6325 }, { "epoch": 0.06753224584724697, "grad_norm": 1.7800993541452785, "learning_rate": 4.9962255968785624e-05, "loss": 0.733, "num_tokens": 37559550.0, "step": 6330 }, { "epoch": 0.06758558885344543, "grad_norm": 1.4559698505090592, "learning_rate": 4.996202581737884e-05, "loss": 0.6134, "num_tokens": 37582560.0, "step": 6335 }, { "epoch": 0.06763893185964388, "grad_norm": 1.4035384486890439, "learning_rate": 4.9961794966999955e-05, "loss": 0.6539, "num_tokens": 37609788.0, "step": 6340 }, { "epoch": 0.06769227486584234, "grad_norm": 2.317424518479338, "learning_rate": 4.996156341765615e-05, "loss": 0.7191, "num_tokens": 37643957.0, "step": 6345 }, { "epoch": 0.0677456178720408, "grad_norm": 1.296109367095146, "learning_rate": 4.996133116935461e-05, "loss": 0.6023, "num_tokens": 37666780.0, "step": 6350 }, { "epoch": 0.06779896087823925, "grad_norm": 2.2040841331848298, "learning_rate": 4.996109822210261e-05, "loss": 0.6187, "num_tokens": 37683296.0, "step": 6355 }, { "epoch": 0.0678523038844377, "grad_norm": 1.611491461443079, "learning_rate": 4.996086457590735e-05, "loss": 0.7724, "num_tokens": 37717287.0, "step": 6360 }, { "epoch": 0.06790564689063616, "grad_norm": 1.8473024716972928, "learning_rate": 4.996063023077613e-05, "loss": 0.6575, "num_tokens": 37750936.0, "step": 6365 }, { "epoch": 0.06795898989683463, "grad_norm": 1.694471360348325, "learning_rate": 4.996039518671622e-05, "loss": 0.7121, "num_tokens": 37771350.0, "step": 6370 }, { "epoch": 0.06801233290303309, "grad_norm": 1.1484067849277613, "learning_rate": 4.996015944373496e-05, "loss": 0.6657, "num_tokens": 37802237.0, "step": 6375 }, { "epoch": 0.06806567590923154, "grad_norm": 1.853794262926677, "learning_rate": 4.9959923001839666e-05, "loss": 0.616, "num_tokens": 37816325.0, "step": 6380 }, { "epoch": 0.06811901891543, "grad_norm": 1.1539451657519506, "learning_rate": 4.995968586103771e-05, "loss": 0.888, "num_tokens": 37856514.0, "step": 6385 }, { "epoch": 0.06817236192162845, "grad_norm": 1.2449709122244355, "learning_rate": 4.9959448021336454e-05, "loss": 0.6188, "num_tokens": 37891687.0, "step": 6390 }, { "epoch": 0.06822570492782691, "grad_norm": 1.1650398579923258, "learning_rate": 4.995920948274331e-05, "loss": 0.6204, "num_tokens": 37935211.0, "step": 6395 }, { "epoch": 0.06827904793402537, "grad_norm": 1.5990509547583942, "learning_rate": 4.99589702452657e-05, "loss": 0.6735, "num_tokens": 37961424.0, "step": 6400 }, { "epoch": 0.06833239094022382, "grad_norm": 2.569967846368588, "learning_rate": 4.9958730308911075e-05, "loss": 0.6289, "num_tokens": 37991844.0, "step": 6405 }, { "epoch": 0.06838573394642228, "grad_norm": 1.0824182129415114, "learning_rate": 4.9958489673686885e-05, "loss": 0.6652, "num_tokens": 38017744.0, "step": 6410 }, { "epoch": 0.06843907695262075, "grad_norm": 1.8398842370054578, "learning_rate": 4.995824833960063e-05, "loss": 0.6207, "num_tokens": 38036881.0, "step": 6415 }, { "epoch": 0.0684924199588192, "grad_norm": 1.7174582936760987, "learning_rate": 4.995800630665982e-05, "loss": 0.5798, "num_tokens": 38059708.0, "step": 6420 }, { "epoch": 0.06854576296501766, "grad_norm": 2.2245296942128108, "learning_rate": 4.995776357487198e-05, "loss": 0.6733, "num_tokens": 38090179.0, "step": 6425 }, { "epoch": 0.06859910597121611, "grad_norm": 1.977523940949569, "learning_rate": 4.9957520144244675e-05, "loss": 0.8443, "num_tokens": 38123127.0, "step": 6430 }, { "epoch": 0.06865244897741457, "grad_norm": 1.2916552380827944, "learning_rate": 4.995727601478547e-05, "loss": 0.7522, "num_tokens": 38152389.0, "step": 6435 }, { "epoch": 0.06870579198361303, "grad_norm": 2.4781617012848365, "learning_rate": 4.995703118650196e-05, "loss": 0.7609, "num_tokens": 38191106.0, "step": 6440 }, { "epoch": 0.06875913498981148, "grad_norm": 1.5757492635284962, "learning_rate": 4.995678565940176e-05, "loss": 0.597, "num_tokens": 38215803.0, "step": 6445 }, { "epoch": 0.06881247799600994, "grad_norm": 1.9586521045775644, "learning_rate": 4.9956539433492525e-05, "loss": 0.6689, "num_tokens": 38246504.0, "step": 6450 }, { "epoch": 0.0688658210022084, "grad_norm": 1.3730648127662317, "learning_rate": 4.995629250878191e-05, "loss": 0.8055, "num_tokens": 38275168.0, "step": 6455 }, { "epoch": 0.06891916400840686, "grad_norm": 1.4169562669863074, "learning_rate": 4.995604488527761e-05, "loss": 0.6852, "num_tokens": 38318229.0, "step": 6460 }, { "epoch": 0.06897250701460532, "grad_norm": 1.7521509905717314, "learning_rate": 4.99557965629873e-05, "loss": 0.7792, "num_tokens": 38361935.0, "step": 6465 }, { "epoch": 0.06902585002080378, "grad_norm": 1.390136253508477, "learning_rate": 4.995554754191874e-05, "loss": 0.7712, "num_tokens": 38395519.0, "step": 6470 }, { "epoch": 0.06907919302700223, "grad_norm": 1.3163423468842084, "learning_rate": 4.995529782207966e-05, "loss": 0.605, "num_tokens": 38414231.0, "step": 6475 }, { "epoch": 0.06913253603320069, "grad_norm": 1.466725321058068, "learning_rate": 4.9955047403477836e-05, "loss": 0.6778, "num_tokens": 38449337.0, "step": 6480 }, { "epoch": 0.06918587903939914, "grad_norm": 2.035222441567585, "learning_rate": 4.995479628612106e-05, "loss": 0.7868, "num_tokens": 38478058.0, "step": 6485 }, { "epoch": 0.0692392220455976, "grad_norm": 2.011231660910893, "learning_rate": 4.995454447001715e-05, "loss": 0.7927, "num_tokens": 38510184.0, "step": 6490 }, { "epoch": 0.06929256505179605, "grad_norm": 2.141017419652547, "learning_rate": 4.9954291955173934e-05, "loss": 0.6758, "num_tokens": 38541252.0, "step": 6495 }, { "epoch": 0.06934590805799451, "grad_norm": 1.6044653780851543, "learning_rate": 4.995403874159929e-05, "loss": 0.6854, "num_tokens": 38564259.0, "step": 6500 }, { "epoch": 0.06939925106419298, "grad_norm": 2.853158381456996, "learning_rate": 4.9953784829301064e-05, "loss": 0.8863, "num_tokens": 38579936.0, "step": 6505 }, { "epoch": 0.06945259407039144, "grad_norm": 3.413863340589821, "learning_rate": 4.9953530218287185e-05, "loss": 0.7408, "num_tokens": 38613644.0, "step": 6510 }, { "epoch": 0.06950593707658989, "grad_norm": 1.3571488318237552, "learning_rate": 4.9953274908565565e-05, "loss": 0.6903, "num_tokens": 38646722.0, "step": 6515 }, { "epoch": 0.06955928008278835, "grad_norm": 1.9761855532601118, "learning_rate": 4.9953018900144146e-05, "loss": 0.7474, "num_tokens": 38676528.0, "step": 6520 }, { "epoch": 0.0696126230889868, "grad_norm": 2.210449075780366, "learning_rate": 4.99527621930309e-05, "loss": 0.8308, "num_tokens": 38722940.0, "step": 6525 }, { "epoch": 0.06966596609518526, "grad_norm": 1.885859681958635, "learning_rate": 4.995250478723382e-05, "loss": 0.6019, "num_tokens": 38742744.0, "step": 6530 }, { "epoch": 0.06971930910138371, "grad_norm": 1.3536483524604008, "learning_rate": 4.995224668276091e-05, "loss": 0.5972, "num_tokens": 38768469.0, "step": 6535 }, { "epoch": 0.06977265210758217, "grad_norm": 1.1600800807524898, "learning_rate": 4.9951987879620185e-05, "loss": 0.5785, "num_tokens": 38796556.0, "step": 6540 }, { "epoch": 0.06982599511378063, "grad_norm": 1.4852186326242829, "learning_rate": 4.995172837781973e-05, "loss": 0.7419, "num_tokens": 38828997.0, "step": 6545 }, { "epoch": 0.0698793381199791, "grad_norm": 1.6230040183073497, "learning_rate": 4.9951468177367605e-05, "loss": 0.9436, "num_tokens": 38854192.0, "step": 6550 }, { "epoch": 0.06993268112617755, "grad_norm": 1.0937761743946075, "learning_rate": 4.99512072782719e-05, "loss": 0.649, "num_tokens": 38890994.0, "step": 6555 }, { "epoch": 0.069986024132376, "grad_norm": 1.0700631066638675, "learning_rate": 4.9950945680540754e-05, "loss": 0.6174, "num_tokens": 38917825.0, "step": 6560 }, { "epoch": 0.07003936713857446, "grad_norm": 1.6385744002010492, "learning_rate": 4.995068338418228e-05, "loss": 0.7232, "num_tokens": 38937106.0, "step": 6565 }, { "epoch": 0.07009271014477292, "grad_norm": 1.6593825523483237, "learning_rate": 4.9950420389204656e-05, "loss": 0.7375, "num_tokens": 38958340.0, "step": 6570 }, { "epoch": 0.07014605315097137, "grad_norm": 4.017490241171196, "learning_rate": 4.9950156695616065e-05, "loss": 0.8292, "num_tokens": 38980296.0, "step": 6575 }, { "epoch": 0.07019939615716983, "grad_norm": 1.3126895255108464, "learning_rate": 4.994989230342472e-05, "loss": 0.6323, "num_tokens": 39019726.0, "step": 6580 }, { "epoch": 0.07025273916336829, "grad_norm": 1.6246428939520141, "learning_rate": 4.994962721263883e-05, "loss": 0.7198, "num_tokens": 39045237.0, "step": 6585 }, { "epoch": 0.07030608216956674, "grad_norm": 1.2742851346604818, "learning_rate": 4.994936142326665e-05, "loss": 0.5929, "num_tokens": 39069199.0, "step": 6590 }, { "epoch": 0.07035942517576521, "grad_norm": 2.5738397447236205, "learning_rate": 4.994909493531646e-05, "loss": 0.7119, "num_tokens": 39100490.0, "step": 6595 }, { "epoch": 0.07041276818196367, "grad_norm": 1.407815816213306, "learning_rate": 4.994882774879656e-05, "loss": 0.7719, "num_tokens": 39125896.0, "step": 6600 }, { "epoch": 0.07046611118816212, "grad_norm": 1.0519383028684974, "learning_rate": 4.994855986371524e-05, "loss": 0.6482, "num_tokens": 39160122.0, "step": 6605 }, { "epoch": 0.07051945419436058, "grad_norm": 2.539794578496457, "learning_rate": 4.994829128008084e-05, "loss": 0.7488, "num_tokens": 39191144.0, "step": 6610 }, { "epoch": 0.07057279720055903, "grad_norm": 1.3109562171719686, "learning_rate": 4.994802199790174e-05, "loss": 0.5608, "num_tokens": 39211376.0, "step": 6615 }, { "epoch": 0.07062614020675749, "grad_norm": 1.084064307035328, "learning_rate": 4.99477520171863e-05, "loss": 0.6794, "num_tokens": 39247443.0, "step": 6620 }, { "epoch": 0.07067948321295595, "grad_norm": 1.9237045647423032, "learning_rate": 4.994748133794293e-05, "loss": 0.7436, "num_tokens": 39273309.0, "step": 6625 }, { "epoch": 0.0707328262191544, "grad_norm": 1.9694758105400576, "learning_rate": 4.9947209960180035e-05, "loss": 0.6173, "num_tokens": 39314335.0, "step": 6630 }, { "epoch": 0.07078616922535286, "grad_norm": 1.4780495106965945, "learning_rate": 4.994693788390609e-05, "loss": 0.6606, "num_tokens": 39334770.0, "step": 6635 }, { "epoch": 0.07083951223155133, "grad_norm": 1.3121250687963413, "learning_rate": 4.9946665109129534e-05, "loss": 0.6422, "num_tokens": 39359207.0, "step": 6640 }, { "epoch": 0.07089285523774978, "grad_norm": 1.4613530029693143, "learning_rate": 4.994639163585887e-05, "loss": 0.6561, "num_tokens": 39379911.0, "step": 6645 }, { "epoch": 0.07094619824394824, "grad_norm": 1.1446090581614865, "learning_rate": 4.994611746410261e-05, "loss": 0.6574, "num_tokens": 39400382.0, "step": 6650 }, { "epoch": 0.0709995412501467, "grad_norm": 3.0881897518738435, "learning_rate": 4.9945842593869274e-05, "loss": 0.7612, "num_tokens": 39419503.0, "step": 6655 }, { "epoch": 0.07105288425634515, "grad_norm": 1.7198868777653797, "learning_rate": 4.9945567025167424e-05, "loss": 0.7983, "num_tokens": 39449764.0, "step": 6660 }, { "epoch": 0.0711062272625436, "grad_norm": 1.7557115001919816, "learning_rate": 4.9945290758005634e-05, "loss": 0.7506, "num_tokens": 39479848.0, "step": 6665 }, { "epoch": 0.07115957026874206, "grad_norm": 1.1468039195827735, "learning_rate": 4.994501379239249e-05, "loss": 0.7833, "num_tokens": 39513657.0, "step": 6670 }, { "epoch": 0.07121291327494052, "grad_norm": 1.2406393248462189, "learning_rate": 4.994473612833663e-05, "loss": 0.5844, "num_tokens": 39531430.0, "step": 6675 }, { "epoch": 0.07126625628113897, "grad_norm": 1.1396492498215085, "learning_rate": 4.994445776584669e-05, "loss": 0.6739, "num_tokens": 39566247.0, "step": 6680 }, { "epoch": 0.07131959928733744, "grad_norm": 1.270975725841598, "learning_rate": 4.9944178704931314e-05, "loss": 0.7468, "num_tokens": 39593375.0, "step": 6685 }, { "epoch": 0.0713729422935359, "grad_norm": 1.3663875935860532, "learning_rate": 4.994389894559921e-05, "loss": 0.9727, "num_tokens": 39637101.0, "step": 6690 }, { "epoch": 0.07142628529973435, "grad_norm": 1.2844847300740194, "learning_rate": 4.994361848785906e-05, "loss": 0.6471, "num_tokens": 39684011.0, "step": 6695 }, { "epoch": 0.07147962830593281, "grad_norm": 1.4561490547981628, "learning_rate": 4.994333733171961e-05, "loss": 0.7773, "num_tokens": 39709470.0, "step": 6700 }, { "epoch": 0.07153297131213127, "grad_norm": 1.1628716312289722, "learning_rate": 4.99430554771896e-05, "loss": 0.7527, "num_tokens": 39758694.0, "step": 6705 }, { "epoch": 0.07158631431832972, "grad_norm": 2.0899716118078295, "learning_rate": 4.99427729242778e-05, "loss": 0.7406, "num_tokens": 39782182.0, "step": 6710 }, { "epoch": 0.07163965732452818, "grad_norm": 1.2218740372655934, "learning_rate": 4.994248967299301e-05, "loss": 0.7815, "num_tokens": 39812771.0, "step": 6715 }, { "epoch": 0.07169300033072663, "grad_norm": 1.6690731362596616, "learning_rate": 4.9942205723344044e-05, "loss": 0.5753, "num_tokens": 39846738.0, "step": 6720 }, { "epoch": 0.07174634333692509, "grad_norm": 2.202252088803103, "learning_rate": 4.9941921075339726e-05, "loss": 0.8341, "num_tokens": 39873801.0, "step": 6725 }, { "epoch": 0.07179968634312356, "grad_norm": 2.005177494121645, "learning_rate": 4.9941635728988917e-05, "loss": 0.6603, "num_tokens": 39916491.0, "step": 6730 }, { "epoch": 0.07185302934932201, "grad_norm": 1.279948176483804, "learning_rate": 4.9941349684300506e-05, "loss": 0.6311, "num_tokens": 39935299.0, "step": 6735 }, { "epoch": 0.07190637235552047, "grad_norm": 1.3779173380603629, "learning_rate": 4.994106294128339e-05, "loss": 0.6152, "num_tokens": 39971427.0, "step": 6740 }, { "epoch": 0.07195971536171893, "grad_norm": 1.9785580869208172, "learning_rate": 4.994077549994649e-05, "loss": 0.7333, "num_tokens": 39986302.0, "step": 6745 }, { "epoch": 0.07201305836791738, "grad_norm": 2.1106588987678783, "learning_rate": 4.994048736029876e-05, "loss": 0.7257, "num_tokens": 40024707.0, "step": 6750 }, { "epoch": 0.07206640137411584, "grad_norm": 1.5312250475681937, "learning_rate": 4.994019852234914e-05, "loss": 0.7587, "num_tokens": 40051612.0, "step": 6755 }, { "epoch": 0.0721197443803143, "grad_norm": 4.459476203870743, "learning_rate": 4.993990898610665e-05, "loss": 0.7692, "num_tokens": 40082798.0, "step": 6760 }, { "epoch": 0.07217308738651275, "grad_norm": 1.861739438409108, "learning_rate": 4.993961875158028e-05, "loss": 0.7427, "num_tokens": 40110998.0, "step": 6765 }, { "epoch": 0.0722264303927112, "grad_norm": 2.454254046961855, "learning_rate": 4.9939327818779064e-05, "loss": 0.8416, "num_tokens": 40135590.0, "step": 6770 }, { "epoch": 0.07227977339890967, "grad_norm": 1.2597472077828022, "learning_rate": 4.993903618771206e-05, "loss": 0.6647, "num_tokens": 40150695.0, "step": 6775 }, { "epoch": 0.07233311640510813, "grad_norm": 1.0508756866615372, "learning_rate": 4.993874385838834e-05, "loss": 0.6222, "num_tokens": 40191592.0, "step": 6780 }, { "epoch": 0.07238645941130659, "grad_norm": 1.0461549692078953, "learning_rate": 4.9938450830816996e-05, "loss": 0.5852, "num_tokens": 40233755.0, "step": 6785 }, { "epoch": 0.07243980241750504, "grad_norm": 1.1438484486061706, "learning_rate": 4.993815710500716e-05, "loss": 0.5836, "num_tokens": 40256508.0, "step": 6790 }, { "epoch": 0.0724931454237035, "grad_norm": 2.144201010532692, "learning_rate": 4.993786268096797e-05, "loss": 0.7343, "num_tokens": 40291058.0, "step": 6795 }, { "epoch": 0.07254648842990195, "grad_norm": 1.339622838782329, "learning_rate": 4.993756755870857e-05, "loss": 0.7205, "num_tokens": 40311353.0, "step": 6800 }, { "epoch": 0.07259983143610041, "grad_norm": 1.4841705789046247, "learning_rate": 4.993727173823816e-05, "loss": 0.6716, "num_tokens": 40356892.0, "step": 6805 }, { "epoch": 0.07265317444229887, "grad_norm": 3.568733989640221, "learning_rate": 4.993697521956595e-05, "loss": 0.6736, "num_tokens": 40388412.0, "step": 6810 }, { "epoch": 0.07270651744849732, "grad_norm": 1.5360990764708844, "learning_rate": 4.993667800270114e-05, "loss": 0.7408, "num_tokens": 40420010.0, "step": 6815 }, { "epoch": 0.07275986045469579, "grad_norm": 2.195347867510983, "learning_rate": 4.9936380087653006e-05, "loss": 0.6783, "num_tokens": 40447599.0, "step": 6820 }, { "epoch": 0.07281320346089425, "grad_norm": 1.3922837787910547, "learning_rate": 4.993608147443081e-05, "loss": 0.6841, "num_tokens": 40480187.0, "step": 6825 }, { "epoch": 0.0728665464670927, "grad_norm": 1.3117065812815043, "learning_rate": 4.993578216304384e-05, "loss": 0.686, "num_tokens": 40511789.0, "step": 6830 }, { "epoch": 0.07291988947329116, "grad_norm": 1.379885063386498, "learning_rate": 4.9935482153501426e-05, "loss": 0.6998, "num_tokens": 40533608.0, "step": 6835 }, { "epoch": 0.07297323247948961, "grad_norm": 2.528637877691709, "learning_rate": 4.993518144581287e-05, "loss": 0.7478, "num_tokens": 40560324.0, "step": 6840 }, { "epoch": 0.07302657548568807, "grad_norm": 1.1970617183030712, "learning_rate": 4.993488003998757e-05, "loss": 0.6194, "num_tokens": 40595770.0, "step": 6845 }, { "epoch": 0.07307991849188653, "grad_norm": 3.2696996325506205, "learning_rate": 4.993457793603488e-05, "loss": 0.6867, "num_tokens": 40615950.0, "step": 6850 }, { "epoch": 0.07313326149808498, "grad_norm": 1.0690613499908703, "learning_rate": 4.99342751339642e-05, "loss": 0.58, "num_tokens": 40648625.0, "step": 6855 }, { "epoch": 0.07318660450428344, "grad_norm": 2.053755640312161, "learning_rate": 4.993397163378496e-05, "loss": 0.6987, "num_tokens": 40681653.0, "step": 6860 }, { "epoch": 0.0732399475104819, "grad_norm": 2.139148169906689, "learning_rate": 4.993366743550661e-05, "loss": 0.8503, "num_tokens": 40707617.0, "step": 6865 }, { "epoch": 0.07329329051668036, "grad_norm": 1.7363137705360125, "learning_rate": 4.993336253913861e-05, "loss": 0.6508, "num_tokens": 40730346.0, "step": 6870 }, { "epoch": 0.07334663352287882, "grad_norm": 1.6828303923351202, "learning_rate": 4.993305694469044e-05, "loss": 0.7841, "num_tokens": 40761920.0, "step": 6875 }, { "epoch": 0.07339997652907727, "grad_norm": 1.3607312158889968, "learning_rate": 4.993275065217162e-05, "loss": 0.7638, "num_tokens": 40804304.0, "step": 6880 }, { "epoch": 0.07345331953527573, "grad_norm": 2.061559310684811, "learning_rate": 4.993244366159168e-05, "loss": 0.5322, "num_tokens": 40825804.0, "step": 6885 }, { "epoch": 0.07350666254147419, "grad_norm": 1.3220522702552087, "learning_rate": 4.993213597296017e-05, "loss": 0.6148, "num_tokens": 40843641.0, "step": 6890 }, { "epoch": 0.07356000554767264, "grad_norm": 1.3477209872452314, "learning_rate": 4.9931827586286664e-05, "loss": 0.721, "num_tokens": 40874800.0, "step": 6895 }, { "epoch": 0.0736133485538711, "grad_norm": 1.5397808613974318, "learning_rate": 4.993151850158076e-05, "loss": 0.7834, "num_tokens": 40909047.0, "step": 6900 }, { "epoch": 0.07366669156006955, "grad_norm": 1.469929373901147, "learning_rate": 4.993120871885208e-05, "loss": 0.678, "num_tokens": 40933995.0, "step": 6905 }, { "epoch": 0.07372003456626802, "grad_norm": 1.3400184264630266, "learning_rate": 4.993089823811026e-05, "loss": 0.6433, "num_tokens": 40960817.0, "step": 6910 }, { "epoch": 0.07377337757246648, "grad_norm": 2.273429881310505, "learning_rate": 4.993058705936495e-05, "loss": 0.7168, "num_tokens": 40980301.0, "step": 6915 }, { "epoch": 0.07382672057866493, "grad_norm": 1.8570072350762037, "learning_rate": 4.993027518262585e-05, "loss": 0.6246, "num_tokens": 41000559.0, "step": 6920 }, { "epoch": 0.07388006358486339, "grad_norm": 1.7898643393419844, "learning_rate": 4.9929962607902665e-05, "loss": 0.651, "num_tokens": 41023717.0, "step": 6925 }, { "epoch": 0.07393340659106185, "grad_norm": 1.190533500715751, "learning_rate": 4.9929649335205115e-05, "loss": 0.6757, "num_tokens": 41069890.0, "step": 6930 }, { "epoch": 0.0739867495972603, "grad_norm": 1.631946089056461, "learning_rate": 4.992933536454294e-05, "loss": 0.6764, "num_tokens": 41101514.0, "step": 6935 }, { "epoch": 0.07404009260345876, "grad_norm": 1.4742717042849898, "learning_rate": 4.992902069592593e-05, "loss": 0.6628, "num_tokens": 41129238.0, "step": 6940 }, { "epoch": 0.07409343560965721, "grad_norm": 2.116647506671732, "learning_rate": 4.9928705329363865e-05, "loss": 0.8478, "num_tokens": 41162333.0, "step": 6945 }, { "epoch": 0.07414677861585567, "grad_norm": 1.1721867229551086, "learning_rate": 4.992838926486656e-05, "loss": 0.6209, "num_tokens": 41189950.0, "step": 6950 }, { "epoch": 0.07420012162205414, "grad_norm": 1.7724993623048033, "learning_rate": 4.992807250244385e-05, "loss": 0.6553, "num_tokens": 41213278.0, "step": 6955 }, { "epoch": 0.0742534646282526, "grad_norm": 1.4246685930734442, "learning_rate": 4.9927755042105584e-05, "loss": 0.8766, "num_tokens": 41244260.0, "step": 6960 }, { "epoch": 0.07430680763445105, "grad_norm": 1.40559045771177, "learning_rate": 4.992743688386165e-05, "loss": 0.6692, "num_tokens": 41283284.0, "step": 6965 }, { "epoch": 0.0743601506406495, "grad_norm": 1.8881646321581507, "learning_rate": 4.992711802772196e-05, "loss": 0.6974, "num_tokens": 41316319.0, "step": 6970 }, { "epoch": 0.07441349364684796, "grad_norm": 1.6200715972698032, "learning_rate": 4.992679847369642e-05, "loss": 0.8395, "num_tokens": 41344838.0, "step": 6975 }, { "epoch": 0.07446683665304642, "grad_norm": 1.3233833069852643, "learning_rate": 4.992647822179497e-05, "loss": 0.7142, "num_tokens": 41391524.0, "step": 6980 }, { "epoch": 0.07452017965924487, "grad_norm": 1.9761860803140578, "learning_rate": 4.992615727202759e-05, "loss": 0.8827, "num_tokens": 41438131.0, "step": 6985 }, { "epoch": 0.07457352266544333, "grad_norm": 1.1072962689556105, "learning_rate": 4.9925835624404254e-05, "loss": 0.7486, "num_tokens": 41467576.0, "step": 6990 }, { "epoch": 0.07462686567164178, "grad_norm": 0.8771025593835606, "learning_rate": 4.992551327893498e-05, "loss": 0.7629, "num_tokens": 41504881.0, "step": 6995 }, { "epoch": 0.07468020867784025, "grad_norm": 2.344782760529327, "learning_rate": 4.99251902356298e-05, "loss": 0.5907, "num_tokens": 41527099.0, "step": 7000 }, { "epoch": 0.07473355168403871, "grad_norm": 2.001548599418726, "learning_rate": 4.992486649449876e-05, "loss": 0.6952, "num_tokens": 41555502.0, "step": 7005 }, { "epoch": 0.07478689469023717, "grad_norm": 1.2894477002820965, "learning_rate": 4.992454205555193e-05, "loss": 0.6335, "num_tokens": 41599942.0, "step": 7010 }, { "epoch": 0.07484023769643562, "grad_norm": 1.4451251094004127, "learning_rate": 4.992421691879942e-05, "loss": 0.6367, "num_tokens": 41628478.0, "step": 7015 }, { "epoch": 0.07489358070263408, "grad_norm": 1.397117308256135, "learning_rate": 4.9923891084251345e-05, "loss": 0.6632, "num_tokens": 41672105.0, "step": 7020 }, { "epoch": 0.07494692370883253, "grad_norm": 1.0203049495653036, "learning_rate": 4.992356455191783e-05, "loss": 0.6165, "num_tokens": 41716320.0, "step": 7025 }, { "epoch": 0.07500026671503099, "grad_norm": 1.139069087575042, "learning_rate": 4.9923237321809045e-05, "loss": 0.7938, "num_tokens": 41759991.0, "step": 7030 }, { "epoch": 0.07505360972122944, "grad_norm": 1.0578430477758753, "learning_rate": 4.992290939393518e-05, "loss": 0.7644, "num_tokens": 41796327.0, "step": 7035 }, { "epoch": 0.0751069527274279, "grad_norm": 1.7174663083377237, "learning_rate": 4.9922580768306426e-05, "loss": 0.5594, "num_tokens": 41826860.0, "step": 7040 }, { "epoch": 0.07516029573362637, "grad_norm": 1.1311365471833532, "learning_rate": 4.9922251444933025e-05, "loss": 0.661, "num_tokens": 41860450.0, "step": 7045 }, { "epoch": 0.07521363873982483, "grad_norm": 1.5190915917188106, "learning_rate": 4.9921921423825205e-05, "loss": 0.6445, "num_tokens": 41897481.0, "step": 7050 }, { "epoch": 0.07526698174602328, "grad_norm": 2.8084517026040228, "learning_rate": 4.992159070499325e-05, "loss": 0.7607, "num_tokens": 41930753.0, "step": 7055 }, { "epoch": 0.07532032475222174, "grad_norm": 1.8954917991195066, "learning_rate": 4.9921259288447455e-05, "loss": 0.6152, "num_tokens": 41949936.0, "step": 7060 }, { "epoch": 0.0753736677584202, "grad_norm": 1.6588642139344627, "learning_rate": 4.992092717419812e-05, "loss": 0.6645, "num_tokens": 41977062.0, "step": 7065 }, { "epoch": 0.07542701076461865, "grad_norm": 2.8940253683498094, "learning_rate": 4.992059436225558e-05, "loss": 0.7633, "num_tokens": 41992549.0, "step": 7070 }, { "epoch": 0.0754803537708171, "grad_norm": 1.8341771202338997, "learning_rate": 4.99202608526302e-05, "loss": 0.6803, "num_tokens": 42020966.0, "step": 7075 }, { "epoch": 0.07553369677701556, "grad_norm": 1.4863906621265555, "learning_rate": 4.991992664533236e-05, "loss": 0.6124, "num_tokens": 42045530.0, "step": 7080 }, { "epoch": 0.07558703978321402, "grad_norm": 1.3273884150313986, "learning_rate": 4.991959174037245e-05, "loss": 0.6362, "num_tokens": 42079793.0, "step": 7085 }, { "epoch": 0.07564038278941249, "grad_norm": 1.3829659834827608, "learning_rate": 4.99192561377609e-05, "loss": 0.6902, "num_tokens": 42115504.0, "step": 7090 }, { "epoch": 0.07569372579561094, "grad_norm": 2.88388571834704, "learning_rate": 4.991891983750814e-05, "loss": 0.6833, "num_tokens": 42141573.0, "step": 7095 }, { "epoch": 0.0757470688018094, "grad_norm": 1.2955195018705072, "learning_rate": 4.991858283962465e-05, "loss": 0.6623, "num_tokens": 42175305.0, "step": 7100 }, { "epoch": 0.07580041180800785, "grad_norm": 1.2546501727144705, "learning_rate": 4.991824514412092e-05, "loss": 0.7034, "num_tokens": 42217110.0, "step": 7105 }, { "epoch": 0.07585375481420631, "grad_norm": 1.275397500853055, "learning_rate": 4.991790675100744e-05, "loss": 0.5872, "num_tokens": 42239885.0, "step": 7110 }, { "epoch": 0.07590709782040476, "grad_norm": 3.244002178029237, "learning_rate": 4.991756766029475e-05, "loss": 0.6819, "num_tokens": 42256901.0, "step": 7115 }, { "epoch": 0.07596044082660322, "grad_norm": 2.21602640120175, "learning_rate": 4.9917227871993407e-05, "loss": 0.6337, "num_tokens": 42279795.0, "step": 7120 }, { "epoch": 0.07601378383280168, "grad_norm": 1.1778974439042897, "learning_rate": 4.9916887386113966e-05, "loss": 0.6291, "num_tokens": 42291130.0, "step": 7125 }, { "epoch": 0.07606712683900013, "grad_norm": 1.0728509960145638, "learning_rate": 4.991654620266705e-05, "loss": 0.734, "num_tokens": 42332006.0, "step": 7130 }, { "epoch": 0.0761204698451986, "grad_norm": 1.694377390356285, "learning_rate": 4.9916204321663255e-05, "loss": 0.6297, "num_tokens": 42357183.0, "step": 7135 }, { "epoch": 0.07617381285139706, "grad_norm": 1.0017623061992755, "learning_rate": 4.991586174311322e-05, "loss": 0.5664, "num_tokens": 42387163.0, "step": 7140 }, { "epoch": 0.07622715585759551, "grad_norm": 1.8130538248998, "learning_rate": 4.991551846702762e-05, "loss": 0.6078, "num_tokens": 42406875.0, "step": 7145 }, { "epoch": 0.07628049886379397, "grad_norm": 1.5133090704099283, "learning_rate": 4.9915174493417124e-05, "loss": 0.623, "num_tokens": 42436905.0, "step": 7150 }, { "epoch": 0.07633384186999242, "grad_norm": 1.3484145710516824, "learning_rate": 4.991482982229244e-05, "loss": 0.6988, "num_tokens": 42471441.0, "step": 7155 }, { "epoch": 0.07638718487619088, "grad_norm": 1.1791516611201072, "learning_rate": 4.9914484453664295e-05, "loss": 0.6902, "num_tokens": 42494648.0, "step": 7160 }, { "epoch": 0.07644052788238934, "grad_norm": 1.4498279548441426, "learning_rate": 4.991413838754343e-05, "loss": 0.6687, "num_tokens": 42535896.0, "step": 7165 }, { "epoch": 0.07649387088858779, "grad_norm": 1.3573721580171338, "learning_rate": 4.991379162394062e-05, "loss": 0.5843, "num_tokens": 42555162.0, "step": 7170 }, { "epoch": 0.07654721389478625, "grad_norm": 1.656727125221313, "learning_rate": 4.991344416286666e-05, "loss": 0.7154, "num_tokens": 42587068.0, "step": 7175 }, { "epoch": 0.07660055690098472, "grad_norm": 1.3926042216944212, "learning_rate": 4.991309600433234e-05, "loss": 0.5778, "num_tokens": 42618547.0, "step": 7180 }, { "epoch": 0.07665389990718317, "grad_norm": 1.9340115369873536, "learning_rate": 4.9912747148348526e-05, "loss": 0.8281, "num_tokens": 42651577.0, "step": 7185 }, { "epoch": 0.07670724291338163, "grad_norm": 1.2381950909819608, "learning_rate": 4.991239759492606e-05, "loss": 0.5549, "num_tokens": 42674146.0, "step": 7190 }, { "epoch": 0.07676058591958008, "grad_norm": 1.232660046337011, "learning_rate": 4.991204734407581e-05, "loss": 0.7749, "num_tokens": 42716509.0, "step": 7195 }, { "epoch": 0.07681392892577854, "grad_norm": 1.2504599746712464, "learning_rate": 4.991169639580868e-05, "loss": 0.5969, "num_tokens": 42737662.0, "step": 7200 }, { "epoch": 0.076867271931977, "grad_norm": 3.4657860530065494, "learning_rate": 4.9911344750135595e-05, "loss": 0.6185, "num_tokens": 42756597.0, "step": 7205 }, { "epoch": 0.07692061493817545, "grad_norm": 2.320778839587859, "learning_rate": 4.9910992407067495e-05, "loss": 0.5313, "num_tokens": 42773917.0, "step": 7210 }, { "epoch": 0.07697395794437391, "grad_norm": 2.0807303650888285, "learning_rate": 4.9910639366615344e-05, "loss": 0.6563, "num_tokens": 42791588.0, "step": 7215 }, { "epoch": 0.07702730095057236, "grad_norm": 1.4973633160780913, "learning_rate": 4.991028562879013e-05, "loss": 0.8333, "num_tokens": 42832741.0, "step": 7220 }, { "epoch": 0.07708064395677083, "grad_norm": 2.2526663662794415, "learning_rate": 4.990993119360286e-05, "loss": 0.784, "num_tokens": 42857767.0, "step": 7225 }, { "epoch": 0.07713398696296929, "grad_norm": 1.3476253520706338, "learning_rate": 4.9909576061064565e-05, "loss": 0.6969, "num_tokens": 42886955.0, "step": 7230 }, { "epoch": 0.07718732996916775, "grad_norm": 1.91544905165747, "learning_rate": 4.9909220231186294e-05, "loss": 0.8567, "num_tokens": 42910385.0, "step": 7235 }, { "epoch": 0.0772406729753662, "grad_norm": 1.9037115535496454, "learning_rate": 4.9908863703979116e-05, "loss": 0.7465, "num_tokens": 42944463.0, "step": 7240 }, { "epoch": 0.07729401598156466, "grad_norm": 2.0332494621907458, "learning_rate": 4.990850647945413e-05, "loss": 0.727, "num_tokens": 42980344.0, "step": 7245 }, { "epoch": 0.07734735898776311, "grad_norm": 1.8122611406488802, "learning_rate": 4.990814855762245e-05, "loss": 0.6811, "num_tokens": 43016800.0, "step": 7250 }, { "epoch": 0.07740070199396157, "grad_norm": 1.5110887373400856, "learning_rate": 4.990778993849522e-05, "loss": 0.6163, "num_tokens": 43034358.0, "step": 7255 }, { "epoch": 0.07745404500016002, "grad_norm": 1.3051650886803345, "learning_rate": 4.9907430622083586e-05, "loss": 0.6247, "num_tokens": 43057715.0, "step": 7260 }, { "epoch": 0.07750738800635848, "grad_norm": 1.3366960600442621, "learning_rate": 4.990707060839874e-05, "loss": 0.6601, "num_tokens": 43094035.0, "step": 7265 }, { "epoch": 0.07756073101255695, "grad_norm": 1.2697127306788976, "learning_rate": 4.990670989745188e-05, "loss": 0.5668, "num_tokens": 43133943.0, "step": 7270 }, { "epoch": 0.0776140740187554, "grad_norm": 1.9695645423617918, "learning_rate": 4.990634848925424e-05, "loss": 0.6455, "num_tokens": 43168989.0, "step": 7275 }, { "epoch": 0.07766741702495386, "grad_norm": 2.017499890982201, "learning_rate": 4.990598638381705e-05, "loss": 0.7168, "num_tokens": 43200466.0, "step": 7280 }, { "epoch": 0.07772076003115232, "grad_norm": 2.587575421652722, "learning_rate": 4.990562358115159e-05, "loss": 0.721, "num_tokens": 43226377.0, "step": 7285 }, { "epoch": 0.07777410303735077, "grad_norm": 1.909145815051451, "learning_rate": 4.990526008126915e-05, "loss": 0.5939, "num_tokens": 43249445.0, "step": 7290 }, { "epoch": 0.07782744604354923, "grad_norm": 1.2211511345165909, "learning_rate": 4.990489588418104e-05, "loss": 0.6874, "num_tokens": 43279600.0, "step": 7295 }, { "epoch": 0.07788078904974768, "grad_norm": 1.8944440150394297, "learning_rate": 4.9904530989898584e-05, "loss": 0.5392, "num_tokens": 43307403.0, "step": 7300 }, { "epoch": 0.07793413205594614, "grad_norm": 1.4724290596279677, "learning_rate": 4.9904165398433145e-05, "loss": 0.567, "num_tokens": 43331136.0, "step": 7305 }, { "epoch": 0.0779874750621446, "grad_norm": 1.1092757861138294, "learning_rate": 4.9903799109796096e-05, "loss": 0.7832, "num_tokens": 43357551.0, "step": 7310 }, { "epoch": 0.07804081806834307, "grad_norm": 1.8558521868678914, "learning_rate": 4.990343212399884e-05, "loss": 0.6627, "num_tokens": 43398547.0, "step": 7315 }, { "epoch": 0.07809416107454152, "grad_norm": 1.245945062463828, "learning_rate": 4.99030644410528e-05, "loss": 0.7086, "num_tokens": 43420456.0, "step": 7320 }, { "epoch": 0.07814750408073998, "grad_norm": 1.8298395618422112, "learning_rate": 4.99026960609694e-05, "loss": 0.7108, "num_tokens": 43459617.0, "step": 7325 }, { "epoch": 0.07820084708693843, "grad_norm": 1.248636648106453, "learning_rate": 4.990232698376013e-05, "loss": 0.6397, "num_tokens": 43488625.0, "step": 7330 }, { "epoch": 0.07825419009313689, "grad_norm": 1.0163521372100592, "learning_rate": 4.9901957209436445e-05, "loss": 0.81, "num_tokens": 43526801.0, "step": 7335 }, { "epoch": 0.07830753309933534, "grad_norm": 1.561936305849827, "learning_rate": 4.990158673800988e-05, "loss": 0.5871, "num_tokens": 43549212.0, "step": 7340 }, { "epoch": 0.0783608761055338, "grad_norm": 1.2645321544588968, "learning_rate": 4.990121556949194e-05, "loss": 0.631, "num_tokens": 43578973.0, "step": 7345 }, { "epoch": 0.07841421911173226, "grad_norm": 1.5900218694581927, "learning_rate": 4.9900843703894184e-05, "loss": 0.601, "num_tokens": 43599157.0, "step": 7350 }, { "epoch": 0.07846756211793071, "grad_norm": 1.9544343836999618, "learning_rate": 4.99004711412282e-05, "loss": 0.8564, "num_tokens": 43637388.0, "step": 7355 }, { "epoch": 0.07852090512412918, "grad_norm": 1.8718071019197953, "learning_rate": 4.990009788150555e-05, "loss": 0.9455, "num_tokens": 43675049.0, "step": 7360 }, { "epoch": 0.07857424813032764, "grad_norm": 3.817601916275685, "learning_rate": 4.989972392473787e-05, "loss": 0.7267, "num_tokens": 43707026.0, "step": 7365 }, { "epoch": 0.07862759113652609, "grad_norm": 1.5059094924025171, "learning_rate": 4.989934927093679e-05, "loss": 0.5989, "num_tokens": 43728786.0, "step": 7370 }, { "epoch": 0.07868093414272455, "grad_norm": 1.3267147687878469, "learning_rate": 4.9898973920113965e-05, "loss": 0.6917, "num_tokens": 43763021.0, "step": 7375 }, { "epoch": 0.078734277148923, "grad_norm": 2.6282108905670394, "learning_rate": 4.98985978722811e-05, "loss": 0.6416, "num_tokens": 43783360.0, "step": 7380 }, { "epoch": 0.07878762015512146, "grad_norm": 1.2485412450769529, "learning_rate": 4.9898221127449856e-05, "loss": 0.7608, "num_tokens": 43817535.0, "step": 7385 }, { "epoch": 0.07884096316131992, "grad_norm": 2.4827395840274042, "learning_rate": 4.989784368563199e-05, "loss": 0.7145, "num_tokens": 43846146.0, "step": 7390 }, { "epoch": 0.07889430616751837, "grad_norm": 1.9093467862053441, "learning_rate": 4.989746554683923e-05, "loss": 0.5816, "num_tokens": 43864878.0, "step": 7395 }, { "epoch": 0.07894764917371683, "grad_norm": 1.1151102815869964, "learning_rate": 4.9897086711083355e-05, "loss": 0.6818, "num_tokens": 43894419.0, "step": 7400 }, { "epoch": 0.0790009921799153, "grad_norm": 2.0493985227875866, "learning_rate": 4.989670717837614e-05, "loss": 0.7884, "num_tokens": 43910095.0, "step": 7405 }, { "epoch": 0.07905433518611375, "grad_norm": 1.8112833016367553, "learning_rate": 4.98963269487294e-05, "loss": 0.7766, "num_tokens": 43939237.0, "step": 7410 }, { "epoch": 0.07910767819231221, "grad_norm": 1.358911551562949, "learning_rate": 4.9895946022154964e-05, "loss": 0.5923, "num_tokens": 43970514.0, "step": 7415 }, { "epoch": 0.07916102119851066, "grad_norm": 2.4418791192360563, "learning_rate": 4.98955643986647e-05, "loss": 0.716, "num_tokens": 43995940.0, "step": 7420 }, { "epoch": 0.07921436420470912, "grad_norm": 1.782323941036777, "learning_rate": 4.989518207827047e-05, "loss": 0.6267, "num_tokens": 44015321.0, "step": 7425 }, { "epoch": 0.07926770721090758, "grad_norm": 1.2007892465414616, "learning_rate": 4.989479906098418e-05, "loss": 0.8492, "num_tokens": 44065247.0, "step": 7430 }, { "epoch": 0.07932105021710603, "grad_norm": 1.2655613575092017, "learning_rate": 4.9894415346817744e-05, "loss": 0.7203, "num_tokens": 44094598.0, "step": 7435 }, { "epoch": 0.07937439322330449, "grad_norm": 1.0751578045658003, "learning_rate": 4.989403093578309e-05, "loss": 0.6875, "num_tokens": 44122925.0, "step": 7440 }, { "epoch": 0.07942773622950294, "grad_norm": 0.9882922030001933, "learning_rate": 4.989364582789221e-05, "loss": 0.6859, "num_tokens": 44154569.0, "step": 7445 }, { "epoch": 0.07948107923570141, "grad_norm": 0.9751629481048979, "learning_rate": 4.989326002315706e-05, "loss": 0.6337, "num_tokens": 44200623.0, "step": 7450 }, { "epoch": 0.07953442224189987, "grad_norm": 1.0691708242034925, "learning_rate": 4.9892873521589646e-05, "loss": 0.6654, "num_tokens": 44227580.0, "step": 7455 }, { "epoch": 0.07958776524809832, "grad_norm": 1.1944949344932188, "learning_rate": 4.9892486323202015e-05, "loss": 0.7093, "num_tokens": 44251536.0, "step": 7460 }, { "epoch": 0.07964110825429678, "grad_norm": 1.044219825557242, "learning_rate": 4.98920984280062e-05, "loss": 0.6178, "num_tokens": 44291062.0, "step": 7465 }, { "epoch": 0.07969445126049524, "grad_norm": 1.170122003810522, "learning_rate": 4.9891709836014275e-05, "loss": 0.6741, "num_tokens": 44311252.0, "step": 7470 }, { "epoch": 0.07974779426669369, "grad_norm": 1.0826695056780962, "learning_rate": 4.9891320547238344e-05, "loss": 0.5372, "num_tokens": 44348633.0, "step": 7475 }, { "epoch": 0.07980113727289215, "grad_norm": 1.0507242459477355, "learning_rate": 4.989093056169051e-05, "loss": 0.7271, "num_tokens": 44378344.0, "step": 7480 }, { "epoch": 0.0798544802790906, "grad_norm": 1.1448230712941998, "learning_rate": 4.9890539879382904e-05, "loss": 0.6074, "num_tokens": 44411214.0, "step": 7485 }, { "epoch": 0.07990782328528906, "grad_norm": 1.3064167859255587, "learning_rate": 4.989014850032769e-05, "loss": 0.8716, "num_tokens": 44445314.0, "step": 7490 }, { "epoch": 0.07996116629148753, "grad_norm": 1.733826855873953, "learning_rate": 4.988975642453704e-05, "loss": 0.6482, "num_tokens": 44475970.0, "step": 7495 }, { "epoch": 0.08001450929768598, "grad_norm": 1.3895840989530974, "learning_rate": 4.9889363652023156e-05, "loss": 0.634, "num_tokens": 44503106.0, "step": 7500 }, { "epoch": 0.08006785230388444, "grad_norm": 1.1341535249572168, "learning_rate": 4.9888970182798276e-05, "loss": 0.6016, "num_tokens": 44522771.0, "step": 7505 }, { "epoch": 0.0801211953100829, "grad_norm": 0.8983255452530158, "learning_rate": 4.988857601687463e-05, "loss": 0.6367, "num_tokens": 44560495.0, "step": 7510 }, { "epoch": 0.08017453831628135, "grad_norm": 1.9404590091011498, "learning_rate": 4.988818115426448e-05, "loss": 0.5755, "num_tokens": 44580724.0, "step": 7515 }, { "epoch": 0.08022788132247981, "grad_norm": 1.6875700782797667, "learning_rate": 4.9887785594980126e-05, "loss": 0.6751, "num_tokens": 44601987.0, "step": 7520 }, { "epoch": 0.08028122432867826, "grad_norm": 2.6962065105058612, "learning_rate": 4.9887389339033864e-05, "loss": 0.7461, "num_tokens": 44634582.0, "step": 7525 }, { "epoch": 0.08033456733487672, "grad_norm": 1.4989028672627926, "learning_rate": 4.988699238643804e-05, "loss": 0.6277, "num_tokens": 44650155.0, "step": 7530 }, { "epoch": 0.08038791034107517, "grad_norm": 1.7702436986539913, "learning_rate": 4.988659473720499e-05, "loss": 0.5369, "num_tokens": 44668792.0, "step": 7535 }, { "epoch": 0.08044125334727364, "grad_norm": 1.750451855401262, "learning_rate": 4.988619639134709e-05, "loss": 0.6849, "num_tokens": 44687320.0, "step": 7540 }, { "epoch": 0.0804945963534721, "grad_norm": 1.4937434184572147, "learning_rate": 4.988579734887675e-05, "loss": 0.6646, "num_tokens": 44716571.0, "step": 7545 }, { "epoch": 0.08054793935967056, "grad_norm": 1.5197075762266743, "learning_rate": 4.9885397609806375e-05, "loss": 0.6734, "num_tokens": 44752109.0, "step": 7550 }, { "epoch": 0.08060128236586901, "grad_norm": 1.1965270521438307, "learning_rate": 4.988499717414841e-05, "loss": 0.6345, "num_tokens": 44805391.0, "step": 7555 }, { "epoch": 0.08065462537206747, "grad_norm": 1.3737376489158037, "learning_rate": 4.9884596041915306e-05, "loss": 0.6665, "num_tokens": 44831883.0, "step": 7560 }, { "epoch": 0.08070796837826592, "grad_norm": 2.924168338871658, "learning_rate": 4.988419421311956e-05, "loss": 0.6795, "num_tokens": 44848679.0, "step": 7565 }, { "epoch": 0.08076131138446438, "grad_norm": 1.258457680538512, "learning_rate": 4.9883791687773664e-05, "loss": 0.5653, "num_tokens": 44881272.0, "step": 7570 }, { "epoch": 0.08081465439066284, "grad_norm": 1.3495929518868899, "learning_rate": 4.988338846589015e-05, "loss": 0.6227, "num_tokens": 44901351.0, "step": 7575 }, { "epoch": 0.08086799739686129, "grad_norm": 1.1797861185631326, "learning_rate": 4.988298454748157e-05, "loss": 0.5876, "num_tokens": 44937822.0, "step": 7580 }, { "epoch": 0.08092134040305976, "grad_norm": 1.8129875971765756, "learning_rate": 4.988257993256048e-05, "loss": 0.5725, "num_tokens": 44961921.0, "step": 7585 }, { "epoch": 0.08097468340925822, "grad_norm": 1.1127133295694125, "learning_rate": 4.9882174621139476e-05, "loss": 0.8272, "num_tokens": 45006167.0, "step": 7590 }, { "epoch": 0.08102802641545667, "grad_norm": 1.871540681046002, "learning_rate": 4.988176861323117e-05, "loss": 0.5332, "num_tokens": 45029805.0, "step": 7595 }, { "epoch": 0.08108136942165513, "grad_norm": 1.6675992942698077, "learning_rate": 4.98813619088482e-05, "loss": 0.7236, "num_tokens": 45053630.0, "step": 7600 }, { "epoch": 0.08113471242785358, "grad_norm": 1.353164618279045, "learning_rate": 4.9880954508003226e-05, "loss": 0.6176, "num_tokens": 45090881.0, "step": 7605 }, { "epoch": 0.08118805543405204, "grad_norm": 1.127245786996865, "learning_rate": 4.988054641070892e-05, "loss": 0.6584, "num_tokens": 45120904.0, "step": 7610 }, { "epoch": 0.0812413984402505, "grad_norm": 1.7795488667865802, "learning_rate": 4.988013761697797e-05, "loss": 0.6339, "num_tokens": 45134977.0, "step": 7615 }, { "epoch": 0.08129474144644895, "grad_norm": 1.6687690266770008, "learning_rate": 4.987972812682312e-05, "loss": 0.7085, "num_tokens": 45168883.0, "step": 7620 }, { "epoch": 0.0813480844526474, "grad_norm": 1.947335151441781, "learning_rate": 4.987931794025709e-05, "loss": 0.6661, "num_tokens": 45192045.0, "step": 7625 }, { "epoch": 0.08140142745884588, "grad_norm": 1.3658397486072047, "learning_rate": 4.987890705729266e-05, "loss": 0.6785, "num_tokens": 45230913.0, "step": 7630 }, { "epoch": 0.08145477046504433, "grad_norm": 1.464126187074167, "learning_rate": 4.98784954779426e-05, "loss": 0.7338, "num_tokens": 45268127.0, "step": 7635 }, { "epoch": 0.08150811347124279, "grad_norm": 3.658656071837917, "learning_rate": 4.9878083202219744e-05, "loss": 0.6726, "num_tokens": 45288307.0, "step": 7640 }, { "epoch": 0.08156145647744124, "grad_norm": 1.6303668241559397, "learning_rate": 4.9877670230136897e-05, "loss": 0.725, "num_tokens": 45328476.0, "step": 7645 }, { "epoch": 0.0816147994836397, "grad_norm": 2.034549977291457, "learning_rate": 4.9877256561706915e-05, "loss": 0.7421, "num_tokens": 45350012.0, "step": 7650 }, { "epoch": 0.08166814248983816, "grad_norm": 1.2255408989716536, "learning_rate": 4.987684219694267e-05, "loss": 0.7872, "num_tokens": 45390357.0, "step": 7655 }, { "epoch": 0.08172148549603661, "grad_norm": 1.8513791028498017, "learning_rate": 4.9876427135857074e-05, "loss": 0.663, "num_tokens": 45414036.0, "step": 7660 }, { "epoch": 0.08177482850223507, "grad_norm": 1.5122327560343765, "learning_rate": 4.987601137846301e-05, "loss": 0.7213, "num_tokens": 45435971.0, "step": 7665 }, { "epoch": 0.08182817150843352, "grad_norm": 2.679945820177737, "learning_rate": 4.987559492477345e-05, "loss": 0.6455, "num_tokens": 45465524.0, "step": 7670 }, { "epoch": 0.08188151451463199, "grad_norm": 2.514239436193818, "learning_rate": 4.987517777480132e-05, "loss": 0.7828, "num_tokens": 45502971.0, "step": 7675 }, { "epoch": 0.08193485752083045, "grad_norm": 1.9121379342606135, "learning_rate": 4.9874759928559625e-05, "loss": 0.6749, "num_tokens": 45543403.0, "step": 7680 }, { "epoch": 0.0819882005270289, "grad_norm": 1.1411008248042034, "learning_rate": 4.987434138606137e-05, "loss": 0.7627, "num_tokens": 45568820.0, "step": 7685 }, { "epoch": 0.08204154353322736, "grad_norm": 2.0148374257424466, "learning_rate": 4.987392214731955e-05, "loss": 0.7785, "num_tokens": 45580943.0, "step": 7690 }, { "epoch": 0.08209488653942582, "grad_norm": 1.917054132234344, "learning_rate": 4.987350221234725e-05, "loss": 0.6867, "num_tokens": 45604592.0, "step": 7695 }, { "epoch": 0.08214822954562427, "grad_norm": 1.0379166009374736, "learning_rate": 4.987308158115751e-05, "loss": 0.6957, "num_tokens": 45641933.0, "step": 7700 }, { "epoch": 0.08220157255182273, "grad_norm": 1.2361855808786235, "learning_rate": 4.987266025376341e-05, "loss": 0.7182, "num_tokens": 45683890.0, "step": 7705 }, { "epoch": 0.08225491555802118, "grad_norm": 1.7356814337906368, "learning_rate": 4.98722382301781e-05, "loss": 0.7436, "num_tokens": 45727017.0, "step": 7710 }, { "epoch": 0.08230825856421964, "grad_norm": 1.6063696141332489, "learning_rate": 4.987181551041468e-05, "loss": 0.7129, "num_tokens": 45742065.0, "step": 7715 }, { "epoch": 0.08236160157041811, "grad_norm": 1.5798774581559671, "learning_rate": 4.987139209448632e-05, "loss": 0.8139, "num_tokens": 45764596.0, "step": 7720 }, { "epoch": 0.08241494457661656, "grad_norm": 1.5467580745869132, "learning_rate": 4.9870967982406194e-05, "loss": 0.7778, "num_tokens": 45787028.0, "step": 7725 }, { "epoch": 0.08246828758281502, "grad_norm": 1.4444677440606937, "learning_rate": 4.987054317418748e-05, "loss": 0.6976, "num_tokens": 45803732.0, "step": 7730 }, { "epoch": 0.08252163058901348, "grad_norm": 1.1909056530114182, "learning_rate": 4.987011766984343e-05, "loss": 0.6706, "num_tokens": 45832287.0, "step": 7735 }, { "epoch": 0.08257497359521193, "grad_norm": 1.3455991253600919, "learning_rate": 4.9869691469387255e-05, "loss": 0.6556, "num_tokens": 45863012.0, "step": 7740 }, { "epoch": 0.08262831660141039, "grad_norm": 1.3191999638933511, "learning_rate": 4.9869264572832236e-05, "loss": 0.633, "num_tokens": 45885242.0, "step": 7745 }, { "epoch": 0.08268165960760884, "grad_norm": 0.9345492054253656, "learning_rate": 4.986883698019165e-05, "loss": 0.5828, "num_tokens": 45910921.0, "step": 7750 }, { "epoch": 0.0827350026138073, "grad_norm": 1.11567420350806, "learning_rate": 4.98684086914788e-05, "loss": 0.7255, "num_tokens": 45941302.0, "step": 7755 }, { "epoch": 0.08278834562000575, "grad_norm": 1.1831330219063103, "learning_rate": 4.986797970670702e-05, "loss": 0.7905, "num_tokens": 45978851.0, "step": 7760 }, { "epoch": 0.08284168862620422, "grad_norm": 1.2443426162216693, "learning_rate": 4.986755002588966e-05, "loss": 0.6188, "num_tokens": 46002627.0, "step": 7765 }, { "epoch": 0.08289503163240268, "grad_norm": 1.4679606246729116, "learning_rate": 4.986711964904008e-05, "loss": 0.5847, "num_tokens": 46038246.0, "step": 7770 }, { "epoch": 0.08294837463860114, "grad_norm": 1.3760648276836085, "learning_rate": 4.986668857617169e-05, "loss": 0.6769, "num_tokens": 46064635.0, "step": 7775 }, { "epoch": 0.08300171764479959, "grad_norm": 1.5895448278032545, "learning_rate": 4.9866256807297887e-05, "loss": 0.5909, "num_tokens": 46079898.0, "step": 7780 }, { "epoch": 0.08305506065099805, "grad_norm": 1.1181219127802349, "learning_rate": 4.986582434243212e-05, "loss": 0.8068, "num_tokens": 46110469.0, "step": 7785 }, { "epoch": 0.0831084036571965, "grad_norm": 2.3083934668977806, "learning_rate": 4.986539118158784e-05, "loss": 0.8028, "num_tokens": 46127551.0, "step": 7790 }, { "epoch": 0.08316174666339496, "grad_norm": 1.0541971665730432, "learning_rate": 4.986495732477852e-05, "loss": 0.5689, "num_tokens": 46166598.0, "step": 7795 }, { "epoch": 0.08321508966959341, "grad_norm": 1.5218023433149328, "learning_rate": 4.986452277201767e-05, "loss": 0.682, "num_tokens": 46198409.0, "step": 7800 }, { "epoch": 0.08326843267579187, "grad_norm": 1.2686961784794815, "learning_rate": 4.986408752331881e-05, "loss": 0.6752, "num_tokens": 46220463.0, "step": 7805 }, { "epoch": 0.08332177568199034, "grad_norm": 2.5793310128292513, "learning_rate": 4.986365157869548e-05, "loss": 0.665, "num_tokens": 46247990.0, "step": 7810 }, { "epoch": 0.0833751186881888, "grad_norm": 1.2735093635829189, "learning_rate": 4.986321493816125e-05, "loss": 0.7519, "num_tokens": 46274299.0, "step": 7815 }, { "epoch": 0.08342846169438725, "grad_norm": 1.1820401994514738, "learning_rate": 4.986277760172971e-05, "loss": 0.6824, "num_tokens": 46305702.0, "step": 7820 }, { "epoch": 0.08348180470058571, "grad_norm": 1.8730230765779485, "learning_rate": 4.986233956941446e-05, "loss": 1.0181, "num_tokens": 46345616.0, "step": 7825 }, { "epoch": 0.08353514770678416, "grad_norm": 1.3076174056573897, "learning_rate": 4.986190084122914e-05, "loss": 0.6325, "num_tokens": 46384152.0, "step": 7830 }, { "epoch": 0.08358849071298262, "grad_norm": 2.1496647119120955, "learning_rate": 4.98614614171874e-05, "loss": 0.5517, "num_tokens": 46403254.0, "step": 7835 }, { "epoch": 0.08364183371918107, "grad_norm": 1.8405796797755747, "learning_rate": 4.986102129730291e-05, "loss": 0.6263, "num_tokens": 46425608.0, "step": 7840 }, { "epoch": 0.08369517672537953, "grad_norm": 1.4704173153170503, "learning_rate": 4.986058048158937e-05, "loss": 0.6878, "num_tokens": 46453054.0, "step": 7845 }, { "epoch": 0.08374851973157799, "grad_norm": 1.6260448026114829, "learning_rate": 4.9860138970060496e-05, "loss": 0.5747, "num_tokens": 46483143.0, "step": 7850 }, { "epoch": 0.08380186273777646, "grad_norm": 1.384296252399204, "learning_rate": 4.985969676273002e-05, "loss": 0.5439, "num_tokens": 46512148.0, "step": 7855 }, { "epoch": 0.08385520574397491, "grad_norm": 2.064063894098198, "learning_rate": 4.9859253859611715e-05, "loss": 0.79, "num_tokens": 46543441.0, "step": 7860 }, { "epoch": 0.08390854875017337, "grad_norm": 1.2304657358635336, "learning_rate": 4.9858810260719355e-05, "loss": 0.6412, "num_tokens": 46575138.0, "step": 7865 }, { "epoch": 0.08396189175637182, "grad_norm": 1.4100551203523177, "learning_rate": 4.9858365966066746e-05, "loss": 0.6963, "num_tokens": 46608547.0, "step": 7870 }, { "epoch": 0.08401523476257028, "grad_norm": 1.223244506640257, "learning_rate": 4.985792097566772e-05, "loss": 0.6694, "num_tokens": 46641759.0, "step": 7875 }, { "epoch": 0.08406857776876873, "grad_norm": 1.502563605428815, "learning_rate": 4.98574752895361e-05, "loss": 0.5834, "num_tokens": 46673491.0, "step": 7880 }, { "epoch": 0.08412192077496719, "grad_norm": 1.3964709993629416, "learning_rate": 4.985702890768579e-05, "loss": 0.7224, "num_tokens": 46706975.0, "step": 7885 }, { "epoch": 0.08417526378116565, "grad_norm": 1.6208639842228958, "learning_rate": 4.9856581830130657e-05, "loss": 0.5601, "num_tokens": 46722311.0, "step": 7890 }, { "epoch": 0.0842286067873641, "grad_norm": 1.1504108509517712, "learning_rate": 4.9856134056884624e-05, "loss": 0.7289, "num_tokens": 46764379.0, "step": 7895 }, { "epoch": 0.08428194979356257, "grad_norm": 1.5004448135878867, "learning_rate": 4.9855685587961615e-05, "loss": 0.6963, "num_tokens": 46781456.0, "step": 7900 }, { "epoch": 0.08433529279976103, "grad_norm": 1.1523485869391237, "learning_rate": 4.985523642337559e-05, "loss": 0.7177, "num_tokens": 46826063.0, "step": 7905 }, { "epoch": 0.08438863580595948, "grad_norm": 1.371665999153903, "learning_rate": 4.985478656314053e-05, "loss": 0.6585, "num_tokens": 46870589.0, "step": 7910 }, { "epoch": 0.08444197881215794, "grad_norm": 1.09312644050829, "learning_rate": 4.985433600727042e-05, "loss": 0.6392, "num_tokens": 46904790.0, "step": 7915 }, { "epoch": 0.0844953218183564, "grad_norm": 1.6640809689895981, "learning_rate": 4.98538847557793e-05, "loss": 0.647, "num_tokens": 46939676.0, "step": 7920 }, { "epoch": 0.08454866482455485, "grad_norm": 1.2057883854048228, "learning_rate": 4.985343280868121e-05, "loss": 0.6304, "num_tokens": 46991320.0, "step": 7925 }, { "epoch": 0.0846020078307533, "grad_norm": 1.124293840893182, "learning_rate": 4.9852980165990184e-05, "loss": 0.6688, "num_tokens": 47028654.0, "step": 7930 }, { "epoch": 0.08465535083695176, "grad_norm": 2.7521217463749297, "learning_rate": 4.985252682772035e-05, "loss": 0.6173, "num_tokens": 47050502.0, "step": 7935 }, { "epoch": 0.08470869384315022, "grad_norm": 1.3808835973740954, "learning_rate": 4.985207279388578e-05, "loss": 0.8003, "num_tokens": 47082303.0, "step": 7940 }, { "epoch": 0.08476203684934869, "grad_norm": 1.6103528703887726, "learning_rate": 4.985161806450063e-05, "loss": 0.6961, "num_tokens": 47116944.0, "step": 7945 }, { "epoch": 0.08481537985554714, "grad_norm": 1.1398019536442159, "learning_rate": 4.985116263957903e-05, "loss": 0.6292, "num_tokens": 47142568.0, "step": 7950 }, { "epoch": 0.0848687228617456, "grad_norm": 0.8830304602295748, "learning_rate": 4.985070651913515e-05, "loss": 0.6422, "num_tokens": 47184954.0, "step": 7955 }, { "epoch": 0.08492206586794405, "grad_norm": 0.9869098652143204, "learning_rate": 4.985024970318321e-05, "loss": 0.6857, "num_tokens": 47218683.0, "step": 7960 }, { "epoch": 0.08497540887414251, "grad_norm": 0.9547462166002811, "learning_rate": 4.9849792191737397e-05, "loss": 0.7422, "num_tokens": 47257327.0, "step": 7965 }, { "epoch": 0.08502875188034097, "grad_norm": 2.022096901791965, "learning_rate": 4.984933398481197e-05, "loss": 0.8059, "num_tokens": 47282173.0, "step": 7970 }, { "epoch": 0.08508209488653942, "grad_norm": 1.4571250300341476, "learning_rate": 4.9848875082421166e-05, "loss": 0.6796, "num_tokens": 47313716.0, "step": 7975 }, { "epoch": 0.08513543789273788, "grad_norm": 1.6383503341650543, "learning_rate": 4.984841548457928e-05, "loss": 0.6388, "num_tokens": 47346397.0, "step": 7980 }, { "epoch": 0.08518878089893633, "grad_norm": 1.2290817338605131, "learning_rate": 4.984795519130061e-05, "loss": 0.7215, "num_tokens": 47374006.0, "step": 7985 }, { "epoch": 0.0852421239051348, "grad_norm": 1.7470921848305456, "learning_rate": 4.984749420259947e-05, "loss": 0.6357, "num_tokens": 47407764.0, "step": 7990 }, { "epoch": 0.08529546691133326, "grad_norm": 1.710700272237211, "learning_rate": 4.984703251849022e-05, "loss": 0.7903, "num_tokens": 47440515.0, "step": 7995 }, { "epoch": 0.08534880991753171, "grad_norm": 2.537257040758279, "learning_rate": 4.984657013898723e-05, "loss": 0.6957, "num_tokens": 47466657.0, "step": 8000 }, { "epoch": 0.08540215292373017, "grad_norm": 1.2215983474936765, "learning_rate": 4.9846107064104866e-05, "loss": 0.7179, "num_tokens": 47514004.0, "step": 8005 }, { "epoch": 0.08545549592992863, "grad_norm": 1.06762946104004, "learning_rate": 4.984564329385755e-05, "loss": 0.5547, "num_tokens": 47539692.0, "step": 8010 }, { "epoch": 0.08550883893612708, "grad_norm": 1.0287368501804801, "learning_rate": 4.984517882825972e-05, "loss": 0.6823, "num_tokens": 47567525.0, "step": 8015 }, { "epoch": 0.08556218194232554, "grad_norm": 1.3632797528862468, "learning_rate": 4.984471366732582e-05, "loss": 0.5544, "num_tokens": 47599305.0, "step": 8020 }, { "epoch": 0.085615524948524, "grad_norm": 1.2694699771476308, "learning_rate": 4.984424781107032e-05, "loss": 0.6801, "num_tokens": 47628916.0, "step": 8025 }, { "epoch": 0.08566886795472245, "grad_norm": 1.8084298566387214, "learning_rate": 4.9843781259507734e-05, "loss": 0.7939, "num_tokens": 47662417.0, "step": 8030 }, { "epoch": 0.08572221096092092, "grad_norm": 1.3421912509852651, "learning_rate": 4.9843314012652574e-05, "loss": 0.7126, "num_tokens": 47688758.0, "step": 8035 }, { "epoch": 0.08577555396711938, "grad_norm": 2.084785533422158, "learning_rate": 4.984284607051937e-05, "loss": 0.7087, "num_tokens": 47714198.0, "step": 8040 }, { "epoch": 0.08582889697331783, "grad_norm": 1.536266665666096, "learning_rate": 4.9842377433122694e-05, "loss": 0.5817, "num_tokens": 47735058.0, "step": 8045 }, { "epoch": 0.08588223997951629, "grad_norm": 2.3463115288465914, "learning_rate": 4.984190810047711e-05, "loss": 0.8533, "num_tokens": 47760471.0, "step": 8050 }, { "epoch": 0.08593558298571474, "grad_norm": 1.5455090182508782, "learning_rate": 4.984143807259726e-05, "loss": 0.7172, "num_tokens": 47787020.0, "step": 8055 }, { "epoch": 0.0859889259919132, "grad_norm": 1.2110402320469364, "learning_rate": 4.9840967349497736e-05, "loss": 0.8275, "num_tokens": 47827081.0, "step": 8060 }, { "epoch": 0.08604226899811165, "grad_norm": 1.2837497321311229, "learning_rate": 4.984049593119319e-05, "loss": 0.7277, "num_tokens": 47863527.0, "step": 8065 }, { "epoch": 0.08609561200431011, "grad_norm": 0.9261833733197388, "learning_rate": 4.984002381769832e-05, "loss": 0.55, "num_tokens": 47895627.0, "step": 8070 }, { "epoch": 0.08614895501050857, "grad_norm": 1.1881077374419906, "learning_rate": 4.983955100902778e-05, "loss": 0.5028, "num_tokens": 47912058.0, "step": 8075 }, { "epoch": 0.08620229801670704, "grad_norm": 1.8631428518549176, "learning_rate": 4.983907750519631e-05, "loss": 0.6433, "num_tokens": 47942013.0, "step": 8080 }, { "epoch": 0.08625564102290549, "grad_norm": 1.1126702531000419, "learning_rate": 4.983860330621862e-05, "loss": 0.6372, "num_tokens": 47965967.0, "step": 8085 }, { "epoch": 0.08630898402910395, "grad_norm": 1.437592980897619, "learning_rate": 4.983812841210949e-05, "loss": 0.832, "num_tokens": 48002432.0, "step": 8090 }, { "epoch": 0.0863623270353024, "grad_norm": 0.964580481060466, "learning_rate": 4.9837652822883687e-05, "loss": 0.8729, "num_tokens": 48038375.0, "step": 8095 }, { "epoch": 0.08641567004150086, "grad_norm": 2.1031469062127544, "learning_rate": 4.983717653855601e-05, "loss": 0.5603, "num_tokens": 48064546.0, "step": 8100 }, { "epoch": 0.08646901304769931, "grad_norm": 2.1111298086238133, "learning_rate": 4.983669955914128e-05, "loss": 0.6369, "num_tokens": 48084869.0, "step": 8105 }, { "epoch": 0.08652235605389777, "grad_norm": 1.554431192518928, "learning_rate": 4.983622188465434e-05, "loss": 0.6196, "num_tokens": 48106319.0, "step": 8110 }, { "epoch": 0.08657569906009623, "grad_norm": 1.2164073627751508, "learning_rate": 4.983574351511006e-05, "loss": 0.7124, "num_tokens": 48128432.0, "step": 8115 }, { "epoch": 0.08662904206629468, "grad_norm": 1.3959037238883245, "learning_rate": 4.9835264450523315e-05, "loss": 0.6965, "num_tokens": 48160352.0, "step": 8120 }, { "epoch": 0.08668238507249315, "grad_norm": 1.5726718830101465, "learning_rate": 4.983478469090902e-05, "loss": 0.6145, "num_tokens": 48186814.0, "step": 8125 }, { "epoch": 0.0867357280786916, "grad_norm": 2.170118287852767, "learning_rate": 4.9834304236282106e-05, "loss": 0.8294, "num_tokens": 48228536.0, "step": 8130 }, { "epoch": 0.08678907108489006, "grad_norm": 1.0627591587455942, "learning_rate": 4.983382308665751e-05, "loss": 0.6311, "num_tokens": 48258938.0, "step": 8135 }, { "epoch": 0.08684241409108852, "grad_norm": 1.7062542929535414, "learning_rate": 4.9833341242050224e-05, "loss": 0.7768, "num_tokens": 48287315.0, "step": 8140 }, { "epoch": 0.08689575709728697, "grad_norm": 1.2187230044727322, "learning_rate": 4.9832858702475235e-05, "loss": 0.7523, "num_tokens": 48330821.0, "step": 8145 }, { "epoch": 0.08694910010348543, "grad_norm": 1.6592203545267536, "learning_rate": 4.9832375467947545e-05, "loss": 0.6784, "num_tokens": 48371440.0, "step": 8150 }, { "epoch": 0.08700244310968389, "grad_norm": 1.6727451362252939, "learning_rate": 4.983189153848221e-05, "loss": 0.6467, "num_tokens": 48395126.0, "step": 8155 }, { "epoch": 0.08705578611588234, "grad_norm": 1.9175451902597154, "learning_rate": 4.983140691409428e-05, "loss": 0.6545, "num_tokens": 48417309.0, "step": 8160 }, { "epoch": 0.0871091291220808, "grad_norm": 1.4865167516456257, "learning_rate": 4.9830921594798836e-05, "loss": 0.6792, "num_tokens": 48437264.0, "step": 8165 }, { "epoch": 0.08716247212827927, "grad_norm": 1.1601449184992727, "learning_rate": 4.9830435580610984e-05, "loss": 0.6, "num_tokens": 48463063.0, "step": 8170 }, { "epoch": 0.08721581513447772, "grad_norm": 3.266361470194325, "learning_rate": 4.982994887154584e-05, "loss": 0.7672, "num_tokens": 48473100.0, "step": 8175 }, { "epoch": 0.08726915814067618, "grad_norm": 1.5276573576572692, "learning_rate": 4.982946146761856e-05, "loss": 0.6344, "num_tokens": 48507930.0, "step": 8180 }, { "epoch": 0.08732250114687463, "grad_norm": 1.455908844017174, "learning_rate": 4.98289733688443e-05, "loss": 0.7653, "num_tokens": 48552139.0, "step": 8185 }, { "epoch": 0.08737584415307309, "grad_norm": 1.4826312082590745, "learning_rate": 4.982848457523826e-05, "loss": 0.7035, "num_tokens": 48580656.0, "step": 8190 }, { "epoch": 0.08742918715927155, "grad_norm": 1.4346344546378713, "learning_rate": 4.982799508681564e-05, "loss": 0.6159, "num_tokens": 48619908.0, "step": 8195 }, { "epoch": 0.08748253016547, "grad_norm": 1.120589671248142, "learning_rate": 4.982750490359167e-05, "loss": 0.7454, "num_tokens": 48645281.0, "step": 8200 }, { "epoch": 0.08753587317166846, "grad_norm": 2.559268482328458, "learning_rate": 4.9827014025581616e-05, "loss": 0.7557, "num_tokens": 48673551.0, "step": 8205 }, { "epoch": 0.08758921617786691, "grad_norm": 1.180064873562682, "learning_rate": 4.982652245280074e-05, "loss": 0.6502, "num_tokens": 48710500.0, "step": 8210 }, { "epoch": 0.08764255918406538, "grad_norm": 1.2250138912025725, "learning_rate": 4.9826030185264356e-05, "loss": 0.6124, "num_tokens": 48736990.0, "step": 8215 }, { "epoch": 0.08769590219026384, "grad_norm": 1.5371958781099835, "learning_rate": 4.982553722298776e-05, "loss": 0.6157, "num_tokens": 48762792.0, "step": 8220 }, { "epoch": 0.0877492451964623, "grad_norm": 0.8878841035383713, "learning_rate": 4.982504356598631e-05, "loss": 0.6986, "num_tokens": 48797654.0, "step": 8225 }, { "epoch": 0.08780258820266075, "grad_norm": 0.9148552059888514, "learning_rate": 4.9824549214275366e-05, "loss": 0.7276, "num_tokens": 48835448.0, "step": 8230 }, { "epoch": 0.0878559312088592, "grad_norm": 1.7279430826927442, "learning_rate": 4.98240541678703e-05, "loss": 0.7399, "num_tokens": 48865798.0, "step": 8235 }, { "epoch": 0.08790927421505766, "grad_norm": 1.4056976616805734, "learning_rate": 4.982355842678653e-05, "loss": 0.5434, "num_tokens": 48882486.0, "step": 8240 }, { "epoch": 0.08796261722125612, "grad_norm": 1.2858633687706704, "learning_rate": 4.9823061991039466e-05, "loss": 0.6058, "num_tokens": 48902774.0, "step": 8245 }, { "epoch": 0.08801596022745457, "grad_norm": 1.9524526708092491, "learning_rate": 4.9822564860644565e-05, "loss": 0.575, "num_tokens": 48928921.0, "step": 8250 }, { "epoch": 0.08806930323365303, "grad_norm": 1.371339681642693, "learning_rate": 4.9822067035617303e-05, "loss": 0.7841, "num_tokens": 48958023.0, "step": 8255 }, { "epoch": 0.0881226462398515, "grad_norm": 1.174027606311383, "learning_rate": 4.9821568515973166e-05, "loss": 0.6364, "num_tokens": 48993322.0, "step": 8260 }, { "epoch": 0.08817598924604995, "grad_norm": 1.3185102634284598, "learning_rate": 4.982106930172766e-05, "loss": 0.6082, "num_tokens": 49028751.0, "step": 8265 }, { "epoch": 0.08822933225224841, "grad_norm": 1.6709091972684194, "learning_rate": 4.982056939289634e-05, "loss": 0.7372, "num_tokens": 49053822.0, "step": 8270 }, { "epoch": 0.08828267525844687, "grad_norm": 1.0929855818792722, "learning_rate": 4.9820068789494745e-05, "loss": 0.6345, "num_tokens": 49086939.0, "step": 8275 }, { "epoch": 0.08833601826464532, "grad_norm": 2.0322085360844095, "learning_rate": 4.981956749153845e-05, "loss": 0.6482, "num_tokens": 49122795.0, "step": 8280 }, { "epoch": 0.08838936127084378, "grad_norm": 1.6177112318468263, "learning_rate": 4.981906549904306e-05, "loss": 0.6345, "num_tokens": 49147769.0, "step": 8285 }, { "epoch": 0.08844270427704223, "grad_norm": 1.9518134034014345, "learning_rate": 4.9818562812024195e-05, "loss": 0.718, "num_tokens": 49168065.0, "step": 8290 }, { "epoch": 0.08849604728324069, "grad_norm": 1.047306333863157, "learning_rate": 4.981805943049751e-05, "loss": 0.5678, "num_tokens": 49201336.0, "step": 8295 }, { "epoch": 0.08854939028943914, "grad_norm": 2.0731957042014995, "learning_rate": 4.981755535447863e-05, "loss": 0.8929, "num_tokens": 49236953.0, "step": 8300 }, { "epoch": 0.08860273329563761, "grad_norm": 1.3801522229255165, "learning_rate": 4.98170505839833e-05, "loss": 0.686, "num_tokens": 49265401.0, "step": 8305 }, { "epoch": 0.08865607630183607, "grad_norm": 1.4339030749263457, "learning_rate": 4.981654511902719e-05, "loss": 0.7551, "num_tokens": 49302296.0, "step": 8310 }, { "epoch": 0.08870941930803453, "grad_norm": 1.139721370736268, "learning_rate": 4.9816038959626024e-05, "loss": 0.7756, "num_tokens": 49335064.0, "step": 8315 }, { "epoch": 0.08876276231423298, "grad_norm": 1.4101124903323625, "learning_rate": 4.981553210579557e-05, "loss": 0.7839, "num_tokens": 49369486.0, "step": 8320 }, { "epoch": 0.08881610532043144, "grad_norm": 1.3925985702854136, "learning_rate": 4.98150245575516e-05, "loss": 0.7722, "num_tokens": 49409293.0, "step": 8325 }, { "epoch": 0.0888694483266299, "grad_norm": 1.909560457406319, "learning_rate": 4.981451631490989e-05, "loss": 0.8766, "num_tokens": 49443023.0, "step": 8330 }, { "epoch": 0.08892279133282835, "grad_norm": 1.3542938767175363, "learning_rate": 4.9814007377886274e-05, "loss": 0.6994, "num_tokens": 49462456.0, "step": 8335 }, { "epoch": 0.0889761343390268, "grad_norm": 0.9868025949839712, "learning_rate": 4.9813497746496586e-05, "loss": 0.7378, "num_tokens": 49501068.0, "step": 8340 }, { "epoch": 0.08902947734522526, "grad_norm": 0.9280771539776523, "learning_rate": 4.981298742075668e-05, "loss": 0.6439, "num_tokens": 49532231.0, "step": 8345 }, { "epoch": 0.08908282035142373, "grad_norm": 1.9685911795308335, "learning_rate": 4.9812476400682436e-05, "loss": 0.5587, "num_tokens": 49557062.0, "step": 8350 }, { "epoch": 0.08913616335762219, "grad_norm": 1.522654697233462, "learning_rate": 4.9811964686289755e-05, "loss": 0.659, "num_tokens": 49601734.0, "step": 8355 }, { "epoch": 0.08918950636382064, "grad_norm": 1.304241737071284, "learning_rate": 4.981145227759457e-05, "loss": 0.5969, "num_tokens": 49621649.0, "step": 8360 }, { "epoch": 0.0892428493700191, "grad_norm": 3.741671126351809, "learning_rate": 4.9810939174612814e-05, "loss": 0.8649, "num_tokens": 49649784.0, "step": 8365 }, { "epoch": 0.08929619237621755, "grad_norm": 1.451947282571911, "learning_rate": 4.981042537736046e-05, "loss": 0.7762, "num_tokens": 49679976.0, "step": 8370 }, { "epoch": 0.08934953538241601, "grad_norm": 1.1931799477687817, "learning_rate": 4.98099108858535e-05, "loss": 0.7701, "num_tokens": 49707937.0, "step": 8375 }, { "epoch": 0.08940287838861447, "grad_norm": 2.79051888037604, "learning_rate": 4.980939570010793e-05, "loss": 0.725, "num_tokens": 49733663.0, "step": 8380 }, { "epoch": 0.08945622139481292, "grad_norm": 1.6619123304899384, "learning_rate": 4.980887982013979e-05, "loss": 0.7681, "num_tokens": 49758959.0, "step": 8385 }, { "epoch": 0.08950956440101138, "grad_norm": 1.9002456183788177, "learning_rate": 4.980836324596514e-05, "loss": 0.6195, "num_tokens": 49773389.0, "step": 8390 }, { "epoch": 0.08956290740720985, "grad_norm": 2.9754442024393066, "learning_rate": 4.980784597760005e-05, "loss": 0.5816, "num_tokens": 49794075.0, "step": 8395 }, { "epoch": 0.0896162504134083, "grad_norm": 1.3749069160864733, "learning_rate": 4.980732801506061e-05, "loss": 0.8336, "num_tokens": 49823574.0, "step": 8400 }, { "epoch": 0.08966959341960676, "grad_norm": 2.0378440874880708, "learning_rate": 4.980680935836294e-05, "loss": 0.8073, "num_tokens": 49855372.0, "step": 8405 }, { "epoch": 0.08972293642580521, "grad_norm": 1.4407537399550012, "learning_rate": 4.9806290007523195e-05, "loss": 0.5218, "num_tokens": 49879428.0, "step": 8410 }, { "epoch": 0.08977627943200367, "grad_norm": 2.221927856986229, "learning_rate": 4.9805769962557506e-05, "loss": 0.6549, "num_tokens": 49909194.0, "step": 8415 }, { "epoch": 0.08982962243820213, "grad_norm": 1.7123885839067379, "learning_rate": 4.9805249223482084e-05, "loss": 0.5664, "num_tokens": 49945503.0, "step": 8420 }, { "epoch": 0.08988296544440058, "grad_norm": 1.099071112274225, "learning_rate": 4.980472779031312e-05, "loss": 0.5509, "num_tokens": 49973474.0, "step": 8425 }, { "epoch": 0.08993630845059904, "grad_norm": 1.5548570559834607, "learning_rate": 4.9804205663066844e-05, "loss": 0.6317, "num_tokens": 49995213.0, "step": 8430 }, { "epoch": 0.08998965145679749, "grad_norm": 1.3750741589015414, "learning_rate": 4.9803682841759506e-05, "loss": 0.5594, "num_tokens": 50016550.0, "step": 8435 }, { "epoch": 0.09004299446299596, "grad_norm": 2.037072648290612, "learning_rate": 4.9803159326407364e-05, "loss": 0.7892, "num_tokens": 50041478.0, "step": 8440 }, { "epoch": 0.09009633746919442, "grad_norm": 1.3375265617738845, "learning_rate": 4.9802635117026715e-05, "loss": 0.6395, "num_tokens": 50077274.0, "step": 8445 }, { "epoch": 0.09014968047539287, "grad_norm": 1.1644356910056335, "learning_rate": 4.980211021363388e-05, "loss": 0.6392, "num_tokens": 50123400.0, "step": 8450 }, { "epoch": 0.09020302348159133, "grad_norm": 1.462588496705842, "learning_rate": 4.980158461624518e-05, "loss": 0.6888, "num_tokens": 50150636.0, "step": 8455 }, { "epoch": 0.09025636648778979, "grad_norm": 1.5588835315896457, "learning_rate": 4.980105832487698e-05, "loss": 0.7738, "num_tokens": 50173541.0, "step": 8460 }, { "epoch": 0.09030970949398824, "grad_norm": 1.4770226924420373, "learning_rate": 4.980053133954564e-05, "loss": 0.6634, "num_tokens": 50201153.0, "step": 8465 }, { "epoch": 0.0903630525001867, "grad_norm": 1.4959210608134124, "learning_rate": 4.980000366026758e-05, "loss": 0.6953, "num_tokens": 50236780.0, "step": 8470 }, { "epoch": 0.09041639550638515, "grad_norm": 1.3553428265803174, "learning_rate": 4.9799475287059217e-05, "loss": 0.6272, "num_tokens": 50262111.0, "step": 8475 }, { "epoch": 0.09046973851258361, "grad_norm": 1.4093549442565296, "learning_rate": 4.979894621993698e-05, "loss": 0.692, "num_tokens": 50289138.0, "step": 8480 }, { "epoch": 0.09052308151878208, "grad_norm": 1.9571672501472943, "learning_rate": 4.979841645891734e-05, "loss": 0.572, "num_tokens": 50305953.0, "step": 8485 }, { "epoch": 0.09057642452498053, "grad_norm": 1.2802337054586437, "learning_rate": 4.979788600401678e-05, "loss": 0.6154, "num_tokens": 50346704.0, "step": 8490 }, { "epoch": 0.09062976753117899, "grad_norm": 1.280418599265392, "learning_rate": 4.9797354855251816e-05, "loss": 0.5895, "num_tokens": 50387921.0, "step": 8495 }, { "epoch": 0.09068311053737745, "grad_norm": 1.8253347801709594, "learning_rate": 4.9796823012638965e-05, "loss": 0.6726, "num_tokens": 50407673.0, "step": 8500 }, { "epoch": 0.0907364535435759, "grad_norm": 3.314386742296513, "learning_rate": 4.9796290476194776e-05, "loss": 0.6877, "num_tokens": 50431642.0, "step": 8505 }, { "epoch": 0.09078979654977436, "grad_norm": 1.086313771584799, "learning_rate": 4.979575724593584e-05, "loss": 0.5418, "num_tokens": 50456699.0, "step": 8510 }, { "epoch": 0.09084313955597281, "grad_norm": 1.2016247652677925, "learning_rate": 4.979522332187872e-05, "loss": 0.6322, "num_tokens": 50482023.0, "step": 8515 }, { "epoch": 0.09089648256217127, "grad_norm": 1.27931882488248, "learning_rate": 4.979468870404005e-05, "loss": 0.6033, "num_tokens": 50511604.0, "step": 8520 }, { "epoch": 0.09094982556836972, "grad_norm": 1.55184826352094, "learning_rate": 4.9794153392436466e-05, "loss": 0.7008, "num_tokens": 50534036.0, "step": 8525 }, { "epoch": 0.0910031685745682, "grad_norm": 1.4831414528437694, "learning_rate": 4.979361738708462e-05, "loss": 0.5955, "num_tokens": 50558518.0, "step": 8530 }, { "epoch": 0.09105651158076665, "grad_norm": 2.434352089150712, "learning_rate": 4.979308068800119e-05, "loss": 0.5914, "num_tokens": 50581594.0, "step": 8535 }, { "epoch": 0.0911098545869651, "grad_norm": 1.6275396230158146, "learning_rate": 4.979254329520289e-05, "loss": 0.6176, "num_tokens": 50599974.0, "step": 8540 }, { "epoch": 0.09116319759316356, "grad_norm": 2.11061563382851, "learning_rate": 4.979200520870642e-05, "loss": 0.6697, "num_tokens": 50631340.0, "step": 8545 }, { "epoch": 0.09121654059936202, "grad_norm": 0.8860214638868721, "learning_rate": 4.979146642852854e-05, "loss": 0.64, "num_tokens": 50668953.0, "step": 8550 }, { "epoch": 0.09126988360556047, "grad_norm": 1.3369572702453223, "learning_rate": 4.979092695468601e-05, "loss": 0.6701, "num_tokens": 50703011.0, "step": 8555 }, { "epoch": 0.09132322661175893, "grad_norm": 1.8044569147839236, "learning_rate": 4.979038678719564e-05, "loss": 0.6975, "num_tokens": 50721951.0, "step": 8560 }, { "epoch": 0.09137656961795738, "grad_norm": 1.5026951899799932, "learning_rate": 4.97898459260742e-05, "loss": 0.5411, "num_tokens": 50746019.0, "step": 8565 }, { "epoch": 0.09142991262415584, "grad_norm": 1.3373913601601837, "learning_rate": 4.978930437133854e-05, "loss": 0.7802, "num_tokens": 50779400.0, "step": 8570 }, { "epoch": 0.09148325563035431, "grad_norm": 2.2103948542842065, "learning_rate": 4.978876212300552e-05, "loss": 0.7514, "num_tokens": 50794586.0, "step": 8575 }, { "epoch": 0.09153659863655277, "grad_norm": 1.6679114160312256, "learning_rate": 4.9788219181092e-05, "loss": 0.6382, "num_tokens": 50829420.0, "step": 8580 }, { "epoch": 0.09158994164275122, "grad_norm": 1.2015831346427719, "learning_rate": 4.978767554561488e-05, "loss": 0.8225, "num_tokens": 50863752.0, "step": 8585 }, { "epoch": 0.09164328464894968, "grad_norm": 1.4468275917794298, "learning_rate": 4.9787131216591076e-05, "loss": 0.6307, "num_tokens": 50906976.0, "step": 8590 }, { "epoch": 0.09169662765514813, "grad_norm": 1.6967663424323114, "learning_rate": 4.978658619403753e-05, "loss": 0.7338, "num_tokens": 50940921.0, "step": 8595 }, { "epoch": 0.09174997066134659, "grad_norm": 1.1717806924838157, "learning_rate": 4.97860404779712e-05, "loss": 0.7126, "num_tokens": 50985602.0, "step": 8600 }, { "epoch": 0.09180331366754504, "grad_norm": 2.3940253706302563, "learning_rate": 4.978549406840907e-05, "loss": 0.6594, "num_tokens": 51004727.0, "step": 8605 }, { "epoch": 0.0918566566737435, "grad_norm": 1.2434299746287907, "learning_rate": 4.978494696536814e-05, "loss": 0.6697, "num_tokens": 51035134.0, "step": 8610 }, { "epoch": 0.09190999967994196, "grad_norm": 2.0725652850125056, "learning_rate": 4.9784399168865425e-05, "loss": 0.6365, "num_tokens": 51072472.0, "step": 8615 }, { "epoch": 0.09196334268614043, "grad_norm": 1.443533831083976, "learning_rate": 4.9783850678917994e-05, "loss": 0.623, "num_tokens": 51093093.0, "step": 8620 }, { "epoch": 0.09201668569233888, "grad_norm": 1.2519523874454166, "learning_rate": 4.9783301495542895e-05, "loss": 0.6131, "num_tokens": 51122384.0, "step": 8625 }, { "epoch": 0.09207002869853734, "grad_norm": 1.6117067119135384, "learning_rate": 4.978275161875723e-05, "loss": 0.7004, "num_tokens": 51144750.0, "step": 8630 }, { "epoch": 0.0921233717047358, "grad_norm": 2.3538879954738285, "learning_rate": 4.97822010485781e-05, "loss": 0.6792, "num_tokens": 51167955.0, "step": 8635 }, { "epoch": 0.09217671471093425, "grad_norm": 2.0036690557837162, "learning_rate": 4.9781649785022646e-05, "loss": 0.8351, "num_tokens": 51193029.0, "step": 8640 }, { "epoch": 0.0922300577171327, "grad_norm": 0.8775529012875143, "learning_rate": 4.978109782810801e-05, "loss": 0.6301, "num_tokens": 51235857.0, "step": 8645 }, { "epoch": 0.09228340072333116, "grad_norm": 1.2744747143544204, "learning_rate": 4.9780545177851385e-05, "loss": 0.6479, "num_tokens": 51265045.0, "step": 8650 }, { "epoch": 0.09233674372952962, "grad_norm": 2.1492747878009055, "learning_rate": 4.977999183426996e-05, "loss": 0.5733, "num_tokens": 51283288.0, "step": 8655 }, { "epoch": 0.09239008673572807, "grad_norm": 1.9601338831706836, "learning_rate": 4.977943779738095e-05, "loss": 0.7134, "num_tokens": 51315453.0, "step": 8660 }, { "epoch": 0.09244342974192654, "grad_norm": 1.5753271208277497, "learning_rate": 4.9778883067201594e-05, "loss": 0.5636, "num_tokens": 51349053.0, "step": 8665 }, { "epoch": 0.092496772748125, "grad_norm": 6.263022301522349, "learning_rate": 4.9778327643749165e-05, "loss": 0.8552, "num_tokens": 51386250.0, "step": 8670 }, { "epoch": 0.09255011575432345, "grad_norm": 1.5511152822542424, "learning_rate": 4.977777152704094e-05, "loss": 0.698, "num_tokens": 51403978.0, "step": 8675 }, { "epoch": 0.09260345876052191, "grad_norm": 2.760805758636773, "learning_rate": 4.9777214717094224e-05, "loss": 0.7094, "num_tokens": 51421919.0, "step": 8680 }, { "epoch": 0.09265680176672036, "grad_norm": 1.3905438598743611, "learning_rate": 4.977665721392634e-05, "loss": 0.6861, "num_tokens": 51444640.0, "step": 8685 }, { "epoch": 0.09271014477291882, "grad_norm": 2.9083374338495083, "learning_rate": 4.977609901755465e-05, "loss": 0.6459, "num_tokens": 51462009.0, "step": 8690 }, { "epoch": 0.09276348777911728, "grad_norm": 1.054985333416072, "learning_rate": 4.977554012799652e-05, "loss": 0.6569, "num_tokens": 51509998.0, "step": 8695 }, { "epoch": 0.09281683078531573, "grad_norm": 0.9532871495141206, "learning_rate": 4.9774980545269324e-05, "loss": 0.8016, "num_tokens": 51572478.0, "step": 8700 }, { "epoch": 0.09287017379151419, "grad_norm": 1.550700426473008, "learning_rate": 4.9774420269390484e-05, "loss": 0.6735, "num_tokens": 51594579.0, "step": 8705 }, { "epoch": 0.09292351679771266, "grad_norm": 1.1672731674930668, "learning_rate": 4.9773859300377455e-05, "loss": 0.6407, "num_tokens": 51630243.0, "step": 8710 }, { "epoch": 0.09297685980391111, "grad_norm": 1.5166186208083248, "learning_rate": 4.9773297638247666e-05, "loss": 0.7318, "num_tokens": 51656078.0, "step": 8715 }, { "epoch": 0.09303020281010957, "grad_norm": 2.2165843190565315, "learning_rate": 4.9772735283018605e-05, "loss": 0.6074, "num_tokens": 51676036.0, "step": 8720 }, { "epoch": 0.09308354581630802, "grad_norm": 1.502150848621013, "learning_rate": 4.9772172234707776e-05, "loss": 0.6834, "num_tokens": 51703446.0, "step": 8725 }, { "epoch": 0.09313688882250648, "grad_norm": 1.4098479618545412, "learning_rate": 4.9771608493332695e-05, "loss": 0.6677, "num_tokens": 51722628.0, "step": 8730 }, { "epoch": 0.09319023182870494, "grad_norm": 0.9329582075302006, "learning_rate": 4.97710440589109e-05, "loss": 0.6519, "num_tokens": 51785199.0, "step": 8735 }, { "epoch": 0.09324357483490339, "grad_norm": 1.601268913335033, "learning_rate": 4.977047893145996e-05, "loss": 0.704, "num_tokens": 51810713.0, "step": 8740 }, { "epoch": 0.09329691784110185, "grad_norm": 1.4409688989831564, "learning_rate": 4.976991311099746e-05, "loss": 0.6427, "num_tokens": 51833000.0, "step": 8745 }, { "epoch": 0.0933502608473003, "grad_norm": 1.2032869438179086, "learning_rate": 4.9769346597541016e-05, "loss": 0.5702, "num_tokens": 51871558.0, "step": 8750 }, { "epoch": 0.09340360385349877, "grad_norm": 1.0884315380648704, "learning_rate": 4.976877939110825e-05, "loss": 0.6244, "num_tokens": 51901039.0, "step": 8755 }, { "epoch": 0.09345694685969723, "grad_norm": 1.3059197125977144, "learning_rate": 4.9768211491716794e-05, "loss": 0.6891, "num_tokens": 51935541.0, "step": 8760 }, { "epoch": 0.09351028986589568, "grad_norm": 1.2766921176987216, "learning_rate": 4.976764289938435e-05, "loss": 0.7025, "num_tokens": 51957691.0, "step": 8765 }, { "epoch": 0.09356363287209414, "grad_norm": 1.7526137136166628, "learning_rate": 4.9767073614128587e-05, "loss": 0.481, "num_tokens": 51972393.0, "step": 8770 }, { "epoch": 0.0936169758782926, "grad_norm": 1.4448731720067898, "learning_rate": 4.9766503635967245e-05, "loss": 0.6058, "num_tokens": 51994221.0, "step": 8775 }, { "epoch": 0.09367031888449105, "grad_norm": 2.408456662089478, "learning_rate": 4.9765932964918044e-05, "loss": 0.9062, "num_tokens": 52019208.0, "step": 8780 }, { "epoch": 0.09372366189068951, "grad_norm": 0.9963683306279938, "learning_rate": 4.976536160099873e-05, "loss": 0.6354, "num_tokens": 52061617.0, "step": 8785 }, { "epoch": 0.09377700489688796, "grad_norm": 0.9328329637853761, "learning_rate": 4.976478954422712e-05, "loss": 0.6385, "num_tokens": 52092160.0, "step": 8790 }, { "epoch": 0.09383034790308642, "grad_norm": 1.62309177224731, "learning_rate": 4.976421679462097e-05, "loss": 0.588, "num_tokens": 52104468.0, "step": 8795 }, { "epoch": 0.09388369090928489, "grad_norm": 2.4428231962966573, "learning_rate": 4.976364335219814e-05, "loss": 0.8227, "num_tokens": 52126399.0, "step": 8800 }, { "epoch": 0.09393703391548335, "grad_norm": 1.885992237612215, "learning_rate": 4.976306921697646e-05, "loss": 0.6346, "num_tokens": 52146840.0, "step": 8805 }, { "epoch": 0.0939903769216818, "grad_norm": 0.9031068829937803, "learning_rate": 4.9762494388973786e-05, "loss": 0.6944, "num_tokens": 52181041.0, "step": 8810 }, { "epoch": 0.09404371992788026, "grad_norm": 1.154640162967437, "learning_rate": 4.976191886820802e-05, "loss": 0.5592, "num_tokens": 52197933.0, "step": 8815 }, { "epoch": 0.09409706293407871, "grad_norm": 1.2043936249339304, "learning_rate": 4.976134265469707e-05, "loss": 0.669, "num_tokens": 52215811.0, "step": 8820 }, { "epoch": 0.09415040594027717, "grad_norm": 1.6625347859860162, "learning_rate": 4.9760765748458855e-05, "loss": 0.6152, "num_tokens": 52233917.0, "step": 8825 }, { "epoch": 0.09420374894647562, "grad_norm": 1.8590381799483422, "learning_rate": 4.9760188149511336e-05, "loss": 0.7556, "num_tokens": 52267199.0, "step": 8830 }, { "epoch": 0.09425709195267408, "grad_norm": 2.849053493851712, "learning_rate": 4.97596098578725e-05, "loss": 0.8616, "num_tokens": 52300451.0, "step": 8835 }, { "epoch": 0.09431043495887254, "grad_norm": 1.7644084205322899, "learning_rate": 4.975903087356031e-05, "loss": 0.6044, "num_tokens": 52328256.0, "step": 8840 }, { "epoch": 0.094363777965071, "grad_norm": 1.8215184995132323, "learning_rate": 4.9758451196592804e-05, "loss": 0.8238, "num_tokens": 52361616.0, "step": 8845 }, { "epoch": 0.09441712097126946, "grad_norm": 0.9985152930621147, "learning_rate": 4.975787082698802e-05, "loss": 0.6791, "num_tokens": 52391094.0, "step": 8850 }, { "epoch": 0.09447046397746792, "grad_norm": 1.3150542098462878, "learning_rate": 4.9757289764764014e-05, "loss": 0.5535, "num_tokens": 52416362.0, "step": 8855 }, { "epoch": 0.09452380698366637, "grad_norm": 1.3149778482960948, "learning_rate": 4.975670800993887e-05, "loss": 0.6788, "num_tokens": 52435931.0, "step": 8860 }, { "epoch": 0.09457714998986483, "grad_norm": 1.6222911701887213, "learning_rate": 4.9756125562530685e-05, "loss": 0.6932, "num_tokens": 52465864.0, "step": 8865 }, { "epoch": 0.09463049299606328, "grad_norm": 1.0897415220904374, "learning_rate": 4.9755542422557595e-05, "loss": 0.6922, "num_tokens": 52497980.0, "step": 8870 }, { "epoch": 0.09468383600226174, "grad_norm": 1.6491967136919248, "learning_rate": 4.9754958590037736e-05, "loss": 0.804, "num_tokens": 52531102.0, "step": 8875 }, { "epoch": 0.0947371790084602, "grad_norm": 1.3352853588694518, "learning_rate": 4.9754374064989275e-05, "loss": 0.7296, "num_tokens": 52565059.0, "step": 8880 }, { "epoch": 0.09479052201465865, "grad_norm": 0.9779841056347179, "learning_rate": 4.975378884743041e-05, "loss": 0.6507, "num_tokens": 52597442.0, "step": 8885 }, { "epoch": 0.09484386502085712, "grad_norm": 1.4408011490901578, "learning_rate": 4.975320293737935e-05, "loss": 0.5202, "num_tokens": 52614381.0, "step": 8890 }, { "epoch": 0.09489720802705558, "grad_norm": 1.3913405288778293, "learning_rate": 4.975261633485431e-05, "loss": 0.5605, "num_tokens": 52635321.0, "step": 8895 }, { "epoch": 0.09495055103325403, "grad_norm": 1.2792587530926416, "learning_rate": 4.975202903987357e-05, "loss": 0.7276, "num_tokens": 52681326.0, "step": 8900 }, { "epoch": 0.09500389403945249, "grad_norm": 1.3521439502367223, "learning_rate": 4.9751441052455387e-05, "loss": 0.7234, "num_tokens": 52706810.0, "step": 8905 }, { "epoch": 0.09505723704565094, "grad_norm": 3.5378037136959337, "learning_rate": 4.975085237261807e-05, "loss": 0.71, "num_tokens": 52742739.0, "step": 8910 }, { "epoch": 0.0951105800518494, "grad_norm": 1.2990473647559992, "learning_rate": 4.975026300037993e-05, "loss": 0.6972, "num_tokens": 52779037.0, "step": 8915 }, { "epoch": 0.09516392305804786, "grad_norm": 0.9888967280258771, "learning_rate": 4.97496729357593e-05, "loss": 0.58, "num_tokens": 52808848.0, "step": 8920 }, { "epoch": 0.09521726606424631, "grad_norm": 2.1494763666519785, "learning_rate": 4.974908217877456e-05, "loss": 0.9082, "num_tokens": 52831517.0, "step": 8925 }, { "epoch": 0.09527060907044477, "grad_norm": 2.0252758977558867, "learning_rate": 4.974849072944408e-05, "loss": 0.7442, "num_tokens": 52854542.0, "step": 8930 }, { "epoch": 0.09532395207664324, "grad_norm": 1.735853398251012, "learning_rate": 4.974789858778627e-05, "loss": 0.6911, "num_tokens": 52876552.0, "step": 8935 }, { "epoch": 0.09537729508284169, "grad_norm": 1.6736132759411724, "learning_rate": 4.974730575381956e-05, "loss": 0.6575, "num_tokens": 52900073.0, "step": 8940 }, { "epoch": 0.09543063808904015, "grad_norm": 2.0009161887751215, "learning_rate": 4.974671222756238e-05, "loss": 0.7712, "num_tokens": 52929605.0, "step": 8945 }, { "epoch": 0.0954839810952386, "grad_norm": 1.6852892401063206, "learning_rate": 4.974611800903321e-05, "loss": 0.6684, "num_tokens": 52954064.0, "step": 8950 }, { "epoch": 0.09553732410143706, "grad_norm": 1.200342693806805, "learning_rate": 4.974552309825056e-05, "loss": 0.6642, "num_tokens": 52976250.0, "step": 8955 }, { "epoch": 0.09559066710763552, "grad_norm": 1.1133596099215581, "learning_rate": 4.974492749523291e-05, "loss": 0.6261, "num_tokens": 53010874.0, "step": 8960 }, { "epoch": 0.09564401011383397, "grad_norm": 1.7947734886478517, "learning_rate": 4.974433119999881e-05, "loss": 0.6747, "num_tokens": 53054270.0, "step": 8965 }, { "epoch": 0.09569735312003243, "grad_norm": 1.1598400301457836, "learning_rate": 4.9743734212566824e-05, "loss": 0.6521, "num_tokens": 53095072.0, "step": 8970 }, { "epoch": 0.09575069612623088, "grad_norm": 1.3007548536061693, "learning_rate": 4.974313653295551e-05, "loss": 0.7212, "num_tokens": 53121952.0, "step": 8975 }, { "epoch": 0.09580403913242935, "grad_norm": 3.752587555949866, "learning_rate": 4.9742538161183476e-05, "loss": 0.6738, "num_tokens": 53143665.0, "step": 8980 }, { "epoch": 0.09585738213862781, "grad_norm": 0.9200514224329623, "learning_rate": 4.9741939097269346e-05, "loss": 0.5707, "num_tokens": 53182939.0, "step": 8985 }, { "epoch": 0.09591072514482626, "grad_norm": 1.3569331715073742, "learning_rate": 4.974133934123176e-05, "loss": 0.6224, "num_tokens": 53202313.0, "step": 8990 }, { "epoch": 0.09596406815102472, "grad_norm": 1.6097198985016836, "learning_rate": 4.9740738893089375e-05, "loss": 0.5182, "num_tokens": 53222551.0, "step": 8995 }, { "epoch": 0.09601741115722318, "grad_norm": 1.1065779313596815, "learning_rate": 4.974013775286088e-05, "loss": 0.6708, "num_tokens": 53262759.0, "step": 9000 }, { "epoch": 0.09607075416342163, "grad_norm": 2.219849737118556, "learning_rate": 4.973953592056498e-05, "loss": 0.6018, "num_tokens": 53280223.0, "step": 9005 }, { "epoch": 0.09612409716962009, "grad_norm": 2.6283772966455965, "learning_rate": 4.97389333962204e-05, "loss": 0.6611, "num_tokens": 53317558.0, "step": 9010 }, { "epoch": 0.09617744017581854, "grad_norm": 1.6601389997757037, "learning_rate": 4.973833017984589e-05, "loss": 0.6471, "num_tokens": 53340089.0, "step": 9015 }, { "epoch": 0.096230783182017, "grad_norm": 1.035356571365395, "learning_rate": 4.973772627146023e-05, "loss": 0.6161, "num_tokens": 53370879.0, "step": 9020 }, { "epoch": 0.09628412618821547, "grad_norm": 0.9805610509457374, "learning_rate": 4.973712167108221e-05, "loss": 0.7071, "num_tokens": 53400697.0, "step": 9025 }, { "epoch": 0.09633746919441392, "grad_norm": 1.1533989739143196, "learning_rate": 4.9736516378730634e-05, "loss": 0.6036, "num_tokens": 53423633.0, "step": 9030 }, { "epoch": 0.09639081220061238, "grad_norm": 1.3497144006649708, "learning_rate": 4.973591039442435e-05, "loss": 0.7375, "num_tokens": 53459760.0, "step": 9035 }, { "epoch": 0.09644415520681084, "grad_norm": 1.06154211141059, "learning_rate": 4.97353037181822e-05, "loss": 0.6335, "num_tokens": 53502621.0, "step": 9040 }, { "epoch": 0.09649749821300929, "grad_norm": 1.2765838303548385, "learning_rate": 4.9734696350023076e-05, "loss": 1.0208, "num_tokens": 53541828.0, "step": 9045 }, { "epoch": 0.09655084121920775, "grad_norm": 1.4725735623857719, "learning_rate": 4.973408828996587e-05, "loss": 0.6403, "num_tokens": 53562873.0, "step": 9050 }, { "epoch": 0.0966041842254062, "grad_norm": 0.911440619248623, "learning_rate": 4.973347953802951e-05, "loss": 0.5495, "num_tokens": 53606422.0, "step": 9055 }, { "epoch": 0.09665752723160466, "grad_norm": 1.1944586220878215, "learning_rate": 4.973287009423293e-05, "loss": 0.6824, "num_tokens": 53631744.0, "step": 9060 }, { "epoch": 0.09671087023780311, "grad_norm": 2.2046254300476855, "learning_rate": 4.973225995859511e-05, "loss": 0.6871, "num_tokens": 53658263.0, "step": 9065 }, { "epoch": 0.09676421324400158, "grad_norm": 1.3096395284638718, "learning_rate": 4.973164913113501e-05, "loss": 0.6144, "num_tokens": 53679699.0, "step": 9070 }, { "epoch": 0.09681755625020004, "grad_norm": 1.5490809558622962, "learning_rate": 4.973103761187167e-05, "loss": 0.6018, "num_tokens": 53705358.0, "step": 9075 }, { "epoch": 0.0968708992563985, "grad_norm": 1.6427500417639573, "learning_rate": 4.97304254008241e-05, "loss": 0.575, "num_tokens": 53735895.0, "step": 9080 }, { "epoch": 0.09692424226259695, "grad_norm": 1.6974703379926568, "learning_rate": 4.9729812498011347e-05, "loss": 0.7565, "num_tokens": 53767621.0, "step": 9085 }, { "epoch": 0.09697758526879541, "grad_norm": 1.0344343595547796, "learning_rate": 4.97291989034525e-05, "loss": 0.7122, "num_tokens": 53784314.0, "step": 9090 }, { "epoch": 0.09703092827499386, "grad_norm": 1.1023331715804483, "learning_rate": 4.9728584617166637e-05, "loss": 0.6232, "num_tokens": 53808443.0, "step": 9095 }, { "epoch": 0.09708427128119232, "grad_norm": 1.313939160147929, "learning_rate": 4.9727969639172875e-05, "loss": 0.7685, "num_tokens": 53843511.0, "step": 9100 }, { "epoch": 0.09713761428739077, "grad_norm": 1.2999059337436376, "learning_rate": 4.972735396949036e-05, "loss": 0.6843, "num_tokens": 53893807.0, "step": 9105 }, { "epoch": 0.09719095729358923, "grad_norm": 1.4716604715659956, "learning_rate": 4.972673760813825e-05, "loss": 0.6927, "num_tokens": 53931450.0, "step": 9110 }, { "epoch": 0.0972443002997877, "grad_norm": 1.0864635463008199, "learning_rate": 4.972612055513572e-05, "loss": 0.6848, "num_tokens": 53978857.0, "step": 9115 }, { "epoch": 0.09729764330598616, "grad_norm": 1.7310866166142034, "learning_rate": 4.972550281050197e-05, "loss": 0.7402, "num_tokens": 54012592.0, "step": 9120 }, { "epoch": 0.09735098631218461, "grad_norm": 1.0324097423679763, "learning_rate": 4.9724884374256234e-05, "loss": 0.6592, "num_tokens": 54043469.0, "step": 9125 }, { "epoch": 0.09740432931838307, "grad_norm": 1.357720005593618, "learning_rate": 4.972426524641773e-05, "loss": 0.5987, "num_tokens": 54073245.0, "step": 9130 }, { "epoch": 0.09745767232458152, "grad_norm": 1.0847605041637187, "learning_rate": 4.972364542700575e-05, "loss": 0.5315, "num_tokens": 54106728.0, "step": 9135 }, { "epoch": 0.09751101533077998, "grad_norm": 1.2889960732176748, "learning_rate": 4.972302491603957e-05, "loss": 0.7017, "num_tokens": 54130261.0, "step": 9140 }, { "epoch": 0.09756435833697844, "grad_norm": 1.9872519169203804, "learning_rate": 4.972240371353851e-05, "loss": 0.7315, "num_tokens": 54174738.0, "step": 9145 }, { "epoch": 0.09761770134317689, "grad_norm": 1.3973324332551225, "learning_rate": 4.972178181952188e-05, "loss": 0.5989, "num_tokens": 54194339.0, "step": 9150 }, { "epoch": 0.09767104434937535, "grad_norm": 8.04623818794546, "learning_rate": 4.972115923400906e-05, "loss": 0.7176, "num_tokens": 54214803.0, "step": 9155 }, { "epoch": 0.09772438735557382, "grad_norm": 1.388978087500063, "learning_rate": 4.9720535957019405e-05, "loss": 0.6951, "num_tokens": 54244559.0, "step": 9160 }, { "epoch": 0.09777773036177227, "grad_norm": 0.8830384742783381, "learning_rate": 4.9719911988572297e-05, "loss": 0.6204, "num_tokens": 54273464.0, "step": 9165 }, { "epoch": 0.09783107336797073, "grad_norm": 1.3949276501800378, "learning_rate": 4.971928732868718e-05, "loss": 0.5564, "num_tokens": 54296420.0, "step": 9170 }, { "epoch": 0.09788441637416918, "grad_norm": 2.66146171706277, "learning_rate": 4.971866197738349e-05, "loss": 0.673, "num_tokens": 54331270.0, "step": 9175 }, { "epoch": 0.09793775938036764, "grad_norm": 1.6851387932764001, "learning_rate": 4.971803593468066e-05, "loss": 0.794, "num_tokens": 54358626.0, "step": 9180 }, { "epoch": 0.0979911023865661, "grad_norm": 1.2204914919383147, "learning_rate": 4.97174092005982e-05, "loss": 0.7041, "num_tokens": 54387927.0, "step": 9185 }, { "epoch": 0.09804444539276455, "grad_norm": 1.874216921848388, "learning_rate": 4.97167817751556e-05, "loss": 0.691, "num_tokens": 54412007.0, "step": 9190 }, { "epoch": 0.098097788398963, "grad_norm": 2.4258654031572067, "learning_rate": 4.9716153658372386e-05, "loss": 0.6508, "num_tokens": 54425172.0, "step": 9195 }, { "epoch": 0.09815113140516146, "grad_norm": 1.1413277279258485, "learning_rate": 4.9715524850268106e-05, "loss": 0.6313, "num_tokens": 54452602.0, "step": 9200 }, { "epoch": 0.09820447441135993, "grad_norm": 1.1439220396737912, "learning_rate": 4.9714895350862325e-05, "loss": 0.518, "num_tokens": 54481434.0, "step": 9205 }, { "epoch": 0.09825781741755839, "grad_norm": 1.6813789007167101, "learning_rate": 4.9714265160174625e-05, "loss": 0.6396, "num_tokens": 54504273.0, "step": 9210 }, { "epoch": 0.09831116042375684, "grad_norm": 1.5198728198067208, "learning_rate": 4.9713634278224625e-05, "loss": 0.8024, "num_tokens": 54536712.0, "step": 9215 }, { "epoch": 0.0983645034299553, "grad_norm": 1.0597976473315107, "learning_rate": 4.9713002705031955e-05, "loss": 0.6673, "num_tokens": 54576354.0, "step": 9220 }, { "epoch": 0.09841784643615376, "grad_norm": 1.3789537413605364, "learning_rate": 4.9712370440616266e-05, "loss": 0.6454, "num_tokens": 54595992.0, "step": 9225 }, { "epoch": 0.09847118944235221, "grad_norm": 1.340221082817293, "learning_rate": 4.971173748499724e-05, "loss": 0.7049, "num_tokens": 54635162.0, "step": 9230 }, { "epoch": 0.09852453244855067, "grad_norm": 2.524516665089835, "learning_rate": 4.971110383819456e-05, "loss": 0.731, "num_tokens": 54666617.0, "step": 9235 }, { "epoch": 0.09857787545474912, "grad_norm": 1.8338897634916314, "learning_rate": 4.971046950022796e-05, "loss": 0.565, "num_tokens": 54701482.0, "step": 9240 }, { "epoch": 0.09863121846094758, "grad_norm": 1.1867051007083298, "learning_rate": 4.970983447111716e-05, "loss": 0.6657, "num_tokens": 54745733.0, "step": 9245 }, { "epoch": 0.09868456146714605, "grad_norm": 1.5235473511449198, "learning_rate": 4.9709198750881944e-05, "loss": 0.6108, "num_tokens": 54765500.0, "step": 9250 }, { "epoch": 0.0987379044733445, "grad_norm": 1.6947604481049348, "learning_rate": 4.970856233954207e-05, "loss": 0.7963, "num_tokens": 54812157.0, "step": 9255 }, { "epoch": 0.09879124747954296, "grad_norm": 1.2183331488366764, "learning_rate": 4.970792523711737e-05, "loss": 0.6315, "num_tokens": 54838814.0, "step": 9260 }, { "epoch": 0.09884459048574142, "grad_norm": 1.2717346378873313, "learning_rate": 4.970728744362763e-05, "loss": 0.5465, "num_tokens": 54855337.0, "step": 9265 }, { "epoch": 0.09889793349193987, "grad_norm": 1.2614103608799974, "learning_rate": 4.970664895909273e-05, "loss": 0.6131, "num_tokens": 54883571.0, "step": 9270 }, { "epoch": 0.09895127649813833, "grad_norm": 1.6888795377407728, "learning_rate": 4.970600978353253e-05, "loss": 0.6415, "num_tokens": 54898454.0, "step": 9275 }, { "epoch": 0.09900461950433678, "grad_norm": 1.8568449956168736, "learning_rate": 4.9705369916966924e-05, "loss": 0.7872, "num_tokens": 54919625.0, "step": 9280 }, { "epoch": 0.09905796251053524, "grad_norm": 1.5331672598168837, "learning_rate": 4.970472935941581e-05, "loss": 0.6089, "num_tokens": 54948166.0, "step": 9285 }, { "epoch": 0.0991113055167337, "grad_norm": 1.2098343767894602, "learning_rate": 4.970408811089913e-05, "loss": 0.5375, "num_tokens": 54985577.0, "step": 9290 }, { "epoch": 0.09916464852293216, "grad_norm": 1.1789016154041585, "learning_rate": 4.970344617143683e-05, "loss": 0.5622, "num_tokens": 55006684.0, "step": 9295 }, { "epoch": 0.09921799152913062, "grad_norm": 1.0497223469717192, "learning_rate": 4.9702803541048905e-05, "loss": 0.7268, "num_tokens": 55047469.0, "step": 9300 }, { "epoch": 0.09927133453532908, "grad_norm": 1.263486388769024, "learning_rate": 4.9702160219755336e-05, "loss": 0.6436, "num_tokens": 55074315.0, "step": 9305 }, { "epoch": 0.09932467754152753, "grad_norm": 1.455309198972018, "learning_rate": 4.970151620757614e-05, "loss": 0.6618, "num_tokens": 55103456.0, "step": 9310 }, { "epoch": 0.09937802054772599, "grad_norm": 1.051893547572159, "learning_rate": 4.9700871504531365e-05, "loss": 0.6376, "num_tokens": 55143030.0, "step": 9315 }, { "epoch": 0.09943136355392444, "grad_norm": 1.746528099103723, "learning_rate": 4.970022611064107e-05, "loss": 0.7705, "num_tokens": 55176208.0, "step": 9320 }, { "epoch": 0.0994847065601229, "grad_norm": 1.9173301811258678, "learning_rate": 4.969958002592534e-05, "loss": 0.6426, "num_tokens": 55197446.0, "step": 9325 }, { "epoch": 0.09953804956632135, "grad_norm": 1.3917271440602756, "learning_rate": 4.969893325040428e-05, "loss": 0.6498, "num_tokens": 55223301.0, "step": 9330 }, { "epoch": 0.09959139257251981, "grad_norm": 1.4776752095947856, "learning_rate": 4.969828578409801e-05, "loss": 0.5729, "num_tokens": 55253258.0, "step": 9335 }, { "epoch": 0.09964473557871828, "grad_norm": 1.2898123290671197, "learning_rate": 4.969763762702669e-05, "loss": 0.6716, "num_tokens": 55292861.0, "step": 9340 }, { "epoch": 0.09969807858491674, "grad_norm": 1.5161512827785568, "learning_rate": 4.969698877921048e-05, "loss": 0.5648, "num_tokens": 55312531.0, "step": 9345 }, { "epoch": 0.09975142159111519, "grad_norm": 1.6529001234295875, "learning_rate": 4.969633924066957e-05, "loss": 0.5674, "num_tokens": 55326909.0, "step": 9350 }, { "epoch": 0.09980476459731365, "grad_norm": 2.174426154932626, "learning_rate": 4.969568901142418e-05, "loss": 0.7542, "num_tokens": 55345150.0, "step": 9355 }, { "epoch": 0.0998581076035121, "grad_norm": 1.543626260432386, "learning_rate": 4.9695038091494536e-05, "loss": 0.8272, "num_tokens": 55377389.0, "step": 9360 }, { "epoch": 0.09991145060971056, "grad_norm": 1.0845074348791106, "learning_rate": 4.96943864809009e-05, "loss": 0.8134, "num_tokens": 55422708.0, "step": 9365 }, { "epoch": 0.09996479361590901, "grad_norm": 2.5284787520925294, "learning_rate": 4.9693734179663536e-05, "loss": 0.7123, "num_tokens": 55450423.0, "step": 9370 }, { "epoch": 0.10001813662210747, "grad_norm": 1.29339195937793, "learning_rate": 4.969308118780276e-05, "loss": 0.6516, "num_tokens": 55479680.0, "step": 9375 }, { "epoch": 0.10007147962830593, "grad_norm": 1.3539589381529433, "learning_rate": 4.969242750533889e-05, "loss": 0.6814, "num_tokens": 55505858.0, "step": 9380 }, { "epoch": 0.1001248226345044, "grad_norm": 1.4931651472013923, "learning_rate": 4.969177313229224e-05, "loss": 0.7565, "num_tokens": 55546680.0, "step": 9385 }, { "epoch": 0.10017816564070285, "grad_norm": 1.7295544417498023, "learning_rate": 4.969111806868321e-05, "loss": 0.7258, "num_tokens": 55575542.0, "step": 9390 }, { "epoch": 0.10023150864690131, "grad_norm": 1.411433099167965, "learning_rate": 4.9690462314532164e-05, "loss": 0.6372, "num_tokens": 55594215.0, "step": 9395 }, { "epoch": 0.10028485165309976, "grad_norm": 2.8201343311453595, "learning_rate": 4.968980586985951e-05, "loss": 0.7078, "num_tokens": 55625237.0, "step": 9400 }, { "epoch": 0.10033819465929822, "grad_norm": 1.5314086898951387, "learning_rate": 4.968914873468568e-05, "loss": 0.6302, "num_tokens": 55655051.0, "step": 9405 }, { "epoch": 0.10039153766549667, "grad_norm": 1.3508707527828474, "learning_rate": 4.968849090903111e-05, "loss": 0.6926, "num_tokens": 55683875.0, "step": 9410 }, { "epoch": 0.10044488067169513, "grad_norm": 1.47744005143011, "learning_rate": 4.968783239291629e-05, "loss": 0.6637, "num_tokens": 55719900.0, "step": 9415 }, { "epoch": 0.10049822367789359, "grad_norm": 1.3388212258172976, "learning_rate": 4.968717318636169e-05, "loss": 0.7697, "num_tokens": 55763902.0, "step": 9420 }, { "epoch": 0.10055156668409204, "grad_norm": 1.2923857884320389, "learning_rate": 4.9686513289387846e-05, "loss": 0.7045, "num_tokens": 55798860.0, "step": 9425 }, { "epoch": 0.10060490969029051, "grad_norm": 1.3916309390132158, "learning_rate": 4.9685852702015276e-05, "loss": 0.5502, "num_tokens": 55830671.0, "step": 9430 }, { "epoch": 0.10065825269648897, "grad_norm": 2.2347187515654805, "learning_rate": 4.968519142426454e-05, "loss": 0.5992, "num_tokens": 55867748.0, "step": 9435 }, { "epoch": 0.10071159570268742, "grad_norm": 1.7066400700816813, "learning_rate": 4.968452945615622e-05, "loss": 0.6641, "num_tokens": 55892431.0, "step": 9440 }, { "epoch": 0.10076493870888588, "grad_norm": 1.7137099970943783, "learning_rate": 4.9683866797710904e-05, "loss": 0.7813, "num_tokens": 55909159.0, "step": 9445 }, { "epoch": 0.10081828171508433, "grad_norm": 1.4714644328460997, "learning_rate": 4.968320344894923e-05, "loss": 0.547, "num_tokens": 55933454.0, "step": 9450 }, { "epoch": 0.10087162472128279, "grad_norm": 1.121143423389187, "learning_rate": 4.968253940989182e-05, "loss": 0.8642, "num_tokens": 55985115.0, "step": 9455 }, { "epoch": 0.10092496772748125, "grad_norm": 0.9902934614448266, "learning_rate": 4.9681874680559353e-05, "loss": 0.6362, "num_tokens": 56012992.0, "step": 9460 }, { "epoch": 0.1009783107336797, "grad_norm": 1.7160221422695419, "learning_rate": 4.968120926097251e-05, "loss": 0.7643, "num_tokens": 56030883.0, "step": 9465 }, { "epoch": 0.10103165373987816, "grad_norm": 1.6707354898781535, "learning_rate": 4.9680543151152e-05, "loss": 0.7025, "num_tokens": 56060181.0, "step": 9470 }, { "epoch": 0.10108499674607663, "grad_norm": 1.4364165464009633, "learning_rate": 4.967987635111854e-05, "loss": 0.7807, "num_tokens": 56098351.0, "step": 9475 }, { "epoch": 0.10113833975227508, "grad_norm": 0.9647897730576154, "learning_rate": 4.967920886089289e-05, "loss": 0.7232, "num_tokens": 56132932.0, "step": 9480 }, { "epoch": 0.10119168275847354, "grad_norm": 1.2841339224435895, "learning_rate": 4.967854068049582e-05, "loss": 0.5969, "num_tokens": 56176668.0, "step": 9485 }, { "epoch": 0.101245025764672, "grad_norm": 1.682963158442228, "learning_rate": 4.9677871809948105e-05, "loss": 0.7236, "num_tokens": 56205143.0, "step": 9490 }, { "epoch": 0.10129836877087045, "grad_norm": 1.6270305106076794, "learning_rate": 4.9677202249270587e-05, "loss": 0.5871, "num_tokens": 56242416.0, "step": 9495 }, { "epoch": 0.1013517117770689, "grad_norm": 2.6586512127637723, "learning_rate": 4.9676531998484094e-05, "loss": 0.6206, "num_tokens": 56279753.0, "step": 9500 }, { "epoch": 0.10140505478326736, "grad_norm": 1.727516671365071, "learning_rate": 4.9675861057609465e-05, "loss": 0.7506, "num_tokens": 56325568.0, "step": 9505 }, { "epoch": 0.10145839778946582, "grad_norm": 1.4202587712830805, "learning_rate": 4.96751894266676e-05, "loss": 0.653, "num_tokens": 56355503.0, "step": 9510 }, { "epoch": 0.10151174079566427, "grad_norm": 1.384133209814953, "learning_rate": 4.967451710567938e-05, "loss": 0.6294, "num_tokens": 56383303.0, "step": 9515 }, { "epoch": 0.10156508380186274, "grad_norm": 1.2811045342304446, "learning_rate": 4.967384409466574e-05, "loss": 0.7103, "num_tokens": 56408483.0, "step": 9520 }, { "epoch": 0.1016184268080612, "grad_norm": 1.532308272432946, "learning_rate": 4.967317039364762e-05, "loss": 0.5942, "num_tokens": 56432451.0, "step": 9525 }, { "epoch": 0.10167176981425965, "grad_norm": 0.9628854542735708, "learning_rate": 4.967249600264598e-05, "loss": 0.6825, "num_tokens": 56466736.0, "step": 9530 }, { "epoch": 0.10172511282045811, "grad_norm": 1.2841022446097885, "learning_rate": 4.967182092168181e-05, "loss": 0.7131, "num_tokens": 56502051.0, "step": 9535 }, { "epoch": 0.10177845582665657, "grad_norm": 1.5584419814619055, "learning_rate": 4.9671145150776116e-05, "loss": 0.8265, "num_tokens": 56532646.0, "step": 9540 }, { "epoch": 0.10183179883285502, "grad_norm": 0.7892622227113747, "learning_rate": 4.967046868994992e-05, "loss": 0.5435, "num_tokens": 56571291.0, "step": 9545 }, { "epoch": 0.10188514183905348, "grad_norm": 1.294678963559221, "learning_rate": 4.966979153922428e-05, "loss": 0.5964, "num_tokens": 56612382.0, "step": 9550 }, { "epoch": 0.10193848484525193, "grad_norm": 1.2941016215807282, "learning_rate": 4.966911369862027e-05, "loss": 0.7269, "num_tokens": 56653478.0, "step": 9555 }, { "epoch": 0.10199182785145039, "grad_norm": 1.363566616097731, "learning_rate": 4.9668435168158974e-05, "loss": 0.69, "num_tokens": 56683270.0, "step": 9560 }, { "epoch": 0.10204517085764886, "grad_norm": 1.8320495496475324, "learning_rate": 4.9667755947861516e-05, "loss": 0.7569, "num_tokens": 56705966.0, "step": 9565 }, { "epoch": 0.10209851386384731, "grad_norm": 1.6834497424800758, "learning_rate": 4.9667076037749025e-05, "loss": 0.6541, "num_tokens": 56720669.0, "step": 9570 }, { "epoch": 0.10215185687004577, "grad_norm": 1.000151271252784, "learning_rate": 4.9666395437842656e-05, "loss": 0.6454, "num_tokens": 56752987.0, "step": 9575 }, { "epoch": 0.10220519987624423, "grad_norm": 1.6463331565598107, "learning_rate": 4.966571414816359e-05, "loss": 0.6735, "num_tokens": 56781449.0, "step": 9580 }, { "epoch": 0.10225854288244268, "grad_norm": 1.6726400534584756, "learning_rate": 4.9665032168733036e-05, "loss": 0.8224, "num_tokens": 56801489.0, "step": 9585 }, { "epoch": 0.10231188588864114, "grad_norm": 1.3429112323292172, "learning_rate": 4.9664349499572205e-05, "loss": 0.5397, "num_tokens": 56833040.0, "step": 9590 }, { "epoch": 0.1023652288948396, "grad_norm": 1.052577026486689, "learning_rate": 4.966366614070235e-05, "loss": 0.7912, "num_tokens": 56861807.0, "step": 9595 }, { "epoch": 0.10241857190103805, "grad_norm": 1.1648500704955635, "learning_rate": 4.966298209214472e-05, "loss": 0.8135, "num_tokens": 56909889.0, "step": 9600 }, { "epoch": 0.1024719149072365, "grad_norm": 1.3665829241593737, "learning_rate": 4.966229735392062e-05, "loss": 0.569, "num_tokens": 56941491.0, "step": 9605 }, { "epoch": 0.10252525791343498, "grad_norm": 0.9853299065223409, "learning_rate": 4.9661611926051346e-05, "loss": 0.7421, "num_tokens": 56979778.0, "step": 9610 }, { "epoch": 0.10257860091963343, "grad_norm": 1.4430731565848454, "learning_rate": 4.966092580855823e-05, "loss": 0.6336, "num_tokens": 57021679.0, "step": 9615 }, { "epoch": 0.10263194392583189, "grad_norm": 1.224458163635731, "learning_rate": 4.966023900146262e-05, "loss": 0.6427, "num_tokens": 57047228.0, "step": 9620 }, { "epoch": 0.10268528693203034, "grad_norm": 2.323318322550508, "learning_rate": 4.96595515047859e-05, "loss": 0.6623, "num_tokens": 57069621.0, "step": 9625 }, { "epoch": 0.1027386299382288, "grad_norm": 1.0031721096505721, "learning_rate": 4.9658863318549446e-05, "loss": 0.4955, "num_tokens": 57085556.0, "step": 9630 }, { "epoch": 0.10279197294442725, "grad_norm": 1.7680544467156099, "learning_rate": 4.965817444277468e-05, "loss": 0.6855, "num_tokens": 57111917.0, "step": 9635 }, { "epoch": 0.10284531595062571, "grad_norm": 1.1443908431618053, "learning_rate": 4.965748487748304e-05, "loss": 0.566, "num_tokens": 57150145.0, "step": 9640 }, { "epoch": 0.10289865895682417, "grad_norm": 1.1246817223758687, "learning_rate": 4.965679462269599e-05, "loss": 0.6691, "num_tokens": 57182934.0, "step": 9645 }, { "epoch": 0.10295200196302262, "grad_norm": 1.4457327560776754, "learning_rate": 4.9656103678435005e-05, "loss": 0.7445, "num_tokens": 57205322.0, "step": 9650 }, { "epoch": 0.10300534496922109, "grad_norm": 2.002065700855876, "learning_rate": 4.965541204472157e-05, "loss": 0.6977, "num_tokens": 57224073.0, "step": 9655 }, { "epoch": 0.10305868797541955, "grad_norm": 1.9686451256443505, "learning_rate": 4.965471972157723e-05, "loss": 0.7268, "num_tokens": 57255696.0, "step": 9660 }, { "epoch": 0.103112030981618, "grad_norm": 1.5774827040313226, "learning_rate": 4.965402670902352e-05, "loss": 0.6808, "num_tokens": 57287636.0, "step": 9665 }, { "epoch": 0.10316537398781646, "grad_norm": 1.4657966274637906, "learning_rate": 4.9653333007082007e-05, "loss": 0.7636, "num_tokens": 57327590.0, "step": 9670 }, { "epoch": 0.10321871699401491, "grad_norm": 1.0917877750599458, "learning_rate": 4.965263861577426e-05, "loss": 0.703, "num_tokens": 57350970.0, "step": 9675 }, { "epoch": 0.10327206000021337, "grad_norm": 1.5460747223634408, "learning_rate": 4.965194353512192e-05, "loss": 0.4975, "num_tokens": 57369675.0, "step": 9680 }, { "epoch": 0.10332540300641183, "grad_norm": 1.3000878714431983, "learning_rate": 4.9651247765146584e-05, "loss": 0.5669, "num_tokens": 57402719.0, "step": 9685 }, { "epoch": 0.10337874601261028, "grad_norm": 1.0304721341027363, "learning_rate": 4.965055130586993e-05, "loss": 0.486, "num_tokens": 57440113.0, "step": 9690 }, { "epoch": 0.10343208901880874, "grad_norm": 1.106471810609679, "learning_rate": 4.964985415731361e-05, "loss": 0.6033, "num_tokens": 57474945.0, "step": 9695 }, { "epoch": 0.1034854320250072, "grad_norm": 0.8785215395637896, "learning_rate": 4.964915631949932e-05, "loss": 0.713, "num_tokens": 57512788.0, "step": 9700 }, { "epoch": 0.10353877503120566, "grad_norm": 1.17888072745803, "learning_rate": 4.9648457792448795e-05, "loss": 0.6445, "num_tokens": 57541322.0, "step": 9705 }, { "epoch": 0.10359211803740412, "grad_norm": 1.5409570299876212, "learning_rate": 4.9647758576183755e-05, "loss": 0.4993, "num_tokens": 57564656.0, "step": 9710 }, { "epoch": 0.10364546104360257, "grad_norm": 1.3842883342415337, "learning_rate": 4.964705867072595e-05, "loss": 0.6245, "num_tokens": 57589993.0, "step": 9715 }, { "epoch": 0.10369880404980103, "grad_norm": 1.2535533298575605, "learning_rate": 4.964635807609718e-05, "loss": 0.701, "num_tokens": 57628343.0, "step": 9720 }, { "epoch": 0.10375214705599949, "grad_norm": 1.354421197039676, "learning_rate": 4.964565679231923e-05, "loss": 0.6634, "num_tokens": 57647939.0, "step": 9725 }, { "epoch": 0.10380549006219794, "grad_norm": 1.175978748140488, "learning_rate": 4.9644954819413945e-05, "loss": 0.72, "num_tokens": 57678893.0, "step": 9730 }, { "epoch": 0.1038588330683964, "grad_norm": 1.4770610388869336, "learning_rate": 4.964425215740314e-05, "loss": 0.6112, "num_tokens": 57707845.0, "step": 9735 }, { "epoch": 0.10391217607459485, "grad_norm": 1.2051925774231462, "learning_rate": 4.964354880630869e-05, "loss": 0.599, "num_tokens": 57747599.0, "step": 9740 }, { "epoch": 0.10396551908079332, "grad_norm": 1.5861671956998193, "learning_rate": 4.9642844766152494e-05, "loss": 0.6081, "num_tokens": 57770586.0, "step": 9745 }, { "epoch": 0.10401886208699178, "grad_norm": 1.3826377938309107, "learning_rate": 4.964214003695645e-05, "loss": 0.6144, "num_tokens": 57806430.0, "step": 9750 }, { "epoch": 0.10407220509319023, "grad_norm": 1.7434153166647706, "learning_rate": 4.9641434618742486e-05, "loss": 0.5971, "num_tokens": 57828070.0, "step": 9755 }, { "epoch": 0.10412554809938869, "grad_norm": 1.0396522309092446, "learning_rate": 4.9640728511532566e-05, "loss": 0.6175, "num_tokens": 57850087.0, "step": 9760 }, { "epoch": 0.10417889110558715, "grad_norm": 1.1653702778700956, "learning_rate": 4.9640021715348635e-05, "loss": 0.6058, "num_tokens": 57895747.0, "step": 9765 }, { "epoch": 0.1042322341117856, "grad_norm": 2.2935857147971563, "learning_rate": 4.9639314230212716e-05, "loss": 0.8029, "num_tokens": 57921906.0, "step": 9770 }, { "epoch": 0.10428557711798406, "grad_norm": 1.6656113002002484, "learning_rate": 4.963860605614682e-05, "loss": 0.7891, "num_tokens": 57956452.0, "step": 9775 }, { "epoch": 0.10433892012418251, "grad_norm": 1.0216872758192697, "learning_rate": 4.9637897193172965e-05, "loss": 0.5741, "num_tokens": 57979458.0, "step": 9780 }, { "epoch": 0.10439226313038097, "grad_norm": 1.2366187774196924, "learning_rate": 4.963718764131323e-05, "loss": 0.6253, "num_tokens": 58001322.0, "step": 9785 }, { "epoch": 0.10444560613657944, "grad_norm": 1.1946890988245338, "learning_rate": 4.963647740058968e-05, "loss": 0.7384, "num_tokens": 58043668.0, "step": 9790 }, { "epoch": 0.1044989491427779, "grad_norm": 3.6035956236989173, "learning_rate": 4.963576647102443e-05, "loss": 0.6822, "num_tokens": 58071697.0, "step": 9795 }, { "epoch": 0.10455229214897635, "grad_norm": 1.2576101489998572, "learning_rate": 4.963505485263959e-05, "loss": 0.5307, "num_tokens": 58086002.0, "step": 9800 }, { "epoch": 0.1046056351551748, "grad_norm": 1.4643357869022502, "learning_rate": 4.963434254545731e-05, "loss": 0.5139, "num_tokens": 58109981.0, "step": 9805 }, { "epoch": 0.10465897816137326, "grad_norm": 0.9897250416684882, "learning_rate": 4.9633629549499754e-05, "loss": 0.6854, "num_tokens": 58144166.0, "step": 9810 }, { "epoch": 0.10471232116757172, "grad_norm": 2.6459581834358032, "learning_rate": 4.963291586478912e-05, "loss": 0.6819, "num_tokens": 58165520.0, "step": 9815 }, { "epoch": 0.10476566417377017, "grad_norm": 1.1063745094247492, "learning_rate": 4.9632201491347595e-05, "loss": 0.6558, "num_tokens": 58198961.0, "step": 9820 }, { "epoch": 0.10481900717996863, "grad_norm": 1.097891919942326, "learning_rate": 4.9631486429197424e-05, "loss": 0.7438, "num_tokens": 58247027.0, "step": 9825 }, { "epoch": 0.10487235018616708, "grad_norm": 3.141091701568958, "learning_rate": 4.963077067836086e-05, "loss": 0.6997, "num_tokens": 58273261.0, "step": 9830 }, { "epoch": 0.10492569319236555, "grad_norm": 1.4936829979023127, "learning_rate": 4.9630054238860166e-05, "loss": 0.6369, "num_tokens": 58292395.0, "step": 9835 }, { "epoch": 0.10497903619856401, "grad_norm": 1.4925461155661066, "learning_rate": 4.962933711071764e-05, "loss": 0.6492, "num_tokens": 58331874.0, "step": 9840 }, { "epoch": 0.10503237920476247, "grad_norm": 1.068502838185114, "learning_rate": 4.96286192939556e-05, "loss": 0.6305, "num_tokens": 58359903.0, "step": 9845 }, { "epoch": 0.10508572221096092, "grad_norm": 0.9998087835274856, "learning_rate": 4.962790078859638e-05, "loss": 0.6147, "num_tokens": 58387137.0, "step": 9850 }, { "epoch": 0.10513906521715938, "grad_norm": 1.0027571198331946, "learning_rate": 4.962718159466234e-05, "loss": 0.7583, "num_tokens": 58430935.0, "step": 9855 }, { "epoch": 0.10519240822335783, "grad_norm": 2.865804146389819, "learning_rate": 4.9626461712175866e-05, "loss": 0.5882, "num_tokens": 58443106.0, "step": 9860 }, { "epoch": 0.10524575122955629, "grad_norm": 1.923509921825417, "learning_rate": 4.9625741141159335e-05, "loss": 0.6337, "num_tokens": 58468546.0, "step": 9865 }, { "epoch": 0.10529909423575474, "grad_norm": 1.3026179880507964, "learning_rate": 4.9625019881635204e-05, "loss": 0.5732, "num_tokens": 58495165.0, "step": 9870 }, { "epoch": 0.1053524372419532, "grad_norm": 1.0783960906939882, "learning_rate": 4.962429793362589e-05, "loss": 0.535, "num_tokens": 58516996.0, "step": 9875 }, { "epoch": 0.10540578024815167, "grad_norm": 1.3991002447467202, "learning_rate": 4.962357529715387e-05, "loss": 0.5751, "num_tokens": 58544827.0, "step": 9880 }, { "epoch": 0.10545912325435013, "grad_norm": 1.844221797963211, "learning_rate": 4.9622851972241644e-05, "loss": 0.701, "num_tokens": 58573870.0, "step": 9885 }, { "epoch": 0.10551246626054858, "grad_norm": 1.2620149947505057, "learning_rate": 4.962212795891169e-05, "loss": 0.5255, "num_tokens": 58588540.0, "step": 9890 }, { "epoch": 0.10556580926674704, "grad_norm": 1.3340832422376476, "learning_rate": 4.962140325718656e-05, "loss": 0.7494, "num_tokens": 58627720.0, "step": 9895 }, { "epoch": 0.1056191522729455, "grad_norm": 1.8161473028680257, "learning_rate": 4.962067786708879e-05, "loss": 0.6445, "num_tokens": 58647889.0, "step": 9900 }, { "epoch": 0.10567249527914395, "grad_norm": 1.850890651351884, "learning_rate": 4.961995178864098e-05, "loss": 0.6371, "num_tokens": 58672436.0, "step": 9905 }, { "epoch": 0.1057258382853424, "grad_norm": 0.9525116541551037, "learning_rate": 4.96192250218657e-05, "loss": 0.6542, "num_tokens": 58695850.0, "step": 9910 }, { "epoch": 0.10577918129154086, "grad_norm": 1.1546296222199122, "learning_rate": 4.961849756678556e-05, "loss": 0.6518, "num_tokens": 58725475.0, "step": 9915 }, { "epoch": 0.10583252429773932, "grad_norm": 2.09502360436706, "learning_rate": 4.961776942342322e-05, "loss": 0.8009, "num_tokens": 58759721.0, "step": 9920 }, { "epoch": 0.10588586730393779, "grad_norm": 1.015598188548482, "learning_rate": 4.961704059180132e-05, "loss": 0.7549, "num_tokens": 58800476.0, "step": 9925 }, { "epoch": 0.10593921031013624, "grad_norm": 1.0457685538438743, "learning_rate": 4.961631107194255e-05, "loss": 0.6003, "num_tokens": 58823596.0, "step": 9930 }, { "epoch": 0.1059925533163347, "grad_norm": 1.3293531120921167, "learning_rate": 4.961558086386961e-05, "loss": 0.6517, "num_tokens": 58846654.0, "step": 9935 }, { "epoch": 0.10604589632253315, "grad_norm": 1.169055974270408, "learning_rate": 4.961484996760522e-05, "loss": 0.78, "num_tokens": 58876582.0, "step": 9940 }, { "epoch": 0.10609923932873161, "grad_norm": 4.509893507471176, "learning_rate": 4.961411838317212e-05, "loss": 0.8591, "num_tokens": 58907944.0, "step": 9945 }, { "epoch": 0.10615258233493007, "grad_norm": 1.6718591450219054, "learning_rate": 4.9613386110593084e-05, "loss": 0.6668, "num_tokens": 58929203.0, "step": 9950 }, { "epoch": 0.10620592534112852, "grad_norm": 2.1196648457339187, "learning_rate": 4.9612653149890894e-05, "loss": 0.7419, "num_tokens": 58973723.0, "step": 9955 }, { "epoch": 0.10625926834732698, "grad_norm": 1.693023429830008, "learning_rate": 4.961191950108835e-05, "loss": 0.6505, "num_tokens": 59013907.0, "step": 9960 }, { "epoch": 0.10631261135352543, "grad_norm": 2.271787496684978, "learning_rate": 4.96111851642083e-05, "loss": 0.6893, "num_tokens": 59036295.0, "step": 9965 }, { "epoch": 0.1063659543597239, "grad_norm": 2.3027325092902258, "learning_rate": 4.961045013927358e-05, "loss": 0.6297, "num_tokens": 59061053.0, "step": 9970 }, { "epoch": 0.10641929736592236, "grad_norm": 1.088350020752661, "learning_rate": 4.960971442630707e-05, "loss": 0.5699, "num_tokens": 59089567.0, "step": 9975 }, { "epoch": 0.10647264037212081, "grad_norm": 1.2488259281510345, "learning_rate": 4.9608978025331664e-05, "loss": 0.6898, "num_tokens": 59128805.0, "step": 9980 }, { "epoch": 0.10652598337831927, "grad_norm": 1.0516042851127478, "learning_rate": 4.9608240936370264e-05, "loss": 0.6661, "num_tokens": 59156761.0, "step": 9985 }, { "epoch": 0.10657932638451773, "grad_norm": 1.2721952091452724, "learning_rate": 4.960750315944583e-05, "loss": 0.5874, "num_tokens": 59195701.0, "step": 9990 }, { "epoch": 0.10663266939071618, "grad_norm": 1.4312799454295797, "learning_rate": 4.9606764694581303e-05, "loss": 0.6826, "num_tokens": 59225914.0, "step": 9995 }, { "epoch": 0.10668601239691464, "grad_norm": 1.0099947010510208, "learning_rate": 4.960602554179967e-05, "loss": 0.6322, "num_tokens": 59248661.0, "step": 10000 }, { "epoch": 0.10673935540311309, "grad_norm": 1.0831498511797437, "learning_rate": 4.960528570112393e-05, "loss": 0.5644, "num_tokens": 59272343.0, "step": 10005 }, { "epoch": 0.10679269840931155, "grad_norm": 1.9127490340703672, "learning_rate": 4.960454517257711e-05, "loss": 0.6113, "num_tokens": 59293911.0, "step": 10010 }, { "epoch": 0.10684604141551002, "grad_norm": 1.0611978218997997, "learning_rate": 4.960380395618223e-05, "loss": 0.6759, "num_tokens": 59314639.0, "step": 10015 }, { "epoch": 0.10689938442170847, "grad_norm": 1.48936176356556, "learning_rate": 4.960306205196239e-05, "loss": 0.8101, "num_tokens": 59339978.0, "step": 10020 }, { "epoch": 0.10695272742790693, "grad_norm": 1.6509039752382222, "learning_rate": 4.9602319459940655e-05, "loss": 0.6119, "num_tokens": 59378678.0, "step": 10025 }, { "epoch": 0.10700607043410539, "grad_norm": 0.9689952973624535, "learning_rate": 4.9601576180140134e-05, "loss": 0.5512, "num_tokens": 59409449.0, "step": 10030 }, { "epoch": 0.10705941344030384, "grad_norm": 2.1982759554463893, "learning_rate": 4.960083221258396e-05, "loss": 0.6618, "num_tokens": 59437197.0, "step": 10035 }, { "epoch": 0.1071127564465023, "grad_norm": 1.5635388290297503, "learning_rate": 4.960008755729529e-05, "loss": 0.6036, "num_tokens": 59453146.0, "step": 10040 }, { "epoch": 0.10716609945270075, "grad_norm": 1.2118797453948598, "learning_rate": 4.959934221429728e-05, "loss": 0.6196, "num_tokens": 59482755.0, "step": 10045 }, { "epoch": 0.10721944245889921, "grad_norm": 1.3890462986619327, "learning_rate": 4.959859618361315e-05, "loss": 0.6185, "num_tokens": 59514255.0, "step": 10050 }, { "epoch": 0.10727278546509766, "grad_norm": 1.6079326002379288, "learning_rate": 4.9597849465266086e-05, "loss": 0.656, "num_tokens": 59538736.0, "step": 10055 }, { "epoch": 0.10732612847129613, "grad_norm": 1.4363624504259647, "learning_rate": 4.9597102059279335e-05, "loss": 0.7005, "num_tokens": 59566208.0, "step": 10060 }, { "epoch": 0.10737947147749459, "grad_norm": 1.2284999364262943, "learning_rate": 4.9596353965676164e-05, "loss": 0.7415, "num_tokens": 59588976.0, "step": 10065 }, { "epoch": 0.10743281448369305, "grad_norm": 2.2798104340255123, "learning_rate": 4.959560518447985e-05, "loss": 0.6323, "num_tokens": 59617159.0, "step": 10070 }, { "epoch": 0.1074861574898915, "grad_norm": 1.6589364808482143, "learning_rate": 4.959485571571368e-05, "loss": 0.7337, "num_tokens": 59643816.0, "step": 10075 }, { "epoch": 0.10753950049608996, "grad_norm": 0.8526004142479344, "learning_rate": 4.959410555940098e-05, "loss": 0.4833, "num_tokens": 59676292.0, "step": 10080 }, { "epoch": 0.10759284350228841, "grad_norm": 1.5566381324004088, "learning_rate": 4.9593354715565105e-05, "loss": 0.4958, "num_tokens": 59702922.0, "step": 10085 }, { "epoch": 0.10764618650848687, "grad_norm": 1.7702461120068214, "learning_rate": 4.9592603184229414e-05, "loss": 0.6093, "num_tokens": 59728065.0, "step": 10090 }, { "epoch": 0.10769952951468532, "grad_norm": 1.253975763398178, "learning_rate": 4.959185096541728e-05, "loss": 0.7153, "num_tokens": 59766120.0, "step": 10095 }, { "epoch": 0.10775287252088378, "grad_norm": 1.583836188519385, "learning_rate": 4.959109805915213e-05, "loss": 0.5764, "num_tokens": 59794383.0, "step": 10100 }, { "epoch": 0.10780621552708225, "grad_norm": 1.0226906965944207, "learning_rate": 4.9590344465457383e-05, "loss": 0.6766, "num_tokens": 59839358.0, "step": 10105 }, { "epoch": 0.1078595585332807, "grad_norm": 0.8369980063656093, "learning_rate": 4.9589590184356494e-05, "loss": 0.6144, "num_tokens": 59873446.0, "step": 10110 }, { "epoch": 0.10791290153947916, "grad_norm": 0.8977830719169826, "learning_rate": 4.958883521587293e-05, "loss": 0.6296, "num_tokens": 59922017.0, "step": 10115 }, { "epoch": 0.10796624454567762, "grad_norm": 1.8629631358519563, "learning_rate": 4.958807956003019e-05, "loss": 0.7821, "num_tokens": 59941319.0, "step": 10120 }, { "epoch": 0.10801958755187607, "grad_norm": 1.0946231104916793, "learning_rate": 4.958732321685178e-05, "loss": 0.6349, "num_tokens": 59966462.0, "step": 10125 }, { "epoch": 0.10807293055807453, "grad_norm": 1.899754394593879, "learning_rate": 4.958656618636123e-05, "loss": 0.8108, "num_tokens": 60004625.0, "step": 10130 }, { "epoch": 0.10812627356427298, "grad_norm": 1.3602358722013188, "learning_rate": 4.958580846858212e-05, "loss": 0.6219, "num_tokens": 60021174.0, "step": 10135 }, { "epoch": 0.10817961657047144, "grad_norm": 1.5894807907892528, "learning_rate": 4.958505006353802e-05, "loss": 0.7664, "num_tokens": 60058807.0, "step": 10140 }, { "epoch": 0.1082329595766699, "grad_norm": 1.1971220729641008, "learning_rate": 4.9584290971252516e-05, "loss": 0.6009, "num_tokens": 60098916.0, "step": 10145 }, { "epoch": 0.10828630258286837, "grad_norm": 1.1903764492246751, "learning_rate": 4.958353119174925e-05, "loss": 0.7856, "num_tokens": 60139060.0, "step": 10150 }, { "epoch": 0.10833964558906682, "grad_norm": 1.8447190394989186, "learning_rate": 4.958277072505184e-05, "loss": 0.7719, "num_tokens": 60163295.0, "step": 10155 }, { "epoch": 0.10839298859526528, "grad_norm": 1.2804187842866666, "learning_rate": 4.958200957118398e-05, "loss": 0.7128, "num_tokens": 60199916.0, "step": 10160 }, { "epoch": 0.10844633160146373, "grad_norm": 2.2186494393525926, "learning_rate": 4.9581247730169323e-05, "loss": 0.6125, "num_tokens": 60215877.0, "step": 10165 }, { "epoch": 0.10849967460766219, "grad_norm": 1.1736701742942808, "learning_rate": 4.95804852020316e-05, "loss": 0.6806, "num_tokens": 60259064.0, "step": 10170 }, { "epoch": 0.10855301761386064, "grad_norm": 2.9067679497023984, "learning_rate": 4.9579721986794535e-05, "loss": 0.8397, "num_tokens": 60281833.0, "step": 10175 }, { "epoch": 0.1086063606200591, "grad_norm": 1.1670717021202301, "learning_rate": 4.957895808448187e-05, "loss": 0.6378, "num_tokens": 60309499.0, "step": 10180 }, { "epoch": 0.10865970362625756, "grad_norm": 1.9160494004432065, "learning_rate": 4.957819349511739e-05, "loss": 0.6743, "num_tokens": 60333896.0, "step": 10185 }, { "epoch": 0.10871304663245601, "grad_norm": 1.0357037180761808, "learning_rate": 4.957742821872487e-05, "loss": 0.7575, "num_tokens": 60361312.0, "step": 10190 }, { "epoch": 0.10876638963865448, "grad_norm": 1.056474575764223, "learning_rate": 4.957666225532814e-05, "loss": 0.6411, "num_tokens": 60387696.0, "step": 10195 }, { "epoch": 0.10881973264485294, "grad_norm": 1.4447276172620869, "learning_rate": 4.957589560495102e-05, "loss": 0.7479, "num_tokens": 60407240.0, "step": 10200 }, { "epoch": 0.1088730756510514, "grad_norm": 1.7442028024464304, "learning_rate": 4.957512826761737e-05, "loss": 0.7834, "num_tokens": 60430740.0, "step": 10205 }, { "epoch": 0.10892641865724985, "grad_norm": 0.9375992187890128, "learning_rate": 4.957436024335108e-05, "loss": 0.6079, "num_tokens": 60473912.0, "step": 10210 }, { "epoch": 0.1089797616634483, "grad_norm": 1.112940934163212, "learning_rate": 4.957359153217605e-05, "loss": 0.6364, "num_tokens": 60506389.0, "step": 10215 }, { "epoch": 0.10903310466964676, "grad_norm": 1.2859199445518221, "learning_rate": 4.957282213411617e-05, "loss": 0.6046, "num_tokens": 60540420.0, "step": 10220 }, { "epoch": 0.10908644767584522, "grad_norm": 1.418560019235153, "learning_rate": 4.9572052049195424e-05, "loss": 0.7579, "num_tokens": 60562053.0, "step": 10225 }, { "epoch": 0.10913979068204367, "grad_norm": 1.7152391697620752, "learning_rate": 4.957128127743774e-05, "loss": 0.7176, "num_tokens": 60588569.0, "step": 10230 }, { "epoch": 0.10919313368824213, "grad_norm": 1.2447877590766352, "learning_rate": 4.957050981886713e-05, "loss": 0.5879, "num_tokens": 60622545.0, "step": 10235 }, { "epoch": 0.1092464766944406, "grad_norm": 1.4290631332437946, "learning_rate": 4.956973767350758e-05, "loss": 0.6871, "num_tokens": 60650570.0, "step": 10240 }, { "epoch": 0.10929981970063905, "grad_norm": 1.8578919249946895, "learning_rate": 4.956896484138313e-05, "loss": 0.6504, "num_tokens": 60675389.0, "step": 10245 }, { "epoch": 0.10935316270683751, "grad_norm": 1.1639143880107425, "learning_rate": 4.956819132251782e-05, "loss": 0.66, "num_tokens": 60707464.0, "step": 10250 }, { "epoch": 0.10940650571303596, "grad_norm": 1.3650678907758893, "learning_rate": 4.956741711693573e-05, "loss": 0.6907, "num_tokens": 60739532.0, "step": 10255 }, { "epoch": 0.10945984871923442, "grad_norm": 1.344513304196294, "learning_rate": 4.956664222466095e-05, "loss": 0.5196, "num_tokens": 60759215.0, "step": 10260 }, { "epoch": 0.10951319172543288, "grad_norm": 1.2739664452280144, "learning_rate": 4.956586664571759e-05, "loss": 0.6076, "num_tokens": 60782978.0, "step": 10265 }, { "epoch": 0.10956653473163133, "grad_norm": 0.9655509729585922, "learning_rate": 4.956509038012978e-05, "loss": 0.6232, "num_tokens": 60821656.0, "step": 10270 }, { "epoch": 0.10961987773782979, "grad_norm": 1.3809617391408284, "learning_rate": 4.956431342792168e-05, "loss": 0.5414, "num_tokens": 60845734.0, "step": 10275 }, { "epoch": 0.10967322074402824, "grad_norm": 1.1452942810034792, "learning_rate": 4.956353578911748e-05, "loss": 0.5969, "num_tokens": 60879934.0, "step": 10280 }, { "epoch": 0.10972656375022671, "grad_norm": 1.1662231231657734, "learning_rate": 4.956275746374135e-05, "loss": 0.5505, "num_tokens": 60898138.0, "step": 10285 }, { "epoch": 0.10977990675642517, "grad_norm": 1.085763583223784, "learning_rate": 4.956197845181753e-05, "loss": 0.627, "num_tokens": 60933839.0, "step": 10290 }, { "epoch": 0.10983324976262362, "grad_norm": 1.3471738100209216, "learning_rate": 4.9561198753370263e-05, "loss": 0.6827, "num_tokens": 60965803.0, "step": 10295 }, { "epoch": 0.10988659276882208, "grad_norm": 2.129012016430179, "learning_rate": 4.95604183684238e-05, "loss": 0.5817, "num_tokens": 60982826.0, "step": 10300 }, { "epoch": 0.10993993577502054, "grad_norm": 1.2792959852703796, "learning_rate": 4.9559637297002433e-05, "loss": 0.5318, "num_tokens": 61002671.0, "step": 10305 }, { "epoch": 0.10999327878121899, "grad_norm": 0.9053508787064476, "learning_rate": 4.955885553913047e-05, "loss": 0.5808, "num_tokens": 61031912.0, "step": 10310 }, { "epoch": 0.11004662178741745, "grad_norm": 0.8806837025449837, "learning_rate": 4.955807309483222e-05, "loss": 0.5898, "num_tokens": 61067199.0, "step": 10315 }, { "epoch": 0.1100999647936159, "grad_norm": 1.466837201122154, "learning_rate": 4.955728996413205e-05, "loss": 0.6697, "num_tokens": 61094637.0, "step": 10320 }, { "epoch": 0.11015330779981436, "grad_norm": 1.1140231022880587, "learning_rate": 4.9556506147054334e-05, "loss": 0.601, "num_tokens": 61124543.0, "step": 10325 }, { "epoch": 0.11020665080601283, "grad_norm": 0.9060572453672969, "learning_rate": 4.955572164362344e-05, "loss": 0.7203, "num_tokens": 61165584.0, "step": 10330 }, { "epoch": 0.11025999381221128, "grad_norm": 1.8760083017433429, "learning_rate": 4.9554936453863795e-05, "loss": 0.7563, "num_tokens": 61202122.0, "step": 10335 }, { "epoch": 0.11031333681840974, "grad_norm": 1.221957739207846, "learning_rate": 4.955415057779983e-05, "loss": 0.6511, "num_tokens": 61230723.0, "step": 10340 }, { "epoch": 0.1103666798246082, "grad_norm": 1.459917537294422, "learning_rate": 4.9553364015456e-05, "loss": 0.7495, "num_tokens": 61270241.0, "step": 10345 }, { "epoch": 0.11042002283080665, "grad_norm": 0.8827996793553673, "learning_rate": 4.955257676685678e-05, "loss": 0.5954, "num_tokens": 61317491.0, "step": 10350 }, { "epoch": 0.11047336583700511, "grad_norm": 1.7151533176422578, "learning_rate": 4.955178883202667e-05, "loss": 0.7166, "num_tokens": 61343354.0, "step": 10355 }, { "epoch": 0.11052670884320356, "grad_norm": 0.8981511784764096, "learning_rate": 4.955100021099018e-05, "loss": 0.5285, "num_tokens": 61365921.0, "step": 10360 }, { "epoch": 0.11058005184940202, "grad_norm": 1.5557958607156752, "learning_rate": 4.955021090377187e-05, "loss": 0.6085, "num_tokens": 61395990.0, "step": 10365 }, { "epoch": 0.11063339485560048, "grad_norm": 0.9429254477342631, "learning_rate": 4.9549420910396275e-05, "loss": 0.718, "num_tokens": 61440557.0, "step": 10370 }, { "epoch": 0.11068673786179895, "grad_norm": 1.063288600454282, "learning_rate": 4.9548630230888006e-05, "loss": 0.5764, "num_tokens": 61467085.0, "step": 10375 }, { "epoch": 0.1107400808679974, "grad_norm": 1.0359626371540156, "learning_rate": 4.9547838865271644e-05, "loss": 0.7674, "num_tokens": 61489442.0, "step": 10380 }, { "epoch": 0.11079342387419586, "grad_norm": 1.0937624521487168, "learning_rate": 4.954704681357182e-05, "loss": 0.613, "num_tokens": 61528363.0, "step": 10385 }, { "epoch": 0.11084676688039431, "grad_norm": 1.0218994673135093, "learning_rate": 4.9546254075813194e-05, "loss": 0.6087, "num_tokens": 61559774.0, "step": 10390 }, { "epoch": 0.11090010988659277, "grad_norm": 1.0587932925021293, "learning_rate": 4.954546065202043e-05, "loss": 0.6989, "num_tokens": 61606027.0, "step": 10395 }, { "epoch": 0.11095345289279122, "grad_norm": 1.1584973133269298, "learning_rate": 4.954466654221821e-05, "loss": 0.6491, "num_tokens": 61630713.0, "step": 10400 }, { "epoch": 0.11100679589898968, "grad_norm": 2.7951298552481982, "learning_rate": 4.9543871746431236e-05, "loss": 0.4541, "num_tokens": 61656648.0, "step": 10405 }, { "epoch": 0.11106013890518814, "grad_norm": 1.442122821619808, "learning_rate": 4.954307626468426e-05, "loss": 0.6231, "num_tokens": 61677618.0, "step": 10410 }, { "epoch": 0.11111348191138659, "grad_norm": 1.639909666053965, "learning_rate": 4.954228009700203e-05, "loss": 0.5721, "num_tokens": 61711447.0, "step": 10415 }, { "epoch": 0.11116682491758506, "grad_norm": 1.5102579882433167, "learning_rate": 4.954148324340932e-05, "loss": 0.6881, "num_tokens": 61734501.0, "step": 10420 }, { "epoch": 0.11122016792378352, "grad_norm": 0.8284805798548615, "learning_rate": 4.954068570393093e-05, "loss": 0.566, "num_tokens": 61772063.0, "step": 10425 }, { "epoch": 0.11127351092998197, "grad_norm": 0.9953876530682969, "learning_rate": 4.953988747859167e-05, "loss": 0.5932, "num_tokens": 61815745.0, "step": 10430 }, { "epoch": 0.11132685393618043, "grad_norm": 1.5259320993877055, "learning_rate": 4.953908856741638e-05, "loss": 0.6833, "num_tokens": 61846272.0, "step": 10435 }, { "epoch": 0.11138019694237888, "grad_norm": 1.314383804963753, "learning_rate": 4.953828897042993e-05, "loss": 0.6014, "num_tokens": 61880187.0, "step": 10440 }, { "epoch": 0.11143353994857734, "grad_norm": 1.1651024045265739, "learning_rate": 4.9537488687657185e-05, "loss": 0.6223, "num_tokens": 61906419.0, "step": 10445 }, { "epoch": 0.1114868829547758, "grad_norm": 1.1086837119953032, "learning_rate": 4.9536687719123065e-05, "loss": 0.5584, "num_tokens": 61935552.0, "step": 10450 }, { "epoch": 0.11154022596097425, "grad_norm": 1.2717817002419272, "learning_rate": 4.9535886064852484e-05, "loss": 0.4994, "num_tokens": 61955906.0, "step": 10455 }, { "epoch": 0.11159356896717271, "grad_norm": 1.7619884500473508, "learning_rate": 4.953508372487039e-05, "loss": 0.5931, "num_tokens": 61977422.0, "step": 10460 }, { "epoch": 0.11164691197337118, "grad_norm": 0.7758590453494878, "learning_rate": 4.953428069920176e-05, "loss": 0.6054, "num_tokens": 62035441.0, "step": 10465 }, { "epoch": 0.11170025497956963, "grad_norm": 1.0288764351496535, "learning_rate": 4.953347698787157e-05, "loss": 0.6655, "num_tokens": 62076351.0, "step": 10470 }, { "epoch": 0.11175359798576809, "grad_norm": 1.257042701374646, "learning_rate": 4.953267259090483e-05, "loss": 0.693, "num_tokens": 62115793.0, "step": 10475 }, { "epoch": 0.11180694099196654, "grad_norm": 1.4833987145617322, "learning_rate": 4.9531867508326585e-05, "loss": 0.6766, "num_tokens": 62149084.0, "step": 10480 }, { "epoch": 0.111860283998165, "grad_norm": 0.8781509869800607, "learning_rate": 4.9531061740161876e-05, "loss": 0.6113, "num_tokens": 62192191.0, "step": 10485 }, { "epoch": 0.11191362700436346, "grad_norm": 1.2042744419672746, "learning_rate": 4.953025528643577e-05, "loss": 0.6791, "num_tokens": 62238889.0, "step": 10490 }, { "epoch": 0.11196697001056191, "grad_norm": 1.1849271188475408, "learning_rate": 4.952944814717338e-05, "loss": 0.7437, "num_tokens": 62264314.0, "step": 10495 }, { "epoch": 0.11202031301676037, "grad_norm": 1.4332051777732497, "learning_rate": 4.952864032239981e-05, "loss": 0.6814, "num_tokens": 62294671.0, "step": 10500 }, { "epoch": 0.11207365602295882, "grad_norm": 1.1813838145325453, "learning_rate": 4.95278318121402e-05, "loss": 0.5367, "num_tokens": 62315508.0, "step": 10505 }, { "epoch": 0.11212699902915729, "grad_norm": 1.181595593598301, "learning_rate": 4.952702261641972e-05, "loss": 0.7355, "num_tokens": 62335972.0, "step": 10510 }, { "epoch": 0.11218034203535575, "grad_norm": 1.013200488974656, "learning_rate": 4.952621273526353e-05, "loss": 0.6023, "num_tokens": 62367975.0, "step": 10515 }, { "epoch": 0.1122336850415542, "grad_norm": 1.0552063826209996, "learning_rate": 4.952540216869684e-05, "loss": 0.6423, "num_tokens": 62398238.0, "step": 10520 }, { "epoch": 0.11228702804775266, "grad_norm": 2.596764546716407, "learning_rate": 4.9524590916744886e-05, "loss": 0.6421, "num_tokens": 62414779.0, "step": 10525 }, { "epoch": 0.11234037105395112, "grad_norm": 1.7560508274759838, "learning_rate": 4.952377897943289e-05, "loss": 0.7146, "num_tokens": 62452093.0, "step": 10530 }, { "epoch": 0.11239371406014957, "grad_norm": 1.2269248462952285, "learning_rate": 4.952296635678614e-05, "loss": 0.7248, "num_tokens": 62479547.0, "step": 10535 }, { "epoch": 0.11244705706634803, "grad_norm": 1.106755282081983, "learning_rate": 4.9522153048829914e-05, "loss": 0.6827, "num_tokens": 62510998.0, "step": 10540 }, { "epoch": 0.11250040007254648, "grad_norm": 1.2171498322323504, "learning_rate": 4.952133905558952e-05, "loss": 0.5819, "num_tokens": 62541037.0, "step": 10545 }, { "epoch": 0.11255374307874494, "grad_norm": 0.9359111705775564, "learning_rate": 4.952052437709028e-05, "loss": 0.5271, "num_tokens": 62585033.0, "step": 10550 }, { "epoch": 0.11260708608494341, "grad_norm": 1.0016742259354703, "learning_rate": 4.9519709013357565e-05, "loss": 0.6825, "num_tokens": 62632874.0, "step": 10555 }, { "epoch": 0.11266042909114186, "grad_norm": 1.5019727508670018, "learning_rate": 4.951889296441673e-05, "loss": 0.6533, "num_tokens": 62662896.0, "step": 10560 }, { "epoch": 0.11271377209734032, "grad_norm": 1.0108943053406176, "learning_rate": 4.951807623029317e-05, "loss": 0.6799, "num_tokens": 62699912.0, "step": 10565 }, { "epoch": 0.11276711510353878, "grad_norm": 1.5403168623957284, "learning_rate": 4.951725881101231e-05, "loss": 0.6416, "num_tokens": 62722532.0, "step": 10570 }, { "epoch": 0.11282045810973723, "grad_norm": 1.2221334031443418, "learning_rate": 4.951644070659957e-05, "loss": 0.5721, "num_tokens": 62753507.0, "step": 10575 }, { "epoch": 0.11287380111593569, "grad_norm": 0.8816642492065688, "learning_rate": 4.951562191708043e-05, "loss": 0.5967, "num_tokens": 62802931.0, "step": 10580 }, { "epoch": 0.11292714412213414, "grad_norm": 1.2161984323170965, "learning_rate": 4.951480244248035e-05, "loss": 0.7556, "num_tokens": 62833072.0, "step": 10585 }, { "epoch": 0.1129804871283326, "grad_norm": 1.3052274942920437, "learning_rate": 4.951398228282484e-05, "loss": 0.8117, "num_tokens": 62871854.0, "step": 10590 }, { "epoch": 0.11303383013453105, "grad_norm": 0.8672100332773013, "learning_rate": 4.9513161438139426e-05, "loss": 0.62, "num_tokens": 62907858.0, "step": 10595 }, { "epoch": 0.11308717314072952, "grad_norm": 0.9780361704145875, "learning_rate": 4.9512339908449636e-05, "loss": 0.6878, "num_tokens": 62932608.0, "step": 10600 }, { "epoch": 0.11314051614692798, "grad_norm": 2.136167458338121, "learning_rate": 4.9511517693781046e-05, "loss": 0.6726, "num_tokens": 62960386.0, "step": 10605 }, { "epoch": 0.11319385915312644, "grad_norm": 1.0514008368126848, "learning_rate": 4.951069479415924e-05, "loss": 0.6381, "num_tokens": 62998364.0, "step": 10610 }, { "epoch": 0.11324720215932489, "grad_norm": 1.212107023939414, "learning_rate": 4.9509871209609815e-05, "loss": 0.6265, "num_tokens": 63034057.0, "step": 10615 }, { "epoch": 0.11330054516552335, "grad_norm": 1.056459829309299, "learning_rate": 4.9509046940158415e-05, "loss": 0.6084, "num_tokens": 63065002.0, "step": 10620 }, { "epoch": 0.1133538881717218, "grad_norm": 1.3301751510987982, "learning_rate": 4.950822198583068e-05, "loss": 0.7766, "num_tokens": 63099383.0, "step": 10625 }, { "epoch": 0.11340723117792026, "grad_norm": 1.5704104876293707, "learning_rate": 4.950739634665229e-05, "loss": 0.4806, "num_tokens": 63112421.0, "step": 10630 }, { "epoch": 0.11346057418411871, "grad_norm": 1.352220616726085, "learning_rate": 4.950657002264892e-05, "loss": 0.7045, "num_tokens": 63132102.0, "step": 10635 }, { "epoch": 0.11351391719031717, "grad_norm": 1.4795335844207074, "learning_rate": 4.950574301384629e-05, "loss": 0.5965, "num_tokens": 63159787.0, "step": 10640 }, { "epoch": 0.11356726019651564, "grad_norm": 1.766076595608571, "learning_rate": 4.950491532027015e-05, "loss": 0.7597, "num_tokens": 63203500.0, "step": 10645 }, { "epoch": 0.1136206032027141, "grad_norm": 1.3990006990427244, "learning_rate": 4.950408694194624e-05, "loss": 0.7555, "num_tokens": 63240285.0, "step": 10650 }, { "epoch": 0.11367394620891255, "grad_norm": 1.5076348130015347, "learning_rate": 4.9503257878900346e-05, "loss": 0.6289, "num_tokens": 63273458.0, "step": 10655 }, { "epoch": 0.11372728921511101, "grad_norm": 1.0287240775018074, "learning_rate": 4.950242813115825e-05, "loss": 0.6163, "num_tokens": 63309752.0, "step": 10660 }, { "epoch": 0.11378063222130946, "grad_norm": 0.8966503980016657, "learning_rate": 4.95015976987458e-05, "loss": 0.7067, "num_tokens": 63335955.0, "step": 10665 }, { "epoch": 0.11383397522750792, "grad_norm": 1.4864347018929345, "learning_rate": 4.950076658168881e-05, "loss": 0.6026, "num_tokens": 63368168.0, "step": 10670 }, { "epoch": 0.11388731823370637, "grad_norm": 1.5724766969354946, "learning_rate": 4.949993478001316e-05, "loss": 0.7232, "num_tokens": 63382083.0, "step": 10675 }, { "epoch": 0.11394066123990483, "grad_norm": 1.3453212860912964, "learning_rate": 4.949910229374473e-05, "loss": 0.753, "num_tokens": 63418936.0, "step": 10680 }, { "epoch": 0.11399400424610329, "grad_norm": 1.1653268017431104, "learning_rate": 4.949826912290943e-05, "loss": 0.6679, "num_tokens": 63456419.0, "step": 10685 }, { "epoch": 0.11404734725230176, "grad_norm": 1.3551120359844713, "learning_rate": 4.949743526753317e-05, "loss": 0.586, "num_tokens": 63479434.0, "step": 10690 }, { "epoch": 0.11410069025850021, "grad_norm": 1.2151511018731609, "learning_rate": 4.9496600727641915e-05, "loss": 0.6794, "num_tokens": 63502856.0, "step": 10695 }, { "epoch": 0.11415403326469867, "grad_norm": 1.4971389030723004, "learning_rate": 4.949576550326163e-05, "loss": 0.5679, "num_tokens": 63539780.0, "step": 10700 }, { "epoch": 0.11420737627089712, "grad_norm": 1.6195979069316424, "learning_rate": 4.94949295944183e-05, "loss": 0.6907, "num_tokens": 63558625.0, "step": 10705 }, { "epoch": 0.11426071927709558, "grad_norm": 1.1320763781299927, "learning_rate": 4.9494093001137936e-05, "loss": 0.6438, "num_tokens": 63588407.0, "step": 10710 }, { "epoch": 0.11431406228329404, "grad_norm": 2.318803377253386, "learning_rate": 4.949325572344658e-05, "loss": 0.7962, "num_tokens": 63615860.0, "step": 10715 }, { "epoch": 0.11436740528949249, "grad_norm": 1.5221344287600933, "learning_rate": 4.9492417761370276e-05, "loss": 0.5299, "num_tokens": 63644240.0, "step": 10720 }, { "epoch": 0.11442074829569095, "grad_norm": 1.4255176642508958, "learning_rate": 4.94915791149351e-05, "loss": 0.5021, "num_tokens": 63661481.0, "step": 10725 }, { "epoch": 0.1144740913018894, "grad_norm": 1.0349075544204929, "learning_rate": 4.949073978416717e-05, "loss": 0.5634, "num_tokens": 63689562.0, "step": 10730 }, { "epoch": 0.11452743430808787, "grad_norm": 1.154597746994196, "learning_rate": 4.948989976909257e-05, "loss": 0.5605, "num_tokens": 63709206.0, "step": 10735 }, { "epoch": 0.11458077731428633, "grad_norm": 1.0605156130000952, "learning_rate": 4.948905906973748e-05, "loss": 0.7018, "num_tokens": 63745280.0, "step": 10740 }, { "epoch": 0.11463412032048478, "grad_norm": 1.2348552610845036, "learning_rate": 4.948821768612802e-05, "loss": 0.4877, "num_tokens": 63770206.0, "step": 10745 }, { "epoch": 0.11468746332668324, "grad_norm": 1.0978823889284963, "learning_rate": 4.94873756182904e-05, "loss": 0.7752, "num_tokens": 63810357.0, "step": 10750 }, { "epoch": 0.1147408063328817, "grad_norm": 2.750060706722044, "learning_rate": 4.948653286625081e-05, "loss": 0.6245, "num_tokens": 63829037.0, "step": 10755 }, { "epoch": 0.11479414933908015, "grad_norm": 1.5042083979488892, "learning_rate": 4.948568943003547e-05, "loss": 0.6657, "num_tokens": 63866942.0, "step": 10760 }, { "epoch": 0.1148474923452786, "grad_norm": 1.433414442829087, "learning_rate": 4.948484530967065e-05, "loss": 0.7004, "num_tokens": 63897929.0, "step": 10765 }, { "epoch": 0.11490083535147706, "grad_norm": 1.4692578918225876, "learning_rate": 4.94840005051826e-05, "loss": 0.8114, "num_tokens": 63928532.0, "step": 10770 }, { "epoch": 0.11495417835767552, "grad_norm": 1.304047073921986, "learning_rate": 4.948315501659761e-05, "loss": 0.5783, "num_tokens": 63949046.0, "step": 10775 }, { "epoch": 0.11500752136387399, "grad_norm": 1.7048120964163638, "learning_rate": 4.948230884394199e-05, "loss": 0.6341, "num_tokens": 64001816.0, "step": 10780 }, { "epoch": 0.11506086437007244, "grad_norm": 1.7419054071296567, "learning_rate": 4.948146198724207e-05, "loss": 0.6565, "num_tokens": 64021802.0, "step": 10785 }, { "epoch": 0.1151142073762709, "grad_norm": 0.8530096248534044, "learning_rate": 4.9480614446524206e-05, "loss": 0.5571, "num_tokens": 64058849.0, "step": 10790 }, { "epoch": 0.11516755038246936, "grad_norm": 4.809305812186308, "learning_rate": 4.947976622181476e-05, "loss": 0.6469, "num_tokens": 64080343.0, "step": 10795 }, { "epoch": 0.11522089338866781, "grad_norm": 1.5471870021787142, "learning_rate": 4.947891731314015e-05, "loss": 0.5286, "num_tokens": 64108252.0, "step": 10800 }, { "epoch": 0.11527423639486627, "grad_norm": 1.0472296289770602, "learning_rate": 4.947806772052678e-05, "loss": 0.6488, "num_tokens": 64131355.0, "step": 10805 }, { "epoch": 0.11532757940106472, "grad_norm": 2.230240015909093, "learning_rate": 4.947721744400107e-05, "loss": 0.6959, "num_tokens": 64152699.0, "step": 10810 }, { "epoch": 0.11538092240726318, "grad_norm": 1.882315949845475, "learning_rate": 4.9476366483589514e-05, "loss": 0.7651, "num_tokens": 64184472.0, "step": 10815 }, { "epoch": 0.11543426541346163, "grad_norm": 1.1059117122561914, "learning_rate": 4.947551483931856e-05, "loss": 0.619, "num_tokens": 64221374.0, "step": 10820 }, { "epoch": 0.1154876084196601, "grad_norm": 1.4169408480983914, "learning_rate": 4.947466251121473e-05, "loss": 0.6438, "num_tokens": 64247124.0, "step": 10825 }, { "epoch": 0.11554095142585856, "grad_norm": 1.4570787306648862, "learning_rate": 4.947380949930455e-05, "loss": 0.6437, "num_tokens": 64279200.0, "step": 10830 }, { "epoch": 0.11559429443205702, "grad_norm": 4.985395405350341, "learning_rate": 4.9472955803614535e-05, "loss": 0.8324, "num_tokens": 64314531.0, "step": 10835 }, { "epoch": 0.11564763743825547, "grad_norm": 1.4341341881648544, "learning_rate": 4.947210142417128e-05, "loss": 0.5735, "num_tokens": 64334789.0, "step": 10840 }, { "epoch": 0.11570098044445393, "grad_norm": 1.18369661759386, "learning_rate": 4.947124636100136e-05, "loss": 0.5935, "num_tokens": 64362115.0, "step": 10845 }, { "epoch": 0.11575432345065238, "grad_norm": 1.5335854575529826, "learning_rate": 4.947039061413138e-05, "loss": 0.6458, "num_tokens": 64397410.0, "step": 10850 }, { "epoch": 0.11580766645685084, "grad_norm": 0.8100383510832272, "learning_rate": 4.946953418358797e-05, "loss": 0.5596, "num_tokens": 64430658.0, "step": 10855 }, { "epoch": 0.1158610094630493, "grad_norm": 1.6698463272688369, "learning_rate": 4.946867706939779e-05, "loss": 0.56, "num_tokens": 64450951.0, "step": 10860 }, { "epoch": 0.11591435246924775, "grad_norm": 1.0727202033765921, "learning_rate": 4.94678192715875e-05, "loss": 0.864, "num_tokens": 64490465.0, "step": 10865 }, { "epoch": 0.11596769547544622, "grad_norm": 1.152291194464256, "learning_rate": 4.94669607901838e-05, "loss": 0.615, "num_tokens": 64517639.0, "step": 10870 }, { "epoch": 0.11602103848164468, "grad_norm": 1.8234314903487558, "learning_rate": 4.94661016252134e-05, "loss": 0.6129, "num_tokens": 64535884.0, "step": 10875 }, { "epoch": 0.11607438148784313, "grad_norm": 1.3767806668429936, "learning_rate": 4.946524177670304e-05, "loss": 0.8166, "num_tokens": 64564660.0, "step": 10880 }, { "epoch": 0.11612772449404159, "grad_norm": 1.2363677671077593, "learning_rate": 4.946438124467947e-05, "loss": 0.5012, "num_tokens": 64591859.0, "step": 10885 }, { "epoch": 0.11618106750024004, "grad_norm": 1.3039957078553934, "learning_rate": 4.9463520029169477e-05, "loss": 0.6271, "num_tokens": 64625666.0, "step": 10890 }, { "epoch": 0.1162344105064385, "grad_norm": 1.4086593331366737, "learning_rate": 4.946265813019985e-05, "loss": 0.7887, "num_tokens": 64653637.0, "step": 10895 }, { "epoch": 0.11628775351263695, "grad_norm": 0.9524760303067806, "learning_rate": 4.946179554779741e-05, "loss": 0.5353, "num_tokens": 64679150.0, "step": 10900 }, { "epoch": 0.11634109651883541, "grad_norm": 1.5477744043818795, "learning_rate": 4.946093228198901e-05, "loss": 0.5784, "num_tokens": 64704787.0, "step": 10905 }, { "epoch": 0.11639443952503387, "grad_norm": 1.1007719104307243, "learning_rate": 4.9460068332801505e-05, "loss": 0.71, "num_tokens": 64750362.0, "step": 10910 }, { "epoch": 0.11644778253123234, "grad_norm": 2.252187444843127, "learning_rate": 4.9459203700261786e-05, "loss": 0.5568, "num_tokens": 64784214.0, "step": 10915 }, { "epoch": 0.11650112553743079, "grad_norm": 1.2244937392391222, "learning_rate": 4.945833838439675e-05, "loss": 0.5567, "num_tokens": 64800155.0, "step": 10920 }, { "epoch": 0.11655446854362925, "grad_norm": 1.2691911579848472, "learning_rate": 4.9457472385233324e-05, "loss": 0.7004, "num_tokens": 64829820.0, "step": 10925 }, { "epoch": 0.1166078115498277, "grad_norm": 1.2629161825913315, "learning_rate": 4.9456605702798466e-05, "loss": 0.717, "num_tokens": 64851957.0, "step": 10930 }, { "epoch": 0.11666115455602616, "grad_norm": 1.0341189964409507, "learning_rate": 4.945573833711913e-05, "loss": 0.715, "num_tokens": 64895676.0, "step": 10935 }, { "epoch": 0.11671449756222461, "grad_norm": 1.2253147083859963, "learning_rate": 4.9454870288222325e-05, "loss": 0.6916, "num_tokens": 64925850.0, "step": 10940 }, { "epoch": 0.11676784056842307, "grad_norm": 1.0667689056875262, "learning_rate": 4.945400155613504e-05, "loss": 0.7264, "num_tokens": 64964051.0, "step": 10945 }, { "epoch": 0.11682118357462153, "grad_norm": 1.1618395904755188, "learning_rate": 4.945313214088433e-05, "loss": 0.762, "num_tokens": 65004918.0, "step": 10950 }, { "epoch": 0.11687452658081998, "grad_norm": 1.187364184169992, "learning_rate": 4.945226204249724e-05, "loss": 0.63, "num_tokens": 65026702.0, "step": 10955 }, { "epoch": 0.11692786958701845, "grad_norm": 1.0780404829099435, "learning_rate": 4.9451391261000844e-05, "loss": 0.7263, "num_tokens": 65057882.0, "step": 10960 }, { "epoch": 0.11698121259321691, "grad_norm": 1.1275301608222854, "learning_rate": 4.945051979642224e-05, "loss": 0.6504, "num_tokens": 65090011.0, "step": 10965 }, { "epoch": 0.11703455559941536, "grad_norm": 1.3470813473406855, "learning_rate": 4.944964764878856e-05, "loss": 0.6619, "num_tokens": 65106137.0, "step": 10970 }, { "epoch": 0.11708789860561382, "grad_norm": 1.7724291743148717, "learning_rate": 4.944877481812692e-05, "loss": 0.5492, "num_tokens": 65131520.0, "step": 10975 }, { "epoch": 0.11714124161181227, "grad_norm": 1.3964882279054107, "learning_rate": 4.9447901304464496e-05, "loss": 0.6561, "num_tokens": 65172212.0, "step": 10980 }, { "epoch": 0.11719458461801073, "grad_norm": 1.0568398691486214, "learning_rate": 4.9447027107828456e-05, "loss": 0.6514, "num_tokens": 65197145.0, "step": 10985 }, { "epoch": 0.11724792762420919, "grad_norm": 1.4383300919204292, "learning_rate": 4.944615222824603e-05, "loss": 0.5588, "num_tokens": 65223209.0, "step": 10990 }, { "epoch": 0.11730127063040764, "grad_norm": 1.1491891273879355, "learning_rate": 4.944527666574441e-05, "loss": 0.5007, "num_tokens": 65244902.0, "step": 10995 }, { "epoch": 0.1173546136366061, "grad_norm": 1.0343560600420998, "learning_rate": 4.9444400420350865e-05, "loss": 0.5553, "num_tokens": 65274386.0, "step": 11000 }, { "epoch": 0.11740795664280457, "grad_norm": 0.9188743925528048, "learning_rate": 4.944352349209265e-05, "loss": 0.7409, "num_tokens": 65319671.0, "step": 11005 }, { "epoch": 0.11746129964900302, "grad_norm": 1.2340160584805193, "learning_rate": 4.9442645880997054e-05, "loss": 0.6617, "num_tokens": 65365954.0, "step": 11010 }, { "epoch": 0.11751464265520148, "grad_norm": 2.224556700208862, "learning_rate": 4.9441767587091405e-05, "loss": 0.8398, "num_tokens": 65411001.0, "step": 11015 }, { "epoch": 0.11756798566139993, "grad_norm": 1.893384623992745, "learning_rate": 4.944088861040301e-05, "loss": 0.5363, "num_tokens": 65429789.0, "step": 11020 }, { "epoch": 0.11762132866759839, "grad_norm": 1.3191875108561075, "learning_rate": 4.9440008950959224e-05, "loss": 0.6956, "num_tokens": 65450968.0, "step": 11025 }, { "epoch": 0.11767467167379685, "grad_norm": 1.082129073545712, "learning_rate": 4.943912860878743e-05, "loss": 0.6213, "num_tokens": 65497883.0, "step": 11030 }, { "epoch": 0.1177280146799953, "grad_norm": 1.385638448363517, "learning_rate": 4.9438247583915016e-05, "loss": 0.5815, "num_tokens": 65536789.0, "step": 11035 }, { "epoch": 0.11778135768619376, "grad_norm": 0.9932054184581816, "learning_rate": 4.9437365876369404e-05, "loss": 0.5647, "num_tokens": 65561717.0, "step": 11040 }, { "epoch": 0.11783470069239221, "grad_norm": 1.7486047209352447, "learning_rate": 4.943648348617802e-05, "loss": 0.7649, "num_tokens": 65591394.0, "step": 11045 }, { "epoch": 0.11788804369859068, "grad_norm": 1.349866832497625, "learning_rate": 4.943560041336833e-05, "loss": 0.5939, "num_tokens": 65617193.0, "step": 11050 }, { "epoch": 0.11794138670478914, "grad_norm": 1.227907062462705, "learning_rate": 4.9434716657967814e-05, "loss": 0.7638, "num_tokens": 65647360.0, "step": 11055 }, { "epoch": 0.1179947297109876, "grad_norm": 1.5607006605036025, "learning_rate": 4.9433832220003976e-05, "loss": 0.5592, "num_tokens": 65669205.0, "step": 11060 }, { "epoch": 0.11804807271718605, "grad_norm": 1.2336163027943259, "learning_rate": 4.943294709950432e-05, "loss": 0.5618, "num_tokens": 65690019.0, "step": 11065 }, { "epoch": 0.1181014157233845, "grad_norm": 1.784528432371308, "learning_rate": 4.943206129649642e-05, "loss": 0.673, "num_tokens": 65717526.0, "step": 11070 }, { "epoch": 0.11815475872958296, "grad_norm": 1.4415449304455301, "learning_rate": 4.943117481100781e-05, "loss": 0.6177, "num_tokens": 65743675.0, "step": 11075 }, { "epoch": 0.11820810173578142, "grad_norm": 0.981820772984121, "learning_rate": 4.943028764306609e-05, "loss": 0.6257, "num_tokens": 65787565.0, "step": 11080 }, { "epoch": 0.11826144474197987, "grad_norm": 1.286603933535025, "learning_rate": 4.942939979269886e-05, "loss": 0.7276, "num_tokens": 65812265.0, "step": 11085 }, { "epoch": 0.11831478774817833, "grad_norm": 1.566634109242587, "learning_rate": 4.9428511259933764e-05, "loss": 0.7049, "num_tokens": 65834877.0, "step": 11090 }, { "epoch": 0.1183681307543768, "grad_norm": 1.6040278558205094, "learning_rate": 4.942762204479843e-05, "loss": 0.6814, "num_tokens": 65850839.0, "step": 11095 }, { "epoch": 0.11842147376057525, "grad_norm": 1.442385959964582, "learning_rate": 4.942673214732054e-05, "loss": 0.7386, "num_tokens": 65869463.0, "step": 11100 }, { "epoch": 0.11847481676677371, "grad_norm": 2.0247667910152174, "learning_rate": 4.9425841567527785e-05, "loss": 0.6554, "num_tokens": 65898810.0, "step": 11105 }, { "epoch": 0.11852815977297217, "grad_norm": 1.321325328297332, "learning_rate": 4.942495030544788e-05, "loss": 0.6724, "num_tokens": 65932376.0, "step": 11110 }, { "epoch": 0.11858150277917062, "grad_norm": 1.2679751290254366, "learning_rate": 4.942405836110855e-05, "loss": 0.6808, "num_tokens": 65965503.0, "step": 11115 }, { "epoch": 0.11863484578536908, "grad_norm": 1.270884503922113, "learning_rate": 4.942316573453756e-05, "loss": 0.7012, "num_tokens": 65991955.0, "step": 11120 }, { "epoch": 0.11868818879156753, "grad_norm": 1.2425016886456606, "learning_rate": 4.942227242576269e-05, "loss": 0.7166, "num_tokens": 66012220.0, "step": 11125 }, { "epoch": 0.11874153179776599, "grad_norm": 1.0585559495953611, "learning_rate": 4.942137843481172e-05, "loss": 0.6545, "num_tokens": 66044370.0, "step": 11130 }, { "epoch": 0.11879487480396445, "grad_norm": 1.0260543368780137, "learning_rate": 4.9420483761712497e-05, "loss": 0.6741, "num_tokens": 66081626.0, "step": 11135 }, { "epoch": 0.11884821781016291, "grad_norm": 1.4217172498066644, "learning_rate": 4.941958840649284e-05, "loss": 0.7176, "num_tokens": 66117968.0, "step": 11140 }, { "epoch": 0.11890156081636137, "grad_norm": 1.1556657517311952, "learning_rate": 4.9418692369180604e-05, "loss": 0.679, "num_tokens": 66139621.0, "step": 11145 }, { "epoch": 0.11895490382255983, "grad_norm": 1.4726818195548075, "learning_rate": 4.9417795649803697e-05, "loss": 0.6489, "num_tokens": 66152381.0, "step": 11150 }, { "epoch": 0.11900824682875828, "grad_norm": 1.7662598546618096, "learning_rate": 4.9416898248390005e-05, "loss": 0.7439, "num_tokens": 66190204.0, "step": 11155 }, { "epoch": 0.11906158983495674, "grad_norm": 1.9554227490601281, "learning_rate": 4.9416000164967455e-05, "loss": 0.7198, "num_tokens": 66211753.0, "step": 11160 }, { "epoch": 0.1191149328411552, "grad_norm": 1.736099753934411, "learning_rate": 4.9415101399564e-05, "loss": 0.5737, "num_tokens": 66236475.0, "step": 11165 }, { "epoch": 0.11916827584735365, "grad_norm": 0.8623755444383127, "learning_rate": 4.941420195220761e-05, "loss": 0.6401, "num_tokens": 66283536.0, "step": 11170 }, { "epoch": 0.1192216188535521, "grad_norm": 1.8086783759998506, "learning_rate": 4.941330182292626e-05, "loss": 0.8137, "num_tokens": 66318808.0, "step": 11175 }, { "epoch": 0.11927496185975056, "grad_norm": 2.3470834117985215, "learning_rate": 4.941240101174797e-05, "loss": 0.634, "num_tokens": 66339004.0, "step": 11180 }, { "epoch": 0.11932830486594903, "grad_norm": 1.0544086927345506, "learning_rate": 4.9411499518700775e-05, "loss": 0.5908, "num_tokens": 66374331.0, "step": 11185 }, { "epoch": 0.11938164787214749, "grad_norm": 1.0438547703664252, "learning_rate": 4.941059734381272e-05, "loss": 0.5882, "num_tokens": 66412134.0, "step": 11190 }, { "epoch": 0.11943499087834594, "grad_norm": 1.1148580573355404, "learning_rate": 4.9409694487111876e-05, "loss": 0.7236, "num_tokens": 66452128.0, "step": 11195 }, { "epoch": 0.1194883338845444, "grad_norm": 1.1346170461288332, "learning_rate": 4.940879094862634e-05, "loss": 0.6054, "num_tokens": 66485190.0, "step": 11200 }, { "epoch": 0.11954167689074285, "grad_norm": 1.3398549367036636, "learning_rate": 4.9407886728384245e-05, "loss": 0.6501, "num_tokens": 66508858.0, "step": 11205 }, { "epoch": 0.11959501989694131, "grad_norm": 1.6065041082448441, "learning_rate": 4.94069818264137e-05, "loss": 0.5752, "num_tokens": 66525806.0, "step": 11210 }, { "epoch": 0.11964836290313977, "grad_norm": 1.1106253152311514, "learning_rate": 4.94060762427429e-05, "loss": 0.6978, "num_tokens": 66548385.0, "step": 11215 }, { "epoch": 0.11970170590933822, "grad_norm": 1.2009282070688667, "learning_rate": 4.9405169977399986e-05, "loss": 0.5635, "num_tokens": 66574558.0, "step": 11220 }, { "epoch": 0.11975504891553668, "grad_norm": 1.013177412949672, "learning_rate": 4.940426303041318e-05, "loss": 0.7341, "num_tokens": 66615005.0, "step": 11225 }, { "epoch": 0.11980839192173515, "grad_norm": 1.350764788014616, "learning_rate": 4.940335540181071e-05, "loss": 0.5511, "num_tokens": 66638484.0, "step": 11230 }, { "epoch": 0.1198617349279336, "grad_norm": 1.2398607724519073, "learning_rate": 4.9402447091620805e-05, "loss": 0.6769, "num_tokens": 66665155.0, "step": 11235 }, { "epoch": 0.11991507793413206, "grad_norm": 1.3231628749135664, "learning_rate": 4.940153809987173e-05, "loss": 0.6189, "num_tokens": 66689604.0, "step": 11240 }, { "epoch": 0.11996842094033051, "grad_norm": 1.2196677014017696, "learning_rate": 4.9400628426591785e-05, "loss": 0.6741, "num_tokens": 66711300.0, "step": 11245 }, { "epoch": 0.12002176394652897, "grad_norm": 0.9391736733985094, "learning_rate": 4.939971807180926e-05, "loss": 0.5839, "num_tokens": 66737228.0, "step": 11250 }, { "epoch": 0.12007510695272743, "grad_norm": 0.9933229822945506, "learning_rate": 4.9398807035552505e-05, "loss": 0.7483, "num_tokens": 66784861.0, "step": 11255 }, { "epoch": 0.12012844995892588, "grad_norm": 1.481409957082661, "learning_rate": 4.9397895317849835e-05, "loss": 0.6849, "num_tokens": 66801008.0, "step": 11260 }, { "epoch": 0.12018179296512434, "grad_norm": 1.1224230701967146, "learning_rate": 4.9396982918729664e-05, "loss": 0.6541, "num_tokens": 66843656.0, "step": 11265 }, { "epoch": 0.12023513597132279, "grad_norm": 1.9035353111724214, "learning_rate": 4.939606983822035e-05, "loss": 0.4875, "num_tokens": 66863752.0, "step": 11270 }, { "epoch": 0.12028847897752126, "grad_norm": 1.3588489896170173, "learning_rate": 4.939515607635032e-05, "loss": 0.6509, "num_tokens": 66911988.0, "step": 11275 }, { "epoch": 0.12034182198371972, "grad_norm": 1.5670952333271218, "learning_rate": 4.939424163314801e-05, "loss": 0.8646, "num_tokens": 66953512.0, "step": 11280 }, { "epoch": 0.12039516498991817, "grad_norm": 1.3798176558912172, "learning_rate": 4.9393326508641867e-05, "loss": 0.6804, "num_tokens": 66976890.0, "step": 11285 }, { "epoch": 0.12044850799611663, "grad_norm": 1.678218789113345, "learning_rate": 4.939241070286038e-05, "loss": 0.7007, "num_tokens": 67010730.0, "step": 11290 }, { "epoch": 0.12050185100231509, "grad_norm": 1.3137181303214758, "learning_rate": 4.939149421583204e-05, "loss": 0.5243, "num_tokens": 67029144.0, "step": 11295 }, { "epoch": 0.12055519400851354, "grad_norm": 1.0908566823470702, "learning_rate": 4.939057704758536e-05, "loss": 0.6077, "num_tokens": 67061984.0, "step": 11300 }, { "epoch": 0.120608537014712, "grad_norm": 1.6945501172996298, "learning_rate": 4.938965919814889e-05, "loss": 0.6308, "num_tokens": 67113897.0, "step": 11305 }, { "epoch": 0.12066188002091045, "grad_norm": 1.4164236033799678, "learning_rate": 4.938874066755119e-05, "loss": 0.6977, "num_tokens": 67143757.0, "step": 11310 }, { "epoch": 0.12071522302710891, "grad_norm": 1.8693139445901714, "learning_rate": 4.9387821455820846e-05, "loss": 0.7819, "num_tokens": 67172367.0, "step": 11315 }, { "epoch": 0.12076856603330738, "grad_norm": 1.0097897910910838, "learning_rate": 4.938690156298645e-05, "loss": 0.6037, "num_tokens": 67216400.0, "step": 11320 }, { "epoch": 0.12082190903950583, "grad_norm": 1.0882225304832949, "learning_rate": 4.938598098907663e-05, "loss": 0.6706, "num_tokens": 67249072.0, "step": 11325 }, { "epoch": 0.12087525204570429, "grad_norm": 1.8314300865662825, "learning_rate": 4.9385059734120044e-05, "loss": 0.6765, "num_tokens": 67279465.0, "step": 11330 }, { "epoch": 0.12092859505190275, "grad_norm": 1.3300339097497007, "learning_rate": 4.938413779814535e-05, "loss": 0.6063, "num_tokens": 67305095.0, "step": 11335 }, { "epoch": 0.1209819380581012, "grad_norm": 1.2205625798062345, "learning_rate": 4.938321518118124e-05, "loss": 0.6861, "num_tokens": 67353543.0, "step": 11340 }, { "epoch": 0.12103528106429966, "grad_norm": 1.7627257856177563, "learning_rate": 4.9382291883256425e-05, "loss": 0.6484, "num_tokens": 67382648.0, "step": 11345 }, { "epoch": 0.12108862407049811, "grad_norm": 1.4553333082179012, "learning_rate": 4.9381367904399634e-05, "loss": 0.6793, "num_tokens": 67402835.0, "step": 11350 }, { "epoch": 0.12114196707669657, "grad_norm": 1.1432966598000252, "learning_rate": 4.938044324463962e-05, "loss": 0.6269, "num_tokens": 67430310.0, "step": 11355 }, { "epoch": 0.12119531008289502, "grad_norm": 1.4063364903914706, "learning_rate": 4.937951790400515e-05, "loss": 0.8047, "num_tokens": 67466205.0, "step": 11360 }, { "epoch": 0.1212486530890935, "grad_norm": 1.6767504191895264, "learning_rate": 4.937859188252503e-05, "loss": 0.6209, "num_tokens": 67495333.0, "step": 11365 }, { "epoch": 0.12130199609529195, "grad_norm": 1.08792439714063, "learning_rate": 4.937766518022807e-05, "loss": 0.6668, "num_tokens": 67532333.0, "step": 11370 }, { "epoch": 0.1213553391014904, "grad_norm": 1.328370594445369, "learning_rate": 4.9376737797143105e-05, "loss": 0.6918, "num_tokens": 67565986.0, "step": 11375 }, { "epoch": 0.12140868210768886, "grad_norm": 2.6011157253077264, "learning_rate": 4.9375809733298995e-05, "loss": 0.7071, "num_tokens": 67589051.0, "step": 11380 }, { "epoch": 0.12146202511388732, "grad_norm": 1.0234396338866827, "learning_rate": 4.937488098872462e-05, "loss": 0.6853, "num_tokens": 67610517.0, "step": 11385 }, { "epoch": 0.12151536812008577, "grad_norm": 1.2995094585000722, "learning_rate": 4.937395156344888e-05, "loss": 0.6813, "num_tokens": 67644865.0, "step": 11390 }, { "epoch": 0.12156871112628423, "grad_norm": 1.8131560971570824, "learning_rate": 4.937302145750071e-05, "loss": 0.6774, "num_tokens": 67670966.0, "step": 11395 }, { "epoch": 0.12162205413248268, "grad_norm": 0.8572480931064279, "learning_rate": 4.937209067090903e-05, "loss": 0.6782, "num_tokens": 67714202.0, "step": 11400 }, { "epoch": 0.12167539713868114, "grad_norm": 1.7821047133334658, "learning_rate": 4.937115920370281e-05, "loss": 0.6447, "num_tokens": 67748869.0, "step": 11405 }, { "epoch": 0.12172874014487961, "grad_norm": 1.7663000464722949, "learning_rate": 4.937022705591105e-05, "loss": 0.6719, "num_tokens": 67777041.0, "step": 11410 }, { "epoch": 0.12178208315107807, "grad_norm": 1.8110564921983865, "learning_rate": 4.9369294227562745e-05, "loss": 0.6616, "num_tokens": 67804464.0, "step": 11415 }, { "epoch": 0.12183542615727652, "grad_norm": 1.1438457200941479, "learning_rate": 4.936836071868692e-05, "loss": 0.4813, "num_tokens": 67824716.0, "step": 11420 }, { "epoch": 0.12188876916347498, "grad_norm": 1.7469419064529779, "learning_rate": 4.936742652931263e-05, "loss": 0.6201, "num_tokens": 67848893.0, "step": 11425 }, { "epoch": 0.12194211216967343, "grad_norm": 1.192478097236902, "learning_rate": 4.9366491659468944e-05, "loss": 0.5733, "num_tokens": 67877716.0, "step": 11430 }, { "epoch": 0.12199545517587189, "grad_norm": 1.5318620526328612, "learning_rate": 4.936555610918496e-05, "loss": 0.7429, "num_tokens": 67915346.0, "step": 11435 }, { "epoch": 0.12204879818207034, "grad_norm": 1.4523640683039944, "learning_rate": 4.936461987848977e-05, "loss": 0.5666, "num_tokens": 67951050.0, "step": 11440 }, { "epoch": 0.1221021411882688, "grad_norm": 0.8941566698761778, "learning_rate": 4.9363682967412525e-05, "loss": 0.6271, "num_tokens": 67981186.0, "step": 11445 }, { "epoch": 0.12215548419446726, "grad_norm": 1.9179130092558994, "learning_rate": 4.936274537598238e-05, "loss": 0.7696, "num_tokens": 68013660.0, "step": 11450 }, { "epoch": 0.12220882720066573, "grad_norm": 1.5715115436815028, "learning_rate": 4.93618071042285e-05, "loss": 0.8574, "num_tokens": 68048096.0, "step": 11455 }, { "epoch": 0.12226217020686418, "grad_norm": 1.1100913875973957, "learning_rate": 4.93608681521801e-05, "loss": 0.5863, "num_tokens": 68068280.0, "step": 11460 }, { "epoch": 0.12231551321306264, "grad_norm": 0.8990624635262306, "learning_rate": 4.9359928519866375e-05, "loss": 0.5644, "num_tokens": 68102742.0, "step": 11465 }, { "epoch": 0.1223688562192611, "grad_norm": 1.3468979704927015, "learning_rate": 4.935898820731658e-05, "loss": 0.7302, "num_tokens": 68128553.0, "step": 11470 }, { "epoch": 0.12242219922545955, "grad_norm": 1.2195188561332704, "learning_rate": 4.935804721455997e-05, "loss": 0.6597, "num_tokens": 68160720.0, "step": 11475 }, { "epoch": 0.122475542231658, "grad_norm": 1.1000797066192058, "learning_rate": 4.935710554162583e-05, "loss": 0.6267, "num_tokens": 68200888.0, "step": 11480 }, { "epoch": 0.12252888523785646, "grad_norm": 1.6433072020167199, "learning_rate": 4.935616318854346e-05, "loss": 0.6543, "num_tokens": 68227193.0, "step": 11485 }, { "epoch": 0.12258222824405492, "grad_norm": 2.11835268653544, "learning_rate": 4.935522015534218e-05, "loss": 0.561, "num_tokens": 68248004.0, "step": 11490 }, { "epoch": 0.12263557125025337, "grad_norm": 2.2849184001489418, "learning_rate": 4.935427644205135e-05, "loss": 0.6024, "num_tokens": 68265900.0, "step": 11495 }, { "epoch": 0.12268891425645184, "grad_norm": 1.2864887144803405, "learning_rate": 4.9353332048700323e-05, "loss": 0.5853, "num_tokens": 68295649.0, "step": 11500 }, { "epoch": 0.1227422572626503, "grad_norm": 1.872263750202843, "learning_rate": 4.935238697531849e-05, "loss": 0.7511, "num_tokens": 68318738.0, "step": 11505 }, { "epoch": 0.12279560026884875, "grad_norm": 1.5786008907461084, "learning_rate": 4.9351441221935265e-05, "loss": 0.7052, "num_tokens": 68361501.0, "step": 11510 }, { "epoch": 0.12284894327504721, "grad_norm": 1.5791814507774797, "learning_rate": 4.935049478858007e-05, "loss": 0.596, "num_tokens": 68395688.0, "step": 11515 }, { "epoch": 0.12290228628124567, "grad_norm": 5.5406357570760365, "learning_rate": 4.934954767528236e-05, "loss": 0.7783, "num_tokens": 68426882.0, "step": 11520 }, { "epoch": 0.12295562928744412, "grad_norm": 1.0386378167687969, "learning_rate": 4.934859988207161e-05, "loss": 0.8432, "num_tokens": 68458128.0, "step": 11525 }, { "epoch": 0.12300897229364258, "grad_norm": 1.415293959299186, "learning_rate": 4.93476514089773e-05, "loss": 0.6384, "num_tokens": 68491457.0, "step": 11530 }, { "epoch": 0.12306231529984103, "grad_norm": 1.3687235126410142, "learning_rate": 4.934670225602897e-05, "loss": 0.7323, "num_tokens": 68522212.0, "step": 11535 }, { "epoch": 0.12311565830603949, "grad_norm": 1.187550014333134, "learning_rate": 4.934575242325613e-05, "loss": 0.663, "num_tokens": 68560685.0, "step": 11540 }, { "epoch": 0.12316900131223796, "grad_norm": 1.3547321909642283, "learning_rate": 4.9344801910688346e-05, "loss": 0.6508, "num_tokens": 68585861.0, "step": 11545 }, { "epoch": 0.12322234431843641, "grad_norm": 1.4827161184577995, "learning_rate": 4.9343850718355195e-05, "loss": 0.7925, "num_tokens": 68623173.0, "step": 11550 }, { "epoch": 0.12327568732463487, "grad_norm": 1.1564848485290142, "learning_rate": 4.934289884628629e-05, "loss": 0.6555, "num_tokens": 68649267.0, "step": 11555 }, { "epoch": 0.12332903033083333, "grad_norm": 1.0640137435187307, "learning_rate": 4.934194629451123e-05, "loss": 0.6407, "num_tokens": 68681322.0, "step": 11560 }, { "epoch": 0.12338237333703178, "grad_norm": 1.2569042903957441, "learning_rate": 4.9340993063059667e-05, "loss": 0.5838, "num_tokens": 68708567.0, "step": 11565 }, { "epoch": 0.12343571634323024, "grad_norm": 2.6731197285757546, "learning_rate": 4.934003915196126e-05, "loss": 0.7145, "num_tokens": 68734722.0, "step": 11570 }, { "epoch": 0.12348905934942869, "grad_norm": 1.2432603888032476, "learning_rate": 4.9339084561245704e-05, "loss": 0.7168, "num_tokens": 68776240.0, "step": 11575 }, { "epoch": 0.12354240235562715, "grad_norm": 1.3194981248515523, "learning_rate": 4.9338129290942685e-05, "loss": 0.751, "num_tokens": 68800348.0, "step": 11580 }, { "epoch": 0.1235957453618256, "grad_norm": 1.151781703445442, "learning_rate": 4.9337173341081945e-05, "loss": 0.6914, "num_tokens": 68839440.0, "step": 11585 }, { "epoch": 0.12364908836802407, "grad_norm": 1.6820984089207565, "learning_rate": 4.9336216711693224e-05, "loss": 0.7506, "num_tokens": 68858939.0, "step": 11590 }, { "epoch": 0.12370243137422253, "grad_norm": 0.8030156660605766, "learning_rate": 4.93352594028063e-05, "loss": 0.7016, "num_tokens": 68900759.0, "step": 11595 }, { "epoch": 0.12375577438042099, "grad_norm": 1.7498540878685147, "learning_rate": 4.933430141445094e-05, "loss": 0.7743, "num_tokens": 68930147.0, "step": 11600 }, { "epoch": 0.12380911738661944, "grad_norm": 0.8944323868671153, "learning_rate": 4.9333342746656974e-05, "loss": 0.6127, "num_tokens": 68960212.0, "step": 11605 }, { "epoch": 0.1238624603928179, "grad_norm": 0.9076603989226192, "learning_rate": 4.933238339945423e-05, "loss": 0.7043, "num_tokens": 68986553.0, "step": 11610 }, { "epoch": 0.12391580339901635, "grad_norm": 1.63448138647946, "learning_rate": 4.933142337287256e-05, "loss": 0.6245, "num_tokens": 69026325.0, "step": 11615 }, { "epoch": 0.12396914640521481, "grad_norm": 1.7579882579935011, "learning_rate": 4.933046266694184e-05, "loss": 0.7112, "num_tokens": 69045737.0, "step": 11620 }, { "epoch": 0.12402248941141326, "grad_norm": 1.0580873284034202, "learning_rate": 4.932950128169196e-05, "loss": 0.5365, "num_tokens": 69076781.0, "step": 11625 }, { "epoch": 0.12407583241761172, "grad_norm": 1.7763870644000737, "learning_rate": 4.932853921715284e-05, "loss": 0.6313, "num_tokens": 69111988.0, "step": 11630 }, { "epoch": 0.12412917542381019, "grad_norm": 2.123558045109079, "learning_rate": 4.9327576473354415e-05, "loss": 0.6755, "num_tokens": 69140914.0, "step": 11635 }, { "epoch": 0.12418251843000865, "grad_norm": 1.0125896395740057, "learning_rate": 4.932661305032665e-05, "loss": 0.4972, "num_tokens": 69164748.0, "step": 11640 }, { "epoch": 0.1242358614362071, "grad_norm": 1.5438888074936579, "learning_rate": 4.9325648948099515e-05, "loss": 0.669, "num_tokens": 69203457.0, "step": 11645 }, { "epoch": 0.12428920444240556, "grad_norm": 0.9688048845813056, "learning_rate": 4.932468416670302e-05, "loss": 0.6485, "num_tokens": 69237452.0, "step": 11650 }, { "epoch": 0.12434254744860401, "grad_norm": 0.9999041446266143, "learning_rate": 4.932371870616717e-05, "loss": 0.6965, "num_tokens": 69289943.0, "step": 11655 }, { "epoch": 0.12439589045480247, "grad_norm": 1.582247051135791, "learning_rate": 4.932275256652203e-05, "loss": 0.7113, "num_tokens": 69326576.0, "step": 11660 }, { "epoch": 0.12444923346100092, "grad_norm": 1.2532997975179971, "learning_rate": 4.932178574779767e-05, "loss": 0.6028, "num_tokens": 69364593.0, "step": 11665 }, { "epoch": 0.12450257646719938, "grad_norm": 2.1968223609854527, "learning_rate": 4.932081825002414e-05, "loss": 0.5533, "num_tokens": 69400804.0, "step": 11670 }, { "epoch": 0.12455591947339784, "grad_norm": 1.0863395159416873, "learning_rate": 4.931985007323158e-05, "loss": 0.6168, "num_tokens": 69427530.0, "step": 11675 }, { "epoch": 0.1246092624795963, "grad_norm": 1.0331470221093288, "learning_rate": 4.93188812174501e-05, "loss": 0.5732, "num_tokens": 69444477.0, "step": 11680 }, { "epoch": 0.12466260548579476, "grad_norm": 2.186424487196784, "learning_rate": 4.931791168270985e-05, "loss": 0.6938, "num_tokens": 69477766.0, "step": 11685 }, { "epoch": 0.12471594849199322, "grad_norm": 3.139706128081124, "learning_rate": 4.931694146904101e-05, "loss": 0.9277, "num_tokens": 69511335.0, "step": 11690 }, { "epoch": 0.12476929149819167, "grad_norm": 1.0241909743175095, "learning_rate": 4.931597057647376e-05, "loss": 0.5724, "num_tokens": 69529306.0, "step": 11695 }, { "epoch": 0.12482263450439013, "grad_norm": 1.853547911801774, "learning_rate": 4.931499900503832e-05, "loss": 0.6689, "num_tokens": 69555925.0, "step": 11700 }, { "epoch": 0.12487597751058858, "grad_norm": 1.4944065981135708, "learning_rate": 4.931402675476492e-05, "loss": 0.5605, "num_tokens": 69576322.0, "step": 11705 }, { "epoch": 0.12492932051678704, "grad_norm": 1.0483393605274802, "learning_rate": 4.931305382568381e-05, "loss": 0.6765, "num_tokens": 69604179.0, "step": 11710 }, { "epoch": 0.1249826635229855, "grad_norm": 0.917661847488836, "learning_rate": 4.931208021782527e-05, "loss": 0.652, "num_tokens": 69636532.0, "step": 11715 }, { "epoch": 0.12503600652918395, "grad_norm": 1.337102236642971, "learning_rate": 4.931110593121961e-05, "loss": 0.5236, "num_tokens": 69650485.0, "step": 11720 }, { "epoch": 0.12508934953538242, "grad_norm": 1.5241882586566171, "learning_rate": 4.931013096589713e-05, "loss": 0.8174, "num_tokens": 69676921.0, "step": 11725 }, { "epoch": 0.12514269254158086, "grad_norm": 0.7723867326620255, "learning_rate": 4.930915532188816e-05, "loss": 0.6649, "num_tokens": 69718746.0, "step": 11730 }, { "epoch": 0.12519603554777933, "grad_norm": 1.1768042795428755, "learning_rate": 4.930817899922309e-05, "loss": 0.6421, "num_tokens": 69761765.0, "step": 11735 }, { "epoch": 0.12524937855397777, "grad_norm": 0.9986400166032715, "learning_rate": 4.930720199793227e-05, "loss": 0.6809, "num_tokens": 69794224.0, "step": 11740 }, { "epoch": 0.12530272156017624, "grad_norm": 0.8850637345301323, "learning_rate": 4.930622431804613e-05, "loss": 0.6336, "num_tokens": 69833663.0, "step": 11745 }, { "epoch": 0.12535606456637471, "grad_norm": 1.1263041993692433, "learning_rate": 4.9305245959595074e-05, "loss": 0.6722, "num_tokens": 69861162.0, "step": 11750 }, { "epoch": 0.12540940757257316, "grad_norm": 0.8752198737989351, "learning_rate": 4.930426692260955e-05, "loss": 0.6296, "num_tokens": 69882648.0, "step": 11755 }, { "epoch": 0.12546275057877163, "grad_norm": 1.143821509917525, "learning_rate": 4.9303287207120044e-05, "loss": 0.5985, "num_tokens": 69913688.0, "step": 11760 }, { "epoch": 0.12551609358497007, "grad_norm": 2.128876224073744, "learning_rate": 4.9302306813157e-05, "loss": 0.5757, "num_tokens": 69927397.0, "step": 11765 }, { "epoch": 0.12556943659116854, "grad_norm": 1.0617969135020715, "learning_rate": 4.930132574075097e-05, "loss": 0.5815, "num_tokens": 69959359.0, "step": 11770 }, { "epoch": 0.12562277959736698, "grad_norm": 0.9253701738131797, "learning_rate": 4.9300343989932465e-05, "loss": 0.6959, "num_tokens": 69983414.0, "step": 11775 }, { "epoch": 0.12567612260356545, "grad_norm": 1.2584123255746853, "learning_rate": 4.929936156073202e-05, "loss": 0.7625, "num_tokens": 70016707.0, "step": 11780 }, { "epoch": 0.1257294656097639, "grad_norm": 1.3286815723702932, "learning_rate": 4.929837845318022e-05, "loss": 0.6431, "num_tokens": 70050934.0, "step": 11785 }, { "epoch": 0.12578280861596236, "grad_norm": 2.0661677276131956, "learning_rate": 4.929739466730767e-05, "loss": 0.6466, "num_tokens": 70072210.0, "step": 11790 }, { "epoch": 0.12583615162216083, "grad_norm": 1.4861516619812558, "learning_rate": 4.929641020314497e-05, "loss": 0.6363, "num_tokens": 70101135.0, "step": 11795 }, { "epoch": 0.12588949462835927, "grad_norm": 2.6751854832076916, "learning_rate": 4.929542506072275e-05, "loss": 0.7206, "num_tokens": 70123324.0, "step": 11800 }, { "epoch": 0.12594283763455774, "grad_norm": 2.772359343714678, "learning_rate": 4.929443924007167e-05, "loss": 0.6537, "num_tokens": 70142584.0, "step": 11805 }, { "epoch": 0.12599618064075618, "grad_norm": 0.9138868764011128, "learning_rate": 4.929345274122241e-05, "loss": 0.7458, "num_tokens": 70179735.0, "step": 11810 }, { "epoch": 0.12604952364695465, "grad_norm": 1.7231206486480861, "learning_rate": 4.929246556420567e-05, "loss": 0.5748, "num_tokens": 70197421.0, "step": 11815 }, { "epoch": 0.1261028666531531, "grad_norm": 0.8936337748833378, "learning_rate": 4.929147770905216e-05, "loss": 0.6944, "num_tokens": 70225591.0, "step": 11820 }, { "epoch": 0.12615620965935156, "grad_norm": 1.892662351808404, "learning_rate": 4.929048917579263e-05, "loss": 0.5395, "num_tokens": 70242051.0, "step": 11825 }, { "epoch": 0.12620955266555, "grad_norm": 1.5820035384083146, "learning_rate": 4.928949996445783e-05, "loss": 0.5033, "num_tokens": 70263161.0, "step": 11830 }, { "epoch": 0.12626289567174848, "grad_norm": 1.0587291496846887, "learning_rate": 4.928851007507855e-05, "loss": 0.6347, "num_tokens": 70294347.0, "step": 11835 }, { "epoch": 0.12631623867794695, "grad_norm": 1.0922227068754706, "learning_rate": 4.9287519507685586e-05, "loss": 0.5863, "num_tokens": 70332714.0, "step": 11840 }, { "epoch": 0.1263695816841454, "grad_norm": 1.1040367203207493, "learning_rate": 4.928652826230978e-05, "loss": 0.5496, "num_tokens": 70364398.0, "step": 11845 }, { "epoch": 0.12642292469034386, "grad_norm": 1.0273071807854002, "learning_rate": 4.9285536338981955e-05, "loss": 0.6338, "num_tokens": 70388093.0, "step": 11850 }, { "epoch": 0.1264762676965423, "grad_norm": 2.295085111910893, "learning_rate": 4.928454373773299e-05, "loss": 0.6326, "num_tokens": 70403123.0, "step": 11855 }, { "epoch": 0.12652961070274077, "grad_norm": 1.2536338242690916, "learning_rate": 4.928355045859378e-05, "loss": 0.6341, "num_tokens": 70436720.0, "step": 11860 }, { "epoch": 0.1265829537089392, "grad_norm": 0.8336694106894722, "learning_rate": 4.928255650159521e-05, "loss": 0.6179, "num_tokens": 70478805.0, "step": 11865 }, { "epoch": 0.12663629671513768, "grad_norm": 1.2720561253126066, "learning_rate": 4.9281561866768225e-05, "loss": 0.7276, "num_tokens": 70514979.0, "step": 11870 }, { "epoch": 0.12668963972133612, "grad_norm": 1.0530522372141013, "learning_rate": 4.9280566554143785e-05, "loss": 0.5994, "num_tokens": 70537787.0, "step": 11875 }, { "epoch": 0.1267429827275346, "grad_norm": 1.7982507389819167, "learning_rate": 4.927957056375285e-05, "loss": 0.7279, "num_tokens": 70574850.0, "step": 11880 }, { "epoch": 0.12679632573373306, "grad_norm": 1.0984028857803165, "learning_rate": 4.927857389562641e-05, "loss": 0.8469, "num_tokens": 70607572.0, "step": 11885 }, { "epoch": 0.1268496687399315, "grad_norm": 1.0665215298497985, "learning_rate": 4.927757654979549e-05, "loss": 0.7191, "num_tokens": 70649271.0, "step": 11890 }, { "epoch": 0.12690301174612997, "grad_norm": 1.2127512676665453, "learning_rate": 4.9276578526291116e-05, "loss": 0.6557, "num_tokens": 70691306.0, "step": 11895 }, { "epoch": 0.12695635475232842, "grad_norm": 1.9685522166905112, "learning_rate": 4.927557982514436e-05, "loss": 0.6287, "num_tokens": 70713935.0, "step": 11900 }, { "epoch": 0.12700969775852688, "grad_norm": 1.1953822272965977, "learning_rate": 4.927458044638628e-05, "loss": 0.6508, "num_tokens": 70737684.0, "step": 11905 }, { "epoch": 0.12706304076472533, "grad_norm": 0.9701592981550113, "learning_rate": 4.927358039004798e-05, "loss": 0.7494, "num_tokens": 70781073.0, "step": 11910 }, { "epoch": 0.1271163837709238, "grad_norm": 1.3034583374867013, "learning_rate": 4.927257965616058e-05, "loss": 0.534, "num_tokens": 70798309.0, "step": 11915 }, { "epoch": 0.12716972677712224, "grad_norm": 1.344504277971793, "learning_rate": 4.927157824475523e-05, "loss": 0.4951, "num_tokens": 70813408.0, "step": 11920 }, { "epoch": 0.1272230697833207, "grad_norm": 1.2864781587991765, "learning_rate": 4.9270576155863085e-05, "loss": 0.6766, "num_tokens": 70844150.0, "step": 11925 }, { "epoch": 0.12727641278951918, "grad_norm": 2.9798407717586923, "learning_rate": 4.926957338951533e-05, "loss": 0.6265, "num_tokens": 70870462.0, "step": 11930 }, { "epoch": 0.12732975579571762, "grad_norm": 1.1733759065555707, "learning_rate": 4.926856994574316e-05, "loss": 0.5356, "num_tokens": 70900821.0, "step": 11935 }, { "epoch": 0.1273830988019161, "grad_norm": 1.131010279173606, "learning_rate": 4.926756582457781e-05, "loss": 0.683, "num_tokens": 70922758.0, "step": 11940 }, { "epoch": 0.12743644180811453, "grad_norm": 2.072222720945477, "learning_rate": 4.9266561026050526e-05, "loss": 0.7286, "num_tokens": 70961757.0, "step": 11945 }, { "epoch": 0.127489784814313, "grad_norm": 1.0682243918287666, "learning_rate": 4.926555555019257e-05, "loss": 0.7348, "num_tokens": 70999325.0, "step": 11950 }, { "epoch": 0.12754312782051144, "grad_norm": 1.6168921426883383, "learning_rate": 4.926454939703523e-05, "loss": 0.5145, "num_tokens": 71025154.0, "step": 11955 }, { "epoch": 0.1275964708267099, "grad_norm": 1.3143293781052037, "learning_rate": 4.926354256660983e-05, "loss": 0.7656, "num_tokens": 71052636.0, "step": 11960 }, { "epoch": 0.12764981383290835, "grad_norm": 1.176000649667164, "learning_rate": 4.926253505894768e-05, "loss": 0.6886, "num_tokens": 71081296.0, "step": 11965 }, { "epoch": 0.12770315683910682, "grad_norm": 1.0928638235901478, "learning_rate": 4.926152687408014e-05, "loss": 0.7414, "num_tokens": 71123475.0, "step": 11970 }, { "epoch": 0.1277564998453053, "grad_norm": 1.1425250070609967, "learning_rate": 4.9260518012038584e-05, "loss": 0.7994, "num_tokens": 71154795.0, "step": 11975 }, { "epoch": 0.12780984285150374, "grad_norm": 1.1396164722678013, "learning_rate": 4.92595084728544e-05, "loss": 0.5627, "num_tokens": 71172889.0, "step": 11980 }, { "epoch": 0.1278631858577022, "grad_norm": 1.7262114777399629, "learning_rate": 4.925849825655902e-05, "loss": 0.8119, "num_tokens": 71203111.0, "step": 11985 }, { "epoch": 0.12791652886390065, "grad_norm": 1.3657800562145894, "learning_rate": 4.925748736318386e-05, "loss": 0.6354, "num_tokens": 71232833.0, "step": 11990 }, { "epoch": 0.12796987187009912, "grad_norm": 1.3951178162569724, "learning_rate": 4.9256475792760385e-05, "loss": 0.8029, "num_tokens": 71270008.0, "step": 11995 }, { "epoch": 0.12802321487629756, "grad_norm": 1.3230192299232675, "learning_rate": 4.925546354532007e-05, "loss": 0.647, "num_tokens": 71299972.0, "step": 12000 }, { "epoch": 0.12807655788249603, "grad_norm": 0.9972812043804236, "learning_rate": 4.925445062089442e-05, "loss": 0.5631, "num_tokens": 71325201.0, "step": 12005 }, { "epoch": 0.12812990088869447, "grad_norm": 1.1029328210955016, "learning_rate": 4.9253437019514954e-05, "loss": 0.6036, "num_tokens": 71339481.0, "step": 12010 }, { "epoch": 0.12818324389489294, "grad_norm": 1.6944773699130495, "learning_rate": 4.9252422741213206e-05, "loss": 0.592, "num_tokens": 71357312.0, "step": 12015 }, { "epoch": 0.1282365869010914, "grad_norm": 1.2354115871761098, "learning_rate": 4.9251407786020744e-05, "loss": 0.6565, "num_tokens": 71387147.0, "step": 12020 }, { "epoch": 0.12828992990728985, "grad_norm": 1.709062197309638, "learning_rate": 4.9250392153969146e-05, "loss": 0.6746, "num_tokens": 71427051.0, "step": 12025 }, { "epoch": 0.12834327291348832, "grad_norm": 1.741951014968537, "learning_rate": 4.924937584509003e-05, "loss": 0.7689, "num_tokens": 71462146.0, "step": 12030 }, { "epoch": 0.12839661591968676, "grad_norm": 0.8357530736987785, "learning_rate": 4.9248358859415e-05, "loss": 0.7015, "num_tokens": 71500670.0, "step": 12035 }, { "epoch": 0.12844995892588523, "grad_norm": 2.1713129717836948, "learning_rate": 4.924734119697573e-05, "loss": 0.5861, "num_tokens": 71523206.0, "step": 12040 }, { "epoch": 0.12850330193208367, "grad_norm": 1.415963978477737, "learning_rate": 4.924632285780386e-05, "loss": 0.731, "num_tokens": 71551191.0, "step": 12045 }, { "epoch": 0.12855664493828214, "grad_norm": 1.6775652565541483, "learning_rate": 4.9245303841931094e-05, "loss": 0.7766, "num_tokens": 71560721.0, "step": 12050 }, { "epoch": 0.12860998794448059, "grad_norm": 1.171515677098213, "learning_rate": 4.924428414938914e-05, "loss": 0.655, "num_tokens": 71584922.0, "step": 12055 }, { "epoch": 0.12866333095067906, "grad_norm": 1.1008960425807603, "learning_rate": 4.9243263780209734e-05, "loss": 0.5974, "num_tokens": 71617923.0, "step": 12060 }, { "epoch": 0.12871667395687753, "grad_norm": 2.0105886253910725, "learning_rate": 4.9242242734424615e-05, "loss": 0.7768, "num_tokens": 71639045.0, "step": 12065 }, { "epoch": 0.12877001696307597, "grad_norm": 1.2960411561588578, "learning_rate": 4.9241221012065554e-05, "loss": 0.566, "num_tokens": 71669775.0, "step": 12070 }, { "epoch": 0.12882335996927444, "grad_norm": 0.9352270835415214, "learning_rate": 4.924019861316436e-05, "loss": 0.7392, "num_tokens": 71709527.0, "step": 12075 }, { "epoch": 0.12887670297547288, "grad_norm": 1.0265935403358106, "learning_rate": 4.9239175537752845e-05, "loss": 0.6177, "num_tokens": 71759515.0, "step": 12080 }, { "epoch": 0.12893004598167135, "grad_norm": 0.8454268039635706, "learning_rate": 4.9238151785862835e-05, "loss": 0.583, "num_tokens": 71795137.0, "step": 12085 }, { "epoch": 0.1289833889878698, "grad_norm": 0.909136709519561, "learning_rate": 4.9237127357526194e-05, "loss": 0.5577, "num_tokens": 71832484.0, "step": 12090 }, { "epoch": 0.12903673199406826, "grad_norm": 1.1452101839664919, "learning_rate": 4.9236102252774804e-05, "loss": 0.5529, "num_tokens": 71858234.0, "step": 12095 }, { "epoch": 0.1290900750002667, "grad_norm": 1.3269926596657755, "learning_rate": 4.9235076471640556e-05, "loss": 0.7807, "num_tokens": 71895357.0, "step": 12100 }, { "epoch": 0.12914341800646517, "grad_norm": 1.0687339276492698, "learning_rate": 4.923405001415537e-05, "loss": 0.5501, "num_tokens": 71924242.0, "step": 12105 }, { "epoch": 0.12919676101266364, "grad_norm": 0.9416359889751096, "learning_rate": 4.923302288035119e-05, "loss": 0.6693, "num_tokens": 71958744.0, "step": 12110 }, { "epoch": 0.12925010401886208, "grad_norm": 1.322533906300453, "learning_rate": 4.923199507025998e-05, "loss": 0.4895, "num_tokens": 71987919.0, "step": 12115 }, { "epoch": 0.12930344702506055, "grad_norm": 1.2196105960959134, "learning_rate": 4.9230966583913726e-05, "loss": 0.563, "num_tokens": 72016659.0, "step": 12120 }, { "epoch": 0.129356790031259, "grad_norm": 1.5626410927916548, "learning_rate": 4.9229937421344426e-05, "loss": 0.6745, "num_tokens": 72040711.0, "step": 12125 }, { "epoch": 0.12941013303745746, "grad_norm": 1.0377573683652748, "learning_rate": 4.922890758258411e-05, "loss": 0.6215, "num_tokens": 72080450.0, "step": 12130 }, { "epoch": 0.1294634760436559, "grad_norm": 0.8562886508679977, "learning_rate": 4.922787706766482e-05, "loss": 0.621, "num_tokens": 72109508.0, "step": 12135 }, { "epoch": 0.12951681904985438, "grad_norm": 1.2663816362346922, "learning_rate": 4.9226845876618626e-05, "loss": 0.6955, "num_tokens": 72132229.0, "step": 12140 }, { "epoch": 0.12957016205605282, "grad_norm": 1.112109962725183, "learning_rate": 4.9225814009477625e-05, "loss": 0.5926, "num_tokens": 72164986.0, "step": 12145 }, { "epoch": 0.1296235050622513, "grad_norm": 1.3883770527302497, "learning_rate": 4.922478146627391e-05, "loss": 0.621, "num_tokens": 72186141.0, "step": 12150 }, { "epoch": 0.12967684806844976, "grad_norm": 0.9298371732654505, "learning_rate": 4.922374824703961e-05, "loss": 0.6016, "num_tokens": 72211783.0, "step": 12155 }, { "epoch": 0.1297301910746482, "grad_norm": 1.146352092037217, "learning_rate": 4.9222714351806905e-05, "loss": 0.6271, "num_tokens": 72252819.0, "step": 12160 }, { "epoch": 0.12978353408084667, "grad_norm": 1.2040780285488935, "learning_rate": 4.922167978060794e-05, "loss": 0.6975, "num_tokens": 72284657.0, "step": 12165 }, { "epoch": 0.1298368770870451, "grad_norm": 1.1171388428168687, "learning_rate": 4.922064453347492e-05, "loss": 0.719, "num_tokens": 72305107.0, "step": 12170 }, { "epoch": 0.12989022009324358, "grad_norm": 1.35984996043781, "learning_rate": 4.921960861044006e-05, "loss": 0.5982, "num_tokens": 72334266.0, "step": 12175 }, { "epoch": 0.12994356309944202, "grad_norm": 1.5637918582998602, "learning_rate": 4.9218572011535586e-05, "loss": 0.6538, "num_tokens": 72375810.0, "step": 12180 }, { "epoch": 0.1299969061056405, "grad_norm": 0.9525659657644215, "learning_rate": 4.9217534736793765e-05, "loss": 0.5897, "num_tokens": 72414730.0, "step": 12185 }, { "epoch": 0.13005024911183893, "grad_norm": 1.0267394945535835, "learning_rate": 4.9216496786246876e-05, "loss": 0.6018, "num_tokens": 72456284.0, "step": 12190 }, { "epoch": 0.1301035921180374, "grad_norm": 1.2792935371201974, "learning_rate": 4.921545815992721e-05, "loss": 0.6081, "num_tokens": 72493093.0, "step": 12195 }, { "epoch": 0.13015693512423587, "grad_norm": 1.1802493098844082, "learning_rate": 4.921441885786709e-05, "loss": 0.5697, "num_tokens": 72524201.0, "step": 12200 }, { "epoch": 0.13021027813043431, "grad_norm": 1.303166014881451, "learning_rate": 4.921337888009886e-05, "loss": 0.6426, "num_tokens": 72556349.0, "step": 12205 }, { "epoch": 0.13026362113663278, "grad_norm": 1.2773506385520397, "learning_rate": 4.9212338226654884e-05, "loss": 0.6556, "num_tokens": 72588403.0, "step": 12210 }, { "epoch": 0.13031696414283123, "grad_norm": 1.2032495183330756, "learning_rate": 4.921129689756753e-05, "loss": 0.5797, "num_tokens": 72624300.0, "step": 12215 }, { "epoch": 0.1303703071490297, "grad_norm": 1.1752203952536635, "learning_rate": 4.921025489286922e-05, "loss": 0.5755, "num_tokens": 72648592.0, "step": 12220 }, { "epoch": 0.13042365015522814, "grad_norm": 1.4706347247255276, "learning_rate": 4.920921221259237e-05, "loss": 0.5185, "num_tokens": 72664377.0, "step": 12225 }, { "epoch": 0.1304769931614266, "grad_norm": 1.7016442401032896, "learning_rate": 4.920816885676943e-05, "loss": 0.793, "num_tokens": 72705227.0, "step": 12230 }, { "epoch": 0.13053033616762505, "grad_norm": 1.3330025243280164, "learning_rate": 4.9207124825432866e-05, "loss": 0.596, "num_tokens": 72730112.0, "step": 12235 }, { "epoch": 0.13058367917382352, "grad_norm": 1.2323214014099746, "learning_rate": 4.920608011861516e-05, "loss": 0.6229, "num_tokens": 72771440.0, "step": 12240 }, { "epoch": 0.130637022180022, "grad_norm": 1.541793440656599, "learning_rate": 4.920503473634883e-05, "loss": 0.6397, "num_tokens": 72802150.0, "step": 12245 }, { "epoch": 0.13069036518622043, "grad_norm": 1.3437523388773258, "learning_rate": 4.9203988678666405e-05, "loss": 0.5578, "num_tokens": 72817328.0, "step": 12250 }, { "epoch": 0.1307437081924189, "grad_norm": 1.7777343615559718, "learning_rate": 4.920294194560043e-05, "loss": 0.5268, "num_tokens": 72833437.0, "step": 12255 }, { "epoch": 0.13079705119861734, "grad_norm": 1.4469722264774572, "learning_rate": 4.920189453718348e-05, "loss": 0.63, "num_tokens": 72865283.0, "step": 12260 }, { "epoch": 0.1308503942048158, "grad_norm": 1.1849042212734544, "learning_rate": 4.920084645344815e-05, "loss": 0.5525, "num_tokens": 72888305.0, "step": 12265 }, { "epoch": 0.13090373721101425, "grad_norm": 1.194027255834136, "learning_rate": 4.9199797694427054e-05, "loss": 0.5893, "num_tokens": 72919646.0, "step": 12270 }, { "epoch": 0.13095708021721272, "grad_norm": 1.2130607888456024, "learning_rate": 4.919874826015282e-05, "loss": 0.6478, "num_tokens": 72960756.0, "step": 12275 }, { "epoch": 0.13101042322341117, "grad_norm": 1.031643538696176, "learning_rate": 4.9197698150658124e-05, "loss": 0.6562, "num_tokens": 72992828.0, "step": 12280 }, { "epoch": 0.13106376622960964, "grad_norm": 1.0607313589064873, "learning_rate": 4.919664736597562e-05, "loss": 0.5093, "num_tokens": 73016412.0, "step": 12285 }, { "epoch": 0.1311171092358081, "grad_norm": 2.3864000467899436, "learning_rate": 4.919559590613802e-05, "loss": 0.5916, "num_tokens": 73052072.0, "step": 12290 }, { "epoch": 0.13117045224200655, "grad_norm": 1.041092946593589, "learning_rate": 4.919454377117803e-05, "loss": 0.6694, "num_tokens": 73083189.0, "step": 12295 }, { "epoch": 0.13122379524820502, "grad_norm": 1.1620556073886195, "learning_rate": 4.9193490961128416e-05, "loss": 0.5904, "num_tokens": 73113298.0, "step": 12300 }, { "epoch": 0.13127713825440346, "grad_norm": 1.9799972547759517, "learning_rate": 4.919243747602191e-05, "loss": 0.6525, "num_tokens": 73131099.0, "step": 12305 }, { "epoch": 0.13133048126060193, "grad_norm": 1.345242223566893, "learning_rate": 4.9191383315891314e-05, "loss": 0.8364, "num_tokens": 73151179.0, "step": 12310 }, { "epoch": 0.13138382426680037, "grad_norm": 1.56384230070864, "learning_rate": 4.919032848076942e-05, "loss": 0.7267, "num_tokens": 73196824.0, "step": 12315 }, { "epoch": 0.13143716727299884, "grad_norm": 0.7280265660780525, "learning_rate": 4.918927297068906e-05, "loss": 0.7082, "num_tokens": 73242194.0, "step": 12320 }, { "epoch": 0.13149051027919728, "grad_norm": 1.4384606250164436, "learning_rate": 4.918821678568307e-05, "loss": 0.523, "num_tokens": 73255496.0, "step": 12325 }, { "epoch": 0.13154385328539575, "grad_norm": 2.33150088287546, "learning_rate": 4.9187159925784335e-05, "loss": 0.7379, "num_tokens": 73280681.0, "step": 12330 }, { "epoch": 0.13159719629159422, "grad_norm": 1.429430171389868, "learning_rate": 4.9186102391025725e-05, "loss": 0.6712, "num_tokens": 73312909.0, "step": 12335 }, { "epoch": 0.13165053929779266, "grad_norm": 1.1837697981705808, "learning_rate": 4.918504418144014e-05, "loss": 0.6908, "num_tokens": 73349717.0, "step": 12340 }, { "epoch": 0.13170388230399113, "grad_norm": 1.5361855975327905, "learning_rate": 4.918398529706054e-05, "loss": 0.6183, "num_tokens": 73389676.0, "step": 12345 }, { "epoch": 0.13175722531018957, "grad_norm": 1.8921616475451166, "learning_rate": 4.918292573791985e-05, "loss": 0.6846, "num_tokens": 73433449.0, "step": 12350 }, { "epoch": 0.13181056831638804, "grad_norm": 3.022654151874767, "learning_rate": 4.9181865504051053e-05, "loss": 0.8902, "num_tokens": 73468016.0, "step": 12355 }, { "epoch": 0.13186391132258649, "grad_norm": 0.9139045198018897, "learning_rate": 4.918080459548713e-05, "loss": 0.5158, "num_tokens": 73508346.0, "step": 12360 }, { "epoch": 0.13191725432878496, "grad_norm": 0.9369760655864758, "learning_rate": 4.917974301226111e-05, "loss": 0.7196, "num_tokens": 73542662.0, "step": 12365 }, { "epoch": 0.1319705973349834, "grad_norm": 0.9366344412148098, "learning_rate": 4.917868075440602e-05, "loss": 0.6665, "num_tokens": 73600533.0, "step": 12370 }, { "epoch": 0.13202394034118187, "grad_norm": 1.450861064807395, "learning_rate": 4.9177617821954905e-05, "loss": 0.5898, "num_tokens": 73624708.0, "step": 12375 }, { "epoch": 0.13207728334738034, "grad_norm": 1.1451913039384087, "learning_rate": 4.917655421494086e-05, "loss": 0.6522, "num_tokens": 73662870.0, "step": 12380 }, { "epoch": 0.13213062635357878, "grad_norm": 1.6334665363940044, "learning_rate": 4.917548993339697e-05, "loss": 0.7468, "num_tokens": 73699600.0, "step": 12385 }, { "epoch": 0.13218396935977725, "grad_norm": 1.2779164938388672, "learning_rate": 4.9174424977356346e-05, "loss": 0.6027, "num_tokens": 73725722.0, "step": 12390 }, { "epoch": 0.1322373123659757, "grad_norm": 0.9504308371533255, "learning_rate": 4.9173359346852145e-05, "loss": 0.6128, "num_tokens": 73772443.0, "step": 12395 }, { "epoch": 0.13229065537217416, "grad_norm": 2.0351273469181232, "learning_rate": 4.9172293041917524e-05, "loss": 0.6439, "num_tokens": 73786207.0, "step": 12400 }, { "epoch": 0.1323439983783726, "grad_norm": 0.959248640495784, "learning_rate": 4.9171226062585644e-05, "loss": 0.699, "num_tokens": 73817385.0, "step": 12405 }, { "epoch": 0.13239734138457107, "grad_norm": 1.480041679350293, "learning_rate": 4.917015840888974e-05, "loss": 0.5023, "num_tokens": 73841839.0, "step": 12410 }, { "epoch": 0.1324506843907695, "grad_norm": 0.970324234694271, "learning_rate": 4.916909008086301e-05, "loss": 0.6049, "num_tokens": 73874626.0, "step": 12415 }, { "epoch": 0.13250402739696798, "grad_norm": 1.9882679825388347, "learning_rate": 4.916802107853871e-05, "loss": 0.6139, "num_tokens": 73909906.0, "step": 12420 }, { "epoch": 0.13255737040316645, "grad_norm": 1.2039793065569826, "learning_rate": 4.91669514019501e-05, "loss": 0.7633, "num_tokens": 73938744.0, "step": 12425 }, { "epoch": 0.1326107134093649, "grad_norm": 1.0250694288514546, "learning_rate": 4.916588105113047e-05, "loss": 0.5839, "num_tokens": 73959219.0, "step": 12430 }, { "epoch": 0.13266405641556336, "grad_norm": 1.7260818439726118, "learning_rate": 4.916481002611312e-05, "loss": 0.7706, "num_tokens": 73986361.0, "step": 12435 }, { "epoch": 0.1327173994217618, "grad_norm": 1.2357267107120486, "learning_rate": 4.916373832693138e-05, "loss": 0.4778, "num_tokens": 74010057.0, "step": 12440 }, { "epoch": 0.13277074242796028, "grad_norm": 1.047387903305669, "learning_rate": 4.916266595361861e-05, "loss": 0.665, "num_tokens": 74039363.0, "step": 12445 }, { "epoch": 0.13282408543415872, "grad_norm": 1.1692357535463127, "learning_rate": 4.916159290620817e-05, "loss": 0.5253, "num_tokens": 74057096.0, "step": 12450 }, { "epoch": 0.1328774284403572, "grad_norm": 1.0999578740860185, "learning_rate": 4.916051918473345e-05, "loss": 0.6753, "num_tokens": 74088537.0, "step": 12455 }, { "epoch": 0.13293077144655563, "grad_norm": 1.2314833197565271, "learning_rate": 4.9159444789227864e-05, "loss": 0.5608, "num_tokens": 74122492.0, "step": 12460 }, { "epoch": 0.1329841144527541, "grad_norm": 1.555624291398664, "learning_rate": 4.9158369719724846e-05, "loss": 0.5971, "num_tokens": 74140560.0, "step": 12465 }, { "epoch": 0.13303745745895257, "grad_norm": 0.9578020698867961, "learning_rate": 4.915729397625786e-05, "loss": 0.6014, "num_tokens": 74171423.0, "step": 12470 }, { "epoch": 0.133090800465151, "grad_norm": 1.1542542882050657, "learning_rate": 4.915621755886036e-05, "loss": 0.5926, "num_tokens": 74193340.0, "step": 12475 }, { "epoch": 0.13314414347134948, "grad_norm": 0.964349752643185, "learning_rate": 4.9155140467565855e-05, "loss": 0.5526, "num_tokens": 74221358.0, "step": 12480 }, { "epoch": 0.13319748647754792, "grad_norm": 0.9031236237854305, "learning_rate": 4.915406270240786e-05, "loss": 0.8185, "num_tokens": 74249653.0, "step": 12485 }, { "epoch": 0.1332508294837464, "grad_norm": 1.466275075849192, "learning_rate": 4.915298426341991e-05, "loss": 0.6642, "num_tokens": 74272195.0, "step": 12490 }, { "epoch": 0.13330417248994483, "grad_norm": 2.1048653788021996, "learning_rate": 4.915190515063557e-05, "loss": 0.6222, "num_tokens": 74296426.0, "step": 12495 }, { "epoch": 0.1333575154961433, "grad_norm": 1.047250708470257, "learning_rate": 4.915082536408842e-05, "loss": 0.7028, "num_tokens": 74351180.0, "step": 12500 }, { "epoch": 0.13341085850234174, "grad_norm": 0.9473799146001257, "learning_rate": 4.914974490381205e-05, "loss": 0.5419, "num_tokens": 74393596.0, "step": 12505 }, { "epoch": 0.13346420150854021, "grad_norm": 1.0812374697472822, "learning_rate": 4.914866376984009e-05, "loss": 0.5111, "num_tokens": 74408519.0, "step": 12510 }, { "epoch": 0.13351754451473868, "grad_norm": 1.3094483815447528, "learning_rate": 4.914758196220618e-05, "loss": 0.6642, "num_tokens": 74445248.0, "step": 12515 }, { "epoch": 0.13357088752093713, "grad_norm": 1.1077314098243876, "learning_rate": 4.9146499480943984e-05, "loss": 0.7278, "num_tokens": 74469584.0, "step": 12520 }, { "epoch": 0.1336242305271356, "grad_norm": 1.1482018597677888, "learning_rate": 4.914541632608719e-05, "loss": 0.6705, "num_tokens": 74502171.0, "step": 12525 }, { "epoch": 0.13367757353333404, "grad_norm": 1.0616175979009073, "learning_rate": 4.91443324976695e-05, "loss": 0.5959, "num_tokens": 74532703.0, "step": 12530 }, { "epoch": 0.1337309165395325, "grad_norm": 1.588130821549484, "learning_rate": 4.914324799572464e-05, "loss": 0.6792, "num_tokens": 74560920.0, "step": 12535 }, { "epoch": 0.13378425954573095, "grad_norm": 0.9818278701938313, "learning_rate": 4.914216282028636e-05, "loss": 0.666, "num_tokens": 74599161.0, "step": 12540 }, { "epoch": 0.13383760255192942, "grad_norm": 1.3516262810188862, "learning_rate": 4.914107697138843e-05, "loss": 0.6207, "num_tokens": 74635439.0, "step": 12545 }, { "epoch": 0.13389094555812786, "grad_norm": 0.9872596140685636, "learning_rate": 4.913999044906464e-05, "loss": 0.5395, "num_tokens": 74656331.0, "step": 12550 }, { "epoch": 0.13394428856432633, "grad_norm": 1.1446379865652485, "learning_rate": 4.913890325334879e-05, "loss": 0.6856, "num_tokens": 74686812.0, "step": 12555 }, { "epoch": 0.1339976315705248, "grad_norm": 0.7484446839759115, "learning_rate": 4.9137815384274715e-05, "loss": 0.5845, "num_tokens": 74742975.0, "step": 12560 }, { "epoch": 0.13405097457672324, "grad_norm": 1.4395845151579811, "learning_rate": 4.9136726841876276e-05, "loss": 0.5562, "num_tokens": 74762555.0, "step": 12565 }, { "epoch": 0.1341043175829217, "grad_norm": 1.0748052219333828, "learning_rate": 4.913563762618734e-05, "loss": 0.5407, "num_tokens": 74784660.0, "step": 12570 }, { "epoch": 0.13415766058912015, "grad_norm": 1.2826770444258964, "learning_rate": 4.913454773724181e-05, "loss": 0.7387, "num_tokens": 74820185.0, "step": 12575 }, { "epoch": 0.13421100359531862, "grad_norm": 2.6147758015662634, "learning_rate": 4.9133457175073574e-05, "loss": 0.6489, "num_tokens": 74837739.0, "step": 12580 }, { "epoch": 0.13426434660151707, "grad_norm": 0.9269028821099787, "learning_rate": 4.91323659397166e-05, "loss": 0.618, "num_tokens": 74877450.0, "step": 12585 }, { "epoch": 0.13431768960771553, "grad_norm": 1.0183563066907513, "learning_rate": 4.913127403120483e-05, "loss": 0.7809, "num_tokens": 74907708.0, "step": 12590 }, { "epoch": 0.13437103261391398, "grad_norm": 1.1175421718349723, "learning_rate": 4.9130181449572245e-05, "loss": 0.6114, "num_tokens": 74944071.0, "step": 12595 }, { "epoch": 0.13442437562011245, "grad_norm": 0.9802983939806155, "learning_rate": 4.912908819485284e-05, "loss": 0.7644, "num_tokens": 74978009.0, "step": 12600 }, { "epoch": 0.13447771862631092, "grad_norm": 1.3310285854936472, "learning_rate": 4.912799426708065e-05, "loss": 0.5954, "num_tokens": 75010762.0, "step": 12605 }, { "epoch": 0.13453106163250936, "grad_norm": 0.9783225860361628, "learning_rate": 4.9126899666289685e-05, "loss": 0.5663, "num_tokens": 75041903.0, "step": 12610 }, { "epoch": 0.13458440463870783, "grad_norm": 1.4694054763640525, "learning_rate": 4.912580439251404e-05, "loss": 0.7448, "num_tokens": 75079890.0, "step": 12615 }, { "epoch": 0.13463774764490627, "grad_norm": 1.2794784656967528, "learning_rate": 4.912470844578777e-05, "loss": 0.601, "num_tokens": 75109645.0, "step": 12620 }, { "epoch": 0.13469109065110474, "grad_norm": 1.2454167082380827, "learning_rate": 4.912361182614501e-05, "loss": 0.5161, "num_tokens": 75124067.0, "step": 12625 }, { "epoch": 0.13474443365730318, "grad_norm": 2.006046995772611, "learning_rate": 4.912251453361985e-05, "loss": 0.7636, "num_tokens": 75150807.0, "step": 12630 }, { "epoch": 0.13479777666350165, "grad_norm": 1.6042916421458793, "learning_rate": 4.9121416568246456e-05, "loss": 0.588, "num_tokens": 75169901.0, "step": 12635 }, { "epoch": 0.1348511196697001, "grad_norm": 1.913116918655097, "learning_rate": 4.912031793005899e-05, "loss": 0.7373, "num_tokens": 75204120.0, "step": 12640 }, { "epoch": 0.13490446267589856, "grad_norm": 1.4474452056515994, "learning_rate": 4.9119218619091636e-05, "loss": 0.5066, "num_tokens": 75237153.0, "step": 12645 }, { "epoch": 0.13495780568209703, "grad_norm": 2.9144276795301693, "learning_rate": 4.911811863537861e-05, "loss": 0.6538, "num_tokens": 75264171.0, "step": 12650 }, { "epoch": 0.13501114868829547, "grad_norm": 1.104184170489739, "learning_rate": 4.911701797895414e-05, "loss": 0.6421, "num_tokens": 75291084.0, "step": 12655 }, { "epoch": 0.13506449169449394, "grad_norm": 1.391589731576867, "learning_rate": 4.911591664985247e-05, "loss": 0.6384, "num_tokens": 75316366.0, "step": 12660 }, { "epoch": 0.13511783470069239, "grad_norm": 1.0974133883081767, "learning_rate": 4.9114814648107874e-05, "loss": 0.5505, "num_tokens": 75342207.0, "step": 12665 }, { "epoch": 0.13517117770689085, "grad_norm": 1.1059135483970939, "learning_rate": 4.911371197375465e-05, "loss": 0.7816, "num_tokens": 75382705.0, "step": 12670 }, { "epoch": 0.1352245207130893, "grad_norm": 1.0486011821545664, "learning_rate": 4.911260862682709e-05, "loss": 0.6945, "num_tokens": 75412135.0, "step": 12675 }, { "epoch": 0.13527786371928777, "grad_norm": 1.397754293242037, "learning_rate": 4.911150460735956e-05, "loss": 0.8926, "num_tokens": 75449177.0, "step": 12680 }, { "epoch": 0.1353312067254862, "grad_norm": 1.082104093856466, "learning_rate": 4.9110399915386386e-05, "loss": 0.6721, "num_tokens": 75480548.0, "step": 12685 }, { "epoch": 0.13538454973168468, "grad_norm": 1.083412776606692, "learning_rate": 4.910929455094196e-05, "loss": 0.7138, "num_tokens": 75513417.0, "step": 12690 }, { "epoch": 0.13543789273788315, "grad_norm": 1.444726002491384, "learning_rate": 4.9108188514060676e-05, "loss": 0.655, "num_tokens": 75547381.0, "step": 12695 }, { "epoch": 0.1354912357440816, "grad_norm": 1.2221995193817514, "learning_rate": 4.910708180477695e-05, "loss": 0.717, "num_tokens": 75563305.0, "step": 12700 }, { "epoch": 0.13554457875028006, "grad_norm": 0.9463367632279408, "learning_rate": 4.9105974423125215e-05, "loss": 0.5722, "num_tokens": 75587225.0, "step": 12705 }, { "epoch": 0.1355979217564785, "grad_norm": 1.9765765316244575, "learning_rate": 4.910486636913994e-05, "loss": 0.6972, "num_tokens": 75615828.0, "step": 12710 }, { "epoch": 0.13565126476267697, "grad_norm": 1.3094332778046813, "learning_rate": 4.91037576428556e-05, "loss": 0.6186, "num_tokens": 75642450.0, "step": 12715 }, { "epoch": 0.1357046077688754, "grad_norm": 0.8805612929751829, "learning_rate": 4.9102648244306695e-05, "loss": 0.6492, "num_tokens": 75684137.0, "step": 12720 }, { "epoch": 0.13575795077507388, "grad_norm": 1.3740369694167853, "learning_rate": 4.910153817352776e-05, "loss": 0.6687, "num_tokens": 75698947.0, "step": 12725 }, { "epoch": 0.13581129378127232, "grad_norm": 1.0329858015635356, "learning_rate": 4.910042743055333e-05, "loss": 0.5487, "num_tokens": 75737424.0, "step": 12730 }, { "epoch": 0.1358646367874708, "grad_norm": 0.9608964223166806, "learning_rate": 4.9099316015417954e-05, "loss": 0.7676, "num_tokens": 75775274.0, "step": 12735 }, { "epoch": 0.13591797979366926, "grad_norm": 1.0160485279348763, "learning_rate": 4.9098203928156225e-05, "loss": 0.5209, "num_tokens": 75793776.0, "step": 12740 }, { "epoch": 0.1359713227998677, "grad_norm": 1.0465540621096145, "learning_rate": 4.909709116880276e-05, "loss": 0.5865, "num_tokens": 75818182.0, "step": 12745 }, { "epoch": 0.13602466580606618, "grad_norm": 1.362375683065149, "learning_rate": 4.909597773739219e-05, "loss": 0.5887, "num_tokens": 75844996.0, "step": 12750 }, { "epoch": 0.13607800881226462, "grad_norm": 1.2199675216392334, "learning_rate": 4.9094863633959135e-05, "loss": 0.6428, "num_tokens": 75868842.0, "step": 12755 }, { "epoch": 0.1361313518184631, "grad_norm": 1.0019377986064257, "learning_rate": 4.9093748858538296e-05, "loss": 0.6288, "num_tokens": 75910452.0, "step": 12760 }, { "epoch": 0.13618469482466153, "grad_norm": 1.053964285558416, "learning_rate": 4.909263341116434e-05, "loss": 0.6084, "num_tokens": 75952805.0, "step": 12765 }, { "epoch": 0.13623803783086, "grad_norm": 1.52547246801531, "learning_rate": 4.909151729187199e-05, "loss": 0.5215, "num_tokens": 75984348.0, "step": 12770 }, { "epoch": 0.13629138083705844, "grad_norm": 1.1849953903705899, "learning_rate": 4.909040050069597e-05, "loss": 0.6717, "num_tokens": 76009688.0, "step": 12775 }, { "epoch": 0.1363447238432569, "grad_norm": 1.3371896311783464, "learning_rate": 4.908928303767103e-05, "loss": 0.6709, "num_tokens": 76053254.0, "step": 12780 }, { "epoch": 0.13639806684945538, "grad_norm": 1.4938314626741902, "learning_rate": 4.908816490283195e-05, "loss": 0.7738, "num_tokens": 76071487.0, "step": 12785 }, { "epoch": 0.13645140985565382, "grad_norm": 1.4155396997612726, "learning_rate": 4.908704609621352e-05, "loss": 0.6159, "num_tokens": 76095860.0, "step": 12790 }, { "epoch": 0.1365047528618523, "grad_norm": 0.9642725474904178, "learning_rate": 4.908592661785057e-05, "loss": 0.5863, "num_tokens": 76132999.0, "step": 12795 }, { "epoch": 0.13655809586805073, "grad_norm": 1.3251660031258967, "learning_rate": 4.90848064677779e-05, "loss": 0.7278, "num_tokens": 76160914.0, "step": 12800 }, { "epoch": 0.1366114388742492, "grad_norm": 0.8673983955294786, "learning_rate": 4.90836856460304e-05, "loss": 0.5389, "num_tokens": 76203622.0, "step": 12805 }, { "epoch": 0.13666478188044764, "grad_norm": 2.195018624440911, "learning_rate": 4.908256415264293e-05, "loss": 0.6435, "num_tokens": 76228424.0, "step": 12810 }, { "epoch": 0.13671812488664611, "grad_norm": 1.3353127363106936, "learning_rate": 4.908144198765041e-05, "loss": 0.7822, "num_tokens": 76262998.0, "step": 12815 }, { "epoch": 0.13677146789284456, "grad_norm": 1.1370002596041424, "learning_rate": 4.908031915108774e-05, "loss": 0.7772, "num_tokens": 76310576.0, "step": 12820 }, { "epoch": 0.13682481089904303, "grad_norm": 1.181458229531508, "learning_rate": 4.907919564298986e-05, "loss": 0.589, "num_tokens": 76340729.0, "step": 12825 }, { "epoch": 0.1368781539052415, "grad_norm": 0.8555645167265865, "learning_rate": 4.9078071463391736e-05, "loss": 0.6206, "num_tokens": 76373373.0, "step": 12830 }, { "epoch": 0.13693149691143994, "grad_norm": 1.1882933776912237, "learning_rate": 4.9076946612328354e-05, "loss": 0.5126, "num_tokens": 76394896.0, "step": 12835 }, { "epoch": 0.1369848399176384, "grad_norm": 0.8509977856473537, "learning_rate": 4.9075821089834715e-05, "loss": 0.6036, "num_tokens": 76441553.0, "step": 12840 }, { "epoch": 0.13703818292383685, "grad_norm": 1.0360793679916747, "learning_rate": 4.907469489594584e-05, "loss": 0.5483, "num_tokens": 76469379.0, "step": 12845 }, { "epoch": 0.13709152593003532, "grad_norm": 1.6390917251581283, "learning_rate": 4.9073568030696775e-05, "loss": 0.5746, "num_tokens": 76492771.0, "step": 12850 }, { "epoch": 0.13714486893623376, "grad_norm": 1.8304342488647527, "learning_rate": 4.907244049412258e-05, "loss": 0.5401, "num_tokens": 76525458.0, "step": 12855 }, { "epoch": 0.13719821194243223, "grad_norm": 1.4513904108336138, "learning_rate": 4.907131228625836e-05, "loss": 0.6213, "num_tokens": 76550354.0, "step": 12860 }, { "epoch": 0.13725155494863067, "grad_norm": 1.3194416790699695, "learning_rate": 4.907018340713921e-05, "loss": 0.5584, "num_tokens": 76571640.0, "step": 12865 }, { "epoch": 0.13730489795482914, "grad_norm": 1.5633672883417973, "learning_rate": 4.906905385680025e-05, "loss": 0.6477, "num_tokens": 76609271.0, "step": 12870 }, { "epoch": 0.1373582409610276, "grad_norm": 1.11310277910557, "learning_rate": 4.906792363527665e-05, "loss": 0.6451, "num_tokens": 76632105.0, "step": 12875 }, { "epoch": 0.13741158396722605, "grad_norm": 2.260813510901936, "learning_rate": 4.906679274260356e-05, "loss": 0.6355, "num_tokens": 76666991.0, "step": 12880 }, { "epoch": 0.13746492697342452, "grad_norm": 1.3883341477936, "learning_rate": 4.906566117881618e-05, "loss": 0.6177, "num_tokens": 76695680.0, "step": 12885 }, { "epoch": 0.13751826997962296, "grad_norm": 1.2856323574805764, "learning_rate": 4.906452894394972e-05, "loss": 0.9225, "num_tokens": 76719268.0, "step": 12890 }, { "epoch": 0.13757161298582143, "grad_norm": 1.1623843105285898, "learning_rate": 4.9063396038039414e-05, "loss": 0.701, "num_tokens": 76751045.0, "step": 12895 }, { "epoch": 0.13762495599201988, "grad_norm": 0.8715505471106192, "learning_rate": 4.906226246112051e-05, "loss": 0.5838, "num_tokens": 76784495.0, "step": 12900 }, { "epoch": 0.13767829899821835, "grad_norm": 1.9475898980046762, "learning_rate": 4.90611282132283e-05, "loss": 0.5902, "num_tokens": 76824052.0, "step": 12905 }, { "epoch": 0.1377316420044168, "grad_norm": 1.2138608517609049, "learning_rate": 4.905999329439806e-05, "loss": 0.6855, "num_tokens": 76859624.0, "step": 12910 }, { "epoch": 0.13778498501061526, "grad_norm": 1.3151356116981407, "learning_rate": 4.9058857704665114e-05, "loss": 0.5654, "num_tokens": 76872462.0, "step": 12915 }, { "epoch": 0.13783832801681373, "grad_norm": 1.225794165959366, "learning_rate": 4.905772144406481e-05, "loss": 0.6203, "num_tokens": 76903628.0, "step": 12920 }, { "epoch": 0.13789167102301217, "grad_norm": 1.054513091023274, "learning_rate": 4.905658451263249e-05, "loss": 0.6495, "num_tokens": 76937744.0, "step": 12925 }, { "epoch": 0.13794501402921064, "grad_norm": 1.290471744026408, "learning_rate": 4.905544691040353e-05, "loss": 0.5266, "num_tokens": 76951095.0, "step": 12930 }, { "epoch": 0.13799835703540908, "grad_norm": 1.0276733588015294, "learning_rate": 4.905430863741335e-05, "loss": 0.6115, "num_tokens": 76989239.0, "step": 12935 }, { "epoch": 0.13805170004160755, "grad_norm": 1.2488213170611773, "learning_rate": 4.9053169693697346e-05, "loss": 0.7134, "num_tokens": 77017881.0, "step": 12940 }, { "epoch": 0.138105043047806, "grad_norm": 1.1405641438985168, "learning_rate": 4.9052030079290984e-05, "loss": 0.6827, "num_tokens": 77047973.0, "step": 12945 }, { "epoch": 0.13815838605400446, "grad_norm": 0.9412853520978754, "learning_rate": 4.905088979422971e-05, "loss": 0.6279, "num_tokens": 77075997.0, "step": 12950 }, { "epoch": 0.1382117290602029, "grad_norm": 1.4752927909645006, "learning_rate": 4.9049748838549015e-05, "loss": 0.6308, "num_tokens": 77098451.0, "step": 12955 }, { "epoch": 0.13826507206640137, "grad_norm": 1.515474887823402, "learning_rate": 4.90486072122844e-05, "loss": 0.6609, "num_tokens": 77124379.0, "step": 12960 }, { "epoch": 0.13831841507259984, "grad_norm": 1.0317257294493987, "learning_rate": 4.904746491547139e-05, "loss": 0.6424, "num_tokens": 77156543.0, "step": 12965 }, { "epoch": 0.13837175807879828, "grad_norm": 1.3181237240550925, "learning_rate": 4.904632194814553e-05, "loss": 0.648, "num_tokens": 77190212.0, "step": 12970 }, { "epoch": 0.13842510108499675, "grad_norm": 1.0008745938379746, "learning_rate": 4.904517831034239e-05, "loss": 0.6507, "num_tokens": 77236113.0, "step": 12975 }, { "epoch": 0.1384784440911952, "grad_norm": 1.3822722060037183, "learning_rate": 4.904403400209756e-05, "loss": 0.5256, "num_tokens": 77264622.0, "step": 12980 }, { "epoch": 0.13853178709739367, "grad_norm": 2.1678633050400844, "learning_rate": 4.9042889023446645e-05, "loss": 0.8067, "num_tokens": 77291048.0, "step": 12985 }, { "epoch": 0.1385851301035921, "grad_norm": 1.306870542748777, "learning_rate": 4.9041743374425256e-05, "loss": 0.6184, "num_tokens": 77312492.0, "step": 12990 }, { "epoch": 0.13863847310979058, "grad_norm": 1.000916687285631, "learning_rate": 4.904059705506908e-05, "loss": 0.6135, "num_tokens": 77329866.0, "step": 12995 }, { "epoch": 0.13869181611598902, "grad_norm": 1.3288676111577933, "learning_rate": 4.9039450065413766e-05, "loss": 0.6528, "num_tokens": 77351090.0, "step": 13000 }, { "epoch": 0.1387451591221875, "grad_norm": 1.9343198528683698, "learning_rate": 4.9038302405495014e-05, "loss": 0.7059, "num_tokens": 77382927.0, "step": 13005 }, { "epoch": 0.13879850212838596, "grad_norm": 1.3706040635031134, "learning_rate": 4.903715407534852e-05, "loss": 0.8708, "num_tokens": 77425742.0, "step": 13010 }, { "epoch": 0.1388518451345844, "grad_norm": 0.7192405075282975, "learning_rate": 4.9036005075010036e-05, "loss": 0.5905, "num_tokens": 77469424.0, "step": 13015 }, { "epoch": 0.13890518814078287, "grad_norm": 1.1540148700053394, "learning_rate": 4.903485540451531e-05, "loss": 0.7026, "num_tokens": 77496265.0, "step": 13020 }, { "epoch": 0.1389585311469813, "grad_norm": 1.2012906871331703, "learning_rate": 4.9033705063900116e-05, "loss": 0.5922, "num_tokens": 77525476.0, "step": 13025 }, { "epoch": 0.13901187415317978, "grad_norm": 1.1299689107374806, "learning_rate": 4.903255405320025e-05, "loss": 0.5788, "num_tokens": 77554282.0, "step": 13030 }, { "epoch": 0.13906521715937822, "grad_norm": 1.2701412988487824, "learning_rate": 4.903140237245153e-05, "loss": 0.6552, "num_tokens": 77585321.0, "step": 13035 }, { "epoch": 0.1391185601655767, "grad_norm": 1.2543828080562769, "learning_rate": 4.9030250021689804e-05, "loss": 0.7341, "num_tokens": 77613980.0, "step": 13040 }, { "epoch": 0.13917190317177514, "grad_norm": 1.5329998966997307, "learning_rate": 4.902909700095092e-05, "loss": 0.6797, "num_tokens": 77629927.0, "step": 13045 }, { "epoch": 0.1392252461779736, "grad_norm": 1.3192968587716445, "learning_rate": 4.902794331027075e-05, "loss": 0.6384, "num_tokens": 77656283.0, "step": 13050 }, { "epoch": 0.13927858918417207, "grad_norm": 0.9495616669381836, "learning_rate": 4.902678894968521e-05, "loss": 0.6414, "num_tokens": 77705421.0, "step": 13055 }, { "epoch": 0.13933193219037052, "grad_norm": 1.166367217437163, "learning_rate": 4.902563391923022e-05, "loss": 0.6693, "num_tokens": 77735618.0, "step": 13060 }, { "epoch": 0.139385275196569, "grad_norm": 0.8869769401737445, "learning_rate": 4.902447821894171e-05, "loss": 0.6274, "num_tokens": 77773860.0, "step": 13065 }, { "epoch": 0.13943861820276743, "grad_norm": 1.1808077783812396, "learning_rate": 4.902332184885565e-05, "loss": 0.6526, "num_tokens": 77807019.0, "step": 13070 }, { "epoch": 0.1394919612089659, "grad_norm": 2.325559652042456, "learning_rate": 4.9022164809008033e-05, "loss": 0.6723, "num_tokens": 77854003.0, "step": 13075 }, { "epoch": 0.13954530421516434, "grad_norm": 1.013871891875708, "learning_rate": 4.902100709943485e-05, "loss": 0.658, "num_tokens": 77894068.0, "step": 13080 }, { "epoch": 0.1395986472213628, "grad_norm": 0.8036046458446731, "learning_rate": 4.901984872017214e-05, "loss": 0.6474, "num_tokens": 77935907.0, "step": 13085 }, { "epoch": 0.13965199022756125, "grad_norm": 1.1329840427488531, "learning_rate": 4.901868967125592e-05, "loss": 0.571, "num_tokens": 77965193.0, "step": 13090 }, { "epoch": 0.13970533323375972, "grad_norm": 1.480406965083559, "learning_rate": 4.901752995272229e-05, "loss": 0.5611, "num_tokens": 77992029.0, "step": 13095 }, { "epoch": 0.1397586762399582, "grad_norm": 1.3378552672516635, "learning_rate": 4.901636956460733e-05, "loss": 0.6348, "num_tokens": 78031650.0, "step": 13100 }, { "epoch": 0.13981201924615663, "grad_norm": 1.261751555887984, "learning_rate": 4.901520850694713e-05, "loss": 0.7187, "num_tokens": 78068625.0, "step": 13105 }, { "epoch": 0.1398653622523551, "grad_norm": 1.2158609990464542, "learning_rate": 4.901404677977785e-05, "loss": 0.5702, "num_tokens": 78085210.0, "step": 13110 }, { "epoch": 0.13991870525855354, "grad_norm": 3.2759385422630487, "learning_rate": 4.9012884383135624e-05, "loss": 0.6882, "num_tokens": 78118300.0, "step": 13115 }, { "epoch": 0.139972048264752, "grad_norm": 0.9744435250244888, "learning_rate": 4.9011721317056624e-05, "loss": 0.6574, "num_tokens": 78170639.0, "step": 13120 }, { "epoch": 0.14002539127095046, "grad_norm": 0.9054696411227646, "learning_rate": 4.901055758157704e-05, "loss": 0.5631, "num_tokens": 78203125.0, "step": 13125 }, { "epoch": 0.14007873427714893, "grad_norm": 1.829831243550289, "learning_rate": 4.9009393176733085e-05, "loss": 0.7188, "num_tokens": 78222483.0, "step": 13130 }, { "epoch": 0.14013207728334737, "grad_norm": 1.4902940960192665, "learning_rate": 4.9008228102561e-05, "loss": 0.6923, "num_tokens": 78264678.0, "step": 13135 }, { "epoch": 0.14018542028954584, "grad_norm": 1.1525501834601946, "learning_rate": 4.900706235909703e-05, "loss": 0.7138, "num_tokens": 78302955.0, "step": 13140 }, { "epoch": 0.1402387632957443, "grad_norm": 1.1482171151692653, "learning_rate": 4.900589594637747e-05, "loss": 0.7228, "num_tokens": 78320517.0, "step": 13145 }, { "epoch": 0.14029210630194275, "grad_norm": 1.0998315390699374, "learning_rate": 4.9004728864438585e-05, "loss": 0.7059, "num_tokens": 78358322.0, "step": 13150 }, { "epoch": 0.14034544930814122, "grad_norm": 0.8214803344632197, "learning_rate": 4.900356111331672e-05, "loss": 0.7342, "num_tokens": 78403085.0, "step": 13155 }, { "epoch": 0.14039879231433966, "grad_norm": 1.2072477519318605, "learning_rate": 4.900239269304821e-05, "loss": 0.6689, "num_tokens": 78432773.0, "step": 13160 }, { "epoch": 0.14045213532053813, "grad_norm": 1.7023927741590457, "learning_rate": 4.9001223603669394e-05, "loss": 0.6684, "num_tokens": 78471087.0, "step": 13165 }, { "epoch": 0.14050547832673657, "grad_norm": 1.1096809804867775, "learning_rate": 4.900005384521666e-05, "loss": 0.5837, "num_tokens": 78490805.0, "step": 13170 }, { "epoch": 0.14055882133293504, "grad_norm": 1.2472846720128958, "learning_rate": 4.8998883417726424e-05, "loss": 0.6334, "num_tokens": 78522714.0, "step": 13175 }, { "epoch": 0.14061216433913348, "grad_norm": 1.2773313047261747, "learning_rate": 4.89977123212351e-05, "loss": 0.623, "num_tokens": 78546366.0, "step": 13180 }, { "epoch": 0.14066550734533195, "grad_norm": 1.5043316084544218, "learning_rate": 4.899654055577912e-05, "loss": 0.5745, "num_tokens": 78571547.0, "step": 13185 }, { "epoch": 0.14071885035153042, "grad_norm": 1.36169990212295, "learning_rate": 4.899536812139494e-05, "loss": 0.5802, "num_tokens": 78593462.0, "step": 13190 }, { "epoch": 0.14077219335772886, "grad_norm": 1.0508871415097023, "learning_rate": 4.899419501811907e-05, "loss": 0.6361, "num_tokens": 78643257.0, "step": 13195 }, { "epoch": 0.14082553636392733, "grad_norm": 1.7869829522308394, "learning_rate": 4.8993021245988e-05, "loss": 0.5695, "num_tokens": 78667993.0, "step": 13200 }, { "epoch": 0.14087887937012578, "grad_norm": 1.0338639930917444, "learning_rate": 4.899184680503825e-05, "loss": 0.5887, "num_tokens": 78705583.0, "step": 13205 }, { "epoch": 0.14093222237632425, "grad_norm": 1.4403361965291575, "learning_rate": 4.899067169530638e-05, "loss": 0.5576, "num_tokens": 78729399.0, "step": 13210 }, { "epoch": 0.1409855653825227, "grad_norm": 1.1191244009319483, "learning_rate": 4.898949591682895e-05, "loss": 0.765, "num_tokens": 78768869.0, "step": 13215 }, { "epoch": 0.14103890838872116, "grad_norm": 1.3803258807879566, "learning_rate": 4.898831946964256e-05, "loss": 0.7199, "num_tokens": 78800728.0, "step": 13220 }, { "epoch": 0.1410922513949196, "grad_norm": 1.3924459605986814, "learning_rate": 4.8987142353783794e-05, "loss": 0.6766, "num_tokens": 78830082.0, "step": 13225 }, { "epoch": 0.14114559440111807, "grad_norm": 0.8591874090168622, "learning_rate": 4.898596456928929e-05, "loss": 0.6012, "num_tokens": 78860997.0, "step": 13230 }, { "epoch": 0.14119893740731654, "grad_norm": 1.1651290060541863, "learning_rate": 4.89847861161957e-05, "loss": 0.6803, "num_tokens": 78894648.0, "step": 13235 }, { "epoch": 0.14125228041351498, "grad_norm": 1.659001285111992, "learning_rate": 4.89836069945397e-05, "loss": 0.5646, "num_tokens": 78913842.0, "step": 13240 }, { "epoch": 0.14130562341971345, "grad_norm": 1.0389576555474822, "learning_rate": 4.898242720435799e-05, "loss": 0.555, "num_tokens": 78939201.0, "step": 13245 }, { "epoch": 0.1413589664259119, "grad_norm": 1.0109378137872043, "learning_rate": 4.898124674568727e-05, "loss": 0.6726, "num_tokens": 78976255.0, "step": 13250 }, { "epoch": 0.14141230943211036, "grad_norm": 2.0590339075486903, "learning_rate": 4.898006561856426e-05, "loss": 0.6154, "num_tokens": 79003454.0, "step": 13255 }, { "epoch": 0.1414656524383088, "grad_norm": 1.3298730484509431, "learning_rate": 4.897888382302574e-05, "loss": 0.5654, "num_tokens": 79028208.0, "step": 13260 }, { "epoch": 0.14151899544450727, "grad_norm": 1.1701733110885333, "learning_rate": 4.897770135910846e-05, "loss": 0.6889, "num_tokens": 79048378.0, "step": 13265 }, { "epoch": 0.14157233845070571, "grad_norm": 1.5871963903842319, "learning_rate": 4.897651822684925e-05, "loss": 0.6788, "num_tokens": 79064326.0, "step": 13270 }, { "epoch": 0.14162568145690418, "grad_norm": 0.875457541217288, "learning_rate": 4.8975334426284894e-05, "loss": 0.6609, "num_tokens": 79109283.0, "step": 13275 }, { "epoch": 0.14167902446310265, "grad_norm": 0.9276873748723546, "learning_rate": 4.8974149957452254e-05, "loss": 0.6557, "num_tokens": 79150600.0, "step": 13280 }, { "epoch": 0.1417323674693011, "grad_norm": 1.6306093840734057, "learning_rate": 4.8972964820388166e-05, "loss": 0.5841, "num_tokens": 79177250.0, "step": 13285 }, { "epoch": 0.14178571047549957, "grad_norm": 1.0400919798500055, "learning_rate": 4.8971779015129526e-05, "loss": 0.6912, "num_tokens": 79211197.0, "step": 13290 }, { "epoch": 0.141839053481698, "grad_norm": 0.9060287297195836, "learning_rate": 4.897059254171322e-05, "loss": 0.5359, "num_tokens": 79241874.0, "step": 13295 }, { "epoch": 0.14189239648789648, "grad_norm": 1.3602887789280467, "learning_rate": 4.896940540017618e-05, "loss": 0.6661, "num_tokens": 79261575.0, "step": 13300 }, { "epoch": 0.14194573949409492, "grad_norm": 1.2566937824672746, "learning_rate": 4.896821759055535e-05, "loss": 0.6743, "num_tokens": 79291731.0, "step": 13305 }, { "epoch": 0.1419990825002934, "grad_norm": 1.4457384446244237, "learning_rate": 4.896702911288767e-05, "loss": 0.5296, "num_tokens": 79334972.0, "step": 13310 }, { "epoch": 0.14205242550649183, "grad_norm": 0.9060067317198502, "learning_rate": 4.8965839967210156e-05, "loss": 0.698, "num_tokens": 79385966.0, "step": 13315 }, { "epoch": 0.1421057685126903, "grad_norm": 0.8618148491803226, "learning_rate": 4.896465015355978e-05, "loss": 0.5839, "num_tokens": 79405537.0, "step": 13320 }, { "epoch": 0.14215911151888877, "grad_norm": 0.9106811652131155, "learning_rate": 4.8963459671973586e-05, "loss": 0.5684, "num_tokens": 79429316.0, "step": 13325 }, { "epoch": 0.1422124545250872, "grad_norm": 1.0677838230261347, "learning_rate": 4.896226852248862e-05, "loss": 0.549, "num_tokens": 79465328.0, "step": 13330 }, { "epoch": 0.14226579753128568, "grad_norm": 1.0566480860398693, "learning_rate": 4.896107670514194e-05, "loss": 0.679, "num_tokens": 79487940.0, "step": 13335 }, { "epoch": 0.14231914053748412, "grad_norm": 1.1334301215228781, "learning_rate": 4.895988421997063e-05, "loss": 0.5217, "num_tokens": 79511740.0, "step": 13340 }, { "epoch": 0.1423724835436826, "grad_norm": 1.11714602016862, "learning_rate": 4.895869106701181e-05, "loss": 0.7207, "num_tokens": 79554044.0, "step": 13345 }, { "epoch": 0.14242582654988103, "grad_norm": 0.8115287569209815, "learning_rate": 4.895749724630259e-05, "loss": 0.5487, "num_tokens": 79587083.0, "step": 13350 }, { "epoch": 0.1424791695560795, "grad_norm": 2.0149614296385088, "learning_rate": 4.8956302757880144e-05, "loss": 0.5918, "num_tokens": 79618542.0, "step": 13355 }, { "epoch": 0.14253251256227795, "grad_norm": 1.344570689601342, "learning_rate": 4.895510760178161e-05, "loss": 0.6031, "num_tokens": 79643316.0, "step": 13360 }, { "epoch": 0.14258585556847642, "grad_norm": 1.150274921441605, "learning_rate": 4.8953911778044224e-05, "loss": 0.651, "num_tokens": 79672641.0, "step": 13365 }, { "epoch": 0.14263919857467489, "grad_norm": 0.8352861665269936, "learning_rate": 4.895271528670515e-05, "loss": 0.6746, "num_tokens": 79704898.0, "step": 13370 }, { "epoch": 0.14269254158087333, "grad_norm": 0.905657558803975, "learning_rate": 4.895151812780165e-05, "loss": 0.7809, "num_tokens": 79743539.0, "step": 13375 }, { "epoch": 0.1427458845870718, "grad_norm": 0.9292487917965543, "learning_rate": 4.895032030137097e-05, "loss": 0.6303, "num_tokens": 79776992.0, "step": 13380 }, { "epoch": 0.14279922759327024, "grad_norm": 2.0019162741900844, "learning_rate": 4.894912180745038e-05, "loss": 0.6169, "num_tokens": 79795111.0, "step": 13385 }, { "epoch": 0.1428525705994687, "grad_norm": 2.2857806108358876, "learning_rate": 4.894792264607717e-05, "loss": 0.5113, "num_tokens": 79803712.0, "step": 13390 }, { "epoch": 0.14290591360566715, "grad_norm": 1.229758705424527, "learning_rate": 4.894672281728868e-05, "loss": 0.5248, "num_tokens": 79825335.0, "step": 13395 }, { "epoch": 0.14295925661186562, "grad_norm": 1.6779093565830316, "learning_rate": 4.894552232112221e-05, "loss": 0.6282, "num_tokens": 79842906.0, "step": 13400 }, { "epoch": 0.14301259961806406, "grad_norm": 1.2819979404715731, "learning_rate": 4.894432115761514e-05, "loss": 0.767, "num_tokens": 79868084.0, "step": 13405 }, { "epoch": 0.14306594262426253, "grad_norm": 0.8403990228812828, "learning_rate": 4.894311932680485e-05, "loss": 0.6192, "num_tokens": 79915130.0, "step": 13410 }, { "epoch": 0.143119285630461, "grad_norm": 0.9904449684779139, "learning_rate": 4.894191682872873e-05, "loss": 0.6392, "num_tokens": 79963443.0, "step": 13415 }, { "epoch": 0.14317262863665944, "grad_norm": 2.0349987485590573, "learning_rate": 4.8940713663424196e-05, "loss": 0.6262, "num_tokens": 79994353.0, "step": 13420 }, { "epoch": 0.1432259716428579, "grad_norm": 1.2900734743916793, "learning_rate": 4.8939509830928695e-05, "loss": 0.5899, "num_tokens": 80017356.0, "step": 13425 }, { "epoch": 0.14327931464905636, "grad_norm": 1.355471778686567, "learning_rate": 4.8938305331279694e-05, "loss": 0.6984, "num_tokens": 80059334.0, "step": 13430 }, { "epoch": 0.14333265765525482, "grad_norm": 1.1913666567060404, "learning_rate": 4.8937100164514665e-05, "loss": 0.6613, "num_tokens": 80098797.0, "step": 13435 }, { "epoch": 0.14338600066145327, "grad_norm": 1.150288157957496, "learning_rate": 4.893589433067111e-05, "loss": 0.7993, "num_tokens": 80152955.0, "step": 13440 }, { "epoch": 0.14343934366765174, "grad_norm": 0.8142973131755635, "learning_rate": 4.893468782978655e-05, "loss": 0.525, "num_tokens": 80185130.0, "step": 13445 }, { "epoch": 0.14349268667385018, "grad_norm": 1.0252426758822555, "learning_rate": 4.893348066189853e-05, "loss": 0.6419, "num_tokens": 80211034.0, "step": 13450 }, { "epoch": 0.14354602968004865, "grad_norm": 1.5795487929304064, "learning_rate": 4.8932272827044626e-05, "loss": 0.4881, "num_tokens": 80233836.0, "step": 13455 }, { "epoch": 0.14359937268624712, "grad_norm": 1.7690470799501965, "learning_rate": 4.893106432526241e-05, "loss": 0.6364, "num_tokens": 80258863.0, "step": 13460 }, { "epoch": 0.14365271569244556, "grad_norm": 1.0834968713939208, "learning_rate": 4.8929855156589494e-05, "loss": 0.5951, "num_tokens": 80279128.0, "step": 13465 }, { "epoch": 0.14370605869864403, "grad_norm": 1.8053608057945607, "learning_rate": 4.89286453210635e-05, "loss": 0.6792, "num_tokens": 80307736.0, "step": 13470 }, { "epoch": 0.14375940170484247, "grad_norm": 1.1269108351258763, "learning_rate": 4.8927434818722085e-05, "loss": 0.5389, "num_tokens": 80335478.0, "step": 13475 }, { "epoch": 0.14381274471104094, "grad_norm": 0.802829567534249, "learning_rate": 4.892622364960291e-05, "loss": 0.6982, "num_tokens": 80373377.0, "step": 13480 }, { "epoch": 0.14386608771723938, "grad_norm": 1.9046575343570806, "learning_rate": 4.8925011813743665e-05, "loss": 0.7545, "num_tokens": 80400803.0, "step": 13485 }, { "epoch": 0.14391943072343785, "grad_norm": 1.1446622185812023, "learning_rate": 4.892379931118206e-05, "loss": 0.6639, "num_tokens": 80427909.0, "step": 13490 }, { "epoch": 0.1439727737296363, "grad_norm": 2.16700131043748, "learning_rate": 4.892258614195583e-05, "loss": 0.6373, "num_tokens": 80464775.0, "step": 13495 }, { "epoch": 0.14402611673583476, "grad_norm": 1.2725189883621937, "learning_rate": 4.892137230610272e-05, "loss": 0.5562, "num_tokens": 80489244.0, "step": 13500 }, { "epoch": 0.14407945974203323, "grad_norm": 1.4317564516438528, "learning_rate": 4.8920157803660505e-05, "loss": 0.6053, "num_tokens": 80510224.0, "step": 13505 }, { "epoch": 0.14413280274823168, "grad_norm": 2.300020334022075, "learning_rate": 4.891894263466697e-05, "loss": 0.7258, "num_tokens": 80543371.0, "step": 13510 }, { "epoch": 0.14418614575443015, "grad_norm": 1.8098283181158483, "learning_rate": 4.8917726799159945e-05, "loss": 0.7221, "num_tokens": 80573161.0, "step": 13515 }, { "epoch": 0.1442394887606286, "grad_norm": 1.2480427863158545, "learning_rate": 4.891651029717726e-05, "loss": 0.552, "num_tokens": 80600797.0, "step": 13520 }, { "epoch": 0.14429283176682706, "grad_norm": 1.361064735765594, "learning_rate": 4.8915293128756757e-05, "loss": 0.6442, "num_tokens": 80649711.0, "step": 13525 }, { "epoch": 0.1443461747730255, "grad_norm": 1.4391507658262173, "learning_rate": 4.891407529393632e-05, "loss": 0.7255, "num_tokens": 80677425.0, "step": 13530 }, { "epoch": 0.14439951777922397, "grad_norm": 0.946371279830644, "learning_rate": 4.891285679275384e-05, "loss": 0.5974, "num_tokens": 80694875.0, "step": 13535 }, { "epoch": 0.1444528607854224, "grad_norm": 0.9222915586900253, "learning_rate": 4.891163762524725e-05, "loss": 0.6268, "num_tokens": 80723300.0, "step": 13540 }, { "epoch": 0.14450620379162088, "grad_norm": 1.1907151450962785, "learning_rate": 4.891041779145448e-05, "loss": 0.6459, "num_tokens": 80755131.0, "step": 13545 }, { "epoch": 0.14455954679781935, "grad_norm": 0.8501904705041409, "learning_rate": 4.890919729141348e-05, "loss": 0.5894, "num_tokens": 80784161.0, "step": 13550 }, { "epoch": 0.1446128898040178, "grad_norm": 1.6092040431655508, "learning_rate": 4.890797612516224e-05, "loss": 0.5868, "num_tokens": 80807072.0, "step": 13555 }, { "epoch": 0.14466623281021626, "grad_norm": 1.3470443911891912, "learning_rate": 4.890675429273875e-05, "loss": 0.6251, "num_tokens": 80826983.0, "step": 13560 }, { "epoch": 0.1447195758164147, "grad_norm": 0.8793917465706196, "learning_rate": 4.8905531794181045e-05, "loss": 0.601, "num_tokens": 80864664.0, "step": 13565 }, { "epoch": 0.14477291882261317, "grad_norm": 1.2887779179175147, "learning_rate": 4.890430862952715e-05, "loss": 0.5926, "num_tokens": 80893251.0, "step": 13570 }, { "epoch": 0.14482626182881161, "grad_norm": 1.4721453347374194, "learning_rate": 4.890308479881514e-05, "loss": 0.6227, "num_tokens": 80929691.0, "step": 13575 }, { "epoch": 0.14487960483501008, "grad_norm": 0.8920872131318169, "learning_rate": 4.89018603020831e-05, "loss": 0.601, "num_tokens": 80961267.0, "step": 13580 }, { "epoch": 0.14493294784120853, "grad_norm": 1.0863577688027999, "learning_rate": 4.8900635139369114e-05, "loss": 0.5805, "num_tokens": 81003246.0, "step": 13585 }, { "epoch": 0.144986290847407, "grad_norm": 0.729452829144555, "learning_rate": 4.8899409310711336e-05, "loss": 0.6703, "num_tokens": 81054485.0, "step": 13590 }, { "epoch": 0.14503963385360547, "grad_norm": 1.4728724631438859, "learning_rate": 4.8898182816147886e-05, "loss": 0.7932, "num_tokens": 81088994.0, "step": 13595 }, { "epoch": 0.1450929768598039, "grad_norm": 1.6193409961613183, "learning_rate": 4.889695565571695e-05, "loss": 0.6076, "num_tokens": 81108472.0, "step": 13600 }, { "epoch": 0.14514631986600238, "grad_norm": 1.1264426184190415, "learning_rate": 4.8895727829456696e-05, "loss": 0.531, "num_tokens": 81126452.0, "step": 13605 }, { "epoch": 0.14519966287220082, "grad_norm": 1.1675368180495522, "learning_rate": 4.889449933740535e-05, "loss": 0.4419, "num_tokens": 81145330.0, "step": 13610 }, { "epoch": 0.1452530058783993, "grad_norm": 1.4564799170982397, "learning_rate": 4.889327017960111e-05, "loss": 0.758, "num_tokens": 81179166.0, "step": 13615 }, { "epoch": 0.14530634888459773, "grad_norm": 1.3445534968232162, "learning_rate": 4.8892040356082265e-05, "loss": 0.77, "num_tokens": 81214864.0, "step": 13620 }, { "epoch": 0.1453596918907962, "grad_norm": 0.8802836818829807, "learning_rate": 4.889080986688705e-05, "loss": 0.6109, "num_tokens": 81248174.0, "step": 13625 }, { "epoch": 0.14541303489699464, "grad_norm": 1.0347924783537552, "learning_rate": 4.8889578712053775e-05, "loss": 0.7323, "num_tokens": 81275875.0, "step": 13630 }, { "epoch": 0.1454663779031931, "grad_norm": 1.186404036243982, "learning_rate": 4.888834689162075e-05, "loss": 0.5783, "num_tokens": 81303726.0, "step": 13635 }, { "epoch": 0.14551972090939158, "grad_norm": 1.8496181049393792, "learning_rate": 4.88871144056263e-05, "loss": 0.7124, "num_tokens": 81333850.0, "step": 13640 }, { "epoch": 0.14557306391559002, "grad_norm": 0.9731622729063099, "learning_rate": 4.888588125410879e-05, "loss": 0.5282, "num_tokens": 81358494.0, "step": 13645 }, { "epoch": 0.1456264069217885, "grad_norm": 1.0615479441706208, "learning_rate": 4.8884647437106566e-05, "loss": 0.7814, "num_tokens": 81390600.0, "step": 13650 }, { "epoch": 0.14567974992798693, "grad_norm": 1.4752652900251608, "learning_rate": 4.888341295465805e-05, "loss": 0.552, "num_tokens": 81417224.0, "step": 13655 }, { "epoch": 0.1457330929341854, "grad_norm": 1.1805849687020964, "learning_rate": 4.888217780680164e-05, "loss": 0.6227, "num_tokens": 81436817.0, "step": 13660 }, { "epoch": 0.14578643594038385, "grad_norm": 1.3022211068520249, "learning_rate": 4.888094199357578e-05, "loss": 0.6242, "num_tokens": 81461699.0, "step": 13665 }, { "epoch": 0.14583977894658232, "grad_norm": 1.4313755694990549, "learning_rate": 4.887970551501893e-05, "loss": 0.5167, "num_tokens": 81487607.0, "step": 13670 }, { "epoch": 0.14589312195278076, "grad_norm": 1.89393799929377, "learning_rate": 4.887846837116954e-05, "loss": 0.7038, "num_tokens": 81502602.0, "step": 13675 }, { "epoch": 0.14594646495897923, "grad_norm": 1.1581843147497832, "learning_rate": 4.887723056206614e-05, "loss": 0.578, "num_tokens": 81535402.0, "step": 13680 }, { "epoch": 0.1459998079651777, "grad_norm": 1.1395305100452675, "learning_rate": 4.887599208774724e-05, "loss": 0.5336, "num_tokens": 81552881.0, "step": 13685 }, { "epoch": 0.14605315097137614, "grad_norm": 1.1232458976992827, "learning_rate": 4.887475294825137e-05, "loss": 0.624, "num_tokens": 81582256.0, "step": 13690 }, { "epoch": 0.1461064939775746, "grad_norm": 1.8493790024466836, "learning_rate": 4.887351314361708e-05, "loss": 0.6949, "num_tokens": 81614360.0, "step": 13695 }, { "epoch": 0.14615983698377305, "grad_norm": 1.566301408773906, "learning_rate": 4.887227267388298e-05, "loss": 0.7382, "num_tokens": 81651066.0, "step": 13700 }, { "epoch": 0.14621317998997152, "grad_norm": 1.0504391576597656, "learning_rate": 4.887103153908765e-05, "loss": 0.6155, "num_tokens": 81675857.0, "step": 13705 }, { "epoch": 0.14626652299616996, "grad_norm": 1.8811192357022055, "learning_rate": 4.886978973926971e-05, "loss": 0.7617, "num_tokens": 81696023.0, "step": 13710 }, { "epoch": 0.14631986600236843, "grad_norm": 0.9909038905219099, "learning_rate": 4.8868547274467816e-05, "loss": 0.5229, "num_tokens": 81719737.0, "step": 13715 }, { "epoch": 0.14637320900856687, "grad_norm": 1.046249961366785, "learning_rate": 4.886730414472062e-05, "loss": 0.5929, "num_tokens": 81744390.0, "step": 13720 }, { "epoch": 0.14642655201476534, "grad_norm": 1.15591981325966, "learning_rate": 4.8866060350066805e-05, "loss": 0.6277, "num_tokens": 81775004.0, "step": 13725 }, { "epoch": 0.1464798950209638, "grad_norm": 1.1476779423899268, "learning_rate": 4.8864815890545085e-05, "loss": 0.5581, "num_tokens": 81808554.0, "step": 13730 }, { "epoch": 0.14653323802716225, "grad_norm": 1.274829910997798, "learning_rate": 4.886357076619418e-05, "loss": 0.6744, "num_tokens": 81839901.0, "step": 13735 }, { "epoch": 0.14658658103336072, "grad_norm": 1.5286048802229086, "learning_rate": 4.886232497705283e-05, "loss": 0.59, "num_tokens": 81866448.0, "step": 13740 }, { "epoch": 0.14663992403955917, "grad_norm": 1.3020241479662593, "learning_rate": 4.88610785231598e-05, "loss": 0.7309, "num_tokens": 81902570.0, "step": 13745 }, { "epoch": 0.14669326704575764, "grad_norm": 1.7272620835151806, "learning_rate": 4.8859831404553894e-05, "loss": 0.6556, "num_tokens": 81917198.0, "step": 13750 }, { "epoch": 0.14674661005195608, "grad_norm": 1.2482700721692574, "learning_rate": 4.88585836212739e-05, "loss": 0.6785, "num_tokens": 81958909.0, "step": 13755 }, { "epoch": 0.14679995305815455, "grad_norm": 1.0776647308110057, "learning_rate": 4.885733517335866e-05, "loss": 0.7835, "num_tokens": 81973764.0, "step": 13760 }, { "epoch": 0.146853296064353, "grad_norm": 0.880963244727732, "learning_rate": 4.885608606084703e-05, "loss": 0.6027, "num_tokens": 82008251.0, "step": 13765 }, { "epoch": 0.14690663907055146, "grad_norm": 1.2383412947982684, "learning_rate": 4.8854836283777854e-05, "loss": 0.5838, "num_tokens": 82041618.0, "step": 13770 }, { "epoch": 0.14695998207674993, "grad_norm": 1.3182398603458059, "learning_rate": 4.885358584219004e-05, "loss": 0.789, "num_tokens": 82076818.0, "step": 13775 }, { "epoch": 0.14701332508294837, "grad_norm": 1.4046451032354181, "learning_rate": 4.88523347361225e-05, "loss": 0.4912, "num_tokens": 82105576.0, "step": 13780 }, { "epoch": 0.14706666808914684, "grad_norm": 0.8827866959329589, "learning_rate": 4.885108296561416e-05, "loss": 0.6093, "num_tokens": 82121799.0, "step": 13785 }, { "epoch": 0.14712001109534528, "grad_norm": 1.5948180607306508, "learning_rate": 4.8849830530703977e-05, "loss": 0.7861, "num_tokens": 82147626.0, "step": 13790 }, { "epoch": 0.14717335410154375, "grad_norm": 0.926068051075972, "learning_rate": 4.8848577431430915e-05, "loss": 0.6655, "num_tokens": 82189197.0, "step": 13795 }, { "epoch": 0.1472266971077422, "grad_norm": 0.9443774878553194, "learning_rate": 4.884732366783398e-05, "loss": 0.7229, "num_tokens": 82212572.0, "step": 13800 }, { "epoch": 0.14728004011394066, "grad_norm": 0.9981965473368869, "learning_rate": 4.884606923995218e-05, "loss": 0.5861, "num_tokens": 82243244.0, "step": 13805 }, { "epoch": 0.1473333831201391, "grad_norm": 1.308833237033212, "learning_rate": 4.8844814147824544e-05, "loss": 0.5794, "num_tokens": 82269715.0, "step": 13810 }, { "epoch": 0.14738672612633757, "grad_norm": 1.208457492359086, "learning_rate": 4.8843558391490144e-05, "loss": 0.7548, "num_tokens": 82320378.0, "step": 13815 }, { "epoch": 0.14744006913253604, "grad_norm": 3.3585154737345113, "learning_rate": 4.884230197098805e-05, "loss": 0.7259, "num_tokens": 82345643.0, "step": 13820 }, { "epoch": 0.1474934121387345, "grad_norm": 1.2776417010561134, "learning_rate": 4.884104488635735e-05, "loss": 0.9991, "num_tokens": 82368115.0, "step": 13825 }, { "epoch": 0.14754675514493296, "grad_norm": 1.5291458691524307, "learning_rate": 4.883978713763717e-05, "loss": 0.696, "num_tokens": 82411494.0, "step": 13830 }, { "epoch": 0.1476000981511314, "grad_norm": 1.1027324718137008, "learning_rate": 4.8838528724866646e-05, "loss": 0.6329, "num_tokens": 82442503.0, "step": 13835 }, { "epoch": 0.14765344115732987, "grad_norm": 1.1805946033224761, "learning_rate": 4.883726964808494e-05, "loss": 0.6021, "num_tokens": 82469903.0, "step": 13840 }, { "epoch": 0.1477067841635283, "grad_norm": 1.845323448256093, "learning_rate": 4.883600990733124e-05, "loss": 0.5485, "num_tokens": 82491855.0, "step": 13845 }, { "epoch": 0.14776012716972678, "grad_norm": 1.6317914506305868, "learning_rate": 4.883474950264473e-05, "loss": 0.6748, "num_tokens": 82511265.0, "step": 13850 }, { "epoch": 0.14781347017592522, "grad_norm": 1.321025043779226, "learning_rate": 4.8833488434064636e-05, "loss": 0.6181, "num_tokens": 82532850.0, "step": 13855 }, { "epoch": 0.1478668131821237, "grad_norm": 2.0694653594974057, "learning_rate": 4.88322267016302e-05, "loss": 0.6022, "num_tokens": 82567773.0, "step": 13860 }, { "epoch": 0.14792015618832216, "grad_norm": 1.045140529431162, "learning_rate": 4.883096430538069e-05, "loss": 0.6755, "num_tokens": 82605634.0, "step": 13865 }, { "epoch": 0.1479734991945206, "grad_norm": 2.458972775779808, "learning_rate": 4.8829701245355386e-05, "loss": 0.765, "num_tokens": 82646520.0, "step": 13870 }, { "epoch": 0.14802684220071907, "grad_norm": 0.9544198282762636, "learning_rate": 4.8828437521593595e-05, "loss": 0.6691, "num_tokens": 82686476.0, "step": 13875 }, { "epoch": 0.14808018520691751, "grad_norm": 0.9814002664860574, "learning_rate": 4.882717313413463e-05, "loss": 0.6293, "num_tokens": 82726372.0, "step": 13880 }, { "epoch": 0.14813352821311598, "grad_norm": 1.3041224713158812, "learning_rate": 4.882590808301785e-05, "loss": 0.6536, "num_tokens": 82750698.0, "step": 13885 }, { "epoch": 0.14818687121931443, "grad_norm": 1.083479109059726, "learning_rate": 4.882464236828262e-05, "loss": 0.7915, "num_tokens": 82799912.0, "step": 13890 }, { "epoch": 0.1482402142255129, "grad_norm": 1.746859314375018, "learning_rate": 4.8823375989968316e-05, "loss": 0.6731, "num_tokens": 82821386.0, "step": 13895 }, { "epoch": 0.14829355723171134, "grad_norm": 1.2331047829020396, "learning_rate": 4.8822108948114346e-05, "loss": 0.512, "num_tokens": 82840052.0, "step": 13900 }, { "epoch": 0.1483469002379098, "grad_norm": 1.0578486249565973, "learning_rate": 4.882084124276015e-05, "loss": 0.6601, "num_tokens": 82869350.0, "step": 13905 }, { "epoch": 0.14840024324410828, "grad_norm": 1.0112535330247812, "learning_rate": 4.881957287394516e-05, "loss": 0.5818, "num_tokens": 82911404.0, "step": 13910 }, { "epoch": 0.14845358625030672, "grad_norm": 1.2309647988551078, "learning_rate": 4.8818303841708865e-05, "loss": 0.5509, "num_tokens": 82950636.0, "step": 13915 }, { "epoch": 0.1485069292565052, "grad_norm": 0.9200952091471537, "learning_rate": 4.881703414609074e-05, "loss": 0.5318, "num_tokens": 82980445.0, "step": 13920 }, { "epoch": 0.14856027226270363, "grad_norm": 1.3145289009076127, "learning_rate": 4.8815763787130296e-05, "loss": 0.8102, "num_tokens": 83011058.0, "step": 13925 }, { "epoch": 0.1486136152689021, "grad_norm": 1.033723673118394, "learning_rate": 4.881449276486706e-05, "loss": 0.5589, "num_tokens": 83039709.0, "step": 13930 }, { "epoch": 0.14866695827510054, "grad_norm": 2.313286689650389, "learning_rate": 4.881322107934061e-05, "loss": 0.618, "num_tokens": 83059464.0, "step": 13935 }, { "epoch": 0.148720301281299, "grad_norm": 1.4402805024268321, "learning_rate": 4.881194873059048e-05, "loss": 0.6232, "num_tokens": 83083286.0, "step": 13940 }, { "epoch": 0.14877364428749745, "grad_norm": 1.3400417912899003, "learning_rate": 4.881067571865629e-05, "loss": 0.6724, "num_tokens": 83123052.0, "step": 13945 }, { "epoch": 0.14882698729369592, "grad_norm": 1.0006883024360602, "learning_rate": 4.880940204357764e-05, "loss": 0.63, "num_tokens": 83144415.0, "step": 13950 }, { "epoch": 0.1488803302998944, "grad_norm": 1.0703384324722625, "learning_rate": 4.8808127705394176e-05, "loss": 0.6178, "num_tokens": 83160449.0, "step": 13955 }, { "epoch": 0.14893367330609283, "grad_norm": 2.712082817021746, "learning_rate": 4.880685270414554e-05, "loss": 0.7315, "num_tokens": 83185700.0, "step": 13960 }, { "epoch": 0.1489870163122913, "grad_norm": 1.2887978967850091, "learning_rate": 4.880557703987142e-05, "loss": 0.5361, "num_tokens": 83208840.0, "step": 13965 }, { "epoch": 0.14904035931848975, "grad_norm": 0.9539223387009834, "learning_rate": 4.88043007126115e-05, "loss": 0.7142, "num_tokens": 83251998.0, "step": 13970 }, { "epoch": 0.14909370232468822, "grad_norm": 2.891448813415267, "learning_rate": 4.88030237224055e-05, "loss": 0.8073, "num_tokens": 83278549.0, "step": 13975 }, { "epoch": 0.14914704533088666, "grad_norm": 1.3415107367953532, "learning_rate": 4.8801746069293167e-05, "loss": 0.5945, "num_tokens": 83299124.0, "step": 13980 }, { "epoch": 0.14920038833708513, "grad_norm": 1.5361989817681796, "learning_rate": 4.8800467753314245e-05, "loss": 0.6097, "num_tokens": 83337252.0, "step": 13985 }, { "epoch": 0.14925373134328357, "grad_norm": 1.291525875103623, "learning_rate": 4.879918877450853e-05, "loss": 0.6906, "num_tokens": 83364946.0, "step": 13990 }, { "epoch": 0.14930707434948204, "grad_norm": 1.123251204800919, "learning_rate": 4.8797909132915794e-05, "loss": 0.7455, "num_tokens": 83401878.0, "step": 13995 }, { "epoch": 0.1493604173556805, "grad_norm": 0.8564554523337347, "learning_rate": 4.879662882857588e-05, "loss": 0.5977, "num_tokens": 83441946.0, "step": 14000 }, { "epoch": 0.14941376036187895, "grad_norm": 1.818068640215269, "learning_rate": 4.879534786152862e-05, "loss": 0.7266, "num_tokens": 83473410.0, "step": 14005 }, { "epoch": 0.14946710336807742, "grad_norm": 0.9019739555320192, "learning_rate": 4.879406623181388e-05, "loss": 0.6443, "num_tokens": 83510331.0, "step": 14010 }, { "epoch": 0.14952044637427586, "grad_norm": 1.6480043321887063, "learning_rate": 4.879278393947153e-05, "loss": 0.6902, "num_tokens": 83529783.0, "step": 14015 }, { "epoch": 0.14957378938047433, "grad_norm": 1.060329089547994, "learning_rate": 4.879150098454149e-05, "loss": 0.6779, "num_tokens": 83572860.0, "step": 14020 }, { "epoch": 0.14962713238667277, "grad_norm": 1.6556845801477809, "learning_rate": 4.8790217367063665e-05, "loss": 0.681, "num_tokens": 83594692.0, "step": 14025 }, { "epoch": 0.14968047539287124, "grad_norm": 1.1572070201266604, "learning_rate": 4.878893308707802e-05, "loss": 0.566, "num_tokens": 83628491.0, "step": 14030 }, { "epoch": 0.14973381839906968, "grad_norm": 1.214178087477515, "learning_rate": 4.878764814462449e-05, "loss": 0.6429, "num_tokens": 83665197.0, "step": 14035 }, { "epoch": 0.14978716140526815, "grad_norm": 1.5279187092577822, "learning_rate": 4.878636253974309e-05, "loss": 0.6008, "num_tokens": 83688223.0, "step": 14040 }, { "epoch": 0.14984050441146662, "grad_norm": 0.7724682415745265, "learning_rate": 4.87850762724738e-05, "loss": 0.5871, "num_tokens": 83732075.0, "step": 14045 }, { "epoch": 0.14989384741766507, "grad_norm": 1.3127839984331773, "learning_rate": 4.8783789342856665e-05, "loss": 0.7046, "num_tokens": 83752268.0, "step": 14050 }, { "epoch": 0.14994719042386354, "grad_norm": 1.6609750483535173, "learning_rate": 4.878250175093172e-05, "loss": 0.5443, "num_tokens": 83767389.0, "step": 14055 }, { "epoch": 0.15000053343006198, "grad_norm": 1.702531455665942, "learning_rate": 4.878121349673904e-05, "loss": 0.6607, "num_tokens": 83795039.0, "step": 14060 }, { "epoch": 0.15005387643626045, "grad_norm": 0.9852691132295486, "learning_rate": 4.87799245803187e-05, "loss": 0.5913, "num_tokens": 83825511.0, "step": 14065 }, { "epoch": 0.1501072194424589, "grad_norm": 1.1181799908173435, "learning_rate": 4.877863500171083e-05, "loss": 0.6764, "num_tokens": 83861281.0, "step": 14070 }, { "epoch": 0.15016056244865736, "grad_norm": 1.1411961566848363, "learning_rate": 4.877734476095554e-05, "loss": 0.5078, "num_tokens": 83886188.0, "step": 14075 }, { "epoch": 0.1502139054548558, "grad_norm": 1.410383105729829, "learning_rate": 4.877605385809298e-05, "loss": 0.5652, "num_tokens": 83901702.0, "step": 14080 }, { "epoch": 0.15026724846105427, "grad_norm": 1.671835411386229, "learning_rate": 4.8774762293163336e-05, "loss": 0.6226, "num_tokens": 83943076.0, "step": 14085 }, { "epoch": 0.15032059146725274, "grad_norm": 0.9722083962887194, "learning_rate": 4.8773470066206786e-05, "loss": 0.6055, "num_tokens": 83965859.0, "step": 14090 }, { "epoch": 0.15037393447345118, "grad_norm": 1.3414630387021897, "learning_rate": 4.877217717726354e-05, "loss": 0.6411, "num_tokens": 83990275.0, "step": 14095 }, { "epoch": 0.15042727747964965, "grad_norm": 1.7654264492334226, "learning_rate": 4.8770883626373835e-05, "loss": 0.5543, "num_tokens": 84021583.0, "step": 14100 }, { "epoch": 0.1504806204858481, "grad_norm": 1.6766326863448027, "learning_rate": 4.876958941357793e-05, "loss": 0.8619, "num_tokens": 84043568.0, "step": 14105 }, { "epoch": 0.15053396349204656, "grad_norm": 0.8888827900331575, "learning_rate": 4.876829453891608e-05, "loss": 0.6794, "num_tokens": 84066726.0, "step": 14110 }, { "epoch": 0.150587306498245, "grad_norm": 0.860035567204963, "learning_rate": 4.8766999002428606e-05, "loss": 0.5648, "num_tokens": 84107402.0, "step": 14115 }, { "epoch": 0.15064064950444347, "grad_norm": 0.9392036997065127, "learning_rate": 4.87657028041558e-05, "loss": 0.4279, "num_tokens": 84130472.0, "step": 14120 }, { "epoch": 0.15069399251064192, "grad_norm": 1.224579639377272, "learning_rate": 4.8764405944137994e-05, "loss": 0.5739, "num_tokens": 84149126.0, "step": 14125 }, { "epoch": 0.1507473355168404, "grad_norm": 1.5171018157502991, "learning_rate": 4.876310842241556e-05, "loss": 0.5536, "num_tokens": 84170472.0, "step": 14130 }, { "epoch": 0.15080067852303886, "grad_norm": 1.7171244702147364, "learning_rate": 4.8761810239028874e-05, "loss": 0.6224, "num_tokens": 84190388.0, "step": 14135 }, { "epoch": 0.1508540215292373, "grad_norm": 2.1469902248742128, "learning_rate": 4.876051139401832e-05, "loss": 0.5473, "num_tokens": 84201733.0, "step": 14140 }, { "epoch": 0.15090736453543577, "grad_norm": 1.2200428107644743, "learning_rate": 4.875921188742432e-05, "loss": 0.6804, "num_tokens": 84244772.0, "step": 14145 }, { "epoch": 0.1509607075416342, "grad_norm": 1.4143161494729348, "learning_rate": 4.875791171928732e-05, "loss": 0.5759, "num_tokens": 84264075.0, "step": 14150 }, { "epoch": 0.15101405054783268, "grad_norm": 0.9059879426270545, "learning_rate": 4.875661088964777e-05, "loss": 0.7072, "num_tokens": 84298682.0, "step": 14155 }, { "epoch": 0.15106739355403112, "grad_norm": 1.4112322560361923, "learning_rate": 4.875530939854615e-05, "loss": 0.5897, "num_tokens": 84319720.0, "step": 14160 }, { "epoch": 0.1511207365602296, "grad_norm": 0.8745416652125034, "learning_rate": 4.8754007246022956e-05, "loss": 0.7693, "num_tokens": 84349365.0, "step": 14165 }, { "epoch": 0.15117407956642803, "grad_norm": 3.2973819116872836, "learning_rate": 4.8752704432118726e-05, "loss": 0.6601, "num_tokens": 84367901.0, "step": 14170 }, { "epoch": 0.1512274225726265, "grad_norm": 1.0658959020308552, "learning_rate": 4.875140095687398e-05, "loss": 0.7711, "num_tokens": 84397740.0, "step": 14175 }, { "epoch": 0.15128076557882497, "grad_norm": 1.08437663419, "learning_rate": 4.875009682032929e-05, "loss": 0.5984, "num_tokens": 84416729.0, "step": 14180 }, { "epoch": 0.1513341085850234, "grad_norm": 0.9960937409180931, "learning_rate": 4.874879202252523e-05, "loss": 0.5269, "num_tokens": 84438133.0, "step": 14185 }, { "epoch": 0.15138745159122188, "grad_norm": 1.0563707649063914, "learning_rate": 4.874748656350241e-05, "loss": 0.7188, "num_tokens": 84467144.0, "step": 14190 }, { "epoch": 0.15144079459742033, "grad_norm": 1.0179920638928468, "learning_rate": 4.874618044330146e-05, "loss": 0.6158, "num_tokens": 84492710.0, "step": 14195 }, { "epoch": 0.1514941376036188, "grad_norm": 1.1681905445447507, "learning_rate": 4.874487366196301e-05, "loss": 0.7068, "num_tokens": 84518918.0, "step": 14200 }, { "epoch": 0.15154748060981724, "grad_norm": 2.4539740144969953, "learning_rate": 4.874356621952774e-05, "loss": 0.5541, "num_tokens": 84545634.0, "step": 14205 }, { "epoch": 0.1516008236160157, "grad_norm": 2.2460500530870102, "learning_rate": 4.874225811603631e-05, "loss": 0.7193, "num_tokens": 84568650.0, "step": 14210 }, { "epoch": 0.15165416662221415, "grad_norm": 1.2562748157189325, "learning_rate": 4.874094935152945e-05, "loss": 0.7267, "num_tokens": 84605653.0, "step": 14215 }, { "epoch": 0.15170750962841262, "grad_norm": 1.0562747867927194, "learning_rate": 4.8739639926047864e-05, "loss": 0.4911, "num_tokens": 84623045.0, "step": 14220 }, { "epoch": 0.1517608526346111, "grad_norm": 0.9370924976945006, "learning_rate": 4.8738329839632325e-05, "loss": 0.794, "num_tokens": 84654378.0, "step": 14225 }, { "epoch": 0.15181419564080953, "grad_norm": 0.8631516265878615, "learning_rate": 4.873701909232358e-05, "loss": 0.5337, "num_tokens": 84695235.0, "step": 14230 }, { "epoch": 0.151867538647008, "grad_norm": 1.19708228371436, "learning_rate": 4.873570768416242e-05, "loss": 0.5271, "num_tokens": 84719981.0, "step": 14235 }, { "epoch": 0.15192088165320644, "grad_norm": 1.6656671603615205, "learning_rate": 4.873439561518966e-05, "loss": 0.4875, "num_tokens": 84741165.0, "step": 14240 }, { "epoch": 0.1519742246594049, "grad_norm": 0.988586034386694, "learning_rate": 4.873308288544612e-05, "loss": 0.6098, "num_tokens": 84773391.0, "step": 14245 }, { "epoch": 0.15202756766560335, "grad_norm": 1.2956504844215688, "learning_rate": 4.873176949497266e-05, "loss": 0.5952, "num_tokens": 84793818.0, "step": 14250 }, { "epoch": 0.15208091067180182, "grad_norm": 1.006018048251547, "learning_rate": 4.873045544381015e-05, "loss": 0.6444, "num_tokens": 84832558.0, "step": 14255 }, { "epoch": 0.15213425367800026, "grad_norm": 1.1467257283871517, "learning_rate": 4.8729140731999466e-05, "loss": 0.6365, "num_tokens": 84878688.0, "step": 14260 }, { "epoch": 0.15218759668419873, "grad_norm": 1.0527581423041972, "learning_rate": 4.872782535958154e-05, "loss": 0.4678, "num_tokens": 84905281.0, "step": 14265 }, { "epoch": 0.1522409396903972, "grad_norm": 1.0041721395910326, "learning_rate": 4.8726509326597276e-05, "loss": 0.6176, "num_tokens": 84929344.0, "step": 14270 }, { "epoch": 0.15229428269659565, "grad_norm": 1.1408955962010057, "learning_rate": 4.8725192633087655e-05, "loss": 0.6542, "num_tokens": 84954676.0, "step": 14275 }, { "epoch": 0.15234762570279411, "grad_norm": 1.508740494888489, "learning_rate": 4.872387527909363e-05, "loss": 0.6814, "num_tokens": 84989457.0, "step": 14280 }, { "epoch": 0.15240096870899256, "grad_norm": 1.3556384962672057, "learning_rate": 4.8722557264656206e-05, "loss": 0.6363, "num_tokens": 85022907.0, "step": 14285 }, { "epoch": 0.15245431171519103, "grad_norm": 1.0340362293506156, "learning_rate": 4.8721238589816384e-05, "loss": 0.659, "num_tokens": 85056860.0, "step": 14290 }, { "epoch": 0.15250765472138947, "grad_norm": 1.856235010022638, "learning_rate": 4.871991925461521e-05, "loss": 0.5923, "num_tokens": 85079466.0, "step": 14295 }, { "epoch": 0.15256099772758794, "grad_norm": 2.047807122187223, "learning_rate": 4.871859925909375e-05, "loss": 0.6015, "num_tokens": 85113391.0, "step": 14300 }, { "epoch": 0.15261434073378638, "grad_norm": 1.2331963949877571, "learning_rate": 4.8717278603293045e-05, "loss": 0.5746, "num_tokens": 85142211.0, "step": 14305 }, { "epoch": 0.15266768373998485, "grad_norm": 1.3268906706663794, "learning_rate": 4.871595728725422e-05, "loss": 0.5829, "num_tokens": 85168687.0, "step": 14310 }, { "epoch": 0.15272102674618332, "grad_norm": 0.9625571183790622, "learning_rate": 4.871463531101839e-05, "loss": 0.6179, "num_tokens": 85208982.0, "step": 14315 }, { "epoch": 0.15277436975238176, "grad_norm": 1.6089418116511685, "learning_rate": 4.871331267462667e-05, "loss": 0.8121, "num_tokens": 85228531.0, "step": 14320 }, { "epoch": 0.15282771275858023, "grad_norm": 0.9664454592462985, "learning_rate": 4.8711989378120245e-05, "loss": 0.7512, "num_tokens": 85260916.0, "step": 14325 }, { "epoch": 0.15288105576477867, "grad_norm": 1.3984577180324034, "learning_rate": 4.8710665421540277e-05, "loss": 0.5292, "num_tokens": 85309134.0, "step": 14330 }, { "epoch": 0.15293439877097714, "grad_norm": 1.5456332109754791, "learning_rate": 4.8709340804927963e-05, "loss": 0.7308, "num_tokens": 85323274.0, "step": 14335 }, { "epoch": 0.15298774177717558, "grad_norm": 1.570460666637597, "learning_rate": 4.870801552832454e-05, "loss": 0.7159, "num_tokens": 85361149.0, "step": 14340 }, { "epoch": 0.15304108478337405, "grad_norm": 1.105962277090415, "learning_rate": 4.870668959177123e-05, "loss": 0.5092, "num_tokens": 85385616.0, "step": 14345 }, { "epoch": 0.1530944277895725, "grad_norm": 2.433788321751003, "learning_rate": 4.8705362995309296e-05, "loss": 0.8048, "num_tokens": 85415079.0, "step": 14350 }, { "epoch": 0.15314777079577097, "grad_norm": 1.098845039931738, "learning_rate": 4.870403573898003e-05, "loss": 0.5742, "num_tokens": 85436818.0, "step": 14355 }, { "epoch": 0.15320111380196944, "grad_norm": 2.51170502869654, "learning_rate": 4.870270782282472e-05, "loss": 0.6726, "num_tokens": 85461389.0, "step": 14360 }, { "epoch": 0.15325445680816788, "grad_norm": 1.630557722814242, "learning_rate": 4.8701379246884703e-05, "loss": 0.6121, "num_tokens": 85490909.0, "step": 14365 }, { "epoch": 0.15330779981436635, "grad_norm": 2.001342359778183, "learning_rate": 4.87000500112013e-05, "loss": 0.6886, "num_tokens": 85517561.0, "step": 14370 }, { "epoch": 0.1533611428205648, "grad_norm": 1.0776614987095792, "learning_rate": 4.86987201158159e-05, "loss": 0.6272, "num_tokens": 85544454.0, "step": 14375 }, { "epoch": 0.15341448582676326, "grad_norm": 2.698716292040273, "learning_rate": 4.869738956076987e-05, "loss": 0.6242, "num_tokens": 85559477.0, "step": 14380 }, { "epoch": 0.1534678288329617, "grad_norm": 1.525064508445354, "learning_rate": 4.869605834610461e-05, "loss": 0.6514, "num_tokens": 85584289.0, "step": 14385 }, { "epoch": 0.15352117183916017, "grad_norm": 1.028683360102337, "learning_rate": 4.8694726471861554e-05, "loss": 0.5909, "num_tokens": 85609188.0, "step": 14390 }, { "epoch": 0.1535745148453586, "grad_norm": 1.0644306939248882, "learning_rate": 4.8693393938082156e-05, "loss": 0.6192, "num_tokens": 85648994.0, "step": 14395 }, { "epoch": 0.15362785785155708, "grad_norm": 1.3526840204625732, "learning_rate": 4.869206074480786e-05, "loss": 0.545, "num_tokens": 85675897.0, "step": 14400 }, { "epoch": 0.15368120085775555, "grad_norm": 1.9071977251916254, "learning_rate": 4.869072689208017e-05, "loss": 0.6635, "num_tokens": 85697238.0, "step": 14405 }, { "epoch": 0.153734543863954, "grad_norm": 1.0700094419096244, "learning_rate": 4.868939237994058e-05, "loss": 0.7359, "num_tokens": 85719656.0, "step": 14410 }, { "epoch": 0.15378788687015246, "grad_norm": 2.1399142188996736, "learning_rate": 4.8688057208430625e-05, "loss": 0.6091, "num_tokens": 85750034.0, "step": 14415 }, { "epoch": 0.1538412298763509, "grad_norm": 1.391209832285948, "learning_rate": 4.868672137759186e-05, "loss": 0.5248, "num_tokens": 85783514.0, "step": 14420 }, { "epoch": 0.15389457288254937, "grad_norm": 1.3193034412065303, "learning_rate": 4.868538488746583e-05, "loss": 0.6178, "num_tokens": 85810261.0, "step": 14425 }, { "epoch": 0.15394791588874782, "grad_norm": 0.8488910742210096, "learning_rate": 4.868404773809415e-05, "loss": 0.6414, "num_tokens": 85845954.0, "step": 14430 }, { "epoch": 0.15400125889494629, "grad_norm": 1.4851620808248365, "learning_rate": 4.868270992951841e-05, "loss": 0.5843, "num_tokens": 85874670.0, "step": 14435 }, { "epoch": 0.15405460190114473, "grad_norm": 1.3227525104670719, "learning_rate": 4.868137146178025e-05, "loss": 0.7402, "num_tokens": 85907280.0, "step": 14440 }, { "epoch": 0.1541079449073432, "grad_norm": 1.0114869386106524, "learning_rate": 4.8680032334921316e-05, "loss": 0.7251, "num_tokens": 85947838.0, "step": 14445 }, { "epoch": 0.15416128791354167, "grad_norm": 0.8981860535514884, "learning_rate": 4.867869254898329e-05, "loss": 0.6366, "num_tokens": 85996040.0, "step": 14450 }, { "epoch": 0.1542146309197401, "grad_norm": 1.7015895705034307, "learning_rate": 4.867735210400785e-05, "loss": 0.6658, "num_tokens": 86028215.0, "step": 14455 }, { "epoch": 0.15426797392593858, "grad_norm": 2.2246253860056675, "learning_rate": 4.86760110000367e-05, "loss": 0.7097, "num_tokens": 86054749.0, "step": 14460 }, { "epoch": 0.15432131693213702, "grad_norm": 1.5274596203433526, "learning_rate": 4.86746692371116e-05, "loss": 0.7961, "num_tokens": 86091666.0, "step": 14465 }, { "epoch": 0.1543746599383355, "grad_norm": 1.6454435927035975, "learning_rate": 4.8673326815274285e-05, "loss": 0.7707, "num_tokens": 86116001.0, "step": 14470 }, { "epoch": 0.15442800294453393, "grad_norm": 1.3457654552178344, "learning_rate": 4.8671983734566526e-05, "loss": 0.7686, "num_tokens": 86149530.0, "step": 14475 }, { "epoch": 0.1544813459507324, "grad_norm": 0.9647541573564413, "learning_rate": 4.867063999503012e-05, "loss": 0.7794, "num_tokens": 86192179.0, "step": 14480 }, { "epoch": 0.15453468895693084, "grad_norm": 1.539862620946584, "learning_rate": 4.8669295596706886e-05, "loss": 0.7689, "num_tokens": 86234108.0, "step": 14485 }, { "epoch": 0.1545880319631293, "grad_norm": 1.3604955863568737, "learning_rate": 4.866795053963866e-05, "loss": 0.6538, "num_tokens": 86258119.0, "step": 14490 }, { "epoch": 0.15464137496932778, "grad_norm": 0.8172705090644123, "learning_rate": 4.8666604823867284e-05, "loss": 0.6787, "num_tokens": 86299019.0, "step": 14495 }, { "epoch": 0.15469471797552622, "grad_norm": 0.9510256872650495, "learning_rate": 4.866525844943465e-05, "loss": 0.7105, "num_tokens": 86343362.0, "step": 14500 }, { "epoch": 0.1547480609817247, "grad_norm": 2.191458601034755, "learning_rate": 4.8663911416382644e-05, "loss": 0.6082, "num_tokens": 86364211.0, "step": 14505 }, { "epoch": 0.15480140398792314, "grad_norm": 1.3622505114345782, "learning_rate": 4.8662563724753193e-05, "loss": 0.6785, "num_tokens": 86397521.0, "step": 14510 }, { "epoch": 0.1548547469941216, "grad_norm": 1.4301573426016987, "learning_rate": 4.866121537458822e-05, "loss": 0.5197, "num_tokens": 86415625.0, "step": 14515 }, { "epoch": 0.15490809000032005, "grad_norm": 0.9684443107095181, "learning_rate": 4.86598663659297e-05, "loss": 0.7039, "num_tokens": 86448631.0, "step": 14520 }, { "epoch": 0.15496143300651852, "grad_norm": 0.9069708164636568, "learning_rate": 4.8658516698819595e-05, "loss": 0.6633, "num_tokens": 86479982.0, "step": 14525 }, { "epoch": 0.15501477601271696, "grad_norm": 1.0807247209759288, "learning_rate": 4.8657166373299915e-05, "loss": 0.6221, "num_tokens": 86511226.0, "step": 14530 }, { "epoch": 0.15506811901891543, "grad_norm": 0.7523814233030139, "learning_rate": 4.8655815389412674e-05, "loss": 0.7051, "num_tokens": 86555231.0, "step": 14535 }, { "epoch": 0.1551214620251139, "grad_norm": 2.68985920675797, "learning_rate": 4.8654463747199915e-05, "loss": 0.6345, "num_tokens": 86577852.0, "step": 14540 }, { "epoch": 0.15517480503131234, "grad_norm": 0.8191474259145965, "learning_rate": 4.8653111446703696e-05, "loss": 0.5411, "num_tokens": 86619741.0, "step": 14545 }, { "epoch": 0.1552281480375108, "grad_norm": 1.0089978216117872, "learning_rate": 4.865175848796609e-05, "loss": 0.5759, "num_tokens": 86642339.0, "step": 14550 }, { "epoch": 0.15528149104370925, "grad_norm": 2.991358112542407, "learning_rate": 4.865040487102922e-05, "loss": 0.7271, "num_tokens": 86683695.0, "step": 14555 }, { "epoch": 0.15533483404990772, "grad_norm": 0.9693449720560529, "learning_rate": 4.8649050595935185e-05, "loss": 0.6807, "num_tokens": 86722595.0, "step": 14560 }, { "epoch": 0.15538817705610616, "grad_norm": 3.0776787201434046, "learning_rate": 4.8647695662726145e-05, "loss": 0.6919, "num_tokens": 86753485.0, "step": 14565 }, { "epoch": 0.15544152006230463, "grad_norm": 1.5294066421915176, "learning_rate": 4.864634007144425e-05, "loss": 0.6733, "num_tokens": 86778998.0, "step": 14570 }, { "epoch": 0.15549486306850308, "grad_norm": 0.801851861364784, "learning_rate": 4.864498382213169e-05, "loss": 0.5043, "num_tokens": 86810449.0, "step": 14575 }, { "epoch": 0.15554820607470154, "grad_norm": 1.4651394697356004, "learning_rate": 4.8643626914830664e-05, "loss": 0.5739, "num_tokens": 86836952.0, "step": 14580 }, { "epoch": 0.15560154908090001, "grad_norm": 1.2392339609402128, "learning_rate": 4.8642269349583395e-05, "loss": 0.7874, "num_tokens": 86865121.0, "step": 14585 }, { "epoch": 0.15565489208709846, "grad_norm": 1.016624330386726, "learning_rate": 4.8640911126432136e-05, "loss": 0.5891, "num_tokens": 86886425.0, "step": 14590 }, { "epoch": 0.15570823509329693, "grad_norm": 2.2247647804769812, "learning_rate": 4.863955224541915e-05, "loss": 0.8128, "num_tokens": 86917428.0, "step": 14595 }, { "epoch": 0.15576157809949537, "grad_norm": 1.5165419661746844, "learning_rate": 4.863819270658672e-05, "loss": 0.8055, "num_tokens": 86932796.0, "step": 14600 }, { "epoch": 0.15581492110569384, "grad_norm": 1.3354140156579157, "learning_rate": 4.863683250997714e-05, "loss": 0.6399, "num_tokens": 86979285.0, "step": 14605 }, { "epoch": 0.15586826411189228, "grad_norm": 1.037613216678665, "learning_rate": 4.863547165563276e-05, "loss": 0.6836, "num_tokens": 86995827.0, "step": 14610 }, { "epoch": 0.15592160711809075, "grad_norm": 1.5682501321843285, "learning_rate": 4.863411014359592e-05, "loss": 0.7228, "num_tokens": 87020545.0, "step": 14615 }, { "epoch": 0.1559749501242892, "grad_norm": 1.573949792737383, "learning_rate": 4.863274797390897e-05, "loss": 0.5909, "num_tokens": 87041158.0, "step": 14620 }, { "epoch": 0.15602829313048766, "grad_norm": 1.2962882401813762, "learning_rate": 4.8631385146614324e-05, "loss": 0.6597, "num_tokens": 87071655.0, "step": 14625 }, { "epoch": 0.15608163613668613, "grad_norm": 1.5995752109960544, "learning_rate": 4.8630021661754374e-05, "loss": 0.6603, "num_tokens": 87096598.0, "step": 14630 }, { "epoch": 0.15613497914288457, "grad_norm": 1.0720417450465523, "learning_rate": 4.8628657519371546e-05, "loss": 0.5987, "num_tokens": 87124777.0, "step": 14635 }, { "epoch": 0.15618832214908304, "grad_norm": 1.0085594247758984, "learning_rate": 4.86272927195083e-05, "loss": 0.6917, "num_tokens": 87175045.0, "step": 14640 }, { "epoch": 0.15624166515528148, "grad_norm": 1.0157129878788018, "learning_rate": 4.862592726220709e-05, "loss": 0.5651, "num_tokens": 87196220.0, "step": 14645 }, { "epoch": 0.15629500816147995, "grad_norm": 1.6433909083744727, "learning_rate": 4.862456114751043e-05, "loss": 0.4981, "num_tokens": 87217876.0, "step": 14650 }, { "epoch": 0.1563483511676784, "grad_norm": 1.2081905089755272, "learning_rate": 4.862319437546082e-05, "loss": 0.6527, "num_tokens": 87234837.0, "step": 14655 }, { "epoch": 0.15640169417387687, "grad_norm": 0.828190785544282, "learning_rate": 4.862182694610078e-05, "loss": 0.6131, "num_tokens": 87282636.0, "step": 14660 }, { "epoch": 0.1564550371800753, "grad_norm": 1.5096724534872605, "learning_rate": 4.8620458859472885e-05, "loss": 0.6043, "num_tokens": 87298873.0, "step": 14665 }, { "epoch": 0.15650838018627378, "grad_norm": 1.5079920043958435, "learning_rate": 4.861909011561968e-05, "loss": 0.6693, "num_tokens": 87336582.0, "step": 14670 }, { "epoch": 0.15656172319247225, "grad_norm": 1.085524249520109, "learning_rate": 4.861772071458377e-05, "loss": 0.6426, "num_tokens": 87374032.0, "step": 14675 }, { "epoch": 0.1566150661986707, "grad_norm": 1.539963265708495, "learning_rate": 4.861635065640777e-05, "loss": 0.6492, "num_tokens": 87420204.0, "step": 14680 }, { "epoch": 0.15666840920486916, "grad_norm": 0.8926432344489806, "learning_rate": 4.861497994113432e-05, "loss": 0.5785, "num_tokens": 87462887.0, "step": 14685 }, { "epoch": 0.1567217522110676, "grad_norm": 3.9826473969724345, "learning_rate": 4.8613608568806057e-05, "loss": 0.6992, "num_tokens": 87491365.0, "step": 14690 }, { "epoch": 0.15677509521726607, "grad_norm": 0.9255952649992293, "learning_rate": 4.861223653946567e-05, "loss": 0.7153, "num_tokens": 87533103.0, "step": 14695 }, { "epoch": 0.1568284382234645, "grad_norm": 0.9339100635734175, "learning_rate": 4.861086385315585e-05, "loss": 0.5342, "num_tokens": 87560794.0, "step": 14700 }, { "epoch": 0.15688178122966298, "grad_norm": 1.5799123558986459, "learning_rate": 4.860949050991929e-05, "loss": 0.5968, "num_tokens": 87589802.0, "step": 14705 }, { "epoch": 0.15693512423586142, "grad_norm": 1.033591295270846, "learning_rate": 4.860811650979876e-05, "loss": 0.6755, "num_tokens": 87616535.0, "step": 14710 }, { "epoch": 0.1569884672420599, "grad_norm": 1.4728313204500565, "learning_rate": 4.860674185283701e-05, "loss": 0.6733, "num_tokens": 87647880.0, "step": 14715 }, { "epoch": 0.15704181024825836, "grad_norm": 1.195026909296862, "learning_rate": 4.860536653907679e-05, "loss": 0.626, "num_tokens": 87691018.0, "step": 14720 }, { "epoch": 0.1570951532544568, "grad_norm": 1.219689682015228, "learning_rate": 4.860399056856093e-05, "loss": 0.5306, "num_tokens": 87718321.0, "step": 14725 }, { "epoch": 0.15714849626065527, "grad_norm": 1.1165999512055065, "learning_rate": 4.8602613941332234e-05, "loss": 0.6788, "num_tokens": 87744254.0, "step": 14730 }, { "epoch": 0.15720183926685372, "grad_norm": 1.023293058935721, "learning_rate": 4.860123665743352e-05, "loss": 0.6269, "num_tokens": 87778961.0, "step": 14735 }, { "epoch": 0.15725518227305219, "grad_norm": 1.7986641403303776, "learning_rate": 4.8599858716907674e-05, "loss": 0.7057, "num_tokens": 87819493.0, "step": 14740 }, { "epoch": 0.15730852527925063, "grad_norm": 0.7732087087597871, "learning_rate": 4.8598480119797575e-05, "loss": 0.5758, "num_tokens": 87858365.0, "step": 14745 }, { "epoch": 0.1573618682854491, "grad_norm": 1.1259922361754626, "learning_rate": 4.85971008661461e-05, "loss": 0.5468, "num_tokens": 87881186.0, "step": 14750 }, { "epoch": 0.15741521129164754, "grad_norm": 1.2704011416884455, "learning_rate": 4.859572095599618e-05, "loss": 0.6314, "num_tokens": 87908486.0, "step": 14755 }, { "epoch": 0.157468554297846, "grad_norm": 1.4860807420777997, "learning_rate": 4.859434038939077e-05, "loss": 0.5368, "num_tokens": 87930439.0, "step": 14760 }, { "epoch": 0.15752189730404448, "grad_norm": 1.575430865955576, "learning_rate": 4.8592959166372804e-05, "loss": 0.8041, "num_tokens": 87957266.0, "step": 14765 }, { "epoch": 0.15757524031024292, "grad_norm": 1.2938163687366813, "learning_rate": 4.8591577286985274e-05, "loss": 0.5524, "num_tokens": 87986825.0, "step": 14770 }, { "epoch": 0.1576285833164414, "grad_norm": 3.0918583925724543, "learning_rate": 4.859019475127119e-05, "loss": 0.5986, "num_tokens": 88004444.0, "step": 14775 }, { "epoch": 0.15768192632263983, "grad_norm": 1.4170507150543161, "learning_rate": 4.8588811559273556e-05, "loss": 0.6979, "num_tokens": 88026967.0, "step": 14780 }, { "epoch": 0.1577352693288383, "grad_norm": 1.5604976157471362, "learning_rate": 4.8587427711035427e-05, "loss": 0.5725, "num_tokens": 88048086.0, "step": 14785 }, { "epoch": 0.15778861233503674, "grad_norm": 1.433721747647885, "learning_rate": 4.858604320659987e-05, "loss": 0.7414, "num_tokens": 88083076.0, "step": 14790 }, { "epoch": 0.1578419553412352, "grad_norm": 1.386233154491704, "learning_rate": 4.858465804600995e-05, "loss": 0.5495, "num_tokens": 88112607.0, "step": 14795 }, { "epoch": 0.15789529834743365, "grad_norm": 2.1918367598749495, "learning_rate": 4.858327222930878e-05, "loss": 0.5949, "num_tokens": 88141621.0, "step": 14800 }, { "epoch": 0.15794864135363212, "grad_norm": 1.5276351203563772, "learning_rate": 4.85818857565395e-05, "loss": 0.5725, "num_tokens": 88162814.0, "step": 14805 }, { "epoch": 0.1580019843598306, "grad_norm": 1.001318487814814, "learning_rate": 4.8580498627745226e-05, "loss": 0.654, "num_tokens": 88183148.0, "step": 14810 }, { "epoch": 0.15805532736602904, "grad_norm": 0.8868994943548022, "learning_rate": 4.857911084296914e-05, "loss": 0.6216, "num_tokens": 88221356.0, "step": 14815 }, { "epoch": 0.1581086703722275, "grad_norm": 1.5589546558236729, "learning_rate": 4.8577722402254416e-05, "loss": 0.602, "num_tokens": 88253996.0, "step": 14820 }, { "epoch": 0.15816201337842595, "grad_norm": 2.5051751674399574, "learning_rate": 4.857633330564427e-05, "loss": 0.5735, "num_tokens": 88282761.0, "step": 14825 }, { "epoch": 0.15821535638462442, "grad_norm": 1.123743843506413, "learning_rate": 4.857494355318193e-05, "loss": 0.6218, "num_tokens": 88303813.0, "step": 14830 }, { "epoch": 0.15826869939082286, "grad_norm": 0.7761944552705583, "learning_rate": 4.8573553144910624e-05, "loss": 0.6228, "num_tokens": 88341078.0, "step": 14835 }, { "epoch": 0.15832204239702133, "grad_norm": 1.125761524876402, "learning_rate": 4.8572162080873633e-05, "loss": 0.6502, "num_tokens": 88365460.0, "step": 14840 }, { "epoch": 0.15837538540321977, "grad_norm": 0.9841288725689243, "learning_rate": 4.8570770361114246e-05, "loss": 0.7314, "num_tokens": 88405605.0, "step": 14845 }, { "epoch": 0.15842872840941824, "grad_norm": 0.9554784187605667, "learning_rate": 4.856937798567577e-05, "loss": 0.5622, "num_tokens": 88435408.0, "step": 14850 }, { "epoch": 0.1584820714156167, "grad_norm": 0.89789812684146, "learning_rate": 4.856798495460151e-05, "loss": 0.6819, "num_tokens": 88460338.0, "step": 14855 }, { "epoch": 0.15853541442181515, "grad_norm": 1.3667373113673944, "learning_rate": 4.856659126793485e-05, "loss": 0.5311, "num_tokens": 88492183.0, "step": 14860 }, { "epoch": 0.15858875742801362, "grad_norm": 1.258566154042921, "learning_rate": 4.8565196925719146e-05, "loss": 0.6424, "num_tokens": 88510891.0, "step": 14865 }, { "epoch": 0.15864210043421206, "grad_norm": 0.7331695831870778, "learning_rate": 4.856380192799777e-05, "loss": 0.5672, "num_tokens": 88550918.0, "step": 14870 }, { "epoch": 0.15869544344041053, "grad_norm": 0.9658324760648686, "learning_rate": 4.8562406274814145e-05, "loss": 0.5865, "num_tokens": 88589985.0, "step": 14875 }, { "epoch": 0.15874878644660897, "grad_norm": 1.0792509252192661, "learning_rate": 4.856100996621171e-05, "loss": 0.7411, "num_tokens": 88637962.0, "step": 14880 }, { "epoch": 0.15880212945280744, "grad_norm": 0.9853582216908415, "learning_rate": 4.85596130022339e-05, "loss": 0.6517, "num_tokens": 88661149.0, "step": 14885 }, { "epoch": 0.1588554724590059, "grad_norm": 1.0365778481302026, "learning_rate": 4.8558215382924195e-05, "loss": 0.5232, "num_tokens": 88681934.0, "step": 14890 }, { "epoch": 0.15890881546520436, "grad_norm": 1.059387374336723, "learning_rate": 4.855681710832608e-05, "loss": 0.6965, "num_tokens": 88712284.0, "step": 14895 }, { "epoch": 0.15896215847140283, "grad_norm": 1.2434005554779748, "learning_rate": 4.855541817848306e-05, "loss": 0.7846, "num_tokens": 88744109.0, "step": 14900 }, { "epoch": 0.15901550147760127, "grad_norm": 0.9823819373212862, "learning_rate": 4.855401859343868e-05, "loss": 0.6531, "num_tokens": 88787735.0, "step": 14905 }, { "epoch": 0.15906884448379974, "grad_norm": 0.9467359531595277, "learning_rate": 4.855261835323649e-05, "loss": 0.5923, "num_tokens": 88825803.0, "step": 14910 }, { "epoch": 0.15912218748999818, "grad_norm": 1.6370503860487124, "learning_rate": 4.855121745792006e-05, "loss": 0.7989, "num_tokens": 88858442.0, "step": 14915 }, { "epoch": 0.15917553049619665, "grad_norm": 2.0657946586062375, "learning_rate": 4.854981590753299e-05, "loss": 0.7494, "num_tokens": 88876745.0, "step": 14920 }, { "epoch": 0.1592288735023951, "grad_norm": 1.0497912495897428, "learning_rate": 4.854841370211887e-05, "loss": 0.6224, "num_tokens": 88914723.0, "step": 14925 }, { "epoch": 0.15928221650859356, "grad_norm": 0.9489146128564122, "learning_rate": 4.854701084172136e-05, "loss": 0.5206, "num_tokens": 88947015.0, "step": 14930 }, { "epoch": 0.159335559514792, "grad_norm": 1.110305362188179, "learning_rate": 4.8545607326384106e-05, "loss": 0.5856, "num_tokens": 88980473.0, "step": 14935 }, { "epoch": 0.15938890252099047, "grad_norm": 1.0670721840163395, "learning_rate": 4.854420315615078e-05, "loss": 0.521, "num_tokens": 89014272.0, "step": 14940 }, { "epoch": 0.15944224552718894, "grad_norm": 0.8870474797390543, "learning_rate": 4.854279833106507e-05, "loss": 0.5823, "num_tokens": 89034630.0, "step": 14945 }, { "epoch": 0.15949558853338738, "grad_norm": 1.545770539725545, "learning_rate": 4.854139285117071e-05, "loss": 0.6497, "num_tokens": 89075647.0, "step": 14950 }, { "epoch": 0.15954893153958585, "grad_norm": 1.0027851137679293, "learning_rate": 4.853998671651142e-05, "loss": 0.624, "num_tokens": 89104479.0, "step": 14955 }, { "epoch": 0.1596022745457843, "grad_norm": 1.5582356598109854, "learning_rate": 4.853857992713096e-05, "loss": 0.611, "num_tokens": 89133287.0, "step": 14960 }, { "epoch": 0.15965561755198276, "grad_norm": 0.9821203494571156, "learning_rate": 4.8537172483073105e-05, "loss": 0.5621, "num_tokens": 89170223.0, "step": 14965 }, { "epoch": 0.1597089605581812, "grad_norm": 1.3832067159899375, "learning_rate": 4.853576438438166e-05, "loss": 0.708, "num_tokens": 89208089.0, "step": 14970 }, { "epoch": 0.15976230356437968, "grad_norm": 2.109310758290334, "learning_rate": 4.853435563110043e-05, "loss": 0.5448, "num_tokens": 89223442.0, "step": 14975 }, { "epoch": 0.15981564657057812, "grad_norm": 1.2417317966864845, "learning_rate": 4.853294622327326e-05, "loss": 0.5431, "num_tokens": 89239410.0, "step": 14980 }, { "epoch": 0.1598689895767766, "grad_norm": 1.1247337099049004, "learning_rate": 4.853153616094401e-05, "loss": 0.6947, "num_tokens": 89268761.0, "step": 14985 }, { "epoch": 0.15992233258297506, "grad_norm": 1.0679601446159293, "learning_rate": 4.853012544415655e-05, "loss": 0.574, "num_tokens": 89293776.0, "step": 14990 }, { "epoch": 0.1599756755891735, "grad_norm": 1.5711475590133104, "learning_rate": 4.852871407295479e-05, "loss": 0.6318, "num_tokens": 89313258.0, "step": 14995 }, { "epoch": 0.16002901859537197, "grad_norm": 1.2100653679808984, "learning_rate": 4.852730204738264e-05, "loss": 0.6442, "num_tokens": 89352441.0, "step": 15000 }, { "epoch": 0.1600823616015704, "grad_norm": 1.0197074580995713, "learning_rate": 4.852588936748404e-05, "loss": 0.6101, "num_tokens": 89382838.0, "step": 15005 }, { "epoch": 0.16013570460776888, "grad_norm": 0.9386416675048763, "learning_rate": 4.852447603330295e-05, "loss": 0.5184, "num_tokens": 89410768.0, "step": 15010 }, { "epoch": 0.16018904761396732, "grad_norm": 1.1084994601525902, "learning_rate": 4.852306204488335e-05, "loss": 0.7034, "num_tokens": 89436887.0, "step": 15015 }, { "epoch": 0.1602423906201658, "grad_norm": 1.621668178626833, "learning_rate": 4.852164740226925e-05, "loss": 0.8365, "num_tokens": 89469690.0, "step": 15020 }, { "epoch": 0.16029573362636423, "grad_norm": 1.5057983142901508, "learning_rate": 4.852023210550465e-05, "loss": 0.6583, "num_tokens": 89483289.0, "step": 15025 }, { "epoch": 0.1603490766325627, "grad_norm": 2.2328721026734417, "learning_rate": 4.8518816154633614e-05, "loss": 0.695, "num_tokens": 89517943.0, "step": 15030 }, { "epoch": 0.16040241963876117, "grad_norm": 2.504311280524996, "learning_rate": 4.851739954970019e-05, "loss": 0.7229, "num_tokens": 89541552.0, "step": 15035 }, { "epoch": 0.16045576264495962, "grad_norm": 0.8429818865406564, "learning_rate": 4.851598229074846e-05, "loss": 0.5997, "num_tokens": 89579835.0, "step": 15040 }, { "epoch": 0.16050910565115808, "grad_norm": 1.3328406788327527, "learning_rate": 4.8514564377822535e-05, "loss": 0.5365, "num_tokens": 89601925.0, "step": 15045 }, { "epoch": 0.16056244865735653, "grad_norm": 1.1329198158969138, "learning_rate": 4.8513145810966526e-05, "loss": 0.626, "num_tokens": 89633088.0, "step": 15050 }, { "epoch": 0.160615791663555, "grad_norm": 1.9753875392749114, "learning_rate": 4.851172659022459e-05, "loss": 0.7239, "num_tokens": 89683188.0, "step": 15055 }, { "epoch": 0.16066913466975344, "grad_norm": 2.0036186402888, "learning_rate": 4.8510306715640876e-05, "loss": 0.617, "num_tokens": 89728762.0, "step": 15060 }, { "epoch": 0.1607224776759519, "grad_norm": 1.4101403397826062, "learning_rate": 4.8508886187259565e-05, "loss": 0.5406, "num_tokens": 89748455.0, "step": 15065 }, { "epoch": 0.16077582068215035, "grad_norm": 1.1867104389308423, "learning_rate": 4.850746500512489e-05, "loss": 0.5801, "num_tokens": 89783989.0, "step": 15070 }, { "epoch": 0.16082916368834882, "grad_norm": 1.1006810365918938, "learning_rate": 4.8506043169281036e-05, "loss": 0.6421, "num_tokens": 89806433.0, "step": 15075 }, { "epoch": 0.1608825066945473, "grad_norm": 1.0744478819802934, "learning_rate": 4.850462067977227e-05, "loss": 0.7293, "num_tokens": 89836394.0, "step": 15080 }, { "epoch": 0.16093584970074573, "grad_norm": 0.9395458783631127, "learning_rate": 4.850319753664286e-05, "loss": 0.7605, "num_tokens": 89867421.0, "step": 15085 }, { "epoch": 0.1609891927069442, "grad_norm": 2.7517586700830527, "learning_rate": 4.850177373993707e-05, "loss": 0.7788, "num_tokens": 89902395.0, "step": 15090 }, { "epoch": 0.16104253571314264, "grad_norm": 1.1465576461780835, "learning_rate": 4.850034928969924e-05, "loss": 0.5329, "num_tokens": 89937682.0, "step": 15095 }, { "epoch": 0.1610958787193411, "grad_norm": 1.7680817956537216, "learning_rate": 4.849892418597366e-05, "loss": 0.5738, "num_tokens": 89953100.0, "step": 15100 }, { "epoch": 0.16114922172553955, "grad_norm": 1.0755863801642414, "learning_rate": 4.8497498428804706e-05, "loss": 0.6865, "num_tokens": 89976992.0, "step": 15105 }, { "epoch": 0.16120256473173802, "grad_norm": 0.987987057567831, "learning_rate": 4.849607201823672e-05, "loss": 0.7419, "num_tokens": 90009453.0, "step": 15110 }, { "epoch": 0.16125590773793647, "grad_norm": 1.2264640025285558, "learning_rate": 4.8494644954314104e-05, "loss": 0.5042, "num_tokens": 90040481.0, "step": 15115 }, { "epoch": 0.16130925074413494, "grad_norm": 1.4754842094432796, "learning_rate": 4.849321723708127e-05, "loss": 0.599, "num_tokens": 90060334.0, "step": 15120 }, { "epoch": 0.1613625937503334, "grad_norm": 1.844210865155683, "learning_rate": 4.849178886658262e-05, "loss": 0.6045, "num_tokens": 90083314.0, "step": 15125 }, { "epoch": 0.16141593675653185, "grad_norm": 1.0433424142047785, "learning_rate": 4.849035984286263e-05, "loss": 0.6227, "num_tokens": 90126054.0, "step": 15130 }, { "epoch": 0.16146927976273032, "grad_norm": 1.3359298510637891, "learning_rate": 4.848893016596575e-05, "loss": 0.5892, "num_tokens": 90159186.0, "step": 15135 }, { "epoch": 0.16152262276892876, "grad_norm": 1.0173208170766344, "learning_rate": 4.848749983593649e-05, "loss": 0.5814, "num_tokens": 90196615.0, "step": 15140 }, { "epoch": 0.16157596577512723, "grad_norm": 1.0501488817198343, "learning_rate": 4.848606885281932e-05, "loss": 0.6688, "num_tokens": 90218945.0, "step": 15145 }, { "epoch": 0.16162930878132567, "grad_norm": 1.0849739725070617, "learning_rate": 4.848463721665881e-05, "loss": 0.5359, "num_tokens": 90247555.0, "step": 15150 }, { "epoch": 0.16168265178752414, "grad_norm": 0.9028151752320681, "learning_rate": 4.84832049274995e-05, "loss": 0.7374, "num_tokens": 90298167.0, "step": 15155 }, { "epoch": 0.16173599479372258, "grad_norm": 1.1024513623113537, "learning_rate": 4.8481771985385935e-05, "loss": 0.6924, "num_tokens": 90331450.0, "step": 15160 }, { "epoch": 0.16178933779992105, "grad_norm": 1.6396034891341216, "learning_rate": 4.848033839036274e-05, "loss": 0.5537, "num_tokens": 90352882.0, "step": 15165 }, { "epoch": 0.16184268080611952, "grad_norm": 1.188978270083889, "learning_rate": 4.8478904142474505e-05, "loss": 0.652, "num_tokens": 90393003.0, "step": 15170 }, { "epoch": 0.16189602381231796, "grad_norm": 2.7509885679655866, "learning_rate": 4.847746924176586e-05, "loss": 0.5481, "num_tokens": 90424883.0, "step": 15175 }, { "epoch": 0.16194936681851643, "grad_norm": 1.0664726075767652, "learning_rate": 4.847603368828146e-05, "loss": 0.5671, "num_tokens": 90452985.0, "step": 15180 }, { "epoch": 0.16200270982471487, "grad_norm": 0.8984083613402886, "learning_rate": 4.847459748206598e-05, "loss": 0.5424, "num_tokens": 90491647.0, "step": 15185 }, { "epoch": 0.16205605283091334, "grad_norm": 0.6633700965304861, "learning_rate": 4.847316062316411e-05, "loss": 0.5687, "num_tokens": 90519894.0, "step": 15190 }, { "epoch": 0.16210939583711179, "grad_norm": 1.3276777980770642, "learning_rate": 4.8471723111620574e-05, "loss": 0.6744, "num_tokens": 90547669.0, "step": 15195 }, { "epoch": 0.16216273884331026, "grad_norm": 1.487329100620008, "learning_rate": 4.847028494748007e-05, "loss": 0.6608, "num_tokens": 90579891.0, "step": 15200 }, { "epoch": 0.1622160818495087, "grad_norm": 1.4721095589645716, "learning_rate": 4.846884613078738e-05, "loss": 0.5698, "num_tokens": 90609981.0, "step": 15205 }, { "epoch": 0.16226942485570717, "grad_norm": 1.4153102581744064, "learning_rate": 4.846740666158728e-05, "loss": 0.5335, "num_tokens": 90634778.0, "step": 15210 }, { "epoch": 0.16232276786190564, "grad_norm": 1.0200656240944694, "learning_rate": 4.8465966539924544e-05, "loss": 0.5382, "num_tokens": 90653483.0, "step": 15215 }, { "epoch": 0.16237611086810408, "grad_norm": 1.045189451839863, "learning_rate": 4.846452576584399e-05, "loss": 0.6247, "num_tokens": 90673400.0, "step": 15220 }, { "epoch": 0.16242945387430255, "grad_norm": 0.992863090130643, "learning_rate": 4.8463084339390466e-05, "loss": 0.6583, "num_tokens": 90708535.0, "step": 15225 }, { "epoch": 0.162482796880501, "grad_norm": 1.4193719832588867, "learning_rate": 4.846164226060882e-05, "loss": 0.6724, "num_tokens": 90734738.0, "step": 15230 }, { "epoch": 0.16253613988669946, "grad_norm": 1.0000388103530478, "learning_rate": 4.8460199529543916e-05, "loss": 0.5287, "num_tokens": 90760484.0, "step": 15235 }, { "epoch": 0.1625894828928979, "grad_norm": 2.882699677295994, "learning_rate": 4.8458756146240656e-05, "loss": 0.6999, "num_tokens": 90782212.0, "step": 15240 }, { "epoch": 0.16264282589909637, "grad_norm": 2.719713223123183, "learning_rate": 4.8457312110743954e-05, "loss": 0.7564, "num_tokens": 90814078.0, "step": 15245 }, { "epoch": 0.1626961689052948, "grad_norm": 1.0072026580025206, "learning_rate": 4.845586742309875e-05, "loss": 0.6735, "num_tokens": 90859931.0, "step": 15250 }, { "epoch": 0.16274951191149328, "grad_norm": 1.3155608674193673, "learning_rate": 4.8454422083349995e-05, "loss": 0.6305, "num_tokens": 90895246.0, "step": 15255 }, { "epoch": 0.16280285491769175, "grad_norm": 0.9196801713380491, "learning_rate": 4.8452976091542665e-05, "loss": 0.7339, "num_tokens": 90920668.0, "step": 15260 }, { "epoch": 0.1628561979238902, "grad_norm": 0.8912553068938791, "learning_rate": 4.845152944772176e-05, "loss": 0.6648, "num_tokens": 90951282.0, "step": 15265 }, { "epoch": 0.16290954093008866, "grad_norm": 0.8914438460293737, "learning_rate": 4.8450082151932296e-05, "loss": 0.5628, "num_tokens": 90983485.0, "step": 15270 }, { "epoch": 0.1629628839362871, "grad_norm": 1.0438990728059545, "learning_rate": 4.84486342042193e-05, "loss": 0.6338, "num_tokens": 91016280.0, "step": 15275 }, { "epoch": 0.16301622694248558, "grad_norm": 1.8585694336760512, "learning_rate": 4.844718560462785e-05, "loss": 0.6002, "num_tokens": 91038959.0, "step": 15280 }, { "epoch": 0.16306956994868402, "grad_norm": 0.855783112746549, "learning_rate": 4.8445736353202996e-05, "loss": 0.5761, "num_tokens": 91067682.0, "step": 15285 }, { "epoch": 0.1631229129548825, "grad_norm": 1.146343054174269, "learning_rate": 4.844428644998986e-05, "loss": 0.6345, "num_tokens": 91104236.0, "step": 15290 }, { "epoch": 0.16317625596108093, "grad_norm": 1.0212555621993236, "learning_rate": 4.844283589503355e-05, "loss": 0.6711, "num_tokens": 91144752.0, "step": 15295 }, { "epoch": 0.1632295989672794, "grad_norm": 1.317488295989557, "learning_rate": 4.844138468837921e-05, "loss": 0.6324, "num_tokens": 91179308.0, "step": 15300 }, { "epoch": 0.16328294197347787, "grad_norm": 1.3306471322047684, "learning_rate": 4.843993283007198e-05, "loss": 0.6068, "num_tokens": 91203030.0, "step": 15305 }, { "epoch": 0.1633362849796763, "grad_norm": 0.9678829068723923, "learning_rate": 4.843848032015706e-05, "loss": 0.6013, "num_tokens": 91246141.0, "step": 15310 }, { "epoch": 0.16338962798587478, "grad_norm": 1.1169770373507362, "learning_rate": 4.843702715867964e-05, "loss": 0.5685, "num_tokens": 91277935.0, "step": 15315 }, { "epoch": 0.16344297099207322, "grad_norm": 1.1516233191025158, "learning_rate": 4.843557334568494e-05, "loss": 0.6934, "num_tokens": 91310962.0, "step": 15320 }, { "epoch": 0.1634963139982717, "grad_norm": 0.8754677011749455, "learning_rate": 4.84341188812182e-05, "loss": 0.6161, "num_tokens": 91342511.0, "step": 15325 }, { "epoch": 0.16354965700447013, "grad_norm": 1.0375458655676948, "learning_rate": 4.8432663765324687e-05, "loss": 0.6599, "num_tokens": 91381138.0, "step": 15330 }, { "epoch": 0.1636030000106686, "grad_norm": 1.2691838942568112, "learning_rate": 4.843120799804966e-05, "loss": 0.6141, "num_tokens": 91407173.0, "step": 15335 }, { "epoch": 0.16365634301686705, "grad_norm": 1.1269728671547548, "learning_rate": 4.842975157943845e-05, "loss": 0.6017, "num_tokens": 91439655.0, "step": 15340 }, { "epoch": 0.16370968602306551, "grad_norm": 0.7831186113370235, "learning_rate": 4.842829450953635e-05, "loss": 0.5596, "num_tokens": 91474364.0, "step": 15345 }, { "epoch": 0.16376302902926398, "grad_norm": 1.0893956574828418, "learning_rate": 4.842683678838872e-05, "loss": 0.573, "num_tokens": 91500176.0, "step": 15350 }, { "epoch": 0.16381637203546243, "grad_norm": 2.8526740817714655, "learning_rate": 4.842537841604091e-05, "loss": 0.5263, "num_tokens": 91512536.0, "step": 15355 }, { "epoch": 0.1638697150416609, "grad_norm": 1.3289018892819424, "learning_rate": 4.842391939253831e-05, "loss": 0.5755, "num_tokens": 91542428.0, "step": 15360 }, { "epoch": 0.16392305804785934, "grad_norm": 2.6043938311960226, "learning_rate": 4.842245971792631e-05, "loss": 0.6494, "num_tokens": 91564976.0, "step": 15365 }, { "epoch": 0.1639764010540578, "grad_norm": 1.1118266337310985, "learning_rate": 4.8420999392250346e-05, "loss": 0.6206, "num_tokens": 91584015.0, "step": 15370 }, { "epoch": 0.16402974406025625, "grad_norm": 0.9863627191221254, "learning_rate": 4.841953841555585e-05, "loss": 0.6118, "num_tokens": 91611297.0, "step": 15375 }, { "epoch": 0.16408308706645472, "grad_norm": 0.9193880706382496, "learning_rate": 4.84180767878883e-05, "loss": 0.5877, "num_tokens": 91648126.0, "step": 15380 }, { "epoch": 0.16413643007265316, "grad_norm": 0.974653377036531, "learning_rate": 4.8416614509293154e-05, "loss": 0.5901, "num_tokens": 91679422.0, "step": 15385 }, { "epoch": 0.16418977307885163, "grad_norm": 1.4128683770102894, "learning_rate": 4.841515157981593e-05, "loss": 0.5439, "num_tokens": 91710560.0, "step": 15390 }, { "epoch": 0.1642431160850501, "grad_norm": 0.7837453415046413, "learning_rate": 4.8413687999502156e-05, "loss": 0.6755, "num_tokens": 91760560.0, "step": 15395 }, { "epoch": 0.16429645909124854, "grad_norm": 1.4248266869161164, "learning_rate": 4.841222376839737e-05, "loss": 0.5902, "num_tokens": 91789343.0, "step": 15400 }, { "epoch": 0.164349802097447, "grad_norm": 2.947486840877659, "learning_rate": 4.841075888654713e-05, "loss": 0.6979, "num_tokens": 91820558.0, "step": 15405 }, { "epoch": 0.16440314510364545, "grad_norm": 1.4983581711228835, "learning_rate": 4.840929335399703e-05, "loss": 0.6379, "num_tokens": 91846984.0, "step": 15410 }, { "epoch": 0.16445648810984392, "grad_norm": 1.0021926005530266, "learning_rate": 4.8407827170792655e-05, "loss": 0.5272, "num_tokens": 91868797.0, "step": 15415 }, { "epoch": 0.16450983111604237, "grad_norm": 1.1313881569529365, "learning_rate": 4.840636033697966e-05, "loss": 0.6438, "num_tokens": 91911022.0, "step": 15420 }, { "epoch": 0.16456317412224084, "grad_norm": 1.1290465062273296, "learning_rate": 4.8404892852603666e-05, "loss": 0.542, "num_tokens": 91940942.0, "step": 15425 }, { "epoch": 0.16461651712843928, "grad_norm": 1.5182946597891236, "learning_rate": 4.840342471771035e-05, "loss": 0.5901, "num_tokens": 91966799.0, "step": 15430 }, { "epoch": 0.16466986013463775, "grad_norm": 1.27546672223873, "learning_rate": 4.84019559323454e-05, "loss": 0.6129, "num_tokens": 91988913.0, "step": 15435 }, { "epoch": 0.16472320314083622, "grad_norm": 1.4682152837178817, "learning_rate": 4.8400486496554505e-05, "loss": 0.55, "num_tokens": 92005035.0, "step": 15440 }, { "epoch": 0.16477654614703466, "grad_norm": 1.4981704681448775, "learning_rate": 4.839901641038341e-05, "loss": 0.6036, "num_tokens": 92033006.0, "step": 15445 }, { "epoch": 0.16482988915323313, "grad_norm": 1.1558128933610599, "learning_rate": 4.8397545673877846e-05, "loss": 0.6181, "num_tokens": 92055826.0, "step": 15450 }, { "epoch": 0.16488323215943157, "grad_norm": 1.527426096806089, "learning_rate": 4.839607428708359e-05, "loss": 0.7745, "num_tokens": 92089199.0, "step": 15455 }, { "epoch": 0.16493657516563004, "grad_norm": 1.6794471651535408, "learning_rate": 4.8394602250046414e-05, "loss": 0.621, "num_tokens": 92118142.0, "step": 15460 }, { "epoch": 0.16498991817182848, "grad_norm": 1.7340433616297095, "learning_rate": 4.839312956281215e-05, "loss": 0.67, "num_tokens": 92132727.0, "step": 15465 }, { "epoch": 0.16504326117802695, "grad_norm": 0.8374806643714464, "learning_rate": 4.839165622542659e-05, "loss": 0.5838, "num_tokens": 92169981.0, "step": 15470 }, { "epoch": 0.1650966041842254, "grad_norm": 0.9484122003323303, "learning_rate": 4.8390182237935614e-05, "loss": 0.6498, "num_tokens": 92208685.0, "step": 15475 }, { "epoch": 0.16514994719042386, "grad_norm": 1.2427371637566829, "learning_rate": 4.8388707600385077e-05, "loss": 0.6037, "num_tokens": 92244414.0, "step": 15480 }, { "epoch": 0.16520329019662233, "grad_norm": 0.9044475525378152, "learning_rate": 4.8387232312820866e-05, "loss": 0.5723, "num_tokens": 92263414.0, "step": 15485 }, { "epoch": 0.16525663320282077, "grad_norm": 0.9336554947006894, "learning_rate": 4.838575637528889e-05, "loss": 0.6496, "num_tokens": 92300197.0, "step": 15490 }, { "epoch": 0.16530997620901924, "grad_norm": 1.758233226994737, "learning_rate": 4.838427978783507e-05, "loss": 0.6854, "num_tokens": 92337813.0, "step": 15495 }, { "epoch": 0.16536331921521769, "grad_norm": 1.0696350761385283, "learning_rate": 4.838280255050536e-05, "loss": 0.5428, "num_tokens": 92362280.0, "step": 15500 }, { "epoch": 0.16541666222141616, "grad_norm": 1.2364940487174392, "learning_rate": 4.838132466334573e-05, "loss": 0.6103, "num_tokens": 92388447.0, "step": 15505 }, { "epoch": 0.1654700052276146, "grad_norm": 1.358927942182893, "learning_rate": 4.837984612640217e-05, "loss": 0.6917, "num_tokens": 92428283.0, "step": 15510 }, { "epoch": 0.16552334823381307, "grad_norm": 1.08886475110686, "learning_rate": 4.8378366939720684e-05, "loss": 0.5512, "num_tokens": 92449052.0, "step": 15515 }, { "epoch": 0.1655766912400115, "grad_norm": 1.0517790117410695, "learning_rate": 4.8376887103347315e-05, "loss": 0.8113, "num_tokens": 92505502.0, "step": 15520 }, { "epoch": 0.16563003424620998, "grad_norm": 0.991956324169099, "learning_rate": 4.837540661732809e-05, "loss": 0.6058, "num_tokens": 92526717.0, "step": 15525 }, { "epoch": 0.16568337725240845, "grad_norm": 1.1506694512193802, "learning_rate": 4.837392548170909e-05, "loss": 0.6634, "num_tokens": 92566504.0, "step": 15530 }, { "epoch": 0.1657367202586069, "grad_norm": 0.9588496897698614, "learning_rate": 4.837244369653641e-05, "loss": 0.5642, "num_tokens": 92615679.0, "step": 15535 }, { "epoch": 0.16579006326480536, "grad_norm": 1.4479768205659387, "learning_rate": 4.837096126185616e-05, "loss": 0.727, "num_tokens": 92652083.0, "step": 15540 }, { "epoch": 0.1658434062710038, "grad_norm": 1.253680437238604, "learning_rate": 4.836947817771446e-05, "loss": 0.5244, "num_tokens": 92681968.0, "step": 15545 }, { "epoch": 0.16589674927720227, "grad_norm": 0.8026289583303384, "learning_rate": 4.8367994444157466e-05, "loss": 0.7254, "num_tokens": 92731646.0, "step": 15550 }, { "epoch": 0.1659500922834007, "grad_norm": 3.5770652786570376, "learning_rate": 4.8366510061231354e-05, "loss": 0.7502, "num_tokens": 92762541.0, "step": 15555 }, { "epoch": 0.16600343528959918, "grad_norm": 1.0003371602922493, "learning_rate": 4.83650250289823e-05, "loss": 0.6679, "num_tokens": 92779284.0, "step": 15560 }, { "epoch": 0.16605677829579762, "grad_norm": 1.781143295061285, "learning_rate": 4.836353934745654e-05, "loss": 0.5921, "num_tokens": 92815767.0, "step": 15565 }, { "epoch": 0.1661101213019961, "grad_norm": 1.6491580068041571, "learning_rate": 4.836205301670027e-05, "loss": 0.6188, "num_tokens": 92836894.0, "step": 15570 }, { "epoch": 0.16616346430819456, "grad_norm": 0.6780118493954203, "learning_rate": 4.8360566036759786e-05, "loss": 0.6233, "num_tokens": 92870866.0, "step": 15575 }, { "epoch": 0.166216807314393, "grad_norm": 1.4987523123160522, "learning_rate": 4.835907840768132e-05, "loss": 0.6686, "num_tokens": 92906976.0, "step": 15580 }, { "epoch": 0.16627015032059148, "grad_norm": 0.8746154646926879, "learning_rate": 4.8357590129511174e-05, "loss": 0.517, "num_tokens": 92934968.0, "step": 15585 }, { "epoch": 0.16632349332678992, "grad_norm": 1.1355938785279351, "learning_rate": 4.8356101202295685e-05, "loss": 0.5529, "num_tokens": 92971005.0, "step": 15590 }, { "epoch": 0.1663768363329884, "grad_norm": 1.50661012877328, "learning_rate": 4.835461162608115e-05, "loss": 0.6212, "num_tokens": 92999713.0, "step": 15595 }, { "epoch": 0.16643017933918683, "grad_norm": 0.9767631881372766, "learning_rate": 4.835312140091395e-05, "loss": 0.5604, "num_tokens": 93031983.0, "step": 15600 }, { "epoch": 0.1664835223453853, "grad_norm": 1.3698473914505347, "learning_rate": 4.8351630526840434e-05, "loss": 0.729, "num_tokens": 93071168.0, "step": 15605 }, { "epoch": 0.16653686535158374, "grad_norm": 1.1087034755288372, "learning_rate": 4.8350139003907014e-05, "loss": 0.5489, "num_tokens": 93096071.0, "step": 15610 }, { "epoch": 0.1665902083577822, "grad_norm": 1.4643437064590006, "learning_rate": 4.834864683216009e-05, "loss": 0.5767, "num_tokens": 93121596.0, "step": 15615 }, { "epoch": 0.16664355136398068, "grad_norm": 1.6920993736729106, "learning_rate": 4.834715401164611e-05, "loss": 0.5046, "num_tokens": 93149739.0, "step": 15620 }, { "epoch": 0.16669689437017912, "grad_norm": 1.6770550896165648, "learning_rate": 4.834566054241151e-05, "loss": 0.6095, "num_tokens": 93173875.0, "step": 15625 }, { "epoch": 0.1667502373763776, "grad_norm": 0.9335049699422634, "learning_rate": 4.8344166424502776e-05, "loss": 0.5678, "num_tokens": 93200384.0, "step": 15630 }, { "epoch": 0.16680358038257603, "grad_norm": 1.242388750028442, "learning_rate": 4.83426716579664e-05, "loss": 0.7401, "num_tokens": 93224243.0, "step": 15635 }, { "epoch": 0.1668569233887745, "grad_norm": 1.5485242844702984, "learning_rate": 4.834117624284889e-05, "loss": 0.5676, "num_tokens": 93246043.0, "step": 15640 }, { "epoch": 0.16691026639497294, "grad_norm": 1.2520386899563825, "learning_rate": 4.833968017919679e-05, "loss": 0.5975, "num_tokens": 93276874.0, "step": 15645 }, { "epoch": 0.16696360940117141, "grad_norm": 0.9654898329576193, "learning_rate": 4.8338183467056635e-05, "loss": 0.6646, "num_tokens": 93305045.0, "step": 15650 }, { "epoch": 0.16701695240736986, "grad_norm": 1.1140939458628434, "learning_rate": 4.8336686106475026e-05, "loss": 0.687, "num_tokens": 93337450.0, "step": 15655 }, { "epoch": 0.16707029541356833, "grad_norm": 1.531132254121136, "learning_rate": 4.833518809749854e-05, "loss": 0.6763, "num_tokens": 93365130.0, "step": 15660 }, { "epoch": 0.1671236384197668, "grad_norm": 0.847610594320969, "learning_rate": 4.83336894401738e-05, "loss": 0.606, "num_tokens": 93407221.0, "step": 15665 }, { "epoch": 0.16717698142596524, "grad_norm": 0.9823876634188786, "learning_rate": 4.833219013454744e-05, "loss": 0.649, "num_tokens": 93432689.0, "step": 15670 }, { "epoch": 0.1672303244321637, "grad_norm": 1.03246816367343, "learning_rate": 4.833069018066611e-05, "loss": 0.4894, "num_tokens": 93462171.0, "step": 15675 }, { "epoch": 0.16728366743836215, "grad_norm": 1.1509862034920704, "learning_rate": 4.832918957857649e-05, "loss": 0.5453, "num_tokens": 93492833.0, "step": 15680 }, { "epoch": 0.16733701044456062, "grad_norm": 2.4770097751739164, "learning_rate": 4.832768832832527e-05, "loss": 0.6056, "num_tokens": 93508087.0, "step": 15685 }, { "epoch": 0.16739035345075906, "grad_norm": 1.0985680439293288, "learning_rate": 4.8326186429959176e-05, "loss": 0.6601, "num_tokens": 93548783.0, "step": 15690 }, { "epoch": 0.16744369645695753, "grad_norm": 1.735645973213706, "learning_rate": 4.832468388352494e-05, "loss": 0.6476, "num_tokens": 93577674.0, "step": 15695 }, { "epoch": 0.16749703946315597, "grad_norm": 0.7744932907277364, "learning_rate": 4.8323180689069316e-05, "loss": 0.6415, "num_tokens": 93614795.0, "step": 15700 }, { "epoch": 0.16755038246935444, "grad_norm": 1.307617197433348, "learning_rate": 4.832167684663907e-05, "loss": 0.7049, "num_tokens": 93645019.0, "step": 15705 }, { "epoch": 0.1676037254755529, "grad_norm": 0.7672406121204668, "learning_rate": 4.8320172356281026e-05, "loss": 0.5057, "num_tokens": 93686733.0, "step": 15710 }, { "epoch": 0.16765706848175135, "grad_norm": 1.1092038607906767, "learning_rate": 4.831866721804197e-05, "loss": 0.6018, "num_tokens": 93709968.0, "step": 15715 }, { "epoch": 0.16771041148794982, "grad_norm": 0.9845192828169268, "learning_rate": 4.8317161431968763e-05, "loss": 0.5573, "num_tokens": 93740349.0, "step": 15720 }, { "epoch": 0.16776375449414827, "grad_norm": 1.757334300610142, "learning_rate": 4.831565499810825e-05, "loss": 0.5468, "num_tokens": 93760965.0, "step": 15725 }, { "epoch": 0.16781709750034673, "grad_norm": 1.3565461305628794, "learning_rate": 4.8314147916507315e-05, "loss": 0.6201, "num_tokens": 93785804.0, "step": 15730 }, { "epoch": 0.16787044050654518, "grad_norm": 1.5038885174681376, "learning_rate": 4.831264018721284e-05, "loss": 0.5731, "num_tokens": 93827791.0, "step": 15735 }, { "epoch": 0.16792378351274365, "grad_norm": 0.9020932963710563, "learning_rate": 4.8311131810271755e-05, "loss": 0.7781, "num_tokens": 93872055.0, "step": 15740 }, { "epoch": 0.1679771265189421, "grad_norm": 2.1323885907593647, "learning_rate": 4.8309622785730994e-05, "loss": 0.4703, "num_tokens": 93887458.0, "step": 15745 }, { "epoch": 0.16803046952514056, "grad_norm": 0.9297575395279852, "learning_rate": 4.830811311363753e-05, "loss": 0.5603, "num_tokens": 93917652.0, "step": 15750 }, { "epoch": 0.16808381253133903, "grad_norm": 1.4149984795641595, "learning_rate": 4.8306602794038305e-05, "loss": 0.6837, "num_tokens": 93950789.0, "step": 15755 }, { "epoch": 0.16813715553753747, "grad_norm": 1.7273035987173964, "learning_rate": 4.830509182698035e-05, "loss": 0.5611, "num_tokens": 93977963.0, "step": 15760 }, { "epoch": 0.16819049854373594, "grad_norm": 1.0083198874790604, "learning_rate": 4.8303580212510675e-05, "loss": 0.5644, "num_tokens": 94018367.0, "step": 15765 }, { "epoch": 0.16824384154993438, "grad_norm": 1.0958533601823541, "learning_rate": 4.8302067950676315e-05, "loss": 0.6852, "num_tokens": 94050512.0, "step": 15770 }, { "epoch": 0.16829718455613285, "grad_norm": 1.1342231610987967, "learning_rate": 4.8300555041524326e-05, "loss": 0.485, "num_tokens": 94073633.0, "step": 15775 }, { "epoch": 0.1683505275623313, "grad_norm": 1.059548602112702, "learning_rate": 4.829904148510179e-05, "loss": 0.6402, "num_tokens": 94107671.0, "step": 15780 }, { "epoch": 0.16840387056852976, "grad_norm": 4.89479839947933, "learning_rate": 4.8297527281455804e-05, "loss": 0.7078, "num_tokens": 94140166.0, "step": 15785 }, { "epoch": 0.1684572135747282, "grad_norm": 1.1512201871674625, "learning_rate": 4.8296012430633494e-05, "loss": 0.7419, "num_tokens": 94174559.0, "step": 15790 }, { "epoch": 0.16851055658092667, "grad_norm": 1.4390185103665245, "learning_rate": 4.829449693268199e-05, "loss": 0.7411, "num_tokens": 94216306.0, "step": 15795 }, { "epoch": 0.16856389958712514, "grad_norm": 1.3590645634116465, "learning_rate": 4.829298078764845e-05, "loss": 0.625, "num_tokens": 94234739.0, "step": 15800 }, { "epoch": 0.16861724259332359, "grad_norm": 1.1916693031109915, "learning_rate": 4.8291463995580065e-05, "loss": 0.6732, "num_tokens": 94261187.0, "step": 15805 }, { "epoch": 0.16867058559952205, "grad_norm": 1.060456438297939, "learning_rate": 4.8289946556524024e-05, "loss": 0.6781, "num_tokens": 94280720.0, "step": 15810 }, { "epoch": 0.1687239286057205, "grad_norm": 1.011958551160247, "learning_rate": 4.8288428470527554e-05, "loss": 0.7948, "num_tokens": 94317128.0, "step": 15815 }, { "epoch": 0.16877727161191897, "grad_norm": 2.2474512364260644, "learning_rate": 4.828690973763789e-05, "loss": 0.629, "num_tokens": 94347521.0, "step": 15820 }, { "epoch": 0.1688306146181174, "grad_norm": 0.8439864575019222, "learning_rate": 4.828539035790228e-05, "loss": 0.5708, "num_tokens": 94374260.0, "step": 15825 }, { "epoch": 0.16888395762431588, "grad_norm": 0.7885352117965292, "learning_rate": 4.828387033136803e-05, "loss": 0.6433, "num_tokens": 94411341.0, "step": 15830 }, { "epoch": 0.16893730063051432, "grad_norm": 1.9781989828773772, "learning_rate": 4.8282349658082425e-05, "loss": 0.816, "num_tokens": 94447547.0, "step": 15835 }, { "epoch": 0.1689906436367128, "grad_norm": 2.304298872229271, "learning_rate": 4.8280828338092784e-05, "loss": 0.7479, "num_tokens": 94474291.0, "step": 15840 }, { "epoch": 0.16904398664291126, "grad_norm": 1.0498532375108958, "learning_rate": 4.827930637144645e-05, "loss": 0.6743, "num_tokens": 94517387.0, "step": 15845 }, { "epoch": 0.1690973296491097, "grad_norm": 1.0738227221487069, "learning_rate": 4.827778375819078e-05, "loss": 0.6391, "num_tokens": 94550383.0, "step": 15850 }, { "epoch": 0.16915067265530817, "grad_norm": 1.7305501418267184, "learning_rate": 4.827626049837317e-05, "loss": 0.5956, "num_tokens": 94573257.0, "step": 15855 }, { "epoch": 0.1692040156615066, "grad_norm": 0.9425959101152978, "learning_rate": 4.8274736592040996e-05, "loss": 0.6488, "num_tokens": 94595108.0, "step": 15860 }, { "epoch": 0.16925735866770508, "grad_norm": 1.4432659389816775, "learning_rate": 4.82732120392417e-05, "loss": 0.466, "num_tokens": 94612606.0, "step": 15865 }, { "epoch": 0.16931070167390352, "grad_norm": 1.3683061539984085, "learning_rate": 4.827168684002271e-05, "loss": 0.5221, "num_tokens": 94636807.0, "step": 15870 }, { "epoch": 0.169364044680102, "grad_norm": 0.9253446448799738, "learning_rate": 4.8270160994431494e-05, "loss": 0.5194, "num_tokens": 94664362.0, "step": 15875 }, { "epoch": 0.16941738768630044, "grad_norm": 0.7947290591413024, "learning_rate": 4.826863450251554e-05, "loss": 0.4763, "num_tokens": 94689542.0, "step": 15880 }, { "epoch": 0.1694707306924989, "grad_norm": 1.2692416771411132, "learning_rate": 4.8267107364322325e-05, "loss": 0.709, "num_tokens": 94717599.0, "step": 15885 }, { "epoch": 0.16952407369869738, "grad_norm": 1.210848074320517, "learning_rate": 4.8265579579899386e-05, "loss": 0.6541, "num_tokens": 94761610.0, "step": 15890 }, { "epoch": 0.16957741670489582, "grad_norm": 1.1931940451812226, "learning_rate": 4.826405114929428e-05, "loss": 0.506, "num_tokens": 94788716.0, "step": 15895 }, { "epoch": 0.1696307597110943, "grad_norm": 1.0201058760700779, "learning_rate": 4.826252207255454e-05, "loss": 0.568, "num_tokens": 94826247.0, "step": 15900 }, { "epoch": 0.16968410271729273, "grad_norm": 1.0864011728751042, "learning_rate": 4.826099234972776e-05, "loss": 0.5769, "num_tokens": 94853503.0, "step": 15905 }, { "epoch": 0.1697374457234912, "grad_norm": 1.153021764402055, "learning_rate": 4.8259461980861545e-05, "loss": 0.7972, "num_tokens": 94886360.0, "step": 15910 }, { "epoch": 0.16979078872968964, "grad_norm": 1.245610431743166, "learning_rate": 4.8257930966003515e-05, "loss": 0.6813, "num_tokens": 94927858.0, "step": 15915 }, { "epoch": 0.1698441317358881, "grad_norm": 1.34594707219502, "learning_rate": 4.825639930520131e-05, "loss": 0.7318, "num_tokens": 94951484.0, "step": 15920 }, { "epoch": 0.16989747474208655, "grad_norm": 0.8597090079506962, "learning_rate": 4.8254866998502596e-05, "loss": 0.491, "num_tokens": 94980597.0, "step": 15925 }, { "epoch": 0.16995081774828502, "grad_norm": 0.8229787441647285, "learning_rate": 4.8253334045955055e-05, "loss": 0.4644, "num_tokens": 95005383.0, "step": 15930 }, { "epoch": 0.1700041607544835, "grad_norm": 0.780991018793693, "learning_rate": 4.825180044760638e-05, "loss": 0.6964, "num_tokens": 95047725.0, "step": 15935 }, { "epoch": 0.17005750376068193, "grad_norm": 1.9413475161078921, "learning_rate": 4.825026620350431e-05, "loss": 0.6576, "num_tokens": 95059355.0, "step": 15940 }, { "epoch": 0.1701108467668804, "grad_norm": 2.0131053014408486, "learning_rate": 4.824873131369657e-05, "loss": 0.7511, "num_tokens": 95100169.0, "step": 15945 }, { "epoch": 0.17016418977307884, "grad_norm": 1.1620158533349119, "learning_rate": 4.8247195778230935e-05, "loss": 0.5781, "num_tokens": 95122719.0, "step": 15950 }, { "epoch": 0.17021753277927731, "grad_norm": 1.191180649058328, "learning_rate": 4.824565959715518e-05, "loss": 0.508, "num_tokens": 95155567.0, "step": 15955 }, { "epoch": 0.17027087578547576, "grad_norm": 1.1670871196166968, "learning_rate": 4.8244122770517115e-05, "loss": 0.5121, "num_tokens": 95175256.0, "step": 15960 }, { "epoch": 0.17032421879167423, "grad_norm": 1.182049732945624, "learning_rate": 4.8242585298364554e-05, "loss": 0.5987, "num_tokens": 95201915.0, "step": 15965 }, { "epoch": 0.17037756179787267, "grad_norm": 1.2426212894003892, "learning_rate": 4.824104718074535e-05, "loss": 0.72, "num_tokens": 95229702.0, "step": 15970 }, { "epoch": 0.17043090480407114, "grad_norm": 1.048827363229129, "learning_rate": 4.823950841770735e-05, "loss": 0.7271, "num_tokens": 95257609.0, "step": 15975 }, { "epoch": 0.1704842478102696, "grad_norm": 0.9311896786083873, "learning_rate": 4.823796900929846e-05, "loss": 0.5477, "num_tokens": 95281221.0, "step": 15980 }, { "epoch": 0.17053759081646805, "grad_norm": 1.215817482409581, "learning_rate": 4.823642895556657e-05, "loss": 0.6494, "num_tokens": 95319364.0, "step": 15985 }, { "epoch": 0.17059093382266652, "grad_norm": 1.052946588414696, "learning_rate": 4.82348882565596e-05, "loss": 0.7413, "num_tokens": 95356674.0, "step": 15990 }, { "epoch": 0.17064427682886496, "grad_norm": 1.1615188866949844, "learning_rate": 4.82333469123255e-05, "loss": 0.6813, "num_tokens": 95394468.0, "step": 15995 }, { "epoch": 0.17069761983506343, "grad_norm": 1.9337247177246577, "learning_rate": 4.823180492291224e-05, "loss": 0.8502, "num_tokens": 95438170.0, "step": 16000 }, { "epoch": 0.17075096284126187, "grad_norm": 1.3857393400028564, "learning_rate": 4.823026228836778e-05, "loss": 0.6299, "num_tokens": 95463515.0, "step": 16005 }, { "epoch": 0.17080430584746034, "grad_norm": 1.1134941466577664, "learning_rate": 4.822871900874015e-05, "loss": 0.5537, "num_tokens": 95495870.0, "step": 16010 }, { "epoch": 0.17085764885365878, "grad_norm": 1.425082276302906, "learning_rate": 4.822717508407736e-05, "loss": 0.5428, "num_tokens": 95520428.0, "step": 16015 }, { "epoch": 0.17091099185985725, "grad_norm": 1.2253499283399085, "learning_rate": 4.822563051442745e-05, "loss": 0.6106, "num_tokens": 95545147.0, "step": 16020 }, { "epoch": 0.17096433486605572, "grad_norm": 1.0882135478125787, "learning_rate": 4.82240852998385e-05, "loss": 0.549, "num_tokens": 95567512.0, "step": 16025 }, { "epoch": 0.17101767787225416, "grad_norm": 0.9351698623934352, "learning_rate": 4.822253944035858e-05, "loss": 0.5776, "num_tokens": 95594631.0, "step": 16030 }, { "epoch": 0.17107102087845263, "grad_norm": 0.8734499497179138, "learning_rate": 4.82209929360358e-05, "loss": 0.6605, "num_tokens": 95617219.0, "step": 16035 }, { "epoch": 0.17112436388465108, "grad_norm": 1.5344374078076357, "learning_rate": 4.821944578691828e-05, "loss": 0.5821, "num_tokens": 95636674.0, "step": 16040 }, { "epoch": 0.17117770689084955, "grad_norm": 0.8744552542323019, "learning_rate": 4.821789799305416e-05, "loss": 0.4901, "num_tokens": 95659652.0, "step": 16045 }, { "epoch": 0.171231049897048, "grad_norm": 0.8991249055385606, "learning_rate": 4.8216349554491615e-05, "loss": 0.6179, "num_tokens": 95690913.0, "step": 16050 }, { "epoch": 0.17128439290324646, "grad_norm": 1.2687514125583277, "learning_rate": 4.821480047127882e-05, "loss": 0.6833, "num_tokens": 95727183.0, "step": 16055 }, { "epoch": 0.1713377359094449, "grad_norm": 1.192706551684324, "learning_rate": 4.8213250743464e-05, "loss": 0.7561, "num_tokens": 95766105.0, "step": 16060 }, { "epoch": 0.17139107891564337, "grad_norm": 1.0454858863311227, "learning_rate": 4.8211700371095344e-05, "loss": 0.6843, "num_tokens": 95785340.0, "step": 16065 }, { "epoch": 0.17144442192184184, "grad_norm": 1.0174766043067525, "learning_rate": 4.821014935422113e-05, "loss": 0.586, "num_tokens": 95803773.0, "step": 16070 }, { "epoch": 0.17149776492804028, "grad_norm": 1.4316711050827995, "learning_rate": 4.8208597692889596e-05, "loss": 0.6939, "num_tokens": 95831870.0, "step": 16075 }, { "epoch": 0.17155110793423875, "grad_norm": 1.7710875621774076, "learning_rate": 4.8207045387149044e-05, "loss": 0.5842, "num_tokens": 95859458.0, "step": 16080 }, { "epoch": 0.1716044509404372, "grad_norm": 1.331106958100977, "learning_rate": 4.8205492437047773e-05, "loss": 0.5837, "num_tokens": 95888026.0, "step": 16085 }, { "epoch": 0.17165779394663566, "grad_norm": 1.493211701974174, "learning_rate": 4.820393884263411e-05, "loss": 0.5969, "num_tokens": 95906489.0, "step": 16090 }, { "epoch": 0.1717111369528341, "grad_norm": 0.7292851229329463, "learning_rate": 4.8202384603956386e-05, "loss": 0.6381, "num_tokens": 95942198.0, "step": 16095 }, { "epoch": 0.17176447995903257, "grad_norm": 1.2191796154102124, "learning_rate": 4.820082972106299e-05, "loss": 0.5267, "num_tokens": 95955693.0, "step": 16100 }, { "epoch": 0.17181782296523102, "grad_norm": 0.8572752049715792, "learning_rate": 4.8199274194002285e-05, "loss": 0.5935, "num_tokens": 95997524.0, "step": 16105 }, { "epoch": 0.17187116597142948, "grad_norm": 1.130973784000803, "learning_rate": 4.819771802282269e-05, "loss": 0.6553, "num_tokens": 96015610.0, "step": 16110 }, { "epoch": 0.17192450897762795, "grad_norm": 2.200592001765602, "learning_rate": 4.8196161207572625e-05, "loss": 0.5977, "num_tokens": 96037858.0, "step": 16115 }, { "epoch": 0.1719778519838264, "grad_norm": 1.6541094079075906, "learning_rate": 4.819460374830054e-05, "loss": 0.6131, "num_tokens": 96064314.0, "step": 16120 }, { "epoch": 0.17203119499002487, "grad_norm": 0.8622634027796745, "learning_rate": 4.819304564505488e-05, "loss": 0.5861, "num_tokens": 96104205.0, "step": 16125 }, { "epoch": 0.1720845379962233, "grad_norm": 1.3046089774441196, "learning_rate": 4.819148689788415e-05, "loss": 0.6247, "num_tokens": 96129109.0, "step": 16130 }, { "epoch": 0.17213788100242178, "grad_norm": 1.3054825482290666, "learning_rate": 4.818992750683685e-05, "loss": 0.6548, "num_tokens": 96154285.0, "step": 16135 }, { "epoch": 0.17219122400862022, "grad_norm": 0.9372680162500437, "learning_rate": 4.8188367471961504e-05, "loss": 0.6719, "num_tokens": 96194696.0, "step": 16140 }, { "epoch": 0.1722445670148187, "grad_norm": 1.0773894584832213, "learning_rate": 4.818680679330666e-05, "loss": 0.6592, "num_tokens": 96227565.0, "step": 16145 }, { "epoch": 0.17229791002101713, "grad_norm": 1.702056118299086, "learning_rate": 4.818524547092088e-05, "loss": 0.7412, "num_tokens": 96253306.0, "step": 16150 }, { "epoch": 0.1723512530272156, "grad_norm": 2.6534939718524533, "learning_rate": 4.818368350485275e-05, "loss": 0.7224, "num_tokens": 96277803.0, "step": 16155 }, { "epoch": 0.17240459603341407, "grad_norm": 1.3420087659686601, "learning_rate": 4.818212089515087e-05, "loss": 0.6442, "num_tokens": 96317405.0, "step": 16160 }, { "epoch": 0.1724579390396125, "grad_norm": 1.2300862235978336, "learning_rate": 4.8180557641863874e-05, "loss": 0.7525, "num_tokens": 96354308.0, "step": 16165 }, { "epoch": 0.17251128204581098, "grad_norm": 1.0923592298887426, "learning_rate": 4.8178993745040404e-05, "loss": 0.5719, "num_tokens": 96388372.0, "step": 16170 }, { "epoch": 0.17256462505200942, "grad_norm": 2.2395230481080293, "learning_rate": 4.817742920472913e-05, "loss": 0.646, "num_tokens": 96411022.0, "step": 16175 }, { "epoch": 0.1726179680582079, "grad_norm": 1.1474425569156688, "learning_rate": 4.8175864020978725e-05, "loss": 0.6396, "num_tokens": 96438431.0, "step": 16180 }, { "epoch": 0.17267131106440634, "grad_norm": 0.9562124907417546, "learning_rate": 4.817429819383789e-05, "loss": 0.5873, "num_tokens": 96465503.0, "step": 16185 }, { "epoch": 0.1727246540706048, "grad_norm": 0.9295501640447239, "learning_rate": 4.817273172335538e-05, "loss": 0.6212, "num_tokens": 96494875.0, "step": 16190 }, { "epoch": 0.17277799707680325, "grad_norm": 1.5117580615513464, "learning_rate": 4.817116460957991e-05, "loss": 0.575, "num_tokens": 96524700.0, "step": 16195 }, { "epoch": 0.17283134008300172, "grad_norm": 1.133444913650952, "learning_rate": 4.816959685256026e-05, "loss": 0.5741, "num_tokens": 96551561.0, "step": 16200 }, { "epoch": 0.1728846830892002, "grad_norm": 1.4619320566532341, "learning_rate": 4.816802845234522e-05, "loss": 0.5975, "num_tokens": 96569422.0, "step": 16205 }, { "epoch": 0.17293802609539863, "grad_norm": 1.345658991817966, "learning_rate": 4.8166459408983585e-05, "loss": 0.6251, "num_tokens": 96603714.0, "step": 16210 }, { "epoch": 0.1729913691015971, "grad_norm": 1.4531826620717512, "learning_rate": 4.816488972252417e-05, "loss": 0.6609, "num_tokens": 96634343.0, "step": 16215 }, { "epoch": 0.17304471210779554, "grad_norm": 1.4081664512419354, "learning_rate": 4.8163319393015846e-05, "loss": 0.6915, "num_tokens": 96664961.0, "step": 16220 }, { "epoch": 0.173098055113994, "grad_norm": 0.8573854835347972, "learning_rate": 4.816174842050747e-05, "loss": 0.7107, "num_tokens": 96696189.0, "step": 16225 }, { "epoch": 0.17315139812019245, "grad_norm": 1.5310245621713703, "learning_rate": 4.816017680504791e-05, "loss": 0.5339, "num_tokens": 96715194.0, "step": 16230 }, { "epoch": 0.17320474112639092, "grad_norm": 0.8454093243039973, "learning_rate": 4.81586045466861e-05, "loss": 0.5541, "num_tokens": 96749520.0, "step": 16235 }, { "epoch": 0.17325808413258936, "grad_norm": 1.5321135480333432, "learning_rate": 4.815703164547094e-05, "loss": 0.6133, "num_tokens": 96772820.0, "step": 16240 }, { "epoch": 0.17331142713878783, "grad_norm": 1.0809933170503991, "learning_rate": 4.815545810145139e-05, "loss": 0.7925, "num_tokens": 96804328.0, "step": 16245 }, { "epoch": 0.1733647701449863, "grad_norm": 0.8094349656187582, "learning_rate": 4.815388391467641e-05, "loss": 0.7498, "num_tokens": 96849082.0, "step": 16250 }, { "epoch": 0.17341811315118474, "grad_norm": 1.755053153839766, "learning_rate": 4.815230908519499e-05, "loss": 0.9085, "num_tokens": 96876489.0, "step": 16255 }, { "epoch": 0.1734714561573832, "grad_norm": 0.9414352740510946, "learning_rate": 4.8150733613056125e-05, "loss": 0.5588, "num_tokens": 96916348.0, "step": 16260 }, { "epoch": 0.17352479916358166, "grad_norm": 1.0443791408768037, "learning_rate": 4.814915749830886e-05, "loss": 0.6456, "num_tokens": 96961792.0, "step": 16265 }, { "epoch": 0.17357814216978013, "grad_norm": 1.3083732945175306, "learning_rate": 4.814758074100222e-05, "loss": 0.7959, "num_tokens": 97001734.0, "step": 16270 }, { "epoch": 0.17363148517597857, "grad_norm": 1.6553386819008586, "learning_rate": 4.8146003341185275e-05, "loss": 0.5197, "num_tokens": 97019802.0, "step": 16275 }, { "epoch": 0.17368482818217704, "grad_norm": 2.2874741593554977, "learning_rate": 4.814442529890712e-05, "loss": 0.5574, "num_tokens": 97039963.0, "step": 16280 }, { "epoch": 0.17373817118837548, "grad_norm": 1.1394263796548503, "learning_rate": 4.814284661421685e-05, "loss": 0.5535, "num_tokens": 97070725.0, "step": 16285 }, { "epoch": 0.17379151419457395, "grad_norm": 1.0050015271214712, "learning_rate": 4.81412672871636e-05, "loss": 0.6069, "num_tokens": 97115397.0, "step": 16290 }, { "epoch": 0.17384485720077242, "grad_norm": 1.5183428169703723, "learning_rate": 4.81396873177965e-05, "loss": 0.5497, "num_tokens": 97143031.0, "step": 16295 }, { "epoch": 0.17389820020697086, "grad_norm": 1.0241314676043054, "learning_rate": 4.813810670616474e-05, "loss": 0.6086, "num_tokens": 97175418.0, "step": 16300 }, { "epoch": 0.17395154321316933, "grad_norm": 1.2028204157006313, "learning_rate": 4.813652545231749e-05, "loss": 0.5623, "num_tokens": 97204376.0, "step": 16305 }, { "epoch": 0.17400488621936777, "grad_norm": 0.9458804910525934, "learning_rate": 4.8134943556303955e-05, "loss": 0.5741, "num_tokens": 97238342.0, "step": 16310 }, { "epoch": 0.17405822922556624, "grad_norm": 1.1308408653943063, "learning_rate": 4.813336101817336e-05, "loss": 0.5731, "num_tokens": 97270002.0, "step": 16315 }, { "epoch": 0.17411157223176468, "grad_norm": 0.9257105393836738, "learning_rate": 4.813177783797495e-05, "loss": 0.5129, "num_tokens": 97303144.0, "step": 16320 }, { "epoch": 0.17416491523796315, "grad_norm": 1.0875856630324057, "learning_rate": 4.813019401575799e-05, "loss": 0.6382, "num_tokens": 97354338.0, "step": 16325 }, { "epoch": 0.1742182582441616, "grad_norm": 1.506870921990663, "learning_rate": 4.812860955157177e-05, "loss": 0.6641, "num_tokens": 97387144.0, "step": 16330 }, { "epoch": 0.17427160125036006, "grad_norm": 0.788848585671122, "learning_rate": 4.81270244454656e-05, "loss": 0.5944, "num_tokens": 97419306.0, "step": 16335 }, { "epoch": 0.17432494425655853, "grad_norm": 1.8396802763783662, "learning_rate": 4.812543869748879e-05, "loss": 0.6125, "num_tokens": 97448428.0, "step": 16340 }, { "epoch": 0.17437828726275698, "grad_norm": 1.5701734184372313, "learning_rate": 4.81238523076907e-05, "loss": 0.5979, "num_tokens": 97481415.0, "step": 16345 }, { "epoch": 0.17443163026895545, "grad_norm": 1.2949195466875703, "learning_rate": 4.812226527612068e-05, "loss": 0.6494, "num_tokens": 97515027.0, "step": 16350 }, { "epoch": 0.1744849732751539, "grad_norm": 0.7757064817620366, "learning_rate": 4.8120677602828136e-05, "loss": 0.6764, "num_tokens": 97561266.0, "step": 16355 }, { "epoch": 0.17453831628135236, "grad_norm": 0.9541108357568795, "learning_rate": 4.8119089287862454e-05, "loss": 0.4415, "num_tokens": 97592697.0, "step": 16360 }, { "epoch": 0.1745916592875508, "grad_norm": 1.053624374456316, "learning_rate": 4.811750033127306e-05, "loss": 0.6421, "num_tokens": 97614054.0, "step": 16365 }, { "epoch": 0.17464500229374927, "grad_norm": 2.7445732381397265, "learning_rate": 4.811591073310941e-05, "loss": 0.6235, "num_tokens": 97647016.0, "step": 16370 }, { "epoch": 0.1746983452999477, "grad_norm": 1.4996547870301504, "learning_rate": 4.8114320493420974e-05, "loss": 0.688, "num_tokens": 97686237.0, "step": 16375 }, { "epoch": 0.17475168830614618, "grad_norm": 1.3748500218104953, "learning_rate": 4.811272961225722e-05, "loss": 0.7414, "num_tokens": 97723357.0, "step": 16380 }, { "epoch": 0.17480503131234465, "grad_norm": 0.7779751912590918, "learning_rate": 4.811113808966766e-05, "loss": 0.6944, "num_tokens": 97763414.0, "step": 16385 }, { "epoch": 0.1748583743185431, "grad_norm": 6.1496860940350375, "learning_rate": 4.8109545925701824e-05, "loss": 1.0427, "num_tokens": 97789316.0, "step": 16390 }, { "epoch": 0.17491171732474156, "grad_norm": 1.202547772413332, "learning_rate": 4.8107953120409236e-05, "loss": 0.541, "num_tokens": 97805017.0, "step": 16395 }, { "epoch": 0.17496506033094, "grad_norm": 1.0320649161971225, "learning_rate": 4.810635967383949e-05, "loss": 0.6656, "num_tokens": 97838031.0, "step": 16400 }, { "epoch": 0.17501840333713847, "grad_norm": 1.3827162082325208, "learning_rate": 4.810476558604216e-05, "loss": 0.6598, "num_tokens": 97869109.0, "step": 16405 }, { "epoch": 0.17507174634333691, "grad_norm": 2.2087418527066385, "learning_rate": 4.810317085706684e-05, "loss": 0.6333, "num_tokens": 97909340.0, "step": 16410 }, { "epoch": 0.17512508934953538, "grad_norm": 0.8739865315947866, "learning_rate": 4.8101575486963163e-05, "loss": 0.8121, "num_tokens": 97954051.0, "step": 16415 }, { "epoch": 0.17517843235573383, "grad_norm": 0.7644719527171762, "learning_rate": 4.8099979475780784e-05, "loss": 0.5857, "num_tokens": 97996065.0, "step": 16420 }, { "epoch": 0.1752317753619323, "grad_norm": 1.6970969291542508, "learning_rate": 4.8098382823569346e-05, "loss": 0.5998, "num_tokens": 98036470.0, "step": 16425 }, { "epoch": 0.17528511836813077, "grad_norm": 0.9969518256888777, "learning_rate": 4.809678553037855e-05, "loss": 0.6306, "num_tokens": 98074333.0, "step": 16430 }, { "epoch": 0.1753384613743292, "grad_norm": 0.7827720281720706, "learning_rate": 4.80951875962581e-05, "loss": 0.62, "num_tokens": 98104415.0, "step": 16435 }, { "epoch": 0.17539180438052768, "grad_norm": 1.107460290091417, "learning_rate": 4.809358902125771e-05, "loss": 0.4982, "num_tokens": 98128110.0, "step": 16440 }, { "epoch": 0.17544514738672612, "grad_norm": 3.3069563158027226, "learning_rate": 4.809198980542713e-05, "loss": 0.8663, "num_tokens": 98153695.0, "step": 16445 }, { "epoch": 0.1754984903929246, "grad_norm": 3.703141950777478, "learning_rate": 4.8090389948816125e-05, "loss": 0.7651, "num_tokens": 98176322.0, "step": 16450 }, { "epoch": 0.17555183339912303, "grad_norm": 1.4033717038292925, "learning_rate": 4.808878945147448e-05, "loss": 0.6684, "num_tokens": 98205887.0, "step": 16455 }, { "epoch": 0.1756051764053215, "grad_norm": 1.2289520373747584, "learning_rate": 4.8087188313452e-05, "loss": 0.5811, "num_tokens": 98224671.0, "step": 16460 }, { "epoch": 0.17565851941151994, "grad_norm": 0.9960993535572686, "learning_rate": 4.80855865347985e-05, "loss": 0.6112, "num_tokens": 98258507.0, "step": 16465 }, { "epoch": 0.1757118624177184, "grad_norm": 0.8578321941474814, "learning_rate": 4.8083984115563834e-05, "loss": 0.5983, "num_tokens": 98293835.0, "step": 16470 }, { "epoch": 0.17576520542391688, "grad_norm": 1.3021353962085593, "learning_rate": 4.808238105579786e-05, "loss": 0.7752, "num_tokens": 98316940.0, "step": 16475 }, { "epoch": 0.17581854843011532, "grad_norm": 1.1378600851073597, "learning_rate": 4.8080777355550475e-05, "loss": 0.5015, "num_tokens": 98358262.0, "step": 16480 }, { "epoch": 0.1758718914363138, "grad_norm": 1.2862217366490973, "learning_rate": 4.8079173014871566e-05, "loss": 0.641, "num_tokens": 98379824.0, "step": 16485 }, { "epoch": 0.17592523444251223, "grad_norm": 1.1160964202646673, "learning_rate": 4.807756803381106e-05, "loss": 0.5303, "num_tokens": 98406227.0, "step": 16490 }, { "epoch": 0.1759785774487107, "grad_norm": 1.0666522676680668, "learning_rate": 4.8075962412418913e-05, "loss": 0.6211, "num_tokens": 98438783.0, "step": 16495 }, { "epoch": 0.17603192045490915, "grad_norm": 1.71570320125467, "learning_rate": 4.807435615074507e-05, "loss": 0.6697, "num_tokens": 98454992.0, "step": 16500 }, { "epoch": 0.17608526346110762, "grad_norm": 1.073036089792625, "learning_rate": 4.8072749248839535e-05, "loss": 0.4663, "num_tokens": 98484012.0, "step": 16505 }, { "epoch": 0.17613860646730606, "grad_norm": 1.606129894355171, "learning_rate": 4.80711417067523e-05, "loss": 0.68, "num_tokens": 98522237.0, "step": 16510 }, { "epoch": 0.17619194947350453, "grad_norm": 0.9271005210021497, "learning_rate": 4.806953352453338e-05, "loss": 0.5668, "num_tokens": 98551821.0, "step": 16515 }, { "epoch": 0.176245292479703, "grad_norm": 1.0227177428061995, "learning_rate": 4.8067924702232834e-05, "loss": 0.6036, "num_tokens": 98580120.0, "step": 16520 }, { "epoch": 0.17629863548590144, "grad_norm": 0.8421886389116843, "learning_rate": 4.8066315239900715e-05, "loss": 0.6193, "num_tokens": 98603394.0, "step": 16525 }, { "epoch": 0.1763519784920999, "grad_norm": 0.7265313423537072, "learning_rate": 4.806470513758712e-05, "loss": 0.6055, "num_tokens": 98648335.0, "step": 16530 }, { "epoch": 0.17640532149829835, "grad_norm": 1.4974503243626593, "learning_rate": 4.8063094395342126e-05, "loss": 0.428, "num_tokens": 98672883.0, "step": 16535 }, { "epoch": 0.17645866450449682, "grad_norm": 0.8719726479113783, "learning_rate": 4.806148301321588e-05, "loss": 0.6303, "num_tokens": 98708750.0, "step": 16540 }, { "epoch": 0.17651200751069526, "grad_norm": 1.3130902693383129, "learning_rate": 4.805987099125852e-05, "loss": 0.5603, "num_tokens": 98741651.0, "step": 16545 }, { "epoch": 0.17656535051689373, "grad_norm": 1.09910630703973, "learning_rate": 4.805825832952021e-05, "loss": 0.749, "num_tokens": 98780303.0, "step": 16550 }, { "epoch": 0.17661869352309217, "grad_norm": 1.4178447605288662, "learning_rate": 4.805664502805112e-05, "loss": 0.5961, "num_tokens": 98806143.0, "step": 16555 }, { "epoch": 0.17667203652929064, "grad_norm": 2.7546250269429864, "learning_rate": 4.805503108690147e-05, "loss": 0.6547, "num_tokens": 98828485.0, "step": 16560 }, { "epoch": 0.1767253795354891, "grad_norm": 1.0618201337651925, "learning_rate": 4.805341650612147e-05, "loss": 0.5477, "num_tokens": 98855321.0, "step": 16565 }, { "epoch": 0.17677872254168756, "grad_norm": 0.8369785649620598, "learning_rate": 4.805180128576136e-05, "loss": 0.6692, "num_tokens": 98888316.0, "step": 16570 }, { "epoch": 0.17683206554788602, "grad_norm": 0.6629451440715884, "learning_rate": 4.805018542587142e-05, "loss": 0.4808, "num_tokens": 98941293.0, "step": 16575 }, { "epoch": 0.17688540855408447, "grad_norm": 1.6982980366577485, "learning_rate": 4.8048568926501916e-05, "loss": 0.6598, "num_tokens": 98975105.0, "step": 16580 }, { "epoch": 0.17693875156028294, "grad_norm": 1.0459133862404435, "learning_rate": 4.804695178770315e-05, "loss": 0.7217, "num_tokens": 99025388.0, "step": 16585 }, { "epoch": 0.17699209456648138, "grad_norm": 0.9673066760602294, "learning_rate": 4.804533400952545e-05, "loss": 0.5933, "num_tokens": 99061578.0, "step": 16590 }, { "epoch": 0.17704543757267985, "grad_norm": 1.869799113372587, "learning_rate": 4.804371559201916e-05, "loss": 0.6543, "num_tokens": 99109855.0, "step": 16595 }, { "epoch": 0.1770987805788783, "grad_norm": 0.9541618125872168, "learning_rate": 4.804209653523464e-05, "loss": 0.6, "num_tokens": 99137441.0, "step": 16600 }, { "epoch": 0.17715212358507676, "grad_norm": 0.8846449204455543, "learning_rate": 4.804047683922226e-05, "loss": 0.5225, "num_tokens": 99173507.0, "step": 16605 }, { "epoch": 0.17720546659127523, "grad_norm": 1.0518432301271259, "learning_rate": 4.803885650403245e-05, "loss": 0.4842, "num_tokens": 99199512.0, "step": 16610 }, { "epoch": 0.17725880959747367, "grad_norm": 1.369765227210716, "learning_rate": 4.8037235529715605e-05, "loss": 0.673, "num_tokens": 99216102.0, "step": 16615 }, { "epoch": 0.17731215260367214, "grad_norm": 0.7863522458429769, "learning_rate": 4.803561391632217e-05, "loss": 0.5162, "num_tokens": 99254315.0, "step": 16620 }, { "epoch": 0.17736549560987058, "grad_norm": 2.6317883340244586, "learning_rate": 4.803399166390262e-05, "loss": 0.8342, "num_tokens": 99301057.0, "step": 16625 }, { "epoch": 0.17741883861606905, "grad_norm": 1.3495047891104504, "learning_rate": 4.803236877250742e-05, "loss": 0.6117, "num_tokens": 99325961.0, "step": 16630 }, { "epoch": 0.1774721816222675, "grad_norm": 1.4821824995153425, "learning_rate": 4.803074524218707e-05, "loss": 0.7064, "num_tokens": 99353153.0, "step": 16635 }, { "epoch": 0.17752552462846596, "grad_norm": 1.2026740907187445, "learning_rate": 4.8029121072992124e-05, "loss": 0.5034, "num_tokens": 99383692.0, "step": 16640 }, { "epoch": 0.1775788676346644, "grad_norm": 0.9391585343369742, "learning_rate": 4.8027496264973085e-05, "loss": 0.8952, "num_tokens": 99425893.0, "step": 16645 }, { "epoch": 0.17763221064086288, "grad_norm": 0.8239838656580296, "learning_rate": 4.802587081818053e-05, "loss": 0.6408, "num_tokens": 99453950.0, "step": 16650 }, { "epoch": 0.17768555364706135, "grad_norm": 1.29344939868084, "learning_rate": 4.802424473266503e-05, "loss": 0.5904, "num_tokens": 99480340.0, "step": 16655 }, { "epoch": 0.1777388966532598, "grad_norm": 5.39227267050455, "learning_rate": 4.802261800847719e-05, "loss": 0.7359, "num_tokens": 99515875.0, "step": 16660 }, { "epoch": 0.17779223965945826, "grad_norm": 1.776366300792311, "learning_rate": 4.802099064566764e-05, "loss": 0.6378, "num_tokens": 99546312.0, "step": 16665 }, { "epoch": 0.1778455826656567, "grad_norm": 2.188546345092876, "learning_rate": 4.801936264428701e-05, "loss": 0.7128, "num_tokens": 99576824.0, "step": 16670 }, { "epoch": 0.17789892567185517, "grad_norm": 0.7947108498989578, "learning_rate": 4.801773400438596e-05, "loss": 0.6476, "num_tokens": 99611219.0, "step": 16675 }, { "epoch": 0.1779522686780536, "grad_norm": 0.8336464989032312, "learning_rate": 4.8016104726015175e-05, "loss": 0.5452, "num_tokens": 99636207.0, "step": 16680 }, { "epoch": 0.17800561168425208, "grad_norm": 1.4197732260023757, "learning_rate": 4.8014474809225355e-05, "loss": 0.6338, "num_tokens": 99657066.0, "step": 16685 }, { "epoch": 0.17805895469045052, "grad_norm": 1.3380716952646747, "learning_rate": 4.801284425406721e-05, "loss": 0.7893, "num_tokens": 99697382.0, "step": 16690 }, { "epoch": 0.178112297696649, "grad_norm": 0.966871275795061, "learning_rate": 4.801121306059149e-05, "loss": 0.5336, "num_tokens": 99726426.0, "step": 16695 }, { "epoch": 0.17816564070284746, "grad_norm": 1.2027028745986112, "learning_rate": 4.800958122884896e-05, "loss": 0.4849, "num_tokens": 99754128.0, "step": 16700 }, { "epoch": 0.1782189837090459, "grad_norm": 1.0700849761459463, "learning_rate": 4.8007948758890376e-05, "loss": 0.6302, "num_tokens": 99783808.0, "step": 16705 }, { "epoch": 0.17827232671524437, "grad_norm": 1.0095472740528293, "learning_rate": 4.800631565076655e-05, "loss": 0.6868, "num_tokens": 99810333.0, "step": 16710 }, { "epoch": 0.17832566972144281, "grad_norm": 0.89999424630975, "learning_rate": 4.800468190452832e-05, "loss": 0.5364, "num_tokens": 99833023.0, "step": 16715 }, { "epoch": 0.17837901272764128, "grad_norm": 1.312878224094002, "learning_rate": 4.800304752022649e-05, "loss": 0.5948, "num_tokens": 99872553.0, "step": 16720 }, { "epoch": 0.17843235573383973, "grad_norm": 1.1225549739804608, "learning_rate": 4.8001412497911944e-05, "loss": 0.6357, "num_tokens": 99904490.0, "step": 16725 }, { "epoch": 0.1784856987400382, "grad_norm": 1.513160212768941, "learning_rate": 4.799977683763555e-05, "loss": 0.763, "num_tokens": 99936967.0, "step": 16730 }, { "epoch": 0.17853904174623664, "grad_norm": 0.9086899996969601, "learning_rate": 4.7998140539448206e-05, "loss": 0.5371, "num_tokens": 99976404.0, "step": 16735 }, { "epoch": 0.1785923847524351, "grad_norm": 0.9681547788935284, "learning_rate": 4.7996503603400835e-05, "loss": 0.6936, "num_tokens": 100022131.0, "step": 16740 }, { "epoch": 0.17864572775863358, "grad_norm": 0.8961593139129208, "learning_rate": 4.799486602954437e-05, "loss": 0.6116, "num_tokens": 100050124.0, "step": 16745 }, { "epoch": 0.17869907076483202, "grad_norm": 0.9425384782633035, "learning_rate": 4.7993227817929776e-05, "loss": 0.545, "num_tokens": 100073191.0, "step": 16750 }, { "epoch": 0.1787524137710305, "grad_norm": 1.2567178860733084, "learning_rate": 4.7991588968608023e-05, "loss": 0.6149, "num_tokens": 100095846.0, "step": 16755 }, { "epoch": 0.17880575677722893, "grad_norm": 1.1727912966005654, "learning_rate": 4.798994948163012e-05, "loss": 0.563, "num_tokens": 100116459.0, "step": 16760 }, { "epoch": 0.1788590997834274, "grad_norm": 1.3152624692234427, "learning_rate": 4.798830935704707e-05, "loss": 0.6153, "num_tokens": 100140683.0, "step": 16765 }, { "epoch": 0.17891244278962584, "grad_norm": 0.8916255029238832, "learning_rate": 4.798666859490991e-05, "loss": 0.6275, "num_tokens": 100183297.0, "step": 16770 }, { "epoch": 0.1789657857958243, "grad_norm": 2.0711068429039154, "learning_rate": 4.798502719526971e-05, "loss": 0.5693, "num_tokens": 100219007.0, "step": 16775 }, { "epoch": 0.17901912880202275, "grad_norm": 1.330857268726593, "learning_rate": 4.798338515817755e-05, "loss": 0.5642, "num_tokens": 100257783.0, "step": 16780 }, { "epoch": 0.17907247180822122, "grad_norm": 1.6080698033961436, "learning_rate": 4.7981742483684514e-05, "loss": 0.7582, "num_tokens": 100295255.0, "step": 16785 }, { "epoch": 0.1791258148144197, "grad_norm": 1.1096534483680598, "learning_rate": 4.7980099171841717e-05, "loss": 0.6631, "num_tokens": 100327031.0, "step": 16790 }, { "epoch": 0.17917915782061813, "grad_norm": 0.8750373206184657, "learning_rate": 4.79784552227003e-05, "loss": 0.6279, "num_tokens": 100359977.0, "step": 16795 }, { "epoch": 0.1792325008268166, "grad_norm": 0.8132873473709925, "learning_rate": 4.797681063631143e-05, "loss": 0.7482, "num_tokens": 100403220.0, "step": 16800 }, { "epoch": 0.17928584383301505, "grad_norm": 1.036638815347562, "learning_rate": 4.797516541272626e-05, "loss": 0.7173, "num_tokens": 100428522.0, "step": 16805 }, { "epoch": 0.17933918683921352, "grad_norm": 0.9460414790836597, "learning_rate": 4.797351955199601e-05, "loss": 0.6818, "num_tokens": 100465485.0, "step": 16810 }, { "epoch": 0.17939252984541196, "grad_norm": 0.9060214875475734, "learning_rate": 4.7971873054171884e-05, "loss": 0.6115, "num_tokens": 100495531.0, "step": 16815 }, { "epoch": 0.17944587285161043, "grad_norm": 1.080073919681915, "learning_rate": 4.7970225919305124e-05, "loss": 0.6387, "num_tokens": 100535871.0, "step": 16820 }, { "epoch": 0.17949921585780887, "grad_norm": 0.9893934770608623, "learning_rate": 4.796857814744697e-05, "loss": 0.6282, "num_tokens": 100570060.0, "step": 16825 }, { "epoch": 0.17955255886400734, "grad_norm": 0.9916589543490127, "learning_rate": 4.7966929738648714e-05, "loss": 0.5446, "num_tokens": 100602843.0, "step": 16830 }, { "epoch": 0.1796059018702058, "grad_norm": 1.3266473369727718, "learning_rate": 4.7965280692961644e-05, "loss": 0.5798, "num_tokens": 100625687.0, "step": 16835 }, { "epoch": 0.17965924487640425, "grad_norm": 1.439059642147695, "learning_rate": 4.796363101043707e-05, "loss": 0.6497, "num_tokens": 100668365.0, "step": 16840 }, { "epoch": 0.17971258788260272, "grad_norm": 1.2101194271398126, "learning_rate": 4.796198069112634e-05, "loss": 0.5561, "num_tokens": 100695731.0, "step": 16845 }, { "epoch": 0.17976593088880116, "grad_norm": 1.145400756714856, "learning_rate": 4.7960329735080794e-05, "loss": 0.5795, "num_tokens": 100723193.0, "step": 16850 }, { "epoch": 0.17981927389499963, "grad_norm": 0.760232783023696, "learning_rate": 4.7958678142351814e-05, "loss": 0.5831, "num_tokens": 100748567.0, "step": 16855 }, { "epoch": 0.17987261690119807, "grad_norm": 0.8678013649185665, "learning_rate": 4.7957025912990797e-05, "loss": 0.7146, "num_tokens": 100796784.0, "step": 16860 }, { "epoch": 0.17992595990739654, "grad_norm": 1.7890895115402798, "learning_rate": 4.7955373047049154e-05, "loss": 0.6805, "num_tokens": 100821223.0, "step": 16865 }, { "epoch": 0.17997930291359499, "grad_norm": 1.0131293699451611, "learning_rate": 4.7953719544578326e-05, "loss": 0.6112, "num_tokens": 100851374.0, "step": 16870 }, { "epoch": 0.18003264591979345, "grad_norm": 0.9722303947878429, "learning_rate": 4.795206540562975e-05, "loss": 0.6143, "num_tokens": 100872866.0, "step": 16875 }, { "epoch": 0.18008598892599192, "grad_norm": 1.570121438065579, "learning_rate": 4.7950410630254903e-05, "loss": 0.5606, "num_tokens": 100892067.0, "step": 16880 }, { "epoch": 0.18013933193219037, "grad_norm": 1.1507844923507322, "learning_rate": 4.7948755218505296e-05, "loss": 0.6629, "num_tokens": 100914462.0, "step": 16885 }, { "epoch": 0.18019267493838884, "grad_norm": 0.8679596203794693, "learning_rate": 4.794709917043242e-05, "loss": 0.5343, "num_tokens": 100942222.0, "step": 16890 }, { "epoch": 0.18024601794458728, "grad_norm": 1.495784303806423, "learning_rate": 4.794544248608782e-05, "loss": 0.6107, "num_tokens": 100966507.0, "step": 16895 }, { "epoch": 0.18029936095078575, "grad_norm": 0.9544231843981357, "learning_rate": 4.7943785165523044e-05, "loss": 0.5827, "num_tokens": 100997805.0, "step": 16900 }, { "epoch": 0.1803527039569842, "grad_norm": 0.7522499108402534, "learning_rate": 4.7942127208789674e-05, "loss": 0.5551, "num_tokens": 101022791.0, "step": 16905 }, { "epoch": 0.18040604696318266, "grad_norm": 0.796623486296691, "learning_rate": 4.7940468615939285e-05, "loss": 0.6303, "num_tokens": 101049346.0, "step": 16910 }, { "epoch": 0.1804593899693811, "grad_norm": 1.8352963543556402, "learning_rate": 4.793880938702351e-05, "loss": 0.6891, "num_tokens": 101075483.0, "step": 16915 }, { "epoch": 0.18051273297557957, "grad_norm": 1.22430237245988, "learning_rate": 4.793714952209396e-05, "loss": 0.5512, "num_tokens": 101092684.0, "step": 16920 }, { "epoch": 0.18056607598177804, "grad_norm": 0.8890247327349865, "learning_rate": 4.79354890212023e-05, "loss": 0.6156, "num_tokens": 101130401.0, "step": 16925 }, { "epoch": 0.18061941898797648, "grad_norm": 1.5367240351727722, "learning_rate": 4.793382788440019e-05, "loss": 0.6319, "num_tokens": 101161572.0, "step": 16930 }, { "epoch": 0.18067276199417495, "grad_norm": 1.8399445937476444, "learning_rate": 4.793216611173933e-05, "loss": 0.5707, "num_tokens": 101176726.0, "step": 16935 }, { "epoch": 0.1807261050003734, "grad_norm": 1.007167600361849, "learning_rate": 4.793050370327143e-05, "loss": 0.6767, "num_tokens": 101219907.0, "step": 16940 }, { "epoch": 0.18077944800657186, "grad_norm": 0.909956114259474, "learning_rate": 4.792884065904823e-05, "loss": 0.6364, "num_tokens": 101259294.0, "step": 16945 }, { "epoch": 0.1808327910127703, "grad_norm": 0.9718709927056732, "learning_rate": 4.7927176979121466e-05, "loss": 0.6829, "num_tokens": 101302279.0, "step": 16950 }, { "epoch": 0.18088613401896877, "grad_norm": 0.8494585566605216, "learning_rate": 4.792551266354291e-05, "loss": 0.5592, "num_tokens": 101328216.0, "step": 16955 }, { "epoch": 0.18093947702516722, "grad_norm": 3.1594504834663115, "learning_rate": 4.7923847712364364e-05, "loss": 0.5903, "num_tokens": 101357212.0, "step": 16960 }, { "epoch": 0.1809928200313657, "grad_norm": 0.9437985013909098, "learning_rate": 4.7922182125637616e-05, "loss": 0.6304, "num_tokens": 101390405.0, "step": 16965 }, { "epoch": 0.18104616303756416, "grad_norm": 0.7671589230107283, "learning_rate": 4.7920515903414514e-05, "loss": 0.7116, "num_tokens": 101432281.0, "step": 16970 }, { "epoch": 0.1810995060437626, "grad_norm": 0.7751915502887513, "learning_rate": 4.79188490457469e-05, "loss": 0.7089, "num_tokens": 101462691.0, "step": 16975 }, { "epoch": 0.18115284904996107, "grad_norm": 1.1203638623755399, "learning_rate": 4.791718155268665e-05, "loss": 0.5184, "num_tokens": 101484051.0, "step": 16980 }, { "epoch": 0.1812061920561595, "grad_norm": 2.076433980295839, "learning_rate": 4.791551342428564e-05, "loss": 0.6102, "num_tokens": 101508904.0, "step": 16985 }, { "epoch": 0.18125953506235798, "grad_norm": 1.2202863485528592, "learning_rate": 4.7913844660595794e-05, "loss": 0.5776, "num_tokens": 101527095.0, "step": 16990 }, { "epoch": 0.18131287806855642, "grad_norm": 1.3754749655950258, "learning_rate": 4.791217526166903e-05, "loss": 0.6682, "num_tokens": 101570548.0, "step": 16995 }, { "epoch": 0.1813662210747549, "grad_norm": 1.2288743897247603, "learning_rate": 4.7910505227557314e-05, "loss": 0.7976, "num_tokens": 101600952.0, "step": 17000 }, { "epoch": 0.18141956408095333, "grad_norm": 0.7981387238297095, "learning_rate": 4.790883455831258e-05, "loss": 0.5674, "num_tokens": 101620269.0, "step": 17005 }, { "epoch": 0.1814729070871518, "grad_norm": 1.124096206841143, "learning_rate": 4.790716325398684e-05, "loss": 0.5423, "num_tokens": 101656481.0, "step": 17010 }, { "epoch": 0.18152625009335027, "grad_norm": 0.8435731637446088, "learning_rate": 4.790549131463211e-05, "loss": 0.6047, "num_tokens": 101684706.0, "step": 17015 }, { "epoch": 0.18157959309954871, "grad_norm": 1.053563815147865, "learning_rate": 4.790381874030039e-05, "loss": 0.6084, "num_tokens": 101736076.0, "step": 17020 }, { "epoch": 0.18163293610574718, "grad_norm": 1.0280221930840863, "learning_rate": 4.790214553104374e-05, "loss": 0.5121, "num_tokens": 101755911.0, "step": 17025 }, { "epoch": 0.18168627911194563, "grad_norm": 1.4408600291297846, "learning_rate": 4.790047168691423e-05, "loss": 0.6029, "num_tokens": 101782526.0, "step": 17030 }, { "epoch": 0.1817396221181441, "grad_norm": 1.7129804471035528, "learning_rate": 4.789879720796395e-05, "loss": 0.6307, "num_tokens": 101803856.0, "step": 17035 }, { "epoch": 0.18179296512434254, "grad_norm": 1.223633381875147, "learning_rate": 4.7897122094245005e-05, "loss": 0.7278, "num_tokens": 101853954.0, "step": 17040 }, { "epoch": 0.181846308130541, "grad_norm": 0.8917105423826086, "learning_rate": 4.7895446345809517e-05, "loss": 0.5355, "num_tokens": 101883826.0, "step": 17045 }, { "epoch": 0.18189965113673945, "grad_norm": 2.017819057684908, "learning_rate": 4.789376996270962e-05, "loss": 0.6529, "num_tokens": 101898802.0, "step": 17050 }, { "epoch": 0.18195299414293792, "grad_norm": 1.1028600135058644, "learning_rate": 4.7892092944997505e-05, "loss": 0.4866, "num_tokens": 101938010.0, "step": 17055 }, { "epoch": 0.1820063371491364, "grad_norm": 0.8785038213783688, "learning_rate": 4.7890415292725336e-05, "loss": 0.7621, "num_tokens": 101964097.0, "step": 17060 }, { "epoch": 0.18205968015533483, "grad_norm": 1.3797159064311522, "learning_rate": 4.7888737005945327e-05, "loss": 0.647, "num_tokens": 101987245.0, "step": 17065 }, { "epoch": 0.1821130231615333, "grad_norm": 0.8153913294508027, "learning_rate": 4.788705808470971e-05, "loss": 0.5761, "num_tokens": 102016043.0, "step": 17070 }, { "epoch": 0.18216636616773174, "grad_norm": 1.2933394231045579, "learning_rate": 4.788537852907071e-05, "loss": 0.7176, "num_tokens": 102042843.0, "step": 17075 }, { "epoch": 0.1822197091739302, "grad_norm": 1.0183210993243828, "learning_rate": 4.788369833908061e-05, "loss": 0.7876, "num_tokens": 102086105.0, "step": 17080 }, { "epoch": 0.18227305218012865, "grad_norm": 0.8948599378769331, "learning_rate": 4.788201751479168e-05, "loss": 0.465, "num_tokens": 102116640.0, "step": 17085 }, { "epoch": 0.18232639518632712, "grad_norm": 2.716849029560891, "learning_rate": 4.7880336056256244e-05, "loss": 0.8529, "num_tokens": 102134760.0, "step": 17090 }, { "epoch": 0.18237973819252556, "grad_norm": 1.2639373779736927, "learning_rate": 4.78786539635266e-05, "loss": 0.8578, "num_tokens": 102173793.0, "step": 17095 }, { "epoch": 0.18243308119872403, "grad_norm": 2.0838201494161286, "learning_rate": 4.7876971236655107e-05, "loss": 0.6318, "num_tokens": 102197016.0, "step": 17100 }, { "epoch": 0.1824864242049225, "grad_norm": 0.913148616696664, "learning_rate": 4.7875287875694126e-05, "loss": 0.62, "num_tokens": 102222381.0, "step": 17105 }, { "epoch": 0.18253976721112095, "grad_norm": 1.0255001370980619, "learning_rate": 4.787360388069603e-05, "loss": 0.5873, "num_tokens": 102244381.0, "step": 17110 }, { "epoch": 0.18259311021731942, "grad_norm": 1.189345455138882, "learning_rate": 4.7871919251713245e-05, "loss": 0.6603, "num_tokens": 102282471.0, "step": 17115 }, { "epoch": 0.18264645322351786, "grad_norm": 1.4524640573952576, "learning_rate": 4.787023398879817e-05, "loss": 0.4919, "num_tokens": 102314836.0, "step": 17120 }, { "epoch": 0.18269979622971633, "grad_norm": 1.0976259962386663, "learning_rate": 4.786854809200326e-05, "loss": 0.534, "num_tokens": 102335344.0, "step": 17125 }, { "epoch": 0.18275313923591477, "grad_norm": 1.0391800003143767, "learning_rate": 4.7866861561380966e-05, "loss": 0.5623, "num_tokens": 102363497.0, "step": 17130 }, { "epoch": 0.18280648224211324, "grad_norm": 1.1314882149090195, "learning_rate": 4.786517439698378e-05, "loss": 0.6359, "num_tokens": 102396505.0, "step": 17135 }, { "epoch": 0.18285982524831168, "grad_norm": 0.9499745885260369, "learning_rate": 4.786348659886419e-05, "loss": 0.6185, "num_tokens": 102426567.0, "step": 17140 }, { "epoch": 0.18291316825451015, "grad_norm": 1.5388116924693138, "learning_rate": 4.786179816707473e-05, "loss": 0.6952, "num_tokens": 102474595.0, "step": 17145 }, { "epoch": 0.18296651126070862, "grad_norm": 0.9383061240327274, "learning_rate": 4.786010910166793e-05, "loss": 0.588, "num_tokens": 102497802.0, "step": 17150 }, { "epoch": 0.18301985426690706, "grad_norm": 1.0822312169803179, "learning_rate": 4.785841940269636e-05, "loss": 0.5448, "num_tokens": 102529722.0, "step": 17155 }, { "epoch": 0.18307319727310553, "grad_norm": 0.7543072161470463, "learning_rate": 4.78567290702126e-05, "loss": 0.637, "num_tokens": 102555409.0, "step": 17160 }, { "epoch": 0.18312654027930397, "grad_norm": 2.1360019523234315, "learning_rate": 4.785503810426924e-05, "loss": 0.4767, "num_tokens": 102583453.0, "step": 17165 }, { "epoch": 0.18317988328550244, "grad_norm": 0.9031241452832575, "learning_rate": 4.7853346504918905e-05, "loss": 0.6214, "num_tokens": 102616028.0, "step": 17170 }, { "epoch": 0.18323322629170088, "grad_norm": 1.5496200326045355, "learning_rate": 4.785165427221423e-05, "loss": 0.5859, "num_tokens": 102643357.0, "step": 17175 }, { "epoch": 0.18328656929789935, "grad_norm": 1.1069617341565858, "learning_rate": 4.784996140620788e-05, "loss": 0.498, "num_tokens": 102667897.0, "step": 17180 }, { "epoch": 0.1833399123040978, "grad_norm": 1.794777035771677, "learning_rate": 4.7848267906952536e-05, "loss": 0.6128, "num_tokens": 102694403.0, "step": 17185 }, { "epoch": 0.18339325531029627, "grad_norm": 1.091958146910607, "learning_rate": 4.784657377450089e-05, "loss": 0.6594, "num_tokens": 102734276.0, "step": 17190 }, { "epoch": 0.18344659831649474, "grad_norm": 1.2988344673621288, "learning_rate": 4.784487900890566e-05, "loss": 0.5816, "num_tokens": 102771843.0, "step": 17195 }, { "epoch": 0.18349994132269318, "grad_norm": 0.8868890362759108, "learning_rate": 4.784318361021958e-05, "loss": 0.5432, "num_tokens": 102795446.0, "step": 17200 }, { "epoch": 0.18355328432889165, "grad_norm": 0.7372277506176865, "learning_rate": 4.784148757849542e-05, "loss": 0.6192, "num_tokens": 102833830.0, "step": 17205 }, { "epoch": 0.1836066273350901, "grad_norm": 1.3245238569843634, "learning_rate": 4.783979091378595e-05, "loss": 0.5728, "num_tokens": 102853169.0, "step": 17210 }, { "epoch": 0.18365997034128856, "grad_norm": 0.9022118773844222, "learning_rate": 4.7838093616143956e-05, "loss": 0.5658, "num_tokens": 102881606.0, "step": 17215 }, { "epoch": 0.183713313347487, "grad_norm": 1.1729144699596732, "learning_rate": 4.783639568562227e-05, "loss": 0.6701, "num_tokens": 102902616.0, "step": 17220 }, { "epoch": 0.18376665635368547, "grad_norm": 0.9667638396067876, "learning_rate": 4.783469712227372e-05, "loss": 0.5472, "num_tokens": 102935727.0, "step": 17225 }, { "epoch": 0.1838199993598839, "grad_norm": 1.1391122885156364, "learning_rate": 4.783299792615117e-05, "loss": 0.5788, "num_tokens": 102959814.0, "step": 17230 }, { "epoch": 0.18387334236608238, "grad_norm": 0.8608664272176789, "learning_rate": 4.783129809730749e-05, "loss": 0.5693, "num_tokens": 102986777.0, "step": 17235 }, { "epoch": 0.18392668537228085, "grad_norm": 1.2961093150423735, "learning_rate": 4.782959763579557e-05, "loss": 0.614, "num_tokens": 103015597.0, "step": 17240 }, { "epoch": 0.1839800283784793, "grad_norm": 1.2279077804390204, "learning_rate": 4.7827896541668326e-05, "loss": 0.7234, "num_tokens": 103047720.0, "step": 17245 }, { "epoch": 0.18403337138467776, "grad_norm": 1.2943893236711408, "learning_rate": 4.7826194814978696e-05, "loss": 0.6065, "num_tokens": 103072938.0, "step": 17250 }, { "epoch": 0.1840867143908762, "grad_norm": 1.6088214163466013, "learning_rate": 4.782449245577965e-05, "loss": 0.7967, "num_tokens": 103099126.0, "step": 17255 }, { "epoch": 0.18414005739707467, "grad_norm": 1.5428177671226493, "learning_rate": 4.782278946412413e-05, "loss": 0.6768, "num_tokens": 103124284.0, "step": 17260 }, { "epoch": 0.18419340040327312, "grad_norm": 1.202833211747791, "learning_rate": 4.782108584006515e-05, "loss": 0.6498, "num_tokens": 103149874.0, "step": 17265 }, { "epoch": 0.1842467434094716, "grad_norm": 1.8208886184882858, "learning_rate": 4.781938158365572e-05, "loss": 0.6261, "num_tokens": 103163590.0, "step": 17270 }, { "epoch": 0.18430008641567003, "grad_norm": 1.344210888348035, "learning_rate": 4.7817676694948875e-05, "loss": 0.6157, "num_tokens": 103187779.0, "step": 17275 }, { "epoch": 0.1843534294218685, "grad_norm": 1.407656415422454, "learning_rate": 4.781597117399767e-05, "loss": 0.6987, "num_tokens": 103223537.0, "step": 17280 }, { "epoch": 0.18440677242806697, "grad_norm": 1.2768502899059788, "learning_rate": 4.781426502085516e-05, "loss": 0.6772, "num_tokens": 103255939.0, "step": 17285 }, { "epoch": 0.1844601154342654, "grad_norm": 1.0767116486288275, "learning_rate": 4.7812558235574454e-05, "loss": 0.6549, "num_tokens": 103291430.0, "step": 17290 }, { "epoch": 0.18451345844046388, "grad_norm": 4.351356153829378, "learning_rate": 4.7810850818208656e-05, "loss": 0.5054, "num_tokens": 103306242.0, "step": 17295 }, { "epoch": 0.18456680144666232, "grad_norm": 0.9658136783156694, "learning_rate": 4.780914276881091e-05, "loss": 0.5518, "num_tokens": 103355917.0, "step": 17300 }, { "epoch": 0.1846201444528608, "grad_norm": 0.9065366005120385, "learning_rate": 4.780743408743435e-05, "loss": 0.6598, "num_tokens": 103385896.0, "step": 17305 }, { "epoch": 0.18467348745905923, "grad_norm": 1.2232279454251003, "learning_rate": 4.780572477413216e-05, "loss": 0.6079, "num_tokens": 103412175.0, "step": 17310 }, { "epoch": 0.1847268304652577, "grad_norm": 1.505757198404683, "learning_rate": 4.780401482895752e-05, "loss": 0.5989, "num_tokens": 103433000.0, "step": 17315 }, { "epoch": 0.18478017347145614, "grad_norm": 2.1911785367470213, "learning_rate": 4.7802304251963644e-05, "loss": 0.6632, "num_tokens": 103447168.0, "step": 17320 }, { "epoch": 0.1848335164776546, "grad_norm": 1.066678392960179, "learning_rate": 4.780059304320376e-05, "loss": 0.6667, "num_tokens": 103481072.0, "step": 17325 }, { "epoch": 0.18488685948385308, "grad_norm": 1.2415911164346212, "learning_rate": 4.7798881202731124e-05, "loss": 0.6873, "num_tokens": 103515252.0, "step": 17330 }, { "epoch": 0.18494020249005153, "grad_norm": 3.3685337848254813, "learning_rate": 4.779716873059899e-05, "loss": 0.9248, "num_tokens": 103539134.0, "step": 17335 }, { "epoch": 0.18499354549625, "grad_norm": 1.188232064386651, "learning_rate": 4.779545562686066e-05, "loss": 0.6744, "num_tokens": 103564095.0, "step": 17340 }, { "epoch": 0.18504688850244844, "grad_norm": 1.238187034243998, "learning_rate": 4.779374189156945e-05, "loss": 0.674, "num_tokens": 103588921.0, "step": 17345 }, { "epoch": 0.1851002315086469, "grad_norm": 0.8961178518700201, "learning_rate": 4.7792027524778666e-05, "loss": 0.6205, "num_tokens": 103619736.0, "step": 17350 }, { "epoch": 0.18515357451484535, "grad_norm": 0.9871397639621456, "learning_rate": 4.779031252654167e-05, "loss": 0.6277, "num_tokens": 103658638.0, "step": 17355 }, { "epoch": 0.18520691752104382, "grad_norm": 1.0815213889355808, "learning_rate": 4.7788596896911825e-05, "loss": 0.5433, "num_tokens": 103692548.0, "step": 17360 }, { "epoch": 0.18526026052724226, "grad_norm": 2.001809937808503, "learning_rate": 4.778688063594252e-05, "loss": 0.7733, "num_tokens": 103722165.0, "step": 17365 }, { "epoch": 0.18531360353344073, "grad_norm": 0.6780191327612229, "learning_rate": 4.778516374368716e-05, "loss": 0.5912, "num_tokens": 103753798.0, "step": 17370 }, { "epoch": 0.1853669465396392, "grad_norm": 0.8754603619655541, "learning_rate": 4.778344622019917e-05, "loss": 0.6864, "num_tokens": 103802978.0, "step": 17375 }, { "epoch": 0.18542028954583764, "grad_norm": 0.8330582304795298, "learning_rate": 4.778172806553199e-05, "loss": 0.6034, "num_tokens": 103823335.0, "step": 17380 }, { "epoch": 0.1854736325520361, "grad_norm": 1.014399003019862, "learning_rate": 4.77800092797391e-05, "loss": 0.5705, "num_tokens": 103851799.0, "step": 17385 }, { "epoch": 0.18552697555823455, "grad_norm": 0.7506259564489715, "learning_rate": 4.777828986287398e-05, "loss": 0.661, "num_tokens": 103896759.0, "step": 17390 }, { "epoch": 0.18558031856443302, "grad_norm": 1.312007460654938, "learning_rate": 4.777656981499013e-05, "loss": 0.5979, "num_tokens": 103916114.0, "step": 17395 }, { "epoch": 0.18563366157063146, "grad_norm": 1.2549575583955381, "learning_rate": 4.777484913614108e-05, "loss": 0.4554, "num_tokens": 103930089.0, "step": 17400 }, { "epoch": 0.18568700457682993, "grad_norm": 1.6853675233750764, "learning_rate": 4.7773127826380365e-05, "loss": 0.6851, "num_tokens": 103953338.0, "step": 17405 }, { "epoch": 0.18574034758302838, "grad_norm": 1.1158604249134947, "learning_rate": 4.777140588576156e-05, "loss": 0.694, "num_tokens": 103987116.0, "step": 17410 }, { "epoch": 0.18579369058922685, "grad_norm": 0.9558902297547816, "learning_rate": 4.7769683314338234e-05, "loss": 0.5495, "num_tokens": 104004329.0, "step": 17415 }, { "epoch": 0.18584703359542531, "grad_norm": 1.0356552319527133, "learning_rate": 4.7767960112164006e-05, "loss": 0.6101, "num_tokens": 104030444.0, "step": 17420 }, { "epoch": 0.18590037660162376, "grad_norm": 1.5582123000996457, "learning_rate": 4.776623627929249e-05, "loss": 0.5669, "num_tokens": 104042087.0, "step": 17425 }, { "epoch": 0.18595371960782223, "grad_norm": 1.1266121871785861, "learning_rate": 4.7764511815777326e-05, "loss": 0.796, "num_tokens": 104074048.0, "step": 17430 }, { "epoch": 0.18600706261402067, "grad_norm": 1.5792986312296362, "learning_rate": 4.776278672167218e-05, "loss": 0.5545, "num_tokens": 104103139.0, "step": 17435 }, { "epoch": 0.18606040562021914, "grad_norm": 1.3367480432070358, "learning_rate": 4.776106099703073e-05, "loss": 0.7072, "num_tokens": 104145473.0, "step": 17440 }, { "epoch": 0.18611374862641758, "grad_norm": 1.5718283244894005, "learning_rate": 4.7759334641906675e-05, "loss": 0.6369, "num_tokens": 104160028.0, "step": 17445 }, { "epoch": 0.18616709163261605, "grad_norm": 1.5218838081624098, "learning_rate": 4.775760765635375e-05, "loss": 0.6492, "num_tokens": 104182876.0, "step": 17450 }, { "epoch": 0.1862204346388145, "grad_norm": 1.137921426269737, "learning_rate": 4.775588004042568e-05, "loss": 0.649, "num_tokens": 104201937.0, "step": 17455 }, { "epoch": 0.18627377764501296, "grad_norm": 0.7592852299891945, "learning_rate": 4.7754151794176225e-05, "loss": 0.5886, "num_tokens": 104230745.0, "step": 17460 }, { "epoch": 0.18632712065121143, "grad_norm": 1.175843940761706, "learning_rate": 4.775242291765918e-05, "loss": 0.6942, "num_tokens": 104270120.0, "step": 17465 }, { "epoch": 0.18638046365740987, "grad_norm": 1.1803443010245238, "learning_rate": 4.775069341092833e-05, "loss": 0.6148, "num_tokens": 104299587.0, "step": 17470 }, { "epoch": 0.18643380666360834, "grad_norm": 0.8774740701934228, "learning_rate": 4.774896327403749e-05, "loss": 0.6823, "num_tokens": 104348126.0, "step": 17475 }, { "epoch": 0.18648714966980678, "grad_norm": 0.9200324126106203, "learning_rate": 4.774723250704051e-05, "loss": 0.4412, "num_tokens": 104372058.0, "step": 17480 }, { "epoch": 0.18654049267600525, "grad_norm": 1.6539425955412246, "learning_rate": 4.774550110999125e-05, "loss": 0.6661, "num_tokens": 104392050.0, "step": 17485 }, { "epoch": 0.1865938356822037, "grad_norm": 2.7116286812228894, "learning_rate": 4.774376908294357e-05, "loss": 0.7848, "num_tokens": 104420669.0, "step": 17490 }, { "epoch": 0.18664717868840217, "grad_norm": 1.1578296376842105, "learning_rate": 4.7742036425951385e-05, "loss": 0.5443, "num_tokens": 104450824.0, "step": 17495 }, { "epoch": 0.1867005216946006, "grad_norm": 1.2348788535808322, "learning_rate": 4.77403031390686e-05, "loss": 0.6425, "num_tokens": 104472659.0, "step": 17500 }, { "epoch": 0.18675386470079908, "grad_norm": 1.3701059727792684, "learning_rate": 4.773856922234916e-05, "loss": 0.6822, "num_tokens": 104506814.0, "step": 17505 }, { "epoch": 0.18680720770699755, "grad_norm": 0.8949427764652501, "learning_rate": 4.773683467584702e-05, "loss": 0.5743, "num_tokens": 104529922.0, "step": 17510 }, { "epoch": 0.186860550713196, "grad_norm": 1.8059690954292573, "learning_rate": 4.773509949961615e-05, "loss": 0.5371, "num_tokens": 104548711.0, "step": 17515 }, { "epoch": 0.18691389371939446, "grad_norm": 1.4079552143264151, "learning_rate": 4.773336369371055e-05, "loss": 0.6006, "num_tokens": 104589567.0, "step": 17520 }, { "epoch": 0.1869672367255929, "grad_norm": 1.8764760747806566, "learning_rate": 4.773162725818423e-05, "loss": 0.7253, "num_tokens": 104631304.0, "step": 17525 }, { "epoch": 0.18702057973179137, "grad_norm": 1.2364619747080006, "learning_rate": 4.772989019309123e-05, "loss": 0.7577, "num_tokens": 104650009.0, "step": 17530 }, { "epoch": 0.1870739227379898, "grad_norm": 0.850187792283799, "learning_rate": 4.772815249848558e-05, "loss": 0.5821, "num_tokens": 104674440.0, "step": 17535 }, { "epoch": 0.18712726574418828, "grad_norm": 2.481869728789079, "learning_rate": 4.77264141744214e-05, "loss": 0.677, "num_tokens": 104701325.0, "step": 17540 }, { "epoch": 0.18718060875038672, "grad_norm": 1.1767686733642932, "learning_rate": 4.7724675220952744e-05, "loss": 0.6436, "num_tokens": 104736575.0, "step": 17545 }, { "epoch": 0.1872339517565852, "grad_norm": 1.3809973515735783, "learning_rate": 4.7722935638133744e-05, "loss": 0.5362, "num_tokens": 104751071.0, "step": 17550 }, { "epoch": 0.18728729476278366, "grad_norm": 0.7790257568431169, "learning_rate": 4.7721195426018513e-05, "loss": 0.5321, "num_tokens": 104779322.0, "step": 17555 }, { "epoch": 0.1873406377689821, "grad_norm": 1.1935334736981822, "learning_rate": 4.7719454584661236e-05, "loss": 0.5023, "num_tokens": 104813180.0, "step": 17560 }, { "epoch": 0.18739398077518057, "grad_norm": 0.7328500594306392, "learning_rate": 4.7717713114116054e-05, "loss": 0.5795, "num_tokens": 104852568.0, "step": 17565 }, { "epoch": 0.18744732378137902, "grad_norm": 1.0874291028032468, "learning_rate": 4.7715971014437164e-05, "loss": 0.7349, "num_tokens": 104868206.0, "step": 17570 }, { "epoch": 0.18750066678757749, "grad_norm": 0.9096118030936552, "learning_rate": 4.771422828567878e-05, "loss": 0.5327, "num_tokens": 104906038.0, "step": 17575 }, { "epoch": 0.18755400979377593, "grad_norm": 1.5187446205837665, "learning_rate": 4.771248492789515e-05, "loss": 0.8255, "num_tokens": 104929615.0, "step": 17580 }, { "epoch": 0.1876073527999744, "grad_norm": 0.8469360085451391, "learning_rate": 4.771074094114049e-05, "loss": 0.6325, "num_tokens": 104965561.0, "step": 17585 }, { "epoch": 0.18766069580617284, "grad_norm": 1.3809151973929792, "learning_rate": 4.770899632546909e-05, "loss": 0.5476, "num_tokens": 104985604.0, "step": 17590 }, { "epoch": 0.1877140388123713, "grad_norm": 1.4960233442504276, "learning_rate": 4.7707251080935234e-05, "loss": 0.6857, "num_tokens": 105022760.0, "step": 17595 }, { "epoch": 0.18776738181856978, "grad_norm": 2.2387247185276027, "learning_rate": 4.770550520759324e-05, "loss": 0.5767, "num_tokens": 105044617.0, "step": 17600 }, { "epoch": 0.18782072482476822, "grad_norm": 1.6542920397811969, "learning_rate": 4.770375870549742e-05, "loss": 0.7328, "num_tokens": 105083186.0, "step": 17605 }, { "epoch": 0.1878740678309667, "grad_norm": 2.003368417273949, "learning_rate": 4.7702011574702126e-05, "loss": 0.6075, "num_tokens": 105104669.0, "step": 17610 }, { "epoch": 0.18792741083716513, "grad_norm": 0.9473462330903722, "learning_rate": 4.770026381526173e-05, "loss": 0.5947, "num_tokens": 105124259.0, "step": 17615 }, { "epoch": 0.1879807538433636, "grad_norm": 0.7150245145909342, "learning_rate": 4.769851542723062e-05, "loss": 0.5701, "num_tokens": 105162237.0, "step": 17620 }, { "epoch": 0.18803409684956204, "grad_norm": 1.891275440788325, "learning_rate": 4.76967664106632e-05, "loss": 0.7895, "num_tokens": 105188759.0, "step": 17625 }, { "epoch": 0.1880874398557605, "grad_norm": 1.114650684356397, "learning_rate": 4.7695016765613884e-05, "loss": 0.5771, "num_tokens": 105216667.0, "step": 17630 }, { "epoch": 0.18814078286195896, "grad_norm": 1.1566369537168326, "learning_rate": 4.769326649213713e-05, "loss": 0.6925, "num_tokens": 105236268.0, "step": 17635 }, { "epoch": 0.18819412586815742, "grad_norm": 0.9785717655885312, "learning_rate": 4.769151559028741e-05, "loss": 0.6707, "num_tokens": 105273053.0, "step": 17640 }, { "epoch": 0.1882474688743559, "grad_norm": 1.0038688275364263, "learning_rate": 4.7689764060119194e-05, "loss": 0.6884, "num_tokens": 105299800.0, "step": 17645 }, { "epoch": 0.18830081188055434, "grad_norm": 1.186261418059809, "learning_rate": 4.7688011901687e-05, "loss": 0.7348, "num_tokens": 105320637.0, "step": 17650 }, { "epoch": 0.1883541548867528, "grad_norm": 0.8865700472089066, "learning_rate": 4.768625911504533e-05, "loss": 0.5534, "num_tokens": 105337128.0, "step": 17655 }, { "epoch": 0.18840749789295125, "grad_norm": 1.4972904284310296, "learning_rate": 4.768450570024875e-05, "loss": 0.724, "num_tokens": 105377603.0, "step": 17660 }, { "epoch": 0.18846084089914972, "grad_norm": 0.6691939254647606, "learning_rate": 4.768275165735181e-05, "loss": 0.5234, "num_tokens": 105411060.0, "step": 17665 }, { "epoch": 0.18851418390534816, "grad_norm": 1.8058644568984143, "learning_rate": 4.768099698640909e-05, "loss": 0.7833, "num_tokens": 105430228.0, "step": 17670 }, { "epoch": 0.18856752691154663, "grad_norm": 1.0309189113472754, "learning_rate": 4.76792416874752e-05, "loss": 0.6965, "num_tokens": 105471270.0, "step": 17675 }, { "epoch": 0.18862086991774507, "grad_norm": 1.1634307397626968, "learning_rate": 4.767748576060476e-05, "loss": 0.5511, "num_tokens": 105484600.0, "step": 17680 }, { "epoch": 0.18867421292394354, "grad_norm": 0.8690564523909423, "learning_rate": 4.767572920585241e-05, "loss": 0.6491, "num_tokens": 105502408.0, "step": 17685 }, { "epoch": 0.188727555930142, "grad_norm": 0.9591085209467581, "learning_rate": 4.76739720232728e-05, "loss": 0.7039, "num_tokens": 105537189.0, "step": 17690 }, { "epoch": 0.18878089893634045, "grad_norm": 2.183835201873605, "learning_rate": 4.767221421292063e-05, "loss": 0.5952, "num_tokens": 105565058.0, "step": 17695 }, { "epoch": 0.18883424194253892, "grad_norm": 1.285804245404283, "learning_rate": 4.767045577485059e-05, "loss": 0.7289, "num_tokens": 105592062.0, "step": 17700 }, { "epoch": 0.18888758494873736, "grad_norm": 2.595712335335036, "learning_rate": 4.7668696709117385e-05, "loss": 0.71, "num_tokens": 105631243.0, "step": 17705 }, { "epoch": 0.18894092795493583, "grad_norm": 0.8139123430515375, "learning_rate": 4.766693701577577e-05, "loss": 0.6858, "num_tokens": 105664619.0, "step": 17710 }, { "epoch": 0.18899427096113428, "grad_norm": 1.2199618592137662, "learning_rate": 4.76651766948805e-05, "loss": 0.513, "num_tokens": 105679431.0, "step": 17715 }, { "epoch": 0.18904761396733274, "grad_norm": 1.1919050556842634, "learning_rate": 4.766341574648636e-05, "loss": 0.5169, "num_tokens": 105699052.0, "step": 17720 }, { "epoch": 0.1891009569735312, "grad_norm": 1.2418639009002839, "learning_rate": 4.7661654170648135e-05, "loss": 0.4894, "num_tokens": 105723991.0, "step": 17725 }, { "epoch": 0.18915429997972966, "grad_norm": 0.8053010950813556, "learning_rate": 4.765989196742064e-05, "loss": 0.5599, "num_tokens": 105744902.0, "step": 17730 }, { "epoch": 0.18920764298592813, "grad_norm": 1.4302388277595648, "learning_rate": 4.765812913685872e-05, "loss": 0.5148, "num_tokens": 105771612.0, "step": 17735 }, { "epoch": 0.18926098599212657, "grad_norm": 0.8832262294430732, "learning_rate": 4.7656365679017224e-05, "loss": 0.5816, "num_tokens": 105792908.0, "step": 17740 }, { "epoch": 0.18931432899832504, "grad_norm": 1.331098585982162, "learning_rate": 4.7654601593951035e-05, "loss": 0.5621, "num_tokens": 105812728.0, "step": 17745 }, { "epoch": 0.18936767200452348, "grad_norm": 2.9060080860786006, "learning_rate": 4.765283688171504e-05, "loss": 0.7256, "num_tokens": 105846251.0, "step": 17750 }, { "epoch": 0.18942101501072195, "grad_norm": 0.9640474950387946, "learning_rate": 4.765107154236416e-05, "loss": 0.79, "num_tokens": 105880534.0, "step": 17755 }, { "epoch": 0.1894743580169204, "grad_norm": 1.2602802204668067, "learning_rate": 4.764930557595332e-05, "loss": 0.603, "num_tokens": 105902522.0, "step": 17760 }, { "epoch": 0.18952770102311886, "grad_norm": 2.033485011258417, "learning_rate": 4.764753898253749e-05, "loss": 0.7657, "num_tokens": 105935941.0, "step": 17765 }, { "epoch": 0.1895810440293173, "grad_norm": 1.2267491960509123, "learning_rate": 4.7645771762171614e-05, "loss": 0.653, "num_tokens": 105965600.0, "step": 17770 }, { "epoch": 0.18963438703551577, "grad_norm": 1.4618307840391793, "learning_rate": 4.764400391491071e-05, "loss": 0.5915, "num_tokens": 105985386.0, "step": 17775 }, { "epoch": 0.18968773004171424, "grad_norm": 1.054109094241275, "learning_rate": 4.764223544080978e-05, "loss": 0.634, "num_tokens": 106025565.0, "step": 17780 }, { "epoch": 0.18974107304791268, "grad_norm": 1.1836110421639798, "learning_rate": 4.764046633992386e-05, "loss": 0.6205, "num_tokens": 106047409.0, "step": 17785 }, { "epoch": 0.18979441605411115, "grad_norm": 1.270046849626399, "learning_rate": 4.763869661230799e-05, "loss": 0.6284, "num_tokens": 106077164.0, "step": 17790 }, { "epoch": 0.1898477590603096, "grad_norm": 1.1383516938834468, "learning_rate": 4.7636926258017256e-05, "loss": 0.7216, "num_tokens": 106118809.0, "step": 17795 }, { "epoch": 0.18990110206650807, "grad_norm": 1.025767946306268, "learning_rate": 4.763515527710674e-05, "loss": 0.7284, "num_tokens": 106146119.0, "step": 17800 }, { "epoch": 0.1899544450727065, "grad_norm": 0.8651866570816781, "learning_rate": 4.7633383669631536e-05, "loss": 0.5939, "num_tokens": 106168958.0, "step": 17805 }, { "epoch": 0.19000778807890498, "grad_norm": 0.950709038183754, "learning_rate": 4.763161143564681e-05, "loss": 0.6362, "num_tokens": 106214193.0, "step": 17810 }, { "epoch": 0.19006113108510342, "grad_norm": 0.9248828620494425, "learning_rate": 4.762983857520767e-05, "loss": 0.6961, "num_tokens": 106236508.0, "step": 17815 }, { "epoch": 0.1901144740913019, "grad_norm": 0.9780638369232196, "learning_rate": 4.7628065088369304e-05, "loss": 0.6206, "num_tokens": 106265665.0, "step": 17820 }, { "epoch": 0.19016781709750036, "grad_norm": 1.223487762516379, "learning_rate": 4.76262909751869e-05, "loss": 0.6643, "num_tokens": 106295616.0, "step": 17825 }, { "epoch": 0.1902211601036988, "grad_norm": 0.934242710612571, "learning_rate": 4.762451623571566e-05, "loss": 0.615, "num_tokens": 106322814.0, "step": 17830 }, { "epoch": 0.19027450310989727, "grad_norm": 1.0502826049406044, "learning_rate": 4.762274087001081e-05, "loss": 0.5169, "num_tokens": 106343301.0, "step": 17835 }, { "epoch": 0.1903278461160957, "grad_norm": 0.6953921885436368, "learning_rate": 4.76209648781276e-05, "loss": 0.5656, "num_tokens": 106377588.0, "step": 17840 }, { "epoch": 0.19038118912229418, "grad_norm": 1.0459731300058157, "learning_rate": 4.76191882601213e-05, "loss": 0.6053, "num_tokens": 106415376.0, "step": 17845 }, { "epoch": 0.19043453212849262, "grad_norm": 0.6945559865167008, "learning_rate": 4.761741101604717e-05, "loss": 0.5787, "num_tokens": 106449084.0, "step": 17850 }, { "epoch": 0.1904878751346911, "grad_norm": 0.9819280502282663, "learning_rate": 4.7615633145960544e-05, "loss": 0.5349, "num_tokens": 106483265.0, "step": 17855 }, { "epoch": 0.19054121814088953, "grad_norm": 1.1880151323132222, "learning_rate": 4.761385464991673e-05, "loss": 0.598, "num_tokens": 106517113.0, "step": 17860 }, { "epoch": 0.190594561147088, "grad_norm": 1.3722431198009415, "learning_rate": 4.7612075527971075e-05, "loss": 0.7854, "num_tokens": 106545304.0, "step": 17865 }, { "epoch": 0.19064790415328647, "grad_norm": 1.8443504004504727, "learning_rate": 4.7610295780178934e-05, "loss": 0.839, "num_tokens": 106593202.0, "step": 17870 }, { "epoch": 0.19070124715948492, "grad_norm": 1.0481064950736714, "learning_rate": 4.76085154065957e-05, "loss": 0.6337, "num_tokens": 106629584.0, "step": 17875 }, { "epoch": 0.19075459016568339, "grad_norm": 0.9225738686709084, "learning_rate": 4.760673440727678e-05, "loss": 0.8595, "num_tokens": 106668755.0, "step": 17880 }, { "epoch": 0.19080793317188183, "grad_norm": 1.115263904056063, "learning_rate": 4.760495278227758e-05, "loss": 0.5898, "num_tokens": 106689376.0, "step": 17885 }, { "epoch": 0.1908612761780803, "grad_norm": 1.1393411949176424, "learning_rate": 4.760317053165355e-05, "loss": 0.6085, "num_tokens": 106725794.0, "step": 17890 }, { "epoch": 0.19091461918427874, "grad_norm": 1.3552460350584168, "learning_rate": 4.7601387655460135e-05, "loss": 0.5476, "num_tokens": 106751888.0, "step": 17895 }, { "epoch": 0.1909679621904772, "grad_norm": 1.441228363478096, "learning_rate": 4.7599604153752826e-05, "loss": 0.6112, "num_tokens": 106774999.0, "step": 17900 }, { "epoch": 0.19102130519667565, "grad_norm": 1.9287506119729574, "learning_rate": 4.759782002658713e-05, "loss": 0.7256, "num_tokens": 106799414.0, "step": 17905 }, { "epoch": 0.19107464820287412, "grad_norm": 1.1454775971894617, "learning_rate": 4.759603527401856e-05, "loss": 0.7111, "num_tokens": 106833172.0, "step": 17910 }, { "epoch": 0.1911279912090726, "grad_norm": 1.2326569384769406, "learning_rate": 4.7594249896102636e-05, "loss": 0.7153, "num_tokens": 106862484.0, "step": 17915 }, { "epoch": 0.19118133421527103, "grad_norm": 0.8555790672705276, "learning_rate": 4.759246389289494e-05, "loss": 0.5122, "num_tokens": 106901687.0, "step": 17920 }, { "epoch": 0.1912346772214695, "grad_norm": 1.4222573245117913, "learning_rate": 4.759067726445105e-05, "loss": 0.6196, "num_tokens": 106939065.0, "step": 17925 }, { "epoch": 0.19128802022766794, "grad_norm": 1.5175873349653068, "learning_rate": 4.7588890010826525e-05, "loss": 0.5164, "num_tokens": 106967605.0, "step": 17930 }, { "epoch": 0.1913413632338664, "grad_norm": 0.8724334150351664, "learning_rate": 4.7587102132077023e-05, "loss": 0.6587, "num_tokens": 107006120.0, "step": 17935 }, { "epoch": 0.19139470624006485, "grad_norm": 0.8080379454478792, "learning_rate": 4.758531362825816e-05, "loss": 0.4977, "num_tokens": 107039255.0, "step": 17940 }, { "epoch": 0.19144804924626332, "grad_norm": 1.5184020442746948, "learning_rate": 4.758352449942559e-05, "loss": 0.6469, "num_tokens": 107083811.0, "step": 17945 }, { "epoch": 0.19150139225246177, "grad_norm": 1.3371300451005679, "learning_rate": 4.7581734745635e-05, "loss": 0.5136, "num_tokens": 107104471.0, "step": 17950 }, { "epoch": 0.19155473525866024, "grad_norm": 1.5713815623433125, "learning_rate": 4.757994436694206e-05, "loss": 0.5125, "num_tokens": 107121081.0, "step": 17955 }, { "epoch": 0.1916080782648587, "grad_norm": 1.0617510693789152, "learning_rate": 4.7578153363402514e-05, "loss": 0.4928, "num_tokens": 107148451.0, "step": 17960 }, { "epoch": 0.19166142127105715, "grad_norm": 0.9897629682397197, "learning_rate": 4.757636173507206e-05, "loss": 0.6029, "num_tokens": 107184418.0, "step": 17965 }, { "epoch": 0.19171476427725562, "grad_norm": 1.7553762515238256, "learning_rate": 4.757456948200647e-05, "loss": 0.508, "num_tokens": 107206011.0, "step": 17970 }, { "epoch": 0.19176810728345406, "grad_norm": 1.599002017776653, "learning_rate": 4.757277660426152e-05, "loss": 0.5518, "num_tokens": 107223593.0, "step": 17975 }, { "epoch": 0.19182145028965253, "grad_norm": 2.0530805193124144, "learning_rate": 4.7570983101892984e-05, "loss": 0.5609, "num_tokens": 107245434.0, "step": 17980 }, { "epoch": 0.19187479329585097, "grad_norm": 0.8823487853196657, "learning_rate": 4.756918897495669e-05, "loss": 0.688, "num_tokens": 107292523.0, "step": 17985 }, { "epoch": 0.19192813630204944, "grad_norm": 1.9999609760565957, "learning_rate": 4.756739422350845e-05, "loss": 0.6749, "num_tokens": 107319266.0, "step": 17990 }, { "epoch": 0.19198147930824788, "grad_norm": 2.593903009755889, "learning_rate": 4.7565598847604124e-05, "loss": 0.6566, "num_tokens": 107348762.0, "step": 17995 }, { "epoch": 0.19203482231444635, "grad_norm": 1.238683387890016, "learning_rate": 4.7563802847299585e-05, "loss": 0.6242, "num_tokens": 107379980.0, "step": 18000 }, { "epoch": 0.19208816532064482, "grad_norm": 1.2081205429680746, "learning_rate": 4.75620062226507e-05, "loss": 0.5513, "num_tokens": 107408775.0, "step": 18005 }, { "epoch": 0.19214150832684326, "grad_norm": 0.822794900988627, "learning_rate": 4.756020897371341e-05, "loss": 0.6466, "num_tokens": 107439758.0, "step": 18010 }, { "epoch": 0.19219485133304173, "grad_norm": 2.1708821739278124, "learning_rate": 4.7558411100543596e-05, "loss": 0.7574, "num_tokens": 107448339.0, "step": 18015 }, { "epoch": 0.19224819433924017, "grad_norm": 1.1943833853606514, "learning_rate": 4.7556612603197245e-05, "loss": 0.6044, "num_tokens": 107474152.0, "step": 18020 }, { "epoch": 0.19230153734543864, "grad_norm": 1.232016053842209, "learning_rate": 4.755481348173031e-05, "loss": 0.6083, "num_tokens": 107516297.0, "step": 18025 }, { "epoch": 0.1923548803516371, "grad_norm": 2.433878263499937, "learning_rate": 4.7553013736198767e-05, "loss": 0.6911, "num_tokens": 107546892.0, "step": 18030 }, { "epoch": 0.19240822335783556, "grad_norm": 1.036803958561195, "learning_rate": 4.755121336665862e-05, "loss": 0.6172, "num_tokens": 107562422.0, "step": 18035 }, { "epoch": 0.192461566364034, "grad_norm": 1.082940171742392, "learning_rate": 4.754941237316592e-05, "loss": 0.5413, "num_tokens": 107582286.0, "step": 18040 }, { "epoch": 0.19251490937023247, "grad_norm": 1.032028016015965, "learning_rate": 4.754761075577667e-05, "loss": 0.4909, "num_tokens": 107605458.0, "step": 18045 }, { "epoch": 0.19256825237643094, "grad_norm": 1.0001770593363666, "learning_rate": 4.754580851454696e-05, "loss": 0.5273, "num_tokens": 107637280.0, "step": 18050 }, { "epoch": 0.19262159538262938, "grad_norm": 1.1952476138199237, "learning_rate": 4.754400564953286e-05, "loss": 0.6744, "num_tokens": 107667178.0, "step": 18055 }, { "epoch": 0.19267493838882785, "grad_norm": 1.0074613459859427, "learning_rate": 4.754220216079048e-05, "loss": 0.6542, "num_tokens": 107711617.0, "step": 18060 }, { "epoch": 0.1927282813950263, "grad_norm": 1.2937284042097186, "learning_rate": 4.754039804837594e-05, "loss": 0.6197, "num_tokens": 107735087.0, "step": 18065 }, { "epoch": 0.19278162440122476, "grad_norm": 0.8146361116921639, "learning_rate": 4.753859331234538e-05, "loss": 0.663, "num_tokens": 107768932.0, "step": 18070 }, { "epoch": 0.1928349674074232, "grad_norm": 1.1826081994092705, "learning_rate": 4.7536787952754944e-05, "loss": 0.5706, "num_tokens": 107800997.0, "step": 18075 }, { "epoch": 0.19288831041362167, "grad_norm": 0.7558626157176719, "learning_rate": 4.753498196966083e-05, "loss": 0.4644, "num_tokens": 107829210.0, "step": 18080 }, { "epoch": 0.1929416534198201, "grad_norm": 1.2843416496813127, "learning_rate": 4.753317536311923e-05, "loss": 0.4427, "num_tokens": 107851784.0, "step": 18085 }, { "epoch": 0.19299499642601858, "grad_norm": 1.880982044232649, "learning_rate": 4.753136813318635e-05, "loss": 0.6965, "num_tokens": 107878399.0, "step": 18090 }, { "epoch": 0.19304833943221705, "grad_norm": 1.6112155495655054, "learning_rate": 4.752956027991845e-05, "loss": 0.6455, "num_tokens": 107907739.0, "step": 18095 }, { "epoch": 0.1931016824384155, "grad_norm": 0.9683763225798676, "learning_rate": 4.752775180337178e-05, "loss": 0.6817, "num_tokens": 107944379.0, "step": 18100 }, { "epoch": 0.19315502544461396, "grad_norm": 1.568604386431693, "learning_rate": 4.752594270360261e-05, "loss": 0.6046, "num_tokens": 107967296.0, "step": 18105 }, { "epoch": 0.1932083684508124, "grad_norm": 1.095435764520602, "learning_rate": 4.752413298066724e-05, "loss": 0.6901, "num_tokens": 108008099.0, "step": 18110 }, { "epoch": 0.19326171145701088, "grad_norm": 0.9415313601563449, "learning_rate": 4.752232263462197e-05, "loss": 0.5291, "num_tokens": 108032848.0, "step": 18115 }, { "epoch": 0.19331505446320932, "grad_norm": 1.171176334618982, "learning_rate": 4.752051166552316e-05, "loss": 0.6263, "num_tokens": 108060829.0, "step": 18120 }, { "epoch": 0.1933683974694078, "grad_norm": 1.4251881045954888, "learning_rate": 4.751870007342714e-05, "loss": 0.6663, "num_tokens": 108091300.0, "step": 18125 }, { "epoch": 0.19342174047560623, "grad_norm": 0.9354530783889347, "learning_rate": 4.75168878583903e-05, "loss": 0.5849, "num_tokens": 108122261.0, "step": 18130 }, { "epoch": 0.1934750834818047, "grad_norm": 1.6152273672170698, "learning_rate": 4.7515075020469026e-05, "loss": 0.6397, "num_tokens": 108146081.0, "step": 18135 }, { "epoch": 0.19352842648800317, "grad_norm": 0.9403290124134903, "learning_rate": 4.751326155971973e-05, "loss": 0.7609, "num_tokens": 108186819.0, "step": 18140 }, { "epoch": 0.1935817694942016, "grad_norm": 1.2014845213860366, "learning_rate": 4.751144747619884e-05, "loss": 0.5953, "num_tokens": 108218228.0, "step": 18145 }, { "epoch": 0.19363511250040008, "grad_norm": 1.2279026125347863, "learning_rate": 4.7509632769962806e-05, "loss": 0.5798, "num_tokens": 108241602.0, "step": 18150 }, { "epoch": 0.19368845550659852, "grad_norm": 1.1552531289032504, "learning_rate": 4.750781744106811e-05, "loss": 0.7326, "num_tokens": 108288760.0, "step": 18155 }, { "epoch": 0.193741798512797, "grad_norm": 1.07610908717667, "learning_rate": 4.7506001489571225e-05, "loss": 0.8011, "num_tokens": 108323134.0, "step": 18160 }, { "epoch": 0.19379514151899543, "grad_norm": 1.0830197195301117, "learning_rate": 4.750418491552867e-05, "loss": 0.613, "num_tokens": 108356467.0, "step": 18165 }, { "epoch": 0.1938484845251939, "grad_norm": 0.8729960949531851, "learning_rate": 4.750236771899696e-05, "loss": 0.6145, "num_tokens": 108380956.0, "step": 18170 }, { "epoch": 0.19390182753139235, "grad_norm": 1.607982731089456, "learning_rate": 4.750054990003267e-05, "loss": 0.4903, "num_tokens": 108397437.0, "step": 18175 }, { "epoch": 0.19395517053759082, "grad_norm": 0.8191971843626165, "learning_rate": 4.749873145869234e-05, "loss": 0.5622, "num_tokens": 108434089.0, "step": 18180 }, { "epoch": 0.19400851354378928, "grad_norm": 0.8362501804612571, "learning_rate": 4.7496912395032574e-05, "loss": 0.7005, "num_tokens": 108476407.0, "step": 18185 }, { "epoch": 0.19406185654998773, "grad_norm": 1.9400568330787769, "learning_rate": 4.749509270910996e-05, "loss": 0.5618, "num_tokens": 108491631.0, "step": 18190 }, { "epoch": 0.1941151995561862, "grad_norm": 0.787027463109186, "learning_rate": 4.749327240098113e-05, "loss": 0.5869, "num_tokens": 108524492.0, "step": 18195 }, { "epoch": 0.19416854256238464, "grad_norm": 1.339127302132651, "learning_rate": 4.749145147070274e-05, "loss": 0.4857, "num_tokens": 108542516.0, "step": 18200 }, { "epoch": 0.1942218855685831, "grad_norm": 1.0623443150300096, "learning_rate": 4.748962991833144e-05, "loss": 0.6252, "num_tokens": 108583575.0, "step": 18205 }, { "epoch": 0.19427522857478155, "grad_norm": 1.0906963832109398, "learning_rate": 4.7487807743923907e-05, "loss": 0.4473, "num_tokens": 108619454.0, "step": 18210 }, { "epoch": 0.19432857158098002, "grad_norm": 1.0353714581996971, "learning_rate": 4.7485984947536864e-05, "loss": 0.555, "num_tokens": 108638361.0, "step": 18215 }, { "epoch": 0.19438191458717846, "grad_norm": 1.4672111350427668, "learning_rate": 4.748416152922702e-05, "loss": 0.6463, "num_tokens": 108678529.0, "step": 18220 }, { "epoch": 0.19443525759337693, "grad_norm": 0.8591588622461276, "learning_rate": 4.748233748905112e-05, "loss": 0.5486, "num_tokens": 108707036.0, "step": 18225 }, { "epoch": 0.1944886005995754, "grad_norm": 0.9668886722652076, "learning_rate": 4.7480512827065914e-05, "loss": 0.6689, "num_tokens": 108740054.0, "step": 18230 }, { "epoch": 0.19454194360577384, "grad_norm": 0.8972245776362042, "learning_rate": 4.74786875433282e-05, "loss": 0.6334, "num_tokens": 108774928.0, "step": 18235 }, { "epoch": 0.1945952866119723, "grad_norm": 0.9619888477697731, "learning_rate": 4.747686163789476e-05, "loss": 0.5856, "num_tokens": 108801293.0, "step": 18240 }, { "epoch": 0.19464862961817075, "grad_norm": 1.0865729875726402, "learning_rate": 4.747503511082242e-05, "loss": 0.6138, "num_tokens": 108836884.0, "step": 18245 }, { "epoch": 0.19470197262436922, "grad_norm": 0.7833741550304593, "learning_rate": 4.747320796216802e-05, "loss": 0.5429, "num_tokens": 108878228.0, "step": 18250 }, { "epoch": 0.19475531563056767, "grad_norm": 1.456365980795839, "learning_rate": 4.747138019198841e-05, "loss": 0.6872, "num_tokens": 108921087.0, "step": 18255 }, { "epoch": 0.19480865863676614, "grad_norm": 2.8140551370517004, "learning_rate": 4.7469551800340476e-05, "loss": 0.8696, "num_tokens": 108951119.0, "step": 18260 }, { "epoch": 0.19486200164296458, "grad_norm": 0.8959596137913539, "learning_rate": 4.74677227872811e-05, "loss": 0.7319, "num_tokens": 108982121.0, "step": 18265 }, { "epoch": 0.19491534464916305, "grad_norm": 0.8190637847007899, "learning_rate": 4.746589315286722e-05, "loss": 0.7942, "num_tokens": 109030605.0, "step": 18270 }, { "epoch": 0.19496868765536152, "grad_norm": 2.347745775012658, "learning_rate": 4.746406289715575e-05, "loss": 0.6572, "num_tokens": 109061287.0, "step": 18275 }, { "epoch": 0.19502203066155996, "grad_norm": 0.9438458075795592, "learning_rate": 4.746223202020364e-05, "loss": 0.5111, "num_tokens": 109090438.0, "step": 18280 }, { "epoch": 0.19507537366775843, "grad_norm": 1.2729447336351605, "learning_rate": 4.746040052206789e-05, "loss": 0.608, "num_tokens": 109127018.0, "step": 18285 }, { "epoch": 0.19512871667395687, "grad_norm": 0.8747369767874201, "learning_rate": 4.745856840280547e-05, "loss": 0.5823, "num_tokens": 109160062.0, "step": 18290 }, { "epoch": 0.19518205968015534, "grad_norm": 1.2321656698031247, "learning_rate": 4.745673566247339e-05, "loss": 0.5823, "num_tokens": 109191398.0, "step": 18295 }, { "epoch": 0.19523540268635378, "grad_norm": 1.0184852014952797, "learning_rate": 4.7454902301128694e-05, "loss": 0.5924, "num_tokens": 109212882.0, "step": 18300 }, { "epoch": 0.19528874569255225, "grad_norm": 0.8060836344815622, "learning_rate": 4.7453068318828426e-05, "loss": 0.6898, "num_tokens": 109251507.0, "step": 18305 }, { "epoch": 0.1953420886987507, "grad_norm": 1.10541094292367, "learning_rate": 4.7451233715629664e-05, "loss": 0.5224, "num_tokens": 109281035.0, "step": 18310 }, { "epoch": 0.19539543170494916, "grad_norm": 1.954485078074469, "learning_rate": 4.744939849158948e-05, "loss": 0.6092, "num_tokens": 109318201.0, "step": 18315 }, { "epoch": 0.19544877471114763, "grad_norm": 0.8358358214711012, "learning_rate": 4.7447562646764996e-05, "loss": 0.4818, "num_tokens": 109338588.0, "step": 18320 }, { "epoch": 0.19550211771734607, "grad_norm": 1.8964269786962642, "learning_rate": 4.744572618121334e-05, "loss": 0.5997, "num_tokens": 109356891.0, "step": 18325 }, { "epoch": 0.19555546072354454, "grad_norm": 0.9077714896745238, "learning_rate": 4.744388909499164e-05, "loss": 0.6284, "num_tokens": 109401122.0, "step": 18330 }, { "epoch": 0.19560880372974299, "grad_norm": 2.1745687174125, "learning_rate": 4.744205138815708e-05, "loss": 0.5564, "num_tokens": 109423577.0, "step": 18335 }, { "epoch": 0.19566214673594146, "grad_norm": 1.3301787914940701, "learning_rate": 4.744021306076686e-05, "loss": 0.5819, "num_tokens": 109465538.0, "step": 18340 }, { "epoch": 0.1957154897421399, "grad_norm": 0.7678443293300447, "learning_rate": 4.743837411287815e-05, "loss": 0.9632, "num_tokens": 109499490.0, "step": 18345 }, { "epoch": 0.19576883274833837, "grad_norm": 0.7037482377029334, "learning_rate": 4.7436534544548204e-05, "loss": 0.7761, "num_tokens": 109536592.0, "step": 18350 }, { "epoch": 0.1958221757545368, "grad_norm": 0.784962185974152, "learning_rate": 4.743469435583425e-05, "loss": 0.5811, "num_tokens": 109568425.0, "step": 18355 }, { "epoch": 0.19587551876073528, "grad_norm": 1.3783387782700207, "learning_rate": 4.7432853546793557e-05, "loss": 0.6244, "num_tokens": 109598621.0, "step": 18360 }, { "epoch": 0.19592886176693375, "grad_norm": 1.331519325466402, "learning_rate": 4.7431012117483395e-05, "loss": 0.6197, "num_tokens": 109618460.0, "step": 18365 }, { "epoch": 0.1959822047731322, "grad_norm": 0.7131095294395754, "learning_rate": 4.7429170067961087e-05, "loss": 0.6799, "num_tokens": 109668243.0, "step": 18370 }, { "epoch": 0.19603554777933066, "grad_norm": 1.542666624393138, "learning_rate": 4.742732739828394e-05, "loss": 0.4789, "num_tokens": 109684850.0, "step": 18375 }, { "epoch": 0.1960888907855291, "grad_norm": 1.141806824296919, "learning_rate": 4.742548410850929e-05, "loss": 0.7906, "num_tokens": 109711467.0, "step": 18380 }, { "epoch": 0.19614223379172757, "grad_norm": 1.6356032821872124, "learning_rate": 4.742364019869451e-05, "loss": 0.5071, "num_tokens": 109738724.0, "step": 18385 }, { "epoch": 0.196195576797926, "grad_norm": 0.8314926334809767, "learning_rate": 4.7421795668896965e-05, "loss": 0.6241, "num_tokens": 109765367.0, "step": 18390 }, { "epoch": 0.19624891980412448, "grad_norm": 1.4922288925126526, "learning_rate": 4.7419950519174066e-05, "loss": 0.624, "num_tokens": 109781806.0, "step": 18395 }, { "epoch": 0.19630226281032293, "grad_norm": 0.9467946648358735, "learning_rate": 4.741810474958322e-05, "loss": 0.6191, "num_tokens": 109827180.0, "step": 18400 }, { "epoch": 0.1963556058165214, "grad_norm": 1.1652187910365543, "learning_rate": 4.741625836018187e-05, "loss": 0.6002, "num_tokens": 109867637.0, "step": 18405 }, { "epoch": 0.19640894882271986, "grad_norm": 2.4594467769294748, "learning_rate": 4.741441135102746e-05, "loss": 0.6213, "num_tokens": 109896504.0, "step": 18410 }, { "epoch": 0.1964622918289183, "grad_norm": 1.0385208518433249, "learning_rate": 4.7412563722177485e-05, "loss": 0.5891, "num_tokens": 109927629.0, "step": 18415 }, { "epoch": 0.19651563483511678, "grad_norm": 2.623179182528881, "learning_rate": 4.7410715473689424e-05, "loss": 0.5993, "num_tokens": 109949953.0, "step": 18420 }, { "epoch": 0.19656897784131522, "grad_norm": 1.0135484081815218, "learning_rate": 4.740886660562079e-05, "loss": 0.6531, "num_tokens": 109982607.0, "step": 18425 }, { "epoch": 0.1966223208475137, "grad_norm": 1.2843371008226496, "learning_rate": 4.7407017118029123e-05, "loss": 0.6608, "num_tokens": 110011250.0, "step": 18430 }, { "epoch": 0.19667566385371213, "grad_norm": 1.5152416824705537, "learning_rate": 4.740516701097198e-05, "loss": 0.6851, "num_tokens": 110037784.0, "step": 18435 }, { "epoch": 0.1967290068599106, "grad_norm": 0.9913320922899688, "learning_rate": 4.7403316284506926e-05, "loss": 0.6977, "num_tokens": 110077311.0, "step": 18440 }, { "epoch": 0.19678234986610904, "grad_norm": 1.6718232819589467, "learning_rate": 4.7401464938691546e-05, "loss": 0.5825, "num_tokens": 110103187.0, "step": 18445 }, { "epoch": 0.1968356928723075, "grad_norm": 0.9111771236532549, "learning_rate": 4.739961297358346e-05, "loss": 0.4832, "num_tokens": 110136451.0, "step": 18450 }, { "epoch": 0.19688903587850598, "grad_norm": 0.9806610993603893, "learning_rate": 4.739776038924029e-05, "loss": 0.7073, "num_tokens": 110171499.0, "step": 18455 }, { "epoch": 0.19694237888470442, "grad_norm": 0.7620164783175132, "learning_rate": 4.739590718571969e-05, "loss": 0.6275, "num_tokens": 110199866.0, "step": 18460 }, { "epoch": 0.1969957218909029, "grad_norm": 1.32474112627283, "learning_rate": 4.739405336307933e-05, "loss": 0.7292, "num_tokens": 110232231.0, "step": 18465 }, { "epoch": 0.19704906489710133, "grad_norm": 0.7635855446253264, "learning_rate": 4.7392198921376885e-05, "loss": 0.5692, "num_tokens": 110264931.0, "step": 18470 }, { "epoch": 0.1971024079032998, "grad_norm": 1.2826561063693025, "learning_rate": 4.739034386067007e-05, "loss": 0.559, "num_tokens": 110283124.0, "step": 18475 }, { "epoch": 0.19715575090949825, "grad_norm": 1.0001982337803814, "learning_rate": 4.7388488181016615e-05, "loss": 0.6767, "num_tokens": 110322879.0, "step": 18480 }, { "epoch": 0.19720909391569671, "grad_norm": 1.0290134031138096, "learning_rate": 4.738663188247426e-05, "loss": 0.645, "num_tokens": 110353364.0, "step": 18485 }, { "epoch": 0.19726243692189516, "grad_norm": 1.1915804915467743, "learning_rate": 4.7384774965100764e-05, "loss": 0.5111, "num_tokens": 110369065.0, "step": 18490 }, { "epoch": 0.19731577992809363, "grad_norm": 0.8559170137483019, "learning_rate": 4.738291742895391e-05, "loss": 0.6026, "num_tokens": 110400938.0, "step": 18495 }, { "epoch": 0.1973691229342921, "grad_norm": 1.734799980553177, "learning_rate": 4.738105927409153e-05, "loss": 0.5879, "num_tokens": 110430479.0, "step": 18500 }, { "epoch": 0.19742246594049054, "grad_norm": 1.87828411320488, "learning_rate": 4.7379200500571395e-05, "loss": 0.6727, "num_tokens": 110465924.0, "step": 18505 }, { "epoch": 0.197475808946689, "grad_norm": 1.3457293334075089, "learning_rate": 4.737734110845139e-05, "loss": 0.7188, "num_tokens": 110518446.0, "step": 18510 }, { "epoch": 0.19752915195288745, "grad_norm": 2.1605448594834273, "learning_rate": 4.737548109778935e-05, "loss": 0.6619, "num_tokens": 110541528.0, "step": 18515 }, { "epoch": 0.19758249495908592, "grad_norm": 1.556448684325652, "learning_rate": 4.737362046864317e-05, "loss": 0.5593, "num_tokens": 110574841.0, "step": 18520 }, { "epoch": 0.19763583796528436, "grad_norm": 0.9873002474895932, "learning_rate": 4.737175922107074e-05, "loss": 0.6101, "num_tokens": 110611947.0, "step": 18525 }, { "epoch": 0.19768918097148283, "grad_norm": 1.1353051475881812, "learning_rate": 4.736989735512998e-05, "loss": 0.5567, "num_tokens": 110640408.0, "step": 18530 }, { "epoch": 0.19774252397768127, "grad_norm": 1.367229515603704, "learning_rate": 4.736803487087883e-05, "loss": 0.5122, "num_tokens": 110679034.0, "step": 18535 }, { "epoch": 0.19779586698387974, "grad_norm": 0.9021830400662276, "learning_rate": 4.7366171768375246e-05, "loss": 0.5732, "num_tokens": 110714640.0, "step": 18540 }, { "epoch": 0.1978492099900782, "grad_norm": 1.9199779203179663, "learning_rate": 4.7364308047677206e-05, "loss": 0.7113, "num_tokens": 110746606.0, "step": 18545 }, { "epoch": 0.19790255299627665, "grad_norm": 0.9972960630340233, "learning_rate": 4.73624437088427e-05, "loss": 0.6263, "num_tokens": 110776006.0, "step": 18550 }, { "epoch": 0.19795589600247512, "grad_norm": 1.2979439703526807, "learning_rate": 4.7360578751929736e-05, "loss": 0.6615, "num_tokens": 110812856.0, "step": 18555 }, { "epoch": 0.19800923900867357, "grad_norm": 1.0877353378229186, "learning_rate": 4.7358713176996364e-05, "loss": 0.6124, "num_tokens": 110840758.0, "step": 18560 }, { "epoch": 0.19806258201487204, "grad_norm": 1.2802503316377105, "learning_rate": 4.7356846984100625e-05, "loss": 0.6114, "num_tokens": 110862093.0, "step": 18565 }, { "epoch": 0.19811592502107048, "grad_norm": 1.2904608395014272, "learning_rate": 4.73549801733006e-05, "loss": 0.6671, "num_tokens": 110882793.0, "step": 18570 }, { "epoch": 0.19816926802726895, "grad_norm": 1.1358120942377592, "learning_rate": 4.735311274465437e-05, "loss": 0.7387, "num_tokens": 110920590.0, "step": 18575 }, { "epoch": 0.1982226110334674, "grad_norm": 1.5022890255264303, "learning_rate": 4.735124469822005e-05, "loss": 0.5808, "num_tokens": 110942661.0, "step": 18580 }, { "epoch": 0.19827595403966586, "grad_norm": 0.824961668178158, "learning_rate": 4.734937603405578e-05, "loss": 0.5652, "num_tokens": 110980089.0, "step": 18585 }, { "epoch": 0.19832929704586433, "grad_norm": 0.9266817560662634, "learning_rate": 4.734750675221968e-05, "loss": 0.5939, "num_tokens": 110998867.0, "step": 18590 }, { "epoch": 0.19838264005206277, "grad_norm": 2.4687438267727737, "learning_rate": 4.734563685276995e-05, "loss": 0.6373, "num_tokens": 111036072.0, "step": 18595 }, { "epoch": 0.19843598305826124, "grad_norm": 3.907027670887855, "learning_rate": 4.7343766335764774e-05, "loss": 0.6002, "num_tokens": 111057241.0, "step": 18600 }, { "epoch": 0.19848932606445968, "grad_norm": 1.0248771476614507, "learning_rate": 4.7341895201262334e-05, "loss": 0.5191, "num_tokens": 111076931.0, "step": 18605 }, { "epoch": 0.19854266907065815, "grad_norm": 1.5273270792210878, "learning_rate": 4.7340023449320885e-05, "loss": 0.5932, "num_tokens": 111093543.0, "step": 18610 }, { "epoch": 0.1985960120768566, "grad_norm": 1.5227557499852173, "learning_rate": 4.7338151079998656e-05, "loss": 0.5862, "num_tokens": 111115719.0, "step": 18615 }, { "epoch": 0.19864935508305506, "grad_norm": 0.9871758936716248, "learning_rate": 4.733627809335391e-05, "loss": 0.6967, "num_tokens": 111149663.0, "step": 18620 }, { "epoch": 0.1987026980892535, "grad_norm": 1.1487554508590005, "learning_rate": 4.7334404489444934e-05, "loss": 0.5814, "num_tokens": 111176933.0, "step": 18625 }, { "epoch": 0.19875604109545197, "grad_norm": 0.8596419816585817, "learning_rate": 4.733253026833003e-05, "loss": 0.6119, "num_tokens": 111202465.0, "step": 18630 }, { "epoch": 0.19880938410165044, "grad_norm": 1.7782964039028912, "learning_rate": 4.7330655430067536e-05, "loss": 0.5372, "num_tokens": 111222197.0, "step": 18635 }, { "epoch": 0.19886272710784889, "grad_norm": 0.8439602791907616, "learning_rate": 4.732877997471576e-05, "loss": 0.575, "num_tokens": 111252708.0, "step": 18640 }, { "epoch": 0.19891607011404736, "grad_norm": 1.3734681146377905, "learning_rate": 4.732690390233309e-05, "loss": 0.6484, "num_tokens": 111282094.0, "step": 18645 }, { "epoch": 0.1989694131202458, "grad_norm": 1.658372185211423, "learning_rate": 4.7325027212977895e-05, "loss": 0.6837, "num_tokens": 111323073.0, "step": 18650 }, { "epoch": 0.19902275612644427, "grad_norm": 1.399236811479631, "learning_rate": 4.732314990670857e-05, "loss": 0.4355, "num_tokens": 111342851.0, "step": 18655 }, { "epoch": 0.1990760991326427, "grad_norm": 1.1034581482979375, "learning_rate": 4.732127198358354e-05, "loss": 0.6167, "num_tokens": 111377684.0, "step": 18660 }, { "epoch": 0.19912944213884118, "grad_norm": 1.4461001587350568, "learning_rate": 4.731939344366125e-05, "loss": 0.6627, "num_tokens": 111422808.0, "step": 18665 }, { "epoch": 0.19918278514503962, "grad_norm": 1.6945399646254877, "learning_rate": 4.731751428700013e-05, "loss": 0.6915, "num_tokens": 111445577.0, "step": 18670 }, { "epoch": 0.1992361281512381, "grad_norm": 0.9064734561384853, "learning_rate": 4.731563451365869e-05, "loss": 0.6762, "num_tokens": 111471179.0, "step": 18675 }, { "epoch": 0.19928947115743656, "grad_norm": 1.0904898143611554, "learning_rate": 4.7313754123695394e-05, "loss": 0.7403, "num_tokens": 111510601.0, "step": 18680 }, { "epoch": 0.199342814163635, "grad_norm": 1.1938498049322053, "learning_rate": 4.731187311716876e-05, "loss": 0.6733, "num_tokens": 111547955.0, "step": 18685 }, { "epoch": 0.19939615716983347, "grad_norm": 1.082525594774172, "learning_rate": 4.7309991494137346e-05, "loss": 0.7132, "num_tokens": 111575190.0, "step": 18690 }, { "epoch": 0.1994495001760319, "grad_norm": 1.6725903105709818, "learning_rate": 4.730810925465968e-05, "loss": 0.6575, "num_tokens": 111590296.0, "step": 18695 }, { "epoch": 0.19950284318223038, "grad_norm": 1.9460755647005983, "learning_rate": 4.730622639879434e-05, "loss": 0.8136, "num_tokens": 111634069.0, "step": 18700 }, { "epoch": 0.19955618618842882, "grad_norm": 1.3232691151556297, "learning_rate": 4.730434292659992e-05, "loss": 0.5619, "num_tokens": 111657193.0, "step": 18705 }, { "epoch": 0.1996095291946273, "grad_norm": 0.9354403342835372, "learning_rate": 4.730245883813503e-05, "loss": 0.6121, "num_tokens": 111691089.0, "step": 18710 }, { "epoch": 0.19966287220082574, "grad_norm": 1.8538779830281333, "learning_rate": 4.7300574133458296e-05, "loss": 0.6154, "num_tokens": 111736672.0, "step": 18715 }, { "epoch": 0.1997162152070242, "grad_norm": 1.574195093939577, "learning_rate": 4.729868881262836e-05, "loss": 0.7065, "num_tokens": 111770152.0, "step": 18720 }, { "epoch": 0.19976955821322268, "grad_norm": 1.0975643996789581, "learning_rate": 4.7296802875703904e-05, "loss": 0.6767, "num_tokens": 111813912.0, "step": 18725 }, { "epoch": 0.19982290121942112, "grad_norm": 0.7098773950478708, "learning_rate": 4.72949163227436e-05, "loss": 0.5589, "num_tokens": 111851715.0, "step": 18730 }, { "epoch": 0.1998762442256196, "grad_norm": 1.0628838366179616, "learning_rate": 4.729302915380616e-05, "loss": 0.5652, "num_tokens": 111875089.0, "step": 18735 }, { "epoch": 0.19992958723181803, "grad_norm": 1.1460941428283937, "learning_rate": 4.729114136895031e-05, "loss": 0.5843, "num_tokens": 111906583.0, "step": 18740 }, { "epoch": 0.1999829302380165, "grad_norm": 1.3750841364839819, "learning_rate": 4.72892529682348e-05, "loss": 0.4705, "num_tokens": 111933330.0, "step": 18745 }, { "epoch": 0.20003627324421494, "grad_norm": 0.8852349127665451, "learning_rate": 4.7287363951718375e-05, "loss": 0.5391, "num_tokens": 111959787.0, "step": 18750 }, { "epoch": 0.2000896162504134, "grad_norm": 1.7382517480554462, "learning_rate": 4.7285474319459833e-05, "loss": 0.6223, "num_tokens": 111980501.0, "step": 18755 }, { "epoch": 0.20014295925661185, "grad_norm": 1.5768238237733458, "learning_rate": 4.7283584071517965e-05, "loss": 0.5933, "num_tokens": 112003473.0, "step": 18760 }, { "epoch": 0.20019630226281032, "grad_norm": 1.036355001378014, "learning_rate": 4.72816932079516e-05, "loss": 0.5826, "num_tokens": 112026941.0, "step": 18765 }, { "epoch": 0.2002496452690088, "grad_norm": 0.7573188335677249, "learning_rate": 4.727980172881958e-05, "loss": 0.5111, "num_tokens": 112050823.0, "step": 18770 }, { "epoch": 0.20030298827520723, "grad_norm": 1.845985568692883, "learning_rate": 4.7277909634180765e-05, "loss": 0.653, "num_tokens": 112075985.0, "step": 18775 }, { "epoch": 0.2003563312814057, "grad_norm": 1.2336064536071059, "learning_rate": 4.7276016924094016e-05, "loss": 0.6603, "num_tokens": 112107473.0, "step": 18780 }, { "epoch": 0.20040967428760414, "grad_norm": 1.2635915681102134, "learning_rate": 4.7274123598618246e-05, "loss": 0.7374, "num_tokens": 112131004.0, "step": 18785 }, { "epoch": 0.20046301729380261, "grad_norm": 2.234036037027082, "learning_rate": 4.7272229657812364e-05, "loss": 0.5992, "num_tokens": 112144186.0, "step": 18790 }, { "epoch": 0.20051636030000106, "grad_norm": 1.2720334859238702, "learning_rate": 4.7270335101735314e-05, "loss": 0.6615, "num_tokens": 112183873.0, "step": 18795 }, { "epoch": 0.20056970330619953, "grad_norm": 0.7796866157382177, "learning_rate": 4.726843993044604e-05, "loss": 0.6456, "num_tokens": 112222217.0, "step": 18800 }, { "epoch": 0.20062304631239797, "grad_norm": 1.0788486851639416, "learning_rate": 4.726654414400352e-05, "loss": 0.6536, "num_tokens": 112263165.0, "step": 18805 }, { "epoch": 0.20067638931859644, "grad_norm": 1.8988976875679748, "learning_rate": 4.726464774246675e-05, "loss": 0.6225, "num_tokens": 112283710.0, "step": 18810 }, { "epoch": 0.2007297323247949, "grad_norm": 1.739683120868242, "learning_rate": 4.726275072589474e-05, "loss": 0.687, "num_tokens": 112308132.0, "step": 18815 }, { "epoch": 0.20078307533099335, "grad_norm": 1.1057069203304, "learning_rate": 4.7260853094346526e-05, "loss": 0.5837, "num_tokens": 112346422.0, "step": 18820 }, { "epoch": 0.20083641833719182, "grad_norm": 1.1417769850910569, "learning_rate": 4.725895484788115e-05, "loss": 0.5899, "num_tokens": 112367236.0, "step": 18825 }, { "epoch": 0.20088976134339026, "grad_norm": 1.0924318751388382, "learning_rate": 4.725705598655768e-05, "loss": 0.6335, "num_tokens": 112401430.0, "step": 18830 }, { "epoch": 0.20094310434958873, "grad_norm": 0.7119852714075691, "learning_rate": 4.7255156510435214e-05, "loss": 0.5762, "num_tokens": 112441164.0, "step": 18835 }, { "epoch": 0.20099644735578717, "grad_norm": 1.584195003892567, "learning_rate": 4.7253256419572854e-05, "loss": 0.7002, "num_tokens": 112475184.0, "step": 18840 }, { "epoch": 0.20104979036198564, "grad_norm": 1.9132220296356448, "learning_rate": 4.725135571402973e-05, "loss": 0.6261, "num_tokens": 112488246.0, "step": 18845 }, { "epoch": 0.20110313336818408, "grad_norm": 1.075976641748805, "learning_rate": 4.724945439386499e-05, "loss": 0.551, "num_tokens": 112513355.0, "step": 18850 }, { "epoch": 0.20115647637438255, "grad_norm": 1.6471758757893162, "learning_rate": 4.724755245913779e-05, "loss": 0.7137, "num_tokens": 112537720.0, "step": 18855 }, { "epoch": 0.20120981938058102, "grad_norm": 0.6812263619331596, "learning_rate": 4.7245649909907316e-05, "loss": 0.5545, "num_tokens": 112577204.0, "step": 18860 }, { "epoch": 0.20126316238677947, "grad_norm": 1.2082452402273198, "learning_rate": 4.724374674623279e-05, "loss": 0.7528, "num_tokens": 112615187.0, "step": 18865 }, { "epoch": 0.20131650539297793, "grad_norm": 1.6418479668880361, "learning_rate": 4.7241842968173404e-05, "loss": 0.6228, "num_tokens": 112656886.0, "step": 18870 }, { "epoch": 0.20136984839917638, "grad_norm": 1.0237274765119628, "learning_rate": 4.7239938575788426e-05, "loss": 0.5371, "num_tokens": 112688063.0, "step": 18875 }, { "epoch": 0.20142319140537485, "grad_norm": 1.9677790460807556, "learning_rate": 4.7238033569137105e-05, "loss": 0.6723, "num_tokens": 112713541.0, "step": 18880 }, { "epoch": 0.2014765344115733, "grad_norm": 0.8992553339805175, "learning_rate": 4.723612794827872e-05, "loss": 0.7818, "num_tokens": 112761825.0, "step": 18885 }, { "epoch": 0.20152987741777176, "grad_norm": 1.6961698618880146, "learning_rate": 4.723422171327258e-05, "loss": 0.8156, "num_tokens": 112787143.0, "step": 18890 }, { "epoch": 0.2015832204239702, "grad_norm": 1.2818224439118766, "learning_rate": 4.723231486417799e-05, "loss": 0.5578, "num_tokens": 112810833.0, "step": 18895 }, { "epoch": 0.20163656343016867, "grad_norm": 1.4956272897144098, "learning_rate": 4.723040740105429e-05, "loss": 0.6557, "num_tokens": 112834000.0, "step": 18900 }, { "epoch": 0.20168990643636714, "grad_norm": 1.4773228933247105, "learning_rate": 4.722849932396084e-05, "loss": 0.6079, "num_tokens": 112864450.0, "step": 18905 }, { "epoch": 0.20174324944256558, "grad_norm": 1.4684521521474503, "learning_rate": 4.722659063295702e-05, "loss": 0.6409, "num_tokens": 112897781.0, "step": 18910 }, { "epoch": 0.20179659244876405, "grad_norm": 1.3370413219818131, "learning_rate": 4.7224681328102214e-05, "loss": 0.5573, "num_tokens": 112929816.0, "step": 18915 }, { "epoch": 0.2018499354549625, "grad_norm": 1.400178784829268, "learning_rate": 4.722277140945584e-05, "loss": 0.562, "num_tokens": 112952271.0, "step": 18920 }, { "epoch": 0.20190327846116096, "grad_norm": 2.891249524201655, "learning_rate": 4.722086087707733e-05, "loss": 0.7192, "num_tokens": 112966626.0, "step": 18925 }, { "epoch": 0.2019566214673594, "grad_norm": 1.066860079044089, "learning_rate": 4.7218949731026144e-05, "loss": 0.6635, "num_tokens": 113006815.0, "step": 18930 }, { "epoch": 0.20200996447355787, "grad_norm": 2.1493750765804296, "learning_rate": 4.7217037971361744e-05, "loss": 0.9006, "num_tokens": 113033432.0, "step": 18935 }, { "epoch": 0.20206330747975632, "grad_norm": 1.544700192060694, "learning_rate": 4.721512559814362e-05, "loss": 0.6696, "num_tokens": 113049863.0, "step": 18940 }, { "epoch": 0.20211665048595479, "grad_norm": 1.791710725254653, "learning_rate": 4.721321261143129e-05, "loss": 0.6591, "num_tokens": 113087954.0, "step": 18945 }, { "epoch": 0.20216999349215325, "grad_norm": 1.035791897227936, "learning_rate": 4.721129901128427e-05, "loss": 0.5784, "num_tokens": 113121451.0, "step": 18950 }, { "epoch": 0.2022233364983517, "grad_norm": 1.4514938625723728, "learning_rate": 4.720938479776211e-05, "loss": 0.6274, "num_tokens": 113139743.0, "step": 18955 }, { "epoch": 0.20227667950455017, "grad_norm": 1.8310556887404854, "learning_rate": 4.7207469970924384e-05, "loss": 0.5411, "num_tokens": 113170346.0, "step": 18960 }, { "epoch": 0.2023300225107486, "grad_norm": 1.223360485283699, "learning_rate": 4.720555453083067e-05, "loss": 0.7231, "num_tokens": 113207625.0, "step": 18965 }, { "epoch": 0.20238336551694708, "grad_norm": 0.7488675121678199, "learning_rate": 4.7203638477540574e-05, "loss": 0.7704, "num_tokens": 113230839.0, "step": 18970 }, { "epoch": 0.20243670852314552, "grad_norm": 2.38953950423059, "learning_rate": 4.720172181111373e-05, "loss": 0.6503, "num_tokens": 113277200.0, "step": 18975 }, { "epoch": 0.202490051529344, "grad_norm": 1.3294264469284367, "learning_rate": 4.719980453160976e-05, "loss": 0.7105, "num_tokens": 113303072.0, "step": 18980 }, { "epoch": 0.20254339453554243, "grad_norm": 0.8986739425209276, "learning_rate": 4.719788663908834e-05, "loss": 0.5877, "num_tokens": 113339012.0, "step": 18985 }, { "epoch": 0.2025967375417409, "grad_norm": 1.7172730929881874, "learning_rate": 4.719596813360916e-05, "loss": 0.5544, "num_tokens": 113352489.0, "step": 18990 }, { "epoch": 0.20265008054793937, "grad_norm": 1.2832386350572103, "learning_rate": 4.71940490152319e-05, "loss": 0.5863, "num_tokens": 113379909.0, "step": 18995 }, { "epoch": 0.2027034235541378, "grad_norm": 1.2778760488710499, "learning_rate": 4.7192129284016284e-05, "loss": 0.6586, "num_tokens": 113405833.0, "step": 19000 }, { "epoch": 0.20275676656033628, "grad_norm": 1.723229040950798, "learning_rate": 4.719020894002205e-05, "loss": 0.5049, "num_tokens": 113423671.0, "step": 19005 }, { "epoch": 0.20281010956653472, "grad_norm": 1.0417512469485413, "learning_rate": 4.7188287983308976e-05, "loss": 0.6103, "num_tokens": 113467121.0, "step": 19010 }, { "epoch": 0.2028634525727332, "grad_norm": 1.2525297261771522, "learning_rate": 4.718636641393681e-05, "loss": 0.5049, "num_tokens": 113500707.0, "step": 19015 }, { "epoch": 0.20291679557893164, "grad_norm": 1.3566621979141387, "learning_rate": 4.7184444231965355e-05, "loss": 0.506, "num_tokens": 113528860.0, "step": 19020 }, { "epoch": 0.2029701385851301, "grad_norm": 1.3513208835815789, "learning_rate": 4.718252143745443e-05, "loss": 0.6674, "num_tokens": 113548564.0, "step": 19025 }, { "epoch": 0.20302348159132855, "grad_norm": 1.041244702136392, "learning_rate": 4.7180598030463873e-05, "loss": 0.5504, "num_tokens": 113572759.0, "step": 19030 }, { "epoch": 0.20307682459752702, "grad_norm": 0.882258551227459, "learning_rate": 4.717867401105352e-05, "loss": 0.4875, "num_tokens": 113597352.0, "step": 19035 }, { "epoch": 0.2031301676037255, "grad_norm": 1.3818164335372976, "learning_rate": 4.717674937928327e-05, "loss": 0.6326, "num_tokens": 113630310.0, "step": 19040 }, { "epoch": 0.20318351060992393, "grad_norm": 0.8711232734667126, "learning_rate": 4.7174824135212974e-05, "loss": 0.5746, "num_tokens": 113662579.0, "step": 19045 }, { "epoch": 0.2032368536161224, "grad_norm": 1.3474240544490255, "learning_rate": 4.7172898278902584e-05, "loss": 0.5923, "num_tokens": 113695394.0, "step": 19050 }, { "epoch": 0.20329019662232084, "grad_norm": 1.3918281590630055, "learning_rate": 4.717097181041199e-05, "loss": 0.8833, "num_tokens": 113736485.0, "step": 19055 }, { "epoch": 0.2033435396285193, "grad_norm": 4.328464486975034, "learning_rate": 4.716904472980118e-05, "loss": 0.8384, "num_tokens": 113754304.0, "step": 19060 }, { "epoch": 0.20339688263471775, "grad_norm": 0.7898513802820133, "learning_rate": 4.7167117037130087e-05, "loss": 0.5453, "num_tokens": 113791237.0, "step": 19065 }, { "epoch": 0.20345022564091622, "grad_norm": 0.8090572929478862, "learning_rate": 4.7165188732458704e-05, "loss": 0.7463, "num_tokens": 113823795.0, "step": 19070 }, { "epoch": 0.20350356864711466, "grad_norm": 1.2336170756174243, "learning_rate": 4.716325981584705e-05, "loss": 0.5227, "num_tokens": 113843838.0, "step": 19075 }, { "epoch": 0.20355691165331313, "grad_norm": 1.1843002763078847, "learning_rate": 4.7161330287355135e-05, "loss": 0.5447, "num_tokens": 113880040.0, "step": 19080 }, { "epoch": 0.2036102546595116, "grad_norm": 1.5083794770202905, "learning_rate": 4.715940014704302e-05, "loss": 0.5376, "num_tokens": 113901255.0, "step": 19085 }, { "epoch": 0.20366359766571004, "grad_norm": 0.9593828824255399, "learning_rate": 4.715746939497073e-05, "loss": 0.6986, "num_tokens": 113940466.0, "step": 19090 }, { "epoch": 0.20371694067190851, "grad_norm": 1.039881587972177, "learning_rate": 4.7155538031198395e-05, "loss": 0.5542, "num_tokens": 113964150.0, "step": 19095 }, { "epoch": 0.20377028367810696, "grad_norm": 1.712013060241162, "learning_rate": 4.715360605578607e-05, "loss": 0.6029, "num_tokens": 113987535.0, "step": 19100 }, { "epoch": 0.20382362668430543, "grad_norm": 0.8992780755477223, "learning_rate": 4.7151673468793906e-05, "loss": 0.6608, "num_tokens": 114028949.0, "step": 19105 }, { "epoch": 0.20387696969050387, "grad_norm": 1.0085706488232764, "learning_rate": 4.714974027028203e-05, "loss": 0.582, "num_tokens": 114053584.0, "step": 19110 }, { "epoch": 0.20393031269670234, "grad_norm": 1.1287055527638754, "learning_rate": 4.7147806460310595e-05, "loss": 0.5961, "num_tokens": 114079654.0, "step": 19115 }, { "epoch": 0.20398365570290078, "grad_norm": 1.9523886355628854, "learning_rate": 4.714587203893978e-05, "loss": 0.6112, "num_tokens": 114094065.0, "step": 19120 }, { "epoch": 0.20403699870909925, "grad_norm": 1.2085518241346593, "learning_rate": 4.714393700622978e-05, "loss": 0.5952, "num_tokens": 114124023.0, "step": 19125 }, { "epoch": 0.20409034171529772, "grad_norm": 1.0483605192887349, "learning_rate": 4.714200136224081e-05, "loss": 0.6387, "num_tokens": 114171084.0, "step": 19130 }, { "epoch": 0.20414368472149616, "grad_norm": 1.4704401904762294, "learning_rate": 4.7140065107033106e-05, "loss": 0.5307, "num_tokens": 114194137.0, "step": 19135 }, { "epoch": 0.20419702772769463, "grad_norm": 1.1246884366405205, "learning_rate": 4.713812824066692e-05, "loss": 0.5903, "num_tokens": 114222448.0, "step": 19140 }, { "epoch": 0.20425037073389307, "grad_norm": 1.4152991693865202, "learning_rate": 4.713619076320252e-05, "loss": 0.47, "num_tokens": 114238038.0, "step": 19145 }, { "epoch": 0.20430371374009154, "grad_norm": 1.1853641631520524, "learning_rate": 4.7134252674700193e-05, "loss": 0.69, "num_tokens": 114264130.0, "step": 19150 }, { "epoch": 0.20435705674628998, "grad_norm": 1.025720685161634, "learning_rate": 4.713231397522025e-05, "loss": 0.742, "num_tokens": 114300179.0, "step": 19155 }, { "epoch": 0.20441039975248845, "grad_norm": 1.8565078278067624, "learning_rate": 4.713037466482303e-05, "loss": 0.6332, "num_tokens": 114316116.0, "step": 19160 }, { "epoch": 0.2044637427586869, "grad_norm": 1.6080136613745972, "learning_rate": 4.712843474356887e-05, "loss": 0.6073, "num_tokens": 114338978.0, "step": 19165 }, { "epoch": 0.20451708576488536, "grad_norm": 0.8238607554096822, "learning_rate": 4.712649421151814e-05, "loss": 0.5526, "num_tokens": 114374147.0, "step": 19170 }, { "epoch": 0.20457042877108383, "grad_norm": 0.9698939733066522, "learning_rate": 4.712455306873122e-05, "loss": 0.7095, "num_tokens": 114393096.0, "step": 19175 }, { "epoch": 0.20462377177728228, "grad_norm": 0.9707885422335318, "learning_rate": 4.7122611315268514e-05, "loss": 0.6539, "num_tokens": 114419112.0, "step": 19180 }, { "epoch": 0.20467711478348075, "grad_norm": 1.3793763645688308, "learning_rate": 4.712066895119046e-05, "loss": 0.5602, "num_tokens": 114436360.0, "step": 19185 }, { "epoch": 0.2047304577896792, "grad_norm": 1.1945553283671384, "learning_rate": 4.7118725976557494e-05, "loss": 0.6581, "num_tokens": 114469680.0, "step": 19190 }, { "epoch": 0.20478380079587766, "grad_norm": 1.9461997501178843, "learning_rate": 4.7116782391430066e-05, "loss": 0.6347, "num_tokens": 114492123.0, "step": 19195 }, { "epoch": 0.2048371438020761, "grad_norm": 0.9321448992469056, "learning_rate": 4.711483819586867e-05, "loss": 0.657, "num_tokens": 114521504.0, "step": 19200 }, { "epoch": 0.20489048680827457, "grad_norm": 1.194547695849538, "learning_rate": 4.711289338993379e-05, "loss": 0.6069, "num_tokens": 114554041.0, "step": 19205 }, { "epoch": 0.204943829814473, "grad_norm": 1.0258678123370497, "learning_rate": 4.7110947973685954e-05, "loss": 0.679, "num_tokens": 114595451.0, "step": 19210 }, { "epoch": 0.20499717282067148, "grad_norm": 1.2041304398528836, "learning_rate": 4.71090019471857e-05, "loss": 0.5942, "num_tokens": 114624357.0, "step": 19215 }, { "epoch": 0.20505051582686995, "grad_norm": 1.993765202682559, "learning_rate": 4.710705531049359e-05, "loss": 0.5248, "num_tokens": 114645454.0, "step": 19220 }, { "epoch": 0.2051038588330684, "grad_norm": 1.1838465739991935, "learning_rate": 4.7105108063670185e-05, "loss": 0.6337, "num_tokens": 114672060.0, "step": 19225 }, { "epoch": 0.20515720183926686, "grad_norm": 0.9330673992210538, "learning_rate": 4.7103160206776095e-05, "loss": 0.7138, "num_tokens": 114706575.0, "step": 19230 }, { "epoch": 0.2052105448454653, "grad_norm": 0.9576332839599592, "learning_rate": 4.710121173987192e-05, "loss": 0.6127, "num_tokens": 114748584.0, "step": 19235 }, { "epoch": 0.20526388785166377, "grad_norm": 1.053502243102912, "learning_rate": 4.709926266301829e-05, "loss": 0.6549, "num_tokens": 114768068.0, "step": 19240 }, { "epoch": 0.20531723085786222, "grad_norm": 1.1355591589606848, "learning_rate": 4.7097312976275884e-05, "loss": 0.7809, "num_tokens": 114819087.0, "step": 19245 }, { "epoch": 0.20537057386406068, "grad_norm": 0.707879928698777, "learning_rate": 4.709536267970534e-05, "loss": 0.6124, "num_tokens": 114859068.0, "step": 19250 }, { "epoch": 0.20542391687025913, "grad_norm": 1.84494313995304, "learning_rate": 4.7093411773367355e-05, "loss": 0.6674, "num_tokens": 114880520.0, "step": 19255 }, { "epoch": 0.2054772598764576, "grad_norm": 0.8912407801089541, "learning_rate": 4.709146025732266e-05, "loss": 0.6886, "num_tokens": 114920990.0, "step": 19260 }, { "epoch": 0.20553060288265607, "grad_norm": 0.9466898173684464, "learning_rate": 4.708950813163194e-05, "loss": 0.6034, "num_tokens": 114940689.0, "step": 19265 }, { "epoch": 0.2055839458888545, "grad_norm": 0.987936351875028, "learning_rate": 4.708755539635598e-05, "loss": 0.6472, "num_tokens": 114979752.0, "step": 19270 }, { "epoch": 0.20563728889505298, "grad_norm": 0.9808673222299452, "learning_rate": 4.708560205155553e-05, "loss": 0.5504, "num_tokens": 115006367.0, "step": 19275 }, { "epoch": 0.20569063190125142, "grad_norm": 1.5745798787162064, "learning_rate": 4.7083648097291365e-05, "loss": 0.5946, "num_tokens": 115031593.0, "step": 19280 }, { "epoch": 0.2057439749074499, "grad_norm": 2.5034425376860208, "learning_rate": 4.708169353362431e-05, "loss": 0.7084, "num_tokens": 115060361.0, "step": 19285 }, { "epoch": 0.20579731791364833, "grad_norm": 1.4075807176485264, "learning_rate": 4.707973836061516e-05, "loss": 0.6211, "num_tokens": 115080854.0, "step": 19290 }, { "epoch": 0.2058506609198468, "grad_norm": 1.6240429313598708, "learning_rate": 4.707778257832478e-05, "loss": 0.4652, "num_tokens": 115104132.0, "step": 19295 }, { "epoch": 0.20590400392604524, "grad_norm": 1.3994909950250554, "learning_rate": 4.7075826186814016e-05, "loss": 0.647, "num_tokens": 115131813.0, "step": 19300 }, { "epoch": 0.2059573469322437, "grad_norm": 0.9449893111786838, "learning_rate": 4.707386918614375e-05, "loss": 0.5684, "num_tokens": 115160830.0, "step": 19305 }, { "epoch": 0.20601068993844218, "grad_norm": 1.276800084325171, "learning_rate": 4.707191157637488e-05, "loss": 0.5574, "num_tokens": 115184702.0, "step": 19310 }, { "epoch": 0.20606403294464062, "grad_norm": 1.0764201883029516, "learning_rate": 4.7069953357568324e-05, "loss": 0.7329, "num_tokens": 115211300.0, "step": 19315 }, { "epoch": 0.2061173759508391, "grad_norm": 1.803153821209444, "learning_rate": 4.7067994529785025e-05, "loss": 0.6747, "num_tokens": 115231688.0, "step": 19320 }, { "epoch": 0.20617071895703754, "grad_norm": 1.1644139140998084, "learning_rate": 4.706603509308593e-05, "loss": 0.5664, "num_tokens": 115271168.0, "step": 19325 }, { "epoch": 0.206224061963236, "grad_norm": 0.9692876794987879, "learning_rate": 4.7064075047532e-05, "loss": 0.5396, "num_tokens": 115302873.0, "step": 19330 }, { "epoch": 0.20627740496943445, "grad_norm": 1.1739798033414854, "learning_rate": 4.706211439318424e-05, "loss": 0.6188, "num_tokens": 115338237.0, "step": 19335 }, { "epoch": 0.20633074797563292, "grad_norm": 2.282154861593651, "learning_rate": 4.7060153130103676e-05, "loss": 0.5662, "num_tokens": 115363363.0, "step": 19340 }, { "epoch": 0.20638409098183136, "grad_norm": 0.9686938187050532, "learning_rate": 4.705819125835132e-05, "loss": 0.5281, "num_tokens": 115389313.0, "step": 19345 }, { "epoch": 0.20643743398802983, "grad_norm": 1.0854963522740508, "learning_rate": 4.7056228777988224e-05, "loss": 0.4378, "num_tokens": 115404966.0, "step": 19350 }, { "epoch": 0.2064907769942283, "grad_norm": 1.0057157808341877, "learning_rate": 4.705426568907546e-05, "loss": 0.6933, "num_tokens": 115446876.0, "step": 19355 }, { "epoch": 0.20654412000042674, "grad_norm": 1.002102050887582, "learning_rate": 4.705230199167411e-05, "loss": 0.5334, "num_tokens": 115461966.0, "step": 19360 }, { "epoch": 0.2065974630066252, "grad_norm": 0.8484664043078342, "learning_rate": 4.705033768584528e-05, "loss": 0.5243, "num_tokens": 115485718.0, "step": 19365 }, { "epoch": 0.20665080601282365, "grad_norm": 0.8913054143569044, "learning_rate": 4.70483727716501e-05, "loss": 0.61, "num_tokens": 115528256.0, "step": 19370 }, { "epoch": 0.20670414901902212, "grad_norm": 0.9373111921630906, "learning_rate": 4.704640724914972e-05, "loss": 0.4983, "num_tokens": 115545285.0, "step": 19375 }, { "epoch": 0.20675749202522056, "grad_norm": 1.6915869006553486, "learning_rate": 4.70444411184053e-05, "loss": 0.6336, "num_tokens": 115560801.0, "step": 19380 }, { "epoch": 0.20681083503141903, "grad_norm": 1.528100936564977, "learning_rate": 4.7042474379478e-05, "loss": 0.5773, "num_tokens": 115579444.0, "step": 19385 }, { "epoch": 0.20686417803761747, "grad_norm": 0.9606997571241095, "learning_rate": 4.7040507032429046e-05, "loss": 0.6407, "num_tokens": 115625242.0, "step": 19390 }, { "epoch": 0.20691752104381594, "grad_norm": 0.8989789608463316, "learning_rate": 4.7038539077319655e-05, "loss": 0.58, "num_tokens": 115661487.0, "step": 19395 }, { "epoch": 0.2069708640500144, "grad_norm": 0.9380058509160646, "learning_rate": 4.7036570514211064e-05, "loss": 0.5428, "num_tokens": 115688390.0, "step": 19400 }, { "epoch": 0.20702420705621286, "grad_norm": 1.2877883456832693, "learning_rate": 4.703460134316452e-05, "loss": 0.5856, "num_tokens": 115709141.0, "step": 19405 }, { "epoch": 0.20707755006241133, "grad_norm": 1.4035533738974741, "learning_rate": 4.7032631564241314e-05, "loss": 0.6714, "num_tokens": 115738165.0, "step": 19410 }, { "epoch": 0.20713089306860977, "grad_norm": 1.7170401984888506, "learning_rate": 4.703066117750273e-05, "loss": 0.4908, "num_tokens": 115769677.0, "step": 19415 }, { "epoch": 0.20718423607480824, "grad_norm": 1.3039754472361709, "learning_rate": 4.7028690183010086e-05, "loss": 0.6003, "num_tokens": 115815870.0, "step": 19420 }, { "epoch": 0.20723757908100668, "grad_norm": 1.0055813801713986, "learning_rate": 4.702671858082472e-05, "loss": 0.6161, "num_tokens": 115846469.0, "step": 19425 }, { "epoch": 0.20729092208720515, "grad_norm": 1.3376075546279262, "learning_rate": 4.7024746371007976e-05, "loss": 0.5433, "num_tokens": 115871557.0, "step": 19430 }, { "epoch": 0.2073442650934036, "grad_norm": 1.0334020666912171, "learning_rate": 4.7022773553621235e-05, "loss": 0.5271, "num_tokens": 115900708.0, "step": 19435 }, { "epoch": 0.20739760809960206, "grad_norm": 1.9023570471218965, "learning_rate": 4.702080012872588e-05, "loss": 0.6447, "num_tokens": 115935889.0, "step": 19440 }, { "epoch": 0.20745095110580053, "grad_norm": 1.1073590733395922, "learning_rate": 4.7018826096383326e-05, "loss": 0.6992, "num_tokens": 115976838.0, "step": 19445 }, { "epoch": 0.20750429411199897, "grad_norm": 0.9656784763282481, "learning_rate": 4.701685145665499e-05, "loss": 0.6002, "num_tokens": 116003478.0, "step": 19450 }, { "epoch": 0.20755763711819744, "grad_norm": 1.4063948685870886, "learning_rate": 4.701487620960233e-05, "loss": 0.6558, "num_tokens": 116040422.0, "step": 19455 }, { "epoch": 0.20761098012439588, "grad_norm": 1.1261377177309464, "learning_rate": 4.701290035528681e-05, "loss": 0.7194, "num_tokens": 116073077.0, "step": 19460 }, { "epoch": 0.20766432313059435, "grad_norm": 1.0238186113747776, "learning_rate": 4.701092389376991e-05, "loss": 0.5465, "num_tokens": 116104316.0, "step": 19465 }, { "epoch": 0.2077176661367928, "grad_norm": 1.238266429699892, "learning_rate": 4.7008946825113126e-05, "loss": 0.6354, "num_tokens": 116131259.0, "step": 19470 }, { "epoch": 0.20777100914299126, "grad_norm": 0.9915601731430581, "learning_rate": 4.7006969149378e-05, "loss": 0.6993, "num_tokens": 116177860.0, "step": 19475 }, { "epoch": 0.2078243521491897, "grad_norm": 1.8983264916653961, "learning_rate": 4.700499086662606e-05, "loss": 0.6526, "num_tokens": 116195721.0, "step": 19480 }, { "epoch": 0.20787769515538818, "grad_norm": 1.05004650149807, "learning_rate": 4.7003011976918864e-05, "loss": 0.4874, "num_tokens": 116223912.0, "step": 19485 }, { "epoch": 0.20793103816158665, "grad_norm": 1.1733783961071074, "learning_rate": 4.7001032480317995e-05, "loss": 0.6424, "num_tokens": 116244660.0, "step": 19490 }, { "epoch": 0.2079843811677851, "grad_norm": 1.3117454835468905, "learning_rate": 4.6999052376885064e-05, "loss": 0.5951, "num_tokens": 116269150.0, "step": 19495 }, { "epoch": 0.20803772417398356, "grad_norm": 0.7426569801540384, "learning_rate": 4.699707166668166e-05, "loss": 0.6017, "num_tokens": 116308914.0, "step": 19500 }, { "epoch": 0.208091067180182, "grad_norm": 1.013518513782376, "learning_rate": 4.699509034976944e-05, "loss": 0.5208, "num_tokens": 116334123.0, "step": 19505 }, { "epoch": 0.20814441018638047, "grad_norm": 1.3507689034343613, "learning_rate": 4.6993108426210056e-05, "loss": 0.6234, "num_tokens": 116361971.0, "step": 19510 }, { "epoch": 0.2081977531925789, "grad_norm": 1.428648228810858, "learning_rate": 4.699112589606517e-05, "loss": 0.6037, "num_tokens": 116395880.0, "step": 19515 }, { "epoch": 0.20825109619877738, "grad_norm": 0.8806105052787389, "learning_rate": 4.698914275939649e-05, "loss": 0.5422, "num_tokens": 116445027.0, "step": 19520 }, { "epoch": 0.20830443920497582, "grad_norm": 0.8463625040028148, "learning_rate": 4.6987159016265713e-05, "loss": 0.6404, "num_tokens": 116480780.0, "step": 19525 }, { "epoch": 0.2083577822111743, "grad_norm": 1.1244383825531181, "learning_rate": 4.6985174666734586e-05, "loss": 0.6573, "num_tokens": 116521121.0, "step": 19530 }, { "epoch": 0.20841112521737276, "grad_norm": 0.9856013788414799, "learning_rate": 4.6983189710864836e-05, "loss": 0.7743, "num_tokens": 116537435.0, "step": 19535 }, { "epoch": 0.2084644682235712, "grad_norm": 1.163331683065783, "learning_rate": 4.698120414871824e-05, "loss": 0.5501, "num_tokens": 116558903.0, "step": 19540 }, { "epoch": 0.20851781122976967, "grad_norm": 1.1293554221422815, "learning_rate": 4.697921798035659e-05, "loss": 0.7388, "num_tokens": 116601034.0, "step": 19545 }, { "epoch": 0.20857115423596811, "grad_norm": 0.8203409885550671, "learning_rate": 4.697723120584169e-05, "loss": 0.5298, "num_tokens": 116621551.0, "step": 19550 }, { "epoch": 0.20862449724216658, "grad_norm": 0.8805373862963289, "learning_rate": 4.697524382523536e-05, "loss": 0.5348, "num_tokens": 116653851.0, "step": 19555 }, { "epoch": 0.20867784024836503, "grad_norm": 1.2964798984389012, "learning_rate": 4.697325583859945e-05, "loss": 0.6991, "num_tokens": 116680961.0, "step": 19560 }, { "epoch": 0.2087311832545635, "grad_norm": 0.8351950926874541, "learning_rate": 4.6971267245995815e-05, "loss": 0.5162, "num_tokens": 116707754.0, "step": 19565 }, { "epoch": 0.20878452626076194, "grad_norm": 1.1446997755133637, "learning_rate": 4.696927804748634e-05, "loss": 0.5876, "num_tokens": 116725627.0, "step": 19570 }, { "epoch": 0.2088378692669604, "grad_norm": 1.7900341135137035, "learning_rate": 4.696728824313292e-05, "loss": 0.5218, "num_tokens": 116766613.0, "step": 19575 }, { "epoch": 0.20889121227315888, "grad_norm": 0.8553173169486553, "learning_rate": 4.696529783299748e-05, "loss": 0.5807, "num_tokens": 116803813.0, "step": 19580 }, { "epoch": 0.20894455527935732, "grad_norm": 1.0002752057877093, "learning_rate": 4.696330681714194e-05, "loss": 0.5548, "num_tokens": 116825596.0, "step": 19585 }, { "epoch": 0.2089978982855558, "grad_norm": 1.1702419102530246, "learning_rate": 4.6961315195628285e-05, "loss": 0.4618, "num_tokens": 116850447.0, "step": 19590 }, { "epoch": 0.20905124129175423, "grad_norm": 1.6956141725143392, "learning_rate": 4.6959322968518475e-05, "loss": 0.5444, "num_tokens": 116877545.0, "step": 19595 }, { "epoch": 0.2091045842979527, "grad_norm": 0.8876365516341409, "learning_rate": 4.695733013587451e-05, "loss": 0.6681, "num_tokens": 116916061.0, "step": 19600 }, { "epoch": 0.20915792730415114, "grad_norm": 1.2511747598345715, "learning_rate": 4.6955336697758385e-05, "loss": 0.544, "num_tokens": 116931845.0, "step": 19605 }, { "epoch": 0.2092112703103496, "grad_norm": 1.0037295322765423, "learning_rate": 4.695334265423215e-05, "loss": 0.5894, "num_tokens": 116953342.0, "step": 19610 }, { "epoch": 0.20926461331654805, "grad_norm": 1.4173272293542531, "learning_rate": 4.695134800535785e-05, "loss": 0.7314, "num_tokens": 116973799.0, "step": 19615 }, { "epoch": 0.20931795632274652, "grad_norm": 0.7437892972064654, "learning_rate": 4.6949352751197556e-05, "loss": 0.5734, "num_tokens": 117004245.0, "step": 19620 }, { "epoch": 0.209371299328945, "grad_norm": 0.8981547618599309, "learning_rate": 4.694735689181335e-05, "loss": 0.7236, "num_tokens": 117040334.0, "step": 19625 }, { "epoch": 0.20942464233514343, "grad_norm": 1.5529237717833602, "learning_rate": 4.694536042726735e-05, "loss": 0.6479, "num_tokens": 117072712.0, "step": 19630 }, { "epoch": 0.2094779853413419, "grad_norm": 0.8652990045857738, "learning_rate": 4.6943363357621675e-05, "loss": 0.8147, "num_tokens": 117097750.0, "step": 19635 }, { "epoch": 0.20953132834754035, "grad_norm": 1.121124628304534, "learning_rate": 4.694136568293846e-05, "loss": 0.5519, "num_tokens": 117136975.0, "step": 19640 }, { "epoch": 0.20958467135373882, "grad_norm": 0.877063362860595, "learning_rate": 4.693936740327989e-05, "loss": 0.5564, "num_tokens": 117161021.0, "step": 19645 }, { "epoch": 0.20963801435993726, "grad_norm": 0.6931406828881587, "learning_rate": 4.693736851870813e-05, "loss": 0.5534, "num_tokens": 117199108.0, "step": 19650 }, { "epoch": 0.20969135736613573, "grad_norm": 0.9305579805359452, "learning_rate": 4.6935369029285385e-05, "loss": 0.5798, "num_tokens": 117252366.0, "step": 19655 }, { "epoch": 0.20974470037233417, "grad_norm": 1.159446756234751, "learning_rate": 4.693336893507388e-05, "loss": 0.6114, "num_tokens": 117274411.0, "step": 19660 }, { "epoch": 0.20979804337853264, "grad_norm": 1.7700360879847847, "learning_rate": 4.6931368236135854e-05, "loss": 0.6136, "num_tokens": 117298773.0, "step": 19665 }, { "epoch": 0.2098513863847311, "grad_norm": 1.202134008035991, "learning_rate": 4.692936693253356e-05, "loss": 0.461, "num_tokens": 117316962.0, "step": 19670 }, { "epoch": 0.20990472939092955, "grad_norm": 0.7991538565470941, "learning_rate": 4.692736502432928e-05, "loss": 0.5889, "num_tokens": 117366135.0, "step": 19675 }, { "epoch": 0.20995807239712802, "grad_norm": 1.2929708964999898, "learning_rate": 4.69253625115853e-05, "loss": 0.5788, "num_tokens": 117394038.0, "step": 19680 }, { "epoch": 0.21001141540332646, "grad_norm": 1.6197074286575677, "learning_rate": 4.692335939436394e-05, "loss": 0.7198, "num_tokens": 117427542.0, "step": 19685 }, { "epoch": 0.21006475840952493, "grad_norm": 2.211839781581863, "learning_rate": 4.692135567272754e-05, "loss": 0.6239, "num_tokens": 117456372.0, "step": 19690 }, { "epoch": 0.21011810141572337, "grad_norm": 1.164797678882853, "learning_rate": 4.6919351346738435e-05, "loss": 0.8062, "num_tokens": 117488401.0, "step": 19695 }, { "epoch": 0.21017144442192184, "grad_norm": 1.2795656258781012, "learning_rate": 4.6917346416459e-05, "loss": 0.5493, "num_tokens": 117520504.0, "step": 19700 }, { "epoch": 0.21022478742812029, "grad_norm": 0.8966845290526246, "learning_rate": 4.691534088195164e-05, "loss": 0.6874, "num_tokens": 117551430.0, "step": 19705 }, { "epoch": 0.21027813043431876, "grad_norm": 1.0305516897951543, "learning_rate": 4.6913334743278746e-05, "loss": 0.748, "num_tokens": 117586810.0, "step": 19710 }, { "epoch": 0.21033147344051722, "grad_norm": 0.6890975751572789, "learning_rate": 4.6911328000502754e-05, "loss": 0.5737, "num_tokens": 117611305.0, "step": 19715 }, { "epoch": 0.21038481644671567, "grad_norm": 1.5744726762230663, "learning_rate": 4.6909320653686106e-05, "loss": 0.5104, "num_tokens": 117643983.0, "step": 19720 }, { "epoch": 0.21043815945291414, "grad_norm": 0.8776441618467948, "learning_rate": 4.690731270289127e-05, "loss": 0.5667, "num_tokens": 117686975.0, "step": 19725 }, { "epoch": 0.21049150245911258, "grad_norm": 1.4924572831513836, "learning_rate": 4.690530414818072e-05, "loss": 0.6403, "num_tokens": 117724964.0, "step": 19730 }, { "epoch": 0.21054484546531105, "grad_norm": 0.8278854863048049, "learning_rate": 4.6903294989616963e-05, "loss": 0.6774, "num_tokens": 117767734.0, "step": 19735 }, { "epoch": 0.2105981884715095, "grad_norm": 1.176760073417824, "learning_rate": 4.690128522726253e-05, "loss": 0.5807, "num_tokens": 117796921.0, "step": 19740 }, { "epoch": 0.21065153147770796, "grad_norm": 0.6812154604789425, "learning_rate": 4.689927486117995e-05, "loss": 0.5881, "num_tokens": 117826044.0, "step": 19745 }, { "epoch": 0.2107048744839064, "grad_norm": 0.6462030833683631, "learning_rate": 4.689726389143177e-05, "loss": 0.6114, "num_tokens": 117855166.0, "step": 19750 }, { "epoch": 0.21075821749010487, "grad_norm": 0.9889675564191512, "learning_rate": 4.68952523180806e-05, "loss": 0.6146, "num_tokens": 117909840.0, "step": 19755 }, { "epoch": 0.21081156049630334, "grad_norm": 2.2080849051883837, "learning_rate": 4.6893240141189004e-05, "loss": 0.7428, "num_tokens": 117958534.0, "step": 19760 }, { "epoch": 0.21086490350250178, "grad_norm": 0.9536079949029694, "learning_rate": 4.689122736081962e-05, "loss": 0.5902, "num_tokens": 117992027.0, "step": 19765 }, { "epoch": 0.21091824650870025, "grad_norm": 1.093694647546788, "learning_rate": 4.688921397703507e-05, "loss": 0.6176, "num_tokens": 118029583.0, "step": 19770 }, { "epoch": 0.2109715895148987, "grad_norm": 0.6623521177331716, "learning_rate": 4.6887199989898e-05, "loss": 0.4129, "num_tokens": 118056227.0, "step": 19775 }, { "epoch": 0.21102493252109716, "grad_norm": 1.0067828437106519, "learning_rate": 4.6885185399471094e-05, "loss": 0.5156, "num_tokens": 118099639.0, "step": 19780 }, { "epoch": 0.2110782755272956, "grad_norm": 0.8795736381739325, "learning_rate": 4.688317020581703e-05, "loss": 0.4888, "num_tokens": 118122097.0, "step": 19785 }, { "epoch": 0.21113161853349408, "grad_norm": 1.508191329899748, "learning_rate": 4.688115440899853e-05, "loss": 0.5775, "num_tokens": 118148726.0, "step": 19790 }, { "epoch": 0.21118496153969252, "grad_norm": 1.3854248938861473, "learning_rate": 4.6879138009078317e-05, "loss": 0.544, "num_tokens": 118190220.0, "step": 19795 }, { "epoch": 0.211238304545891, "grad_norm": 1.7438067775285488, "learning_rate": 4.6877121006119125e-05, "loss": 0.5989, "num_tokens": 118207887.0, "step": 19800 }, { "epoch": 0.21129164755208946, "grad_norm": 1.3116048682538224, "learning_rate": 4.687510340018374e-05, "loss": 0.5622, "num_tokens": 118240335.0, "step": 19805 }, { "epoch": 0.2113449905582879, "grad_norm": 0.9741349825310546, "learning_rate": 4.6873085191334927e-05, "loss": 0.7272, "num_tokens": 118271505.0, "step": 19810 }, { "epoch": 0.21139833356448637, "grad_norm": 1.3332779269592832, "learning_rate": 4.68710663796355e-05, "loss": 0.757, "num_tokens": 118294065.0, "step": 19815 }, { "epoch": 0.2114516765706848, "grad_norm": 0.6768919641335027, "learning_rate": 4.686904696514827e-05, "loss": 0.5312, "num_tokens": 118348646.0, "step": 19820 }, { "epoch": 0.21150501957688328, "grad_norm": 0.7212159934821611, "learning_rate": 4.6867026947936094e-05, "loss": 0.6671, "num_tokens": 118381242.0, "step": 19825 }, { "epoch": 0.21155836258308172, "grad_norm": 1.8539134386581244, "learning_rate": 4.686500632806182e-05, "loss": 0.6832, "num_tokens": 118400558.0, "step": 19830 }, { "epoch": 0.2116117055892802, "grad_norm": 1.308415806596726, "learning_rate": 4.686298510558832e-05, "loss": 0.5465, "num_tokens": 118424454.0, "step": 19835 }, { "epoch": 0.21166504859547863, "grad_norm": 1.325233318499018, "learning_rate": 4.6860963280578494e-05, "loss": 0.8155, "num_tokens": 118445759.0, "step": 19840 }, { "epoch": 0.2117183916016771, "grad_norm": 2.4783655820794777, "learning_rate": 4.685894085309526e-05, "loss": 0.6344, "num_tokens": 118482213.0, "step": 19845 }, { "epoch": 0.21177173460787557, "grad_norm": 1.2437239279251568, "learning_rate": 4.6856917823201555e-05, "loss": 0.6183, "num_tokens": 118513734.0, "step": 19850 }, { "epoch": 0.21182507761407401, "grad_norm": 1.3997260821503026, "learning_rate": 4.685489419096033e-05, "loss": 0.679, "num_tokens": 118543461.0, "step": 19855 }, { "epoch": 0.21187842062027248, "grad_norm": 1.13641464514638, "learning_rate": 4.685286995643455e-05, "loss": 0.5271, "num_tokens": 118563694.0, "step": 19860 }, { "epoch": 0.21193176362647093, "grad_norm": 1.0447540113637344, "learning_rate": 4.685084511968721e-05, "loss": 0.5363, "num_tokens": 118594589.0, "step": 19865 }, { "epoch": 0.2119851066326694, "grad_norm": 1.0942949039670888, "learning_rate": 4.684881968078133e-05, "loss": 0.6249, "num_tokens": 118630063.0, "step": 19870 }, { "epoch": 0.21203844963886784, "grad_norm": 1.3505465326732022, "learning_rate": 4.6846793639779903e-05, "loss": 0.5911, "num_tokens": 118659782.0, "step": 19875 }, { "epoch": 0.2120917926450663, "grad_norm": 0.7500183092793427, "learning_rate": 4.6844766996746e-05, "loss": 0.6464, "num_tokens": 118695002.0, "step": 19880 }, { "epoch": 0.21214513565126475, "grad_norm": 2.1504283669811315, "learning_rate": 4.68427397517427e-05, "loss": 0.5948, "num_tokens": 118723248.0, "step": 19885 }, { "epoch": 0.21219847865746322, "grad_norm": 1.1563924410469173, "learning_rate": 4.6840711904833056e-05, "loss": 0.7666, "num_tokens": 118750838.0, "step": 19890 }, { "epoch": 0.2122518216636617, "grad_norm": 0.961011766375316, "learning_rate": 4.683868345608019e-05, "loss": 0.5826, "num_tokens": 118782771.0, "step": 19895 }, { "epoch": 0.21230516466986013, "grad_norm": 1.5380494715189628, "learning_rate": 4.683665440554722e-05, "loss": 0.7991, "num_tokens": 118823421.0, "step": 19900 }, { "epoch": 0.2123585076760586, "grad_norm": 1.0012170401785887, "learning_rate": 4.683462475329728e-05, "loss": 0.6791, "num_tokens": 118859486.0, "step": 19905 }, { "epoch": 0.21241185068225704, "grad_norm": 0.8685509825226958, "learning_rate": 4.683259449939353e-05, "loss": 0.5989, "num_tokens": 118888242.0, "step": 19910 }, { "epoch": 0.2124651936884555, "grad_norm": 1.1125587837742639, "learning_rate": 4.683056364389915e-05, "loss": 0.715, "num_tokens": 118929372.0, "step": 19915 }, { "epoch": 0.21251853669465395, "grad_norm": 0.9862628226595437, "learning_rate": 4.6828532186877343e-05, "loss": 0.793, "num_tokens": 118961688.0, "step": 19920 }, { "epoch": 0.21257187970085242, "grad_norm": 1.9888735981535113, "learning_rate": 4.682650012839131e-05, "loss": 0.5676, "num_tokens": 118985681.0, "step": 19925 }, { "epoch": 0.21262522270705086, "grad_norm": 1.1298548153773948, "learning_rate": 4.6824467468504286e-05, "loss": 0.7475, "num_tokens": 119020134.0, "step": 19930 }, { "epoch": 0.21267856571324933, "grad_norm": 2.288163011563962, "learning_rate": 4.6822434207279534e-05, "loss": 0.6753, "num_tokens": 119029481.0, "step": 19935 }, { "epoch": 0.2127319087194478, "grad_norm": 1.4037225071270432, "learning_rate": 4.682040034478032e-05, "loss": 0.5955, "num_tokens": 119053536.0, "step": 19940 }, { "epoch": 0.21278525172564625, "grad_norm": 2.2153133358808406, "learning_rate": 4.681836588106993e-05, "loss": 0.5837, "num_tokens": 119079715.0, "step": 19945 }, { "epoch": 0.21283859473184472, "grad_norm": 0.9005643807398589, "learning_rate": 4.681633081621167e-05, "loss": 0.6043, "num_tokens": 119106482.0, "step": 19950 }, { "epoch": 0.21289193773804316, "grad_norm": 2.7858317165547706, "learning_rate": 4.6814295150268886e-05, "loss": 0.6758, "num_tokens": 119132560.0, "step": 19955 }, { "epoch": 0.21294528074424163, "grad_norm": 0.9014517498506317, "learning_rate": 4.68122588833049e-05, "loss": 0.6099, "num_tokens": 119154308.0, "step": 19960 }, { "epoch": 0.21299862375044007, "grad_norm": 1.0800654698002035, "learning_rate": 4.681022201538309e-05, "loss": 0.5075, "num_tokens": 119176750.0, "step": 19965 }, { "epoch": 0.21305196675663854, "grad_norm": 1.208037690409838, "learning_rate": 4.680818454656683e-05, "loss": 0.5116, "num_tokens": 119197519.0, "step": 19970 }, { "epoch": 0.21310530976283698, "grad_norm": 1.1885147440766275, "learning_rate": 4.680614647691953e-05, "loss": 0.6114, "num_tokens": 119226862.0, "step": 19975 }, { "epoch": 0.21315865276903545, "grad_norm": 1.244608503789343, "learning_rate": 4.6804107806504596e-05, "loss": 0.691, "num_tokens": 119253902.0, "step": 19980 }, { "epoch": 0.21321199577523392, "grad_norm": 3.2262465593989926, "learning_rate": 4.6802068535385493e-05, "loss": 0.6118, "num_tokens": 119270509.0, "step": 19985 }, { "epoch": 0.21326533878143236, "grad_norm": 1.5777495675159563, "learning_rate": 4.6800028663625665e-05, "loss": 0.6894, "num_tokens": 119289288.0, "step": 19990 }, { "epoch": 0.21331868178763083, "grad_norm": 0.8506034647668753, "learning_rate": 4.679798819128859e-05, "loss": 0.5281, "num_tokens": 119328807.0, "step": 19995 }, { "epoch": 0.21337202479382927, "grad_norm": 0.9946203478226657, "learning_rate": 4.679594711843775e-05, "loss": 0.6512, "num_tokens": 119348615.0, "step": 20000 }, { "epoch": 0.21342536780002774, "grad_norm": 1.129061840894325, "learning_rate": 4.679390544513668e-05, "loss": 0.6184, "num_tokens": 119373168.0, "step": 20005 }, { "epoch": 0.21347871080622619, "grad_norm": 0.9056799099688059, "learning_rate": 4.67918631714489e-05, "loss": 0.4717, "num_tokens": 119398408.0, "step": 20010 }, { "epoch": 0.21353205381242465, "grad_norm": 1.5450067401575942, "learning_rate": 4.678982029743796e-05, "loss": 0.6829, "num_tokens": 119431449.0, "step": 20015 }, { "epoch": 0.2135853968186231, "grad_norm": 1.379305988348597, "learning_rate": 4.678777682316744e-05, "loss": 0.6145, "num_tokens": 119448490.0, "step": 20020 }, { "epoch": 0.21363873982482157, "grad_norm": 0.7539022482919078, "learning_rate": 4.678573274870093e-05, "loss": 0.5131, "num_tokens": 119485687.0, "step": 20025 }, { "epoch": 0.21369208283102004, "grad_norm": 1.1502271306627423, "learning_rate": 4.6783688074102025e-05, "loss": 0.568, "num_tokens": 119505176.0, "step": 20030 }, { "epoch": 0.21374542583721848, "grad_norm": 1.1092508166435737, "learning_rate": 4.678164279943436e-05, "loss": 0.684, "num_tokens": 119521093.0, "step": 20035 }, { "epoch": 0.21379876884341695, "grad_norm": 0.8469493711505637, "learning_rate": 4.6779596924761574e-05, "loss": 0.674, "num_tokens": 119557323.0, "step": 20040 }, { "epoch": 0.2138521118496154, "grad_norm": 1.793670604092797, "learning_rate": 4.6777550450147326e-05, "loss": 0.5397, "num_tokens": 119593668.0, "step": 20045 }, { "epoch": 0.21390545485581386, "grad_norm": 0.8685716744820209, "learning_rate": 4.677550337565531e-05, "loss": 0.6626, "num_tokens": 119628439.0, "step": 20050 }, { "epoch": 0.2139587978620123, "grad_norm": 1.2590722920300828, "learning_rate": 4.677345570134922e-05, "loss": 0.5516, "num_tokens": 119657578.0, "step": 20055 }, { "epoch": 0.21401214086821077, "grad_norm": 1.4336984682791527, "learning_rate": 4.677140742729279e-05, "loss": 0.6539, "num_tokens": 119690562.0, "step": 20060 }, { "epoch": 0.2140654838744092, "grad_norm": 0.9447399343136426, "learning_rate": 4.676935855354973e-05, "loss": 0.5192, "num_tokens": 119720913.0, "step": 20065 }, { "epoch": 0.21411882688060768, "grad_norm": 1.3886324388330429, "learning_rate": 4.6767309080183825e-05, "loss": 0.6039, "num_tokens": 119746788.0, "step": 20070 }, { "epoch": 0.21417216988680615, "grad_norm": 1.0544940095024185, "learning_rate": 4.676525900725882e-05, "loss": 0.5152, "num_tokens": 119765891.0, "step": 20075 }, { "epoch": 0.2142255128930046, "grad_norm": 1.0236428650762064, "learning_rate": 4.676320833483854e-05, "loss": 0.5512, "num_tokens": 119811708.0, "step": 20080 }, { "epoch": 0.21427885589920306, "grad_norm": 1.240327802186784, "learning_rate": 4.6761157062986784e-05, "loss": 0.5916, "num_tokens": 119837959.0, "step": 20085 }, { "epoch": 0.2143321989054015, "grad_norm": 1.1140703112532633, "learning_rate": 4.675910519176738e-05, "loss": 0.5747, "num_tokens": 119868825.0, "step": 20090 }, { "epoch": 0.21438554191159997, "grad_norm": 0.963078963321258, "learning_rate": 4.6757052721244186e-05, "loss": 0.588, "num_tokens": 119885578.0, "step": 20095 }, { "epoch": 0.21443888491779842, "grad_norm": 0.8078035989984717, "learning_rate": 4.6754999651481066e-05, "loss": 0.5667, "num_tokens": 119927181.0, "step": 20100 }, { "epoch": 0.2144922279239969, "grad_norm": 1.6710075312417259, "learning_rate": 4.675294598254191e-05, "loss": 0.6381, "num_tokens": 119946832.0, "step": 20105 }, { "epoch": 0.21454557093019533, "grad_norm": 1.4225264163831826, "learning_rate": 4.6750891714490616e-05, "loss": 0.6712, "num_tokens": 119978710.0, "step": 20110 }, { "epoch": 0.2145989139363938, "grad_norm": 1.6600460855231725, "learning_rate": 4.6748836847391114e-05, "loss": 0.6508, "num_tokens": 120005881.0, "step": 20115 }, { "epoch": 0.21465225694259227, "grad_norm": 1.0821657522477213, "learning_rate": 4.674678138130735e-05, "loss": 0.765, "num_tokens": 120054242.0, "step": 20120 }, { "epoch": 0.2147055999487907, "grad_norm": 1.5818057381445298, "learning_rate": 4.674472531630329e-05, "loss": 0.7771, "num_tokens": 120091667.0, "step": 20125 }, { "epoch": 0.21475894295498918, "grad_norm": 1.228285095839775, "learning_rate": 4.674266865244289e-05, "loss": 0.6327, "num_tokens": 120120598.0, "step": 20130 }, { "epoch": 0.21481228596118762, "grad_norm": 0.9292285579492847, "learning_rate": 4.6740611389790184e-05, "loss": 0.6817, "num_tokens": 120155106.0, "step": 20135 }, { "epoch": 0.2148656289673861, "grad_norm": 0.8889707025047304, "learning_rate": 4.673855352840916e-05, "loss": 0.6648, "num_tokens": 120181997.0, "step": 20140 }, { "epoch": 0.21491897197358453, "grad_norm": 1.1219116971399066, "learning_rate": 4.6736495068363875e-05, "loss": 0.6383, "num_tokens": 120219323.0, "step": 20145 }, { "epoch": 0.214972314979783, "grad_norm": 1.6636288250062972, "learning_rate": 4.673443600971838e-05, "loss": 0.6232, "num_tokens": 120250920.0, "step": 20150 }, { "epoch": 0.21502565798598144, "grad_norm": 0.8699277743169183, "learning_rate": 4.673237635253674e-05, "loss": 0.673, "num_tokens": 120287557.0, "step": 20155 }, { "epoch": 0.21507900099217991, "grad_norm": 1.6891386712264256, "learning_rate": 4.673031609688305e-05, "loss": 0.6905, "num_tokens": 120303683.0, "step": 20160 }, { "epoch": 0.21513234399837838, "grad_norm": 2.788276216455708, "learning_rate": 4.672825524282143e-05, "loss": 0.8029, "num_tokens": 120334906.0, "step": 20165 }, { "epoch": 0.21518568700457683, "grad_norm": 1.0780421973034087, "learning_rate": 4.672619379041599e-05, "loss": 0.4771, "num_tokens": 120354758.0, "step": 20170 }, { "epoch": 0.2152390300107753, "grad_norm": 54.92808965987721, "learning_rate": 4.672413173973091e-05, "loss": 1.0495, "num_tokens": 120380309.0, "step": 20175 }, { "epoch": 0.21529237301697374, "grad_norm": 1.1198367959196112, "learning_rate": 4.672206909083033e-05, "loss": 0.7105, "num_tokens": 120430095.0, "step": 20180 }, { "epoch": 0.2153457160231722, "grad_norm": 1.3576047539625085, "learning_rate": 4.672000584377843e-05, "loss": 0.6095, "num_tokens": 120481568.0, "step": 20185 }, { "epoch": 0.21539905902937065, "grad_norm": 2.448296502248484, "learning_rate": 4.6717941998639445e-05, "loss": 0.78, "num_tokens": 120523409.0, "step": 20190 }, { "epoch": 0.21545240203556912, "grad_norm": 1.2153866549978483, "learning_rate": 4.6715877555477574e-05, "loss": 0.5052, "num_tokens": 120539490.0, "step": 20195 }, { "epoch": 0.21550574504176756, "grad_norm": 1.3513749486184716, "learning_rate": 4.671381251435706e-05, "loss": 0.5606, "num_tokens": 120565307.0, "step": 20200 }, { "epoch": 0.21555908804796603, "grad_norm": 0.9334937606303735, "learning_rate": 4.671174687534217e-05, "loss": 0.6533, "num_tokens": 120595317.0, "step": 20205 }, { "epoch": 0.2156124310541645, "grad_norm": 0.7568644512363942, "learning_rate": 4.670968063849718e-05, "loss": 0.5757, "num_tokens": 120632173.0, "step": 20210 }, { "epoch": 0.21566577406036294, "grad_norm": 0.9311941526852321, "learning_rate": 4.670761380388638e-05, "loss": 0.6467, "num_tokens": 120675118.0, "step": 20215 }, { "epoch": 0.2157191170665614, "grad_norm": 0.9662564458779414, "learning_rate": 4.67055463715741e-05, "loss": 0.71, "num_tokens": 120700488.0, "step": 20220 }, { "epoch": 0.21577246007275985, "grad_norm": 1.126537547074179, "learning_rate": 4.670347834162467e-05, "loss": 0.6195, "num_tokens": 120729041.0, "step": 20225 }, { "epoch": 0.21582580307895832, "grad_norm": 0.8261671325512292, "learning_rate": 4.670140971410243e-05, "loss": 0.6191, "num_tokens": 120752667.0, "step": 20230 }, { "epoch": 0.21587914608515676, "grad_norm": 1.2682387315398769, "learning_rate": 4.669934048907176e-05, "loss": 0.7424, "num_tokens": 120799100.0, "step": 20235 }, { "epoch": 0.21593248909135523, "grad_norm": 1.1387046138140096, "learning_rate": 4.6697270666597056e-05, "loss": 0.5185, "num_tokens": 120824873.0, "step": 20240 }, { "epoch": 0.21598583209755368, "grad_norm": 1.1941621735130106, "learning_rate": 4.6695200246742717e-05, "loss": 0.476, "num_tokens": 120850329.0, "step": 20245 }, { "epoch": 0.21603917510375215, "grad_norm": 1.304418148977858, "learning_rate": 4.669312922957317e-05, "loss": 0.6803, "num_tokens": 120867348.0, "step": 20250 }, { "epoch": 0.21609251810995062, "grad_norm": 1.123180039638359, "learning_rate": 4.669105761515288e-05, "loss": 0.6811, "num_tokens": 120917324.0, "step": 20255 }, { "epoch": 0.21614586111614906, "grad_norm": 1.248808228410771, "learning_rate": 4.668898540354628e-05, "loss": 0.7568, "num_tokens": 120938942.0, "step": 20260 }, { "epoch": 0.21619920412234753, "grad_norm": 0.778083785500955, "learning_rate": 4.668691259481788e-05, "loss": 0.6156, "num_tokens": 120975820.0, "step": 20265 }, { "epoch": 0.21625254712854597, "grad_norm": 1.4027712134101593, "learning_rate": 4.668483918903217e-05, "loss": 0.5124, "num_tokens": 120996755.0, "step": 20270 }, { "epoch": 0.21630589013474444, "grad_norm": 0.741590516135498, "learning_rate": 4.6682765186253665e-05, "loss": 0.5536, "num_tokens": 121025884.0, "step": 20275 }, { "epoch": 0.21635923314094288, "grad_norm": 1.2436938616064168, "learning_rate": 4.668069058654692e-05, "loss": 0.5886, "num_tokens": 121052597.0, "step": 20280 }, { "epoch": 0.21641257614714135, "grad_norm": 1.1508824499109878, "learning_rate": 4.6678615389976474e-05, "loss": 0.6993, "num_tokens": 121084928.0, "step": 20285 }, { "epoch": 0.2164659191533398, "grad_norm": 0.9309207857596506, "learning_rate": 4.667653959660692e-05, "loss": 0.5489, "num_tokens": 121115244.0, "step": 20290 }, { "epoch": 0.21651926215953826, "grad_norm": 0.8777063434716578, "learning_rate": 4.667446320650283e-05, "loss": 0.6004, "num_tokens": 121150013.0, "step": 20295 }, { "epoch": 0.21657260516573673, "grad_norm": 1.189485062158964, "learning_rate": 4.667238621972884e-05, "loss": 0.6327, "num_tokens": 121187512.0, "step": 20300 }, { "epoch": 0.21662594817193517, "grad_norm": 0.8444515445061075, "learning_rate": 4.667030863634957e-05, "loss": 0.6632, "num_tokens": 121218365.0, "step": 20305 }, { "epoch": 0.21667929117813364, "grad_norm": 0.9686881524569763, "learning_rate": 4.666823045642967e-05, "loss": 0.7756, "num_tokens": 121245684.0, "step": 20310 }, { "epoch": 0.21673263418433208, "grad_norm": 0.9771618252634178, "learning_rate": 4.666615168003381e-05, "loss": 0.5223, "num_tokens": 121273962.0, "step": 20315 }, { "epoch": 0.21678597719053055, "grad_norm": 1.0171174137564987, "learning_rate": 4.6664072307226686e-05, "loss": 0.5345, "num_tokens": 121316121.0, "step": 20320 }, { "epoch": 0.216839320196729, "grad_norm": 0.9290258859610135, "learning_rate": 4.6661992338072994e-05, "loss": 0.7612, "num_tokens": 121357835.0, "step": 20325 }, { "epoch": 0.21689266320292747, "grad_norm": 1.100218134222874, "learning_rate": 4.665991177263746e-05, "loss": 0.6459, "num_tokens": 121379073.0, "step": 20330 }, { "epoch": 0.2169460062091259, "grad_norm": 0.8019257670109556, "learning_rate": 4.665783061098482e-05, "loss": 0.6421, "num_tokens": 121422024.0, "step": 20335 }, { "epoch": 0.21699934921532438, "grad_norm": 0.6329942591558279, "learning_rate": 4.665574885317985e-05, "loss": 0.5922, "num_tokens": 121469239.0, "step": 20340 }, { "epoch": 0.21705269222152285, "grad_norm": 1.1109748835236601, "learning_rate": 4.6653666499287315e-05, "loss": 0.476, "num_tokens": 121496629.0, "step": 20345 }, { "epoch": 0.2171060352277213, "grad_norm": 0.9072594730953344, "learning_rate": 4.665158354937203e-05, "loss": 0.6456, "num_tokens": 121546315.0, "step": 20350 }, { "epoch": 0.21715937823391976, "grad_norm": 1.2570966164063495, "learning_rate": 4.66495000034988e-05, "loss": 0.5767, "num_tokens": 121571281.0, "step": 20355 }, { "epoch": 0.2172127212401182, "grad_norm": 1.4679003413650145, "learning_rate": 4.664741586173246e-05, "loss": 0.6029, "num_tokens": 121588705.0, "step": 20360 }, { "epoch": 0.21726606424631667, "grad_norm": 0.8309326148823037, "learning_rate": 4.664533112413787e-05, "loss": 0.54, "num_tokens": 121640763.0, "step": 20365 }, { "epoch": 0.2173194072525151, "grad_norm": 0.7808191445360388, "learning_rate": 4.664324579077991e-05, "loss": 0.6903, "num_tokens": 121679161.0, "step": 20370 }, { "epoch": 0.21737275025871358, "grad_norm": 1.3635538797924471, "learning_rate": 4.664115986172346e-05, "loss": 0.549, "num_tokens": 121701945.0, "step": 20375 }, { "epoch": 0.21742609326491202, "grad_norm": 0.9031102212567906, "learning_rate": 4.6639073337033425e-05, "loss": 0.5108, "num_tokens": 121740252.0, "step": 20380 }, { "epoch": 0.2174794362711105, "grad_norm": 1.1020676386964439, "learning_rate": 4.663698621677474e-05, "loss": 0.549, "num_tokens": 121762170.0, "step": 20385 }, { "epoch": 0.21753277927730896, "grad_norm": 1.7774293717852105, "learning_rate": 4.6634898501012356e-05, "loss": 0.6241, "num_tokens": 121778391.0, "step": 20390 }, { "epoch": 0.2175861222835074, "grad_norm": 1.2368128357959374, "learning_rate": 4.663281018981123e-05, "loss": 0.6454, "num_tokens": 121806084.0, "step": 20395 }, { "epoch": 0.21763946528970587, "grad_norm": 1.207487153569292, "learning_rate": 4.663072128323637e-05, "loss": 0.6411, "num_tokens": 121845705.0, "step": 20400 }, { "epoch": 0.21769280829590432, "grad_norm": 3.9000208808475505, "learning_rate": 4.662863178135274e-05, "loss": 0.6654, "num_tokens": 121878054.0, "step": 20405 }, { "epoch": 0.2177461513021028, "grad_norm": 1.504583564780392, "learning_rate": 4.662654168422538e-05, "loss": 0.4778, "num_tokens": 121893145.0, "step": 20410 }, { "epoch": 0.21779949430830123, "grad_norm": 2.1944896689618596, "learning_rate": 4.662445099191934e-05, "loss": 0.5262, "num_tokens": 121915920.0, "step": 20415 }, { "epoch": 0.2178528373144997, "grad_norm": 1.2566529530768717, "learning_rate": 4.662235970449966e-05, "loss": 0.5587, "num_tokens": 121946793.0, "step": 20420 }, { "epoch": 0.21790618032069814, "grad_norm": 2.1538186228452845, "learning_rate": 4.662026782203142e-05, "loss": 0.6428, "num_tokens": 121989262.0, "step": 20425 }, { "epoch": 0.2179595233268966, "grad_norm": 0.8647825354634335, "learning_rate": 4.661817534457974e-05, "loss": 0.6028, "num_tokens": 122024631.0, "step": 20430 }, { "epoch": 0.21801286633309508, "grad_norm": 0.8465375825204665, "learning_rate": 4.661608227220969e-05, "loss": 0.66, "num_tokens": 122055441.0, "step": 20435 }, { "epoch": 0.21806620933929352, "grad_norm": 1.6282895915695887, "learning_rate": 4.6613988604986444e-05, "loss": 0.4935, "num_tokens": 122069924.0, "step": 20440 }, { "epoch": 0.218119552345492, "grad_norm": 1.1050994932941927, "learning_rate": 4.661189434297512e-05, "loss": 0.8019, "num_tokens": 122109530.0, "step": 20445 }, { "epoch": 0.21817289535169043, "grad_norm": 1.7929853255768275, "learning_rate": 4.66097994862409e-05, "loss": 0.5976, "num_tokens": 122130471.0, "step": 20450 }, { "epoch": 0.2182262383578889, "grad_norm": 0.6396047435798574, "learning_rate": 4.6607704034848984e-05, "loss": 0.5284, "num_tokens": 122170221.0, "step": 20455 }, { "epoch": 0.21827958136408734, "grad_norm": 1.8692929862561616, "learning_rate": 4.660560798886456e-05, "loss": 0.5785, "num_tokens": 122206237.0, "step": 20460 }, { "epoch": 0.2183329243702858, "grad_norm": 0.9481268103897813, "learning_rate": 4.660351134835286e-05, "loss": 0.5642, "num_tokens": 122243000.0, "step": 20465 }, { "epoch": 0.21838626737648426, "grad_norm": 2.1889152568049495, "learning_rate": 4.660141411337913e-05, "loss": 0.5533, "num_tokens": 122270168.0, "step": 20470 }, { "epoch": 0.21843961038268273, "grad_norm": 1.2871526069575476, "learning_rate": 4.6599316284008626e-05, "loss": 0.6062, "num_tokens": 122288667.0, "step": 20475 }, { "epoch": 0.2184929533888812, "grad_norm": 0.8626942732653542, "learning_rate": 4.6597217860306626e-05, "loss": 0.6655, "num_tokens": 122311693.0, "step": 20480 }, { "epoch": 0.21854629639507964, "grad_norm": 1.100806798800011, "learning_rate": 4.659511884233844e-05, "loss": 0.3836, "num_tokens": 122329010.0, "step": 20485 }, { "epoch": 0.2185996394012781, "grad_norm": 0.8971813984063253, "learning_rate": 4.659301923016937e-05, "loss": 0.54, "num_tokens": 122363132.0, "step": 20490 }, { "epoch": 0.21865298240747655, "grad_norm": 0.9003421644730555, "learning_rate": 4.6590919023864774e-05, "loss": 0.7283, "num_tokens": 122397520.0, "step": 20495 }, { "epoch": 0.21870632541367502, "grad_norm": 0.7512542966430905, "learning_rate": 4.6588818223489975e-05, "loss": 0.4988, "num_tokens": 122430987.0, "step": 20500 }, { "epoch": 0.21875966841987346, "grad_norm": 1.2597003142142955, "learning_rate": 4.658671682911037e-05, "loss": 0.6416, "num_tokens": 122448523.0, "step": 20505 }, { "epoch": 0.21881301142607193, "grad_norm": 3.180505704477363, "learning_rate": 4.6584614840791344e-05, "loss": 0.5824, "num_tokens": 122483865.0, "step": 20510 }, { "epoch": 0.21886635443227037, "grad_norm": 0.866810087042911, "learning_rate": 4.65825122585983e-05, "loss": 0.6379, "num_tokens": 122523022.0, "step": 20515 }, { "epoch": 0.21891969743846884, "grad_norm": 1.7715558858318647, "learning_rate": 4.658040908259668e-05, "loss": 0.6898, "num_tokens": 122554986.0, "step": 20520 }, { "epoch": 0.2189730404446673, "grad_norm": 0.823557693099973, "learning_rate": 4.657830531285192e-05, "loss": 0.6801, "num_tokens": 122591257.0, "step": 20525 }, { "epoch": 0.21902638345086575, "grad_norm": 1.3209555923161598, "learning_rate": 4.6576200949429476e-05, "loss": 0.6392, "num_tokens": 122620962.0, "step": 20530 }, { "epoch": 0.21907972645706422, "grad_norm": 5.000999733852443, "learning_rate": 4.657409599239485e-05, "loss": 0.7752, "num_tokens": 122646506.0, "step": 20535 }, { "epoch": 0.21913306946326266, "grad_norm": 1.1286180879363694, "learning_rate": 4.657199044181354e-05, "loss": 0.6185, "num_tokens": 122675388.0, "step": 20540 }, { "epoch": 0.21918641246946113, "grad_norm": 0.8552315436940864, "learning_rate": 4.6569884297751053e-05, "loss": 0.7361, "num_tokens": 122708199.0, "step": 20545 }, { "epoch": 0.21923975547565958, "grad_norm": 0.884745603042111, "learning_rate": 4.656777756027294e-05, "loss": 0.5063, "num_tokens": 122726971.0, "step": 20550 }, { "epoch": 0.21929309848185805, "grad_norm": 0.9297531295010805, "learning_rate": 4.6565670229444764e-05, "loss": 0.486, "num_tokens": 122760184.0, "step": 20555 }, { "epoch": 0.2193464414880565, "grad_norm": 1.1737350984701151, "learning_rate": 4.6563562305332086e-05, "loss": 0.6378, "num_tokens": 122783482.0, "step": 20560 }, { "epoch": 0.21939978449425496, "grad_norm": 1.507798226156882, "learning_rate": 4.65614537880005e-05, "loss": 0.5206, "num_tokens": 122810609.0, "step": 20565 }, { "epoch": 0.21945312750045343, "grad_norm": 0.9757852319866182, "learning_rate": 4.655934467751564e-05, "loss": 0.6948, "num_tokens": 122837451.0, "step": 20570 }, { "epoch": 0.21950647050665187, "grad_norm": 1.0995302020758249, "learning_rate": 4.655723497394311e-05, "loss": 0.6311, "num_tokens": 122873966.0, "step": 20575 }, { "epoch": 0.21955981351285034, "grad_norm": 0.7258766495415688, "learning_rate": 4.655512467734858e-05, "loss": 0.5499, "num_tokens": 122897495.0, "step": 20580 }, { "epoch": 0.21961315651904878, "grad_norm": 0.8381399889372394, "learning_rate": 4.6553013787797706e-05, "loss": 0.5701, "num_tokens": 122936708.0, "step": 20585 }, { "epoch": 0.21966649952524725, "grad_norm": 1.5759103465614972, "learning_rate": 4.6550902305356184e-05, "loss": 0.6678, "num_tokens": 122969378.0, "step": 20590 }, { "epoch": 0.2197198425314457, "grad_norm": 0.9180696139492538, "learning_rate": 4.654879023008971e-05, "loss": 0.5327, "num_tokens": 122994587.0, "step": 20595 }, { "epoch": 0.21977318553764416, "grad_norm": 1.2754241725581361, "learning_rate": 4.654667756206401e-05, "loss": 0.6376, "num_tokens": 123015753.0, "step": 20600 }, { "epoch": 0.2198265285438426, "grad_norm": 2.390676182054359, "learning_rate": 4.654456430134482e-05, "loss": 0.5813, "num_tokens": 123032198.0, "step": 20605 }, { "epoch": 0.21987987155004107, "grad_norm": 1.0547255023930258, "learning_rate": 4.654245044799792e-05, "loss": 0.7265, "num_tokens": 123066616.0, "step": 20610 }, { "epoch": 0.21993321455623954, "grad_norm": 1.7735267546455682, "learning_rate": 4.654033600208908e-05, "loss": 0.6774, "num_tokens": 123109138.0, "step": 20615 }, { "epoch": 0.21998655756243798, "grad_norm": 1.1165389042884377, "learning_rate": 4.6538220963684084e-05, "loss": 0.5997, "num_tokens": 123139260.0, "step": 20620 }, { "epoch": 0.22003990056863645, "grad_norm": 0.7879870174423473, "learning_rate": 4.653610533284876e-05, "loss": 0.5278, "num_tokens": 123172970.0, "step": 20625 }, { "epoch": 0.2200932435748349, "grad_norm": 1.4896206001839414, "learning_rate": 4.653398910964893e-05, "loss": 0.4699, "num_tokens": 123192255.0, "step": 20630 }, { "epoch": 0.22014658658103337, "grad_norm": 0.8604811764507361, "learning_rate": 4.653187229415048e-05, "loss": 0.5068, "num_tokens": 123232979.0, "step": 20635 }, { "epoch": 0.2201999295872318, "grad_norm": 1.0047472229855854, "learning_rate": 4.6529754886419245e-05, "loss": 0.7206, "num_tokens": 123256293.0, "step": 20640 }, { "epoch": 0.22025327259343028, "grad_norm": 4.573609273402783, "learning_rate": 4.652763688652111e-05, "loss": 0.8681, "num_tokens": 123283528.0, "step": 20645 }, { "epoch": 0.22030661559962872, "grad_norm": 0.8530350209285068, "learning_rate": 4.652551829452202e-05, "loss": 0.5524, "num_tokens": 123322009.0, "step": 20650 }, { "epoch": 0.2203599586058272, "grad_norm": 0.9515341208536197, "learning_rate": 4.652339911048787e-05, "loss": 0.6209, "num_tokens": 123361783.0, "step": 20655 }, { "epoch": 0.22041330161202566, "grad_norm": 1.7745730746887047, "learning_rate": 4.652127933448461e-05, "loss": 0.6436, "num_tokens": 123384121.0, "step": 20660 }, { "epoch": 0.2204666446182241, "grad_norm": 2.8880785926546104, "learning_rate": 4.6519158966578216e-05, "loss": 0.5768, "num_tokens": 123414022.0, "step": 20665 }, { "epoch": 0.22051998762442257, "grad_norm": 0.9008347169200984, "learning_rate": 4.651703800683467e-05, "loss": 0.7682, "num_tokens": 123444820.0, "step": 20670 }, { "epoch": 0.220573330630621, "grad_norm": 1.3035748884881693, "learning_rate": 4.651491645531995e-05, "loss": 0.6238, "num_tokens": 123463897.0, "step": 20675 }, { "epoch": 0.22062667363681948, "grad_norm": 1.1321590413159528, "learning_rate": 4.651279431210009e-05, "loss": 0.5834, "num_tokens": 123488241.0, "step": 20680 }, { "epoch": 0.22068001664301792, "grad_norm": 1.1837528061291722, "learning_rate": 4.6510671577241125e-05, "loss": 0.5834, "num_tokens": 123514190.0, "step": 20685 }, { "epoch": 0.2207333596492164, "grad_norm": 1.1082676154372975, "learning_rate": 4.650854825080911e-05, "loss": 0.6985, "num_tokens": 123547693.0, "step": 20690 }, { "epoch": 0.22078670265541483, "grad_norm": 1.092077181524155, "learning_rate": 4.6506424332870116e-05, "loss": 0.5953, "num_tokens": 123581687.0, "step": 20695 }, { "epoch": 0.2208400456616133, "grad_norm": 1.106391172084825, "learning_rate": 4.650429982349024e-05, "loss": 0.6222, "num_tokens": 123607076.0, "step": 20700 }, { "epoch": 0.22089338866781177, "grad_norm": 2.187059740713029, "learning_rate": 4.650217472273559e-05, "loss": 0.5906, "num_tokens": 123637694.0, "step": 20705 }, { "epoch": 0.22094673167401022, "grad_norm": 1.2921133033740635, "learning_rate": 4.65000490306723e-05, "loss": 0.6456, "num_tokens": 123667534.0, "step": 20710 }, { "epoch": 0.22100007468020869, "grad_norm": 0.8927103739423128, "learning_rate": 4.64979227473665e-05, "loss": 0.5023, "num_tokens": 123693504.0, "step": 20715 }, { "epoch": 0.22105341768640713, "grad_norm": 1.3694003850501317, "learning_rate": 4.6495795872884375e-05, "loss": 0.6656, "num_tokens": 123722090.0, "step": 20720 }, { "epoch": 0.2211067606926056, "grad_norm": 1.0680527879212924, "learning_rate": 4.64936684072921e-05, "loss": 0.5984, "num_tokens": 123747372.0, "step": 20725 }, { "epoch": 0.22116010369880404, "grad_norm": 1.099523653298087, "learning_rate": 4.649154035065587e-05, "loss": 0.6077, "num_tokens": 123775407.0, "step": 20730 }, { "epoch": 0.2212134467050025, "grad_norm": 0.6400211590696148, "learning_rate": 4.648941170304192e-05, "loss": 0.5786, "num_tokens": 123808689.0, "step": 20735 }, { "epoch": 0.22126678971120095, "grad_norm": 0.8807504093524353, "learning_rate": 4.648728246451648e-05, "loss": 0.578, "num_tokens": 123831088.0, "step": 20740 }, { "epoch": 0.22132013271739942, "grad_norm": 0.9365884603854601, "learning_rate": 4.6485152635145814e-05, "loss": 0.4854, "num_tokens": 123848834.0, "step": 20745 }, { "epoch": 0.2213734757235979, "grad_norm": 0.9229652613938939, "learning_rate": 4.6483022214996195e-05, "loss": 0.635, "num_tokens": 123880947.0, "step": 20750 }, { "epoch": 0.22142681872979633, "grad_norm": 1.46873874553865, "learning_rate": 4.6480891204133917e-05, "loss": 0.5152, "num_tokens": 123913336.0, "step": 20755 }, { "epoch": 0.2214801617359948, "grad_norm": 1.0217162456539617, "learning_rate": 4.647875960262529e-05, "loss": 0.5744, "num_tokens": 123940966.0, "step": 20760 }, { "epoch": 0.22153350474219324, "grad_norm": 0.8779955179194147, "learning_rate": 4.647662741053665e-05, "loss": 0.5772, "num_tokens": 123964509.0, "step": 20765 }, { "epoch": 0.2215868477483917, "grad_norm": 1.6484451647217138, "learning_rate": 4.6474494627934344e-05, "loss": 0.5805, "num_tokens": 124008085.0, "step": 20770 }, { "epoch": 0.22164019075459016, "grad_norm": 1.1563247745453313, "learning_rate": 4.647236125488474e-05, "loss": 0.6827, "num_tokens": 124032371.0, "step": 20775 }, { "epoch": 0.22169353376078862, "grad_norm": 0.8460403237704992, "learning_rate": 4.647022729145423e-05, "loss": 0.6575, "num_tokens": 124083261.0, "step": 20780 }, { "epoch": 0.22174687676698707, "grad_norm": 1.2723328839689116, "learning_rate": 4.64680927377092e-05, "loss": 0.6214, "num_tokens": 124118055.0, "step": 20785 }, { "epoch": 0.22180021977318554, "grad_norm": 1.0623063963883324, "learning_rate": 4.646595759371609e-05, "loss": 0.6113, "num_tokens": 124155949.0, "step": 20790 }, { "epoch": 0.221853562779384, "grad_norm": 0.926445750762492, "learning_rate": 4.6463821859541345e-05, "loss": 0.5627, "num_tokens": 124193782.0, "step": 20795 }, { "epoch": 0.22190690578558245, "grad_norm": 0.8652279065175443, "learning_rate": 4.6461685535251404e-05, "loss": 0.7507, "num_tokens": 124240526.0, "step": 20800 }, { "epoch": 0.22196024879178092, "grad_norm": 1.9231755344202845, "learning_rate": 4.645954862091276e-05, "loss": 0.7697, "num_tokens": 124271290.0, "step": 20805 }, { "epoch": 0.22201359179797936, "grad_norm": 1.2409234553841177, "learning_rate": 4.6457411116591914e-05, "loss": 0.5011, "num_tokens": 124295599.0, "step": 20810 }, { "epoch": 0.22206693480417783, "grad_norm": 1.057570742393087, "learning_rate": 4.645527302235537e-05, "loss": 0.5691, "num_tokens": 124314454.0, "step": 20815 }, { "epoch": 0.22212027781037627, "grad_norm": 1.1651960640000338, "learning_rate": 4.6453134338269665e-05, "loss": 0.5191, "num_tokens": 124338599.0, "step": 20820 }, { "epoch": 0.22217362081657474, "grad_norm": 1.1565390882986806, "learning_rate": 4.645099506440135e-05, "loss": 0.572, "num_tokens": 124370243.0, "step": 20825 }, { "epoch": 0.22222696382277318, "grad_norm": 0.9767389543271301, "learning_rate": 4.6448855200816996e-05, "loss": 0.6464, "num_tokens": 124393109.0, "step": 20830 }, { "epoch": 0.22228030682897165, "grad_norm": 0.8978799055283113, "learning_rate": 4.644671474758319e-05, "loss": 0.6286, "num_tokens": 124414994.0, "step": 20835 }, { "epoch": 0.22233364983517012, "grad_norm": 0.7929700247086433, "learning_rate": 4.644457370476654e-05, "loss": 0.6155, "num_tokens": 124454082.0, "step": 20840 }, { "epoch": 0.22238699284136856, "grad_norm": 1.14390927730633, "learning_rate": 4.6442432072433665e-05, "loss": 0.6559, "num_tokens": 124481023.0, "step": 20845 }, { "epoch": 0.22244033584756703, "grad_norm": 1.6442009971761065, "learning_rate": 4.644028985065122e-05, "loss": 0.8439, "num_tokens": 124505888.0, "step": 20850 }, { "epoch": 0.22249367885376548, "grad_norm": 1.6256744751385706, "learning_rate": 4.643814703948586e-05, "loss": 0.5794, "num_tokens": 124524756.0, "step": 20855 }, { "epoch": 0.22254702185996394, "grad_norm": 3.708181841399197, "learning_rate": 4.643600363900425e-05, "loss": 0.7682, "num_tokens": 124551810.0, "step": 20860 }, { "epoch": 0.2226003648661624, "grad_norm": 1.3776533848991361, "learning_rate": 4.6433859649273106e-05, "loss": 0.6971, "num_tokens": 124581621.0, "step": 20865 }, { "epoch": 0.22265370787236086, "grad_norm": 1.0870745905494956, "learning_rate": 4.643171507035916e-05, "loss": 0.6684, "num_tokens": 124614378.0, "step": 20870 }, { "epoch": 0.2227070508785593, "grad_norm": 0.666993529917074, "learning_rate": 4.64295699023291e-05, "loss": 0.5698, "num_tokens": 124646447.0, "step": 20875 }, { "epoch": 0.22276039388475777, "grad_norm": 1.1462493016755568, "learning_rate": 4.6427424145249726e-05, "loss": 0.6491, "num_tokens": 124670009.0, "step": 20880 }, { "epoch": 0.22281373689095624, "grad_norm": 1.334743523081026, "learning_rate": 4.642527779918779e-05, "loss": 0.4919, "num_tokens": 124693804.0, "step": 20885 }, { "epoch": 0.22286707989715468, "grad_norm": 1.1723365647567634, "learning_rate": 4.642313086421008e-05, "loss": 0.8873, "num_tokens": 124727476.0, "step": 20890 }, { "epoch": 0.22292042290335315, "grad_norm": 1.0160325033219273, "learning_rate": 4.6420983340383404e-05, "loss": 0.5007, "num_tokens": 124758230.0, "step": 20895 }, { "epoch": 0.2229737659095516, "grad_norm": 1.062620521315562, "learning_rate": 4.641883522777459e-05, "loss": 0.684, "num_tokens": 124797617.0, "step": 20900 }, { "epoch": 0.22302710891575006, "grad_norm": 0.9244874340832645, "learning_rate": 4.641668652645049e-05, "loss": 0.593, "num_tokens": 124822802.0, "step": 20905 }, { "epoch": 0.2230804519219485, "grad_norm": 0.6902155104202853, "learning_rate": 4.641453723647796e-05, "loss": 0.4836, "num_tokens": 124857335.0, "step": 20910 }, { "epoch": 0.22313379492814697, "grad_norm": 0.8080482221668995, "learning_rate": 4.641238735792389e-05, "loss": 0.5435, "num_tokens": 124881361.0, "step": 20915 }, { "epoch": 0.22318713793434541, "grad_norm": 1.0073156681464772, "learning_rate": 4.6410236890855156e-05, "loss": 0.5591, "num_tokens": 124917092.0, "step": 20920 }, { "epoch": 0.22324048094054388, "grad_norm": 1.3654576094852977, "learning_rate": 4.64080858353387e-05, "loss": 0.5974, "num_tokens": 124941612.0, "step": 20925 }, { "epoch": 0.22329382394674235, "grad_norm": 1.3861044482100915, "learning_rate": 4.6405934191441456e-05, "loss": 0.5957, "num_tokens": 124989546.0, "step": 20930 }, { "epoch": 0.2233471669529408, "grad_norm": 1.501123535804052, "learning_rate": 4.640378195923036e-05, "loss": 0.649, "num_tokens": 125014196.0, "step": 20935 }, { "epoch": 0.22340050995913927, "grad_norm": 0.9479759400651954, "learning_rate": 4.640162913877241e-05, "loss": 0.6792, "num_tokens": 125061016.0, "step": 20940 }, { "epoch": 0.2234538529653377, "grad_norm": 0.9545842978762002, "learning_rate": 4.639947573013459e-05, "loss": 0.5366, "num_tokens": 125091191.0, "step": 20945 }, { "epoch": 0.22350719597153618, "grad_norm": 1.0735577749994816, "learning_rate": 4.639732173338389e-05, "loss": 0.6501, "num_tokens": 125113973.0, "step": 20950 }, { "epoch": 0.22356053897773462, "grad_norm": 1.3942427385355312, "learning_rate": 4.639516714858736e-05, "loss": 0.5268, "num_tokens": 125131962.0, "step": 20955 }, { "epoch": 0.2236138819839331, "grad_norm": 1.1735322153840413, "learning_rate": 4.639301197581205e-05, "loss": 0.6824, "num_tokens": 125157986.0, "step": 20960 }, { "epoch": 0.22366722499013153, "grad_norm": 0.9214444990829828, "learning_rate": 4.639085621512501e-05, "loss": 0.6974, "num_tokens": 125197447.0, "step": 20965 }, { "epoch": 0.22372056799633, "grad_norm": 1.3016136585084797, "learning_rate": 4.6388699866593326e-05, "loss": 0.4868, "num_tokens": 125211884.0, "step": 20970 }, { "epoch": 0.22377391100252847, "grad_norm": 0.997352124667747, "learning_rate": 4.638654293028411e-05, "loss": 0.6582, "num_tokens": 125239752.0, "step": 20975 }, { "epoch": 0.2238272540087269, "grad_norm": 1.1183071993163565, "learning_rate": 4.638438540626446e-05, "loss": 0.6383, "num_tokens": 125256545.0, "step": 20980 }, { "epoch": 0.22388059701492538, "grad_norm": 1.2588449065122107, "learning_rate": 4.638222729460153e-05, "loss": 0.6883, "num_tokens": 125295260.0, "step": 20985 }, { "epoch": 0.22393394002112382, "grad_norm": 1.200421392541493, "learning_rate": 4.638006859536247e-05, "loss": 0.6294, "num_tokens": 125329950.0, "step": 20990 }, { "epoch": 0.2239872830273223, "grad_norm": 2.1529926730126254, "learning_rate": 4.6377909308614455e-05, "loss": 0.7178, "num_tokens": 125366789.0, "step": 20995 }, { "epoch": 0.22404062603352073, "grad_norm": 0.8665554063729869, "learning_rate": 4.637574943442468e-05, "loss": 0.6376, "num_tokens": 125388164.0, "step": 21000 }, { "epoch": 0.2240939690397192, "grad_norm": 1.932867783260216, "learning_rate": 4.6373588972860355e-05, "loss": 0.5959, "num_tokens": 125410411.0, "step": 21005 }, { "epoch": 0.22414731204591765, "grad_norm": 0.9764126205602904, "learning_rate": 4.637142792398871e-05, "loss": 0.548, "num_tokens": 125441200.0, "step": 21010 }, { "epoch": 0.22420065505211612, "grad_norm": 0.8272001196337682, "learning_rate": 4.6369266287876985e-05, "loss": 0.57, "num_tokens": 125476853.0, "step": 21015 }, { "epoch": 0.22425399805831459, "grad_norm": 1.0736467822139024, "learning_rate": 4.636710406459245e-05, "loss": 0.5187, "num_tokens": 125502977.0, "step": 21020 }, { "epoch": 0.22430734106451303, "grad_norm": 1.9202935514988595, "learning_rate": 4.636494125420241e-05, "loss": 0.5476, "num_tokens": 125515620.0, "step": 21025 }, { "epoch": 0.2243606840707115, "grad_norm": 1.1145427841271944, "learning_rate": 4.636277785677413e-05, "loss": 0.6234, "num_tokens": 125541328.0, "step": 21030 }, { "epoch": 0.22441402707690994, "grad_norm": 0.8103782139211921, "learning_rate": 4.6360613872374953e-05, "loss": 0.5831, "num_tokens": 125578395.0, "step": 21035 }, { "epoch": 0.2244673700831084, "grad_norm": 0.8687446430210126, "learning_rate": 4.635844930107221e-05, "loss": 0.4738, "num_tokens": 125609622.0, "step": 21040 }, { "epoch": 0.22452071308930685, "grad_norm": 1.0917863581258505, "learning_rate": 4.6356284142933264e-05, "loss": 0.7888, "num_tokens": 125636582.0, "step": 21045 }, { "epoch": 0.22457405609550532, "grad_norm": 1.2981971319429741, "learning_rate": 4.635411839802549e-05, "loss": 0.5979, "num_tokens": 125662083.0, "step": 21050 }, { "epoch": 0.22462739910170376, "grad_norm": 1.0833358802051414, "learning_rate": 4.635195206641628e-05, "loss": 0.6763, "num_tokens": 125699210.0, "step": 21055 }, { "epoch": 0.22468074210790223, "grad_norm": 1.019471144929348, "learning_rate": 4.634978514817304e-05, "loss": 0.5497, "num_tokens": 125729148.0, "step": 21060 }, { "epoch": 0.2247340851141007, "grad_norm": 2.190028842763689, "learning_rate": 4.634761764336321e-05, "loss": 0.574, "num_tokens": 125753620.0, "step": 21065 }, { "epoch": 0.22478742812029914, "grad_norm": 1.3866943898749762, "learning_rate": 4.6345449552054224e-05, "loss": 0.5388, "num_tokens": 125790153.0, "step": 21070 }, { "epoch": 0.2248407711264976, "grad_norm": 1.1689452798676245, "learning_rate": 4.634328087431356e-05, "loss": 0.6952, "num_tokens": 125814485.0, "step": 21075 }, { "epoch": 0.22489411413269605, "grad_norm": 1.036166407355562, "learning_rate": 4.634111161020871e-05, "loss": 0.705, "num_tokens": 125867104.0, "step": 21080 }, { "epoch": 0.22494745713889452, "grad_norm": 1.3272795275734262, "learning_rate": 4.633894175980716e-05, "loss": 0.5216, "num_tokens": 125886413.0, "step": 21085 }, { "epoch": 0.22500080014509297, "grad_norm": 0.8526826014953902, "learning_rate": 4.6336771323176436e-05, "loss": 0.6012, "num_tokens": 125910892.0, "step": 21090 }, { "epoch": 0.22505414315129144, "grad_norm": 1.0923472919492614, "learning_rate": 4.633460030038409e-05, "loss": 0.5831, "num_tokens": 125942586.0, "step": 21095 }, { "epoch": 0.22510748615748988, "grad_norm": 1.1428794887343312, "learning_rate": 4.633242869149766e-05, "loss": 0.5248, "num_tokens": 125988624.0, "step": 21100 }, { "epoch": 0.22516082916368835, "grad_norm": 1.3769554748201227, "learning_rate": 4.633025649658473e-05, "loss": 0.5165, "num_tokens": 126009971.0, "step": 21105 }, { "epoch": 0.22521417216988682, "grad_norm": 1.2367143995208356, "learning_rate": 4.632808371571291e-05, "loss": 0.6341, "num_tokens": 126037919.0, "step": 21110 }, { "epoch": 0.22526751517608526, "grad_norm": 1.476373142021521, "learning_rate": 4.632591034894979e-05, "loss": 0.5901, "num_tokens": 126064086.0, "step": 21115 }, { "epoch": 0.22532085818228373, "grad_norm": 1.0403915333716898, "learning_rate": 4.6323736396363006e-05, "loss": 0.5569, "num_tokens": 126094524.0, "step": 21120 }, { "epoch": 0.22537420118848217, "grad_norm": 1.8218640707372105, "learning_rate": 4.632156185802021e-05, "loss": 0.5424, "num_tokens": 126120467.0, "step": 21125 }, { "epoch": 0.22542754419468064, "grad_norm": 0.6830625724500728, "learning_rate": 4.631938673398908e-05, "loss": 0.5742, "num_tokens": 126170636.0, "step": 21130 }, { "epoch": 0.22548088720087908, "grad_norm": 1.0827307822046324, "learning_rate": 4.6317211024337284e-05, "loss": 0.6412, "num_tokens": 126203423.0, "step": 21135 }, { "epoch": 0.22553423020707755, "grad_norm": 1.0138203209578962, "learning_rate": 4.631503472913253e-05, "loss": 0.714, "num_tokens": 126231866.0, "step": 21140 }, { "epoch": 0.225587573213276, "grad_norm": 1.087034258161118, "learning_rate": 4.6312857848442557e-05, "loss": 0.5531, "num_tokens": 126261219.0, "step": 21145 }, { "epoch": 0.22564091621947446, "grad_norm": 1.737333988090401, "learning_rate": 4.631068038233507e-05, "loss": 0.5987, "num_tokens": 126284304.0, "step": 21150 }, { "epoch": 0.22569425922567293, "grad_norm": 1.2521013535687922, "learning_rate": 4.630850233087786e-05, "loss": 0.6842, "num_tokens": 126308782.0, "step": 21155 }, { "epoch": 0.22574760223187137, "grad_norm": 1.136971072833536, "learning_rate": 4.630632369413869e-05, "loss": 0.6718, "num_tokens": 126340476.0, "step": 21160 }, { "epoch": 0.22580094523806984, "grad_norm": 0.8956752531321313, "learning_rate": 4.630414447218536e-05, "loss": 0.5215, "num_tokens": 126360194.0, "step": 21165 }, { "epoch": 0.2258542882442683, "grad_norm": 1.2824946826265873, "learning_rate": 4.630196466508567e-05, "loss": 0.4358, "num_tokens": 126380796.0, "step": 21170 }, { "epoch": 0.22590763125046676, "grad_norm": 1.726429837753573, "learning_rate": 4.6299784272907466e-05, "loss": 0.5998, "num_tokens": 126407675.0, "step": 21175 }, { "epoch": 0.2259609742566652, "grad_norm": 0.8714057069419682, "learning_rate": 4.6297603295718586e-05, "loss": 0.7153, "num_tokens": 126443449.0, "step": 21180 }, { "epoch": 0.22601431726286367, "grad_norm": 1.3064633116145814, "learning_rate": 4.6295421733586905e-05, "loss": 0.5892, "num_tokens": 126470619.0, "step": 21185 }, { "epoch": 0.2260676602690621, "grad_norm": 0.7518344319618707, "learning_rate": 4.6293239586580303e-05, "loss": 0.6135, "num_tokens": 126520952.0, "step": 21190 }, { "epoch": 0.22612100327526058, "grad_norm": 1.012206793019175, "learning_rate": 4.62910568547667e-05, "loss": 0.477, "num_tokens": 126548806.0, "step": 21195 }, { "epoch": 0.22617434628145905, "grad_norm": 1.3125894498997246, "learning_rate": 4.628887353821399e-05, "loss": 0.5329, "num_tokens": 126581252.0, "step": 21200 }, { "epoch": 0.2262276892876575, "grad_norm": 0.9977360848041741, "learning_rate": 4.628668963699014e-05, "loss": 0.6608, "num_tokens": 126614182.0, "step": 21205 }, { "epoch": 0.22628103229385596, "grad_norm": 1.0902225347767716, "learning_rate": 4.6284505151163086e-05, "loss": 0.5542, "num_tokens": 126642573.0, "step": 21210 }, { "epoch": 0.2263343753000544, "grad_norm": 0.8486496436823258, "learning_rate": 4.628232008080083e-05, "loss": 0.561, "num_tokens": 126679931.0, "step": 21215 }, { "epoch": 0.22638771830625287, "grad_norm": 1.045902415186481, "learning_rate": 4.628013442597134e-05, "loss": 0.5944, "num_tokens": 126717581.0, "step": 21220 }, { "epoch": 0.2264410613124513, "grad_norm": 0.7889544037427464, "learning_rate": 4.6277948186742654e-05, "loss": 0.5765, "num_tokens": 126748789.0, "step": 21225 }, { "epoch": 0.22649440431864978, "grad_norm": 0.8377230402377565, "learning_rate": 4.627576136318279e-05, "loss": 0.5306, "num_tokens": 126782376.0, "step": 21230 }, { "epoch": 0.22654774732484823, "grad_norm": 3.0008236290730967, "learning_rate": 4.627357395535979e-05, "loss": 0.5149, "num_tokens": 126799251.0, "step": 21235 }, { "epoch": 0.2266010903310467, "grad_norm": 1.6548728871709453, "learning_rate": 4.627138596334174e-05, "loss": 0.5637, "num_tokens": 126831233.0, "step": 21240 }, { "epoch": 0.22665443333724516, "grad_norm": 0.7006526438046355, "learning_rate": 4.62691973871967e-05, "loss": 0.4924, "num_tokens": 126873178.0, "step": 21245 }, { "epoch": 0.2267077763434436, "grad_norm": 0.8612509456374257, "learning_rate": 4.6267008226992813e-05, "loss": 0.5599, "num_tokens": 126904622.0, "step": 21250 }, { "epoch": 0.22676111934964208, "grad_norm": 0.9574669342498614, "learning_rate": 4.626481848279817e-05, "loss": 0.6536, "num_tokens": 126926159.0, "step": 21255 }, { "epoch": 0.22681446235584052, "grad_norm": 1.4244025269179903, "learning_rate": 4.626262815468092e-05, "loss": 0.6336, "num_tokens": 126964111.0, "step": 21260 }, { "epoch": 0.226867805362039, "grad_norm": 2.2350657823892233, "learning_rate": 4.626043724270922e-05, "loss": 0.6096, "num_tokens": 126986990.0, "step": 21265 }, { "epoch": 0.22692114836823743, "grad_norm": 1.1276121710213711, "learning_rate": 4.625824574695124e-05, "loss": 0.5884, "num_tokens": 127015677.0, "step": 21270 }, { "epoch": 0.2269744913744359, "grad_norm": 0.707946772023492, "learning_rate": 4.6256053667475194e-05, "loss": 0.6067, "num_tokens": 127066308.0, "step": 21275 }, { "epoch": 0.22702783438063434, "grad_norm": 1.0768739194040042, "learning_rate": 4.625386100434928e-05, "loss": 0.6198, "num_tokens": 127102598.0, "step": 21280 }, { "epoch": 0.2270811773868328, "grad_norm": 0.7978448103378314, "learning_rate": 4.625166775764173e-05, "loss": 0.7146, "num_tokens": 127140952.0, "step": 21285 }, { "epoch": 0.22713452039303128, "grad_norm": 0.8888075284560838, "learning_rate": 4.6249473927420797e-05, "loss": 0.6461, "num_tokens": 127166682.0, "step": 21290 }, { "epoch": 0.22718786339922972, "grad_norm": 0.8955681419174792, "learning_rate": 4.624727951375475e-05, "loss": 0.6023, "num_tokens": 127203966.0, "step": 21295 }, { "epoch": 0.2272412064054282, "grad_norm": 0.81203503775799, "learning_rate": 4.624508451671188e-05, "loss": 0.5846, "num_tokens": 127237702.0, "step": 21300 }, { "epoch": 0.22729454941162663, "grad_norm": 0.8065889220020204, "learning_rate": 4.624288893636047e-05, "loss": 0.5997, "num_tokens": 127267051.0, "step": 21305 }, { "epoch": 0.2273478924178251, "grad_norm": 1.0637762076086417, "learning_rate": 4.6240692772768863e-05, "loss": 0.5569, "num_tokens": 127288654.0, "step": 21310 }, { "epoch": 0.22740123542402355, "grad_norm": 2.1264156878672966, "learning_rate": 4.623849602600539e-05, "loss": 0.5688, "num_tokens": 127316512.0, "step": 21315 }, { "epoch": 0.22745457843022202, "grad_norm": 0.8539817192541301, "learning_rate": 4.6236298696138416e-05, "loss": 0.6097, "num_tokens": 127357896.0, "step": 21320 }, { "epoch": 0.22750792143642046, "grad_norm": 0.9095243490925213, "learning_rate": 4.62341007832363e-05, "loss": 0.5924, "num_tokens": 127399781.0, "step": 21325 }, { "epoch": 0.22756126444261893, "grad_norm": 1.016465735340518, "learning_rate": 4.623190228736746e-05, "loss": 0.6046, "num_tokens": 127424554.0, "step": 21330 }, { "epoch": 0.2276146074488174, "grad_norm": 1.4058653609860174, "learning_rate": 4.622970320860029e-05, "loss": 0.5855, "num_tokens": 127454762.0, "step": 21335 }, { "epoch": 0.22766795045501584, "grad_norm": 1.2798187112814623, "learning_rate": 4.622750354700323e-05, "loss": 0.6279, "num_tokens": 127474521.0, "step": 21340 }, { "epoch": 0.2277212934612143, "grad_norm": 1.3119398586269397, "learning_rate": 4.622530330264473e-05, "loss": 0.7103, "num_tokens": 127509046.0, "step": 21345 }, { "epoch": 0.22777463646741275, "grad_norm": 0.8537534770479903, "learning_rate": 4.622310247559325e-05, "loss": 0.48, "num_tokens": 127528311.0, "step": 21350 }, { "epoch": 0.22782797947361122, "grad_norm": 1.0924653284863042, "learning_rate": 4.6220901065917276e-05, "loss": 0.6156, "num_tokens": 127568634.0, "step": 21355 }, { "epoch": 0.22788132247980966, "grad_norm": 1.259590751630727, "learning_rate": 4.621869907368532e-05, "loss": 0.5961, "num_tokens": 127590732.0, "step": 21360 }, { "epoch": 0.22793466548600813, "grad_norm": 0.8327181665939218, "learning_rate": 4.62164964989659e-05, "loss": 0.5377, "num_tokens": 127633866.0, "step": 21365 }, { "epoch": 0.22798800849220657, "grad_norm": 0.9055388789499791, "learning_rate": 4.6214293341827556e-05, "loss": 0.6224, "num_tokens": 127663246.0, "step": 21370 }, { "epoch": 0.22804135149840504, "grad_norm": 1.262679812165348, "learning_rate": 4.621208960233884e-05, "loss": 0.5922, "num_tokens": 127697784.0, "step": 21375 }, { "epoch": 0.2280946945046035, "grad_norm": 1.0068002788970611, "learning_rate": 4.6209885280568326e-05, "loss": 0.599, "num_tokens": 127717529.0, "step": 21380 }, { "epoch": 0.22814803751080195, "grad_norm": 0.8195843845067314, "learning_rate": 4.6207680376584614e-05, "loss": 0.6022, "num_tokens": 127749472.0, "step": 21385 }, { "epoch": 0.22820138051700042, "grad_norm": 0.8834877141436351, "learning_rate": 4.620547489045632e-05, "loss": 0.6743, "num_tokens": 127786097.0, "step": 21390 }, { "epoch": 0.22825472352319887, "grad_norm": 1.1798000727235025, "learning_rate": 4.6203268822252075e-05, "loss": 0.6324, "num_tokens": 127807545.0, "step": 21395 }, { "epoch": 0.22830806652939734, "grad_norm": 1.186117397812188, "learning_rate": 4.620106217204051e-05, "loss": 0.5682, "num_tokens": 127847632.0, "step": 21400 }, { "epoch": 0.22836140953559578, "grad_norm": 1.1833709868531275, "learning_rate": 4.619885493989031e-05, "loss": 0.5904, "num_tokens": 127873027.0, "step": 21405 }, { "epoch": 0.22841475254179425, "grad_norm": 1.8188858582912801, "learning_rate": 4.619664712587015e-05, "loss": 0.7959, "num_tokens": 127894194.0, "step": 21410 }, { "epoch": 0.2284680955479927, "grad_norm": 2.7906709467202178, "learning_rate": 4.619443873004874e-05, "loss": 0.5733, "num_tokens": 127917018.0, "step": 21415 }, { "epoch": 0.22852143855419116, "grad_norm": 0.8673394789618897, "learning_rate": 4.6192229752494794e-05, "loss": 0.6148, "num_tokens": 127952756.0, "step": 21420 }, { "epoch": 0.22857478156038963, "grad_norm": 1.1006486815918173, "learning_rate": 4.619002019327705e-05, "loss": 0.7326, "num_tokens": 127993897.0, "step": 21425 }, { "epoch": 0.22862812456658807, "grad_norm": 2.5605571296799363, "learning_rate": 4.618781005246427e-05, "loss": 0.5662, "num_tokens": 128024139.0, "step": 21430 }, { "epoch": 0.22868146757278654, "grad_norm": 0.9514784603111827, "learning_rate": 4.618559933012523e-05, "loss": 0.5321, "num_tokens": 128049737.0, "step": 21435 }, { "epoch": 0.22873481057898498, "grad_norm": 0.8337142295845974, "learning_rate": 4.6183388026328714e-05, "loss": 0.5182, "num_tokens": 128075174.0, "step": 21440 }, { "epoch": 0.22878815358518345, "grad_norm": 1.2528456205407201, "learning_rate": 4.6181176141143545e-05, "loss": 0.5947, "num_tokens": 128104536.0, "step": 21445 }, { "epoch": 0.2288414965913819, "grad_norm": 1.3529230612837422, "learning_rate": 4.6178963674638546e-05, "loss": 0.5857, "num_tokens": 128134247.0, "step": 21450 }, { "epoch": 0.22889483959758036, "grad_norm": 1.268779522485341, "learning_rate": 4.617675062688256e-05, "loss": 0.5407, "num_tokens": 128166579.0, "step": 21455 }, { "epoch": 0.2289481826037788, "grad_norm": 0.9893418506843619, "learning_rate": 4.617453699794446e-05, "loss": 0.6724, "num_tokens": 128180447.0, "step": 21460 }, { "epoch": 0.22900152560997727, "grad_norm": 1.3975019270934843, "learning_rate": 4.617232278789313e-05, "loss": 0.5963, "num_tokens": 128209044.0, "step": 21465 }, { "epoch": 0.22905486861617574, "grad_norm": 1.085267919481106, "learning_rate": 4.6170107996797466e-05, "loss": 0.6759, "num_tokens": 128223754.0, "step": 21470 }, { "epoch": 0.22910821162237419, "grad_norm": 1.2345377642540394, "learning_rate": 4.616789262472639e-05, "loss": 0.6834, "num_tokens": 128251153.0, "step": 21475 }, { "epoch": 0.22916155462857266, "grad_norm": 1.6520553948458718, "learning_rate": 4.616567667174885e-05, "loss": 0.6735, "num_tokens": 128306164.0, "step": 21480 }, { "epoch": 0.2292148976347711, "grad_norm": 1.459477936085554, "learning_rate": 4.6163460137933776e-05, "loss": 0.6836, "num_tokens": 128327943.0, "step": 21485 }, { "epoch": 0.22926824064096957, "grad_norm": 1.153865839066317, "learning_rate": 4.6161243023350176e-05, "loss": 0.6794, "num_tokens": 128348921.0, "step": 21490 }, { "epoch": 0.229321583647168, "grad_norm": 1.1249243162710385, "learning_rate": 4.615902532806701e-05, "loss": 0.6351, "num_tokens": 128380369.0, "step": 21495 }, { "epoch": 0.22937492665336648, "grad_norm": 1.0889447023624197, "learning_rate": 4.6156807052153314e-05, "loss": 0.6769, "num_tokens": 128412048.0, "step": 21500 }, { "epoch": 0.22942826965956492, "grad_norm": 0.9912260108451995, "learning_rate": 4.6154588195678096e-05, "loss": 0.5249, "num_tokens": 128440537.0, "step": 21505 }, { "epoch": 0.2294816126657634, "grad_norm": 1.1223654287567422, "learning_rate": 4.615236875871041e-05, "loss": 0.5714, "num_tokens": 128463812.0, "step": 21510 }, { "epoch": 0.22953495567196186, "grad_norm": 1.4588379438531547, "learning_rate": 4.6150148741319334e-05, "loss": 0.6328, "num_tokens": 128490915.0, "step": 21515 }, { "epoch": 0.2295882986781603, "grad_norm": 0.9837153210579447, "learning_rate": 4.614792814357392e-05, "loss": 0.497, "num_tokens": 128529541.0, "step": 21520 }, { "epoch": 0.22964164168435877, "grad_norm": 2.4110304870121433, "learning_rate": 4.6145706965543296e-05, "loss": 0.5694, "num_tokens": 128563003.0, "step": 21525 }, { "epoch": 0.2296949846905572, "grad_norm": 1.017503355164143, "learning_rate": 4.614348520729657e-05, "loss": 0.6412, "num_tokens": 128590715.0, "step": 21530 }, { "epoch": 0.22974832769675568, "grad_norm": 0.6211347543547575, "learning_rate": 4.614126286890287e-05, "loss": 0.5456, "num_tokens": 128624160.0, "step": 21535 }, { "epoch": 0.22980167070295413, "grad_norm": 1.6270348664971082, "learning_rate": 4.613903995043137e-05, "loss": 0.614, "num_tokens": 128651437.0, "step": 21540 }, { "epoch": 0.2298550137091526, "grad_norm": 1.30459705508642, "learning_rate": 4.613681645195124e-05, "loss": 0.5941, "num_tokens": 128673959.0, "step": 21545 }, { "epoch": 0.22990835671535104, "grad_norm": 2.0508106790572076, "learning_rate": 4.613459237353165e-05, "loss": 0.7875, "num_tokens": 128690689.0, "step": 21550 }, { "epoch": 0.2299616997215495, "grad_norm": 0.7637137168533583, "learning_rate": 4.6132367715241826e-05, "loss": 0.6141, "num_tokens": 128724557.0, "step": 21555 }, { "epoch": 0.23001504272774798, "grad_norm": 1.0003999256724034, "learning_rate": 4.6130142477150995e-05, "loss": 0.675, "num_tokens": 128749832.0, "step": 21560 }, { "epoch": 0.23006838573394642, "grad_norm": 1.18935984012797, "learning_rate": 4.612791665932839e-05, "loss": 0.5233, "num_tokens": 128780340.0, "step": 21565 }, { "epoch": 0.2301217287401449, "grad_norm": 0.8162069178786242, "learning_rate": 4.6125690261843285e-05, "loss": 0.4692, "num_tokens": 128804476.0, "step": 21570 }, { "epoch": 0.23017507174634333, "grad_norm": 1.1587000619589087, "learning_rate": 4.6123463284764954e-05, "loss": 0.6602, "num_tokens": 128841319.0, "step": 21575 }, { "epoch": 0.2302284147525418, "grad_norm": 0.9992339133828833, "learning_rate": 4.6121235728162706e-05, "loss": 0.469, "num_tokens": 128870118.0, "step": 21580 }, { "epoch": 0.23028175775874024, "grad_norm": 0.8901054565521068, "learning_rate": 4.611900759210585e-05, "loss": 0.6095, "num_tokens": 128910197.0, "step": 21585 }, { "epoch": 0.2303351007649387, "grad_norm": 0.9094737964243448, "learning_rate": 4.611677887666371e-05, "loss": 0.5823, "num_tokens": 128948955.0, "step": 21590 }, { "epoch": 0.23038844377113715, "grad_norm": 0.9184237822272509, "learning_rate": 4.611454958190567e-05, "loss": 0.7334, "num_tokens": 129004259.0, "step": 21595 }, { "epoch": 0.23044178677733562, "grad_norm": 3.1954933356106134, "learning_rate": 4.611231970790107e-05, "loss": 0.5921, "num_tokens": 129049487.0, "step": 21600 }, { "epoch": 0.2304951297835341, "grad_norm": 0.9050037940242994, "learning_rate": 4.6110089254719315e-05, "loss": 0.4966, "num_tokens": 129076614.0, "step": 21605 }, { "epoch": 0.23054847278973253, "grad_norm": 1.1704634852057376, "learning_rate": 4.610785822242981e-05, "loss": 0.5301, "num_tokens": 129100606.0, "step": 21610 }, { "epoch": 0.230601815795931, "grad_norm": 0.628292813382232, "learning_rate": 4.610562661110197e-05, "loss": 0.5939, "num_tokens": 129150192.0, "step": 21615 }, { "epoch": 0.23065515880212945, "grad_norm": 0.7600397513810683, "learning_rate": 4.610339442080526e-05, "loss": 0.7213, "num_tokens": 129188713.0, "step": 21620 }, { "epoch": 0.23070850180832791, "grad_norm": 3.3378033356861185, "learning_rate": 4.6101161651609116e-05, "loss": 0.7294, "num_tokens": 129229216.0, "step": 21625 }, { "epoch": 0.23076184481452636, "grad_norm": 0.941454430806337, "learning_rate": 4.609892830358304e-05, "loss": 0.6637, "num_tokens": 129265769.0, "step": 21630 }, { "epoch": 0.23081518782072483, "grad_norm": 1.0646599640950478, "learning_rate": 4.609669437679652e-05, "loss": 0.6613, "num_tokens": 129299197.0, "step": 21635 }, { "epoch": 0.23086853082692327, "grad_norm": 1.4232160146435828, "learning_rate": 4.6094459871319054e-05, "loss": 0.6697, "num_tokens": 129327569.0, "step": 21640 }, { "epoch": 0.23092187383312174, "grad_norm": 1.1683230422107043, "learning_rate": 4.609222478722021e-05, "loss": 0.5985, "num_tokens": 129352489.0, "step": 21645 }, { "epoch": 0.2309752168393202, "grad_norm": 0.9135075763206575, "learning_rate": 4.608998912456951e-05, "loss": 0.5162, "num_tokens": 129382026.0, "step": 21650 }, { "epoch": 0.23102855984551865, "grad_norm": 0.8629500588742806, "learning_rate": 4.608775288343653e-05, "loss": 0.5575, "num_tokens": 129404652.0, "step": 21655 }, { "epoch": 0.23108190285171712, "grad_norm": 1.0522312973233756, "learning_rate": 4.608551606389086e-05, "loss": 0.7638, "num_tokens": 129436774.0, "step": 21660 }, { "epoch": 0.23113524585791556, "grad_norm": 2.2574016685882907, "learning_rate": 4.608327866600212e-05, "loss": 0.7537, "num_tokens": 129457329.0, "step": 21665 }, { "epoch": 0.23118858886411403, "grad_norm": 4.575821324628683, "learning_rate": 4.6081040689839906e-05, "loss": 0.7342, "num_tokens": 129495210.0, "step": 21670 }, { "epoch": 0.23124193187031247, "grad_norm": 1.1021497581558644, "learning_rate": 4.607880213547387e-05, "loss": 0.5334, "num_tokens": 129528156.0, "step": 21675 }, { "epoch": 0.23129527487651094, "grad_norm": 1.9577366528599498, "learning_rate": 4.6076563002973686e-05, "loss": 0.5725, "num_tokens": 129541974.0, "step": 21680 }, { "epoch": 0.23134861788270938, "grad_norm": 1.071498010085623, "learning_rate": 4.6074323292409004e-05, "loss": 0.6266, "num_tokens": 129567955.0, "step": 21685 }, { "epoch": 0.23140196088890785, "grad_norm": 1.2729607719835052, "learning_rate": 4.6072083003849544e-05, "loss": 0.7852, "num_tokens": 129593423.0, "step": 21690 }, { "epoch": 0.23145530389510632, "grad_norm": 0.9636886007898816, "learning_rate": 4.606984213736501e-05, "loss": 0.6699, "num_tokens": 129620686.0, "step": 21695 }, { "epoch": 0.23150864690130477, "grad_norm": 1.6166986909027639, "learning_rate": 4.6067600693025125e-05, "loss": 0.6849, "num_tokens": 129650452.0, "step": 21700 }, { "epoch": 0.23156198990750324, "grad_norm": 1.1602205533854095, "learning_rate": 4.6065358670899655e-05, "loss": 0.6521, "num_tokens": 129680438.0, "step": 21705 }, { "epoch": 0.23161533291370168, "grad_norm": 1.6003284621484575, "learning_rate": 4.606311607105835e-05, "loss": 0.5578, "num_tokens": 129716259.0, "step": 21710 }, { "epoch": 0.23166867591990015, "grad_norm": 0.9619917373790862, "learning_rate": 4.6060872893571006e-05, "loss": 0.5338, "num_tokens": 129739044.0, "step": 21715 }, { "epoch": 0.2317220189260986, "grad_norm": 0.8646059211663912, "learning_rate": 4.605862913850742e-05, "loss": 0.5363, "num_tokens": 129780686.0, "step": 21720 }, { "epoch": 0.23177536193229706, "grad_norm": 0.9462854484123443, "learning_rate": 4.605638480593742e-05, "loss": 0.7721, "num_tokens": 129814654.0, "step": 21725 }, { "epoch": 0.2318287049384955, "grad_norm": 2.624147511202119, "learning_rate": 4.6054139895930835e-05, "loss": 0.6537, "num_tokens": 129827744.0, "step": 21730 }, { "epoch": 0.23188204794469397, "grad_norm": 1.3795756146495535, "learning_rate": 4.605189440855753e-05, "loss": 0.7367, "num_tokens": 129845948.0, "step": 21735 }, { "epoch": 0.23193539095089244, "grad_norm": 0.98846704272215, "learning_rate": 4.604964834388737e-05, "loss": 0.416, "num_tokens": 129866439.0, "step": 21740 }, { "epoch": 0.23198873395709088, "grad_norm": 1.7584152533921724, "learning_rate": 4.604740170199027e-05, "loss": 0.6796, "num_tokens": 129901030.0, "step": 21745 }, { "epoch": 0.23204207696328935, "grad_norm": 1.76563030564768, "learning_rate": 4.6045154482936125e-05, "loss": 0.522, "num_tokens": 129924383.0, "step": 21750 }, { "epoch": 0.2320954199694878, "grad_norm": 1.6083862952735197, "learning_rate": 4.6042906686794855e-05, "loss": 0.5864, "num_tokens": 129950086.0, "step": 21755 }, { "epoch": 0.23214876297568626, "grad_norm": 1.2781969262874215, "learning_rate": 4.604065831363642e-05, "loss": 0.5895, "num_tokens": 129971056.0, "step": 21760 }, { "epoch": 0.2322021059818847, "grad_norm": 1.0323287385087092, "learning_rate": 4.603840936353079e-05, "loss": 0.6175, "num_tokens": 130003136.0, "step": 21765 }, { "epoch": 0.23225544898808317, "grad_norm": 1.0649473385848167, "learning_rate": 4.603615983654793e-05, "loss": 0.6437, "num_tokens": 130036823.0, "step": 21770 }, { "epoch": 0.23230879199428162, "grad_norm": 0.7822056851007516, "learning_rate": 4.603390973275786e-05, "loss": 0.6355, "num_tokens": 130066885.0, "step": 21775 }, { "epoch": 0.23236213500048009, "grad_norm": 0.9177674769517531, "learning_rate": 4.603165905223058e-05, "loss": 0.6684, "num_tokens": 130100286.0, "step": 21780 }, { "epoch": 0.23241547800667856, "grad_norm": 1.0471313808202125, "learning_rate": 4.602940779503614e-05, "loss": 0.6555, "num_tokens": 130127722.0, "step": 21785 }, { "epoch": 0.232468821012877, "grad_norm": 1.4637902327545607, "learning_rate": 4.6027155961244595e-05, "loss": 0.4513, "num_tokens": 130148461.0, "step": 21790 }, { "epoch": 0.23252216401907547, "grad_norm": 3.4848532298704566, "learning_rate": 4.6024903550926e-05, "loss": 0.7904, "num_tokens": 130175888.0, "step": 21795 }, { "epoch": 0.2325755070252739, "grad_norm": 1.002610961936388, "learning_rate": 4.602265056415046e-05, "loss": 0.5369, "num_tokens": 130208632.0, "step": 21800 }, { "epoch": 0.23262885003147238, "grad_norm": 3.5585034798130035, "learning_rate": 4.602039700098809e-05, "loss": 0.6133, "num_tokens": 130241106.0, "step": 21805 }, { "epoch": 0.23268219303767082, "grad_norm": 1.0602676701831546, "learning_rate": 4.6018142861509e-05, "loss": 0.5629, "num_tokens": 130278751.0, "step": 21810 }, { "epoch": 0.2327355360438693, "grad_norm": 1.694137388411455, "learning_rate": 4.6015888145783344e-05, "loss": 0.6952, "num_tokens": 130300228.0, "step": 21815 }, { "epoch": 0.23278887905006773, "grad_norm": 1.7136383418509176, "learning_rate": 4.601363285388128e-05, "loss": 0.6868, "num_tokens": 130350676.0, "step": 21820 }, { "epoch": 0.2328422220562662, "grad_norm": 1.7452152133510077, "learning_rate": 4.601137698587299e-05, "loss": 0.6944, "num_tokens": 130364242.0, "step": 21825 }, { "epoch": 0.23289556506246467, "grad_norm": 1.009314259458275, "learning_rate": 4.6009120541828675e-05, "loss": 0.661, "num_tokens": 130401703.0, "step": 21830 }, { "epoch": 0.2329489080686631, "grad_norm": 1.1131741122979146, "learning_rate": 4.6006863521818544e-05, "loss": 0.5106, "num_tokens": 130426336.0, "step": 21835 }, { "epoch": 0.23300225107486158, "grad_norm": 0.9965701703720611, "learning_rate": 4.600460592591283e-05, "loss": 0.5804, "num_tokens": 130454114.0, "step": 21840 }, { "epoch": 0.23305559408106002, "grad_norm": 0.9218736715092329, "learning_rate": 4.60023477541818e-05, "loss": 0.5455, "num_tokens": 130493725.0, "step": 21845 }, { "epoch": 0.2331089370872585, "grad_norm": 1.4041020653251353, "learning_rate": 4.600008900669571e-05, "loss": 0.7783, "num_tokens": 130527352.0, "step": 21850 }, { "epoch": 0.23316228009345694, "grad_norm": 1.7736124137511158, "learning_rate": 4.599782968352485e-05, "loss": 0.4981, "num_tokens": 130547443.0, "step": 21855 }, { "epoch": 0.2332156230996554, "grad_norm": 1.0703395834496456, "learning_rate": 4.5995569784739514e-05, "loss": 0.5797, "num_tokens": 130564922.0, "step": 21860 }, { "epoch": 0.23326896610585385, "grad_norm": 1.3830993066048778, "learning_rate": 4.5993309310410054e-05, "loss": 0.6223, "num_tokens": 130586897.0, "step": 21865 }, { "epoch": 0.23332230911205232, "grad_norm": 0.7139634589956342, "learning_rate": 4.599104826060679e-05, "loss": 0.6514, "num_tokens": 130625167.0, "step": 21870 }, { "epoch": 0.2333756521182508, "grad_norm": 1.2904625654337882, "learning_rate": 4.598878663540008e-05, "loss": 0.5215, "num_tokens": 130646070.0, "step": 21875 }, { "epoch": 0.23342899512444923, "grad_norm": 1.297030298123966, "learning_rate": 4.5986524434860315e-05, "loss": 0.5265, "num_tokens": 130662960.0, "step": 21880 }, { "epoch": 0.2334823381306477, "grad_norm": 1.765321592826148, "learning_rate": 4.598426165905787e-05, "loss": 0.692, "num_tokens": 130683974.0, "step": 21885 }, { "epoch": 0.23353568113684614, "grad_norm": 0.8432813413273743, "learning_rate": 4.598199830806318e-05, "loss": 0.4347, "num_tokens": 130716038.0, "step": 21890 }, { "epoch": 0.2335890241430446, "grad_norm": 1.1754383771362884, "learning_rate": 4.597973438194667e-05, "loss": 0.6228, "num_tokens": 130745939.0, "step": 21895 }, { "epoch": 0.23364236714924305, "grad_norm": 0.8043132040758435, "learning_rate": 4.5977469880778774e-05, "loss": 0.6357, "num_tokens": 130771574.0, "step": 21900 }, { "epoch": 0.23369571015544152, "grad_norm": 1.2027967717890162, "learning_rate": 4.597520480462997e-05, "loss": 0.6273, "num_tokens": 130807875.0, "step": 21905 }, { "epoch": 0.23374905316163996, "grad_norm": 1.132355780838102, "learning_rate": 4.597293915357074e-05, "loss": 0.5828, "num_tokens": 130835441.0, "step": 21910 }, { "epoch": 0.23380239616783843, "grad_norm": 1.044526727971721, "learning_rate": 4.5970672927671595e-05, "loss": 0.5996, "num_tokens": 130863114.0, "step": 21915 }, { "epoch": 0.2338557391740369, "grad_norm": 0.8218941728795834, "learning_rate": 4.5968406127003044e-05, "loss": 0.6313, "num_tokens": 130895781.0, "step": 21920 }, { "epoch": 0.23390908218023534, "grad_norm": 1.422013030072645, "learning_rate": 4.5966138751635635e-05, "loss": 0.5882, "num_tokens": 130915399.0, "step": 21925 }, { "epoch": 0.23396242518643381, "grad_norm": 1.040984485280362, "learning_rate": 4.5963870801639916e-05, "loss": 0.707, "num_tokens": 130951637.0, "step": 21930 }, { "epoch": 0.23401576819263226, "grad_norm": 0.8788079357903446, "learning_rate": 4.5961602277086455e-05, "loss": 0.6735, "num_tokens": 130979141.0, "step": 21935 }, { "epoch": 0.23406911119883073, "grad_norm": 1.1843941048425302, "learning_rate": 4.595933317804587e-05, "loss": 0.5686, "num_tokens": 131013130.0, "step": 21940 }, { "epoch": 0.23412245420502917, "grad_norm": 0.9618896879747885, "learning_rate": 4.595706350458874e-05, "loss": 0.5292, "num_tokens": 131037451.0, "step": 21945 }, { "epoch": 0.23417579721122764, "grad_norm": 1.3757708802647062, "learning_rate": 4.5954793256785705e-05, "loss": 0.6106, "num_tokens": 131058789.0, "step": 21950 }, { "epoch": 0.23422914021742608, "grad_norm": 2.1287035978831756, "learning_rate": 4.5952522434707416e-05, "loss": 0.5869, "num_tokens": 131090139.0, "step": 21955 }, { "epoch": 0.23428248322362455, "grad_norm": 1.1111130341613134, "learning_rate": 4.5950251038424524e-05, "loss": 0.6678, "num_tokens": 131119969.0, "step": 21960 }, { "epoch": 0.23433582622982302, "grad_norm": 1.810733549718081, "learning_rate": 4.5947979068007723e-05, "loss": 0.6153, "num_tokens": 131139951.0, "step": 21965 }, { "epoch": 0.23438916923602146, "grad_norm": 1.424253042639266, "learning_rate": 4.5945706523527706e-05, "loss": 0.6612, "num_tokens": 131177606.0, "step": 21970 }, { "epoch": 0.23444251224221993, "grad_norm": 1.2681032595320088, "learning_rate": 4.5943433405055196e-05, "loss": 0.5468, "num_tokens": 131203458.0, "step": 21975 }, { "epoch": 0.23449585524841837, "grad_norm": 1.3171674038998784, "learning_rate": 4.594115971266092e-05, "loss": 0.5478, "num_tokens": 131225885.0, "step": 21980 }, { "epoch": 0.23454919825461684, "grad_norm": 1.1184580218662385, "learning_rate": 4.593888544641563e-05, "loss": 0.5637, "num_tokens": 131251249.0, "step": 21985 }, { "epoch": 0.23460254126081528, "grad_norm": 1.2700004443264756, "learning_rate": 4.59366106063901e-05, "loss": 0.6415, "num_tokens": 131291109.0, "step": 21990 }, { "epoch": 0.23465588426701375, "grad_norm": 0.7825152712096964, "learning_rate": 4.593433519265512e-05, "loss": 0.5807, "num_tokens": 131323542.0, "step": 21995 }, { "epoch": 0.2347092272732122, "grad_norm": 1.2379813752808504, "learning_rate": 4.5932059205281486e-05, "loss": 0.7159, "num_tokens": 131353595.0, "step": 22000 }, { "epoch": 0.23476257027941067, "grad_norm": 0.697999306149756, "learning_rate": 4.592978264434004e-05, "loss": 0.53, "num_tokens": 131383774.0, "step": 22005 }, { "epoch": 0.23481591328560913, "grad_norm": 1.3011435291772895, "learning_rate": 4.5927505509901614e-05, "loss": 0.6406, "num_tokens": 131417829.0, "step": 22010 }, { "epoch": 0.23486925629180758, "grad_norm": 1.297297169258856, "learning_rate": 4.592522780203706e-05, "loss": 0.4707, "num_tokens": 131433593.0, "step": 22015 }, { "epoch": 0.23492259929800605, "grad_norm": 1.1058639999766169, "learning_rate": 4.5922949520817264e-05, "loss": 0.4926, "num_tokens": 131452171.0, "step": 22020 }, { "epoch": 0.2349759423042045, "grad_norm": 0.7887114507228897, "learning_rate": 4.592067066631313e-05, "loss": 0.6013, "num_tokens": 131484658.0, "step": 22025 }, { "epoch": 0.23502928531040296, "grad_norm": 0.8213886792651817, "learning_rate": 4.5918391238595554e-05, "loss": 0.6156, "num_tokens": 131513664.0, "step": 22030 }, { "epoch": 0.2350826283166014, "grad_norm": 1.3968217052091565, "learning_rate": 4.591611123773548e-05, "loss": 0.5302, "num_tokens": 131538728.0, "step": 22035 }, { "epoch": 0.23513597132279987, "grad_norm": 1.1707408863524904, "learning_rate": 4.591383066380385e-05, "loss": 0.6501, "num_tokens": 131572815.0, "step": 22040 }, { "epoch": 0.2351893143289983, "grad_norm": 0.9640898868315407, "learning_rate": 4.591154951687163e-05, "loss": 0.7576, "num_tokens": 131606031.0, "step": 22045 }, { "epoch": 0.23524265733519678, "grad_norm": 2.851160613303981, "learning_rate": 4.590926779700981e-05, "loss": 0.8723, "num_tokens": 131643381.0, "step": 22050 }, { "epoch": 0.23529600034139525, "grad_norm": 1.0184721332788165, "learning_rate": 4.5906985504289385e-05, "loss": 0.6305, "num_tokens": 131672496.0, "step": 22055 }, { "epoch": 0.2353493433475937, "grad_norm": 1.2673080728690511, "learning_rate": 4.5904702638781386e-05, "loss": 0.6436, "num_tokens": 131711542.0, "step": 22060 }, { "epoch": 0.23540268635379216, "grad_norm": 1.4719631400826394, "learning_rate": 4.5902419200556844e-05, "loss": 0.569, "num_tokens": 131751759.0, "step": 22065 }, { "epoch": 0.2354560293599906, "grad_norm": 1.3914334285338519, "learning_rate": 4.5900135189686815e-05, "loss": 0.5979, "num_tokens": 131773282.0, "step": 22070 }, { "epoch": 0.23550937236618907, "grad_norm": 0.8312391487802221, "learning_rate": 4.5897850606242375e-05, "loss": 0.5611, "num_tokens": 131799679.0, "step": 22075 }, { "epoch": 0.23556271537238752, "grad_norm": 0.8965187213378468, "learning_rate": 4.589556545029461e-05, "loss": 0.7396, "num_tokens": 131847305.0, "step": 22080 }, { "epoch": 0.23561605837858599, "grad_norm": 1.2852990426178683, "learning_rate": 4.589327972191465e-05, "loss": 0.514, "num_tokens": 131880061.0, "step": 22085 }, { "epoch": 0.23566940138478443, "grad_norm": 0.8488664401399585, "learning_rate": 4.5890993421173586e-05, "loss": 0.6172, "num_tokens": 131911072.0, "step": 22090 }, { "epoch": 0.2357227443909829, "grad_norm": 1.3118827405226872, "learning_rate": 4.5888706548142596e-05, "loss": 0.769, "num_tokens": 131939509.0, "step": 22095 }, { "epoch": 0.23577608739718137, "grad_norm": 1.0492194196369369, "learning_rate": 4.588641910289282e-05, "loss": 0.6816, "num_tokens": 131964959.0, "step": 22100 }, { "epoch": 0.2358294304033798, "grad_norm": 0.878981717903315, "learning_rate": 4.5884131085495455e-05, "loss": 0.6604, "num_tokens": 131997795.0, "step": 22105 }, { "epoch": 0.23588277340957828, "grad_norm": 1.0188324072188297, "learning_rate": 4.588184249602169e-05, "loss": 0.7657, "num_tokens": 132026867.0, "step": 22110 }, { "epoch": 0.23593611641577672, "grad_norm": 1.110732581780844, "learning_rate": 4.587955333454274e-05, "loss": 0.625, "num_tokens": 132050309.0, "step": 22115 }, { "epoch": 0.2359894594219752, "grad_norm": 1.418862456165778, "learning_rate": 4.587726360112986e-05, "loss": 0.6212, "num_tokens": 132074579.0, "step": 22120 }, { "epoch": 0.23604280242817363, "grad_norm": 0.9748404302171061, "learning_rate": 4.587497329585426e-05, "loss": 0.7611, "num_tokens": 132111272.0, "step": 22125 }, { "epoch": 0.2360961454343721, "grad_norm": 1.0439184002547266, "learning_rate": 4.587268241878724e-05, "loss": 0.6506, "num_tokens": 132143100.0, "step": 22130 }, { "epoch": 0.23614948844057054, "grad_norm": 1.1492100143610038, "learning_rate": 4.58703909700001e-05, "loss": 0.6389, "num_tokens": 132170527.0, "step": 22135 }, { "epoch": 0.236202831446769, "grad_norm": 2.155151877260674, "learning_rate": 4.5868098949564114e-05, "loss": 0.6384, "num_tokens": 132204885.0, "step": 22140 }, { "epoch": 0.23625617445296748, "grad_norm": 0.9501495818537248, "learning_rate": 4.586580635755061e-05, "loss": 0.5681, "num_tokens": 132238559.0, "step": 22145 }, { "epoch": 0.23630951745916592, "grad_norm": 0.9643940694448738, "learning_rate": 4.586351319403095e-05, "loss": 0.6645, "num_tokens": 132291000.0, "step": 22150 }, { "epoch": 0.2363628604653644, "grad_norm": 1.3173947851658356, "learning_rate": 4.5861219459076475e-05, "loss": 0.6012, "num_tokens": 132324617.0, "step": 22155 }, { "epoch": 0.23641620347156284, "grad_norm": 0.7085464814114383, "learning_rate": 4.585892515275857e-05, "loss": 0.6388, "num_tokens": 132369660.0, "step": 22160 }, { "epoch": 0.2364695464777613, "grad_norm": 0.8363068440606728, "learning_rate": 4.585663027514862e-05, "loss": 0.548, "num_tokens": 132396271.0, "step": 22165 }, { "epoch": 0.23652288948395975, "grad_norm": 1.093760139842027, "learning_rate": 4.585433482631804e-05, "loss": 0.6435, "num_tokens": 132429536.0, "step": 22170 }, { "epoch": 0.23657623249015822, "grad_norm": 0.7316424073506491, "learning_rate": 4.585203880633826e-05, "loss": 0.605, "num_tokens": 132482789.0, "step": 22175 }, { "epoch": 0.23662957549635666, "grad_norm": 0.8762846999495456, "learning_rate": 4.5849742215280726e-05, "loss": 0.5848, "num_tokens": 132532759.0, "step": 22180 }, { "epoch": 0.23668291850255513, "grad_norm": 1.0700352421172759, "learning_rate": 4.584744505321691e-05, "loss": 0.5809, "num_tokens": 132556355.0, "step": 22185 }, { "epoch": 0.2367362615087536, "grad_norm": 0.7322076634482678, "learning_rate": 4.584514732021829e-05, "loss": 0.4891, "num_tokens": 132593028.0, "step": 22190 }, { "epoch": 0.23678960451495204, "grad_norm": 0.9777747654658623, "learning_rate": 4.584284901635637e-05, "loss": 0.5029, "num_tokens": 132620404.0, "step": 22195 }, { "epoch": 0.2368429475211505, "grad_norm": 1.3712240557722086, "learning_rate": 4.584055014170266e-05, "loss": 0.4654, "num_tokens": 132635847.0, "step": 22200 }, { "epoch": 0.23689629052734895, "grad_norm": 1.624864329513207, "learning_rate": 4.583825069632871e-05, "loss": 0.5088, "num_tokens": 132665385.0, "step": 22205 }, { "epoch": 0.23694963353354742, "grad_norm": 1.8901314910593552, "learning_rate": 4.583595068030606e-05, "loss": 0.5441, "num_tokens": 132677744.0, "step": 22210 }, { "epoch": 0.23700297653974586, "grad_norm": 1.0583775647133622, "learning_rate": 4.583365009370629e-05, "loss": 0.8122, "num_tokens": 132703332.0, "step": 22215 }, { "epoch": 0.23705631954594433, "grad_norm": 1.8487799540853138, "learning_rate": 4.583134893660099e-05, "loss": 0.6712, "num_tokens": 132737390.0, "step": 22220 }, { "epoch": 0.23710966255214277, "grad_norm": 0.7101428496740779, "learning_rate": 4.5829047209061765e-05, "loss": 0.5303, "num_tokens": 132758835.0, "step": 22225 }, { "epoch": 0.23716300555834124, "grad_norm": 2.037114555292707, "learning_rate": 4.582674491116023e-05, "loss": 0.691, "num_tokens": 132791383.0, "step": 22230 }, { "epoch": 0.23721634856453971, "grad_norm": 1.0241514497191502, "learning_rate": 4.582444204296805e-05, "loss": 0.6628, "num_tokens": 132825249.0, "step": 22235 }, { "epoch": 0.23726969157073816, "grad_norm": 2.6249639127594184, "learning_rate": 4.582213860455687e-05, "loss": 0.7176, "num_tokens": 132849966.0, "step": 22240 }, { "epoch": 0.23732303457693663, "grad_norm": 0.9171106998187178, "learning_rate": 4.581983459599837e-05, "loss": 0.6095, "num_tokens": 132879351.0, "step": 22245 }, { "epoch": 0.23737637758313507, "grad_norm": 1.0787265341982228, "learning_rate": 4.5817530017364245e-05, "loss": 0.6586, "num_tokens": 132914145.0, "step": 22250 }, { "epoch": 0.23742972058933354, "grad_norm": 0.7089826268758901, "learning_rate": 4.5815224868726214e-05, "loss": 0.643, "num_tokens": 132953176.0, "step": 22255 }, { "epoch": 0.23748306359553198, "grad_norm": 1.1447990733253024, "learning_rate": 4.5812919150156006e-05, "loss": 0.6547, "num_tokens": 132971848.0, "step": 22260 }, { "epoch": 0.23753640660173045, "grad_norm": 1.2057457750212717, "learning_rate": 4.581061286172537e-05, "loss": 0.672, "num_tokens": 133004466.0, "step": 22265 }, { "epoch": 0.2375897496079289, "grad_norm": 0.9315187910604646, "learning_rate": 4.5808306003506076e-05, "loss": 0.8811, "num_tokens": 133026470.0, "step": 22270 }, { "epoch": 0.23764309261412736, "grad_norm": 1.4655943430423095, "learning_rate": 4.5805998575569895e-05, "loss": 0.508, "num_tokens": 133059204.0, "step": 22275 }, { "epoch": 0.23769643562032583, "grad_norm": 0.8697730419657387, "learning_rate": 4.580369057798865e-05, "loss": 0.6384, "num_tokens": 133094313.0, "step": 22280 }, { "epoch": 0.23774977862652427, "grad_norm": 7.918528037647045, "learning_rate": 4.580138201083414e-05, "loss": 0.6492, "num_tokens": 133122426.0, "step": 22285 }, { "epoch": 0.23780312163272274, "grad_norm": 1.334375221233005, "learning_rate": 4.579907287417822e-05, "loss": 0.506, "num_tokens": 133142705.0, "step": 22290 }, { "epoch": 0.23785646463892118, "grad_norm": 0.6543748358276459, "learning_rate": 4.579676316809274e-05, "loss": 0.6455, "num_tokens": 133174959.0, "step": 22295 }, { "epoch": 0.23790980764511965, "grad_norm": 0.9367220068718706, "learning_rate": 4.579445289264957e-05, "loss": 0.6732, "num_tokens": 133205050.0, "step": 22300 }, { "epoch": 0.2379631506513181, "grad_norm": 1.27695780825436, "learning_rate": 4.579214204792061e-05, "loss": 0.6019, "num_tokens": 133233316.0, "step": 22305 }, { "epoch": 0.23801649365751656, "grad_norm": 0.9599432859038007, "learning_rate": 4.578983063397776e-05, "loss": 0.5037, "num_tokens": 133264089.0, "step": 22310 }, { "epoch": 0.238069836663715, "grad_norm": 2.268283993501039, "learning_rate": 4.578751865089295e-05, "loss": 0.6142, "num_tokens": 133288883.0, "step": 22315 }, { "epoch": 0.23812317966991348, "grad_norm": 1.2420134755224268, "learning_rate": 4.578520609873812e-05, "loss": 0.6582, "num_tokens": 133312972.0, "step": 22320 }, { "epoch": 0.23817652267611195, "grad_norm": 1.6641376788273075, "learning_rate": 4.578289297758524e-05, "loss": 0.5952, "num_tokens": 133344019.0, "step": 22325 }, { "epoch": 0.2382298656823104, "grad_norm": 0.8521195820562377, "learning_rate": 4.5780579287506275e-05, "loss": 0.7022, "num_tokens": 133385690.0, "step": 22330 }, { "epoch": 0.23828320868850886, "grad_norm": 0.7028904557381309, "learning_rate": 4.577826502857324e-05, "loss": 0.5547, "num_tokens": 133417541.0, "step": 22335 }, { "epoch": 0.2383365516947073, "grad_norm": 1.2113537363553208, "learning_rate": 4.577595020085815e-05, "loss": 0.4476, "num_tokens": 133437744.0, "step": 22340 }, { "epoch": 0.23838989470090577, "grad_norm": 1.2322480335131623, "learning_rate": 4.5773634804433016e-05, "loss": 0.6688, "num_tokens": 133469118.0, "step": 22345 }, { "epoch": 0.2384432377071042, "grad_norm": 2.8365578670681906, "learning_rate": 4.5771318839369904e-05, "loss": 0.7448, "num_tokens": 133502421.0, "step": 22350 }, { "epoch": 0.23849658071330268, "grad_norm": 2.0568695429680517, "learning_rate": 4.576900230574088e-05, "loss": 0.7334, "num_tokens": 133523392.0, "step": 22355 }, { "epoch": 0.23854992371950112, "grad_norm": 1.6271734744005955, "learning_rate": 4.5766685203618036e-05, "loss": 0.6018, "num_tokens": 133553442.0, "step": 22360 }, { "epoch": 0.2386032667256996, "grad_norm": 1.466397397618829, "learning_rate": 4.5764367533073465e-05, "loss": 0.5796, "num_tokens": 133583000.0, "step": 22365 }, { "epoch": 0.23865660973189806, "grad_norm": 1.7372150029659186, "learning_rate": 4.5762049294179293e-05, "loss": 0.5878, "num_tokens": 133601514.0, "step": 22370 }, { "epoch": 0.2387099527380965, "grad_norm": 1.359627522990556, "learning_rate": 4.5759730487007655e-05, "loss": 0.511, "num_tokens": 133638123.0, "step": 22375 }, { "epoch": 0.23876329574429497, "grad_norm": 1.7839426064424897, "learning_rate": 4.5757411111630716e-05, "loss": 0.7809, "num_tokens": 133656286.0, "step": 22380 }, { "epoch": 0.23881663875049342, "grad_norm": 1.7778591600094797, "learning_rate": 4.5755091168120645e-05, "loss": 0.6288, "num_tokens": 133672107.0, "step": 22385 }, { "epoch": 0.23886998175669188, "grad_norm": 1.069923637060144, "learning_rate": 4.5752770656549635e-05, "loss": 0.5682, "num_tokens": 133706931.0, "step": 22390 }, { "epoch": 0.23892332476289033, "grad_norm": 1.2196745115145695, "learning_rate": 4.575044957698989e-05, "loss": 0.7498, "num_tokens": 133734038.0, "step": 22395 }, { "epoch": 0.2389766677690888, "grad_norm": 0.9183324190343248, "learning_rate": 4.574812792951363e-05, "loss": 0.6982, "num_tokens": 133765982.0, "step": 22400 }, { "epoch": 0.23903001077528724, "grad_norm": 3.0286571319882976, "learning_rate": 4.574580571419314e-05, "loss": 0.5854, "num_tokens": 133782726.0, "step": 22405 }, { "epoch": 0.2390833537814857, "grad_norm": 1.279970549929924, "learning_rate": 4.5743482931100626e-05, "loss": 0.4666, "num_tokens": 133801752.0, "step": 22410 }, { "epoch": 0.23913669678768418, "grad_norm": 1.960872434334313, "learning_rate": 4.574115958030842e-05, "loss": 0.5903, "num_tokens": 133820566.0, "step": 22415 }, { "epoch": 0.23919003979388262, "grad_norm": 0.7566880101907281, "learning_rate": 4.5738835661888776e-05, "loss": 0.6632, "num_tokens": 133860644.0, "step": 22420 }, { "epoch": 0.2392433828000811, "grad_norm": 1.1273375330745001, "learning_rate": 4.573651117591404e-05, "loss": 0.5626, "num_tokens": 133882422.0, "step": 22425 }, { "epoch": 0.23929672580627953, "grad_norm": 1.3658581485797203, "learning_rate": 4.573418612245654e-05, "loss": 0.5236, "num_tokens": 133918456.0, "step": 22430 }, { "epoch": 0.239350068812478, "grad_norm": 2.4737359888597994, "learning_rate": 4.573186050158862e-05, "loss": 0.7113, "num_tokens": 133942639.0, "step": 22435 }, { "epoch": 0.23940341181867644, "grad_norm": 1.1464107031878181, "learning_rate": 4.572953431338264e-05, "loss": 0.5701, "num_tokens": 133966015.0, "step": 22440 }, { "epoch": 0.2394567548248749, "grad_norm": 0.8589014066561365, "learning_rate": 4.572720755791101e-05, "loss": 0.5581, "num_tokens": 133994852.0, "step": 22445 }, { "epoch": 0.23951009783107335, "grad_norm": 0.9931328574541115, "learning_rate": 4.5724880235246107e-05, "loss": 0.5216, "num_tokens": 134015105.0, "step": 22450 }, { "epoch": 0.23956344083727182, "grad_norm": 1.299673562197649, "learning_rate": 4.572255234546037e-05, "loss": 0.703, "num_tokens": 134037057.0, "step": 22455 }, { "epoch": 0.2396167838434703, "grad_norm": 2.588602076870198, "learning_rate": 4.572022388862624e-05, "loss": 0.7667, "num_tokens": 134068968.0, "step": 22460 }, { "epoch": 0.23967012684966874, "grad_norm": 0.9524289252229298, "learning_rate": 4.571789486481617e-05, "loss": 0.5975, "num_tokens": 134096931.0, "step": 22465 }, { "epoch": 0.2397234698558672, "grad_norm": 1.1855789965889005, "learning_rate": 4.5715565274102624e-05, "loss": 0.6404, "num_tokens": 134119203.0, "step": 22470 }, { "epoch": 0.23977681286206565, "grad_norm": 0.7276898676701287, "learning_rate": 4.571323511655811e-05, "loss": 0.6983, "num_tokens": 134160907.0, "step": 22475 }, { "epoch": 0.23983015586826412, "grad_norm": 1.1324371248149419, "learning_rate": 4.5710904392255124e-05, "loss": 0.4801, "num_tokens": 134187042.0, "step": 22480 }, { "epoch": 0.23988349887446256, "grad_norm": 0.8032915209675339, "learning_rate": 4.57085731012662e-05, "loss": 0.5631, "num_tokens": 134225861.0, "step": 22485 }, { "epoch": 0.23993684188066103, "grad_norm": 1.0888402622161544, "learning_rate": 4.5706241243663886e-05, "loss": 0.5294, "num_tokens": 134248310.0, "step": 22490 }, { "epoch": 0.23999018488685947, "grad_norm": 1.2375476745550276, "learning_rate": 4.5703908819520744e-05, "loss": 0.5485, "num_tokens": 134277189.0, "step": 22495 }, { "epoch": 0.24004352789305794, "grad_norm": 0.9929472637654654, "learning_rate": 4.5701575828909344e-05, "loss": 0.5647, "num_tokens": 134314654.0, "step": 22500 }, { "epoch": 0.2400968708992564, "grad_norm": 1.398316676741353, "learning_rate": 4.569924227190229e-05, "loss": 0.7162, "num_tokens": 134333378.0, "step": 22505 }, { "epoch": 0.24015021390545485, "grad_norm": 1.6279081079167288, "learning_rate": 4.56969081485722e-05, "loss": 0.6017, "num_tokens": 134363817.0, "step": 22510 }, { "epoch": 0.24020355691165332, "grad_norm": 1.836184481045918, "learning_rate": 4.569457345899171e-05, "loss": 0.6824, "num_tokens": 134398589.0, "step": 22515 }, { "epoch": 0.24025689991785176, "grad_norm": 1.2765939865154796, "learning_rate": 4.569223820323347e-05, "loss": 0.6104, "num_tokens": 134420400.0, "step": 22520 }, { "epoch": 0.24031024292405023, "grad_norm": 0.8869135749064748, "learning_rate": 4.5689902381370144e-05, "loss": 0.6725, "num_tokens": 134450038.0, "step": 22525 }, { "epoch": 0.24036358593024867, "grad_norm": 0.8934430804545697, "learning_rate": 4.568756599347441e-05, "loss": 0.6345, "num_tokens": 134475064.0, "step": 22530 }, { "epoch": 0.24041692893644714, "grad_norm": 1.1107952264258092, "learning_rate": 4.568522903961899e-05, "loss": 0.6166, "num_tokens": 134503267.0, "step": 22535 }, { "epoch": 0.24047027194264559, "grad_norm": 0.9333289811527059, "learning_rate": 4.568289151987659e-05, "loss": 0.5587, "num_tokens": 134536430.0, "step": 22540 }, { "epoch": 0.24052361494884406, "grad_norm": 0.9673540186283621, "learning_rate": 4.568055343431996e-05, "loss": 0.5526, "num_tokens": 134565637.0, "step": 22545 }, { "epoch": 0.24057695795504253, "grad_norm": 1.0434855306960111, "learning_rate": 4.5678214783021845e-05, "loss": 0.7105, "num_tokens": 134591516.0, "step": 22550 }, { "epoch": 0.24063030096124097, "grad_norm": 1.3249705093373347, "learning_rate": 4.567587556605503e-05, "loss": 0.6335, "num_tokens": 134617580.0, "step": 22555 }, { "epoch": 0.24068364396743944, "grad_norm": 0.7825910163227539, "learning_rate": 4.56735357834923e-05, "loss": 0.5299, "num_tokens": 134643087.0, "step": 22560 }, { "epoch": 0.24073698697363788, "grad_norm": 1.4165883923009635, "learning_rate": 4.567119543540647e-05, "loss": 0.5362, "num_tokens": 134669795.0, "step": 22565 }, { "epoch": 0.24079032997983635, "grad_norm": 1.4392660141888218, "learning_rate": 4.5668854521870355e-05, "loss": 0.6218, "num_tokens": 134704713.0, "step": 22570 }, { "epoch": 0.2408436729860348, "grad_norm": 1.654658683907777, "learning_rate": 4.566651304295681e-05, "loss": 0.5377, "num_tokens": 134730533.0, "step": 22575 }, { "epoch": 0.24089701599223326, "grad_norm": 3.0615306571431926, "learning_rate": 4.566417099873869e-05, "loss": 0.7164, "num_tokens": 134752416.0, "step": 22580 }, { "epoch": 0.2409503589984317, "grad_norm": 1.1575075429344965, "learning_rate": 4.566182838928889e-05, "loss": 0.5782, "num_tokens": 134776136.0, "step": 22585 }, { "epoch": 0.24100370200463017, "grad_norm": 0.7220958601466003, "learning_rate": 4.565948521468029e-05, "loss": 0.4782, "num_tokens": 134803389.0, "step": 22590 }, { "epoch": 0.24105704501082864, "grad_norm": 0.6710524112628041, "learning_rate": 4.5657141474985806e-05, "loss": 0.6701, "num_tokens": 134834888.0, "step": 22595 }, { "epoch": 0.24111038801702708, "grad_norm": 0.9460858131973285, "learning_rate": 4.5654797170278377e-05, "loss": 0.6229, "num_tokens": 134854918.0, "step": 22600 }, { "epoch": 0.24116373102322555, "grad_norm": 0.8547991278844937, "learning_rate": 4.565245230063096e-05, "loss": 0.6204, "num_tokens": 134881779.0, "step": 22605 }, { "epoch": 0.241217074029424, "grad_norm": 0.8448591894160785, "learning_rate": 4.565010686611651e-05, "loss": 0.5652, "num_tokens": 134913474.0, "step": 22610 }, { "epoch": 0.24127041703562246, "grad_norm": 0.5091018135464506, "learning_rate": 4.5647760866808006e-05, "loss": 0.5322, "num_tokens": 134953284.0, "step": 22615 }, { "epoch": 0.2413237600418209, "grad_norm": 1.0922864243031938, "learning_rate": 4.5645414302778466e-05, "loss": 0.5076, "num_tokens": 134991381.0, "step": 22620 }, { "epoch": 0.24137710304801938, "grad_norm": 1.5429417076283287, "learning_rate": 4.564306717410091e-05, "loss": 0.595, "num_tokens": 135010329.0, "step": 22625 }, { "epoch": 0.24143044605421782, "grad_norm": 1.3293177827075335, "learning_rate": 4.564071948084836e-05, "loss": 0.6508, "num_tokens": 135051271.0, "step": 22630 }, { "epoch": 0.2414837890604163, "grad_norm": 1.220775454927578, "learning_rate": 4.5638371223093896e-05, "loss": 0.6536, "num_tokens": 135085553.0, "step": 22635 }, { "epoch": 0.24153713206661476, "grad_norm": 0.8942567681059083, "learning_rate": 4.563602240091057e-05, "loss": 0.5736, "num_tokens": 135105680.0, "step": 22640 }, { "epoch": 0.2415904750728132, "grad_norm": 1.5412873012171147, "learning_rate": 4.5633673014371475e-05, "loss": 0.7635, "num_tokens": 135122874.0, "step": 22645 }, { "epoch": 0.24164381807901167, "grad_norm": 1.5488847538288388, "learning_rate": 4.563132306354973e-05, "loss": 0.5491, "num_tokens": 135144189.0, "step": 22650 }, { "epoch": 0.2416971610852101, "grad_norm": 1.0313633252098173, "learning_rate": 4.562897254851845e-05, "loss": 0.6609, "num_tokens": 135178227.0, "step": 22655 }, { "epoch": 0.24175050409140858, "grad_norm": 1.496365902610484, "learning_rate": 4.562662146935078e-05, "loss": 0.7783, "num_tokens": 135202507.0, "step": 22660 }, { "epoch": 0.24180384709760702, "grad_norm": 0.7846442179612819, "learning_rate": 4.5624269826119885e-05, "loss": 1.0194, "num_tokens": 135236102.0, "step": 22665 }, { "epoch": 0.2418571901038055, "grad_norm": 1.1260698128971232, "learning_rate": 4.5621917618898945e-05, "loss": 0.4746, "num_tokens": 135258540.0, "step": 22670 }, { "epoch": 0.24191053311000393, "grad_norm": 1.057383792177978, "learning_rate": 4.5619564847761146e-05, "loss": 0.5787, "num_tokens": 135288977.0, "step": 22675 }, { "epoch": 0.2419638761162024, "grad_norm": 1.3291015367651198, "learning_rate": 4.561721151277972e-05, "loss": 0.642, "num_tokens": 135322021.0, "step": 22680 }, { "epoch": 0.24201721912240087, "grad_norm": 1.284269320913322, "learning_rate": 4.561485761402787e-05, "loss": 0.5757, "num_tokens": 135352084.0, "step": 22685 }, { "epoch": 0.24207056212859931, "grad_norm": 0.7975195953403684, "learning_rate": 4.561250315157887e-05, "loss": 0.5626, "num_tokens": 135394460.0, "step": 22690 }, { "epoch": 0.24212390513479778, "grad_norm": 0.774982138669784, "learning_rate": 4.5610148125505966e-05, "loss": 0.6294, "num_tokens": 135428011.0, "step": 22695 }, { "epoch": 0.24217724814099623, "grad_norm": 1.3500358381624642, "learning_rate": 4.560779253588246e-05, "loss": 0.7134, "num_tokens": 135446292.0, "step": 22700 }, { "epoch": 0.2422305911471947, "grad_norm": 1.4227367854806563, "learning_rate": 4.560543638278164e-05, "loss": 0.618, "num_tokens": 135465055.0, "step": 22705 }, { "epoch": 0.24228393415339314, "grad_norm": 1.560300325533125, "learning_rate": 4.560307966627684e-05, "loss": 0.5952, "num_tokens": 135490026.0, "step": 22710 }, { "epoch": 0.2423372771595916, "grad_norm": 0.9760924358204618, "learning_rate": 4.560072238644138e-05, "loss": 0.663, "num_tokens": 135521063.0, "step": 22715 }, { "epoch": 0.24239062016579005, "grad_norm": 1.0400151229564012, "learning_rate": 4.559836454334862e-05, "loss": 0.5777, "num_tokens": 135541389.0, "step": 22720 }, { "epoch": 0.24244396317198852, "grad_norm": 0.7529833217103236, "learning_rate": 4.559600613707193e-05, "loss": 0.4814, "num_tokens": 135575113.0, "step": 22725 }, { "epoch": 0.242497306178187, "grad_norm": 0.9581671898015357, "learning_rate": 4.559364716768469e-05, "loss": 0.5346, "num_tokens": 135603584.0, "step": 22730 }, { "epoch": 0.24255064918438543, "grad_norm": 0.9009750806625844, "learning_rate": 4.559128763526033e-05, "loss": 0.5723, "num_tokens": 135625713.0, "step": 22735 }, { "epoch": 0.2426039921905839, "grad_norm": 2.4704609289044517, "learning_rate": 4.5588927539872245e-05, "loss": 0.5866, "num_tokens": 135654427.0, "step": 22740 }, { "epoch": 0.24265733519678234, "grad_norm": 1.3523793533128223, "learning_rate": 4.55865668815939e-05, "loss": 0.6448, "num_tokens": 135670796.0, "step": 22745 }, { "epoch": 0.2427106782029808, "grad_norm": 2.8380938787229937, "learning_rate": 4.558420566049874e-05, "loss": 0.6426, "num_tokens": 135714506.0, "step": 22750 }, { "epoch": 0.24276402120917925, "grad_norm": 2.300820837464744, "learning_rate": 4.558184387666025e-05, "loss": 0.5851, "num_tokens": 135735782.0, "step": 22755 }, { "epoch": 0.24281736421537772, "grad_norm": 1.3160460786409285, "learning_rate": 4.557948153015192e-05, "loss": 0.4832, "num_tokens": 135768891.0, "step": 22760 }, { "epoch": 0.24287070722157617, "grad_norm": 0.9819761805089907, "learning_rate": 4.557711862104726e-05, "loss": 0.6007, "num_tokens": 135794544.0, "step": 22765 }, { "epoch": 0.24292405022777463, "grad_norm": 0.7936796076977211, "learning_rate": 4.55747551494198e-05, "loss": 0.6117, "num_tokens": 135824287.0, "step": 22770 }, { "epoch": 0.2429773932339731, "grad_norm": 2.038510068407215, "learning_rate": 4.5572391115343085e-05, "loss": 0.6826, "num_tokens": 135843601.0, "step": 22775 }, { "epoch": 0.24303073624017155, "grad_norm": 1.0978101853533118, "learning_rate": 4.557002651889068e-05, "loss": 0.7369, "num_tokens": 135879584.0, "step": 22780 }, { "epoch": 0.24308407924637002, "grad_norm": 1.0889743641030352, "learning_rate": 4.5567661360136163e-05, "loss": 0.5149, "num_tokens": 135900432.0, "step": 22785 }, { "epoch": 0.24313742225256846, "grad_norm": 0.8760248998229051, "learning_rate": 4.556529563915314e-05, "loss": 0.6418, "num_tokens": 135929595.0, "step": 22790 }, { "epoch": 0.24319076525876693, "grad_norm": 0.9816377714754854, "learning_rate": 4.556292935601523e-05, "loss": 0.4874, "num_tokens": 135958715.0, "step": 22795 }, { "epoch": 0.24324410826496537, "grad_norm": 1.767425909127182, "learning_rate": 4.556056251079606e-05, "loss": 0.5717, "num_tokens": 135981616.0, "step": 22800 }, { "epoch": 0.24329745127116384, "grad_norm": 0.9867683625730737, "learning_rate": 4.5558195103569266e-05, "loss": 0.8304, "num_tokens": 136006989.0, "step": 22805 }, { "epoch": 0.24335079427736228, "grad_norm": 1.5542356628866512, "learning_rate": 4.5555827134408546e-05, "loss": 0.6356, "num_tokens": 136031603.0, "step": 22810 }, { "epoch": 0.24340413728356075, "grad_norm": 1.7158368595099471, "learning_rate": 4.5553458603387574e-05, "loss": 0.7052, "num_tokens": 136057632.0, "step": 22815 }, { "epoch": 0.24345748028975922, "grad_norm": 1.3573325788275916, "learning_rate": 4.555108951058005e-05, "loss": 0.6552, "num_tokens": 136090585.0, "step": 22820 }, { "epoch": 0.24351082329595766, "grad_norm": 1.5254658287081095, "learning_rate": 4.55487198560597e-05, "loss": 0.6146, "num_tokens": 136117617.0, "step": 22825 }, { "epoch": 0.24356416630215613, "grad_norm": 0.8404248714970918, "learning_rate": 4.554634963990026e-05, "loss": 0.6285, "num_tokens": 136153705.0, "step": 22830 }, { "epoch": 0.24361750930835457, "grad_norm": 1.207032148150547, "learning_rate": 4.5543978862175494e-05, "loss": 0.8359, "num_tokens": 136191007.0, "step": 22835 }, { "epoch": 0.24367085231455304, "grad_norm": 0.7280864669412533, "learning_rate": 4.5541607522959155e-05, "loss": 0.6385, "num_tokens": 136244466.0, "step": 22840 }, { "epoch": 0.24372419532075149, "grad_norm": 0.7863685641212372, "learning_rate": 4.553923562232507e-05, "loss": 0.7025, "num_tokens": 136276629.0, "step": 22845 }, { "epoch": 0.24377753832694996, "grad_norm": 0.8365993423216634, "learning_rate": 4.5536863160347e-05, "loss": 0.5153, "num_tokens": 136311491.0, "step": 22850 }, { "epoch": 0.2438308813331484, "grad_norm": 0.7769151958864293, "learning_rate": 4.553449013709882e-05, "loss": 0.4831, "num_tokens": 136339996.0, "step": 22855 }, { "epoch": 0.24388422433934687, "grad_norm": 0.7369825071901004, "learning_rate": 4.553211655265434e-05, "loss": 0.5948, "num_tokens": 136373237.0, "step": 22860 }, { "epoch": 0.24393756734554534, "grad_norm": 0.7688003780809497, "learning_rate": 4.552974240708743e-05, "loss": 0.5908, "num_tokens": 136414864.0, "step": 22865 }, { "epoch": 0.24399091035174378, "grad_norm": 1.3403137156272262, "learning_rate": 4.552736770047197e-05, "loss": 0.5215, "num_tokens": 136440365.0, "step": 22870 }, { "epoch": 0.24404425335794225, "grad_norm": 1.4171816227624991, "learning_rate": 4.552499243288186e-05, "loss": 0.6426, "num_tokens": 136474753.0, "step": 22875 }, { "epoch": 0.2440975963641407, "grad_norm": 1.021649465704116, "learning_rate": 4.552261660439101e-05, "loss": 0.6857, "num_tokens": 136507786.0, "step": 22880 }, { "epoch": 0.24415093937033916, "grad_norm": 1.6409940509864296, "learning_rate": 4.552024021507335e-05, "loss": 0.6336, "num_tokens": 136538006.0, "step": 22885 }, { "epoch": 0.2442042823765376, "grad_norm": 0.8935186222149683, "learning_rate": 4.551786326500283e-05, "loss": 0.4939, "num_tokens": 136568363.0, "step": 22890 }, { "epoch": 0.24425762538273607, "grad_norm": 0.830738724884765, "learning_rate": 4.551548575425342e-05, "loss": 0.5298, "num_tokens": 136612584.0, "step": 22895 }, { "epoch": 0.2443109683889345, "grad_norm": 1.0669254717456755, "learning_rate": 4.551310768289909e-05, "loss": 0.4723, "num_tokens": 136642421.0, "step": 22900 }, { "epoch": 0.24436431139513298, "grad_norm": 1.1077120555234667, "learning_rate": 4.551072905101385e-05, "loss": 0.6038, "num_tokens": 136685629.0, "step": 22905 }, { "epoch": 0.24441765440133145, "grad_norm": 1.0541762611776049, "learning_rate": 4.5508349858671715e-05, "loss": 0.4944, "num_tokens": 136713825.0, "step": 22910 }, { "epoch": 0.2444709974075299, "grad_norm": 1.1258908388292632, "learning_rate": 4.5505970105946724e-05, "loss": 0.5839, "num_tokens": 136750491.0, "step": 22915 }, { "epoch": 0.24452434041372836, "grad_norm": 1.3411927204215306, "learning_rate": 4.5503589792912935e-05, "loss": 0.6501, "num_tokens": 136788428.0, "step": 22920 }, { "epoch": 0.2445776834199268, "grad_norm": 1.2138991133222023, "learning_rate": 4.550120891964441e-05, "loss": 0.6138, "num_tokens": 136816798.0, "step": 22925 }, { "epoch": 0.24463102642612528, "grad_norm": 0.8264857368637616, "learning_rate": 4.5498827486215234e-05, "loss": 0.5576, "num_tokens": 136849087.0, "step": 22930 }, { "epoch": 0.24468436943232372, "grad_norm": 0.8611623790371025, "learning_rate": 4.5496445492699526e-05, "loss": 0.6186, "num_tokens": 136880714.0, "step": 22935 }, { "epoch": 0.2447377124385222, "grad_norm": 1.0440343348890322, "learning_rate": 4.5494062939171394e-05, "loss": 0.5847, "num_tokens": 136918717.0, "step": 22940 }, { "epoch": 0.24479105544472063, "grad_norm": 1.4417504586004881, "learning_rate": 4.549167982570498e-05, "loss": 0.692, "num_tokens": 136945769.0, "step": 22945 }, { "epoch": 0.2448443984509191, "grad_norm": 1.381651296137981, "learning_rate": 4.548929615237445e-05, "loss": 0.494, "num_tokens": 136964286.0, "step": 22950 }, { "epoch": 0.24489774145711757, "grad_norm": 1.0472701937918396, "learning_rate": 4.5486911919253975e-05, "loss": 0.6621, "num_tokens": 137002768.0, "step": 22955 }, { "epoch": 0.244951084463316, "grad_norm": 1.3507766441296536, "learning_rate": 4.5484527126417745e-05, "loss": 0.5674, "num_tokens": 137032661.0, "step": 22960 }, { "epoch": 0.24500442746951448, "grad_norm": 0.9837674899275333, "learning_rate": 4.548214177393998e-05, "loss": 0.6438, "num_tokens": 137051664.0, "step": 22965 }, { "epoch": 0.24505777047571292, "grad_norm": 2.003451623948852, "learning_rate": 4.5479755861894894e-05, "loss": 0.4881, "num_tokens": 137065807.0, "step": 22970 }, { "epoch": 0.2451111134819114, "grad_norm": 1.027543103708403, "learning_rate": 4.5477369390356734e-05, "loss": 0.6827, "num_tokens": 137096493.0, "step": 22975 }, { "epoch": 0.24516445648810983, "grad_norm": 1.1150502627108998, "learning_rate": 4.547498235939977e-05, "loss": 0.6254, "num_tokens": 137136872.0, "step": 22980 }, { "epoch": 0.2452177994943083, "grad_norm": 1.2541810613382127, "learning_rate": 4.547259476909828e-05, "loss": 0.7405, "num_tokens": 137174539.0, "step": 22985 }, { "epoch": 0.24527114250050674, "grad_norm": 1.2477050727711705, "learning_rate": 4.5470206619526545e-05, "loss": 0.4628, "num_tokens": 137201405.0, "step": 22990 }, { "epoch": 0.24532448550670521, "grad_norm": 0.8122576669185542, "learning_rate": 4.54678179107589e-05, "loss": 0.7365, "num_tokens": 137246233.0, "step": 22995 }, { "epoch": 0.24537782851290368, "grad_norm": 0.7720544002501505, "learning_rate": 4.5465428642869665e-05, "loss": 0.669, "num_tokens": 137305787.0, "step": 23000 }, { "epoch": 0.24543117151910213, "grad_norm": 1.1676139824761524, "learning_rate": 4.5463038815933196e-05, "loss": 0.579, "num_tokens": 137331067.0, "step": 23005 }, { "epoch": 0.2454845145253006, "grad_norm": 1.4886466852114313, "learning_rate": 4.5460648430023856e-05, "loss": 0.6614, "num_tokens": 137367280.0, "step": 23010 }, { "epoch": 0.24553785753149904, "grad_norm": 0.9434855823347631, "learning_rate": 4.5458257485216035e-05, "loss": 0.4768, "num_tokens": 137383641.0, "step": 23015 }, { "epoch": 0.2455912005376975, "grad_norm": 0.7494058257273317, "learning_rate": 4.5455865981584115e-05, "loss": 0.4954, "num_tokens": 137404913.0, "step": 23020 }, { "epoch": 0.24564454354389595, "grad_norm": 1.5213362684361713, "learning_rate": 4.545347391920254e-05, "loss": 0.5089, "num_tokens": 137426326.0, "step": 23025 }, { "epoch": 0.24569788655009442, "grad_norm": 0.848788089450572, "learning_rate": 4.545108129814572e-05, "loss": 0.5827, "num_tokens": 137449564.0, "step": 23030 }, { "epoch": 0.24575122955629286, "grad_norm": 1.3852294969360461, "learning_rate": 4.544868811848814e-05, "loss": 0.6904, "num_tokens": 137493445.0, "step": 23035 }, { "epoch": 0.24580457256249133, "grad_norm": 1.4991791184764285, "learning_rate": 4.5446294380304237e-05, "loss": 0.5295, "num_tokens": 137522281.0, "step": 23040 }, { "epoch": 0.2458579155686898, "grad_norm": 0.8940086814765037, "learning_rate": 4.5443900083668526e-05, "loss": 0.6017, "num_tokens": 137550973.0, "step": 23045 }, { "epoch": 0.24591125857488824, "grad_norm": 0.9770221144836205, "learning_rate": 4.54415052286555e-05, "loss": 0.5616, "num_tokens": 137577603.0, "step": 23050 }, { "epoch": 0.2459646015810867, "grad_norm": 0.6678690295503203, "learning_rate": 4.5439109815339686e-05, "loss": 0.5602, "num_tokens": 137607170.0, "step": 23055 }, { "epoch": 0.24601794458728515, "grad_norm": 1.9104620366552256, "learning_rate": 4.543671384379563e-05, "loss": 0.767, "num_tokens": 137638672.0, "step": 23060 }, { "epoch": 0.24607128759348362, "grad_norm": 1.199780282440975, "learning_rate": 4.543431731409786e-05, "loss": 0.4874, "num_tokens": 137658890.0, "step": 23065 }, { "epoch": 0.24612463059968206, "grad_norm": 1.4463792878839181, "learning_rate": 4.543192022632099e-05, "loss": 0.5587, "num_tokens": 137682205.0, "step": 23070 }, { "epoch": 0.24617797360588053, "grad_norm": 0.7277741682934198, "learning_rate": 4.542952258053959e-05, "loss": 0.7273, "num_tokens": 137713412.0, "step": 23075 }, { "epoch": 0.24623131661207898, "grad_norm": 1.5232841314339358, "learning_rate": 4.542712437682828e-05, "loss": 0.6232, "num_tokens": 137763736.0, "step": 23080 }, { "epoch": 0.24628465961827745, "grad_norm": 0.7620844552404381, "learning_rate": 4.5424725615261674e-05, "loss": 0.6049, "num_tokens": 137798277.0, "step": 23085 }, { "epoch": 0.24633800262447592, "grad_norm": 1.6934392389306279, "learning_rate": 4.5422326295914435e-05, "loss": 0.5192, "num_tokens": 137812015.0, "step": 23090 }, { "epoch": 0.24639134563067436, "grad_norm": 1.6192455960204966, "learning_rate": 4.5419926418861214e-05, "loss": 0.5752, "num_tokens": 137837996.0, "step": 23095 }, { "epoch": 0.24644468863687283, "grad_norm": 0.817186157252562, "learning_rate": 4.541752598417669e-05, "loss": 0.5324, "num_tokens": 137868427.0, "step": 23100 }, { "epoch": 0.24649803164307127, "grad_norm": 1.5157450610564012, "learning_rate": 4.541512499193556e-05, "loss": 0.7235, "num_tokens": 137903903.0, "step": 23105 }, { "epoch": 0.24655137464926974, "grad_norm": 1.377644164052321, "learning_rate": 4.541272344221253e-05, "loss": 0.58, "num_tokens": 137936295.0, "step": 23110 }, { "epoch": 0.24660471765546818, "grad_norm": 1.6344544374199728, "learning_rate": 4.541032133508236e-05, "loss": 0.6454, "num_tokens": 137975101.0, "step": 23115 }, { "epoch": 0.24665806066166665, "grad_norm": 0.6732781669689308, "learning_rate": 4.540791867061977e-05, "loss": 0.5474, "num_tokens": 138027590.0, "step": 23120 }, { "epoch": 0.2467114036678651, "grad_norm": 0.970901387177091, "learning_rate": 4.540551544889953e-05, "loss": 0.6421, "num_tokens": 138054464.0, "step": 23125 }, { "epoch": 0.24676474667406356, "grad_norm": 0.9894429388327214, "learning_rate": 4.5403111669996437e-05, "loss": 0.5662, "num_tokens": 138078420.0, "step": 23130 }, { "epoch": 0.24681808968026203, "grad_norm": 1.2385769550036574, "learning_rate": 4.5400707333985274e-05, "loss": 0.6495, "num_tokens": 138106920.0, "step": 23135 }, { "epoch": 0.24687143268646047, "grad_norm": 1.1564929138603954, "learning_rate": 4.539830244094087e-05, "loss": 0.6266, "num_tokens": 138131884.0, "step": 23140 }, { "epoch": 0.24692477569265894, "grad_norm": 1.276599570871047, "learning_rate": 4.539589699093806e-05, "loss": 0.5708, "num_tokens": 138147954.0, "step": 23145 }, { "epoch": 0.24697811869885739, "grad_norm": 0.91613695189477, "learning_rate": 4.539349098405169e-05, "loss": 0.4967, "num_tokens": 138183719.0, "step": 23150 }, { "epoch": 0.24703146170505585, "grad_norm": 1.3994076561292117, "learning_rate": 4.539108442035664e-05, "loss": 0.681, "num_tokens": 138208433.0, "step": 23155 }, { "epoch": 0.2470848047112543, "grad_norm": 0.7923560424732876, "learning_rate": 4.538867729992779e-05, "loss": 0.5186, "num_tokens": 138231963.0, "step": 23160 }, { "epoch": 0.24713814771745277, "grad_norm": 0.7704059756773296, "learning_rate": 4.538626962284005e-05, "loss": 0.5949, "num_tokens": 138260049.0, "step": 23165 }, { "epoch": 0.2471914907236512, "grad_norm": 1.0373479233118057, "learning_rate": 4.5383861389168337e-05, "loss": 0.5961, "num_tokens": 138278940.0, "step": 23170 }, { "epoch": 0.24724483372984968, "grad_norm": 0.9177184853310705, "learning_rate": 4.538145259898759e-05, "loss": 0.5492, "num_tokens": 138306630.0, "step": 23175 }, { "epoch": 0.24729817673604815, "grad_norm": 1.2424706830443388, "learning_rate": 4.537904325237277e-05, "loss": 0.694, "num_tokens": 138333564.0, "step": 23180 }, { "epoch": 0.2473515197422466, "grad_norm": 0.776107946823516, "learning_rate": 4.537663334939885e-05, "loss": 0.6064, "num_tokens": 138374842.0, "step": 23185 }, { "epoch": 0.24740486274844506, "grad_norm": 1.1018686610532147, "learning_rate": 4.5374222890140816e-05, "loss": 0.5978, "num_tokens": 138398381.0, "step": 23190 }, { "epoch": 0.2474582057546435, "grad_norm": 1.866960693780317, "learning_rate": 4.537181187467368e-05, "loss": 0.5873, "num_tokens": 138423051.0, "step": 23195 }, { "epoch": 0.24751154876084197, "grad_norm": 1.3630844374265485, "learning_rate": 4.536940030307248e-05, "loss": 0.6369, "num_tokens": 138452997.0, "step": 23200 }, { "epoch": 0.2475648917670404, "grad_norm": 1.6689653874370947, "learning_rate": 4.536698817541223e-05, "loss": 0.6324, "num_tokens": 138473882.0, "step": 23205 }, { "epoch": 0.24761823477323888, "grad_norm": 1.3897323033731466, "learning_rate": 4.536457549176802e-05, "loss": 0.495, "num_tokens": 138497166.0, "step": 23210 }, { "epoch": 0.24767157777943732, "grad_norm": 1.8093636598867466, "learning_rate": 4.536216225221491e-05, "loss": 0.6859, "num_tokens": 138522796.0, "step": 23215 }, { "epoch": 0.2477249207856358, "grad_norm": 1.9641704685054302, "learning_rate": 4.5359748456828e-05, "loss": 0.6514, "num_tokens": 138542486.0, "step": 23220 }, { "epoch": 0.24777826379183426, "grad_norm": 0.8996931535184232, "learning_rate": 4.535733410568241e-05, "loss": 0.5659, "num_tokens": 138566584.0, "step": 23225 }, { "epoch": 0.2478316067980327, "grad_norm": 1.1958767530179526, "learning_rate": 4.535491919885325e-05, "loss": 0.6422, "num_tokens": 138609978.0, "step": 23230 }, { "epoch": 0.24788494980423117, "grad_norm": 1.3892472268482237, "learning_rate": 4.5352503736415694e-05, "loss": 0.6776, "num_tokens": 138642725.0, "step": 23235 }, { "epoch": 0.24793829281042962, "grad_norm": 1.0268944149898493, "learning_rate": 4.5350087718444885e-05, "loss": 0.5617, "num_tokens": 138671330.0, "step": 23240 }, { "epoch": 0.2479916358166281, "grad_norm": 0.8641708439748552, "learning_rate": 4.5347671145016005e-05, "loss": 0.5676, "num_tokens": 138705938.0, "step": 23245 }, { "epoch": 0.24804497882282653, "grad_norm": 1.1009443986139642, "learning_rate": 4.534525401620428e-05, "loss": 0.6648, "num_tokens": 138732812.0, "step": 23250 }, { "epoch": 0.248098321829025, "grad_norm": 1.4363612136715498, "learning_rate": 4.534283633208488e-05, "loss": 0.5769, "num_tokens": 138764534.0, "step": 23255 }, { "epoch": 0.24815166483522344, "grad_norm": 1.2196332639144685, "learning_rate": 4.534041809273307e-05, "loss": 0.6556, "num_tokens": 138781673.0, "step": 23260 }, { "epoch": 0.2482050078414219, "grad_norm": 1.2549843721658556, "learning_rate": 4.53379992982241e-05, "loss": 0.4876, "num_tokens": 138814889.0, "step": 23265 }, { "epoch": 0.24825835084762038, "grad_norm": 1.382911187255987, "learning_rate": 4.533557994863323e-05, "loss": 0.5069, "num_tokens": 138843028.0, "step": 23270 }, { "epoch": 0.24831169385381882, "grad_norm": 1.0355362553318102, "learning_rate": 4.533316004403575e-05, "loss": 0.5781, "num_tokens": 138875652.0, "step": 23275 }, { "epoch": 0.2483650368600173, "grad_norm": 0.6124566309508426, "learning_rate": 4.533073958450696e-05, "loss": 0.6374, "num_tokens": 138920117.0, "step": 23280 }, { "epoch": 0.24841837986621573, "grad_norm": 0.7283720223338656, "learning_rate": 4.5328318570122176e-05, "loss": 0.4878, "num_tokens": 138954605.0, "step": 23285 }, { "epoch": 0.2484717228724142, "grad_norm": 1.5225966020459052, "learning_rate": 4.532589700095674e-05, "loss": 0.6281, "num_tokens": 138974368.0, "step": 23290 }, { "epoch": 0.24852506587861264, "grad_norm": 0.8587331506592004, "learning_rate": 4.532347487708601e-05, "loss": 0.5626, "num_tokens": 138995577.0, "step": 23295 }, { "epoch": 0.24857840888481111, "grad_norm": 0.967221649561805, "learning_rate": 4.532105219858535e-05, "loss": 0.4493, "num_tokens": 139018720.0, "step": 23300 }, { "epoch": 0.24863175189100956, "grad_norm": 1.1334864811375167, "learning_rate": 4.531862896553014e-05, "loss": 0.6277, "num_tokens": 139058467.0, "step": 23305 }, { "epoch": 0.24868509489720803, "grad_norm": 0.961898471243908, "learning_rate": 4.531620517799581e-05, "loss": 0.5163, "num_tokens": 139094487.0, "step": 23310 }, { "epoch": 0.2487384379034065, "grad_norm": 0.7399371006777202, "learning_rate": 4.5313780836057764e-05, "loss": 0.5195, "num_tokens": 139122353.0, "step": 23315 }, { "epoch": 0.24879178090960494, "grad_norm": 1.8549088472280664, "learning_rate": 4.531135593979145e-05, "loss": 0.5495, "num_tokens": 139147749.0, "step": 23320 }, { "epoch": 0.2488451239158034, "grad_norm": 0.7884275910568118, "learning_rate": 4.5308930489272324e-05, "loss": 0.5952, "num_tokens": 139178848.0, "step": 23325 }, { "epoch": 0.24889846692200185, "grad_norm": 0.6675594458812736, "learning_rate": 4.530650448457586e-05, "loss": 0.6086, "num_tokens": 139222188.0, "step": 23330 }, { "epoch": 0.24895180992820032, "grad_norm": 1.1959816526089702, "learning_rate": 4.530407792577756e-05, "loss": 0.5804, "num_tokens": 139254795.0, "step": 23335 }, { "epoch": 0.24900515293439876, "grad_norm": 1.160767184665524, "learning_rate": 4.530165081295292e-05, "loss": 0.5348, "num_tokens": 139291184.0, "step": 23340 }, { "epoch": 0.24905849594059723, "grad_norm": 1.0893240384983225, "learning_rate": 4.5299223146177474e-05, "loss": 0.6894, "num_tokens": 139328099.0, "step": 23345 }, { "epoch": 0.24911183894679567, "grad_norm": 2.1007288724578617, "learning_rate": 4.529679492552676e-05, "loss": 0.5038, "num_tokens": 139358883.0, "step": 23350 }, { "epoch": 0.24916518195299414, "grad_norm": 1.1217360546703286, "learning_rate": 4.529436615107635e-05, "loss": 0.5851, "num_tokens": 139388608.0, "step": 23355 }, { "epoch": 0.2492185249591926, "grad_norm": 1.3885609720208427, "learning_rate": 4.529193682290181e-05, "loss": 0.8096, "num_tokens": 139412841.0, "step": 23360 }, { "epoch": 0.24927186796539105, "grad_norm": 1.6450449295586456, "learning_rate": 4.528950694107874e-05, "loss": 0.5577, "num_tokens": 139436677.0, "step": 23365 }, { "epoch": 0.24932521097158952, "grad_norm": 1.2510050849510708, "learning_rate": 4.5287076505682766e-05, "loss": 0.5324, "num_tokens": 139460806.0, "step": 23370 }, { "epoch": 0.24937855397778796, "grad_norm": 1.055267065340127, "learning_rate": 4.52846455167895e-05, "loss": 0.6859, "num_tokens": 139493011.0, "step": 23375 }, { "epoch": 0.24943189698398643, "grad_norm": 1.3317821213942707, "learning_rate": 4.528221397447459e-05, "loss": 0.6023, "num_tokens": 139511999.0, "step": 23380 }, { "epoch": 0.24948523999018488, "grad_norm": 1.1312516320928319, "learning_rate": 4.527978187881371e-05, "loss": 0.5663, "num_tokens": 139532785.0, "step": 23385 }, { "epoch": 0.24953858299638335, "grad_norm": 1.4254782313436427, "learning_rate": 4.527734922988255e-05, "loss": 0.591, "num_tokens": 139564725.0, "step": 23390 }, { "epoch": 0.2495919260025818, "grad_norm": 0.755938596804037, "learning_rate": 4.527491602775679e-05, "loss": 0.6573, "num_tokens": 139603425.0, "step": 23395 }, { "epoch": 0.24964526900878026, "grad_norm": 2.0206541693670874, "learning_rate": 4.527248227251215e-05, "loss": 0.5947, "num_tokens": 139647231.0, "step": 23400 }, { "epoch": 0.24969861201497873, "grad_norm": 0.9837946574358654, "learning_rate": 4.5270047964224374e-05, "loss": 0.583, "num_tokens": 139675925.0, "step": 23405 }, { "epoch": 0.24975195502117717, "grad_norm": 0.7509074539224446, "learning_rate": 4.5267613102969203e-05, "loss": 0.7449, "num_tokens": 139717921.0, "step": 23410 }, { "epoch": 0.24980529802737564, "grad_norm": 1.0090311746418312, "learning_rate": 4.5265177688822404e-05, "loss": 0.6147, "num_tokens": 139746820.0, "step": 23415 }, { "epoch": 0.24985864103357408, "grad_norm": 0.9230679606883294, "learning_rate": 4.526274172185977e-05, "loss": 0.6254, "num_tokens": 139792277.0, "step": 23420 }, { "epoch": 0.24991198403977255, "grad_norm": 0.8190653661354659, "learning_rate": 4.52603052021571e-05, "loss": 0.5346, "num_tokens": 139810185.0, "step": 23425 }, { "epoch": 0.249965327045971, "grad_norm": 1.487104993573777, "learning_rate": 4.525786812979021e-05, "loss": 0.7213, "num_tokens": 139847721.0, "step": 23430 }, { "epoch": 0.25001867005216943, "grad_norm": 1.4517634325775917, "learning_rate": 4.5255430504834946e-05, "loss": 0.6585, "num_tokens": 139858913.0, "step": 23435 }, { "epoch": 0.2500720130583679, "grad_norm": 1.638833832009041, "learning_rate": 4.525299232736715e-05, "loss": 0.6673, "num_tokens": 139888678.0, "step": 23440 }, { "epoch": 0.2501253560645664, "grad_norm": 0.7563393719942207, "learning_rate": 4.52505535974627e-05, "loss": 0.5487, "num_tokens": 139916837.0, "step": 23445 }, { "epoch": 0.25017869907076484, "grad_norm": 0.9302039352203733, "learning_rate": 4.524811431519748e-05, "loss": 0.5178, "num_tokens": 139936396.0, "step": 23450 }, { "epoch": 0.2502320420769633, "grad_norm": 1.2892583822227257, "learning_rate": 4.52456744806474e-05, "loss": 0.5758, "num_tokens": 139957445.0, "step": 23455 }, { "epoch": 0.2502853850831617, "grad_norm": 0.7504915571027255, "learning_rate": 4.5243234093888385e-05, "loss": 0.5648, "num_tokens": 139993351.0, "step": 23460 }, { "epoch": 0.2503387280893602, "grad_norm": 10.279288617351805, "learning_rate": 4.524079315499637e-05, "loss": 1.0332, "num_tokens": 140026313.0, "step": 23465 }, { "epoch": 0.25039207109555867, "grad_norm": 1.5091175793929206, "learning_rate": 4.5238351664047305e-05, "loss": 0.613, "num_tokens": 140055765.0, "step": 23470 }, { "epoch": 0.25044541410175714, "grad_norm": 1.6803770225033325, "learning_rate": 4.523590962111718e-05, "loss": 0.5695, "num_tokens": 140075070.0, "step": 23475 }, { "epoch": 0.25049875710795555, "grad_norm": 1.026351626555413, "learning_rate": 4.523346702628197e-05, "loss": 0.5719, "num_tokens": 140101901.0, "step": 23480 }, { "epoch": 0.250552100114154, "grad_norm": 1.0182517263804745, "learning_rate": 4.523102387961769e-05, "loss": 0.7186, "num_tokens": 140120408.0, "step": 23485 }, { "epoch": 0.2506054431203525, "grad_norm": 0.9839962234609431, "learning_rate": 4.522858018120038e-05, "loss": 0.5408, "num_tokens": 140154207.0, "step": 23490 }, { "epoch": 0.25065878612655096, "grad_norm": 1.3473091866046074, "learning_rate": 4.522613593110606e-05, "loss": 0.5066, "num_tokens": 140170888.0, "step": 23495 }, { "epoch": 0.25071212913274943, "grad_norm": 2.001931947420131, "learning_rate": 4.5223691129410806e-05, "loss": 0.6403, "num_tokens": 140193560.0, "step": 23500 }, { "epoch": 0.25076547213894784, "grad_norm": 1.357325269618234, "learning_rate": 4.522124577619069e-05, "loss": 0.8034, "num_tokens": 140223741.0, "step": 23505 }, { "epoch": 0.2508188151451463, "grad_norm": 1.7387992342157592, "learning_rate": 4.521879987152181e-05, "loss": 0.5726, "num_tokens": 140241606.0, "step": 23510 }, { "epoch": 0.2508721581513448, "grad_norm": 1.5506376110498938, "learning_rate": 4.521635341548025e-05, "loss": 0.475, "num_tokens": 140258506.0, "step": 23515 }, { "epoch": 0.25092550115754325, "grad_norm": 1.5303203553978548, "learning_rate": 4.521390640814219e-05, "loss": 0.6689, "num_tokens": 140291163.0, "step": 23520 }, { "epoch": 0.25097884416374167, "grad_norm": 0.8244238960207821, "learning_rate": 4.521145884958374e-05, "loss": 0.5221, "num_tokens": 140318062.0, "step": 23525 }, { "epoch": 0.25103218716994014, "grad_norm": 1.7096758028679648, "learning_rate": 4.5209010739881065e-05, "loss": 0.5998, "num_tokens": 140338810.0, "step": 23530 }, { "epoch": 0.2510855301761386, "grad_norm": 0.8316363985287243, "learning_rate": 4.5206562079110354e-05, "loss": 0.523, "num_tokens": 140377907.0, "step": 23535 }, { "epoch": 0.2511388731823371, "grad_norm": 1.209947520013252, "learning_rate": 4.52041128673478e-05, "loss": 0.4563, "num_tokens": 140397705.0, "step": 23540 }, { "epoch": 0.25119221618853554, "grad_norm": 0.8954923533557728, "learning_rate": 4.520166310466962e-05, "loss": 0.4672, "num_tokens": 140424002.0, "step": 23545 }, { "epoch": 0.25124555919473396, "grad_norm": 1.0218136225205827, "learning_rate": 4.5199212791152055e-05, "loss": 0.6007, "num_tokens": 140452440.0, "step": 23550 }, { "epoch": 0.25129890220093243, "grad_norm": 0.9556541676882493, "learning_rate": 4.5196761926871326e-05, "loss": 0.7399, "num_tokens": 140484613.0, "step": 23555 }, { "epoch": 0.2513522452071309, "grad_norm": 2.3625882680408554, "learning_rate": 4.519431051190372e-05, "loss": 0.6358, "num_tokens": 140510859.0, "step": 23560 }, { "epoch": 0.25140558821332937, "grad_norm": 0.9717161525269796, "learning_rate": 4.5191858546325526e-05, "loss": 0.6302, "num_tokens": 140558736.0, "step": 23565 }, { "epoch": 0.2514589312195278, "grad_norm": 0.8266881546096099, "learning_rate": 4.518940603021303e-05, "loss": 0.6141, "num_tokens": 140597457.0, "step": 23570 }, { "epoch": 0.25151227422572625, "grad_norm": 2.00704056972004, "learning_rate": 4.5186952963642545e-05, "loss": 0.6235, "num_tokens": 140615116.0, "step": 23575 }, { "epoch": 0.2515656172319247, "grad_norm": 1.248869293083236, "learning_rate": 4.518449934669042e-05, "loss": 0.6149, "num_tokens": 140634309.0, "step": 23580 }, { "epoch": 0.2516189602381232, "grad_norm": 1.0301729060736722, "learning_rate": 4.5182045179433005e-05, "loss": 0.5611, "num_tokens": 140664120.0, "step": 23585 }, { "epoch": 0.25167230324432166, "grad_norm": 1.454306496410828, "learning_rate": 4.517959046194665e-05, "loss": 0.5006, "num_tokens": 140697383.0, "step": 23590 }, { "epoch": 0.2517256462505201, "grad_norm": 1.10710654297595, "learning_rate": 4.5177135194307766e-05, "loss": 0.5673, "num_tokens": 140736311.0, "step": 23595 }, { "epoch": 0.25177898925671854, "grad_norm": 1.1861188995336802, "learning_rate": 4.517467937659275e-05, "loss": 0.5753, "num_tokens": 140756686.0, "step": 23600 }, { "epoch": 0.251832332262917, "grad_norm": 0.6685511981038351, "learning_rate": 4.5172223008878e-05, "loss": 0.7345, "num_tokens": 140811630.0, "step": 23605 }, { "epoch": 0.2518856752691155, "grad_norm": 0.8023200190393709, "learning_rate": 4.5169766091239986e-05, "loss": 0.4824, "num_tokens": 140840611.0, "step": 23610 }, { "epoch": 0.2519390182753139, "grad_norm": 1.542445265031443, "learning_rate": 4.5167308623755136e-05, "loss": 0.6016, "num_tokens": 140862639.0, "step": 23615 }, { "epoch": 0.25199236128151237, "grad_norm": 0.996283492080268, "learning_rate": 4.516485060649994e-05, "loss": 0.5675, "num_tokens": 140886663.0, "step": 23620 }, { "epoch": 0.25204570428771084, "grad_norm": 1.149857441425483, "learning_rate": 4.5162392039550866e-05, "loss": 0.5421, "num_tokens": 140908109.0, "step": 23625 }, { "epoch": 0.2520990472939093, "grad_norm": 1.7812668375792955, "learning_rate": 4.5159932922984435e-05, "loss": 0.7777, "num_tokens": 140923280.0, "step": 23630 }, { "epoch": 0.2521523903001078, "grad_norm": 1.6827867421955847, "learning_rate": 4.515747325687717e-05, "loss": 0.633, "num_tokens": 140944012.0, "step": 23635 }, { "epoch": 0.2522057333063062, "grad_norm": 1.6488394579410928, "learning_rate": 4.51550130413056e-05, "loss": 0.6676, "num_tokens": 140963712.0, "step": 23640 }, { "epoch": 0.25225907631250466, "grad_norm": 1.1449807345170802, "learning_rate": 4.51525522763463e-05, "loss": 0.7722, "num_tokens": 140981834.0, "step": 23645 }, { "epoch": 0.25231241931870313, "grad_norm": 1.2256858261958192, "learning_rate": 4.515009096207582e-05, "loss": 0.6131, "num_tokens": 141020373.0, "step": 23650 }, { "epoch": 0.2523657623249016, "grad_norm": 1.4764327769120513, "learning_rate": 4.5147629098570776e-05, "loss": 0.5993, "num_tokens": 141055724.0, "step": 23655 }, { "epoch": 0.2524191053311, "grad_norm": 1.168681055851669, "learning_rate": 4.514516668590776e-05, "loss": 0.6011, "num_tokens": 141079713.0, "step": 23660 }, { "epoch": 0.2524724483372985, "grad_norm": 0.9649921536789524, "learning_rate": 4.514270372416339e-05, "loss": 0.5775, "num_tokens": 141122873.0, "step": 23665 }, { "epoch": 0.25252579134349695, "grad_norm": 1.1508518966850647, "learning_rate": 4.514024021341433e-05, "loss": 0.5392, "num_tokens": 141138041.0, "step": 23670 }, { "epoch": 0.2525791343496954, "grad_norm": 1.10054415774363, "learning_rate": 4.5137776153737226e-05, "loss": 0.5639, "num_tokens": 141161973.0, "step": 23675 }, { "epoch": 0.2526324773558939, "grad_norm": 0.7806164785970944, "learning_rate": 4.513531154520876e-05, "loss": 0.6676, "num_tokens": 141196084.0, "step": 23680 }, { "epoch": 0.2526858203620923, "grad_norm": 1.016837522027785, "learning_rate": 4.513284638790562e-05, "loss": 0.4627, "num_tokens": 141214180.0, "step": 23685 }, { "epoch": 0.2527391633682908, "grad_norm": 1.4328469775319057, "learning_rate": 4.513038068190452e-05, "loss": 0.4609, "num_tokens": 141235531.0, "step": 23690 }, { "epoch": 0.25279250637448925, "grad_norm": 0.7086343998806148, "learning_rate": 4.512791442728219e-05, "loss": 0.5438, "num_tokens": 141267631.0, "step": 23695 }, { "epoch": 0.2528458493806877, "grad_norm": 1.214057181641647, "learning_rate": 4.5125447624115365e-05, "loss": 0.5956, "num_tokens": 141293305.0, "step": 23700 }, { "epoch": 0.25289919238688613, "grad_norm": 0.8957950346616664, "learning_rate": 4.5122980272480816e-05, "loss": 0.7424, "num_tokens": 141347649.0, "step": 23705 }, { "epoch": 0.2529525353930846, "grad_norm": 0.7272804174656143, "learning_rate": 4.512051237245532e-05, "loss": 0.7984, "num_tokens": 141384606.0, "step": 23710 }, { "epoch": 0.25300587839928307, "grad_norm": 2.2919359640214156, "learning_rate": 4.511804392411567e-05, "loss": 0.8176, "num_tokens": 141429340.0, "step": 23715 }, { "epoch": 0.25305922140548154, "grad_norm": 1.0389283737943154, "learning_rate": 4.5115574927538687e-05, "loss": 0.5123, "num_tokens": 141476840.0, "step": 23720 }, { "epoch": 0.25311256441168, "grad_norm": 1.009436599805928, "learning_rate": 4.51131053828012e-05, "loss": 0.5909, "num_tokens": 141524355.0, "step": 23725 }, { "epoch": 0.2531659074178784, "grad_norm": 0.9983814013485984, "learning_rate": 4.511063528998003e-05, "loss": 0.5995, "num_tokens": 141566155.0, "step": 23730 }, { "epoch": 0.2532192504240769, "grad_norm": 0.6232887696730562, "learning_rate": 4.510816464915208e-05, "loss": 0.6786, "num_tokens": 141601943.0, "step": 23735 }, { "epoch": 0.25327259343027536, "grad_norm": 0.8609836511050318, "learning_rate": 4.510569346039421e-05, "loss": 0.6291, "num_tokens": 141644209.0, "step": 23740 }, { "epoch": 0.25332593643647383, "grad_norm": 1.02541644819472, "learning_rate": 4.5103221723783334e-05, "loss": 0.6427, "num_tokens": 141666108.0, "step": 23745 }, { "epoch": 0.25337927944267225, "grad_norm": 1.0137723916664045, "learning_rate": 4.510074943939634e-05, "loss": 0.5209, "num_tokens": 141691772.0, "step": 23750 }, { "epoch": 0.2534326224488707, "grad_norm": 1.1946068005456445, "learning_rate": 4.509827660731019e-05, "loss": 0.5217, "num_tokens": 141733124.0, "step": 23755 }, { "epoch": 0.2534859654550692, "grad_norm": 1.569626382240761, "learning_rate": 4.509580322760181e-05, "loss": 0.5785, "num_tokens": 141776979.0, "step": 23760 }, { "epoch": 0.25353930846126765, "grad_norm": 0.8365777851674826, "learning_rate": 4.509332930034818e-05, "loss": 0.463, "num_tokens": 141804356.0, "step": 23765 }, { "epoch": 0.2535926514674661, "grad_norm": 1.1742001723911595, "learning_rate": 4.509085482562628e-05, "loss": 0.6098, "num_tokens": 141837076.0, "step": 23770 }, { "epoch": 0.25364599447366454, "grad_norm": 0.8035036517204234, "learning_rate": 4.508837980351311e-05, "loss": 0.7052, "num_tokens": 141872794.0, "step": 23775 }, { "epoch": 0.253699337479863, "grad_norm": 1.0391164024892035, "learning_rate": 4.508590423408569e-05, "loss": 0.5753, "num_tokens": 141895893.0, "step": 23780 }, { "epoch": 0.2537526804860615, "grad_norm": 0.7170447549777669, "learning_rate": 4.508342811742105e-05, "loss": 0.4288, "num_tokens": 141936990.0, "step": 23785 }, { "epoch": 0.25380602349225995, "grad_norm": 2.400389067464482, "learning_rate": 4.5080951453596243e-05, "loss": 0.7136, "num_tokens": 141970433.0, "step": 23790 }, { "epoch": 0.25385936649845836, "grad_norm": 1.186168898573969, "learning_rate": 4.5078474242688344e-05, "loss": 0.5684, "num_tokens": 141995249.0, "step": 23795 }, { "epoch": 0.25391270950465683, "grad_norm": 1.5212910627090686, "learning_rate": 4.507599648477443e-05, "loss": 0.5039, "num_tokens": 142014725.0, "step": 23800 }, { "epoch": 0.2539660525108553, "grad_norm": 1.3736247929414136, "learning_rate": 4.5073518179931615e-05, "loss": 0.4618, "num_tokens": 142042216.0, "step": 23805 }, { "epoch": 0.25401939551705377, "grad_norm": 1.4463639262281691, "learning_rate": 4.5071039328237e-05, "loss": 0.9141, "num_tokens": 142087574.0, "step": 23810 }, { "epoch": 0.25407273852325224, "grad_norm": 1.321299835488556, "learning_rate": 4.506855992976774e-05, "loss": 0.7175, "num_tokens": 142127740.0, "step": 23815 }, { "epoch": 0.25412608152945065, "grad_norm": 2.9172242672372977, "learning_rate": 4.506607998460097e-05, "loss": 0.7647, "num_tokens": 142153415.0, "step": 23820 }, { "epoch": 0.2541794245356491, "grad_norm": 0.8094989848013525, "learning_rate": 4.506359949281389e-05, "loss": 0.5567, "num_tokens": 142193971.0, "step": 23825 }, { "epoch": 0.2542327675418476, "grad_norm": 1.0126394664864364, "learning_rate": 4.506111845448366e-05, "loss": 0.6428, "num_tokens": 142230007.0, "step": 23830 }, { "epoch": 0.25428611054804606, "grad_norm": 0.9019655066331325, "learning_rate": 4.50586368696875e-05, "loss": 0.5879, "num_tokens": 142247480.0, "step": 23835 }, { "epoch": 0.2543394535542445, "grad_norm": 1.460292361923047, "learning_rate": 4.505615473850263e-05, "loss": 0.5973, "num_tokens": 142280107.0, "step": 23840 }, { "epoch": 0.25439279656044295, "grad_norm": 0.894563944516109, "learning_rate": 4.505367206100628e-05, "loss": 0.8122, "num_tokens": 142325009.0, "step": 23845 }, { "epoch": 0.2544461395666414, "grad_norm": 1.0721289076160085, "learning_rate": 4.505118883727571e-05, "loss": 0.6074, "num_tokens": 142339640.0, "step": 23850 }, { "epoch": 0.2544994825728399, "grad_norm": 1.227716040292494, "learning_rate": 4.5048705067388195e-05, "loss": 0.7361, "num_tokens": 142369646.0, "step": 23855 }, { "epoch": 0.25455282557903836, "grad_norm": 1.1957123406324677, "learning_rate": 4.504622075142103e-05, "loss": 0.5676, "num_tokens": 142398388.0, "step": 23860 }, { "epoch": 0.25460616858523677, "grad_norm": 1.2556627686268054, "learning_rate": 4.5043735889451516e-05, "loss": 0.6304, "num_tokens": 142438082.0, "step": 23865 }, { "epoch": 0.25465951159143524, "grad_norm": 1.2322311059275701, "learning_rate": 4.504125048155697e-05, "loss": 0.5144, "num_tokens": 142471371.0, "step": 23870 }, { "epoch": 0.2547128545976337, "grad_norm": 2.293274656199517, "learning_rate": 4.5038764527814745e-05, "loss": 0.7051, "num_tokens": 142506988.0, "step": 23875 }, { "epoch": 0.2547661976038322, "grad_norm": 1.5336605160175918, "learning_rate": 4.503627802830219e-05, "loss": 0.6533, "num_tokens": 142542929.0, "step": 23880 }, { "epoch": 0.2548195406100306, "grad_norm": 1.0867987106430619, "learning_rate": 4.503379098309668e-05, "loss": 0.5031, "num_tokens": 142567575.0, "step": 23885 }, { "epoch": 0.25487288361622906, "grad_norm": 1.3482422114341024, "learning_rate": 4.503130339227563e-05, "loss": 0.6142, "num_tokens": 142588666.0, "step": 23890 }, { "epoch": 0.25492622662242753, "grad_norm": 1.2794103620226678, "learning_rate": 4.502881525591641e-05, "loss": 0.7123, "num_tokens": 142633664.0, "step": 23895 }, { "epoch": 0.254979569628626, "grad_norm": 1.094901308559169, "learning_rate": 4.5026326574096466e-05, "loss": 0.6903, "num_tokens": 142663186.0, "step": 23900 }, { "epoch": 0.25503291263482447, "grad_norm": 1.238472070282181, "learning_rate": 4.5023837346893245e-05, "loss": 0.6613, "num_tokens": 142680276.0, "step": 23905 }, { "epoch": 0.2550862556410229, "grad_norm": 0.852210472423108, "learning_rate": 4.50213475743842e-05, "loss": 0.5232, "num_tokens": 142719512.0, "step": 23910 }, { "epoch": 0.25513959864722136, "grad_norm": 1.1742387593594712, "learning_rate": 4.50188572566468e-05, "loss": 0.6286, "num_tokens": 142750101.0, "step": 23915 }, { "epoch": 0.2551929416534198, "grad_norm": 1.058626079921383, "learning_rate": 4.501636639375856e-05, "loss": 0.5646, "num_tokens": 142789534.0, "step": 23920 }, { "epoch": 0.2552462846596183, "grad_norm": 0.965477463119449, "learning_rate": 4.501387498579696e-05, "loss": 0.5228, "num_tokens": 142816259.0, "step": 23925 }, { "epoch": 0.2552996276658167, "grad_norm": 1.7745068504820143, "learning_rate": 4.501138303283956e-05, "loss": 0.6848, "num_tokens": 142844941.0, "step": 23930 }, { "epoch": 0.2553529706720152, "grad_norm": 1.2279405485423187, "learning_rate": 4.500889053496388e-05, "loss": 0.6642, "num_tokens": 142872250.0, "step": 23935 }, { "epoch": 0.25540631367821365, "grad_norm": 1.3928646149561268, "learning_rate": 4.50063974922475e-05, "loss": 0.5478, "num_tokens": 142899762.0, "step": 23940 }, { "epoch": 0.2554596566844121, "grad_norm": 0.6751686790021869, "learning_rate": 4.5003903904767986e-05, "loss": 0.6607, "num_tokens": 142942600.0, "step": 23945 }, { "epoch": 0.2555129996906106, "grad_norm": 1.1174870782514812, "learning_rate": 4.500140977260294e-05, "loss": 0.6621, "num_tokens": 142972057.0, "step": 23950 }, { "epoch": 0.255566342696809, "grad_norm": 1.9039962711785308, "learning_rate": 4.499891509582996e-05, "loss": 0.6033, "num_tokens": 142998503.0, "step": 23955 }, { "epoch": 0.25561968570300747, "grad_norm": 0.8801898712546539, "learning_rate": 4.499641987452669e-05, "loss": 0.5132, "num_tokens": 143022885.0, "step": 23960 }, { "epoch": 0.25567302870920594, "grad_norm": 1.094413561988589, "learning_rate": 4.499392410877078e-05, "loss": 0.5783, "num_tokens": 143063856.0, "step": 23965 }, { "epoch": 0.2557263717154044, "grad_norm": 1.6905947615112722, "learning_rate": 4.499142779863988e-05, "loss": 0.5412, "num_tokens": 143098836.0, "step": 23970 }, { "epoch": 0.2557797147216028, "grad_norm": 0.9628564707470473, "learning_rate": 4.498893094421167e-05, "loss": 0.6491, "num_tokens": 143123051.0, "step": 23975 }, { "epoch": 0.2558330577278013, "grad_norm": 1.6936953498688458, "learning_rate": 4.4986433545563856e-05, "loss": 0.5882, "num_tokens": 143144047.0, "step": 23980 }, { "epoch": 0.25588640073399976, "grad_norm": 0.9862452493075404, "learning_rate": 4.4983935602774155e-05, "loss": 0.781, "num_tokens": 143193395.0, "step": 23985 }, { "epoch": 0.25593974374019823, "grad_norm": 0.8866061470952168, "learning_rate": 4.4981437115920285e-05, "loss": 0.5522, "num_tokens": 143216216.0, "step": 23990 }, { "epoch": 0.2559930867463967, "grad_norm": 1.1634206777547973, "learning_rate": 4.497893808508e-05, "loss": 0.5831, "num_tokens": 143244231.0, "step": 23995 }, { "epoch": 0.2560464297525951, "grad_norm": 2.4885094776610517, "learning_rate": 4.497643851033107e-05, "loss": 0.6647, "num_tokens": 143277757.0, "step": 24000 }, { "epoch": 0.2560997727587936, "grad_norm": 1.0176927873339385, "learning_rate": 4.4973938391751265e-05, "loss": 0.6373, "num_tokens": 143310304.0, "step": 24005 }, { "epoch": 0.25615311576499206, "grad_norm": 0.9768588527017038, "learning_rate": 4.497143772941839e-05, "loss": 0.7404, "num_tokens": 143337359.0, "step": 24010 }, { "epoch": 0.2562064587711905, "grad_norm": 1.0663002680966776, "learning_rate": 4.496893652341026e-05, "loss": 0.5216, "num_tokens": 143358602.0, "step": 24015 }, { "epoch": 0.25625980177738894, "grad_norm": 1.3427581210531114, "learning_rate": 4.49664347738047e-05, "loss": 0.6634, "num_tokens": 143395406.0, "step": 24020 }, { "epoch": 0.2563131447835874, "grad_norm": 1.6953404802797074, "learning_rate": 4.496393248067958e-05, "loss": 0.6086, "num_tokens": 143428937.0, "step": 24025 }, { "epoch": 0.2563664877897859, "grad_norm": 2.009353927761207, "learning_rate": 4.496142964411275e-05, "loss": 0.674, "num_tokens": 143457273.0, "step": 24030 }, { "epoch": 0.25641983079598435, "grad_norm": 0.7656442121578988, "learning_rate": 4.49589262641821e-05, "loss": 0.5897, "num_tokens": 143489272.0, "step": 24035 }, { "epoch": 0.2564731738021828, "grad_norm": 1.0377737229973998, "learning_rate": 4.495642234096552e-05, "loss": 0.6615, "num_tokens": 143536464.0, "step": 24040 }, { "epoch": 0.25652651680838123, "grad_norm": 1.0333092743019208, "learning_rate": 4.4953917874540935e-05, "loss": 0.6756, "num_tokens": 143558741.0, "step": 24045 }, { "epoch": 0.2565798598145797, "grad_norm": 0.8686022642763137, "learning_rate": 4.4951412864986276e-05, "loss": 0.6124, "num_tokens": 143580721.0, "step": 24050 }, { "epoch": 0.2566332028207782, "grad_norm": 0.9117683187258685, "learning_rate": 4.4948907312379495e-05, "loss": 0.5933, "num_tokens": 143599407.0, "step": 24055 }, { "epoch": 0.25668654582697664, "grad_norm": 1.0642518963354575, "learning_rate": 4.494640121679856e-05, "loss": 0.6179, "num_tokens": 143640206.0, "step": 24060 }, { "epoch": 0.25673988883317506, "grad_norm": 2.386815940687978, "learning_rate": 4.4943894578321454e-05, "loss": 0.732, "num_tokens": 143662155.0, "step": 24065 }, { "epoch": 0.2567932318393735, "grad_norm": 1.4186430669380674, "learning_rate": 4.494138739702618e-05, "loss": 0.5041, "num_tokens": 143688500.0, "step": 24070 }, { "epoch": 0.256846574845572, "grad_norm": 0.9019487058739376, "learning_rate": 4.4938879672990764e-05, "loss": 0.7305, "num_tokens": 143733217.0, "step": 24075 }, { "epoch": 0.25689991785177047, "grad_norm": 1.1547815764118885, "learning_rate": 4.4936371406293224e-05, "loss": 0.5284, "num_tokens": 143764332.0, "step": 24080 }, { "epoch": 0.25695326085796893, "grad_norm": 0.84833061526444, "learning_rate": 4.493386259701162e-05, "loss": 0.6136, "num_tokens": 143805552.0, "step": 24085 }, { "epoch": 0.25700660386416735, "grad_norm": 0.8364584897050182, "learning_rate": 4.493135324522403e-05, "loss": 0.5625, "num_tokens": 143826948.0, "step": 24090 }, { "epoch": 0.2570599468703658, "grad_norm": 1.071794627939976, "learning_rate": 4.492884335100853e-05, "loss": 0.676, "num_tokens": 143851989.0, "step": 24095 }, { "epoch": 0.2571132898765643, "grad_norm": 1.1460372378593848, "learning_rate": 4.492633291444322e-05, "loss": 0.5412, "num_tokens": 143889927.0, "step": 24100 }, { "epoch": 0.25716663288276276, "grad_norm": 0.8090923283752481, "learning_rate": 4.492382193560622e-05, "loss": 0.492, "num_tokens": 143918066.0, "step": 24105 }, { "epoch": 0.25721997588896117, "grad_norm": 0.6730983141039942, "learning_rate": 4.492131041457568e-05, "loss": 0.5239, "num_tokens": 143943931.0, "step": 24110 }, { "epoch": 0.25727331889515964, "grad_norm": 1.3885612820913922, "learning_rate": 4.491879835142974e-05, "loss": 0.5984, "num_tokens": 143975667.0, "step": 24115 }, { "epoch": 0.2573266619013581, "grad_norm": 0.7634745249142676, "learning_rate": 4.491628574624658e-05, "loss": 0.5427, "num_tokens": 144005601.0, "step": 24120 }, { "epoch": 0.2573800049075566, "grad_norm": 1.3508426013069588, "learning_rate": 4.491377259910437e-05, "loss": 0.4769, "num_tokens": 144026142.0, "step": 24125 }, { "epoch": 0.25743334791375505, "grad_norm": 0.8889095558889496, "learning_rate": 4.491125891008134e-05, "loss": 0.6346, "num_tokens": 144047445.0, "step": 24130 }, { "epoch": 0.25748669091995346, "grad_norm": 0.7741649238600868, "learning_rate": 4.490874467925569e-05, "loss": 0.6061, "num_tokens": 144072847.0, "step": 24135 }, { "epoch": 0.25754003392615193, "grad_norm": 1.35982802224424, "learning_rate": 4.490622990670566e-05, "loss": 0.6342, "num_tokens": 144088444.0, "step": 24140 }, { "epoch": 0.2575933769323504, "grad_norm": 0.9416114066678962, "learning_rate": 4.4903714592509514e-05, "loss": 0.6848, "num_tokens": 144124292.0, "step": 24145 }, { "epoch": 0.2576467199385489, "grad_norm": 0.8764467106116053, "learning_rate": 4.490119873674552e-05, "loss": 0.6034, "num_tokens": 144164258.0, "step": 24150 }, { "epoch": 0.2577000629447473, "grad_norm": 1.4774480859195172, "learning_rate": 4.489868233949196e-05, "loss": 0.5963, "num_tokens": 144181080.0, "step": 24155 }, { "epoch": 0.25775340595094576, "grad_norm": 0.8532832563950355, "learning_rate": 4.489616540082715e-05, "loss": 0.6236, "num_tokens": 144208145.0, "step": 24160 }, { "epoch": 0.2578067489571442, "grad_norm": 0.9847409122368659, "learning_rate": 4.4893647920829394e-05, "loss": 0.6071, "num_tokens": 144248680.0, "step": 24165 }, { "epoch": 0.2578600919633427, "grad_norm": 2.0558961894022945, "learning_rate": 4.489112989957705e-05, "loss": 0.7101, "num_tokens": 144268598.0, "step": 24170 }, { "epoch": 0.25791343496954117, "grad_norm": 1.4674797033347733, "learning_rate": 4.488861133714846e-05, "loss": 0.7109, "num_tokens": 144297679.0, "step": 24175 }, { "epoch": 0.2579667779757396, "grad_norm": 0.9611013670303211, "learning_rate": 4.4886092233622016e-05, "loss": 0.6382, "num_tokens": 144337966.0, "step": 24180 }, { "epoch": 0.25802012098193805, "grad_norm": 1.4987307535480572, "learning_rate": 4.488357258907608e-05, "loss": 0.6162, "num_tokens": 144368413.0, "step": 24185 }, { "epoch": 0.2580734639881365, "grad_norm": 0.7768317360320851, "learning_rate": 4.4881052403589077e-05, "loss": 0.6779, "num_tokens": 144416953.0, "step": 24190 }, { "epoch": 0.258126806994335, "grad_norm": 1.1805984315195837, "learning_rate": 4.4878531677239425e-05, "loss": 0.6685, "num_tokens": 144436371.0, "step": 24195 }, { "epoch": 0.2581801500005334, "grad_norm": 1.2466960604287252, "learning_rate": 4.487601041010556e-05, "loss": 0.5733, "num_tokens": 144461007.0, "step": 24200 }, { "epoch": 0.2582334930067319, "grad_norm": 1.0116459217353129, "learning_rate": 4.487348860226594e-05, "loss": 0.5008, "num_tokens": 144477532.0, "step": 24205 }, { "epoch": 0.25828683601293034, "grad_norm": 0.82401872266614, "learning_rate": 4.487096625379905e-05, "loss": 0.6292, "num_tokens": 144499062.0, "step": 24210 }, { "epoch": 0.2583401790191288, "grad_norm": 1.5926047739647413, "learning_rate": 4.486844336478337e-05, "loss": 0.5306, "num_tokens": 144514764.0, "step": 24215 }, { "epoch": 0.2583935220253273, "grad_norm": 1.2150125291457168, "learning_rate": 4.4865919935297404e-05, "loss": 0.6428, "num_tokens": 144541965.0, "step": 24220 }, { "epoch": 0.2584468650315257, "grad_norm": 1.2397610711264009, "learning_rate": 4.486339596541969e-05, "loss": 0.5135, "num_tokens": 144555795.0, "step": 24225 }, { "epoch": 0.25850020803772417, "grad_norm": 1.378918204541226, "learning_rate": 4.486087145522875e-05, "loss": 0.5405, "num_tokens": 144578057.0, "step": 24230 }, { "epoch": 0.25855355104392264, "grad_norm": 0.8021620645407114, "learning_rate": 4.485834640480315e-05, "loss": 0.5106, "num_tokens": 144606176.0, "step": 24235 }, { "epoch": 0.2586068940501211, "grad_norm": 1.1348385432245631, "learning_rate": 4.485582081422146e-05, "loss": 0.5487, "num_tokens": 144640269.0, "step": 24240 }, { "epoch": 0.2586602370563195, "grad_norm": 1.1197435885186326, "learning_rate": 4.485329468356229e-05, "loss": 0.49, "num_tokens": 144665209.0, "step": 24245 }, { "epoch": 0.258713580062518, "grad_norm": 0.8744562845265723, "learning_rate": 4.485076801290422e-05, "loss": 0.4545, "num_tokens": 144684039.0, "step": 24250 }, { "epoch": 0.25876692306871646, "grad_norm": 1.7605825763829357, "learning_rate": 4.4848240802325896e-05, "loss": 0.6301, "num_tokens": 144717035.0, "step": 24255 }, { "epoch": 0.25882026607491493, "grad_norm": 0.9893530434039854, "learning_rate": 4.4845713051905954e-05, "loss": 0.6732, "num_tokens": 144748459.0, "step": 24260 }, { "epoch": 0.2588736090811134, "grad_norm": 1.6922663850743234, "learning_rate": 4.484318476172305e-05, "loss": 0.6964, "num_tokens": 144785506.0, "step": 24265 }, { "epoch": 0.2589269520873118, "grad_norm": 1.148264531905828, "learning_rate": 4.4840655931855866e-05, "loss": 0.6641, "num_tokens": 144820224.0, "step": 24270 }, { "epoch": 0.2589802950935103, "grad_norm": 0.9986321527059766, "learning_rate": 4.483812656238308e-05, "loss": 0.4671, "num_tokens": 144842675.0, "step": 24275 }, { "epoch": 0.25903363809970875, "grad_norm": 1.260703523203701, "learning_rate": 4.483559665338341e-05, "loss": 0.5407, "num_tokens": 144870387.0, "step": 24280 }, { "epoch": 0.2590869811059072, "grad_norm": 0.9698242582287687, "learning_rate": 4.483306620493558e-05, "loss": 0.5296, "num_tokens": 144909912.0, "step": 24285 }, { "epoch": 0.25914032411210564, "grad_norm": 1.6502428489600371, "learning_rate": 4.483053521711833e-05, "loss": 0.667, "num_tokens": 144931634.0, "step": 24290 }, { "epoch": 0.2591936671183041, "grad_norm": 0.7352948427005667, "learning_rate": 4.482800369001043e-05, "loss": 0.688, "num_tokens": 144965770.0, "step": 24295 }, { "epoch": 0.2592470101245026, "grad_norm": 0.9779595700297273, "learning_rate": 4.482547162369065e-05, "loss": 0.649, "num_tokens": 145005906.0, "step": 24300 }, { "epoch": 0.25930035313070104, "grad_norm": 0.9093140716602359, "learning_rate": 4.4822939018237765e-05, "loss": 0.5346, "num_tokens": 145046696.0, "step": 24305 }, { "epoch": 0.2593536961368995, "grad_norm": 1.202841143536248, "learning_rate": 4.482040587373061e-05, "loss": 0.6104, "num_tokens": 145071804.0, "step": 24310 }, { "epoch": 0.25940703914309793, "grad_norm": 0.759372907222425, "learning_rate": 4.4817872190248e-05, "loss": 0.6909, "num_tokens": 145115126.0, "step": 24315 }, { "epoch": 0.2594603821492964, "grad_norm": 1.0460026830435034, "learning_rate": 4.4815337967868776e-05, "loss": 0.5827, "num_tokens": 145136704.0, "step": 24320 }, { "epoch": 0.25951372515549487, "grad_norm": 1.1231533148041197, "learning_rate": 4.481280320667181e-05, "loss": 0.5545, "num_tokens": 145159522.0, "step": 24325 }, { "epoch": 0.25956706816169334, "grad_norm": 0.8454285247234277, "learning_rate": 4.481026790673596e-05, "loss": 0.5784, "num_tokens": 145186728.0, "step": 24330 }, { "epoch": 0.25962041116789175, "grad_norm": 0.8601828396579371, "learning_rate": 4.480773206814014e-05, "loss": 0.6346, "num_tokens": 145212963.0, "step": 24335 }, { "epoch": 0.2596737541740902, "grad_norm": 0.660599156510562, "learning_rate": 4.480519569096324e-05, "loss": 0.5537, "num_tokens": 145246405.0, "step": 24340 }, { "epoch": 0.2597270971802887, "grad_norm": 0.9219860542855322, "learning_rate": 4.48026587752842e-05, "loss": 0.5827, "num_tokens": 145281131.0, "step": 24345 }, { "epoch": 0.25978044018648716, "grad_norm": 0.9544209617379301, "learning_rate": 4.480012132118196e-05, "loss": 0.757, "num_tokens": 145300715.0, "step": 24350 }, { "epoch": 0.25983378319268563, "grad_norm": 1.689710610138226, "learning_rate": 4.479758332873548e-05, "loss": 0.5524, "num_tokens": 145329915.0, "step": 24355 }, { "epoch": 0.25988712619888404, "grad_norm": 1.402897701723838, "learning_rate": 4.479504479802373e-05, "loss": 0.549, "num_tokens": 145373067.0, "step": 24360 }, { "epoch": 0.2599404692050825, "grad_norm": 1.2496326103279485, "learning_rate": 4.479250572912572e-05, "loss": 0.5634, "num_tokens": 145420868.0, "step": 24365 }, { "epoch": 0.259993812211281, "grad_norm": 1.1380289238746117, "learning_rate": 4.478996612212045e-05, "loss": 0.5045, "num_tokens": 145446983.0, "step": 24370 }, { "epoch": 0.26004715521747945, "grad_norm": 1.0743134329596982, "learning_rate": 4.478742597708695e-05, "loss": 0.4735, "num_tokens": 145462608.0, "step": 24375 }, { "epoch": 0.26010049822367787, "grad_norm": 1.2078901234745105, "learning_rate": 4.478488529410426e-05, "loss": 0.5959, "num_tokens": 145494660.0, "step": 24380 }, { "epoch": 0.26015384122987634, "grad_norm": 1.0441899635235048, "learning_rate": 4.478234407325144e-05, "loss": 0.5896, "num_tokens": 145517817.0, "step": 24385 }, { "epoch": 0.2602071842360748, "grad_norm": 0.8873689939335363, "learning_rate": 4.477980231460757e-05, "loss": 0.5532, "num_tokens": 145545816.0, "step": 24390 }, { "epoch": 0.2602605272422733, "grad_norm": 1.442580649961837, "learning_rate": 4.477726001825176e-05, "loss": 0.5441, "num_tokens": 145570231.0, "step": 24395 }, { "epoch": 0.26031387024847175, "grad_norm": 1.5116184282820107, "learning_rate": 4.477471718426309e-05, "loss": 0.6708, "num_tokens": 145603908.0, "step": 24400 }, { "epoch": 0.26036721325467016, "grad_norm": 1.0492127166583396, "learning_rate": 4.477217381272071e-05, "loss": 0.6285, "num_tokens": 145647395.0, "step": 24405 }, { "epoch": 0.26042055626086863, "grad_norm": 0.7262495644811371, "learning_rate": 4.4769629903703766e-05, "loss": 0.7186, "num_tokens": 145686116.0, "step": 24410 }, { "epoch": 0.2604738992670671, "grad_norm": 1.4879587598168391, "learning_rate": 4.476708545729141e-05, "loss": 0.6296, "num_tokens": 145712154.0, "step": 24415 }, { "epoch": 0.26052724227326557, "grad_norm": 1.0834190690381653, "learning_rate": 4.4764540473562816e-05, "loss": 0.6349, "num_tokens": 145742428.0, "step": 24420 }, { "epoch": 0.260580585279464, "grad_norm": 0.756605410738157, "learning_rate": 4.4761994952597186e-05, "loss": 0.4871, "num_tokens": 145769573.0, "step": 24425 }, { "epoch": 0.26063392828566245, "grad_norm": 0.9770910418718242, "learning_rate": 4.475944889447374e-05, "loss": 0.5251, "num_tokens": 145793067.0, "step": 24430 }, { "epoch": 0.2606872712918609, "grad_norm": 1.9818790816148557, "learning_rate": 4.4756902299271686e-05, "loss": 0.5692, "num_tokens": 145821773.0, "step": 24435 }, { "epoch": 0.2607406142980594, "grad_norm": 1.4139929173862227, "learning_rate": 4.4754355167070286e-05, "loss": 0.5576, "num_tokens": 145849146.0, "step": 24440 }, { "epoch": 0.26079395730425786, "grad_norm": 0.9802284350395546, "learning_rate": 4.475180749794878e-05, "loss": 0.6549, "num_tokens": 145882246.0, "step": 24445 }, { "epoch": 0.2608473003104563, "grad_norm": 1.2778520856440074, "learning_rate": 4.474925929198648e-05, "loss": 0.6211, "num_tokens": 145914548.0, "step": 24450 }, { "epoch": 0.26090064331665475, "grad_norm": 0.7644706252175177, "learning_rate": 4.474671054926265e-05, "loss": 0.5484, "num_tokens": 145943099.0, "step": 24455 }, { "epoch": 0.2609539863228532, "grad_norm": 1.2928763147827675, "learning_rate": 4.4744161269856624e-05, "loss": 0.5498, "num_tokens": 145975506.0, "step": 24460 }, { "epoch": 0.2610073293290517, "grad_norm": 0.6959882859529712, "learning_rate": 4.47416114538477e-05, "loss": 0.4961, "num_tokens": 146019219.0, "step": 24465 }, { "epoch": 0.2610606723352501, "grad_norm": 1.5057068882696203, "learning_rate": 4.4739061101315264e-05, "loss": 0.668, "num_tokens": 146048066.0, "step": 24470 }, { "epoch": 0.26111401534144857, "grad_norm": 1.0594486922256992, "learning_rate": 4.4736510212338646e-05, "loss": 0.6193, "num_tokens": 146077966.0, "step": 24475 }, { "epoch": 0.26116735834764704, "grad_norm": 1.3790321980215599, "learning_rate": 4.473395878699724e-05, "loss": 0.5984, "num_tokens": 146097501.0, "step": 24480 }, { "epoch": 0.2612207013538455, "grad_norm": 0.8474351706608931, "learning_rate": 4.473140682537043e-05, "loss": 0.5558, "num_tokens": 146144662.0, "step": 24485 }, { "epoch": 0.261274044360044, "grad_norm": 1.0553439154752728, "learning_rate": 4.472885432753764e-05, "loss": 0.522, "num_tokens": 146183250.0, "step": 24490 }, { "epoch": 0.2613273873662424, "grad_norm": 5.239691756525987, "learning_rate": 4.472630129357829e-05, "loss": 0.6772, "num_tokens": 146212736.0, "step": 24495 }, { "epoch": 0.26138073037244086, "grad_norm": 1.0411434622217564, "learning_rate": 4.4723747723571826e-05, "loss": 0.635, "num_tokens": 146244526.0, "step": 24500 }, { "epoch": 0.26143407337863933, "grad_norm": 1.3904665305846735, "learning_rate": 4.472119361759772e-05, "loss": 0.649, "num_tokens": 146271984.0, "step": 24505 }, { "epoch": 0.2614874163848378, "grad_norm": 0.6768148270357474, "learning_rate": 4.471863897573542e-05, "loss": 0.569, "num_tokens": 146313011.0, "step": 24510 }, { "epoch": 0.2615407593910362, "grad_norm": 0.7566760331459779, "learning_rate": 4.4716083798064465e-05, "loss": 0.5823, "num_tokens": 146354063.0, "step": 24515 }, { "epoch": 0.2615941023972347, "grad_norm": 0.9072111786827741, "learning_rate": 4.471352808466433e-05, "loss": 0.6282, "num_tokens": 146393870.0, "step": 24520 }, { "epoch": 0.26164744540343315, "grad_norm": 1.3109991138491872, "learning_rate": 4.471097183561457e-05, "loss": 0.714, "num_tokens": 146411032.0, "step": 24525 }, { "epoch": 0.2617007884096316, "grad_norm": 0.6553885594996154, "learning_rate": 4.470841505099472e-05, "loss": 0.5813, "num_tokens": 146448889.0, "step": 24530 }, { "epoch": 0.2617541314158301, "grad_norm": 0.8805114733025192, "learning_rate": 4.470585773088433e-05, "loss": 0.5274, "num_tokens": 146476090.0, "step": 24535 }, { "epoch": 0.2618074744220285, "grad_norm": 1.1007230231573655, "learning_rate": 4.4703299875363e-05, "loss": 0.5278, "num_tokens": 146506080.0, "step": 24540 }, { "epoch": 0.261860817428227, "grad_norm": 0.9126756779546995, "learning_rate": 4.470074148451031e-05, "loss": 0.4883, "num_tokens": 146525639.0, "step": 24545 }, { "epoch": 0.26191416043442545, "grad_norm": 0.949288090903135, "learning_rate": 4.469818255840588e-05, "loss": 0.5797, "num_tokens": 146547118.0, "step": 24550 }, { "epoch": 0.2619675034406239, "grad_norm": 0.8095363652514804, "learning_rate": 4.4695623097129325e-05, "loss": 0.4651, "num_tokens": 146576555.0, "step": 24555 }, { "epoch": 0.26202084644682233, "grad_norm": 1.021377562379937, "learning_rate": 4.46930631007603e-05, "loss": 0.5869, "num_tokens": 146602656.0, "step": 24560 }, { "epoch": 0.2620741894530208, "grad_norm": 1.1773049178736696, "learning_rate": 4.4690502569378475e-05, "loss": 0.5876, "num_tokens": 146622901.0, "step": 24565 }, { "epoch": 0.26212753245921927, "grad_norm": 1.445601309949435, "learning_rate": 4.468794150306352e-05, "loss": 0.6496, "num_tokens": 146658410.0, "step": 24570 }, { "epoch": 0.26218087546541774, "grad_norm": 1.0426839393624667, "learning_rate": 4.468537990189513e-05, "loss": 0.5641, "num_tokens": 146681439.0, "step": 24575 }, { "epoch": 0.2622342184716162, "grad_norm": 1.513455138854569, "learning_rate": 4.4682817765953014e-05, "loss": 0.6019, "num_tokens": 146695886.0, "step": 24580 }, { "epoch": 0.2622875614778146, "grad_norm": 1.303790014190387, "learning_rate": 4.468025509531691e-05, "loss": 0.4846, "num_tokens": 146720109.0, "step": 24585 }, { "epoch": 0.2623409044840131, "grad_norm": 1.2772195679319027, "learning_rate": 4.4677691890066554e-05, "loss": 0.5824, "num_tokens": 146744092.0, "step": 24590 }, { "epoch": 0.26239424749021156, "grad_norm": 0.9302608682790376, "learning_rate": 4.46751281502817e-05, "loss": 0.5835, "num_tokens": 146776190.0, "step": 24595 }, { "epoch": 0.26244759049641003, "grad_norm": 0.9577372812660494, "learning_rate": 4.467256387604215e-05, "loss": 0.6913, "num_tokens": 146795523.0, "step": 24600 }, { "epoch": 0.26250093350260845, "grad_norm": 0.919731086736508, "learning_rate": 4.466999906742768e-05, "loss": 0.6694, "num_tokens": 146809980.0, "step": 24605 }, { "epoch": 0.2625542765088069, "grad_norm": 0.9849340958907622, "learning_rate": 4.466743372451811e-05, "loss": 0.5661, "num_tokens": 146847075.0, "step": 24610 }, { "epoch": 0.2626076195150054, "grad_norm": 0.8794025726838548, "learning_rate": 4.4664867847393265e-05, "loss": 0.8087, "num_tokens": 146878556.0, "step": 24615 }, { "epoch": 0.26266096252120386, "grad_norm": 0.9306135222862928, "learning_rate": 4.4662301436132986e-05, "loss": 0.4571, "num_tokens": 146901043.0, "step": 24620 }, { "epoch": 0.2627143055274023, "grad_norm": 0.9827644172057399, "learning_rate": 4.465973449081714e-05, "loss": 0.5247, "num_tokens": 146928114.0, "step": 24625 }, { "epoch": 0.26276764853360074, "grad_norm": 1.9635589334120964, "learning_rate": 4.465716701152561e-05, "loss": 0.6904, "num_tokens": 146958554.0, "step": 24630 }, { "epoch": 0.2628209915397992, "grad_norm": 0.7070715284821423, "learning_rate": 4.465459899833828e-05, "loss": 0.5802, "num_tokens": 146989657.0, "step": 24635 }, { "epoch": 0.2628743345459977, "grad_norm": 1.1534563195487346, "learning_rate": 4.465203045133506e-05, "loss": 0.6036, "num_tokens": 147007396.0, "step": 24640 }, { "epoch": 0.26292767755219615, "grad_norm": 0.9459331569290467, "learning_rate": 4.464946137059589e-05, "loss": 0.5563, "num_tokens": 147038024.0, "step": 24645 }, { "epoch": 0.26298102055839456, "grad_norm": 1.3493137651250269, "learning_rate": 4.464689175620071e-05, "loss": 0.5651, "num_tokens": 147072013.0, "step": 24650 }, { "epoch": 0.26303436356459303, "grad_norm": 1.3773113513170652, "learning_rate": 4.464432160822947e-05, "loss": 0.6108, "num_tokens": 147092570.0, "step": 24655 }, { "epoch": 0.2630877065707915, "grad_norm": 1.5911506286260946, "learning_rate": 4.4641750926762166e-05, "loss": 0.5089, "num_tokens": 147117896.0, "step": 24660 }, { "epoch": 0.26314104957698997, "grad_norm": 1.2602915264711587, "learning_rate": 4.463917971187878e-05, "loss": 0.6819, "num_tokens": 147150237.0, "step": 24665 }, { "epoch": 0.26319439258318844, "grad_norm": 0.9913402291549261, "learning_rate": 4.4636607963659326e-05, "loss": 0.5208, "num_tokens": 147171468.0, "step": 24670 }, { "epoch": 0.26324773558938686, "grad_norm": 0.9435593410929596, "learning_rate": 4.463403568218384e-05, "loss": 0.5235, "num_tokens": 147203422.0, "step": 24675 }, { "epoch": 0.2633010785955853, "grad_norm": 1.6217154917453538, "learning_rate": 4.463146286753235e-05, "loss": 0.4603, "num_tokens": 147225107.0, "step": 24680 }, { "epoch": 0.2633544216017838, "grad_norm": 1.0397717910614566, "learning_rate": 4.4628889519784925e-05, "loss": 0.7295, "num_tokens": 147246612.0, "step": 24685 }, { "epoch": 0.26340776460798226, "grad_norm": 0.9778558578527498, "learning_rate": 4.4626315639021636e-05, "loss": 0.5986, "num_tokens": 147273245.0, "step": 24690 }, { "epoch": 0.2634611076141807, "grad_norm": 0.8540168854121757, "learning_rate": 4.462374122532259e-05, "loss": 0.5494, "num_tokens": 147305921.0, "step": 24695 }, { "epoch": 0.26351445062037915, "grad_norm": 1.4865407238146982, "learning_rate": 4.462116627876789e-05, "loss": 0.6084, "num_tokens": 147331680.0, "step": 24700 }, { "epoch": 0.2635677936265776, "grad_norm": 1.138859150511851, "learning_rate": 4.4618590799437664e-05, "loss": 0.7471, "num_tokens": 147373311.0, "step": 24705 }, { "epoch": 0.2636211366327761, "grad_norm": 1.04034734882025, "learning_rate": 4.461601478741206e-05, "loss": 0.6478, "num_tokens": 147400152.0, "step": 24710 }, { "epoch": 0.26367447963897456, "grad_norm": 0.8830502862108438, "learning_rate": 4.461343824277123e-05, "loss": 0.5855, "num_tokens": 147435069.0, "step": 24715 }, { "epoch": 0.26372782264517297, "grad_norm": 0.9675394068132179, "learning_rate": 4.4610861165595344e-05, "loss": 0.6252, "num_tokens": 147469788.0, "step": 24720 }, { "epoch": 0.26378116565137144, "grad_norm": 0.9629269167482334, "learning_rate": 4.460828355596461e-05, "loss": 0.6373, "num_tokens": 147497687.0, "step": 24725 }, { "epoch": 0.2638345086575699, "grad_norm": 0.8699246365448785, "learning_rate": 4.460570541395924e-05, "loss": 0.6152, "num_tokens": 147531584.0, "step": 24730 }, { "epoch": 0.2638878516637684, "grad_norm": 1.3712651647202694, "learning_rate": 4.4603126739659444e-05, "loss": 0.5379, "num_tokens": 147548302.0, "step": 24735 }, { "epoch": 0.2639411946699668, "grad_norm": 1.0238474488139937, "learning_rate": 4.4600547533145484e-05, "loss": 0.5322, "num_tokens": 147586370.0, "step": 24740 }, { "epoch": 0.26399453767616526, "grad_norm": 1.6870420552319816, "learning_rate": 4.45979677944976e-05, "loss": 0.5059, "num_tokens": 147618162.0, "step": 24745 }, { "epoch": 0.26404788068236373, "grad_norm": 0.7054128069292646, "learning_rate": 4.459538752379608e-05, "loss": 0.6167, "num_tokens": 147660763.0, "step": 24750 }, { "epoch": 0.2641012236885622, "grad_norm": 1.036715536830425, "learning_rate": 4.459280672112122e-05, "loss": 0.5577, "num_tokens": 147681996.0, "step": 24755 }, { "epoch": 0.2641545666947607, "grad_norm": 1.2217092873344135, "learning_rate": 4.4590225386553325e-05, "loss": 0.6508, "num_tokens": 147706819.0, "step": 24760 }, { "epoch": 0.2642079097009591, "grad_norm": 0.7975836488645652, "learning_rate": 4.4587643520172715e-05, "loss": 0.5726, "num_tokens": 147738903.0, "step": 24765 }, { "epoch": 0.26426125270715756, "grad_norm": 0.9804766283576108, "learning_rate": 4.458506112205974e-05, "loss": 0.5303, "num_tokens": 147766980.0, "step": 24770 }, { "epoch": 0.264314595713356, "grad_norm": 1.4505749975408693, "learning_rate": 4.458247819229476e-05, "loss": 0.4617, "num_tokens": 147790729.0, "step": 24775 }, { "epoch": 0.2643679387195545, "grad_norm": 0.8507571654912706, "learning_rate": 4.457989473095815e-05, "loss": 0.5702, "num_tokens": 147818823.0, "step": 24780 }, { "epoch": 0.2644212817257529, "grad_norm": 0.9283342629228704, "learning_rate": 4.45773107381303e-05, "loss": 0.6852, "num_tokens": 147867537.0, "step": 24785 }, { "epoch": 0.2644746247319514, "grad_norm": 0.8753825040381904, "learning_rate": 4.4574726213891604e-05, "loss": 0.6097, "num_tokens": 147901566.0, "step": 24790 }, { "epoch": 0.26452796773814985, "grad_norm": 1.1759419006838456, "learning_rate": 4.457214115832251e-05, "loss": 0.5216, "num_tokens": 147920267.0, "step": 24795 }, { "epoch": 0.2645813107443483, "grad_norm": 1.3924756164618737, "learning_rate": 4.456955557150345e-05, "loss": 0.5373, "num_tokens": 147956888.0, "step": 24800 }, { "epoch": 0.2646346537505468, "grad_norm": 1.2981838533569587, "learning_rate": 4.456696945351488e-05, "loss": 0.5491, "num_tokens": 147988246.0, "step": 24805 }, { "epoch": 0.2646879967567452, "grad_norm": 1.0115574503304252, "learning_rate": 4.456438280443728e-05, "loss": 0.6276, "num_tokens": 148016280.0, "step": 24810 }, { "epoch": 0.2647413397629437, "grad_norm": 1.4366031701828523, "learning_rate": 4.4561795624351133e-05, "loss": 0.5446, "num_tokens": 148042605.0, "step": 24815 }, { "epoch": 0.26479468276914214, "grad_norm": 1.9906888292530132, "learning_rate": 4.4559207913336956e-05, "loss": 0.5409, "num_tokens": 148070622.0, "step": 24820 }, { "epoch": 0.2648480257753406, "grad_norm": 1.5404188440387683, "learning_rate": 4.455661967147527e-05, "loss": 0.543, "num_tokens": 148095558.0, "step": 24825 }, { "epoch": 0.264901368781539, "grad_norm": 2.557483810467647, "learning_rate": 4.455403089884661e-05, "loss": 0.7374, "num_tokens": 148122770.0, "step": 24830 }, { "epoch": 0.2649547117877375, "grad_norm": 1.0897592479878284, "learning_rate": 4.4551441595531546e-05, "loss": 0.6504, "num_tokens": 148156323.0, "step": 24835 }, { "epoch": 0.26500805479393597, "grad_norm": 1.0793186134154769, "learning_rate": 4.4548851761610646e-05, "loss": 0.6563, "num_tokens": 148181803.0, "step": 24840 }, { "epoch": 0.26506139780013444, "grad_norm": 0.768048523714523, "learning_rate": 4.454626139716448e-05, "loss": 0.4778, "num_tokens": 148221551.0, "step": 24845 }, { "epoch": 0.2651147408063329, "grad_norm": 1.4091830642205616, "learning_rate": 4.45436705022737e-05, "loss": 0.5999, "num_tokens": 148258839.0, "step": 24850 }, { "epoch": 0.2651680838125313, "grad_norm": 1.297514704050842, "learning_rate": 4.4541079077018885e-05, "loss": 0.6169, "num_tokens": 148295615.0, "step": 24855 }, { "epoch": 0.2652214268187298, "grad_norm": 1.282564680824692, "learning_rate": 4.45384871214807e-05, "loss": 0.6766, "num_tokens": 148332429.0, "step": 24860 }, { "epoch": 0.26527476982492826, "grad_norm": 1.0378376653362127, "learning_rate": 4.453589463573979e-05, "loss": 0.4735, "num_tokens": 148359404.0, "step": 24865 }, { "epoch": 0.26532811283112673, "grad_norm": 1.114790621212403, "learning_rate": 4.4533301619876836e-05, "loss": 0.7224, "num_tokens": 148402212.0, "step": 24870 }, { "epoch": 0.26538145583732514, "grad_norm": 0.822725670955193, "learning_rate": 4.453070807397252e-05, "loss": 0.6759, "num_tokens": 148434537.0, "step": 24875 }, { "epoch": 0.2654347988435236, "grad_norm": 0.6700441657293805, "learning_rate": 4.452811399810755e-05, "loss": 0.5969, "num_tokens": 148485473.0, "step": 24880 }, { "epoch": 0.2654881418497221, "grad_norm": 1.1682274141397768, "learning_rate": 4.452551939236265e-05, "loss": 0.567, "num_tokens": 148522176.0, "step": 24885 }, { "epoch": 0.26554148485592055, "grad_norm": 1.708229962732444, "learning_rate": 4.452292425681855e-05, "loss": 0.5554, "num_tokens": 148540987.0, "step": 24890 }, { "epoch": 0.265594827862119, "grad_norm": 0.733112071098871, "learning_rate": 4.4520328591556024e-05, "loss": 0.4842, "num_tokens": 148575639.0, "step": 24895 }, { "epoch": 0.26564817086831743, "grad_norm": 1.3039546101535116, "learning_rate": 4.451773239665583e-05, "loss": 0.6392, "num_tokens": 148595668.0, "step": 24900 }, { "epoch": 0.2657015138745159, "grad_norm": 0.9515630348769801, "learning_rate": 4.451513567219875e-05, "loss": 0.5251, "num_tokens": 148632011.0, "step": 24905 }, { "epoch": 0.2657548568807144, "grad_norm": 0.9814166690071989, "learning_rate": 4.4512538418265617e-05, "loss": 0.7443, "num_tokens": 148662197.0, "step": 24910 }, { "epoch": 0.26580819988691284, "grad_norm": 1.7759723398685252, "learning_rate": 4.450994063493722e-05, "loss": 0.5661, "num_tokens": 148672948.0, "step": 24915 }, { "epoch": 0.26586154289311126, "grad_norm": 0.9810866982017546, "learning_rate": 4.450734232229442e-05, "loss": 0.5947, "num_tokens": 148698873.0, "step": 24920 }, { "epoch": 0.2659148858993097, "grad_norm": 1.125805498514164, "learning_rate": 4.450474348041805e-05, "loss": 0.5273, "num_tokens": 148731601.0, "step": 24925 }, { "epoch": 0.2659682289055082, "grad_norm": 1.2994830763413632, "learning_rate": 4.4502144109389e-05, "loss": 0.812, "num_tokens": 148761247.0, "step": 24930 }, { "epoch": 0.26602157191170667, "grad_norm": 0.9953817732997339, "learning_rate": 4.449954420928814e-05, "loss": 0.6114, "num_tokens": 148784227.0, "step": 24935 }, { "epoch": 0.26607491491790514, "grad_norm": 0.8708083496325789, "learning_rate": 4.4496943780196385e-05, "loss": 0.6015, "num_tokens": 148809898.0, "step": 24940 }, { "epoch": 0.26612825792410355, "grad_norm": 1.2175598322076642, "learning_rate": 4.4494342822194655e-05, "loss": 0.6452, "num_tokens": 148832110.0, "step": 24945 }, { "epoch": 0.266181600930302, "grad_norm": 1.086825621814438, "learning_rate": 4.4491741335363876e-05, "loss": 0.6358, "num_tokens": 148857638.0, "step": 24950 }, { "epoch": 0.2662349439365005, "grad_norm": 1.1239265650733157, "learning_rate": 4.448913931978502e-05, "loss": 0.6354, "num_tokens": 148904140.0, "step": 24955 }, { "epoch": 0.26628828694269896, "grad_norm": 1.9202517056904356, "learning_rate": 4.448653677553904e-05, "loss": 0.6966, "num_tokens": 148940122.0, "step": 24960 }, { "epoch": 0.2663416299488974, "grad_norm": 0.9121601068073953, "learning_rate": 4.448393370270693e-05, "loss": 0.6288, "num_tokens": 148963767.0, "step": 24965 }, { "epoch": 0.26639497295509584, "grad_norm": 1.202470876745318, "learning_rate": 4.4481330101369684e-05, "loss": 0.6215, "num_tokens": 148996084.0, "step": 24970 }, { "epoch": 0.2664483159612943, "grad_norm": 1.0181830662077753, "learning_rate": 4.4478725971608326e-05, "loss": 0.6022, "num_tokens": 149030622.0, "step": 24975 }, { "epoch": 0.2665016589674928, "grad_norm": 1.106623394975683, "learning_rate": 4.44761213135039e-05, "loss": 0.631, "num_tokens": 149056011.0, "step": 24980 }, { "epoch": 0.26655500197369125, "grad_norm": 0.9414064723286442, "learning_rate": 4.447351612713744e-05, "loss": 0.5827, "num_tokens": 149086621.0, "step": 24985 }, { "epoch": 0.26660834497988967, "grad_norm": 1.0238555843620267, "learning_rate": 4.447091041259002e-05, "loss": 0.6502, "num_tokens": 149125101.0, "step": 24990 }, { "epoch": 0.26666168798608814, "grad_norm": 1.3123704328095434, "learning_rate": 4.4468304169942734e-05, "loss": 0.73, "num_tokens": 149167618.0, "step": 24995 }, { "epoch": 0.2667150309922866, "grad_norm": 1.0359455120503185, "learning_rate": 4.4465697399276676e-05, "loss": 0.689, "num_tokens": 149205502.0, "step": 25000 }, { "epoch": 0.2667683739984851, "grad_norm": 1.2533926729276597, "learning_rate": 4.446309010067296e-05, "loss": 0.5609, "num_tokens": 149227817.0, "step": 25005 }, { "epoch": 0.2668217170046835, "grad_norm": 1.003094075513629, "learning_rate": 4.4460482274212723e-05, "loss": 0.6488, "num_tokens": 149261441.0, "step": 25010 }, { "epoch": 0.26687506001088196, "grad_norm": 1.5469102204805554, "learning_rate": 4.4457873919977113e-05, "loss": 0.6531, "num_tokens": 149292860.0, "step": 25015 }, { "epoch": 0.26692840301708043, "grad_norm": 1.476918603870565, "learning_rate": 4.44552650380473e-05, "loss": 0.5852, "num_tokens": 149328331.0, "step": 25020 }, { "epoch": 0.2669817460232789, "grad_norm": 1.587510776059611, "learning_rate": 4.4452655628504484e-05, "loss": 0.6646, "num_tokens": 149354019.0, "step": 25025 }, { "epoch": 0.26703508902947737, "grad_norm": 1.0164551186072637, "learning_rate": 4.445004569142982e-05, "loss": 0.5959, "num_tokens": 149383333.0, "step": 25030 }, { "epoch": 0.2670884320356758, "grad_norm": 1.3155013400372375, "learning_rate": 4.444743522690457e-05, "loss": 0.6406, "num_tokens": 149417416.0, "step": 25035 }, { "epoch": 0.26714177504187425, "grad_norm": 1.0939455473641357, "learning_rate": 4.444482423500994e-05, "loss": 0.6481, "num_tokens": 149454049.0, "step": 25040 }, { "epoch": 0.2671951180480727, "grad_norm": 0.8261305714499195, "learning_rate": 4.4442212715827184e-05, "loss": 0.4715, "num_tokens": 149478816.0, "step": 25045 }, { "epoch": 0.2672484610542712, "grad_norm": 0.7861471749664164, "learning_rate": 4.443960066943757e-05, "loss": 0.495, "num_tokens": 149512215.0, "step": 25050 }, { "epoch": 0.2673018040604696, "grad_norm": 0.7567443989570904, "learning_rate": 4.443698809592238e-05, "loss": 0.5004, "num_tokens": 149540796.0, "step": 25055 }, { "epoch": 0.2673551470666681, "grad_norm": 0.8870097167412593, "learning_rate": 4.4434374995362895e-05, "loss": 0.6943, "num_tokens": 149571835.0, "step": 25060 }, { "epoch": 0.26740849007286654, "grad_norm": 0.7042164535067462, "learning_rate": 4.4431761367840466e-05, "loss": 0.4595, "num_tokens": 149599064.0, "step": 25065 }, { "epoch": 0.267461833079065, "grad_norm": 1.7822092953204525, "learning_rate": 4.442914721343639e-05, "loss": 0.5921, "num_tokens": 149634510.0, "step": 25070 }, { "epoch": 0.2675151760852635, "grad_norm": 0.881853394630184, "learning_rate": 4.442653253223203e-05, "loss": 0.5894, "num_tokens": 149668108.0, "step": 25075 }, { "epoch": 0.2675685190914619, "grad_norm": 1.5241201038190872, "learning_rate": 4.442391732430874e-05, "loss": 0.5269, "num_tokens": 149691910.0, "step": 25080 }, { "epoch": 0.26762186209766037, "grad_norm": 1.0191291620236225, "learning_rate": 4.442130158974792e-05, "loss": 0.5961, "num_tokens": 149727900.0, "step": 25085 }, { "epoch": 0.26767520510385884, "grad_norm": 0.8783629645112646, "learning_rate": 4.4418685328630936e-05, "loss": 0.6093, "num_tokens": 149762260.0, "step": 25090 }, { "epoch": 0.2677285481100573, "grad_norm": 1.1694729789766096, "learning_rate": 4.441606854103922e-05, "loss": 0.6968, "num_tokens": 149819214.0, "step": 25095 }, { "epoch": 0.2677818911162557, "grad_norm": 1.8555849329211715, "learning_rate": 4.441345122705421e-05, "loss": 0.5528, "num_tokens": 149838461.0, "step": 25100 }, { "epoch": 0.2678352341224542, "grad_norm": 0.6795196035425437, "learning_rate": 4.4410833386757326e-05, "loss": 0.5384, "num_tokens": 149888680.0, "step": 25105 }, { "epoch": 0.26788857712865266, "grad_norm": 1.9466023144338085, "learning_rate": 4.440821502023004e-05, "loss": 0.6264, "num_tokens": 149919239.0, "step": 25110 }, { "epoch": 0.26794192013485113, "grad_norm": 0.9031344780968764, "learning_rate": 4.440559612755385e-05, "loss": 0.5282, "num_tokens": 149951152.0, "step": 25115 }, { "epoch": 0.2679952631410496, "grad_norm": 0.8389530559543095, "learning_rate": 4.440297670881022e-05, "loss": 0.5688, "num_tokens": 149983545.0, "step": 25120 }, { "epoch": 0.268048606147248, "grad_norm": 0.8163922137597599, "learning_rate": 4.4400356764080675e-05, "loss": 0.5073, "num_tokens": 150010959.0, "step": 25125 }, { "epoch": 0.2681019491534465, "grad_norm": 2.004983071812149, "learning_rate": 4.439773629344675e-05, "loss": 0.5803, "num_tokens": 150043470.0, "step": 25130 }, { "epoch": 0.26815529215964495, "grad_norm": 0.9054672046818912, "learning_rate": 4.439511529698997e-05, "loss": 0.6735, "num_tokens": 150086069.0, "step": 25135 }, { "epoch": 0.2682086351658434, "grad_norm": 1.698676846791348, "learning_rate": 4.439249377479191e-05, "loss": 0.4902, "num_tokens": 150120296.0, "step": 25140 }, { "epoch": 0.26826197817204184, "grad_norm": 1.5538770679168394, "learning_rate": 4.438987172693414e-05, "loss": 0.6032, "num_tokens": 150146884.0, "step": 25145 }, { "epoch": 0.2683153211782403, "grad_norm": 1.0055015671603857, "learning_rate": 4.4387249153498255e-05, "loss": 0.6639, "num_tokens": 150178896.0, "step": 25150 }, { "epoch": 0.2683686641844388, "grad_norm": 1.3928894429107233, "learning_rate": 4.438462605456587e-05, "loss": 0.5165, "num_tokens": 150199603.0, "step": 25155 }, { "epoch": 0.26842200719063725, "grad_norm": 1.310483274879073, "learning_rate": 4.43820024302186e-05, "loss": 0.5456, "num_tokens": 150228698.0, "step": 25160 }, { "epoch": 0.2684753501968357, "grad_norm": 1.189018381479716, "learning_rate": 4.4379378280538095e-05, "loss": 0.5528, "num_tokens": 150259393.0, "step": 25165 }, { "epoch": 0.26852869320303413, "grad_norm": 1.456751075690394, "learning_rate": 4.4376753605605996e-05, "loss": 0.6914, "num_tokens": 150290637.0, "step": 25170 }, { "epoch": 0.2685820362092326, "grad_norm": 1.0180284542174716, "learning_rate": 4.437412840550401e-05, "loss": 0.6627, "num_tokens": 150331596.0, "step": 25175 }, { "epoch": 0.26863537921543107, "grad_norm": 1.1567570329130288, "learning_rate": 4.437150268031379e-05, "loss": 0.6254, "num_tokens": 150374451.0, "step": 25180 }, { "epoch": 0.26868872222162954, "grad_norm": 1.1906455619037342, "learning_rate": 4.4368876430117065e-05, "loss": 0.6636, "num_tokens": 150398383.0, "step": 25185 }, { "epoch": 0.26874206522782795, "grad_norm": 1.1571707578757242, "learning_rate": 4.4366249654995565e-05, "loss": 0.7512, "num_tokens": 150429456.0, "step": 25190 }, { "epoch": 0.2687954082340264, "grad_norm": 1.672562598106111, "learning_rate": 4.436362235503102e-05, "loss": 0.6689, "num_tokens": 150450906.0, "step": 25195 }, { "epoch": 0.2688487512402249, "grad_norm": 1.061970902137993, "learning_rate": 4.436099453030517e-05, "loss": 0.6138, "num_tokens": 150470710.0, "step": 25200 }, { "epoch": 0.26890209424642336, "grad_norm": 1.3340532539264212, "learning_rate": 4.435836618089982e-05, "loss": 0.6429, "num_tokens": 150495259.0, "step": 25205 }, { "epoch": 0.26895543725262183, "grad_norm": 1.112104664215734, "learning_rate": 4.435573730689674e-05, "loss": 0.5566, "num_tokens": 150527275.0, "step": 25210 }, { "epoch": 0.26900878025882025, "grad_norm": 1.0225438531871005, "learning_rate": 4.4353107908377736e-05, "loss": 0.5665, "num_tokens": 150546366.0, "step": 25215 }, { "epoch": 0.2690621232650187, "grad_norm": 1.3494626142543351, "learning_rate": 4.4350477985424624e-05, "loss": 0.51, "num_tokens": 150560008.0, "step": 25220 }, { "epoch": 0.2691154662712172, "grad_norm": 2.80904226137577, "learning_rate": 4.4347847538119257e-05, "loss": 0.6667, "num_tokens": 150597588.0, "step": 25225 }, { "epoch": 0.26916880927741565, "grad_norm": 0.7401150087217204, "learning_rate": 4.4345216566543476e-05, "loss": 0.5223, "num_tokens": 150627406.0, "step": 25230 }, { "epoch": 0.26922215228361407, "grad_norm": 2.513126737018951, "learning_rate": 4.434258507077916e-05, "loss": 0.6571, "num_tokens": 150646204.0, "step": 25235 }, { "epoch": 0.26927549528981254, "grad_norm": 0.6965406425919634, "learning_rate": 4.43399530509082e-05, "loss": 0.505, "num_tokens": 150667034.0, "step": 25240 }, { "epoch": 0.269328838296011, "grad_norm": 1.7251497679255041, "learning_rate": 4.4337320507012477e-05, "loss": 0.6974, "num_tokens": 150687576.0, "step": 25245 }, { "epoch": 0.2693821813022095, "grad_norm": 1.4121434341141135, "learning_rate": 4.433468743917393e-05, "loss": 0.593, "num_tokens": 150710459.0, "step": 25250 }, { "epoch": 0.26943552430840795, "grad_norm": 0.9277390639973384, "learning_rate": 4.433205384747449e-05, "loss": 0.7328, "num_tokens": 150751372.0, "step": 25255 }, { "epoch": 0.26948886731460636, "grad_norm": 2.0914324131454793, "learning_rate": 4.432941973199611e-05, "loss": 0.6607, "num_tokens": 150773619.0, "step": 25260 }, { "epoch": 0.26954221032080483, "grad_norm": 1.3414575344106738, "learning_rate": 4.432678509282075e-05, "loss": 0.5673, "num_tokens": 150808706.0, "step": 25265 }, { "epoch": 0.2695955533270033, "grad_norm": 0.7332674974319914, "learning_rate": 4.432414993003041e-05, "loss": 0.4725, "num_tokens": 150841883.0, "step": 25270 }, { "epoch": 0.26964889633320177, "grad_norm": 1.5720450668411992, "learning_rate": 4.432151424370708e-05, "loss": 0.6564, "num_tokens": 150870801.0, "step": 25275 }, { "epoch": 0.2697022393394002, "grad_norm": 1.0502785410925497, "learning_rate": 4.4318878033932784e-05, "loss": 0.6449, "num_tokens": 150912454.0, "step": 25280 }, { "epoch": 0.26975558234559865, "grad_norm": 0.7214949378521285, "learning_rate": 4.431624130078954e-05, "loss": 0.5639, "num_tokens": 150945911.0, "step": 25285 }, { "epoch": 0.2698089253517971, "grad_norm": 0.9475599356657644, "learning_rate": 4.4313604044359406e-05, "loss": 0.5447, "num_tokens": 150966807.0, "step": 25290 }, { "epoch": 0.2698622683579956, "grad_norm": 1.9231161030960753, "learning_rate": 4.431096626472446e-05, "loss": 0.6546, "num_tokens": 150986753.0, "step": 25295 }, { "epoch": 0.26991561136419406, "grad_norm": 1.0444411677428145, "learning_rate": 4.430832796196677e-05, "loss": 0.6472, "num_tokens": 151027828.0, "step": 25300 }, { "epoch": 0.2699689543703925, "grad_norm": 1.0785017183463053, "learning_rate": 4.430568913616844e-05, "loss": 0.5204, "num_tokens": 151051864.0, "step": 25305 }, { "epoch": 0.27002229737659095, "grad_norm": 0.8631641321483007, "learning_rate": 4.4303049787411585e-05, "loss": 0.5363, "num_tokens": 151085557.0, "step": 25310 }, { "epoch": 0.2700756403827894, "grad_norm": 0.9784571757723411, "learning_rate": 4.430040991577833e-05, "loss": 0.6013, "num_tokens": 151106382.0, "step": 25315 }, { "epoch": 0.2701289833889879, "grad_norm": 0.8073113579947844, "learning_rate": 4.429776952135083e-05, "loss": 0.6402, "num_tokens": 151135604.0, "step": 25320 }, { "epoch": 0.2701823263951863, "grad_norm": 0.9121800533567745, "learning_rate": 4.429512860421125e-05, "loss": 0.5038, "num_tokens": 151159653.0, "step": 25325 }, { "epoch": 0.27023566940138477, "grad_norm": 0.8207432034788991, "learning_rate": 4.4292487164441764e-05, "loss": 0.5251, "num_tokens": 151192830.0, "step": 25330 }, { "epoch": 0.27028901240758324, "grad_norm": 1.1978540602433936, "learning_rate": 4.428984520212457e-05, "loss": 0.5774, "num_tokens": 151224889.0, "step": 25335 }, { "epoch": 0.2703423554137817, "grad_norm": 1.1517573149946176, "learning_rate": 4.428720271734188e-05, "loss": 0.5474, "num_tokens": 151238498.0, "step": 25340 }, { "epoch": 0.2703956984199802, "grad_norm": 1.2866905035636953, "learning_rate": 4.4284559710175924e-05, "loss": 0.5941, "num_tokens": 151262795.0, "step": 25345 }, { "epoch": 0.2704490414261786, "grad_norm": 0.9507352211646513, "learning_rate": 4.428191618070895e-05, "loss": 0.7227, "num_tokens": 151291438.0, "step": 25350 }, { "epoch": 0.27050238443237706, "grad_norm": 1.0138599087596782, "learning_rate": 4.427927212902321e-05, "loss": 0.6157, "num_tokens": 151333013.0, "step": 25355 }, { "epoch": 0.27055572743857553, "grad_norm": 1.3899952344207345, "learning_rate": 4.427662755520099e-05, "loss": 0.4358, "num_tokens": 151355672.0, "step": 25360 }, { "epoch": 0.270609070444774, "grad_norm": 1.003877339668651, "learning_rate": 4.4273982459324575e-05, "loss": 0.7095, "num_tokens": 151390244.0, "step": 25365 }, { "epoch": 0.2706624134509724, "grad_norm": 1.453778664265145, "learning_rate": 4.4271336841476285e-05, "loss": 0.6405, "num_tokens": 151417750.0, "step": 25370 }, { "epoch": 0.2707157564571709, "grad_norm": 1.066467415730548, "learning_rate": 4.426869070173845e-05, "loss": 0.5334, "num_tokens": 151461189.0, "step": 25375 }, { "epoch": 0.27076909946336936, "grad_norm": 0.9673158857227142, "learning_rate": 4.426604404019339e-05, "loss": 0.5195, "num_tokens": 151492741.0, "step": 25380 }, { "epoch": 0.2708224424695678, "grad_norm": 0.6949517240139536, "learning_rate": 4.426339685692348e-05, "loss": 0.6579, "num_tokens": 151520223.0, "step": 25385 }, { "epoch": 0.2708757854757663, "grad_norm": 1.568061580615673, "learning_rate": 4.42607491520111e-05, "loss": 0.7543, "num_tokens": 151561609.0, "step": 25390 }, { "epoch": 0.2709291284819647, "grad_norm": 1.2791163743709755, "learning_rate": 4.425810092553863e-05, "loss": 0.6965, "num_tokens": 151589865.0, "step": 25395 }, { "epoch": 0.2709824714881632, "grad_norm": 1.3467208647265907, "learning_rate": 4.425545217758848e-05, "loss": 0.7024, "num_tokens": 151622828.0, "step": 25400 }, { "epoch": 0.27103581449436165, "grad_norm": 2.053122305094344, "learning_rate": 4.425280290824308e-05, "loss": 0.6945, "num_tokens": 151650789.0, "step": 25405 }, { "epoch": 0.2710891575005601, "grad_norm": 0.890377630018435, "learning_rate": 4.4250153117584866e-05, "loss": 0.6505, "num_tokens": 151682718.0, "step": 25410 }, { "epoch": 0.27114250050675853, "grad_norm": 1.8732398007238351, "learning_rate": 4.424750280569628e-05, "loss": 0.5888, "num_tokens": 151717584.0, "step": 25415 }, { "epoch": 0.271195843512957, "grad_norm": 1.5108590276561429, "learning_rate": 4.424485197265982e-05, "loss": 0.5756, "num_tokens": 151738204.0, "step": 25420 }, { "epoch": 0.27124918651915547, "grad_norm": 1.2752589180260696, "learning_rate": 4.4242200618557954e-05, "loss": 0.6015, "num_tokens": 151773850.0, "step": 25425 }, { "epoch": 0.27130252952535394, "grad_norm": 1.6207806053538982, "learning_rate": 4.4239548743473195e-05, "loss": 0.6017, "num_tokens": 151790695.0, "step": 25430 }, { "epoch": 0.2713558725315524, "grad_norm": 1.7521384482261826, "learning_rate": 4.423689634748807e-05, "loss": 0.4691, "num_tokens": 151812676.0, "step": 25435 }, { "epoch": 0.2714092155377508, "grad_norm": 1.2749499353613605, "learning_rate": 4.4234243430685105e-05, "loss": 0.6104, "num_tokens": 151835104.0, "step": 25440 }, { "epoch": 0.2714625585439493, "grad_norm": 1.6983031123554915, "learning_rate": 4.423158999314686e-05, "loss": 0.4927, "num_tokens": 151860062.0, "step": 25445 }, { "epoch": 0.27151590155014776, "grad_norm": 1.1019844008934592, "learning_rate": 4.4228936034955896e-05, "loss": 0.6153, "num_tokens": 151889938.0, "step": 25450 }, { "epoch": 0.27156924455634623, "grad_norm": 0.8813666420717542, "learning_rate": 4.42262815561948e-05, "loss": 0.6112, "num_tokens": 151912419.0, "step": 25455 }, { "epoch": 0.27162258756254465, "grad_norm": 0.7569083600374218, "learning_rate": 4.422362655694619e-05, "loss": 0.6204, "num_tokens": 151962596.0, "step": 25460 }, { "epoch": 0.2716759305687431, "grad_norm": 1.264904903024695, "learning_rate": 4.422097103729267e-05, "loss": 0.6856, "num_tokens": 151991821.0, "step": 25465 }, { "epoch": 0.2717292735749416, "grad_norm": 1.2556857751549257, "learning_rate": 4.421831499731688e-05, "loss": 0.5442, "num_tokens": 152033104.0, "step": 25470 }, { "epoch": 0.27178261658114006, "grad_norm": 0.8426553230394589, "learning_rate": 4.421565843710146e-05, "loss": 0.4947, "num_tokens": 152070290.0, "step": 25475 }, { "epoch": 0.2718359595873385, "grad_norm": 1.1934920746795352, "learning_rate": 4.421300135672909e-05, "loss": 0.6412, "num_tokens": 152098964.0, "step": 25480 }, { "epoch": 0.27188930259353694, "grad_norm": 1.1757196753029635, "learning_rate": 4.421034375628245e-05, "loss": 0.6731, "num_tokens": 152137130.0, "step": 25485 }, { "epoch": 0.2719426455997354, "grad_norm": 1.2441175396821376, "learning_rate": 4.4207685635844234e-05, "loss": 0.537, "num_tokens": 152165131.0, "step": 25490 }, { "epoch": 0.2719959886059339, "grad_norm": 1.152871858760504, "learning_rate": 4.4205026995497154e-05, "loss": 0.4859, "num_tokens": 152189202.0, "step": 25495 }, { "epoch": 0.27204933161213235, "grad_norm": 1.6528657637428343, "learning_rate": 4.420236783532395e-05, "loss": 0.6311, "num_tokens": 152226031.0, "step": 25500 }, { "epoch": 0.27210267461833076, "grad_norm": 1.3230943973634095, "learning_rate": 4.419970815540736e-05, "loss": 0.5678, "num_tokens": 152257329.0, "step": 25505 }, { "epoch": 0.27215601762452923, "grad_norm": 1.1214612538855186, "learning_rate": 4.4197047955830175e-05, "loss": 0.673, "num_tokens": 152291605.0, "step": 25510 }, { "epoch": 0.2722093606307277, "grad_norm": 1.1484893004709014, "learning_rate": 4.419438723667513e-05, "loss": 0.6915, "num_tokens": 152324618.0, "step": 25515 }, { "epoch": 0.2722627036369262, "grad_norm": 1.2110708417581888, "learning_rate": 4.419172599802506e-05, "loss": 0.6051, "num_tokens": 152361068.0, "step": 25520 }, { "epoch": 0.27231604664312464, "grad_norm": 0.7591484808748171, "learning_rate": 4.418906423996276e-05, "loss": 0.4442, "num_tokens": 152384627.0, "step": 25525 }, { "epoch": 0.27236938964932306, "grad_norm": 0.7804338567478241, "learning_rate": 4.4186401962571064e-05, "loss": 0.5636, "num_tokens": 152419857.0, "step": 25530 }, { "epoch": 0.2724227326555215, "grad_norm": 0.7700487359368974, "learning_rate": 4.418373916593281e-05, "loss": 0.6047, "num_tokens": 152451010.0, "step": 25535 }, { "epoch": 0.27247607566172, "grad_norm": 0.8302924426438604, "learning_rate": 4.418107585013085e-05, "loss": 0.5276, "num_tokens": 152485532.0, "step": 25540 }, { "epoch": 0.27252941866791847, "grad_norm": 1.4391538589644792, "learning_rate": 4.41784120152481e-05, "loss": 0.6901, "num_tokens": 152509522.0, "step": 25545 }, { "epoch": 0.2725827616741169, "grad_norm": 1.4813829353422574, "learning_rate": 4.4175747661367404e-05, "loss": 0.6258, "num_tokens": 152550501.0, "step": 25550 }, { "epoch": 0.27263610468031535, "grad_norm": 1.2705663302460668, "learning_rate": 4.4173082788571705e-05, "loss": 0.5148, "num_tokens": 152574381.0, "step": 25555 }, { "epoch": 0.2726894476865138, "grad_norm": 1.0088360942007886, "learning_rate": 4.417041739694391e-05, "loss": 0.6075, "num_tokens": 152612235.0, "step": 25560 }, { "epoch": 0.2727427906927123, "grad_norm": 0.7458991347081219, "learning_rate": 4.4167751486566984e-05, "loss": 0.5152, "num_tokens": 152630651.0, "step": 25565 }, { "epoch": 0.27279613369891076, "grad_norm": 0.8068745985235672, "learning_rate": 4.416508505752385e-05, "loss": 0.5764, "num_tokens": 152666060.0, "step": 25570 }, { "epoch": 0.2728494767051092, "grad_norm": 0.8461311540640483, "learning_rate": 4.416241810989751e-05, "loss": 0.6464, "num_tokens": 152701758.0, "step": 25575 }, { "epoch": 0.27290281971130764, "grad_norm": 1.4180825562804842, "learning_rate": 4.415975064377094e-05, "loss": 0.6892, "num_tokens": 152722077.0, "step": 25580 }, { "epoch": 0.2729561627175061, "grad_norm": 0.8195344622940544, "learning_rate": 4.415708265922715e-05, "loss": 0.5459, "num_tokens": 152745994.0, "step": 25585 }, { "epoch": 0.2730095057237046, "grad_norm": 1.5399940688435279, "learning_rate": 4.415441415634917e-05, "loss": 0.5939, "num_tokens": 152771837.0, "step": 25590 }, { "epoch": 0.273062848729903, "grad_norm": 1.0676950988153555, "learning_rate": 4.415174513522002e-05, "loss": 0.5093, "num_tokens": 152799220.0, "step": 25595 }, { "epoch": 0.27311619173610147, "grad_norm": 1.691975020244177, "learning_rate": 4.4149075595922765e-05, "loss": 0.5909, "num_tokens": 152809678.0, "step": 25600 }, { "epoch": 0.27316953474229994, "grad_norm": 1.0626625759048551, "learning_rate": 4.414640553854048e-05, "loss": 0.5869, "num_tokens": 152843586.0, "step": 25605 }, { "epoch": 0.2732228777484984, "grad_norm": 1.0026802662657233, "learning_rate": 4.414373496315625e-05, "loss": 0.4974, "num_tokens": 152880665.0, "step": 25610 }, { "epoch": 0.2732762207546969, "grad_norm": 0.8806536659331745, "learning_rate": 4.414106386985317e-05, "loss": 0.6461, "num_tokens": 152938379.0, "step": 25615 }, { "epoch": 0.2733295637608953, "grad_norm": 0.8289084560586284, "learning_rate": 4.4138392258714364e-05, "loss": 0.5705, "num_tokens": 152969017.0, "step": 25620 }, { "epoch": 0.27338290676709376, "grad_norm": 0.9041656729711401, "learning_rate": 4.413572012982297e-05, "loss": 0.4779, "num_tokens": 152993829.0, "step": 25625 }, { "epoch": 0.27343624977329223, "grad_norm": 0.9076227678553954, "learning_rate": 4.413304748326213e-05, "loss": 0.652, "num_tokens": 153031390.0, "step": 25630 }, { "epoch": 0.2734895927794907, "grad_norm": 0.9017955975826575, "learning_rate": 4.413037431911503e-05, "loss": 0.4423, "num_tokens": 153061732.0, "step": 25635 }, { "epoch": 0.2735429357856891, "grad_norm": 0.895182426008467, "learning_rate": 4.4127700637464834e-05, "loss": 0.5391, "num_tokens": 153084601.0, "step": 25640 }, { "epoch": 0.2735962787918876, "grad_norm": 1.4622317553506063, "learning_rate": 4.412502643839474e-05, "loss": 0.523, "num_tokens": 153108925.0, "step": 25645 }, { "epoch": 0.27364962179808605, "grad_norm": 0.9682396890607509, "learning_rate": 4.412235172198799e-05, "loss": 0.506, "num_tokens": 153137422.0, "step": 25650 }, { "epoch": 0.2737029648042845, "grad_norm": 1.1066858561836834, "learning_rate": 4.411967648832779e-05, "loss": 0.478, "num_tokens": 153158644.0, "step": 25655 }, { "epoch": 0.273756307810483, "grad_norm": 0.6858846359376944, "learning_rate": 4.411700073749739e-05, "loss": 0.513, "num_tokens": 153183490.0, "step": 25660 }, { "epoch": 0.2738096508166814, "grad_norm": 1.1041067900486945, "learning_rate": 4.411432446958007e-05, "loss": 0.495, "num_tokens": 153204177.0, "step": 25665 }, { "epoch": 0.2738629938228799, "grad_norm": 0.78355944313052, "learning_rate": 4.4111647684659084e-05, "loss": 0.7248, "num_tokens": 153243268.0, "step": 25670 }, { "epoch": 0.27391633682907834, "grad_norm": 1.1842137784141733, "learning_rate": 4.410897038281775e-05, "loss": 0.5211, "num_tokens": 153263546.0, "step": 25675 }, { "epoch": 0.2739696798352768, "grad_norm": 5.977737295128593, "learning_rate": 4.410629256413937e-05, "loss": 0.6352, "num_tokens": 153284379.0, "step": 25680 }, { "epoch": 0.27402302284147523, "grad_norm": 1.2613951321804286, "learning_rate": 4.4103614228707285e-05, "loss": 0.6119, "num_tokens": 153307786.0, "step": 25685 }, { "epoch": 0.2740763658476737, "grad_norm": 0.8372456294222914, "learning_rate": 4.410093537660483e-05, "loss": 0.5177, "num_tokens": 153324579.0, "step": 25690 }, { "epoch": 0.27412970885387217, "grad_norm": 0.9542090163229053, "learning_rate": 4.409825600791536e-05, "loss": 0.5434, "num_tokens": 153357126.0, "step": 25695 }, { "epoch": 0.27418305186007064, "grad_norm": 1.1337617080437354, "learning_rate": 4.409557612272225e-05, "loss": 0.5697, "num_tokens": 153404686.0, "step": 25700 }, { "epoch": 0.2742363948662691, "grad_norm": 0.7069932283436534, "learning_rate": 4.4092895721108915e-05, "loss": 0.5645, "num_tokens": 153442723.0, "step": 25705 }, { "epoch": 0.2742897378724675, "grad_norm": 0.895924908892656, "learning_rate": 4.409021480315873e-05, "loss": 0.5166, "num_tokens": 153464983.0, "step": 25710 }, { "epoch": 0.274343080878666, "grad_norm": 0.6780337320184767, "learning_rate": 4.4087533368955156e-05, "loss": 0.6215, "num_tokens": 153507154.0, "step": 25715 }, { "epoch": 0.27439642388486446, "grad_norm": 1.0053549141569231, "learning_rate": 4.408485141858161e-05, "loss": 0.5866, "num_tokens": 153522670.0, "step": 25720 }, { "epoch": 0.27444976689106293, "grad_norm": 1.3569810902206407, "learning_rate": 4.408216895212155e-05, "loss": 0.5464, "num_tokens": 153552016.0, "step": 25725 }, { "epoch": 0.27450310989726134, "grad_norm": 1.0309235536368087, "learning_rate": 4.407948596965846e-05, "loss": 0.5215, "num_tokens": 153570845.0, "step": 25730 }, { "epoch": 0.2745564529034598, "grad_norm": 0.9586642441323351, "learning_rate": 4.407680247127581e-05, "loss": 0.5747, "num_tokens": 153594436.0, "step": 25735 }, { "epoch": 0.2746097959096583, "grad_norm": 0.8487384890334242, "learning_rate": 4.407411845705712e-05, "loss": 0.7412, "num_tokens": 153626247.0, "step": 25740 }, { "epoch": 0.27466313891585675, "grad_norm": 0.7197723423798763, "learning_rate": 4.407143392708591e-05, "loss": 0.6135, "num_tokens": 153657861.0, "step": 25745 }, { "epoch": 0.2747164819220552, "grad_norm": 1.2320008220445513, "learning_rate": 4.406874888144571e-05, "loss": 0.4566, "num_tokens": 153680113.0, "step": 25750 }, { "epoch": 0.27476982492825364, "grad_norm": 2.417815663570517, "learning_rate": 4.4066063320220094e-05, "loss": 0.6172, "num_tokens": 153710850.0, "step": 25755 }, { "epoch": 0.2748231679344521, "grad_norm": 1.3687853581423701, "learning_rate": 4.40633772434926e-05, "loss": 0.6119, "num_tokens": 153736474.0, "step": 25760 }, { "epoch": 0.2748765109406506, "grad_norm": 0.7542934135984135, "learning_rate": 4.4060690651346845e-05, "loss": 0.6158, "num_tokens": 153775610.0, "step": 25765 }, { "epoch": 0.27492985394684905, "grad_norm": 1.0391641767834334, "learning_rate": 4.40580035438664e-05, "loss": 0.6006, "num_tokens": 153797811.0, "step": 25770 }, { "epoch": 0.27498319695304746, "grad_norm": 1.308736300620982, "learning_rate": 4.405531592113489e-05, "loss": 0.6037, "num_tokens": 153831135.0, "step": 25775 }, { "epoch": 0.27503653995924593, "grad_norm": 1.1803116017917483, "learning_rate": 4.4052627783235963e-05, "loss": 0.6265, "num_tokens": 153865853.0, "step": 25780 }, { "epoch": 0.2750898829654444, "grad_norm": 0.8351279459205695, "learning_rate": 4.404993913025326e-05, "loss": 0.7245, "num_tokens": 153900914.0, "step": 25785 }, { "epoch": 0.27514322597164287, "grad_norm": 0.6605138870004217, "learning_rate": 4.404724996227044e-05, "loss": 0.5425, "num_tokens": 153938948.0, "step": 25790 }, { "epoch": 0.27519656897784134, "grad_norm": 1.9925888007580135, "learning_rate": 4.40445602793712e-05, "loss": 0.5133, "num_tokens": 153962515.0, "step": 25795 }, { "epoch": 0.27524991198403975, "grad_norm": 1.243010192851144, "learning_rate": 4.404187008163922e-05, "loss": 0.6508, "num_tokens": 153981564.0, "step": 25800 }, { "epoch": 0.2753032549902382, "grad_norm": 0.7642691852881994, "learning_rate": 4.4039179369158215e-05, "loss": 0.6686, "num_tokens": 154030460.0, "step": 25805 }, { "epoch": 0.2753565979964367, "grad_norm": 0.9936658059742679, "learning_rate": 4.4036488142011936e-05, "loss": 0.5034, "num_tokens": 154060584.0, "step": 25810 }, { "epoch": 0.27540994100263516, "grad_norm": 1.2208851660057447, "learning_rate": 4.40337964002841e-05, "loss": 0.4613, "num_tokens": 154093728.0, "step": 25815 }, { "epoch": 0.2754632840088336, "grad_norm": 1.4980438920686785, "learning_rate": 4.403110414405849e-05, "loss": 0.5428, "num_tokens": 154118037.0, "step": 25820 }, { "epoch": 0.27551662701503205, "grad_norm": 1.7280018281613567, "learning_rate": 4.402841137341887e-05, "loss": 0.654, "num_tokens": 154152781.0, "step": 25825 }, { "epoch": 0.2755699700212305, "grad_norm": 1.6657016003645746, "learning_rate": 4.402571808844904e-05, "loss": 0.5126, "num_tokens": 154175911.0, "step": 25830 }, { "epoch": 0.275623313027429, "grad_norm": 0.7535135586924172, "learning_rate": 4.402302428923281e-05, "loss": 0.5931, "num_tokens": 154207605.0, "step": 25835 }, { "epoch": 0.27567665603362745, "grad_norm": 1.8484271761531181, "learning_rate": 4.4020329975853996e-05, "loss": 0.6023, "num_tokens": 154227840.0, "step": 25840 }, { "epoch": 0.27572999903982587, "grad_norm": 1.2645127236236697, "learning_rate": 4.401763514839645e-05, "loss": 0.5294, "num_tokens": 154248934.0, "step": 25845 }, { "epoch": 0.27578334204602434, "grad_norm": 0.9087468489115844, "learning_rate": 4.4014939806944034e-05, "loss": 0.61, "num_tokens": 154272626.0, "step": 25850 }, { "epoch": 0.2758366850522228, "grad_norm": 0.9903374454180389, "learning_rate": 4.401224395158061e-05, "loss": 0.5883, "num_tokens": 154297497.0, "step": 25855 }, { "epoch": 0.2758900280584213, "grad_norm": 1.8802156432133652, "learning_rate": 4.400954758239007e-05, "loss": 0.6116, "num_tokens": 154327481.0, "step": 25860 }, { "epoch": 0.2759433710646197, "grad_norm": 1.2866819840786088, "learning_rate": 4.400685069945631e-05, "loss": 0.4809, "num_tokens": 154348427.0, "step": 25865 }, { "epoch": 0.27599671407081816, "grad_norm": 0.6449918003896316, "learning_rate": 4.400415330286328e-05, "loss": 0.4976, "num_tokens": 154377822.0, "step": 25870 }, { "epoch": 0.27605005707701663, "grad_norm": 0.8519405530518968, "learning_rate": 4.4001455392694895e-05, "loss": 0.7695, "num_tokens": 154416313.0, "step": 25875 }, { "epoch": 0.2761034000832151, "grad_norm": 1.23392606076497, "learning_rate": 4.39987569690351e-05, "loss": 0.685, "num_tokens": 154467269.0, "step": 25880 }, { "epoch": 0.27615674308941357, "grad_norm": 0.9585718680008827, "learning_rate": 4.399605803196789e-05, "loss": 0.5144, "num_tokens": 154486621.0, "step": 25885 }, { "epoch": 0.276210086095612, "grad_norm": 1.7516321370953385, "learning_rate": 4.3993358581577236e-05, "loss": 0.5474, "num_tokens": 154512184.0, "step": 25890 }, { "epoch": 0.27626342910181045, "grad_norm": 1.3667251669704552, "learning_rate": 4.399065861794715e-05, "loss": 0.6201, "num_tokens": 154542214.0, "step": 25895 }, { "epoch": 0.2763167721080089, "grad_norm": 2.165726979484783, "learning_rate": 4.398795814116163e-05, "loss": 0.666, "num_tokens": 154582115.0, "step": 25900 }, { "epoch": 0.2763701151142074, "grad_norm": 1.2094339004481436, "learning_rate": 4.398525715130471e-05, "loss": 0.4952, "num_tokens": 154618935.0, "step": 25905 }, { "epoch": 0.2764234581204058, "grad_norm": 1.3896830989118414, "learning_rate": 4.3982555648460464e-05, "loss": 0.5414, "num_tokens": 154637951.0, "step": 25910 }, { "epoch": 0.2764768011266043, "grad_norm": 1.4897909049966545, "learning_rate": 4.3979853632712944e-05, "loss": 0.7218, "num_tokens": 154669849.0, "step": 25915 }, { "epoch": 0.27653014413280275, "grad_norm": 0.8927535938826217, "learning_rate": 4.3977151104146234e-05, "loss": 0.5091, "num_tokens": 154713852.0, "step": 25920 }, { "epoch": 0.2765834871390012, "grad_norm": 0.9997829801097308, "learning_rate": 4.397444806284441e-05, "loss": 0.5061, "num_tokens": 154758708.0, "step": 25925 }, { "epoch": 0.2766368301451997, "grad_norm": 0.8298178693261491, "learning_rate": 4.397174450889161e-05, "loss": 0.6914, "num_tokens": 154815095.0, "step": 25930 }, { "epoch": 0.2766901731513981, "grad_norm": 0.9633531107363171, "learning_rate": 4.396904044237195e-05, "loss": 0.5881, "num_tokens": 154847486.0, "step": 25935 }, { "epoch": 0.27674351615759657, "grad_norm": 1.5949913162407208, "learning_rate": 4.3966335863369586e-05, "loss": 0.6811, "num_tokens": 154865372.0, "step": 25940 }, { "epoch": 0.27679685916379504, "grad_norm": 1.5762100764673732, "learning_rate": 4.396363077196867e-05, "loss": 0.656, "num_tokens": 154892696.0, "step": 25945 }, { "epoch": 0.2768502021699935, "grad_norm": 1.172174715663496, "learning_rate": 4.396092516825338e-05, "loss": 0.6263, "num_tokens": 154929694.0, "step": 25950 }, { "epoch": 0.2769035451761919, "grad_norm": 0.7274067262563431, "learning_rate": 4.395821905230792e-05, "loss": 0.5478, "num_tokens": 154962104.0, "step": 25955 }, { "epoch": 0.2769568881823904, "grad_norm": 1.8056226426908093, "learning_rate": 4.395551242421648e-05, "loss": 0.8572, "num_tokens": 154985521.0, "step": 25960 }, { "epoch": 0.27701023118858886, "grad_norm": 0.728896079560107, "learning_rate": 4.395280528406329e-05, "loss": 0.6496, "num_tokens": 155016500.0, "step": 25965 }, { "epoch": 0.27706357419478733, "grad_norm": 1.3037644976970697, "learning_rate": 4.39500976319326e-05, "loss": 0.6393, "num_tokens": 155041827.0, "step": 25970 }, { "epoch": 0.2771169172009858, "grad_norm": 1.4313857809449733, "learning_rate": 4.3947389467908666e-05, "loss": 0.8891, "num_tokens": 155074558.0, "step": 25975 }, { "epoch": 0.2771702602071842, "grad_norm": 0.988145693298086, "learning_rate": 4.394468079207575e-05, "loss": 0.6598, "num_tokens": 155110189.0, "step": 25980 }, { "epoch": 0.2772236032133827, "grad_norm": 1.4234187916142702, "learning_rate": 4.3941971604518146e-05, "loss": 0.6228, "num_tokens": 155156470.0, "step": 25985 }, { "epoch": 0.27727694621958116, "grad_norm": 1.762960221655018, "learning_rate": 4.3939261905320166e-05, "loss": 0.5624, "num_tokens": 155176400.0, "step": 25990 }, { "epoch": 0.2773302892257796, "grad_norm": 1.056888068618674, "learning_rate": 4.393655169456612e-05, "loss": 0.6428, "num_tokens": 155201506.0, "step": 25995 }, { "epoch": 0.27738363223197804, "grad_norm": 0.7448449929452765, "learning_rate": 4.393384097234034e-05, "loss": 0.5194, "num_tokens": 155232976.0, "step": 26000 }, { "epoch": 0.2774369752381765, "grad_norm": 0.8318580700607582, "learning_rate": 4.3931129738727184e-05, "loss": 0.5321, "num_tokens": 155266145.0, "step": 26005 }, { "epoch": 0.277490318244375, "grad_norm": 1.0485251335631602, "learning_rate": 4.392841799381103e-05, "loss": 0.5684, "num_tokens": 155309022.0, "step": 26010 }, { "epoch": 0.27754366125057345, "grad_norm": 1.1437076234930614, "learning_rate": 4.392570573767624e-05, "loss": 0.59, "num_tokens": 155333729.0, "step": 26015 }, { "epoch": 0.2775970042567719, "grad_norm": 0.8864990343196956, "learning_rate": 4.392299297040724e-05, "loss": 0.575, "num_tokens": 155361975.0, "step": 26020 }, { "epoch": 0.27765034726297033, "grad_norm": 1.6785818077405588, "learning_rate": 4.392027969208843e-05, "loss": 0.5875, "num_tokens": 155386581.0, "step": 26025 }, { "epoch": 0.2777036902691688, "grad_norm": 0.9767638445478751, "learning_rate": 4.391756590280424e-05, "loss": 0.6009, "num_tokens": 155413673.0, "step": 26030 }, { "epoch": 0.27775703327536727, "grad_norm": 1.1162108617282096, "learning_rate": 4.391485160263913e-05, "loss": 0.63, "num_tokens": 155436342.0, "step": 26035 }, { "epoch": 0.27781037628156574, "grad_norm": 1.6914306998398227, "learning_rate": 4.391213679167754e-05, "loss": 0.9183, "num_tokens": 155462512.0, "step": 26040 }, { "epoch": 0.27786371928776415, "grad_norm": 1.495762618578599, "learning_rate": 4.3909421470003974e-05, "loss": 0.567, "num_tokens": 155485107.0, "step": 26045 }, { "epoch": 0.2779170622939626, "grad_norm": 0.9752974735447214, "learning_rate": 4.3906705637702915e-05, "loss": 0.6841, "num_tokens": 155516456.0, "step": 26050 }, { "epoch": 0.2779704053001611, "grad_norm": 1.0451719937823531, "learning_rate": 4.3903989294858886e-05, "loss": 0.4874, "num_tokens": 155534775.0, "step": 26055 }, { "epoch": 0.27802374830635956, "grad_norm": 1.7699032827416505, "learning_rate": 4.3901272441556394e-05, "loss": 0.7358, "num_tokens": 155570521.0, "step": 26060 }, { "epoch": 0.27807709131255803, "grad_norm": 1.5964373675054306, "learning_rate": 4.389855507788e-05, "loss": 0.549, "num_tokens": 155595988.0, "step": 26065 }, { "epoch": 0.27813043431875645, "grad_norm": 0.9802936454976688, "learning_rate": 4.3895837203914246e-05, "loss": 0.4682, "num_tokens": 155626511.0, "step": 26070 }, { "epoch": 0.2781837773249549, "grad_norm": 0.6984607139952125, "learning_rate": 4.3893118819743725e-05, "loss": 0.6264, "num_tokens": 155667838.0, "step": 26075 }, { "epoch": 0.2782371203311534, "grad_norm": 0.8564097306327978, "learning_rate": 4.389039992545302e-05, "loss": 0.5434, "num_tokens": 155700469.0, "step": 26080 }, { "epoch": 0.27829046333735186, "grad_norm": 1.0191624044231098, "learning_rate": 4.3887680521126736e-05, "loss": 0.6824, "num_tokens": 155735201.0, "step": 26085 }, { "epoch": 0.27834380634355027, "grad_norm": 0.8371904270059893, "learning_rate": 4.388496060684949e-05, "loss": 0.7679, "num_tokens": 155756057.0, "step": 26090 }, { "epoch": 0.27839714934974874, "grad_norm": 0.8725077836681471, "learning_rate": 4.388224018270592e-05, "loss": 0.6419, "num_tokens": 155787056.0, "step": 26095 }, { "epoch": 0.2784504923559472, "grad_norm": 1.4527470520313175, "learning_rate": 4.3879519248780696e-05, "loss": 0.6645, "num_tokens": 155812637.0, "step": 26100 }, { "epoch": 0.2785038353621457, "grad_norm": 1.2635360848571058, "learning_rate": 4.3876797805158476e-05, "loss": 0.5363, "num_tokens": 155831243.0, "step": 26105 }, { "epoch": 0.27855717836834415, "grad_norm": 0.8076056219260075, "learning_rate": 4.387407585192395e-05, "loss": 0.552, "num_tokens": 155866903.0, "step": 26110 }, { "epoch": 0.27861052137454256, "grad_norm": 1.2035045230153063, "learning_rate": 4.387135338916181e-05, "loss": 0.7069, "num_tokens": 155895166.0, "step": 26115 }, { "epoch": 0.27866386438074103, "grad_norm": 0.9531376792199465, "learning_rate": 4.3868630416956784e-05, "loss": 0.5468, "num_tokens": 155924565.0, "step": 26120 }, { "epoch": 0.2787172073869395, "grad_norm": 0.8395370405038498, "learning_rate": 4.3865906935393594e-05, "loss": 0.5864, "num_tokens": 155954081.0, "step": 26125 }, { "epoch": 0.278770550393138, "grad_norm": 1.1227601032661552, "learning_rate": 4.386318294455701e-05, "loss": 0.5575, "num_tokens": 155977914.0, "step": 26130 }, { "epoch": 0.2788238933993364, "grad_norm": 0.9743884509043786, "learning_rate": 4.386045844453177e-05, "loss": 0.6941, "num_tokens": 156008866.0, "step": 26135 }, { "epoch": 0.27887723640553486, "grad_norm": 0.8866357114448096, "learning_rate": 4.385773343540268e-05, "loss": 0.5685, "num_tokens": 156032869.0, "step": 26140 }, { "epoch": 0.2789305794117333, "grad_norm": 0.9168996044120344, "learning_rate": 4.3855007917254525e-05, "loss": 0.7371, "num_tokens": 156070934.0, "step": 26145 }, { "epoch": 0.2789839224179318, "grad_norm": 0.9668243039616401, "learning_rate": 4.3852281890172106e-05, "loss": 0.6339, "num_tokens": 156104448.0, "step": 26150 }, { "epoch": 0.27903726542413027, "grad_norm": 1.1180227950214563, "learning_rate": 4.3849555354240276e-05, "loss": 0.6037, "num_tokens": 156153510.0, "step": 26155 }, { "epoch": 0.2790906084303287, "grad_norm": 1.1967046976417353, "learning_rate": 4.384682830954386e-05, "loss": 0.7783, "num_tokens": 156194055.0, "step": 26160 }, { "epoch": 0.27914395143652715, "grad_norm": 1.2232749040631652, "learning_rate": 4.384410075616772e-05, "loss": 0.6098, "num_tokens": 156209470.0, "step": 26165 }, { "epoch": 0.2791972944427256, "grad_norm": 1.3430041941088948, "learning_rate": 4.384137269419675e-05, "loss": 0.5834, "num_tokens": 156240996.0, "step": 26170 }, { "epoch": 0.2792506374489241, "grad_norm": 0.8239789119570262, "learning_rate": 4.3838644123715814e-05, "loss": 0.5097, "num_tokens": 156285007.0, "step": 26175 }, { "epoch": 0.2793039804551225, "grad_norm": 1.0725502972980783, "learning_rate": 4.383591504480983e-05, "loss": 0.763, "num_tokens": 156308379.0, "step": 26180 }, { "epoch": 0.27935732346132097, "grad_norm": 0.9065688490909934, "learning_rate": 4.383318545756375e-05, "loss": 0.4597, "num_tokens": 156336911.0, "step": 26185 }, { "epoch": 0.27941066646751944, "grad_norm": 0.7696937836922267, "learning_rate": 4.383045536206247e-05, "loss": 0.6602, "num_tokens": 156374824.0, "step": 26190 }, { "epoch": 0.2794640094737179, "grad_norm": 1.1988360841160492, "learning_rate": 4.3827724758390956e-05, "loss": 0.5598, "num_tokens": 156395439.0, "step": 26195 }, { "epoch": 0.2795173524799164, "grad_norm": 0.8505496607183879, "learning_rate": 4.38249936466342e-05, "loss": 0.5477, "num_tokens": 156431415.0, "step": 26200 }, { "epoch": 0.2795706954861148, "grad_norm": 3.287736539588045, "learning_rate": 4.382226202687717e-05, "loss": 0.5525, "num_tokens": 156474578.0, "step": 26205 }, { "epoch": 0.27962403849231326, "grad_norm": 0.7520460772598564, "learning_rate": 4.3819529899204866e-05, "loss": 0.7005, "num_tokens": 156516022.0, "step": 26210 }, { "epoch": 0.27967738149851173, "grad_norm": 0.8058324124022025, "learning_rate": 4.381679726370231e-05, "loss": 0.5596, "num_tokens": 156548289.0, "step": 26215 }, { "epoch": 0.2797307245047102, "grad_norm": 0.7938669717548746, "learning_rate": 4.381406412045455e-05, "loss": 0.5494, "num_tokens": 156582085.0, "step": 26220 }, { "epoch": 0.2797840675109086, "grad_norm": 1.2017077536416414, "learning_rate": 4.381133046954662e-05, "loss": 0.5758, "num_tokens": 156607842.0, "step": 26225 }, { "epoch": 0.2798374105171071, "grad_norm": 1.4736738844808095, "learning_rate": 4.3808596311063595e-05, "loss": 0.5288, "num_tokens": 156630792.0, "step": 26230 }, { "epoch": 0.27989075352330556, "grad_norm": 1.6951139392537855, "learning_rate": 4.380586164509055e-05, "loss": 0.5611, "num_tokens": 156666075.0, "step": 26235 }, { "epoch": 0.279944096529504, "grad_norm": 1.3640248664884516, "learning_rate": 4.380312647171258e-05, "loss": 0.5194, "num_tokens": 156683573.0, "step": 26240 }, { "epoch": 0.2799974395357025, "grad_norm": 1.2731606848202413, "learning_rate": 4.3800390791014804e-05, "loss": 0.6079, "num_tokens": 156720694.0, "step": 26245 }, { "epoch": 0.2800507825419009, "grad_norm": 0.9659258040440543, "learning_rate": 4.3797654603082346e-05, "loss": 0.4525, "num_tokens": 156734157.0, "step": 26250 }, { "epoch": 0.2801041255480994, "grad_norm": 0.8016166808709245, "learning_rate": 4.3794917908000356e-05, "loss": 0.5181, "num_tokens": 156752172.0, "step": 26255 }, { "epoch": 0.28015746855429785, "grad_norm": 0.8369782213930178, "learning_rate": 4.379218070585399e-05, "loss": 0.5569, "num_tokens": 156780280.0, "step": 26260 }, { "epoch": 0.2802108115604963, "grad_norm": 1.8048599202067988, "learning_rate": 4.378944299672842e-05, "loss": 0.6734, "num_tokens": 156798896.0, "step": 26265 }, { "epoch": 0.28026415456669473, "grad_norm": 1.1278772016885934, "learning_rate": 4.3786704780708854e-05, "loss": 0.6064, "num_tokens": 156824283.0, "step": 26270 }, { "epoch": 0.2803174975728932, "grad_norm": 0.9372160543677709, "learning_rate": 4.3783966057880485e-05, "loss": 0.5394, "num_tokens": 156850994.0, "step": 26275 }, { "epoch": 0.2803708405790917, "grad_norm": 1.6954980865327658, "learning_rate": 4.378122682832853e-05, "loss": 0.5559, "num_tokens": 156878028.0, "step": 26280 }, { "epoch": 0.28042418358529014, "grad_norm": 0.7236583428101042, "learning_rate": 4.377848709213826e-05, "loss": 0.4641, "num_tokens": 156916817.0, "step": 26285 }, { "epoch": 0.2804775265914886, "grad_norm": 1.5114976081781804, "learning_rate": 4.3775746849394896e-05, "loss": 0.5448, "num_tokens": 156943627.0, "step": 26290 }, { "epoch": 0.280530869597687, "grad_norm": 1.2706783281116842, "learning_rate": 4.377300610018372e-05, "loss": 0.7687, "num_tokens": 156969391.0, "step": 26295 }, { "epoch": 0.2805842126038855, "grad_norm": 2.7116037246585654, "learning_rate": 4.377026484459003e-05, "loss": 0.7011, "num_tokens": 156995939.0, "step": 26300 }, { "epoch": 0.28063755561008397, "grad_norm": 0.9108007134963563, "learning_rate": 4.3767523082699107e-05, "loss": 0.7169, "num_tokens": 157037618.0, "step": 26305 }, { "epoch": 0.28069089861628244, "grad_norm": 0.9068550760250705, "learning_rate": 4.3764780814596285e-05, "loss": 0.5683, "num_tokens": 157062133.0, "step": 26310 }, { "epoch": 0.28074424162248085, "grad_norm": 0.9882915735110807, "learning_rate": 4.376203804036689e-05, "loss": 0.5575, "num_tokens": 157085967.0, "step": 26315 }, { "epoch": 0.2807975846286793, "grad_norm": 0.7141354204894093, "learning_rate": 4.3759294760096274e-05, "loss": 0.7673, "num_tokens": 157128056.0, "step": 26320 }, { "epoch": 0.2808509276348778, "grad_norm": 1.3851278953905382, "learning_rate": 4.3756550973869806e-05, "loss": 0.609, "num_tokens": 157140077.0, "step": 26325 }, { "epoch": 0.28090427064107626, "grad_norm": 0.6650092340732889, "learning_rate": 4.3753806681772866e-05, "loss": 0.6131, "num_tokens": 157175399.0, "step": 26330 }, { "epoch": 0.28095761364727473, "grad_norm": 0.9914989731544253, "learning_rate": 4.375106188389084e-05, "loss": 0.5536, "num_tokens": 157212809.0, "step": 26335 }, { "epoch": 0.28101095665347314, "grad_norm": 0.7653445302974335, "learning_rate": 4.374831658030915e-05, "loss": 0.6048, "num_tokens": 157234032.0, "step": 26340 }, { "epoch": 0.2810642996596716, "grad_norm": 1.1497712614225728, "learning_rate": 4.3745570771113236e-05, "loss": 0.7968, "num_tokens": 157267133.0, "step": 26345 }, { "epoch": 0.2811176426658701, "grad_norm": 0.9351942038410046, "learning_rate": 4.374282445638851e-05, "loss": 0.6449, "num_tokens": 157288768.0, "step": 26350 }, { "epoch": 0.28117098567206855, "grad_norm": 1.089932715981616, "learning_rate": 4.374007763622047e-05, "loss": 0.5518, "num_tokens": 157312625.0, "step": 26355 }, { "epoch": 0.28122432867826697, "grad_norm": 1.1602751154610673, "learning_rate": 4.373733031069456e-05, "loss": 0.7433, "num_tokens": 157343996.0, "step": 26360 }, { "epoch": 0.28127767168446544, "grad_norm": 1.0672188279334782, "learning_rate": 4.373458247989628e-05, "loss": 0.6331, "num_tokens": 157389503.0, "step": 26365 }, { "epoch": 0.2813310146906639, "grad_norm": 0.8386951492105362, "learning_rate": 4.373183414391114e-05, "loss": 0.5467, "num_tokens": 157409689.0, "step": 26370 }, { "epoch": 0.2813843576968624, "grad_norm": 1.3468747924212925, "learning_rate": 4.3729085302824674e-05, "loss": 0.5781, "num_tokens": 157438010.0, "step": 26375 }, { "epoch": 0.28143770070306084, "grad_norm": 0.7271124495399993, "learning_rate": 4.37263359567224e-05, "loss": 0.5284, "num_tokens": 157471959.0, "step": 26380 }, { "epoch": 0.28149104370925926, "grad_norm": 1.0595563266149197, "learning_rate": 4.372358610568989e-05, "loss": 0.4476, "num_tokens": 157499793.0, "step": 26385 }, { "epoch": 0.28154438671545773, "grad_norm": 1.34591747337671, "learning_rate": 4.372083574981269e-05, "loss": 0.4506, "num_tokens": 157521248.0, "step": 26390 }, { "epoch": 0.2815977297216562, "grad_norm": 0.7406223219696811, "learning_rate": 4.3718084889176415e-05, "loss": 0.5627, "num_tokens": 157551940.0, "step": 26395 }, { "epoch": 0.28165107272785467, "grad_norm": 0.9828890500798114, "learning_rate": 4.3715333523866644e-05, "loss": 0.5608, "num_tokens": 157579072.0, "step": 26400 }, { "epoch": 0.2817044157340531, "grad_norm": 1.4726216782484343, "learning_rate": 4.3712581653969e-05, "loss": 0.712, "num_tokens": 157610678.0, "step": 26405 }, { "epoch": 0.28175775874025155, "grad_norm": 1.1334012230232562, "learning_rate": 4.370982927956912e-05, "loss": 0.6116, "num_tokens": 157638104.0, "step": 26410 }, { "epoch": 0.28181110174645, "grad_norm": 2.2287549675550253, "learning_rate": 4.370707640075264e-05, "loss": 0.6933, "num_tokens": 157669586.0, "step": 26415 }, { "epoch": 0.2818644447526485, "grad_norm": 1.1182743050124224, "learning_rate": 4.3704323017605245e-05, "loss": 0.4779, "num_tokens": 157693921.0, "step": 26420 }, { "epoch": 0.28191778775884696, "grad_norm": 0.700482513887422, "learning_rate": 4.370156913021259e-05, "loss": 0.5547, "num_tokens": 157728372.0, "step": 26425 }, { "epoch": 0.2819711307650454, "grad_norm": 0.8715635500314853, "learning_rate": 4.3698814738660395e-05, "loss": 0.6374, "num_tokens": 157756478.0, "step": 26430 }, { "epoch": 0.28202447377124384, "grad_norm": 1.6211710238842192, "learning_rate": 4.3696059843034346e-05, "loss": 0.699, "num_tokens": 157782625.0, "step": 26435 }, { "epoch": 0.2820778167774423, "grad_norm": 0.8377247793138508, "learning_rate": 4.36933044434202e-05, "loss": 0.7023, "num_tokens": 157811343.0, "step": 26440 }, { "epoch": 0.2821311597836408, "grad_norm": 1.1533213256431276, "learning_rate": 4.369054853990366e-05, "loss": 0.5119, "num_tokens": 157836088.0, "step": 26445 }, { "epoch": 0.2821845027898392, "grad_norm": 1.302603267661369, "learning_rate": 4.368779213257052e-05, "loss": 0.6723, "num_tokens": 157870908.0, "step": 26450 }, { "epoch": 0.28223784579603767, "grad_norm": 0.8207168952673651, "learning_rate": 4.368503522150654e-05, "loss": 0.5945, "num_tokens": 157899986.0, "step": 26455 }, { "epoch": 0.28229118880223614, "grad_norm": 1.1747542563677837, "learning_rate": 4.3682277806797504e-05, "loss": 0.5192, "num_tokens": 157911923.0, "step": 26460 }, { "epoch": 0.2823445318084346, "grad_norm": 1.080878803039164, "learning_rate": 4.3679519888529226e-05, "loss": 0.6404, "num_tokens": 157940084.0, "step": 26465 }, { "epoch": 0.2823978748146331, "grad_norm": 0.7725853909126787, "learning_rate": 4.367676146678751e-05, "loss": 0.4512, "num_tokens": 157971218.0, "step": 26470 }, { "epoch": 0.2824512178208315, "grad_norm": 1.2303697087188157, "learning_rate": 4.367400254165822e-05, "loss": 0.6397, "num_tokens": 158007450.0, "step": 26475 }, { "epoch": 0.28250456082702996, "grad_norm": 1.4254509750409001, "learning_rate": 4.3671243113227184e-05, "loss": 0.6127, "num_tokens": 158043876.0, "step": 26480 }, { "epoch": 0.28255790383322843, "grad_norm": 1.9566741176228384, "learning_rate": 4.3668483181580286e-05, "loss": 0.5909, "num_tokens": 158072171.0, "step": 26485 }, { "epoch": 0.2826112468394269, "grad_norm": 1.7630552919999118, "learning_rate": 4.36657227468034e-05, "loss": 0.5657, "num_tokens": 158089117.0, "step": 26490 }, { "epoch": 0.2826645898456253, "grad_norm": 1.5413253905459512, "learning_rate": 4.366296180898243e-05, "loss": 0.4079, "num_tokens": 158107862.0, "step": 26495 }, { "epoch": 0.2827179328518238, "grad_norm": 2.0709143765401876, "learning_rate": 4.366020036820328e-05, "loss": 0.6519, "num_tokens": 158146714.0, "step": 26500 }, { "epoch": 0.28277127585802225, "grad_norm": 1.1828456906702822, "learning_rate": 4.36574384245519e-05, "loss": 0.597, "num_tokens": 158179729.0, "step": 26505 }, { "epoch": 0.2828246188642207, "grad_norm": 1.4065091885198588, "learning_rate": 4.3654675978114215e-05, "loss": 0.5013, "num_tokens": 158211165.0, "step": 26510 }, { "epoch": 0.2828779618704192, "grad_norm": 1.139442976733941, "learning_rate": 4.36519130289762e-05, "loss": 0.5882, "num_tokens": 158251482.0, "step": 26515 }, { "epoch": 0.2829313048766176, "grad_norm": 1.2274161076077041, "learning_rate": 4.364914957722383e-05, "loss": 0.6221, "num_tokens": 158273967.0, "step": 26520 }, { "epoch": 0.2829846478828161, "grad_norm": 1.030976865044824, "learning_rate": 4.364638562294309e-05, "loss": 0.6055, "num_tokens": 158303403.0, "step": 26525 }, { "epoch": 0.28303799088901455, "grad_norm": 0.9087425067921441, "learning_rate": 4.3643621166220005e-05, "loss": 0.5822, "num_tokens": 158339268.0, "step": 26530 }, { "epoch": 0.283091333895213, "grad_norm": 1.0553282771801704, "learning_rate": 4.3640856207140576e-05, "loss": 0.5488, "num_tokens": 158360635.0, "step": 26535 }, { "epoch": 0.28314467690141143, "grad_norm": 0.8288237102325358, "learning_rate": 4.363809074579087e-05, "loss": 0.5132, "num_tokens": 158384762.0, "step": 26540 }, { "epoch": 0.2831980199076099, "grad_norm": 0.7537966313430498, "learning_rate": 4.363532478225693e-05, "loss": 0.4884, "num_tokens": 158424310.0, "step": 26545 }, { "epoch": 0.28325136291380837, "grad_norm": 0.7695950703218944, "learning_rate": 4.363255831662481e-05, "loss": 0.5077, "num_tokens": 158465318.0, "step": 26550 }, { "epoch": 0.28330470592000684, "grad_norm": 1.1447443533320716, "learning_rate": 4.3629791348980626e-05, "loss": 0.5109, "num_tokens": 158488940.0, "step": 26555 }, { "epoch": 0.2833580489262053, "grad_norm": 1.4128014238043591, "learning_rate": 4.3627023879410453e-05, "loss": 0.5192, "num_tokens": 158515202.0, "step": 26560 }, { "epoch": 0.2834113919324037, "grad_norm": 1.3884870462069339, "learning_rate": 4.362425590800044e-05, "loss": 0.5845, "num_tokens": 158539148.0, "step": 26565 }, { "epoch": 0.2834647349386022, "grad_norm": 1.0678879985941845, "learning_rate": 4.3621487434836696e-05, "loss": 0.6162, "num_tokens": 158567094.0, "step": 26570 }, { "epoch": 0.28351807794480066, "grad_norm": 1.0199180056399781, "learning_rate": 4.361871846000537e-05, "loss": 0.4321, "num_tokens": 158589019.0, "step": 26575 }, { "epoch": 0.28357142095099913, "grad_norm": 1.1133408814878247, "learning_rate": 4.361594898359264e-05, "loss": 0.6429, "num_tokens": 158628029.0, "step": 26580 }, { "epoch": 0.28362476395719755, "grad_norm": 1.4328778112193223, "learning_rate": 4.3613179005684676e-05, "loss": 0.5507, "num_tokens": 158662724.0, "step": 26585 }, { "epoch": 0.283678106963396, "grad_norm": 0.8597359516865587, "learning_rate": 4.3610408526367693e-05, "loss": 0.5322, "num_tokens": 158700117.0, "step": 26590 }, { "epoch": 0.2837314499695945, "grad_norm": 0.8934762756429822, "learning_rate": 4.360763754572788e-05, "loss": 0.5864, "num_tokens": 158723684.0, "step": 26595 }, { "epoch": 0.28378479297579295, "grad_norm": 1.022783300143932, "learning_rate": 4.360486606385147e-05, "loss": 0.6769, "num_tokens": 158752485.0, "step": 26600 }, { "epoch": 0.2838381359819914, "grad_norm": 1.4170434834443293, "learning_rate": 4.360209408082471e-05, "loss": 0.6286, "num_tokens": 158793625.0, "step": 26605 }, { "epoch": 0.28389147898818984, "grad_norm": 2.9810780104090235, "learning_rate": 4.3599321596733856e-05, "loss": 0.588, "num_tokens": 158811176.0, "step": 26610 }, { "epoch": 0.2839448219943883, "grad_norm": 0.774006651554063, "learning_rate": 4.3596548611665185e-05, "loss": 0.6026, "num_tokens": 158850813.0, "step": 26615 }, { "epoch": 0.2839981650005868, "grad_norm": 1.2456006501636068, "learning_rate": 4.359377512570499e-05, "loss": 0.6796, "num_tokens": 158874382.0, "step": 26620 }, { "epoch": 0.28405150800678525, "grad_norm": 1.1381284925232118, "learning_rate": 4.359100113893955e-05, "loss": 0.6138, "num_tokens": 158916224.0, "step": 26625 }, { "epoch": 0.28410485101298366, "grad_norm": 1.8048698033370507, "learning_rate": 4.358822665145523e-05, "loss": 0.5781, "num_tokens": 158936930.0, "step": 26630 }, { "epoch": 0.28415819401918213, "grad_norm": 1.1634593877468085, "learning_rate": 4.358545166333833e-05, "loss": 0.7074, "num_tokens": 158958641.0, "step": 26635 }, { "epoch": 0.2842115370253806, "grad_norm": 0.9263357782365707, "learning_rate": 4.3582676174675215e-05, "loss": 0.5831, "num_tokens": 158993240.0, "step": 26640 }, { "epoch": 0.28426488003157907, "grad_norm": 1.0716972859282767, "learning_rate": 4.3579900185552256e-05, "loss": 0.6399, "num_tokens": 159030200.0, "step": 26645 }, { "epoch": 0.28431822303777754, "grad_norm": 1.3048527693616025, "learning_rate": 4.357712369605583e-05, "loss": 0.4914, "num_tokens": 159049484.0, "step": 26650 }, { "epoch": 0.28437156604397595, "grad_norm": 0.9774340254445791, "learning_rate": 4.357434670627234e-05, "loss": 0.651, "num_tokens": 159089011.0, "step": 26655 }, { "epoch": 0.2844249090501744, "grad_norm": 1.324423723001952, "learning_rate": 4.35715692162882e-05, "loss": 0.687, "num_tokens": 159112464.0, "step": 26660 }, { "epoch": 0.2844782520563729, "grad_norm": 1.7403552067305714, "learning_rate": 4.356879122618984e-05, "loss": 0.6344, "num_tokens": 159142458.0, "step": 26665 }, { "epoch": 0.28453159506257136, "grad_norm": 1.838916715090321, "learning_rate": 4.356601273606369e-05, "loss": 0.5402, "num_tokens": 159180403.0, "step": 26670 }, { "epoch": 0.2845849380687698, "grad_norm": 0.7497001160001475, "learning_rate": 4.3563233745996235e-05, "loss": 0.7003, "num_tokens": 159216644.0, "step": 26675 }, { "epoch": 0.28463828107496825, "grad_norm": 1.3651216996017868, "learning_rate": 4.356045425607395e-05, "loss": 0.577, "num_tokens": 159258277.0, "step": 26680 }, { "epoch": 0.2846916240811667, "grad_norm": 0.953751461300793, "learning_rate": 4.35576742663833e-05, "loss": 0.7325, "num_tokens": 159285200.0, "step": 26685 }, { "epoch": 0.2847449670873652, "grad_norm": 0.8000515332254912, "learning_rate": 4.355489377701081e-05, "loss": 0.5958, "num_tokens": 159320313.0, "step": 26690 }, { "epoch": 0.28479831009356366, "grad_norm": 1.0983399568814383, "learning_rate": 4.355211278804301e-05, "loss": 0.4976, "num_tokens": 159343130.0, "step": 26695 }, { "epoch": 0.28485165309976207, "grad_norm": 1.536775879809346, "learning_rate": 4.3549331299566434e-05, "loss": 0.532, "num_tokens": 159380587.0, "step": 26700 }, { "epoch": 0.28490499610596054, "grad_norm": 0.775264877890144, "learning_rate": 4.354654931166763e-05, "loss": 0.5843, "num_tokens": 159418072.0, "step": 26705 }, { "epoch": 0.284958339112159, "grad_norm": 0.888958043814602, "learning_rate": 4.354376682443318e-05, "loss": 0.4682, "num_tokens": 159437086.0, "step": 26710 }, { "epoch": 0.2850116821183575, "grad_norm": 1.0138552404104617, "learning_rate": 4.354098383794965e-05, "loss": 0.5575, "num_tokens": 159454981.0, "step": 26715 }, { "epoch": 0.2850650251245559, "grad_norm": 0.9256460408215307, "learning_rate": 4.353820035230366e-05, "loss": 0.6205, "num_tokens": 159499350.0, "step": 26720 }, { "epoch": 0.28511836813075436, "grad_norm": 0.7401684068665032, "learning_rate": 4.353541636758181e-05, "loss": 0.5063, "num_tokens": 159523005.0, "step": 26725 }, { "epoch": 0.28517171113695283, "grad_norm": 1.3707907117551537, "learning_rate": 4.353263188387075e-05, "loss": 0.6039, "num_tokens": 159541772.0, "step": 26730 }, { "epoch": 0.2852250541431513, "grad_norm": 1.2539300542091043, "learning_rate": 4.352984690125712e-05, "loss": 0.493, "num_tokens": 159561701.0, "step": 26735 }, { "epoch": 0.28527839714934977, "grad_norm": 0.6549002129712174, "learning_rate": 4.3527061419827576e-05, "loss": 0.629, "num_tokens": 159593278.0, "step": 26740 }, { "epoch": 0.2853317401555482, "grad_norm": 1.1497435881323381, "learning_rate": 4.352427543966879e-05, "loss": 0.5129, "num_tokens": 159620716.0, "step": 26745 }, { "epoch": 0.28538508316174666, "grad_norm": 1.1890476134324135, "learning_rate": 4.352148896086749e-05, "loss": 0.5574, "num_tokens": 159643864.0, "step": 26750 }, { "epoch": 0.2854384261679451, "grad_norm": 1.04273708323018, "learning_rate": 4.351870198351035e-05, "loss": 0.6336, "num_tokens": 159672176.0, "step": 26755 }, { "epoch": 0.2854917691741436, "grad_norm": 1.0185790718764478, "learning_rate": 4.35159145076841e-05, "loss": 0.4547, "num_tokens": 159689660.0, "step": 26760 }, { "epoch": 0.285545112180342, "grad_norm": 1.3295858314820226, "learning_rate": 4.35131265334755e-05, "loss": 0.5726, "num_tokens": 159721651.0, "step": 26765 }, { "epoch": 0.2855984551865405, "grad_norm": 1.3086502938171618, "learning_rate": 4.351033806097129e-05, "loss": 0.5704, "num_tokens": 159757293.0, "step": 26770 }, { "epoch": 0.28565179819273895, "grad_norm": 0.9965092037627749, "learning_rate": 4.350754909025824e-05, "loss": 0.6155, "num_tokens": 159789701.0, "step": 26775 }, { "epoch": 0.2857051411989374, "grad_norm": 1.015626170130903, "learning_rate": 4.3504759621423145e-05, "loss": 0.5724, "num_tokens": 159829894.0, "step": 26780 }, { "epoch": 0.2857584842051359, "grad_norm": 0.7718730616307593, "learning_rate": 4.3501969654552814e-05, "loss": 0.6095, "num_tokens": 159858542.0, "step": 26785 }, { "epoch": 0.2858118272113343, "grad_norm": 1.1747194913995949, "learning_rate": 4.349917918973405e-05, "loss": 0.5486, "num_tokens": 159877776.0, "step": 26790 }, { "epoch": 0.28586517021753277, "grad_norm": 0.8061141472925746, "learning_rate": 4.349638822705369e-05, "loss": 0.5677, "num_tokens": 159915356.0, "step": 26795 }, { "epoch": 0.28591851322373124, "grad_norm": 1.0631592862278871, "learning_rate": 4.3493596766598586e-05, "loss": 0.8344, "num_tokens": 159959689.0, "step": 26800 }, { "epoch": 0.2859718562299297, "grad_norm": 0.9475724243377803, "learning_rate": 4.349080480845561e-05, "loss": 0.5591, "num_tokens": 159989120.0, "step": 26805 }, { "epoch": 0.2860251992361281, "grad_norm": 1.4164975319427346, "learning_rate": 4.3488012352711635e-05, "loss": 0.6593, "num_tokens": 160023982.0, "step": 26810 }, { "epoch": 0.2860785422423266, "grad_norm": 1.272834887319789, "learning_rate": 4.348521939945355e-05, "loss": 0.5727, "num_tokens": 160045452.0, "step": 26815 }, { "epoch": 0.28613188524852506, "grad_norm": 1.293395802843967, "learning_rate": 4.348242594876827e-05, "loss": 0.564, "num_tokens": 160062562.0, "step": 26820 }, { "epoch": 0.28618522825472353, "grad_norm": 1.4168614217871487, "learning_rate": 4.347963200074272e-05, "loss": 0.6127, "num_tokens": 160090145.0, "step": 26825 }, { "epoch": 0.286238571260922, "grad_norm": 1.1448325663650871, "learning_rate": 4.3476837555463856e-05, "loss": 0.5539, "num_tokens": 160109943.0, "step": 26830 }, { "epoch": 0.2862919142671204, "grad_norm": 0.8608367061523595, "learning_rate": 4.347404261301862e-05, "loss": 0.4806, "num_tokens": 160131031.0, "step": 26835 }, { "epoch": 0.2863452572733189, "grad_norm": 1.3179848517536075, "learning_rate": 4.347124717349399e-05, "loss": 0.5484, "num_tokens": 160159512.0, "step": 26840 }, { "epoch": 0.28639860027951736, "grad_norm": 0.8016789304230775, "learning_rate": 4.346845123697695e-05, "loss": 0.4487, "num_tokens": 160192798.0, "step": 26845 }, { "epoch": 0.2864519432857158, "grad_norm": 0.8703342586675605, "learning_rate": 4.346565480355451e-05, "loss": 0.603, "num_tokens": 160228272.0, "step": 26850 }, { "epoch": 0.28650528629191424, "grad_norm": 0.79749267386623, "learning_rate": 4.346285787331369e-05, "loss": 0.6147, "num_tokens": 160257844.0, "step": 26855 }, { "epoch": 0.2865586292981127, "grad_norm": 0.7601209935402697, "learning_rate": 4.346006044634153e-05, "loss": 0.6472, "num_tokens": 160306520.0, "step": 26860 }, { "epoch": 0.2866119723043112, "grad_norm": 0.8868700250761838, "learning_rate": 4.345726252272505e-05, "loss": 0.8056, "num_tokens": 160339463.0, "step": 26865 }, { "epoch": 0.28666531531050965, "grad_norm": 0.7208418177631236, "learning_rate": 4.345446410255135e-05, "loss": 0.5382, "num_tokens": 160375799.0, "step": 26870 }, { "epoch": 0.2867186583167081, "grad_norm": 0.6829297345644234, "learning_rate": 4.3451665185907496e-05, "loss": 0.5331, "num_tokens": 160407685.0, "step": 26875 }, { "epoch": 0.28677200132290653, "grad_norm": 0.7281419228357426, "learning_rate": 4.3448865772880594e-05, "loss": 0.5806, "num_tokens": 160433326.0, "step": 26880 }, { "epoch": 0.286825344329105, "grad_norm": 1.4043832151317681, "learning_rate": 4.344606586355774e-05, "loss": 0.5503, "num_tokens": 160452538.0, "step": 26885 }, { "epoch": 0.2868786873353035, "grad_norm": 0.7886513622770498, "learning_rate": 4.3443265458026075e-05, "loss": 0.6558, "num_tokens": 160480383.0, "step": 26890 }, { "epoch": 0.28693203034150194, "grad_norm": 1.5577034558508422, "learning_rate": 4.344046455637274e-05, "loss": 0.6619, "num_tokens": 160513446.0, "step": 26895 }, { "epoch": 0.28698537334770036, "grad_norm": 1.324763084903605, "learning_rate": 4.3437663158684885e-05, "loss": 0.6582, "num_tokens": 160546413.0, "step": 26900 }, { "epoch": 0.2870387163538988, "grad_norm": 0.6951341080433673, "learning_rate": 4.3434861265049694e-05, "loss": 0.6399, "num_tokens": 160570091.0, "step": 26905 }, { "epoch": 0.2870920593600973, "grad_norm": 0.9693574914817036, "learning_rate": 4.343205887555434e-05, "loss": 0.4356, "num_tokens": 160583227.0, "step": 26910 }, { "epoch": 0.28714540236629577, "grad_norm": 1.4843989313879407, "learning_rate": 4.342925599028606e-05, "loss": 0.4806, "num_tokens": 160611899.0, "step": 26915 }, { "epoch": 0.28719874537249424, "grad_norm": 0.8627054474810181, "learning_rate": 4.342645260933203e-05, "loss": 0.6235, "num_tokens": 160633073.0, "step": 26920 }, { "epoch": 0.28725208837869265, "grad_norm": 1.2622602885689709, "learning_rate": 4.3423648732779526e-05, "loss": 0.5402, "num_tokens": 160659016.0, "step": 26925 }, { "epoch": 0.2873054313848911, "grad_norm": 1.1687773740678156, "learning_rate": 4.342084436071578e-05, "loss": 0.5239, "num_tokens": 160684261.0, "step": 26930 }, { "epoch": 0.2873587743910896, "grad_norm": 2.03722281292728, "learning_rate": 4.3418039493228054e-05, "loss": 0.6362, "num_tokens": 160717223.0, "step": 26935 }, { "epoch": 0.28741211739728806, "grad_norm": 1.2354881159026, "learning_rate": 4.341523413040363e-05, "loss": 0.5938, "num_tokens": 160737717.0, "step": 26940 }, { "epoch": 0.2874654604034865, "grad_norm": 1.1425023515024553, "learning_rate": 4.341242827232982e-05, "loss": 0.5867, "num_tokens": 160758336.0, "step": 26945 }, { "epoch": 0.28751880340968494, "grad_norm": 0.6696235417272542, "learning_rate": 4.340962191909393e-05, "loss": 0.5597, "num_tokens": 160806008.0, "step": 26950 }, { "epoch": 0.2875721464158834, "grad_norm": 0.7893818471969827, "learning_rate": 4.340681507078328e-05, "loss": 0.5161, "num_tokens": 160833801.0, "step": 26955 }, { "epoch": 0.2876254894220819, "grad_norm": 1.1194354784321372, "learning_rate": 4.3404007727485216e-05, "loss": 0.6904, "num_tokens": 160873536.0, "step": 26960 }, { "epoch": 0.28767883242828035, "grad_norm": 0.925989723835461, "learning_rate": 4.34011998892871e-05, "loss": 0.7078, "num_tokens": 160905009.0, "step": 26965 }, { "epoch": 0.28773217543447877, "grad_norm": 2.6876588459874693, "learning_rate": 4.339839155627631e-05, "loss": 0.7286, "num_tokens": 160931033.0, "step": 26970 }, { "epoch": 0.28778551844067723, "grad_norm": 1.6835228064072048, "learning_rate": 4.339558272854023e-05, "loss": 0.6315, "num_tokens": 160962122.0, "step": 26975 }, { "epoch": 0.2878388614468757, "grad_norm": 1.542296385074497, "learning_rate": 4.339277340616626e-05, "loss": 0.516, "num_tokens": 160979626.0, "step": 26980 }, { "epoch": 0.2878922044530742, "grad_norm": 1.202304352301318, "learning_rate": 4.338996358924183e-05, "loss": 0.5178, "num_tokens": 160999917.0, "step": 26985 }, { "epoch": 0.2879455474592726, "grad_norm": 1.032015275538618, "learning_rate": 4.3387153277854374e-05, "loss": 0.5228, "num_tokens": 161036192.0, "step": 26990 }, { "epoch": 0.28799889046547106, "grad_norm": 1.0131021350019886, "learning_rate": 4.338434247209134e-05, "loss": 0.5816, "num_tokens": 161073829.0, "step": 26995 }, { "epoch": 0.2880522334716695, "grad_norm": 2.1676425089117224, "learning_rate": 4.3381531172040194e-05, "loss": 0.5119, "num_tokens": 161105991.0, "step": 27000 }, { "epoch": 0.288105576477868, "grad_norm": 0.6793919740868021, "learning_rate": 4.337871937778842e-05, "loss": 0.5766, "num_tokens": 161139247.0, "step": 27005 }, { "epoch": 0.28815891948406647, "grad_norm": 0.9808673279309004, "learning_rate": 4.3375907089423516e-05, "loss": 0.699, "num_tokens": 161182761.0, "step": 27010 }, { "epoch": 0.2882122624902649, "grad_norm": 1.447515134663185, "learning_rate": 4.3373094307032994e-05, "loss": 0.5161, "num_tokens": 161200351.0, "step": 27015 }, { "epoch": 0.28826560549646335, "grad_norm": 0.833802743171291, "learning_rate": 4.3370281030704384e-05, "loss": 0.5487, "num_tokens": 161236186.0, "step": 27020 }, { "epoch": 0.2883189485026618, "grad_norm": 2.2340455714538514, "learning_rate": 4.336746726052522e-05, "loss": 0.5985, "num_tokens": 161264591.0, "step": 27025 }, { "epoch": 0.2883722915088603, "grad_norm": 1.533783483680243, "learning_rate": 4.336465299658307e-05, "loss": 0.4955, "num_tokens": 161280693.0, "step": 27030 }, { "epoch": 0.2884256345150587, "grad_norm": 1.1876542695248395, "learning_rate": 4.336183823896551e-05, "loss": 0.6748, "num_tokens": 161308271.0, "step": 27035 }, { "epoch": 0.2884789775212572, "grad_norm": 0.8157661164683357, "learning_rate": 4.335902298776013e-05, "loss": 0.5657, "num_tokens": 161356330.0, "step": 27040 }, { "epoch": 0.28853232052745564, "grad_norm": 1.1402916684928364, "learning_rate": 4.3356207243054514e-05, "loss": 0.5452, "num_tokens": 161383193.0, "step": 27045 }, { "epoch": 0.2885856635336541, "grad_norm": 0.879307853665544, "learning_rate": 4.335339100493631e-05, "loss": 0.5751, "num_tokens": 161416542.0, "step": 27050 }, { "epoch": 0.2886390065398526, "grad_norm": 1.3086214175535338, "learning_rate": 4.3350574273493136e-05, "loss": 0.7721, "num_tokens": 161453572.0, "step": 27055 }, { "epoch": 0.288692349546051, "grad_norm": 4.102137148670898, "learning_rate": 4.3347757048812646e-05, "loss": 0.727, "num_tokens": 161476527.0, "step": 27060 }, { "epoch": 0.28874569255224947, "grad_norm": 1.2912717306411325, "learning_rate": 4.3344939330982514e-05, "loss": 0.5667, "num_tokens": 161516376.0, "step": 27065 }, { "epoch": 0.28879903555844794, "grad_norm": 0.8652607914569481, "learning_rate": 4.334212112009042e-05, "loss": 0.5129, "num_tokens": 161555369.0, "step": 27070 }, { "epoch": 0.2888523785646464, "grad_norm": 2.861411073855275, "learning_rate": 4.3339302416224054e-05, "loss": 0.7161, "num_tokens": 161583853.0, "step": 27075 }, { "epoch": 0.2889057215708448, "grad_norm": 0.8751469881644508, "learning_rate": 4.333648321947112e-05, "loss": 0.537, "num_tokens": 161612296.0, "step": 27080 }, { "epoch": 0.2889590645770433, "grad_norm": 0.716207106640633, "learning_rate": 4.333366352991937e-05, "loss": 0.5897, "num_tokens": 161643263.0, "step": 27085 }, { "epoch": 0.28901240758324176, "grad_norm": 1.8318206381979363, "learning_rate": 4.3330843347656534e-05, "loss": 0.5646, "num_tokens": 161669823.0, "step": 27090 }, { "epoch": 0.28906575058944023, "grad_norm": 0.7545579702226786, "learning_rate": 4.3328022672770375e-05, "loss": 0.5912, "num_tokens": 161703268.0, "step": 27095 }, { "epoch": 0.2891190935956387, "grad_norm": 0.8611629950500492, "learning_rate": 4.332520150534866e-05, "loss": 0.528, "num_tokens": 161744299.0, "step": 27100 }, { "epoch": 0.2891724366018371, "grad_norm": 0.8846102364207739, "learning_rate": 4.332237984547916e-05, "loss": 0.5498, "num_tokens": 161785391.0, "step": 27105 }, { "epoch": 0.2892257796080356, "grad_norm": 0.7402563787178669, "learning_rate": 4.3319557693249725e-05, "loss": 0.5627, "num_tokens": 161816495.0, "step": 27110 }, { "epoch": 0.28927912261423405, "grad_norm": 0.8618691063745395, "learning_rate": 4.3316735048748136e-05, "loss": 0.5874, "num_tokens": 161835972.0, "step": 27115 }, { "epoch": 0.2893324656204325, "grad_norm": 0.9179433154134762, "learning_rate": 4.3313911912062244e-05, "loss": 0.5655, "num_tokens": 161877664.0, "step": 27120 }, { "epoch": 0.28938580862663094, "grad_norm": 1.1027827524680984, "learning_rate": 4.3311088283279896e-05, "loss": 0.5995, "num_tokens": 161915466.0, "step": 27125 }, { "epoch": 0.2894391516328294, "grad_norm": 0.8332716961879781, "learning_rate": 4.330826416248896e-05, "loss": 0.5987, "num_tokens": 161941318.0, "step": 27130 }, { "epoch": 0.2894924946390279, "grad_norm": 1.0598477553765018, "learning_rate": 4.330543954977731e-05, "loss": 0.7242, "num_tokens": 161965610.0, "step": 27135 }, { "epoch": 0.28954583764522634, "grad_norm": 0.8965752420235421, "learning_rate": 4.330261444523285e-05, "loss": 0.507, "num_tokens": 161996375.0, "step": 27140 }, { "epoch": 0.2895991806514248, "grad_norm": 1.2853526379309759, "learning_rate": 4.329978884894348e-05, "loss": 0.6178, "num_tokens": 162016651.0, "step": 27145 }, { "epoch": 0.28965252365762323, "grad_norm": 0.822650112905772, "learning_rate": 4.3296962760997146e-05, "loss": 0.5536, "num_tokens": 162060408.0, "step": 27150 }, { "epoch": 0.2897058666638217, "grad_norm": 1.6925981011421718, "learning_rate": 4.329413618148178e-05, "loss": 0.4927, "num_tokens": 162072125.0, "step": 27155 }, { "epoch": 0.28975920967002017, "grad_norm": 0.9396446094866031, "learning_rate": 4.3291309110485326e-05, "loss": 0.6027, "num_tokens": 162103484.0, "step": 27160 }, { "epoch": 0.28981255267621864, "grad_norm": 1.7149529910998067, "learning_rate": 4.3288481548095774e-05, "loss": 0.7093, "num_tokens": 162122532.0, "step": 27165 }, { "epoch": 0.28986589568241705, "grad_norm": 0.8475372310463514, "learning_rate": 4.3285653494401106e-05, "loss": 0.5775, "num_tokens": 162162036.0, "step": 27170 }, { "epoch": 0.2899192386886155, "grad_norm": 1.1524034463983697, "learning_rate": 4.328282494948933e-05, "loss": 0.611, "num_tokens": 162189863.0, "step": 27175 }, { "epoch": 0.289972581694814, "grad_norm": 1.4820344514256152, "learning_rate": 4.3279995913448454e-05, "loss": 0.6304, "num_tokens": 162214759.0, "step": 27180 }, { "epoch": 0.29002592470101246, "grad_norm": 1.6729556808154809, "learning_rate": 4.327716638636653e-05, "loss": 0.6994, "num_tokens": 162242640.0, "step": 27185 }, { "epoch": 0.29007926770721093, "grad_norm": 0.9631067256428875, "learning_rate": 4.327433636833158e-05, "loss": 0.4838, "num_tokens": 162264549.0, "step": 27190 }, { "epoch": 0.29013261071340934, "grad_norm": 1.0330435110598208, "learning_rate": 4.3271505859431695e-05, "loss": 0.5914, "num_tokens": 162292238.0, "step": 27195 }, { "epoch": 0.2901859537196078, "grad_norm": 0.929912777719158, "learning_rate": 4.326867485975493e-05, "loss": 0.6691, "num_tokens": 162331530.0, "step": 27200 }, { "epoch": 0.2902392967258063, "grad_norm": 1.08931178139257, "learning_rate": 4.326584336938941e-05, "loss": 0.6327, "num_tokens": 162378359.0, "step": 27205 }, { "epoch": 0.29029263973200475, "grad_norm": 0.799596672667883, "learning_rate": 4.326301138842321e-05, "loss": 0.5356, "num_tokens": 162398229.0, "step": 27210 }, { "epoch": 0.29034598273820317, "grad_norm": 0.8245350678252744, "learning_rate": 4.3260178916944495e-05, "loss": 0.4949, "num_tokens": 162433673.0, "step": 27215 }, { "epoch": 0.29039932574440164, "grad_norm": 0.7892197276086826, "learning_rate": 4.325734595504137e-05, "loss": 0.5624, "num_tokens": 162468640.0, "step": 27220 }, { "epoch": 0.2904526687506001, "grad_norm": 1.1858202053598512, "learning_rate": 4.325451250280201e-05, "loss": 0.6157, "num_tokens": 162486005.0, "step": 27225 }, { "epoch": 0.2905060117567986, "grad_norm": 1.2955749156275307, "learning_rate": 4.3251678560314576e-05, "loss": 0.6892, "num_tokens": 162506265.0, "step": 27230 }, { "epoch": 0.29055935476299705, "grad_norm": 1.2785309764001032, "learning_rate": 4.324884412766727e-05, "loss": 0.5823, "num_tokens": 162525804.0, "step": 27235 }, { "epoch": 0.29061269776919546, "grad_norm": 1.4741150216635368, "learning_rate": 4.324600920494828e-05, "loss": 0.6067, "num_tokens": 162560159.0, "step": 27240 }, { "epoch": 0.29066604077539393, "grad_norm": 0.9649944256877487, "learning_rate": 4.3243173792245825e-05, "loss": 0.6392, "num_tokens": 162587969.0, "step": 27245 }, { "epoch": 0.2907193837815924, "grad_norm": 1.4969939619796362, "learning_rate": 4.324033788964814e-05, "loss": 0.78, "num_tokens": 162621450.0, "step": 27250 }, { "epoch": 0.29077272678779087, "grad_norm": 1.767913654013241, "learning_rate": 4.3237501497243465e-05, "loss": 0.7844, "num_tokens": 162665459.0, "step": 27255 }, { "epoch": 0.2908260697939893, "grad_norm": 1.1513947182372626, "learning_rate": 4.323466461512008e-05, "loss": 0.6525, "num_tokens": 162697917.0, "step": 27260 }, { "epoch": 0.29087941280018775, "grad_norm": 0.9451848025293557, "learning_rate": 4.323182724336625e-05, "loss": 0.5042, "num_tokens": 162730643.0, "step": 27265 }, { "epoch": 0.2909327558063862, "grad_norm": 0.9494558176709611, "learning_rate": 4.322898938207026e-05, "loss": 0.5392, "num_tokens": 162773255.0, "step": 27270 }, { "epoch": 0.2909860988125847, "grad_norm": 1.023154970146816, "learning_rate": 4.322615103132044e-05, "loss": 0.5766, "num_tokens": 162802862.0, "step": 27275 }, { "epoch": 0.29103944181878316, "grad_norm": 1.0421370103638632, "learning_rate": 4.3223312191205094e-05, "loss": 0.5484, "num_tokens": 162835644.0, "step": 27280 }, { "epoch": 0.2910927848249816, "grad_norm": 0.8633313760772137, "learning_rate": 4.3220472861812575e-05, "loss": 0.6348, "num_tokens": 162859345.0, "step": 27285 }, { "epoch": 0.29114612783118005, "grad_norm": 2.0334209265978753, "learning_rate": 4.3217633043231235e-05, "loss": 0.6052, "num_tokens": 162894875.0, "step": 27290 }, { "epoch": 0.2911994708373785, "grad_norm": 0.9650243915166002, "learning_rate": 4.321479273554943e-05, "loss": 0.6882, "num_tokens": 162914498.0, "step": 27295 }, { "epoch": 0.291252813843577, "grad_norm": 0.8245618709026461, "learning_rate": 4.321195193885556e-05, "loss": 0.6111, "num_tokens": 162935524.0, "step": 27300 }, { "epoch": 0.2913061568497754, "grad_norm": 1.1552595698207175, "learning_rate": 4.320911065323802e-05, "loss": 0.6425, "num_tokens": 162966654.0, "step": 27305 }, { "epoch": 0.29135949985597387, "grad_norm": 1.2890675822709643, "learning_rate": 4.3206268878785216e-05, "loss": 0.5916, "num_tokens": 163002960.0, "step": 27310 }, { "epoch": 0.29141284286217234, "grad_norm": 0.9222585968328584, "learning_rate": 4.32034266155856e-05, "loss": 0.5149, "num_tokens": 163035701.0, "step": 27315 }, { "epoch": 0.2914661858683708, "grad_norm": 0.8392911530409122, "learning_rate": 4.320058386372759e-05, "loss": 0.6715, "num_tokens": 163053303.0, "step": 27320 }, { "epoch": 0.2915195288745693, "grad_norm": 1.0973684196578595, "learning_rate": 4.319774062329967e-05, "loss": 0.582, "num_tokens": 163082145.0, "step": 27325 }, { "epoch": 0.2915728718807677, "grad_norm": 0.92426011638455, "learning_rate": 4.31948968943903e-05, "loss": 0.6026, "num_tokens": 163099367.0, "step": 27330 }, { "epoch": 0.29162621488696616, "grad_norm": 0.7270459852737837, "learning_rate": 4.319205267708798e-05, "loss": 0.6682, "num_tokens": 163131283.0, "step": 27335 }, { "epoch": 0.29167955789316463, "grad_norm": 1.1867034610210818, "learning_rate": 4.3189207971481205e-05, "loss": 0.5512, "num_tokens": 163168521.0, "step": 27340 }, { "epoch": 0.2917329008993631, "grad_norm": 1.1433250737626428, "learning_rate": 4.318636277765851e-05, "loss": 0.6892, "num_tokens": 163212240.0, "step": 27345 }, { "epoch": 0.2917862439055615, "grad_norm": 0.8267249196874279, "learning_rate": 4.318351709570843e-05, "loss": 0.5421, "num_tokens": 163240260.0, "step": 27350 }, { "epoch": 0.29183958691176, "grad_norm": 1.0478007820547097, "learning_rate": 4.3180670925719505e-05, "loss": 0.6635, "num_tokens": 163269560.0, "step": 27355 }, { "epoch": 0.29189292991795845, "grad_norm": 1.107167173910571, "learning_rate": 4.317782426778032e-05, "loss": 0.6134, "num_tokens": 163305990.0, "step": 27360 }, { "epoch": 0.2919462729241569, "grad_norm": 1.0689876680299308, "learning_rate": 4.3174977121979436e-05, "loss": 0.585, "num_tokens": 163333501.0, "step": 27365 }, { "epoch": 0.2919996159303554, "grad_norm": 1.5428081281824553, "learning_rate": 4.317212948840546e-05, "loss": 0.7324, "num_tokens": 163367319.0, "step": 27370 }, { "epoch": 0.2920529589365538, "grad_norm": 1.2342073181156483, "learning_rate": 4.3169281367147015e-05, "loss": 0.7139, "num_tokens": 163414884.0, "step": 27375 }, { "epoch": 0.2921063019427523, "grad_norm": 1.2531696452646157, "learning_rate": 4.316643275829272e-05, "loss": 0.541, "num_tokens": 163442874.0, "step": 27380 }, { "epoch": 0.29215964494895075, "grad_norm": 1.4400805807767494, "learning_rate": 4.316358366193121e-05, "loss": 0.6102, "num_tokens": 163471900.0, "step": 27385 }, { "epoch": 0.2922129879551492, "grad_norm": 1.0144926482077516, "learning_rate": 4.316073407815116e-05, "loss": 0.5036, "num_tokens": 163494334.0, "step": 27390 }, { "epoch": 0.29226633096134763, "grad_norm": 0.8952480453846551, "learning_rate": 4.315788400704123e-05, "loss": 0.5243, "num_tokens": 163534671.0, "step": 27395 }, { "epoch": 0.2923196739675461, "grad_norm": 0.7718192003912195, "learning_rate": 4.315503344869011e-05, "loss": 0.5839, "num_tokens": 163580184.0, "step": 27400 }, { "epoch": 0.29237301697374457, "grad_norm": 0.929524292863264, "learning_rate": 4.3152182403186505e-05, "loss": 0.6257, "num_tokens": 163601161.0, "step": 27405 }, { "epoch": 0.29242635997994304, "grad_norm": 0.9551123631877769, "learning_rate": 4.3149330870619134e-05, "loss": 0.6525, "num_tokens": 163639898.0, "step": 27410 }, { "epoch": 0.2924797029861415, "grad_norm": 0.9721877717486401, "learning_rate": 4.314647885107673e-05, "loss": 0.5756, "num_tokens": 163677457.0, "step": 27415 }, { "epoch": 0.2925330459923399, "grad_norm": 1.1686987915546154, "learning_rate": 4.314362634464804e-05, "loss": 0.5082, "num_tokens": 163706382.0, "step": 27420 }, { "epoch": 0.2925863889985384, "grad_norm": 1.1537736640314884, "learning_rate": 4.3140773351421845e-05, "loss": 0.5503, "num_tokens": 163743309.0, "step": 27425 }, { "epoch": 0.29263973200473686, "grad_norm": 1.4818798239074995, "learning_rate": 4.31379198714869e-05, "loss": 0.48, "num_tokens": 163762281.0, "step": 27430 }, { "epoch": 0.29269307501093533, "grad_norm": 1.322595972738227, "learning_rate": 4.3135065904932004e-05, "loss": 0.514, "num_tokens": 163799326.0, "step": 27435 }, { "epoch": 0.29274641801713375, "grad_norm": 0.9811593774638816, "learning_rate": 4.313221145184598e-05, "loss": 0.6999, "num_tokens": 163835025.0, "step": 27440 }, { "epoch": 0.2927997610233322, "grad_norm": 0.757906343681063, "learning_rate": 4.312935651231764e-05, "loss": 0.5444, "num_tokens": 163872276.0, "step": 27445 }, { "epoch": 0.2928531040295307, "grad_norm": 1.2138554285595329, "learning_rate": 4.312650108643584e-05, "loss": 0.6733, "num_tokens": 163905538.0, "step": 27450 }, { "epoch": 0.29290644703572916, "grad_norm": 0.7400895555709049, "learning_rate": 4.312364517428942e-05, "loss": 0.473, "num_tokens": 163957416.0, "step": 27455 }, { "epoch": 0.2929597900419276, "grad_norm": 1.6950829602750837, "learning_rate": 4.3120788775967245e-05, "loss": 0.6054, "num_tokens": 163996714.0, "step": 27460 }, { "epoch": 0.29301313304812604, "grad_norm": 2.7424630907942396, "learning_rate": 4.311793189155822e-05, "loss": 0.5864, "num_tokens": 164009412.0, "step": 27465 }, { "epoch": 0.2930664760543245, "grad_norm": 0.9168843745428461, "learning_rate": 4.3115074521151236e-05, "loss": 0.5806, "num_tokens": 164047144.0, "step": 27470 }, { "epoch": 0.293119819060523, "grad_norm": 0.6358503282072111, "learning_rate": 4.311221666483519e-05, "loss": 0.5831, "num_tokens": 164082962.0, "step": 27475 }, { "epoch": 0.29317316206672145, "grad_norm": 1.0168539210963157, "learning_rate": 4.3109358322699044e-05, "loss": 0.5862, "num_tokens": 164113862.0, "step": 27480 }, { "epoch": 0.29322650507291986, "grad_norm": 1.1488476638594685, "learning_rate": 4.3106499494831723e-05, "loss": 0.6742, "num_tokens": 164149582.0, "step": 27485 }, { "epoch": 0.29327984807911833, "grad_norm": 1.0635991813281325, "learning_rate": 4.31036401813222e-05, "loss": 0.6523, "num_tokens": 164190175.0, "step": 27490 }, { "epoch": 0.2933331910853168, "grad_norm": 0.7527805506104268, "learning_rate": 4.310078038225945e-05, "loss": 0.4981, "num_tokens": 164220087.0, "step": 27495 }, { "epoch": 0.29338653409151527, "grad_norm": 1.0839446956410803, "learning_rate": 4.3097920097732444e-05, "loss": 0.5382, "num_tokens": 164247081.0, "step": 27500 }, { "epoch": 0.29343987709771374, "grad_norm": 0.8592480713292422, "learning_rate": 4.309505932783022e-05, "loss": 0.5025, "num_tokens": 164264602.0, "step": 27505 }, { "epoch": 0.29349322010391216, "grad_norm": 0.9771880960678867, "learning_rate": 4.309219807264177e-05, "loss": 0.5137, "num_tokens": 164294173.0, "step": 27510 }, { "epoch": 0.2935465631101106, "grad_norm": 0.9566698019755545, "learning_rate": 4.3089336332256154e-05, "loss": 0.6398, "num_tokens": 164332772.0, "step": 27515 }, { "epoch": 0.2935999061163091, "grad_norm": 1.1373353003361777, "learning_rate": 4.3086474106762395e-05, "loss": 0.6644, "num_tokens": 164374316.0, "step": 27520 }, { "epoch": 0.29365324912250756, "grad_norm": 1.5002759588837462, "learning_rate": 4.30836113962496e-05, "loss": 0.6509, "num_tokens": 164404659.0, "step": 27525 }, { "epoch": 0.293706592128706, "grad_norm": 1.1996644183368075, "learning_rate": 4.308074820080681e-05, "loss": 0.5142, "num_tokens": 164440514.0, "step": 27530 }, { "epoch": 0.29375993513490445, "grad_norm": 3.166112568359307, "learning_rate": 4.307788452052315e-05, "loss": 0.5676, "num_tokens": 164457045.0, "step": 27535 }, { "epoch": 0.2938132781411029, "grad_norm": 1.9993691900275565, "learning_rate": 4.307502035548772e-05, "loss": 0.679, "num_tokens": 164484109.0, "step": 27540 }, { "epoch": 0.2938666211473014, "grad_norm": 1.2156468168358023, "learning_rate": 4.307215570578965e-05, "loss": 0.6319, "num_tokens": 164510543.0, "step": 27545 }, { "epoch": 0.29391996415349986, "grad_norm": 1.014956925546626, "learning_rate": 4.306929057151808e-05, "loss": 0.5586, "num_tokens": 164546565.0, "step": 27550 }, { "epoch": 0.29397330715969827, "grad_norm": 1.1252985610240767, "learning_rate": 4.3066424952762165e-05, "loss": 0.4677, "num_tokens": 164571622.0, "step": 27555 }, { "epoch": 0.29402665016589674, "grad_norm": 1.0667556939256995, "learning_rate": 4.306355884961108e-05, "loss": 0.5809, "num_tokens": 164627468.0, "step": 27560 }, { "epoch": 0.2940799931720952, "grad_norm": 0.9576221731567053, "learning_rate": 4.306069226215401e-05, "loss": 0.5333, "num_tokens": 164658922.0, "step": 27565 }, { "epoch": 0.2941333361782937, "grad_norm": 0.990275566331788, "learning_rate": 4.305782519048016e-05, "loss": 0.6526, "num_tokens": 164698068.0, "step": 27570 }, { "epoch": 0.2941866791844921, "grad_norm": 0.8537779977523349, "learning_rate": 4.3054957634678754e-05, "loss": 0.557, "num_tokens": 164726905.0, "step": 27575 }, { "epoch": 0.29424002219069056, "grad_norm": 1.2359532882380995, "learning_rate": 4.305208959483901e-05, "loss": 0.4705, "num_tokens": 164743342.0, "step": 27580 }, { "epoch": 0.29429336519688903, "grad_norm": 0.8511104210600648, "learning_rate": 4.3049221071050186e-05, "loss": 0.6931, "num_tokens": 164767095.0, "step": 27585 }, { "epoch": 0.2943467082030875, "grad_norm": 1.0434603188884972, "learning_rate": 4.304635206340154e-05, "loss": 0.5476, "num_tokens": 164801069.0, "step": 27590 }, { "epoch": 0.294400051209286, "grad_norm": 1.0116892913855504, "learning_rate": 4.3043482571982355e-05, "loss": 0.5739, "num_tokens": 164825548.0, "step": 27595 }, { "epoch": 0.2944533942154844, "grad_norm": 0.9610073991053887, "learning_rate": 4.3040612596881914e-05, "loss": 0.492, "num_tokens": 164843463.0, "step": 27600 }, { "epoch": 0.29450673722168286, "grad_norm": 1.4802579720683393, "learning_rate": 4.303774213818953e-05, "loss": 0.572, "num_tokens": 164861370.0, "step": 27605 }, { "epoch": 0.2945600802278813, "grad_norm": 1.0959664923325239, "learning_rate": 4.3034871195994524e-05, "loss": 0.6051, "num_tokens": 164888303.0, "step": 27610 }, { "epoch": 0.2946134232340798, "grad_norm": 1.4616139600638232, "learning_rate": 4.303199977038624e-05, "loss": 0.6676, "num_tokens": 164910234.0, "step": 27615 }, { "epoch": 0.2946667662402782, "grad_norm": 1.2318528190603613, "learning_rate": 4.3029127861454034e-05, "loss": 0.4443, "num_tokens": 164928538.0, "step": 27620 }, { "epoch": 0.2947201092464767, "grad_norm": 1.3422197579909603, "learning_rate": 4.302625546928725e-05, "loss": 0.5647, "num_tokens": 164952051.0, "step": 27625 }, { "epoch": 0.29477345225267515, "grad_norm": 1.1954985517632586, "learning_rate": 4.30233825939753e-05, "loss": 0.5451, "num_tokens": 164976549.0, "step": 27630 }, { "epoch": 0.2948267952588736, "grad_norm": 1.3496587559942599, "learning_rate": 4.302050923560757e-05, "loss": 0.4984, "num_tokens": 164999189.0, "step": 27635 }, { "epoch": 0.2948801382650721, "grad_norm": 1.337404459982393, "learning_rate": 4.301763539427346e-05, "loss": 0.5992, "num_tokens": 165045421.0, "step": 27640 }, { "epoch": 0.2949334812712705, "grad_norm": 1.0285694744962877, "learning_rate": 4.3014761070062425e-05, "loss": 0.5867, "num_tokens": 165080351.0, "step": 27645 }, { "epoch": 0.294986824277469, "grad_norm": 3.553429541852664, "learning_rate": 4.3011886263063885e-05, "loss": 0.7914, "num_tokens": 165099356.0, "step": 27650 }, { "epoch": 0.29504016728366744, "grad_norm": 1.6505555867255857, "learning_rate": 4.300901097336731e-05, "loss": 0.553, "num_tokens": 165138332.0, "step": 27655 }, { "epoch": 0.2950935102898659, "grad_norm": 1.1209963652030182, "learning_rate": 4.300613520106217e-05, "loss": 0.4951, "num_tokens": 165170411.0, "step": 27660 }, { "epoch": 0.2951468532960643, "grad_norm": 0.9725822469475339, "learning_rate": 4.3003258946237955e-05, "loss": 0.5009, "num_tokens": 165198925.0, "step": 27665 }, { "epoch": 0.2952001963022628, "grad_norm": 1.1559758749113864, "learning_rate": 4.300038220898417e-05, "loss": 0.6664, "num_tokens": 165228893.0, "step": 27670 }, { "epoch": 0.29525353930846127, "grad_norm": 0.9870982196558012, "learning_rate": 4.299750498939032e-05, "loss": 0.4868, "num_tokens": 165254645.0, "step": 27675 }, { "epoch": 0.29530688231465974, "grad_norm": 0.9447269906010238, "learning_rate": 4.299462728754595e-05, "loss": 0.6103, "num_tokens": 165289194.0, "step": 27680 }, { "epoch": 0.2953602253208582, "grad_norm": 1.0745386764110176, "learning_rate": 4.299174910354061e-05, "loss": 0.5081, "num_tokens": 165306428.0, "step": 27685 }, { "epoch": 0.2954135683270566, "grad_norm": 1.023727594054218, "learning_rate": 4.2988870437463856e-05, "loss": 0.5818, "num_tokens": 165334784.0, "step": 27690 }, { "epoch": 0.2954669113332551, "grad_norm": 0.8796646195015397, "learning_rate": 4.298599128940527e-05, "loss": 0.6093, "num_tokens": 165376418.0, "step": 27695 }, { "epoch": 0.29552025433945356, "grad_norm": 0.8803396018144161, "learning_rate": 4.298311165945444e-05, "loss": 0.566, "num_tokens": 165405123.0, "step": 27700 }, { "epoch": 0.29557359734565203, "grad_norm": 0.7026044436349329, "learning_rate": 4.298023154770099e-05, "loss": 0.5858, "num_tokens": 165462254.0, "step": 27705 }, { "epoch": 0.29562694035185044, "grad_norm": 0.9606377440101382, "learning_rate": 4.297735095423451e-05, "loss": 0.5341, "num_tokens": 165483374.0, "step": 27710 }, { "epoch": 0.2956802833580489, "grad_norm": 0.7657669224215995, "learning_rate": 4.297446987914468e-05, "loss": 0.5172, "num_tokens": 165513015.0, "step": 27715 }, { "epoch": 0.2957336263642474, "grad_norm": 1.3887625240905233, "learning_rate": 4.297158832252113e-05, "loss": 0.5971, "num_tokens": 165539888.0, "step": 27720 }, { "epoch": 0.29578696937044585, "grad_norm": 1.074975791337157, "learning_rate": 4.296870628445352e-05, "loss": 0.6068, "num_tokens": 165578814.0, "step": 27725 }, { "epoch": 0.2958403123766443, "grad_norm": 1.2976174431002923, "learning_rate": 4.2965823765031556e-05, "loss": 0.5516, "num_tokens": 165594049.0, "step": 27730 }, { "epoch": 0.29589365538284274, "grad_norm": 1.4870706211181377, "learning_rate": 4.296294076434491e-05, "loss": 0.6191, "num_tokens": 165619724.0, "step": 27735 }, { "epoch": 0.2959469983890412, "grad_norm": 2.4868018956355535, "learning_rate": 4.2960057282483324e-05, "loss": 0.7153, "num_tokens": 165645422.0, "step": 27740 }, { "epoch": 0.2960003413952397, "grad_norm": 0.7149684937021354, "learning_rate": 4.295717331953651e-05, "loss": 0.5592, "num_tokens": 165689498.0, "step": 27745 }, { "epoch": 0.29605368440143814, "grad_norm": 1.0023846228864155, "learning_rate": 4.2954288875594204e-05, "loss": 0.6339, "num_tokens": 165713363.0, "step": 27750 }, { "epoch": 0.29610702740763656, "grad_norm": 1.099428748405444, "learning_rate": 4.2951403950746174e-05, "loss": 0.6658, "num_tokens": 165751678.0, "step": 27755 }, { "epoch": 0.29616037041383503, "grad_norm": 1.1091589595063598, "learning_rate": 4.2948518545082195e-05, "loss": 0.5512, "num_tokens": 165775144.0, "step": 27760 }, { "epoch": 0.2962137134200335, "grad_norm": 0.8783490688157857, "learning_rate": 4.294563265869205e-05, "loss": 0.6047, "num_tokens": 165808477.0, "step": 27765 }, { "epoch": 0.29626705642623197, "grad_norm": 0.6881215296621604, "learning_rate": 4.294274629166553e-05, "loss": 0.6702, "num_tokens": 165845770.0, "step": 27770 }, { "epoch": 0.29632039943243044, "grad_norm": 1.126021323821016, "learning_rate": 4.293985944409248e-05, "loss": 0.5669, "num_tokens": 165873202.0, "step": 27775 }, { "epoch": 0.29637374243862885, "grad_norm": 0.7814613203969335, "learning_rate": 4.293697211606273e-05, "loss": 0.5751, "num_tokens": 165905570.0, "step": 27780 }, { "epoch": 0.2964270854448273, "grad_norm": 1.4063367591188545, "learning_rate": 4.293408430766609e-05, "loss": 0.5533, "num_tokens": 165928442.0, "step": 27785 }, { "epoch": 0.2964804284510258, "grad_norm": 1.0059127234954226, "learning_rate": 4.2931196018992466e-05, "loss": 0.3843, "num_tokens": 165954599.0, "step": 27790 }, { "epoch": 0.29653377145722426, "grad_norm": 0.6843222432689358, "learning_rate": 4.292830725013171e-05, "loss": 0.5442, "num_tokens": 165997008.0, "step": 27795 }, { "epoch": 0.2965871144634227, "grad_norm": 1.0581964165215219, "learning_rate": 4.292541800117373e-05, "loss": 0.5807, "num_tokens": 166030517.0, "step": 27800 }, { "epoch": 0.29664045746962114, "grad_norm": 1.5802348194734082, "learning_rate": 4.292252827220842e-05, "loss": 0.5824, "num_tokens": 166045250.0, "step": 27805 }, { "epoch": 0.2966938004758196, "grad_norm": 7.2140008840767385, "learning_rate": 4.291963806332572e-05, "loss": 0.6585, "num_tokens": 166072731.0, "step": 27810 }, { "epoch": 0.2967471434820181, "grad_norm": 1.398276624668601, "learning_rate": 4.291674737461554e-05, "loss": 0.5305, "num_tokens": 166087780.0, "step": 27815 }, { "epoch": 0.29680048648821655, "grad_norm": 1.2228069070371335, "learning_rate": 4.291385620616786e-05, "loss": 0.4791, "num_tokens": 166128332.0, "step": 27820 }, { "epoch": 0.29685382949441497, "grad_norm": 1.3314706449398734, "learning_rate": 4.291096455807263e-05, "loss": 0.501, "num_tokens": 166153082.0, "step": 27825 }, { "epoch": 0.29690717250061344, "grad_norm": 1.4208221352039963, "learning_rate": 4.290807243041984e-05, "loss": 0.6431, "num_tokens": 166174260.0, "step": 27830 }, { "epoch": 0.2969605155068119, "grad_norm": 1.127144174267249, "learning_rate": 4.290517982329949e-05, "loss": 0.6512, "num_tokens": 166230418.0, "step": 27835 }, { "epoch": 0.2970138585130104, "grad_norm": 1.1128772804676887, "learning_rate": 4.290228673680158e-05, "loss": 0.5888, "num_tokens": 166249544.0, "step": 27840 }, { "epoch": 0.2970672015192088, "grad_norm": 0.6811982007474264, "learning_rate": 4.289939317101615e-05, "loss": 0.4692, "num_tokens": 166284817.0, "step": 27845 }, { "epoch": 0.29712054452540726, "grad_norm": 0.5707030919807083, "learning_rate": 4.2896499126033226e-05, "loss": 0.5654, "num_tokens": 166328144.0, "step": 27850 }, { "epoch": 0.29717388753160573, "grad_norm": 1.1543320562345687, "learning_rate": 4.289360460194289e-05, "loss": 0.5385, "num_tokens": 166351893.0, "step": 27855 }, { "epoch": 0.2972272305378042, "grad_norm": 1.303897209419344, "learning_rate": 4.289070959883519e-05, "loss": 0.5379, "num_tokens": 166388464.0, "step": 27860 }, { "epoch": 0.29728057354400267, "grad_norm": 0.8867492759930249, "learning_rate": 4.288781411680021e-05, "loss": 0.6534, "num_tokens": 166424668.0, "step": 27865 }, { "epoch": 0.2973339165502011, "grad_norm": 0.917753044629304, "learning_rate": 4.2884918155928075e-05, "loss": 0.6806, "num_tokens": 166462922.0, "step": 27870 }, { "epoch": 0.29738725955639955, "grad_norm": 1.1093638689910321, "learning_rate": 4.288202171630889e-05, "loss": 0.5777, "num_tokens": 166493339.0, "step": 27875 }, { "epoch": 0.297440602562598, "grad_norm": 1.0504116528313412, "learning_rate": 4.287912479803278e-05, "loss": 0.511, "num_tokens": 166532770.0, "step": 27880 }, { "epoch": 0.2974939455687965, "grad_norm": 1.0323899803640204, "learning_rate": 4.287622740118989e-05, "loss": 0.6513, "num_tokens": 166578613.0, "step": 27885 }, { "epoch": 0.2975472885749949, "grad_norm": 4.011398719407789, "learning_rate": 4.287332952587039e-05, "loss": 0.6767, "num_tokens": 166617334.0, "step": 27890 }, { "epoch": 0.2976006315811934, "grad_norm": 0.7452129360567574, "learning_rate": 4.287043117216446e-05, "loss": 0.4652, "num_tokens": 166637277.0, "step": 27895 }, { "epoch": 0.29765397458739185, "grad_norm": 0.9812636878704999, "learning_rate": 4.286753234016229e-05, "loss": 0.5758, "num_tokens": 166663944.0, "step": 27900 }, { "epoch": 0.2977073175935903, "grad_norm": 1.261653975341764, "learning_rate": 4.286463302995406e-05, "loss": 0.5722, "num_tokens": 166692605.0, "step": 27905 }, { "epoch": 0.2977606605997888, "grad_norm": 0.9048709961989878, "learning_rate": 4.286173324163002e-05, "loss": 0.5561, "num_tokens": 166717305.0, "step": 27910 }, { "epoch": 0.2978140036059872, "grad_norm": 0.705879844952905, "learning_rate": 4.28588329752804e-05, "loss": 0.6054, "num_tokens": 166749812.0, "step": 27915 }, { "epoch": 0.29786734661218567, "grad_norm": 1.166140278295211, "learning_rate": 4.285593223099543e-05, "loss": 0.555, "num_tokens": 166770884.0, "step": 27920 }, { "epoch": 0.29792068961838414, "grad_norm": 1.0984902923480386, "learning_rate": 4.285303100886541e-05, "loss": 0.6163, "num_tokens": 166794533.0, "step": 27925 }, { "epoch": 0.2979740326245826, "grad_norm": 0.9561673586146765, "learning_rate": 4.285012930898059e-05, "loss": 0.5802, "num_tokens": 166817100.0, "step": 27930 }, { "epoch": 0.298027375630781, "grad_norm": 0.9115663070635052, "learning_rate": 4.2847227131431276e-05, "loss": 0.4837, "num_tokens": 166843173.0, "step": 27935 }, { "epoch": 0.2980807186369795, "grad_norm": 0.7290997402935242, "learning_rate": 4.284432447630778e-05, "loss": 0.609, "num_tokens": 166868593.0, "step": 27940 }, { "epoch": 0.29813406164317796, "grad_norm": 0.8356885905791984, "learning_rate": 4.284142134370043e-05, "loss": 0.55, "num_tokens": 166896969.0, "step": 27945 }, { "epoch": 0.29818740464937643, "grad_norm": 1.5346440484380102, "learning_rate": 4.283851773369955e-05, "loss": 0.692, "num_tokens": 166924254.0, "step": 27950 }, { "epoch": 0.2982407476555749, "grad_norm": 1.9603881678588542, "learning_rate": 4.283561364639551e-05, "loss": 0.6198, "num_tokens": 166944462.0, "step": 27955 }, { "epoch": 0.2982940906617733, "grad_norm": 1.0929123048523495, "learning_rate": 4.2832709081878676e-05, "loss": 0.583, "num_tokens": 166967957.0, "step": 27960 }, { "epoch": 0.2983474336679718, "grad_norm": 0.8446129349531613, "learning_rate": 4.2829804040239424e-05, "loss": 0.5547, "num_tokens": 167006742.0, "step": 27965 }, { "epoch": 0.29840077667417025, "grad_norm": 0.8056276889680217, "learning_rate": 4.2826898521568157e-05, "loss": 0.4566, "num_tokens": 167042297.0, "step": 27970 }, { "epoch": 0.2984541196803687, "grad_norm": 1.2426463885465515, "learning_rate": 4.28239925259553e-05, "loss": 0.544, "num_tokens": 167066252.0, "step": 27975 }, { "epoch": 0.29850746268656714, "grad_norm": 0.7855799417390004, "learning_rate": 4.282108605349126e-05, "loss": 0.723, "num_tokens": 167101670.0, "step": 27980 }, { "epoch": 0.2985608056927656, "grad_norm": 0.9414102878978016, "learning_rate": 4.28181791042665e-05, "loss": 0.5352, "num_tokens": 167138644.0, "step": 27985 }, { "epoch": 0.2986141486989641, "grad_norm": 0.6017831331356897, "learning_rate": 4.281527167837147e-05, "loss": 0.6137, "num_tokens": 167173284.0, "step": 27990 }, { "epoch": 0.29866749170516255, "grad_norm": 2.4748589553160603, "learning_rate": 4.281236377589664e-05, "loss": 0.6807, "num_tokens": 167219434.0, "step": 27995 }, { "epoch": 0.298720834711361, "grad_norm": 0.7008235574450862, "learning_rate": 4.280945539693251e-05, "loss": 0.6563, "num_tokens": 167270494.0, "step": 28000 }, { "epoch": 0.29877417771755943, "grad_norm": 1.5247074700279837, "learning_rate": 4.2806546541569566e-05, "loss": 0.4948, "num_tokens": 167297617.0, "step": 28005 }, { "epoch": 0.2988275207237579, "grad_norm": 0.7064207389733316, "learning_rate": 4.2803637209898335e-05, "loss": 0.6127, "num_tokens": 167322671.0, "step": 28010 }, { "epoch": 0.29888086372995637, "grad_norm": 0.795665510205727, "learning_rate": 4.280072740200936e-05, "loss": 0.5599, "num_tokens": 167357788.0, "step": 28015 }, { "epoch": 0.29893420673615484, "grad_norm": 0.70094529128042, "learning_rate": 4.2797817117993165e-05, "loss": 0.5267, "num_tokens": 167395758.0, "step": 28020 }, { "epoch": 0.29898754974235325, "grad_norm": 1.208929798342783, "learning_rate": 4.279490635794033e-05, "loss": 0.5826, "num_tokens": 167418094.0, "step": 28025 }, { "epoch": 0.2990408927485517, "grad_norm": 1.203604263461494, "learning_rate": 4.279199512194142e-05, "loss": 0.5503, "num_tokens": 167446047.0, "step": 28030 }, { "epoch": 0.2990942357547502, "grad_norm": 1.119963119788873, "learning_rate": 4.278908341008703e-05, "loss": 0.4616, "num_tokens": 167472634.0, "step": 28035 }, { "epoch": 0.29914757876094866, "grad_norm": 4.170175978426013, "learning_rate": 4.278617122246778e-05, "loss": 0.6257, "num_tokens": 167506788.0, "step": 28040 }, { "epoch": 0.29920092176714713, "grad_norm": 0.8290851275503472, "learning_rate": 4.2783258559174275e-05, "loss": 0.8015, "num_tokens": 167538850.0, "step": 28045 }, { "epoch": 0.29925426477334555, "grad_norm": 1.5373504056504108, "learning_rate": 4.278034542029715e-05, "loss": 0.7165, "num_tokens": 167573044.0, "step": 28050 }, { "epoch": 0.299307607779544, "grad_norm": 1.1507552241640706, "learning_rate": 4.277743180592707e-05, "loss": 0.5565, "num_tokens": 167595056.0, "step": 28055 }, { "epoch": 0.2993609507857425, "grad_norm": 0.9208825500246467, "learning_rate": 4.27745177161547e-05, "loss": 0.5629, "num_tokens": 167612689.0, "step": 28060 }, { "epoch": 0.29941429379194096, "grad_norm": 0.930750615836113, "learning_rate": 4.2771603151070695e-05, "loss": 0.5503, "num_tokens": 167636945.0, "step": 28065 }, { "epoch": 0.29946763679813937, "grad_norm": 2.1425859872134922, "learning_rate": 4.276868811076578e-05, "loss": 0.6981, "num_tokens": 167659222.0, "step": 28070 }, { "epoch": 0.29952097980433784, "grad_norm": 0.789724246290116, "learning_rate": 4.276577259533065e-05, "loss": 0.4608, "num_tokens": 167689406.0, "step": 28075 }, { "epoch": 0.2995743228105363, "grad_norm": 0.8942134249912591, "learning_rate": 4.276285660485603e-05, "loss": 0.5776, "num_tokens": 167717750.0, "step": 28080 }, { "epoch": 0.2996276658167348, "grad_norm": 0.9471262530041439, "learning_rate": 4.275994013943267e-05, "loss": 0.5244, "num_tokens": 167745665.0, "step": 28085 }, { "epoch": 0.29968100882293325, "grad_norm": 0.9501903663957159, "learning_rate": 4.275702319915132e-05, "loss": 0.6637, "num_tokens": 167776201.0, "step": 28090 }, { "epoch": 0.29973435182913166, "grad_norm": 0.643811734920697, "learning_rate": 4.275410578410274e-05, "loss": 0.4994, "num_tokens": 167808600.0, "step": 28095 }, { "epoch": 0.29978769483533013, "grad_norm": 1.5633797074467854, "learning_rate": 4.275118789437773e-05, "loss": 0.5729, "num_tokens": 167832064.0, "step": 28100 }, { "epoch": 0.2998410378415286, "grad_norm": 1.4097148503030803, "learning_rate": 4.274826953006707e-05, "loss": 0.7601, "num_tokens": 167850586.0, "step": 28105 }, { "epoch": 0.29989438084772707, "grad_norm": 1.0678539621780945, "learning_rate": 4.2745350691261585e-05, "loss": 0.5156, "num_tokens": 167882488.0, "step": 28110 }, { "epoch": 0.2999477238539255, "grad_norm": 0.8992098948757546, "learning_rate": 4.2742431378052106e-05, "loss": 0.6743, "num_tokens": 167935761.0, "step": 28115 }, { "epoch": 0.30000106686012395, "grad_norm": 0.7229573303649907, "learning_rate": 4.2739511590529466e-05, "loss": 0.4496, "num_tokens": 167956493.0, "step": 28120 }, { "epoch": 0.3000544098663224, "grad_norm": 0.7023795845689846, "learning_rate": 4.273659132878453e-05, "loss": 0.554, "num_tokens": 167999629.0, "step": 28125 }, { "epoch": 0.3001077528725209, "grad_norm": 0.9763951961740299, "learning_rate": 4.273367059290817e-05, "loss": 0.5054, "num_tokens": 168033904.0, "step": 28130 }, { "epoch": 0.30016109587871936, "grad_norm": 0.6759500196043535, "learning_rate": 4.273074938299127e-05, "loss": 0.6217, "num_tokens": 168068414.0, "step": 28135 }, { "epoch": 0.3002144388849178, "grad_norm": 0.9678929189382562, "learning_rate": 4.272782769912473e-05, "loss": 0.5973, "num_tokens": 168117516.0, "step": 28140 }, { "epoch": 0.30026778189111625, "grad_norm": 5.141328735536522, "learning_rate": 4.272490554139949e-05, "loss": 0.7442, "num_tokens": 168154203.0, "step": 28145 }, { "epoch": 0.3003211248973147, "grad_norm": 2.9436558106424418, "learning_rate": 4.272198290990645e-05, "loss": 0.6332, "num_tokens": 168177222.0, "step": 28150 }, { "epoch": 0.3003744679035132, "grad_norm": 1.5251447178479955, "learning_rate": 4.271905980473656e-05, "loss": 0.799, "num_tokens": 168205979.0, "step": 28155 }, { "epoch": 0.3004278109097116, "grad_norm": 1.290593016754642, "learning_rate": 4.2716136225980795e-05, "loss": 0.6221, "num_tokens": 168223299.0, "step": 28160 }, { "epoch": 0.30048115391591007, "grad_norm": 0.766863454972055, "learning_rate": 4.271321217373013e-05, "loss": 0.7481, "num_tokens": 168271072.0, "step": 28165 }, { "epoch": 0.30053449692210854, "grad_norm": 0.7129424790011487, "learning_rate": 4.271028764807554e-05, "loss": 0.6905, "num_tokens": 168313291.0, "step": 28170 }, { "epoch": 0.300587839928307, "grad_norm": 1.2207576735912646, "learning_rate": 4.270736264910805e-05, "loss": 0.5674, "num_tokens": 168341381.0, "step": 28175 }, { "epoch": 0.3006411829345055, "grad_norm": 0.744944258284991, "learning_rate": 4.270443717691868e-05, "loss": 0.5336, "num_tokens": 168381391.0, "step": 28180 }, { "epoch": 0.3006945259407039, "grad_norm": 1.3303849640691272, "learning_rate": 4.270151123159844e-05, "loss": 0.5573, "num_tokens": 168404027.0, "step": 28185 }, { "epoch": 0.30074786894690236, "grad_norm": 1.338164358222659, "learning_rate": 4.26985848132384e-05, "loss": 0.6285, "num_tokens": 168432117.0, "step": 28190 }, { "epoch": 0.30080121195310083, "grad_norm": 1.3439465311259922, "learning_rate": 4.269565792192962e-05, "loss": 0.665, "num_tokens": 168449242.0, "step": 28195 }, { "epoch": 0.3008545549592993, "grad_norm": 1.414441483003199, "learning_rate": 4.269273055776318e-05, "loss": 0.5155, "num_tokens": 168494752.0, "step": 28200 }, { "epoch": 0.3009078979654977, "grad_norm": 1.9862544518550473, "learning_rate": 4.268980272083017e-05, "loss": 0.6491, "num_tokens": 168522504.0, "step": 28205 }, { "epoch": 0.3009612409716962, "grad_norm": 1.2699267473201175, "learning_rate": 4.2686874411221704e-05, "loss": 0.6036, "num_tokens": 168561914.0, "step": 28210 }, { "epoch": 0.30101458397789466, "grad_norm": 1.910328182372463, "learning_rate": 4.2683945629028896e-05, "loss": 0.7265, "num_tokens": 168593056.0, "step": 28215 }, { "epoch": 0.3010679269840931, "grad_norm": 1.6053427401399905, "learning_rate": 4.2681016374342895e-05, "loss": 0.5551, "num_tokens": 168614820.0, "step": 28220 }, { "epoch": 0.3011212699902916, "grad_norm": 0.8795374699143302, "learning_rate": 4.267808664725484e-05, "loss": 0.5513, "num_tokens": 168645366.0, "step": 28225 }, { "epoch": 0.30117461299649, "grad_norm": 0.7995502094692518, "learning_rate": 4.267515644785592e-05, "loss": 0.5582, "num_tokens": 168676599.0, "step": 28230 }, { "epoch": 0.3012279560026885, "grad_norm": 0.8667535716848024, "learning_rate": 4.2672225776237286e-05, "loss": 0.4788, "num_tokens": 168695842.0, "step": 28235 }, { "epoch": 0.30128129900888695, "grad_norm": 0.8864082194470282, "learning_rate": 4.266929463249015e-05, "loss": 0.5202, "num_tokens": 168730404.0, "step": 28240 }, { "epoch": 0.3013346420150854, "grad_norm": 0.9680038948169704, "learning_rate": 4.2666363016705733e-05, "loss": 0.5083, "num_tokens": 168760259.0, "step": 28245 }, { "epoch": 0.30138798502128383, "grad_norm": 1.3977409475320102, "learning_rate": 4.2663430928975244e-05, "loss": 0.5885, "num_tokens": 168797339.0, "step": 28250 }, { "epoch": 0.3014413280274823, "grad_norm": 0.9881263411695478, "learning_rate": 4.266049836938994e-05, "loss": 0.6058, "num_tokens": 168819742.0, "step": 28255 }, { "epoch": 0.3014946710336808, "grad_norm": 1.022909535960108, "learning_rate": 4.265756533804106e-05, "loss": 0.5114, "num_tokens": 168852143.0, "step": 28260 }, { "epoch": 0.30154801403987924, "grad_norm": 1.6410462915617219, "learning_rate": 4.265463183501988e-05, "loss": 0.7009, "num_tokens": 168877526.0, "step": 28265 }, { "epoch": 0.3016013570460777, "grad_norm": 0.9618334318308553, "learning_rate": 4.2651697860417696e-05, "loss": 0.5886, "num_tokens": 168917049.0, "step": 28270 }, { "epoch": 0.3016547000522761, "grad_norm": 0.9206923912590902, "learning_rate": 4.264876341432578e-05, "loss": 0.6406, "num_tokens": 168949215.0, "step": 28275 }, { "epoch": 0.3017080430584746, "grad_norm": 1.3089389142147287, "learning_rate": 4.264582849683548e-05, "loss": 0.514, "num_tokens": 168975876.0, "step": 28280 }, { "epoch": 0.30176138606467307, "grad_norm": 1.0735052784442252, "learning_rate": 4.26428931080381e-05, "loss": 0.5793, "num_tokens": 169005078.0, "step": 28285 }, { "epoch": 0.30181472907087153, "grad_norm": 1.365324637246972, "learning_rate": 4.263995724802498e-05, "loss": 0.5121, "num_tokens": 169033379.0, "step": 28290 }, { "epoch": 0.30186807207706995, "grad_norm": 1.056727954556107, "learning_rate": 4.263702091688751e-05, "loss": 0.5938, "num_tokens": 169063132.0, "step": 28295 }, { "epoch": 0.3019214150832684, "grad_norm": 0.7858682185981702, "learning_rate": 4.263408411471703e-05, "loss": 0.6993, "num_tokens": 169098864.0, "step": 28300 }, { "epoch": 0.3019747580894669, "grad_norm": 0.9731051832504618, "learning_rate": 4.263114684160494e-05, "loss": 0.518, "num_tokens": 169112495.0, "step": 28305 }, { "epoch": 0.30202810109566536, "grad_norm": 1.3443500822949586, "learning_rate": 4.262820909764264e-05, "loss": 0.5389, "num_tokens": 169149534.0, "step": 28310 }, { "epoch": 0.3020814441018638, "grad_norm": 1.0511130296954976, "learning_rate": 4.2625270882921555e-05, "loss": 0.6065, "num_tokens": 169188576.0, "step": 28315 }, { "epoch": 0.30213478710806224, "grad_norm": 0.8895823041774814, "learning_rate": 4.2622332197533085e-05, "loss": 0.614, "num_tokens": 169217712.0, "step": 28320 }, { "epoch": 0.3021881301142607, "grad_norm": 1.024705258165382, "learning_rate": 4.261939304156872e-05, "loss": 0.5369, "num_tokens": 169244278.0, "step": 28325 }, { "epoch": 0.3022414731204592, "grad_norm": 0.6913757703229771, "learning_rate": 4.26164534151199e-05, "loss": 0.743, "num_tokens": 169289562.0, "step": 28330 }, { "epoch": 0.30229481612665765, "grad_norm": 1.3376751556537603, "learning_rate": 4.2613513318278095e-05, "loss": 0.5857, "num_tokens": 169319989.0, "step": 28335 }, { "epoch": 0.30234815913285606, "grad_norm": 1.970027607132472, "learning_rate": 4.2610572751134796e-05, "loss": 0.5935, "num_tokens": 169361515.0, "step": 28340 }, { "epoch": 0.30240150213905453, "grad_norm": 0.7473771070061475, "learning_rate": 4.260763171378151e-05, "loss": 0.5292, "num_tokens": 169388303.0, "step": 28345 }, { "epoch": 0.302454845145253, "grad_norm": 1.1790936433769414, "learning_rate": 4.260469020630976e-05, "loss": 0.6383, "num_tokens": 169428879.0, "step": 28350 }, { "epoch": 0.3025081881514515, "grad_norm": 0.9981311418417014, "learning_rate": 4.2601748228811084e-05, "loss": 0.7453, "num_tokens": 169471692.0, "step": 28355 }, { "epoch": 0.30256153115764994, "grad_norm": 0.9890019644117606, "learning_rate": 4.2598805781377014e-05, "loss": 0.4788, "num_tokens": 169501806.0, "step": 28360 }, { "epoch": 0.30261487416384836, "grad_norm": 1.3449741811970988, "learning_rate": 4.259586286409913e-05, "loss": 0.6729, "num_tokens": 169524516.0, "step": 28365 }, { "epoch": 0.3026682171700468, "grad_norm": 1.3681756613312206, "learning_rate": 4.2592919477068995e-05, "loss": 0.5881, "num_tokens": 169556557.0, "step": 28370 }, { "epoch": 0.3027215601762453, "grad_norm": 1.6809130667462193, "learning_rate": 4.258997562037821e-05, "loss": 0.6936, "num_tokens": 169580228.0, "step": 28375 }, { "epoch": 0.30277490318244377, "grad_norm": 1.0706983653079953, "learning_rate": 4.2587031294118376e-05, "loss": 0.4728, "num_tokens": 169612928.0, "step": 28380 }, { "epoch": 0.3028282461886422, "grad_norm": 0.836948547194015, "learning_rate": 4.258408649838112e-05, "loss": 0.6045, "num_tokens": 169644257.0, "step": 28385 }, { "epoch": 0.30288158919484065, "grad_norm": 0.8650110460009721, "learning_rate": 4.258114123325808e-05, "loss": 0.6315, "num_tokens": 169670461.0, "step": 28390 }, { "epoch": 0.3029349322010391, "grad_norm": 0.9879312170769403, "learning_rate": 4.2578195498840896e-05, "loss": 0.6679, "num_tokens": 169718027.0, "step": 28395 }, { "epoch": 0.3029882752072376, "grad_norm": 1.566919845287169, "learning_rate": 4.2575249295221244e-05, "loss": 0.5474, "num_tokens": 169741513.0, "step": 28400 }, { "epoch": 0.30304161821343606, "grad_norm": 0.7660943830695853, "learning_rate": 4.257230262249079e-05, "loss": 0.5697, "num_tokens": 169764033.0, "step": 28405 }, { "epoch": 0.3030949612196345, "grad_norm": 0.7831102073158449, "learning_rate": 4.256935548074124e-05, "loss": 0.5703, "num_tokens": 169807014.0, "step": 28410 }, { "epoch": 0.30314830422583294, "grad_norm": 1.0301932820580446, "learning_rate": 4.2566407870064314e-05, "loss": 0.6064, "num_tokens": 169837366.0, "step": 28415 }, { "epoch": 0.3032016472320314, "grad_norm": 1.6431294759683324, "learning_rate": 4.2563459790551714e-05, "loss": 0.7257, "num_tokens": 169874587.0, "step": 28420 }, { "epoch": 0.3032549902382299, "grad_norm": 1.9715463046663686, "learning_rate": 4.2560511242295194e-05, "loss": 0.584, "num_tokens": 169909158.0, "step": 28425 }, { "epoch": 0.3033083332444283, "grad_norm": 1.2250722502885634, "learning_rate": 4.2557562225386485e-05, "loss": 0.6648, "num_tokens": 169934679.0, "step": 28430 }, { "epoch": 0.30336167625062677, "grad_norm": 1.0905270484361755, "learning_rate": 4.255461273991738e-05, "loss": 0.452, "num_tokens": 169954642.0, "step": 28435 }, { "epoch": 0.30341501925682524, "grad_norm": 1.5204708057676413, "learning_rate": 4.255166278597964e-05, "loss": 0.5532, "num_tokens": 169969293.0, "step": 28440 }, { "epoch": 0.3034683622630237, "grad_norm": 1.4133758122629967, "learning_rate": 4.254871236366508e-05, "loss": 0.6238, "num_tokens": 169996186.0, "step": 28445 }, { "epoch": 0.3035217052692222, "grad_norm": 0.8376534920102847, "learning_rate": 4.25457614730655e-05, "loss": 0.6579, "num_tokens": 170021475.0, "step": 28450 }, { "epoch": 0.3035750482754206, "grad_norm": 0.8041190379376614, "learning_rate": 4.254281011427272e-05, "loss": 0.6057, "num_tokens": 170051908.0, "step": 28455 }, { "epoch": 0.30362839128161906, "grad_norm": 1.289179565623334, "learning_rate": 4.2539858287378595e-05, "loss": 0.5553, "num_tokens": 170077563.0, "step": 28460 }, { "epoch": 0.30368173428781753, "grad_norm": 1.89104329040425, "learning_rate": 4.253690599247498e-05, "loss": 0.6437, "num_tokens": 170100952.0, "step": 28465 }, { "epoch": 0.303735077294016, "grad_norm": 1.4421121524090061, "learning_rate": 4.253395322965373e-05, "loss": 0.5655, "num_tokens": 170124742.0, "step": 28470 }, { "epoch": 0.3037884203002144, "grad_norm": 2.306168854140915, "learning_rate": 4.253099999900673e-05, "loss": 0.5756, "num_tokens": 170162924.0, "step": 28475 }, { "epoch": 0.3038417633064129, "grad_norm": 1.716882261995137, "learning_rate": 4.252804630062589e-05, "loss": 0.5397, "num_tokens": 170189422.0, "step": 28480 }, { "epoch": 0.30389510631261135, "grad_norm": 0.7011942717593546, "learning_rate": 4.252509213460312e-05, "loss": 0.5369, "num_tokens": 170233149.0, "step": 28485 }, { "epoch": 0.3039484493188098, "grad_norm": 1.5223293660741402, "learning_rate": 4.252213750103035e-05, "loss": 0.5861, "num_tokens": 170259840.0, "step": 28490 }, { "epoch": 0.3040017923250083, "grad_norm": 1.504249120560581, "learning_rate": 4.25191823999995e-05, "loss": 0.549, "num_tokens": 170292574.0, "step": 28495 }, { "epoch": 0.3040551353312067, "grad_norm": 1.1033738245294649, "learning_rate": 4.251622683160256e-05, "loss": 0.6507, "num_tokens": 170313509.0, "step": 28500 }, { "epoch": 0.3041084783374052, "grad_norm": 0.8258117931913962, "learning_rate": 4.251327079593147e-05, "loss": 0.8269, "num_tokens": 170353303.0, "step": 28505 }, { "epoch": 0.30416182134360364, "grad_norm": 0.8271068099229927, "learning_rate": 4.251031429307825e-05, "loss": 0.5616, "num_tokens": 170393640.0, "step": 28510 }, { "epoch": 0.3042151643498021, "grad_norm": 0.7751613971792654, "learning_rate": 4.2507357323134865e-05, "loss": 0.5945, "num_tokens": 170437602.0, "step": 28515 }, { "epoch": 0.30426850735600053, "grad_norm": 1.7594682696614006, "learning_rate": 4.250439988619335e-05, "loss": 0.5939, "num_tokens": 170455940.0, "step": 28520 }, { "epoch": 0.304321850362199, "grad_norm": 1.6919283426549871, "learning_rate": 4.2501441982345734e-05, "loss": 0.5624, "num_tokens": 170487044.0, "step": 28525 }, { "epoch": 0.30437519336839747, "grad_norm": 1.0057133165379748, "learning_rate": 4.249848361168406e-05, "loss": 0.5014, "num_tokens": 170514036.0, "step": 28530 }, { "epoch": 0.30442853637459594, "grad_norm": 1.3096576998656801, "learning_rate": 4.249552477430038e-05, "loss": 0.4932, "num_tokens": 170531362.0, "step": 28535 }, { "epoch": 0.3044818793807944, "grad_norm": 0.7120850847014069, "learning_rate": 4.249256547028677e-05, "loss": 0.5182, "num_tokens": 170557677.0, "step": 28540 }, { "epoch": 0.3045352223869928, "grad_norm": 1.4399208313760505, "learning_rate": 4.248960569973532e-05, "loss": 0.5509, "num_tokens": 170586928.0, "step": 28545 }, { "epoch": 0.3045885653931913, "grad_norm": 0.8070732189150095, "learning_rate": 4.2486645462738135e-05, "loss": 0.5991, "num_tokens": 170639053.0, "step": 28550 }, { "epoch": 0.30464190839938976, "grad_norm": 2.2071226353101805, "learning_rate": 4.248368475938732e-05, "loss": 0.7273, "num_tokens": 170656027.0, "step": 28555 }, { "epoch": 0.30469525140558823, "grad_norm": 1.6749773120566747, "learning_rate": 4.248072358977501e-05, "loss": 0.5495, "num_tokens": 170673117.0, "step": 28560 }, { "epoch": 0.30474859441178664, "grad_norm": 2.2613499413370097, "learning_rate": 4.2477761953993356e-05, "loss": 0.5651, "num_tokens": 170694832.0, "step": 28565 }, { "epoch": 0.3048019374179851, "grad_norm": 1.6706676959956606, "learning_rate": 4.247479985213452e-05, "loss": 0.6413, "num_tokens": 170718453.0, "step": 28570 }, { "epoch": 0.3048552804241836, "grad_norm": 1.1550489113914668, "learning_rate": 4.247183728429067e-05, "loss": 0.5735, "num_tokens": 170740931.0, "step": 28575 }, { "epoch": 0.30490862343038205, "grad_norm": 1.0649720421764952, "learning_rate": 4.246887425055399e-05, "loss": 0.5579, "num_tokens": 170756525.0, "step": 28580 }, { "epoch": 0.3049619664365805, "grad_norm": 2.518550221316539, "learning_rate": 4.246591075101669e-05, "loss": 0.6307, "num_tokens": 170781748.0, "step": 28585 }, { "epoch": 0.30501530944277894, "grad_norm": 0.7849588670939435, "learning_rate": 4.2462946785771e-05, "loss": 0.5056, "num_tokens": 170822113.0, "step": 28590 }, { "epoch": 0.3050686524489774, "grad_norm": 1.3702483549406919, "learning_rate": 4.245998235490914e-05, "loss": 0.5982, "num_tokens": 170851211.0, "step": 28595 }, { "epoch": 0.3051219954551759, "grad_norm": 0.7492894377998528, "learning_rate": 4.2457017458523346e-05, "loss": 0.5107, "num_tokens": 170886916.0, "step": 28600 }, { "epoch": 0.30517533846137435, "grad_norm": 0.8515501486911525, "learning_rate": 4.24540520967059e-05, "loss": 0.7213, "num_tokens": 170921256.0, "step": 28605 }, { "epoch": 0.30522868146757276, "grad_norm": 0.8004027911459717, "learning_rate": 4.2451086269549065e-05, "loss": 0.4733, "num_tokens": 170956652.0, "step": 28610 }, { "epoch": 0.30528202447377123, "grad_norm": 1.2246915667293197, "learning_rate": 4.244811997714513e-05, "loss": 0.5114, "num_tokens": 170974174.0, "step": 28615 }, { "epoch": 0.3053353674799697, "grad_norm": 1.3737618975448176, "learning_rate": 4.2445153219586417e-05, "loss": 0.5736, "num_tokens": 170994357.0, "step": 28620 }, { "epoch": 0.30538871048616817, "grad_norm": 1.0323509982456531, "learning_rate": 4.244218599696523e-05, "loss": 0.5567, "num_tokens": 171038121.0, "step": 28625 }, { "epoch": 0.30544205349236664, "grad_norm": 2.8338249744473476, "learning_rate": 4.2439218309373906e-05, "loss": 0.591, "num_tokens": 171064634.0, "step": 28630 }, { "epoch": 0.30549539649856505, "grad_norm": 1.9097299928700469, "learning_rate": 4.243625015690479e-05, "loss": 0.5206, "num_tokens": 171092900.0, "step": 28635 }, { "epoch": 0.3055487395047635, "grad_norm": 1.2578144811376726, "learning_rate": 4.243328153965026e-05, "loss": 0.5331, "num_tokens": 171115167.0, "step": 28640 }, { "epoch": 0.305602082510962, "grad_norm": 1.3290555488773148, "learning_rate": 4.243031245770267e-05, "loss": 0.5705, "num_tokens": 171135872.0, "step": 28645 }, { "epoch": 0.30565542551716046, "grad_norm": 0.8796494451365858, "learning_rate": 4.2427342911154433e-05, "loss": 0.5395, "num_tokens": 171163021.0, "step": 28650 }, { "epoch": 0.3057087685233589, "grad_norm": 0.9777067123874245, "learning_rate": 4.242437290009795e-05, "loss": 0.583, "num_tokens": 171198249.0, "step": 28655 }, { "epoch": 0.30576211152955735, "grad_norm": 1.4789348756336564, "learning_rate": 4.2421402424625625e-05, "loss": 0.5534, "num_tokens": 171224037.0, "step": 28660 }, { "epoch": 0.3058154545357558, "grad_norm": 1.0076715574746906, "learning_rate": 4.241843148482992e-05, "loss": 0.5483, "num_tokens": 171261157.0, "step": 28665 }, { "epoch": 0.3058687975419543, "grad_norm": 1.3378796901371983, "learning_rate": 4.2415460080803255e-05, "loss": 0.6938, "num_tokens": 171290622.0, "step": 28670 }, { "epoch": 0.30592214054815275, "grad_norm": 0.7582072640438565, "learning_rate": 4.2412488212638116e-05, "loss": 0.6288, "num_tokens": 171340388.0, "step": 28675 }, { "epoch": 0.30597548355435117, "grad_norm": 1.3412443163558185, "learning_rate": 4.240951588042698e-05, "loss": 0.5267, "num_tokens": 171364766.0, "step": 28680 }, { "epoch": 0.30602882656054964, "grad_norm": 0.7897680298425288, "learning_rate": 4.2406543084262335e-05, "loss": 0.6239, "num_tokens": 171398872.0, "step": 28685 }, { "epoch": 0.3060821695667481, "grad_norm": 0.7198994890430209, "learning_rate": 4.240356982423668e-05, "loss": 0.5206, "num_tokens": 171436915.0, "step": 28690 }, { "epoch": 0.3061355125729466, "grad_norm": 1.890036960954294, "learning_rate": 4.2400596100442554e-05, "loss": 0.5426, "num_tokens": 171478298.0, "step": 28695 }, { "epoch": 0.306188855579145, "grad_norm": 0.8525304378050351, "learning_rate": 4.2397621912972476e-05, "loss": 0.4936, "num_tokens": 171516982.0, "step": 28700 }, { "epoch": 0.30624219858534346, "grad_norm": 0.9560747494721108, "learning_rate": 4.239464726191901e-05, "loss": 0.5414, "num_tokens": 171543358.0, "step": 28705 }, { "epoch": 0.30629554159154193, "grad_norm": 1.0333217381760162, "learning_rate": 4.239167214737471e-05, "loss": 0.4877, "num_tokens": 171563629.0, "step": 28710 }, { "epoch": 0.3063488845977404, "grad_norm": 1.1116358757515037, "learning_rate": 4.238869656943217e-05, "loss": 0.4532, "num_tokens": 171596420.0, "step": 28715 }, { "epoch": 0.30640222760393887, "grad_norm": 1.2041149793015788, "learning_rate": 4.238572052818397e-05, "loss": 0.581, "num_tokens": 171623957.0, "step": 28720 }, { "epoch": 0.3064555706101373, "grad_norm": 1.0743228641031801, "learning_rate": 4.238274402372271e-05, "loss": 0.5697, "num_tokens": 171654426.0, "step": 28725 }, { "epoch": 0.30650891361633575, "grad_norm": 2.344995320215216, "learning_rate": 4.237976705614105e-05, "loss": 0.6401, "num_tokens": 171676235.0, "step": 28730 }, { "epoch": 0.3065622566225342, "grad_norm": 0.8822075418654036, "learning_rate": 4.237678962553159e-05, "loss": 0.4948, "num_tokens": 171719680.0, "step": 28735 }, { "epoch": 0.3066155996287327, "grad_norm": 0.9071021446561637, "learning_rate": 4.2373811731986995e-05, "loss": 0.6828, "num_tokens": 171745705.0, "step": 28740 }, { "epoch": 0.3066689426349311, "grad_norm": 1.3283491609117453, "learning_rate": 4.2370833375599936e-05, "loss": 0.6568, "num_tokens": 171786527.0, "step": 28745 }, { "epoch": 0.3067222856411296, "grad_norm": 1.1046320370427074, "learning_rate": 4.236785455646308e-05, "loss": 0.494, "num_tokens": 171810001.0, "step": 28750 }, { "epoch": 0.30677562864732805, "grad_norm": 0.8239874333481121, "learning_rate": 4.236487527466914e-05, "loss": 0.4481, "num_tokens": 171835079.0, "step": 28755 }, { "epoch": 0.3068289716535265, "grad_norm": 0.6584722651283448, "learning_rate": 4.23618955303108e-05, "loss": 0.5983, "num_tokens": 171872726.0, "step": 28760 }, { "epoch": 0.306882314659725, "grad_norm": 1.015430654446287, "learning_rate": 4.2358915323480805e-05, "loss": 0.5907, "num_tokens": 171895808.0, "step": 28765 }, { "epoch": 0.3069356576659234, "grad_norm": 0.8477427506664139, "learning_rate": 4.2355934654271896e-05, "loss": 0.5008, "num_tokens": 171915219.0, "step": 28770 }, { "epoch": 0.30698900067212187, "grad_norm": 0.6352232562062617, "learning_rate": 4.2352953522776806e-05, "loss": 0.5477, "num_tokens": 171947178.0, "step": 28775 }, { "epoch": 0.30704234367832034, "grad_norm": 1.0961771898802357, "learning_rate": 4.2349971929088315e-05, "loss": 0.662, "num_tokens": 171976727.0, "step": 28780 }, { "epoch": 0.3070956866845188, "grad_norm": 0.8062294234355567, "learning_rate": 4.23469898732992e-05, "loss": 0.5097, "num_tokens": 172019093.0, "step": 28785 }, { "epoch": 0.3071490296907172, "grad_norm": 1.1742530268740998, "learning_rate": 4.2344007355502254e-05, "loss": 0.6678, "num_tokens": 172057981.0, "step": 28790 }, { "epoch": 0.3072023726969157, "grad_norm": 1.0515236589274635, "learning_rate": 4.2341024375790286e-05, "loss": 0.7581, "num_tokens": 172096501.0, "step": 28795 }, { "epoch": 0.30725571570311416, "grad_norm": 1.0482577102278943, "learning_rate": 4.233804093425613e-05, "loss": 0.5152, "num_tokens": 172132000.0, "step": 28800 }, { "epoch": 0.30730905870931263, "grad_norm": 0.8103187538210598, "learning_rate": 4.233505703099262e-05, "loss": 0.6197, "num_tokens": 172186368.0, "step": 28805 }, { "epoch": 0.3073624017155111, "grad_norm": 0.8426816247708465, "learning_rate": 4.23320726660926e-05, "loss": 0.5013, "num_tokens": 172220880.0, "step": 28810 }, { "epoch": 0.3074157447217095, "grad_norm": 1.2556645918338751, "learning_rate": 4.232908783964895e-05, "loss": 0.616, "num_tokens": 172264632.0, "step": 28815 }, { "epoch": 0.307469087727908, "grad_norm": 1.282366069689141, "learning_rate": 4.232610255175455e-05, "loss": 0.5567, "num_tokens": 172288473.0, "step": 28820 }, { "epoch": 0.30752243073410646, "grad_norm": 1.1130789242227006, "learning_rate": 4.2323116802502276e-05, "loss": 0.445, "num_tokens": 172318271.0, "step": 28825 }, { "epoch": 0.3075757737403049, "grad_norm": 0.9230646047574479, "learning_rate": 4.2320130591985076e-05, "loss": 0.5269, "num_tokens": 172355010.0, "step": 28830 }, { "epoch": 0.30762911674650334, "grad_norm": 1.7691396522084464, "learning_rate": 4.2317143920295835e-05, "loss": 0.5701, "num_tokens": 172375208.0, "step": 28835 }, { "epoch": 0.3076824597527018, "grad_norm": 0.9812396131263559, "learning_rate": 4.231415678752752e-05, "loss": 0.5178, "num_tokens": 172399679.0, "step": 28840 }, { "epoch": 0.3077358027589003, "grad_norm": 0.9439982937217323, "learning_rate": 4.231116919377308e-05, "loss": 0.7189, "num_tokens": 172432188.0, "step": 28845 }, { "epoch": 0.30778914576509875, "grad_norm": 1.1863559055600883, "learning_rate": 4.230818113912547e-05, "loss": 0.7684, "num_tokens": 172459451.0, "step": 28850 }, { "epoch": 0.3078424887712972, "grad_norm": 1.2018298982784568, "learning_rate": 4.230519262367768e-05, "loss": 0.685, "num_tokens": 172481381.0, "step": 28855 }, { "epoch": 0.30789583177749563, "grad_norm": 0.9796151135931827, "learning_rate": 4.23022036475227e-05, "loss": 0.5669, "num_tokens": 172512443.0, "step": 28860 }, { "epoch": 0.3079491747836941, "grad_norm": 1.11330274362461, "learning_rate": 4.229921421075357e-05, "loss": 0.5856, "num_tokens": 172546714.0, "step": 28865 }, { "epoch": 0.30800251778989257, "grad_norm": 0.9128611608483453, "learning_rate": 4.229622431346327e-05, "loss": 0.4623, "num_tokens": 172569164.0, "step": 28870 }, { "epoch": 0.30805586079609104, "grad_norm": 1.023754819260227, "learning_rate": 4.229323395574487e-05, "loss": 0.6667, "num_tokens": 172595256.0, "step": 28875 }, { "epoch": 0.30810920380228946, "grad_norm": 0.8391598911110055, "learning_rate": 4.229024313769141e-05, "loss": 0.5675, "num_tokens": 172651926.0, "step": 28880 }, { "epoch": 0.3081625468084879, "grad_norm": 1.25007656979049, "learning_rate": 4.2287251859395966e-05, "loss": 0.4294, "num_tokens": 172680251.0, "step": 28885 }, { "epoch": 0.3082158898146864, "grad_norm": 0.6918873493983375, "learning_rate": 4.228426012095162e-05, "loss": 0.7066, "num_tokens": 172724778.0, "step": 28890 }, { "epoch": 0.30826923282088486, "grad_norm": 1.0698515778471342, "learning_rate": 4.228126792245147e-05, "loss": 0.6225, "num_tokens": 172749722.0, "step": 28895 }, { "epoch": 0.30832257582708333, "grad_norm": 0.7679329493182787, "learning_rate": 4.2278275263988616e-05, "loss": 0.5875, "num_tokens": 172799807.0, "step": 28900 }, { "epoch": 0.30837591883328175, "grad_norm": 0.7575647410408086, "learning_rate": 4.2275282145656195e-05, "loss": 0.5049, "num_tokens": 172839383.0, "step": 28905 }, { "epoch": 0.3084292618394802, "grad_norm": 0.7629932586192886, "learning_rate": 4.2272288567547344e-05, "loss": 0.471, "num_tokens": 172854283.0, "step": 28910 }, { "epoch": 0.3084826048456787, "grad_norm": 0.9412423877191527, "learning_rate": 4.226929452975522e-05, "loss": 0.5325, "num_tokens": 172889276.0, "step": 28915 }, { "epoch": 0.30853594785187716, "grad_norm": 0.9859131960898725, "learning_rate": 4.226630003237298e-05, "loss": 0.5601, "num_tokens": 172911566.0, "step": 28920 }, { "epoch": 0.30858929085807557, "grad_norm": 1.33317467139922, "learning_rate": 4.2263305075493817e-05, "loss": 0.6825, "num_tokens": 172936844.0, "step": 28925 }, { "epoch": 0.30864263386427404, "grad_norm": 1.340581924885946, "learning_rate": 4.226030965921092e-05, "loss": 0.5003, "num_tokens": 172962819.0, "step": 28930 }, { "epoch": 0.3086959768704725, "grad_norm": 1.552560032733205, "learning_rate": 4.225731378361751e-05, "loss": 0.4324, "num_tokens": 172980532.0, "step": 28935 }, { "epoch": 0.308749319876671, "grad_norm": 1.2303694817731308, "learning_rate": 4.225431744880681e-05, "loss": 0.661, "num_tokens": 173015618.0, "step": 28940 }, { "epoch": 0.30880266288286945, "grad_norm": 1.6369117137054339, "learning_rate": 4.225132065487205e-05, "loss": 0.5106, "num_tokens": 173060150.0, "step": 28945 }, { "epoch": 0.30885600588906786, "grad_norm": 0.9291655355354126, "learning_rate": 4.22483234019065e-05, "loss": 0.6841, "num_tokens": 173109061.0, "step": 28950 }, { "epoch": 0.30890934889526633, "grad_norm": 1.058161942673244, "learning_rate": 4.2245325690003415e-05, "loss": 0.4958, "num_tokens": 173127161.0, "step": 28955 }, { "epoch": 0.3089626919014648, "grad_norm": 1.1715645875146021, "learning_rate": 4.224232751925607e-05, "loss": 0.6062, "num_tokens": 173166657.0, "step": 28960 }, { "epoch": 0.3090160349076633, "grad_norm": 1.2352406908514297, "learning_rate": 4.2239328889757794e-05, "loss": 0.634, "num_tokens": 173191237.0, "step": 28965 }, { "epoch": 0.3090693779138617, "grad_norm": 1.2477674727150614, "learning_rate": 4.223632980160187e-05, "loss": 0.5527, "num_tokens": 173222596.0, "step": 28970 }, { "epoch": 0.30912272092006016, "grad_norm": 1.933959337752326, "learning_rate": 4.223333025488163e-05, "loss": 0.7412, "num_tokens": 173257972.0, "step": 28975 }, { "epoch": 0.3091760639262586, "grad_norm": 0.9914593926466303, "learning_rate": 4.223033024969042e-05, "loss": 0.5183, "num_tokens": 173277891.0, "step": 28980 }, { "epoch": 0.3092294069324571, "grad_norm": 1.143938666814746, "learning_rate": 4.222732978612159e-05, "loss": 0.5839, "num_tokens": 173299057.0, "step": 28985 }, { "epoch": 0.30928274993865557, "grad_norm": 1.395372044005693, "learning_rate": 4.22243288642685e-05, "loss": 0.5016, "num_tokens": 173325260.0, "step": 28990 }, { "epoch": 0.309336092944854, "grad_norm": 1.3910456688563722, "learning_rate": 4.222132748422455e-05, "loss": 0.6701, "num_tokens": 173344798.0, "step": 28995 }, { "epoch": 0.30938943595105245, "grad_norm": 1.4908452598479403, "learning_rate": 4.221832564608312e-05, "loss": 0.5315, "num_tokens": 173365093.0, "step": 29000 }, { "epoch": 0.3094427789572509, "grad_norm": 0.8968601855101375, "learning_rate": 4.221532334993763e-05, "loss": 0.4965, "num_tokens": 173396472.0, "step": 29005 }, { "epoch": 0.3094961219634494, "grad_norm": 1.1556206029830756, "learning_rate": 4.22123205958815e-05, "loss": 0.5825, "num_tokens": 173431587.0, "step": 29010 }, { "epoch": 0.3095494649696478, "grad_norm": 1.095244653336566, "learning_rate": 4.220931738400818e-05, "loss": 0.519, "num_tokens": 173475973.0, "step": 29015 }, { "epoch": 0.3096028079758463, "grad_norm": 1.566526110362866, "learning_rate": 4.220631371441112e-05, "loss": 0.6724, "num_tokens": 173501620.0, "step": 29020 }, { "epoch": 0.30965615098204474, "grad_norm": 0.6840877242563543, "learning_rate": 4.220330958718378e-05, "loss": 0.5227, "num_tokens": 173529225.0, "step": 29025 }, { "epoch": 0.3097094939882432, "grad_norm": 2.1210189240427506, "learning_rate": 4.2200305002419645e-05, "loss": 0.6303, "num_tokens": 173556280.0, "step": 29030 }, { "epoch": 0.3097628369944417, "grad_norm": 0.7113426261060906, "learning_rate": 4.219729996021221e-05, "loss": 0.5438, "num_tokens": 173584161.0, "step": 29035 }, { "epoch": 0.3098161800006401, "grad_norm": 0.824685411582751, "learning_rate": 4.2194294460655006e-05, "loss": 0.5091, "num_tokens": 173616801.0, "step": 29040 }, { "epoch": 0.30986952300683857, "grad_norm": 1.436962602755522, "learning_rate": 4.219128850384152e-05, "loss": 0.8142, "num_tokens": 173657283.0, "step": 29045 }, { "epoch": 0.30992286601303703, "grad_norm": 1.054185162623596, "learning_rate": 4.2188282089865325e-05, "loss": 0.593, "num_tokens": 173673176.0, "step": 29050 }, { "epoch": 0.3099762090192355, "grad_norm": 2.109144070681747, "learning_rate": 4.218527521881996e-05, "loss": 0.7171, "num_tokens": 173710762.0, "step": 29055 }, { "epoch": 0.3100295520254339, "grad_norm": 1.097184759955142, "learning_rate": 4.2182267890798985e-05, "loss": 0.4602, "num_tokens": 173732907.0, "step": 29060 }, { "epoch": 0.3100828950316324, "grad_norm": 0.9802033132883691, "learning_rate": 4.217926010589601e-05, "loss": 0.5501, "num_tokens": 173752017.0, "step": 29065 }, { "epoch": 0.31013623803783086, "grad_norm": 1.7270084000375607, "learning_rate": 4.21762518642046e-05, "loss": 0.524, "num_tokens": 173763280.0, "step": 29070 }, { "epoch": 0.3101895810440293, "grad_norm": 0.9126269239737083, "learning_rate": 4.217324316581838e-05, "loss": 0.4923, "num_tokens": 173798302.0, "step": 29075 }, { "epoch": 0.3102429240502278, "grad_norm": 1.0367482427197074, "learning_rate": 4.2170234010830974e-05, "loss": 0.652, "num_tokens": 173851011.0, "step": 29080 }, { "epoch": 0.3102962670564262, "grad_norm": 1.9655067273224973, "learning_rate": 4.216722439933602e-05, "loss": 0.5438, "num_tokens": 173872101.0, "step": 29085 }, { "epoch": 0.3103496100626247, "grad_norm": 1.94795131504182, "learning_rate": 4.216421433142716e-05, "loss": 0.7708, "num_tokens": 173897496.0, "step": 29090 }, { "epoch": 0.31040295306882315, "grad_norm": 0.9822178933531313, "learning_rate": 4.2161203807198086e-05, "loss": 0.6344, "num_tokens": 173932897.0, "step": 29095 }, { "epoch": 0.3104562960750216, "grad_norm": 0.8340804665317249, "learning_rate": 4.215819282674246e-05, "loss": 0.541, "num_tokens": 173956880.0, "step": 29100 }, { "epoch": 0.31050963908122003, "grad_norm": 0.8345077344290576, "learning_rate": 4.2155181390153974e-05, "loss": 0.602, "num_tokens": 173997241.0, "step": 29105 }, { "epoch": 0.3105629820874185, "grad_norm": 0.8558167263663229, "learning_rate": 4.215216949752635e-05, "loss": 0.822, "num_tokens": 174024072.0, "step": 29110 }, { "epoch": 0.310616325093617, "grad_norm": 2.5448112291288814, "learning_rate": 4.2149157148953314e-05, "loss": 0.589, "num_tokens": 174053557.0, "step": 29115 }, { "epoch": 0.31066966809981544, "grad_norm": 2.606908780171282, "learning_rate": 4.214614434452859e-05, "loss": 0.7104, "num_tokens": 174083393.0, "step": 29120 }, { "epoch": 0.3107230111060139, "grad_norm": 2.0272232167462763, "learning_rate": 4.2143131084345946e-05, "loss": 0.4276, "num_tokens": 174137631.0, "step": 29125 }, { "epoch": 0.3107763541122123, "grad_norm": 1.1482286446364116, "learning_rate": 4.2140117368499136e-05, "loss": 0.7173, "num_tokens": 174162441.0, "step": 29130 }, { "epoch": 0.3108296971184108, "grad_norm": 0.6838467868011868, "learning_rate": 4.213710319708194e-05, "loss": 0.565, "num_tokens": 174194234.0, "step": 29135 }, { "epoch": 0.31088304012460927, "grad_norm": 1.1823502662123542, "learning_rate": 4.2134088570188164e-05, "loss": 0.5058, "num_tokens": 174210082.0, "step": 29140 }, { "epoch": 0.31093638313080774, "grad_norm": 1.026240653194425, "learning_rate": 4.213107348791161e-05, "loss": 0.5669, "num_tokens": 174248525.0, "step": 29145 }, { "epoch": 0.31098972613700615, "grad_norm": 2.187766976134684, "learning_rate": 4.21280579503461e-05, "loss": 0.5543, "num_tokens": 174284677.0, "step": 29150 }, { "epoch": 0.3110430691432046, "grad_norm": 0.8856931663272724, "learning_rate": 4.212504195758548e-05, "loss": 0.5959, "num_tokens": 174324734.0, "step": 29155 }, { "epoch": 0.3110964121494031, "grad_norm": 1.5099793505089218, "learning_rate": 4.2122025509723587e-05, "loss": 0.6693, "num_tokens": 174356785.0, "step": 29160 }, { "epoch": 0.31114975515560156, "grad_norm": 1.1747705330807876, "learning_rate": 4.21190086068543e-05, "loss": 0.5944, "num_tokens": 174384055.0, "step": 29165 }, { "epoch": 0.31120309816180003, "grad_norm": 1.3858713376051375, "learning_rate": 4.211599124907149e-05, "loss": 0.5618, "num_tokens": 174405501.0, "step": 29170 }, { "epoch": 0.31125644116799844, "grad_norm": 1.027008849448957, "learning_rate": 4.211297343646906e-05, "loss": 0.6038, "num_tokens": 174433336.0, "step": 29175 }, { "epoch": 0.3113097841741969, "grad_norm": 0.9953414206700926, "learning_rate": 4.2109955169140904e-05, "loss": 0.7273, "num_tokens": 174465654.0, "step": 29180 }, { "epoch": 0.3113631271803954, "grad_norm": 1.5675140821884503, "learning_rate": 4.2106936447180955e-05, "loss": 0.5712, "num_tokens": 174497968.0, "step": 29185 }, { "epoch": 0.31141647018659385, "grad_norm": 1.5129737724283134, "learning_rate": 4.2103917270683156e-05, "loss": 0.5947, "num_tokens": 174533726.0, "step": 29190 }, { "epoch": 0.31146981319279227, "grad_norm": 1.0331175174363556, "learning_rate": 4.2100897639741434e-05, "loss": 0.5262, "num_tokens": 174562495.0, "step": 29195 }, { "epoch": 0.31152315619899074, "grad_norm": 0.9918240805417465, "learning_rate": 4.2097877554449776e-05, "loss": 0.5466, "num_tokens": 174587769.0, "step": 29200 }, { "epoch": 0.3115764992051892, "grad_norm": 0.6889798723464241, "learning_rate": 4.209485701490216e-05, "loss": 0.5395, "num_tokens": 174619420.0, "step": 29205 }, { "epoch": 0.3116298422113877, "grad_norm": 0.8220015478312697, "learning_rate": 4.209183602119257e-05, "loss": 0.4998, "num_tokens": 174645656.0, "step": 29210 }, { "epoch": 0.31168318521758615, "grad_norm": 0.761598692962607, "learning_rate": 4.208881457341501e-05, "loss": 0.5565, "num_tokens": 174671117.0, "step": 29215 }, { "epoch": 0.31173652822378456, "grad_norm": 6.738398470634769, "learning_rate": 4.2085792671663504e-05, "loss": 0.9134, "num_tokens": 174712138.0, "step": 29220 }, { "epoch": 0.31178987122998303, "grad_norm": 0.9587959017350781, "learning_rate": 4.20827703160321e-05, "loss": 0.6618, "num_tokens": 174744909.0, "step": 29225 }, { "epoch": 0.3118432142361815, "grad_norm": 0.7616929067986752, "learning_rate": 4.207974750661483e-05, "loss": 0.5542, "num_tokens": 174793335.0, "step": 29230 }, { "epoch": 0.31189655724237997, "grad_norm": 0.8775444197723732, "learning_rate": 4.2076724243505766e-05, "loss": 0.4738, "num_tokens": 174818576.0, "step": 29235 }, { "epoch": 0.3119499002485784, "grad_norm": 0.963484097730361, "learning_rate": 4.2073700526798985e-05, "loss": 0.6312, "num_tokens": 174851884.0, "step": 29240 }, { "epoch": 0.31200324325477685, "grad_norm": 1.4953361486260894, "learning_rate": 4.207067635658858e-05, "loss": 0.7242, "num_tokens": 174885514.0, "step": 29245 }, { "epoch": 0.3120565862609753, "grad_norm": 0.6685138738035151, "learning_rate": 4.206765173296866e-05, "loss": 0.5344, "num_tokens": 174926380.0, "step": 29250 }, { "epoch": 0.3121099292671738, "grad_norm": 0.8012179585535072, "learning_rate": 4.206462665603334e-05, "loss": 0.6866, "num_tokens": 174959952.0, "step": 29255 }, { "epoch": 0.31216327227337226, "grad_norm": 0.6682131652107708, "learning_rate": 4.2061601125876746e-05, "loss": 0.6556, "num_tokens": 174990762.0, "step": 29260 }, { "epoch": 0.3122166152795707, "grad_norm": 0.8481567810772112, "learning_rate": 4.2058575142593046e-05, "loss": 0.596, "num_tokens": 175013248.0, "step": 29265 }, { "epoch": 0.31226995828576914, "grad_norm": 0.8823326568896103, "learning_rate": 4.205554870627639e-05, "loss": 0.5955, "num_tokens": 175046263.0, "step": 29270 }, { "epoch": 0.3123233012919676, "grad_norm": 1.0395309771086985, "learning_rate": 4.205252181702096e-05, "loss": 0.6042, "num_tokens": 175077854.0, "step": 29275 }, { "epoch": 0.3123766442981661, "grad_norm": 0.7577088803600479, "learning_rate": 4.204949447492093e-05, "loss": 0.6391, "num_tokens": 175123127.0, "step": 29280 }, { "epoch": 0.3124299873043645, "grad_norm": 1.7276623461147267, "learning_rate": 4.204646668007052e-05, "loss": 0.553, "num_tokens": 175152884.0, "step": 29285 }, { "epoch": 0.31248333031056297, "grad_norm": 0.6832867855078381, "learning_rate": 4.204343843256396e-05, "loss": 0.5248, "num_tokens": 175203807.0, "step": 29290 }, { "epoch": 0.31253667331676144, "grad_norm": 1.4147088786574509, "learning_rate": 4.2040409732495454e-05, "loss": 0.5356, "num_tokens": 175232783.0, "step": 29295 }, { "epoch": 0.3125900163229599, "grad_norm": 1.022458292632763, "learning_rate": 4.203738057995927e-05, "loss": 0.4922, "num_tokens": 175269665.0, "step": 29300 }, { "epoch": 0.3126433593291584, "grad_norm": 1.0892561017402287, "learning_rate": 4.2034350975049667e-05, "loss": 0.5624, "num_tokens": 175287487.0, "step": 29305 }, { "epoch": 0.3126967023353568, "grad_norm": 1.03743422632801, "learning_rate": 4.2031320917860914e-05, "loss": 0.5188, "num_tokens": 175331099.0, "step": 29310 }, { "epoch": 0.31275004534155526, "grad_norm": 0.9450107074322421, "learning_rate": 4.2028290408487295e-05, "loss": 0.5515, "num_tokens": 175382137.0, "step": 29315 }, { "epoch": 0.31280338834775373, "grad_norm": 0.7645892795623292, "learning_rate": 4.202525944702312e-05, "loss": 0.5589, "num_tokens": 175419107.0, "step": 29320 }, { "epoch": 0.3128567313539522, "grad_norm": 1.5444806881728204, "learning_rate": 4.2022228033562714e-05, "loss": 0.5972, "num_tokens": 175453536.0, "step": 29325 }, { "epoch": 0.3129100743601506, "grad_norm": 1.1231153176763673, "learning_rate": 4.2019196168200396e-05, "loss": 0.6782, "num_tokens": 175481647.0, "step": 29330 }, { "epoch": 0.3129634173663491, "grad_norm": 0.7026433763409465, "learning_rate": 4.201616385103052e-05, "loss": 0.5465, "num_tokens": 175516714.0, "step": 29335 }, { "epoch": 0.31301676037254755, "grad_norm": 1.3368134929690738, "learning_rate": 4.201313108214744e-05, "loss": 0.4832, "num_tokens": 175546165.0, "step": 29340 }, { "epoch": 0.313070103378746, "grad_norm": 1.7857420316981496, "learning_rate": 4.201009786164553e-05, "loss": 0.6327, "num_tokens": 175557737.0, "step": 29345 }, { "epoch": 0.3131234463849445, "grad_norm": 0.9844366091504109, "learning_rate": 4.200706418961919e-05, "loss": 0.6837, "num_tokens": 175583091.0, "step": 29350 }, { "epoch": 0.3131767893911429, "grad_norm": 2.882539409973805, "learning_rate": 4.20040300661628e-05, "loss": 0.5133, "num_tokens": 175599289.0, "step": 29355 }, { "epoch": 0.3132301323973414, "grad_norm": 0.7889443988046007, "learning_rate": 4.2000995491370785e-05, "loss": 0.5527, "num_tokens": 175633218.0, "step": 29360 }, { "epoch": 0.31328347540353985, "grad_norm": 1.094741444431819, "learning_rate": 4.1997960465337584e-05, "loss": 0.462, "num_tokens": 175653050.0, "step": 29365 }, { "epoch": 0.3133368184097383, "grad_norm": 1.2487938652921442, "learning_rate": 4.199492498815763e-05, "loss": 0.4831, "num_tokens": 175671504.0, "step": 29370 }, { "epoch": 0.31339016141593673, "grad_norm": 1.1817554772206944, "learning_rate": 4.199188905992538e-05, "loss": 0.529, "num_tokens": 175696609.0, "step": 29375 }, { "epoch": 0.3134435044221352, "grad_norm": 0.9579941424087772, "learning_rate": 4.198885268073532e-05, "loss": 0.4295, "num_tokens": 175711347.0, "step": 29380 }, { "epoch": 0.31349684742833367, "grad_norm": 1.2761429516444371, "learning_rate": 4.198581585068192e-05, "loss": 0.5312, "num_tokens": 175737508.0, "step": 29385 }, { "epoch": 0.31355019043453214, "grad_norm": 0.9948603835411997, "learning_rate": 4.198277856985968e-05, "loss": 0.4577, "num_tokens": 175768058.0, "step": 29390 }, { "epoch": 0.3136035334407306, "grad_norm": 1.7092936930649774, "learning_rate": 4.197974083836312e-05, "loss": 0.5738, "num_tokens": 175798610.0, "step": 29395 }, { "epoch": 0.313656876446929, "grad_norm": 0.8841316302995572, "learning_rate": 4.197670265628678e-05, "loss": 0.6409, "num_tokens": 175841415.0, "step": 29400 }, { "epoch": 0.3137102194531275, "grad_norm": 0.7980900042669706, "learning_rate": 4.197366402372517e-05, "loss": 0.6555, "num_tokens": 175880585.0, "step": 29405 }, { "epoch": 0.31376356245932596, "grad_norm": 0.9290658892869863, "learning_rate": 4.197062494077288e-05, "loss": 0.6675, "num_tokens": 175911429.0, "step": 29410 }, { "epoch": 0.31381690546552443, "grad_norm": 0.8876322888767271, "learning_rate": 4.1967585407524465e-05, "loss": 0.6318, "num_tokens": 175932615.0, "step": 29415 }, { "epoch": 0.31387024847172285, "grad_norm": 1.0228852601067464, "learning_rate": 4.1964545424074496e-05, "loss": 0.5668, "num_tokens": 175966128.0, "step": 29420 }, { "epoch": 0.3139235914779213, "grad_norm": 1.1974598686807458, "learning_rate": 4.1961504990517597e-05, "loss": 0.5507, "num_tokens": 175992120.0, "step": 29425 }, { "epoch": 0.3139769344841198, "grad_norm": 0.9132617939804603, "learning_rate": 4.195846410694837e-05, "loss": 0.6619, "num_tokens": 176026931.0, "step": 29430 }, { "epoch": 0.31403027749031825, "grad_norm": 0.7726458178021439, "learning_rate": 4.195542277346142e-05, "loss": 0.4654, "num_tokens": 176057075.0, "step": 29435 }, { "epoch": 0.3140836204965167, "grad_norm": 1.2700531161198965, "learning_rate": 4.195238099015143e-05, "loss": 0.5879, "num_tokens": 176086331.0, "step": 29440 }, { "epoch": 0.31413696350271514, "grad_norm": 0.8830065623013473, "learning_rate": 4.194933875711301e-05, "loss": 0.5975, "num_tokens": 176125075.0, "step": 29445 }, { "epoch": 0.3141903065089136, "grad_norm": 1.13304799852734, "learning_rate": 4.194629607444086e-05, "loss": 0.5565, "num_tokens": 176159287.0, "step": 29450 }, { "epoch": 0.3142436495151121, "grad_norm": 0.7486577728671375, "learning_rate": 4.194325294222964e-05, "loss": 0.483, "num_tokens": 176206388.0, "step": 29455 }, { "epoch": 0.31429699252131055, "grad_norm": 1.09686408247884, "learning_rate": 4.1940209360574065e-05, "loss": 0.5793, "num_tokens": 176238962.0, "step": 29460 }, { "epoch": 0.31435033552750896, "grad_norm": 1.5719931049926568, "learning_rate": 4.193716532956883e-05, "loss": 0.6417, "num_tokens": 176260920.0, "step": 29465 }, { "epoch": 0.31440367853370743, "grad_norm": 0.7204977540540279, "learning_rate": 4.1934120849308664e-05, "loss": 0.7325, "num_tokens": 176301618.0, "step": 29470 }, { "epoch": 0.3144570215399059, "grad_norm": 0.9317030565205049, "learning_rate": 4.193107591988831e-05, "loss": 0.5556, "num_tokens": 176326865.0, "step": 29475 }, { "epoch": 0.31451036454610437, "grad_norm": 1.423802943298927, "learning_rate": 4.192803054140251e-05, "loss": 0.4695, "num_tokens": 176349999.0, "step": 29480 }, { "epoch": 0.31456370755230284, "grad_norm": 1.1630543526284254, "learning_rate": 4.1924984713946045e-05, "loss": 0.5212, "num_tokens": 176377732.0, "step": 29485 }, { "epoch": 0.31461705055850125, "grad_norm": 0.7502465240968796, "learning_rate": 4.192193843761368e-05, "loss": 0.6224, "num_tokens": 176404541.0, "step": 29490 }, { "epoch": 0.3146703935646997, "grad_norm": 1.1268698546283213, "learning_rate": 4.1918891712500213e-05, "loss": 0.5462, "num_tokens": 176436574.0, "step": 29495 }, { "epoch": 0.3147237365708982, "grad_norm": 0.7555252436544778, "learning_rate": 4.1915844538700455e-05, "loss": 0.502, "num_tokens": 176463765.0, "step": 29500 }, { "epoch": 0.31477707957709666, "grad_norm": 0.7863616022936721, "learning_rate": 4.191279691630923e-05, "loss": 0.6507, "num_tokens": 176490191.0, "step": 29505 }, { "epoch": 0.3148304225832951, "grad_norm": 0.8180232635084381, "learning_rate": 4.1909748845421356e-05, "loss": 0.5212, "num_tokens": 176532852.0, "step": 29510 }, { "epoch": 0.31488376558949355, "grad_norm": 1.2174200167760283, "learning_rate": 4.190670032613171e-05, "loss": 0.4791, "num_tokens": 176557978.0, "step": 29515 }, { "epoch": 0.314937108595692, "grad_norm": 0.8492989701516261, "learning_rate": 4.190365135853514e-05, "loss": 0.6388, "num_tokens": 176593606.0, "step": 29520 }, { "epoch": 0.3149904516018905, "grad_norm": 0.8962535483700782, "learning_rate": 4.190060194272652e-05, "loss": 0.5808, "num_tokens": 176627493.0, "step": 29525 }, { "epoch": 0.31504379460808896, "grad_norm": 1.0615884962807418, "learning_rate": 4.189755207880075e-05, "loss": 0.5448, "num_tokens": 176650685.0, "step": 29530 }, { "epoch": 0.31509713761428737, "grad_norm": 1.0257162357545864, "learning_rate": 4.1894501766852733e-05, "loss": 0.6848, "num_tokens": 176682929.0, "step": 29535 }, { "epoch": 0.31515048062048584, "grad_norm": 0.7594885768931624, "learning_rate": 4.1891451006977386e-05, "loss": 0.6021, "num_tokens": 176718373.0, "step": 29540 }, { "epoch": 0.3152038236266843, "grad_norm": 1.1425882352738965, "learning_rate": 4.188839979926965e-05, "loss": 0.4931, "num_tokens": 176744703.0, "step": 29545 }, { "epoch": 0.3152571666328828, "grad_norm": 0.9355106294049184, "learning_rate": 4.188534814382446e-05, "loss": 0.4905, "num_tokens": 176781307.0, "step": 29550 }, { "epoch": 0.3153105096390812, "grad_norm": 1.060467470773798, "learning_rate": 4.188229604073679e-05, "loss": 0.5912, "num_tokens": 176830632.0, "step": 29555 }, { "epoch": 0.31536385264527966, "grad_norm": 2.1206210667412457, "learning_rate": 4.187924349010161e-05, "loss": 0.6239, "num_tokens": 176857580.0, "step": 29560 }, { "epoch": 0.31541719565147813, "grad_norm": 1.091352510625761, "learning_rate": 4.1876190492013904e-05, "loss": 0.5429, "num_tokens": 176876656.0, "step": 29565 }, { "epoch": 0.3154705386576766, "grad_norm": 0.9445398795450725, "learning_rate": 4.1873137046568684e-05, "loss": 0.5735, "num_tokens": 176913018.0, "step": 29570 }, { "epoch": 0.31552388166387507, "grad_norm": 1.5645199003325674, "learning_rate": 4.187008315386096e-05, "loss": 0.5692, "num_tokens": 176933276.0, "step": 29575 }, { "epoch": 0.3155772246700735, "grad_norm": 0.8391183928072031, "learning_rate": 4.1867028813985754e-05, "loss": 0.5117, "num_tokens": 176957615.0, "step": 29580 }, { "epoch": 0.31563056767627196, "grad_norm": 1.0756420372908038, "learning_rate": 4.186397402703814e-05, "loss": 0.519, "num_tokens": 176982139.0, "step": 29585 }, { "epoch": 0.3156839106824704, "grad_norm": 1.1343681582968193, "learning_rate": 4.186091879311315e-05, "loss": 0.5328, "num_tokens": 177009656.0, "step": 29590 }, { "epoch": 0.3157372536886689, "grad_norm": 2.19504511781984, "learning_rate": 4.185786311230586e-05, "loss": 0.6105, "num_tokens": 177025658.0, "step": 29595 }, { "epoch": 0.3157905966948673, "grad_norm": 1.1291779862708995, "learning_rate": 4.185480698471137e-05, "loss": 0.5133, "num_tokens": 177055882.0, "step": 29600 }, { "epoch": 0.3158439397010658, "grad_norm": 1.311893913203787, "learning_rate": 4.1851750410424774e-05, "loss": 0.5525, "num_tokens": 177094665.0, "step": 29605 }, { "epoch": 0.31589728270726425, "grad_norm": 1.238187204766296, "learning_rate": 4.1848693389541175e-05, "loss": 0.6941, "num_tokens": 177124633.0, "step": 29610 }, { "epoch": 0.3159506257134627, "grad_norm": 0.7865525757434282, "learning_rate": 4.1845635922155724e-05, "loss": 0.5753, "num_tokens": 177152660.0, "step": 29615 }, { "epoch": 0.3160039687196612, "grad_norm": 0.7629863707023834, "learning_rate": 4.184257800836354e-05, "loss": 0.5937, "num_tokens": 177195231.0, "step": 29620 }, { "epoch": 0.3160573117258596, "grad_norm": 0.9667341137646305, "learning_rate": 4.183951964825979e-05, "loss": 0.5399, "num_tokens": 177218151.0, "step": 29625 }, { "epoch": 0.31611065473205807, "grad_norm": 0.6519097127914822, "learning_rate": 4.183646084193965e-05, "loss": 0.4802, "num_tokens": 177253643.0, "step": 29630 }, { "epoch": 0.31616399773825654, "grad_norm": 1.2241426107248545, "learning_rate": 4.1833401589498286e-05, "loss": 0.4868, "num_tokens": 177281494.0, "step": 29635 }, { "epoch": 0.316217340744455, "grad_norm": 1.3075095549990687, "learning_rate": 4.183034189103091e-05, "loss": 0.5733, "num_tokens": 177299842.0, "step": 29640 }, { "epoch": 0.3162706837506534, "grad_norm": 1.081784539531978, "learning_rate": 4.182728174663273e-05, "loss": 0.6128, "num_tokens": 177320766.0, "step": 29645 }, { "epoch": 0.3163240267568519, "grad_norm": 1.283868187752296, "learning_rate": 4.182422115639898e-05, "loss": 0.6399, "num_tokens": 177346421.0, "step": 29650 }, { "epoch": 0.31637736976305036, "grad_norm": 1.2351094224777777, "learning_rate": 4.182116012042487e-05, "loss": 0.5617, "num_tokens": 177370185.0, "step": 29655 }, { "epoch": 0.31643071276924883, "grad_norm": 0.7954836015136078, "learning_rate": 4.18180986388057e-05, "loss": 0.4862, "num_tokens": 177412411.0, "step": 29660 }, { "epoch": 0.3164840557754473, "grad_norm": 1.1027341954168484, "learning_rate": 4.181503671163669e-05, "loss": 0.6037, "num_tokens": 177455692.0, "step": 29665 }, { "epoch": 0.3165373987816457, "grad_norm": 1.2549308406758382, "learning_rate": 4.181197433901315e-05, "loss": 0.574, "num_tokens": 177485373.0, "step": 29670 }, { "epoch": 0.3165907417878442, "grad_norm": 0.9128153622517752, "learning_rate": 4.180891152103037e-05, "loss": 0.5109, "num_tokens": 177516353.0, "step": 29675 }, { "epoch": 0.31664408479404266, "grad_norm": 0.9956606596984724, "learning_rate": 4.1805848257783646e-05, "loss": 0.5178, "num_tokens": 177554936.0, "step": 29680 }, { "epoch": 0.3166974278002411, "grad_norm": 1.1591260033469621, "learning_rate": 4.1802784549368306e-05, "loss": 0.5682, "num_tokens": 177570929.0, "step": 29685 }, { "epoch": 0.31675077080643954, "grad_norm": 0.5842073016410233, "learning_rate": 4.17997203958797e-05, "loss": 0.5378, "num_tokens": 177608766.0, "step": 29690 }, { "epoch": 0.316804113812638, "grad_norm": 0.7121442192876647, "learning_rate": 4.1796655797413164e-05, "loss": 0.6405, "num_tokens": 177646620.0, "step": 29695 }, { "epoch": 0.3168574568188365, "grad_norm": 1.4061010833408671, "learning_rate": 4.179359075406406e-05, "loss": 0.6038, "num_tokens": 177673491.0, "step": 29700 }, { "epoch": 0.31691079982503495, "grad_norm": 1.0340387053770927, "learning_rate": 4.1790525265927784e-05, "loss": 0.4723, "num_tokens": 177693341.0, "step": 29705 }, { "epoch": 0.3169641428312334, "grad_norm": 1.3012602265975828, "learning_rate": 4.1787459333099705e-05, "loss": 0.56, "num_tokens": 177709047.0, "step": 29710 }, { "epoch": 0.31701748583743183, "grad_norm": 1.0682036379203546, "learning_rate": 4.178439295567525e-05, "loss": 0.5639, "num_tokens": 177736171.0, "step": 29715 }, { "epoch": 0.3170708288436303, "grad_norm": 0.7521583453030376, "learning_rate": 4.178132613374981e-05, "loss": 0.642, "num_tokens": 177769508.0, "step": 29720 }, { "epoch": 0.3171241718498288, "grad_norm": 0.8196252185098941, "learning_rate": 4.1778258867418846e-05, "loss": 0.4429, "num_tokens": 177794988.0, "step": 29725 }, { "epoch": 0.31717751485602724, "grad_norm": 1.607323609013944, "learning_rate": 4.177519115677779e-05, "loss": 0.5528, "num_tokens": 177836376.0, "step": 29730 }, { "epoch": 0.31723085786222566, "grad_norm": 0.8162801605379217, "learning_rate": 4.177212300192212e-05, "loss": 0.594, "num_tokens": 177865397.0, "step": 29735 }, { "epoch": 0.3172842008684241, "grad_norm": 0.8383896076509003, "learning_rate": 4.176905440294728e-05, "loss": 0.5703, "num_tokens": 177898366.0, "step": 29740 }, { "epoch": 0.3173375438746226, "grad_norm": 0.7651019496459848, "learning_rate": 4.1765985359948784e-05, "loss": 0.5837, "num_tokens": 177931857.0, "step": 29745 }, { "epoch": 0.31739088688082107, "grad_norm": 3.2729382571933083, "learning_rate": 4.1762915873022135e-05, "loss": 0.6528, "num_tokens": 177969851.0, "step": 29750 }, { "epoch": 0.31744422988701954, "grad_norm": 0.8122158528618932, "learning_rate": 4.175984594226283e-05, "loss": 0.4242, "num_tokens": 178000921.0, "step": 29755 }, { "epoch": 0.31749757289321795, "grad_norm": 1.1737077104846216, "learning_rate": 4.175677556776641e-05, "loss": 0.4936, "num_tokens": 178019887.0, "step": 29760 }, { "epoch": 0.3175509158994164, "grad_norm": 1.3086690322150307, "learning_rate": 4.1753704749628425e-05, "loss": 0.5866, "num_tokens": 178052433.0, "step": 29765 }, { "epoch": 0.3176042589056149, "grad_norm": 0.834194046179187, "learning_rate": 4.1750633487944425e-05, "loss": 0.7363, "num_tokens": 178085474.0, "step": 29770 }, { "epoch": 0.31765760191181336, "grad_norm": 0.8148254327035501, "learning_rate": 4.174756178280998e-05, "loss": 0.5002, "num_tokens": 178109318.0, "step": 29775 }, { "epoch": 0.3177109449180118, "grad_norm": 1.8028511230852855, "learning_rate": 4.174448963432068e-05, "loss": 0.7021, "num_tokens": 178125136.0, "step": 29780 }, { "epoch": 0.31776428792421024, "grad_norm": 1.2395547258753261, "learning_rate": 4.174141704257212e-05, "loss": 0.6273, "num_tokens": 178145660.0, "step": 29785 }, { "epoch": 0.3178176309304087, "grad_norm": 0.8698565266591229, "learning_rate": 4.1738344007659916e-05, "loss": 0.6389, "num_tokens": 178195697.0, "step": 29790 }, { "epoch": 0.3178709739366072, "grad_norm": 1.3796011072377328, "learning_rate": 4.1735270529679685e-05, "loss": 0.6439, "num_tokens": 178216806.0, "step": 29795 }, { "epoch": 0.31792431694280565, "grad_norm": 1.7717112880330028, "learning_rate": 4.173219660872708e-05, "loss": 0.6224, "num_tokens": 178234627.0, "step": 29800 }, { "epoch": 0.31797765994900407, "grad_norm": 1.3886221242988015, "learning_rate": 4.172912224489775e-05, "loss": 0.6325, "num_tokens": 178270297.0, "step": 29805 }, { "epoch": 0.31803100295520254, "grad_norm": 1.2619202829334286, "learning_rate": 4.172604743828737e-05, "loss": 0.5464, "num_tokens": 178295827.0, "step": 29810 }, { "epoch": 0.318084345961401, "grad_norm": 0.8443468544985296, "learning_rate": 4.172297218899161e-05, "loss": 0.569, "num_tokens": 178325076.0, "step": 29815 }, { "epoch": 0.3181376889675995, "grad_norm": 0.8996734657497439, "learning_rate": 4.171989649710617e-05, "loss": 0.6002, "num_tokens": 178365991.0, "step": 29820 }, { "epoch": 0.3181910319737979, "grad_norm": 0.8572664075757096, "learning_rate": 4.1716820362726764e-05, "loss": 0.5265, "num_tokens": 178396596.0, "step": 29825 }, { "epoch": 0.31824437497999636, "grad_norm": 0.8369376335250455, "learning_rate": 4.17137437859491e-05, "loss": 0.6018, "num_tokens": 178423242.0, "step": 29830 }, { "epoch": 0.31829771798619483, "grad_norm": 1.1055584268079341, "learning_rate": 4.171066676686893e-05, "loss": 0.618, "num_tokens": 178465671.0, "step": 29835 }, { "epoch": 0.3183510609923933, "grad_norm": 0.9514841773895345, "learning_rate": 4.1707589305582e-05, "loss": 0.4789, "num_tokens": 178495965.0, "step": 29840 }, { "epoch": 0.31840440399859177, "grad_norm": 0.8894139124146216, "learning_rate": 4.170451140218408e-05, "loss": 0.5365, "num_tokens": 178514802.0, "step": 29845 }, { "epoch": 0.3184577470047902, "grad_norm": 1.364150844671832, "learning_rate": 4.170143305677093e-05, "loss": 0.6072, "num_tokens": 178541422.0, "step": 29850 }, { "epoch": 0.31851109001098865, "grad_norm": 1.0105371493793045, "learning_rate": 4.169835426943837e-05, "loss": 0.6328, "num_tokens": 178573821.0, "step": 29855 }, { "epoch": 0.3185644330171871, "grad_norm": 1.3765325696772064, "learning_rate": 4.1695275040282175e-05, "loss": 0.4819, "num_tokens": 178603012.0, "step": 29860 }, { "epoch": 0.3186177760233856, "grad_norm": 1.6620660356265873, "learning_rate": 4.169219536939818e-05, "loss": 0.6138, "num_tokens": 178638250.0, "step": 29865 }, { "epoch": 0.318671119029584, "grad_norm": 1.0689885314339418, "learning_rate": 4.1689115256882224e-05, "loss": 0.5273, "num_tokens": 178661661.0, "step": 29870 }, { "epoch": 0.3187244620357825, "grad_norm": 0.9531588218829432, "learning_rate": 4.168603470283014e-05, "loss": 0.4662, "num_tokens": 178684404.0, "step": 29875 }, { "epoch": 0.31877780504198094, "grad_norm": 0.9447164348215839, "learning_rate": 4.16829537073378e-05, "loss": 0.5778, "num_tokens": 178717824.0, "step": 29880 }, { "epoch": 0.3188311480481794, "grad_norm": 0.9147627445191936, "learning_rate": 4.1679872270501073e-05, "loss": 0.5279, "num_tokens": 178746889.0, "step": 29885 }, { "epoch": 0.3188844910543779, "grad_norm": 0.7102062683095209, "learning_rate": 4.167679039241584e-05, "loss": 0.5755, "num_tokens": 178783795.0, "step": 29890 }, { "epoch": 0.3189378340605763, "grad_norm": 1.1037349551057805, "learning_rate": 4.167370807317802e-05, "loss": 0.6434, "num_tokens": 178804325.0, "step": 29895 }, { "epoch": 0.31899117706677477, "grad_norm": 1.2765517569368088, "learning_rate": 4.167062531288352e-05, "loss": 0.5456, "num_tokens": 178830914.0, "step": 29900 }, { "epoch": 0.31904452007297324, "grad_norm": 0.7467866740132034, "learning_rate": 4.166754211162826e-05, "loss": 0.6112, "num_tokens": 178874749.0, "step": 29905 }, { "epoch": 0.3190978630791717, "grad_norm": 1.2489786496198463, "learning_rate": 4.166445846950818e-05, "loss": 0.574, "num_tokens": 178896364.0, "step": 29910 }, { "epoch": 0.3191512060853701, "grad_norm": 0.9122726251348348, "learning_rate": 4.166137438661926e-05, "loss": 0.5955, "num_tokens": 178934618.0, "step": 29915 }, { "epoch": 0.3192045490915686, "grad_norm": 1.9121745788832472, "learning_rate": 4.1658289863057466e-05, "loss": 0.6848, "num_tokens": 178961080.0, "step": 29920 }, { "epoch": 0.31925789209776706, "grad_norm": 1.056364473384178, "learning_rate": 4.165520489891876e-05, "loss": 0.5433, "num_tokens": 178982376.0, "step": 29925 }, { "epoch": 0.31931123510396553, "grad_norm": 1.441524838968854, "learning_rate": 4.1652119494299154e-05, "loss": 0.5126, "num_tokens": 179002423.0, "step": 29930 }, { "epoch": 0.319364578110164, "grad_norm": 1.1049485332569147, "learning_rate": 4.1649033649294675e-05, "loss": 0.64, "num_tokens": 179033021.0, "step": 29935 }, { "epoch": 0.3194179211163624, "grad_norm": 1.020979028472678, "learning_rate": 4.164594736400131e-05, "loss": 0.4835, "num_tokens": 179058238.0, "step": 29940 }, { "epoch": 0.3194712641225609, "grad_norm": 0.7568178083851163, "learning_rate": 4.164286063851513e-05, "loss": 0.6175, "num_tokens": 179090943.0, "step": 29945 }, { "epoch": 0.31952460712875935, "grad_norm": 1.1380688553465355, "learning_rate": 4.163977347293217e-05, "loss": 0.5573, "num_tokens": 179106997.0, "step": 29950 }, { "epoch": 0.3195779501349578, "grad_norm": 0.9806395926816358, "learning_rate": 4.163668586734851e-05, "loss": 0.7786, "num_tokens": 179128439.0, "step": 29955 }, { "epoch": 0.31963129314115624, "grad_norm": 1.3723783565933327, "learning_rate": 4.1633597821860225e-05, "loss": 0.6955, "num_tokens": 179167915.0, "step": 29960 }, { "epoch": 0.3196846361473547, "grad_norm": 1.1554161979318633, "learning_rate": 4.16305093365634e-05, "loss": 0.5525, "num_tokens": 179187119.0, "step": 29965 }, { "epoch": 0.3197379791535532, "grad_norm": 0.7134674708150607, "learning_rate": 4.1627420411554155e-05, "loss": 0.7546, "num_tokens": 179217866.0, "step": 29970 }, { "epoch": 0.31979132215975165, "grad_norm": 0.8464024809634972, "learning_rate": 4.1624331046928606e-05, "loss": 0.5871, "num_tokens": 179250983.0, "step": 29975 }, { "epoch": 0.3198446651659501, "grad_norm": 1.2241852821830685, "learning_rate": 4.1621241242782885e-05, "loss": 0.6001, "num_tokens": 179290620.0, "step": 29980 }, { "epoch": 0.31989800817214853, "grad_norm": 1.2331361331372113, "learning_rate": 4.161815099921314e-05, "loss": 0.4853, "num_tokens": 179319563.0, "step": 29985 }, { "epoch": 0.319951351178347, "grad_norm": 1.1976477627192572, "learning_rate": 4.161506031631554e-05, "loss": 0.5067, "num_tokens": 179361903.0, "step": 29990 }, { "epoch": 0.32000469418454547, "grad_norm": 1.2155219663105699, "learning_rate": 4.161196919418624e-05, "loss": 0.7028, "num_tokens": 179402745.0, "step": 29995 }, { "epoch": 0.32005803719074394, "grad_norm": 1.4957654251531785, "learning_rate": 4.160887763292147e-05, "loss": 0.6735, "num_tokens": 179438824.0, "step": 30000 }, { "epoch": 0.32011138019694235, "grad_norm": 1.0605126568086298, "learning_rate": 4.16057856326174e-05, "loss": 0.4448, "num_tokens": 179457426.0, "step": 30005 }, { "epoch": 0.3201647232031408, "grad_norm": 1.3039644692668755, "learning_rate": 4.1602693193370244e-05, "loss": 0.5928, "num_tokens": 179486173.0, "step": 30010 }, { "epoch": 0.3202180662093393, "grad_norm": 0.8253358091923357, "learning_rate": 4.159960031527626e-05, "loss": 0.6032, "num_tokens": 179502796.0, "step": 30015 }, { "epoch": 0.32027140921553776, "grad_norm": 0.9245495087024748, "learning_rate": 4.159650699843167e-05, "loss": 0.5521, "num_tokens": 179536962.0, "step": 30020 }, { "epoch": 0.32032475222173623, "grad_norm": 0.7839066832810938, "learning_rate": 4.159341324293273e-05, "loss": 0.6225, "num_tokens": 179577739.0, "step": 30025 }, { "epoch": 0.32037809522793465, "grad_norm": 2.003651186378712, "learning_rate": 4.1590319048875725e-05, "loss": 0.5835, "num_tokens": 179601713.0, "step": 30030 }, { "epoch": 0.3204314382341331, "grad_norm": 0.7710568439134224, "learning_rate": 4.158722441635694e-05, "loss": 0.5561, "num_tokens": 179637417.0, "step": 30035 }, { "epoch": 0.3204847812403316, "grad_norm": 0.7358618116045323, "learning_rate": 4.1584129345472653e-05, "loss": 0.6154, "num_tokens": 179676322.0, "step": 30040 }, { "epoch": 0.32053812424653005, "grad_norm": 0.8219928245654865, "learning_rate": 4.15810338363192e-05, "loss": 0.4542, "num_tokens": 179698278.0, "step": 30045 }, { "epoch": 0.32059146725272847, "grad_norm": 0.8193204082010522, "learning_rate": 4.1577937888992894e-05, "loss": 0.618, "num_tokens": 179726723.0, "step": 30050 }, { "epoch": 0.32064481025892694, "grad_norm": 0.9200252172517325, "learning_rate": 4.1574841503590075e-05, "loss": 0.5293, "num_tokens": 179771121.0, "step": 30055 }, { "epoch": 0.3206981532651254, "grad_norm": 0.7268283475399142, "learning_rate": 4.1571744680207105e-05, "loss": 0.6097, "num_tokens": 179809956.0, "step": 30060 }, { "epoch": 0.3207514962713239, "grad_norm": 1.133486510314885, "learning_rate": 4.156864741894034e-05, "loss": 0.563, "num_tokens": 179828968.0, "step": 30065 }, { "epoch": 0.32080483927752235, "grad_norm": 0.8298941707637704, "learning_rate": 4.1565549719886174e-05, "loss": 0.6831, "num_tokens": 179865154.0, "step": 30070 }, { "epoch": 0.32085818228372076, "grad_norm": 0.7128227606766412, "learning_rate": 4.1562451583140984e-05, "loss": 0.6279, "num_tokens": 179895712.0, "step": 30075 }, { "epoch": 0.32091152528991923, "grad_norm": 0.8634822926439338, "learning_rate": 4.1559353008801186e-05, "loss": 0.4948, "num_tokens": 179917640.0, "step": 30080 }, { "epoch": 0.3209648682961177, "grad_norm": 0.9263965036622644, "learning_rate": 4.15562539969632e-05, "loss": 0.4912, "num_tokens": 179946107.0, "step": 30085 }, { "epoch": 0.32101821130231617, "grad_norm": 0.9767356916748957, "learning_rate": 4.155315454772346e-05, "loss": 0.4658, "num_tokens": 179965456.0, "step": 30090 }, { "epoch": 0.3210715543085146, "grad_norm": 1.3827783860425598, "learning_rate": 4.155005466117842e-05, "loss": 0.5403, "num_tokens": 179999423.0, "step": 30095 }, { "epoch": 0.32112489731471305, "grad_norm": 1.0933213854758117, "learning_rate": 4.1546954337424534e-05, "loss": 0.8244, "num_tokens": 180046051.0, "step": 30100 }, { "epoch": 0.3211782403209115, "grad_norm": 1.5302558216943443, "learning_rate": 4.15438535765583e-05, "loss": 0.666, "num_tokens": 180086530.0, "step": 30105 }, { "epoch": 0.32123158332711, "grad_norm": 0.8849032464823224, "learning_rate": 4.154075237867617e-05, "loss": 0.5811, "num_tokens": 180106103.0, "step": 30110 }, { "epoch": 0.32128492633330846, "grad_norm": 1.2091238715701962, "learning_rate": 4.153765074387467e-05, "loss": 0.6743, "num_tokens": 180134492.0, "step": 30115 }, { "epoch": 0.3213382693395069, "grad_norm": 1.4753552148926272, "learning_rate": 4.153454867225032e-05, "loss": 0.6494, "num_tokens": 180161408.0, "step": 30120 }, { "epoch": 0.32139161234570535, "grad_norm": 0.7392466095023177, "learning_rate": 4.153144616389964e-05, "loss": 0.7166, "num_tokens": 180204860.0, "step": 30125 }, { "epoch": 0.3214449553519038, "grad_norm": 0.8947378906896587, "learning_rate": 4.152834321891918e-05, "loss": 0.4125, "num_tokens": 180231137.0, "step": 30130 }, { "epoch": 0.3214982983581023, "grad_norm": 0.76927005760758, "learning_rate": 4.1525239837405496e-05, "loss": 0.6276, "num_tokens": 180273628.0, "step": 30135 }, { "epoch": 0.3215516413643007, "grad_norm": 0.7095449490988903, "learning_rate": 4.1522136019455146e-05, "loss": 0.6089, "num_tokens": 180311280.0, "step": 30140 }, { "epoch": 0.32160498437049917, "grad_norm": 1.0115567498664413, "learning_rate": 4.1519031765164724e-05, "loss": 0.5005, "num_tokens": 180337351.0, "step": 30145 }, { "epoch": 0.32165832737669764, "grad_norm": 1.3427100243084376, "learning_rate": 4.151592707463085e-05, "loss": 0.6973, "num_tokens": 180360692.0, "step": 30150 }, { "epoch": 0.3217116703828961, "grad_norm": 0.5933530244661899, "learning_rate": 4.151282194795009e-05, "loss": 0.5225, "num_tokens": 180398471.0, "step": 30155 }, { "epoch": 0.3217650133890946, "grad_norm": 1.1325686541156446, "learning_rate": 4.15097163852191e-05, "loss": 0.6763, "num_tokens": 180432858.0, "step": 30160 }, { "epoch": 0.321818356395293, "grad_norm": 0.8764669191264539, "learning_rate": 4.150661038653453e-05, "loss": 0.5505, "num_tokens": 180467582.0, "step": 30165 }, { "epoch": 0.32187169940149146, "grad_norm": 1.1156014024643974, "learning_rate": 4.1503503951993e-05, "loss": 0.4758, "num_tokens": 180483825.0, "step": 30170 }, { "epoch": 0.32192504240768993, "grad_norm": 3.70645910519865, "learning_rate": 4.150039708169119e-05, "loss": 0.7605, "num_tokens": 180507054.0, "step": 30175 }, { "epoch": 0.3219783854138884, "grad_norm": 1.1921736786274553, "learning_rate": 4.149728977572579e-05, "loss": 0.5005, "num_tokens": 180532872.0, "step": 30180 }, { "epoch": 0.3220317284200868, "grad_norm": 1.2474420485013586, "learning_rate": 4.149418203419348e-05, "loss": 0.5668, "num_tokens": 180564950.0, "step": 30185 }, { "epoch": 0.3220850714262853, "grad_norm": 0.9854322652371094, "learning_rate": 4.1491073857190966e-05, "loss": 0.5518, "num_tokens": 180588195.0, "step": 30190 }, { "epoch": 0.32213841443248376, "grad_norm": 1.544088735948882, "learning_rate": 4.1487965244814976e-05, "loss": 0.6131, "num_tokens": 180620231.0, "step": 30195 }, { "epoch": 0.3221917574386822, "grad_norm": 0.7548663683596404, "learning_rate": 4.148485619716224e-05, "loss": 0.5245, "num_tokens": 180649272.0, "step": 30200 }, { "epoch": 0.3222451004448807, "grad_norm": 0.9409235465956421, "learning_rate": 4.1481746714329494e-05, "loss": 0.5801, "num_tokens": 180679270.0, "step": 30205 }, { "epoch": 0.3222984434510791, "grad_norm": 0.7484766839513486, "learning_rate": 4.1478636796413525e-05, "loss": 0.6064, "num_tokens": 180708135.0, "step": 30210 }, { "epoch": 0.3223517864572776, "grad_norm": 1.685944195844141, "learning_rate": 4.1475526443511083e-05, "loss": 0.5776, "num_tokens": 180733321.0, "step": 30215 }, { "epoch": 0.32240512946347605, "grad_norm": 1.342506826735561, "learning_rate": 4.147241565571896e-05, "loss": 0.4933, "num_tokens": 180760279.0, "step": 30220 }, { "epoch": 0.3224584724696745, "grad_norm": 1.0022025772152523, "learning_rate": 4.146930443313398e-05, "loss": 0.5279, "num_tokens": 180800642.0, "step": 30225 }, { "epoch": 0.32251181547587293, "grad_norm": 1.0318804649458884, "learning_rate": 4.146619277585293e-05, "loss": 0.658, "num_tokens": 180829862.0, "step": 30230 }, { "epoch": 0.3225651584820714, "grad_norm": 1.1809639011316573, "learning_rate": 4.1463080683972645e-05, "loss": 0.5933, "num_tokens": 180848480.0, "step": 30235 }, { "epoch": 0.32261850148826987, "grad_norm": 0.8836368669211214, "learning_rate": 4.145996815758997e-05, "loss": 0.5935, "num_tokens": 180865573.0, "step": 30240 }, { "epoch": 0.32267184449446834, "grad_norm": 0.698020650243835, "learning_rate": 4.1456855196801766e-05, "loss": 0.5125, "num_tokens": 180895344.0, "step": 30245 }, { "epoch": 0.3227251875006668, "grad_norm": 0.9751711953885264, "learning_rate": 4.1453741801704885e-05, "loss": 0.6287, "num_tokens": 180918668.0, "step": 30250 }, { "epoch": 0.3227785305068652, "grad_norm": 1.3031331075302506, "learning_rate": 4.1450627972396236e-05, "loss": 0.5484, "num_tokens": 180937034.0, "step": 30255 }, { "epoch": 0.3228318735130637, "grad_norm": 1.0284077155674036, "learning_rate": 4.144751370897269e-05, "loss": 0.5577, "num_tokens": 180967473.0, "step": 30260 }, { "epoch": 0.32288521651926216, "grad_norm": 1.192836145192834, "learning_rate": 4.144439901153117e-05, "loss": 0.6541, "num_tokens": 180999112.0, "step": 30265 }, { "epoch": 0.32293855952546063, "grad_norm": 1.328797128700664, "learning_rate": 4.14412838801686e-05, "loss": 0.6975, "num_tokens": 181037082.0, "step": 30270 }, { "epoch": 0.32299190253165905, "grad_norm": 0.9041359179047725, "learning_rate": 4.14381683149819e-05, "loss": 0.4665, "num_tokens": 181069994.0, "step": 30275 }, { "epoch": 0.3230452455378575, "grad_norm": 1.0954862146598938, "learning_rate": 4.143505231606804e-05, "loss": 0.6246, "num_tokens": 181105659.0, "step": 30280 }, { "epoch": 0.323098588544056, "grad_norm": 1.198658355876668, "learning_rate": 4.143193588352397e-05, "loss": 0.5361, "num_tokens": 181121972.0, "step": 30285 }, { "epoch": 0.32315193155025446, "grad_norm": 0.9140009782341524, "learning_rate": 4.142881901744669e-05, "loss": 0.5889, "num_tokens": 181161122.0, "step": 30290 }, { "epoch": 0.3232052745564529, "grad_norm": 0.6294731335352944, "learning_rate": 4.1425701717933154e-05, "loss": 0.6298, "num_tokens": 181200374.0, "step": 30295 }, { "epoch": 0.32325861756265134, "grad_norm": 1.025905824910468, "learning_rate": 4.1422583985080384e-05, "loss": 0.4979, "num_tokens": 181238558.0, "step": 30300 }, { "epoch": 0.3233119605688498, "grad_norm": 1.3116067636185533, "learning_rate": 4.1419465818985406e-05, "loss": 0.6985, "num_tokens": 181291347.0, "step": 30305 }, { "epoch": 0.3233653035750483, "grad_norm": 0.959821527955983, "learning_rate": 4.1416347219745236e-05, "loss": 0.5546, "num_tokens": 181331212.0, "step": 30310 }, { "epoch": 0.32341864658124675, "grad_norm": 0.9242202443947317, "learning_rate": 4.141322818745693e-05, "loss": 0.5835, "num_tokens": 181380601.0, "step": 30315 }, { "epoch": 0.32347198958744516, "grad_norm": 1.1905999036566794, "learning_rate": 4.141010872221755e-05, "loss": 0.6628, "num_tokens": 181398221.0, "step": 30320 }, { "epoch": 0.32352533259364363, "grad_norm": 0.9532196003693814, "learning_rate": 4.140698882412414e-05, "loss": 0.5541, "num_tokens": 181429197.0, "step": 30325 }, { "epoch": 0.3235786755998421, "grad_norm": 0.9369362244602406, "learning_rate": 4.1403868493273815e-05, "loss": 0.5482, "num_tokens": 181452501.0, "step": 30330 }, { "epoch": 0.3236320186060406, "grad_norm": 0.9539640079851829, "learning_rate": 4.140074772976366e-05, "loss": 0.6835, "num_tokens": 181495276.0, "step": 30335 }, { "epoch": 0.32368536161223904, "grad_norm": 1.2656199357959035, "learning_rate": 4.13976265336908e-05, "loss": 0.5588, "num_tokens": 181534134.0, "step": 30340 }, { "epoch": 0.32373870461843746, "grad_norm": 0.7463618800020434, "learning_rate": 4.139450490515234e-05, "loss": 0.4527, "num_tokens": 181563308.0, "step": 30345 }, { "epoch": 0.3237920476246359, "grad_norm": 2.216105249355336, "learning_rate": 4.139138284424542e-05, "loss": 0.6264, "num_tokens": 181595660.0, "step": 30350 }, { "epoch": 0.3238453906308344, "grad_norm": 1.60384149582859, "learning_rate": 4.138826035106721e-05, "loss": 0.6649, "num_tokens": 181612040.0, "step": 30355 }, { "epoch": 0.32389873363703287, "grad_norm": 0.9204997257932652, "learning_rate": 4.1385137425714855e-05, "loss": 0.6541, "num_tokens": 181650677.0, "step": 30360 }, { "epoch": 0.3239520766432313, "grad_norm": 0.7313068231502956, "learning_rate": 4.138201406828555e-05, "loss": 0.5239, "num_tokens": 181676577.0, "step": 30365 }, { "epoch": 0.32400541964942975, "grad_norm": 1.0933844104648365, "learning_rate": 4.137889027887648e-05, "loss": 0.4824, "num_tokens": 181708798.0, "step": 30370 }, { "epoch": 0.3240587626556282, "grad_norm": 0.7669627577354537, "learning_rate": 4.1375766057584855e-05, "loss": 0.6238, "num_tokens": 181726106.0, "step": 30375 }, { "epoch": 0.3241121056618267, "grad_norm": 0.9479665840714301, "learning_rate": 4.137264140450789e-05, "loss": 0.4613, "num_tokens": 181744518.0, "step": 30380 }, { "epoch": 0.32416544866802516, "grad_norm": 1.5936402727261765, "learning_rate": 4.1369516319742816e-05, "loss": 0.5655, "num_tokens": 181782444.0, "step": 30385 }, { "epoch": 0.32421879167422357, "grad_norm": 0.7916824982375116, "learning_rate": 4.1366390803386895e-05, "loss": 0.5279, "num_tokens": 181807660.0, "step": 30390 }, { "epoch": 0.32427213468042204, "grad_norm": 0.6425447960809157, "learning_rate": 4.136326485553737e-05, "loss": 0.4371, "num_tokens": 181834562.0, "step": 30395 }, { "epoch": 0.3243254776866205, "grad_norm": 1.928617899665972, "learning_rate": 4.136013847629151e-05, "loss": 0.6816, "num_tokens": 181861425.0, "step": 30400 }, { "epoch": 0.324378820692819, "grad_norm": 1.197550453059307, "learning_rate": 4.135701166574661e-05, "loss": 0.5429, "num_tokens": 181887530.0, "step": 30405 }, { "epoch": 0.3244321636990174, "grad_norm": 1.0397202769481269, "learning_rate": 4.135388442399998e-05, "loss": 0.5931, "num_tokens": 181914436.0, "step": 30410 }, { "epoch": 0.32448550670521586, "grad_norm": 0.9633676101316281, "learning_rate": 4.135075675114892e-05, "loss": 0.4673, "num_tokens": 181937246.0, "step": 30415 }, { "epoch": 0.32453884971141433, "grad_norm": 1.1965795205635759, "learning_rate": 4.134762864729077e-05, "loss": 0.4526, "num_tokens": 181960773.0, "step": 30420 }, { "epoch": 0.3245921927176128, "grad_norm": 0.7352574325136476, "learning_rate": 4.134450011252284e-05, "loss": 0.5985, "num_tokens": 182003691.0, "step": 30425 }, { "epoch": 0.3246455357238113, "grad_norm": 2.521333890896595, "learning_rate": 4.1341371146942514e-05, "loss": 0.5031, "num_tokens": 182032133.0, "step": 30430 }, { "epoch": 0.3246988787300097, "grad_norm": 1.4941591832585759, "learning_rate": 4.133824175064715e-05, "loss": 0.5135, "num_tokens": 182063639.0, "step": 30435 }, { "epoch": 0.32475222173620816, "grad_norm": 1.0841054908838388, "learning_rate": 4.1335111923734125e-05, "loss": 0.4553, "num_tokens": 182087079.0, "step": 30440 }, { "epoch": 0.3248055647424066, "grad_norm": 1.2337449659428041, "learning_rate": 4.1331981666300834e-05, "loss": 0.6697, "num_tokens": 182119044.0, "step": 30445 }, { "epoch": 0.3248589077486051, "grad_norm": 2.0623986171506155, "learning_rate": 4.132885097844469e-05, "loss": 0.5292, "num_tokens": 182141175.0, "step": 30450 }, { "epoch": 0.3249122507548035, "grad_norm": 0.9476186823433291, "learning_rate": 4.13257198602631e-05, "loss": 0.7046, "num_tokens": 182191200.0, "step": 30455 }, { "epoch": 0.324965593761002, "grad_norm": 0.7475618286392572, "learning_rate": 4.132258831185351e-05, "loss": 0.5083, "num_tokens": 182227226.0, "step": 30460 }, { "epoch": 0.32501893676720045, "grad_norm": 0.8207018285233157, "learning_rate": 4.1319456333313376e-05, "loss": 0.4535, "num_tokens": 182250009.0, "step": 30465 }, { "epoch": 0.3250722797733989, "grad_norm": 0.9215699282756475, "learning_rate": 4.1316323924740135e-05, "loss": 0.5646, "num_tokens": 182272293.0, "step": 30470 }, { "epoch": 0.3251256227795974, "grad_norm": 0.8828271967365903, "learning_rate": 4.131319108623128e-05, "loss": 0.5068, "num_tokens": 182298451.0, "step": 30475 }, { "epoch": 0.3251789657857958, "grad_norm": 2.016679632884111, "learning_rate": 4.1310057817884285e-05, "loss": 0.6178, "num_tokens": 182320409.0, "step": 30480 }, { "epoch": 0.3252323087919943, "grad_norm": 1.5331458940838616, "learning_rate": 4.130692411979666e-05, "loss": 0.6856, "num_tokens": 182344015.0, "step": 30485 }, { "epoch": 0.32528565179819274, "grad_norm": 0.8857596905629921, "learning_rate": 4.130378999206592e-05, "loss": 0.6116, "num_tokens": 182377207.0, "step": 30490 }, { "epoch": 0.3253389948043912, "grad_norm": 1.0667075545007036, "learning_rate": 4.130065543478958e-05, "loss": 0.5252, "num_tokens": 182405488.0, "step": 30495 }, { "epoch": 0.3253923378105896, "grad_norm": 1.576664286542414, "learning_rate": 4.12975204480652e-05, "loss": 0.567, "num_tokens": 182432179.0, "step": 30500 }, { "epoch": 0.3254456808167881, "grad_norm": 1.0605927329747435, "learning_rate": 4.129438503199032e-05, "loss": 0.5612, "num_tokens": 182469997.0, "step": 30505 }, { "epoch": 0.32549902382298657, "grad_norm": 0.7455731824595736, "learning_rate": 4.129124918666252e-05, "loss": 0.5276, "num_tokens": 182509576.0, "step": 30510 }, { "epoch": 0.32555236682918504, "grad_norm": 1.0367331901159536, "learning_rate": 4.1288112912179364e-05, "loss": 0.6078, "num_tokens": 182533887.0, "step": 30515 }, { "epoch": 0.3256057098353835, "grad_norm": 0.8859834654903117, "learning_rate": 4.1284976208638455e-05, "loss": 0.5483, "num_tokens": 182559176.0, "step": 30520 }, { "epoch": 0.3256590528415819, "grad_norm": 1.1298510701658673, "learning_rate": 4.128183907613741e-05, "loss": 0.6013, "num_tokens": 182598227.0, "step": 30525 }, { "epoch": 0.3257123958477804, "grad_norm": 1.4148458392301821, "learning_rate": 4.127870151477383e-05, "loss": 0.5784, "num_tokens": 182617525.0, "step": 30530 }, { "epoch": 0.32576573885397886, "grad_norm": 0.7030379765812199, "learning_rate": 4.1275563524645364e-05, "loss": 0.6196, "num_tokens": 182666859.0, "step": 30535 }, { "epoch": 0.32581908186017733, "grad_norm": 0.7672920853673922, "learning_rate": 4.1272425105849665e-05, "loss": 0.4487, "num_tokens": 182688709.0, "step": 30540 }, { "epoch": 0.32587242486637574, "grad_norm": 0.8447094760553067, "learning_rate": 4.126928625848438e-05, "loss": 0.5853, "num_tokens": 182734861.0, "step": 30545 }, { "epoch": 0.3259257678725742, "grad_norm": 1.0307771975318196, "learning_rate": 4.126614698264719e-05, "loss": 0.8723, "num_tokens": 182763459.0, "step": 30550 }, { "epoch": 0.3259791108787727, "grad_norm": 0.9107495686986709, "learning_rate": 4.126300727843579e-05, "loss": 0.5855, "num_tokens": 182787338.0, "step": 30555 }, { "epoch": 0.32603245388497115, "grad_norm": 2.6718078359464634, "learning_rate": 4.125986714594786e-05, "loss": 0.4594, "num_tokens": 182799413.0, "step": 30560 }, { "epoch": 0.3260857968911696, "grad_norm": 1.7036834063822843, "learning_rate": 4.125672658528114e-05, "loss": 0.5464, "num_tokens": 182828046.0, "step": 30565 }, { "epoch": 0.32613913989736804, "grad_norm": 1.0770254813043827, "learning_rate": 4.125358559653334e-05, "loss": 0.574, "num_tokens": 182852598.0, "step": 30570 }, { "epoch": 0.3261924829035665, "grad_norm": 0.8954930968413554, "learning_rate": 4.12504441798022e-05, "loss": 0.5537, "num_tokens": 182875123.0, "step": 30575 }, { "epoch": 0.326245825909765, "grad_norm": 1.409289937168653, "learning_rate": 4.124730233518549e-05, "loss": 0.6385, "num_tokens": 182892178.0, "step": 30580 }, { "epoch": 0.32629916891596344, "grad_norm": 0.8441573656547926, "learning_rate": 4.1244160062780975e-05, "loss": 0.5862, "num_tokens": 182932952.0, "step": 30585 }, { "epoch": 0.32635251192216186, "grad_norm": 0.9905000257176386, "learning_rate": 4.1241017362686416e-05, "loss": 0.5054, "num_tokens": 182965960.0, "step": 30590 }, { "epoch": 0.32640585492836033, "grad_norm": 0.6797429821163797, "learning_rate": 4.123787423499963e-05, "loss": 0.5581, "num_tokens": 183004510.0, "step": 30595 }, { "epoch": 0.3264591979345588, "grad_norm": 0.9284557973606798, "learning_rate": 4.123473067981842e-05, "loss": 0.4896, "num_tokens": 183026678.0, "step": 30600 }, { "epoch": 0.32651254094075727, "grad_norm": 2.1279788438302276, "learning_rate": 4.12315866972406e-05, "loss": 0.4966, "num_tokens": 183048351.0, "step": 30605 }, { "epoch": 0.32656588394695574, "grad_norm": 1.1151027081789304, "learning_rate": 4.1228442287364e-05, "loss": 0.6769, "num_tokens": 183071771.0, "step": 30610 }, { "epoch": 0.32661922695315415, "grad_norm": 1.3716161609056818, "learning_rate": 4.122529745028648e-05, "loss": 0.5536, "num_tokens": 183101971.0, "step": 30615 }, { "epoch": 0.3266725699593526, "grad_norm": 1.1979743436622152, "learning_rate": 4.122215218610589e-05, "loss": 0.4695, "num_tokens": 183127558.0, "step": 30620 }, { "epoch": 0.3267259129655511, "grad_norm": 1.0395476443029257, "learning_rate": 4.121900649492012e-05, "loss": 0.5805, "num_tokens": 183155027.0, "step": 30625 }, { "epoch": 0.32677925597174956, "grad_norm": 0.9359445822372092, "learning_rate": 4.1215860376827045e-05, "loss": 0.6845, "num_tokens": 183195937.0, "step": 30630 }, { "epoch": 0.326832598977948, "grad_norm": 1.4821883834114853, "learning_rate": 4.121271383192457e-05, "loss": 0.6092, "num_tokens": 183219903.0, "step": 30635 }, { "epoch": 0.32688594198414644, "grad_norm": 1.1756848637932948, "learning_rate": 4.120956686031061e-05, "loss": 0.5262, "num_tokens": 183249366.0, "step": 30640 }, { "epoch": 0.3269392849903449, "grad_norm": 2.0685134512506047, "learning_rate": 4.120641946208309e-05, "loss": 0.6971, "num_tokens": 183265505.0, "step": 30645 }, { "epoch": 0.3269926279965434, "grad_norm": 0.7402692517205907, "learning_rate": 4.120327163733993e-05, "loss": 0.6084, "num_tokens": 183314797.0, "step": 30650 }, { "epoch": 0.32704597100274185, "grad_norm": 1.0673364811682367, "learning_rate": 4.120012338617912e-05, "loss": 0.6035, "num_tokens": 183343425.0, "step": 30655 }, { "epoch": 0.32709931400894027, "grad_norm": 1.087852460857967, "learning_rate": 4.119697470869861e-05, "loss": 0.4548, "num_tokens": 183362134.0, "step": 30660 }, { "epoch": 0.32715265701513874, "grad_norm": 1.0375081009888738, "learning_rate": 4.119382560499638e-05, "loss": 0.5369, "num_tokens": 183384393.0, "step": 30665 }, { "epoch": 0.3272060000213372, "grad_norm": 0.7587603358573932, "learning_rate": 4.1190676075170426e-05, "loss": 0.6184, "num_tokens": 183417899.0, "step": 30670 }, { "epoch": 0.3272593430275357, "grad_norm": 0.7284521370106328, "learning_rate": 4.1187526119318756e-05, "loss": 0.5978, "num_tokens": 183450613.0, "step": 30675 }, { "epoch": 0.3273126860337341, "grad_norm": 1.4309647924192381, "learning_rate": 4.118437573753938e-05, "loss": 0.5454, "num_tokens": 183475152.0, "step": 30680 }, { "epoch": 0.32736602903993256, "grad_norm": 0.9742739764490281, "learning_rate": 4.118122492993035e-05, "loss": 0.5154, "num_tokens": 183495812.0, "step": 30685 }, { "epoch": 0.32741937204613103, "grad_norm": 1.7848739236755151, "learning_rate": 4.11780736965897e-05, "loss": 0.5266, "num_tokens": 183512898.0, "step": 30690 }, { "epoch": 0.3274727150523295, "grad_norm": 0.7915864964073154, "learning_rate": 4.1174922037615484e-05, "loss": 0.5061, "num_tokens": 183534683.0, "step": 30695 }, { "epoch": 0.32752605805852797, "grad_norm": 1.453996804520476, "learning_rate": 4.11717699531058e-05, "loss": 0.6077, "num_tokens": 183581386.0, "step": 30700 }, { "epoch": 0.3275794010647264, "grad_norm": 0.6245212979108001, "learning_rate": 4.1168617443158704e-05, "loss": 0.6244, "num_tokens": 183614195.0, "step": 30705 }, { "epoch": 0.32763274407092485, "grad_norm": 0.7429671354614246, "learning_rate": 4.116546450787231e-05, "loss": 0.5317, "num_tokens": 183660608.0, "step": 30710 }, { "epoch": 0.3276860870771233, "grad_norm": 0.7576868445939187, "learning_rate": 4.116231114734473e-05, "loss": 0.8096, "num_tokens": 183703288.0, "step": 30715 }, { "epoch": 0.3277394300833218, "grad_norm": 1.0073544723939607, "learning_rate": 4.11591573616741e-05, "loss": 0.5855, "num_tokens": 183746129.0, "step": 30720 }, { "epoch": 0.3277927730895202, "grad_norm": 0.9333158646287485, "learning_rate": 4.1156003150958536e-05, "loss": 0.5909, "num_tokens": 183770839.0, "step": 30725 }, { "epoch": 0.3278461160957187, "grad_norm": 0.9397265897003376, "learning_rate": 4.115284851529621e-05, "loss": 0.5023, "num_tokens": 183793883.0, "step": 30730 }, { "epoch": 0.32789945910191715, "grad_norm": 0.8554461867481193, "learning_rate": 4.114969345478529e-05, "loss": 0.6731, "num_tokens": 183824102.0, "step": 30735 }, { "epoch": 0.3279528021081156, "grad_norm": 1.0199202380963885, "learning_rate": 4.114653796952393e-05, "loss": 0.5862, "num_tokens": 183849351.0, "step": 30740 }, { "epoch": 0.3280061451143141, "grad_norm": 1.0309588006961548, "learning_rate": 4.114338205961035e-05, "loss": 0.5416, "num_tokens": 183890326.0, "step": 30745 }, { "epoch": 0.3280594881205125, "grad_norm": 2.2092784638631446, "learning_rate": 4.114022572514275e-05, "loss": 0.4852, "num_tokens": 183913070.0, "step": 30750 }, { "epoch": 0.32811283112671097, "grad_norm": 1.7969596973085287, "learning_rate": 4.113706896621933e-05, "loss": 0.6094, "num_tokens": 183932484.0, "step": 30755 }, { "epoch": 0.32816617413290944, "grad_norm": 0.8575671293369628, "learning_rate": 4.1133911782938336e-05, "loss": 0.4906, "num_tokens": 183958415.0, "step": 30760 }, { "epoch": 0.3282195171391079, "grad_norm": 1.352263835348938, "learning_rate": 4.113075417539803e-05, "loss": 0.4287, "num_tokens": 183976762.0, "step": 30765 }, { "epoch": 0.3282728601453063, "grad_norm": 0.9611705636982153, "learning_rate": 4.112759614369664e-05, "loss": 0.6028, "num_tokens": 184017458.0, "step": 30770 }, { "epoch": 0.3283262031515048, "grad_norm": 1.032465605986521, "learning_rate": 4.112443768793244e-05, "loss": 0.6166, "num_tokens": 184048949.0, "step": 30775 }, { "epoch": 0.32837954615770326, "grad_norm": 0.9839515459981979, "learning_rate": 4.112127880820374e-05, "loss": 0.5502, "num_tokens": 184076013.0, "step": 30780 }, { "epoch": 0.32843288916390173, "grad_norm": 1.0083050340229742, "learning_rate": 4.111811950460881e-05, "loss": 0.6031, "num_tokens": 184101277.0, "step": 30785 }, { "epoch": 0.3284862321701002, "grad_norm": 1.088876829757983, "learning_rate": 4.1114959777245994e-05, "loss": 0.574, "num_tokens": 184145242.0, "step": 30790 }, { "epoch": 0.3285395751762986, "grad_norm": 1.6778860717056934, "learning_rate": 4.111179962621358e-05, "loss": 0.4351, "num_tokens": 184162208.0, "step": 30795 }, { "epoch": 0.3285929181824971, "grad_norm": 1.108393855787753, "learning_rate": 4.1108639051609915e-05, "loss": 0.54, "num_tokens": 184183364.0, "step": 30800 }, { "epoch": 0.32864626118869555, "grad_norm": 0.8897410173960473, "learning_rate": 4.1105478053533364e-05, "loss": 0.5966, "num_tokens": 184211354.0, "step": 30805 }, { "epoch": 0.328699604194894, "grad_norm": 0.8643620428975541, "learning_rate": 4.110231663208229e-05, "loss": 0.6317, "num_tokens": 184252799.0, "step": 30810 }, { "epoch": 0.32875294720109244, "grad_norm": 0.9837562873862402, "learning_rate": 4.1099154787355046e-05, "loss": 0.5865, "num_tokens": 184285520.0, "step": 30815 }, { "epoch": 0.3288062902072909, "grad_norm": 0.9033449691620338, "learning_rate": 4.1095992519450055e-05, "loss": 0.6296, "num_tokens": 184331519.0, "step": 30820 }, { "epoch": 0.3288596332134894, "grad_norm": 0.9957882529322342, "learning_rate": 4.109282982846569e-05, "loss": 0.5476, "num_tokens": 184357874.0, "step": 30825 }, { "epoch": 0.32891297621968785, "grad_norm": 0.6882256737016013, "learning_rate": 4.1089666714500386e-05, "loss": 0.4667, "num_tokens": 184388254.0, "step": 30830 }, { "epoch": 0.3289663192258863, "grad_norm": 0.7655789358359296, "learning_rate": 4.108650317765257e-05, "loss": 0.5962, "num_tokens": 184422418.0, "step": 30835 }, { "epoch": 0.32901966223208473, "grad_norm": 1.0395587748229351, "learning_rate": 4.1083339218020684e-05, "loss": 0.6189, "num_tokens": 184447466.0, "step": 30840 }, { "epoch": 0.3290730052382832, "grad_norm": 1.1010818680390981, "learning_rate": 4.108017483570318e-05, "loss": 0.495, "num_tokens": 184463423.0, "step": 30845 }, { "epoch": 0.32912634824448167, "grad_norm": 1.295959673018763, "learning_rate": 4.107701003079853e-05, "loss": 0.4884, "num_tokens": 184496148.0, "step": 30850 }, { "epoch": 0.32917969125068014, "grad_norm": 0.7659085691889272, "learning_rate": 4.1073844803405214e-05, "loss": 0.6422, "num_tokens": 184551606.0, "step": 30855 }, { "epoch": 0.32923303425687855, "grad_norm": 1.2432768899183848, "learning_rate": 4.1070679153621726e-05, "loss": 0.6144, "num_tokens": 184589659.0, "step": 30860 }, { "epoch": 0.329286377263077, "grad_norm": 1.289971105005155, "learning_rate": 4.106751308154659e-05, "loss": 0.5352, "num_tokens": 184609918.0, "step": 30865 }, { "epoch": 0.3293397202692755, "grad_norm": 0.9503266556187194, "learning_rate": 4.1064346587278305e-05, "loss": 0.4724, "num_tokens": 184643000.0, "step": 30870 }, { "epoch": 0.32939306327547396, "grad_norm": 0.9996950176900165, "learning_rate": 4.106117967091542e-05, "loss": 0.4914, "num_tokens": 184673240.0, "step": 30875 }, { "epoch": 0.32944640628167243, "grad_norm": 0.9475793033432568, "learning_rate": 4.105801233255647e-05, "loss": 0.5869, "num_tokens": 184709079.0, "step": 30880 }, { "epoch": 0.32949974928787085, "grad_norm": 0.9480793369349996, "learning_rate": 4.105484457230004e-05, "loss": 0.6585, "num_tokens": 184759010.0, "step": 30885 }, { "epoch": 0.3295530922940693, "grad_norm": 1.0575387298242693, "learning_rate": 4.105167639024468e-05, "loss": 0.5918, "num_tokens": 184782698.0, "step": 30890 }, { "epoch": 0.3296064353002678, "grad_norm": 1.2070450797865075, "learning_rate": 4.104850778648899e-05, "loss": 0.6015, "num_tokens": 184813641.0, "step": 30895 }, { "epoch": 0.32965977830646626, "grad_norm": 0.8587040016925664, "learning_rate": 4.1045338761131564e-05, "loss": 0.4831, "num_tokens": 184836840.0, "step": 30900 }, { "epoch": 0.32971312131266467, "grad_norm": 1.1950659048199028, "learning_rate": 4.104216931427102e-05, "loss": 0.6878, "num_tokens": 184868795.0, "step": 30905 }, { "epoch": 0.32976646431886314, "grad_norm": 2.444758957481425, "learning_rate": 4.1038999446005986e-05, "loss": 0.5349, "num_tokens": 184899954.0, "step": 30910 }, { "epoch": 0.3298198073250616, "grad_norm": 1.0186893107135753, "learning_rate": 4.10358291564351e-05, "loss": 0.6449, "num_tokens": 184938847.0, "step": 30915 }, { "epoch": 0.3298731503312601, "grad_norm": 1.060374721691971, "learning_rate": 4.103265844565701e-05, "loss": 0.6554, "num_tokens": 184969809.0, "step": 30920 }, { "epoch": 0.32992649333745855, "grad_norm": 0.712279214962151, "learning_rate": 4.1029487313770394e-05, "loss": 0.5304, "num_tokens": 184996938.0, "step": 30925 }, { "epoch": 0.32997983634365696, "grad_norm": 0.8105199802269216, "learning_rate": 4.1026315760873906e-05, "loss": 0.6399, "num_tokens": 185039500.0, "step": 30930 }, { "epoch": 0.33003317934985543, "grad_norm": 3.587972189566684, "learning_rate": 4.102314378706627e-05, "loss": 0.6518, "num_tokens": 185064845.0, "step": 30935 }, { "epoch": 0.3300865223560539, "grad_norm": 0.6537792129015536, "learning_rate": 4.101997139244617e-05, "loss": 0.5141, "num_tokens": 185097034.0, "step": 30940 }, { "epoch": 0.33013986536225237, "grad_norm": 1.18112923005208, "learning_rate": 4.101679857711234e-05, "loss": 0.5353, "num_tokens": 185124060.0, "step": 30945 }, { "epoch": 0.3301932083684508, "grad_norm": 0.6904038744606484, "learning_rate": 4.101362534116349e-05, "loss": 0.6336, "num_tokens": 185159621.0, "step": 30950 }, { "epoch": 0.33024655137464926, "grad_norm": 0.9473071892760959, "learning_rate": 4.101045168469839e-05, "loss": 0.5548, "num_tokens": 185182609.0, "step": 30955 }, { "epoch": 0.3302998943808477, "grad_norm": 1.5104988755586615, "learning_rate": 4.100727760781577e-05, "loss": 0.6866, "num_tokens": 185213495.0, "step": 30960 }, { "epoch": 0.3303532373870462, "grad_norm": 1.519806183527104, "learning_rate": 4.100410311061443e-05, "loss": 0.5934, "num_tokens": 185239593.0, "step": 30965 }, { "epoch": 0.33040658039324466, "grad_norm": 0.906469383570487, "learning_rate": 4.100092819319313e-05, "loss": 0.5434, "num_tokens": 185252845.0, "step": 30970 }, { "epoch": 0.3304599233994431, "grad_norm": 2.454742248290581, "learning_rate": 4.099775285565068e-05, "loss": 0.5843, "num_tokens": 185280123.0, "step": 30975 }, { "epoch": 0.33051326640564155, "grad_norm": 0.9338430702827734, "learning_rate": 4.099457709808589e-05, "loss": 0.7143, "num_tokens": 185305325.0, "step": 30980 }, { "epoch": 0.33056660941184, "grad_norm": 0.8385875798510347, "learning_rate": 4.099140092059758e-05, "loss": 0.6328, "num_tokens": 185337581.0, "step": 30985 }, { "epoch": 0.3306199524180385, "grad_norm": 1.1355023267170676, "learning_rate": 4.098822432328457e-05, "loss": 0.6141, "num_tokens": 185370747.0, "step": 30990 }, { "epoch": 0.3306732954242369, "grad_norm": 1.0452567451589132, "learning_rate": 4.098504730624574e-05, "loss": 0.5958, "num_tokens": 185428238.0, "step": 30995 }, { "epoch": 0.33072663843043537, "grad_norm": 2.29100516979131, "learning_rate": 4.098186986957994e-05, "loss": 0.8494, "num_tokens": 185454226.0, "step": 31000 }, { "epoch": 0.33077998143663384, "grad_norm": 1.0212054384782419, "learning_rate": 4.097869201338602e-05, "loss": 0.5144, "num_tokens": 185490022.0, "step": 31005 }, { "epoch": 0.3308333244428323, "grad_norm": 0.984609872957891, "learning_rate": 4.097551373776291e-05, "loss": 0.4933, "num_tokens": 185507564.0, "step": 31010 }, { "epoch": 0.3308866674490308, "grad_norm": 0.9692657067113928, "learning_rate": 4.097233504280948e-05, "loss": 0.6725, "num_tokens": 185533954.0, "step": 31015 }, { "epoch": 0.3309400104552292, "grad_norm": 1.2948023644914766, "learning_rate": 4.0969155928624674e-05, "loss": 0.6585, "num_tokens": 185559233.0, "step": 31020 }, { "epoch": 0.33099335346142766, "grad_norm": 0.9757632291307922, "learning_rate": 4.096597639530739e-05, "loss": 0.7721, "num_tokens": 185601261.0, "step": 31025 }, { "epoch": 0.33104669646762613, "grad_norm": 1.0544734127010782, "learning_rate": 4.096279644295658e-05, "loss": 0.5586, "num_tokens": 185617580.0, "step": 31030 }, { "epoch": 0.3311000394738246, "grad_norm": 1.5724808910761439, "learning_rate": 4.09596160716712e-05, "loss": 0.7012, "num_tokens": 185644142.0, "step": 31035 }, { "epoch": 0.331153382480023, "grad_norm": 1.1762439687760164, "learning_rate": 4.0956435281550223e-05, "loss": 0.607, "num_tokens": 185690559.0, "step": 31040 }, { "epoch": 0.3312067254862215, "grad_norm": 1.110099547387415, "learning_rate": 4.095325407269261e-05, "loss": 0.6446, "num_tokens": 185720260.0, "step": 31045 }, { "epoch": 0.33126006849241996, "grad_norm": 0.6487836710869623, "learning_rate": 4.0950072445197356e-05, "loss": 0.7932, "num_tokens": 185760632.0, "step": 31050 }, { "epoch": 0.3313134114986184, "grad_norm": 1.6931546499524106, "learning_rate": 4.094689039916349e-05, "loss": 0.5429, "num_tokens": 185788310.0, "step": 31055 }, { "epoch": 0.3313667545048169, "grad_norm": 3.4397420262595815, "learning_rate": 4.0943707934690013e-05, "loss": 0.6081, "num_tokens": 185819133.0, "step": 31060 }, { "epoch": 0.3314200975110153, "grad_norm": 1.3046882193082276, "learning_rate": 4.094052505187596e-05, "loss": 0.7278, "num_tokens": 185851307.0, "step": 31065 }, { "epoch": 0.3314734405172138, "grad_norm": 1.2023532973072848, "learning_rate": 4.093734175082036e-05, "loss": 0.6342, "num_tokens": 185896045.0, "step": 31070 }, { "epoch": 0.33152678352341225, "grad_norm": 0.6936926755171204, "learning_rate": 4.093415803162231e-05, "loss": 0.4839, "num_tokens": 185938228.0, "step": 31075 }, { "epoch": 0.3315801265296107, "grad_norm": 0.7235941216192947, "learning_rate": 4.093097389438083e-05, "loss": 0.6427, "num_tokens": 185971214.0, "step": 31080 }, { "epoch": 0.33163346953580913, "grad_norm": 1.1674387291824277, "learning_rate": 4.092778933919505e-05, "loss": 0.6158, "num_tokens": 186014564.0, "step": 31085 }, { "epoch": 0.3316868125420076, "grad_norm": 0.7214009717672337, "learning_rate": 4.0924604366164044e-05, "loss": 0.5283, "num_tokens": 186044289.0, "step": 31090 }, { "epoch": 0.3317401555482061, "grad_norm": 0.8029128958448744, "learning_rate": 4.092141897538692e-05, "loss": 0.4635, "num_tokens": 186068903.0, "step": 31095 }, { "epoch": 0.33179349855440454, "grad_norm": 1.0631728332616435, "learning_rate": 4.091823316696282e-05, "loss": 0.5054, "num_tokens": 186091327.0, "step": 31100 }, { "epoch": 0.331846841560603, "grad_norm": 1.04969689823652, "learning_rate": 4.091504694099085e-05, "loss": 0.5697, "num_tokens": 186128740.0, "step": 31105 }, { "epoch": 0.3319001845668014, "grad_norm": 1.6514081151111395, "learning_rate": 4.091186029757017e-05, "loss": 0.6527, "num_tokens": 186143132.0, "step": 31110 }, { "epoch": 0.3319535275729999, "grad_norm": 0.765835985854087, "learning_rate": 4.090867323679996e-05, "loss": 0.5244, "num_tokens": 186183003.0, "step": 31115 }, { "epoch": 0.33200687057919837, "grad_norm": 0.7659856174701989, "learning_rate": 4.090548575877938e-05, "loss": 0.637, "num_tokens": 186227303.0, "step": 31120 }, { "epoch": 0.33206021358539684, "grad_norm": 0.9733599628138305, "learning_rate": 4.090229786360761e-05, "loss": 0.6123, "num_tokens": 186251186.0, "step": 31125 }, { "epoch": 0.33211355659159525, "grad_norm": 1.271625959280192, "learning_rate": 4.089910955138387e-05, "loss": 0.5491, "num_tokens": 186290811.0, "step": 31130 }, { "epoch": 0.3321668995977937, "grad_norm": 0.8100231368326535, "learning_rate": 4.089592082220736e-05, "loss": 0.5169, "num_tokens": 186315728.0, "step": 31135 }, { "epoch": 0.3322202426039922, "grad_norm": 1.3825746280243112, "learning_rate": 4.08927316761773e-05, "loss": 0.5504, "num_tokens": 186351897.0, "step": 31140 }, { "epoch": 0.33227358561019066, "grad_norm": 0.662429781585069, "learning_rate": 4.0889542113392955e-05, "loss": 0.53, "num_tokens": 186380646.0, "step": 31145 }, { "epoch": 0.33232692861638913, "grad_norm": 0.9728782097545787, "learning_rate": 4.0886352133953555e-05, "loss": 0.6193, "num_tokens": 186411684.0, "step": 31150 }, { "epoch": 0.33238027162258754, "grad_norm": 1.2860741156468625, "learning_rate": 4.088316173795837e-05, "loss": 0.7152, "num_tokens": 186463694.0, "step": 31155 }, { "epoch": 0.332433614628786, "grad_norm": 1.213882393555927, "learning_rate": 4.087997092550668e-05, "loss": 0.6243, "num_tokens": 186499138.0, "step": 31160 }, { "epoch": 0.3324869576349845, "grad_norm": 1.0558976540617035, "learning_rate": 4.087677969669779e-05, "loss": 0.5239, "num_tokens": 186535376.0, "step": 31165 }, { "epoch": 0.33254030064118295, "grad_norm": 0.9900390735349341, "learning_rate": 4.0873588051630976e-05, "loss": 0.5789, "num_tokens": 186553919.0, "step": 31170 }, { "epoch": 0.33259364364738137, "grad_norm": 1.26753307853145, "learning_rate": 4.0870395990405587e-05, "loss": 0.652, "num_tokens": 186571729.0, "step": 31175 }, { "epoch": 0.33264698665357983, "grad_norm": 1.192967648898108, "learning_rate": 4.086720351312093e-05, "loss": 0.6065, "num_tokens": 186597797.0, "step": 31180 }, { "epoch": 0.3327003296597783, "grad_norm": 1.0047876386837646, "learning_rate": 4.086401061987636e-05, "loss": 0.502, "num_tokens": 186625137.0, "step": 31185 }, { "epoch": 0.3327536726659768, "grad_norm": 0.9978086185978668, "learning_rate": 4.0860817310771225e-05, "loss": 0.6134, "num_tokens": 186640334.0, "step": 31190 }, { "epoch": 0.33280701567217524, "grad_norm": 0.7764879324755751, "learning_rate": 4.085762358590491e-05, "loss": 0.6006, "num_tokens": 186675425.0, "step": 31195 }, { "epoch": 0.33286035867837366, "grad_norm": 0.8854866602272256, "learning_rate": 4.0854429445376773e-05, "loss": 0.5107, "num_tokens": 186708443.0, "step": 31200 }, { "epoch": 0.3329137016845721, "grad_norm": 0.8559237825672464, "learning_rate": 4.085123488928623e-05, "loss": 0.6489, "num_tokens": 186751454.0, "step": 31205 }, { "epoch": 0.3329670446907706, "grad_norm": 0.7571911583100311, "learning_rate": 4.0848039917732686e-05, "loss": 0.5028, "num_tokens": 186782229.0, "step": 31210 }, { "epoch": 0.33302038769696907, "grad_norm": 1.5200798199871088, "learning_rate": 4.0844844530815544e-05, "loss": 0.4979, "num_tokens": 186809938.0, "step": 31215 }, { "epoch": 0.3330737307031675, "grad_norm": 0.8137139321983495, "learning_rate": 4.0841648728634265e-05, "loss": 0.5832, "num_tokens": 186842696.0, "step": 31220 }, { "epoch": 0.33312707370936595, "grad_norm": 0.7063298259915054, "learning_rate": 4.083845251128827e-05, "loss": 0.6238, "num_tokens": 186870482.0, "step": 31225 }, { "epoch": 0.3331804167155644, "grad_norm": 1.1929386703365334, "learning_rate": 4.083525587887704e-05, "loss": 0.5111, "num_tokens": 186905788.0, "step": 31230 }, { "epoch": 0.3332337597217629, "grad_norm": 1.7176420682173903, "learning_rate": 4.0832058831500033e-05, "loss": 0.5981, "num_tokens": 186947421.0, "step": 31235 }, { "epoch": 0.33328710272796136, "grad_norm": 0.8919525219601788, "learning_rate": 4.082886136925675e-05, "loss": 0.593, "num_tokens": 186971676.0, "step": 31240 }, { "epoch": 0.3333404457341598, "grad_norm": 0.8113070699584936, "learning_rate": 4.082566349224667e-05, "loss": 0.46, "num_tokens": 187003503.0, "step": 31245 }, { "epoch": 0.33339378874035824, "grad_norm": 0.6334551166881364, "learning_rate": 4.082246520056931e-05, "loss": 0.4421, "num_tokens": 187037412.0, "step": 31250 }, { "epoch": 0.3334471317465567, "grad_norm": 0.580504661782373, "learning_rate": 4.0819266494324204e-05, "loss": 0.7189, "num_tokens": 187079135.0, "step": 31255 }, { "epoch": 0.3335004747527552, "grad_norm": 1.149160622838666, "learning_rate": 4.081606737361089e-05, "loss": 0.5668, "num_tokens": 187108101.0, "step": 31260 }, { "epoch": 0.3335538177589536, "grad_norm": 1.1756823101633826, "learning_rate": 4.08128678385289e-05, "loss": 0.4581, "num_tokens": 187132432.0, "step": 31265 }, { "epoch": 0.33360716076515207, "grad_norm": 1.3647301950669077, "learning_rate": 4.0809667889177817e-05, "loss": 0.6113, "num_tokens": 187145622.0, "step": 31270 }, { "epoch": 0.33366050377135054, "grad_norm": 3.661401971901617, "learning_rate": 4.08064675256572e-05, "loss": 0.6407, "num_tokens": 187170597.0, "step": 31275 }, { "epoch": 0.333713846777549, "grad_norm": 1.1568158429378084, "learning_rate": 4.080326674806665e-05, "loss": 0.5972, "num_tokens": 187210923.0, "step": 31280 }, { "epoch": 0.3337671897837475, "grad_norm": 0.9248880065687201, "learning_rate": 4.080006555650577e-05, "loss": 0.6916, "num_tokens": 187242057.0, "step": 31285 }, { "epoch": 0.3338205327899459, "grad_norm": 1.3311506380125722, "learning_rate": 4.079686395107416e-05, "loss": 0.6641, "num_tokens": 187267587.0, "step": 31290 }, { "epoch": 0.33387387579614436, "grad_norm": 1.9957632984598643, "learning_rate": 4.0793661931871464e-05, "loss": 0.7624, "num_tokens": 187315217.0, "step": 31295 }, { "epoch": 0.33392721880234283, "grad_norm": 0.6902260796529905, "learning_rate": 4.079045949899731e-05, "loss": 0.5695, "num_tokens": 187349626.0, "step": 31300 }, { "epoch": 0.3339805618085413, "grad_norm": 0.9035867519734351, "learning_rate": 4.0787256652551345e-05, "loss": 0.4875, "num_tokens": 187370255.0, "step": 31305 }, { "epoch": 0.3340339048147397, "grad_norm": 0.953185153488836, "learning_rate": 4.0784053392633266e-05, "loss": 0.4743, "num_tokens": 187406587.0, "step": 31310 }, { "epoch": 0.3340872478209382, "grad_norm": 0.8676228615745124, "learning_rate": 4.078084971934272e-05, "loss": 0.6664, "num_tokens": 187439309.0, "step": 31315 }, { "epoch": 0.33414059082713665, "grad_norm": 0.8996789572422663, "learning_rate": 4.077764563277941e-05, "loss": 0.5262, "num_tokens": 187469602.0, "step": 31320 }, { "epoch": 0.3341939338333351, "grad_norm": 0.6043107050885557, "learning_rate": 4.0774441133043044e-05, "loss": 0.5941, "num_tokens": 187505065.0, "step": 31325 }, { "epoch": 0.3342472768395336, "grad_norm": 1.216115405938139, "learning_rate": 4.0771236220233335e-05, "loss": 0.4933, "num_tokens": 187525471.0, "step": 31330 }, { "epoch": 0.334300619845732, "grad_norm": 1.0176430518898967, "learning_rate": 4.0768030894450016e-05, "loss": 0.5449, "num_tokens": 187553404.0, "step": 31335 }, { "epoch": 0.3343539628519305, "grad_norm": 1.2276890783000027, "learning_rate": 4.076482515579283e-05, "loss": 0.5861, "num_tokens": 187592114.0, "step": 31340 }, { "epoch": 0.33440730585812894, "grad_norm": 1.1181229715514454, "learning_rate": 4.0761619004361533e-05, "loss": 0.6399, "num_tokens": 187625699.0, "step": 31345 }, { "epoch": 0.3344606488643274, "grad_norm": 0.9954977916661103, "learning_rate": 4.075841244025588e-05, "loss": 0.5918, "num_tokens": 187649292.0, "step": 31350 }, { "epoch": 0.33451399187052583, "grad_norm": 1.679237453247659, "learning_rate": 4.075520546357568e-05, "loss": 0.5165, "num_tokens": 187667051.0, "step": 31355 }, { "epoch": 0.3345673348767243, "grad_norm": 1.0817834193708027, "learning_rate": 4.075199807442071e-05, "loss": 0.5812, "num_tokens": 187699370.0, "step": 31360 }, { "epoch": 0.33462067788292277, "grad_norm": 0.7378907588104741, "learning_rate": 4.0748790272890784e-05, "loss": 0.5346, "num_tokens": 187736553.0, "step": 31365 }, { "epoch": 0.33467402088912124, "grad_norm": 1.173842620621963, "learning_rate": 4.0745582059085714e-05, "loss": 0.6315, "num_tokens": 187767984.0, "step": 31370 }, { "epoch": 0.3347273638953197, "grad_norm": 1.2181408358878103, "learning_rate": 4.074237343310533e-05, "loss": 0.5293, "num_tokens": 187790556.0, "step": 31375 }, { "epoch": 0.3347807069015181, "grad_norm": 0.7990443553899382, "learning_rate": 4.07391643950495e-05, "loss": 0.6996, "num_tokens": 187832418.0, "step": 31380 }, { "epoch": 0.3348340499077166, "grad_norm": 0.6630383222657454, "learning_rate": 4.0735954945018056e-05, "loss": 0.5619, "num_tokens": 187872607.0, "step": 31385 }, { "epoch": 0.33488739291391506, "grad_norm": 0.8300506994398508, "learning_rate": 4.0732745083110887e-05, "loss": 0.5224, "num_tokens": 187891528.0, "step": 31390 }, { "epoch": 0.33494073592011353, "grad_norm": 3.4952607228082626, "learning_rate": 4.072953480942787e-05, "loss": 0.8816, "num_tokens": 187924061.0, "step": 31395 }, { "epoch": 0.33499407892631194, "grad_norm": 1.054832612234258, "learning_rate": 4.07263241240689e-05, "loss": 0.4734, "num_tokens": 187942498.0, "step": 31400 }, { "epoch": 0.3350474219325104, "grad_norm": 3.3273775307868734, "learning_rate": 4.07231130271339e-05, "loss": 0.5637, "num_tokens": 187980187.0, "step": 31405 }, { "epoch": 0.3351007649387089, "grad_norm": 1.0962309647898956, "learning_rate": 4.0719901518722786e-05, "loss": 0.5606, "num_tokens": 187994606.0, "step": 31410 }, { "epoch": 0.33515410794490735, "grad_norm": 0.7554003501087903, "learning_rate": 4.071668959893548e-05, "loss": 0.6318, "num_tokens": 188037515.0, "step": 31415 }, { "epoch": 0.3352074509511058, "grad_norm": 0.9756277085702054, "learning_rate": 4.0713477267871946e-05, "loss": 0.7187, "num_tokens": 188057134.0, "step": 31420 }, { "epoch": 0.33526079395730424, "grad_norm": 1.5485064115024902, "learning_rate": 4.071026452563214e-05, "loss": 0.5672, "num_tokens": 188084892.0, "step": 31425 }, { "epoch": 0.3353141369635027, "grad_norm": 1.073787364362137, "learning_rate": 4.0707051372316044e-05, "loss": 0.5758, "num_tokens": 188115457.0, "step": 31430 }, { "epoch": 0.3353674799697012, "grad_norm": 1.1867560201714398, "learning_rate": 4.070383780802363e-05, "loss": 0.4819, "num_tokens": 188144216.0, "step": 31435 }, { "epoch": 0.33542082297589965, "grad_norm": 1.1525798515966654, "learning_rate": 4.07006238328549e-05, "loss": 0.5103, "num_tokens": 188157669.0, "step": 31440 }, { "epoch": 0.33547416598209806, "grad_norm": 0.9091776106108104, "learning_rate": 4.0697409446909876e-05, "loss": 0.5094, "num_tokens": 188194368.0, "step": 31445 }, { "epoch": 0.33552750898829653, "grad_norm": 0.7995387468370909, "learning_rate": 4.0694194650288584e-05, "loss": 0.5583, "num_tokens": 188219513.0, "step": 31450 }, { "epoch": 0.335580851994495, "grad_norm": 0.7527988472983006, "learning_rate": 4.0690979443091056e-05, "loss": 0.8089, "num_tokens": 188258033.0, "step": 31455 }, { "epoch": 0.33563419500069347, "grad_norm": 1.0319263847309201, "learning_rate": 4.068776382541733e-05, "loss": 0.512, "num_tokens": 188291164.0, "step": 31460 }, { "epoch": 0.33568753800689194, "grad_norm": 0.673136482639189, "learning_rate": 4.068454779736749e-05, "loss": 0.5816, "num_tokens": 188319171.0, "step": 31465 }, { "epoch": 0.33574088101309035, "grad_norm": 1.17435870102352, "learning_rate": 4.068133135904161e-05, "loss": 0.5347, "num_tokens": 188338827.0, "step": 31470 }, { "epoch": 0.3357942240192888, "grad_norm": 1.0407735101557674, "learning_rate": 4.067811451053977e-05, "loss": 0.6468, "num_tokens": 188359867.0, "step": 31475 }, { "epoch": 0.3358475670254873, "grad_norm": 0.9700883088297926, "learning_rate": 4.0674897251962064e-05, "loss": 0.529, "num_tokens": 188381482.0, "step": 31480 }, { "epoch": 0.33590091003168576, "grad_norm": 1.471361515360652, "learning_rate": 4.0671679583408635e-05, "loss": 0.5768, "num_tokens": 188399310.0, "step": 31485 }, { "epoch": 0.3359542530378842, "grad_norm": 2.016839631376864, "learning_rate": 4.0668461504979575e-05, "loss": 0.5873, "num_tokens": 188437495.0, "step": 31490 }, { "epoch": 0.33600759604408265, "grad_norm": 1.0890062047194982, "learning_rate": 4.0665243016775056e-05, "loss": 0.5889, "num_tokens": 188469844.0, "step": 31495 }, { "epoch": 0.3360609390502811, "grad_norm": 0.9329622168964546, "learning_rate": 4.066202411889521e-05, "loss": 0.4849, "num_tokens": 188494777.0, "step": 31500 }, { "epoch": 0.3361142820564796, "grad_norm": 0.9228295576041808, "learning_rate": 4.065880481144022e-05, "loss": 0.5496, "num_tokens": 188528530.0, "step": 31505 }, { "epoch": 0.33616762506267805, "grad_norm": 0.9343734396537362, "learning_rate": 4.065558509451023e-05, "loss": 0.6527, "num_tokens": 188575115.0, "step": 31510 }, { "epoch": 0.33622096806887647, "grad_norm": 0.9222191282241092, "learning_rate": 4.0652364968205475e-05, "loss": 0.4967, "num_tokens": 188592324.0, "step": 31515 }, { "epoch": 0.33627431107507494, "grad_norm": 1.4540708956977173, "learning_rate": 4.064914443262613e-05, "loss": 0.6671, "num_tokens": 188621368.0, "step": 31520 }, { "epoch": 0.3363276540812734, "grad_norm": 0.5679922192258713, "learning_rate": 4.064592348787242e-05, "loss": 0.5946, "num_tokens": 188670850.0, "step": 31525 }, { "epoch": 0.3363809970874719, "grad_norm": 1.058476855642919, "learning_rate": 4.064270213404457e-05, "loss": 0.4929, "num_tokens": 188708450.0, "step": 31530 }, { "epoch": 0.3364343400936703, "grad_norm": 0.9908577763780012, "learning_rate": 4.063948037124283e-05, "loss": 0.5717, "num_tokens": 188733016.0, "step": 31535 }, { "epoch": 0.33648768309986876, "grad_norm": 1.4561188179664561, "learning_rate": 4.0636258199567455e-05, "loss": 0.7225, "num_tokens": 188776192.0, "step": 31540 }, { "epoch": 0.33654102610606723, "grad_norm": 0.7487155170216101, "learning_rate": 4.063303561911871e-05, "loss": 0.5518, "num_tokens": 188818126.0, "step": 31545 }, { "epoch": 0.3365943691122657, "grad_norm": 0.850695512363767, "learning_rate": 4.0629812629996856e-05, "loss": 0.4947, "num_tokens": 188840742.0, "step": 31550 }, { "epoch": 0.33664771211846417, "grad_norm": 0.973513565454003, "learning_rate": 4.062658923230221e-05, "loss": 0.5494, "num_tokens": 188878941.0, "step": 31555 }, { "epoch": 0.3367010551246626, "grad_norm": 0.9949551648855738, "learning_rate": 4.062336542613507e-05, "loss": 0.5104, "num_tokens": 188909019.0, "step": 31560 }, { "epoch": 0.33675439813086105, "grad_norm": 1.7375757399617056, "learning_rate": 4.0620141211595755e-05, "loss": 0.6409, "num_tokens": 188929292.0, "step": 31565 }, { "epoch": 0.3368077411370595, "grad_norm": 0.9211361294149957, "learning_rate": 4.061691658878459e-05, "loss": 0.6215, "num_tokens": 188957410.0, "step": 31570 }, { "epoch": 0.336861084143258, "grad_norm": 1.7547740488844903, "learning_rate": 4.0613691557801935e-05, "loss": 0.4943, "num_tokens": 188988360.0, "step": 31575 }, { "epoch": 0.3369144271494564, "grad_norm": 1.2269582950602154, "learning_rate": 4.0610466118748124e-05, "loss": 0.571, "num_tokens": 189012636.0, "step": 31580 }, { "epoch": 0.3369677701556549, "grad_norm": 1.197703168885714, "learning_rate": 4.0607240271723544e-05, "loss": 0.6337, "num_tokens": 189039603.0, "step": 31585 }, { "epoch": 0.33702111316185335, "grad_norm": 0.9110356406057305, "learning_rate": 4.060401401682857e-05, "loss": 0.411, "num_tokens": 189059200.0, "step": 31590 }, { "epoch": 0.3370744561680518, "grad_norm": 0.8675549881574904, "learning_rate": 4.0600787354163595e-05, "loss": 0.5567, "num_tokens": 189092930.0, "step": 31595 }, { "epoch": 0.3371277991742503, "grad_norm": 0.9670928623873318, "learning_rate": 4.059756028382902e-05, "loss": 0.5258, "num_tokens": 189134429.0, "step": 31600 }, { "epoch": 0.3371811421804487, "grad_norm": 1.082888653350132, "learning_rate": 4.059433280592528e-05, "loss": 0.6902, "num_tokens": 189157050.0, "step": 31605 }, { "epoch": 0.33723448518664717, "grad_norm": 0.9724646306012568, "learning_rate": 4.0591104920552794e-05, "loss": 0.6098, "num_tokens": 189184199.0, "step": 31610 }, { "epoch": 0.33728782819284564, "grad_norm": 0.9973876020763871, "learning_rate": 4.058787662781202e-05, "loss": 0.5373, "num_tokens": 189215392.0, "step": 31615 }, { "epoch": 0.3373411711990441, "grad_norm": 3.6276725257931575, "learning_rate": 4.0584647927803407e-05, "loss": 0.6206, "num_tokens": 189236111.0, "step": 31620 }, { "epoch": 0.3373945142052425, "grad_norm": 0.7981306643116777, "learning_rate": 4.058141882062743e-05, "loss": 0.5286, "num_tokens": 189274142.0, "step": 31625 }, { "epoch": 0.337447857211441, "grad_norm": 1.7551845836819175, "learning_rate": 4.057818930638456e-05, "loss": 0.6058, "num_tokens": 189306559.0, "step": 31630 }, { "epoch": 0.33750120021763946, "grad_norm": 0.9644136647369446, "learning_rate": 4.05749593851753e-05, "loss": 0.5874, "num_tokens": 189345367.0, "step": 31635 }, { "epoch": 0.33755454322383793, "grad_norm": 0.8324061196000796, "learning_rate": 4.0571729057100174e-05, "loss": 0.4967, "num_tokens": 189363096.0, "step": 31640 }, { "epoch": 0.3376078862300364, "grad_norm": 0.924800095567682, "learning_rate": 4.056849832225968e-05, "loss": 0.5769, "num_tokens": 189389735.0, "step": 31645 }, { "epoch": 0.3376612292362348, "grad_norm": 1.0697234666661941, "learning_rate": 4.056526718075437e-05, "loss": 0.459, "num_tokens": 189405630.0, "step": 31650 }, { "epoch": 0.3377145722424333, "grad_norm": 0.8116560151429755, "learning_rate": 4.056203563268477e-05, "loss": 0.5879, "num_tokens": 189446900.0, "step": 31655 }, { "epoch": 0.33776791524863176, "grad_norm": 1.173270811860469, "learning_rate": 4.055880367815146e-05, "loss": 0.4847, "num_tokens": 189472465.0, "step": 31660 }, { "epoch": 0.3378212582548302, "grad_norm": 2.1932963665832363, "learning_rate": 4.0555571317255e-05, "loss": 0.6708, "num_tokens": 189496629.0, "step": 31665 }, { "epoch": 0.33787460126102864, "grad_norm": 1.0105481263793794, "learning_rate": 4.0552338550095985e-05, "loss": 0.6048, "num_tokens": 189524382.0, "step": 31670 }, { "epoch": 0.3379279442672271, "grad_norm": 0.6986135948758776, "learning_rate": 4.0549105376774995e-05, "loss": 0.5074, "num_tokens": 189556489.0, "step": 31675 }, { "epoch": 0.3379812872734256, "grad_norm": 0.7447334388191438, "learning_rate": 4.054587179739266e-05, "loss": 0.5104, "num_tokens": 189580008.0, "step": 31680 }, { "epoch": 0.33803463027962405, "grad_norm": 1.71637106985424, "learning_rate": 4.054263781204958e-05, "loss": 0.613, "num_tokens": 189606767.0, "step": 31685 }, { "epoch": 0.3380879732858225, "grad_norm": 1.0820152055241719, "learning_rate": 4.05394034208464e-05, "loss": 0.5704, "num_tokens": 189633766.0, "step": 31690 }, { "epoch": 0.33814131629202093, "grad_norm": 1.5558236474514324, "learning_rate": 4.053616862388378e-05, "loss": 0.5467, "num_tokens": 189659653.0, "step": 31695 }, { "epoch": 0.3381946592982194, "grad_norm": 1.444044385512733, "learning_rate": 4.053293342126237e-05, "loss": 0.5426, "num_tokens": 189669431.0, "step": 31700 }, { "epoch": 0.33824800230441787, "grad_norm": 0.8854346643516126, "learning_rate": 4.0529697813082834e-05, "loss": 0.6048, "num_tokens": 189694288.0, "step": 31705 }, { "epoch": 0.33830134531061634, "grad_norm": 1.0199585667198965, "learning_rate": 4.052646179944587e-05, "loss": 0.627, "num_tokens": 189721544.0, "step": 31710 }, { "epoch": 0.33835468831681476, "grad_norm": 1.0095300053111995, "learning_rate": 4.052322538045217e-05, "loss": 0.4679, "num_tokens": 189754144.0, "step": 31715 }, { "epoch": 0.3384080313230132, "grad_norm": 0.762803011975931, "learning_rate": 4.051998855620245e-05, "loss": 0.5504, "num_tokens": 189789628.0, "step": 31720 }, { "epoch": 0.3384613743292117, "grad_norm": 1.1587024123629903, "learning_rate": 4.051675132679742e-05, "loss": 0.5137, "num_tokens": 189820700.0, "step": 31725 }, { "epoch": 0.33851471733541016, "grad_norm": 1.029029695544267, "learning_rate": 4.051351369233784e-05, "loss": 0.5269, "num_tokens": 189849921.0, "step": 31730 }, { "epoch": 0.33856806034160863, "grad_norm": 1.7115579413215514, "learning_rate": 4.051027565292443e-05, "loss": 0.503, "num_tokens": 189886295.0, "step": 31735 }, { "epoch": 0.33862140334780705, "grad_norm": 2.0169376048166665, "learning_rate": 4.050703720865798e-05, "loss": 0.6406, "num_tokens": 189908615.0, "step": 31740 }, { "epoch": 0.3386747463540055, "grad_norm": 1.1256884440611514, "learning_rate": 4.0503798359639244e-05, "loss": 0.5876, "num_tokens": 189933327.0, "step": 31745 }, { "epoch": 0.338728089360204, "grad_norm": 0.834219052803585, "learning_rate": 4.050055910596901e-05, "loss": 0.5507, "num_tokens": 189963842.0, "step": 31750 }, { "epoch": 0.33878143236640246, "grad_norm": 1.1315797951190423, "learning_rate": 4.0497319447748075e-05, "loss": 0.4506, "num_tokens": 189979337.0, "step": 31755 }, { "epoch": 0.33883477537260087, "grad_norm": 0.9297485071996288, "learning_rate": 4.049407938507726e-05, "loss": 0.6079, "num_tokens": 190021103.0, "step": 31760 }, { "epoch": 0.33888811837879934, "grad_norm": 0.909552686479441, "learning_rate": 4.04908389180574e-05, "loss": 0.5269, "num_tokens": 190043951.0, "step": 31765 }, { "epoch": 0.3389414613849978, "grad_norm": 1.1532080699117562, "learning_rate": 4.04875980467893e-05, "loss": 0.5552, "num_tokens": 190075360.0, "step": 31770 }, { "epoch": 0.3389948043911963, "grad_norm": 1.1746197408286927, "learning_rate": 4.048435677137383e-05, "loss": 0.7062, "num_tokens": 190111344.0, "step": 31775 }, { "epoch": 0.33904814739739475, "grad_norm": 0.8309148744190127, "learning_rate": 4.048111509191185e-05, "loss": 0.5372, "num_tokens": 190148432.0, "step": 31780 }, { "epoch": 0.33910149040359316, "grad_norm": 0.9133725515599085, "learning_rate": 4.047787300850424e-05, "loss": 0.69, "num_tokens": 190188415.0, "step": 31785 }, { "epoch": 0.33915483340979163, "grad_norm": 0.6837702176446655, "learning_rate": 4.0474630521251874e-05, "loss": 0.577, "num_tokens": 190227438.0, "step": 31790 }, { "epoch": 0.3392081764159901, "grad_norm": 1.7627482492131465, "learning_rate": 4.0471387630255645e-05, "loss": 0.6681, "num_tokens": 190240929.0, "step": 31795 }, { "epoch": 0.3392615194221886, "grad_norm": 0.9650430630469391, "learning_rate": 4.046814433561649e-05, "loss": 0.5722, "num_tokens": 190277185.0, "step": 31800 }, { "epoch": 0.339314862428387, "grad_norm": 1.0361803990084848, "learning_rate": 4.046490063743532e-05, "loss": 0.4937, "num_tokens": 190292026.0, "step": 31805 }, { "epoch": 0.33936820543458546, "grad_norm": 3.1094082537827905, "learning_rate": 4.0461656535813065e-05, "loss": 0.6025, "num_tokens": 190325585.0, "step": 31810 }, { "epoch": 0.3394215484407839, "grad_norm": 0.6754348089032747, "learning_rate": 4.0458412030850686e-05, "loss": 0.6473, "num_tokens": 190362982.0, "step": 31815 }, { "epoch": 0.3394748914469824, "grad_norm": 0.8764202215092806, "learning_rate": 4.0455167122649146e-05, "loss": 0.7106, "num_tokens": 190417964.0, "step": 31820 }, { "epoch": 0.33952823445318087, "grad_norm": 0.5597970292615708, "learning_rate": 4.045192181130941e-05, "loss": 0.5562, "num_tokens": 190449501.0, "step": 31825 }, { "epoch": 0.3395815774593793, "grad_norm": 1.608826511986855, "learning_rate": 4.044867609693248e-05, "loss": 0.5845, "num_tokens": 190482829.0, "step": 31830 }, { "epoch": 0.33963492046557775, "grad_norm": 0.774111797262326, "learning_rate": 4.0445429979619336e-05, "loss": 0.522, "num_tokens": 190519155.0, "step": 31835 }, { "epoch": 0.3396882634717762, "grad_norm": 0.7543974038680011, "learning_rate": 4.0442183459471014e-05, "loss": 0.5281, "num_tokens": 190562471.0, "step": 31840 }, { "epoch": 0.3397416064779747, "grad_norm": 0.7517625419475201, "learning_rate": 4.043893653658851e-05, "loss": 0.6018, "num_tokens": 190602445.0, "step": 31845 }, { "epoch": 0.3397949494841731, "grad_norm": 0.8930459294016166, "learning_rate": 4.043568921107289e-05, "loss": 0.5451, "num_tokens": 190634809.0, "step": 31850 }, { "epoch": 0.3398482924903716, "grad_norm": 1.4032545265507006, "learning_rate": 4.043244148302519e-05, "loss": 0.5931, "num_tokens": 190659170.0, "step": 31855 }, { "epoch": 0.33990163549657004, "grad_norm": 0.8861303494825254, "learning_rate": 4.0429193352546487e-05, "loss": 0.4667, "num_tokens": 190692726.0, "step": 31860 }, { "epoch": 0.3399549785027685, "grad_norm": 0.9443861244013506, "learning_rate": 4.042594481973782e-05, "loss": 0.4723, "num_tokens": 190709401.0, "step": 31865 }, { "epoch": 0.340008321508967, "grad_norm": 0.9342215568946612, "learning_rate": 4.042269588470032e-05, "loss": 0.6229, "num_tokens": 190755693.0, "step": 31870 }, { "epoch": 0.3400616645151654, "grad_norm": 1.0190985022992567, "learning_rate": 4.041944654753506e-05, "loss": 0.4719, "num_tokens": 190788658.0, "step": 31875 }, { "epoch": 0.34011500752136387, "grad_norm": 1.5455269376880048, "learning_rate": 4.041619680834316e-05, "loss": 0.6037, "num_tokens": 190813035.0, "step": 31880 }, { "epoch": 0.34016835052756234, "grad_norm": 1.095541867756673, "learning_rate": 4.041294666722575e-05, "loss": 0.6375, "num_tokens": 190841400.0, "step": 31885 }, { "epoch": 0.3402216935337608, "grad_norm": 1.001486195613575, "learning_rate": 4.040969612428396e-05, "loss": 0.6888, "num_tokens": 190879822.0, "step": 31890 }, { "epoch": 0.3402750365399592, "grad_norm": 1.0449170424280114, "learning_rate": 4.0406445179618944e-05, "loss": 0.57, "num_tokens": 190914330.0, "step": 31895 }, { "epoch": 0.3403283795461577, "grad_norm": 1.3859009017264565, "learning_rate": 4.040319383333187e-05, "loss": 0.4923, "num_tokens": 190940346.0, "step": 31900 }, { "epoch": 0.34038172255235616, "grad_norm": 0.9988607051124166, "learning_rate": 4.039994208552391e-05, "loss": 0.5165, "num_tokens": 190964549.0, "step": 31905 }, { "epoch": 0.34043506555855463, "grad_norm": 1.0438089759004257, "learning_rate": 4.0396689936296236e-05, "loss": 0.4875, "num_tokens": 190993229.0, "step": 31910 }, { "epoch": 0.3404884085647531, "grad_norm": 0.9558050666254715, "learning_rate": 4.039343738575007e-05, "loss": 0.5045, "num_tokens": 191028182.0, "step": 31915 }, { "epoch": 0.3405417515709515, "grad_norm": 1.2112133367209112, "learning_rate": 4.0390184433986615e-05, "loss": 0.4636, "num_tokens": 191045650.0, "step": 31920 }, { "epoch": 0.34059509457715, "grad_norm": 1.3235044653633619, "learning_rate": 4.038693108110711e-05, "loss": 0.5665, "num_tokens": 191072415.0, "step": 31925 }, { "epoch": 0.34064843758334845, "grad_norm": 2.1575060664930117, "learning_rate": 4.0383677327212766e-05, "loss": 0.6187, "num_tokens": 191108864.0, "step": 31930 }, { "epoch": 0.3407017805895469, "grad_norm": 1.2660049300566258, "learning_rate": 4.038042317240485e-05, "loss": 0.4564, "num_tokens": 191128122.0, "step": 31935 }, { "epoch": 0.34075512359574534, "grad_norm": 1.2753971126393295, "learning_rate": 4.0377168616784614e-05, "loss": 0.6589, "num_tokens": 191166008.0, "step": 31940 }, { "epoch": 0.3408084666019438, "grad_norm": 1.414690307532164, "learning_rate": 4.037391366045335e-05, "loss": 0.5728, "num_tokens": 191189022.0, "step": 31945 }, { "epoch": 0.3408618096081423, "grad_norm": 1.0047416262489413, "learning_rate": 4.0370658303512344e-05, "loss": 0.4644, "num_tokens": 191214677.0, "step": 31950 }, { "epoch": 0.34091515261434074, "grad_norm": 0.6813185727876464, "learning_rate": 4.036740254606288e-05, "loss": 0.5595, "num_tokens": 191252088.0, "step": 31955 }, { "epoch": 0.3409684956205392, "grad_norm": 1.0257596549319132, "learning_rate": 4.036414638820628e-05, "loss": 0.5998, "num_tokens": 191286875.0, "step": 31960 }, { "epoch": 0.34102183862673763, "grad_norm": 0.8676831439530286, "learning_rate": 4.036088983004387e-05, "loss": 0.5749, "num_tokens": 191325559.0, "step": 31965 }, { "epoch": 0.3410751816329361, "grad_norm": 0.9306531803424769, "learning_rate": 4.035763287167697e-05, "loss": 0.6252, "num_tokens": 191350842.0, "step": 31970 }, { "epoch": 0.34112852463913457, "grad_norm": 3.007198511075567, "learning_rate": 4.035437551320697e-05, "loss": 0.5925, "num_tokens": 191371684.0, "step": 31975 }, { "epoch": 0.34118186764533304, "grad_norm": 1.1293996748887447, "learning_rate": 4.0351117754735196e-05, "loss": 0.5526, "num_tokens": 191394960.0, "step": 31980 }, { "epoch": 0.34123521065153145, "grad_norm": 1.2837198531553433, "learning_rate": 4.034785959636303e-05, "loss": 0.474, "num_tokens": 191408013.0, "step": 31985 }, { "epoch": 0.3412885536577299, "grad_norm": 1.246229134848549, "learning_rate": 4.034460103819187e-05, "loss": 0.5825, "num_tokens": 191433803.0, "step": 31990 }, { "epoch": 0.3413418966639284, "grad_norm": 0.8339647193536698, "learning_rate": 4.034134208032311e-05, "loss": 0.6087, "num_tokens": 191468372.0, "step": 31995 }, { "epoch": 0.34139523967012686, "grad_norm": 0.5896940158390609, "learning_rate": 4.033808272285816e-05, "loss": 0.5979, "num_tokens": 191512142.0, "step": 32000 }, { "epoch": 0.34144858267632533, "grad_norm": 2.083847568276479, "learning_rate": 4.033482296589844e-05, "loss": 0.5452, "num_tokens": 191541320.0, "step": 32005 }, { "epoch": 0.34150192568252374, "grad_norm": 1.2252647616240513, "learning_rate": 4.0331562809545405e-05, "loss": 0.4752, "num_tokens": 191558189.0, "step": 32010 }, { "epoch": 0.3415552686887222, "grad_norm": 1.0401836273338871, "learning_rate": 4.032830225390049e-05, "loss": 0.7028, "num_tokens": 191574625.0, "step": 32015 }, { "epoch": 0.3416086116949207, "grad_norm": 0.7984719194691642, "learning_rate": 4.0325041299065145e-05, "loss": 0.5746, "num_tokens": 191604124.0, "step": 32020 }, { "epoch": 0.34166195470111915, "grad_norm": 1.1409230384950322, "learning_rate": 4.032177994514088e-05, "loss": 0.5112, "num_tokens": 191625858.0, "step": 32025 }, { "epoch": 0.34171529770731757, "grad_norm": 0.7897258585949647, "learning_rate": 4.031851819222914e-05, "loss": 0.4996, "num_tokens": 191653953.0, "step": 32030 }, { "epoch": 0.34176864071351604, "grad_norm": 0.6693912026812655, "learning_rate": 4.031525604043145e-05, "loss": 0.4431, "num_tokens": 191689401.0, "step": 32035 }, { "epoch": 0.3418219837197145, "grad_norm": 0.9006872585561146, "learning_rate": 4.0311993489849315e-05, "loss": 0.5769, "num_tokens": 191729797.0, "step": 32040 }, { "epoch": 0.341875326725913, "grad_norm": 0.9513673620254193, "learning_rate": 4.030873054058426e-05, "loss": 0.525, "num_tokens": 191768448.0, "step": 32045 }, { "epoch": 0.34192866973211145, "grad_norm": 1.4614930192443414, "learning_rate": 4.030546719273782e-05, "loss": 0.6105, "num_tokens": 191797817.0, "step": 32050 }, { "epoch": 0.34198201273830986, "grad_norm": 0.841024986429514, "learning_rate": 4.030220344641155e-05, "loss": 0.6251, "num_tokens": 191832742.0, "step": 32055 }, { "epoch": 0.34203535574450833, "grad_norm": 0.9171322283331211, "learning_rate": 4.0298939301707e-05, "loss": 0.5741, "num_tokens": 191876525.0, "step": 32060 }, { "epoch": 0.3420886987507068, "grad_norm": 0.7616257340835637, "learning_rate": 4.029567475872574e-05, "loss": 0.6072, "num_tokens": 191913214.0, "step": 32065 }, { "epoch": 0.34214204175690527, "grad_norm": 0.9443575713474907, "learning_rate": 4.029240981756938e-05, "loss": 0.5374, "num_tokens": 191950948.0, "step": 32070 }, { "epoch": 0.3421953847631037, "grad_norm": 0.8234846875473695, "learning_rate": 4.0289144478339496e-05, "loss": 0.505, "num_tokens": 191987286.0, "step": 32075 }, { "epoch": 0.34224872776930215, "grad_norm": 1.1048592073530166, "learning_rate": 4.02858787411377e-05, "loss": 0.5441, "num_tokens": 192027148.0, "step": 32080 }, { "epoch": 0.3423020707755006, "grad_norm": 1.7093371415452636, "learning_rate": 4.028261260606563e-05, "loss": 0.4988, "num_tokens": 192049008.0, "step": 32085 }, { "epoch": 0.3423554137816991, "grad_norm": 0.7610576687545652, "learning_rate": 4.0279346073224906e-05, "loss": 0.5433, "num_tokens": 192084090.0, "step": 32090 }, { "epoch": 0.34240875678789756, "grad_norm": 0.8290606168251552, "learning_rate": 4.0276079142717186e-05, "loss": 0.6507, "num_tokens": 192119529.0, "step": 32095 }, { "epoch": 0.342462099794096, "grad_norm": 1.4534513897034655, "learning_rate": 4.0272811814644124e-05, "loss": 0.5847, "num_tokens": 192140029.0, "step": 32100 }, { "epoch": 0.34251544280029445, "grad_norm": 0.9367637669318863, "learning_rate": 4.026954408910739e-05, "loss": 0.5779, "num_tokens": 192175738.0, "step": 32105 }, { "epoch": 0.3425687858064929, "grad_norm": 0.7688450499672711, "learning_rate": 4.026627596620868e-05, "loss": 0.5884, "num_tokens": 192210586.0, "step": 32110 }, { "epoch": 0.3426221288126914, "grad_norm": 2.4078626500732856, "learning_rate": 4.026300744604969e-05, "loss": 0.5811, "num_tokens": 192229572.0, "step": 32115 }, { "epoch": 0.3426754718188898, "grad_norm": 1.1537692318805044, "learning_rate": 4.025973852873211e-05, "loss": 0.4826, "num_tokens": 192258026.0, "step": 32120 }, { "epoch": 0.34272881482508827, "grad_norm": 0.7690915078591212, "learning_rate": 4.0256469214357684e-05, "loss": 0.5344, "num_tokens": 192286103.0, "step": 32125 }, { "epoch": 0.34278215783128674, "grad_norm": 0.7965035422698605, "learning_rate": 4.0253199503028134e-05, "loss": 0.6311, "num_tokens": 192331360.0, "step": 32130 }, { "epoch": 0.3428355008374852, "grad_norm": 0.8064352679947333, "learning_rate": 4.0249929394845216e-05, "loss": 0.4952, "num_tokens": 192351522.0, "step": 32135 }, { "epoch": 0.3428888438436837, "grad_norm": 1.258418003648771, "learning_rate": 4.0246658889910684e-05, "loss": 0.7261, "num_tokens": 192386151.0, "step": 32140 }, { "epoch": 0.3429421868498821, "grad_norm": 1.731791996269806, "learning_rate": 4.024338798832631e-05, "loss": 0.53, "num_tokens": 192424868.0, "step": 32145 }, { "epoch": 0.34299552985608056, "grad_norm": 0.6419317946478544, "learning_rate": 4.024011669019387e-05, "loss": 0.5051, "num_tokens": 192460096.0, "step": 32150 }, { "epoch": 0.34304887286227903, "grad_norm": 1.8610102188435793, "learning_rate": 4.023684499561518e-05, "loss": 0.7638, "num_tokens": 192480589.0, "step": 32155 }, { "epoch": 0.3431022158684775, "grad_norm": 1.1975496152704475, "learning_rate": 4.023357290469203e-05, "loss": 0.461, "num_tokens": 192504425.0, "step": 32160 }, { "epoch": 0.3431555588746759, "grad_norm": 0.7061494271650418, "learning_rate": 4.023030041752624e-05, "loss": 0.5269, "num_tokens": 192540358.0, "step": 32165 }, { "epoch": 0.3432089018808744, "grad_norm": 0.8580460161935314, "learning_rate": 4.0227027534219655e-05, "loss": 0.4989, "num_tokens": 192580933.0, "step": 32170 }, { "epoch": 0.34326224488707285, "grad_norm": 0.6306514443323433, "learning_rate": 4.0223754254874125e-05, "loss": 0.511, "num_tokens": 192621112.0, "step": 32175 }, { "epoch": 0.3433155878932713, "grad_norm": 0.8175180715218693, "learning_rate": 4.022048057959149e-05, "loss": 0.504, "num_tokens": 192643857.0, "step": 32180 }, { "epoch": 0.3433689308994698, "grad_norm": 1.0721168044305494, "learning_rate": 4.021720650847362e-05, "loss": 0.5414, "num_tokens": 192659029.0, "step": 32185 }, { "epoch": 0.3434222739056682, "grad_norm": 1.0764201159465872, "learning_rate": 4.021393204162242e-05, "loss": 0.5732, "num_tokens": 192679318.0, "step": 32190 }, { "epoch": 0.3434756169118667, "grad_norm": 1.2943030467601542, "learning_rate": 4.021065717913976e-05, "loss": 0.7124, "num_tokens": 192710446.0, "step": 32195 }, { "epoch": 0.34352895991806515, "grad_norm": 1.055203796037424, "learning_rate": 4.020738192112756e-05, "loss": 0.5416, "num_tokens": 192744212.0, "step": 32200 }, { "epoch": 0.3435823029242636, "grad_norm": 0.8380120031152782, "learning_rate": 4.0204106267687734e-05, "loss": 0.619, "num_tokens": 192768722.0, "step": 32205 }, { "epoch": 0.34363564593046203, "grad_norm": 1.4001704269833606, "learning_rate": 4.0200830218922216e-05, "loss": 0.4832, "num_tokens": 192783075.0, "step": 32210 }, { "epoch": 0.3436889889366605, "grad_norm": 0.9344309239208741, "learning_rate": 4.019755377493296e-05, "loss": 0.5227, "num_tokens": 192816154.0, "step": 32215 }, { "epoch": 0.34374233194285897, "grad_norm": 0.8914351827999724, "learning_rate": 4.01942769358219e-05, "loss": 0.5392, "num_tokens": 192846184.0, "step": 32220 }, { "epoch": 0.34379567494905744, "grad_norm": 1.087450574176487, "learning_rate": 4.019099970169102e-05, "loss": 0.4842, "num_tokens": 192873960.0, "step": 32225 }, { "epoch": 0.3438490179552559, "grad_norm": 1.005152344904573, "learning_rate": 4.01877220726423e-05, "loss": 0.7234, "num_tokens": 192901626.0, "step": 32230 }, { "epoch": 0.3439023609614543, "grad_norm": 1.1176709680819426, "learning_rate": 4.018444404877772e-05, "loss": 0.5963, "num_tokens": 192938933.0, "step": 32235 }, { "epoch": 0.3439557039676528, "grad_norm": 1.1938162062177473, "learning_rate": 4.018116563019931e-05, "loss": 0.5538, "num_tokens": 192971799.0, "step": 32240 }, { "epoch": 0.34400904697385126, "grad_norm": 0.8844783243487352, "learning_rate": 4.017788681700907e-05, "loss": 0.6181, "num_tokens": 192998740.0, "step": 32245 }, { "epoch": 0.34406238998004973, "grad_norm": 0.90206223452103, "learning_rate": 4.017460760930902e-05, "loss": 0.6631, "num_tokens": 193023578.0, "step": 32250 }, { "epoch": 0.34411573298624815, "grad_norm": 1.0882460389229731, "learning_rate": 4.017132800720123e-05, "loss": 0.5334, "num_tokens": 193042636.0, "step": 32255 }, { "epoch": 0.3441690759924466, "grad_norm": 0.9133108207840464, "learning_rate": 4.016804801078774e-05, "loss": 0.5212, "num_tokens": 193060891.0, "step": 32260 }, { "epoch": 0.3442224189986451, "grad_norm": 1.0925206983017985, "learning_rate": 4.016476762017061e-05, "loss": 0.607, "num_tokens": 193090825.0, "step": 32265 }, { "epoch": 0.34427576200484356, "grad_norm": 1.925373017320664, "learning_rate": 4.016148683545193e-05, "loss": 0.5862, "num_tokens": 193109351.0, "step": 32270 }, { "epoch": 0.344329105011042, "grad_norm": 0.9656971594898031, "learning_rate": 4.015820565673379e-05, "loss": 0.6973, "num_tokens": 193150484.0, "step": 32275 }, { "epoch": 0.34438244801724044, "grad_norm": 0.6303912489393348, "learning_rate": 4.015492408411829e-05, "loss": 0.4939, "num_tokens": 193188253.0, "step": 32280 }, { "epoch": 0.3444357910234389, "grad_norm": 0.8630246727335009, "learning_rate": 4.015164211770754e-05, "loss": 0.6216, "num_tokens": 193228181.0, "step": 32285 }, { "epoch": 0.3444891340296374, "grad_norm": 1.6012510422369681, "learning_rate": 4.0148359757603674e-05, "loss": 0.4387, "num_tokens": 193248558.0, "step": 32290 }, { "epoch": 0.34454247703583585, "grad_norm": 0.9130895217212636, "learning_rate": 4.014507700390884e-05, "loss": 0.6384, "num_tokens": 193278465.0, "step": 32295 }, { "epoch": 0.34459582004203426, "grad_norm": 0.7335631792990568, "learning_rate": 4.014179385672518e-05, "loss": 0.5252, "num_tokens": 193321222.0, "step": 32300 }, { "epoch": 0.34464916304823273, "grad_norm": 0.6428366993311153, "learning_rate": 4.013851031615486e-05, "loss": 0.4053, "num_tokens": 193351996.0, "step": 32305 }, { "epoch": 0.3447025060544312, "grad_norm": 0.9135044551172473, "learning_rate": 4.013522638230005e-05, "loss": 0.5657, "num_tokens": 193372641.0, "step": 32310 }, { "epoch": 0.34475584906062967, "grad_norm": 1.924219112001479, "learning_rate": 4.013194205526297e-05, "loss": 0.6082, "num_tokens": 193399411.0, "step": 32315 }, { "epoch": 0.34480919206682814, "grad_norm": 1.5781794115040446, "learning_rate": 4.0128657335145794e-05, "loss": 0.4804, "num_tokens": 193419599.0, "step": 32320 }, { "epoch": 0.34486253507302655, "grad_norm": 2.623316866510115, "learning_rate": 4.0125372222050735e-05, "loss": 0.5337, "num_tokens": 193447336.0, "step": 32325 }, { "epoch": 0.344915878079225, "grad_norm": 1.2451219872201653, "learning_rate": 4.012208671608003e-05, "loss": 0.4802, "num_tokens": 193478017.0, "step": 32330 }, { "epoch": 0.3449692210854235, "grad_norm": 1.1307375115143492, "learning_rate": 4.011880081733591e-05, "loss": 0.729, "num_tokens": 193513259.0, "step": 32335 }, { "epoch": 0.34502256409162196, "grad_norm": 0.8340552070873164, "learning_rate": 4.011551452592063e-05, "loss": 0.6743, "num_tokens": 193550395.0, "step": 32340 }, { "epoch": 0.3450759070978204, "grad_norm": 0.9777607065037915, "learning_rate": 4.011222784193645e-05, "loss": 0.461, "num_tokens": 193563141.0, "step": 32345 }, { "epoch": 0.34512925010401885, "grad_norm": 1.003790424728815, "learning_rate": 4.010894076548565e-05, "loss": 0.5148, "num_tokens": 193596270.0, "step": 32350 }, { "epoch": 0.3451825931102173, "grad_norm": 0.7363107738895883, "learning_rate": 4.01056532966705e-05, "loss": 0.7029, "num_tokens": 193635264.0, "step": 32355 }, { "epoch": 0.3452359361164158, "grad_norm": 0.9644270736163939, "learning_rate": 4.010236543559332e-05, "loss": 0.5178, "num_tokens": 193663808.0, "step": 32360 }, { "epoch": 0.34528927912261426, "grad_norm": 0.9401489738532275, "learning_rate": 4.009907718235642e-05, "loss": 0.584, "num_tokens": 193693121.0, "step": 32365 }, { "epoch": 0.34534262212881267, "grad_norm": 0.7768640630577064, "learning_rate": 4.009578853706211e-05, "loss": 0.5536, "num_tokens": 193732731.0, "step": 32370 }, { "epoch": 0.34539596513501114, "grad_norm": 2.1128323722408715, "learning_rate": 4.0092499499812736e-05, "loss": 0.5571, "num_tokens": 193752257.0, "step": 32375 }, { "epoch": 0.3454493081412096, "grad_norm": 1.0964351666435124, "learning_rate": 4.0089210070710646e-05, "loss": 0.7071, "num_tokens": 193790035.0, "step": 32380 }, { "epoch": 0.3455026511474081, "grad_norm": 0.9928053737481004, "learning_rate": 4.008592024985819e-05, "loss": 0.5609, "num_tokens": 193824259.0, "step": 32385 }, { "epoch": 0.3455559941536065, "grad_norm": 0.8643690159851787, "learning_rate": 4.0082630037357755e-05, "loss": 0.5998, "num_tokens": 193860019.0, "step": 32390 }, { "epoch": 0.34560933715980496, "grad_norm": 1.0047688490870188, "learning_rate": 4.007933943331172e-05, "loss": 0.6035, "num_tokens": 193892845.0, "step": 32395 }, { "epoch": 0.34566268016600343, "grad_norm": 0.9956039940608821, "learning_rate": 4.0076048437822466e-05, "loss": 0.6122, "num_tokens": 193911623.0, "step": 32400 }, { "epoch": 0.3457160231722019, "grad_norm": 1.0019406177674315, "learning_rate": 4.007275705099243e-05, "loss": 0.5819, "num_tokens": 193928805.0, "step": 32405 }, { "epoch": 0.3457693661784004, "grad_norm": 0.8109402785266983, "learning_rate": 4.006946527292402e-05, "loss": 0.5372, "num_tokens": 193980213.0, "step": 32410 }, { "epoch": 0.3458227091845988, "grad_norm": 1.1296565140548502, "learning_rate": 4.0066173103719664e-05, "loss": 0.4802, "num_tokens": 193994570.0, "step": 32415 }, { "epoch": 0.34587605219079726, "grad_norm": 1.092173466556425, "learning_rate": 4.0062880543481815e-05, "loss": 0.6806, "num_tokens": 194029842.0, "step": 32420 }, { "epoch": 0.3459293951969957, "grad_norm": 0.887732581548416, "learning_rate": 4.005958759231293e-05, "loss": 0.6214, "num_tokens": 194058050.0, "step": 32425 }, { "epoch": 0.3459827382031942, "grad_norm": 1.2157850628895255, "learning_rate": 4.0056294250315476e-05, "loss": 0.539, "num_tokens": 194090270.0, "step": 32430 }, { "epoch": 0.3460360812093926, "grad_norm": 2.570567685148505, "learning_rate": 4.0053000517591935e-05, "loss": 0.515, "num_tokens": 194111457.0, "step": 32435 }, { "epoch": 0.3460894242155911, "grad_norm": 0.7104802824569509, "learning_rate": 4.0049706394244804e-05, "loss": 0.6056, "num_tokens": 194144698.0, "step": 32440 }, { "epoch": 0.34614276722178955, "grad_norm": 2.1935660209586407, "learning_rate": 4.004641188037658e-05, "loss": 0.6014, "num_tokens": 194164375.0, "step": 32445 }, { "epoch": 0.346196110227988, "grad_norm": 0.7305778978809003, "learning_rate": 4.004311697608981e-05, "loss": 0.6524, "num_tokens": 194207464.0, "step": 32450 }, { "epoch": 0.3462494532341865, "grad_norm": 0.8832796917134349, "learning_rate": 4.0039821681486985e-05, "loss": 0.5235, "num_tokens": 194237591.0, "step": 32455 }, { "epoch": 0.3463027962403849, "grad_norm": 3.7612293618945514, "learning_rate": 4.003652599667067e-05, "loss": 0.6338, "num_tokens": 194261146.0, "step": 32460 }, { "epoch": 0.34635613924658337, "grad_norm": 6.5622237546692075, "learning_rate": 4.003322992174342e-05, "loss": 0.7609, "num_tokens": 194275867.0, "step": 32465 }, { "epoch": 0.34640948225278184, "grad_norm": 1.8754906365872692, "learning_rate": 4.00299334568078e-05, "loss": 0.5638, "num_tokens": 194299244.0, "step": 32470 }, { "epoch": 0.3464628252589803, "grad_norm": 0.9287937764596476, "learning_rate": 4.0026636601966386e-05, "loss": 0.7207, "num_tokens": 194332298.0, "step": 32475 }, { "epoch": 0.3465161682651787, "grad_norm": 0.7940419825160827, "learning_rate": 4.002333935732177e-05, "loss": 0.6504, "num_tokens": 194359916.0, "step": 32480 }, { "epoch": 0.3465695112713772, "grad_norm": 0.887572492026347, "learning_rate": 4.002004172297656e-05, "loss": 0.5823, "num_tokens": 194402655.0, "step": 32485 }, { "epoch": 0.34662285427757566, "grad_norm": 0.7618703094343896, "learning_rate": 4.0016743699033364e-05, "loss": 0.4911, "num_tokens": 194447882.0, "step": 32490 }, { "epoch": 0.34667619728377413, "grad_norm": 1.7838777693475136, "learning_rate": 4.001344528559482e-05, "loss": 0.5749, "num_tokens": 194473599.0, "step": 32495 }, { "epoch": 0.3467295402899726, "grad_norm": 1.0350936765869672, "learning_rate": 4.001014648276356e-05, "loss": 0.4893, "num_tokens": 194489372.0, "step": 32500 }, { "epoch": 0.346782883296171, "grad_norm": 1.1739354242159912, "learning_rate": 4.000684729064223e-05, "loss": 0.5883, "num_tokens": 194520852.0, "step": 32505 }, { "epoch": 0.3468362263023695, "grad_norm": 0.8827981490645259, "learning_rate": 4.000354770933352e-05, "loss": 0.5927, "num_tokens": 194563769.0, "step": 32510 }, { "epoch": 0.34688956930856796, "grad_norm": 0.5405786296989007, "learning_rate": 4.000024773894007e-05, "loss": 0.5827, "num_tokens": 194596354.0, "step": 32515 }, { "epoch": 0.3469429123147664, "grad_norm": 0.9841844108638849, "learning_rate": 3.999694737956459e-05, "loss": 0.5424, "num_tokens": 194618059.0, "step": 32520 }, { "epoch": 0.34699625532096484, "grad_norm": 2.3344765531148, "learning_rate": 3.999364663130979e-05, "loss": 0.6183, "num_tokens": 194642962.0, "step": 32525 }, { "epoch": 0.3470495983271633, "grad_norm": 0.7879237209520735, "learning_rate": 3.999034549427836e-05, "loss": 0.5562, "num_tokens": 194662680.0, "step": 32530 }, { "epoch": 0.3471029413333618, "grad_norm": 0.8163636885972297, "learning_rate": 3.998704396857303e-05, "loss": 0.6719, "num_tokens": 194692391.0, "step": 32535 }, { "epoch": 0.34715628433956025, "grad_norm": 1.588791003685531, "learning_rate": 3.998374205429655e-05, "loss": 0.6899, "num_tokens": 194724651.0, "step": 32540 }, { "epoch": 0.3472096273457587, "grad_norm": 0.7688665743225024, "learning_rate": 3.9980439751551654e-05, "loss": 0.6863, "num_tokens": 194763676.0, "step": 32545 }, { "epoch": 0.34726297035195713, "grad_norm": 1.7484799592468565, "learning_rate": 3.997713706044111e-05, "loss": 0.6443, "num_tokens": 194791495.0, "step": 32550 }, { "epoch": 0.3473163133581556, "grad_norm": 0.8949418589230659, "learning_rate": 3.997383398106769e-05, "loss": 0.6183, "num_tokens": 194822547.0, "step": 32555 }, { "epoch": 0.3473696563643541, "grad_norm": 0.8432867215279067, "learning_rate": 3.997053051353417e-05, "loss": 0.6027, "num_tokens": 194854157.0, "step": 32560 }, { "epoch": 0.34742299937055254, "grad_norm": 1.5730804960593185, "learning_rate": 3.996722665794336e-05, "loss": 0.4822, "num_tokens": 194883458.0, "step": 32565 }, { "epoch": 0.34747634237675096, "grad_norm": 1.0170778326845804, "learning_rate": 3.9963922414398075e-05, "loss": 0.6909, "num_tokens": 194922995.0, "step": 32570 }, { "epoch": 0.3475296853829494, "grad_norm": 0.6048555554047843, "learning_rate": 3.996061778300112e-05, "loss": 0.5729, "num_tokens": 194956187.0, "step": 32575 }, { "epoch": 0.3475830283891479, "grad_norm": 1.066207901319417, "learning_rate": 3.995731276385533e-05, "loss": 0.4996, "num_tokens": 194990342.0, "step": 32580 }, { "epoch": 0.34763637139534637, "grad_norm": 0.7889707659624975, "learning_rate": 3.9954007357063564e-05, "loss": 0.5782, "num_tokens": 195015631.0, "step": 32585 }, { "epoch": 0.34768971440154484, "grad_norm": 0.8721054726538403, "learning_rate": 3.995070156272866e-05, "loss": 0.4903, "num_tokens": 195046720.0, "step": 32590 }, { "epoch": 0.34774305740774325, "grad_norm": 1.0192788216452187, "learning_rate": 3.99473953809535e-05, "loss": 0.5367, "num_tokens": 195068129.0, "step": 32595 }, { "epoch": 0.3477964004139417, "grad_norm": 0.7586575440534833, "learning_rate": 3.9944088811840974e-05, "loss": 0.4845, "num_tokens": 195110324.0, "step": 32600 }, { "epoch": 0.3478497434201402, "grad_norm": 1.6920838004565548, "learning_rate": 3.9940781855493956e-05, "loss": 0.6425, "num_tokens": 195150503.0, "step": 32605 }, { "epoch": 0.34790308642633866, "grad_norm": 0.7803230853307829, "learning_rate": 3.9937474512015354e-05, "loss": 0.5735, "num_tokens": 195187912.0, "step": 32610 }, { "epoch": 0.3479564294325371, "grad_norm": 1.7086860557014791, "learning_rate": 3.9934166781508106e-05, "loss": 0.5116, "num_tokens": 195195920.0, "step": 32615 }, { "epoch": 0.34800977243873554, "grad_norm": 0.8548273439982726, "learning_rate": 3.9930858664075124e-05, "loss": 0.5345, "num_tokens": 195247037.0, "step": 32620 }, { "epoch": 0.348063115444934, "grad_norm": 1.3357820751990503, "learning_rate": 3.992755015981935e-05, "loss": 0.6356, "num_tokens": 195292823.0, "step": 32625 }, { "epoch": 0.3481164584511325, "grad_norm": 1.458808914580827, "learning_rate": 3.992424126884374e-05, "loss": 0.5391, "num_tokens": 195307862.0, "step": 32630 }, { "epoch": 0.34816980145733095, "grad_norm": 0.8769079665472328, "learning_rate": 3.992093199125127e-05, "loss": 0.5576, "num_tokens": 195340881.0, "step": 32635 }, { "epoch": 0.34822314446352937, "grad_norm": 0.7673324262770999, "learning_rate": 3.9917622327144906e-05, "loss": 0.4369, "num_tokens": 195367749.0, "step": 32640 }, { "epoch": 0.34827648746972784, "grad_norm": 0.7395220870735265, "learning_rate": 3.991431227662764e-05, "loss": 0.5323, "num_tokens": 195394664.0, "step": 32645 }, { "epoch": 0.3483298304759263, "grad_norm": 0.6160303246660986, "learning_rate": 3.991100183980248e-05, "loss": 0.6116, "num_tokens": 195441502.0, "step": 32650 }, { "epoch": 0.3483831734821248, "grad_norm": 1.0788543005395657, "learning_rate": 3.990769101677243e-05, "loss": 0.5623, "num_tokens": 195462980.0, "step": 32655 }, { "epoch": 0.3484365164883232, "grad_norm": 0.7144839573683887, "learning_rate": 3.990437980764052e-05, "loss": 0.4714, "num_tokens": 195508133.0, "step": 32660 }, { "epoch": 0.34848985949452166, "grad_norm": 0.9480575700767503, "learning_rate": 3.99010682125098e-05, "loss": 0.5264, "num_tokens": 195539674.0, "step": 32665 }, { "epoch": 0.34854320250072013, "grad_norm": 0.8376707435183232, "learning_rate": 3.9897756231483306e-05, "loss": 0.5484, "num_tokens": 195585357.0, "step": 32670 }, { "epoch": 0.3485965455069186, "grad_norm": 1.3651518727467051, "learning_rate": 3.98944438646641e-05, "loss": 0.5524, "num_tokens": 195613398.0, "step": 32675 }, { "epoch": 0.34864988851311707, "grad_norm": 1.352740170488548, "learning_rate": 3.9891131112155266e-05, "loss": 0.5782, "num_tokens": 195644806.0, "step": 32680 }, { "epoch": 0.3487032315193155, "grad_norm": 1.4060601224122387, "learning_rate": 3.988781797405987e-05, "loss": 0.5765, "num_tokens": 195662363.0, "step": 32685 }, { "epoch": 0.34875657452551395, "grad_norm": 0.6257190096856393, "learning_rate": 3.988450445048104e-05, "loss": 0.4968, "num_tokens": 195708072.0, "step": 32690 }, { "epoch": 0.3488099175317124, "grad_norm": 1.8418514899506666, "learning_rate": 3.988119054152187e-05, "loss": 0.6694, "num_tokens": 195728465.0, "step": 32695 }, { "epoch": 0.3488632605379109, "grad_norm": 1.7358397295560726, "learning_rate": 3.9877876247285476e-05, "loss": 0.5941, "num_tokens": 195758312.0, "step": 32700 }, { "epoch": 0.3489166035441093, "grad_norm": 1.2115529908088427, "learning_rate": 3.987456156787499e-05, "loss": 0.6086, "num_tokens": 195790018.0, "step": 32705 }, { "epoch": 0.3489699465503078, "grad_norm": 1.5736920673442099, "learning_rate": 3.9871246503393576e-05, "loss": 0.6418, "num_tokens": 195812492.0, "step": 32710 }, { "epoch": 0.34902328955650624, "grad_norm": 1.1935626749485007, "learning_rate": 3.986793105394438e-05, "loss": 0.543, "num_tokens": 195842446.0, "step": 32715 }, { "epoch": 0.3490766325627047, "grad_norm": 0.642377133987286, "learning_rate": 3.986461521963057e-05, "loss": 0.4604, "num_tokens": 195866299.0, "step": 32720 }, { "epoch": 0.3491299755689032, "grad_norm": 1.1243002453212945, "learning_rate": 3.986129900055534e-05, "loss": 0.5589, "num_tokens": 195893337.0, "step": 32725 }, { "epoch": 0.3491833185751016, "grad_norm": 1.8764887237480257, "learning_rate": 3.985798239682187e-05, "loss": 0.7698, "num_tokens": 195932908.0, "step": 32730 }, { "epoch": 0.34923666158130007, "grad_norm": 0.9585123205869582, "learning_rate": 3.9854665408533376e-05, "loss": 0.4223, "num_tokens": 195960594.0, "step": 32735 }, { "epoch": 0.34929000458749854, "grad_norm": 1.0872056933605492, "learning_rate": 3.9851348035793065e-05, "loss": 0.5341, "num_tokens": 195986394.0, "step": 32740 }, { "epoch": 0.349343347593697, "grad_norm": 1.6429587234335368, "learning_rate": 3.984803027870418e-05, "loss": 0.522, "num_tokens": 196009450.0, "step": 32745 }, { "epoch": 0.3493966905998954, "grad_norm": 1.9436040798159335, "learning_rate": 3.984471213736996e-05, "loss": 0.6358, "num_tokens": 196032191.0, "step": 32750 }, { "epoch": 0.3494500336060939, "grad_norm": 1.5345703275736318, "learning_rate": 3.984139361189365e-05, "loss": 0.4708, "num_tokens": 196057713.0, "step": 32755 }, { "epoch": 0.34950337661229236, "grad_norm": 0.9893527018522792, "learning_rate": 3.983807470237852e-05, "loss": 0.5793, "num_tokens": 196077161.0, "step": 32760 }, { "epoch": 0.34955671961849083, "grad_norm": 1.5107847072715315, "learning_rate": 3.9834755408927846e-05, "loss": 0.544, "num_tokens": 196120950.0, "step": 32765 }, { "epoch": 0.3496100626246893, "grad_norm": 0.7618210251344888, "learning_rate": 3.983143573164492e-05, "loss": 0.545, "num_tokens": 196154602.0, "step": 32770 }, { "epoch": 0.3496634056308877, "grad_norm": 1.0678957836901597, "learning_rate": 3.982811567063305e-05, "loss": 0.5253, "num_tokens": 196183869.0, "step": 32775 }, { "epoch": 0.3497167486370862, "grad_norm": 0.9023057449432987, "learning_rate": 3.982479522599554e-05, "loss": 0.4846, "num_tokens": 196209373.0, "step": 32780 }, { "epoch": 0.34977009164328465, "grad_norm": 1.0069219338577808, "learning_rate": 3.982147439783571e-05, "loss": 0.6483, "num_tokens": 196231511.0, "step": 32785 }, { "epoch": 0.3498234346494831, "grad_norm": 0.901192787016775, "learning_rate": 3.981815318625691e-05, "loss": 0.6373, "num_tokens": 196265314.0, "step": 32790 }, { "epoch": 0.34987677765568154, "grad_norm": 0.8709023691441671, "learning_rate": 3.981483159136249e-05, "loss": 0.4904, "num_tokens": 196296471.0, "step": 32795 }, { "epoch": 0.34993012066188, "grad_norm": 0.6287685013752193, "learning_rate": 3.981150961325581e-05, "loss": 0.525, "num_tokens": 196331151.0, "step": 32800 }, { "epoch": 0.3499834636680785, "grad_norm": 1.0666525842085834, "learning_rate": 3.980818725204023e-05, "loss": 0.4725, "num_tokens": 196371264.0, "step": 32805 }, { "epoch": 0.35003680667427695, "grad_norm": 1.2731277382322053, "learning_rate": 3.980486450781916e-05, "loss": 0.5935, "num_tokens": 196396441.0, "step": 32810 }, { "epoch": 0.3500901496804754, "grad_norm": 1.3672125371170245, "learning_rate": 3.9801541380695964e-05, "loss": 0.6019, "num_tokens": 196425044.0, "step": 32815 }, { "epoch": 0.35014349268667383, "grad_norm": 1.6153926973328847, "learning_rate": 3.9798217870774076e-05, "loss": 0.5117, "num_tokens": 196445574.0, "step": 32820 }, { "epoch": 0.3501968356928723, "grad_norm": 0.9737755506028144, "learning_rate": 3.979489397815691e-05, "loss": 0.4855, "num_tokens": 196488310.0, "step": 32825 }, { "epoch": 0.35025017869907077, "grad_norm": 0.8416720923511601, "learning_rate": 3.979156970294788e-05, "loss": 0.3851, "num_tokens": 196508927.0, "step": 32830 }, { "epoch": 0.35030352170526924, "grad_norm": 1.4196968427012622, "learning_rate": 3.978824504525047e-05, "loss": 0.581, "num_tokens": 196534718.0, "step": 32835 }, { "epoch": 0.35035686471146765, "grad_norm": 1.2154930585118917, "learning_rate": 3.978492000516811e-05, "loss": 0.552, "num_tokens": 196564830.0, "step": 32840 }, { "epoch": 0.3504102077176661, "grad_norm": 0.8894957850816071, "learning_rate": 3.9781594582804274e-05, "loss": 0.4861, "num_tokens": 196592336.0, "step": 32845 }, { "epoch": 0.3504635507238646, "grad_norm": 1.1466940145632087, "learning_rate": 3.977826877826244e-05, "loss": 0.5059, "num_tokens": 196615077.0, "step": 32850 }, { "epoch": 0.35051689373006306, "grad_norm": 1.1077401036647643, "learning_rate": 3.97749425916461e-05, "loss": 0.4539, "num_tokens": 196644049.0, "step": 32855 }, { "epoch": 0.35057023673626153, "grad_norm": 1.6054573223908222, "learning_rate": 3.977161602305876e-05, "loss": 0.6053, "num_tokens": 196670889.0, "step": 32860 }, { "epoch": 0.35062357974245995, "grad_norm": 0.7747856035556391, "learning_rate": 3.9768289072603944e-05, "loss": 0.5432, "num_tokens": 196718295.0, "step": 32865 }, { "epoch": 0.3506769227486584, "grad_norm": 1.2648411563281452, "learning_rate": 3.976496174038516e-05, "loss": 0.5818, "num_tokens": 196740856.0, "step": 32870 }, { "epoch": 0.3507302657548569, "grad_norm": 0.9622130511411621, "learning_rate": 3.976163402650596e-05, "loss": 0.665, "num_tokens": 196776841.0, "step": 32875 }, { "epoch": 0.35078360876105535, "grad_norm": 0.8103749141954502, "learning_rate": 3.975830593106991e-05, "loss": 0.5364, "num_tokens": 196798616.0, "step": 32880 }, { "epoch": 0.35083695176725377, "grad_norm": 0.9159958913601206, "learning_rate": 3.975497745418054e-05, "loss": 0.7413, "num_tokens": 196826939.0, "step": 32885 }, { "epoch": 0.35089029477345224, "grad_norm": 1.0024568681659174, "learning_rate": 3.975164859594146e-05, "loss": 0.5098, "num_tokens": 196860425.0, "step": 32890 }, { "epoch": 0.3509436377796507, "grad_norm": 1.1102600532638818, "learning_rate": 3.974831935645623e-05, "loss": 0.5722, "num_tokens": 196894165.0, "step": 32895 }, { "epoch": 0.3509969807858492, "grad_norm": 0.713177391884089, "learning_rate": 3.974498973582847e-05, "loss": 0.5545, "num_tokens": 196924097.0, "step": 32900 }, { "epoch": 0.35105032379204765, "grad_norm": 0.9586213586280122, "learning_rate": 3.974165973416177e-05, "loss": 0.5219, "num_tokens": 196941406.0, "step": 32905 }, { "epoch": 0.35110366679824606, "grad_norm": 1.2002879438657883, "learning_rate": 3.973832935155977e-05, "loss": 0.6067, "num_tokens": 196972643.0, "step": 32910 }, { "epoch": 0.35115700980444453, "grad_norm": 1.0181146417647673, "learning_rate": 3.9734998588126105e-05, "loss": 0.6323, "num_tokens": 196997303.0, "step": 32915 }, { "epoch": 0.351210352810643, "grad_norm": 0.9274815864808635, "learning_rate": 3.97316674439644e-05, "loss": 0.5326, "num_tokens": 197024827.0, "step": 32920 }, { "epoch": 0.35126369581684147, "grad_norm": 1.1777760393932872, "learning_rate": 3.972833591917835e-05, "loss": 0.5902, "num_tokens": 197053209.0, "step": 32925 }, { "epoch": 0.3513170388230399, "grad_norm": 0.856683602770078, "learning_rate": 3.972500401387159e-05, "loss": 0.5265, "num_tokens": 197085259.0, "step": 32930 }, { "epoch": 0.35137038182923835, "grad_norm": 0.8186510580664964, "learning_rate": 3.972167172814781e-05, "loss": 0.5388, "num_tokens": 197116798.0, "step": 32935 }, { "epoch": 0.3514237248354368, "grad_norm": 0.8607150258615907, "learning_rate": 3.971833906211072e-05, "loss": 0.4562, "num_tokens": 197149636.0, "step": 32940 }, { "epoch": 0.3514770678416353, "grad_norm": 1.2080250416903773, "learning_rate": 3.971500601586402e-05, "loss": 0.5925, "num_tokens": 197177335.0, "step": 32945 }, { "epoch": 0.35153041084783376, "grad_norm": 1.301791284244433, "learning_rate": 3.971167258951141e-05, "loss": 0.4097, "num_tokens": 197190554.0, "step": 32950 }, { "epoch": 0.3515837538540322, "grad_norm": 1.9064162104834084, "learning_rate": 3.970833878315664e-05, "loss": 0.4821, "num_tokens": 197221356.0, "step": 32955 }, { "epoch": 0.35163709686023065, "grad_norm": 1.0429604026009442, "learning_rate": 3.970500459690344e-05, "loss": 0.5808, "num_tokens": 197256984.0, "step": 32960 }, { "epoch": 0.3516904398664291, "grad_norm": 1.0296199062809082, "learning_rate": 3.970167003085557e-05, "loss": 0.5358, "num_tokens": 197292879.0, "step": 32965 }, { "epoch": 0.3517437828726276, "grad_norm": 1.5108210801233892, "learning_rate": 3.96983350851168e-05, "loss": 0.6298, "num_tokens": 197320837.0, "step": 32970 }, { "epoch": 0.351797125878826, "grad_norm": 0.9662510297563294, "learning_rate": 3.969499975979089e-05, "loss": 0.5582, "num_tokens": 197346381.0, "step": 32975 }, { "epoch": 0.35185046888502447, "grad_norm": 0.8489035161135512, "learning_rate": 3.969166405498163e-05, "loss": 0.5498, "num_tokens": 197372673.0, "step": 32980 }, { "epoch": 0.35190381189122294, "grad_norm": 1.5606366484781353, "learning_rate": 3.968832797079284e-05, "loss": 0.6169, "num_tokens": 197404073.0, "step": 32985 }, { "epoch": 0.3519571548974214, "grad_norm": 1.1364778164994704, "learning_rate": 3.968499150732831e-05, "loss": 0.5904, "num_tokens": 197426301.0, "step": 32990 }, { "epoch": 0.3520104979036199, "grad_norm": 0.9441777357423486, "learning_rate": 3.968165466469187e-05, "loss": 0.5205, "num_tokens": 197452562.0, "step": 32995 }, { "epoch": 0.3520638409098183, "grad_norm": 0.7254343771713867, "learning_rate": 3.9678317442987365e-05, "loss": 0.6434, "num_tokens": 197499459.0, "step": 33000 }, { "epoch": 0.35211718391601676, "grad_norm": 0.883396431836508, "learning_rate": 3.967497984231863e-05, "loss": 0.6418, "num_tokens": 197542573.0, "step": 33005 }, { "epoch": 0.35217052692221523, "grad_norm": 1.0349389821776265, "learning_rate": 3.9671641862789536e-05, "loss": 0.5784, "num_tokens": 197578226.0, "step": 33010 }, { "epoch": 0.3522238699284137, "grad_norm": 1.102293372612529, "learning_rate": 3.966830350450395e-05, "loss": 0.6142, "num_tokens": 197612073.0, "step": 33015 }, { "epoch": 0.3522772129346121, "grad_norm": 1.8884083009312325, "learning_rate": 3.966496476756575e-05, "loss": 0.4386, "num_tokens": 197629420.0, "step": 33020 }, { "epoch": 0.3523305559408106, "grad_norm": 1.1518269085941883, "learning_rate": 3.9661625652078836e-05, "loss": 0.7092, "num_tokens": 197666713.0, "step": 33025 }, { "epoch": 0.35238389894700906, "grad_norm": 1.0475774113589864, "learning_rate": 3.965828615814711e-05, "loss": 0.5787, "num_tokens": 197694569.0, "step": 33030 }, { "epoch": 0.3524372419532075, "grad_norm": 1.0846249130024155, "learning_rate": 3.96549462858745e-05, "loss": 0.5286, "num_tokens": 197724056.0, "step": 33035 }, { "epoch": 0.352490584959406, "grad_norm": 1.1769615573155567, "learning_rate": 3.965160603536492e-05, "loss": 0.5913, "num_tokens": 197759943.0, "step": 33040 }, { "epoch": 0.3525439279656044, "grad_norm": 1.0148465729962404, "learning_rate": 3.964826540672232e-05, "loss": 0.4829, "num_tokens": 197783202.0, "step": 33045 }, { "epoch": 0.3525972709718029, "grad_norm": 1.4598448133777295, "learning_rate": 3.964492440005066e-05, "loss": 0.5407, "num_tokens": 197809021.0, "step": 33050 }, { "epoch": 0.35265061397800135, "grad_norm": 1.5330803212078283, "learning_rate": 3.9641583015453896e-05, "loss": 0.5226, "num_tokens": 197834858.0, "step": 33055 }, { "epoch": 0.3527039569841998, "grad_norm": 0.8942802796262881, "learning_rate": 3.9638241253036004e-05, "loss": 0.618, "num_tokens": 197869347.0, "step": 33060 }, { "epoch": 0.35275729999039823, "grad_norm": 1.1234801812836006, "learning_rate": 3.963489911290099e-05, "loss": 0.564, "num_tokens": 197906381.0, "step": 33065 }, { "epoch": 0.3528106429965967, "grad_norm": 1.084831415048567, "learning_rate": 3.963155659515282e-05, "loss": 0.671, "num_tokens": 197944732.0, "step": 33070 }, { "epoch": 0.35286398600279517, "grad_norm": 2.4984706637880847, "learning_rate": 3.962821369989555e-05, "loss": 0.4966, "num_tokens": 197978329.0, "step": 33075 }, { "epoch": 0.35291732900899364, "grad_norm": 1.3378157259986783, "learning_rate": 3.962487042723317e-05, "loss": 0.5964, "num_tokens": 197998792.0, "step": 33080 }, { "epoch": 0.3529706720151921, "grad_norm": 0.7630297145791715, "learning_rate": 3.962152677726973e-05, "loss": 0.4893, "num_tokens": 198043775.0, "step": 33085 }, { "epoch": 0.3530240150213905, "grad_norm": 2.059276141194805, "learning_rate": 3.9618182750109275e-05, "loss": 0.4872, "num_tokens": 198062476.0, "step": 33090 }, { "epoch": 0.353077358027589, "grad_norm": 1.1457891123375523, "learning_rate": 3.961483834585587e-05, "loss": 0.5242, "num_tokens": 198087195.0, "step": 33095 }, { "epoch": 0.35313070103378746, "grad_norm": 0.8686225413100261, "learning_rate": 3.961149356461356e-05, "loss": 0.5429, "num_tokens": 198109781.0, "step": 33100 }, { "epoch": 0.35318404403998593, "grad_norm": 2.8701739726908357, "learning_rate": 3.9608148406486465e-05, "loss": 0.4531, "num_tokens": 198126045.0, "step": 33105 }, { "epoch": 0.35323738704618435, "grad_norm": 0.8117411640999035, "learning_rate": 3.9604802871578664e-05, "loss": 0.6174, "num_tokens": 198161165.0, "step": 33110 }, { "epoch": 0.3532907300523828, "grad_norm": 0.8012612028993809, "learning_rate": 3.960145695999425e-05, "loss": 0.5759, "num_tokens": 198198655.0, "step": 33115 }, { "epoch": 0.3533440730585813, "grad_norm": 0.8897081123550127, "learning_rate": 3.959811067183736e-05, "loss": 0.5107, "num_tokens": 198231053.0, "step": 33120 }, { "epoch": 0.35339741606477976, "grad_norm": 0.9455001696121033, "learning_rate": 3.9594764007212124e-05, "loss": 0.7285, "num_tokens": 198248100.0, "step": 33125 }, { "epoch": 0.3534507590709782, "grad_norm": 1.2683041794859649, "learning_rate": 3.959141696622265e-05, "loss": 0.5177, "num_tokens": 198277819.0, "step": 33130 }, { "epoch": 0.35350410207717664, "grad_norm": 1.5402334265905546, "learning_rate": 3.958806954897314e-05, "loss": 0.5601, "num_tokens": 198305222.0, "step": 33135 }, { "epoch": 0.3535574450833751, "grad_norm": 0.5762548277905014, "learning_rate": 3.958472175556773e-05, "loss": 0.5167, "num_tokens": 198359792.0, "step": 33140 }, { "epoch": 0.3536107880895736, "grad_norm": 1.3711352541450768, "learning_rate": 3.958137358611061e-05, "loss": 0.5828, "num_tokens": 198384302.0, "step": 33145 }, { "epoch": 0.35366413109577205, "grad_norm": 1.4567678015920442, "learning_rate": 3.957802504070594e-05, "loss": 0.7818, "num_tokens": 198404449.0, "step": 33150 }, { "epoch": 0.35371747410197046, "grad_norm": 0.9010076033915109, "learning_rate": 3.957467611945795e-05, "loss": 0.529, "num_tokens": 198454569.0, "step": 33155 }, { "epoch": 0.35377081710816893, "grad_norm": 2.2617031462658543, "learning_rate": 3.957132682247084e-05, "loss": 0.5351, "num_tokens": 198477386.0, "step": 33160 }, { "epoch": 0.3538241601143674, "grad_norm": 1.3703705806554853, "learning_rate": 3.956797714984884e-05, "loss": 0.4752, "num_tokens": 198494163.0, "step": 33165 }, { "epoch": 0.3538775031205659, "grad_norm": 0.9286327415493421, "learning_rate": 3.956462710169617e-05, "loss": 0.5342, "num_tokens": 198524570.0, "step": 33170 }, { "epoch": 0.35393084612676434, "grad_norm": 3.4888359888092184, "learning_rate": 3.95612766781171e-05, "loss": 0.5867, "num_tokens": 198554033.0, "step": 33175 }, { "epoch": 0.35398418913296276, "grad_norm": 2.6407897821907884, "learning_rate": 3.955792587921586e-05, "loss": 0.6142, "num_tokens": 198586247.0, "step": 33180 }, { "epoch": 0.3540375321391612, "grad_norm": 0.9393853129974845, "learning_rate": 3.955457470509674e-05, "loss": 0.5791, "num_tokens": 198610089.0, "step": 33185 }, { "epoch": 0.3540908751453597, "grad_norm": 0.8351291772532617, "learning_rate": 3.955122315586401e-05, "loss": 0.4441, "num_tokens": 198635179.0, "step": 33190 }, { "epoch": 0.35414421815155817, "grad_norm": 1.578865099447057, "learning_rate": 3.954787123162199e-05, "loss": 0.4759, "num_tokens": 198661908.0, "step": 33195 }, { "epoch": 0.3541975611577566, "grad_norm": 1.0212958163816805, "learning_rate": 3.954451893247494e-05, "loss": 0.6158, "num_tokens": 198690845.0, "step": 33200 }, { "epoch": 0.35425090416395505, "grad_norm": 2.8569179321739386, "learning_rate": 3.954116625852721e-05, "loss": 0.5742, "num_tokens": 198738351.0, "step": 33205 }, { "epoch": 0.3543042471701535, "grad_norm": 1.1346038609881133, "learning_rate": 3.953781320988312e-05, "loss": 0.5058, "num_tokens": 198761878.0, "step": 33210 }, { "epoch": 0.354357590176352, "grad_norm": 0.6650951301525313, "learning_rate": 3.953445978664701e-05, "loss": 0.4284, "num_tokens": 198787299.0, "step": 33215 }, { "epoch": 0.35441093318255046, "grad_norm": 0.8277384514938358, "learning_rate": 3.953110598892323e-05, "loss": 0.4483, "num_tokens": 198815306.0, "step": 33220 }, { "epoch": 0.3544642761887489, "grad_norm": 0.8715126128603146, "learning_rate": 3.952775181681614e-05, "loss": 0.4836, "num_tokens": 198854486.0, "step": 33225 }, { "epoch": 0.35451761919494734, "grad_norm": 1.2269317297861912, "learning_rate": 3.952439727043013e-05, "loss": 0.629, "num_tokens": 198879439.0, "step": 33230 }, { "epoch": 0.3545709622011458, "grad_norm": 1.2606600004617117, "learning_rate": 3.952104234986957e-05, "loss": 0.6301, "num_tokens": 198909677.0, "step": 33235 }, { "epoch": 0.3546243052073443, "grad_norm": 0.5661095178549842, "learning_rate": 3.9517687055238854e-05, "loss": 0.455, "num_tokens": 198941123.0, "step": 33240 }, { "epoch": 0.3546776482135427, "grad_norm": 1.0614444710285238, "learning_rate": 3.9514331386642406e-05, "loss": 0.7219, "num_tokens": 198982691.0, "step": 33245 }, { "epoch": 0.35473099121974117, "grad_norm": 0.7802248593281654, "learning_rate": 3.951097534418466e-05, "loss": 0.4829, "num_tokens": 199008443.0, "step": 33250 }, { "epoch": 0.35478433422593963, "grad_norm": 1.3447872496671576, "learning_rate": 3.950761892797002e-05, "loss": 0.5468, "num_tokens": 199042008.0, "step": 33255 }, { "epoch": 0.3548376772321381, "grad_norm": 1.0235810887564853, "learning_rate": 3.950426213810294e-05, "loss": 0.4566, "num_tokens": 199065468.0, "step": 33260 }, { "epoch": 0.3548910202383366, "grad_norm": 0.9952085972868625, "learning_rate": 3.950090497468788e-05, "loss": 0.6426, "num_tokens": 199088602.0, "step": 33265 }, { "epoch": 0.354944363244535, "grad_norm": 0.8227617901918945, "learning_rate": 3.949754743782932e-05, "loss": 0.6566, "num_tokens": 199135770.0, "step": 33270 }, { "epoch": 0.35499770625073346, "grad_norm": 0.8935229642329874, "learning_rate": 3.949418952763171e-05, "loss": 0.5028, "num_tokens": 199174502.0, "step": 33275 }, { "epoch": 0.3550510492569319, "grad_norm": 0.9496124234777675, "learning_rate": 3.9490831244199575e-05, "loss": 0.6024, "num_tokens": 199215371.0, "step": 33280 }, { "epoch": 0.3551043922631304, "grad_norm": 0.631431142886732, "learning_rate": 3.9487472587637396e-05, "loss": 0.6298, "num_tokens": 199256934.0, "step": 33285 }, { "epoch": 0.3551577352693288, "grad_norm": 0.9530396201854068, "learning_rate": 3.948411355804969e-05, "loss": 0.5968, "num_tokens": 199291745.0, "step": 33290 }, { "epoch": 0.3552110782755273, "grad_norm": 0.7915437203076459, "learning_rate": 3.948075415554098e-05, "loss": 0.5234, "num_tokens": 199321599.0, "step": 33295 }, { "epoch": 0.35526442128172575, "grad_norm": 1.0458958618787806, "learning_rate": 3.9477394380215824e-05, "loss": 0.6136, "num_tokens": 199352307.0, "step": 33300 }, { "epoch": 0.3553177642879242, "grad_norm": 0.6557697575290123, "learning_rate": 3.947403423217875e-05, "loss": 0.5859, "num_tokens": 199383977.0, "step": 33305 }, { "epoch": 0.3553711072941227, "grad_norm": 0.702022588249255, "learning_rate": 3.947067371153432e-05, "loss": 0.5784, "num_tokens": 199430279.0, "step": 33310 }, { "epoch": 0.3554244503003211, "grad_norm": 0.9987357232676326, "learning_rate": 3.946731281838713e-05, "loss": 0.4773, "num_tokens": 199445109.0, "step": 33315 }, { "epoch": 0.3554777933065196, "grad_norm": 2.720996022249673, "learning_rate": 3.946395155284173e-05, "loss": 0.7172, "num_tokens": 199455359.0, "step": 33320 }, { "epoch": 0.35553113631271804, "grad_norm": 2.7362482645279234, "learning_rate": 3.9460589915002736e-05, "loss": 0.5993, "num_tokens": 199474792.0, "step": 33325 }, { "epoch": 0.3555844793189165, "grad_norm": 1.22355585819636, "learning_rate": 3.945722790497476e-05, "loss": 0.6684, "num_tokens": 199509266.0, "step": 33330 }, { "epoch": 0.3556378223251149, "grad_norm": 1.1676478445867733, "learning_rate": 3.94538655228624e-05, "loss": 0.5915, "num_tokens": 199526888.0, "step": 33335 }, { "epoch": 0.3556911653313134, "grad_norm": 0.6884355911853199, "learning_rate": 3.945050276877031e-05, "loss": 0.673, "num_tokens": 199568108.0, "step": 33340 }, { "epoch": 0.35574450833751187, "grad_norm": 0.6664479253720916, "learning_rate": 3.944713964280311e-05, "loss": 0.4434, "num_tokens": 199595218.0, "step": 33345 }, { "epoch": 0.35579785134371034, "grad_norm": 0.9335472769483494, "learning_rate": 3.9443776145065476e-05, "loss": 0.5918, "num_tokens": 199625862.0, "step": 33350 }, { "epoch": 0.3558511943499088, "grad_norm": 2.9678222463510093, "learning_rate": 3.944041227566205e-05, "loss": 0.5593, "num_tokens": 199655769.0, "step": 33355 }, { "epoch": 0.3559045373561072, "grad_norm": 0.7177569394972981, "learning_rate": 3.943704803469753e-05, "loss": 0.5208, "num_tokens": 199699326.0, "step": 33360 }, { "epoch": 0.3559578803623057, "grad_norm": 0.9502836413986578, "learning_rate": 3.943368342227659e-05, "loss": 0.6012, "num_tokens": 199748746.0, "step": 33365 }, { "epoch": 0.35601122336850416, "grad_norm": 0.7292324651760141, "learning_rate": 3.943031843850394e-05, "loss": 0.4551, "num_tokens": 199789882.0, "step": 33370 }, { "epoch": 0.35606456637470263, "grad_norm": 1.6763210575036454, "learning_rate": 3.942695308348428e-05, "loss": 0.6201, "num_tokens": 199816638.0, "step": 33375 }, { "epoch": 0.35611790938090104, "grad_norm": 1.6917670898131985, "learning_rate": 3.942358735732233e-05, "loss": 0.5594, "num_tokens": 199839540.0, "step": 33380 }, { "epoch": 0.3561712523870995, "grad_norm": 0.8320527735574016, "learning_rate": 3.9420221260122846e-05, "loss": 0.4405, "num_tokens": 199869733.0, "step": 33385 }, { "epoch": 0.356224595393298, "grad_norm": 1.0305299763941753, "learning_rate": 3.941685479199056e-05, "loss": 0.6133, "num_tokens": 199899508.0, "step": 33390 }, { "epoch": 0.35627793839949645, "grad_norm": 0.9780507995323627, "learning_rate": 3.941348795303023e-05, "loss": 0.4363, "num_tokens": 199924354.0, "step": 33395 }, { "epoch": 0.3563312814056949, "grad_norm": 0.7185599029187553, "learning_rate": 3.941012074334662e-05, "loss": 0.4922, "num_tokens": 199953810.0, "step": 33400 }, { "epoch": 0.35638462441189334, "grad_norm": 0.7904827343410612, "learning_rate": 3.940675316304453e-05, "loss": 0.4949, "num_tokens": 199980956.0, "step": 33405 }, { "epoch": 0.3564379674180918, "grad_norm": 0.9010885489147333, "learning_rate": 3.9403385212228715e-05, "loss": 0.6214, "num_tokens": 200003478.0, "step": 33410 }, { "epoch": 0.3564913104242903, "grad_norm": 0.9013620772403041, "learning_rate": 3.9400016891004026e-05, "loss": 0.5621, "num_tokens": 200028313.0, "step": 33415 }, { "epoch": 0.35654465343048874, "grad_norm": 1.2978003679626555, "learning_rate": 3.939664819947524e-05, "loss": 0.6241, "num_tokens": 200057980.0, "step": 33420 }, { "epoch": 0.35659799643668716, "grad_norm": 1.4871438432676882, "learning_rate": 3.9393279137747205e-05, "loss": 0.6185, "num_tokens": 200076048.0, "step": 33425 }, { "epoch": 0.35665133944288563, "grad_norm": 1.1344773289428423, "learning_rate": 3.938990970592476e-05, "loss": 0.5955, "num_tokens": 200098268.0, "step": 33430 }, { "epoch": 0.3567046824490841, "grad_norm": 1.2637389231258926, "learning_rate": 3.938653990411274e-05, "loss": 0.6394, "num_tokens": 200128622.0, "step": 33435 }, { "epoch": 0.35675802545528257, "grad_norm": 0.8340803165305396, "learning_rate": 3.938316973241601e-05, "loss": 0.5721, "num_tokens": 200149872.0, "step": 33440 }, { "epoch": 0.35681136846148104, "grad_norm": 1.4815960983607632, "learning_rate": 3.937979919093946e-05, "loss": 0.5479, "num_tokens": 200176358.0, "step": 33445 }, { "epoch": 0.35686471146767945, "grad_norm": 1.083953611191782, "learning_rate": 3.937642827978795e-05, "loss": 0.6079, "num_tokens": 200205559.0, "step": 33450 }, { "epoch": 0.3569180544738779, "grad_norm": 1.4123920117996371, "learning_rate": 3.937305699906638e-05, "loss": 0.5128, "num_tokens": 200226115.0, "step": 33455 }, { "epoch": 0.3569713974800764, "grad_norm": 0.8228714074671754, "learning_rate": 3.936968534887967e-05, "loss": 0.564, "num_tokens": 200254383.0, "step": 33460 }, { "epoch": 0.35702474048627486, "grad_norm": 2.4195067065225073, "learning_rate": 3.936631332933274e-05, "loss": 0.5097, "num_tokens": 200285020.0, "step": 33465 }, { "epoch": 0.3570780834924733, "grad_norm": 0.9278210315841199, "learning_rate": 3.936294094053051e-05, "loss": 0.5876, "num_tokens": 200319653.0, "step": 33470 }, { "epoch": 0.35713142649867174, "grad_norm": 0.9914027589108544, "learning_rate": 3.935956818257792e-05, "loss": 0.556, "num_tokens": 200354267.0, "step": 33475 }, { "epoch": 0.3571847695048702, "grad_norm": 2.5684280632544185, "learning_rate": 3.935619505557993e-05, "loss": 0.522, "num_tokens": 200383307.0, "step": 33480 }, { "epoch": 0.3572381125110687, "grad_norm": 0.9837685409366963, "learning_rate": 3.93528215596415e-05, "loss": 0.6067, "num_tokens": 200416145.0, "step": 33485 }, { "epoch": 0.35729145551726715, "grad_norm": 1.0507100119349722, "learning_rate": 3.934944769486763e-05, "loss": 0.5743, "num_tokens": 200453467.0, "step": 33490 }, { "epoch": 0.35734479852346557, "grad_norm": 1.3695396525552737, "learning_rate": 3.9346073461363266e-05, "loss": 0.6216, "num_tokens": 200481070.0, "step": 33495 }, { "epoch": 0.35739814152966404, "grad_norm": 0.9036420451587418, "learning_rate": 3.934269885923343e-05, "loss": 0.6543, "num_tokens": 200508065.0, "step": 33500 }, { "epoch": 0.3574514845358625, "grad_norm": 1.2414100347615598, "learning_rate": 3.933932388858313e-05, "loss": 0.6833, "num_tokens": 200548369.0, "step": 33505 }, { "epoch": 0.357504827542061, "grad_norm": 1.0114762805504627, "learning_rate": 3.9335948549517404e-05, "loss": 0.716, "num_tokens": 200583959.0, "step": 33510 }, { "epoch": 0.3575581705482594, "grad_norm": 1.1021693130724712, "learning_rate": 3.933257284214126e-05, "loss": 0.6431, "num_tokens": 200602635.0, "step": 33515 }, { "epoch": 0.35761151355445786, "grad_norm": 1.4813383584884792, "learning_rate": 3.9329196766559754e-05, "loss": 0.609, "num_tokens": 200618948.0, "step": 33520 }, { "epoch": 0.35766485656065633, "grad_norm": 1.647709617684609, "learning_rate": 3.932582032287795e-05, "loss": 0.66, "num_tokens": 200648126.0, "step": 33525 }, { "epoch": 0.3577181995668548, "grad_norm": 8.334164553795228, "learning_rate": 3.9322443511200897e-05, "loss": 0.758, "num_tokens": 200685638.0, "step": 33530 }, { "epoch": 0.35777154257305327, "grad_norm": 1.515094121163522, "learning_rate": 3.931906633163369e-05, "loss": 0.7028, "num_tokens": 200720001.0, "step": 33535 }, { "epoch": 0.3578248855792517, "grad_norm": 1.6271712910915626, "learning_rate": 3.931568878428142e-05, "loss": 0.6218, "num_tokens": 200752614.0, "step": 33540 }, { "epoch": 0.35787822858545015, "grad_norm": 0.7294208407462892, "learning_rate": 3.931231086924918e-05, "loss": 0.5003, "num_tokens": 200788364.0, "step": 33545 }, { "epoch": 0.3579315715916486, "grad_norm": 1.3605071955713561, "learning_rate": 3.930893258664209e-05, "loss": 0.5793, "num_tokens": 200817047.0, "step": 33550 }, { "epoch": 0.3579849145978471, "grad_norm": 0.8813043028544456, "learning_rate": 3.9305553936565275e-05, "loss": 0.6841, "num_tokens": 200840111.0, "step": 33555 }, { "epoch": 0.3580382576040455, "grad_norm": 0.7647646354808093, "learning_rate": 3.9302174919123874e-05, "loss": 0.5837, "num_tokens": 200874274.0, "step": 33560 }, { "epoch": 0.358091600610244, "grad_norm": 0.9611705729574489, "learning_rate": 3.9298795534423034e-05, "loss": 0.6171, "num_tokens": 200912729.0, "step": 33565 }, { "epoch": 0.35814494361644245, "grad_norm": 2.407120348302694, "learning_rate": 3.92954157825679e-05, "loss": 0.6598, "num_tokens": 200937473.0, "step": 33570 }, { "epoch": 0.3581982866226409, "grad_norm": 0.7513196658524133, "learning_rate": 3.929203566366366e-05, "loss": 0.5891, "num_tokens": 200961220.0, "step": 33575 }, { "epoch": 0.3582516296288394, "grad_norm": 1.3813318291886794, "learning_rate": 3.92886551778155e-05, "loss": 0.611, "num_tokens": 201004026.0, "step": 33580 }, { "epoch": 0.3583049726350378, "grad_norm": 0.9423861970866092, "learning_rate": 3.92852743251286e-05, "loss": 0.5617, "num_tokens": 201031675.0, "step": 33585 }, { "epoch": 0.35835831564123627, "grad_norm": 6.22841665288207, "learning_rate": 3.9281893105708175e-05, "loss": 0.8175, "num_tokens": 201050210.0, "step": 33590 }, { "epoch": 0.35841165864743474, "grad_norm": 1.0211392910635742, "learning_rate": 3.927851151965943e-05, "loss": 0.5435, "num_tokens": 201066495.0, "step": 33595 }, { "epoch": 0.3584650016536332, "grad_norm": 0.7097030221529059, "learning_rate": 3.92751295670876e-05, "loss": 0.5587, "num_tokens": 201102127.0, "step": 33600 }, { "epoch": 0.3585183446598316, "grad_norm": 1.3917667320483522, "learning_rate": 3.927174724809793e-05, "loss": 0.5636, "num_tokens": 201120663.0, "step": 33605 }, { "epoch": 0.3585716876660301, "grad_norm": 0.9323149151296489, "learning_rate": 3.926836456279566e-05, "loss": 0.5583, "num_tokens": 201152658.0, "step": 33610 }, { "epoch": 0.35862503067222856, "grad_norm": 1.119804595142665, "learning_rate": 3.926498151128607e-05, "loss": 0.5115, "num_tokens": 201179234.0, "step": 33615 }, { "epoch": 0.35867837367842703, "grad_norm": 1.100174578918126, "learning_rate": 3.926159809367441e-05, "loss": 0.5011, "num_tokens": 201202991.0, "step": 33620 }, { "epoch": 0.3587317166846255, "grad_norm": 0.6230172482264041, "learning_rate": 3.925821431006598e-05, "loss": 0.6079, "num_tokens": 201245670.0, "step": 33625 }, { "epoch": 0.3587850596908239, "grad_norm": 1.546903875155018, "learning_rate": 3.9254830160566064e-05, "loss": 0.5905, "num_tokens": 201261140.0, "step": 33630 }, { "epoch": 0.3588384026970224, "grad_norm": 0.7937304721732802, "learning_rate": 3.9251445645279984e-05, "loss": 0.5565, "num_tokens": 201290248.0, "step": 33635 }, { "epoch": 0.35889174570322085, "grad_norm": 1.541198245616229, "learning_rate": 3.924806076431306e-05, "loss": 0.4935, "num_tokens": 201311811.0, "step": 33640 }, { "epoch": 0.3589450887094193, "grad_norm": 0.8361766132136907, "learning_rate": 3.924467551777061e-05, "loss": 0.5691, "num_tokens": 201330833.0, "step": 33645 }, { "epoch": 0.35899843171561774, "grad_norm": 0.9819604003457827, "learning_rate": 3.924128990575798e-05, "loss": 0.5203, "num_tokens": 201349716.0, "step": 33650 }, { "epoch": 0.3590517747218162, "grad_norm": 1.2970279322593918, "learning_rate": 3.9237903928380535e-05, "loss": 0.5802, "num_tokens": 201366362.0, "step": 33655 }, { "epoch": 0.3591051177280147, "grad_norm": 0.6403530808219219, "learning_rate": 3.9234517585743624e-05, "loss": 0.5279, "num_tokens": 201410433.0, "step": 33660 }, { "epoch": 0.35915846073421315, "grad_norm": 1.147941201774084, "learning_rate": 3.9231130877952625e-05, "loss": 0.6098, "num_tokens": 201444426.0, "step": 33665 }, { "epoch": 0.3592118037404116, "grad_norm": 1.620024260560849, "learning_rate": 3.922774380511294e-05, "loss": 0.7831, "num_tokens": 201475651.0, "step": 33670 }, { "epoch": 0.35926514674661003, "grad_norm": 1.384216049805203, "learning_rate": 3.922435636732994e-05, "loss": 0.5791, "num_tokens": 201516242.0, "step": 33675 }, { "epoch": 0.3593184897528085, "grad_norm": 0.7179900986359596, "learning_rate": 3.922096856470907e-05, "loss": 0.6301, "num_tokens": 201551143.0, "step": 33680 }, { "epoch": 0.35937183275900697, "grad_norm": 0.7507870610530825, "learning_rate": 3.921758039735573e-05, "loss": 0.5658, "num_tokens": 201580124.0, "step": 33685 }, { "epoch": 0.35942517576520544, "grad_norm": 1.2356348633571779, "learning_rate": 3.921419186537535e-05, "loss": 0.5614, "num_tokens": 201604198.0, "step": 33690 }, { "epoch": 0.35947851877140385, "grad_norm": 0.7060672985699683, "learning_rate": 3.921080296887339e-05, "loss": 0.5486, "num_tokens": 201640762.0, "step": 33695 }, { "epoch": 0.3595318617776023, "grad_norm": 1.5836260404293672, "learning_rate": 3.920741370795529e-05, "loss": 0.6091, "num_tokens": 201660648.0, "step": 33700 }, { "epoch": 0.3595852047838008, "grad_norm": 0.836248505328467, "learning_rate": 3.920402408272653e-05, "loss": 0.5332, "num_tokens": 201673839.0, "step": 33705 }, { "epoch": 0.35963854778999926, "grad_norm": 0.9288078178351818, "learning_rate": 3.920063409329257e-05, "loss": 0.6698, "num_tokens": 201723960.0, "step": 33710 }, { "epoch": 0.35969189079619773, "grad_norm": 0.9867810173998638, "learning_rate": 3.9197243739758924e-05, "loss": 0.41, "num_tokens": 201752411.0, "step": 33715 }, { "epoch": 0.35974523380239615, "grad_norm": 0.8218959796747239, "learning_rate": 3.9193853022231067e-05, "loss": 0.5134, "num_tokens": 201781695.0, "step": 33720 }, { "epoch": 0.3597985768085946, "grad_norm": 3.647357247998434, "learning_rate": 3.919046194081453e-05, "loss": 0.5445, "num_tokens": 201799677.0, "step": 33725 }, { "epoch": 0.3598519198147931, "grad_norm": 2.610249134408543, "learning_rate": 3.918707049561483e-05, "loss": 0.5614, "num_tokens": 201839393.0, "step": 33730 }, { "epoch": 0.35990526282099156, "grad_norm": 0.8288544261613561, "learning_rate": 3.9183678686737494e-05, "loss": 0.5939, "num_tokens": 201869882.0, "step": 33735 }, { "epoch": 0.35995860582718997, "grad_norm": 1.217946609164158, "learning_rate": 3.9180286514288085e-05, "loss": 0.5789, "num_tokens": 201900608.0, "step": 33740 }, { "epoch": 0.36001194883338844, "grad_norm": 1.2505073043500263, "learning_rate": 3.917689397837216e-05, "loss": 0.4316, "num_tokens": 201923012.0, "step": 33745 }, { "epoch": 0.3600652918395869, "grad_norm": 0.8939285154846358, "learning_rate": 3.917350107909526e-05, "loss": 0.5081, "num_tokens": 201948841.0, "step": 33750 }, { "epoch": 0.3601186348457854, "grad_norm": 1.9169345391024295, "learning_rate": 3.9170107816562996e-05, "loss": 0.6099, "num_tokens": 201981402.0, "step": 33755 }, { "epoch": 0.36017197785198385, "grad_norm": 0.8428846726526075, "learning_rate": 3.9166714190880945e-05, "loss": 0.6698, "num_tokens": 202001316.0, "step": 33760 }, { "epoch": 0.36022532085818226, "grad_norm": 0.9350862917189501, "learning_rate": 3.916332020215471e-05, "loss": 0.5366, "num_tokens": 202022043.0, "step": 33765 }, { "epoch": 0.36027866386438073, "grad_norm": 0.8251183508783699, "learning_rate": 3.915992585048992e-05, "loss": 0.5401, "num_tokens": 202049961.0, "step": 33770 }, { "epoch": 0.3603320068705792, "grad_norm": 0.8409463752447747, "learning_rate": 3.915653113599217e-05, "loss": 0.7219, "num_tokens": 202087266.0, "step": 33775 }, { "epoch": 0.36038534987677767, "grad_norm": 1.010725909527809, "learning_rate": 3.915313605876713e-05, "loss": 0.4976, "num_tokens": 202113447.0, "step": 33780 }, { "epoch": 0.3604386928829761, "grad_norm": 0.7670238793343406, "learning_rate": 3.914974061892042e-05, "loss": 0.6614, "num_tokens": 202148100.0, "step": 33785 }, { "epoch": 0.36049203588917456, "grad_norm": 0.7747187419129528, "learning_rate": 3.914634481655772e-05, "loss": 0.6394, "num_tokens": 202182355.0, "step": 33790 }, { "epoch": 0.360545378895373, "grad_norm": 1.364395738523349, "learning_rate": 3.914294865178469e-05, "loss": 0.4768, "num_tokens": 202199301.0, "step": 33795 }, { "epoch": 0.3605987219015715, "grad_norm": 0.6143566499297826, "learning_rate": 3.913955212470701e-05, "loss": 0.4886, "num_tokens": 202235031.0, "step": 33800 }, { "epoch": 0.36065206490776996, "grad_norm": 1.654247353449887, "learning_rate": 3.913615523543037e-05, "loss": 0.6914, "num_tokens": 202266772.0, "step": 33805 }, { "epoch": 0.3607054079139684, "grad_norm": 1.2740998602084694, "learning_rate": 3.9132757984060484e-05, "loss": 0.6018, "num_tokens": 202303650.0, "step": 33810 }, { "epoch": 0.36075875092016685, "grad_norm": 0.7935642303527117, "learning_rate": 3.912936037070308e-05, "loss": 0.5514, "num_tokens": 202328641.0, "step": 33815 }, { "epoch": 0.3608120939263653, "grad_norm": 1.2088715613536096, "learning_rate": 3.912596239546385e-05, "loss": 0.4685, "num_tokens": 202359552.0, "step": 33820 }, { "epoch": 0.3608654369325638, "grad_norm": 0.8735823180253164, "learning_rate": 3.912256405844856e-05, "loss": 0.6891, "num_tokens": 202380516.0, "step": 33825 }, { "epoch": 0.3609187799387622, "grad_norm": 1.9427231855484135, "learning_rate": 3.911916535976294e-05, "loss": 0.5279, "num_tokens": 202403015.0, "step": 33830 }, { "epoch": 0.36097212294496067, "grad_norm": 0.782743014185841, "learning_rate": 3.911576629951277e-05, "loss": 0.6185, "num_tokens": 202445161.0, "step": 33835 }, { "epoch": 0.36102546595115914, "grad_norm": 1.3258907082232805, "learning_rate": 3.911236687780381e-05, "loss": 0.6385, "num_tokens": 202475799.0, "step": 33840 }, { "epoch": 0.3610788089573576, "grad_norm": 0.8395005971735229, "learning_rate": 3.910896709474185e-05, "loss": 0.5205, "num_tokens": 202506697.0, "step": 33845 }, { "epoch": 0.3611321519635561, "grad_norm": 0.9598769165244251, "learning_rate": 3.910556695043267e-05, "loss": 0.5082, "num_tokens": 202524291.0, "step": 33850 }, { "epoch": 0.3611854949697545, "grad_norm": 0.803463897235123, "learning_rate": 3.9102166444982084e-05, "loss": 0.5117, "num_tokens": 202571966.0, "step": 33855 }, { "epoch": 0.36123883797595296, "grad_norm": 0.8754491114377595, "learning_rate": 3.909876557849592e-05, "loss": 0.4863, "num_tokens": 202592333.0, "step": 33860 }, { "epoch": 0.36129218098215143, "grad_norm": 1.0802058362601885, "learning_rate": 3.909536435107999e-05, "loss": 0.4905, "num_tokens": 202609143.0, "step": 33865 }, { "epoch": 0.3613455239883499, "grad_norm": 0.9069160708344299, "learning_rate": 3.909196276284014e-05, "loss": 0.4822, "num_tokens": 202626184.0, "step": 33870 }, { "epoch": 0.3613988669945483, "grad_norm": 1.0688214386098562, "learning_rate": 3.908856081388222e-05, "loss": 0.6106, "num_tokens": 202653840.0, "step": 33875 }, { "epoch": 0.3614522100007468, "grad_norm": 1.2479157476625329, "learning_rate": 3.908515850431209e-05, "loss": 0.5798, "num_tokens": 202678885.0, "step": 33880 }, { "epoch": 0.36150555300694526, "grad_norm": 2.004540948387666, "learning_rate": 3.908175583423562e-05, "loss": 0.4871, "num_tokens": 202698248.0, "step": 33885 }, { "epoch": 0.3615588960131437, "grad_norm": 1.24919604019098, "learning_rate": 3.907835280375871e-05, "loss": 0.5318, "num_tokens": 202724399.0, "step": 33890 }, { "epoch": 0.3616122390193422, "grad_norm": 0.9370395030035429, "learning_rate": 3.907494941298723e-05, "loss": 0.6151, "num_tokens": 202746825.0, "step": 33895 }, { "epoch": 0.3616655820255406, "grad_norm": 1.0820928199394606, "learning_rate": 3.9071545662027104e-05, "loss": 0.3989, "num_tokens": 202765137.0, "step": 33900 }, { "epoch": 0.3617189250317391, "grad_norm": 0.7043750376662656, "learning_rate": 3.906814155098425e-05, "loss": 0.4934, "num_tokens": 202814434.0, "step": 33905 }, { "epoch": 0.36177226803793755, "grad_norm": 0.8897185986426177, "learning_rate": 3.906473707996459e-05, "loss": 0.6056, "num_tokens": 202853577.0, "step": 33910 }, { "epoch": 0.361825611044136, "grad_norm": 0.9636992324394372, "learning_rate": 3.906133224907406e-05, "loss": 0.576, "num_tokens": 202870238.0, "step": 33915 }, { "epoch": 0.36187895405033443, "grad_norm": 0.8978497934007306, "learning_rate": 3.905792705841863e-05, "loss": 0.5816, "num_tokens": 202903048.0, "step": 33920 }, { "epoch": 0.3619322970565329, "grad_norm": 0.9780929036013801, "learning_rate": 3.905452150810425e-05, "loss": 0.525, "num_tokens": 202917487.0, "step": 33925 }, { "epoch": 0.3619856400627314, "grad_norm": 0.8263907112046394, "learning_rate": 3.9051115598236884e-05, "loss": 0.6125, "num_tokens": 202949029.0, "step": 33930 }, { "epoch": 0.36203898306892984, "grad_norm": 1.338209232788585, "learning_rate": 3.904770932892253e-05, "loss": 0.5773, "num_tokens": 202974593.0, "step": 33935 }, { "epoch": 0.3620923260751283, "grad_norm": 0.8006514196827585, "learning_rate": 3.904430270026719e-05, "loss": 0.5534, "num_tokens": 203009519.0, "step": 33940 }, { "epoch": 0.3621456690813267, "grad_norm": 1.5483608811944891, "learning_rate": 3.9040895712376854e-05, "loss": 0.5586, "num_tokens": 203042789.0, "step": 33945 }, { "epoch": 0.3621990120875252, "grad_norm": 1.5553796624414526, "learning_rate": 3.903748836535755e-05, "loss": 0.547, "num_tokens": 203071876.0, "step": 33950 }, { "epoch": 0.36225235509372367, "grad_norm": 1.1168146811574042, "learning_rate": 3.9034080659315306e-05, "loss": 0.522, "num_tokens": 203090803.0, "step": 33955 }, { "epoch": 0.36230569809992214, "grad_norm": 0.9182345047563747, "learning_rate": 3.9030672594356164e-05, "loss": 0.4767, "num_tokens": 203113332.0, "step": 33960 }, { "epoch": 0.36235904110612055, "grad_norm": 2.6426228786201764, "learning_rate": 3.902726417058619e-05, "loss": 0.6336, "num_tokens": 203127544.0, "step": 33965 }, { "epoch": 0.362412384112319, "grad_norm": 1.075558568583535, "learning_rate": 3.902385538811141e-05, "loss": 0.572, "num_tokens": 203157914.0, "step": 33970 }, { "epoch": 0.3624657271185175, "grad_norm": 0.9348354993802829, "learning_rate": 3.9020446247037934e-05, "loss": 0.5127, "num_tokens": 203177859.0, "step": 33975 }, { "epoch": 0.36251907012471596, "grad_norm": 0.9080395733641737, "learning_rate": 3.9017036747471835e-05, "loss": 0.5013, "num_tokens": 203206205.0, "step": 33980 }, { "epoch": 0.36257241313091443, "grad_norm": 0.7964015828814807, "learning_rate": 3.9013626889519205e-05, "loss": 0.5108, "num_tokens": 203234796.0, "step": 33985 }, { "epoch": 0.36262575613711284, "grad_norm": 1.839005463203751, "learning_rate": 3.901021667328615e-05, "loss": 0.6378, "num_tokens": 203253442.0, "step": 33990 }, { "epoch": 0.3626790991433113, "grad_norm": 0.9976072578183101, "learning_rate": 3.900680609887881e-05, "loss": 0.5696, "num_tokens": 203275130.0, "step": 33995 }, { "epoch": 0.3627324421495098, "grad_norm": 1.5031760192098846, "learning_rate": 3.900339516640329e-05, "loss": 0.6471, "num_tokens": 203300310.0, "step": 34000 }, { "epoch": 0.36278578515570825, "grad_norm": 1.0736934227867676, "learning_rate": 3.899998387596574e-05, "loss": 0.4889, "num_tokens": 203318906.0, "step": 34005 }, { "epoch": 0.36283912816190667, "grad_norm": 2.8486286574517603, "learning_rate": 3.899657222767232e-05, "loss": 0.6358, "num_tokens": 203333283.0, "step": 34010 }, { "epoch": 0.36289247116810514, "grad_norm": 1.233837732304909, "learning_rate": 3.8993160221629174e-05, "loss": 0.5615, "num_tokens": 203367135.0, "step": 34015 }, { "epoch": 0.3629458141743036, "grad_norm": 0.8014976625261768, "learning_rate": 3.898974785794251e-05, "loss": 0.6382, "num_tokens": 203391671.0, "step": 34020 }, { "epoch": 0.3629991571805021, "grad_norm": 1.6234742483633173, "learning_rate": 3.8986335136718476e-05, "loss": 0.6387, "num_tokens": 203414034.0, "step": 34025 }, { "epoch": 0.36305250018670054, "grad_norm": 2.672786731108279, "learning_rate": 3.8982922058063284e-05, "loss": 0.5808, "num_tokens": 203437793.0, "step": 34030 }, { "epoch": 0.36310584319289896, "grad_norm": 0.9482366137203776, "learning_rate": 3.897950862208316e-05, "loss": 0.5859, "num_tokens": 203472577.0, "step": 34035 }, { "epoch": 0.36315918619909743, "grad_norm": 0.8672043124473741, "learning_rate": 3.8976094828884295e-05, "loss": 0.5351, "num_tokens": 203511712.0, "step": 34040 }, { "epoch": 0.3632125292052959, "grad_norm": 0.8977248340753902, "learning_rate": 3.897268067857294e-05, "loss": 0.6152, "num_tokens": 203545140.0, "step": 34045 }, { "epoch": 0.36326587221149437, "grad_norm": 1.2164082565621896, "learning_rate": 3.8969266171255324e-05, "loss": 0.5106, "num_tokens": 203581305.0, "step": 34050 }, { "epoch": 0.3633192152176928, "grad_norm": 0.7708657813356071, "learning_rate": 3.89658513070377e-05, "loss": 0.5563, "num_tokens": 203618016.0, "step": 34055 }, { "epoch": 0.36337255822389125, "grad_norm": 1.0956790758604005, "learning_rate": 3.896243608602634e-05, "loss": 0.6034, "num_tokens": 203658280.0, "step": 34060 }, { "epoch": 0.3634259012300897, "grad_norm": 1.4253005971972663, "learning_rate": 3.895902050832751e-05, "loss": 0.5585, "num_tokens": 203684343.0, "step": 34065 }, { "epoch": 0.3634792442362882, "grad_norm": 0.7276409563969415, "learning_rate": 3.89556045740475e-05, "loss": 0.5264, "num_tokens": 203718072.0, "step": 34070 }, { "epoch": 0.36353258724248666, "grad_norm": 1.2049182510453706, "learning_rate": 3.8952188283292605e-05, "loss": 0.5797, "num_tokens": 203734688.0, "step": 34075 }, { "epoch": 0.3635859302486851, "grad_norm": 0.7113400068361794, "learning_rate": 3.8948771636169126e-05, "loss": 0.5892, "num_tokens": 203775449.0, "step": 34080 }, { "epoch": 0.36363927325488354, "grad_norm": 0.8679943704869815, "learning_rate": 3.894535463278341e-05, "loss": 0.4307, "num_tokens": 203803152.0, "step": 34085 }, { "epoch": 0.363692616261082, "grad_norm": 0.8231210446120709, "learning_rate": 3.8941937273241765e-05, "loss": 0.4912, "num_tokens": 203841481.0, "step": 34090 }, { "epoch": 0.3637459592672805, "grad_norm": 3.5047715266376263, "learning_rate": 3.8938519557650516e-05, "loss": 0.6067, "num_tokens": 203871017.0, "step": 34095 }, { "epoch": 0.3637993022734789, "grad_norm": 0.8680826061136853, "learning_rate": 3.8935101486116046e-05, "loss": 0.5126, "num_tokens": 203895271.0, "step": 34100 }, { "epoch": 0.36385264527967737, "grad_norm": 1.2178541288030509, "learning_rate": 3.893168305874471e-05, "loss": 0.5379, "num_tokens": 203911843.0, "step": 34105 }, { "epoch": 0.36390598828587584, "grad_norm": 0.6504119066962116, "learning_rate": 3.892826427564287e-05, "loss": 0.669, "num_tokens": 203947271.0, "step": 34110 }, { "epoch": 0.3639593312920743, "grad_norm": 1.1825711018808567, "learning_rate": 3.892484513691692e-05, "loss": 0.5203, "num_tokens": 203972998.0, "step": 34115 }, { "epoch": 0.3640126742982728, "grad_norm": 0.7658162885636325, "learning_rate": 3.892142564267326e-05, "loss": 0.6341, "num_tokens": 204007715.0, "step": 34120 }, { "epoch": 0.3640660173044712, "grad_norm": 4.627580435780733, "learning_rate": 3.8918005793018296e-05, "loss": 0.4593, "num_tokens": 204019012.0, "step": 34125 }, { "epoch": 0.36411936031066966, "grad_norm": 1.171748926460027, "learning_rate": 3.891458558805844e-05, "loss": 0.6779, "num_tokens": 204059643.0, "step": 34130 }, { "epoch": 0.36417270331686813, "grad_norm": 2.0801264515925624, "learning_rate": 3.891116502790013e-05, "loss": 0.5622, "num_tokens": 204098277.0, "step": 34135 }, { "epoch": 0.3642260463230666, "grad_norm": 0.8335474563359473, "learning_rate": 3.89077441126498e-05, "loss": 0.5653, "num_tokens": 204134972.0, "step": 34140 }, { "epoch": 0.364279389329265, "grad_norm": 0.6479136186231581, "learning_rate": 3.8904322842413914e-05, "loss": 0.6038, "num_tokens": 204170478.0, "step": 34145 }, { "epoch": 0.3643327323354635, "grad_norm": 0.7841553486116785, "learning_rate": 3.890090121729892e-05, "loss": 0.6654, "num_tokens": 204204938.0, "step": 34150 }, { "epoch": 0.36438607534166195, "grad_norm": 1.3518901624971387, "learning_rate": 3.8897479237411294e-05, "loss": 0.5579, "num_tokens": 204230210.0, "step": 34155 }, { "epoch": 0.3644394183478604, "grad_norm": 0.6786047226987664, "learning_rate": 3.889405690285753e-05, "loss": 0.5703, "num_tokens": 204261261.0, "step": 34160 }, { "epoch": 0.3644927613540589, "grad_norm": 0.7184606480120925, "learning_rate": 3.889063421374412e-05, "loss": 0.5594, "num_tokens": 204295137.0, "step": 34165 }, { "epoch": 0.3645461043602573, "grad_norm": 1.0331864235022556, "learning_rate": 3.888721117017757e-05, "loss": 0.5162, "num_tokens": 204322138.0, "step": 34170 }, { "epoch": 0.3645994473664558, "grad_norm": 0.8866036424305073, "learning_rate": 3.88837877722644e-05, "loss": 0.5642, "num_tokens": 204349995.0, "step": 34175 }, { "epoch": 0.36465279037265425, "grad_norm": 0.9150484205523591, "learning_rate": 3.888036402011114e-05, "loss": 0.513, "num_tokens": 204389650.0, "step": 34180 }, { "epoch": 0.3647061333788527, "grad_norm": 1.036152873219956, "learning_rate": 3.8876939913824315e-05, "loss": 0.5247, "num_tokens": 204418713.0, "step": 34185 }, { "epoch": 0.36475947638505113, "grad_norm": 0.8870839473567046, "learning_rate": 3.88735154535105e-05, "loss": 0.5757, "num_tokens": 204459796.0, "step": 34190 }, { "epoch": 0.3648128193912496, "grad_norm": 0.6044058982443247, "learning_rate": 3.887009063927624e-05, "loss": 0.5618, "num_tokens": 204497198.0, "step": 34195 }, { "epoch": 0.36486616239744807, "grad_norm": 1.0267753056221507, "learning_rate": 3.886666547122813e-05, "loss": 0.4814, "num_tokens": 204524073.0, "step": 34200 }, { "epoch": 0.36491950540364654, "grad_norm": 1.7908280092589526, "learning_rate": 3.8863239949472716e-05, "loss": 0.4978, "num_tokens": 204557618.0, "step": 34205 }, { "epoch": 0.364972848409845, "grad_norm": 1.0581439984897483, "learning_rate": 3.8859814074116625e-05, "loss": 0.5284, "num_tokens": 204597736.0, "step": 34210 }, { "epoch": 0.3650261914160434, "grad_norm": 1.0495621023485582, "learning_rate": 3.8856387845266464e-05, "loss": 0.5117, "num_tokens": 204616467.0, "step": 34215 }, { "epoch": 0.3650795344222419, "grad_norm": 0.915868996810418, "learning_rate": 3.8852961263028825e-05, "loss": 0.5616, "num_tokens": 204640028.0, "step": 34220 }, { "epoch": 0.36513287742844036, "grad_norm": 1.093963411552527, "learning_rate": 3.884953432751035e-05, "loss": 0.6181, "num_tokens": 204668203.0, "step": 34225 }, { "epoch": 0.36518622043463883, "grad_norm": 0.672032084467009, "learning_rate": 3.8846107038817683e-05, "loss": 0.4961, "num_tokens": 204699294.0, "step": 34230 }, { "epoch": 0.36523956344083724, "grad_norm": 1.1022578507139766, "learning_rate": 3.884267939705748e-05, "loss": 0.7475, "num_tokens": 204732202.0, "step": 34235 }, { "epoch": 0.3652929064470357, "grad_norm": 1.2882221799422213, "learning_rate": 3.8839251402336386e-05, "loss": 0.5943, "num_tokens": 204769389.0, "step": 34240 }, { "epoch": 0.3653462494532342, "grad_norm": 0.7291099903024699, "learning_rate": 3.8835823054761074e-05, "loss": 0.4894, "num_tokens": 204807136.0, "step": 34245 }, { "epoch": 0.36539959245943265, "grad_norm": 1.7442918001698955, "learning_rate": 3.883239435443824e-05, "loss": 0.5368, "num_tokens": 204831917.0, "step": 34250 }, { "epoch": 0.3654529354656311, "grad_norm": 0.9120547101941133, "learning_rate": 3.8828965301474565e-05, "loss": 0.5141, "num_tokens": 204864234.0, "step": 34255 }, { "epoch": 0.36550627847182954, "grad_norm": 0.825241216318256, "learning_rate": 3.8825535895976766e-05, "loss": 0.5151, "num_tokens": 204893303.0, "step": 34260 }, { "epoch": 0.365559621478028, "grad_norm": 2.4242269882366814, "learning_rate": 3.8822106138051556e-05, "loss": 0.7322, "num_tokens": 204933779.0, "step": 34265 }, { "epoch": 0.3656129644842265, "grad_norm": 2.0079614856761565, "learning_rate": 3.881867602780565e-05, "loss": 0.7083, "num_tokens": 204978354.0, "step": 34270 }, { "epoch": 0.36566630749042495, "grad_norm": 0.8923065627584937, "learning_rate": 3.88152455653458e-05, "loss": 0.4686, "num_tokens": 205008141.0, "step": 34275 }, { "epoch": 0.36571965049662336, "grad_norm": 1.4181880637634103, "learning_rate": 3.881181475077876e-05, "loss": 0.5312, "num_tokens": 205033472.0, "step": 34280 }, { "epoch": 0.36577299350282183, "grad_norm": 2.486159155012354, "learning_rate": 3.880838358421127e-05, "loss": 0.6865, "num_tokens": 205057161.0, "step": 34285 }, { "epoch": 0.3658263365090203, "grad_norm": 1.0819176780683295, "learning_rate": 3.8804952065750107e-05, "loss": 0.5711, "num_tokens": 205090047.0, "step": 34290 }, { "epoch": 0.36587967951521877, "grad_norm": 1.2693849493662501, "learning_rate": 3.880152019550206e-05, "loss": 0.6079, "num_tokens": 205117160.0, "step": 34295 }, { "epoch": 0.36593302252141724, "grad_norm": 1.398170586450604, "learning_rate": 3.879808797357392e-05, "loss": 0.5844, "num_tokens": 205147994.0, "step": 34300 }, { "epoch": 0.36598636552761565, "grad_norm": 1.110482153453631, "learning_rate": 3.8794655400072485e-05, "loss": 0.5181, "num_tokens": 205176007.0, "step": 34305 }, { "epoch": 0.3660397085338141, "grad_norm": 1.0407143891404549, "learning_rate": 3.879122247510459e-05, "loss": 0.5044, "num_tokens": 205209779.0, "step": 34310 }, { "epoch": 0.3660930515400126, "grad_norm": 1.2966503607655908, "learning_rate": 3.878778919877703e-05, "loss": 0.5341, "num_tokens": 205241731.0, "step": 34315 }, { "epoch": 0.36614639454621106, "grad_norm": 0.8250548213357365, "learning_rate": 3.878435557119665e-05, "loss": 0.6197, "num_tokens": 205270172.0, "step": 34320 }, { "epoch": 0.3661997375524095, "grad_norm": 1.0454935456812657, "learning_rate": 3.878092159247032e-05, "loss": 0.4838, "num_tokens": 205299721.0, "step": 34325 }, { "epoch": 0.36625308055860795, "grad_norm": 1.0111103519897462, "learning_rate": 3.877748726270487e-05, "loss": 0.6656, "num_tokens": 205322952.0, "step": 34330 }, { "epoch": 0.3663064235648064, "grad_norm": 1.0483696012203298, "learning_rate": 3.877405258200718e-05, "loss": 0.5657, "num_tokens": 205356656.0, "step": 34335 }, { "epoch": 0.3663597665710049, "grad_norm": 1.365411742858727, "learning_rate": 3.877061755048414e-05, "loss": 0.5909, "num_tokens": 205380448.0, "step": 34340 }, { "epoch": 0.36641310957720336, "grad_norm": 0.7447372222788389, "learning_rate": 3.8767182168242625e-05, "loss": 0.575, "num_tokens": 205430276.0, "step": 34345 }, { "epoch": 0.36646645258340177, "grad_norm": 1.4521870453799357, "learning_rate": 3.8763746435389547e-05, "loss": 0.4749, "num_tokens": 205453618.0, "step": 34350 }, { "epoch": 0.36651979558960024, "grad_norm": 0.8915678640936694, "learning_rate": 3.876031035203182e-05, "loss": 0.4737, "num_tokens": 205476312.0, "step": 34355 }, { "epoch": 0.3665731385957987, "grad_norm": 1.7858078069643095, "learning_rate": 3.8756873918276354e-05, "loss": 0.4245, "num_tokens": 205494090.0, "step": 34360 }, { "epoch": 0.3666264816019972, "grad_norm": 0.9151589803095591, "learning_rate": 3.8753437134230106e-05, "loss": 0.554, "num_tokens": 205532424.0, "step": 34365 }, { "epoch": 0.3666798246081956, "grad_norm": 0.7803267463381386, "learning_rate": 3.875e-05, "loss": 0.4539, "num_tokens": 205552279.0, "step": 34370 }, { "epoch": 0.36673316761439406, "grad_norm": 0.9519267359645596, "learning_rate": 3.8746562515693007e-05, "loss": 0.7058, "num_tokens": 205589898.0, "step": 34375 }, { "epoch": 0.36678651062059253, "grad_norm": 1.028211292098216, "learning_rate": 3.8743124681416096e-05, "loss": 0.4857, "num_tokens": 205614784.0, "step": 34380 }, { "epoch": 0.366839853626791, "grad_norm": 1.8825148101510474, "learning_rate": 3.873968649727623e-05, "loss": 0.6436, "num_tokens": 205644330.0, "step": 34385 }, { "epoch": 0.36689319663298947, "grad_norm": 1.0685082228571894, "learning_rate": 3.87362479633804e-05, "loss": 0.5428, "num_tokens": 205672097.0, "step": 34390 }, { "epoch": 0.3669465396391879, "grad_norm": 0.9757950800183212, "learning_rate": 3.873280907983563e-05, "loss": 0.6654, "num_tokens": 205708721.0, "step": 34395 }, { "epoch": 0.36699988264538635, "grad_norm": 1.3491698464845652, "learning_rate": 3.872936984674891e-05, "loss": 0.5154, "num_tokens": 205730596.0, "step": 34400 }, { "epoch": 0.3670532256515848, "grad_norm": 0.913594380459708, "learning_rate": 3.8725930264227256e-05, "loss": 0.6144, "num_tokens": 205771649.0, "step": 34405 }, { "epoch": 0.3671065686577833, "grad_norm": 1.1921438993453803, "learning_rate": 3.872249033237772e-05, "loss": 0.572, "num_tokens": 205801653.0, "step": 34410 }, { "epoch": 0.3671599116639817, "grad_norm": 1.533159317133618, "learning_rate": 3.871905005130733e-05, "loss": 0.4928, "num_tokens": 205821007.0, "step": 34415 }, { "epoch": 0.3672132546701802, "grad_norm": 0.6596681993260676, "learning_rate": 3.8715609421123155e-05, "loss": 0.5507, "num_tokens": 205865157.0, "step": 34420 }, { "epoch": 0.36726659767637865, "grad_norm": 1.7597678776310943, "learning_rate": 3.871216844193225e-05, "loss": 0.5173, "num_tokens": 205910149.0, "step": 34425 }, { "epoch": 0.3673199406825771, "grad_norm": 1.028499085229139, "learning_rate": 3.8708727113841694e-05, "loss": 0.5202, "num_tokens": 205937718.0, "step": 34430 }, { "epoch": 0.3673732836887756, "grad_norm": 0.8905103700963007, "learning_rate": 3.8705285436958564e-05, "loss": 0.531, "num_tokens": 205974716.0, "step": 34435 }, { "epoch": 0.367426626694974, "grad_norm": 1.3145496148776619, "learning_rate": 3.870184341138998e-05, "loss": 0.576, "num_tokens": 206014318.0, "step": 34440 }, { "epoch": 0.36747996970117247, "grad_norm": 1.1767550730737508, "learning_rate": 3.8698401037243034e-05, "loss": 0.6573, "num_tokens": 206043864.0, "step": 34445 }, { "epoch": 0.36753331270737094, "grad_norm": 1.3729447194477638, "learning_rate": 3.8694958314624845e-05, "loss": 0.4792, "num_tokens": 206089755.0, "step": 34450 }, { "epoch": 0.3675866557135694, "grad_norm": 1.7399053289640263, "learning_rate": 3.869151524364256e-05, "loss": 0.5043, "num_tokens": 206103819.0, "step": 34455 }, { "epoch": 0.3676399987197678, "grad_norm": 0.7435711676160183, "learning_rate": 3.86880718244033e-05, "loss": 0.7537, "num_tokens": 206140323.0, "step": 34460 }, { "epoch": 0.3676933417259663, "grad_norm": 1.4393977607986475, "learning_rate": 3.868462805701423e-05, "loss": 0.6329, "num_tokens": 206165284.0, "step": 34465 }, { "epoch": 0.36774668473216476, "grad_norm": 1.0091960939370677, "learning_rate": 3.86811839415825e-05, "loss": 0.5144, "num_tokens": 206179107.0, "step": 34470 }, { "epoch": 0.36780002773836323, "grad_norm": 0.695277393596224, "learning_rate": 3.8677739478215304e-05, "loss": 0.5786, "num_tokens": 206233924.0, "step": 34475 }, { "epoch": 0.3678533707445617, "grad_norm": 0.601560545472359, "learning_rate": 3.86742946670198e-05, "loss": 0.5299, "num_tokens": 206283862.0, "step": 34480 }, { "epoch": 0.3679067137507601, "grad_norm": 1.6874718951169558, "learning_rate": 3.8670849508103206e-05, "loss": 0.5687, "num_tokens": 206308359.0, "step": 34485 }, { "epoch": 0.3679600567569586, "grad_norm": 0.9383761894209, "learning_rate": 3.866740400157273e-05, "loss": 0.6861, "num_tokens": 206346063.0, "step": 34490 }, { "epoch": 0.36801339976315706, "grad_norm": 1.0024242742242044, "learning_rate": 3.8663958147535575e-05, "loss": 0.7118, "num_tokens": 206389436.0, "step": 34495 }, { "epoch": 0.3680667427693555, "grad_norm": 1.4463197009487165, "learning_rate": 3.866051194609897e-05, "loss": 0.6959, "num_tokens": 206410214.0, "step": 34500 }, { "epoch": 0.36812008577555394, "grad_norm": 0.7793863292023651, "learning_rate": 3.865706539737016e-05, "loss": 0.5401, "num_tokens": 206435419.0, "step": 34505 }, { "epoch": 0.3681734287817524, "grad_norm": 0.9972778172093852, "learning_rate": 3.865361850145639e-05, "loss": 0.5558, "num_tokens": 206454897.0, "step": 34510 }, { "epoch": 0.3682267717879509, "grad_norm": 1.3624062812127153, "learning_rate": 3.8650171258464926e-05, "loss": 0.5475, "num_tokens": 206476859.0, "step": 34515 }, { "epoch": 0.36828011479414935, "grad_norm": 1.2228171900192, "learning_rate": 3.8646723668503034e-05, "loss": 0.5276, "num_tokens": 206504229.0, "step": 34520 }, { "epoch": 0.3683334578003478, "grad_norm": 0.8468672208194766, "learning_rate": 3.8643275731678005e-05, "loss": 0.552, "num_tokens": 206541772.0, "step": 34525 }, { "epoch": 0.36838680080654623, "grad_norm": 1.3378516789099284, "learning_rate": 3.863982744809711e-05, "loss": 0.5768, "num_tokens": 206568149.0, "step": 34530 }, { "epoch": 0.3684401438127447, "grad_norm": 1.3482676130391833, "learning_rate": 3.863637881786767e-05, "loss": 0.5189, "num_tokens": 206584177.0, "step": 34535 }, { "epoch": 0.3684934868189432, "grad_norm": 1.5958076389910405, "learning_rate": 3.8632929841097e-05, "loss": 0.4914, "num_tokens": 206612861.0, "step": 34540 }, { "epoch": 0.36854682982514164, "grad_norm": 0.9135448454690319, "learning_rate": 3.862948051789242e-05, "loss": 0.6773, "num_tokens": 206644236.0, "step": 34545 }, { "epoch": 0.36860017283134006, "grad_norm": 0.6510146157485013, "learning_rate": 3.8626030848361266e-05, "loss": 0.5173, "num_tokens": 206691086.0, "step": 34550 }, { "epoch": 0.3686535158375385, "grad_norm": 1.081013011931967, "learning_rate": 3.862258083261088e-05, "loss": 0.6966, "num_tokens": 206731293.0, "step": 34555 }, { "epoch": 0.368706858843737, "grad_norm": 0.9155297281691955, "learning_rate": 3.8619130470748636e-05, "loss": 0.4726, "num_tokens": 206761213.0, "step": 34560 }, { "epoch": 0.36876020184993547, "grad_norm": 1.524093066455536, "learning_rate": 3.861567976288189e-05, "loss": 0.7429, "num_tokens": 206799055.0, "step": 34565 }, { "epoch": 0.36881354485613393, "grad_norm": 1.0167005921367707, "learning_rate": 3.861222870911801e-05, "loss": 0.5601, "num_tokens": 206837511.0, "step": 34570 }, { "epoch": 0.36886688786233235, "grad_norm": 1.3905279434153732, "learning_rate": 3.860877730956441e-05, "loss": 0.642, "num_tokens": 206861481.0, "step": 34575 }, { "epoch": 0.3689202308685308, "grad_norm": 0.779898691179601, "learning_rate": 3.8605325564328474e-05, "loss": 0.5255, "num_tokens": 206889014.0, "step": 34580 }, { "epoch": 0.3689735738747293, "grad_norm": 0.650164463716618, "learning_rate": 3.860187347351762e-05, "loss": 0.4561, "num_tokens": 206915917.0, "step": 34585 }, { "epoch": 0.36902691688092776, "grad_norm": 1.910266569182114, "learning_rate": 3.8598421037239265e-05, "loss": 0.521, "num_tokens": 206941483.0, "step": 34590 }, { "epoch": 0.36908025988712617, "grad_norm": 0.6976418560793137, "learning_rate": 3.859496825560084e-05, "loss": 0.6907, "num_tokens": 206976280.0, "step": 34595 }, { "epoch": 0.36913360289332464, "grad_norm": 0.9576865624506352, "learning_rate": 3.8591515128709806e-05, "loss": 0.5432, "num_tokens": 207008151.0, "step": 34600 }, { "epoch": 0.3691869458995231, "grad_norm": 0.8403340679971045, "learning_rate": 3.85880616566736e-05, "loss": 0.481, "num_tokens": 207028158.0, "step": 34605 }, { "epoch": 0.3692402889057216, "grad_norm": 0.926741675884379, "learning_rate": 3.858460783959968e-05, "loss": 0.4616, "num_tokens": 207050410.0, "step": 34610 }, { "epoch": 0.36929363191192005, "grad_norm": 0.6382049574328865, "learning_rate": 3.858115367759553e-05, "loss": 0.5312, "num_tokens": 207078925.0, "step": 34615 }, { "epoch": 0.36934697491811846, "grad_norm": 1.1293014943869746, "learning_rate": 3.857769917076866e-05, "loss": 0.7031, "num_tokens": 207108154.0, "step": 34620 }, { "epoch": 0.36940031792431693, "grad_norm": 1.0086836515984812, "learning_rate": 3.857424431922652e-05, "loss": 0.6328, "num_tokens": 207158573.0, "step": 34625 }, { "epoch": 0.3694536609305154, "grad_norm": 1.167819342947951, "learning_rate": 3.857078912307666e-05, "loss": 0.556, "num_tokens": 207191366.0, "step": 34630 }, { "epoch": 0.3695070039367139, "grad_norm": 1.6246213391489692, "learning_rate": 3.8567333582426586e-05, "loss": 0.5284, "num_tokens": 207227005.0, "step": 34635 }, { "epoch": 0.3695603469429123, "grad_norm": 0.8683742072934796, "learning_rate": 3.856387769738381e-05, "loss": 0.6849, "num_tokens": 207262112.0, "step": 34640 }, { "epoch": 0.36961368994911076, "grad_norm": 0.7553401751119785, "learning_rate": 3.8560421468055894e-05, "loss": 0.4737, "num_tokens": 207293501.0, "step": 34645 }, { "epoch": 0.3696670329553092, "grad_norm": 1.0251699903688722, "learning_rate": 3.8556964894550376e-05, "loss": 0.4491, "num_tokens": 207312870.0, "step": 34650 }, { "epoch": 0.3697203759615077, "grad_norm": 1.2212656298134872, "learning_rate": 3.855350797697484e-05, "loss": 0.4562, "num_tokens": 207342339.0, "step": 34655 }, { "epoch": 0.36977371896770617, "grad_norm": 2.287149254843514, "learning_rate": 3.8550050715436816e-05, "loss": 0.6601, "num_tokens": 207379700.0, "step": 34660 }, { "epoch": 0.3698270619739046, "grad_norm": 0.8756117158925049, "learning_rate": 3.854659311004392e-05, "loss": 0.4686, "num_tokens": 207410887.0, "step": 34665 }, { "epoch": 0.36988040498010305, "grad_norm": 1.8761327069739266, "learning_rate": 3.8543135160903743e-05, "loss": 0.6376, "num_tokens": 207436762.0, "step": 34670 }, { "epoch": 0.3699337479863015, "grad_norm": 1.0719961345332167, "learning_rate": 3.853967686812388e-05, "loss": 0.5722, "num_tokens": 207469213.0, "step": 34675 }, { "epoch": 0.3699870909925, "grad_norm": 1.4827657909860392, "learning_rate": 3.8536218231811946e-05, "loss": 0.4742, "num_tokens": 207491986.0, "step": 34680 }, { "epoch": 0.3700404339986984, "grad_norm": 1.0114997876422323, "learning_rate": 3.853275925207557e-05, "loss": 0.6835, "num_tokens": 207532907.0, "step": 34685 }, { "epoch": 0.3700937770048969, "grad_norm": 0.92692290791343, "learning_rate": 3.852929992902239e-05, "loss": 0.6334, "num_tokens": 207551585.0, "step": 34690 }, { "epoch": 0.37014712001109534, "grad_norm": 1.1419970542366928, "learning_rate": 3.8525840262760055e-05, "loss": 0.527, "num_tokens": 207589636.0, "step": 34695 }, { "epoch": 0.3702004630172938, "grad_norm": 0.9421202133691268, "learning_rate": 3.852238025339621e-05, "loss": 0.542, "num_tokens": 207612071.0, "step": 34700 }, { "epoch": 0.3702538060234923, "grad_norm": 1.0715120218420655, "learning_rate": 3.8518919901038535e-05, "loss": 0.5769, "num_tokens": 207641589.0, "step": 34705 }, { "epoch": 0.3703071490296907, "grad_norm": 0.7129140964005876, "learning_rate": 3.8515459205794714e-05, "loss": 0.6118, "num_tokens": 207684837.0, "step": 34710 }, { "epoch": 0.37036049203588917, "grad_norm": 0.8819782159283445, "learning_rate": 3.851199816777241e-05, "loss": 0.5266, "num_tokens": 207710038.0, "step": 34715 }, { "epoch": 0.37041383504208764, "grad_norm": 0.8280686521418946, "learning_rate": 3.8508536787079356e-05, "loss": 0.651, "num_tokens": 207742151.0, "step": 34720 }, { "epoch": 0.3704671780482861, "grad_norm": 0.8522498035117616, "learning_rate": 3.850507506382325e-05, "loss": 0.725, "num_tokens": 207785741.0, "step": 34725 }, { "epoch": 0.3705205210544845, "grad_norm": 0.5848827669628981, "learning_rate": 3.850161299811181e-05, "loss": 0.4473, "num_tokens": 207814077.0, "step": 34730 }, { "epoch": 0.370573864060683, "grad_norm": 1.1324611844707877, "learning_rate": 3.849815059005277e-05, "loss": 0.6854, "num_tokens": 207839684.0, "step": 34735 }, { "epoch": 0.37062720706688146, "grad_norm": 1.0063517259742898, "learning_rate": 3.849468783975388e-05, "loss": 0.4791, "num_tokens": 207866913.0, "step": 34740 }, { "epoch": 0.37068055007307993, "grad_norm": 1.6340909634983507, "learning_rate": 3.8491224747322886e-05, "loss": 0.6407, "num_tokens": 207900555.0, "step": 34745 }, { "epoch": 0.3707338930792784, "grad_norm": 1.0811823839170505, "learning_rate": 3.848776131286755e-05, "loss": 0.52, "num_tokens": 207929658.0, "step": 34750 }, { "epoch": 0.3707872360854768, "grad_norm": 0.7203587104829892, "learning_rate": 3.8484297536495665e-05, "loss": 0.6258, "num_tokens": 207961011.0, "step": 34755 }, { "epoch": 0.3708405790916753, "grad_norm": 0.9809927691090969, "learning_rate": 3.848083341831498e-05, "loss": 0.5775, "num_tokens": 207991085.0, "step": 34760 }, { "epoch": 0.37089392209787375, "grad_norm": 1.0093024241130415, "learning_rate": 3.847736895843333e-05, "loss": 0.5987, "num_tokens": 208019178.0, "step": 34765 }, { "epoch": 0.3709472651040722, "grad_norm": 0.9763258017596057, "learning_rate": 3.847390415695851e-05, "loss": 0.5498, "num_tokens": 208043927.0, "step": 34770 }, { "epoch": 0.37100060811027064, "grad_norm": 1.7765284972721602, "learning_rate": 3.847043901399832e-05, "loss": 0.4872, "num_tokens": 208080860.0, "step": 34775 }, { "epoch": 0.3710539511164691, "grad_norm": 0.8438383500270804, "learning_rate": 3.846697352966061e-05, "loss": 0.6854, "num_tokens": 208115056.0, "step": 34780 }, { "epoch": 0.3711072941226676, "grad_norm": 0.9380654879913524, "learning_rate": 3.846350770405322e-05, "loss": 0.4981, "num_tokens": 208134111.0, "step": 34785 }, { "epoch": 0.37116063712886604, "grad_norm": 1.092462992554961, "learning_rate": 3.846004153728397e-05, "loss": 0.4778, "num_tokens": 208155246.0, "step": 34790 }, { "epoch": 0.3712139801350645, "grad_norm": 0.6899743227517242, "learning_rate": 3.845657502946075e-05, "loss": 0.4783, "num_tokens": 208208841.0, "step": 34795 }, { "epoch": 0.37126732314126293, "grad_norm": 1.0766496057275676, "learning_rate": 3.845310818069142e-05, "loss": 0.4724, "num_tokens": 208239844.0, "step": 34800 }, { "epoch": 0.3713206661474614, "grad_norm": 0.9316150829706218, "learning_rate": 3.844964099108386e-05, "loss": 0.4885, "num_tokens": 208300764.0, "step": 34805 }, { "epoch": 0.37137400915365987, "grad_norm": 1.3049984001295822, "learning_rate": 3.844617346074597e-05, "loss": 0.4774, "num_tokens": 208324398.0, "step": 34810 }, { "epoch": 0.37142735215985834, "grad_norm": 0.8776012830703136, "learning_rate": 3.844270558978564e-05, "loss": 0.5147, "num_tokens": 208347540.0, "step": 34815 }, { "epoch": 0.37148069516605675, "grad_norm": 1.0970312991126756, "learning_rate": 3.843923737831079e-05, "loss": 0.6405, "num_tokens": 208389215.0, "step": 34820 }, { "epoch": 0.3715340381722552, "grad_norm": 0.9714690448879739, "learning_rate": 3.843576882642934e-05, "loss": 0.5482, "num_tokens": 208419537.0, "step": 34825 }, { "epoch": 0.3715873811784537, "grad_norm": 0.9160170716525696, "learning_rate": 3.843229993424923e-05, "loss": 0.6756, "num_tokens": 208471578.0, "step": 34830 }, { "epoch": 0.37164072418465216, "grad_norm": 0.5810816022243512, "learning_rate": 3.8428830701878404e-05, "loss": 0.5249, "num_tokens": 208513393.0, "step": 34835 }, { "epoch": 0.37169406719085063, "grad_norm": 1.2712314694669904, "learning_rate": 3.842536112942481e-05, "loss": 0.439, "num_tokens": 208537167.0, "step": 34840 }, { "epoch": 0.37174741019704904, "grad_norm": 0.8212552802604607, "learning_rate": 3.842189121699642e-05, "loss": 0.5129, "num_tokens": 208565625.0, "step": 34845 }, { "epoch": 0.3718007532032475, "grad_norm": 0.9281049179626754, "learning_rate": 3.8418420964701205e-05, "loss": 0.7294, "num_tokens": 208594595.0, "step": 34850 }, { "epoch": 0.371854096209446, "grad_norm": 2.071152657917311, "learning_rate": 3.8414950372647165e-05, "loss": 0.5653, "num_tokens": 208622957.0, "step": 34855 }, { "epoch": 0.37190743921564445, "grad_norm": 0.804639786569068, "learning_rate": 3.841147944094229e-05, "loss": 0.4927, "num_tokens": 208654378.0, "step": 34860 }, { "epoch": 0.37196078222184287, "grad_norm": 0.9176827432097779, "learning_rate": 3.8408008169694585e-05, "loss": 0.6728, "num_tokens": 208681740.0, "step": 34865 }, { "epoch": 0.37201412522804134, "grad_norm": 0.7478816854290875, "learning_rate": 3.8404536559012065e-05, "loss": 0.4999, "num_tokens": 208712883.0, "step": 34870 }, { "epoch": 0.3720674682342398, "grad_norm": 0.8441958315918233, "learning_rate": 3.840106460900278e-05, "loss": 0.4356, "num_tokens": 208734734.0, "step": 34875 }, { "epoch": 0.3721208112404383, "grad_norm": 0.81526156076887, "learning_rate": 3.839759231977474e-05, "loss": 0.5554, "num_tokens": 208772401.0, "step": 34880 }, { "epoch": 0.37217415424663675, "grad_norm": 1.1621415582298602, "learning_rate": 3.839411969143603e-05, "loss": 0.5462, "num_tokens": 208801113.0, "step": 34885 }, { "epoch": 0.37222749725283516, "grad_norm": 0.7211122752121938, "learning_rate": 3.839064672409468e-05, "loss": 0.578, "num_tokens": 208833144.0, "step": 34890 }, { "epoch": 0.37228084025903363, "grad_norm": 1.6381618462938805, "learning_rate": 3.838717341785877e-05, "loss": 0.6777, "num_tokens": 208859917.0, "step": 34895 }, { "epoch": 0.3723341832652321, "grad_norm": 0.7287288209498465, "learning_rate": 3.838369977283639e-05, "loss": 0.5173, "num_tokens": 208892032.0, "step": 34900 }, { "epoch": 0.37238752627143057, "grad_norm": 1.0085325665925307, "learning_rate": 3.8380225789135634e-05, "loss": 0.4672, "num_tokens": 208920380.0, "step": 34905 }, { "epoch": 0.372440869277629, "grad_norm": 1.2116957310361545, "learning_rate": 3.83767514668646e-05, "loss": 0.5317, "num_tokens": 208949500.0, "step": 34910 }, { "epoch": 0.37249421228382745, "grad_norm": 0.7275085740498808, "learning_rate": 3.8373276806131395e-05, "loss": 0.4827, "num_tokens": 208973604.0, "step": 34915 }, { "epoch": 0.3725475552900259, "grad_norm": 1.1010087143871932, "learning_rate": 3.836980180704415e-05, "loss": 0.4211, "num_tokens": 209002760.0, "step": 34920 }, { "epoch": 0.3726008982962244, "grad_norm": 1.2941893268313405, "learning_rate": 3.8366326469711e-05, "loss": 0.5608, "num_tokens": 209023102.0, "step": 34925 }, { "epoch": 0.37265424130242286, "grad_norm": 1.2132266051326466, "learning_rate": 3.8362850794240096e-05, "loss": 0.6315, "num_tokens": 209069996.0, "step": 34930 }, { "epoch": 0.3727075843086213, "grad_norm": 0.9168593282773749, "learning_rate": 3.8359374780739595e-05, "loss": 0.5994, "num_tokens": 209096839.0, "step": 34935 }, { "epoch": 0.37276092731481975, "grad_norm": 1.2217255485403857, "learning_rate": 3.835589842931763e-05, "loss": 0.6264, "num_tokens": 209113503.0, "step": 34940 }, { "epoch": 0.3728142703210182, "grad_norm": 1.2758356219991995, "learning_rate": 3.835242174008243e-05, "loss": 0.6444, "num_tokens": 209144433.0, "step": 34945 }, { "epoch": 0.3728676133272167, "grad_norm": 1.570574245738886, "learning_rate": 3.8348944713142146e-05, "loss": 0.5609, "num_tokens": 209183088.0, "step": 34950 }, { "epoch": 0.3729209563334151, "grad_norm": 1.4110351880654706, "learning_rate": 3.834546734860499e-05, "loss": 0.5022, "num_tokens": 209201420.0, "step": 34955 }, { "epoch": 0.37297429933961357, "grad_norm": 0.7171314699148259, "learning_rate": 3.834198964657917e-05, "loss": 0.6434, "num_tokens": 209226435.0, "step": 34960 }, { "epoch": 0.37302764234581204, "grad_norm": 0.8406988559195766, "learning_rate": 3.83385116071729e-05, "loss": 0.7642, "num_tokens": 209258976.0, "step": 34965 }, { "epoch": 0.3730809853520105, "grad_norm": 0.989675189026291, "learning_rate": 3.8335033230494404e-05, "loss": 0.5316, "num_tokens": 209295621.0, "step": 34970 }, { "epoch": 0.373134328358209, "grad_norm": 1.5639114817831403, "learning_rate": 3.833155451665194e-05, "loss": 0.4432, "num_tokens": 209322374.0, "step": 34975 }, { "epoch": 0.3731876713644074, "grad_norm": 0.7732820308062902, "learning_rate": 3.8328075465753746e-05, "loss": 0.6265, "num_tokens": 209359819.0, "step": 34980 }, { "epoch": 0.37324101437060586, "grad_norm": 1.625129871970537, "learning_rate": 3.832459607790809e-05, "loss": 0.4635, "num_tokens": 209380943.0, "step": 34985 }, { "epoch": 0.37329435737680433, "grad_norm": 1.8742800411178906, "learning_rate": 3.832111635322323e-05, "loss": 0.5032, "num_tokens": 209397799.0, "step": 34990 }, { "epoch": 0.3733477003830028, "grad_norm": 1.5812707505728658, "learning_rate": 3.831763629180746e-05, "loss": 0.4985, "num_tokens": 209415245.0, "step": 34995 }, { "epoch": 0.3734010433892012, "grad_norm": 0.9305202975562303, "learning_rate": 3.8314155893769064e-05, "loss": 0.6134, "num_tokens": 209441536.0, "step": 35000 }, { "epoch": 0.3734543863953997, "grad_norm": 1.0711912901713991, "learning_rate": 3.8310675159216353e-05, "loss": 0.606, "num_tokens": 209468178.0, "step": 35005 }, { "epoch": 0.37350772940159815, "grad_norm": 1.3440564663834755, "learning_rate": 3.8307194088257636e-05, "loss": 0.4637, "num_tokens": 209494423.0, "step": 35010 }, { "epoch": 0.3735610724077966, "grad_norm": 1.0372198653893245, "learning_rate": 3.830371268100124e-05, "loss": 0.5383, "num_tokens": 209517030.0, "step": 35015 }, { "epoch": 0.3736144154139951, "grad_norm": 1.185549444149175, "learning_rate": 3.830023093755549e-05, "loss": 0.5129, "num_tokens": 209551807.0, "step": 35020 }, { "epoch": 0.3736677584201935, "grad_norm": 1.051717347057428, "learning_rate": 3.829674885802875e-05, "loss": 0.5581, "num_tokens": 209576401.0, "step": 35025 }, { "epoch": 0.373721101426392, "grad_norm": 1.098714278765693, "learning_rate": 3.829326644252935e-05, "loss": 0.513, "num_tokens": 209600401.0, "step": 35030 }, { "epoch": 0.37377444443259045, "grad_norm": 0.9873970104667759, "learning_rate": 3.828978369116567e-05, "loss": 0.5037, "num_tokens": 209635516.0, "step": 35035 }, { "epoch": 0.3738277874387889, "grad_norm": 0.7418848908043596, "learning_rate": 3.8286300604046096e-05, "loss": 0.6242, "num_tokens": 209671527.0, "step": 35040 }, { "epoch": 0.37388113044498733, "grad_norm": 0.7653416720240855, "learning_rate": 3.828281718127899e-05, "loss": 0.7277, "num_tokens": 209700346.0, "step": 35045 }, { "epoch": 0.3739344734511858, "grad_norm": 1.0718639951592146, "learning_rate": 3.827933342297276e-05, "loss": 0.4886, "num_tokens": 209724954.0, "step": 35050 }, { "epoch": 0.37398781645738427, "grad_norm": 1.1411203206593517, "learning_rate": 3.827584932923583e-05, "loss": 0.5781, "num_tokens": 209755955.0, "step": 35055 }, { "epoch": 0.37404115946358274, "grad_norm": 1.071390656600695, "learning_rate": 3.827236490017659e-05, "loss": 0.6692, "num_tokens": 209785614.0, "step": 35060 }, { "epoch": 0.3740945024697812, "grad_norm": 2.086061113988016, "learning_rate": 3.826888013590349e-05, "loss": 0.6905, "num_tokens": 209813122.0, "step": 35065 }, { "epoch": 0.3741478454759796, "grad_norm": 0.9115947789158354, "learning_rate": 3.8265395036524956e-05, "loss": 0.5994, "num_tokens": 209840620.0, "step": 35070 }, { "epoch": 0.3742011884821781, "grad_norm": 0.8017511372674535, "learning_rate": 3.8261909602149446e-05, "loss": 0.4888, "num_tokens": 209871376.0, "step": 35075 }, { "epoch": 0.37425453148837656, "grad_norm": 1.0786831062540436, "learning_rate": 3.8258423832885406e-05, "loss": 0.4445, "num_tokens": 209887089.0, "step": 35080 }, { "epoch": 0.37430787449457503, "grad_norm": 1.1003581795870616, "learning_rate": 3.825493772884132e-05, "loss": 0.5984, "num_tokens": 209912853.0, "step": 35085 }, { "epoch": 0.37436121750077345, "grad_norm": 1.2079972268425188, "learning_rate": 3.825145129012566e-05, "loss": 0.5684, "num_tokens": 209943712.0, "step": 35090 }, { "epoch": 0.3744145605069719, "grad_norm": 1.7599403870352093, "learning_rate": 3.8247964516846926e-05, "loss": 0.4321, "num_tokens": 209963533.0, "step": 35095 }, { "epoch": 0.3744679035131704, "grad_norm": 1.3981169432228895, "learning_rate": 3.824447740911361e-05, "loss": 0.5453, "num_tokens": 209981750.0, "step": 35100 }, { "epoch": 0.37452124651936886, "grad_norm": 0.8004057437438332, "learning_rate": 3.824098996703422e-05, "loss": 0.4054, "num_tokens": 210004326.0, "step": 35105 }, { "epoch": 0.3745745895255673, "grad_norm": 2.0037150290437817, "learning_rate": 3.82375021907173e-05, "loss": 0.674, "num_tokens": 210031856.0, "step": 35110 }, { "epoch": 0.37462793253176574, "grad_norm": 1.0382544117197536, "learning_rate": 3.823401408027135e-05, "loss": 0.524, "num_tokens": 210065314.0, "step": 35115 }, { "epoch": 0.3746812755379642, "grad_norm": 0.925804475609779, "learning_rate": 3.8230525635804934e-05, "loss": 0.617, "num_tokens": 210091728.0, "step": 35120 }, { "epoch": 0.3747346185441627, "grad_norm": 0.9557229887970663, "learning_rate": 3.8227036857426614e-05, "loss": 0.5218, "num_tokens": 210122455.0, "step": 35125 }, { "epoch": 0.37478796155036115, "grad_norm": 1.217125142284628, "learning_rate": 3.822354774524493e-05, "loss": 0.5232, "num_tokens": 210179900.0, "step": 35130 }, { "epoch": 0.37484130455655956, "grad_norm": 0.909785097085916, "learning_rate": 3.822005829936847e-05, "loss": 0.4956, "num_tokens": 210205559.0, "step": 35135 }, { "epoch": 0.37489464756275803, "grad_norm": 0.8193690249121013, "learning_rate": 3.8216568519905816e-05, "loss": 0.5178, "num_tokens": 210232234.0, "step": 35140 }, { "epoch": 0.3749479905689565, "grad_norm": 0.6997470035501772, "learning_rate": 3.821307840696557e-05, "loss": 0.5174, "num_tokens": 210259757.0, "step": 35145 }, { "epoch": 0.37500133357515497, "grad_norm": 0.7779966729709589, "learning_rate": 3.820958796065631e-05, "loss": 0.5053, "num_tokens": 210284860.0, "step": 35150 }, { "epoch": 0.37505467658135344, "grad_norm": 1.1092543591589756, "learning_rate": 3.820609718108668e-05, "loss": 0.6442, "num_tokens": 210314542.0, "step": 35155 }, { "epoch": 0.37510801958755186, "grad_norm": 1.102302954910136, "learning_rate": 3.82026060683653e-05, "loss": 0.553, "num_tokens": 210345203.0, "step": 35160 }, { "epoch": 0.3751613625937503, "grad_norm": 0.9493896470692164, "learning_rate": 3.8199114622600804e-05, "loss": 0.6808, "num_tokens": 210374395.0, "step": 35165 }, { "epoch": 0.3752147055999488, "grad_norm": 1.269456495338537, "learning_rate": 3.819562284390184e-05, "loss": 0.6514, "num_tokens": 210399634.0, "step": 35170 }, { "epoch": 0.37526804860614726, "grad_norm": 0.9594937156136646, "learning_rate": 3.819213073237705e-05, "loss": 0.5347, "num_tokens": 210444916.0, "step": 35175 }, { "epoch": 0.3753213916123457, "grad_norm": 1.8419505685290907, "learning_rate": 3.818863828813512e-05, "loss": 0.6332, "num_tokens": 210465173.0, "step": 35180 }, { "epoch": 0.37537473461854415, "grad_norm": 0.9478427226992799, "learning_rate": 3.8185145511284724e-05, "loss": 0.5494, "num_tokens": 210491810.0, "step": 35185 }, { "epoch": 0.3754280776247426, "grad_norm": 1.19063361145559, "learning_rate": 3.8181652401934544e-05, "loss": 0.5337, "num_tokens": 210527028.0, "step": 35190 }, { "epoch": 0.3754814206309411, "grad_norm": 1.7566586028780153, "learning_rate": 3.817815896019328e-05, "loss": 0.5352, "num_tokens": 210555640.0, "step": 35195 }, { "epoch": 0.37553476363713956, "grad_norm": 0.6828635664062175, "learning_rate": 3.817466518616965e-05, "loss": 0.5839, "num_tokens": 210585632.0, "step": 35200 }, { "epoch": 0.37558810664333797, "grad_norm": 0.8605922392740375, "learning_rate": 3.8171171079972364e-05, "loss": 0.7222, "num_tokens": 210614855.0, "step": 35205 }, { "epoch": 0.37564144964953644, "grad_norm": 1.1050797448921896, "learning_rate": 3.816767664171015e-05, "loss": 0.5266, "num_tokens": 210635196.0, "step": 35210 }, { "epoch": 0.3756947926557349, "grad_norm": 0.9481490460508046, "learning_rate": 3.816418187149175e-05, "loss": 0.5581, "num_tokens": 210662026.0, "step": 35215 }, { "epoch": 0.3757481356619334, "grad_norm": 0.7399158243922047, "learning_rate": 3.816068676942592e-05, "loss": 0.5534, "num_tokens": 210683023.0, "step": 35220 }, { "epoch": 0.3758014786681318, "grad_norm": 1.0084745000134976, "learning_rate": 3.815719133562142e-05, "loss": 0.4337, "num_tokens": 210713722.0, "step": 35225 }, { "epoch": 0.37585482167433026, "grad_norm": 1.4700709045697042, "learning_rate": 3.8153695570187005e-05, "loss": 0.5967, "num_tokens": 210734682.0, "step": 35230 }, { "epoch": 0.37590816468052873, "grad_norm": 2.4101511425060123, "learning_rate": 3.815019947323147e-05, "loss": 0.5546, "num_tokens": 210759613.0, "step": 35235 }, { "epoch": 0.3759615076867272, "grad_norm": 0.9339156573426904, "learning_rate": 3.814670304486361e-05, "loss": 0.5024, "num_tokens": 210790308.0, "step": 35240 }, { "epoch": 0.3760148506929257, "grad_norm": 0.7497493491884513, "learning_rate": 3.814320628519221e-05, "loss": 0.6827, "num_tokens": 210824435.0, "step": 35245 }, { "epoch": 0.3760681936991241, "grad_norm": 1.1312203150360485, "learning_rate": 3.81397091943261e-05, "loss": 0.5571, "num_tokens": 210845450.0, "step": 35250 }, { "epoch": 0.37612153670532256, "grad_norm": 0.7265272074137495, "learning_rate": 3.813621177237409e-05, "loss": 0.5101, "num_tokens": 210871521.0, "step": 35255 }, { "epoch": 0.376174879711521, "grad_norm": 0.8606255082443525, "learning_rate": 3.8132714019445024e-05, "loss": 0.4999, "num_tokens": 210907689.0, "step": 35260 }, { "epoch": 0.3762282227177195, "grad_norm": 1.5189069173283976, "learning_rate": 3.812921593564773e-05, "loss": 0.4881, "num_tokens": 210948601.0, "step": 35265 }, { "epoch": 0.3762815657239179, "grad_norm": 2.047007531362096, "learning_rate": 3.8125717521091064e-05, "loss": 0.4788, "num_tokens": 210966388.0, "step": 35270 }, { "epoch": 0.3763349087301164, "grad_norm": 0.8297147829788242, "learning_rate": 3.812221877588391e-05, "loss": 0.6529, "num_tokens": 211004245.0, "step": 35275 }, { "epoch": 0.37638825173631485, "grad_norm": 0.7216012211723697, "learning_rate": 3.811871970013512e-05, "loss": 0.5531, "num_tokens": 211033102.0, "step": 35280 }, { "epoch": 0.3764415947425133, "grad_norm": 0.8798307075524817, "learning_rate": 3.811522029395358e-05, "loss": 0.6214, "num_tokens": 211078762.0, "step": 35285 }, { "epoch": 0.3764949377487118, "grad_norm": 0.9124419553497465, "learning_rate": 3.811172055744819e-05, "loss": 0.6531, "num_tokens": 211110348.0, "step": 35290 }, { "epoch": 0.3765482807549102, "grad_norm": 0.9613379724652742, "learning_rate": 3.810822049072786e-05, "loss": 0.6695, "num_tokens": 211140352.0, "step": 35295 }, { "epoch": 0.3766016237611087, "grad_norm": 1.2167636531555384, "learning_rate": 3.810472009390149e-05, "loss": 0.7187, "num_tokens": 211162963.0, "step": 35300 }, { "epoch": 0.37665496676730714, "grad_norm": 0.7374040599199164, "learning_rate": 3.810121936707802e-05, "loss": 0.4982, "num_tokens": 211186345.0, "step": 35305 }, { "epoch": 0.3767083097735056, "grad_norm": 0.9183963777451922, "learning_rate": 3.809771831036638e-05, "loss": 0.6379, "num_tokens": 211205398.0, "step": 35310 }, { "epoch": 0.376761652779704, "grad_norm": 0.8649321060929421, "learning_rate": 3.80942169238755e-05, "loss": 0.5772, "num_tokens": 211227233.0, "step": 35315 }, { "epoch": 0.3768149957859025, "grad_norm": 1.2508663037478562, "learning_rate": 3.8090715207714365e-05, "loss": 0.5694, "num_tokens": 211259196.0, "step": 35320 }, { "epoch": 0.37686833879210097, "grad_norm": 1.019483660448917, "learning_rate": 3.8087213161991926e-05, "loss": 0.5056, "num_tokens": 211275840.0, "step": 35325 }, { "epoch": 0.37692168179829943, "grad_norm": 0.9262586340096505, "learning_rate": 3.808371078681715e-05, "loss": 0.4863, "num_tokens": 211296381.0, "step": 35330 }, { "epoch": 0.3769750248044979, "grad_norm": 1.3405275169039914, "learning_rate": 3.8080208082299046e-05, "loss": 0.7852, "num_tokens": 211329212.0, "step": 35335 }, { "epoch": 0.3770283678106963, "grad_norm": 1.1719738956267662, "learning_rate": 3.807670504854659e-05, "loss": 0.5124, "num_tokens": 211352113.0, "step": 35340 }, { "epoch": 0.3770817108168948, "grad_norm": 0.8803773945936492, "learning_rate": 3.8073201685668796e-05, "loss": 0.6387, "num_tokens": 211388304.0, "step": 35345 }, { "epoch": 0.37713505382309326, "grad_norm": 0.8712066365802291, "learning_rate": 3.80696979937747e-05, "loss": 0.548, "num_tokens": 211419262.0, "step": 35350 }, { "epoch": 0.3771883968292917, "grad_norm": 0.8600106738579147, "learning_rate": 3.8066193972973295e-05, "loss": 0.4797, "num_tokens": 211462009.0, "step": 35355 }, { "epoch": 0.37724173983549014, "grad_norm": 3.334552807200123, "learning_rate": 3.806268962337365e-05, "loss": 0.624, "num_tokens": 211484186.0, "step": 35360 }, { "epoch": 0.3772950828416886, "grad_norm": 5.254635707282243, "learning_rate": 3.805918494508479e-05, "loss": 0.577, "num_tokens": 211525646.0, "step": 35365 }, { "epoch": 0.3773484258478871, "grad_norm": 0.8534091263164548, "learning_rate": 3.805567993821579e-05, "loss": 0.6671, "num_tokens": 211552920.0, "step": 35370 }, { "epoch": 0.37740176885408555, "grad_norm": 1.973179726862995, "learning_rate": 3.805217460287571e-05, "loss": 0.5519, "num_tokens": 211572426.0, "step": 35375 }, { "epoch": 0.377455111860284, "grad_norm": 0.9300576961686486, "learning_rate": 3.804866893917363e-05, "loss": 0.5337, "num_tokens": 211605032.0, "step": 35380 }, { "epoch": 0.37750845486648243, "grad_norm": 0.9857110931504885, "learning_rate": 3.804516294721865e-05, "loss": 0.549, "num_tokens": 211634007.0, "step": 35385 }, { "epoch": 0.3775617978726809, "grad_norm": 1.7135118701348018, "learning_rate": 3.804165662711984e-05, "loss": 0.6131, "num_tokens": 211662926.0, "step": 35390 }, { "epoch": 0.3776151408788794, "grad_norm": 1.1790475150968116, "learning_rate": 3.803814997898635e-05, "loss": 0.4985, "num_tokens": 211692824.0, "step": 35395 }, { "epoch": 0.37766848388507784, "grad_norm": 0.9933409682967966, "learning_rate": 3.803464300292726e-05, "loss": 0.5587, "num_tokens": 211722972.0, "step": 35400 }, { "epoch": 0.37772182689127626, "grad_norm": 0.9466836174580855, "learning_rate": 3.8031135699051736e-05, "loss": 0.5784, "num_tokens": 211755333.0, "step": 35405 }, { "epoch": 0.3777751698974747, "grad_norm": 1.5553580029967424, "learning_rate": 3.802762806746889e-05, "loss": 0.6662, "num_tokens": 211775975.0, "step": 35410 }, { "epoch": 0.3778285129036732, "grad_norm": 0.8686988547364363, "learning_rate": 3.802412010828788e-05, "loss": 0.6692, "num_tokens": 211824515.0, "step": 35415 }, { "epoch": 0.37788185590987167, "grad_norm": 1.11053717469402, "learning_rate": 3.802061182161788e-05, "loss": 0.5269, "num_tokens": 211847579.0, "step": 35420 }, { "epoch": 0.37793519891607014, "grad_norm": 0.9128371617044848, "learning_rate": 3.801710320756805e-05, "loss": 0.4283, "num_tokens": 211875531.0, "step": 35425 }, { "epoch": 0.37798854192226855, "grad_norm": 1.311179465084692, "learning_rate": 3.8013594266247556e-05, "loss": 0.3882, "num_tokens": 211889157.0, "step": 35430 }, { "epoch": 0.378041884928467, "grad_norm": 0.8509067655739176, "learning_rate": 3.801008499776562e-05, "loss": 0.4738, "num_tokens": 211922507.0, "step": 35435 }, { "epoch": 0.3780952279346655, "grad_norm": 0.8408225029893471, "learning_rate": 3.800657540223142e-05, "loss": 0.59, "num_tokens": 211967187.0, "step": 35440 }, { "epoch": 0.37814857094086396, "grad_norm": 1.0612222447879744, "learning_rate": 3.8003065479754176e-05, "loss": 0.5668, "num_tokens": 211997236.0, "step": 35445 }, { "epoch": 0.3782019139470624, "grad_norm": 0.9482810192521101, "learning_rate": 3.7999555230443104e-05, "loss": 0.5571, "num_tokens": 212020019.0, "step": 35450 }, { "epoch": 0.37825525695326084, "grad_norm": 0.7350601707327092, "learning_rate": 3.7996044654407444e-05, "loss": 0.5125, "num_tokens": 212060946.0, "step": 35455 }, { "epoch": 0.3783085999594593, "grad_norm": 2.139327059780415, "learning_rate": 3.7992533751756434e-05, "loss": 0.679, "num_tokens": 212106985.0, "step": 35460 }, { "epoch": 0.3783619429656578, "grad_norm": 1.0575482272057168, "learning_rate": 3.7989022522599323e-05, "loss": 0.5364, "num_tokens": 212136971.0, "step": 35465 }, { "epoch": 0.37841528597185625, "grad_norm": 1.4053107788675525, "learning_rate": 3.798551096704538e-05, "loss": 0.5783, "num_tokens": 212163688.0, "step": 35470 }, { "epoch": 0.37846862897805467, "grad_norm": 0.942908771754536, "learning_rate": 3.798199908520387e-05, "loss": 0.5321, "num_tokens": 212199445.0, "step": 35475 }, { "epoch": 0.37852197198425314, "grad_norm": 1.082103756689916, "learning_rate": 3.797848687718408e-05, "loss": 0.7349, "num_tokens": 212229892.0, "step": 35480 }, { "epoch": 0.3785753149904516, "grad_norm": 1.7191798031223795, "learning_rate": 3.797497434309531e-05, "loss": 0.6271, "num_tokens": 212245305.0, "step": 35485 }, { "epoch": 0.3786286579966501, "grad_norm": 0.7335143440639984, "learning_rate": 3.797146148304684e-05, "loss": 0.5321, "num_tokens": 212269559.0, "step": 35490 }, { "epoch": 0.3786820010028485, "grad_norm": 1.541254394246394, "learning_rate": 3.796794829714801e-05, "loss": 0.4402, "num_tokens": 212291182.0, "step": 35495 }, { "epoch": 0.37873534400904696, "grad_norm": 1.1618659096370374, "learning_rate": 3.7964434785508125e-05, "loss": 0.4623, "num_tokens": 212313376.0, "step": 35500 }, { "epoch": 0.37878868701524543, "grad_norm": 1.1176862627477964, "learning_rate": 3.796092094823652e-05, "loss": 0.6334, "num_tokens": 212337956.0, "step": 35505 }, { "epoch": 0.3788420300214439, "grad_norm": 1.0546321065915119, "learning_rate": 3.7957406785442546e-05, "loss": 0.5389, "num_tokens": 212369725.0, "step": 35510 }, { "epoch": 0.37889537302764237, "grad_norm": 1.0735407985526577, "learning_rate": 3.795389229723556e-05, "loss": 0.585, "num_tokens": 212407616.0, "step": 35515 }, { "epoch": 0.3789487160338408, "grad_norm": 0.8655092299751732, "learning_rate": 3.795037748372491e-05, "loss": 0.5836, "num_tokens": 212446145.0, "step": 35520 }, { "epoch": 0.37900205904003925, "grad_norm": 0.821418006964249, "learning_rate": 3.794686234501998e-05, "loss": 0.5887, "num_tokens": 212467453.0, "step": 35525 }, { "epoch": 0.3790554020462377, "grad_norm": 1.1742018932647327, "learning_rate": 3.794334688123016e-05, "loss": 0.4932, "num_tokens": 212499117.0, "step": 35530 }, { "epoch": 0.3791087450524362, "grad_norm": 0.7090868149685067, "learning_rate": 3.7939831092464824e-05, "loss": 0.4042, "num_tokens": 212533686.0, "step": 35535 }, { "epoch": 0.3791620880586346, "grad_norm": 3.084437584914829, "learning_rate": 3.793631497883339e-05, "loss": 0.615, "num_tokens": 212574084.0, "step": 35540 }, { "epoch": 0.3792154310648331, "grad_norm": 1.8496369205134684, "learning_rate": 3.793279854044528e-05, "loss": 0.6707, "num_tokens": 212603694.0, "step": 35545 }, { "epoch": 0.37926877407103154, "grad_norm": 0.8582392064585121, "learning_rate": 3.7929281777409906e-05, "loss": 0.4907, "num_tokens": 212640735.0, "step": 35550 }, { "epoch": 0.37932211707723, "grad_norm": 2.1063751545860883, "learning_rate": 3.792576468983671e-05, "loss": 0.6053, "num_tokens": 212672090.0, "step": 35555 }, { "epoch": 0.3793754600834285, "grad_norm": 0.9292308992647503, "learning_rate": 3.792224727783511e-05, "loss": 0.5526, "num_tokens": 212693655.0, "step": 35560 }, { "epoch": 0.3794288030896269, "grad_norm": 0.801602367711149, "learning_rate": 3.791872954151461e-05, "loss": 0.5852, "num_tokens": 212726102.0, "step": 35565 }, { "epoch": 0.37948214609582537, "grad_norm": 0.8105162275471014, "learning_rate": 3.791521148098463e-05, "loss": 0.6258, "num_tokens": 212766773.0, "step": 35570 }, { "epoch": 0.37953548910202384, "grad_norm": 1.0317603572207499, "learning_rate": 3.7911693096354666e-05, "loss": 0.5976, "num_tokens": 212784674.0, "step": 35575 }, { "epoch": 0.3795888321082223, "grad_norm": 1.7408214168339515, "learning_rate": 3.7908174387734197e-05, "loss": 0.5525, "num_tokens": 212813678.0, "step": 35580 }, { "epoch": 0.3796421751144207, "grad_norm": 1.183318501152802, "learning_rate": 3.790465535523273e-05, "loss": 0.4481, "num_tokens": 212834300.0, "step": 35585 }, { "epoch": 0.3796955181206192, "grad_norm": 1.0947209827422766, "learning_rate": 3.790113599895975e-05, "loss": 0.517, "num_tokens": 212844009.0, "step": 35590 }, { "epoch": 0.37974886112681766, "grad_norm": 0.9945905332404896, "learning_rate": 3.789761631902479e-05, "loss": 0.7465, "num_tokens": 212886226.0, "step": 35595 }, { "epoch": 0.37980220413301613, "grad_norm": 1.217204131448548, "learning_rate": 3.789409631553736e-05, "loss": 0.505, "num_tokens": 212913519.0, "step": 35600 }, { "epoch": 0.3798555471392146, "grad_norm": 0.9731164673529789, "learning_rate": 3.789057598860701e-05, "loss": 0.5991, "num_tokens": 212940073.0, "step": 35605 }, { "epoch": 0.379908890145413, "grad_norm": 1.378502125426716, "learning_rate": 3.788705533834327e-05, "loss": 0.5085, "num_tokens": 212971109.0, "step": 35610 }, { "epoch": 0.3799622331516115, "grad_norm": 0.8236579348106482, "learning_rate": 3.788353436485571e-05, "loss": 0.574, "num_tokens": 212988453.0, "step": 35615 }, { "epoch": 0.38001557615780995, "grad_norm": 1.8452881520689173, "learning_rate": 3.7880013068253887e-05, "loss": 0.5943, "num_tokens": 213023358.0, "step": 35620 }, { "epoch": 0.3800689191640084, "grad_norm": 0.89434804308437, "learning_rate": 3.7876491448647376e-05, "loss": 0.4682, "num_tokens": 213044638.0, "step": 35625 }, { "epoch": 0.38012226217020684, "grad_norm": 0.8320029336273518, "learning_rate": 3.7872969506145774e-05, "loss": 0.456, "num_tokens": 213079901.0, "step": 35630 }, { "epoch": 0.3801756051764053, "grad_norm": 1.1886466470882922, "learning_rate": 3.786944724085865e-05, "loss": 0.4981, "num_tokens": 213102853.0, "step": 35635 }, { "epoch": 0.3802289481826038, "grad_norm": 1.306406468226778, "learning_rate": 3.786592465289565e-05, "loss": 0.607, "num_tokens": 213129525.0, "step": 35640 }, { "epoch": 0.38028229118880225, "grad_norm": 0.9143928891071033, "learning_rate": 3.7862401742366354e-05, "loss": 0.4686, "num_tokens": 213156673.0, "step": 35645 }, { "epoch": 0.3803356341950007, "grad_norm": 0.8159347514386752, "learning_rate": 3.78588785093804e-05, "loss": 0.5218, "num_tokens": 213189440.0, "step": 35650 }, { "epoch": 0.38038897720119913, "grad_norm": 0.994303692647604, "learning_rate": 3.7855354954047426e-05, "loss": 0.6316, "num_tokens": 213217759.0, "step": 35655 }, { "epoch": 0.3804423202073976, "grad_norm": 0.7342523604861788, "learning_rate": 3.785183107647708e-05, "loss": 0.7178, "num_tokens": 213250102.0, "step": 35660 }, { "epoch": 0.38049566321359607, "grad_norm": 1.0100730504387145, "learning_rate": 3.784830687677901e-05, "loss": 0.5683, "num_tokens": 213268715.0, "step": 35665 }, { "epoch": 0.38054900621979454, "grad_norm": 0.9191066372750967, "learning_rate": 3.784478235506289e-05, "loss": 0.6823, "num_tokens": 213301455.0, "step": 35670 }, { "epoch": 0.38060234922599295, "grad_norm": 2.4571616009840507, "learning_rate": 3.784125751143838e-05, "loss": 0.4905, "num_tokens": 213327554.0, "step": 35675 }, { "epoch": 0.3806556922321914, "grad_norm": 0.7344686669882927, "learning_rate": 3.7837732346015195e-05, "loss": 0.5172, "num_tokens": 213366141.0, "step": 35680 }, { "epoch": 0.3807090352383899, "grad_norm": 1.5474598754119147, "learning_rate": 3.7834206858903004e-05, "loss": 0.4759, "num_tokens": 213390835.0, "step": 35685 }, { "epoch": 0.38076237824458836, "grad_norm": 1.644403768954602, "learning_rate": 3.783068105021152e-05, "loss": 0.6911, "num_tokens": 213402993.0, "step": 35690 }, { "epoch": 0.38081572125078683, "grad_norm": 0.7157600629480989, "learning_rate": 3.7827154920050464e-05, "loss": 0.5172, "num_tokens": 213436206.0, "step": 35695 }, { "epoch": 0.38086906425698525, "grad_norm": 1.1577402863135762, "learning_rate": 3.7823628468529564e-05, "loss": 0.5336, "num_tokens": 213467335.0, "step": 35700 }, { "epoch": 0.3809224072631837, "grad_norm": 1.485712724577393, "learning_rate": 3.7820101695758545e-05, "loss": 0.5634, "num_tokens": 213482199.0, "step": 35705 }, { "epoch": 0.3809757502693822, "grad_norm": 1.1248231541856135, "learning_rate": 3.781657460184717e-05, "loss": 0.4913, "num_tokens": 213502322.0, "step": 35710 }, { "epoch": 0.38102909327558065, "grad_norm": 1.006351830166683, "learning_rate": 3.781304718690518e-05, "loss": 0.5601, "num_tokens": 213536032.0, "step": 35715 }, { "epoch": 0.38108243628177907, "grad_norm": 1.0857782921247057, "learning_rate": 3.780951945104234e-05, "loss": 0.612, "num_tokens": 213560404.0, "step": 35720 }, { "epoch": 0.38113577928797754, "grad_norm": 0.9677985826430366, "learning_rate": 3.780599139436842e-05, "loss": 0.5277, "num_tokens": 213592228.0, "step": 35725 }, { "epoch": 0.381189122294176, "grad_norm": 0.6347025341835362, "learning_rate": 3.7802463016993244e-05, "loss": 0.5575, "num_tokens": 213620027.0, "step": 35730 }, { "epoch": 0.3812424653003745, "grad_norm": 0.7326829038874073, "learning_rate": 3.779893431902657e-05, "loss": 0.5856, "num_tokens": 213651353.0, "step": 35735 }, { "epoch": 0.38129580830657295, "grad_norm": 1.0924727668714604, "learning_rate": 3.77954053005782e-05, "loss": 0.5883, "num_tokens": 213673719.0, "step": 35740 }, { "epoch": 0.38134915131277136, "grad_norm": 1.1602833405451978, "learning_rate": 3.7791875961757974e-05, "loss": 0.6435, "num_tokens": 213705493.0, "step": 35745 }, { "epoch": 0.38140249431896983, "grad_norm": 0.8166762214045574, "learning_rate": 3.778834630267572e-05, "loss": 0.6234, "num_tokens": 213746455.0, "step": 35750 }, { "epoch": 0.3814558373251683, "grad_norm": 1.685988307674829, "learning_rate": 3.778481632344125e-05, "loss": 0.5839, "num_tokens": 213767734.0, "step": 35755 }, { "epoch": 0.38150918033136677, "grad_norm": 0.7995223887612436, "learning_rate": 3.778128602416442e-05, "loss": 0.5377, "num_tokens": 213808174.0, "step": 35760 }, { "epoch": 0.3815625233375652, "grad_norm": 1.2696161247022308, "learning_rate": 3.777775540495509e-05, "loss": 0.5807, "num_tokens": 213835586.0, "step": 35765 }, { "epoch": 0.38161586634376365, "grad_norm": 1.913135456725357, "learning_rate": 3.7774224465923125e-05, "loss": 0.6329, "num_tokens": 213868616.0, "step": 35770 }, { "epoch": 0.3816692093499621, "grad_norm": 3.5347187248350194, "learning_rate": 3.77706932071784e-05, "loss": 0.7147, "num_tokens": 213903299.0, "step": 35775 }, { "epoch": 0.3817225523561606, "grad_norm": 0.9936096694521495, "learning_rate": 3.7767161628830795e-05, "loss": 0.6247, "num_tokens": 213936649.0, "step": 35780 }, { "epoch": 0.38177589536235906, "grad_norm": 1.1898087165944156, "learning_rate": 3.776362973099021e-05, "loss": 0.6382, "num_tokens": 213960666.0, "step": 35785 }, { "epoch": 0.3818292383685575, "grad_norm": 0.8438688055429676, "learning_rate": 3.776009751376655e-05, "loss": 0.5796, "num_tokens": 213997929.0, "step": 35790 }, { "epoch": 0.38188258137475595, "grad_norm": 1.1495817027280557, "learning_rate": 3.7756564977269737e-05, "loss": 0.5661, "num_tokens": 214036546.0, "step": 35795 }, { "epoch": 0.3819359243809544, "grad_norm": 0.6108448767886882, "learning_rate": 3.7753032121609676e-05, "loss": 0.5974, "num_tokens": 214072569.0, "step": 35800 }, { "epoch": 0.3819892673871529, "grad_norm": 1.1082567766792573, "learning_rate": 3.7749498946896325e-05, "loss": 0.5929, "num_tokens": 214107236.0, "step": 35805 }, { "epoch": 0.3820426103933513, "grad_norm": 1.3221351345506984, "learning_rate": 3.7745965453239624e-05, "loss": 0.6418, "num_tokens": 214134605.0, "step": 35810 }, { "epoch": 0.38209595339954977, "grad_norm": 1.5612735637818682, "learning_rate": 3.7742431640749516e-05, "loss": 0.6051, "num_tokens": 214155646.0, "step": 35815 }, { "epoch": 0.38214929640574824, "grad_norm": 0.7082856155269794, "learning_rate": 3.773889750953597e-05, "loss": 0.5138, "num_tokens": 214179785.0, "step": 35820 }, { "epoch": 0.3822026394119467, "grad_norm": 1.6431787958272819, "learning_rate": 3.7735363059708975e-05, "loss": 0.6264, "num_tokens": 214198927.0, "step": 35825 }, { "epoch": 0.3822559824181452, "grad_norm": 1.1430137334303192, "learning_rate": 3.77318282913785e-05, "loss": 0.5751, "num_tokens": 214218276.0, "step": 35830 }, { "epoch": 0.3823093254243436, "grad_norm": 0.6849112696961297, "learning_rate": 3.772829320465455e-05, "loss": 0.4468, "num_tokens": 214238269.0, "step": 35835 }, { "epoch": 0.38236266843054206, "grad_norm": 1.9133050786237473, "learning_rate": 3.772475779964712e-05, "loss": 0.55, "num_tokens": 214261738.0, "step": 35840 }, { "epoch": 0.38241601143674053, "grad_norm": 1.5632991641392564, "learning_rate": 3.772122207646623e-05, "loss": 0.5962, "num_tokens": 214277041.0, "step": 35845 }, { "epoch": 0.382469354442939, "grad_norm": 0.8414231456004823, "learning_rate": 3.771768603522191e-05, "loss": 0.6238, "num_tokens": 214329240.0, "step": 35850 }, { "epoch": 0.3825226974491374, "grad_norm": 0.6722545881037378, "learning_rate": 3.771414967602418e-05, "loss": 0.558, "num_tokens": 214376668.0, "step": 35855 }, { "epoch": 0.3825760404553359, "grad_norm": 0.7717055640235658, "learning_rate": 3.77106129989831e-05, "loss": 0.5172, "num_tokens": 214401939.0, "step": 35860 }, { "epoch": 0.38262938346153436, "grad_norm": 0.6759452351708084, "learning_rate": 3.770707600420871e-05, "loss": 0.547, "num_tokens": 214432954.0, "step": 35865 }, { "epoch": 0.3826827264677328, "grad_norm": 1.110617132620375, "learning_rate": 3.770353869181108e-05, "loss": 0.5561, "num_tokens": 214462059.0, "step": 35870 }, { "epoch": 0.3827360694739313, "grad_norm": 1.241411300526607, "learning_rate": 3.770000106190029e-05, "loss": 0.4876, "num_tokens": 214506890.0, "step": 35875 }, { "epoch": 0.3827894124801297, "grad_norm": 0.7722242595224669, "learning_rate": 3.769646311458642e-05, "loss": 0.6476, "num_tokens": 214542038.0, "step": 35880 }, { "epoch": 0.3828427554863282, "grad_norm": 1.058633974121661, "learning_rate": 3.7692924849979557e-05, "loss": 0.4944, "num_tokens": 214573230.0, "step": 35885 }, { "epoch": 0.38289609849252665, "grad_norm": 0.7072699618753383, "learning_rate": 3.768938626818981e-05, "loss": 0.5925, "num_tokens": 214602117.0, "step": 35890 }, { "epoch": 0.3829494414987251, "grad_norm": 1.1308169915812032, "learning_rate": 3.768584736932729e-05, "loss": 0.5437, "num_tokens": 214626294.0, "step": 35895 }, { "epoch": 0.38300278450492353, "grad_norm": 1.669427890693444, "learning_rate": 3.768230815350213e-05, "loss": 0.4368, "num_tokens": 214641586.0, "step": 35900 }, { "epoch": 0.383056127511122, "grad_norm": 0.9104855623178827, "learning_rate": 3.7678768620824445e-05, "loss": 0.5452, "num_tokens": 214675312.0, "step": 35905 }, { "epoch": 0.38310947051732047, "grad_norm": 1.0904807444087468, "learning_rate": 3.767522877140439e-05, "loss": 0.5579, "num_tokens": 214710169.0, "step": 35910 }, { "epoch": 0.38316281352351894, "grad_norm": 1.2458416162956545, "learning_rate": 3.767168860535213e-05, "loss": 0.64, "num_tokens": 214754605.0, "step": 35915 }, { "epoch": 0.3832161565297174, "grad_norm": 1.2669730549938945, "learning_rate": 3.76681481227778e-05, "loss": 0.4894, "num_tokens": 214794609.0, "step": 35920 }, { "epoch": 0.3832694995359158, "grad_norm": 1.4018372405673545, "learning_rate": 3.766460732379159e-05, "loss": 0.5228, "num_tokens": 214820940.0, "step": 35925 }, { "epoch": 0.3833228425421143, "grad_norm": 1.065152466806307, "learning_rate": 3.766106620850368e-05, "loss": 0.542, "num_tokens": 214851995.0, "step": 35930 }, { "epoch": 0.38337618554831276, "grad_norm": 0.9602581192389295, "learning_rate": 3.765752477702425e-05, "loss": 0.5493, "num_tokens": 214886519.0, "step": 35935 }, { "epoch": 0.38342952855451123, "grad_norm": 1.168192807475492, "learning_rate": 3.765398302946353e-05, "loss": 0.6224, "num_tokens": 214923960.0, "step": 35940 }, { "epoch": 0.38348287156070965, "grad_norm": 0.8639505453228086, "learning_rate": 3.765044096593171e-05, "loss": 0.6422, "num_tokens": 214957110.0, "step": 35945 }, { "epoch": 0.3835362145669081, "grad_norm": 1.309877823822955, "learning_rate": 3.764689858653901e-05, "loss": 0.5234, "num_tokens": 214985470.0, "step": 35950 }, { "epoch": 0.3835895575731066, "grad_norm": 1.008876692427421, "learning_rate": 3.764335589139568e-05, "loss": 0.5961, "num_tokens": 215008741.0, "step": 35955 }, { "epoch": 0.38364290057930506, "grad_norm": 0.9882847176390136, "learning_rate": 3.763981288061194e-05, "loss": 0.5579, "num_tokens": 215039211.0, "step": 35960 }, { "epoch": 0.3836962435855035, "grad_norm": 0.7201648456656102, "learning_rate": 3.763626955429805e-05, "loss": 0.656, "num_tokens": 215066976.0, "step": 35965 }, { "epoch": 0.38374958659170194, "grad_norm": 0.843979558307458, "learning_rate": 3.763272591256428e-05, "loss": 0.6562, "num_tokens": 215088433.0, "step": 35970 }, { "epoch": 0.3838029295979004, "grad_norm": 0.7437442686168064, "learning_rate": 3.762918195552089e-05, "loss": 0.4629, "num_tokens": 215115739.0, "step": 35975 }, { "epoch": 0.3838562726040989, "grad_norm": 0.9008676277949154, "learning_rate": 3.762563768327816e-05, "loss": 0.6799, "num_tokens": 215153550.0, "step": 35980 }, { "epoch": 0.38390961561029735, "grad_norm": 1.04929809836605, "learning_rate": 3.7622093095946384e-05, "loss": 0.6218, "num_tokens": 215185492.0, "step": 35985 }, { "epoch": 0.38396295861649576, "grad_norm": 2.0518962817518753, "learning_rate": 3.761854819363587e-05, "loss": 0.6639, "num_tokens": 215216501.0, "step": 35990 }, { "epoch": 0.38401630162269423, "grad_norm": 1.4475234643265296, "learning_rate": 3.76150029764569e-05, "loss": 0.5872, "num_tokens": 215239103.0, "step": 35995 }, { "epoch": 0.3840696446288927, "grad_norm": 0.7029198674382521, "learning_rate": 3.7611457444519834e-05, "loss": 0.5193, "num_tokens": 215271195.0, "step": 36000 }, { "epoch": 0.3841229876350912, "grad_norm": 1.3177963476967394, "learning_rate": 3.760791159793498e-05, "loss": 0.4845, "num_tokens": 215295055.0, "step": 36005 }, { "epoch": 0.38417633064128964, "grad_norm": 1.1398929546785752, "learning_rate": 3.7604365436812675e-05, "loss": 0.6198, "num_tokens": 215326081.0, "step": 36010 }, { "epoch": 0.38422967364748806, "grad_norm": 0.958451775061734, "learning_rate": 3.760081896126327e-05, "loss": 0.6822, "num_tokens": 215367335.0, "step": 36015 }, { "epoch": 0.3842830166536865, "grad_norm": 1.2731282712774448, "learning_rate": 3.759727217139713e-05, "loss": 0.6404, "num_tokens": 215392930.0, "step": 36020 }, { "epoch": 0.384336359659885, "grad_norm": 0.8276593059631157, "learning_rate": 3.759372506732462e-05, "loss": 0.8042, "num_tokens": 215420378.0, "step": 36025 }, { "epoch": 0.38438970266608347, "grad_norm": 0.9279867089033094, "learning_rate": 3.759017764915612e-05, "loss": 0.463, "num_tokens": 215440507.0, "step": 36030 }, { "epoch": 0.3844430456722819, "grad_norm": 0.7212004314730421, "learning_rate": 3.758662991700201e-05, "loss": 0.5032, "num_tokens": 215476617.0, "step": 36035 }, { "epoch": 0.38449638867848035, "grad_norm": 0.7276437726033823, "learning_rate": 3.758308187097271e-05, "loss": 0.5701, "num_tokens": 215501266.0, "step": 36040 }, { "epoch": 0.3845497316846788, "grad_norm": 3.206400213912928, "learning_rate": 3.757953351117861e-05, "loss": 0.5486, "num_tokens": 215530998.0, "step": 36045 }, { "epoch": 0.3846030746908773, "grad_norm": 1.5230371890926915, "learning_rate": 3.7575984837730124e-05, "loss": 0.5483, "num_tokens": 215564068.0, "step": 36050 }, { "epoch": 0.38465641769707576, "grad_norm": 2.124010354021026, "learning_rate": 3.757243585073769e-05, "loss": 0.6014, "num_tokens": 215588436.0, "step": 36055 }, { "epoch": 0.3847097607032742, "grad_norm": 0.8825588767899513, "learning_rate": 3.7568886550311736e-05, "loss": 0.5302, "num_tokens": 215615082.0, "step": 36060 }, { "epoch": 0.38476310370947264, "grad_norm": 0.9161240308092056, "learning_rate": 3.756533693656272e-05, "loss": 0.6141, "num_tokens": 215640448.0, "step": 36065 }, { "epoch": 0.3848164467156711, "grad_norm": 1.2650902977050869, "learning_rate": 3.75617870096011e-05, "loss": 0.6006, "num_tokens": 215666577.0, "step": 36070 }, { "epoch": 0.3848697897218696, "grad_norm": 0.7006360790926023, "learning_rate": 3.755823676953733e-05, "loss": 0.6089, "num_tokens": 215698768.0, "step": 36075 }, { "epoch": 0.384923132728068, "grad_norm": 1.1965439614325575, "learning_rate": 3.7554686216481885e-05, "loss": 0.5092, "num_tokens": 215737142.0, "step": 36080 }, { "epoch": 0.38497647573426647, "grad_norm": 0.9235839127202444, "learning_rate": 3.7551135350545266e-05, "loss": 0.585, "num_tokens": 215770506.0, "step": 36085 }, { "epoch": 0.38502981874046494, "grad_norm": 0.8071760650737738, "learning_rate": 3.7547584171837956e-05, "loss": 0.6399, "num_tokens": 215800083.0, "step": 36090 }, { "epoch": 0.3850831617466634, "grad_norm": 1.1794652198510789, "learning_rate": 3.754403268047046e-05, "loss": 0.6055, "num_tokens": 215818885.0, "step": 36095 }, { "epoch": 0.3851365047528619, "grad_norm": 1.1133845899166075, "learning_rate": 3.754048087655331e-05, "loss": 0.6284, "num_tokens": 215842918.0, "step": 36100 }, { "epoch": 0.3851898477590603, "grad_norm": 0.7530960895263795, "learning_rate": 3.753692876019701e-05, "loss": 0.4814, "num_tokens": 215876519.0, "step": 36105 }, { "epoch": 0.38524319076525876, "grad_norm": 1.1137878646740307, "learning_rate": 3.7533376331512104e-05, "loss": 0.4442, "num_tokens": 215903122.0, "step": 36110 }, { "epoch": 0.38529653377145723, "grad_norm": 0.6942923838806264, "learning_rate": 3.752982359060915e-05, "loss": 0.5265, "num_tokens": 215932201.0, "step": 36115 }, { "epoch": 0.3853498767776557, "grad_norm": 1.3957824253569358, "learning_rate": 3.752627053759867e-05, "loss": 0.575, "num_tokens": 215964410.0, "step": 36120 }, { "epoch": 0.3854032197838541, "grad_norm": 0.9956850894722188, "learning_rate": 3.7522717172591256e-05, "loss": 0.6051, "num_tokens": 216000530.0, "step": 36125 }, { "epoch": 0.3854565627900526, "grad_norm": 1.0749390056645993, "learning_rate": 3.751916349569746e-05, "loss": 0.5861, "num_tokens": 216037236.0, "step": 36130 }, { "epoch": 0.38550990579625105, "grad_norm": 0.9473720627895054, "learning_rate": 3.7515609507027886e-05, "loss": 0.5051, "num_tokens": 216063817.0, "step": 36135 }, { "epoch": 0.3855632488024495, "grad_norm": 0.9587602362685439, "learning_rate": 3.7512055206693115e-05, "loss": 0.6717, "num_tokens": 216107622.0, "step": 36140 }, { "epoch": 0.385616591808648, "grad_norm": 0.9900588642890213, "learning_rate": 3.750850059480375e-05, "loss": 0.5724, "num_tokens": 216154457.0, "step": 36145 }, { "epoch": 0.3856699348148464, "grad_norm": 0.9153532824429196, "learning_rate": 3.7504945671470404e-05, "loss": 0.5346, "num_tokens": 216172716.0, "step": 36150 }, { "epoch": 0.3857232778210449, "grad_norm": 1.2178453968226157, "learning_rate": 3.75013904368037e-05, "loss": 0.5063, "num_tokens": 216193542.0, "step": 36155 }, { "epoch": 0.38577662082724334, "grad_norm": 1.5307803612008368, "learning_rate": 3.749783489091427e-05, "loss": 0.7009, "num_tokens": 216231144.0, "step": 36160 }, { "epoch": 0.3858299638334418, "grad_norm": 0.8453270150318835, "learning_rate": 3.749427903391275e-05, "loss": 0.552, "num_tokens": 216257470.0, "step": 36165 }, { "epoch": 0.3858833068396402, "grad_norm": 1.248739239594665, "learning_rate": 3.74907228659098e-05, "loss": 0.4777, "num_tokens": 216284027.0, "step": 36170 }, { "epoch": 0.3859366498458387, "grad_norm": 0.7204507019948558, "learning_rate": 3.748716638701608e-05, "loss": 0.548, "num_tokens": 216305266.0, "step": 36175 }, { "epoch": 0.38598999285203717, "grad_norm": 1.4858080303658945, "learning_rate": 3.748360959734225e-05, "loss": 0.6881, "num_tokens": 216337917.0, "step": 36180 }, { "epoch": 0.38604333585823564, "grad_norm": 1.2329652732677643, "learning_rate": 3.748005249699899e-05, "loss": 0.5231, "num_tokens": 216370574.0, "step": 36185 }, { "epoch": 0.3860966788644341, "grad_norm": 1.108714266140632, "learning_rate": 3.747649508609701e-05, "loss": 0.8002, "num_tokens": 216404939.0, "step": 36190 }, { "epoch": 0.3861500218706325, "grad_norm": 0.7515810650120551, "learning_rate": 3.747293736474698e-05, "loss": 0.4719, "num_tokens": 216432795.0, "step": 36195 }, { "epoch": 0.386203364876831, "grad_norm": 1.1067927836320786, "learning_rate": 3.7469379333059636e-05, "loss": 0.6915, "num_tokens": 216483780.0, "step": 36200 }, { "epoch": 0.38625670788302946, "grad_norm": 1.3572997397985018, "learning_rate": 3.746582099114568e-05, "loss": 0.592, "num_tokens": 216515381.0, "step": 36205 }, { "epoch": 0.38631005088922793, "grad_norm": 1.3829372904348205, "learning_rate": 3.746226233911585e-05, "loss": 0.5463, "num_tokens": 216543724.0, "step": 36210 }, { "epoch": 0.38636339389542634, "grad_norm": 1.6677350855945465, "learning_rate": 3.745870337708087e-05, "loss": 0.5099, "num_tokens": 216572378.0, "step": 36215 }, { "epoch": 0.3864167369016248, "grad_norm": 1.083159730714622, "learning_rate": 3.7455144105151504e-05, "loss": 0.6063, "num_tokens": 216596502.0, "step": 36220 }, { "epoch": 0.3864700799078233, "grad_norm": 0.8130869172824239, "learning_rate": 3.7451584523438506e-05, "loss": 0.4784, "num_tokens": 216623143.0, "step": 36225 }, { "epoch": 0.38652342291402175, "grad_norm": 1.3827530170462157, "learning_rate": 3.744802463205263e-05, "loss": 0.588, "num_tokens": 216669288.0, "step": 36230 }, { "epoch": 0.3865767659202202, "grad_norm": 3.648439557188578, "learning_rate": 3.744446443110467e-05, "loss": 0.6442, "num_tokens": 216707871.0, "step": 36235 }, { "epoch": 0.38663010892641864, "grad_norm": 0.8116964584153378, "learning_rate": 3.744090392070539e-05, "loss": 0.5288, "num_tokens": 216725313.0, "step": 36240 }, { "epoch": 0.3866834519326171, "grad_norm": 1.1084634058122096, "learning_rate": 3.743734310096561e-05, "loss": 0.5979, "num_tokens": 216752501.0, "step": 36245 }, { "epoch": 0.3867367949388156, "grad_norm": 0.9133298431744399, "learning_rate": 3.743378197199612e-05, "loss": 0.5762, "num_tokens": 216786714.0, "step": 36250 }, { "epoch": 0.38679013794501405, "grad_norm": 0.8829328544800065, "learning_rate": 3.743022053390774e-05, "loss": 0.6371, "num_tokens": 216821523.0, "step": 36255 }, { "epoch": 0.38684348095121246, "grad_norm": 1.4619457316609108, "learning_rate": 3.7426658786811294e-05, "loss": 0.5119, "num_tokens": 216855046.0, "step": 36260 }, { "epoch": 0.38689682395741093, "grad_norm": 1.1679002992762206, "learning_rate": 3.742309673081762e-05, "loss": 0.5574, "num_tokens": 216871851.0, "step": 36265 }, { "epoch": 0.3869501669636094, "grad_norm": 1.5647453088157515, "learning_rate": 3.741953436603756e-05, "loss": 0.656, "num_tokens": 216891781.0, "step": 36270 }, { "epoch": 0.38700350996980787, "grad_norm": 0.863128515699378, "learning_rate": 3.7415971692581954e-05, "loss": 0.5509, "num_tokens": 216918847.0, "step": 36275 }, { "epoch": 0.38705685297600634, "grad_norm": 0.7242070649344883, "learning_rate": 3.7412408710561685e-05, "loss": 0.5573, "num_tokens": 216958249.0, "step": 36280 }, { "epoch": 0.38711019598220475, "grad_norm": 0.767219980618807, "learning_rate": 3.740884542008762e-05, "loss": 0.6085, "num_tokens": 217001478.0, "step": 36285 }, { "epoch": 0.3871635389884032, "grad_norm": 1.439504815407094, "learning_rate": 3.740528182127063e-05, "loss": 0.4453, "num_tokens": 217017012.0, "step": 36290 }, { "epoch": 0.3872168819946017, "grad_norm": 2.4483814864106477, "learning_rate": 3.7401717914221625e-05, "loss": 0.6354, "num_tokens": 217040709.0, "step": 36295 }, { "epoch": 0.38727022500080016, "grad_norm": 0.8972908993905144, "learning_rate": 3.7398153699051496e-05, "loss": 0.565, "num_tokens": 217086832.0, "step": 36300 }, { "epoch": 0.3873235680069986, "grad_norm": 1.9027993364431683, "learning_rate": 3.739458917587115e-05, "loss": 0.6028, "num_tokens": 217109798.0, "step": 36305 }, { "epoch": 0.38737691101319705, "grad_norm": 0.9445204758189044, "learning_rate": 3.739102434479151e-05, "loss": 0.6445, "num_tokens": 217143895.0, "step": 36310 }, { "epoch": 0.3874302540193955, "grad_norm": 0.8445770442496797, "learning_rate": 3.738745920592352e-05, "loss": 0.5572, "num_tokens": 217179058.0, "step": 36315 }, { "epoch": 0.387483597025594, "grad_norm": 1.0988520103331314, "learning_rate": 3.738389375937811e-05, "loss": 0.5451, "num_tokens": 217208489.0, "step": 36320 }, { "epoch": 0.38753694003179245, "grad_norm": 1.0603700323035545, "learning_rate": 3.7380328005266216e-05, "loss": 0.4762, "num_tokens": 217228136.0, "step": 36325 }, { "epoch": 0.38759028303799087, "grad_norm": 0.7404224278873514, "learning_rate": 3.737676194369882e-05, "loss": 0.4435, "num_tokens": 217259100.0, "step": 36330 }, { "epoch": 0.38764362604418934, "grad_norm": 0.8935729595941357, "learning_rate": 3.737319557478688e-05, "loss": 0.4942, "num_tokens": 217278022.0, "step": 36335 }, { "epoch": 0.3876969690503878, "grad_norm": 1.008783803006817, "learning_rate": 3.736962889864137e-05, "loss": 0.6102, "num_tokens": 217318151.0, "step": 36340 }, { "epoch": 0.3877503120565863, "grad_norm": 1.1193996147258845, "learning_rate": 3.7366061915373274e-05, "loss": 0.4441, "num_tokens": 217346492.0, "step": 36345 }, { "epoch": 0.3878036550627847, "grad_norm": 1.4398617476867845, "learning_rate": 3.73624946250936e-05, "loss": 0.4684, "num_tokens": 217361460.0, "step": 36350 }, { "epoch": 0.38785699806898316, "grad_norm": 1.0068432569272356, "learning_rate": 3.735892702791337e-05, "loss": 0.577, "num_tokens": 217394927.0, "step": 36355 }, { "epoch": 0.38791034107518163, "grad_norm": 1.9680322560731136, "learning_rate": 3.735535912394356e-05, "loss": 0.672, "num_tokens": 217421944.0, "step": 36360 }, { "epoch": 0.3879636840813801, "grad_norm": 0.7577216891050893, "learning_rate": 3.735179091329522e-05, "loss": 0.5744, "num_tokens": 217458006.0, "step": 36365 }, { "epoch": 0.38801702708757857, "grad_norm": 0.9627657629094605, "learning_rate": 3.734822239607939e-05, "loss": 0.5178, "num_tokens": 217491195.0, "step": 36370 }, { "epoch": 0.388070370093777, "grad_norm": 0.9510306651564172, "learning_rate": 3.7344653572407105e-05, "loss": 0.4365, "num_tokens": 217509454.0, "step": 36375 }, { "epoch": 0.38812371309997545, "grad_norm": 1.2086121387738855, "learning_rate": 3.7341084442389415e-05, "loss": 0.5128, "num_tokens": 217525496.0, "step": 36380 }, { "epoch": 0.3881770561061739, "grad_norm": 0.7491066962950604, "learning_rate": 3.7337515006137405e-05, "loss": 0.6484, "num_tokens": 217568055.0, "step": 36385 }, { "epoch": 0.3882303991123724, "grad_norm": 0.7648747927888809, "learning_rate": 3.733394526376214e-05, "loss": 0.4725, "num_tokens": 217600182.0, "step": 36390 }, { "epoch": 0.3882837421185708, "grad_norm": 0.8975537608330645, "learning_rate": 3.733037521537468e-05, "loss": 0.4756, "num_tokens": 217629509.0, "step": 36395 }, { "epoch": 0.3883370851247693, "grad_norm": 1.5671806298557063, "learning_rate": 3.732680486108614e-05, "loss": 0.5498, "num_tokens": 217652555.0, "step": 36400 }, { "epoch": 0.38839042813096775, "grad_norm": 0.7741654346355169, "learning_rate": 3.7323234201007615e-05, "loss": 0.6103, "num_tokens": 217690701.0, "step": 36405 }, { "epoch": 0.3884437711371662, "grad_norm": 0.9932196382774494, "learning_rate": 3.731966323525023e-05, "loss": 0.4333, "num_tokens": 217705278.0, "step": 36410 }, { "epoch": 0.3884971141433647, "grad_norm": 0.9385203241404539, "learning_rate": 3.731609196392509e-05, "loss": 0.3747, "num_tokens": 217719817.0, "step": 36415 }, { "epoch": 0.3885504571495631, "grad_norm": 0.948674966353218, "learning_rate": 3.731252038714332e-05, "loss": 0.5284, "num_tokens": 217737432.0, "step": 36420 }, { "epoch": 0.38860380015576157, "grad_norm": 0.9585137726424129, "learning_rate": 3.730894850501609e-05, "loss": 0.6048, "num_tokens": 217767322.0, "step": 36425 }, { "epoch": 0.38865714316196004, "grad_norm": 2.8030520073075738, "learning_rate": 3.7305376317654524e-05, "loss": 0.5759, "num_tokens": 217799025.0, "step": 36430 }, { "epoch": 0.3887104861681585, "grad_norm": 0.9996574574047181, "learning_rate": 3.7301803825169784e-05, "loss": 0.4997, "num_tokens": 217824780.0, "step": 36435 }, { "epoch": 0.3887638291743569, "grad_norm": 0.812725314741727, "learning_rate": 3.7298231027673034e-05, "loss": 0.5598, "num_tokens": 217871810.0, "step": 36440 }, { "epoch": 0.3888171721805554, "grad_norm": 1.1726808604216117, "learning_rate": 3.729465792527548e-05, "loss": 0.5933, "num_tokens": 217904820.0, "step": 36445 }, { "epoch": 0.38887051518675386, "grad_norm": 1.1875904611001542, "learning_rate": 3.7291084518088274e-05, "loss": 0.4924, "num_tokens": 217944208.0, "step": 36450 }, { "epoch": 0.38892385819295233, "grad_norm": 1.4597941123639764, "learning_rate": 3.7287510806222635e-05, "loss": 0.6576, "num_tokens": 217968573.0, "step": 36455 }, { "epoch": 0.3889772011991508, "grad_norm": 1.412278873728972, "learning_rate": 3.7283936789789765e-05, "loss": 0.6526, "num_tokens": 217989431.0, "step": 36460 }, { "epoch": 0.3890305442053492, "grad_norm": 1.3682921023468209, "learning_rate": 3.728036246890088e-05, "loss": 0.4845, "num_tokens": 218019682.0, "step": 36465 }, { "epoch": 0.3890838872115477, "grad_norm": 1.320090322167454, "learning_rate": 3.7276787843667204e-05, "loss": 0.5887, "num_tokens": 218053934.0, "step": 36470 }, { "epoch": 0.38913723021774616, "grad_norm": 1.3052227763864692, "learning_rate": 3.727321291419997e-05, "loss": 0.6484, "num_tokens": 218105104.0, "step": 36475 }, { "epoch": 0.3891905732239446, "grad_norm": 1.195477252707485, "learning_rate": 3.726963768061042e-05, "loss": 0.6842, "num_tokens": 218144024.0, "step": 36480 }, { "epoch": 0.38924391623014304, "grad_norm": 0.8452619126802592, "learning_rate": 3.7266062143009826e-05, "loss": 0.5412, "num_tokens": 218164956.0, "step": 36485 }, { "epoch": 0.3892972592363415, "grad_norm": 0.9022312661284112, "learning_rate": 3.726248630150943e-05, "loss": 0.4599, "num_tokens": 218200244.0, "step": 36490 }, { "epoch": 0.38935060224254, "grad_norm": 0.6641090578329321, "learning_rate": 3.725891015622052e-05, "loss": 0.5657, "num_tokens": 218227809.0, "step": 36495 }, { "epoch": 0.38940394524873845, "grad_norm": 0.9946894994789157, "learning_rate": 3.725533370725436e-05, "loss": 0.5135, "num_tokens": 218255735.0, "step": 36500 }, { "epoch": 0.3894572882549369, "grad_norm": 2.590720746385786, "learning_rate": 3.7251756954722264e-05, "loss": 0.6565, "num_tokens": 218278721.0, "step": 36505 }, { "epoch": 0.38951063126113533, "grad_norm": 0.8289145153183772, "learning_rate": 3.7248179898735516e-05, "loss": 0.7481, "num_tokens": 218318303.0, "step": 36510 }, { "epoch": 0.3895639742673338, "grad_norm": 1.1418089595155068, "learning_rate": 3.724460253940543e-05, "loss": 0.664, "num_tokens": 218351197.0, "step": 36515 }, { "epoch": 0.38961731727353227, "grad_norm": 1.1631452492307277, "learning_rate": 3.7241024876843334e-05, "loss": 0.4878, "num_tokens": 218379375.0, "step": 36520 }, { "epoch": 0.38967066027973074, "grad_norm": 1.6482521320783803, "learning_rate": 3.723744691116055e-05, "loss": 0.4682, "num_tokens": 218396902.0, "step": 36525 }, { "epoch": 0.38972400328592915, "grad_norm": 0.8076414240328673, "learning_rate": 3.723386864246842e-05, "loss": 0.67, "num_tokens": 218447020.0, "step": 36530 }, { "epoch": 0.3897773462921276, "grad_norm": 0.7247899813786158, "learning_rate": 3.72302900708783e-05, "loss": 0.5734, "num_tokens": 218475099.0, "step": 36535 }, { "epoch": 0.3898306892983261, "grad_norm": 1.0973129317729018, "learning_rate": 3.7226711196501524e-05, "loss": 0.5713, "num_tokens": 218500225.0, "step": 36540 }, { "epoch": 0.38988403230452456, "grad_norm": 0.8818431683954903, "learning_rate": 3.722313201944948e-05, "loss": 0.4816, "num_tokens": 218528367.0, "step": 36545 }, { "epoch": 0.38993737531072303, "grad_norm": 1.633005290344145, "learning_rate": 3.7219552539833546e-05, "loss": 0.6929, "num_tokens": 218584310.0, "step": 36550 }, { "epoch": 0.38999071831692145, "grad_norm": 1.2432677972485036, "learning_rate": 3.7215972757765094e-05, "loss": 0.7161, "num_tokens": 218609438.0, "step": 36555 }, { "epoch": 0.3900440613231199, "grad_norm": 0.9296992478533737, "learning_rate": 3.721239267335553e-05, "loss": 0.4693, "num_tokens": 218629470.0, "step": 36560 }, { "epoch": 0.3900974043293184, "grad_norm": 0.6168892847252477, "learning_rate": 3.720881228671626e-05, "loss": 0.5023, "num_tokens": 218669442.0, "step": 36565 }, { "epoch": 0.39015074733551686, "grad_norm": 0.8624576984431901, "learning_rate": 3.720523159795869e-05, "loss": 0.614, "num_tokens": 218694506.0, "step": 36570 }, { "epoch": 0.39020409034171527, "grad_norm": 0.6507971670742116, "learning_rate": 3.720165060719425e-05, "loss": 0.47, "num_tokens": 218713852.0, "step": 36575 }, { "epoch": 0.39025743334791374, "grad_norm": 1.2108650379246746, "learning_rate": 3.719806931453437e-05, "loss": 0.5482, "num_tokens": 218747042.0, "step": 36580 }, { "epoch": 0.3903107763541122, "grad_norm": 0.7126869840872342, "learning_rate": 3.7194487720090487e-05, "loss": 0.5505, "num_tokens": 218791072.0, "step": 36585 }, { "epoch": 0.3903641193603107, "grad_norm": 0.862467461574206, "learning_rate": 3.719090582397407e-05, "loss": 0.4717, "num_tokens": 218825047.0, "step": 36590 }, { "epoch": 0.39041746236650915, "grad_norm": 1.2611885730548391, "learning_rate": 3.7187323626296566e-05, "loss": 0.5328, "num_tokens": 218851702.0, "step": 36595 }, { "epoch": 0.39047080537270756, "grad_norm": 1.0426615052421158, "learning_rate": 3.718374112716944e-05, "loss": 0.6005, "num_tokens": 218888754.0, "step": 36600 }, { "epoch": 0.39052414837890603, "grad_norm": 0.7454676373897025, "learning_rate": 3.718015832670419e-05, "loss": 0.5571, "num_tokens": 218923479.0, "step": 36605 }, { "epoch": 0.3905774913851045, "grad_norm": 1.4898645794444432, "learning_rate": 3.717657522501231e-05, "loss": 0.576, "num_tokens": 218960598.0, "step": 36610 }, { "epoch": 0.390630834391303, "grad_norm": 1.1558963527913406, "learning_rate": 3.717299182220525e-05, "loss": 0.5542, "num_tokens": 218996984.0, "step": 36615 }, { "epoch": 0.3906841773975014, "grad_norm": 0.6344915135051565, "learning_rate": 3.716940811839458e-05, "loss": 0.4851, "num_tokens": 219042248.0, "step": 36620 }, { "epoch": 0.39073752040369986, "grad_norm": 0.9233506710803663, "learning_rate": 3.7165824113691786e-05, "loss": 0.5736, "num_tokens": 219068543.0, "step": 36625 }, { "epoch": 0.3907908634098983, "grad_norm": 1.0869653443500162, "learning_rate": 3.71622398082084e-05, "loss": 0.6376, "num_tokens": 219089670.0, "step": 36630 }, { "epoch": 0.3908442064160968, "grad_norm": 1.6145703256727397, "learning_rate": 3.715865520205595e-05, "loss": 0.6217, "num_tokens": 219149990.0, "step": 36635 }, { "epoch": 0.39089754942229527, "grad_norm": 0.7369889712842055, "learning_rate": 3.7155070295346e-05, "loss": 0.5221, "num_tokens": 219181187.0, "step": 36640 }, { "epoch": 0.3909508924284937, "grad_norm": 3.3346638020188184, "learning_rate": 3.71514850881901e-05, "loss": 0.5945, "num_tokens": 219203339.0, "step": 36645 }, { "epoch": 0.39100423543469215, "grad_norm": 1.3648437761987147, "learning_rate": 3.714789958069979e-05, "loss": 0.5211, "num_tokens": 219226431.0, "step": 36650 }, { "epoch": 0.3910575784408906, "grad_norm": 1.0957216225646749, "learning_rate": 3.714431377298668e-05, "loss": 0.5, "num_tokens": 219257482.0, "step": 36655 }, { "epoch": 0.3911109214470891, "grad_norm": 0.823697747360275, "learning_rate": 3.7140727665162324e-05, "loss": 0.5047, "num_tokens": 219285857.0, "step": 36660 }, { "epoch": 0.3911642644532875, "grad_norm": 0.714043367427268, "learning_rate": 3.713714125733832e-05, "loss": 0.6489, "num_tokens": 219304626.0, "step": 36665 }, { "epoch": 0.39121760745948597, "grad_norm": 1.0646594183681706, "learning_rate": 3.713355454962629e-05, "loss": 0.5399, "num_tokens": 219327427.0, "step": 36670 }, { "epoch": 0.39127095046568444, "grad_norm": 1.8515317900761514, "learning_rate": 3.7129967542137815e-05, "loss": 0.5193, "num_tokens": 219358137.0, "step": 36675 }, { "epoch": 0.3913242934718829, "grad_norm": 0.7551877865497748, "learning_rate": 3.712638023498455e-05, "loss": 0.5159, "num_tokens": 219406684.0, "step": 36680 }, { "epoch": 0.3913776364780814, "grad_norm": 1.275552584381211, "learning_rate": 3.712279262827809e-05, "loss": 0.607, "num_tokens": 219428315.0, "step": 36685 }, { "epoch": 0.3914309794842798, "grad_norm": 1.4904982478534965, "learning_rate": 3.711920472213009e-05, "loss": 0.5325, "num_tokens": 219458963.0, "step": 36690 }, { "epoch": 0.39148432249047826, "grad_norm": 0.816591780067836, "learning_rate": 3.71156165166522e-05, "loss": 0.4961, "num_tokens": 219479025.0, "step": 36695 }, { "epoch": 0.39153766549667673, "grad_norm": 0.8079949938632679, "learning_rate": 3.711202801195608e-05, "loss": 0.575, "num_tokens": 219507545.0, "step": 36700 }, { "epoch": 0.3915910085028752, "grad_norm": 0.9956792568173465, "learning_rate": 3.710843920815339e-05, "loss": 0.4858, "num_tokens": 219539062.0, "step": 36705 }, { "epoch": 0.3916443515090736, "grad_norm": 1.043610129610201, "learning_rate": 3.710485010535581e-05, "loss": 0.5788, "num_tokens": 219574532.0, "step": 36710 }, { "epoch": 0.3916976945152721, "grad_norm": 1.1530690044879173, "learning_rate": 3.710126070367502e-05, "loss": 0.6948, "num_tokens": 219613975.0, "step": 36715 }, { "epoch": 0.39175103752147056, "grad_norm": 1.119532570297966, "learning_rate": 3.709767100322272e-05, "loss": 0.5819, "num_tokens": 219640135.0, "step": 36720 }, { "epoch": 0.391804380527669, "grad_norm": 0.7161446307055815, "learning_rate": 3.7094081004110606e-05, "loss": 0.4939, "num_tokens": 219669595.0, "step": 36725 }, { "epoch": 0.3918577235338675, "grad_norm": 0.587450301090291, "learning_rate": 3.70904907064504e-05, "loss": 0.4419, "num_tokens": 219722607.0, "step": 36730 }, { "epoch": 0.3919110665400659, "grad_norm": 1.094531991427482, "learning_rate": 3.7086900110353837e-05, "loss": 0.5051, "num_tokens": 219742207.0, "step": 36735 }, { "epoch": 0.3919644095462644, "grad_norm": 0.6971951327953062, "learning_rate": 3.708330921593262e-05, "loss": 0.499, "num_tokens": 219791701.0, "step": 36740 }, { "epoch": 0.39201775255246285, "grad_norm": 0.8044615331729905, "learning_rate": 3.70797180232985e-05, "loss": 0.5932, "num_tokens": 219826247.0, "step": 36745 }, { "epoch": 0.3920710955586613, "grad_norm": 0.892783738471104, "learning_rate": 3.7076126532563245e-05, "loss": 0.5323, "num_tokens": 219851445.0, "step": 36750 }, { "epoch": 0.39212443856485973, "grad_norm": 0.8282266755616665, "learning_rate": 3.70725347438386e-05, "loss": 0.5926, "num_tokens": 219884491.0, "step": 36755 }, { "epoch": 0.3921777815710582, "grad_norm": 1.4283793363007267, "learning_rate": 3.706894265723634e-05, "loss": 0.7348, "num_tokens": 219905825.0, "step": 36760 }, { "epoch": 0.3922311245772567, "grad_norm": 0.9927782202061267, "learning_rate": 3.7065350272868224e-05, "loss": 0.5409, "num_tokens": 219939133.0, "step": 36765 }, { "epoch": 0.39228446758345514, "grad_norm": 1.3578516487362156, "learning_rate": 3.706175759084607e-05, "loss": 0.5668, "num_tokens": 219954419.0, "step": 36770 }, { "epoch": 0.3923378105896536, "grad_norm": 1.7316812567050959, "learning_rate": 3.705816461128166e-05, "loss": 0.7282, "num_tokens": 219982906.0, "step": 36775 }, { "epoch": 0.392391153595852, "grad_norm": 2.3363892307039746, "learning_rate": 3.7054571334286794e-05, "loss": 0.5801, "num_tokens": 219997205.0, "step": 36780 }, { "epoch": 0.3924444966020505, "grad_norm": 0.9067967692411096, "learning_rate": 3.7050977759973294e-05, "loss": 0.5709, "num_tokens": 220018668.0, "step": 36785 }, { "epoch": 0.39249783960824897, "grad_norm": 1.4160722817209304, "learning_rate": 3.704738388845299e-05, "loss": 0.5072, "num_tokens": 220040116.0, "step": 36790 }, { "epoch": 0.39255118261444744, "grad_norm": 0.7907940625424995, "learning_rate": 3.70437897198377e-05, "loss": 0.4914, "num_tokens": 220083387.0, "step": 36795 }, { "epoch": 0.39260452562064585, "grad_norm": 0.9648348891879264, "learning_rate": 3.704019525423929e-05, "loss": 0.5996, "num_tokens": 220108684.0, "step": 36800 }, { "epoch": 0.3926578686268443, "grad_norm": 0.932179062541851, "learning_rate": 3.7036600491769586e-05, "loss": 0.5879, "num_tokens": 220135684.0, "step": 36805 }, { "epoch": 0.3927112116330428, "grad_norm": 0.6800964361555872, "learning_rate": 3.7033005432540474e-05, "loss": 0.585, "num_tokens": 220171179.0, "step": 36810 }, { "epoch": 0.39276455463924126, "grad_norm": 1.1834726374159281, "learning_rate": 3.702941007666381e-05, "loss": 0.5369, "num_tokens": 220191189.0, "step": 36815 }, { "epoch": 0.39281789764543973, "grad_norm": 0.7485545943140319, "learning_rate": 3.702581442425148e-05, "loss": 0.5217, "num_tokens": 220234664.0, "step": 36820 }, { "epoch": 0.39287124065163814, "grad_norm": 0.9056180220106556, "learning_rate": 3.702221847541537e-05, "loss": 0.5647, "num_tokens": 220264621.0, "step": 36825 }, { "epoch": 0.3929245836578366, "grad_norm": 1.04239169366955, "learning_rate": 3.701862223026738e-05, "loss": 0.519, "num_tokens": 220291958.0, "step": 36830 }, { "epoch": 0.3929779266640351, "grad_norm": 1.1537944543302736, "learning_rate": 3.701502568891943e-05, "loss": 0.6253, "num_tokens": 220323889.0, "step": 36835 }, { "epoch": 0.39303126967023355, "grad_norm": 0.6189267335509699, "learning_rate": 3.701142885148341e-05, "loss": 0.5017, "num_tokens": 220361055.0, "step": 36840 }, { "epoch": 0.39308461267643197, "grad_norm": 1.2316840099947566, "learning_rate": 3.700783171807126e-05, "loss": 0.4868, "num_tokens": 220396347.0, "step": 36845 }, { "epoch": 0.39313795568263044, "grad_norm": 0.7666701714267401, "learning_rate": 3.700423428879493e-05, "loss": 0.5772, "num_tokens": 220426141.0, "step": 36850 }, { "epoch": 0.3931912986888289, "grad_norm": 0.7289377604574772, "learning_rate": 3.700063656376634e-05, "loss": 0.4938, "num_tokens": 220457739.0, "step": 36855 }, { "epoch": 0.3932446416950274, "grad_norm": 1.701283608776797, "learning_rate": 3.699703854309746e-05, "loss": 0.6812, "num_tokens": 220485381.0, "step": 36860 }, { "epoch": 0.39329798470122584, "grad_norm": 0.9990872361481576, "learning_rate": 3.6993440226900245e-05, "loss": 0.7006, "num_tokens": 220507326.0, "step": 36865 }, { "epoch": 0.39335132770742426, "grad_norm": 0.7225372962977584, "learning_rate": 3.6989841615286666e-05, "loss": 0.5066, "num_tokens": 220555833.0, "step": 36870 }, { "epoch": 0.39340467071362273, "grad_norm": 1.6575682207764852, "learning_rate": 3.698624270836872e-05, "loss": 0.56, "num_tokens": 220585346.0, "step": 36875 }, { "epoch": 0.3934580137198212, "grad_norm": 0.9239621176212599, "learning_rate": 3.698264350625838e-05, "loss": 0.4642, "num_tokens": 220604139.0, "step": 36880 }, { "epoch": 0.39351135672601967, "grad_norm": 0.999142909201398, "learning_rate": 3.697904400906765e-05, "loss": 0.5518, "num_tokens": 220644645.0, "step": 36885 }, { "epoch": 0.3935646997322181, "grad_norm": 0.9511444667593116, "learning_rate": 3.697544421690854e-05, "loss": 0.7421, "num_tokens": 220674044.0, "step": 36890 }, { "epoch": 0.39361804273841655, "grad_norm": 0.8679627435983323, "learning_rate": 3.697184412989308e-05, "loss": 0.484, "num_tokens": 220691989.0, "step": 36895 }, { "epoch": 0.393671385744615, "grad_norm": 1.1206968050703163, "learning_rate": 3.696824374813327e-05, "loss": 0.4056, "num_tokens": 220711176.0, "step": 36900 }, { "epoch": 0.3937247287508135, "grad_norm": 1.2572974741687546, "learning_rate": 3.6964643071741176e-05, "loss": 0.4741, "num_tokens": 220722209.0, "step": 36905 }, { "epoch": 0.39377807175701196, "grad_norm": 0.7687661840311097, "learning_rate": 3.696104210082883e-05, "loss": 0.5214, "num_tokens": 220746226.0, "step": 36910 }, { "epoch": 0.3938314147632104, "grad_norm": 0.9366451979495456, "learning_rate": 3.695744083550828e-05, "loss": 0.6981, "num_tokens": 220789523.0, "step": 36915 }, { "epoch": 0.39388475776940884, "grad_norm": 0.8545946647189215, "learning_rate": 3.6953839275891606e-05, "loss": 0.6344, "num_tokens": 220822559.0, "step": 36920 }, { "epoch": 0.3939381007756073, "grad_norm": 0.7493201473603209, "learning_rate": 3.695023742209086e-05, "loss": 0.5295, "num_tokens": 220850155.0, "step": 36925 }, { "epoch": 0.3939914437818058, "grad_norm": 0.9455884721494768, "learning_rate": 3.694663527421815e-05, "loss": 0.4824, "num_tokens": 220883976.0, "step": 36930 }, { "epoch": 0.3940447867880042, "grad_norm": 1.0234456137216759, "learning_rate": 3.6943032832385555e-05, "loss": 0.5638, "num_tokens": 220915915.0, "step": 36935 }, { "epoch": 0.39409812979420267, "grad_norm": 1.5926532879397286, "learning_rate": 3.693943009670516e-05, "loss": 0.5325, "num_tokens": 220941847.0, "step": 36940 }, { "epoch": 0.39415147280040114, "grad_norm": 0.8983456441920276, "learning_rate": 3.69358270672891e-05, "loss": 0.5454, "num_tokens": 220974967.0, "step": 36945 }, { "epoch": 0.3942048158065996, "grad_norm": 1.189315907197721, "learning_rate": 3.693222374424948e-05, "loss": 0.6464, "num_tokens": 221005023.0, "step": 36950 }, { "epoch": 0.3942581588127981, "grad_norm": 0.7737123731735863, "learning_rate": 3.6928620127698435e-05, "loss": 0.611, "num_tokens": 221047356.0, "step": 36955 }, { "epoch": 0.3943115018189965, "grad_norm": 1.5218596683378158, "learning_rate": 3.6925016217748095e-05, "loss": 0.7508, "num_tokens": 221095532.0, "step": 36960 }, { "epoch": 0.39436484482519496, "grad_norm": 1.0814511614837932, "learning_rate": 3.692141201451061e-05, "loss": 0.4675, "num_tokens": 221131536.0, "step": 36965 }, { "epoch": 0.39441818783139343, "grad_norm": 0.9816521375698919, "learning_rate": 3.691780751809814e-05, "loss": 0.5504, "num_tokens": 221165388.0, "step": 36970 }, { "epoch": 0.3944715308375919, "grad_norm": 0.9197792848498246, "learning_rate": 3.691420272862284e-05, "loss": 0.4953, "num_tokens": 221193237.0, "step": 36975 }, { "epoch": 0.3945248738437903, "grad_norm": 0.8292403808488921, "learning_rate": 3.6910597646196886e-05, "loss": 0.6308, "num_tokens": 221246884.0, "step": 36980 }, { "epoch": 0.3945782168499888, "grad_norm": 0.968683869073817, "learning_rate": 3.690699227093247e-05, "loss": 0.5093, "num_tokens": 221274500.0, "step": 36985 }, { "epoch": 0.39463155985618725, "grad_norm": 0.7506017041716612, "learning_rate": 3.6903386602941774e-05, "loss": 0.5646, "num_tokens": 221310653.0, "step": 36990 }, { "epoch": 0.3946849028623857, "grad_norm": 1.9444582644769326, "learning_rate": 3.6899780642337e-05, "loss": 0.6218, "num_tokens": 221337394.0, "step": 36995 }, { "epoch": 0.3947382458685842, "grad_norm": 1.5288429284261305, "learning_rate": 3.6896174389230365e-05, "loss": 0.4934, "num_tokens": 221363758.0, "step": 37000 }, { "epoch": 0.3947915888747826, "grad_norm": 1.0080754011923045, "learning_rate": 3.689256784373407e-05, "loss": 0.6067, "num_tokens": 221389233.0, "step": 37005 }, { "epoch": 0.3948449318809811, "grad_norm": 1.65992951685494, "learning_rate": 3.688896100596037e-05, "loss": 0.6162, "num_tokens": 221415338.0, "step": 37010 }, { "epoch": 0.39489827488717955, "grad_norm": 0.9635081777205251, "learning_rate": 3.688535387602149e-05, "loss": 0.6627, "num_tokens": 221452505.0, "step": 37015 }, { "epoch": 0.394951617893378, "grad_norm": 0.961031478585396, "learning_rate": 3.688174645402967e-05, "loss": 0.6349, "num_tokens": 221481301.0, "step": 37020 }, { "epoch": 0.39500496089957643, "grad_norm": 0.876887350608029, "learning_rate": 3.687813874009717e-05, "loss": 0.499, "num_tokens": 221509256.0, "step": 37025 }, { "epoch": 0.3950583039057749, "grad_norm": 1.4075253536617258, "learning_rate": 3.687453073433626e-05, "loss": 0.647, "num_tokens": 221523120.0, "step": 37030 }, { "epoch": 0.39511164691197337, "grad_norm": 0.810228585151982, "learning_rate": 3.6870922436859214e-05, "loss": 0.6067, "num_tokens": 221554609.0, "step": 37035 }, { "epoch": 0.39516498991817184, "grad_norm": 0.7518520211083144, "learning_rate": 3.68673138477783e-05, "loss": 0.6031, "num_tokens": 221572320.0, "step": 37040 }, { "epoch": 0.3952183329243703, "grad_norm": 4.154020494846117, "learning_rate": 3.686370496720582e-05, "loss": 0.6353, "num_tokens": 221625487.0, "step": 37045 }, { "epoch": 0.3952716759305687, "grad_norm": 1.065351972108324, "learning_rate": 3.686009579525408e-05, "loss": 0.6256, "num_tokens": 221658193.0, "step": 37050 }, { "epoch": 0.3953250189367672, "grad_norm": 3.1284680999169248, "learning_rate": 3.685648633203539e-05, "loss": 0.6908, "num_tokens": 221705319.0, "step": 37055 }, { "epoch": 0.39537836194296566, "grad_norm": 0.832769389975497, "learning_rate": 3.685287657766205e-05, "loss": 0.4574, "num_tokens": 221734404.0, "step": 37060 }, { "epoch": 0.39543170494916413, "grad_norm": 1.155469085869443, "learning_rate": 3.6849266532246414e-05, "loss": 0.6041, "num_tokens": 221749976.0, "step": 37065 }, { "epoch": 0.39548504795536255, "grad_norm": 0.8187916809291509, "learning_rate": 3.68456561959008e-05, "loss": 0.539, "num_tokens": 221776348.0, "step": 37070 }, { "epoch": 0.395538390961561, "grad_norm": 0.9122063911303424, "learning_rate": 3.684204556873756e-05, "loss": 0.4836, "num_tokens": 221795866.0, "step": 37075 }, { "epoch": 0.3955917339677595, "grad_norm": 1.140211279950568, "learning_rate": 3.683843465086907e-05, "loss": 0.521, "num_tokens": 221808560.0, "step": 37080 }, { "epoch": 0.39564507697395795, "grad_norm": 1.5339227692274484, "learning_rate": 3.6834823442407664e-05, "loss": 0.6678, "num_tokens": 221830742.0, "step": 37085 }, { "epoch": 0.3956984199801564, "grad_norm": 1.0937677163292858, "learning_rate": 3.683121194346571e-05, "loss": 0.5556, "num_tokens": 221867160.0, "step": 37090 }, { "epoch": 0.39575176298635484, "grad_norm": 0.8164404229428419, "learning_rate": 3.6827600154155625e-05, "loss": 0.5429, "num_tokens": 221902559.0, "step": 37095 }, { "epoch": 0.3958051059925533, "grad_norm": 1.1243664711874284, "learning_rate": 3.682398807458978e-05, "loss": 0.5426, "num_tokens": 221942357.0, "step": 37100 }, { "epoch": 0.3958584489987518, "grad_norm": 0.7018588459354789, "learning_rate": 3.682037570488058e-05, "loss": 0.5289, "num_tokens": 221970084.0, "step": 37105 }, { "epoch": 0.39591179200495025, "grad_norm": 0.667350891698804, "learning_rate": 3.681676304514043e-05, "loss": 0.5797, "num_tokens": 222005165.0, "step": 37110 }, { "epoch": 0.39596513501114866, "grad_norm": 0.9374186662690913, "learning_rate": 3.6813150095481753e-05, "loss": 0.4716, "num_tokens": 222028952.0, "step": 37115 }, { "epoch": 0.39601847801734713, "grad_norm": 1.5491432012032735, "learning_rate": 3.680953685601697e-05, "loss": 0.5868, "num_tokens": 222057295.0, "step": 37120 }, { "epoch": 0.3960718210235456, "grad_norm": 1.506768109822543, "learning_rate": 3.6805923326858524e-05, "loss": 0.5688, "num_tokens": 222079990.0, "step": 37125 }, { "epoch": 0.39612516402974407, "grad_norm": 0.6366973614453258, "learning_rate": 3.6802309508118866e-05, "loss": 0.5601, "num_tokens": 222112199.0, "step": 37130 }, { "epoch": 0.39617850703594254, "grad_norm": 1.1385780353740351, "learning_rate": 3.6798695399910435e-05, "loss": 0.5838, "num_tokens": 222146742.0, "step": 37135 }, { "epoch": 0.39623185004214095, "grad_norm": 1.081932387597149, "learning_rate": 3.67950810023457e-05, "loss": 0.6121, "num_tokens": 222164869.0, "step": 37140 }, { "epoch": 0.3962851930483394, "grad_norm": 1.522058084231441, "learning_rate": 3.679146631553715e-05, "loss": 0.5507, "num_tokens": 222205448.0, "step": 37145 }, { "epoch": 0.3963385360545379, "grad_norm": 1.5779738592548609, "learning_rate": 3.678785133959724e-05, "loss": 0.6071, "num_tokens": 222253441.0, "step": 37150 }, { "epoch": 0.39639187906073636, "grad_norm": 1.3824612486473788, "learning_rate": 3.678423607463848e-05, "loss": 0.4766, "num_tokens": 222274219.0, "step": 37155 }, { "epoch": 0.3964452220669348, "grad_norm": 0.9247625704245457, "learning_rate": 3.6780620520773365e-05, "loss": 0.5262, "num_tokens": 222298476.0, "step": 37160 }, { "epoch": 0.39649856507313325, "grad_norm": 0.7914820013263372, "learning_rate": 3.67770046781144e-05, "loss": 0.4562, "num_tokens": 222315335.0, "step": 37165 }, { "epoch": 0.3965519080793317, "grad_norm": 1.4859196805245525, "learning_rate": 3.677338854677411e-05, "loss": 0.643, "num_tokens": 222338199.0, "step": 37170 }, { "epoch": 0.3966052510855302, "grad_norm": 0.8600256534439696, "learning_rate": 3.676977212686502e-05, "loss": 0.6684, "num_tokens": 222370786.0, "step": 37175 }, { "epoch": 0.39665859409172866, "grad_norm": 1.4615352115914086, "learning_rate": 3.676615541849965e-05, "loss": 0.46, "num_tokens": 222400955.0, "step": 37180 }, { "epoch": 0.39671193709792707, "grad_norm": 0.8001408290538525, "learning_rate": 3.676253842179056e-05, "loss": 0.4532, "num_tokens": 222433585.0, "step": 37185 }, { "epoch": 0.39676528010412554, "grad_norm": 1.0512422947144422, "learning_rate": 3.67589211368503e-05, "loss": 0.769, "num_tokens": 222479102.0, "step": 37190 }, { "epoch": 0.396818623110324, "grad_norm": 0.9144637111544073, "learning_rate": 3.675530356379144e-05, "loss": 0.491, "num_tokens": 222512491.0, "step": 37195 }, { "epoch": 0.3968719661165225, "grad_norm": 0.9053764585651264, "learning_rate": 3.6751685702726534e-05, "loss": 0.6094, "num_tokens": 222548049.0, "step": 37200 }, { "epoch": 0.3969253091227209, "grad_norm": 0.9635511351038931, "learning_rate": 3.674806755376818e-05, "loss": 0.5627, "num_tokens": 222582620.0, "step": 37205 }, { "epoch": 0.39697865212891936, "grad_norm": 0.6953385709993573, "learning_rate": 3.674444911702896e-05, "loss": 0.4707, "num_tokens": 222608336.0, "step": 37210 }, { "epoch": 0.39703199513511783, "grad_norm": 0.7271102026149101, "learning_rate": 3.674083039262146e-05, "loss": 0.5977, "num_tokens": 222630880.0, "step": 37215 }, { "epoch": 0.3970853381413163, "grad_norm": 0.7958612529748672, "learning_rate": 3.673721138065831e-05, "loss": 0.6344, "num_tokens": 222668386.0, "step": 37220 }, { "epoch": 0.39713868114751477, "grad_norm": 1.0681067787737006, "learning_rate": 3.673359208125212e-05, "loss": 0.5582, "num_tokens": 222695463.0, "step": 37225 }, { "epoch": 0.3971920241537132, "grad_norm": 0.8649686045760034, "learning_rate": 3.67299724945155e-05, "loss": 0.5931, "num_tokens": 222719184.0, "step": 37230 }, { "epoch": 0.39724536715991166, "grad_norm": 0.8659502941254923, "learning_rate": 3.67263526205611e-05, "loss": 0.514, "num_tokens": 222752620.0, "step": 37235 }, { "epoch": 0.3972987101661101, "grad_norm": 0.8750483176991009, "learning_rate": 3.672273245950156e-05, "loss": 0.5622, "num_tokens": 222786151.0, "step": 37240 }, { "epoch": 0.3973520531723086, "grad_norm": 1.068271337565074, "learning_rate": 3.6719112011449526e-05, "loss": 0.62, "num_tokens": 222816956.0, "step": 37245 }, { "epoch": 0.397405396178507, "grad_norm": 1.181408925179804, "learning_rate": 3.6715491276517666e-05, "loss": 0.5784, "num_tokens": 222848593.0, "step": 37250 }, { "epoch": 0.3974587391847055, "grad_norm": 1.0055159202489157, "learning_rate": 3.671187025481864e-05, "loss": 0.4973, "num_tokens": 222865964.0, "step": 37255 }, { "epoch": 0.39751208219090395, "grad_norm": 1.0825354334658364, "learning_rate": 3.6708248946465135e-05, "loss": 0.5221, "num_tokens": 222912298.0, "step": 37260 }, { "epoch": 0.3975654251971024, "grad_norm": 0.8971375670960824, "learning_rate": 3.670462735156985e-05, "loss": 0.6168, "num_tokens": 222945910.0, "step": 37265 }, { "epoch": 0.3976187682033009, "grad_norm": 1.510682129182395, "learning_rate": 3.670100547024545e-05, "loss": 0.5453, "num_tokens": 222975034.0, "step": 37270 }, { "epoch": 0.3976721112094993, "grad_norm": 1.7674618052145332, "learning_rate": 3.669738330260467e-05, "loss": 0.5315, "num_tokens": 223000132.0, "step": 37275 }, { "epoch": 0.39772545421569777, "grad_norm": 8.724324131377609, "learning_rate": 3.669376084876021e-05, "loss": 0.8705, "num_tokens": 223017707.0, "step": 37280 }, { "epoch": 0.39777879722189624, "grad_norm": 1.1248331122238797, "learning_rate": 3.66901381088248e-05, "loss": 0.6834, "num_tokens": 223041794.0, "step": 37285 }, { "epoch": 0.3978321402280947, "grad_norm": 1.2250807303849647, "learning_rate": 3.6686515082911166e-05, "loss": 0.5375, "num_tokens": 223065901.0, "step": 37290 }, { "epoch": 0.3978854832342931, "grad_norm": 1.8571592408433075, "learning_rate": 3.6682891771132056e-05, "loss": 0.5669, "num_tokens": 223089162.0, "step": 37295 }, { "epoch": 0.3979388262404916, "grad_norm": 1.0712774057535743, "learning_rate": 3.6679268173600214e-05, "loss": 0.5393, "num_tokens": 223102713.0, "step": 37300 }, { "epoch": 0.39799216924669006, "grad_norm": 1.0996050770995316, "learning_rate": 3.6675644290428406e-05, "loss": 0.4573, "num_tokens": 223128010.0, "step": 37305 }, { "epoch": 0.39804551225288853, "grad_norm": 0.7009249463056125, "learning_rate": 3.667202012172939e-05, "loss": 0.4116, "num_tokens": 223150452.0, "step": 37310 }, { "epoch": 0.398098855259087, "grad_norm": 3.110530193096228, "learning_rate": 3.666839566761594e-05, "loss": 0.5058, "num_tokens": 223197013.0, "step": 37315 }, { "epoch": 0.3981521982652854, "grad_norm": 1.6322367556696467, "learning_rate": 3.666477092820086e-05, "loss": 0.6159, "num_tokens": 223230005.0, "step": 37320 }, { "epoch": 0.3982055412714839, "grad_norm": 1.008716689936696, "learning_rate": 3.666114590359693e-05, "loss": 0.5382, "num_tokens": 223260026.0, "step": 37325 }, { "epoch": 0.39825888427768236, "grad_norm": 1.0984221422044176, "learning_rate": 3.665752059391696e-05, "loss": 0.6459, "num_tokens": 223282009.0, "step": 37330 }, { "epoch": 0.3983122272838808, "grad_norm": 0.9833915508790169, "learning_rate": 3.665389499927376e-05, "loss": 0.568, "num_tokens": 223312116.0, "step": 37335 }, { "epoch": 0.39836557029007924, "grad_norm": 0.9514184888764774, "learning_rate": 3.665026911978015e-05, "loss": 0.5482, "num_tokens": 223331570.0, "step": 37340 }, { "epoch": 0.3984189132962777, "grad_norm": 1.6182740635775978, "learning_rate": 3.664664295554895e-05, "loss": 0.5599, "num_tokens": 223365135.0, "step": 37345 }, { "epoch": 0.3984722563024762, "grad_norm": 0.9363020668009329, "learning_rate": 3.664301650669302e-05, "loss": 0.464, "num_tokens": 223377949.0, "step": 37350 }, { "epoch": 0.39852559930867465, "grad_norm": 1.3141950289073894, "learning_rate": 3.663938977332519e-05, "loss": 0.5179, "num_tokens": 223410388.0, "step": 37355 }, { "epoch": 0.3985789423148731, "grad_norm": 0.9775100427422189, "learning_rate": 3.663576275555833e-05, "loss": 0.5539, "num_tokens": 223443227.0, "step": 37360 }, { "epoch": 0.39863228532107153, "grad_norm": 1.2227792941384197, "learning_rate": 3.663213545350529e-05, "loss": 0.5525, "num_tokens": 223473134.0, "step": 37365 }, { "epoch": 0.39868562832727, "grad_norm": 1.2327687021402394, "learning_rate": 3.662850786727896e-05, "loss": 0.6344, "num_tokens": 223502632.0, "step": 37370 }, { "epoch": 0.3987389713334685, "grad_norm": 0.7682885571528089, "learning_rate": 3.6624879996992214e-05, "loss": 0.4503, "num_tokens": 223524851.0, "step": 37375 }, { "epoch": 0.39879231433966694, "grad_norm": 0.771033212368861, "learning_rate": 3.6621251842757945e-05, "loss": 0.5398, "num_tokens": 223550101.0, "step": 37380 }, { "epoch": 0.39884565734586536, "grad_norm": 0.6908170047465277, "learning_rate": 3.661762340468905e-05, "loss": 0.5967, "num_tokens": 223579771.0, "step": 37385 }, { "epoch": 0.3988990003520638, "grad_norm": 0.7221095045595484, "learning_rate": 3.661399468289845e-05, "loss": 0.4902, "num_tokens": 223612421.0, "step": 37390 }, { "epoch": 0.3989523433582623, "grad_norm": 1.0243226974771436, "learning_rate": 3.6610365677499054e-05, "loss": 0.5534, "num_tokens": 223642422.0, "step": 37395 }, { "epoch": 0.39900568636446077, "grad_norm": 0.8033379726639855, "learning_rate": 3.660673638860378e-05, "loss": 0.4701, "num_tokens": 223665873.0, "step": 37400 }, { "epoch": 0.39905902937065924, "grad_norm": 1.2784103710730466, "learning_rate": 3.660310681632559e-05, "loss": 0.4805, "num_tokens": 223692192.0, "step": 37405 }, { "epoch": 0.39911237237685765, "grad_norm": 1.950268850074174, "learning_rate": 3.659947696077742e-05, "loss": 0.552, "num_tokens": 223719683.0, "step": 37410 }, { "epoch": 0.3991657153830561, "grad_norm": 1.9596851793141252, "learning_rate": 3.65958468220722e-05, "loss": 0.4797, "num_tokens": 223753135.0, "step": 37415 }, { "epoch": 0.3992190583892546, "grad_norm": 0.8065962610264457, "learning_rate": 3.659221640032292e-05, "loss": 0.5899, "num_tokens": 223793214.0, "step": 37420 }, { "epoch": 0.39927240139545306, "grad_norm": 1.0677291955708457, "learning_rate": 3.6588585695642535e-05, "loss": 0.5482, "num_tokens": 223816807.0, "step": 37425 }, { "epoch": 0.3993257444016515, "grad_norm": 0.9008709612943866, "learning_rate": 3.6584954708144044e-05, "loss": 0.4444, "num_tokens": 223836379.0, "step": 37430 }, { "epoch": 0.39937908740784994, "grad_norm": 0.5974455372805122, "learning_rate": 3.658132343794041e-05, "loss": 0.5175, "num_tokens": 223868553.0, "step": 37435 }, { "epoch": 0.3994324304140484, "grad_norm": 0.8566250249873514, "learning_rate": 3.657769188514465e-05, "loss": 0.5913, "num_tokens": 223892351.0, "step": 37440 }, { "epoch": 0.3994857734202469, "grad_norm": 2.0870759911241543, "learning_rate": 3.6574060049869766e-05, "loss": 0.6456, "num_tokens": 223908873.0, "step": 37445 }, { "epoch": 0.39953911642644535, "grad_norm": 1.2819831194621678, "learning_rate": 3.657042793222877e-05, "loss": 0.6134, "num_tokens": 223939940.0, "step": 37450 }, { "epoch": 0.39959245943264377, "grad_norm": 1.3775791072064343, "learning_rate": 3.656679553233469e-05, "loss": 0.5844, "num_tokens": 223969517.0, "step": 37455 }, { "epoch": 0.39964580243884223, "grad_norm": 0.7729693435413566, "learning_rate": 3.656316285030055e-05, "loss": 0.5778, "num_tokens": 223994398.0, "step": 37460 }, { "epoch": 0.3996991454450407, "grad_norm": 0.9391216685878218, "learning_rate": 3.6559529886239406e-05, "loss": 0.4312, "num_tokens": 224011364.0, "step": 37465 }, { "epoch": 0.3997524884512392, "grad_norm": 0.6883474132390752, "learning_rate": 3.65558966402643e-05, "loss": 0.6195, "num_tokens": 224058987.0, "step": 37470 }, { "epoch": 0.3998058314574376, "grad_norm": 0.9201170362997919, "learning_rate": 3.655226311248829e-05, "loss": 0.5694, "num_tokens": 224093165.0, "step": 37475 }, { "epoch": 0.39985917446363606, "grad_norm": 0.9677760580315782, "learning_rate": 3.654862930302444e-05, "loss": 0.6324, "num_tokens": 224116111.0, "step": 37480 }, { "epoch": 0.3999125174698345, "grad_norm": 1.1616364400879895, "learning_rate": 3.654499521198584e-05, "loss": 0.7042, "num_tokens": 224151975.0, "step": 37485 }, { "epoch": 0.399965860476033, "grad_norm": 1.2714718997574164, "learning_rate": 3.6541360839485565e-05, "loss": 0.5891, "num_tokens": 224192692.0, "step": 37490 }, { "epoch": 0.40001920348223147, "grad_norm": 0.777416744291306, "learning_rate": 3.6537726185636715e-05, "loss": 0.531, "num_tokens": 224237347.0, "step": 37495 }, { "epoch": 0.4000725464884299, "grad_norm": 0.8383179655992652, "learning_rate": 3.653409125055239e-05, "loss": 0.5892, "num_tokens": 224261767.0, "step": 37500 }, { "epoch": 0.40012588949462835, "grad_norm": 0.7202503196564701, "learning_rate": 3.6530456034345693e-05, "loss": 0.5146, "num_tokens": 224291351.0, "step": 37505 }, { "epoch": 0.4001792325008268, "grad_norm": 0.694377314954683, "learning_rate": 3.652682053712977e-05, "loss": 0.5913, "num_tokens": 224341654.0, "step": 37510 }, { "epoch": 0.4002325755070253, "grad_norm": 1.4175265861194237, "learning_rate": 3.652318475901772e-05, "loss": 0.5273, "num_tokens": 224366377.0, "step": 37515 }, { "epoch": 0.4002859185132237, "grad_norm": 0.7812333233201904, "learning_rate": 3.6519548700122705e-05, "loss": 0.4888, "num_tokens": 224395063.0, "step": 37520 }, { "epoch": 0.4003392615194222, "grad_norm": 0.6490683875416683, "learning_rate": 3.651591236055785e-05, "loss": 0.5245, "num_tokens": 224434495.0, "step": 37525 }, { "epoch": 0.40039260452562064, "grad_norm": 1.0316277281773836, "learning_rate": 3.651227574043632e-05, "loss": 0.6143, "num_tokens": 224464505.0, "step": 37530 }, { "epoch": 0.4004459475318191, "grad_norm": 1.7060823135103582, "learning_rate": 3.650863883987129e-05, "loss": 0.485, "num_tokens": 224491805.0, "step": 37535 }, { "epoch": 0.4004992905380176, "grad_norm": 1.0462694697055175, "learning_rate": 3.6505001658975925e-05, "loss": 0.4609, "num_tokens": 224506612.0, "step": 37540 }, { "epoch": 0.400552633544216, "grad_norm": 0.8760404115753799, "learning_rate": 3.6501364197863404e-05, "loss": 0.4956, "num_tokens": 224539046.0, "step": 37545 }, { "epoch": 0.40060597655041447, "grad_norm": 0.7419659169138406, "learning_rate": 3.6497726456646906e-05, "loss": 0.5502, "num_tokens": 224574295.0, "step": 37550 }, { "epoch": 0.40065931955661294, "grad_norm": 0.8506107998383314, "learning_rate": 3.6494088435439656e-05, "loss": 0.7966, "num_tokens": 224596228.0, "step": 37555 }, { "epoch": 0.4007126625628114, "grad_norm": 1.2135772850111681, "learning_rate": 3.6490450134354844e-05, "loss": 0.5942, "num_tokens": 224623813.0, "step": 37560 }, { "epoch": 0.4007660055690098, "grad_norm": 1.019294293111787, "learning_rate": 3.648681155350569e-05, "loss": 0.4428, "num_tokens": 224645507.0, "step": 37565 }, { "epoch": 0.4008193485752083, "grad_norm": 0.9776464229854214, "learning_rate": 3.648317269300542e-05, "loss": 0.4845, "num_tokens": 224669829.0, "step": 37570 }, { "epoch": 0.40087269158140676, "grad_norm": 0.995789882185872, "learning_rate": 3.647953355296728e-05, "loss": 0.557, "num_tokens": 224694605.0, "step": 37575 }, { "epoch": 0.40092603458760523, "grad_norm": 1.0190623813506576, "learning_rate": 3.647589413350448e-05, "loss": 0.5117, "num_tokens": 224709375.0, "step": 37580 }, { "epoch": 0.4009793775938037, "grad_norm": 0.591853678706002, "learning_rate": 3.64722544347303e-05, "loss": 0.479, "num_tokens": 224749348.0, "step": 37585 }, { "epoch": 0.4010327206000021, "grad_norm": 0.8121417254381081, "learning_rate": 3.646861445675799e-05, "loss": 0.5416, "num_tokens": 224774205.0, "step": 37590 }, { "epoch": 0.4010860636062006, "grad_norm": 0.6915526805980698, "learning_rate": 3.6464974199700824e-05, "loss": 0.5448, "num_tokens": 224806567.0, "step": 37595 }, { "epoch": 0.40113940661239905, "grad_norm": 1.270483677445195, "learning_rate": 3.646133366367207e-05, "loss": 0.5391, "num_tokens": 224828773.0, "step": 37600 }, { "epoch": 0.4011927496185975, "grad_norm": 0.9006577418824595, "learning_rate": 3.6457692848785024e-05, "loss": 0.486, "num_tokens": 224861658.0, "step": 37605 }, { "epoch": 0.40124609262479594, "grad_norm": 0.9908907294833655, "learning_rate": 3.645405175515297e-05, "loss": 0.4541, "num_tokens": 224892036.0, "step": 37610 }, { "epoch": 0.4012994356309944, "grad_norm": 0.8020074224460852, "learning_rate": 3.6450410382889236e-05, "loss": 0.5028, "num_tokens": 224917919.0, "step": 37615 }, { "epoch": 0.4013527786371929, "grad_norm": 2.212835561697411, "learning_rate": 3.6446768732107094e-05, "loss": 0.5182, "num_tokens": 224937321.0, "step": 37620 }, { "epoch": 0.40140612164339134, "grad_norm": 1.3598813764561655, "learning_rate": 3.644312680291989e-05, "loss": 0.6246, "num_tokens": 224973597.0, "step": 37625 }, { "epoch": 0.4014594646495898, "grad_norm": 0.7544492241132998, "learning_rate": 3.6439484595440965e-05, "loss": 0.5421, "num_tokens": 225004790.0, "step": 37630 }, { "epoch": 0.40151280765578823, "grad_norm": 1.021600113145695, "learning_rate": 3.643584210978363e-05, "loss": 0.5327, "num_tokens": 225036725.0, "step": 37635 }, { "epoch": 0.4015661506619867, "grad_norm": 0.6518113731068974, "learning_rate": 3.643219934606124e-05, "loss": 0.435, "num_tokens": 225073987.0, "step": 37640 }, { "epoch": 0.40161949366818517, "grad_norm": 0.7478034839176022, "learning_rate": 3.642855630438715e-05, "loss": 0.576, "num_tokens": 225109999.0, "step": 37645 }, { "epoch": 0.40167283667438364, "grad_norm": 1.348485082094082, "learning_rate": 3.642491298487474e-05, "loss": 0.636, "num_tokens": 225130967.0, "step": 37650 }, { "epoch": 0.40172617968058205, "grad_norm": 1.417167669907414, "learning_rate": 3.642126938763737e-05, "loss": 0.4784, "num_tokens": 225154752.0, "step": 37655 }, { "epoch": 0.4017795226867805, "grad_norm": 0.9021221372151015, "learning_rate": 3.641762551278841e-05, "loss": 0.4762, "num_tokens": 225178601.0, "step": 37660 }, { "epoch": 0.401832865692979, "grad_norm": 0.981286542079559, "learning_rate": 3.641398136044127e-05, "loss": 0.5824, "num_tokens": 225217581.0, "step": 37665 }, { "epoch": 0.40188620869917746, "grad_norm": 0.6380669491581274, "learning_rate": 3.6410336930709344e-05, "loss": 0.4851, "num_tokens": 225252681.0, "step": 37670 }, { "epoch": 0.40193955170537593, "grad_norm": 1.7404901044156467, "learning_rate": 3.640669222370603e-05, "loss": 0.6165, "num_tokens": 225279281.0, "step": 37675 }, { "epoch": 0.40199289471157434, "grad_norm": 0.9662590167860742, "learning_rate": 3.6403047239544745e-05, "loss": 0.5265, "num_tokens": 225310024.0, "step": 37680 }, { "epoch": 0.4020462377177728, "grad_norm": 0.7386881876501368, "learning_rate": 3.639940197833892e-05, "loss": 0.5471, "num_tokens": 225346710.0, "step": 37685 }, { "epoch": 0.4020995807239713, "grad_norm": 0.8690347831252959, "learning_rate": 3.639575644020199e-05, "loss": 0.5571, "num_tokens": 225398589.0, "step": 37690 }, { "epoch": 0.40215292373016975, "grad_norm": 0.7306542798834116, "learning_rate": 3.6392110625247386e-05, "loss": 0.6163, "num_tokens": 225428423.0, "step": 37695 }, { "epoch": 0.40220626673636817, "grad_norm": 0.7569219611073279, "learning_rate": 3.638846453358857e-05, "loss": 0.4368, "num_tokens": 225462425.0, "step": 37700 }, { "epoch": 0.40225960974256664, "grad_norm": 0.6588591153914567, "learning_rate": 3.638481816533899e-05, "loss": 0.5786, "num_tokens": 225491156.0, "step": 37705 }, { "epoch": 0.4023129527487651, "grad_norm": 0.6881246963803779, "learning_rate": 3.6381171520612115e-05, "loss": 0.506, "num_tokens": 225518958.0, "step": 37710 }, { "epoch": 0.4023662957549636, "grad_norm": 0.7150163266139244, "learning_rate": 3.637752459952143e-05, "loss": 0.5733, "num_tokens": 225543245.0, "step": 37715 }, { "epoch": 0.40241963876116205, "grad_norm": 1.0023736792863893, "learning_rate": 3.6373877402180416e-05, "loss": 0.464, "num_tokens": 225571650.0, "step": 37720 }, { "epoch": 0.40247298176736046, "grad_norm": 1.6520628347744097, "learning_rate": 3.637022992870256e-05, "loss": 0.5973, "num_tokens": 225599728.0, "step": 37725 }, { "epoch": 0.40252632477355893, "grad_norm": 0.9412360549738963, "learning_rate": 3.636658217920137e-05, "loss": 0.4691, "num_tokens": 225628010.0, "step": 37730 }, { "epoch": 0.4025796677797574, "grad_norm": 1.0881815539306587, "learning_rate": 3.6362934153790355e-05, "loss": 0.5339, "num_tokens": 225667097.0, "step": 37735 }, { "epoch": 0.40263301078595587, "grad_norm": 0.8506495735525306, "learning_rate": 3.635928585258304e-05, "loss": 0.4757, "num_tokens": 225699481.0, "step": 37740 }, { "epoch": 0.4026863537921543, "grad_norm": 0.9717845511347484, "learning_rate": 3.635563727569294e-05, "loss": 0.785, "num_tokens": 225739342.0, "step": 37745 }, { "epoch": 0.40273969679835275, "grad_norm": 0.7939355967377062, "learning_rate": 3.63519884232336e-05, "loss": 0.6032, "num_tokens": 225771205.0, "step": 37750 }, { "epoch": 0.4027930398045512, "grad_norm": 0.8109672730698834, "learning_rate": 3.6348339295318565e-05, "loss": 0.5596, "num_tokens": 225806326.0, "step": 37755 }, { "epoch": 0.4028463828107497, "grad_norm": 1.3178958402891665, "learning_rate": 3.6344689892061376e-05, "loss": 0.5563, "num_tokens": 225828573.0, "step": 37760 }, { "epoch": 0.40289972581694816, "grad_norm": 0.799747805827866, "learning_rate": 3.6341040213575616e-05, "loss": 0.4704, "num_tokens": 225851561.0, "step": 37765 }, { "epoch": 0.4029530688231466, "grad_norm": 0.7457762052270871, "learning_rate": 3.633739025997484e-05, "loss": 0.6359, "num_tokens": 225879648.0, "step": 37770 }, { "epoch": 0.40300641182934505, "grad_norm": 1.2562410305560574, "learning_rate": 3.633374003137264e-05, "loss": 0.5423, "num_tokens": 225902911.0, "step": 37775 }, { "epoch": 0.4030597548355435, "grad_norm": 1.0009643977909495, "learning_rate": 3.633008952788259e-05, "loss": 0.452, "num_tokens": 225927229.0, "step": 37780 }, { "epoch": 0.403113097841742, "grad_norm": 1.220328111292539, "learning_rate": 3.6326438749618286e-05, "loss": 0.4233, "num_tokens": 225957890.0, "step": 37785 }, { "epoch": 0.4031664408479404, "grad_norm": 1.1621978324827118, "learning_rate": 3.632278769669334e-05, "loss": 0.6298, "num_tokens": 225999617.0, "step": 37790 }, { "epoch": 0.40321978385413887, "grad_norm": 1.0141749628432384, "learning_rate": 3.631913636922137e-05, "loss": 0.5174, "num_tokens": 226021889.0, "step": 37795 }, { "epoch": 0.40327312686033734, "grad_norm": 0.9595442493329592, "learning_rate": 3.631548476731599e-05, "loss": 0.6464, "num_tokens": 226038919.0, "step": 37800 }, { "epoch": 0.4033264698665358, "grad_norm": 0.6417252292915597, "learning_rate": 3.631183289109082e-05, "loss": 0.5636, "num_tokens": 226070099.0, "step": 37805 }, { "epoch": 0.4033798128727343, "grad_norm": 1.118010955264337, "learning_rate": 3.630818074065952e-05, "loss": 0.4323, "num_tokens": 226096326.0, "step": 37810 }, { "epoch": 0.4034331558789327, "grad_norm": 1.2750606519150505, "learning_rate": 3.630452831613573e-05, "loss": 0.5835, "num_tokens": 226123520.0, "step": 37815 }, { "epoch": 0.40348649888513116, "grad_norm": 1.0111204690415692, "learning_rate": 3.63008756176331e-05, "loss": 0.5113, "num_tokens": 226137440.0, "step": 37820 }, { "epoch": 0.40353984189132963, "grad_norm": 1.1481598661159675, "learning_rate": 3.62972226452653e-05, "loss": 0.5403, "num_tokens": 226153418.0, "step": 37825 }, { "epoch": 0.4035931848975281, "grad_norm": 0.801910989771073, "learning_rate": 3.6293569399146e-05, "loss": 0.4766, "num_tokens": 226182689.0, "step": 37830 }, { "epoch": 0.4036465279037265, "grad_norm": 0.8407691046824285, "learning_rate": 3.628991587938888e-05, "loss": 0.628, "num_tokens": 226218841.0, "step": 37835 }, { "epoch": 0.403699870909925, "grad_norm": 1.4728627123303695, "learning_rate": 3.628626208610763e-05, "loss": 0.6119, "num_tokens": 226231065.0, "step": 37840 }, { "epoch": 0.40375321391612345, "grad_norm": 0.9483844506183446, "learning_rate": 3.6282608019415966e-05, "loss": 0.4706, "num_tokens": 226255235.0, "step": 37845 }, { "epoch": 0.4038065569223219, "grad_norm": 0.6745857846876646, "learning_rate": 3.627895367942757e-05, "loss": 0.5014, "num_tokens": 226297538.0, "step": 37850 }, { "epoch": 0.4038598999285204, "grad_norm": 1.2279114203868173, "learning_rate": 3.627529906625617e-05, "loss": 0.5515, "num_tokens": 226328619.0, "step": 37855 }, { "epoch": 0.4039132429347188, "grad_norm": 0.9317036828902809, "learning_rate": 3.627164418001548e-05, "loss": 0.6008, "num_tokens": 226356295.0, "step": 37860 }, { "epoch": 0.4039665859409173, "grad_norm": 0.864888557886207, "learning_rate": 3.626798902081925e-05, "loss": 0.5565, "num_tokens": 226390689.0, "step": 37865 }, { "epoch": 0.40401992894711575, "grad_norm": 1.3084253119788507, "learning_rate": 3.6264333588781216e-05, "loss": 0.5753, "num_tokens": 226425862.0, "step": 37870 }, { "epoch": 0.4040732719533142, "grad_norm": 0.7381479041538588, "learning_rate": 3.626067788401511e-05, "loss": 0.5672, "num_tokens": 226456860.0, "step": 37875 }, { "epoch": 0.40412661495951263, "grad_norm": 0.8608668272790762, "learning_rate": 3.625702190663471e-05, "loss": 0.4303, "num_tokens": 226477345.0, "step": 37880 }, { "epoch": 0.4041799579657111, "grad_norm": 1.118244816445934, "learning_rate": 3.625336565675378e-05, "loss": 0.4476, "num_tokens": 226508708.0, "step": 37885 }, { "epoch": 0.40423330097190957, "grad_norm": 0.898201243243697, "learning_rate": 3.624970913448609e-05, "loss": 0.4667, "num_tokens": 226528821.0, "step": 37890 }, { "epoch": 0.40428664397810804, "grad_norm": 0.8818264268144885, "learning_rate": 3.624605233994541e-05, "loss": 0.5935, "num_tokens": 226556238.0, "step": 37895 }, { "epoch": 0.4043399869843065, "grad_norm": 0.9909924784950535, "learning_rate": 3.624239527324556e-05, "loss": 0.4868, "num_tokens": 226584567.0, "step": 37900 }, { "epoch": 0.4043933299905049, "grad_norm": 0.8906745669943659, "learning_rate": 3.6238737934500324e-05, "loss": 0.5371, "num_tokens": 226616076.0, "step": 37905 }, { "epoch": 0.4044466729967034, "grad_norm": 0.857898462844329, "learning_rate": 3.6235080323823515e-05, "loss": 0.5547, "num_tokens": 226641652.0, "step": 37910 }, { "epoch": 0.40450001600290186, "grad_norm": 1.2164439590051828, "learning_rate": 3.6231422441328947e-05, "loss": 0.5845, "num_tokens": 226676415.0, "step": 37915 }, { "epoch": 0.40455335900910033, "grad_norm": 0.8592727922530966, "learning_rate": 3.622776428713045e-05, "loss": 0.6759, "num_tokens": 226712054.0, "step": 37920 }, { "epoch": 0.40460670201529875, "grad_norm": 1.3502959132945471, "learning_rate": 3.6224105861341846e-05, "loss": 0.4678, "num_tokens": 226749587.0, "step": 37925 }, { "epoch": 0.4046600450214972, "grad_norm": 1.0169041729995856, "learning_rate": 3.6220447164076995e-05, "loss": 0.5737, "num_tokens": 226776417.0, "step": 37930 }, { "epoch": 0.4047133880276957, "grad_norm": 1.0801111665323184, "learning_rate": 3.621678819544974e-05, "loss": 0.6009, "num_tokens": 226807380.0, "step": 37935 }, { "epoch": 0.40476673103389416, "grad_norm": 1.0717296335746946, "learning_rate": 3.621312895557394e-05, "loss": 0.7764, "num_tokens": 226846713.0, "step": 37940 }, { "epoch": 0.4048200740400926, "grad_norm": 1.1043613235754435, "learning_rate": 3.620946944456347e-05, "loss": 0.5557, "num_tokens": 226876218.0, "step": 37945 }, { "epoch": 0.40487341704629104, "grad_norm": 0.8177993329501091, "learning_rate": 3.620580966253219e-05, "loss": 0.5823, "num_tokens": 226906766.0, "step": 37950 }, { "epoch": 0.4049267600524895, "grad_norm": 1.3720381727001016, "learning_rate": 3.6202149609594e-05, "loss": 0.6504, "num_tokens": 226949009.0, "step": 37955 }, { "epoch": 0.404980103058688, "grad_norm": 0.9651933224716616, "learning_rate": 3.61984892858628e-05, "loss": 0.524, "num_tokens": 226986392.0, "step": 37960 }, { "epoch": 0.40503344606488645, "grad_norm": 1.1000228206602327, "learning_rate": 3.619482869145247e-05, "loss": 0.4408, "num_tokens": 227015691.0, "step": 37965 }, { "epoch": 0.40508678907108486, "grad_norm": 0.7817086093987069, "learning_rate": 3.619116782647692e-05, "loss": 0.5973, "num_tokens": 227047489.0, "step": 37970 }, { "epoch": 0.40514013207728333, "grad_norm": 1.3173570062659603, "learning_rate": 3.618750669105009e-05, "loss": 0.463, "num_tokens": 227062608.0, "step": 37975 }, { "epoch": 0.4051934750834818, "grad_norm": 0.8017576517102004, "learning_rate": 3.61838452852859e-05, "loss": 0.5227, "num_tokens": 227110012.0, "step": 37980 }, { "epoch": 0.40524681808968027, "grad_norm": 0.7863075129845317, "learning_rate": 3.618018360929828e-05, "loss": 0.6268, "num_tokens": 227146087.0, "step": 37985 }, { "epoch": 0.40530016109587874, "grad_norm": 0.707701920812996, "learning_rate": 3.6176521663201176e-05, "loss": 0.5197, "num_tokens": 227181246.0, "step": 37990 }, { "epoch": 0.40535350410207716, "grad_norm": 1.0687189990792485, "learning_rate": 3.6172859447108545e-05, "loss": 0.6581, "num_tokens": 227211815.0, "step": 37995 }, { "epoch": 0.4054068471082756, "grad_norm": 0.8817090344281631, "learning_rate": 3.616919696113433e-05, "loss": 0.6111, "num_tokens": 227246895.0, "step": 38000 }, { "epoch": 0.4054601901144741, "grad_norm": 1.3216788151690724, "learning_rate": 3.616553420539252e-05, "loss": 0.4959, "num_tokens": 227264442.0, "step": 38005 }, { "epoch": 0.40551353312067256, "grad_norm": 0.9618169022886413, "learning_rate": 3.616187117999708e-05, "loss": 0.4908, "num_tokens": 227284879.0, "step": 38010 }, { "epoch": 0.405566876126871, "grad_norm": 1.0455881529703877, "learning_rate": 3.6158207885062004e-05, "loss": 0.5304, "num_tokens": 227309911.0, "step": 38015 }, { "epoch": 0.40562021913306945, "grad_norm": 0.766669629581232, "learning_rate": 3.615454432070129e-05, "loss": 0.6301, "num_tokens": 227349602.0, "step": 38020 }, { "epoch": 0.4056735621392679, "grad_norm": 1.160390075445492, "learning_rate": 3.615088048702892e-05, "loss": 0.5126, "num_tokens": 227377026.0, "step": 38025 }, { "epoch": 0.4057269051454664, "grad_norm": 0.80252448293188, "learning_rate": 3.6147216384158934e-05, "loss": 0.5487, "num_tokens": 227398448.0, "step": 38030 }, { "epoch": 0.40578024815166486, "grad_norm": 1.518730086197522, "learning_rate": 3.6143552012205324e-05, "loss": 0.6102, "num_tokens": 227448112.0, "step": 38035 }, { "epoch": 0.40583359115786327, "grad_norm": 0.7486378818787766, "learning_rate": 3.6139887371282134e-05, "loss": 0.5054, "num_tokens": 227494459.0, "step": 38040 }, { "epoch": 0.40588693416406174, "grad_norm": 1.5907584333594778, "learning_rate": 3.6136222461503396e-05, "loss": 0.611, "num_tokens": 227519916.0, "step": 38045 }, { "epoch": 0.4059402771702602, "grad_norm": 0.8306900681013646, "learning_rate": 3.613255728298316e-05, "loss": 0.5661, "num_tokens": 227550551.0, "step": 38050 }, { "epoch": 0.4059936201764587, "grad_norm": 0.9307436257120268, "learning_rate": 3.612889183583546e-05, "loss": 0.4689, "num_tokens": 227571672.0, "step": 38055 }, { "epoch": 0.4060469631826571, "grad_norm": 0.8703330763503453, "learning_rate": 3.6125226120174374e-05, "loss": 0.56, "num_tokens": 227599286.0, "step": 38060 }, { "epoch": 0.40610030618885556, "grad_norm": 0.874503614923205, "learning_rate": 3.6121560136113973e-05, "loss": 0.4577, "num_tokens": 227632778.0, "step": 38065 }, { "epoch": 0.40615364919505403, "grad_norm": 0.9857929655565754, "learning_rate": 3.611789388376833e-05, "loss": 0.5101, "num_tokens": 227656340.0, "step": 38070 }, { "epoch": 0.4062069922012525, "grad_norm": 1.0933869675472783, "learning_rate": 3.611422736325153e-05, "loss": 0.5377, "num_tokens": 227699924.0, "step": 38075 }, { "epoch": 0.406260335207451, "grad_norm": 0.6751347422286694, "learning_rate": 3.611056057467767e-05, "loss": 0.561, "num_tokens": 227748575.0, "step": 38080 }, { "epoch": 0.4063136782136494, "grad_norm": 0.7520641570417422, "learning_rate": 3.6106893518160844e-05, "loss": 0.5442, "num_tokens": 227780898.0, "step": 38085 }, { "epoch": 0.40636702121984786, "grad_norm": 0.9541855744831437, "learning_rate": 3.610322619381518e-05, "loss": 0.4029, "num_tokens": 227805211.0, "step": 38090 }, { "epoch": 0.4064203642260463, "grad_norm": 0.8922772471622161, "learning_rate": 3.6099558601754785e-05, "loss": 0.4451, "num_tokens": 227828188.0, "step": 38095 }, { "epoch": 0.4064737072322448, "grad_norm": 1.9009308731853116, "learning_rate": 3.6095890742093785e-05, "loss": 0.5264, "num_tokens": 227840232.0, "step": 38100 }, { "epoch": 0.4065270502384432, "grad_norm": 0.7869879444261508, "learning_rate": 3.609222261494633e-05, "loss": 0.5314, "num_tokens": 227885549.0, "step": 38105 }, { "epoch": 0.4065803932446417, "grad_norm": 0.9976706767059923, "learning_rate": 3.6088554220426555e-05, "loss": 0.6279, "num_tokens": 227913598.0, "step": 38110 }, { "epoch": 0.40663373625084015, "grad_norm": 0.8641549973390085, "learning_rate": 3.60848855586486e-05, "loss": 0.6668, "num_tokens": 227956410.0, "step": 38115 }, { "epoch": 0.4066870792570386, "grad_norm": 1.0503793948186202, "learning_rate": 3.608121662972666e-05, "loss": 0.4352, "num_tokens": 227971179.0, "step": 38120 }, { "epoch": 0.4067404222632371, "grad_norm": 0.8725949727703086, "learning_rate": 3.607754743377488e-05, "loss": 0.5103, "num_tokens": 227993959.0, "step": 38125 }, { "epoch": 0.4067937652694355, "grad_norm": 1.188840729872943, "learning_rate": 3.607387797090744e-05, "loss": 0.5324, "num_tokens": 228022910.0, "step": 38130 }, { "epoch": 0.406847108275634, "grad_norm": 1.1241345127248366, "learning_rate": 3.607020824123852e-05, "loss": 0.467, "num_tokens": 228041131.0, "step": 38135 }, { "epoch": 0.40690045128183244, "grad_norm": 0.92672576449335, "learning_rate": 3.606653824488233e-05, "loss": 0.5812, "num_tokens": 228070956.0, "step": 38140 }, { "epoch": 0.4069537942880309, "grad_norm": 1.203782636959474, "learning_rate": 3.606286798195307e-05, "loss": 0.5073, "num_tokens": 228093659.0, "step": 38145 }, { "epoch": 0.4070071372942293, "grad_norm": 0.5754839733466711, "learning_rate": 3.605919745256495e-05, "loss": 0.5275, "num_tokens": 228143389.0, "step": 38150 }, { "epoch": 0.4070604803004278, "grad_norm": 0.8288918839530999, "learning_rate": 3.605552665683218e-05, "loss": 0.5783, "num_tokens": 228170970.0, "step": 38155 }, { "epoch": 0.40711382330662627, "grad_norm": 0.5343572657302813, "learning_rate": 3.6051855594868986e-05, "loss": 0.5656, "num_tokens": 228214245.0, "step": 38160 }, { "epoch": 0.40716716631282474, "grad_norm": 0.6248681886132756, "learning_rate": 3.604818426678962e-05, "loss": 0.53, "num_tokens": 228250815.0, "step": 38165 }, { "epoch": 0.4072205093190232, "grad_norm": 0.8639533282824253, "learning_rate": 3.6044512672708325e-05, "loss": 0.5114, "num_tokens": 228277397.0, "step": 38170 }, { "epoch": 0.4072738523252216, "grad_norm": 1.1452129788329242, "learning_rate": 3.604084081273933e-05, "loss": 0.5586, "num_tokens": 228313811.0, "step": 38175 }, { "epoch": 0.4073271953314201, "grad_norm": 1.0105076730226068, "learning_rate": 3.6037168686996935e-05, "loss": 0.5428, "num_tokens": 228357525.0, "step": 38180 }, { "epoch": 0.40738053833761856, "grad_norm": 1.2090867728741999, "learning_rate": 3.603349629559537e-05, "loss": 0.5258, "num_tokens": 228381371.0, "step": 38185 }, { "epoch": 0.40743388134381703, "grad_norm": 0.8757859095904177, "learning_rate": 3.602982363864893e-05, "loss": 0.5464, "num_tokens": 228401990.0, "step": 38190 }, { "epoch": 0.40748722435001544, "grad_norm": 1.6367742768311762, "learning_rate": 3.6026150716271905e-05, "loss": 0.532, "num_tokens": 228424652.0, "step": 38195 }, { "epoch": 0.4075405673562139, "grad_norm": 0.8501771227029298, "learning_rate": 3.602247752857858e-05, "loss": 0.5479, "num_tokens": 228457985.0, "step": 38200 }, { "epoch": 0.4075939103624124, "grad_norm": 1.2067453152740832, "learning_rate": 3.6018804075683253e-05, "loss": 0.7074, "num_tokens": 228481194.0, "step": 38205 }, { "epoch": 0.40764725336861085, "grad_norm": 0.7850432048612996, "learning_rate": 3.601513035770025e-05, "loss": 0.4472, "num_tokens": 228514123.0, "step": 38210 }, { "epoch": 0.4077005963748093, "grad_norm": 1.133337348153076, "learning_rate": 3.601145637474389e-05, "loss": 0.7376, "num_tokens": 228564472.0, "step": 38215 }, { "epoch": 0.40775393938100774, "grad_norm": 1.9531176718610834, "learning_rate": 3.600778212692847e-05, "loss": 0.5869, "num_tokens": 228597318.0, "step": 38220 }, { "epoch": 0.4078072823872062, "grad_norm": 0.6781922194219391, "learning_rate": 3.6004107614368354e-05, "loss": 0.5904, "num_tokens": 228636569.0, "step": 38225 }, { "epoch": 0.4078606253934047, "grad_norm": 0.8977066007365648, "learning_rate": 3.600043283717788e-05, "loss": 0.5421, "num_tokens": 228663701.0, "step": 38230 }, { "epoch": 0.40791396839960314, "grad_norm": 0.9034187181647377, "learning_rate": 3.599675779547139e-05, "loss": 0.5129, "num_tokens": 228697682.0, "step": 38235 }, { "epoch": 0.40796731140580156, "grad_norm": 1.2251668472537025, "learning_rate": 3.599308248936325e-05, "loss": 0.4959, "num_tokens": 228726043.0, "step": 38240 }, { "epoch": 0.40802065441200003, "grad_norm": 0.8939046688433745, "learning_rate": 3.598940691896784e-05, "loss": 0.6161, "num_tokens": 228767099.0, "step": 38245 }, { "epoch": 0.4080739974181985, "grad_norm": 0.9305718975110262, "learning_rate": 3.5985731084399516e-05, "loss": 0.4485, "num_tokens": 228802239.0, "step": 38250 }, { "epoch": 0.40812734042439697, "grad_norm": 1.6399444227001172, "learning_rate": 3.598205498577267e-05, "loss": 0.6346, "num_tokens": 228828870.0, "step": 38255 }, { "epoch": 0.40818068343059544, "grad_norm": 1.0397245693032444, "learning_rate": 3.59783786232017e-05, "loss": 0.5826, "num_tokens": 228855499.0, "step": 38260 }, { "epoch": 0.40823402643679385, "grad_norm": 0.9039016392616455, "learning_rate": 3.5974701996801006e-05, "loss": 0.4917, "num_tokens": 228901634.0, "step": 38265 }, { "epoch": 0.4082873694429923, "grad_norm": 0.9650534310035791, "learning_rate": 3.597102510668498e-05, "loss": 0.5139, "num_tokens": 228916113.0, "step": 38270 }, { "epoch": 0.4083407124491908, "grad_norm": 1.02633726765135, "learning_rate": 3.5967347952968064e-05, "loss": 0.5032, "num_tokens": 228961921.0, "step": 38275 }, { "epoch": 0.40839405545538926, "grad_norm": 0.8255826376479388, "learning_rate": 3.596367053576466e-05, "loss": 0.5798, "num_tokens": 228994674.0, "step": 38280 }, { "epoch": 0.4084473984615877, "grad_norm": 0.8706184591657936, "learning_rate": 3.595999285518923e-05, "loss": 0.5259, "num_tokens": 229026957.0, "step": 38285 }, { "epoch": 0.40850074146778614, "grad_norm": 1.147389875238303, "learning_rate": 3.5956314911356194e-05, "loss": 0.558, "num_tokens": 229066046.0, "step": 38290 }, { "epoch": 0.4085540844739846, "grad_norm": 1.39228238423584, "learning_rate": 3.595263670437999e-05, "loss": 0.6392, "num_tokens": 229093597.0, "step": 38295 }, { "epoch": 0.4086074274801831, "grad_norm": 0.8360522665075719, "learning_rate": 3.594895823437512e-05, "loss": 0.6333, "num_tokens": 229130953.0, "step": 38300 }, { "epoch": 0.40866077048638155, "grad_norm": 1.3205076187539029, "learning_rate": 3.594527950145601e-05, "loss": 0.5028, "num_tokens": 229175276.0, "step": 38305 }, { "epoch": 0.40871411349257997, "grad_norm": 0.8841388002954528, "learning_rate": 3.594160050573716e-05, "loss": 0.4264, "num_tokens": 229192882.0, "step": 38310 }, { "epoch": 0.40876745649877844, "grad_norm": 0.8036291839410764, "learning_rate": 3.593792124733303e-05, "loss": 0.5462, "num_tokens": 229221590.0, "step": 38315 }, { "epoch": 0.4088207995049769, "grad_norm": 1.2362406559554475, "learning_rate": 3.593424172635813e-05, "loss": 0.5374, "num_tokens": 229236333.0, "step": 38320 }, { "epoch": 0.4088741425111754, "grad_norm": 2.386324727450159, "learning_rate": 3.593056194292695e-05, "loss": 0.6353, "num_tokens": 229272449.0, "step": 38325 }, { "epoch": 0.4089274855173738, "grad_norm": 0.7853061573898221, "learning_rate": 3.5926881897154e-05, "loss": 0.5623, "num_tokens": 229308455.0, "step": 38330 }, { "epoch": 0.40898082852357226, "grad_norm": 1.2647471044722942, "learning_rate": 3.5923201589153785e-05, "loss": 0.4464, "num_tokens": 229323227.0, "step": 38335 }, { "epoch": 0.40903417152977073, "grad_norm": 1.268037035905608, "learning_rate": 3.591952101904085e-05, "loss": 0.5752, "num_tokens": 229343334.0, "step": 38340 }, { "epoch": 0.4090875145359692, "grad_norm": 1.275888970493143, "learning_rate": 3.591584018692971e-05, "loss": 0.5771, "num_tokens": 229367549.0, "step": 38345 }, { "epoch": 0.40914085754216767, "grad_norm": 1.052476811509996, "learning_rate": 3.591215909293491e-05, "loss": 0.4566, "num_tokens": 229383803.0, "step": 38350 }, { "epoch": 0.4091942005483661, "grad_norm": 1.4279936672549272, "learning_rate": 3.5908477737171006e-05, "loss": 0.5672, "num_tokens": 229407551.0, "step": 38355 }, { "epoch": 0.40924754355456455, "grad_norm": 0.8772553125971168, "learning_rate": 3.590479611975254e-05, "loss": 0.4911, "num_tokens": 229435564.0, "step": 38360 }, { "epoch": 0.409300886560763, "grad_norm": 0.64339007686682, "learning_rate": 3.590111424079408e-05, "loss": 0.5831, "num_tokens": 229480526.0, "step": 38365 }, { "epoch": 0.4093542295669615, "grad_norm": 1.2913491704138154, "learning_rate": 3.58974321004102e-05, "loss": 0.6372, "num_tokens": 229507874.0, "step": 38370 }, { "epoch": 0.4094075725731599, "grad_norm": 0.8113023127036832, "learning_rate": 3.589374969871549e-05, "loss": 0.5116, "num_tokens": 229537164.0, "step": 38375 }, { "epoch": 0.4094609155793584, "grad_norm": 0.6457533651055769, "learning_rate": 3.589006703582452e-05, "loss": 0.4276, "num_tokens": 229560233.0, "step": 38380 }, { "epoch": 0.40951425858555685, "grad_norm": 0.753523479331539, "learning_rate": 3.5886384111851906e-05, "loss": 0.5683, "num_tokens": 229607786.0, "step": 38385 }, { "epoch": 0.4095676015917553, "grad_norm": 0.6285477943843482, "learning_rate": 3.588270092691224e-05, "loss": 0.6323, "num_tokens": 229649771.0, "step": 38390 }, { "epoch": 0.4096209445979538, "grad_norm": 1.1068431392919367, "learning_rate": 3.587901748112014e-05, "loss": 0.5068, "num_tokens": 229685018.0, "step": 38395 }, { "epoch": 0.4096742876041522, "grad_norm": 1.1563932920946307, "learning_rate": 3.587533377459023e-05, "loss": 0.6349, "num_tokens": 229710487.0, "step": 38400 }, { "epoch": 0.40972763061035067, "grad_norm": 0.9371568545236345, "learning_rate": 3.587164980743714e-05, "loss": 0.6465, "num_tokens": 229734877.0, "step": 38405 }, { "epoch": 0.40978097361654914, "grad_norm": 1.5102225455504268, "learning_rate": 3.58679655797755e-05, "loss": 0.4221, "num_tokens": 229753403.0, "step": 38410 }, { "epoch": 0.4098343166227476, "grad_norm": 1.0163344786048163, "learning_rate": 3.5864281091719956e-05, "loss": 0.5924, "num_tokens": 229784057.0, "step": 38415 }, { "epoch": 0.409887659628946, "grad_norm": 0.7764491695469166, "learning_rate": 3.5860596343385174e-05, "loss": 0.4975, "num_tokens": 229813032.0, "step": 38420 }, { "epoch": 0.4099410026351445, "grad_norm": 0.9893697025945435, "learning_rate": 3.5856911334885794e-05, "loss": 0.5396, "num_tokens": 229850707.0, "step": 38425 }, { "epoch": 0.40999434564134296, "grad_norm": 0.6112298791144245, "learning_rate": 3.5853226066336505e-05, "loss": 0.4472, "num_tokens": 229878099.0, "step": 38430 }, { "epoch": 0.41004768864754143, "grad_norm": 1.0908720763372242, "learning_rate": 3.584954053785198e-05, "loss": 0.5568, "num_tokens": 229905803.0, "step": 38435 }, { "epoch": 0.4101010316537399, "grad_norm": 1.447449019866641, "learning_rate": 3.5845854749546905e-05, "loss": 0.4639, "num_tokens": 229942361.0, "step": 38440 }, { "epoch": 0.4101543746599383, "grad_norm": 0.8875782222095142, "learning_rate": 3.584216870153597e-05, "loss": 0.6119, "num_tokens": 229981932.0, "step": 38445 }, { "epoch": 0.4102077176661368, "grad_norm": 1.2341788907214069, "learning_rate": 3.5838482393933885e-05, "loss": 0.453, "num_tokens": 230007388.0, "step": 38450 }, { "epoch": 0.41026106067233525, "grad_norm": 0.9985818393464736, "learning_rate": 3.583479582685535e-05, "loss": 0.578, "num_tokens": 230032499.0, "step": 38455 }, { "epoch": 0.4103144036785337, "grad_norm": 0.8831235094346419, "learning_rate": 3.5831109000415095e-05, "loss": 0.553, "num_tokens": 230070035.0, "step": 38460 }, { "epoch": 0.41036774668473214, "grad_norm": 1.0879263417169602, "learning_rate": 3.582742191472783e-05, "loss": 0.5831, "num_tokens": 230101132.0, "step": 38465 }, { "epoch": 0.4104210896909306, "grad_norm": 1.0908363413105133, "learning_rate": 3.582373456990831e-05, "loss": 0.5124, "num_tokens": 230121604.0, "step": 38470 }, { "epoch": 0.4104744326971291, "grad_norm": 0.914249026818864, "learning_rate": 3.582004696607126e-05, "loss": 0.4419, "num_tokens": 230147645.0, "step": 38475 }, { "epoch": 0.41052777570332755, "grad_norm": 0.9012770897571124, "learning_rate": 3.5816359103331446e-05, "loss": 0.6917, "num_tokens": 230193426.0, "step": 38480 }, { "epoch": 0.410581118709526, "grad_norm": 1.1111216923405374, "learning_rate": 3.581267098180362e-05, "loss": 0.3922, "num_tokens": 230218612.0, "step": 38485 }, { "epoch": 0.41063446171572443, "grad_norm": 0.5771541085684533, "learning_rate": 3.580898260160254e-05, "loss": 0.5545, "num_tokens": 230253443.0, "step": 38490 }, { "epoch": 0.4106878047219229, "grad_norm": 1.3725076680471244, "learning_rate": 3.5805293962842993e-05, "loss": 0.4508, "num_tokens": 230289204.0, "step": 38495 }, { "epoch": 0.41074114772812137, "grad_norm": 1.7307536476237644, "learning_rate": 3.5801605065639754e-05, "loss": 0.7271, "num_tokens": 230329000.0, "step": 38500 }, { "epoch": 0.41079449073431984, "grad_norm": 1.2478601433918108, "learning_rate": 3.579791591010763e-05, "loss": 0.4352, "num_tokens": 230364211.0, "step": 38505 }, { "epoch": 0.41084783374051825, "grad_norm": 0.9620905458446294, "learning_rate": 3.5794226496361397e-05, "loss": 0.5419, "num_tokens": 230406896.0, "step": 38510 }, { "epoch": 0.4109011767467167, "grad_norm": 0.8929074994060864, "learning_rate": 3.5790536824515865e-05, "loss": 0.5227, "num_tokens": 230447173.0, "step": 38515 }, { "epoch": 0.4109545197529152, "grad_norm": 1.2915031994192196, "learning_rate": 3.578684689468586e-05, "loss": 0.5024, "num_tokens": 230479640.0, "step": 38520 }, { "epoch": 0.41100786275911366, "grad_norm": 1.0103567825247763, "learning_rate": 3.5783156706986207e-05, "loss": 0.6186, "num_tokens": 230491890.0, "step": 38525 }, { "epoch": 0.41106120576531213, "grad_norm": 0.8364763213759585, "learning_rate": 3.577946626153173e-05, "loss": 0.6044, "num_tokens": 230521117.0, "step": 38530 }, { "epoch": 0.41111454877151055, "grad_norm": 0.9288041518792444, "learning_rate": 3.577577555843727e-05, "loss": 0.5139, "num_tokens": 230553734.0, "step": 38535 }, { "epoch": 0.411167891777709, "grad_norm": 0.7814533584659195, "learning_rate": 3.577208459781767e-05, "loss": 0.7013, "num_tokens": 230579627.0, "step": 38540 }, { "epoch": 0.4112212347839075, "grad_norm": 0.6990324118144506, "learning_rate": 3.57683933797878e-05, "loss": 0.6044, "num_tokens": 230616844.0, "step": 38545 }, { "epoch": 0.41127457779010596, "grad_norm": 0.9751960790108591, "learning_rate": 3.5764701904462495e-05, "loss": 0.5588, "num_tokens": 230642458.0, "step": 38550 }, { "epoch": 0.41132792079630437, "grad_norm": 1.1848060967751974, "learning_rate": 3.576101017195665e-05, "loss": 0.5485, "num_tokens": 230667032.0, "step": 38555 }, { "epoch": 0.41138126380250284, "grad_norm": 1.442175140858502, "learning_rate": 3.575731818238514e-05, "loss": 0.6834, "num_tokens": 230700264.0, "step": 38560 }, { "epoch": 0.4114346068087013, "grad_norm": 1.2295495466151758, "learning_rate": 3.575362593586285e-05, "loss": 0.6139, "num_tokens": 230722890.0, "step": 38565 }, { "epoch": 0.4114879498148998, "grad_norm": 0.8298838185424547, "learning_rate": 3.574993343250467e-05, "loss": 0.5704, "num_tokens": 230762351.0, "step": 38570 }, { "epoch": 0.41154129282109825, "grad_norm": 1.3102734323377396, "learning_rate": 3.574624067242551e-05, "loss": 0.5919, "num_tokens": 230793749.0, "step": 38575 }, { "epoch": 0.41159463582729666, "grad_norm": 0.9756074732138799, "learning_rate": 3.5742547655740274e-05, "loss": 0.4244, "num_tokens": 230809088.0, "step": 38580 }, { "epoch": 0.41164797883349513, "grad_norm": 0.7773891717009422, "learning_rate": 3.573885438256389e-05, "loss": 0.466, "num_tokens": 230838675.0, "step": 38585 }, { "epoch": 0.4117013218396936, "grad_norm": 0.9963680428879539, "learning_rate": 3.573516085301127e-05, "loss": 0.5111, "num_tokens": 230862524.0, "step": 38590 }, { "epoch": 0.41175466484589207, "grad_norm": 1.076073552375195, "learning_rate": 3.573146706719738e-05, "loss": 0.4967, "num_tokens": 230881260.0, "step": 38595 }, { "epoch": 0.4118080078520905, "grad_norm": 0.7840611991583541, "learning_rate": 3.572777302523713e-05, "loss": 0.5552, "num_tokens": 230913480.0, "step": 38600 }, { "epoch": 0.41186135085828895, "grad_norm": 1.326809825839254, "learning_rate": 3.5724078727245486e-05, "loss": 0.6038, "num_tokens": 230935548.0, "step": 38605 }, { "epoch": 0.4119146938644874, "grad_norm": 1.1744862767709199, "learning_rate": 3.5720384173337406e-05, "loss": 0.5322, "num_tokens": 230973386.0, "step": 38610 }, { "epoch": 0.4119680368706859, "grad_norm": 1.0072526476206176, "learning_rate": 3.5716689363627856e-05, "loss": 0.6007, "num_tokens": 231005415.0, "step": 38615 }, { "epoch": 0.41202137987688436, "grad_norm": 0.8168059119106393, "learning_rate": 3.571299429823181e-05, "loss": 0.5991, "num_tokens": 231038417.0, "step": 38620 }, { "epoch": 0.4120747228830828, "grad_norm": 0.9217086991591606, "learning_rate": 3.570929897726425e-05, "loss": 0.7575, "num_tokens": 231081184.0, "step": 38625 }, { "epoch": 0.41212806588928125, "grad_norm": 1.4093602470645101, "learning_rate": 3.570560340084016e-05, "loss": 0.612, "num_tokens": 231103249.0, "step": 38630 }, { "epoch": 0.4121814088954797, "grad_norm": 0.6949025142512129, "learning_rate": 3.570190756907457e-05, "loss": 0.4504, "num_tokens": 231131487.0, "step": 38635 }, { "epoch": 0.4122347519016782, "grad_norm": 1.2542482213234274, "learning_rate": 3.5698211482082446e-05, "loss": 0.6179, "num_tokens": 231162439.0, "step": 38640 }, { "epoch": 0.4122880949078766, "grad_norm": 0.8607649379860971, "learning_rate": 3.569451513997882e-05, "loss": 0.6605, "num_tokens": 231186780.0, "step": 38645 }, { "epoch": 0.41234143791407507, "grad_norm": 1.4453078357591096, "learning_rate": 3.569081854287872e-05, "loss": 0.4931, "num_tokens": 231206528.0, "step": 38650 }, { "epoch": 0.41239478092027354, "grad_norm": 0.9715077705155906, "learning_rate": 3.5687121690897165e-05, "loss": 0.4823, "num_tokens": 231236222.0, "step": 38655 }, { "epoch": 0.412448123926472, "grad_norm": 1.2998443654638894, "learning_rate": 3.568342458414921e-05, "loss": 0.6709, "num_tokens": 231257910.0, "step": 38660 }, { "epoch": 0.4125014669326705, "grad_norm": 1.1209908941154447, "learning_rate": 3.567972722274988e-05, "loss": 0.5637, "num_tokens": 231271050.0, "step": 38665 }, { "epoch": 0.4125548099388689, "grad_norm": 0.6963718128127274, "learning_rate": 3.5676029606814256e-05, "loss": 0.6688, "num_tokens": 231310330.0, "step": 38670 }, { "epoch": 0.41260815294506736, "grad_norm": 0.9673159500456073, "learning_rate": 3.567233173645737e-05, "loss": 0.5998, "num_tokens": 231355746.0, "step": 38675 }, { "epoch": 0.41266149595126583, "grad_norm": 0.9643222863523924, "learning_rate": 3.56686336117943e-05, "loss": 0.4542, "num_tokens": 231396528.0, "step": 38680 }, { "epoch": 0.4127148389574643, "grad_norm": 0.7483987894944581, "learning_rate": 3.566493523294015e-05, "loss": 0.5224, "num_tokens": 231432012.0, "step": 38685 }, { "epoch": 0.4127681819636627, "grad_norm": 1.0207256996293832, "learning_rate": 3.5661236600009986e-05, "loss": 0.4527, "num_tokens": 231464848.0, "step": 38690 }, { "epoch": 0.4128215249698612, "grad_norm": 0.671437316079911, "learning_rate": 3.565753771311889e-05, "loss": 0.4688, "num_tokens": 231510465.0, "step": 38695 }, { "epoch": 0.41287486797605966, "grad_norm": 1.0825659641082137, "learning_rate": 3.5653838572381984e-05, "loss": 0.5262, "num_tokens": 231538427.0, "step": 38700 }, { "epoch": 0.4129282109822581, "grad_norm": 0.7164284220087006, "learning_rate": 3.565013917791437e-05, "loss": 0.4781, "num_tokens": 231570638.0, "step": 38705 }, { "epoch": 0.4129815539884566, "grad_norm": 0.8424097894666102, "learning_rate": 3.564643952983116e-05, "loss": 0.5115, "num_tokens": 231604085.0, "step": 38710 }, { "epoch": 0.413034896994655, "grad_norm": 0.734790662455154, "learning_rate": 3.564273962824749e-05, "loss": 0.5817, "num_tokens": 231647194.0, "step": 38715 }, { "epoch": 0.4130882400008535, "grad_norm": 1.5105712757465606, "learning_rate": 3.563903947327849e-05, "loss": 0.6562, "num_tokens": 231678126.0, "step": 38720 }, { "epoch": 0.41314158300705195, "grad_norm": 1.478579585835267, "learning_rate": 3.563533906503929e-05, "loss": 0.5879, "num_tokens": 231693668.0, "step": 38725 }, { "epoch": 0.4131949260132504, "grad_norm": 1.429679213044255, "learning_rate": 3.5631638403645064e-05, "loss": 0.5678, "num_tokens": 231707929.0, "step": 38730 }, { "epoch": 0.41324826901944883, "grad_norm": 1.7460528075315709, "learning_rate": 3.562793748921095e-05, "loss": 0.5197, "num_tokens": 231733555.0, "step": 38735 }, { "epoch": 0.4133016120256473, "grad_norm": 0.7771383787660916, "learning_rate": 3.5624236321852105e-05, "loss": 0.5425, "num_tokens": 231780518.0, "step": 38740 }, { "epoch": 0.41335495503184577, "grad_norm": 1.0128061919709963, "learning_rate": 3.5620534901683725e-05, "loss": 0.6708, "num_tokens": 231806722.0, "step": 38745 }, { "epoch": 0.41340829803804424, "grad_norm": 2.7397554976842473, "learning_rate": 3.5616833228820975e-05, "loss": 0.6524, "num_tokens": 231845462.0, "step": 38750 }, { "epoch": 0.4134616410442427, "grad_norm": 1.1009123158310108, "learning_rate": 3.5613131303379044e-05, "loss": 0.5217, "num_tokens": 231862644.0, "step": 38755 }, { "epoch": 0.4135149840504411, "grad_norm": 1.1780923672547103, "learning_rate": 3.5609429125473136e-05, "loss": 0.5466, "num_tokens": 231898631.0, "step": 38760 }, { "epoch": 0.4135683270566396, "grad_norm": 0.9860131738486945, "learning_rate": 3.560572669521845e-05, "loss": 0.5868, "num_tokens": 231916722.0, "step": 38765 }, { "epoch": 0.41362167006283806, "grad_norm": 0.7227777532377273, "learning_rate": 3.5602024012730195e-05, "loss": 0.4925, "num_tokens": 231953730.0, "step": 38770 }, { "epoch": 0.41367501306903653, "grad_norm": 4.563184754393472, "learning_rate": 3.5598321078123595e-05, "loss": 0.6335, "num_tokens": 231972281.0, "step": 38775 }, { "epoch": 0.41372835607523495, "grad_norm": 0.6435794816735417, "learning_rate": 3.559461789151388e-05, "loss": 0.5208, "num_tokens": 232009822.0, "step": 38780 }, { "epoch": 0.4137816990814334, "grad_norm": 1.1469198712039042, "learning_rate": 3.559091445301629e-05, "loss": 0.5209, "num_tokens": 232029819.0, "step": 38785 }, { "epoch": 0.4138350420876319, "grad_norm": 0.7439413436389495, "learning_rate": 3.558721076274605e-05, "loss": 0.6155, "num_tokens": 232074778.0, "step": 38790 }, { "epoch": 0.41388838509383036, "grad_norm": 1.3371902819668424, "learning_rate": 3.558350682081843e-05, "loss": 0.5734, "num_tokens": 232105835.0, "step": 38795 }, { "epoch": 0.4139417281000288, "grad_norm": 1.139629962346911, "learning_rate": 3.5579802627348684e-05, "loss": 0.4896, "num_tokens": 232143267.0, "step": 38800 }, { "epoch": 0.41399507110622724, "grad_norm": 0.9875456719683798, "learning_rate": 3.557609818245207e-05, "loss": 0.7316, "num_tokens": 232182847.0, "step": 38805 }, { "epoch": 0.4140484141124257, "grad_norm": 0.6621312572774413, "learning_rate": 3.5572393486243864e-05, "loss": 0.5502, "num_tokens": 232218532.0, "step": 38810 }, { "epoch": 0.4141017571186242, "grad_norm": 1.6317228490074756, "learning_rate": 3.556868853883937e-05, "loss": 0.6149, "num_tokens": 232261881.0, "step": 38815 }, { "epoch": 0.41415510012482265, "grad_norm": 0.7213584694098626, "learning_rate": 3.556498334035386e-05, "loss": 0.5183, "num_tokens": 232293212.0, "step": 38820 }, { "epoch": 0.41420844313102106, "grad_norm": 1.0159827539139312, "learning_rate": 3.556127789090262e-05, "loss": 0.6836, "num_tokens": 232313146.0, "step": 38825 }, { "epoch": 0.41426178613721953, "grad_norm": 0.9373451006935154, "learning_rate": 3.555757219060098e-05, "loss": 0.56, "num_tokens": 232350303.0, "step": 38830 }, { "epoch": 0.414315129143418, "grad_norm": 0.5716425140264487, "learning_rate": 3.555386623956424e-05, "loss": 0.5312, "num_tokens": 232385539.0, "step": 38835 }, { "epoch": 0.4143684721496165, "grad_norm": 0.7935657553337891, "learning_rate": 3.555016003790773e-05, "loss": 0.4788, "num_tokens": 232418693.0, "step": 38840 }, { "epoch": 0.41442181515581494, "grad_norm": 0.6231860868363615, "learning_rate": 3.554645358574677e-05, "loss": 0.5048, "num_tokens": 232453066.0, "step": 38845 }, { "epoch": 0.41447515816201336, "grad_norm": 1.102697338404411, "learning_rate": 3.554274688319671e-05, "loss": 0.6671, "num_tokens": 232479038.0, "step": 38850 }, { "epoch": 0.4145285011682118, "grad_norm": 1.2093904345141977, "learning_rate": 3.553903993037288e-05, "loss": 0.5332, "num_tokens": 232503079.0, "step": 38855 }, { "epoch": 0.4145818441744103, "grad_norm": 0.6592754412965247, "learning_rate": 3.553533272739064e-05, "loss": 0.5882, "num_tokens": 232538398.0, "step": 38860 }, { "epoch": 0.41463518718060877, "grad_norm": 0.7479050238856818, "learning_rate": 3.553162527436536e-05, "loss": 0.4504, "num_tokens": 232560822.0, "step": 38865 }, { "epoch": 0.4146885301868072, "grad_norm": 0.9108708255294814, "learning_rate": 3.5527917571412386e-05, "loss": 0.4422, "num_tokens": 232590656.0, "step": 38870 }, { "epoch": 0.41474187319300565, "grad_norm": 0.929863755826846, "learning_rate": 3.552420961864712e-05, "loss": 0.5541, "num_tokens": 232627317.0, "step": 38875 }, { "epoch": 0.4147952161992041, "grad_norm": 1.6872052746368598, "learning_rate": 3.5520501416184925e-05, "loss": 0.5392, "num_tokens": 232659926.0, "step": 38880 }, { "epoch": 0.4148485592054026, "grad_norm": 2.6135382389276844, "learning_rate": 3.55167929641412e-05, "loss": 0.6347, "num_tokens": 232676848.0, "step": 38885 }, { "epoch": 0.41490190221160106, "grad_norm": 0.8572795539730039, "learning_rate": 3.5513084262631354e-05, "loss": 0.6329, "num_tokens": 232714597.0, "step": 38890 }, { "epoch": 0.4149552452177995, "grad_norm": 0.9242160918932014, "learning_rate": 3.550937531177078e-05, "loss": 0.5536, "num_tokens": 232738947.0, "step": 38895 }, { "epoch": 0.41500858822399794, "grad_norm": 0.9881174910716486, "learning_rate": 3.5505666111674885e-05, "loss": 0.4981, "num_tokens": 232762486.0, "step": 38900 }, { "epoch": 0.4150619312301964, "grad_norm": 1.0056735719479521, "learning_rate": 3.550195666245912e-05, "loss": 0.6334, "num_tokens": 232798886.0, "step": 38905 }, { "epoch": 0.4151152742363949, "grad_norm": 1.9099012024562405, "learning_rate": 3.54982469642389e-05, "loss": 0.4734, "num_tokens": 232811810.0, "step": 38910 }, { "epoch": 0.4151686172425933, "grad_norm": 1.1876753316316675, "learning_rate": 3.5494537017129654e-05, "loss": 0.7263, "num_tokens": 232836112.0, "step": 38915 }, { "epoch": 0.41522196024879177, "grad_norm": 1.0381192174044331, "learning_rate": 3.549082682124684e-05, "loss": 0.4698, "num_tokens": 232861855.0, "step": 38920 }, { "epoch": 0.41527530325499024, "grad_norm": 0.9759750946910362, "learning_rate": 3.548711637670592e-05, "loss": 0.6499, "num_tokens": 232899708.0, "step": 38925 }, { "epoch": 0.4153286462611887, "grad_norm": 1.0222547824782855, "learning_rate": 3.548340568362233e-05, "loss": 0.5073, "num_tokens": 232935733.0, "step": 38930 }, { "epoch": 0.4153819892673872, "grad_norm": 1.0958682699533968, "learning_rate": 3.547969474211156e-05, "loss": 0.6193, "num_tokens": 232967969.0, "step": 38935 }, { "epoch": 0.4154353322735856, "grad_norm": 0.9306792932496591, "learning_rate": 3.5475983552289074e-05, "loss": 0.5185, "num_tokens": 233002540.0, "step": 38940 }, { "epoch": 0.41548867527978406, "grad_norm": 1.2191376257137885, "learning_rate": 3.5472272114270375e-05, "loss": 0.4914, "num_tokens": 233032319.0, "step": 38945 }, { "epoch": 0.41554201828598253, "grad_norm": 0.9131320959120276, "learning_rate": 3.546856042817093e-05, "loss": 0.5786, "num_tokens": 233060857.0, "step": 38950 }, { "epoch": 0.415595361292181, "grad_norm": 1.0226909596227105, "learning_rate": 3.546484849410626e-05, "loss": 0.689, "num_tokens": 233096441.0, "step": 38955 }, { "epoch": 0.4156487042983794, "grad_norm": 1.3575519429564582, "learning_rate": 3.546113631219187e-05, "loss": 0.6093, "num_tokens": 233122116.0, "step": 38960 }, { "epoch": 0.4157020473045779, "grad_norm": 0.8481056451443585, "learning_rate": 3.5457423882543265e-05, "loss": 0.5874, "num_tokens": 233158639.0, "step": 38965 }, { "epoch": 0.41575539031077635, "grad_norm": 1.375345794551946, "learning_rate": 3.5453711205275974e-05, "loss": 0.7255, "num_tokens": 233184236.0, "step": 38970 }, { "epoch": 0.4158087333169748, "grad_norm": 0.844725186974593, "learning_rate": 3.544999828050553e-05, "loss": 0.536, "num_tokens": 233226184.0, "step": 38975 }, { "epoch": 0.4158620763231733, "grad_norm": 0.923220217374037, "learning_rate": 3.5446285108347466e-05, "loss": 0.5723, "num_tokens": 233250163.0, "step": 38980 }, { "epoch": 0.4159154193293717, "grad_norm": 0.736964637326288, "learning_rate": 3.544257168891733e-05, "loss": 0.5855, "num_tokens": 233284281.0, "step": 38985 }, { "epoch": 0.4159687623355702, "grad_norm": 0.647949481842361, "learning_rate": 3.543885802233068e-05, "loss": 0.4863, "num_tokens": 233326607.0, "step": 38990 }, { "epoch": 0.41602210534176864, "grad_norm": 6.266887817429022, "learning_rate": 3.5435144108703075e-05, "loss": 0.6184, "num_tokens": 233351201.0, "step": 38995 }, { "epoch": 0.4160754483479671, "grad_norm": 0.8818665697776068, "learning_rate": 3.543142994815009e-05, "loss": 0.6454, "num_tokens": 233375223.0, "step": 39000 }, { "epoch": 0.41612879135416553, "grad_norm": 0.6000014489255195, "learning_rate": 3.5427715540787285e-05, "loss": 0.6083, "num_tokens": 233399124.0, "step": 39005 }, { "epoch": 0.416182134360364, "grad_norm": 0.76728530632798, "learning_rate": 3.542400088673026e-05, "loss": 0.6059, "num_tokens": 233431220.0, "step": 39010 }, { "epoch": 0.41623547736656247, "grad_norm": 1.114315026982849, "learning_rate": 3.542028598609461e-05, "loss": 0.6286, "num_tokens": 233467791.0, "step": 39015 }, { "epoch": 0.41628882037276094, "grad_norm": 1.337645543619046, "learning_rate": 3.5416570838995926e-05, "loss": 0.5265, "num_tokens": 233493140.0, "step": 39020 }, { "epoch": 0.4163421633789594, "grad_norm": 1.1183630507447733, "learning_rate": 3.541285544554982e-05, "loss": 0.4097, "num_tokens": 233526162.0, "step": 39025 }, { "epoch": 0.4163955063851578, "grad_norm": 0.6736567366142935, "learning_rate": 3.54091398058719e-05, "loss": 0.4984, "num_tokens": 233560924.0, "step": 39030 }, { "epoch": 0.4164488493913563, "grad_norm": 0.7126513671716996, "learning_rate": 3.5405423920077804e-05, "loss": 0.6058, "num_tokens": 233587196.0, "step": 39035 }, { "epoch": 0.41650219239755476, "grad_norm": 0.7921445321833867, "learning_rate": 3.5401707788283145e-05, "loss": 0.5308, "num_tokens": 233617525.0, "step": 39040 }, { "epoch": 0.41655553540375323, "grad_norm": 1.4233234661819327, "learning_rate": 3.5397991410603576e-05, "loss": 0.5852, "num_tokens": 233642308.0, "step": 39045 }, { "epoch": 0.41660887840995164, "grad_norm": 1.2456365107041192, "learning_rate": 3.5394274787154734e-05, "loss": 0.5204, "num_tokens": 233662527.0, "step": 39050 }, { "epoch": 0.4166622214161501, "grad_norm": 1.3613918565375986, "learning_rate": 3.539055791805228e-05, "loss": 0.4944, "num_tokens": 233695629.0, "step": 39055 }, { "epoch": 0.4167155644223486, "grad_norm": 1.1568929497067013, "learning_rate": 3.538684080341186e-05, "loss": 0.591, "num_tokens": 233727180.0, "step": 39060 }, { "epoch": 0.41676890742854705, "grad_norm": 0.8042098227069151, "learning_rate": 3.538312344334917e-05, "loss": 0.4372, "num_tokens": 233758466.0, "step": 39065 }, { "epoch": 0.4168222504347455, "grad_norm": 0.9850246631283388, "learning_rate": 3.537940583797986e-05, "loss": 0.4549, "num_tokens": 233787937.0, "step": 39070 }, { "epoch": 0.41687559344094394, "grad_norm": 4.9801297686092, "learning_rate": 3.537568798741963e-05, "loss": 0.48, "num_tokens": 233824143.0, "step": 39075 }, { "epoch": 0.4169289364471424, "grad_norm": 0.8219786786724939, "learning_rate": 3.5371969891784166e-05, "loss": 0.5732, "num_tokens": 233858938.0, "step": 39080 }, { "epoch": 0.4169822794533409, "grad_norm": 1.1824773577480714, "learning_rate": 3.536825155118917e-05, "loss": 0.5331, "num_tokens": 233889016.0, "step": 39085 }, { "epoch": 0.41703562245953935, "grad_norm": 0.8763912992403158, "learning_rate": 3.5364532965750345e-05, "loss": 0.5962, "num_tokens": 233931451.0, "step": 39090 }, { "epoch": 0.41708896546573776, "grad_norm": 0.7009969164873566, "learning_rate": 3.5360814135583405e-05, "loss": 0.5017, "num_tokens": 233962385.0, "step": 39095 }, { "epoch": 0.41714230847193623, "grad_norm": 1.5373393776385311, "learning_rate": 3.5357095060804084e-05, "loss": 0.5505, "num_tokens": 233983057.0, "step": 39100 }, { "epoch": 0.4171956514781347, "grad_norm": 0.6880427636504333, "learning_rate": 3.535337574152809e-05, "loss": 0.5146, "num_tokens": 234012677.0, "step": 39105 }, { "epoch": 0.41724899448433317, "grad_norm": 0.7110518426500168, "learning_rate": 3.534965617787119e-05, "loss": 0.7031, "num_tokens": 234040552.0, "step": 39110 }, { "epoch": 0.41730233749053164, "grad_norm": 0.9065992685314974, "learning_rate": 3.534593636994911e-05, "loss": 0.5852, "num_tokens": 234066077.0, "step": 39115 }, { "epoch": 0.41735568049673005, "grad_norm": 0.683960254117699, "learning_rate": 3.53422163178776e-05, "loss": 0.59, "num_tokens": 234109138.0, "step": 39120 }, { "epoch": 0.4174090235029285, "grad_norm": 1.7160043003208063, "learning_rate": 3.533849602177243e-05, "loss": 0.6222, "num_tokens": 234131702.0, "step": 39125 }, { "epoch": 0.417462366509127, "grad_norm": 0.7809935581149362, "learning_rate": 3.533477548174936e-05, "loss": 0.5748, "num_tokens": 234160994.0, "step": 39130 }, { "epoch": 0.41751570951532546, "grad_norm": 0.8089275803984077, "learning_rate": 3.533105469792418e-05, "loss": 0.538, "num_tokens": 234178217.0, "step": 39135 }, { "epoch": 0.4175690525215239, "grad_norm": 0.645893291372752, "learning_rate": 3.532733367041265e-05, "loss": 0.4693, "num_tokens": 234217829.0, "step": 39140 }, { "epoch": 0.41762239552772235, "grad_norm": 1.1389714388496477, "learning_rate": 3.5323612399330594e-05, "loss": 0.5521, "num_tokens": 234248290.0, "step": 39145 }, { "epoch": 0.4176757385339208, "grad_norm": 2.089421642309642, "learning_rate": 3.531989088479377e-05, "loss": 0.5768, "num_tokens": 234264527.0, "step": 39150 }, { "epoch": 0.4177290815401193, "grad_norm": 1.2509744630184998, "learning_rate": 3.5316169126918015e-05, "loss": 0.6004, "num_tokens": 234304494.0, "step": 39155 }, { "epoch": 0.41778242454631775, "grad_norm": 0.6212913305488758, "learning_rate": 3.531244712581913e-05, "loss": 0.5387, "num_tokens": 234337401.0, "step": 39160 }, { "epoch": 0.41783576755251617, "grad_norm": 1.085540061337912, "learning_rate": 3.5308724881612934e-05, "loss": 0.4736, "num_tokens": 234366484.0, "step": 39165 }, { "epoch": 0.41788911055871464, "grad_norm": 1.2710413159292364, "learning_rate": 3.530500239441526e-05, "loss": 0.502, "num_tokens": 234395172.0, "step": 39170 }, { "epoch": 0.4179424535649131, "grad_norm": 1.0277203129299344, "learning_rate": 3.530127966434194e-05, "loss": 0.6198, "num_tokens": 234436039.0, "step": 39175 }, { "epoch": 0.4179957965711116, "grad_norm": 1.4046250310900845, "learning_rate": 3.529755669150883e-05, "loss": 0.5663, "num_tokens": 234459213.0, "step": 39180 }, { "epoch": 0.41804913957731, "grad_norm": 0.791608023350167, "learning_rate": 3.5293833476031765e-05, "loss": 0.6043, "num_tokens": 234483671.0, "step": 39185 }, { "epoch": 0.41810248258350846, "grad_norm": 0.9714681932223348, "learning_rate": 3.529011001802662e-05, "loss": 0.5049, "num_tokens": 234503587.0, "step": 39190 }, { "epoch": 0.41815582558970693, "grad_norm": 1.0201848835812342, "learning_rate": 3.528638631760925e-05, "loss": 0.5251, "num_tokens": 234525233.0, "step": 39195 }, { "epoch": 0.4182091685959054, "grad_norm": 1.1155786385169866, "learning_rate": 3.5282662374895525e-05, "loss": 0.6389, "num_tokens": 234557768.0, "step": 39200 }, { "epoch": 0.41826251160210387, "grad_norm": 1.2613317305076879, "learning_rate": 3.527893819000134e-05, "loss": 0.555, "num_tokens": 234593737.0, "step": 39205 }, { "epoch": 0.4183158546083023, "grad_norm": 1.0310892793383204, "learning_rate": 3.5275213763042576e-05, "loss": 0.5877, "num_tokens": 234612848.0, "step": 39210 }, { "epoch": 0.41836919761450075, "grad_norm": 0.8647897933617676, "learning_rate": 3.527148909413512e-05, "loss": 0.5336, "num_tokens": 234650365.0, "step": 39215 }, { "epoch": 0.4184225406206992, "grad_norm": 0.8653933263687432, "learning_rate": 3.5267764183394894e-05, "loss": 0.4594, "num_tokens": 234668942.0, "step": 39220 }, { "epoch": 0.4184758836268977, "grad_norm": 1.4959517548632164, "learning_rate": 3.5264039030937804e-05, "loss": 0.479, "num_tokens": 234696379.0, "step": 39225 }, { "epoch": 0.4185292266330961, "grad_norm": 0.6869171941863645, "learning_rate": 3.5260313636879764e-05, "loss": 0.6382, "num_tokens": 234729885.0, "step": 39230 }, { "epoch": 0.4185825696392946, "grad_norm": 0.8874324954845811, "learning_rate": 3.525658800133672e-05, "loss": 0.6893, "num_tokens": 234767127.0, "step": 39235 }, { "epoch": 0.41863591264549305, "grad_norm": 1.3244346020767999, "learning_rate": 3.5252862124424565e-05, "loss": 0.5846, "num_tokens": 234787641.0, "step": 39240 }, { "epoch": 0.4186892556516915, "grad_norm": 0.7327273369227342, "learning_rate": 3.524913600625927e-05, "loss": 0.6237, "num_tokens": 234827530.0, "step": 39245 }, { "epoch": 0.41874259865789, "grad_norm": 0.8136582925291589, "learning_rate": 3.524540964695679e-05, "loss": 0.4925, "num_tokens": 234847957.0, "step": 39250 }, { "epoch": 0.4187959416640884, "grad_norm": 1.2864302776565697, "learning_rate": 3.5241683046633065e-05, "loss": 0.4688, "num_tokens": 234860843.0, "step": 39255 }, { "epoch": 0.41884928467028687, "grad_norm": 0.8072275567932718, "learning_rate": 3.523795620540407e-05, "loss": 0.5489, "num_tokens": 234903734.0, "step": 39260 }, { "epoch": 0.41890262767648534, "grad_norm": 0.6449859431639431, "learning_rate": 3.523422912338577e-05, "loss": 0.6502, "num_tokens": 234948710.0, "step": 39265 }, { "epoch": 0.4189559706826838, "grad_norm": 0.8816619240757816, "learning_rate": 3.523050180069414e-05, "loss": 0.6018, "num_tokens": 234980414.0, "step": 39270 }, { "epoch": 0.4190093136888822, "grad_norm": 0.8949325050872031, "learning_rate": 3.5226774237445184e-05, "loss": 0.6268, "num_tokens": 235015732.0, "step": 39275 }, { "epoch": 0.4190626566950807, "grad_norm": 1.52966980254344, "learning_rate": 3.522304643375488e-05, "loss": 0.4775, "num_tokens": 235029296.0, "step": 39280 }, { "epoch": 0.41911599970127916, "grad_norm": 0.7974339167416122, "learning_rate": 3.521931838973923e-05, "loss": 0.5399, "num_tokens": 235069101.0, "step": 39285 }, { "epoch": 0.41916934270747763, "grad_norm": 0.8323386646285654, "learning_rate": 3.521559010551426e-05, "loss": 0.5491, "num_tokens": 235092802.0, "step": 39290 }, { "epoch": 0.4192226857136761, "grad_norm": 1.0827030052194073, "learning_rate": 3.521186158119596e-05, "loss": 0.4601, "num_tokens": 235108897.0, "step": 39295 }, { "epoch": 0.4192760287198745, "grad_norm": 0.851345816531705, "learning_rate": 3.520813281690037e-05, "loss": 0.5388, "num_tokens": 235138012.0, "step": 39300 }, { "epoch": 0.419329371726073, "grad_norm": 0.8101489677324776, "learning_rate": 3.520440381274352e-05, "loss": 0.5875, "num_tokens": 235157263.0, "step": 39305 }, { "epoch": 0.41938271473227146, "grad_norm": 1.4080796341054385, "learning_rate": 3.520067456884146e-05, "loss": 0.4718, "num_tokens": 235184350.0, "step": 39310 }, { "epoch": 0.4194360577384699, "grad_norm": 1.1984809141405286, "learning_rate": 3.5196945085310216e-05, "loss": 0.5411, "num_tokens": 235221639.0, "step": 39315 }, { "epoch": 0.41948940074466834, "grad_norm": 0.6490910431914862, "learning_rate": 3.519321536226585e-05, "loss": 0.4946, "num_tokens": 235250447.0, "step": 39320 }, { "epoch": 0.4195427437508668, "grad_norm": 1.54891612838065, "learning_rate": 3.518948539982443e-05, "loss": 0.5587, "num_tokens": 235282018.0, "step": 39325 }, { "epoch": 0.4195960867570653, "grad_norm": 1.4925361409006814, "learning_rate": 3.5185755198102014e-05, "loss": 0.7067, "num_tokens": 235310085.0, "step": 39330 }, { "epoch": 0.41964942976326375, "grad_norm": 7.9060093747846185, "learning_rate": 3.518202475721469e-05, "loss": 0.5845, "num_tokens": 235338948.0, "step": 39335 }, { "epoch": 0.4197027727694622, "grad_norm": 0.8367372671972214, "learning_rate": 3.517829407727853e-05, "loss": 0.6058, "num_tokens": 235361591.0, "step": 39340 }, { "epoch": 0.41975611577566063, "grad_norm": 0.7560370292303825, "learning_rate": 3.517456315840963e-05, "loss": 0.6358, "num_tokens": 235381681.0, "step": 39345 }, { "epoch": 0.4198094587818591, "grad_norm": 0.8396597782179173, "learning_rate": 3.5170832000724084e-05, "loss": 0.494, "num_tokens": 235403671.0, "step": 39350 }, { "epoch": 0.41986280178805757, "grad_norm": 0.9911706189835853, "learning_rate": 3.516710060433801e-05, "loss": 0.4725, "num_tokens": 235427640.0, "step": 39355 }, { "epoch": 0.41991614479425604, "grad_norm": 1.0237684054659202, "learning_rate": 3.516336896936751e-05, "loss": 0.5198, "num_tokens": 235464027.0, "step": 39360 }, { "epoch": 0.41996948780045446, "grad_norm": 1.0053785274858904, "learning_rate": 3.515963709592871e-05, "loss": 0.4784, "num_tokens": 235492087.0, "step": 39365 }, { "epoch": 0.4200228308066529, "grad_norm": 0.8935071534461828, "learning_rate": 3.5155904984137736e-05, "loss": 0.5552, "num_tokens": 235516301.0, "step": 39370 }, { "epoch": 0.4200761738128514, "grad_norm": 1.094074336614452, "learning_rate": 3.515217263411073e-05, "loss": 0.5945, "num_tokens": 235554118.0, "step": 39375 }, { "epoch": 0.42012951681904986, "grad_norm": 0.748801808210743, "learning_rate": 3.514844004596382e-05, "loss": 0.5114, "num_tokens": 235577515.0, "step": 39380 }, { "epoch": 0.42018285982524833, "grad_norm": 1.0121992794990171, "learning_rate": 3.514470721981317e-05, "loss": 0.5932, "num_tokens": 235609379.0, "step": 39385 }, { "epoch": 0.42023620283144675, "grad_norm": 0.8896580757451699, "learning_rate": 3.514097415577494e-05, "loss": 0.5217, "num_tokens": 235637351.0, "step": 39390 }, { "epoch": 0.4202895458376452, "grad_norm": 1.678201290217573, "learning_rate": 3.513724085396528e-05, "loss": 0.4933, "num_tokens": 235650696.0, "step": 39395 }, { "epoch": 0.4203428888438437, "grad_norm": 0.9290884517201243, "learning_rate": 3.5133507314500376e-05, "loss": 0.5732, "num_tokens": 235676223.0, "step": 39400 }, { "epoch": 0.42039623185004216, "grad_norm": 0.93236345319461, "learning_rate": 3.51297735374964e-05, "loss": 0.4793, "num_tokens": 235700654.0, "step": 39405 }, { "epoch": 0.42044957485624057, "grad_norm": 1.0425074811872928, "learning_rate": 3.5126039523069546e-05, "loss": 0.5532, "num_tokens": 235725487.0, "step": 39410 }, { "epoch": 0.42050291786243904, "grad_norm": 0.8284809356722144, "learning_rate": 3.512230527133601e-05, "loss": 0.6275, "num_tokens": 235766914.0, "step": 39415 }, { "epoch": 0.4205562608686375, "grad_norm": 0.803305629982459, "learning_rate": 3.511857078241199e-05, "loss": 0.6222, "num_tokens": 235808069.0, "step": 39420 }, { "epoch": 0.420609603874836, "grad_norm": 0.6586413435911364, "learning_rate": 3.511483605641369e-05, "loss": 0.5109, "num_tokens": 235843448.0, "step": 39425 }, { "epoch": 0.42066294688103445, "grad_norm": 1.6550537962259677, "learning_rate": 3.5111101093457346e-05, "loss": 0.5544, "num_tokens": 235876103.0, "step": 39430 }, { "epoch": 0.42071628988723286, "grad_norm": 0.7207470068239652, "learning_rate": 3.5107365893659156e-05, "loss": 0.6656, "num_tokens": 235909342.0, "step": 39435 }, { "epoch": 0.42076963289343133, "grad_norm": 1.1498681485516704, "learning_rate": 3.510363045713537e-05, "loss": 0.5305, "num_tokens": 235936634.0, "step": 39440 }, { "epoch": 0.4208229758996298, "grad_norm": 1.2687376392622862, "learning_rate": 3.5099894784002227e-05, "loss": 0.6294, "num_tokens": 235975818.0, "step": 39445 }, { "epoch": 0.4208763189058283, "grad_norm": 1.1014331694663553, "learning_rate": 3.509615887437596e-05, "loss": 0.6237, "num_tokens": 236004032.0, "step": 39450 }, { "epoch": 0.4209296619120267, "grad_norm": 1.0420361268995102, "learning_rate": 3.5092422728372843e-05, "loss": 0.7048, "num_tokens": 236039155.0, "step": 39455 }, { "epoch": 0.42098300491822516, "grad_norm": 0.952292796368432, "learning_rate": 3.508868634610912e-05, "loss": 0.5424, "num_tokens": 236076883.0, "step": 39460 }, { "epoch": 0.4210363479244236, "grad_norm": 0.9311599350456539, "learning_rate": 3.508494972770106e-05, "loss": 0.4717, "num_tokens": 236112331.0, "step": 39465 }, { "epoch": 0.4210896909306221, "grad_norm": 1.8959553873722652, "learning_rate": 3.508121287326495e-05, "loss": 0.5626, "num_tokens": 236133319.0, "step": 39470 }, { "epoch": 0.42114303393682057, "grad_norm": 0.7264824233031583, "learning_rate": 3.5077475782917075e-05, "loss": 0.5401, "num_tokens": 236171614.0, "step": 39475 }, { "epoch": 0.421196376943019, "grad_norm": 0.8866239064655848, "learning_rate": 3.507373845677371e-05, "loss": 0.657, "num_tokens": 236210307.0, "step": 39480 }, { "epoch": 0.42124971994921745, "grad_norm": 0.8570972234362024, "learning_rate": 3.5070000894951154e-05, "loss": 0.5355, "num_tokens": 236232401.0, "step": 39485 }, { "epoch": 0.4213030629554159, "grad_norm": 0.6613417633030642, "learning_rate": 3.506626309756573e-05, "loss": 0.509, "num_tokens": 236265069.0, "step": 39490 }, { "epoch": 0.4213564059616144, "grad_norm": 0.8539967827898227, "learning_rate": 3.506252506473374e-05, "loss": 0.475, "num_tokens": 236289198.0, "step": 39495 }, { "epoch": 0.4214097489678128, "grad_norm": 1.0407315625454123, "learning_rate": 3.50587867965715e-05, "loss": 0.6307, "num_tokens": 236321872.0, "step": 39500 }, { "epoch": 0.4214630919740113, "grad_norm": 0.6184447840192143, "learning_rate": 3.505504829319534e-05, "loss": 0.5804, "num_tokens": 236352800.0, "step": 39505 }, { "epoch": 0.42151643498020974, "grad_norm": 1.0555286796580488, "learning_rate": 3.5051309554721605e-05, "loss": 0.7347, "num_tokens": 236380636.0, "step": 39510 }, { "epoch": 0.4215697779864082, "grad_norm": 0.6602343744030336, "learning_rate": 3.504757058126662e-05, "loss": 0.4092, "num_tokens": 236406794.0, "step": 39515 }, { "epoch": 0.4216231209926067, "grad_norm": 1.9485964848399482, "learning_rate": 3.5043831372946746e-05, "loss": 0.6851, "num_tokens": 236436173.0, "step": 39520 }, { "epoch": 0.4216764639988051, "grad_norm": 1.043865398355275, "learning_rate": 3.5040091929878325e-05, "loss": 0.5626, "num_tokens": 236477620.0, "step": 39525 }, { "epoch": 0.42172980700500357, "grad_norm": 0.6641932359386871, "learning_rate": 3.503635225217774e-05, "loss": 0.5226, "num_tokens": 236508786.0, "step": 39530 }, { "epoch": 0.42178315001120203, "grad_norm": 1.7374977779949812, "learning_rate": 3.503261233996135e-05, "loss": 0.5931, "num_tokens": 236539783.0, "step": 39535 }, { "epoch": 0.4218364930174005, "grad_norm": 0.8870580841112878, "learning_rate": 3.502887219334553e-05, "loss": 0.4384, "num_tokens": 236574044.0, "step": 39540 }, { "epoch": 0.4218898360235989, "grad_norm": 0.9454054604606432, "learning_rate": 3.502513181244669e-05, "loss": 0.5789, "num_tokens": 236619231.0, "step": 39545 }, { "epoch": 0.4219431790297974, "grad_norm": 0.841950811168524, "learning_rate": 3.502139119738119e-05, "loss": 0.4467, "num_tokens": 236651371.0, "step": 39550 }, { "epoch": 0.42199652203599586, "grad_norm": 0.9417627132374743, "learning_rate": 3.501765034826544e-05, "loss": 0.653, "num_tokens": 236673849.0, "step": 39555 }, { "epoch": 0.4220498650421943, "grad_norm": 0.9598435406735129, "learning_rate": 3.501390926521587e-05, "loss": 0.4928, "num_tokens": 236691382.0, "step": 39560 }, { "epoch": 0.4221032080483928, "grad_norm": 0.9106047260430283, "learning_rate": 3.501016794834887e-05, "loss": 0.5152, "num_tokens": 236719340.0, "step": 39565 }, { "epoch": 0.4221565510545912, "grad_norm": 0.8883976285964175, "learning_rate": 3.500642639778087e-05, "loss": 0.5767, "num_tokens": 236755229.0, "step": 39570 }, { "epoch": 0.4222098940607897, "grad_norm": 0.8712710378946567, "learning_rate": 3.5002684613628295e-05, "loss": 0.5437, "num_tokens": 236781541.0, "step": 39575 }, { "epoch": 0.42226323706698815, "grad_norm": 0.8200345294462364, "learning_rate": 3.499894259600759e-05, "loss": 0.5062, "num_tokens": 236837059.0, "step": 39580 }, { "epoch": 0.4223165800731866, "grad_norm": 0.8952488998010024, "learning_rate": 3.49952003450352e-05, "loss": 0.6937, "num_tokens": 236880076.0, "step": 39585 }, { "epoch": 0.42236992307938503, "grad_norm": 0.5268496831666228, "learning_rate": 3.499145786082756e-05, "loss": 0.5926, "num_tokens": 236916953.0, "step": 39590 }, { "epoch": 0.4224232660855835, "grad_norm": 1.555108652832255, "learning_rate": 3.498771514350114e-05, "loss": 0.576, "num_tokens": 236947870.0, "step": 39595 }, { "epoch": 0.422476609091782, "grad_norm": 0.8447861999962455, "learning_rate": 3.498397219317241e-05, "loss": 0.4816, "num_tokens": 236975716.0, "step": 39600 }, { "epoch": 0.42252995209798044, "grad_norm": 1.1064983098501495, "learning_rate": 3.498022900995784e-05, "loss": 0.5016, "num_tokens": 236995152.0, "step": 39605 }, { "epoch": 0.4225832951041789, "grad_norm": 1.4047164775331848, "learning_rate": 3.4976485593973904e-05, "loss": 0.6239, "num_tokens": 237017237.0, "step": 39610 }, { "epoch": 0.4226366381103773, "grad_norm": 1.1052534370512601, "learning_rate": 3.497274194533709e-05, "loss": 0.5031, "num_tokens": 237036026.0, "step": 39615 }, { "epoch": 0.4226899811165758, "grad_norm": 1.1679951385666782, "learning_rate": 3.49689980641639e-05, "loss": 0.4946, "num_tokens": 237058917.0, "step": 39620 }, { "epoch": 0.42274332412277427, "grad_norm": 0.6823721087491831, "learning_rate": 3.496525395057084e-05, "loss": 0.4787, "num_tokens": 237084573.0, "step": 39625 }, { "epoch": 0.42279666712897274, "grad_norm": 0.7546645469622614, "learning_rate": 3.49615096046744e-05, "loss": 0.6149, "num_tokens": 237114515.0, "step": 39630 }, { "epoch": 0.42285001013517115, "grad_norm": 0.8407928296985554, "learning_rate": 3.495776502659111e-05, "loss": 0.4764, "num_tokens": 237145235.0, "step": 39635 }, { "epoch": 0.4229033531413696, "grad_norm": 0.874569677416154, "learning_rate": 3.49540202164375e-05, "loss": 0.6375, "num_tokens": 237178189.0, "step": 39640 }, { "epoch": 0.4229566961475681, "grad_norm": 1.5682039048772927, "learning_rate": 3.4950275174330075e-05, "loss": 0.5649, "num_tokens": 237199393.0, "step": 39645 }, { "epoch": 0.42301003915376656, "grad_norm": 1.1502974976194082, "learning_rate": 3.49465299003854e-05, "loss": 0.596, "num_tokens": 237221856.0, "step": 39650 }, { "epoch": 0.42306338215996503, "grad_norm": 1.4722262056015873, "learning_rate": 3.494278439472001e-05, "loss": 0.6483, "num_tokens": 237240978.0, "step": 39655 }, { "epoch": 0.42311672516616344, "grad_norm": 0.9387235564724189, "learning_rate": 3.4939038657450456e-05, "loss": 0.6228, "num_tokens": 237266173.0, "step": 39660 }, { "epoch": 0.4231700681723619, "grad_norm": 1.0431701544939878, "learning_rate": 3.49352926886933e-05, "loss": 0.8033, "num_tokens": 237296728.0, "step": 39665 }, { "epoch": 0.4232234111785604, "grad_norm": 0.7468563690715402, "learning_rate": 3.493154648856511e-05, "loss": 0.5616, "num_tokens": 237333185.0, "step": 39670 }, { "epoch": 0.42327675418475885, "grad_norm": 1.7263358863059508, "learning_rate": 3.492780005718245e-05, "loss": 0.5747, "num_tokens": 237371688.0, "step": 39675 }, { "epoch": 0.42333009719095727, "grad_norm": 1.2185638204834206, "learning_rate": 3.492405339466192e-05, "loss": 0.6044, "num_tokens": 237394471.0, "step": 39680 }, { "epoch": 0.42338344019715574, "grad_norm": 0.9739133008083123, "learning_rate": 3.4920306501120096e-05, "loss": 0.4702, "num_tokens": 237421144.0, "step": 39685 }, { "epoch": 0.4234367832033542, "grad_norm": 1.2259804079034973, "learning_rate": 3.491655937667357e-05, "loss": 0.568, "num_tokens": 237440644.0, "step": 39690 }, { "epoch": 0.4234901262095527, "grad_norm": 1.337864271548825, "learning_rate": 3.491281202143895e-05, "loss": 0.4823, "num_tokens": 237467706.0, "step": 39695 }, { "epoch": 0.42354346921575114, "grad_norm": 1.2232522985468766, "learning_rate": 3.490906443553285e-05, "loss": 0.5149, "num_tokens": 237495917.0, "step": 39700 }, { "epoch": 0.42359681222194956, "grad_norm": 0.934788308868796, "learning_rate": 3.490531661907188e-05, "loss": 0.4952, "num_tokens": 237536133.0, "step": 39705 }, { "epoch": 0.42365015522814803, "grad_norm": 1.12604717402601, "learning_rate": 3.490156857217267e-05, "loss": 0.5253, "num_tokens": 237553223.0, "step": 39710 }, { "epoch": 0.4237034982343465, "grad_norm": 0.8307174822422472, "learning_rate": 3.489782029495185e-05, "loss": 0.5873, "num_tokens": 237599417.0, "step": 39715 }, { "epoch": 0.42375684124054497, "grad_norm": 1.043484475722864, "learning_rate": 3.489407178752605e-05, "loss": 0.5387, "num_tokens": 237614631.0, "step": 39720 }, { "epoch": 0.4238101842467434, "grad_norm": 0.8374303835007746, "learning_rate": 3.489032305001194e-05, "loss": 0.5703, "num_tokens": 237652302.0, "step": 39725 }, { "epoch": 0.42386352725294185, "grad_norm": 1.7526298237555191, "learning_rate": 3.4886574082526143e-05, "loss": 0.5813, "num_tokens": 237673492.0, "step": 39730 }, { "epoch": 0.4239168702591403, "grad_norm": 1.0768543235153363, "learning_rate": 3.488282488518535e-05, "loss": 0.378, "num_tokens": 237697989.0, "step": 39735 }, { "epoch": 0.4239702132653388, "grad_norm": 1.8874323898658993, "learning_rate": 3.48790754581062e-05, "loss": 0.6413, "num_tokens": 237729191.0, "step": 39740 }, { "epoch": 0.42402355627153726, "grad_norm": 2.3395491805750575, "learning_rate": 3.4875325801405366e-05, "loss": 0.5065, "num_tokens": 237755914.0, "step": 39745 }, { "epoch": 0.4240768992777357, "grad_norm": 1.2144327246805025, "learning_rate": 3.487157591519956e-05, "loss": 0.5382, "num_tokens": 237795267.0, "step": 39750 }, { "epoch": 0.42413024228393414, "grad_norm": 0.7735242490947715, "learning_rate": 3.486782579960545e-05, "loss": 0.4592, "num_tokens": 237825037.0, "step": 39755 }, { "epoch": 0.4241835852901326, "grad_norm": 1.1322611227907258, "learning_rate": 3.486407545473973e-05, "loss": 0.8184, "num_tokens": 237866737.0, "step": 39760 }, { "epoch": 0.4242369282963311, "grad_norm": 0.9155118589175476, "learning_rate": 3.486032488071912e-05, "loss": 0.7232, "num_tokens": 237915691.0, "step": 39765 }, { "epoch": 0.4242902713025295, "grad_norm": 0.6495093513879965, "learning_rate": 3.48565740776603e-05, "loss": 0.4791, "num_tokens": 237970808.0, "step": 39770 }, { "epoch": 0.42434361430872797, "grad_norm": 1.5448864372289903, "learning_rate": 3.4852823045680015e-05, "loss": 0.545, "num_tokens": 237986118.0, "step": 39775 }, { "epoch": 0.42439695731492644, "grad_norm": 1.546456667862509, "learning_rate": 3.4849071784894975e-05, "loss": 0.4675, "num_tokens": 238016758.0, "step": 39780 }, { "epoch": 0.4244503003211249, "grad_norm": 1.78603546444979, "learning_rate": 3.484532029542193e-05, "loss": 0.5306, "num_tokens": 238045451.0, "step": 39785 }, { "epoch": 0.4245036433273234, "grad_norm": 0.8864699014715074, "learning_rate": 3.484156857737759e-05, "loss": 0.5154, "num_tokens": 238073507.0, "step": 39790 }, { "epoch": 0.4245569863335218, "grad_norm": 0.8834290789628892, "learning_rate": 3.483781663087873e-05, "loss": 0.5255, "num_tokens": 238104940.0, "step": 39795 }, { "epoch": 0.42461032933972026, "grad_norm": 0.8961341822238736, "learning_rate": 3.483406445604208e-05, "loss": 0.5283, "num_tokens": 238130749.0, "step": 39800 }, { "epoch": 0.42466367234591873, "grad_norm": 1.0907943209232493, "learning_rate": 3.48303120529844e-05, "loss": 0.4734, "num_tokens": 238148632.0, "step": 39805 }, { "epoch": 0.4247170153521172, "grad_norm": 0.7000998623586646, "learning_rate": 3.482655942182248e-05, "loss": 0.4974, "num_tokens": 238182457.0, "step": 39810 }, { "epoch": 0.4247703583583156, "grad_norm": 1.5623941673934019, "learning_rate": 3.4822806562673075e-05, "loss": 0.5661, "num_tokens": 238211894.0, "step": 39815 }, { "epoch": 0.4248237013645141, "grad_norm": 0.9318528123110862, "learning_rate": 3.4819053475652976e-05, "loss": 0.6015, "num_tokens": 238241138.0, "step": 39820 }, { "epoch": 0.42487704437071255, "grad_norm": 0.7292845301824021, "learning_rate": 3.4815300160878965e-05, "loss": 0.4793, "num_tokens": 238264208.0, "step": 39825 }, { "epoch": 0.424930387376911, "grad_norm": 0.9170683949359159, "learning_rate": 3.481154661846783e-05, "loss": 0.4678, "num_tokens": 238290265.0, "step": 39830 }, { "epoch": 0.4249837303831095, "grad_norm": 1.1126417296090878, "learning_rate": 3.480779284853639e-05, "loss": 0.5291, "num_tokens": 238309617.0, "step": 39835 }, { "epoch": 0.4250370733893079, "grad_norm": 0.9020869572580499, "learning_rate": 3.4804038851201445e-05, "loss": 0.6382, "num_tokens": 238339259.0, "step": 39840 }, { "epoch": 0.4250904163955064, "grad_norm": 0.7837255622610554, "learning_rate": 3.480028462657982e-05, "loss": 0.569, "num_tokens": 238370768.0, "step": 39845 }, { "epoch": 0.42514375940170485, "grad_norm": 0.8244947581873561, "learning_rate": 3.4796530174788325e-05, "loss": 0.6318, "num_tokens": 238399788.0, "step": 39850 }, { "epoch": 0.4251971024079033, "grad_norm": 0.8753270117283752, "learning_rate": 3.47927754959438e-05, "loss": 0.535, "num_tokens": 238426549.0, "step": 39855 }, { "epoch": 0.42525044541410173, "grad_norm": 0.7521026474600574, "learning_rate": 3.478902059016309e-05, "loss": 0.5067, "num_tokens": 238463130.0, "step": 39860 }, { "epoch": 0.4253037884203002, "grad_norm": 0.7930631704719351, "learning_rate": 3.4785265457563015e-05, "loss": 0.5001, "num_tokens": 238499907.0, "step": 39865 }, { "epoch": 0.42535713142649867, "grad_norm": 1.071235443618113, "learning_rate": 3.478151009826045e-05, "loss": 0.571, "num_tokens": 238528457.0, "step": 39870 }, { "epoch": 0.42541047443269714, "grad_norm": 1.790528710054154, "learning_rate": 3.4777754512372254e-05, "loss": 0.6507, "num_tokens": 238552207.0, "step": 39875 }, { "epoch": 0.4254638174388956, "grad_norm": 1.1515507386285213, "learning_rate": 3.477399870001528e-05, "loss": 0.4855, "num_tokens": 238571803.0, "step": 39880 }, { "epoch": 0.425517160445094, "grad_norm": 0.9745963917135597, "learning_rate": 3.4770242661306414e-05, "loss": 0.6082, "num_tokens": 238598741.0, "step": 39885 }, { "epoch": 0.4255705034512925, "grad_norm": 1.0494022529298739, "learning_rate": 3.4766486396362523e-05, "loss": 0.5735, "num_tokens": 238634785.0, "step": 39890 }, { "epoch": 0.42562384645749096, "grad_norm": 0.756540638513643, "learning_rate": 3.4762729905300504e-05, "loss": 0.6929, "num_tokens": 238672409.0, "step": 39895 }, { "epoch": 0.42567718946368943, "grad_norm": 0.5969002544571412, "learning_rate": 3.4758973188237246e-05, "loss": 0.4864, "num_tokens": 238708170.0, "step": 39900 }, { "epoch": 0.42573053246988785, "grad_norm": 0.7960075853040938, "learning_rate": 3.4755216245289655e-05, "loss": 0.6048, "num_tokens": 238739258.0, "step": 39905 }, { "epoch": 0.4257838754760863, "grad_norm": 0.9167558393006734, "learning_rate": 3.475145907657464e-05, "loss": 0.5692, "num_tokens": 238770940.0, "step": 39910 }, { "epoch": 0.4258372184822848, "grad_norm": 0.876253938559794, "learning_rate": 3.474770168220911e-05, "loss": 0.5673, "num_tokens": 238797165.0, "step": 39915 }, { "epoch": 0.42589056148848325, "grad_norm": 0.9065782461354989, "learning_rate": 3.474394406230999e-05, "loss": 0.6446, "num_tokens": 238831408.0, "step": 39920 }, { "epoch": 0.4259439044946817, "grad_norm": 0.9137495376313861, "learning_rate": 3.4740186216994206e-05, "loss": 0.6514, "num_tokens": 238868433.0, "step": 39925 }, { "epoch": 0.42599724750088014, "grad_norm": 0.8543404312344124, "learning_rate": 3.4736428146378716e-05, "loss": 0.5591, "num_tokens": 238899511.0, "step": 39930 }, { "epoch": 0.4260505905070786, "grad_norm": 0.9559150954485423, "learning_rate": 3.473266985058043e-05, "loss": 0.521, "num_tokens": 238917758.0, "step": 39935 }, { "epoch": 0.4261039335132771, "grad_norm": 0.780227872959552, "learning_rate": 3.472891132971631e-05, "loss": 0.4555, "num_tokens": 238947139.0, "step": 39940 }, { "epoch": 0.42615727651947555, "grad_norm": 1.1155227678816109, "learning_rate": 3.4725152583903334e-05, "loss": 0.5977, "num_tokens": 238983752.0, "step": 39945 }, { "epoch": 0.42621061952567396, "grad_norm": 2.7667974383203013, "learning_rate": 3.4721393613258444e-05, "loss": 0.5438, "num_tokens": 239006070.0, "step": 39950 }, { "epoch": 0.42626396253187243, "grad_norm": 0.944146035940159, "learning_rate": 3.471763441789861e-05, "loss": 0.5392, "num_tokens": 239041531.0, "step": 39955 }, { "epoch": 0.4263173055380709, "grad_norm": 0.7902655270633969, "learning_rate": 3.4713874997940834e-05, "loss": 0.544, "num_tokens": 239076624.0, "step": 39960 }, { "epoch": 0.42637064854426937, "grad_norm": 0.9134521476030104, "learning_rate": 3.471011535350208e-05, "loss": 0.5897, "num_tokens": 239116146.0, "step": 39965 }, { "epoch": 0.42642399155046784, "grad_norm": 0.7777156598270396, "learning_rate": 3.470635548469934e-05, "loss": 0.493, "num_tokens": 239138987.0, "step": 39970 }, { "epoch": 0.42647733455666625, "grad_norm": 1.3543949465467289, "learning_rate": 3.4702595391649625e-05, "loss": 0.5041, "num_tokens": 239156915.0, "step": 39975 }, { "epoch": 0.4265306775628647, "grad_norm": 1.3717288050454965, "learning_rate": 3.4698835074469934e-05, "loss": 0.4784, "num_tokens": 239177654.0, "step": 39980 }, { "epoch": 0.4265840205690632, "grad_norm": 1.4507443701238993, "learning_rate": 3.469507453327728e-05, "loss": 0.5699, "num_tokens": 239202852.0, "step": 39985 }, { "epoch": 0.42663736357526166, "grad_norm": 1.3027005331973114, "learning_rate": 3.469131376818869e-05, "loss": 0.5101, "num_tokens": 239220836.0, "step": 39990 }, { "epoch": 0.4266907065814601, "grad_norm": 0.9655919251464128, "learning_rate": 3.468755277932119e-05, "loss": 0.6144, "num_tokens": 239247560.0, "step": 39995 }, { "epoch": 0.42674404958765855, "grad_norm": 0.9271788463119489, "learning_rate": 3.46837915667918e-05, "loss": 0.4852, "num_tokens": 239271145.0, "step": 40000 }, { "epoch": 0.426797392593857, "grad_norm": 0.7935602365057127, "learning_rate": 3.468003013071758e-05, "loss": 0.5219, "num_tokens": 239297296.0, "step": 40005 }, { "epoch": 0.4268507356000555, "grad_norm": 0.9336521770541875, "learning_rate": 3.4676268471215567e-05, "loss": 0.5553, "num_tokens": 239336000.0, "step": 40010 }, { "epoch": 0.42690407860625396, "grad_norm": 0.6295572905494577, "learning_rate": 3.467250658840282e-05, "loss": 0.7169, "num_tokens": 239359369.0, "step": 40015 }, { "epoch": 0.42695742161245237, "grad_norm": 0.9677076771719403, "learning_rate": 3.4668744482396406e-05, "loss": 0.6551, "num_tokens": 239397046.0, "step": 40020 }, { "epoch": 0.42701076461865084, "grad_norm": 1.0966316977684063, "learning_rate": 3.466498215331339e-05, "loss": 0.4901, "num_tokens": 239413052.0, "step": 40025 }, { "epoch": 0.4270641076248493, "grad_norm": 0.8452752194145324, "learning_rate": 3.4661219601270835e-05, "loss": 0.5567, "num_tokens": 239451670.0, "step": 40030 }, { "epoch": 0.4271174506310478, "grad_norm": 0.8492027979053393, "learning_rate": 3.4657456826385846e-05, "loss": 0.4443, "num_tokens": 239476382.0, "step": 40035 }, { "epoch": 0.4271707936372462, "grad_norm": 0.6615442613231017, "learning_rate": 3.46536938287755e-05, "loss": 0.5588, "num_tokens": 239516468.0, "step": 40040 }, { "epoch": 0.42722413664344466, "grad_norm": 0.8644990542637967, "learning_rate": 3.464993060855689e-05, "loss": 0.4475, "num_tokens": 239541201.0, "step": 40045 }, { "epoch": 0.42727747964964313, "grad_norm": 0.8132728751652697, "learning_rate": 3.464616716584713e-05, "loss": 0.5357, "num_tokens": 239574307.0, "step": 40050 }, { "epoch": 0.4273308226558416, "grad_norm": 1.0440041589138995, "learning_rate": 3.464240350076333e-05, "loss": 0.6018, "num_tokens": 239609778.0, "step": 40055 }, { "epoch": 0.42738416566204007, "grad_norm": 0.941252794931178, "learning_rate": 3.46386396134226e-05, "loss": 0.5914, "num_tokens": 239647243.0, "step": 40060 }, { "epoch": 0.4274375086682385, "grad_norm": 1.051440413760194, "learning_rate": 3.463487550394207e-05, "loss": 0.5091, "num_tokens": 239666595.0, "step": 40065 }, { "epoch": 0.42749085167443696, "grad_norm": 0.6594776540182932, "learning_rate": 3.463111117243887e-05, "loss": 0.5346, "num_tokens": 239720497.0, "step": 40070 }, { "epoch": 0.4275441946806354, "grad_norm": 1.6612412151842215, "learning_rate": 3.462734661903014e-05, "loss": 0.5287, "num_tokens": 239737731.0, "step": 40075 }, { "epoch": 0.4275975376868339, "grad_norm": 0.9030544946756677, "learning_rate": 3.462358184383302e-05, "loss": 0.6168, "num_tokens": 239771501.0, "step": 40080 }, { "epoch": 0.4276508806930323, "grad_norm": 0.9515058414621396, "learning_rate": 3.461981684696467e-05, "loss": 0.6801, "num_tokens": 239827786.0, "step": 40085 }, { "epoch": 0.4277042236992308, "grad_norm": 1.205257498840834, "learning_rate": 3.4616051628542237e-05, "loss": 0.502, "num_tokens": 239844077.0, "step": 40090 }, { "epoch": 0.42775756670542925, "grad_norm": 0.9586295039813553, "learning_rate": 3.46122861886829e-05, "loss": 0.5482, "num_tokens": 239870317.0, "step": 40095 }, { "epoch": 0.4278109097116277, "grad_norm": 1.1134553006593488, "learning_rate": 3.460852052750382e-05, "loss": 0.5655, "num_tokens": 239893314.0, "step": 40100 }, { "epoch": 0.4278642527178262, "grad_norm": 1.0651238934354854, "learning_rate": 3.4604754645122185e-05, "loss": 0.679, "num_tokens": 239931901.0, "step": 40105 }, { "epoch": 0.4279175957240246, "grad_norm": 0.7905406993195477, "learning_rate": 3.4600988541655184e-05, "loss": 0.6425, "num_tokens": 239963934.0, "step": 40110 }, { "epoch": 0.42797093873022307, "grad_norm": 3.446740014867732, "learning_rate": 3.459722221722e-05, "loss": 0.5359, "num_tokens": 239982179.0, "step": 40115 }, { "epoch": 0.42802428173642154, "grad_norm": 0.8860338593156368, "learning_rate": 3.4593455671933846e-05, "loss": 0.8935, "num_tokens": 240008382.0, "step": 40120 }, { "epoch": 0.42807762474262, "grad_norm": 0.9274023392915768, "learning_rate": 3.4589688905913906e-05, "loss": 0.5718, "num_tokens": 240029656.0, "step": 40125 }, { "epoch": 0.4281309677488184, "grad_norm": 0.7723006236596016, "learning_rate": 3.4585921919277425e-05, "loss": 0.4917, "num_tokens": 240063920.0, "step": 40130 }, { "epoch": 0.4281843107550169, "grad_norm": 1.1273291275667594, "learning_rate": 3.45821547121416e-05, "loss": 0.5934, "num_tokens": 240086463.0, "step": 40135 }, { "epoch": 0.42823765376121536, "grad_norm": 0.723011613821836, "learning_rate": 3.4578387284623675e-05, "loss": 0.6459, "num_tokens": 240114491.0, "step": 40140 }, { "epoch": 0.42829099676741383, "grad_norm": 1.3614923272780746, "learning_rate": 3.457461963684087e-05, "loss": 0.5329, "num_tokens": 240139334.0, "step": 40145 }, { "epoch": 0.4283443397736123, "grad_norm": 0.7731104243709114, "learning_rate": 3.457085176891044e-05, "loss": 0.4497, "num_tokens": 240173424.0, "step": 40150 }, { "epoch": 0.4283976827798107, "grad_norm": 1.1504858320366165, "learning_rate": 3.4567083680949624e-05, "loss": 0.5348, "num_tokens": 240197423.0, "step": 40155 }, { "epoch": 0.4284510257860092, "grad_norm": 1.0766637912978219, "learning_rate": 3.456331537307568e-05, "loss": 0.5594, "num_tokens": 240226147.0, "step": 40160 }, { "epoch": 0.42850436879220766, "grad_norm": 1.1765801949899968, "learning_rate": 3.455954684540587e-05, "loss": 0.4726, "num_tokens": 240253633.0, "step": 40165 }, { "epoch": 0.4285577117984061, "grad_norm": 0.6225974531859956, "learning_rate": 3.455577809805746e-05, "loss": 0.4536, "num_tokens": 240279483.0, "step": 40170 }, { "epoch": 0.42861105480460454, "grad_norm": 1.803878466218633, "learning_rate": 3.4552009131147726e-05, "loss": 0.5427, "num_tokens": 240312069.0, "step": 40175 }, { "epoch": 0.428664397810803, "grad_norm": 1.186661091952428, "learning_rate": 3.454823994479396e-05, "loss": 0.5914, "num_tokens": 240348129.0, "step": 40180 }, { "epoch": 0.4287177408170015, "grad_norm": 1.5564925849870865, "learning_rate": 3.454447053911345e-05, "loss": 0.5389, "num_tokens": 240374931.0, "step": 40185 }, { "epoch": 0.42877108382319995, "grad_norm": 4.440486391783664, "learning_rate": 3.4540700914223476e-05, "loss": 0.6528, "num_tokens": 240408851.0, "step": 40190 }, { "epoch": 0.4288244268293984, "grad_norm": 1.173924174536062, "learning_rate": 3.4536931070241355e-05, "loss": 0.6322, "num_tokens": 240440586.0, "step": 40195 }, { "epoch": 0.42887776983559683, "grad_norm": 1.1703175232886616, "learning_rate": 3.453316100728439e-05, "loss": 0.6518, "num_tokens": 240460682.0, "step": 40200 }, { "epoch": 0.4289311128417953, "grad_norm": 0.8441221158885698, "learning_rate": 3.4529390725469904e-05, "loss": 0.5727, "num_tokens": 240477706.0, "step": 40205 }, { "epoch": 0.4289844558479938, "grad_norm": 0.9208980258040881, "learning_rate": 3.4525620224915215e-05, "loss": 0.531, "num_tokens": 240515850.0, "step": 40210 }, { "epoch": 0.42903779885419224, "grad_norm": 0.8690463375739002, "learning_rate": 3.452184950573766e-05, "loss": 0.4851, "num_tokens": 240538459.0, "step": 40215 }, { "epoch": 0.42909114186039066, "grad_norm": 0.8142652546358458, "learning_rate": 3.451807856805457e-05, "loss": 0.6509, "num_tokens": 240568140.0, "step": 40220 }, { "epoch": 0.4291444848665891, "grad_norm": 1.5952459611253986, "learning_rate": 3.4514307411983295e-05, "loss": 0.6777, "num_tokens": 240593519.0, "step": 40225 }, { "epoch": 0.4291978278727876, "grad_norm": 1.081421479666013, "learning_rate": 3.4510536037641175e-05, "loss": 0.5948, "num_tokens": 240630403.0, "step": 40230 }, { "epoch": 0.42925117087898607, "grad_norm": 0.9027688012099984, "learning_rate": 3.450676444514557e-05, "loss": 0.5573, "num_tokens": 240657985.0, "step": 40235 }, { "epoch": 0.42930451388518454, "grad_norm": 0.8797675082940439, "learning_rate": 3.4502992634613865e-05, "loss": 0.5038, "num_tokens": 240686771.0, "step": 40240 }, { "epoch": 0.42935785689138295, "grad_norm": 0.5660308347945068, "learning_rate": 3.44992206061634e-05, "loss": 0.5631, "num_tokens": 240718194.0, "step": 40245 }, { "epoch": 0.4294111998975814, "grad_norm": 1.34943222520886, "learning_rate": 3.449544835991156e-05, "loss": 0.5206, "num_tokens": 240739124.0, "step": 40250 }, { "epoch": 0.4294645429037799, "grad_norm": 1.1609622043564134, "learning_rate": 3.449167589597574e-05, "loss": 0.4938, "num_tokens": 240758798.0, "step": 40255 }, { "epoch": 0.42951788590997836, "grad_norm": 0.6607514664624738, "learning_rate": 3.4487903214473344e-05, "loss": 0.45, "num_tokens": 240788201.0, "step": 40260 }, { "epoch": 0.4295712289161768, "grad_norm": 0.9506072271391041, "learning_rate": 3.448413031552174e-05, "loss": 0.4634, "num_tokens": 240807603.0, "step": 40265 }, { "epoch": 0.42962457192237524, "grad_norm": 0.6212416114525532, "learning_rate": 3.448035719923834e-05, "loss": 0.6257, "num_tokens": 240843354.0, "step": 40270 }, { "epoch": 0.4296779149285737, "grad_norm": 0.8658143396061156, "learning_rate": 3.447658386574057e-05, "loss": 0.6166, "num_tokens": 240874255.0, "step": 40275 }, { "epoch": 0.4297312579347722, "grad_norm": 1.019866234070865, "learning_rate": 3.4472810315145845e-05, "loss": 0.4955, "num_tokens": 240891940.0, "step": 40280 }, { "epoch": 0.42978460094097065, "grad_norm": 0.8239926168699814, "learning_rate": 3.4469036547571574e-05, "loss": 0.6584, "num_tokens": 240931124.0, "step": 40285 }, { "epoch": 0.42983794394716907, "grad_norm": 1.1316366963452629, "learning_rate": 3.446526256313521e-05, "loss": 0.6723, "num_tokens": 240959956.0, "step": 40290 }, { "epoch": 0.42989128695336754, "grad_norm": 0.8413870725487413, "learning_rate": 3.446148836195418e-05, "loss": 0.5001, "num_tokens": 240980878.0, "step": 40295 }, { "epoch": 0.429944629959566, "grad_norm": 1.2156451664933203, "learning_rate": 3.445771394414593e-05, "loss": 0.5121, "num_tokens": 241004375.0, "step": 40300 }, { "epoch": 0.4299979729657645, "grad_norm": 1.5641358663430307, "learning_rate": 3.4453939309827914e-05, "loss": 0.6159, "num_tokens": 241028427.0, "step": 40305 }, { "epoch": 0.4300513159719629, "grad_norm": 1.7189003157406126, "learning_rate": 3.445016445911759e-05, "loss": 0.5861, "num_tokens": 241068522.0, "step": 40310 }, { "epoch": 0.43010465897816136, "grad_norm": 1.0748418118279948, "learning_rate": 3.444638939213243e-05, "loss": 0.5904, "num_tokens": 241093826.0, "step": 40315 }, { "epoch": 0.43015800198435983, "grad_norm": 0.9329786481580923, "learning_rate": 3.44426141089899e-05, "loss": 0.5875, "num_tokens": 241114261.0, "step": 40320 }, { "epoch": 0.4302113449905583, "grad_norm": 0.6703536253166029, "learning_rate": 3.443883860980747e-05, "loss": 0.459, "num_tokens": 241144940.0, "step": 40325 }, { "epoch": 0.43026468799675677, "grad_norm": 0.8028605086195033, "learning_rate": 3.443506289470264e-05, "loss": 0.5626, "num_tokens": 241181460.0, "step": 40330 }, { "epoch": 0.4303180310029552, "grad_norm": 1.0791606607685138, "learning_rate": 3.44312869637929e-05, "loss": 0.5154, "num_tokens": 241212566.0, "step": 40335 }, { "epoch": 0.43037137400915365, "grad_norm": 1.4663254935799557, "learning_rate": 3.442751081719574e-05, "loss": 0.6449, "num_tokens": 241245611.0, "step": 40340 }, { "epoch": 0.4304247170153521, "grad_norm": 1.075279891306716, "learning_rate": 3.442373445502868e-05, "loss": 0.5672, "num_tokens": 241276663.0, "step": 40345 }, { "epoch": 0.4304780600215506, "grad_norm": 1.0164199855358496, "learning_rate": 3.4419957877409224e-05, "loss": 0.5279, "num_tokens": 241301694.0, "step": 40350 }, { "epoch": 0.430531403027749, "grad_norm": 1.0241014631949714, "learning_rate": 3.441618108445488e-05, "loss": 0.5765, "num_tokens": 241319957.0, "step": 40355 }, { "epoch": 0.4305847460339475, "grad_norm": 1.5632528603378104, "learning_rate": 3.4412404076283205e-05, "loss": 0.5716, "num_tokens": 241349886.0, "step": 40360 }, { "epoch": 0.43063808904014594, "grad_norm": 0.9844171487999857, "learning_rate": 3.440862685301171e-05, "loss": 0.4332, "num_tokens": 241372455.0, "step": 40365 }, { "epoch": 0.4306914320463444, "grad_norm": 0.877770817190704, "learning_rate": 3.4404849414757936e-05, "loss": 0.5481, "num_tokens": 241410267.0, "step": 40370 }, { "epoch": 0.4307447750525429, "grad_norm": 1.6281063630942396, "learning_rate": 3.440107176163943e-05, "loss": 0.6152, "num_tokens": 241426686.0, "step": 40375 }, { "epoch": 0.4307981180587413, "grad_norm": 0.967653252957769, "learning_rate": 3.439729389377375e-05, "loss": 0.5564, "num_tokens": 241451236.0, "step": 40380 }, { "epoch": 0.43085146106493977, "grad_norm": 2.602283008243241, "learning_rate": 3.439351581127844e-05, "loss": 0.5643, "num_tokens": 241476669.0, "step": 40385 }, { "epoch": 0.43090480407113824, "grad_norm": 1.1621762881007511, "learning_rate": 3.4389737514271095e-05, "loss": 0.4191, "num_tokens": 241510896.0, "step": 40390 }, { "epoch": 0.4309581470773367, "grad_norm": 0.7973814525665243, "learning_rate": 3.438595900286926e-05, "loss": 0.5923, "num_tokens": 241559330.0, "step": 40395 }, { "epoch": 0.4310114900835351, "grad_norm": 0.7816146387238903, "learning_rate": 3.438218027719052e-05, "loss": 0.5554, "num_tokens": 241585355.0, "step": 40400 }, { "epoch": 0.4310648330897336, "grad_norm": 1.7488256865583398, "learning_rate": 3.437840133735248e-05, "loss": 0.6344, "num_tokens": 241623425.0, "step": 40405 }, { "epoch": 0.43111817609593206, "grad_norm": 0.7194462926795486, "learning_rate": 3.437462218347272e-05, "loss": 0.5592, "num_tokens": 241652298.0, "step": 40410 }, { "epoch": 0.43117151910213053, "grad_norm": 1.2368977461351023, "learning_rate": 3.4370842815668816e-05, "loss": 0.4281, "num_tokens": 241678236.0, "step": 40415 }, { "epoch": 0.431224862108329, "grad_norm": 0.9673094152437376, "learning_rate": 3.4367063234058416e-05, "loss": 0.5486, "num_tokens": 241709353.0, "step": 40420 }, { "epoch": 0.4312782051145274, "grad_norm": 1.4336961786100253, "learning_rate": 3.4363283438759106e-05, "loss": 0.6263, "num_tokens": 241735256.0, "step": 40425 }, { "epoch": 0.4313315481207259, "grad_norm": 0.9470371550053595, "learning_rate": 3.435950342988851e-05, "loss": 0.6103, "num_tokens": 241776427.0, "step": 40430 }, { "epoch": 0.43138489112692435, "grad_norm": 1.05226923531423, "learning_rate": 3.435572320756427e-05, "loss": 0.592, "num_tokens": 241804762.0, "step": 40435 }, { "epoch": 0.4314382341331228, "grad_norm": 0.8855236320004106, "learning_rate": 3.4351942771904e-05, "loss": 0.4132, "num_tokens": 241820622.0, "step": 40440 }, { "epoch": 0.43149157713932124, "grad_norm": 1.1564025270613336, "learning_rate": 3.4348162123025336e-05, "loss": 0.6514, "num_tokens": 241848409.0, "step": 40445 }, { "epoch": 0.4315449201455197, "grad_norm": 1.5892336673410064, "learning_rate": 3.434438126104594e-05, "loss": 0.6362, "num_tokens": 241871436.0, "step": 40450 }, { "epoch": 0.4315982631517182, "grad_norm": 0.8345000469333244, "learning_rate": 3.434060018608346e-05, "loss": 0.4712, "num_tokens": 241900811.0, "step": 40455 }, { "epoch": 0.43165160615791665, "grad_norm": 1.127537610680469, "learning_rate": 3.433681889825555e-05, "loss": 0.5371, "num_tokens": 241923398.0, "step": 40460 }, { "epoch": 0.4317049491641151, "grad_norm": 0.5772262856632193, "learning_rate": 3.433303739767989e-05, "loss": 0.5947, "num_tokens": 241959470.0, "step": 40465 }, { "epoch": 0.43175829217031353, "grad_norm": 0.7686804588791253, "learning_rate": 3.4329255684474125e-05, "loss": 0.5776, "num_tokens": 242001665.0, "step": 40470 }, { "epoch": 0.431811635176512, "grad_norm": 1.2801180069758384, "learning_rate": 3.432547375875596e-05, "loss": 0.5907, "num_tokens": 242022279.0, "step": 40475 }, { "epoch": 0.43186497818271047, "grad_norm": 1.558025688662108, "learning_rate": 3.432169162064307e-05, "loss": 0.4969, "num_tokens": 242034289.0, "step": 40480 }, { "epoch": 0.43191832118890894, "grad_norm": 0.9566887436961611, "learning_rate": 3.431790927025314e-05, "loss": 0.6928, "num_tokens": 242060858.0, "step": 40485 }, { "epoch": 0.43197166419510735, "grad_norm": 1.4627017582302, "learning_rate": 3.431412670770389e-05, "loss": 0.5295, "num_tokens": 242087480.0, "step": 40490 }, { "epoch": 0.4320250072013058, "grad_norm": 1.5442168320843785, "learning_rate": 3.4310343933113016e-05, "loss": 0.6572, "num_tokens": 242119992.0, "step": 40495 }, { "epoch": 0.4320783502075043, "grad_norm": 1.1711820042388734, "learning_rate": 3.430656094659822e-05, "loss": 0.5338, "num_tokens": 242169385.0, "step": 40500 }, { "epoch": 0.43213169321370276, "grad_norm": 1.2864595176338476, "learning_rate": 3.430277774827723e-05, "loss": 0.4987, "num_tokens": 242199203.0, "step": 40505 }, { "epoch": 0.43218503621990123, "grad_norm": 1.17313468673699, "learning_rate": 3.429899433826777e-05, "loss": 0.4319, "num_tokens": 242223763.0, "step": 40510 }, { "epoch": 0.43223837922609964, "grad_norm": 0.8469729643572436, "learning_rate": 3.429521071668758e-05, "loss": 0.4882, "num_tokens": 242252035.0, "step": 40515 }, { "epoch": 0.4322917222322981, "grad_norm": 1.0685031355055425, "learning_rate": 3.429142688365437e-05, "loss": 0.5229, "num_tokens": 242286640.0, "step": 40520 }, { "epoch": 0.4323450652384966, "grad_norm": 0.9371734724375551, "learning_rate": 3.4287642839285925e-05, "loss": 0.4562, "num_tokens": 242312355.0, "step": 40525 }, { "epoch": 0.43239840824469505, "grad_norm": 0.8373099864532314, "learning_rate": 3.428385858369996e-05, "loss": 0.6911, "num_tokens": 242349190.0, "step": 40530 }, { "epoch": 0.43245175125089347, "grad_norm": 0.8729986036458238, "learning_rate": 3.428007411701427e-05, "loss": 0.4698, "num_tokens": 242380443.0, "step": 40535 }, { "epoch": 0.43250509425709194, "grad_norm": 0.6793323472527674, "learning_rate": 3.427628943934659e-05, "loss": 0.6058, "num_tokens": 242420916.0, "step": 40540 }, { "epoch": 0.4325584372632904, "grad_norm": 0.7149832262969342, "learning_rate": 3.42725045508147e-05, "loss": 0.7124, "num_tokens": 242443125.0, "step": 40545 }, { "epoch": 0.4326117802694889, "grad_norm": 0.8693436244280681, "learning_rate": 3.4268719451536376e-05, "loss": 0.5412, "num_tokens": 242470202.0, "step": 40550 }, { "epoch": 0.43266512327568735, "grad_norm": 1.010019844144182, "learning_rate": 3.4264934141629415e-05, "loss": 0.4606, "num_tokens": 242489468.0, "step": 40555 }, { "epoch": 0.43271846628188576, "grad_norm": 0.830862880215163, "learning_rate": 3.426114862121159e-05, "loss": 0.5995, "num_tokens": 242532270.0, "step": 40560 }, { "epoch": 0.43277180928808423, "grad_norm": 1.193012223082156, "learning_rate": 3.425736289040071e-05, "loss": 0.7429, "num_tokens": 242558001.0, "step": 40565 }, { "epoch": 0.4328251522942827, "grad_norm": 1.4322596233214844, "learning_rate": 3.425357694931459e-05, "loss": 0.6602, "num_tokens": 242594610.0, "step": 40570 }, { "epoch": 0.43287849530048117, "grad_norm": 0.7944186481881693, "learning_rate": 3.424979079807101e-05, "loss": 0.5266, "num_tokens": 242614166.0, "step": 40575 }, { "epoch": 0.4329318383066796, "grad_norm": 2.685486539534635, "learning_rate": 3.4246004436787814e-05, "loss": 0.5318, "num_tokens": 242644336.0, "step": 40580 }, { "epoch": 0.43298518131287805, "grad_norm": 0.9308979089620439, "learning_rate": 3.424221786558282e-05, "loss": 0.5778, "num_tokens": 242681739.0, "step": 40585 }, { "epoch": 0.4330385243190765, "grad_norm": 1.3796874222784923, "learning_rate": 3.4238431084573847e-05, "loss": 0.5609, "num_tokens": 242712762.0, "step": 40590 }, { "epoch": 0.433091867325275, "grad_norm": 0.6049709320250817, "learning_rate": 3.4234644093878735e-05, "loss": 0.4527, "num_tokens": 242752830.0, "step": 40595 }, { "epoch": 0.43314521033147346, "grad_norm": 1.0919378573455338, "learning_rate": 3.4230856893615345e-05, "loss": 0.5106, "num_tokens": 242785359.0, "step": 40600 }, { "epoch": 0.4331985533376719, "grad_norm": 1.105602241444488, "learning_rate": 3.422706948390151e-05, "loss": 0.5439, "num_tokens": 242805502.0, "step": 40605 }, { "epoch": 0.43325189634387035, "grad_norm": 0.9782387792079025, "learning_rate": 3.4223281864855086e-05, "loss": 0.4551, "num_tokens": 242833048.0, "step": 40610 }, { "epoch": 0.4333052393500688, "grad_norm": 0.7892909688418668, "learning_rate": 3.421949403659394e-05, "loss": 0.4812, "num_tokens": 242855657.0, "step": 40615 }, { "epoch": 0.4333585823562673, "grad_norm": 0.8035287782817286, "learning_rate": 3.421570599923595e-05, "loss": 0.4724, "num_tokens": 242886756.0, "step": 40620 }, { "epoch": 0.4334119253624657, "grad_norm": 1.0656697998934306, "learning_rate": 3.421191775289898e-05, "loss": 0.4883, "num_tokens": 242907627.0, "step": 40625 }, { "epoch": 0.43346526836866417, "grad_norm": 0.9121142443388222, "learning_rate": 3.420812929770091e-05, "loss": 0.7266, "num_tokens": 242938107.0, "step": 40630 }, { "epoch": 0.43351861137486264, "grad_norm": 0.7819751442829589, "learning_rate": 3.420434063375964e-05, "loss": 0.5316, "num_tokens": 242968898.0, "step": 40635 }, { "epoch": 0.4335719543810611, "grad_norm": 0.6904256558769131, "learning_rate": 3.420055176119307e-05, "loss": 0.5643, "num_tokens": 242992742.0, "step": 40640 }, { "epoch": 0.4336252973872596, "grad_norm": 1.121190443431501, "learning_rate": 3.4196762680119074e-05, "loss": 0.7218, "num_tokens": 243007884.0, "step": 40645 }, { "epoch": 0.433678640393458, "grad_norm": 1.4249435999882756, "learning_rate": 3.419297339065559e-05, "loss": 0.743, "num_tokens": 243039435.0, "step": 40650 }, { "epoch": 0.43373198339965646, "grad_norm": 0.9289957253465265, "learning_rate": 3.418918389292052e-05, "loss": 0.5676, "num_tokens": 243078855.0, "step": 40655 }, { "epoch": 0.43378532640585493, "grad_norm": 1.4288841130141248, "learning_rate": 3.41853941870318e-05, "loss": 0.4991, "num_tokens": 243100901.0, "step": 40660 }, { "epoch": 0.4338386694120534, "grad_norm": 0.7688306727994692, "learning_rate": 3.418160427310732e-05, "loss": 0.7064, "num_tokens": 243147705.0, "step": 40665 }, { "epoch": 0.4338920124182518, "grad_norm": 0.7614378794167286, "learning_rate": 3.4177814151265056e-05, "loss": 0.8249, "num_tokens": 243191294.0, "step": 40670 }, { "epoch": 0.4339453554244503, "grad_norm": 0.8145376714923438, "learning_rate": 3.4174023821622926e-05, "loss": 0.5311, "num_tokens": 243236698.0, "step": 40675 }, { "epoch": 0.43399869843064875, "grad_norm": 0.8950313275184408, "learning_rate": 3.417023328429888e-05, "loss": 0.6677, "num_tokens": 243267622.0, "step": 40680 }, { "epoch": 0.4340520414368472, "grad_norm": 0.9043093652254935, "learning_rate": 3.416644253941088e-05, "loss": 0.4493, "num_tokens": 243307358.0, "step": 40685 }, { "epoch": 0.4341053844430457, "grad_norm": 1.053751033955633, "learning_rate": 3.4162651587076886e-05, "loss": 0.6057, "num_tokens": 243341827.0, "step": 40690 }, { "epoch": 0.4341587274492441, "grad_norm": 0.9421135169197647, "learning_rate": 3.4158860427414865e-05, "loss": 0.5224, "num_tokens": 243365633.0, "step": 40695 }, { "epoch": 0.4342120704554426, "grad_norm": 1.1199795527588132, "learning_rate": 3.4155069060542774e-05, "loss": 0.5368, "num_tokens": 243384760.0, "step": 40700 }, { "epoch": 0.43426541346164105, "grad_norm": 1.033580228818119, "learning_rate": 3.41512774865786e-05, "loss": 0.5798, "num_tokens": 243431039.0, "step": 40705 }, { "epoch": 0.4343187564678395, "grad_norm": 0.9403733385805614, "learning_rate": 3.414748570564034e-05, "loss": 0.5309, "num_tokens": 243464765.0, "step": 40710 }, { "epoch": 0.43437209947403793, "grad_norm": 1.0051419540607274, "learning_rate": 3.414369371784598e-05, "loss": 0.5565, "num_tokens": 243491130.0, "step": 40715 }, { "epoch": 0.4344254424802364, "grad_norm": 0.8259578663361618, "learning_rate": 3.4139901523313514e-05, "loss": 0.6158, "num_tokens": 243509886.0, "step": 40720 }, { "epoch": 0.43447878548643487, "grad_norm": 0.6335571103574847, "learning_rate": 3.413610912216095e-05, "loss": 0.5084, "num_tokens": 243531930.0, "step": 40725 }, { "epoch": 0.43453212849263334, "grad_norm": 0.6494475062360404, "learning_rate": 3.4132316514506314e-05, "loss": 0.5649, "num_tokens": 243564647.0, "step": 40730 }, { "epoch": 0.4345854714988318, "grad_norm": 0.8656446573576871, "learning_rate": 3.4128523700467604e-05, "loss": 0.6909, "num_tokens": 243597579.0, "step": 40735 }, { "epoch": 0.4346388145050302, "grad_norm": 1.1237975474952366, "learning_rate": 3.412473068016284e-05, "loss": 0.5038, "num_tokens": 243623591.0, "step": 40740 }, { "epoch": 0.4346921575112287, "grad_norm": 0.6441539123896521, "learning_rate": 3.412093745371007e-05, "loss": 0.6387, "num_tokens": 243656499.0, "step": 40745 }, { "epoch": 0.43474550051742716, "grad_norm": 0.8590278849989561, "learning_rate": 3.411714402122734e-05, "loss": 0.4918, "num_tokens": 243701773.0, "step": 40750 }, { "epoch": 0.43479884352362563, "grad_norm": 1.2720909728834982, "learning_rate": 3.411335038283266e-05, "loss": 0.5989, "num_tokens": 243721137.0, "step": 40755 }, { "epoch": 0.43485218652982405, "grad_norm": 0.8674562226243308, "learning_rate": 3.4109556538644124e-05, "loss": 0.4646, "num_tokens": 243750485.0, "step": 40760 }, { "epoch": 0.4349055295360225, "grad_norm": 1.0191911054341938, "learning_rate": 3.410576248877975e-05, "loss": 0.5486, "num_tokens": 243773962.0, "step": 40765 }, { "epoch": 0.434958872542221, "grad_norm": 0.6967500032686311, "learning_rate": 3.4101968233357617e-05, "loss": 0.5547, "num_tokens": 243819956.0, "step": 40770 }, { "epoch": 0.43501221554841946, "grad_norm": 1.2264326477692133, "learning_rate": 3.4098173772495794e-05, "loss": 0.436, "num_tokens": 243840685.0, "step": 40775 }, { "epoch": 0.4350655585546179, "grad_norm": 0.8463075307003199, "learning_rate": 3.409437910631236e-05, "loss": 0.5581, "num_tokens": 243885472.0, "step": 40780 }, { "epoch": 0.43511890156081634, "grad_norm": 1.0805778093717915, "learning_rate": 3.4090584234925386e-05, "loss": 0.4685, "num_tokens": 243919832.0, "step": 40785 }, { "epoch": 0.4351722445670148, "grad_norm": 0.9224408115064779, "learning_rate": 3.408678915845297e-05, "loss": 0.4362, "num_tokens": 243939337.0, "step": 40790 }, { "epoch": 0.4352255875732133, "grad_norm": 0.8055402236208642, "learning_rate": 3.408299387701322e-05, "loss": 0.4734, "num_tokens": 243974132.0, "step": 40795 }, { "epoch": 0.43527893057941175, "grad_norm": 0.6404391236639156, "learning_rate": 3.4079198390724195e-05, "loss": 0.5402, "num_tokens": 244012374.0, "step": 40800 }, { "epoch": 0.43533227358561016, "grad_norm": 0.9437579771806799, "learning_rate": 3.407540269970405e-05, "loss": 0.3996, "num_tokens": 244037056.0, "step": 40805 }, { "epoch": 0.43538561659180863, "grad_norm": 1.4456287983276936, "learning_rate": 3.407160680407088e-05, "loss": 0.5508, "num_tokens": 244056164.0, "step": 40810 }, { "epoch": 0.4354389595980071, "grad_norm": 1.1308242414924532, "learning_rate": 3.406781070394279e-05, "loss": 0.7344, "num_tokens": 244087765.0, "step": 40815 }, { "epoch": 0.4354923026042056, "grad_norm": 0.8827087242058498, "learning_rate": 3.406401439943793e-05, "loss": 0.6944, "num_tokens": 244120855.0, "step": 40820 }, { "epoch": 0.43554564561040404, "grad_norm": 0.6125891752416732, "learning_rate": 3.406021789067443e-05, "loss": 0.4663, "num_tokens": 244160839.0, "step": 40825 }, { "epoch": 0.43559898861660246, "grad_norm": 1.2363824598370956, "learning_rate": 3.4056421177770415e-05, "loss": 0.5488, "num_tokens": 244180393.0, "step": 40830 }, { "epoch": 0.4356523316228009, "grad_norm": 1.5325668408379605, "learning_rate": 3.4052624260844046e-05, "loss": 0.6003, "num_tokens": 244206087.0, "step": 40835 }, { "epoch": 0.4357056746289994, "grad_norm": 0.6824712532523579, "learning_rate": 3.404882714001347e-05, "loss": 0.5556, "num_tokens": 244227813.0, "step": 40840 }, { "epoch": 0.43575901763519787, "grad_norm": 0.918449212647213, "learning_rate": 3.4045029815396846e-05, "loss": 0.4792, "num_tokens": 244263100.0, "step": 40845 }, { "epoch": 0.4358123606413963, "grad_norm": 1.057287979239429, "learning_rate": 3.404123228711234e-05, "loss": 0.5418, "num_tokens": 244284984.0, "step": 40850 }, { "epoch": 0.43586570364759475, "grad_norm": 1.0079778953785734, "learning_rate": 3.4037434555278114e-05, "loss": 0.3851, "num_tokens": 244308082.0, "step": 40855 }, { "epoch": 0.4359190466537932, "grad_norm": 0.9048283968822977, "learning_rate": 3.4033636620012346e-05, "loss": 0.5885, "num_tokens": 244326593.0, "step": 40860 }, { "epoch": 0.4359723896599917, "grad_norm": 1.2758135076021253, "learning_rate": 3.402983848143325e-05, "loss": 0.4203, "num_tokens": 244358632.0, "step": 40865 }, { "epoch": 0.43602573266619016, "grad_norm": 0.9066690850238351, "learning_rate": 3.4026040139658974e-05, "loss": 0.5244, "num_tokens": 244381735.0, "step": 40870 }, { "epoch": 0.43607907567238857, "grad_norm": 0.9048876150322865, "learning_rate": 3.402224159480774e-05, "loss": 0.4954, "num_tokens": 244428271.0, "step": 40875 }, { "epoch": 0.43613241867858704, "grad_norm": 1.1957702925200246, "learning_rate": 3.401844284699774e-05, "loss": 0.504, "num_tokens": 244456143.0, "step": 40880 }, { "epoch": 0.4361857616847855, "grad_norm": 1.626144653668292, "learning_rate": 3.4014643896347194e-05, "loss": 0.5715, "num_tokens": 244479814.0, "step": 40885 }, { "epoch": 0.436239104690984, "grad_norm": 0.8770608691641516, "learning_rate": 3.401084474297431e-05, "loss": 0.4842, "num_tokens": 244532622.0, "step": 40890 }, { "epoch": 0.4362924476971824, "grad_norm": 0.699987255752085, "learning_rate": 3.400704538699731e-05, "loss": 0.665, "num_tokens": 244564491.0, "step": 40895 }, { "epoch": 0.43634579070338086, "grad_norm": 1.065553893331264, "learning_rate": 3.400324582853442e-05, "loss": 0.4477, "num_tokens": 244587758.0, "step": 40900 }, { "epoch": 0.43639913370957933, "grad_norm": 0.6801422291277861, "learning_rate": 3.399944606770388e-05, "loss": 0.6441, "num_tokens": 244619810.0, "step": 40905 }, { "epoch": 0.4364524767157778, "grad_norm": 0.8156747467583852, "learning_rate": 3.399564610462393e-05, "loss": 0.535, "num_tokens": 244654415.0, "step": 40910 }, { "epoch": 0.4365058197219763, "grad_norm": 0.6620136962054197, "learning_rate": 3.3991845939412825e-05, "loss": 0.4953, "num_tokens": 244676670.0, "step": 40915 }, { "epoch": 0.4365591627281747, "grad_norm": 0.8361572821553106, "learning_rate": 3.398804557218879e-05, "loss": 0.463, "num_tokens": 244704785.0, "step": 40920 }, { "epoch": 0.43661250573437316, "grad_norm": 1.750174099264829, "learning_rate": 3.398424500307012e-05, "loss": 0.4829, "num_tokens": 244739181.0, "step": 40925 }, { "epoch": 0.4366658487405716, "grad_norm": 1.1224686959630463, "learning_rate": 3.398044423217505e-05, "loss": 0.5718, "num_tokens": 244782593.0, "step": 40930 }, { "epoch": 0.4367191917467701, "grad_norm": 0.7843205742870744, "learning_rate": 3.397664325962188e-05, "loss": 0.5076, "num_tokens": 244816097.0, "step": 40935 }, { "epoch": 0.4367725347529685, "grad_norm": 0.5472919889566933, "learning_rate": 3.397284208552887e-05, "loss": 0.4593, "num_tokens": 244860270.0, "step": 40940 }, { "epoch": 0.436825877759167, "grad_norm": 0.9747697718188464, "learning_rate": 3.396904071001431e-05, "loss": 0.4602, "num_tokens": 244888765.0, "step": 40945 }, { "epoch": 0.43687922076536545, "grad_norm": 0.7209860476826384, "learning_rate": 3.396523913319649e-05, "loss": 0.4303, "num_tokens": 244922681.0, "step": 40950 }, { "epoch": 0.4369325637715639, "grad_norm": 0.9017816218506193, "learning_rate": 3.396143735519371e-05, "loss": 0.4549, "num_tokens": 244941703.0, "step": 40955 }, { "epoch": 0.4369859067777624, "grad_norm": 0.8245372205889137, "learning_rate": 3.3957635376124266e-05, "loss": 0.5059, "num_tokens": 244967987.0, "step": 40960 }, { "epoch": 0.4370392497839608, "grad_norm": 1.2867947798490909, "learning_rate": 3.3953833196106474e-05, "loss": 0.6193, "num_tokens": 245002794.0, "step": 40965 }, { "epoch": 0.4370925927901593, "grad_norm": 1.500057567291872, "learning_rate": 3.395003081525867e-05, "loss": 0.6272, "num_tokens": 245041477.0, "step": 40970 }, { "epoch": 0.43714593579635774, "grad_norm": 0.9466655527299, "learning_rate": 3.3946228233699135e-05, "loss": 0.6552, "num_tokens": 245097647.0, "step": 40975 }, { "epoch": 0.4371992788025562, "grad_norm": 0.8214946387595935, "learning_rate": 3.3942425451546214e-05, "loss": 0.4431, "num_tokens": 245130995.0, "step": 40980 }, { "epoch": 0.4372526218087546, "grad_norm": 1.076263341001874, "learning_rate": 3.393862246891826e-05, "loss": 0.4637, "num_tokens": 245150877.0, "step": 40985 }, { "epoch": 0.4373059648149531, "grad_norm": 0.8628354473682547, "learning_rate": 3.3934819285933594e-05, "loss": 0.8197, "num_tokens": 245202188.0, "step": 40990 }, { "epoch": 0.43735930782115157, "grad_norm": 0.9568093310558452, "learning_rate": 3.393101590271057e-05, "loss": 0.6138, "num_tokens": 245230798.0, "step": 40995 }, { "epoch": 0.43741265082735004, "grad_norm": 0.7983064405630086, "learning_rate": 3.3927212319367534e-05, "loss": 0.5028, "num_tokens": 245269794.0, "step": 41000 }, { "epoch": 0.4374659938335485, "grad_norm": 0.8184665710092248, "learning_rate": 3.392340853602287e-05, "loss": 0.6261, "num_tokens": 245289540.0, "step": 41005 }, { "epoch": 0.4375193368397469, "grad_norm": 1.825864908709299, "learning_rate": 3.3919604552794915e-05, "loss": 0.4859, "num_tokens": 245307834.0, "step": 41010 }, { "epoch": 0.4375726798459454, "grad_norm": 0.5716790662079224, "learning_rate": 3.391580036980205e-05, "loss": 0.4907, "num_tokens": 245341158.0, "step": 41015 }, { "epoch": 0.43762602285214386, "grad_norm": 1.1129936167385919, "learning_rate": 3.391199598716266e-05, "loss": 0.711, "num_tokens": 245373093.0, "step": 41020 }, { "epoch": 0.43767936585834233, "grad_norm": 0.9336240730657096, "learning_rate": 3.390819140499512e-05, "loss": 0.5907, "num_tokens": 245403736.0, "step": 41025 }, { "epoch": 0.43773270886454074, "grad_norm": 0.9453979861614366, "learning_rate": 3.390438662341783e-05, "loss": 0.4753, "num_tokens": 245441606.0, "step": 41030 }, { "epoch": 0.4377860518707392, "grad_norm": 0.789778297030526, "learning_rate": 3.390058164254919e-05, "loss": 0.4877, "num_tokens": 245478878.0, "step": 41035 }, { "epoch": 0.4378393948769377, "grad_norm": 0.640908730736052, "learning_rate": 3.389677646250759e-05, "loss": 0.4823, "num_tokens": 245526117.0, "step": 41040 }, { "epoch": 0.43789273788313615, "grad_norm": 0.6893721361631097, "learning_rate": 3.3892971083411444e-05, "loss": 0.6066, "num_tokens": 245559149.0, "step": 41045 }, { "epoch": 0.4379460808893346, "grad_norm": 0.7966900868821658, "learning_rate": 3.388916550537917e-05, "loss": 0.5446, "num_tokens": 245595075.0, "step": 41050 }, { "epoch": 0.43799942389553304, "grad_norm": 1.0870417697100399, "learning_rate": 3.388535972852919e-05, "loss": 0.5854, "num_tokens": 245622329.0, "step": 41055 }, { "epoch": 0.4380527669017315, "grad_norm": 1.0255326729292822, "learning_rate": 3.3881553752979936e-05, "loss": 0.6133, "num_tokens": 245661409.0, "step": 41060 }, { "epoch": 0.43810610990793, "grad_norm": 1.0300509915337153, "learning_rate": 3.387774757884984e-05, "loss": 0.5083, "num_tokens": 245679670.0, "step": 41065 }, { "epoch": 0.43815945291412844, "grad_norm": 1.7231014301022782, "learning_rate": 3.387394120625733e-05, "loss": 0.5119, "num_tokens": 245703425.0, "step": 41070 }, { "epoch": 0.43821279592032686, "grad_norm": 2.0162500496791966, "learning_rate": 3.387013463532086e-05, "loss": 0.8023, "num_tokens": 245730959.0, "step": 41075 }, { "epoch": 0.43826613892652533, "grad_norm": 1.093664466214195, "learning_rate": 3.3866327866158895e-05, "loss": 0.5298, "num_tokens": 245767416.0, "step": 41080 }, { "epoch": 0.4383194819327238, "grad_norm": 0.9578759621947464, "learning_rate": 3.3862520898889874e-05, "loss": 0.6534, "num_tokens": 245806094.0, "step": 41085 }, { "epoch": 0.43837282493892227, "grad_norm": 0.8308256329478051, "learning_rate": 3.385871373363228e-05, "loss": 0.5714, "num_tokens": 245833674.0, "step": 41090 }, { "epoch": 0.43842616794512074, "grad_norm": 0.7579507130919273, "learning_rate": 3.385490637050457e-05, "loss": 0.4256, "num_tokens": 245869546.0, "step": 41095 }, { "epoch": 0.43847951095131915, "grad_norm": 1.226373431352721, "learning_rate": 3.385109880962523e-05, "loss": 0.5979, "num_tokens": 245903189.0, "step": 41100 }, { "epoch": 0.4385328539575176, "grad_norm": 1.1706549011226393, "learning_rate": 3.384729105111274e-05, "loss": 0.6075, "num_tokens": 245931716.0, "step": 41105 }, { "epoch": 0.4385861969637161, "grad_norm": 0.6001576776639983, "learning_rate": 3.384348309508558e-05, "loss": 0.4657, "num_tokens": 245975251.0, "step": 41110 }, { "epoch": 0.43863953996991456, "grad_norm": 1.1930459465459462, "learning_rate": 3.383967494166227e-05, "loss": 0.4885, "num_tokens": 246008202.0, "step": 41115 }, { "epoch": 0.438692882976113, "grad_norm": 0.9702795965127612, "learning_rate": 3.38358665909613e-05, "loss": 0.5639, "num_tokens": 246035880.0, "step": 41120 }, { "epoch": 0.43874622598231144, "grad_norm": 0.8186331180199734, "learning_rate": 3.3832058043101166e-05, "loss": 0.5006, "num_tokens": 246057552.0, "step": 41125 }, { "epoch": 0.4387995689885099, "grad_norm": 2.7020497376507846, "learning_rate": 3.382824929820039e-05, "loss": 0.6617, "num_tokens": 246092203.0, "step": 41130 }, { "epoch": 0.4388529119947084, "grad_norm": 1.002444869677853, "learning_rate": 3.3824440356377515e-05, "loss": 0.528, "num_tokens": 246114628.0, "step": 41135 }, { "epoch": 0.43890625500090685, "grad_norm": 1.037159808139486, "learning_rate": 3.3820631217751026e-05, "loss": 0.5817, "num_tokens": 246149553.0, "step": 41140 }, { "epoch": 0.43895959800710527, "grad_norm": 1.2600437526401584, "learning_rate": 3.381682188243948e-05, "loss": 0.3976, "num_tokens": 246160694.0, "step": 41145 }, { "epoch": 0.43901294101330374, "grad_norm": 0.900975554972566, "learning_rate": 3.381301235056142e-05, "loss": 0.6168, "num_tokens": 246191174.0, "step": 41150 }, { "epoch": 0.4390662840195022, "grad_norm": 0.7852715357166165, "learning_rate": 3.380920262223538e-05, "loss": 0.5211, "num_tokens": 246217088.0, "step": 41155 }, { "epoch": 0.4391196270257007, "grad_norm": 0.8892629232553527, "learning_rate": 3.3805392697579904e-05, "loss": 0.7008, "num_tokens": 246256580.0, "step": 41160 }, { "epoch": 0.4391729700318991, "grad_norm": 1.3660611112402843, "learning_rate": 3.380158257671357e-05, "loss": 0.5649, "num_tokens": 246270185.0, "step": 41165 }, { "epoch": 0.43922631303809756, "grad_norm": 1.5989491445396082, "learning_rate": 3.3797772259754925e-05, "loss": 0.5387, "num_tokens": 246288449.0, "step": 41170 }, { "epoch": 0.43927965604429603, "grad_norm": 1.0650687462316513, "learning_rate": 3.379396174682254e-05, "loss": 0.5983, "num_tokens": 246326636.0, "step": 41175 }, { "epoch": 0.4393329990504945, "grad_norm": 1.0138654525868203, "learning_rate": 3.3790151038035005e-05, "loss": 0.556, "num_tokens": 246357323.0, "step": 41180 }, { "epoch": 0.43938634205669297, "grad_norm": 0.7920711927172744, "learning_rate": 3.378634013351088e-05, "loss": 0.6511, "num_tokens": 246408038.0, "step": 41185 }, { "epoch": 0.4394396850628914, "grad_norm": 0.6491454799719542, "learning_rate": 3.378252903336877e-05, "loss": 0.6134, "num_tokens": 246453687.0, "step": 41190 }, { "epoch": 0.43949302806908985, "grad_norm": 0.9618461098579023, "learning_rate": 3.377871773772726e-05, "loss": 0.7339, "num_tokens": 246508834.0, "step": 41195 }, { "epoch": 0.4395463710752883, "grad_norm": 0.7863684779500787, "learning_rate": 3.377490624670494e-05, "loss": 0.6905, "num_tokens": 246542995.0, "step": 41200 }, { "epoch": 0.4395997140814868, "grad_norm": 0.6968778821269558, "learning_rate": 3.377109456042044e-05, "loss": 0.6516, "num_tokens": 246569817.0, "step": 41205 }, { "epoch": 0.4396530570876852, "grad_norm": 0.6996759482152547, "learning_rate": 3.376728267899236e-05, "loss": 0.5065, "num_tokens": 246595829.0, "step": 41210 }, { "epoch": 0.4397064000938837, "grad_norm": 1.374921613530201, "learning_rate": 3.376347060253931e-05, "loss": 0.5481, "num_tokens": 246615438.0, "step": 41215 }, { "epoch": 0.43975974310008215, "grad_norm": 0.8530487125656058, "learning_rate": 3.375965833117991e-05, "loss": 0.6192, "num_tokens": 246641070.0, "step": 41220 }, { "epoch": 0.4398130861062806, "grad_norm": 1.164076329355316, "learning_rate": 3.3755845865032813e-05, "loss": 0.4274, "num_tokens": 246662614.0, "step": 41225 }, { "epoch": 0.4398664291124791, "grad_norm": 1.1753501909469293, "learning_rate": 3.375203320421664e-05, "loss": 0.5546, "num_tokens": 246690011.0, "step": 41230 }, { "epoch": 0.4399197721186775, "grad_norm": 0.9967820217349977, "learning_rate": 3.3748220348850036e-05, "loss": 0.5305, "num_tokens": 246709833.0, "step": 41235 }, { "epoch": 0.43997311512487597, "grad_norm": 0.9711878658068599, "learning_rate": 3.3744407299051644e-05, "loss": 0.5215, "num_tokens": 246730507.0, "step": 41240 }, { "epoch": 0.44002645813107444, "grad_norm": 0.7717608747627643, "learning_rate": 3.374059405494013e-05, "loss": 0.695, "num_tokens": 246766500.0, "step": 41245 }, { "epoch": 0.4400798011372729, "grad_norm": 1.0639089611239865, "learning_rate": 3.373678061663414e-05, "loss": 0.5391, "num_tokens": 246787138.0, "step": 41250 }, { "epoch": 0.4401331441434713, "grad_norm": 0.9276073808173595, "learning_rate": 3.3732966984252363e-05, "loss": 0.5975, "num_tokens": 246817598.0, "step": 41255 }, { "epoch": 0.4401864871496698, "grad_norm": 0.8098862228801736, "learning_rate": 3.3729153157913444e-05, "loss": 0.5957, "num_tokens": 246856678.0, "step": 41260 }, { "epoch": 0.44023983015586826, "grad_norm": 1.3209485630269089, "learning_rate": 3.3725339137736075e-05, "loss": 0.5096, "num_tokens": 246890469.0, "step": 41265 }, { "epoch": 0.44029317316206673, "grad_norm": 0.8020733931366512, "learning_rate": 3.3721524923838945e-05, "loss": 0.5142, "num_tokens": 246923247.0, "step": 41270 }, { "epoch": 0.4403465161682652, "grad_norm": 1.3829388652431769, "learning_rate": 3.3717710516340725e-05, "loss": 0.6886, "num_tokens": 246939216.0, "step": 41275 }, { "epoch": 0.4403998591744636, "grad_norm": 1.5525132931592787, "learning_rate": 3.3713895915360136e-05, "loss": 0.588, "num_tokens": 246976387.0, "step": 41280 }, { "epoch": 0.4404532021806621, "grad_norm": 1.3015195874442695, "learning_rate": 3.371008112101587e-05, "loss": 0.7039, "num_tokens": 247000495.0, "step": 41285 }, { "epoch": 0.44050654518686055, "grad_norm": 0.8437001693204667, "learning_rate": 3.370626613342664e-05, "loss": 0.4655, "num_tokens": 247026849.0, "step": 41290 }, { "epoch": 0.440559888193059, "grad_norm": 0.9558220711822165, "learning_rate": 3.3702450952711144e-05, "loss": 0.5071, "num_tokens": 247054118.0, "step": 41295 }, { "epoch": 0.44061323119925744, "grad_norm": 1.0673856747235955, "learning_rate": 3.369863557898813e-05, "loss": 0.4513, "num_tokens": 247089009.0, "step": 41300 }, { "epoch": 0.4406665742054559, "grad_norm": 1.1653317304522985, "learning_rate": 3.369482001237629e-05, "loss": 0.6184, "num_tokens": 247137232.0, "step": 41305 }, { "epoch": 0.4407199172116544, "grad_norm": 1.49954327500185, "learning_rate": 3.369100425299439e-05, "loss": 0.4948, "num_tokens": 247163094.0, "step": 41310 }, { "epoch": 0.44077326021785285, "grad_norm": 1.0445962049694264, "learning_rate": 3.3687188300961146e-05, "loss": 0.4654, "num_tokens": 247186788.0, "step": 41315 }, { "epoch": 0.4408266032240513, "grad_norm": 1.3132411461643831, "learning_rate": 3.3683372156395317e-05, "loss": 0.4947, "num_tokens": 247202128.0, "step": 41320 }, { "epoch": 0.44087994623024973, "grad_norm": 0.7339205785037795, "learning_rate": 3.367955581941565e-05, "loss": 0.4987, "num_tokens": 247236241.0, "step": 41325 }, { "epoch": 0.4409332892364482, "grad_norm": 0.7534300863996821, "learning_rate": 3.367573929014089e-05, "loss": 0.5642, "num_tokens": 247271278.0, "step": 41330 }, { "epoch": 0.44098663224264667, "grad_norm": 0.9304857277228884, "learning_rate": 3.3671922568689815e-05, "loss": 0.5082, "num_tokens": 247308231.0, "step": 41335 }, { "epoch": 0.44103997524884514, "grad_norm": 0.7768100966234407, "learning_rate": 3.366810565518118e-05, "loss": 0.5069, "num_tokens": 247335600.0, "step": 41340 }, { "epoch": 0.44109331825504355, "grad_norm": 0.7845490143625309, "learning_rate": 3.366428854973378e-05, "loss": 0.5828, "num_tokens": 247369519.0, "step": 41345 }, { "epoch": 0.441146661261242, "grad_norm": 0.8404196205392983, "learning_rate": 3.366047125246637e-05, "loss": 0.5021, "num_tokens": 247399620.0, "step": 41350 }, { "epoch": 0.4412000042674405, "grad_norm": 0.8524281722157343, "learning_rate": 3.3656653763497756e-05, "loss": 0.546, "num_tokens": 247433352.0, "step": 41355 }, { "epoch": 0.44125334727363896, "grad_norm": 0.7983989676847235, "learning_rate": 3.3652836082946714e-05, "loss": 0.549, "num_tokens": 247469074.0, "step": 41360 }, { "epoch": 0.44130669027983743, "grad_norm": 0.7228658517031988, "learning_rate": 3.3649018210932046e-05, "loss": 0.5537, "num_tokens": 247501484.0, "step": 41365 }, { "epoch": 0.44136003328603585, "grad_norm": 1.715478869582535, "learning_rate": 3.364520014757259e-05, "loss": 0.4722, "num_tokens": 247514402.0, "step": 41370 }, { "epoch": 0.4414133762922343, "grad_norm": 0.9884404636882207, "learning_rate": 3.36413818929871e-05, "loss": 0.4002, "num_tokens": 247536365.0, "step": 41375 }, { "epoch": 0.4414667192984328, "grad_norm": 0.8846229037381594, "learning_rate": 3.363756344729443e-05, "loss": 0.5462, "num_tokens": 247573920.0, "step": 41380 }, { "epoch": 0.44152006230463126, "grad_norm": 1.0090092772032337, "learning_rate": 3.3633744810613393e-05, "loss": 0.5257, "num_tokens": 247594895.0, "step": 41385 }, { "epoch": 0.44157340531082967, "grad_norm": 0.8955300500082255, "learning_rate": 3.362992598306282e-05, "loss": 0.4487, "num_tokens": 247623454.0, "step": 41390 }, { "epoch": 0.44162674831702814, "grad_norm": 1.6957348809646875, "learning_rate": 3.362610696476153e-05, "loss": 0.7199, "num_tokens": 247653507.0, "step": 41395 }, { "epoch": 0.4416800913232266, "grad_norm": 0.8941275869371884, "learning_rate": 3.362228775582839e-05, "loss": 0.55, "num_tokens": 247696878.0, "step": 41400 }, { "epoch": 0.4417334343294251, "grad_norm": 1.157949461192744, "learning_rate": 3.3618468356382224e-05, "loss": 0.6756, "num_tokens": 247718159.0, "step": 41405 }, { "epoch": 0.44178677733562355, "grad_norm": 1.5814405919066294, "learning_rate": 3.361464876654189e-05, "loss": 0.5067, "num_tokens": 247745409.0, "step": 41410 }, { "epoch": 0.44184012034182196, "grad_norm": 0.812358198562352, "learning_rate": 3.361082898642625e-05, "loss": 0.4334, "num_tokens": 247764693.0, "step": 41415 }, { "epoch": 0.44189346334802043, "grad_norm": 1.5492522846745826, "learning_rate": 3.3607009016154155e-05, "loss": 0.5196, "num_tokens": 247789553.0, "step": 41420 }, { "epoch": 0.4419468063542189, "grad_norm": 0.5734532084021173, "learning_rate": 3.3603188855844486e-05, "loss": 0.8251, "num_tokens": 247810654.0, "step": 41425 }, { "epoch": 0.44200014936041737, "grad_norm": 1.3529767922246074, "learning_rate": 3.359936850561612e-05, "loss": 0.4153, "num_tokens": 247821117.0, "step": 41430 }, { "epoch": 0.4420534923666158, "grad_norm": 0.7263810048992352, "learning_rate": 3.3595547965587936e-05, "loss": 0.5546, "num_tokens": 247850535.0, "step": 41435 }, { "epoch": 0.44210683537281426, "grad_norm": 0.8468975008834336, "learning_rate": 3.3591727235878814e-05, "loss": 0.4459, "num_tokens": 247872506.0, "step": 41440 }, { "epoch": 0.4421601783790127, "grad_norm": 1.2227088391946064, "learning_rate": 3.358790631660766e-05, "loss": 0.5426, "num_tokens": 247895014.0, "step": 41445 }, { "epoch": 0.4422135213852112, "grad_norm": 0.840997519951612, "learning_rate": 3.358408520789336e-05, "loss": 0.4871, "num_tokens": 247912598.0, "step": 41450 }, { "epoch": 0.44226686439140966, "grad_norm": 1.6127766549714824, "learning_rate": 3.358026390985483e-05, "loss": 0.5596, "num_tokens": 247941116.0, "step": 41455 }, { "epoch": 0.4423202073976081, "grad_norm": 1.29050131718865, "learning_rate": 3.3576442422610976e-05, "loss": 0.5234, "num_tokens": 247970227.0, "step": 41460 }, { "epoch": 0.44237355040380655, "grad_norm": 1.069710915154847, "learning_rate": 3.357262074628072e-05, "loss": 0.5185, "num_tokens": 247990576.0, "step": 41465 }, { "epoch": 0.442426893410005, "grad_norm": 1.0281150207015772, "learning_rate": 3.356879888098297e-05, "loss": 0.481, "num_tokens": 248017503.0, "step": 41470 }, { "epoch": 0.4424802364162035, "grad_norm": 0.825706150691024, "learning_rate": 3.356497682683666e-05, "loss": 0.6132, "num_tokens": 248043441.0, "step": 41475 }, { "epoch": 0.4425335794224019, "grad_norm": 1.33854651087901, "learning_rate": 3.3561154583960744e-05, "loss": 0.5463, "num_tokens": 248067979.0, "step": 41480 }, { "epoch": 0.44258692242860037, "grad_norm": 0.7479334689798952, "learning_rate": 3.355733215247414e-05, "loss": 0.5712, "num_tokens": 248112920.0, "step": 41485 }, { "epoch": 0.44264026543479884, "grad_norm": 1.0069078660446598, "learning_rate": 3.3553509532495795e-05, "loss": 0.6273, "num_tokens": 248144367.0, "step": 41490 }, { "epoch": 0.4426936084409973, "grad_norm": 1.4445630760816581, "learning_rate": 3.354968672414468e-05, "loss": 0.6098, "num_tokens": 248173199.0, "step": 41495 }, { "epoch": 0.4427469514471958, "grad_norm": 1.5362779334607668, "learning_rate": 3.354586372753973e-05, "loss": 0.4762, "num_tokens": 248194619.0, "step": 41500 }, { "epoch": 0.4428002944533942, "grad_norm": 1.1938324050570093, "learning_rate": 3.354204054279994e-05, "loss": 0.6017, "num_tokens": 248230090.0, "step": 41505 }, { "epoch": 0.44285363745959266, "grad_norm": 0.8314040254403064, "learning_rate": 3.353821717004424e-05, "loss": 0.5016, "num_tokens": 248262853.0, "step": 41510 }, { "epoch": 0.44290698046579113, "grad_norm": 0.9987940805420766, "learning_rate": 3.353439360939162e-05, "loss": 0.4496, "num_tokens": 248299126.0, "step": 41515 }, { "epoch": 0.4429603234719896, "grad_norm": 0.6521204794428648, "learning_rate": 3.353056986096108e-05, "loss": 0.5334, "num_tokens": 248334101.0, "step": 41520 }, { "epoch": 0.443013666478188, "grad_norm": 0.9145555136322219, "learning_rate": 3.3526745924871584e-05, "loss": 0.4481, "num_tokens": 248359234.0, "step": 41525 }, { "epoch": 0.4430670094843865, "grad_norm": 0.8613941149087296, "learning_rate": 3.352292180124213e-05, "loss": 0.5652, "num_tokens": 248380397.0, "step": 41530 }, { "epoch": 0.44312035249058496, "grad_norm": 0.9418602098983094, "learning_rate": 3.351909749019174e-05, "loss": 0.4317, "num_tokens": 248402811.0, "step": 41535 }, { "epoch": 0.4431736954967834, "grad_norm": 1.0178463960255033, "learning_rate": 3.351527299183938e-05, "loss": 0.4236, "num_tokens": 248425811.0, "step": 41540 }, { "epoch": 0.4432270385029819, "grad_norm": 1.2158368377104847, "learning_rate": 3.3511448306304085e-05, "loss": 0.625, "num_tokens": 248461018.0, "step": 41545 }, { "epoch": 0.4432803815091803, "grad_norm": 0.9061966526434849, "learning_rate": 3.350762343370487e-05, "loss": 0.4907, "num_tokens": 248484389.0, "step": 41550 }, { "epoch": 0.4433337245153788, "grad_norm": 1.1301295002804752, "learning_rate": 3.350379837416076e-05, "loss": 0.5707, "num_tokens": 248502313.0, "step": 41555 }, { "epoch": 0.44338706752157725, "grad_norm": 1.1305931113926255, "learning_rate": 3.349997312779077e-05, "loss": 0.5493, "num_tokens": 248535271.0, "step": 41560 }, { "epoch": 0.4434404105277757, "grad_norm": 1.0678209349693841, "learning_rate": 3.3496147694713934e-05, "loss": 0.5418, "num_tokens": 248561934.0, "step": 41565 }, { "epoch": 0.44349375353397413, "grad_norm": 1.1299858838786208, "learning_rate": 3.349232207504931e-05, "loss": 0.5562, "num_tokens": 248571466.0, "step": 41570 }, { "epoch": 0.4435470965401726, "grad_norm": 0.8787183451424441, "learning_rate": 3.3488496268915924e-05, "loss": 0.634, "num_tokens": 248606815.0, "step": 41575 }, { "epoch": 0.4436004395463711, "grad_norm": 0.9085708449302357, "learning_rate": 3.348467027643284e-05, "loss": 0.5811, "num_tokens": 248624033.0, "step": 41580 }, { "epoch": 0.44365378255256954, "grad_norm": 1.3518730679365365, "learning_rate": 3.34808440977191e-05, "loss": 0.4781, "num_tokens": 248654915.0, "step": 41585 }, { "epoch": 0.443707125558768, "grad_norm": 8.64644942904897, "learning_rate": 3.347701773289379e-05, "loss": 0.8039, "num_tokens": 248686909.0, "step": 41590 }, { "epoch": 0.4437604685649664, "grad_norm": 1.1412543486732707, "learning_rate": 3.347319118207596e-05, "loss": 0.484, "num_tokens": 248718371.0, "step": 41595 }, { "epoch": 0.4438138115711649, "grad_norm": 0.7533896463282059, "learning_rate": 3.346936444538468e-05, "loss": 0.6402, "num_tokens": 248751095.0, "step": 41600 }, { "epoch": 0.44386715457736337, "grad_norm": 1.5332237887475433, "learning_rate": 3.346553752293905e-05, "loss": 0.5049, "num_tokens": 248792624.0, "step": 41605 }, { "epoch": 0.44392049758356183, "grad_norm": 0.8004033296372124, "learning_rate": 3.3461710414858156e-05, "loss": 0.5133, "num_tokens": 248815866.0, "step": 41610 }, { "epoch": 0.44397384058976025, "grad_norm": 3.444018076832327, "learning_rate": 3.345788312126106e-05, "loss": 0.5825, "num_tokens": 248856010.0, "step": 41615 }, { "epoch": 0.4440271835959587, "grad_norm": 0.9398885482560159, "learning_rate": 3.3454055642266885e-05, "loss": 0.6422, "num_tokens": 248900284.0, "step": 41620 }, { "epoch": 0.4440805266021572, "grad_norm": 1.671820870659696, "learning_rate": 3.345022797799474e-05, "loss": 0.5358, "num_tokens": 248921513.0, "step": 41625 }, { "epoch": 0.44413386960835566, "grad_norm": 0.7831566246670882, "learning_rate": 3.344640012856371e-05, "loss": 0.3414, "num_tokens": 248940382.0, "step": 41630 }, { "epoch": 0.4441872126145541, "grad_norm": 0.7619245852539452, "learning_rate": 3.344257209409292e-05, "loss": 0.514, "num_tokens": 248981038.0, "step": 41635 }, { "epoch": 0.44424055562075254, "grad_norm": 1.2328165699510782, "learning_rate": 3.34387438747015e-05, "loss": 0.4314, "num_tokens": 248995984.0, "step": 41640 }, { "epoch": 0.444293898626951, "grad_norm": 0.7791398350199842, "learning_rate": 3.343491547050856e-05, "loss": 0.5615, "num_tokens": 249027703.0, "step": 41645 }, { "epoch": 0.4443472416331495, "grad_norm": 1.4522319771072016, "learning_rate": 3.3431086881633255e-05, "loss": 0.5376, "num_tokens": 249043709.0, "step": 41650 }, { "epoch": 0.44440058463934795, "grad_norm": 0.615407727902206, "learning_rate": 3.3427258108194706e-05, "loss": 0.5489, "num_tokens": 249086225.0, "step": 41655 }, { "epoch": 0.44445392764554636, "grad_norm": 0.8541847108505717, "learning_rate": 3.3423429150312056e-05, "loss": 0.5333, "num_tokens": 249112972.0, "step": 41660 }, { "epoch": 0.44450727065174483, "grad_norm": 0.9289142377049053, "learning_rate": 3.341960000810446e-05, "loss": 0.5305, "num_tokens": 249156217.0, "step": 41665 }, { "epoch": 0.4445606136579433, "grad_norm": 0.7234363365191927, "learning_rate": 3.341577068169107e-05, "loss": 0.5815, "num_tokens": 249197747.0, "step": 41670 }, { "epoch": 0.4446139566641418, "grad_norm": 1.123550721987432, "learning_rate": 3.341194117119104e-05, "loss": 0.5558, "num_tokens": 249222490.0, "step": 41675 }, { "epoch": 0.44466729967034024, "grad_norm": 0.660641018189053, "learning_rate": 3.340811147672355e-05, "loss": 0.4381, "num_tokens": 249259340.0, "step": 41680 }, { "epoch": 0.44472064267653866, "grad_norm": 1.2202145312509924, "learning_rate": 3.3404281598407774e-05, "loss": 0.5885, "num_tokens": 249275756.0, "step": 41685 }, { "epoch": 0.4447739856827371, "grad_norm": 1.0505399811621026, "learning_rate": 3.340045153636287e-05, "loss": 0.4955, "num_tokens": 249301841.0, "step": 41690 }, { "epoch": 0.4448273286889356, "grad_norm": 0.5734616450267216, "learning_rate": 3.339662129070804e-05, "loss": 0.5372, "num_tokens": 249347819.0, "step": 41695 }, { "epoch": 0.44488067169513407, "grad_norm": 0.8935373207907169, "learning_rate": 3.339279086156247e-05, "loss": 0.6125, "num_tokens": 249372149.0, "step": 41700 }, { "epoch": 0.4449340147013325, "grad_norm": 1.3548920885767846, "learning_rate": 3.338896024904535e-05, "loss": 0.7357, "num_tokens": 249413652.0, "step": 41705 }, { "epoch": 0.44498735770753095, "grad_norm": 1.0859894330383422, "learning_rate": 3.3385129453275884e-05, "loss": 0.5059, "num_tokens": 249452605.0, "step": 41710 }, { "epoch": 0.4450407007137294, "grad_norm": 0.7755467988000143, "learning_rate": 3.338129847437328e-05, "loss": 0.6104, "num_tokens": 249477531.0, "step": 41715 }, { "epoch": 0.4450940437199279, "grad_norm": 1.4486946249855797, "learning_rate": 3.337746731245674e-05, "loss": 0.4869, "num_tokens": 249498576.0, "step": 41720 }, { "epoch": 0.44514738672612636, "grad_norm": 0.9854835904462715, "learning_rate": 3.3373635967645497e-05, "loss": 0.5052, "num_tokens": 249521689.0, "step": 41725 }, { "epoch": 0.4452007297323248, "grad_norm": 0.9268491883079649, "learning_rate": 3.336980444005877e-05, "loss": 0.6366, "num_tokens": 249559293.0, "step": 41730 }, { "epoch": 0.44525407273852324, "grad_norm": 0.929776614693425, "learning_rate": 3.336597272981577e-05, "loss": 0.5627, "num_tokens": 249583177.0, "step": 41735 }, { "epoch": 0.4453074157447217, "grad_norm": 2.129871644278512, "learning_rate": 3.336214083703576e-05, "loss": 0.5051, "num_tokens": 249602967.0, "step": 41740 }, { "epoch": 0.4453607587509202, "grad_norm": 0.9494749105720395, "learning_rate": 3.335830876183798e-05, "loss": 0.6299, "num_tokens": 249633490.0, "step": 41745 }, { "epoch": 0.4454141017571186, "grad_norm": 1.1682051377712632, "learning_rate": 3.335447650434164e-05, "loss": 0.4614, "num_tokens": 249654728.0, "step": 41750 }, { "epoch": 0.44546744476331707, "grad_norm": 1.3942713016462116, "learning_rate": 3.335064406466604e-05, "loss": 0.5694, "num_tokens": 249680296.0, "step": 41755 }, { "epoch": 0.44552078776951554, "grad_norm": 1.9635169068292544, "learning_rate": 3.3346811442930395e-05, "loss": 0.4625, "num_tokens": 249695184.0, "step": 41760 }, { "epoch": 0.445574130775714, "grad_norm": 0.9128378508911851, "learning_rate": 3.334297863925399e-05, "loss": 0.6269, "num_tokens": 249724926.0, "step": 41765 }, { "epoch": 0.4456274737819125, "grad_norm": 0.9944071240415008, "learning_rate": 3.33391456537561e-05, "loss": 0.647, "num_tokens": 249746642.0, "step": 41770 }, { "epoch": 0.4456808167881109, "grad_norm": 1.5227707701441515, "learning_rate": 3.333531248655599e-05, "loss": 0.5469, "num_tokens": 249787472.0, "step": 41775 }, { "epoch": 0.44573415979430936, "grad_norm": 1.053438740952606, "learning_rate": 3.3331479137772945e-05, "loss": 0.4805, "num_tokens": 249810535.0, "step": 41780 }, { "epoch": 0.44578750280050783, "grad_norm": 0.9376041941593601, "learning_rate": 3.3327645607526235e-05, "loss": 0.5917, "num_tokens": 249842101.0, "step": 41785 }, { "epoch": 0.4458408458067063, "grad_norm": 0.9739013270116266, "learning_rate": 3.332381189593517e-05, "loss": 0.4901, "num_tokens": 249868202.0, "step": 41790 }, { "epoch": 0.4458941888129047, "grad_norm": 1.2589689058202969, "learning_rate": 3.3319978003119046e-05, "loss": 0.7108, "num_tokens": 249907387.0, "step": 41795 }, { "epoch": 0.4459475318191032, "grad_norm": 1.3237751245082114, "learning_rate": 3.331614392919715e-05, "loss": 0.5841, "num_tokens": 249933642.0, "step": 41800 }, { "epoch": 0.44600087482530165, "grad_norm": 1.1368829658505832, "learning_rate": 3.331230967428882e-05, "loss": 0.5575, "num_tokens": 249961474.0, "step": 41805 }, { "epoch": 0.4460542178315001, "grad_norm": 1.0296584898832242, "learning_rate": 3.330847523851334e-05, "loss": 0.4937, "num_tokens": 249984488.0, "step": 41810 }, { "epoch": 0.4461075608376986, "grad_norm": 1.2404871418925685, "learning_rate": 3.330464062199004e-05, "loss": 0.7492, "num_tokens": 250015817.0, "step": 41815 }, { "epoch": 0.446160903843897, "grad_norm": 0.8879586281473896, "learning_rate": 3.330080582483824e-05, "loss": 0.4693, "num_tokens": 250045805.0, "step": 41820 }, { "epoch": 0.4462142468500955, "grad_norm": 0.823290982016336, "learning_rate": 3.3296970847177296e-05, "loss": 0.4736, "num_tokens": 250082226.0, "step": 41825 }, { "epoch": 0.44626758985629394, "grad_norm": 0.8853635182982972, "learning_rate": 3.329313568912652e-05, "loss": 0.5414, "num_tokens": 250122453.0, "step": 41830 }, { "epoch": 0.4463209328624924, "grad_norm": 0.8237327167494899, "learning_rate": 3.328930035080526e-05, "loss": 0.735, "num_tokens": 250150989.0, "step": 41835 }, { "epoch": 0.44637427586869083, "grad_norm": 0.8495721673644866, "learning_rate": 3.328546483233286e-05, "loss": 0.5832, "num_tokens": 250188761.0, "step": 41840 }, { "epoch": 0.4464276188748893, "grad_norm": 0.6117385189614514, "learning_rate": 3.328162913382869e-05, "loss": 0.4594, "num_tokens": 250215365.0, "step": 41845 }, { "epoch": 0.44648096188108777, "grad_norm": 0.6874541230127269, "learning_rate": 3.327779325541208e-05, "loss": 0.5851, "num_tokens": 250257285.0, "step": 41850 }, { "epoch": 0.44653430488728624, "grad_norm": 0.7358728769052908, "learning_rate": 3.327395719720242e-05, "loss": 0.4449, "num_tokens": 250287701.0, "step": 41855 }, { "epoch": 0.4465876478934847, "grad_norm": 1.634821029238609, "learning_rate": 3.327012095931907e-05, "loss": 0.4604, "num_tokens": 250312275.0, "step": 41860 }, { "epoch": 0.4466409908996831, "grad_norm": 0.96039394372111, "learning_rate": 3.326628454188141e-05, "loss": 0.5608, "num_tokens": 250342007.0, "step": 41865 }, { "epoch": 0.4466943339058816, "grad_norm": 0.6524562520278566, "learning_rate": 3.326244794500882e-05, "loss": 0.4996, "num_tokens": 250379619.0, "step": 41870 }, { "epoch": 0.44674767691208006, "grad_norm": 0.7357542784513641, "learning_rate": 3.3258611168820684e-05, "loss": 0.6692, "num_tokens": 250404436.0, "step": 41875 }, { "epoch": 0.44680101991827853, "grad_norm": 0.8697183856473892, "learning_rate": 3.325477421343639e-05, "loss": 0.6752, "num_tokens": 250448544.0, "step": 41880 }, { "epoch": 0.44685436292447694, "grad_norm": 1.283571411185088, "learning_rate": 3.3250937078975365e-05, "loss": 0.5328, "num_tokens": 250467864.0, "step": 41885 }, { "epoch": 0.4469077059306754, "grad_norm": 0.9261479147959797, "learning_rate": 3.3247099765556976e-05, "loss": 0.4808, "num_tokens": 250485240.0, "step": 41890 }, { "epoch": 0.4469610489368739, "grad_norm": 2.040911096158473, "learning_rate": 3.324326227330065e-05, "loss": 0.6284, "num_tokens": 250523129.0, "step": 41895 }, { "epoch": 0.44701439194307235, "grad_norm": 1.2428455614642904, "learning_rate": 3.32394246023258e-05, "loss": 0.5637, "num_tokens": 250545992.0, "step": 41900 }, { "epoch": 0.4470677349492708, "grad_norm": 0.9978395078443811, "learning_rate": 3.3235586752751844e-05, "loss": 0.6008, "num_tokens": 250583351.0, "step": 41905 }, { "epoch": 0.44712107795546924, "grad_norm": 0.8409871578909804, "learning_rate": 3.323174872469821e-05, "loss": 0.5417, "num_tokens": 250617388.0, "step": 41910 }, { "epoch": 0.4471744209616677, "grad_norm": 0.9165840425554357, "learning_rate": 3.3227910518284324e-05, "loss": 0.5357, "num_tokens": 250642310.0, "step": 41915 }, { "epoch": 0.4472277639678662, "grad_norm": 1.0998625317420763, "learning_rate": 3.3224072133629635e-05, "loss": 0.594, "num_tokens": 250671856.0, "step": 41920 }, { "epoch": 0.44728110697406465, "grad_norm": 0.7451661741651269, "learning_rate": 3.322023357085357e-05, "loss": 0.5516, "num_tokens": 250695763.0, "step": 41925 }, { "epoch": 0.44733444998026306, "grad_norm": 1.238654288049241, "learning_rate": 3.321639483007559e-05, "loss": 0.4779, "num_tokens": 250722366.0, "step": 41930 }, { "epoch": 0.44738779298646153, "grad_norm": 1.6132551064586766, "learning_rate": 3.3212555911415154e-05, "loss": 0.5648, "num_tokens": 250758096.0, "step": 41935 }, { "epoch": 0.44744113599266, "grad_norm": 0.8075855825218164, "learning_rate": 3.32087168149917e-05, "loss": 0.4653, "num_tokens": 250800795.0, "step": 41940 }, { "epoch": 0.44749447899885847, "grad_norm": 1.3023839514004152, "learning_rate": 3.320487754092471e-05, "loss": 0.5002, "num_tokens": 250819732.0, "step": 41945 }, { "epoch": 0.44754782200505694, "grad_norm": 0.9118017425855129, "learning_rate": 3.3201038089333644e-05, "loss": 0.4494, "num_tokens": 250843142.0, "step": 41950 }, { "epoch": 0.44760116501125535, "grad_norm": 0.8885200934737285, "learning_rate": 3.3197198460337994e-05, "loss": 0.5865, "num_tokens": 250872938.0, "step": 41955 }, { "epoch": 0.4476545080174538, "grad_norm": 0.798767178090261, "learning_rate": 3.3193358654057224e-05, "loss": 0.5313, "num_tokens": 250906049.0, "step": 41960 }, { "epoch": 0.4477078510236523, "grad_norm": 1.1290991362835119, "learning_rate": 3.3189518670610825e-05, "loss": 0.4367, "num_tokens": 250924003.0, "step": 41965 }, { "epoch": 0.44776119402985076, "grad_norm": 0.9153335166509516, "learning_rate": 3.31856785101183e-05, "loss": 0.4669, "num_tokens": 250957915.0, "step": 41970 }, { "epoch": 0.4478145370360492, "grad_norm": 2.375127987565206, "learning_rate": 3.318183817269913e-05, "loss": 0.7473, "num_tokens": 250986083.0, "step": 41975 }, { "epoch": 0.44786788004224765, "grad_norm": 1.3571887098914355, "learning_rate": 3.317799765847283e-05, "loss": 0.4973, "num_tokens": 250997885.0, "step": 41980 }, { "epoch": 0.4479212230484461, "grad_norm": 0.8420973870716084, "learning_rate": 3.31741569675589e-05, "loss": 0.6869, "num_tokens": 251039476.0, "step": 41985 }, { "epoch": 0.4479745660546446, "grad_norm": 1.7867670229644994, "learning_rate": 3.317031610007686e-05, "loss": 0.6173, "num_tokens": 251065635.0, "step": 41990 }, { "epoch": 0.44802790906084305, "grad_norm": 0.8735695752989056, "learning_rate": 3.316647505614624e-05, "loss": 0.4924, "num_tokens": 251086121.0, "step": 41995 }, { "epoch": 0.44808125206704147, "grad_norm": 1.060738333031505, "learning_rate": 3.316263383588655e-05, "loss": 0.5665, "num_tokens": 251110352.0, "step": 42000 }, { "epoch": 0.44813459507323994, "grad_norm": 0.9157172822683182, "learning_rate": 3.3158792439417325e-05, "loss": 0.5831, "num_tokens": 251134401.0, "step": 42005 }, { "epoch": 0.4481879380794384, "grad_norm": 1.1665761922352353, "learning_rate": 3.315495086685811e-05, "loss": 0.5084, "num_tokens": 251152822.0, "step": 42010 }, { "epoch": 0.4482412810856369, "grad_norm": 0.8417475097041994, "learning_rate": 3.3151109118328436e-05, "loss": 0.5552, "num_tokens": 251177364.0, "step": 42015 }, { "epoch": 0.4482946240918353, "grad_norm": 1.0706985184273698, "learning_rate": 3.314726719394785e-05, "loss": 0.5482, "num_tokens": 251202805.0, "step": 42020 }, { "epoch": 0.44834796709803376, "grad_norm": 0.968191417047723, "learning_rate": 3.31434250938359e-05, "loss": 0.5624, "num_tokens": 251249565.0, "step": 42025 }, { "epoch": 0.44840131010423223, "grad_norm": 0.7916213575114189, "learning_rate": 3.3139582818112174e-05, "loss": 0.5989, "num_tokens": 251286535.0, "step": 42030 }, { "epoch": 0.4484546531104307, "grad_norm": 0.98849976713397, "learning_rate": 3.31357403668962e-05, "loss": 0.6746, "num_tokens": 251324239.0, "step": 42035 }, { "epoch": 0.44850799611662917, "grad_norm": 0.9123896372806369, "learning_rate": 3.3131897740307574e-05, "loss": 0.5673, "num_tokens": 251363780.0, "step": 42040 }, { "epoch": 0.4485613391228276, "grad_norm": 0.8441617306531506, "learning_rate": 3.3128054938465844e-05, "loss": 0.5945, "num_tokens": 251401968.0, "step": 42045 }, { "epoch": 0.44861468212902605, "grad_norm": 1.1434695121564145, "learning_rate": 3.312421196149061e-05, "loss": 0.5187, "num_tokens": 251426895.0, "step": 42050 }, { "epoch": 0.4486680251352245, "grad_norm": 1.0878045320163034, "learning_rate": 3.312036880950146e-05, "loss": 0.6605, "num_tokens": 251469288.0, "step": 42055 }, { "epoch": 0.448721368141423, "grad_norm": 1.5504552993801837, "learning_rate": 3.311652548261797e-05, "loss": 0.4235, "num_tokens": 251494082.0, "step": 42060 }, { "epoch": 0.4487747111476214, "grad_norm": 0.9652909496221905, "learning_rate": 3.3112681980959746e-05, "loss": 0.4228, "num_tokens": 251510723.0, "step": 42065 }, { "epoch": 0.4488280541538199, "grad_norm": 1.0792600973494697, "learning_rate": 3.310883830464639e-05, "loss": 0.5505, "num_tokens": 251539584.0, "step": 42070 }, { "epoch": 0.44888139716001835, "grad_norm": 0.9381523882866121, "learning_rate": 3.31049944537975e-05, "loss": 0.5758, "num_tokens": 251573331.0, "step": 42075 }, { "epoch": 0.4489347401662168, "grad_norm": 1.3844596470009805, "learning_rate": 3.3101150428532695e-05, "loss": 0.4953, "num_tokens": 251593933.0, "step": 42080 }, { "epoch": 0.4489880831724153, "grad_norm": 0.7703715375536828, "learning_rate": 3.30973062289716e-05, "loss": 0.515, "num_tokens": 251625524.0, "step": 42085 }, { "epoch": 0.4490414261786137, "grad_norm": 0.9390800234031281, "learning_rate": 3.309346185523383e-05, "loss": 0.5755, "num_tokens": 251666386.0, "step": 42090 }, { "epoch": 0.44909476918481217, "grad_norm": 1.1171135871435094, "learning_rate": 3.308961730743901e-05, "loss": 0.5295, "num_tokens": 251701398.0, "step": 42095 }, { "epoch": 0.44914811219101064, "grad_norm": 1.3230128085928494, "learning_rate": 3.30857725857068e-05, "loss": 0.6864, "num_tokens": 251731947.0, "step": 42100 }, { "epoch": 0.4492014551972091, "grad_norm": 1.1028507168989699, "learning_rate": 3.30819276901568e-05, "loss": 0.4892, "num_tokens": 251770043.0, "step": 42105 }, { "epoch": 0.4492547982034075, "grad_norm": 0.7728426293415505, "learning_rate": 3.307808262090869e-05, "loss": 0.4052, "num_tokens": 251792615.0, "step": 42110 }, { "epoch": 0.449308141209606, "grad_norm": 1.0004831539649583, "learning_rate": 3.30742373780821e-05, "loss": 0.6392, "num_tokens": 251833299.0, "step": 42115 }, { "epoch": 0.44936148421580446, "grad_norm": 1.0204283182184128, "learning_rate": 3.307039196179669e-05, "loss": 0.6018, "num_tokens": 251863680.0, "step": 42120 }, { "epoch": 0.44941482722200293, "grad_norm": 1.272818590008942, "learning_rate": 3.306654637217213e-05, "loss": 0.4556, "num_tokens": 251886398.0, "step": 42125 }, { "epoch": 0.4494681702282014, "grad_norm": 0.7193915685808132, "learning_rate": 3.3062700609328076e-05, "loss": 0.4929, "num_tokens": 251918493.0, "step": 42130 }, { "epoch": 0.4495215132343998, "grad_norm": 0.8189383508500206, "learning_rate": 3.305885467338421e-05, "loss": 0.5239, "num_tokens": 251942850.0, "step": 42135 }, { "epoch": 0.4495748562405983, "grad_norm": 0.8466464253615387, "learning_rate": 3.30550085644602e-05, "loss": 0.6623, "num_tokens": 251968839.0, "step": 42140 }, { "epoch": 0.44962819924679676, "grad_norm": 1.3235297850911636, "learning_rate": 3.3051162282675734e-05, "loss": 0.4732, "num_tokens": 251995726.0, "step": 42145 }, { "epoch": 0.4496815422529952, "grad_norm": 0.7568577949748436, "learning_rate": 3.30473158281505e-05, "loss": 0.4678, "num_tokens": 252031522.0, "step": 42150 }, { "epoch": 0.44973488525919364, "grad_norm": 0.5823655828944247, "learning_rate": 3.3043469201004196e-05, "loss": 0.4776, "num_tokens": 252063480.0, "step": 42155 }, { "epoch": 0.4497882282653921, "grad_norm": 0.9104520498280124, "learning_rate": 3.303962240135652e-05, "loss": 0.4967, "num_tokens": 252090634.0, "step": 42160 }, { "epoch": 0.4498415712715906, "grad_norm": 1.0484135047713243, "learning_rate": 3.303577542932716e-05, "loss": 0.4732, "num_tokens": 252122857.0, "step": 42165 }, { "epoch": 0.44989491427778905, "grad_norm": 1.2932399174719416, "learning_rate": 3.303192828503585e-05, "loss": 0.4568, "num_tokens": 252152679.0, "step": 42170 }, { "epoch": 0.4499482572839875, "grad_norm": 0.901275480489698, "learning_rate": 3.3028080968602296e-05, "loss": 0.4427, "num_tokens": 252187978.0, "step": 42175 }, { "epoch": 0.45000160029018593, "grad_norm": 1.7730233432253961, "learning_rate": 3.302423348014621e-05, "loss": 0.5702, "num_tokens": 252222400.0, "step": 42180 }, { "epoch": 0.4500549432963844, "grad_norm": 0.8224516756267537, "learning_rate": 3.302038581978733e-05, "loss": 0.5203, "num_tokens": 252266861.0, "step": 42185 }, { "epoch": 0.45010828630258287, "grad_norm": 0.7540822559323167, "learning_rate": 3.301653798764538e-05, "loss": 0.4159, "num_tokens": 252300161.0, "step": 42190 }, { "epoch": 0.45016162930878134, "grad_norm": 0.728230338035674, "learning_rate": 3.3012689983840105e-05, "loss": 0.555, "num_tokens": 252333101.0, "step": 42195 }, { "epoch": 0.45021497231497976, "grad_norm": 0.8131807299708865, "learning_rate": 3.3008841808491234e-05, "loss": 0.4695, "num_tokens": 252352113.0, "step": 42200 }, { "epoch": 0.4502683153211782, "grad_norm": 0.7074712006414992, "learning_rate": 3.300499346171853e-05, "loss": 0.4576, "num_tokens": 252381295.0, "step": 42205 }, { "epoch": 0.4503216583273767, "grad_norm": 0.7934769522722309, "learning_rate": 3.300114494364173e-05, "loss": 0.4826, "num_tokens": 252418023.0, "step": 42210 }, { "epoch": 0.45037500133357516, "grad_norm": 1.1827300631612114, "learning_rate": 3.2997296254380595e-05, "loss": 0.5932, "num_tokens": 252437585.0, "step": 42215 }, { "epoch": 0.45042834433977363, "grad_norm": 0.9347577540999635, "learning_rate": 3.29934473940549e-05, "loss": 0.5409, "num_tokens": 252483804.0, "step": 42220 }, { "epoch": 0.45048168734597205, "grad_norm": 1.3348613160108154, "learning_rate": 3.29895983627844e-05, "loss": 0.461, "num_tokens": 252506350.0, "step": 42225 }, { "epoch": 0.4505350303521705, "grad_norm": 0.9665729796979574, "learning_rate": 3.2985749160688885e-05, "loss": 0.6015, "num_tokens": 252547672.0, "step": 42230 }, { "epoch": 0.450588373358369, "grad_norm": 0.87606844216736, "learning_rate": 3.2981899787888113e-05, "loss": 0.5572, "num_tokens": 252583698.0, "step": 42235 }, { "epoch": 0.45064171636456746, "grad_norm": 0.9866978468692937, "learning_rate": 3.297805024450188e-05, "loss": 0.5499, "num_tokens": 252607265.0, "step": 42240 }, { "epoch": 0.45069505937076587, "grad_norm": 0.9984148540621992, "learning_rate": 3.297420053064999e-05, "loss": 0.5808, "num_tokens": 252646983.0, "step": 42245 }, { "epoch": 0.45074840237696434, "grad_norm": 0.7456248957634299, "learning_rate": 3.2970350646452207e-05, "loss": 0.6408, "num_tokens": 252679678.0, "step": 42250 }, { "epoch": 0.4508017453831628, "grad_norm": 0.8857899967394559, "learning_rate": 3.2966500592028356e-05, "loss": 0.5884, "num_tokens": 252710984.0, "step": 42255 }, { "epoch": 0.4508550883893613, "grad_norm": 1.287079618600465, "learning_rate": 3.296265036749823e-05, "loss": 0.514, "num_tokens": 252732676.0, "step": 42260 }, { "epoch": 0.45090843139555975, "grad_norm": 0.8503572187558774, "learning_rate": 3.2958799972981655e-05, "loss": 0.5682, "num_tokens": 252772932.0, "step": 42265 }, { "epoch": 0.45096177440175816, "grad_norm": 1.4495399582998043, "learning_rate": 3.295494940859843e-05, "loss": 0.4614, "num_tokens": 252801408.0, "step": 42270 }, { "epoch": 0.45101511740795663, "grad_norm": 1.3431899353271317, "learning_rate": 3.295109867446839e-05, "loss": 0.5041, "num_tokens": 252829799.0, "step": 42275 }, { "epoch": 0.4510684604141551, "grad_norm": 1.3026673631995296, "learning_rate": 3.2947247770711346e-05, "loss": 0.6268, "num_tokens": 252867752.0, "step": 42280 }, { "epoch": 0.4511218034203536, "grad_norm": 1.282578280489633, "learning_rate": 3.294339669744715e-05, "loss": 0.524, "num_tokens": 252910209.0, "step": 42285 }, { "epoch": 0.451175146426552, "grad_norm": 1.785763276220278, "learning_rate": 3.293954545479562e-05, "loss": 0.5317, "num_tokens": 252929406.0, "step": 42290 }, { "epoch": 0.45122848943275046, "grad_norm": 0.9911653158604581, "learning_rate": 3.293569404287662e-05, "loss": 0.5999, "num_tokens": 252956359.0, "step": 42295 }, { "epoch": 0.4512818324389489, "grad_norm": 1.5111639497233367, "learning_rate": 3.293184246180998e-05, "loss": 0.5702, "num_tokens": 252991100.0, "step": 42300 }, { "epoch": 0.4513351754451474, "grad_norm": 1.2260118166646763, "learning_rate": 3.2927990711715564e-05, "loss": 0.5406, "num_tokens": 253020700.0, "step": 42305 }, { "epoch": 0.45138851845134587, "grad_norm": 1.2248065651273374, "learning_rate": 3.292413879271323e-05, "loss": 0.6264, "num_tokens": 253046386.0, "step": 42310 }, { "epoch": 0.4514418614575443, "grad_norm": 0.9767271356925532, "learning_rate": 3.292028670492282e-05, "loss": 0.5273, "num_tokens": 253069695.0, "step": 42315 }, { "epoch": 0.45149520446374275, "grad_norm": 1.0909364540517308, "learning_rate": 3.291643444846424e-05, "loss": 0.5092, "num_tokens": 253097834.0, "step": 42320 }, { "epoch": 0.4515485474699412, "grad_norm": 0.9933280238352424, "learning_rate": 3.291258202345734e-05, "loss": 0.754, "num_tokens": 253138119.0, "step": 42325 }, { "epoch": 0.4516018904761397, "grad_norm": 0.6878358743678964, "learning_rate": 3.2908729430021997e-05, "loss": 0.4956, "num_tokens": 253166333.0, "step": 42330 }, { "epoch": 0.4516552334823381, "grad_norm": 1.181828648474139, "learning_rate": 3.2904876668278114e-05, "loss": 0.6101, "num_tokens": 253186726.0, "step": 42335 }, { "epoch": 0.4517085764885366, "grad_norm": 1.15070335792934, "learning_rate": 3.2901023738345574e-05, "loss": 0.5898, "num_tokens": 253205292.0, "step": 42340 }, { "epoch": 0.45176191949473504, "grad_norm": 0.8570812968031111, "learning_rate": 3.289717064034426e-05, "loss": 0.5412, "num_tokens": 253234320.0, "step": 42345 }, { "epoch": 0.4518152625009335, "grad_norm": 0.9042447063262815, "learning_rate": 3.2893317374394084e-05, "loss": 0.6482, "num_tokens": 253277478.0, "step": 42350 }, { "epoch": 0.451868605507132, "grad_norm": 1.5766951977872796, "learning_rate": 3.288946394061495e-05, "loss": 0.5212, "num_tokens": 253306520.0, "step": 42355 }, { "epoch": 0.4519219485133304, "grad_norm": 2.131044825919245, "learning_rate": 3.2885610339126774e-05, "loss": 0.6943, "num_tokens": 253361347.0, "step": 42360 }, { "epoch": 0.45197529151952887, "grad_norm": 0.6367414369707315, "learning_rate": 3.288175657004946e-05, "loss": 1.0605, "num_tokens": 253394190.0, "step": 42365 }, { "epoch": 0.45202863452572734, "grad_norm": 1.4765307047374452, "learning_rate": 3.287790263350294e-05, "loss": 0.6254, "num_tokens": 253423475.0, "step": 42370 }, { "epoch": 0.4520819775319258, "grad_norm": 2.059857131502025, "learning_rate": 3.2874048529607135e-05, "loss": 0.5655, "num_tokens": 253439970.0, "step": 42375 }, { "epoch": 0.4521353205381242, "grad_norm": 4.334961873530292, "learning_rate": 3.2870194258481976e-05, "loss": 0.5375, "num_tokens": 253465659.0, "step": 42380 }, { "epoch": 0.4521886635443227, "grad_norm": 0.8330980058445048, "learning_rate": 3.286633982024741e-05, "loss": 0.5315, "num_tokens": 253485971.0, "step": 42385 }, { "epoch": 0.45224200655052116, "grad_norm": 1.3872799319848397, "learning_rate": 3.286248521502336e-05, "loss": 0.5999, "num_tokens": 253516011.0, "step": 42390 }, { "epoch": 0.45229534955671963, "grad_norm": 1.540128239991378, "learning_rate": 3.28586304429298e-05, "loss": 0.6482, "num_tokens": 253549667.0, "step": 42395 }, { "epoch": 0.4523486925629181, "grad_norm": 2.035354288968226, "learning_rate": 3.2854775504086655e-05, "loss": 0.5329, "num_tokens": 253576656.0, "step": 42400 }, { "epoch": 0.4524020355691165, "grad_norm": 0.9482273552679233, "learning_rate": 3.285092039861389e-05, "loss": 0.5644, "num_tokens": 253606185.0, "step": 42405 }, { "epoch": 0.452455378575315, "grad_norm": 1.1288439979570017, "learning_rate": 3.284706512663149e-05, "loss": 0.5371, "num_tokens": 253628080.0, "step": 42410 }, { "epoch": 0.45250872158151345, "grad_norm": 0.7841090466148443, "learning_rate": 3.284320968825939e-05, "loss": 0.5227, "num_tokens": 253652294.0, "step": 42415 }, { "epoch": 0.4525620645877119, "grad_norm": 0.9048112477181699, "learning_rate": 3.2839354083617585e-05, "loss": 0.6594, "num_tokens": 253688750.0, "step": 42420 }, { "epoch": 0.45261540759391033, "grad_norm": 0.6508354964460671, "learning_rate": 3.2835498312826054e-05, "loss": 0.5759, "num_tokens": 253723446.0, "step": 42425 }, { "epoch": 0.4526687506001088, "grad_norm": 1.3632409522118836, "learning_rate": 3.283164237600478e-05, "loss": 0.405, "num_tokens": 253735763.0, "step": 42430 }, { "epoch": 0.4527220936063073, "grad_norm": 0.6373503809760974, "learning_rate": 3.282778627327373e-05, "loss": 0.4647, "num_tokens": 253760160.0, "step": 42435 }, { "epoch": 0.45277543661250574, "grad_norm": 0.988008015564886, "learning_rate": 3.282393000475293e-05, "loss": 0.4859, "num_tokens": 253780415.0, "step": 42440 }, { "epoch": 0.4528287796187042, "grad_norm": 1.2555253402185647, "learning_rate": 3.2820073570562356e-05, "loss": 0.5918, "num_tokens": 253806284.0, "step": 42445 }, { "epoch": 0.4528821226249026, "grad_norm": 1.1218684040008045, "learning_rate": 3.2816216970822025e-05, "loss": 0.5056, "num_tokens": 253831805.0, "step": 42450 }, { "epoch": 0.4529354656311011, "grad_norm": 1.0219782833024602, "learning_rate": 3.281236020565194e-05, "loss": 0.5743, "num_tokens": 253862380.0, "step": 42455 }, { "epoch": 0.45298880863729957, "grad_norm": 0.8211593867019038, "learning_rate": 3.2808503275172115e-05, "loss": 0.487, "num_tokens": 253886941.0, "step": 42460 }, { "epoch": 0.45304215164349804, "grad_norm": 0.9073465476813567, "learning_rate": 3.280464617950257e-05, "loss": 0.5633, "num_tokens": 253918603.0, "step": 42465 }, { "epoch": 0.45309549464969645, "grad_norm": 0.7183279132066428, "learning_rate": 3.2800788918763336e-05, "loss": 0.5563, "num_tokens": 253955130.0, "step": 42470 }, { "epoch": 0.4531488376558949, "grad_norm": 2.529880230143276, "learning_rate": 3.279693149307444e-05, "loss": 0.5127, "num_tokens": 253980834.0, "step": 42475 }, { "epoch": 0.4532021806620934, "grad_norm": 0.7985220103785695, "learning_rate": 3.279307390255591e-05, "loss": 0.4939, "num_tokens": 254005194.0, "step": 42480 }, { "epoch": 0.45325552366829186, "grad_norm": 0.7532096224347459, "learning_rate": 3.27892161473278e-05, "loss": 0.546, "num_tokens": 254023586.0, "step": 42485 }, { "epoch": 0.45330886667449033, "grad_norm": 0.9663886198398521, "learning_rate": 3.278535822751014e-05, "loss": 0.4974, "num_tokens": 254051961.0, "step": 42490 }, { "epoch": 0.45336220968068874, "grad_norm": 0.6845448258162973, "learning_rate": 3.278150014322299e-05, "loss": 0.4903, "num_tokens": 254084428.0, "step": 42495 }, { "epoch": 0.4534155526868872, "grad_norm": 1.0225407355099045, "learning_rate": 3.277764189458641e-05, "loss": 0.4765, "num_tokens": 254108479.0, "step": 42500 }, { "epoch": 0.4534688956930857, "grad_norm": 0.5491025092311278, "learning_rate": 3.277378348172045e-05, "loss": 0.4722, "num_tokens": 254159047.0, "step": 42505 }, { "epoch": 0.45352223869928415, "grad_norm": 0.7348321902857328, "learning_rate": 3.276992490474518e-05, "loss": 0.4279, "num_tokens": 254191284.0, "step": 42510 }, { "epoch": 0.45357558170548257, "grad_norm": 0.843720686794366, "learning_rate": 3.276606616378068e-05, "loss": 0.6499, "num_tokens": 254229091.0, "step": 42515 }, { "epoch": 0.45362892471168104, "grad_norm": 0.9079537458067607, "learning_rate": 3.276220725894701e-05, "loss": 0.5629, "num_tokens": 254269618.0, "step": 42520 }, { "epoch": 0.4536822677178795, "grad_norm": 1.0885205852418227, "learning_rate": 3.275834819036427e-05, "loss": 0.5456, "num_tokens": 254303474.0, "step": 42525 }, { "epoch": 0.453735610724078, "grad_norm": 1.089449163418715, "learning_rate": 3.2754488958152516e-05, "loss": 0.5568, "num_tokens": 254324560.0, "step": 42530 }, { "epoch": 0.45378895373027645, "grad_norm": 0.875784998744459, "learning_rate": 3.2750629562431866e-05, "loss": 0.4858, "num_tokens": 254343315.0, "step": 42535 }, { "epoch": 0.45384229673647486, "grad_norm": 0.7342960003225112, "learning_rate": 3.2746770003322416e-05, "loss": 0.5745, "num_tokens": 254381453.0, "step": 42540 }, { "epoch": 0.45389563974267333, "grad_norm": 1.9480400719569715, "learning_rate": 3.274291028094426e-05, "loss": 0.5694, "num_tokens": 254409217.0, "step": 42545 }, { "epoch": 0.4539489827488718, "grad_norm": 0.8336439906660557, "learning_rate": 3.27390503954175e-05, "loss": 0.5122, "num_tokens": 254431862.0, "step": 42550 }, { "epoch": 0.45400232575507027, "grad_norm": 1.056100385886691, "learning_rate": 3.273519034686225e-05, "loss": 0.5418, "num_tokens": 254465155.0, "step": 42555 }, { "epoch": 0.4540556687612687, "grad_norm": 1.2614323997244667, "learning_rate": 3.273133013539864e-05, "loss": 0.533, "num_tokens": 254497259.0, "step": 42560 }, { "epoch": 0.45410901176746715, "grad_norm": 1.6354426646111668, "learning_rate": 3.272746976114677e-05, "loss": 0.5502, "num_tokens": 254516825.0, "step": 42565 }, { "epoch": 0.4541623547736656, "grad_norm": 2.0735916965573, "learning_rate": 3.272360922422679e-05, "loss": 0.5279, "num_tokens": 254547887.0, "step": 42570 }, { "epoch": 0.4542156977798641, "grad_norm": 0.9710175671725123, "learning_rate": 3.271974852475882e-05, "loss": 0.577, "num_tokens": 254580409.0, "step": 42575 }, { "epoch": 0.45426904078606256, "grad_norm": 0.6222031775267154, "learning_rate": 3.271588766286299e-05, "loss": 0.4757, "num_tokens": 254606668.0, "step": 42580 }, { "epoch": 0.454322383792261, "grad_norm": 2.000839533927793, "learning_rate": 3.271202663865945e-05, "loss": 0.6076, "num_tokens": 254621528.0, "step": 42585 }, { "epoch": 0.45437572679845945, "grad_norm": 0.8837394025179637, "learning_rate": 3.2708165452268354e-05, "loss": 0.6624, "num_tokens": 254649181.0, "step": 42590 }, { "epoch": 0.4544290698046579, "grad_norm": 1.1006828415313943, "learning_rate": 3.270430410380984e-05, "loss": 0.6424, "num_tokens": 254673531.0, "step": 42595 }, { "epoch": 0.4544824128108564, "grad_norm": 2.5569460465329, "learning_rate": 3.2700442593404074e-05, "loss": 0.5483, "num_tokens": 254695213.0, "step": 42600 }, { "epoch": 0.4545357558170548, "grad_norm": 0.9657929784681362, "learning_rate": 3.269658092117122e-05, "loss": 0.5327, "num_tokens": 254714221.0, "step": 42605 }, { "epoch": 0.45458909882325327, "grad_norm": 0.8326892874356565, "learning_rate": 3.269271908723144e-05, "loss": 0.4744, "num_tokens": 254749418.0, "step": 42610 }, { "epoch": 0.45464244182945174, "grad_norm": 2.847122289221398, "learning_rate": 3.26888570917049e-05, "loss": 0.6505, "num_tokens": 254767084.0, "step": 42615 }, { "epoch": 0.4546957848356502, "grad_norm": 0.8022681975319373, "learning_rate": 3.26849949347118e-05, "loss": 0.6093, "num_tokens": 254802676.0, "step": 42620 }, { "epoch": 0.4547491278418487, "grad_norm": 0.9433398939485149, "learning_rate": 3.26811326163723e-05, "loss": 0.4639, "num_tokens": 254822611.0, "step": 42625 }, { "epoch": 0.4548024708480471, "grad_norm": 0.7786805300175039, "learning_rate": 3.26772701368066e-05, "loss": 0.5979, "num_tokens": 254891225.0, "step": 42630 }, { "epoch": 0.45485581385424556, "grad_norm": 0.5696748666796553, "learning_rate": 3.267340749613488e-05, "loss": 0.5363, "num_tokens": 254940610.0, "step": 42635 }, { "epoch": 0.45490915686044403, "grad_norm": 0.8604101555200504, "learning_rate": 3.266954469447734e-05, "loss": 0.5373, "num_tokens": 254973908.0, "step": 42640 }, { "epoch": 0.4549624998666425, "grad_norm": 0.7603326608367347, "learning_rate": 3.266568173195421e-05, "loss": 0.5411, "num_tokens": 254995010.0, "step": 42645 }, { "epoch": 0.4550158428728409, "grad_norm": 1.5383117668918167, "learning_rate": 3.2661818608685664e-05, "loss": 0.7517, "num_tokens": 255023564.0, "step": 42650 }, { "epoch": 0.4550691858790394, "grad_norm": 2.0265141962095576, "learning_rate": 3.265795532479192e-05, "loss": 0.5452, "num_tokens": 255065549.0, "step": 42655 }, { "epoch": 0.45512252888523785, "grad_norm": 0.8332237372896466, "learning_rate": 3.26540918803932e-05, "loss": 0.5089, "num_tokens": 255090279.0, "step": 42660 }, { "epoch": 0.4551758718914363, "grad_norm": 0.9408531089970156, "learning_rate": 3.265022827560973e-05, "loss": 0.5912, "num_tokens": 255138642.0, "step": 42665 }, { "epoch": 0.4552292148976348, "grad_norm": 0.6853213803171776, "learning_rate": 3.264636451056174e-05, "loss": 0.4714, "num_tokens": 255175231.0, "step": 42670 }, { "epoch": 0.4552825579038332, "grad_norm": 1.5223029265739252, "learning_rate": 3.264250058536946e-05, "loss": 0.7224, "num_tokens": 255203926.0, "step": 42675 }, { "epoch": 0.4553359009100317, "grad_norm": 0.8652553188744305, "learning_rate": 3.2638636500153116e-05, "loss": 0.4731, "num_tokens": 255230403.0, "step": 42680 }, { "epoch": 0.45538924391623015, "grad_norm": 0.8756200226456461, "learning_rate": 3.263477225503296e-05, "loss": 0.5089, "num_tokens": 255262480.0, "step": 42685 }, { "epoch": 0.4554425869224286, "grad_norm": 1.4344112529027735, "learning_rate": 3.263090785012924e-05, "loss": 0.5511, "num_tokens": 255295196.0, "step": 42690 }, { "epoch": 0.45549592992862703, "grad_norm": 0.905589894018169, "learning_rate": 3.262704328556221e-05, "loss": 0.5248, "num_tokens": 255322444.0, "step": 42695 }, { "epoch": 0.4555492729348255, "grad_norm": 1.8620984765642932, "learning_rate": 3.262317856145212e-05, "loss": 0.6382, "num_tokens": 255343578.0, "step": 42700 }, { "epoch": 0.45560261594102397, "grad_norm": 0.8973379642477067, "learning_rate": 3.261931367791924e-05, "loss": 0.6148, "num_tokens": 255371046.0, "step": 42705 }, { "epoch": 0.45565595894722244, "grad_norm": 1.0698246667848363, "learning_rate": 3.261544863508383e-05, "loss": 0.4549, "num_tokens": 255396208.0, "step": 42710 }, { "epoch": 0.4557093019534209, "grad_norm": 1.9200403630193525, "learning_rate": 3.2611583433066165e-05, "loss": 0.5443, "num_tokens": 255414328.0, "step": 42715 }, { "epoch": 0.4557626449596193, "grad_norm": 0.7399332978479799, "learning_rate": 3.260771807198653e-05, "loss": 0.5214, "num_tokens": 255433548.0, "step": 42720 }, { "epoch": 0.4558159879658178, "grad_norm": 1.6460286605735786, "learning_rate": 3.2603852551965195e-05, "loss": 0.5372, "num_tokens": 255465465.0, "step": 42725 }, { "epoch": 0.45586933097201626, "grad_norm": 1.4243885787269663, "learning_rate": 3.259998687312245e-05, "loss": 0.5206, "num_tokens": 255489444.0, "step": 42730 }, { "epoch": 0.45592267397821473, "grad_norm": 1.0802740189584603, "learning_rate": 3.259612103557859e-05, "loss": 0.6949, "num_tokens": 255532737.0, "step": 42735 }, { "epoch": 0.45597601698441315, "grad_norm": 0.7360818954264577, "learning_rate": 3.259225503945392e-05, "loss": 0.5104, "num_tokens": 255555430.0, "step": 42740 }, { "epoch": 0.4560293599906116, "grad_norm": 0.8705879661896854, "learning_rate": 3.258838888486872e-05, "loss": 0.4566, "num_tokens": 255583735.0, "step": 42745 }, { "epoch": 0.4560827029968101, "grad_norm": 1.1745989278163962, "learning_rate": 3.2584522571943324e-05, "loss": 0.4958, "num_tokens": 255614276.0, "step": 42750 }, { "epoch": 0.45613604600300856, "grad_norm": 1.458308003474874, "learning_rate": 3.2580656100798016e-05, "loss": 0.5402, "num_tokens": 255640249.0, "step": 42755 }, { "epoch": 0.456189389009207, "grad_norm": 1.0113155644791008, "learning_rate": 3.2576789471553135e-05, "loss": 0.6895, "num_tokens": 255669614.0, "step": 42760 }, { "epoch": 0.45624273201540544, "grad_norm": 0.8195412191263709, "learning_rate": 3.257292268432899e-05, "loss": 0.414, "num_tokens": 255685734.0, "step": 42765 }, { "epoch": 0.4562960750216039, "grad_norm": 0.6991708610257245, "learning_rate": 3.2569055739245914e-05, "loss": 0.6039, "num_tokens": 255727047.0, "step": 42770 }, { "epoch": 0.4563494180278024, "grad_norm": 0.6220989288660803, "learning_rate": 3.2565188636424234e-05, "loss": 0.6643, "num_tokens": 255779313.0, "step": 42775 }, { "epoch": 0.45640276103400085, "grad_norm": 0.736695107122571, "learning_rate": 3.256132137598429e-05, "loss": 0.5607, "num_tokens": 255815255.0, "step": 42780 }, { "epoch": 0.45645610404019926, "grad_norm": 0.8507369048002106, "learning_rate": 3.255745395804641e-05, "loss": 0.6005, "num_tokens": 255850567.0, "step": 42785 }, { "epoch": 0.45650944704639773, "grad_norm": 1.0280719776656875, "learning_rate": 3.255358638273096e-05, "loss": 0.6439, "num_tokens": 255899836.0, "step": 42790 }, { "epoch": 0.4565627900525962, "grad_norm": 1.2547599106876155, "learning_rate": 3.254971865015829e-05, "loss": 0.6517, "num_tokens": 255920767.0, "step": 42795 }, { "epoch": 0.45661613305879467, "grad_norm": 1.577981668329304, "learning_rate": 3.254585076044874e-05, "loss": 0.5694, "num_tokens": 255970179.0, "step": 42800 }, { "epoch": 0.45666947606499314, "grad_norm": 0.990927816686169, "learning_rate": 3.2541982713722665e-05, "loss": 0.5473, "num_tokens": 255995031.0, "step": 42805 }, { "epoch": 0.45672281907119155, "grad_norm": 1.0195603239734732, "learning_rate": 3.2538114510100464e-05, "loss": 0.4819, "num_tokens": 256012179.0, "step": 42810 }, { "epoch": 0.45677616207739, "grad_norm": 0.5980763336714391, "learning_rate": 3.2534246149702486e-05, "loss": 0.5045, "num_tokens": 256048334.0, "step": 42815 }, { "epoch": 0.4568295050835885, "grad_norm": 1.0962461848087506, "learning_rate": 3.25303776326491e-05, "loss": 0.5834, "num_tokens": 256072360.0, "step": 42820 }, { "epoch": 0.45688284808978696, "grad_norm": 1.1593357662246282, "learning_rate": 3.25265089590607e-05, "loss": 0.435, "num_tokens": 256092946.0, "step": 42825 }, { "epoch": 0.4569361910959854, "grad_norm": 1.0230689766685332, "learning_rate": 3.252264012905766e-05, "loss": 0.6394, "num_tokens": 256117405.0, "step": 42830 }, { "epoch": 0.45698953410218385, "grad_norm": 1.0968688048056892, "learning_rate": 3.251877114276038e-05, "loss": 0.5485, "num_tokens": 256144675.0, "step": 42835 }, { "epoch": 0.4570428771083823, "grad_norm": 1.143098013967946, "learning_rate": 3.251490200028925e-05, "loss": 0.4615, "num_tokens": 256169122.0, "step": 42840 }, { "epoch": 0.4570962201145808, "grad_norm": 0.907668139605757, "learning_rate": 3.2511032701764684e-05, "loss": 0.4577, "num_tokens": 256198302.0, "step": 42845 }, { "epoch": 0.45714956312077926, "grad_norm": 1.1408006844792566, "learning_rate": 3.2507163247307056e-05, "loss": 0.4172, "num_tokens": 256216662.0, "step": 42850 }, { "epoch": 0.45720290612697767, "grad_norm": 0.5774189246744998, "learning_rate": 3.2503293637036795e-05, "loss": 0.6954, "num_tokens": 256256547.0, "step": 42855 }, { "epoch": 0.45725624913317614, "grad_norm": 1.3975095603065095, "learning_rate": 3.2499423871074316e-05, "loss": 0.4549, "num_tokens": 256290022.0, "step": 42860 }, { "epoch": 0.4573095921393746, "grad_norm": 1.0902269821491135, "learning_rate": 3.249555394954004e-05, "loss": 0.7176, "num_tokens": 256328966.0, "step": 42865 }, { "epoch": 0.4573629351455731, "grad_norm": 0.8406300456100768, "learning_rate": 3.249168387255439e-05, "loss": 0.6306, "num_tokens": 256374131.0, "step": 42870 }, { "epoch": 0.4574162781517715, "grad_norm": 0.7898082371941757, "learning_rate": 3.248781364023778e-05, "loss": 0.4269, "num_tokens": 256392340.0, "step": 42875 }, { "epoch": 0.45746962115796996, "grad_norm": 0.8837509347446347, "learning_rate": 3.2483943252710654e-05, "loss": 0.4804, "num_tokens": 256417909.0, "step": 42880 }, { "epoch": 0.45752296416416843, "grad_norm": 1.6004770405224387, "learning_rate": 3.2480072710093454e-05, "loss": 0.657, "num_tokens": 256438012.0, "step": 42885 }, { "epoch": 0.4575763071703669, "grad_norm": 0.6911115511474536, "learning_rate": 3.247620201250662e-05, "loss": 0.4684, "num_tokens": 256460837.0, "step": 42890 }, { "epoch": 0.4576296501765654, "grad_norm": 0.7912827845400681, "learning_rate": 3.247233116007061e-05, "loss": 0.497, "num_tokens": 256491843.0, "step": 42895 }, { "epoch": 0.4576829931827638, "grad_norm": 0.9131617529511774, "learning_rate": 3.246846015290585e-05, "loss": 0.5832, "num_tokens": 256524208.0, "step": 42900 }, { "epoch": 0.45773633618896226, "grad_norm": 0.8524754044366166, "learning_rate": 3.246458899113283e-05, "loss": 0.654, "num_tokens": 256562267.0, "step": 42905 }, { "epoch": 0.4577896791951607, "grad_norm": 0.8290428241933953, "learning_rate": 3.2460717674871995e-05, "loss": 0.612, "num_tokens": 256592467.0, "step": 42910 }, { "epoch": 0.4578430222013592, "grad_norm": 0.7571134034766119, "learning_rate": 3.245684620424382e-05, "loss": 0.4941, "num_tokens": 256626887.0, "step": 42915 }, { "epoch": 0.4578963652075576, "grad_norm": 0.6941278884235687, "learning_rate": 3.245297457936876e-05, "loss": 0.568, "num_tokens": 256662243.0, "step": 42920 }, { "epoch": 0.4579497082137561, "grad_norm": 0.9087458770619589, "learning_rate": 3.244910280036731e-05, "loss": 0.3971, "num_tokens": 256694594.0, "step": 42925 }, { "epoch": 0.45800305121995455, "grad_norm": 1.3203574972518723, "learning_rate": 3.244523086735996e-05, "loss": 0.5341, "num_tokens": 256713393.0, "step": 42930 }, { "epoch": 0.458056394226153, "grad_norm": 0.8621759718808332, "learning_rate": 3.2441358780467165e-05, "loss": 0.4935, "num_tokens": 256742178.0, "step": 42935 }, { "epoch": 0.4581097372323515, "grad_norm": 0.9426860540821791, "learning_rate": 3.243748653980944e-05, "loss": 0.5666, "num_tokens": 256786648.0, "step": 42940 }, { "epoch": 0.4581630802385499, "grad_norm": 0.7138666000486276, "learning_rate": 3.243361414550728e-05, "loss": 0.4794, "num_tokens": 256815003.0, "step": 42945 }, { "epoch": 0.45821642324474837, "grad_norm": 0.8966460917362788, "learning_rate": 3.242974159768118e-05, "loss": 0.4862, "num_tokens": 256835801.0, "step": 42950 }, { "epoch": 0.45826976625094684, "grad_norm": 1.16834435927648, "learning_rate": 3.242586889645164e-05, "loss": 0.4689, "num_tokens": 256858972.0, "step": 42955 }, { "epoch": 0.4583231092571453, "grad_norm": 1.1740996464175213, "learning_rate": 3.2421996041939194e-05, "loss": 0.5584, "num_tokens": 256884308.0, "step": 42960 }, { "epoch": 0.4583764522633437, "grad_norm": 0.6884053283256921, "learning_rate": 3.241812303426432e-05, "loss": 0.6161, "num_tokens": 256918688.0, "step": 42965 }, { "epoch": 0.4584297952695422, "grad_norm": 0.8989000515479495, "learning_rate": 3.241424987354758e-05, "loss": 0.4486, "num_tokens": 256948570.0, "step": 42970 }, { "epoch": 0.45848313827574066, "grad_norm": 1.004417424864672, "learning_rate": 3.2410376559909464e-05, "loss": 0.5434, "num_tokens": 256981721.0, "step": 42975 }, { "epoch": 0.45853648128193913, "grad_norm": 0.6258335792552138, "learning_rate": 3.2406503093470516e-05, "loss": 0.5532, "num_tokens": 257016806.0, "step": 42980 }, { "epoch": 0.4585898242881376, "grad_norm": 0.7238800087386381, "learning_rate": 3.2402629474351284e-05, "loss": 0.4665, "num_tokens": 257044773.0, "step": 42985 }, { "epoch": 0.458643167294336, "grad_norm": 1.2475027144225581, "learning_rate": 3.239875570267228e-05, "loss": 0.4804, "num_tokens": 257064090.0, "step": 42990 }, { "epoch": 0.4586965103005345, "grad_norm": 0.8684627392735362, "learning_rate": 3.2394881778554066e-05, "loss": 0.5196, "num_tokens": 257092632.0, "step": 42995 }, { "epoch": 0.45874985330673296, "grad_norm": 0.7426720751301259, "learning_rate": 3.2391007702117185e-05, "loss": 0.6771, "num_tokens": 257123722.0, "step": 43000 }, { "epoch": 0.4588031963129314, "grad_norm": 1.7052253050592252, "learning_rate": 3.238713347348219e-05, "loss": 0.5835, "num_tokens": 257158766.0, "step": 43005 }, { "epoch": 0.45885653931912984, "grad_norm": 0.680378760568, "learning_rate": 3.2383259092769644e-05, "loss": 0.5021, "num_tokens": 257185530.0, "step": 43010 }, { "epoch": 0.4589098823253283, "grad_norm": 1.74258946336084, "learning_rate": 3.2379384560100096e-05, "loss": 0.5559, "num_tokens": 257201993.0, "step": 43015 }, { "epoch": 0.4589632253315268, "grad_norm": 1.1106802284227537, "learning_rate": 3.2375509875594126e-05, "loss": 0.4957, "num_tokens": 257224253.0, "step": 43020 }, { "epoch": 0.45901656833772525, "grad_norm": 1.2307148482173291, "learning_rate": 3.23716350393723e-05, "loss": 0.6642, "num_tokens": 257252902.0, "step": 43025 }, { "epoch": 0.4590699113439237, "grad_norm": 1.702435850471613, "learning_rate": 3.236776005155521e-05, "loss": 0.5549, "num_tokens": 257282178.0, "step": 43030 }, { "epoch": 0.45912325435012213, "grad_norm": 0.7231151950872434, "learning_rate": 3.236388491226342e-05, "loss": 0.4826, "num_tokens": 257318839.0, "step": 43035 }, { "epoch": 0.4591765973563206, "grad_norm": 1.0514486297254777, "learning_rate": 3.2360009621617524e-05, "loss": 0.5326, "num_tokens": 257341926.0, "step": 43040 }, { "epoch": 0.4592299403625191, "grad_norm": 1.0178892489681999, "learning_rate": 3.235613417973811e-05, "loss": 0.4955, "num_tokens": 257379058.0, "step": 43045 }, { "epoch": 0.45928328336871754, "grad_norm": 0.7378588482396677, "learning_rate": 3.235225858674578e-05, "loss": 0.5014, "num_tokens": 257430386.0, "step": 43050 }, { "epoch": 0.45933662637491596, "grad_norm": 1.1198345560492553, "learning_rate": 3.234838284276112e-05, "loss": 0.5765, "num_tokens": 257446862.0, "step": 43055 }, { "epoch": 0.4593899693811144, "grad_norm": 0.7856861749267885, "learning_rate": 3.234450694790474e-05, "loss": 0.5129, "num_tokens": 257482704.0, "step": 43060 }, { "epoch": 0.4594433123873129, "grad_norm": 1.135577577791172, "learning_rate": 3.234063090229726e-05, "loss": 0.452, "num_tokens": 257511273.0, "step": 43065 }, { "epoch": 0.45949665539351137, "grad_norm": 0.6010418652103517, "learning_rate": 3.23367547060593e-05, "loss": 0.4534, "num_tokens": 257544724.0, "step": 43070 }, { "epoch": 0.45954999839970984, "grad_norm": 0.7149166126859337, "learning_rate": 3.233287835931146e-05, "loss": 0.8064, "num_tokens": 257590197.0, "step": 43075 }, { "epoch": 0.45960334140590825, "grad_norm": 0.6134347541233588, "learning_rate": 3.232900186217438e-05, "loss": 0.5497, "num_tokens": 257626393.0, "step": 43080 }, { "epoch": 0.4596566844121067, "grad_norm": 0.8755678430479518, "learning_rate": 3.232512521476867e-05, "loss": 0.55, "num_tokens": 257653415.0, "step": 43085 }, { "epoch": 0.4597100274183052, "grad_norm": 1.155749373243832, "learning_rate": 3.232124841721498e-05, "loss": 0.5822, "num_tokens": 257679326.0, "step": 43090 }, { "epoch": 0.45976337042450366, "grad_norm": 0.8996255861329088, "learning_rate": 3.231737146963394e-05, "loss": 0.4937, "num_tokens": 257702677.0, "step": 43095 }, { "epoch": 0.4598167134307021, "grad_norm": 0.7982138607398642, "learning_rate": 3.2313494372146194e-05, "loss": 0.5202, "num_tokens": 257745939.0, "step": 43100 }, { "epoch": 0.45987005643690054, "grad_norm": 0.6875255614731752, "learning_rate": 3.2309617124872395e-05, "loss": 0.6069, "num_tokens": 257797100.0, "step": 43105 }, { "epoch": 0.459923399443099, "grad_norm": 0.9970692246470868, "learning_rate": 3.230573972793319e-05, "loss": 0.531, "num_tokens": 257837231.0, "step": 43110 }, { "epoch": 0.4599767424492975, "grad_norm": 1.3276754760474305, "learning_rate": 3.230186218144923e-05, "loss": 0.5687, "num_tokens": 257877795.0, "step": 43115 }, { "epoch": 0.46003008545549595, "grad_norm": 0.8807507365936472, "learning_rate": 3.229798448554119e-05, "loss": 0.5691, "num_tokens": 257907945.0, "step": 43120 }, { "epoch": 0.46008342846169437, "grad_norm": 0.6642979315667281, "learning_rate": 3.2294106640329725e-05, "loss": 0.5013, "num_tokens": 257937883.0, "step": 43125 }, { "epoch": 0.46013677146789284, "grad_norm": 0.9548674419595686, "learning_rate": 3.22902286459355e-05, "loss": 0.5322, "num_tokens": 257961828.0, "step": 43130 }, { "epoch": 0.4601901144740913, "grad_norm": 1.2865038201830261, "learning_rate": 3.2286350502479216e-05, "loss": 0.6532, "num_tokens": 257979291.0, "step": 43135 }, { "epoch": 0.4602434574802898, "grad_norm": 0.7321512926426181, "learning_rate": 3.228247221008152e-05, "loss": 0.5461, "num_tokens": 258022503.0, "step": 43140 }, { "epoch": 0.4602968004864882, "grad_norm": 1.4782433666685022, "learning_rate": 3.2278593768863116e-05, "loss": 0.542, "num_tokens": 258045233.0, "step": 43145 }, { "epoch": 0.46035014349268666, "grad_norm": 1.103695066776709, "learning_rate": 3.22747151789447e-05, "loss": 0.6311, "num_tokens": 258076826.0, "step": 43150 }, { "epoch": 0.46040348649888513, "grad_norm": 1.0404321209646241, "learning_rate": 3.227083644044694e-05, "loss": 0.6084, "num_tokens": 258128399.0, "step": 43155 }, { "epoch": 0.4604568295050836, "grad_norm": 0.7912852561379571, "learning_rate": 3.226695755349056e-05, "loss": 0.4343, "num_tokens": 258165854.0, "step": 43160 }, { "epoch": 0.46051017251128207, "grad_norm": 1.1989908038906856, "learning_rate": 3.226307851819626e-05, "loss": 0.5168, "num_tokens": 258191844.0, "step": 43165 }, { "epoch": 0.4605635155174805, "grad_norm": 0.6353404592012226, "learning_rate": 3.225919933468472e-05, "loss": 0.3843, "num_tokens": 258222692.0, "step": 43170 }, { "epoch": 0.46061685852367895, "grad_norm": 0.9314846989036007, "learning_rate": 3.2255320003076685e-05, "loss": 0.6316, "num_tokens": 258256733.0, "step": 43175 }, { "epoch": 0.4606702015298774, "grad_norm": 0.7405952919647257, "learning_rate": 3.225144052349286e-05, "loss": 0.4365, "num_tokens": 258289065.0, "step": 43180 }, { "epoch": 0.4607235445360759, "grad_norm": 0.7149501909947548, "learning_rate": 3.2247560896053966e-05, "loss": 0.4302, "num_tokens": 258310390.0, "step": 43185 }, { "epoch": 0.4607768875422743, "grad_norm": 1.2053411985496152, "learning_rate": 3.2243681120880715e-05, "loss": 0.4096, "num_tokens": 258334981.0, "step": 43190 }, { "epoch": 0.4608302305484728, "grad_norm": 0.9793595617064325, "learning_rate": 3.2239801198093866e-05, "loss": 0.4742, "num_tokens": 258352221.0, "step": 43195 }, { "epoch": 0.46088357355467124, "grad_norm": 0.8374310259648091, "learning_rate": 3.223592112781413e-05, "loss": 0.548, "num_tokens": 258396985.0, "step": 43200 }, { "epoch": 0.4609369165608697, "grad_norm": 1.3161695656029844, "learning_rate": 3.223204091016227e-05, "loss": 0.5316, "num_tokens": 258425029.0, "step": 43205 }, { "epoch": 0.4609902595670682, "grad_norm": 0.9197341133335173, "learning_rate": 3.2228160545258996e-05, "loss": 0.3994, "num_tokens": 258451303.0, "step": 43210 }, { "epoch": 0.4610436025732666, "grad_norm": 0.9609962142407974, "learning_rate": 3.22242800332251e-05, "loss": 0.5076, "num_tokens": 258482906.0, "step": 43215 }, { "epoch": 0.46109694557946507, "grad_norm": 1.0188843734653106, "learning_rate": 3.2220399374181295e-05, "loss": 0.5467, "num_tokens": 258507458.0, "step": 43220 }, { "epoch": 0.46115028858566354, "grad_norm": 0.6163258135602108, "learning_rate": 3.2216518568248365e-05, "loss": 0.5177, "num_tokens": 258546435.0, "step": 43225 }, { "epoch": 0.461203631591862, "grad_norm": 0.8390968050534339, "learning_rate": 3.221263761554707e-05, "loss": 0.4108, "num_tokens": 258573492.0, "step": 43230 }, { "epoch": 0.4612569745980604, "grad_norm": 1.273959182537998, "learning_rate": 3.2208756516198163e-05, "loss": 0.5219, "num_tokens": 258595335.0, "step": 43235 }, { "epoch": 0.4613103176042589, "grad_norm": 0.974632751351102, "learning_rate": 3.220487527032243e-05, "loss": 0.5628, "num_tokens": 258611954.0, "step": 43240 }, { "epoch": 0.46136366061045736, "grad_norm": 0.7791153964332901, "learning_rate": 3.220099387804065e-05, "loss": 0.6215, "num_tokens": 258648849.0, "step": 43245 }, { "epoch": 0.46141700361665583, "grad_norm": 1.9330210683380475, "learning_rate": 3.219711233947359e-05, "loss": 0.691, "num_tokens": 258673407.0, "step": 43250 }, { "epoch": 0.4614703466228543, "grad_norm": 1.3413188359800903, "learning_rate": 3.219323065474204e-05, "loss": 0.5911, "num_tokens": 258702395.0, "step": 43255 }, { "epoch": 0.4615236896290527, "grad_norm": 1.7578349232015817, "learning_rate": 3.2189348823966795e-05, "loss": 0.5974, "num_tokens": 258729391.0, "step": 43260 }, { "epoch": 0.4615770326352512, "grad_norm": 0.6451380962984636, "learning_rate": 3.218546684726864e-05, "loss": 0.4336, "num_tokens": 258751510.0, "step": 43265 }, { "epoch": 0.46163037564144965, "grad_norm": 0.8974434933696628, "learning_rate": 3.2181584724768397e-05, "loss": 0.4863, "num_tokens": 258776192.0, "step": 43270 }, { "epoch": 0.4616837186476481, "grad_norm": 0.7163728053003996, "learning_rate": 3.2177702456586836e-05, "loss": 0.4135, "num_tokens": 258810368.0, "step": 43275 }, { "epoch": 0.46173706165384654, "grad_norm": 1.1044426677074592, "learning_rate": 3.2173820042844785e-05, "loss": 0.762, "num_tokens": 258855459.0, "step": 43280 }, { "epoch": 0.461790404660045, "grad_norm": 1.470021457877225, "learning_rate": 3.216993748366306e-05, "loss": 0.4947, "num_tokens": 258886124.0, "step": 43285 }, { "epoch": 0.4618437476662435, "grad_norm": 1.7555160625375057, "learning_rate": 3.216605477916248e-05, "loss": 0.4905, "num_tokens": 258919920.0, "step": 43290 }, { "epoch": 0.46189709067244195, "grad_norm": 0.6893333824527967, "learning_rate": 3.2162171929463845e-05, "loss": 0.609, "num_tokens": 258960282.0, "step": 43295 }, { "epoch": 0.4619504336786404, "grad_norm": 0.7930009300696785, "learning_rate": 3.215828893468801e-05, "loss": 0.4287, "num_tokens": 258987636.0, "step": 43300 }, { "epoch": 0.46200377668483883, "grad_norm": 1.6589243145049795, "learning_rate": 3.215440579495578e-05, "loss": 0.6507, "num_tokens": 259037408.0, "step": 43305 }, { "epoch": 0.4620571196910373, "grad_norm": 0.7735066768886051, "learning_rate": 3.215052251038801e-05, "loss": 0.4837, "num_tokens": 259065865.0, "step": 43310 }, { "epoch": 0.46211046269723577, "grad_norm": 2.0888402426851638, "learning_rate": 3.214663908110553e-05, "loss": 0.6815, "num_tokens": 259113320.0, "step": 43315 }, { "epoch": 0.46216380570343424, "grad_norm": 1.8465761939683258, "learning_rate": 3.2142755507229184e-05, "loss": 0.5494, "num_tokens": 259142484.0, "step": 43320 }, { "epoch": 0.46221714870963265, "grad_norm": 0.8545617638035166, "learning_rate": 3.2138871788879825e-05, "loss": 0.516, "num_tokens": 259167697.0, "step": 43325 }, { "epoch": 0.4622704917158311, "grad_norm": 1.0085871258246968, "learning_rate": 3.21349879261783e-05, "loss": 0.5127, "num_tokens": 259203449.0, "step": 43330 }, { "epoch": 0.4623238347220296, "grad_norm": 1.0499112756416649, "learning_rate": 3.213110391924548e-05, "loss": 0.5436, "num_tokens": 259234341.0, "step": 43335 }, { "epoch": 0.46237717772822806, "grad_norm": 0.8054053180114349, "learning_rate": 3.212721976820222e-05, "loss": 0.5766, "num_tokens": 259262902.0, "step": 43340 }, { "epoch": 0.46243052073442653, "grad_norm": 0.8258956247822946, "learning_rate": 3.212333547316937e-05, "loss": 0.5062, "num_tokens": 259297266.0, "step": 43345 }, { "epoch": 0.46248386374062495, "grad_norm": 1.6640755986462261, "learning_rate": 3.2119451034267825e-05, "loss": 0.488, "num_tokens": 259316514.0, "step": 43350 }, { "epoch": 0.4625372067468234, "grad_norm": 0.7521098545914865, "learning_rate": 3.2115566451618453e-05, "loss": 0.5929, "num_tokens": 259345717.0, "step": 43355 }, { "epoch": 0.4625905497530219, "grad_norm": 0.797825107975131, "learning_rate": 3.211168172534214e-05, "loss": 0.5736, "num_tokens": 259377269.0, "step": 43360 }, { "epoch": 0.46264389275922035, "grad_norm": 0.7870189944805747, "learning_rate": 3.210779685555975e-05, "loss": 0.5494, "num_tokens": 259400234.0, "step": 43365 }, { "epoch": 0.46269723576541877, "grad_norm": 0.6185645738173094, "learning_rate": 3.2103911842392195e-05, "loss": 0.5173, "num_tokens": 259443762.0, "step": 43370 }, { "epoch": 0.46275057877161724, "grad_norm": 0.5895762277495576, "learning_rate": 3.210002668596036e-05, "loss": 0.5832, "num_tokens": 259505795.0, "step": 43375 }, { "epoch": 0.4628039217778157, "grad_norm": 1.0185356086315385, "learning_rate": 3.209614138638515e-05, "loss": 0.4677, "num_tokens": 259524777.0, "step": 43380 }, { "epoch": 0.4628572647840142, "grad_norm": 1.0023153446521968, "learning_rate": 3.209225594378745e-05, "loss": 0.6191, "num_tokens": 259546741.0, "step": 43385 }, { "epoch": 0.46291060779021265, "grad_norm": 1.0064506111985965, "learning_rate": 3.2088370358288175e-05, "loss": 0.4957, "num_tokens": 259574483.0, "step": 43390 }, { "epoch": 0.46296395079641106, "grad_norm": 1.3511271743852593, "learning_rate": 3.208448463000825e-05, "loss": 0.5952, "num_tokens": 259617878.0, "step": 43395 }, { "epoch": 0.46301729380260953, "grad_norm": 1.0450465687231136, "learning_rate": 3.2080598759068576e-05, "loss": 0.5327, "num_tokens": 259639720.0, "step": 43400 }, { "epoch": 0.463070636808808, "grad_norm": 0.713382175453474, "learning_rate": 3.207671274559008e-05, "loss": 0.489, "num_tokens": 259668882.0, "step": 43405 }, { "epoch": 0.46312397981500647, "grad_norm": 1.1055161992746312, "learning_rate": 3.207282658969368e-05, "loss": 0.5719, "num_tokens": 259703558.0, "step": 43410 }, { "epoch": 0.4631773228212049, "grad_norm": 1.4202596464637154, "learning_rate": 3.2068940291500314e-05, "loss": 0.493, "num_tokens": 259723195.0, "step": 43415 }, { "epoch": 0.46323066582740335, "grad_norm": 0.8723470845736228, "learning_rate": 3.20650538511309e-05, "loss": 0.5436, "num_tokens": 259762878.0, "step": 43420 }, { "epoch": 0.4632840088336018, "grad_norm": 0.8081816793021446, "learning_rate": 3.20611672687064e-05, "loss": 0.5135, "num_tokens": 259786498.0, "step": 43425 }, { "epoch": 0.4633373518398003, "grad_norm": 0.9391467757493309, "learning_rate": 3.205728054434774e-05, "loss": 0.5701, "num_tokens": 259816596.0, "step": 43430 }, { "epoch": 0.46339069484599876, "grad_norm": 1.089856187797078, "learning_rate": 3.205339367817587e-05, "loss": 0.4464, "num_tokens": 259853145.0, "step": 43435 }, { "epoch": 0.4634440378521972, "grad_norm": 0.7473599046446217, "learning_rate": 3.2049506670311735e-05, "loss": 0.5505, "num_tokens": 259903241.0, "step": 43440 }, { "epoch": 0.46349738085839565, "grad_norm": 1.1358722937534722, "learning_rate": 3.20456195208763e-05, "loss": 0.5903, "num_tokens": 259929187.0, "step": 43445 }, { "epoch": 0.4635507238645941, "grad_norm": 0.9001579187009384, "learning_rate": 3.204173222999053e-05, "loss": 0.6303, "num_tokens": 259970351.0, "step": 43450 }, { "epoch": 0.4636040668707926, "grad_norm": 1.8224439561959842, "learning_rate": 3.203784479777538e-05, "loss": 0.5548, "num_tokens": 259994660.0, "step": 43455 }, { "epoch": 0.463657409876991, "grad_norm": 1.2256170453132929, "learning_rate": 3.2033957224351815e-05, "loss": 0.7582, "num_tokens": 260038885.0, "step": 43460 }, { "epoch": 0.46371075288318947, "grad_norm": 1.232976163311766, "learning_rate": 3.203006950984082e-05, "loss": 0.5598, "num_tokens": 260065998.0, "step": 43465 }, { "epoch": 0.46376409588938794, "grad_norm": 1.2415461859310573, "learning_rate": 3.202618165436336e-05, "loss": 0.6464, "num_tokens": 260105142.0, "step": 43470 }, { "epoch": 0.4638174388955864, "grad_norm": 0.7806479999978798, "learning_rate": 3.2022293658040436e-05, "loss": 0.4331, "num_tokens": 260141702.0, "step": 43475 }, { "epoch": 0.4638707819017849, "grad_norm": 0.9727163415620611, "learning_rate": 3.201840552099301e-05, "loss": 0.6504, "num_tokens": 260181082.0, "step": 43480 }, { "epoch": 0.4639241249079833, "grad_norm": 1.3586075231856662, "learning_rate": 3.201451724334209e-05, "loss": 0.5489, "num_tokens": 260219665.0, "step": 43485 }, { "epoch": 0.46397746791418176, "grad_norm": 1.0282585983560175, "learning_rate": 3.2010628825208674e-05, "loss": 0.6053, "num_tokens": 260253498.0, "step": 43490 }, { "epoch": 0.46403081092038023, "grad_norm": 0.9128608658063165, "learning_rate": 3.2006740266713744e-05, "loss": 0.5616, "num_tokens": 260301546.0, "step": 43495 }, { "epoch": 0.4640841539265787, "grad_norm": 1.0698822165886754, "learning_rate": 3.2002851567978306e-05, "loss": 0.5403, "num_tokens": 260336638.0, "step": 43500 }, { "epoch": 0.4641374969327771, "grad_norm": 0.6343043907387856, "learning_rate": 3.199896272912339e-05, "loss": 0.5498, "num_tokens": 260363773.0, "step": 43505 }, { "epoch": 0.4641908399389756, "grad_norm": 0.9959730908734366, "learning_rate": 3.199507375027e-05, "loss": 0.5599, "num_tokens": 260398657.0, "step": 43510 }, { "epoch": 0.46424418294517406, "grad_norm": 1.061618757577182, "learning_rate": 3.1991184631539135e-05, "loss": 0.3981, "num_tokens": 260421631.0, "step": 43515 }, { "epoch": 0.4642975259513725, "grad_norm": 0.7979850862190976, "learning_rate": 3.1987295373051834e-05, "loss": 0.5354, "num_tokens": 260456429.0, "step": 43520 }, { "epoch": 0.464350868957571, "grad_norm": 1.2365989498636794, "learning_rate": 3.198340597492912e-05, "loss": 0.4573, "num_tokens": 260472473.0, "step": 43525 }, { "epoch": 0.4644042119637694, "grad_norm": 0.7517547153144775, "learning_rate": 3.197951643729202e-05, "loss": 0.4071, "num_tokens": 260489262.0, "step": 43530 }, { "epoch": 0.4644575549699679, "grad_norm": 0.7049375797439489, "learning_rate": 3.197562676026157e-05, "loss": 0.5815, "num_tokens": 260521151.0, "step": 43535 }, { "epoch": 0.46451089797616635, "grad_norm": 1.299696062913108, "learning_rate": 3.197173694395881e-05, "loss": 0.4841, "num_tokens": 260540447.0, "step": 43540 }, { "epoch": 0.4645642409823648, "grad_norm": 0.8050311427385818, "learning_rate": 3.196784698850477e-05, "loss": 0.573, "num_tokens": 260577962.0, "step": 43545 }, { "epoch": 0.46461758398856323, "grad_norm": 1.1011561968902939, "learning_rate": 3.196395689402052e-05, "loss": 0.5696, "num_tokens": 260611425.0, "step": 43550 }, { "epoch": 0.4646709269947617, "grad_norm": 0.9294848137784475, "learning_rate": 3.1960066660627104e-05, "loss": 0.5868, "num_tokens": 260632716.0, "step": 43555 }, { "epoch": 0.46472427000096017, "grad_norm": 1.969302962260267, "learning_rate": 3.195617628844557e-05, "loss": 0.5627, "num_tokens": 260653917.0, "step": 43560 }, { "epoch": 0.46477761300715864, "grad_norm": 1.3358993245385113, "learning_rate": 3.195228577759698e-05, "loss": 0.496, "num_tokens": 260674712.0, "step": 43565 }, { "epoch": 0.4648309560133571, "grad_norm": 0.7984600873493464, "learning_rate": 3.194839512820241e-05, "loss": 0.4734, "num_tokens": 260708633.0, "step": 43570 }, { "epoch": 0.4648842990195555, "grad_norm": 1.3772992391545307, "learning_rate": 3.194450434038291e-05, "loss": 0.5725, "num_tokens": 260728483.0, "step": 43575 }, { "epoch": 0.464937642025754, "grad_norm": 0.812421072770327, "learning_rate": 3.1940613414259575e-05, "loss": 0.5, "num_tokens": 260758917.0, "step": 43580 }, { "epoch": 0.46499098503195246, "grad_norm": 1.838516553694041, "learning_rate": 3.193672234995347e-05, "loss": 0.4873, "num_tokens": 260789984.0, "step": 43585 }, { "epoch": 0.46504432803815093, "grad_norm": 1.0471653354667319, "learning_rate": 3.193283114758567e-05, "loss": 0.492, "num_tokens": 260811232.0, "step": 43590 }, { "epoch": 0.46509767104434935, "grad_norm": 1.2125600434933255, "learning_rate": 3.192893980727728e-05, "loss": 0.5251, "num_tokens": 260834986.0, "step": 43595 }, { "epoch": 0.4651510140505478, "grad_norm": 0.7744594136771369, "learning_rate": 3.1925048329149375e-05, "loss": 0.5254, "num_tokens": 260862883.0, "step": 43600 }, { "epoch": 0.4652043570567463, "grad_norm": 1.1125291400081492, "learning_rate": 3.192115671332305e-05, "loss": 0.5597, "num_tokens": 260894049.0, "step": 43605 }, { "epoch": 0.46525770006294476, "grad_norm": 0.7754537251834157, "learning_rate": 3.1917264959919415e-05, "loss": 0.5918, "num_tokens": 260940006.0, "step": 43610 }, { "epoch": 0.4653110430691432, "grad_norm": 1.1732726299762393, "learning_rate": 3.191337306905958e-05, "loss": 0.5615, "num_tokens": 260979976.0, "step": 43615 }, { "epoch": 0.46536438607534164, "grad_norm": 0.9258045108497281, "learning_rate": 3.190948104086462e-05, "loss": 0.5891, "num_tokens": 261017938.0, "step": 43620 }, { "epoch": 0.4654177290815401, "grad_norm": 1.1406010014583365, "learning_rate": 3.1905588875455675e-05, "loss": 0.4788, "num_tokens": 261041910.0, "step": 43625 }, { "epoch": 0.4654710720877386, "grad_norm": 1.1756979742731906, "learning_rate": 3.190169657295386e-05, "loss": 0.5926, "num_tokens": 261073179.0, "step": 43630 }, { "epoch": 0.46552441509393705, "grad_norm": 0.6793753264727607, "learning_rate": 3.189780413348028e-05, "loss": 0.5341, "num_tokens": 261097285.0, "step": 43635 }, { "epoch": 0.46557775810013546, "grad_norm": 0.8079470540272643, "learning_rate": 3.189391155715607e-05, "loss": 0.5014, "num_tokens": 261126129.0, "step": 43640 }, { "epoch": 0.46563110110633393, "grad_norm": 1.4953902430456, "learning_rate": 3.1890018844102366e-05, "loss": 0.4677, "num_tokens": 261163879.0, "step": 43645 }, { "epoch": 0.4656844441125324, "grad_norm": 0.7996189057175199, "learning_rate": 3.188612599444028e-05, "loss": 0.6484, "num_tokens": 261205263.0, "step": 43650 }, { "epoch": 0.4657377871187309, "grad_norm": 0.8171132282300066, "learning_rate": 3.188223300829098e-05, "loss": 0.4936, "num_tokens": 261235647.0, "step": 43655 }, { "epoch": 0.46579113012492934, "grad_norm": 1.1354799571922378, "learning_rate": 3.187833988577558e-05, "loss": 0.5679, "num_tokens": 261264572.0, "step": 43660 }, { "epoch": 0.46584447313112776, "grad_norm": 0.8485191217382491, "learning_rate": 3.1874446627015225e-05, "loss": 0.4846, "num_tokens": 261291550.0, "step": 43665 }, { "epoch": 0.4658978161373262, "grad_norm": 0.92329129942942, "learning_rate": 3.18705532321311e-05, "loss": 0.5772, "num_tokens": 261329822.0, "step": 43670 }, { "epoch": 0.4659511591435247, "grad_norm": 0.6973703738836313, "learning_rate": 3.186665970124431e-05, "loss": 0.4543, "num_tokens": 261363653.0, "step": 43675 }, { "epoch": 0.46600450214972317, "grad_norm": 0.9616274382595703, "learning_rate": 3.186276603447605e-05, "loss": 0.4797, "num_tokens": 261399686.0, "step": 43680 }, { "epoch": 0.4660578451559216, "grad_norm": 0.7181680802327124, "learning_rate": 3.185887223194748e-05, "loss": 0.4616, "num_tokens": 261434983.0, "step": 43685 }, { "epoch": 0.46611118816212005, "grad_norm": 0.8872713972514542, "learning_rate": 3.1854978293779756e-05, "loss": 0.6284, "num_tokens": 261462206.0, "step": 43690 }, { "epoch": 0.4661645311683185, "grad_norm": 1.7096917021149567, "learning_rate": 3.1851084220094044e-05, "loss": 0.5053, "num_tokens": 261483249.0, "step": 43695 }, { "epoch": 0.466217874174517, "grad_norm": 1.0123799103015592, "learning_rate": 3.184719001101154e-05, "loss": 0.6169, "num_tokens": 261512513.0, "step": 43700 }, { "epoch": 0.46627121718071546, "grad_norm": 1.156669978799229, "learning_rate": 3.1843295666653405e-05, "loss": 0.4885, "num_tokens": 261530627.0, "step": 43705 }, { "epoch": 0.4663245601869139, "grad_norm": 0.937859022196992, "learning_rate": 3.183940118714084e-05, "loss": 0.6262, "num_tokens": 261553043.0, "step": 43710 }, { "epoch": 0.46637790319311234, "grad_norm": 0.7816986259677372, "learning_rate": 3.183550657259501e-05, "loss": 0.483, "num_tokens": 261592436.0, "step": 43715 }, { "epoch": 0.4664312461993108, "grad_norm": 0.7843875858114181, "learning_rate": 3.183161182313713e-05, "loss": 0.525, "num_tokens": 261622837.0, "step": 43720 }, { "epoch": 0.4664845892055093, "grad_norm": 1.1815839550873113, "learning_rate": 3.182771693888839e-05, "loss": 0.5615, "num_tokens": 261646068.0, "step": 43725 }, { "epoch": 0.4665379322117077, "grad_norm": 0.8015938970754038, "learning_rate": 3.182382191996998e-05, "loss": 0.4809, "num_tokens": 261680509.0, "step": 43730 }, { "epoch": 0.46659127521790617, "grad_norm": 1.1597552098084978, "learning_rate": 3.1819926766503114e-05, "loss": 0.5186, "num_tokens": 261703054.0, "step": 43735 }, { "epoch": 0.46664461822410463, "grad_norm": 1.41628261378735, "learning_rate": 3.1816031478609e-05, "loss": 0.6257, "num_tokens": 261731176.0, "step": 43740 }, { "epoch": 0.4666979612303031, "grad_norm": 1.3563236725024614, "learning_rate": 3.181213605640886e-05, "loss": 0.5138, "num_tokens": 261745927.0, "step": 43745 }, { "epoch": 0.4667513042365016, "grad_norm": 0.8469887325443588, "learning_rate": 3.180824050002389e-05, "loss": 0.5675, "num_tokens": 261790847.0, "step": 43750 }, { "epoch": 0.4668046472427, "grad_norm": 0.6718012885090539, "learning_rate": 3.180434480957534e-05, "loss": 0.5083, "num_tokens": 261822895.0, "step": 43755 }, { "epoch": 0.46685799024889846, "grad_norm": 0.7752328653104466, "learning_rate": 3.180044898518441e-05, "loss": 0.4918, "num_tokens": 261838967.0, "step": 43760 }, { "epoch": 0.4669113332550969, "grad_norm": 0.7772046559859578, "learning_rate": 3.1796553026972346e-05, "loss": 0.4862, "num_tokens": 261862301.0, "step": 43765 }, { "epoch": 0.4669646762612954, "grad_norm": 0.9932154486466811, "learning_rate": 3.179265693506037e-05, "loss": 0.5481, "num_tokens": 261885905.0, "step": 43770 }, { "epoch": 0.4670180192674938, "grad_norm": 0.9962610532828391, "learning_rate": 3.178876070956974e-05, "loss": 0.4727, "num_tokens": 261913901.0, "step": 43775 }, { "epoch": 0.4670713622736923, "grad_norm": 0.9327628469501705, "learning_rate": 3.178486435062168e-05, "loss": 0.4489, "num_tokens": 261933892.0, "step": 43780 }, { "epoch": 0.46712470527989075, "grad_norm": 0.8009630765605217, "learning_rate": 3.178096785833744e-05, "loss": 0.6529, "num_tokens": 261975401.0, "step": 43785 }, { "epoch": 0.4671780482860892, "grad_norm": 0.6580909037814555, "learning_rate": 3.1777071232838276e-05, "loss": 0.5871, "num_tokens": 262030384.0, "step": 43790 }, { "epoch": 0.4672313912922877, "grad_norm": 0.8248980589415323, "learning_rate": 3.177317447424544e-05, "loss": 0.5276, "num_tokens": 262064348.0, "step": 43795 }, { "epoch": 0.4672847342984861, "grad_norm": 0.5325172057684212, "learning_rate": 3.176927758268019e-05, "loss": 0.5225, "num_tokens": 262108105.0, "step": 43800 }, { "epoch": 0.4673380773046846, "grad_norm": 1.8575599683960113, "learning_rate": 3.1765380558263794e-05, "loss": 0.5981, "num_tokens": 262136000.0, "step": 43805 }, { "epoch": 0.46739142031088304, "grad_norm": 0.8683173474116385, "learning_rate": 3.176148340111752e-05, "loss": 0.3924, "num_tokens": 262158332.0, "step": 43810 }, { "epoch": 0.4674447633170815, "grad_norm": 1.0442513412188041, "learning_rate": 3.175758611136263e-05, "loss": 0.4479, "num_tokens": 262185755.0, "step": 43815 }, { "epoch": 0.4674981063232799, "grad_norm": 0.7347308059326695, "learning_rate": 3.1753688689120406e-05, "loss": 0.486, "num_tokens": 262214887.0, "step": 43820 }, { "epoch": 0.4675514493294784, "grad_norm": 1.0684494062959702, "learning_rate": 3.174979113451213e-05, "loss": 0.6404, "num_tokens": 262239921.0, "step": 43825 }, { "epoch": 0.46760479233567687, "grad_norm": 1.1887832906964746, "learning_rate": 3.174589344765907e-05, "loss": 0.5837, "num_tokens": 262290952.0, "step": 43830 }, { "epoch": 0.46765813534187534, "grad_norm": 0.7721803450616019, "learning_rate": 3.174199562868255e-05, "loss": 0.4993, "num_tokens": 262336978.0, "step": 43835 }, { "epoch": 0.4677114783480738, "grad_norm": 0.6341010425946003, "learning_rate": 3.173809767770383e-05, "loss": 0.5723, "num_tokens": 262384995.0, "step": 43840 }, { "epoch": 0.4677648213542722, "grad_norm": 0.8332310199457978, "learning_rate": 3.173419959484421e-05, "loss": 0.4905, "num_tokens": 262418117.0, "step": 43845 }, { "epoch": 0.4678181643604707, "grad_norm": 1.082040783135864, "learning_rate": 3.1730301380225e-05, "loss": 0.5835, "num_tokens": 262444151.0, "step": 43850 }, { "epoch": 0.46787150736666916, "grad_norm": 1.6936759020942531, "learning_rate": 3.172640303396751e-05, "loss": 0.6106, "num_tokens": 262461733.0, "step": 43855 }, { "epoch": 0.46792485037286763, "grad_norm": 0.8954029694510628, "learning_rate": 3.1722504556193015e-05, "loss": 0.6097, "num_tokens": 262485472.0, "step": 43860 }, { "epoch": 0.46797819337906604, "grad_norm": 1.439769669081635, "learning_rate": 3.171860594702287e-05, "loss": 0.5871, "num_tokens": 262494995.0, "step": 43865 }, { "epoch": 0.4680315363852645, "grad_norm": 0.5412846259980082, "learning_rate": 3.171470720657836e-05, "loss": 0.4598, "num_tokens": 262522911.0, "step": 43870 }, { "epoch": 0.468084879391463, "grad_norm": 1.5548468665407478, "learning_rate": 3.171080833498083e-05, "loss": 0.5637, "num_tokens": 262546146.0, "step": 43875 }, { "epoch": 0.46813822239766145, "grad_norm": 1.4625934796147193, "learning_rate": 3.1706909332351596e-05, "loss": 0.5006, "num_tokens": 262571813.0, "step": 43880 }, { "epoch": 0.4681915654038599, "grad_norm": 0.8116375897152747, "learning_rate": 3.1703010198811974e-05, "loss": 0.4807, "num_tokens": 262603592.0, "step": 43885 }, { "epoch": 0.46824490841005834, "grad_norm": 0.5518474647639567, "learning_rate": 3.169911093448332e-05, "loss": 0.4652, "num_tokens": 262627526.0, "step": 43890 }, { "epoch": 0.4682982514162568, "grad_norm": 1.3794684015846013, "learning_rate": 3.169521153948695e-05, "loss": 0.5561, "num_tokens": 262640120.0, "step": 43895 }, { "epoch": 0.4683515944224553, "grad_norm": 1.7567631371487504, "learning_rate": 3.1691312013944214e-05, "loss": 0.6577, "num_tokens": 262659081.0, "step": 43900 }, { "epoch": 0.46840493742865374, "grad_norm": 1.0366051657535285, "learning_rate": 3.1687412357976456e-05, "loss": 0.4241, "num_tokens": 262676095.0, "step": 43905 }, { "epoch": 0.46845828043485216, "grad_norm": 1.0040011975798606, "learning_rate": 3.1683512571705046e-05, "loss": 0.5882, "num_tokens": 262719552.0, "step": 43910 }, { "epoch": 0.46851162344105063, "grad_norm": 1.1390057914051495, "learning_rate": 3.167961265525129e-05, "loss": 0.4526, "num_tokens": 262758007.0, "step": 43915 }, { "epoch": 0.4685649664472491, "grad_norm": 0.8561101361218812, "learning_rate": 3.167571260873659e-05, "loss": 0.6684, "num_tokens": 262792408.0, "step": 43920 }, { "epoch": 0.46861830945344757, "grad_norm": 0.7563985057037331, "learning_rate": 3.167181243228229e-05, "loss": 0.6905, "num_tokens": 262821155.0, "step": 43925 }, { "epoch": 0.46867165245964604, "grad_norm": 0.6133697168489438, "learning_rate": 3.1667912126009746e-05, "loss": 0.6404, "num_tokens": 262843424.0, "step": 43930 }, { "epoch": 0.46872499546584445, "grad_norm": 0.7087074503236934, "learning_rate": 3.166401169004035e-05, "loss": 0.5418, "num_tokens": 262877485.0, "step": 43935 }, { "epoch": 0.4687783384720429, "grad_norm": 0.8129915694995367, "learning_rate": 3.1660111124495455e-05, "loss": 0.5067, "num_tokens": 262911538.0, "step": 43940 }, { "epoch": 0.4688316814782414, "grad_norm": 1.7883980556719892, "learning_rate": 3.165621042949645e-05, "loss": 0.5026, "num_tokens": 262943999.0, "step": 43945 }, { "epoch": 0.46888502448443986, "grad_norm": 0.9292802962966961, "learning_rate": 3.165230960516472e-05, "loss": 0.5452, "num_tokens": 262969557.0, "step": 43950 }, { "epoch": 0.4689383674906383, "grad_norm": 0.6660992874844299, "learning_rate": 3.1648408651621635e-05, "loss": 0.5105, "num_tokens": 263012342.0, "step": 43955 }, { "epoch": 0.46899171049683674, "grad_norm": 1.1629977746317979, "learning_rate": 3.164450756898859e-05, "loss": 0.4406, "num_tokens": 263034964.0, "step": 43960 }, { "epoch": 0.4690450535030352, "grad_norm": 0.7607932382517576, "learning_rate": 3.1640606357387e-05, "loss": 0.61, "num_tokens": 263063221.0, "step": 43965 }, { "epoch": 0.4690983965092337, "grad_norm": 0.9045692003098108, "learning_rate": 3.1636705016938235e-05, "loss": 0.5639, "num_tokens": 263085956.0, "step": 43970 }, { "epoch": 0.46915173951543215, "grad_norm": 0.8429953348678989, "learning_rate": 3.16328035477637e-05, "loss": 0.5031, "num_tokens": 263118356.0, "step": 43975 }, { "epoch": 0.46920508252163057, "grad_norm": 0.7678180455521463, "learning_rate": 3.1628901949984815e-05, "loss": 0.5294, "num_tokens": 263149154.0, "step": 43980 }, { "epoch": 0.46925842552782904, "grad_norm": 10.312226391213173, "learning_rate": 3.162500022372299e-05, "loss": 0.7959, "num_tokens": 263171730.0, "step": 43985 }, { "epoch": 0.4693117685340275, "grad_norm": 1.0325583143385255, "learning_rate": 3.162109836909961e-05, "loss": 0.562, "num_tokens": 263199865.0, "step": 43990 }, { "epoch": 0.469365111540226, "grad_norm": 0.7275983154665803, "learning_rate": 3.161719638623612e-05, "loss": 0.3996, "num_tokens": 263231814.0, "step": 43995 }, { "epoch": 0.4694184545464244, "grad_norm": 0.6846541650374859, "learning_rate": 3.161329427525395e-05, "loss": 0.4511, "num_tokens": 263267393.0, "step": 44000 }, { "epoch": 0.46947179755262286, "grad_norm": 0.9158446584350165, "learning_rate": 3.1609392036274505e-05, "loss": 0.444, "num_tokens": 263312764.0, "step": 44005 }, { "epoch": 0.46952514055882133, "grad_norm": 0.8331032519612243, "learning_rate": 3.160548966941922e-05, "loss": 0.4501, "num_tokens": 263346319.0, "step": 44010 }, { "epoch": 0.4695784835650198, "grad_norm": 0.7318084790616122, "learning_rate": 3.1601587174809525e-05, "loss": 0.5498, "num_tokens": 263379215.0, "step": 44015 }, { "epoch": 0.46963182657121827, "grad_norm": 0.8610395779876421, "learning_rate": 3.159768455256686e-05, "loss": 0.5317, "num_tokens": 263411613.0, "step": 44020 }, { "epoch": 0.4696851695774167, "grad_norm": 1.123163351795001, "learning_rate": 3.1593781802812674e-05, "loss": 0.4836, "num_tokens": 263431078.0, "step": 44025 }, { "epoch": 0.46973851258361515, "grad_norm": 1.7177783904539659, "learning_rate": 3.158987892566841e-05, "loss": 0.6104, "num_tokens": 263444425.0, "step": 44030 }, { "epoch": 0.4697918555898136, "grad_norm": 1.1395992141319868, "learning_rate": 3.1585975921255514e-05, "loss": 0.5239, "num_tokens": 263484720.0, "step": 44035 }, { "epoch": 0.4698451985960121, "grad_norm": 1.0012592607048665, "learning_rate": 3.158207278969544e-05, "loss": 0.5096, "num_tokens": 263514854.0, "step": 44040 }, { "epoch": 0.4698985416022105, "grad_norm": 0.6660224512967234, "learning_rate": 3.157816953110964e-05, "loss": 0.5702, "num_tokens": 263544667.0, "step": 44045 }, { "epoch": 0.469951884608409, "grad_norm": 0.8680784091205713, "learning_rate": 3.157426614561958e-05, "loss": 0.9952, "num_tokens": 263563566.0, "step": 44050 }, { "epoch": 0.47000522761460745, "grad_norm": 1.2385658923622391, "learning_rate": 3.1570362633346736e-05, "loss": 0.4744, "num_tokens": 263586858.0, "step": 44055 }, { "epoch": 0.4700585706208059, "grad_norm": 1.782602594431159, "learning_rate": 3.156645899441256e-05, "loss": 0.4812, "num_tokens": 263616774.0, "step": 44060 }, { "epoch": 0.4701119136270044, "grad_norm": 0.8008987121106307, "learning_rate": 3.156255522893853e-05, "loss": 0.5943, "num_tokens": 263640924.0, "step": 44065 }, { "epoch": 0.4701652566332028, "grad_norm": 1.296752223567854, "learning_rate": 3.155865133704614e-05, "loss": 0.619, "num_tokens": 263685080.0, "step": 44070 }, { "epoch": 0.47021859963940127, "grad_norm": 1.0277887267673054, "learning_rate": 3.1554747318856845e-05, "loss": 0.579, "num_tokens": 263710353.0, "step": 44075 }, { "epoch": 0.47027194264559974, "grad_norm": 0.7673572364434216, "learning_rate": 3.155084317449214e-05, "loss": 0.529, "num_tokens": 263741770.0, "step": 44080 }, { "epoch": 0.4703252856517982, "grad_norm": 1.0889198492844239, "learning_rate": 3.154693890407352e-05, "loss": 0.5371, "num_tokens": 263761683.0, "step": 44085 }, { "epoch": 0.4703786286579966, "grad_norm": 0.8111352340244739, "learning_rate": 3.1543034507722485e-05, "loss": 0.6857, "num_tokens": 263810803.0, "step": 44090 }, { "epoch": 0.4704319716641951, "grad_norm": 1.1390841635163362, "learning_rate": 3.15391299855605e-05, "loss": 0.5436, "num_tokens": 263842234.0, "step": 44095 }, { "epoch": 0.47048531467039356, "grad_norm": 1.0875491335785716, "learning_rate": 3.15352253377091e-05, "loss": 0.5011, "num_tokens": 263864165.0, "step": 44100 }, { "epoch": 0.47053865767659203, "grad_norm": 0.8714676976458942, "learning_rate": 3.1531320564289774e-05, "loss": 0.8032, "num_tokens": 263912546.0, "step": 44105 }, { "epoch": 0.4705920006827905, "grad_norm": 0.6627246780791934, "learning_rate": 3.1527415665424035e-05, "loss": 0.5872, "num_tokens": 263959997.0, "step": 44110 }, { "epoch": 0.4706453436889889, "grad_norm": 0.884311066194785, "learning_rate": 3.152351064123338e-05, "loss": 0.4993, "num_tokens": 263989059.0, "step": 44115 }, { "epoch": 0.4706986866951874, "grad_norm": 0.8044649371198642, "learning_rate": 3.151960549183935e-05, "loss": 0.5938, "num_tokens": 264019700.0, "step": 44120 }, { "epoch": 0.47075202970138585, "grad_norm": 1.0533234352596306, "learning_rate": 3.151570021736346e-05, "loss": 0.4159, "num_tokens": 264043165.0, "step": 44125 }, { "epoch": 0.4708053727075843, "grad_norm": 0.9405970777599032, "learning_rate": 3.1511794817927224e-05, "loss": 0.4149, "num_tokens": 264074674.0, "step": 44130 }, { "epoch": 0.47085871571378274, "grad_norm": 0.8441428409022412, "learning_rate": 3.150788929365217e-05, "loss": 0.5116, "num_tokens": 264113275.0, "step": 44135 }, { "epoch": 0.4709120587199812, "grad_norm": 0.8919863432971463, "learning_rate": 3.1503983644659824e-05, "loss": 0.5501, "num_tokens": 264150732.0, "step": 44140 }, { "epoch": 0.4709654017261797, "grad_norm": 0.788144471148985, "learning_rate": 3.150007787107174e-05, "loss": 0.5944, "num_tokens": 264180007.0, "step": 44145 }, { "epoch": 0.47101874473237815, "grad_norm": 0.9063728455862113, "learning_rate": 3.149617197300945e-05, "loss": 0.6245, "num_tokens": 264220612.0, "step": 44150 }, { "epoch": 0.4710720877385766, "grad_norm": 1.0158494494438934, "learning_rate": 3.1492265950594496e-05, "loss": 0.511, "num_tokens": 264249681.0, "step": 44155 }, { "epoch": 0.47112543074477503, "grad_norm": 0.9267610694535487, "learning_rate": 3.148835980394842e-05, "loss": 0.6747, "num_tokens": 264287905.0, "step": 44160 }, { "epoch": 0.4711787737509735, "grad_norm": 0.9745828890526413, "learning_rate": 3.148445353319279e-05, "loss": 0.5088, "num_tokens": 264316581.0, "step": 44165 }, { "epoch": 0.47123211675717197, "grad_norm": 8.529919678569437, "learning_rate": 3.148054713844915e-05, "loss": 0.55, "num_tokens": 264344878.0, "step": 44170 }, { "epoch": 0.47128545976337044, "grad_norm": 1.0106861798400855, "learning_rate": 3.147664061983905e-05, "loss": 0.4801, "num_tokens": 264361500.0, "step": 44175 }, { "epoch": 0.47133880276956885, "grad_norm": 1.160182059091876, "learning_rate": 3.147273397748407e-05, "loss": 0.5059, "num_tokens": 264388453.0, "step": 44180 }, { "epoch": 0.4713921457757673, "grad_norm": 1.001617486960526, "learning_rate": 3.146882721150577e-05, "loss": 0.5443, "num_tokens": 264414524.0, "step": 44185 }, { "epoch": 0.4714454887819658, "grad_norm": 2.397612229062939, "learning_rate": 3.146492032202571e-05, "loss": 0.6567, "num_tokens": 264444914.0, "step": 44190 }, { "epoch": 0.47149883178816426, "grad_norm": 1.184672975626948, "learning_rate": 3.1461013309165486e-05, "loss": 0.6386, "num_tokens": 264475020.0, "step": 44195 }, { "epoch": 0.47155217479436273, "grad_norm": 0.8772823713237025, "learning_rate": 3.145710617304665e-05, "loss": 0.5319, "num_tokens": 264498963.0, "step": 44200 }, { "epoch": 0.47160551780056115, "grad_norm": 3.069920186396523, "learning_rate": 3.145319891379081e-05, "loss": 0.5099, "num_tokens": 264522587.0, "step": 44205 }, { "epoch": 0.4716588608067596, "grad_norm": 0.8335625794028625, "learning_rate": 3.144929153151953e-05, "loss": 0.5369, "num_tokens": 264547002.0, "step": 44210 }, { "epoch": 0.4717122038129581, "grad_norm": 0.9856468681975632, "learning_rate": 3.144538402635442e-05, "loss": 0.618, "num_tokens": 264596011.0, "step": 44215 }, { "epoch": 0.47176554681915656, "grad_norm": 0.8875967178568436, "learning_rate": 3.144147639841706e-05, "loss": 0.4958, "num_tokens": 264620642.0, "step": 44220 }, { "epoch": 0.47181888982535497, "grad_norm": 1.3512287054896963, "learning_rate": 3.1437568647829044e-05, "loss": 0.6298, "num_tokens": 264640805.0, "step": 44225 }, { "epoch": 0.47187223283155344, "grad_norm": 1.027382451275513, "learning_rate": 3.143366077471198e-05, "loss": 0.457, "num_tokens": 264662142.0, "step": 44230 }, { "epoch": 0.4719255758377519, "grad_norm": 0.8423580193075576, "learning_rate": 3.142975277918748e-05, "loss": 0.451, "num_tokens": 264687839.0, "step": 44235 }, { "epoch": 0.4719789188439504, "grad_norm": 0.8269705084434471, "learning_rate": 3.142584466137714e-05, "loss": 0.4779, "num_tokens": 264718405.0, "step": 44240 }, { "epoch": 0.47203226185014885, "grad_norm": 1.5908451040208522, "learning_rate": 3.142193642140258e-05, "loss": 0.5909, "num_tokens": 264737315.0, "step": 44245 }, { "epoch": 0.47208560485634726, "grad_norm": 0.9399762315406806, "learning_rate": 3.141802805938541e-05, "loss": 0.4248, "num_tokens": 264758137.0, "step": 44250 }, { "epoch": 0.47213894786254573, "grad_norm": 0.7728352576213268, "learning_rate": 3.141411957544726e-05, "loss": 0.5461, "num_tokens": 264788333.0, "step": 44255 }, { "epoch": 0.4721922908687442, "grad_norm": 1.743211212923904, "learning_rate": 3.1410210969709746e-05, "loss": 0.5389, "num_tokens": 264817304.0, "step": 44260 }, { "epoch": 0.47224563387494267, "grad_norm": 0.9473192033788852, "learning_rate": 3.14063022422945e-05, "loss": 0.5529, "num_tokens": 264840136.0, "step": 44265 }, { "epoch": 0.4722989768811411, "grad_norm": 1.056873552009876, "learning_rate": 3.1402393393323154e-05, "loss": 0.5222, "num_tokens": 264868679.0, "step": 44270 }, { "epoch": 0.47235231988733956, "grad_norm": 0.6971599227749851, "learning_rate": 3.139848442291734e-05, "loss": 0.5419, "num_tokens": 264902584.0, "step": 44275 }, { "epoch": 0.472405662893538, "grad_norm": 1.1715928619941263, "learning_rate": 3.13945753311987e-05, "loss": 0.6641, "num_tokens": 264951286.0, "step": 44280 }, { "epoch": 0.4724590058997365, "grad_norm": 1.8170883039786996, "learning_rate": 3.1390666118288874e-05, "loss": 0.5627, "num_tokens": 264988192.0, "step": 44285 }, { "epoch": 0.47251234890593496, "grad_norm": 1.0184795240303997, "learning_rate": 3.138675678430951e-05, "loss": 0.6107, "num_tokens": 265020773.0, "step": 44290 }, { "epoch": 0.4725656919121334, "grad_norm": 0.9281710808856117, "learning_rate": 3.138284732938226e-05, "loss": 0.6703, "num_tokens": 265060315.0, "step": 44295 }, { "epoch": 0.47261903491833185, "grad_norm": 2.6404425912574125, "learning_rate": 3.137893775362878e-05, "loss": 0.6065, "num_tokens": 265075200.0, "step": 44300 }, { "epoch": 0.4726723779245303, "grad_norm": 1.0038787149252242, "learning_rate": 3.1375028057170706e-05, "loss": 0.5358, "num_tokens": 265104338.0, "step": 44305 }, { "epoch": 0.4727257209307288, "grad_norm": 0.7769489825724031, "learning_rate": 3.137111824012974e-05, "loss": 0.5801, "num_tokens": 265150371.0, "step": 44310 }, { "epoch": 0.4727790639369272, "grad_norm": 0.7154928682278383, "learning_rate": 3.136720830262751e-05, "loss": 0.723, "num_tokens": 265184380.0, "step": 44315 }, { "epoch": 0.47283240694312567, "grad_norm": 0.9510444140502384, "learning_rate": 3.136329824478571e-05, "loss": 0.5736, "num_tokens": 265226568.0, "step": 44320 }, { "epoch": 0.47288574994932414, "grad_norm": 0.7906212971078891, "learning_rate": 3.135938806672601e-05, "loss": 0.4439, "num_tokens": 265249258.0, "step": 44325 }, { "epoch": 0.4729390929555226, "grad_norm": 1.0381748911810786, "learning_rate": 3.1355477768570075e-05, "loss": 0.5147, "num_tokens": 265278140.0, "step": 44330 }, { "epoch": 0.4729924359617211, "grad_norm": 1.049606927373273, "learning_rate": 3.135156735043958e-05, "loss": 0.4778, "num_tokens": 265302705.0, "step": 44335 }, { "epoch": 0.4730457789679195, "grad_norm": 0.8000494498153908, "learning_rate": 3.134765681245624e-05, "loss": 0.5496, "num_tokens": 265343381.0, "step": 44340 }, { "epoch": 0.47309912197411796, "grad_norm": 0.6776254246894197, "learning_rate": 3.134374615474171e-05, "loss": 0.5496, "num_tokens": 265368952.0, "step": 44345 }, { "epoch": 0.47315246498031643, "grad_norm": 0.9897630677814117, "learning_rate": 3.13398353774177e-05, "loss": 0.4802, "num_tokens": 265392341.0, "step": 44350 }, { "epoch": 0.4732058079865149, "grad_norm": 1.0081160805429976, "learning_rate": 3.1335924480605896e-05, "loss": 0.5739, "num_tokens": 265404610.0, "step": 44355 }, { "epoch": 0.4732591509927133, "grad_norm": 1.3565395508320466, "learning_rate": 3.1332013464428e-05, "loss": 0.4936, "num_tokens": 265431643.0, "step": 44360 }, { "epoch": 0.4733124939989118, "grad_norm": 0.8179535781714781, "learning_rate": 3.1328102329005724e-05, "loss": 0.5203, "num_tokens": 265453653.0, "step": 44365 }, { "epoch": 0.47336583700511026, "grad_norm": 0.8922450037372197, "learning_rate": 3.1324191074460765e-05, "loss": 0.5399, "num_tokens": 265495433.0, "step": 44370 }, { "epoch": 0.4734191800113087, "grad_norm": 1.164095388655264, "learning_rate": 3.1320279700914825e-05, "loss": 0.7571, "num_tokens": 265535344.0, "step": 44375 }, { "epoch": 0.4734725230175072, "grad_norm": 0.8870132394964209, "learning_rate": 3.131636820848964e-05, "loss": 0.5367, "num_tokens": 265556383.0, "step": 44380 }, { "epoch": 0.4735258660237056, "grad_norm": 0.9014754648005987, "learning_rate": 3.1312456597306914e-05, "loss": 0.5406, "num_tokens": 265594192.0, "step": 44385 }, { "epoch": 0.4735792090299041, "grad_norm": 1.1151629279478792, "learning_rate": 3.1308544867488367e-05, "loss": 0.4323, "num_tokens": 265614785.0, "step": 44390 }, { "epoch": 0.47363255203610255, "grad_norm": 1.4417886894492853, "learning_rate": 3.130463301915573e-05, "loss": 0.6693, "num_tokens": 265653471.0, "step": 44395 }, { "epoch": 0.473685895042301, "grad_norm": 0.922650509599274, "learning_rate": 3.1300721052430724e-05, "loss": 0.6164, "num_tokens": 265682500.0, "step": 44400 }, { "epoch": 0.47373923804849943, "grad_norm": 0.6384656916356198, "learning_rate": 3.129680896743508e-05, "loss": 0.608, "num_tokens": 265715549.0, "step": 44405 }, { "epoch": 0.4737925810546979, "grad_norm": 1.1996747425532839, "learning_rate": 3.129289676429055e-05, "loss": 0.5389, "num_tokens": 265743165.0, "step": 44410 }, { "epoch": 0.4738459240608964, "grad_norm": 1.0595365342139245, "learning_rate": 3.1288984443118863e-05, "loss": 0.6002, "num_tokens": 265767019.0, "step": 44415 }, { "epoch": 0.47389926706709484, "grad_norm": 0.6562545382341696, "learning_rate": 3.1285072004041756e-05, "loss": 0.4686, "num_tokens": 265803691.0, "step": 44420 }, { "epoch": 0.4739526100732933, "grad_norm": 4.464236173218135, "learning_rate": 3.1281159447180984e-05, "loss": 0.5974, "num_tokens": 265852620.0, "step": 44425 }, { "epoch": 0.4740059530794917, "grad_norm": 1.649214535974146, "learning_rate": 3.12772467726583e-05, "loss": 0.7142, "num_tokens": 265866529.0, "step": 44430 }, { "epoch": 0.4740592960856902, "grad_norm": 1.2122539166556663, "learning_rate": 3.127333398059546e-05, "loss": 0.6073, "num_tokens": 265884479.0, "step": 44435 }, { "epoch": 0.47411263909188867, "grad_norm": 1.1183685033394286, "learning_rate": 3.126942107111421e-05, "loss": 0.6352, "num_tokens": 265915086.0, "step": 44440 }, { "epoch": 0.47416598209808714, "grad_norm": 0.7224309884417044, "learning_rate": 3.126550804433632e-05, "loss": 0.5818, "num_tokens": 265957837.0, "step": 44445 }, { "epoch": 0.47421932510428555, "grad_norm": 0.9400402368606734, "learning_rate": 3.126159490038355e-05, "loss": 0.639, "num_tokens": 265998858.0, "step": 44450 }, { "epoch": 0.474272668110484, "grad_norm": 0.6886239734582378, "learning_rate": 3.125768163937768e-05, "loss": 0.4751, "num_tokens": 266033921.0, "step": 44455 }, { "epoch": 0.4743260111166825, "grad_norm": 0.6010961579703784, "learning_rate": 3.1253768261440475e-05, "loss": 0.5613, "num_tokens": 266063182.0, "step": 44460 }, { "epoch": 0.47437935412288096, "grad_norm": 1.6442008506637797, "learning_rate": 3.124985476669371e-05, "loss": 0.5291, "num_tokens": 266113101.0, "step": 44465 }, { "epoch": 0.47443269712907943, "grad_norm": 1.085507985191104, "learning_rate": 3.1245941155259165e-05, "loss": 0.6042, "num_tokens": 266139172.0, "step": 44470 }, { "epoch": 0.47448604013527784, "grad_norm": 1.0194278366877048, "learning_rate": 3.124202742725864e-05, "loss": 0.5671, "num_tokens": 266169648.0, "step": 44475 }, { "epoch": 0.4745393831414763, "grad_norm": 1.1257172049809663, "learning_rate": 3.123811358281389e-05, "loss": 0.5078, "num_tokens": 266198448.0, "step": 44480 }, { "epoch": 0.4745927261476748, "grad_norm": 1.8529418891685925, "learning_rate": 3.123419962204673e-05, "loss": 0.5679, "num_tokens": 266217810.0, "step": 44485 }, { "epoch": 0.47464606915387325, "grad_norm": 1.8281656138749705, "learning_rate": 3.1230285545078946e-05, "loss": 0.5031, "num_tokens": 266243486.0, "step": 44490 }, { "epoch": 0.47469941216007167, "grad_norm": 0.8722889318946901, "learning_rate": 3.1226371352032345e-05, "loss": 0.6491, "num_tokens": 266276815.0, "step": 44495 }, { "epoch": 0.47475275516627014, "grad_norm": 1.0872610305899284, "learning_rate": 3.122245704302872e-05, "loss": 0.5497, "num_tokens": 266309396.0, "step": 44500 }, { "epoch": 0.4748060981724686, "grad_norm": 1.2616721010964402, "learning_rate": 3.1218542618189874e-05, "loss": 0.5477, "num_tokens": 266342951.0, "step": 44505 }, { "epoch": 0.4748594411786671, "grad_norm": 1.3309966452989068, "learning_rate": 3.121462807763762e-05, "loss": 0.6287, "num_tokens": 266372395.0, "step": 44510 }, { "epoch": 0.47491278418486554, "grad_norm": 0.8228279095230635, "learning_rate": 3.121071342149377e-05, "loss": 0.4884, "num_tokens": 266414173.0, "step": 44515 }, { "epoch": 0.47496612719106396, "grad_norm": 2.132347240042401, "learning_rate": 3.120679864988014e-05, "loss": 0.6553, "num_tokens": 266444392.0, "step": 44520 }, { "epoch": 0.47501947019726243, "grad_norm": 0.7241097379908567, "learning_rate": 3.1202883762918556e-05, "loss": 0.5582, "num_tokens": 266474276.0, "step": 44525 }, { "epoch": 0.4750728132034609, "grad_norm": 1.0187050681015373, "learning_rate": 3.119896876073084e-05, "loss": 0.5565, "num_tokens": 266495181.0, "step": 44530 }, { "epoch": 0.47512615620965937, "grad_norm": 1.6216740863771562, "learning_rate": 3.1195053643438794e-05, "loss": 0.6813, "num_tokens": 266517712.0, "step": 44535 }, { "epoch": 0.4751794992158578, "grad_norm": 1.3955959623600256, "learning_rate": 3.119113841116428e-05, "loss": 0.5546, "num_tokens": 266533484.0, "step": 44540 }, { "epoch": 0.47523284222205625, "grad_norm": 0.7281461475615552, "learning_rate": 3.1187223064029126e-05, "loss": 0.5237, "num_tokens": 266565486.0, "step": 44545 }, { "epoch": 0.4752861852282547, "grad_norm": 1.823518459282713, "learning_rate": 3.118330760215515e-05, "loss": 0.4751, "num_tokens": 266592346.0, "step": 44550 }, { "epoch": 0.4753395282344532, "grad_norm": 1.003680122703316, "learning_rate": 3.117939202566421e-05, "loss": 0.5989, "num_tokens": 266631024.0, "step": 44555 }, { "epoch": 0.47539287124065166, "grad_norm": 2.043341284036614, "learning_rate": 3.1175476334678155e-05, "loss": 0.5772, "num_tokens": 266664571.0, "step": 44560 }, { "epoch": 0.4754462142468501, "grad_norm": 0.9988220074615466, "learning_rate": 3.117156052931883e-05, "loss": 0.5537, "num_tokens": 266691245.0, "step": 44565 }, { "epoch": 0.47549955725304854, "grad_norm": 1.5061112424706538, "learning_rate": 3.1167644609708075e-05, "loss": 0.5233, "num_tokens": 266723694.0, "step": 44570 }, { "epoch": 0.475552900259247, "grad_norm": 0.9016755300712698, "learning_rate": 3.116372857596775e-05, "loss": 0.6015, "num_tokens": 266752995.0, "step": 44575 }, { "epoch": 0.4756062432654455, "grad_norm": 1.4604681836221147, "learning_rate": 3.115981242821973e-05, "loss": 0.5931, "num_tokens": 266783533.0, "step": 44580 }, { "epoch": 0.4756595862716439, "grad_norm": 0.656924266199582, "learning_rate": 3.1155896166585855e-05, "loss": 0.4923, "num_tokens": 266821663.0, "step": 44585 }, { "epoch": 0.47571292927784237, "grad_norm": 1.7238632909645786, "learning_rate": 3.1151979791188e-05, "loss": 0.5681, "num_tokens": 266855833.0, "step": 44590 }, { "epoch": 0.47576627228404084, "grad_norm": 0.638352877496484, "learning_rate": 3.114806330214804e-05, "loss": 0.5616, "num_tokens": 266885752.0, "step": 44595 }, { "epoch": 0.4758196152902393, "grad_norm": 1.0995436799084792, "learning_rate": 3.114414669958784e-05, "loss": 0.5559, "num_tokens": 266902225.0, "step": 44600 }, { "epoch": 0.4758729582964378, "grad_norm": 1.0063320876182011, "learning_rate": 3.1140229983629285e-05, "loss": 0.4248, "num_tokens": 266919749.0, "step": 44605 }, { "epoch": 0.4759263013026362, "grad_norm": 1.0729415101142374, "learning_rate": 3.113631315439425e-05, "loss": 0.4658, "num_tokens": 266941817.0, "step": 44610 }, { "epoch": 0.47597964430883466, "grad_norm": 0.837267966305359, "learning_rate": 3.1132396212004604e-05, "loss": 0.5624, "num_tokens": 266974924.0, "step": 44615 }, { "epoch": 0.47603298731503313, "grad_norm": 1.1361200503176854, "learning_rate": 3.112847915658227e-05, "loss": 0.4084, "num_tokens": 266997494.0, "step": 44620 }, { "epoch": 0.4760863303212316, "grad_norm": 0.8203077447778815, "learning_rate": 3.1124561988249105e-05, "loss": 0.5245, "num_tokens": 267042267.0, "step": 44625 }, { "epoch": 0.47613967332743, "grad_norm": 0.7319767655964429, "learning_rate": 3.112064470712702e-05, "loss": 0.5188, "num_tokens": 267081487.0, "step": 44630 }, { "epoch": 0.4761930163336285, "grad_norm": 1.1246671074136931, "learning_rate": 3.1116727313337904e-05, "loss": 0.6233, "num_tokens": 267116471.0, "step": 44635 }, { "epoch": 0.47624635933982695, "grad_norm": 1.4013518405891219, "learning_rate": 3.111280980700367e-05, "loss": 0.5006, "num_tokens": 267147235.0, "step": 44640 }, { "epoch": 0.4762997023460254, "grad_norm": 0.9179960421936261, "learning_rate": 3.110889218824621e-05, "loss": 0.5173, "num_tokens": 267176567.0, "step": 44645 }, { "epoch": 0.4763530453522239, "grad_norm": 0.892261068403418, "learning_rate": 3.110497445718744e-05, "loss": 0.5377, "num_tokens": 267205889.0, "step": 44650 }, { "epoch": 0.4764063883584223, "grad_norm": 0.874599807814514, "learning_rate": 3.110105661394927e-05, "loss": 0.4638, "num_tokens": 267236155.0, "step": 44655 }, { "epoch": 0.4764597313646208, "grad_norm": 0.7376198271701959, "learning_rate": 3.109713865865362e-05, "loss": 0.5104, "num_tokens": 267274721.0, "step": 44660 }, { "epoch": 0.47651307437081925, "grad_norm": 0.6200731465768479, "learning_rate": 3.1093220591422396e-05, "loss": 0.7093, "num_tokens": 267295794.0, "step": 44665 }, { "epoch": 0.4765664173770177, "grad_norm": 0.8856954034642166, "learning_rate": 3.108930241237753e-05, "loss": 0.5662, "num_tokens": 267322682.0, "step": 44670 }, { "epoch": 0.47661976038321613, "grad_norm": 0.8709346534105092, "learning_rate": 3.108538412164095e-05, "loss": 0.4832, "num_tokens": 267345098.0, "step": 44675 }, { "epoch": 0.4766731033894146, "grad_norm": 0.9753561168768712, "learning_rate": 3.108146571933458e-05, "loss": 0.4372, "num_tokens": 267376337.0, "step": 44680 }, { "epoch": 0.47672644639561307, "grad_norm": 0.9153867166767578, "learning_rate": 3.107754720558035e-05, "loss": 0.5127, "num_tokens": 267399886.0, "step": 44685 }, { "epoch": 0.47677978940181154, "grad_norm": 1.744769821512313, "learning_rate": 3.10736285805002e-05, "loss": 0.6024, "num_tokens": 267446310.0, "step": 44690 }, { "epoch": 0.47683313240801, "grad_norm": 1.0228434944837421, "learning_rate": 3.1069709844216064e-05, "loss": 0.5542, "num_tokens": 267472190.0, "step": 44695 }, { "epoch": 0.4768864754142084, "grad_norm": 0.6921893623231722, "learning_rate": 3.10657909968499e-05, "loss": 0.6234, "num_tokens": 267511748.0, "step": 44700 }, { "epoch": 0.4769398184204069, "grad_norm": 0.7919195017318643, "learning_rate": 3.106187203852364e-05, "loss": 0.3953, "num_tokens": 267535164.0, "step": 44705 }, { "epoch": 0.47699316142660536, "grad_norm": 0.7255491505438489, "learning_rate": 3.105795296935924e-05, "loss": 0.4631, "num_tokens": 267568046.0, "step": 44710 }, { "epoch": 0.47704650443280383, "grad_norm": 0.9770916936439183, "learning_rate": 3.1054033789478646e-05, "loss": 0.379, "num_tokens": 267592421.0, "step": 44715 }, { "epoch": 0.47709984743900224, "grad_norm": 1.6764603327316823, "learning_rate": 3.105011449900382e-05, "loss": 0.682, "num_tokens": 267619222.0, "step": 44720 }, { "epoch": 0.4771531904452007, "grad_norm": 1.2125159318954017, "learning_rate": 3.104619509805673e-05, "loss": 0.5642, "num_tokens": 267640017.0, "step": 44725 }, { "epoch": 0.4772065334513992, "grad_norm": 0.9168327670241674, "learning_rate": 3.104227558675934e-05, "loss": 0.6462, "num_tokens": 267681231.0, "step": 44730 }, { "epoch": 0.47725987645759765, "grad_norm": 0.7660318852075573, "learning_rate": 3.103835596523359e-05, "loss": 0.4798, "num_tokens": 267706287.0, "step": 44735 }, { "epoch": 0.4773132194637961, "grad_norm": 1.0768604565941415, "learning_rate": 3.1034436233601476e-05, "loss": 0.5637, "num_tokens": 267738883.0, "step": 44740 }, { "epoch": 0.47736656246999454, "grad_norm": 1.1908721284622557, "learning_rate": 3.103051639198497e-05, "loss": 0.5474, "num_tokens": 267760665.0, "step": 44745 }, { "epoch": 0.477419905476193, "grad_norm": 1.5743630488981808, "learning_rate": 3.102659644050606e-05, "loss": 0.4697, "num_tokens": 267781456.0, "step": 44750 }, { "epoch": 0.4774732484823915, "grad_norm": 0.879186047091396, "learning_rate": 3.1022676379286695e-05, "loss": 0.6212, "num_tokens": 267820152.0, "step": 44755 }, { "epoch": 0.47752659148858995, "grad_norm": 1.305138911929416, "learning_rate": 3.101875620844888e-05, "loss": 0.5309, "num_tokens": 267849761.0, "step": 44760 }, { "epoch": 0.47757993449478836, "grad_norm": 1.1049211030779045, "learning_rate": 3.10148359281146e-05, "loss": 0.5783, "num_tokens": 267874604.0, "step": 44765 }, { "epoch": 0.47763327750098683, "grad_norm": 0.7065475206741589, "learning_rate": 3.1010915538405847e-05, "loss": 0.7109, "num_tokens": 267924571.0, "step": 44770 }, { "epoch": 0.4776866205071853, "grad_norm": 0.8190808870916549, "learning_rate": 3.1006995039444606e-05, "loss": 0.4994, "num_tokens": 267978955.0, "step": 44775 }, { "epoch": 0.47773996351338377, "grad_norm": 1.1532544092553023, "learning_rate": 3.1003074431352894e-05, "loss": 0.4744, "num_tokens": 267999880.0, "step": 44780 }, { "epoch": 0.47779330651958224, "grad_norm": 0.646161595843182, "learning_rate": 3.09991537142527e-05, "loss": 0.4859, "num_tokens": 268033811.0, "step": 44785 }, { "epoch": 0.47784664952578065, "grad_norm": 1.1552517487178955, "learning_rate": 3.099523288826603e-05, "loss": 0.5695, "num_tokens": 268053357.0, "step": 44790 }, { "epoch": 0.4778999925319791, "grad_norm": 1.1262234596414447, "learning_rate": 3.099131195351488e-05, "loss": 0.5618, "num_tokens": 268067637.0, "step": 44795 }, { "epoch": 0.4779533355381776, "grad_norm": 1.4430055288188308, "learning_rate": 3.098739091012128e-05, "loss": 0.4781, "num_tokens": 268098790.0, "step": 44800 }, { "epoch": 0.47800667854437606, "grad_norm": 0.8036597863492965, "learning_rate": 3.098346975820725e-05, "loss": 0.5981, "num_tokens": 268125777.0, "step": 44805 }, { "epoch": 0.4780600215505745, "grad_norm": 0.9040485590283074, "learning_rate": 3.097954849789478e-05, "loss": 0.4838, "num_tokens": 268147637.0, "step": 44810 }, { "epoch": 0.47811336455677295, "grad_norm": 0.905578540261226, "learning_rate": 3.097562712930592e-05, "loss": 0.6045, "num_tokens": 268197931.0, "step": 44815 }, { "epoch": 0.4781667075629714, "grad_norm": 3.078967825184061, "learning_rate": 3.0971705652562674e-05, "loss": 0.5581, "num_tokens": 268218373.0, "step": 44820 }, { "epoch": 0.4782200505691699, "grad_norm": 1.3323164038752813, "learning_rate": 3.096778406778708e-05, "loss": 0.4883, "num_tokens": 268244407.0, "step": 44825 }, { "epoch": 0.47827339357536836, "grad_norm": 0.8537756609102819, "learning_rate": 3.0963862375101174e-05, "loss": 0.5712, "num_tokens": 268274321.0, "step": 44830 }, { "epoch": 0.47832673658156677, "grad_norm": 0.8081892679099908, "learning_rate": 3.0959940574626986e-05, "loss": 0.5097, "num_tokens": 268296333.0, "step": 44835 }, { "epoch": 0.47838007958776524, "grad_norm": 0.6978556877946389, "learning_rate": 3.0956018666486556e-05, "loss": 0.6827, "num_tokens": 268337674.0, "step": 44840 }, { "epoch": 0.4784334225939637, "grad_norm": 0.8279880739205855, "learning_rate": 3.0952096650801916e-05, "loss": 0.4495, "num_tokens": 268357165.0, "step": 44845 }, { "epoch": 0.4784867656001622, "grad_norm": 0.7105806984395404, "learning_rate": 3.0948174527695114e-05, "loss": 0.5185, "num_tokens": 268399303.0, "step": 44850 }, { "epoch": 0.4785401086063606, "grad_norm": 1.3733958848923093, "learning_rate": 3.0944252297288225e-05, "loss": 0.5319, "num_tokens": 268418989.0, "step": 44855 }, { "epoch": 0.47859345161255906, "grad_norm": 0.7953418262628889, "learning_rate": 3.094032995970327e-05, "loss": 0.535, "num_tokens": 268448141.0, "step": 44860 }, { "epoch": 0.47864679461875753, "grad_norm": 1.0673013499430215, "learning_rate": 3.09364075150623e-05, "loss": 0.546, "num_tokens": 268484066.0, "step": 44865 }, { "epoch": 0.478700137624956, "grad_norm": 0.8983073313334908, "learning_rate": 3.093248496348739e-05, "loss": 0.3967, "num_tokens": 268513888.0, "step": 44870 }, { "epoch": 0.47875348063115447, "grad_norm": 0.8135332548964934, "learning_rate": 3.0928562305100614e-05, "loss": 0.6112, "num_tokens": 268549318.0, "step": 44875 }, { "epoch": 0.4788068236373529, "grad_norm": 0.8763070369265443, "learning_rate": 3.092463954002401e-05, "loss": 0.55, "num_tokens": 268586746.0, "step": 44880 }, { "epoch": 0.47886016664355135, "grad_norm": 1.3132819789637404, "learning_rate": 3.092071666837966e-05, "loss": 0.4488, "num_tokens": 268602159.0, "step": 44885 }, { "epoch": 0.4789135096497498, "grad_norm": 0.8693800722257737, "learning_rate": 3.091679369028964e-05, "loss": 0.603, "num_tokens": 268631388.0, "step": 44890 }, { "epoch": 0.4789668526559483, "grad_norm": 0.7901212870961128, "learning_rate": 3.091287060587601e-05, "loss": 0.5007, "num_tokens": 268658697.0, "step": 44895 }, { "epoch": 0.4790201956621467, "grad_norm": 1.331551974778624, "learning_rate": 3.090894741526086e-05, "loss": 0.4071, "num_tokens": 268685640.0, "step": 44900 }, { "epoch": 0.4790735386683452, "grad_norm": 0.9671195627999708, "learning_rate": 3.0905024118566265e-05, "loss": 0.5631, "num_tokens": 268722684.0, "step": 44905 }, { "epoch": 0.47912688167454365, "grad_norm": 1.2575530497850402, "learning_rate": 3.0901100715914315e-05, "loss": 0.6499, "num_tokens": 268749757.0, "step": 44910 }, { "epoch": 0.4791802246807421, "grad_norm": 0.9062228054394191, "learning_rate": 3.089717720742711e-05, "loss": 0.4731, "num_tokens": 268768301.0, "step": 44915 }, { "epoch": 0.4792335676869406, "grad_norm": 0.8363950921281894, "learning_rate": 3.089325359322671e-05, "loss": 0.6391, "num_tokens": 268827830.0, "step": 44920 }, { "epoch": 0.479286910693139, "grad_norm": 0.6479240595178699, "learning_rate": 3.088932987343523e-05, "loss": 0.477, "num_tokens": 268854270.0, "step": 44925 }, { "epoch": 0.47934025369933747, "grad_norm": 1.167050149875904, "learning_rate": 3.088540604817478e-05, "loss": 0.6297, "num_tokens": 268875743.0, "step": 44930 }, { "epoch": 0.47939359670553594, "grad_norm": 0.8862889897419881, "learning_rate": 3.088148211756744e-05, "loss": 0.5746, "num_tokens": 268909263.0, "step": 44935 }, { "epoch": 0.4794469397117344, "grad_norm": 1.3945299176791788, "learning_rate": 3.0877558081735314e-05, "loss": 0.6434, "num_tokens": 268947142.0, "step": 44940 }, { "epoch": 0.4795002827179328, "grad_norm": 0.8343461130104204, "learning_rate": 3.0873633940800523e-05, "loss": 0.493, "num_tokens": 268967977.0, "step": 44945 }, { "epoch": 0.4795536257241313, "grad_norm": 1.023083227751352, "learning_rate": 3.086970969488519e-05, "loss": 0.506, "num_tokens": 269004757.0, "step": 44950 }, { "epoch": 0.47960696873032976, "grad_norm": 1.4225410257666384, "learning_rate": 3.086578534411139e-05, "loss": 0.5723, "num_tokens": 269027560.0, "step": 44955 }, { "epoch": 0.47966031173652823, "grad_norm": 2.497139478634585, "learning_rate": 3.0861860888601266e-05, "loss": 0.5943, "num_tokens": 269072345.0, "step": 44960 }, { "epoch": 0.4797136547427267, "grad_norm": 0.977970814289529, "learning_rate": 3.085793632847695e-05, "loss": 0.5335, "num_tokens": 269088129.0, "step": 44965 }, { "epoch": 0.4797669977489251, "grad_norm": 0.7089293588952004, "learning_rate": 3.0854011663860544e-05, "loss": 0.5865, "num_tokens": 269125595.0, "step": 44970 }, { "epoch": 0.4798203407551236, "grad_norm": 0.9010452733886497, "learning_rate": 3.085008689487419e-05, "loss": 0.7177, "num_tokens": 269160867.0, "step": 44975 }, { "epoch": 0.47987368376132206, "grad_norm": 0.9255080036787172, "learning_rate": 3.0846162021640003e-05, "loss": 0.4409, "num_tokens": 269186237.0, "step": 44980 }, { "epoch": 0.4799270267675205, "grad_norm": 0.6776234815183283, "learning_rate": 3.0842237044280133e-05, "loss": 0.5881, "num_tokens": 269220757.0, "step": 44985 }, { "epoch": 0.47998036977371894, "grad_norm": 1.0113102054650764, "learning_rate": 3.083831196291671e-05, "loss": 0.5646, "num_tokens": 269266884.0, "step": 44990 }, { "epoch": 0.4800337127799174, "grad_norm": 1.0172715962084544, "learning_rate": 3.083438677767188e-05, "loss": 0.5417, "num_tokens": 269303426.0, "step": 44995 }, { "epoch": 0.4800870557861159, "grad_norm": 0.862701217373915, "learning_rate": 3.0830461488667784e-05, "loss": 0.7366, "num_tokens": 269341948.0, "step": 45000 }, { "epoch": 0.48014039879231435, "grad_norm": 0.6719529565201755, "learning_rate": 3.0826536096026566e-05, "loss": 0.6248, "num_tokens": 269386268.0, "step": 45005 }, { "epoch": 0.4801937417985128, "grad_norm": 1.1394535565695434, "learning_rate": 3.082261059987037e-05, "loss": 0.4938, "num_tokens": 269425916.0, "step": 45010 }, { "epoch": 0.48024708480471123, "grad_norm": 0.6367336495238686, "learning_rate": 3.081868500032136e-05, "loss": 0.4662, "num_tokens": 269458270.0, "step": 45015 }, { "epoch": 0.4803004278109097, "grad_norm": 0.7503116145377128, "learning_rate": 3.08147592975017e-05, "loss": 0.5767, "num_tokens": 269487767.0, "step": 45020 }, { "epoch": 0.48035377081710817, "grad_norm": 1.1250441346391964, "learning_rate": 3.081083349153353e-05, "loss": 0.4783, "num_tokens": 269517420.0, "step": 45025 }, { "epoch": 0.48040711382330664, "grad_norm": 0.8020196736891199, "learning_rate": 3.080690758253901e-05, "loss": 0.5201, "num_tokens": 269550122.0, "step": 45030 }, { "epoch": 0.48046045682950506, "grad_norm": 0.7992691876659627, "learning_rate": 3.080298157064034e-05, "loss": 0.6017, "num_tokens": 269565882.0, "step": 45035 }, { "epoch": 0.4805137998357035, "grad_norm": 0.898919675063459, "learning_rate": 3.079905545595966e-05, "loss": 0.4781, "num_tokens": 269588201.0, "step": 45040 }, { "epoch": 0.480567142841902, "grad_norm": 0.7917410572057612, "learning_rate": 3.0795129238619155e-05, "loss": 0.5268, "num_tokens": 269612286.0, "step": 45045 }, { "epoch": 0.48062048584810046, "grad_norm": 0.7164149750109281, "learning_rate": 3.079120291874099e-05, "loss": 0.5118, "num_tokens": 269629466.0, "step": 45050 }, { "epoch": 0.48067382885429893, "grad_norm": 1.5096284433097078, "learning_rate": 3.078727649644735e-05, "loss": 0.4659, "num_tokens": 269657033.0, "step": 45055 }, { "epoch": 0.48072717186049735, "grad_norm": 0.8727680772346853, "learning_rate": 3.078334997186042e-05, "loss": 0.5826, "num_tokens": 269688077.0, "step": 45060 }, { "epoch": 0.4807805148666958, "grad_norm": 0.9405525330987109, "learning_rate": 3.077942334510238e-05, "loss": 0.5258, "num_tokens": 269707830.0, "step": 45065 }, { "epoch": 0.4808338578728943, "grad_norm": 1.0116822051701673, "learning_rate": 3.077549661629543e-05, "loss": 0.6542, "num_tokens": 269729572.0, "step": 45070 }, { "epoch": 0.48088720087909276, "grad_norm": 1.0379709170668716, "learning_rate": 3.077156978556175e-05, "loss": 0.7007, "num_tokens": 269754804.0, "step": 45075 }, { "epoch": 0.48094054388529117, "grad_norm": 0.9809686868170701, "learning_rate": 3.076764285302354e-05, "loss": 0.5971, "num_tokens": 269785971.0, "step": 45080 }, { "epoch": 0.48099388689148964, "grad_norm": 1.3253037563925611, "learning_rate": 3.0763715818802985e-05, "loss": 0.5048, "num_tokens": 269814714.0, "step": 45085 }, { "epoch": 0.4810472298976881, "grad_norm": 1.0611065002851052, "learning_rate": 3.075978868302231e-05, "loss": 0.5127, "num_tokens": 269839927.0, "step": 45090 }, { "epoch": 0.4811005729038866, "grad_norm": 0.9310955114277625, "learning_rate": 3.07558614458037e-05, "loss": 0.5133, "num_tokens": 269876283.0, "step": 45095 }, { "epoch": 0.48115391591008505, "grad_norm": 0.7009502085779221, "learning_rate": 3.0751934107269376e-05, "loss": 0.5048, "num_tokens": 269915543.0, "step": 45100 }, { "epoch": 0.48120725891628346, "grad_norm": 0.672158982318317, "learning_rate": 3.074800666754153e-05, "loss": 0.6376, "num_tokens": 269952060.0, "step": 45105 }, { "epoch": 0.48126060192248193, "grad_norm": 0.7032311721578052, "learning_rate": 3.07440791267424e-05, "loss": 0.4818, "num_tokens": 269980848.0, "step": 45110 }, { "epoch": 0.4813139449286804, "grad_norm": 1.0719676708685164, "learning_rate": 3.074015148499419e-05, "loss": 0.4641, "num_tokens": 270003342.0, "step": 45115 }, { "epoch": 0.4813672879348789, "grad_norm": 0.7252672968172762, "learning_rate": 3.0736223742419115e-05, "loss": 0.4763, "num_tokens": 270033989.0, "step": 45120 }, { "epoch": 0.4814206309410773, "grad_norm": 0.7713651533501426, "learning_rate": 3.073229589913941e-05, "loss": 0.5007, "num_tokens": 270072446.0, "step": 45125 }, { "epoch": 0.48147397394727576, "grad_norm": 1.129340185343144, "learning_rate": 3.072836795527729e-05, "loss": 0.553, "num_tokens": 270105691.0, "step": 45130 }, { "epoch": 0.4815273169534742, "grad_norm": 1.226031949688593, "learning_rate": 3.0724439910955e-05, "loss": 0.5273, "num_tokens": 270125851.0, "step": 45135 }, { "epoch": 0.4815806599596727, "grad_norm": 0.7707330509955354, "learning_rate": 3.072051176629476e-05, "loss": 0.4276, "num_tokens": 270152385.0, "step": 45140 }, { "epoch": 0.48163400296587117, "grad_norm": 1.3413325437152772, "learning_rate": 3.071658352141881e-05, "loss": 0.5382, "num_tokens": 270181384.0, "step": 45145 }, { "epoch": 0.4816873459720696, "grad_norm": 0.7730475334535509, "learning_rate": 3.0712655176449375e-05, "loss": 0.5033, "num_tokens": 270220293.0, "step": 45150 }, { "epoch": 0.48174068897826805, "grad_norm": 1.204640735807998, "learning_rate": 3.070872673150872e-05, "loss": 0.5556, "num_tokens": 270243384.0, "step": 45155 }, { "epoch": 0.4817940319844665, "grad_norm": 3.361694948684285, "learning_rate": 3.070479818671908e-05, "loss": 0.751, "num_tokens": 270279299.0, "step": 45160 }, { "epoch": 0.481847374990665, "grad_norm": 2.572552378279329, "learning_rate": 3.070086954220271e-05, "loss": 0.7131, "num_tokens": 270310489.0, "step": 45165 }, { "epoch": 0.4819007179968634, "grad_norm": 1.0801788430687544, "learning_rate": 3.0696940798081846e-05, "loss": 0.4976, "num_tokens": 270340613.0, "step": 45170 }, { "epoch": 0.4819540610030619, "grad_norm": 0.6387396644687166, "learning_rate": 3.0693011954478754e-05, "loss": 0.4854, "num_tokens": 270381044.0, "step": 45175 }, { "epoch": 0.48200740400926034, "grad_norm": 0.7873795876326195, "learning_rate": 3.068908301151568e-05, "loss": 0.5445, "num_tokens": 270412793.0, "step": 45180 }, { "epoch": 0.4820607470154588, "grad_norm": 0.7312203249692671, "learning_rate": 3.0685153969314906e-05, "loss": 0.5174, "num_tokens": 270442185.0, "step": 45185 }, { "epoch": 0.4821140900216573, "grad_norm": 1.0997970251263467, "learning_rate": 3.068122482799868e-05, "loss": 0.4264, "num_tokens": 270458816.0, "step": 45190 }, { "epoch": 0.4821674330278557, "grad_norm": 0.9134461852907336, "learning_rate": 3.067729558768926e-05, "loss": 0.7065, "num_tokens": 270474966.0, "step": 45195 }, { "epoch": 0.48222077603405417, "grad_norm": 0.7268246385273458, "learning_rate": 3.067336624850894e-05, "loss": 0.5447, "num_tokens": 270511391.0, "step": 45200 }, { "epoch": 0.48227411904025264, "grad_norm": 1.098074713203653, "learning_rate": 3.066943681057998e-05, "loss": 0.6046, "num_tokens": 270540104.0, "step": 45205 }, { "epoch": 0.4823274620464511, "grad_norm": 0.695203018846276, "learning_rate": 3.066550727402465e-05, "loss": 0.6553, "num_tokens": 270587610.0, "step": 45210 }, { "epoch": 0.4823808050526495, "grad_norm": 0.8573593158728336, "learning_rate": 3.066157763896524e-05, "loss": 0.5659, "num_tokens": 270603982.0, "step": 45215 }, { "epoch": 0.482434148058848, "grad_norm": 0.8016868120837876, "learning_rate": 3.065764790552403e-05, "loss": 0.4873, "num_tokens": 270655954.0, "step": 45220 }, { "epoch": 0.48248749106504646, "grad_norm": 0.863465862907778, "learning_rate": 3.06537180738233e-05, "loss": 0.4632, "num_tokens": 270687657.0, "step": 45225 }, { "epoch": 0.48254083407124493, "grad_norm": 1.2491967365786691, "learning_rate": 3.064978814398534e-05, "loss": 0.4633, "num_tokens": 270719057.0, "step": 45230 }, { "epoch": 0.4825941770774434, "grad_norm": 1.0646642245177507, "learning_rate": 3.064585811613245e-05, "loss": 0.4768, "num_tokens": 270749015.0, "step": 45235 }, { "epoch": 0.4826475200836418, "grad_norm": 1.5081463275985532, "learning_rate": 3.064192799038691e-05, "loss": 0.4772, "num_tokens": 270768040.0, "step": 45240 }, { "epoch": 0.4827008630898403, "grad_norm": 0.8747299838102429, "learning_rate": 3.063799776687103e-05, "loss": 0.484, "num_tokens": 270802517.0, "step": 45245 }, { "epoch": 0.48275420609603875, "grad_norm": 0.6485466069114781, "learning_rate": 3.0634067445707106e-05, "loss": 0.5084, "num_tokens": 270838160.0, "step": 45250 }, { "epoch": 0.4828075491022372, "grad_norm": 1.1498135932847813, "learning_rate": 3.063013702701743e-05, "loss": 0.686, "num_tokens": 270868007.0, "step": 45255 }, { "epoch": 0.48286089210843564, "grad_norm": 1.1330767366865524, "learning_rate": 3.062620651092433e-05, "loss": 0.5543, "num_tokens": 270893605.0, "step": 45260 }, { "epoch": 0.4829142351146341, "grad_norm": 0.830378745553284, "learning_rate": 3.06222758975501e-05, "loss": 0.5266, "num_tokens": 270929636.0, "step": 45265 }, { "epoch": 0.4829675781208326, "grad_norm": 0.8507277657358705, "learning_rate": 3.0618345187017056e-05, "loss": 0.5863, "num_tokens": 270965784.0, "step": 45270 }, { "epoch": 0.48302092112703104, "grad_norm": 0.8750318524240621, "learning_rate": 3.061441437944752e-05, "loss": 0.7407, "num_tokens": 271002352.0, "step": 45275 }, { "epoch": 0.4830742641332295, "grad_norm": 1.5913292931227494, "learning_rate": 3.06104834749638e-05, "loss": 0.5316, "num_tokens": 271020876.0, "step": 45280 }, { "epoch": 0.48312760713942793, "grad_norm": 1.6330795929642754, "learning_rate": 3.060655247368823e-05, "loss": 0.5771, "num_tokens": 271040599.0, "step": 45285 }, { "epoch": 0.4831809501456264, "grad_norm": 1.016132632659668, "learning_rate": 3.0602621375743126e-05, "loss": 0.4921, "num_tokens": 271073106.0, "step": 45290 }, { "epoch": 0.48323429315182487, "grad_norm": 0.8357312364390174, "learning_rate": 3.0598690181250815e-05, "loss": 0.555, "num_tokens": 271097707.0, "step": 45295 }, { "epoch": 0.48328763615802334, "grad_norm": 0.8311696036371216, "learning_rate": 3.059475889033363e-05, "loss": 0.45, "num_tokens": 271116068.0, "step": 45300 }, { "epoch": 0.48334097916422175, "grad_norm": 1.094767228769572, "learning_rate": 3.059082750311391e-05, "loss": 0.5596, "num_tokens": 271137877.0, "step": 45305 }, { "epoch": 0.4833943221704202, "grad_norm": 0.909105971048047, "learning_rate": 3.058689601971398e-05, "loss": 0.6263, "num_tokens": 271195204.0, "step": 45310 }, { "epoch": 0.4834476651766187, "grad_norm": 0.8853978875897613, "learning_rate": 3.058296444025619e-05, "loss": 0.648, "num_tokens": 271232746.0, "step": 45315 }, { "epoch": 0.48350100818281716, "grad_norm": 1.9595899672510952, "learning_rate": 3.057903276486288e-05, "loss": 0.5014, "num_tokens": 271271781.0, "step": 45320 }, { "epoch": 0.48355435118901563, "grad_norm": 0.7577838481685868, "learning_rate": 3.057510099365639e-05, "loss": 0.5053, "num_tokens": 271296079.0, "step": 45325 }, { "epoch": 0.48360769419521404, "grad_norm": 0.6922260013732391, "learning_rate": 3.057116912675909e-05, "loss": 0.4746, "num_tokens": 271322852.0, "step": 45330 }, { "epoch": 0.4836610372014125, "grad_norm": 0.6182238075446257, "learning_rate": 3.05672371642933e-05, "loss": 0.615, "num_tokens": 271358761.0, "step": 45335 }, { "epoch": 0.483714380207611, "grad_norm": 1.0503417765220369, "learning_rate": 3.056330510638138e-05, "loss": 0.5004, "num_tokens": 271382746.0, "step": 45340 }, { "epoch": 0.48376772321380945, "grad_norm": 1.188230647360555, "learning_rate": 3.055937295314571e-05, "loss": 0.623, "num_tokens": 271414534.0, "step": 45345 }, { "epoch": 0.48382106622000787, "grad_norm": 1.0942141000350745, "learning_rate": 3.055544070470865e-05, "loss": 0.6444, "num_tokens": 271447875.0, "step": 45350 }, { "epoch": 0.48387440922620634, "grad_norm": 0.7564769598123915, "learning_rate": 3.055150836119253e-05, "loss": 0.568, "num_tokens": 271490005.0, "step": 45355 }, { "epoch": 0.4839277522324048, "grad_norm": 1.2005020314576273, "learning_rate": 3.054757592271975e-05, "loss": 0.6104, "num_tokens": 271512097.0, "step": 45360 }, { "epoch": 0.4839810952386033, "grad_norm": 0.7993060726351083, "learning_rate": 3.0543643389412665e-05, "loss": 0.5101, "num_tokens": 271540865.0, "step": 45365 }, { "epoch": 0.48403443824480175, "grad_norm": 1.0416172432327264, "learning_rate": 3.053971076139365e-05, "loss": 0.535, "num_tokens": 271567604.0, "step": 45370 }, { "epoch": 0.48408778125100016, "grad_norm": 0.7616941184894046, "learning_rate": 3.0535778038785076e-05, "loss": 0.4648, "num_tokens": 271588714.0, "step": 45375 }, { "epoch": 0.48414112425719863, "grad_norm": 1.342911883501767, "learning_rate": 3.053184522170933e-05, "loss": 0.5911, "num_tokens": 271619648.0, "step": 45380 }, { "epoch": 0.4841944672633971, "grad_norm": 0.858126341301555, "learning_rate": 3.0527912310288784e-05, "loss": 0.6004, "num_tokens": 271647135.0, "step": 45385 }, { "epoch": 0.48424781026959557, "grad_norm": 0.9665023494785656, "learning_rate": 3.052397930464583e-05, "loss": 0.5157, "num_tokens": 271681845.0, "step": 45390 }, { "epoch": 0.484301153275794, "grad_norm": 0.7289034583740158, "learning_rate": 3.052004620490285e-05, "loss": 0.5541, "num_tokens": 271704433.0, "step": 45395 }, { "epoch": 0.48435449628199245, "grad_norm": 1.7730956866011953, "learning_rate": 3.0516113011182234e-05, "loss": 0.5739, "num_tokens": 271736437.0, "step": 45400 }, { "epoch": 0.4844078392881909, "grad_norm": 0.7226604449706653, "learning_rate": 3.051217972360638e-05, "loss": 0.4178, "num_tokens": 271761754.0, "step": 45405 }, { "epoch": 0.4844611822943894, "grad_norm": 0.9651011437026299, "learning_rate": 3.050824634229768e-05, "loss": 0.4027, "num_tokens": 271779659.0, "step": 45410 }, { "epoch": 0.48451452530058786, "grad_norm": 1.3194902395118864, "learning_rate": 3.050431286737852e-05, "loss": 0.6491, "num_tokens": 271826093.0, "step": 45415 }, { "epoch": 0.4845678683067863, "grad_norm": 1.0649459138125195, "learning_rate": 3.0500379298971334e-05, "loss": 0.5528, "num_tokens": 271847361.0, "step": 45420 }, { "epoch": 0.48462121131298475, "grad_norm": 0.6609052214823595, "learning_rate": 3.0496445637198496e-05, "loss": 0.4935, "num_tokens": 271879647.0, "step": 45425 }, { "epoch": 0.4846745543191832, "grad_norm": 1.4490131880590895, "learning_rate": 3.0492511882182422e-05, "loss": 0.5206, "num_tokens": 271899092.0, "step": 45430 }, { "epoch": 0.4847278973253817, "grad_norm": 0.940160765140753, "learning_rate": 3.0488578034045535e-05, "loss": 0.6241, "num_tokens": 271939934.0, "step": 45435 }, { "epoch": 0.4847812403315801, "grad_norm": 1.1264335916417374, "learning_rate": 3.0484644092910237e-05, "loss": 0.6517, "num_tokens": 271974065.0, "step": 45440 }, { "epoch": 0.48483458333777857, "grad_norm": 1.495552065872985, "learning_rate": 3.0480710058898936e-05, "loss": 0.6417, "num_tokens": 272012079.0, "step": 45445 }, { "epoch": 0.48488792634397704, "grad_norm": 1.1143990628747549, "learning_rate": 3.0476775932134067e-05, "loss": 0.5488, "num_tokens": 272038968.0, "step": 45450 }, { "epoch": 0.4849412693501755, "grad_norm": 1.2198186259801234, "learning_rate": 3.0472841712738048e-05, "loss": 0.5386, "num_tokens": 272070398.0, "step": 45455 }, { "epoch": 0.484994612356374, "grad_norm": 2.244371749025261, "learning_rate": 3.0468907400833295e-05, "loss": 0.4644, "num_tokens": 272092390.0, "step": 45460 }, { "epoch": 0.4850479553625724, "grad_norm": 1.1410700237333813, "learning_rate": 3.0464972996542252e-05, "loss": 0.576, "num_tokens": 272118298.0, "step": 45465 }, { "epoch": 0.48510129836877086, "grad_norm": 1.4394221872370352, "learning_rate": 3.0461038499987326e-05, "loss": 0.5035, "num_tokens": 272136735.0, "step": 45470 }, { "epoch": 0.48515464137496933, "grad_norm": 1.3722045519215789, "learning_rate": 3.0457103911290972e-05, "loss": 0.6244, "num_tokens": 272171907.0, "step": 45475 }, { "epoch": 0.4852079843811678, "grad_norm": 1.11812802482192, "learning_rate": 3.0453169230575616e-05, "loss": 0.629, "num_tokens": 272212324.0, "step": 45480 }, { "epoch": 0.4852613273873662, "grad_norm": 0.77717299360638, "learning_rate": 3.0449234457963704e-05, "loss": 0.5761, "num_tokens": 272256275.0, "step": 45485 }, { "epoch": 0.4853146703935647, "grad_norm": 0.7251417237374348, "learning_rate": 3.0445299593577666e-05, "loss": 0.4258, "num_tokens": 272286366.0, "step": 45490 }, { "epoch": 0.48536801339976315, "grad_norm": 1.0380363718901904, "learning_rate": 3.0441364637539966e-05, "loss": 0.5571, "num_tokens": 272313222.0, "step": 45495 }, { "epoch": 0.4854213564059616, "grad_norm": 1.289875965816578, "learning_rate": 3.043742958997303e-05, "loss": 0.5526, "num_tokens": 272363705.0, "step": 45500 }, { "epoch": 0.4854746994121601, "grad_norm": 0.6729276585258304, "learning_rate": 3.043349445099932e-05, "loss": 0.5518, "num_tokens": 272402676.0, "step": 45505 }, { "epoch": 0.4855280424183585, "grad_norm": 2.4993387302433967, "learning_rate": 3.0429559220741288e-05, "loss": 0.4655, "num_tokens": 272428895.0, "step": 45510 }, { "epoch": 0.485581385424557, "grad_norm": 1.0286142622336678, "learning_rate": 3.0425623899321397e-05, "loss": 0.5221, "num_tokens": 272466423.0, "step": 45515 }, { "epoch": 0.48563472843075545, "grad_norm": 1.0902926902020578, "learning_rate": 3.0421688486862094e-05, "loss": 0.6057, "num_tokens": 272505139.0, "step": 45520 }, { "epoch": 0.4856880714369539, "grad_norm": 1.0398641105424897, "learning_rate": 3.0417752983485846e-05, "loss": 0.5193, "num_tokens": 272542925.0, "step": 45525 }, { "epoch": 0.48574141444315233, "grad_norm": 0.9564980131062023, "learning_rate": 3.0413817389315126e-05, "loss": 0.6145, "num_tokens": 272574391.0, "step": 45530 }, { "epoch": 0.4857947574493508, "grad_norm": 0.8137687342968842, "learning_rate": 3.0409881704472386e-05, "loss": 0.5352, "num_tokens": 272610618.0, "step": 45535 }, { "epoch": 0.48584810045554927, "grad_norm": 1.454670424550971, "learning_rate": 3.0405945929080105e-05, "loss": 0.5114, "num_tokens": 272637835.0, "step": 45540 }, { "epoch": 0.48590144346174774, "grad_norm": 1.4420364299607698, "learning_rate": 3.0402010063260756e-05, "loss": 0.6193, "num_tokens": 272666053.0, "step": 45545 }, { "epoch": 0.4859547864679462, "grad_norm": 1.4146412480376196, "learning_rate": 3.0398074107136822e-05, "loss": 0.4428, "num_tokens": 272686952.0, "step": 45550 }, { "epoch": 0.4860081294741446, "grad_norm": 1.1874791369424949, "learning_rate": 3.0394138060830764e-05, "loss": 0.4405, "num_tokens": 272718518.0, "step": 45555 }, { "epoch": 0.4860614724803431, "grad_norm": 0.8270115697461519, "learning_rate": 3.039020192446508e-05, "loss": 0.4214, "num_tokens": 272743394.0, "step": 45560 }, { "epoch": 0.48611481548654156, "grad_norm": 0.7677802041626313, "learning_rate": 3.0386265698162246e-05, "loss": 0.6145, "num_tokens": 272770566.0, "step": 45565 }, { "epoch": 0.48616815849274003, "grad_norm": 1.7086969727666437, "learning_rate": 3.0382329382044756e-05, "loss": 0.5267, "num_tokens": 272803541.0, "step": 45570 }, { "epoch": 0.48622150149893845, "grad_norm": 1.1429093175480733, "learning_rate": 3.0378392976235093e-05, "loss": 0.5496, "num_tokens": 272825342.0, "step": 45575 }, { "epoch": 0.4862748445051369, "grad_norm": 1.1219042700441246, "learning_rate": 3.037445648085575e-05, "loss": 0.5453, "num_tokens": 272860800.0, "step": 45580 }, { "epoch": 0.4863281875113354, "grad_norm": 0.8080605076754335, "learning_rate": 3.0370519896029238e-05, "loss": 0.4545, "num_tokens": 272908855.0, "step": 45585 }, { "epoch": 0.48638153051753386, "grad_norm": 2.1921958356426394, "learning_rate": 3.0366583221878036e-05, "loss": 0.5536, "num_tokens": 272939087.0, "step": 45590 }, { "epoch": 0.4864348735237323, "grad_norm": 1.1495804156668554, "learning_rate": 3.0362646458524642e-05, "loss": 0.657, "num_tokens": 272970176.0, "step": 45595 }, { "epoch": 0.48648821652993074, "grad_norm": 1.2873453295859443, "learning_rate": 3.035870960609158e-05, "loss": 0.4849, "num_tokens": 273006318.0, "step": 45600 }, { "epoch": 0.4865415595361292, "grad_norm": 2.3391147436591466, "learning_rate": 3.0354772664701346e-05, "loss": 0.5176, "num_tokens": 273019249.0, "step": 45605 }, { "epoch": 0.4865949025423277, "grad_norm": 0.8784448716265291, "learning_rate": 3.0350835634476453e-05, "loss": 0.6312, "num_tokens": 273046197.0, "step": 45610 }, { "epoch": 0.48664824554852615, "grad_norm": 1.1197869549100792, "learning_rate": 3.0346898515539407e-05, "loss": 0.5406, "num_tokens": 273075185.0, "step": 45615 }, { "epoch": 0.48670158855472456, "grad_norm": 1.4820138814586838, "learning_rate": 3.034296130801273e-05, "loss": 0.661, "num_tokens": 273096267.0, "step": 45620 }, { "epoch": 0.48675493156092303, "grad_norm": 1.060085456749329, "learning_rate": 3.0339024012018934e-05, "loss": 0.4649, "num_tokens": 273118480.0, "step": 45625 }, { "epoch": 0.4868082745671215, "grad_norm": 0.6964415721520906, "learning_rate": 3.0335086627680544e-05, "loss": 0.5334, "num_tokens": 273143607.0, "step": 45630 }, { "epoch": 0.48686161757331997, "grad_norm": 2.1814388366413486, "learning_rate": 3.0331149155120077e-05, "loss": 0.6016, "num_tokens": 273175275.0, "step": 45635 }, { "epoch": 0.48691496057951844, "grad_norm": 0.9285901099281149, "learning_rate": 3.032721159446007e-05, "loss": 0.6026, "num_tokens": 273213253.0, "step": 45640 }, { "epoch": 0.48696830358571686, "grad_norm": 0.775905569624785, "learning_rate": 3.0323273945823045e-05, "loss": 0.7259, "num_tokens": 273254153.0, "step": 45645 }, { "epoch": 0.4870216465919153, "grad_norm": 1.6283932834395984, "learning_rate": 3.031933620933153e-05, "loss": 0.6443, "num_tokens": 273265359.0, "step": 45650 }, { "epoch": 0.4870749895981138, "grad_norm": 1.0475059505995112, "learning_rate": 3.0315398385108062e-05, "loss": 0.7131, "num_tokens": 273301504.0, "step": 45655 }, { "epoch": 0.48712833260431226, "grad_norm": 0.7242347827965925, "learning_rate": 3.0311460473275187e-05, "loss": 0.6448, "num_tokens": 273331426.0, "step": 45660 }, { "epoch": 0.4871816756105107, "grad_norm": 0.6782051972923695, "learning_rate": 3.0307522473955437e-05, "loss": 0.5075, "num_tokens": 273371803.0, "step": 45665 }, { "epoch": 0.48723501861670915, "grad_norm": 0.6092276540086754, "learning_rate": 3.0303584387271343e-05, "loss": 0.5801, "num_tokens": 273419240.0, "step": 45670 }, { "epoch": 0.4872883616229076, "grad_norm": 0.6991525629620412, "learning_rate": 3.0299646213345468e-05, "loss": 0.4263, "num_tokens": 273453928.0, "step": 45675 }, { "epoch": 0.4873417046291061, "grad_norm": 1.4736041230789156, "learning_rate": 3.0295707952300363e-05, "loss": 0.4621, "num_tokens": 273473033.0, "step": 45680 }, { "epoch": 0.48739504763530456, "grad_norm": 0.8260974329866783, "learning_rate": 3.029176960425855e-05, "loss": 0.5349, "num_tokens": 273505235.0, "step": 45685 }, { "epoch": 0.48744839064150297, "grad_norm": 1.1658076824167458, "learning_rate": 3.028783116934261e-05, "loss": 0.6267, "num_tokens": 273548144.0, "step": 45690 }, { "epoch": 0.48750173364770144, "grad_norm": 0.8468359949663786, "learning_rate": 3.0283892647675095e-05, "loss": 0.4396, "num_tokens": 273589003.0, "step": 45695 }, { "epoch": 0.4875550766538999, "grad_norm": 1.1295090620447665, "learning_rate": 3.0279954039378554e-05, "loss": 0.4762, "num_tokens": 273626807.0, "step": 45700 }, { "epoch": 0.4876084196600984, "grad_norm": 1.1720935428313635, "learning_rate": 3.0276015344575558e-05, "loss": 0.5145, "num_tokens": 273661273.0, "step": 45705 }, { "epoch": 0.4876617626662968, "grad_norm": 0.8861266891399968, "learning_rate": 3.0272076563388656e-05, "loss": 0.4802, "num_tokens": 273689219.0, "step": 45710 }, { "epoch": 0.48771510567249526, "grad_norm": 1.522728667821354, "learning_rate": 3.026813769594044e-05, "loss": 0.5109, "num_tokens": 273728581.0, "step": 45715 }, { "epoch": 0.48776844867869373, "grad_norm": 1.733268292196344, "learning_rate": 3.0264198742353456e-05, "loss": 0.6151, "num_tokens": 273755466.0, "step": 45720 }, { "epoch": 0.4878217916848922, "grad_norm": 1.2901613724243044, "learning_rate": 3.0260259702750287e-05, "loss": 0.6038, "num_tokens": 273789741.0, "step": 45725 }, { "epoch": 0.4878751346910907, "grad_norm": 0.8204504549845327, "learning_rate": 3.0256320577253504e-05, "loss": 0.5148, "num_tokens": 273816024.0, "step": 45730 }, { "epoch": 0.4879284776972891, "grad_norm": 0.6816111015311606, "learning_rate": 3.0252381365985687e-05, "loss": 0.4666, "num_tokens": 273842950.0, "step": 45735 }, { "epoch": 0.48798182070348756, "grad_norm": 0.7630416075700516, "learning_rate": 3.0248442069069423e-05, "loss": 0.5501, "num_tokens": 273883392.0, "step": 45740 }, { "epoch": 0.488035163709686, "grad_norm": 1.7910132582551297, "learning_rate": 3.0244502686627272e-05, "loss": 0.6488, "num_tokens": 273913166.0, "step": 45745 }, { "epoch": 0.4880885067158845, "grad_norm": 0.8087046729252875, "learning_rate": 3.0240563218781853e-05, "loss": 0.6644, "num_tokens": 273936578.0, "step": 45750 }, { "epoch": 0.4881418497220829, "grad_norm": 1.1048129111202776, "learning_rate": 3.0236623665655716e-05, "loss": 0.5921, "num_tokens": 273963275.0, "step": 45755 }, { "epoch": 0.4881951927282814, "grad_norm": 2.8581588884693168, "learning_rate": 3.023268402737149e-05, "loss": 0.5929, "num_tokens": 273982161.0, "step": 45760 }, { "epoch": 0.48824853573447985, "grad_norm": 0.7864296237312363, "learning_rate": 3.0228744304051737e-05, "loss": 0.556, "num_tokens": 274023148.0, "step": 45765 }, { "epoch": 0.4883018787406783, "grad_norm": 0.7054611280242121, "learning_rate": 3.0224804495819077e-05, "loss": 0.4752, "num_tokens": 274055512.0, "step": 45770 }, { "epoch": 0.4883552217468768, "grad_norm": 0.8674551360484557, "learning_rate": 3.0220864602796095e-05, "loss": 0.4057, "num_tokens": 274075453.0, "step": 45775 }, { "epoch": 0.4884085647530752, "grad_norm": 1.2191885032579504, "learning_rate": 3.0216924625105393e-05, "loss": 0.4999, "num_tokens": 274108554.0, "step": 45780 }, { "epoch": 0.4884619077592737, "grad_norm": 1.291387011629305, "learning_rate": 3.021298456286957e-05, "loss": 0.5944, "num_tokens": 274129850.0, "step": 45785 }, { "epoch": 0.48851525076547214, "grad_norm": 1.0409228733216076, "learning_rate": 3.020904441621125e-05, "loss": 0.5356, "num_tokens": 274171981.0, "step": 45790 }, { "epoch": 0.4885685937716706, "grad_norm": 1.1747203033641918, "learning_rate": 3.0205104185253032e-05, "loss": 0.6952, "num_tokens": 274208115.0, "step": 45795 }, { "epoch": 0.488621936777869, "grad_norm": 0.5652267822226945, "learning_rate": 3.0201163870117523e-05, "loss": 0.5326, "num_tokens": 274251742.0, "step": 45800 }, { "epoch": 0.4886752797840675, "grad_norm": 0.9947841205090111, "learning_rate": 3.019722347092735e-05, "loss": 0.4426, "num_tokens": 274288802.0, "step": 45805 }, { "epoch": 0.48872862279026597, "grad_norm": 1.134237041782338, "learning_rate": 3.0193282987805115e-05, "loss": 0.5982, "num_tokens": 274313235.0, "step": 45810 }, { "epoch": 0.48878196579646443, "grad_norm": 1.0633540199762497, "learning_rate": 3.0189342420873447e-05, "loss": 0.4313, "num_tokens": 274337021.0, "step": 45815 }, { "epoch": 0.4888353088026629, "grad_norm": 1.398888518787809, "learning_rate": 3.0185401770254974e-05, "loss": 0.5914, "num_tokens": 274379493.0, "step": 45820 }, { "epoch": 0.4888886518088613, "grad_norm": 1.3112744640892475, "learning_rate": 3.0181461036072306e-05, "loss": 0.5225, "num_tokens": 274408604.0, "step": 45825 }, { "epoch": 0.4889419948150598, "grad_norm": 1.2450215564558387, "learning_rate": 3.0177520218448074e-05, "loss": 0.5918, "num_tokens": 274429144.0, "step": 45830 }, { "epoch": 0.48899533782125826, "grad_norm": 1.3275874376149932, "learning_rate": 3.0173579317504924e-05, "loss": 0.419, "num_tokens": 274441216.0, "step": 45835 }, { "epoch": 0.4890486808274567, "grad_norm": 0.9020040441628232, "learning_rate": 3.0169638333365474e-05, "loss": 0.6808, "num_tokens": 274477598.0, "step": 45840 }, { "epoch": 0.48910202383365514, "grad_norm": 1.0507331370510369, "learning_rate": 3.0165697266152358e-05, "loss": 0.4453, "num_tokens": 274501909.0, "step": 45845 }, { "epoch": 0.4891553668398536, "grad_norm": 0.9908115373244499, "learning_rate": 3.0161756115988226e-05, "loss": 0.7083, "num_tokens": 274526843.0, "step": 45850 }, { "epoch": 0.4892087098460521, "grad_norm": 0.6435693312878189, "learning_rate": 3.0157814882995706e-05, "loss": 0.4283, "num_tokens": 274556286.0, "step": 45855 }, { "epoch": 0.48926205285225055, "grad_norm": 0.6738711217196603, "learning_rate": 3.0153873567297446e-05, "loss": 0.6006, "num_tokens": 274592309.0, "step": 45860 }, { "epoch": 0.489315395858449, "grad_norm": 0.9683949037686728, "learning_rate": 3.01499321690161e-05, "loss": 0.4471, "num_tokens": 274608569.0, "step": 45865 }, { "epoch": 0.48936873886464743, "grad_norm": 0.6494395168990336, "learning_rate": 3.01459906882743e-05, "loss": 0.4158, "num_tokens": 274629529.0, "step": 45870 }, { "epoch": 0.4894220818708459, "grad_norm": 1.1488178526259019, "learning_rate": 3.01420491251947e-05, "loss": 0.5356, "num_tokens": 274669707.0, "step": 45875 }, { "epoch": 0.4894754248770444, "grad_norm": 0.6955048078361763, "learning_rate": 3.0138107479899975e-05, "loss": 0.5688, "num_tokens": 274700560.0, "step": 45880 }, { "epoch": 0.48952876788324284, "grad_norm": 0.7675620030442026, "learning_rate": 3.013416575251275e-05, "loss": 0.4275, "num_tokens": 274727121.0, "step": 45885 }, { "epoch": 0.48958211088944126, "grad_norm": 0.908924503707908, "learning_rate": 3.0130223943155694e-05, "loss": 0.4797, "num_tokens": 274763006.0, "step": 45890 }, { "epoch": 0.4896354538956397, "grad_norm": 0.7201251976790416, "learning_rate": 3.012628205195149e-05, "loss": 0.559, "num_tokens": 274793424.0, "step": 45895 }, { "epoch": 0.4896887969018382, "grad_norm": 0.983158533761611, "learning_rate": 3.012234007902277e-05, "loss": 0.6027, "num_tokens": 274830332.0, "step": 45900 }, { "epoch": 0.48974213990803667, "grad_norm": 1.0082572133070922, "learning_rate": 3.0118398024492206e-05, "loss": 0.6616, "num_tokens": 274866591.0, "step": 45905 }, { "epoch": 0.48979548291423514, "grad_norm": 0.8562791443691979, "learning_rate": 3.0114455888482486e-05, "loss": 0.6109, "num_tokens": 274887448.0, "step": 45910 }, { "epoch": 0.48984882592043355, "grad_norm": 0.8731718819394256, "learning_rate": 3.011051367111627e-05, "loss": 0.472, "num_tokens": 274916292.0, "step": 45915 }, { "epoch": 0.489902168926632, "grad_norm": 1.164556356722587, "learning_rate": 3.0106571372516225e-05, "loss": 0.6475, "num_tokens": 274931454.0, "step": 45920 }, { "epoch": 0.4899555119328305, "grad_norm": 1.379163639945479, "learning_rate": 3.0102628992805033e-05, "loss": 0.5191, "num_tokens": 274965818.0, "step": 45925 }, { "epoch": 0.49000885493902896, "grad_norm": 0.9861419150214293, "learning_rate": 3.0098686532105368e-05, "loss": 0.5414, "num_tokens": 274992362.0, "step": 45930 }, { "epoch": 0.4900621979452274, "grad_norm": 3.449189275442883, "learning_rate": 3.0094743990539925e-05, "loss": 0.6803, "num_tokens": 275025069.0, "step": 45935 }, { "epoch": 0.49011554095142584, "grad_norm": 1.165610201928875, "learning_rate": 3.0090801368231375e-05, "loss": 0.5128, "num_tokens": 275050263.0, "step": 45940 }, { "epoch": 0.4901688839576243, "grad_norm": 1.1183032001197086, "learning_rate": 3.0086858665302415e-05, "loss": 0.5914, "num_tokens": 275071457.0, "step": 45945 }, { "epoch": 0.4902222269638228, "grad_norm": 0.7630455481978792, "learning_rate": 3.0082915881875716e-05, "loss": 0.5599, "num_tokens": 275106793.0, "step": 45950 }, { "epoch": 0.49027556997002125, "grad_norm": 1.5357565079393714, "learning_rate": 3.0078973018073986e-05, "loss": 0.6139, "num_tokens": 275137110.0, "step": 45955 }, { "epoch": 0.49032891297621967, "grad_norm": 1.0175613033042556, "learning_rate": 3.007503007401991e-05, "loss": 0.3589, "num_tokens": 275155647.0, "step": 45960 }, { "epoch": 0.49038225598241814, "grad_norm": 0.7156263197920288, "learning_rate": 3.0071087049836188e-05, "loss": 0.5374, "num_tokens": 275192164.0, "step": 45965 }, { "epoch": 0.4904355989886166, "grad_norm": 2.005294128120576, "learning_rate": 3.0067143945645526e-05, "loss": 0.5442, "num_tokens": 275205036.0, "step": 45970 }, { "epoch": 0.4904889419948151, "grad_norm": 0.5619494803961412, "learning_rate": 3.006320076157061e-05, "loss": 0.6383, "num_tokens": 275258125.0, "step": 45975 }, { "epoch": 0.4905422850010135, "grad_norm": 1.6093409468953985, "learning_rate": 3.0059257497734145e-05, "loss": 0.5374, "num_tokens": 275283868.0, "step": 45980 }, { "epoch": 0.49059562800721196, "grad_norm": 0.7769042101654887, "learning_rate": 3.005531415425885e-05, "loss": 0.6393, "num_tokens": 275318382.0, "step": 45985 }, { "epoch": 0.49064897101341043, "grad_norm": 1.389223871212106, "learning_rate": 3.0051370731267436e-05, "loss": 0.5362, "num_tokens": 275339639.0, "step": 45990 }, { "epoch": 0.4907023140196089, "grad_norm": 1.069272269665264, "learning_rate": 3.004742722888259e-05, "loss": 0.5287, "num_tokens": 275364430.0, "step": 45995 }, { "epoch": 0.49075565702580737, "grad_norm": 0.6575124053692004, "learning_rate": 3.0043483647227048e-05, "loss": 0.5189, "num_tokens": 275403416.0, "step": 46000 }, { "epoch": 0.4908090000320058, "grad_norm": 2.5828581720888377, "learning_rate": 3.0039539986423528e-05, "loss": 0.5403, "num_tokens": 275426942.0, "step": 46005 }, { "epoch": 0.49086234303820425, "grad_norm": 1.0127500060911239, "learning_rate": 3.0035596246594727e-05, "loss": 0.3518, "num_tokens": 275456100.0, "step": 46010 }, { "epoch": 0.4909156860444027, "grad_norm": 0.8648390058882094, "learning_rate": 3.0031652427863384e-05, "loss": 0.4571, "num_tokens": 275489398.0, "step": 46015 }, { "epoch": 0.4909690290506012, "grad_norm": 1.4176533672944418, "learning_rate": 3.0027708530352217e-05, "loss": 0.5249, "num_tokens": 275514371.0, "step": 46020 }, { "epoch": 0.4910223720567996, "grad_norm": 1.168075761085914, "learning_rate": 3.0023764554183957e-05, "loss": 0.5607, "num_tokens": 275540139.0, "step": 46025 }, { "epoch": 0.4910757150629981, "grad_norm": 0.8286010163837609, "learning_rate": 3.0019820499481327e-05, "loss": 0.534, "num_tokens": 275578900.0, "step": 46030 }, { "epoch": 0.49112905806919654, "grad_norm": 1.2110369361897264, "learning_rate": 3.001587636636705e-05, "loss": 0.4194, "num_tokens": 275602628.0, "step": 46035 }, { "epoch": 0.491182401075395, "grad_norm": 1.0200388306124588, "learning_rate": 3.001193215496388e-05, "loss": 0.6236, "num_tokens": 275627430.0, "step": 46040 }, { "epoch": 0.4912357440815935, "grad_norm": 1.6378497139502188, "learning_rate": 3.0007987865394534e-05, "loss": 0.6152, "num_tokens": 275658523.0, "step": 46045 }, { "epoch": 0.4912890870877919, "grad_norm": 1.0286842339065572, "learning_rate": 3.0004043497781755e-05, "loss": 0.6396, "num_tokens": 275679083.0, "step": 46050 }, { "epoch": 0.49134243009399037, "grad_norm": 0.8398559952567469, "learning_rate": 3.0000099052248287e-05, "loss": 0.6656, "num_tokens": 275706072.0, "step": 46055 }, { "epoch": 0.49139577310018884, "grad_norm": 0.7661966304186753, "learning_rate": 2.999615452891688e-05, "loss": 0.5141, "num_tokens": 275743792.0, "step": 46060 }, { "epoch": 0.4914491161063873, "grad_norm": 0.7722362927736645, "learning_rate": 2.9992209927910264e-05, "loss": 0.6542, "num_tokens": 275784429.0, "step": 46065 }, { "epoch": 0.4915024591125857, "grad_norm": 1.6545228827571086, "learning_rate": 2.9988265249351195e-05, "loss": 0.7376, "num_tokens": 275801169.0, "step": 46070 }, { "epoch": 0.4915558021187842, "grad_norm": 1.6083800841276248, "learning_rate": 2.9984320493362422e-05, "loss": 0.5499, "num_tokens": 275820301.0, "step": 46075 }, { "epoch": 0.49160914512498266, "grad_norm": 0.8576905370165635, "learning_rate": 2.9980375660066708e-05, "loss": 0.7141, "num_tokens": 275852045.0, "step": 46080 }, { "epoch": 0.49166248813118113, "grad_norm": 1.1848022064127477, "learning_rate": 2.9976430749586782e-05, "loss": 0.5374, "num_tokens": 275883069.0, "step": 46085 }, { "epoch": 0.4917158311373796, "grad_norm": 0.9238496444907913, "learning_rate": 2.9972485762045426e-05, "loss": 0.6428, "num_tokens": 275921320.0, "step": 46090 }, { "epoch": 0.491769174143578, "grad_norm": 0.9239504790917876, "learning_rate": 2.996854069756539e-05, "loss": 0.6181, "num_tokens": 275967439.0, "step": 46095 }, { "epoch": 0.4918225171497765, "grad_norm": 1.8950201334461898, "learning_rate": 2.996459555626944e-05, "loss": 0.481, "num_tokens": 275996793.0, "step": 46100 }, { "epoch": 0.49187586015597495, "grad_norm": 0.6647422984271699, "learning_rate": 2.9960650338280337e-05, "loss": 0.4854, "num_tokens": 276026212.0, "step": 46105 }, { "epoch": 0.4919292031621734, "grad_norm": 0.9117503393555279, "learning_rate": 2.9956705043720857e-05, "loss": 0.8027, "num_tokens": 276038466.0, "step": 46110 }, { "epoch": 0.49198254616837184, "grad_norm": 0.7718666545338442, "learning_rate": 2.9952759672713753e-05, "loss": 0.512, "num_tokens": 276067847.0, "step": 46115 }, { "epoch": 0.4920358891745703, "grad_norm": 6.280898691154109, "learning_rate": 2.994881422538181e-05, "loss": 0.6645, "num_tokens": 276090306.0, "step": 46120 }, { "epoch": 0.4920892321807688, "grad_norm": 1.323931643360214, "learning_rate": 2.9944868701847795e-05, "loss": 0.5427, "num_tokens": 276119562.0, "step": 46125 }, { "epoch": 0.49214257518696725, "grad_norm": 1.5495487540728987, "learning_rate": 2.9940923102234488e-05, "loss": 0.5415, "num_tokens": 276145425.0, "step": 46130 }, { "epoch": 0.4921959181931657, "grad_norm": 1.0001554667816634, "learning_rate": 2.9936977426664677e-05, "loss": 0.5427, "num_tokens": 276177542.0, "step": 46135 }, { "epoch": 0.49224926119936413, "grad_norm": 1.5196363952977936, "learning_rate": 2.993303167526113e-05, "loss": 0.4335, "num_tokens": 276196071.0, "step": 46140 }, { "epoch": 0.4923026042055626, "grad_norm": 0.9205885705186291, "learning_rate": 2.9929085848146626e-05, "loss": 0.5056, "num_tokens": 276219125.0, "step": 46145 }, { "epoch": 0.49235594721176107, "grad_norm": 0.5625772544034805, "learning_rate": 2.9925139945443965e-05, "loss": 0.4504, "num_tokens": 276263033.0, "step": 46150 }, { "epoch": 0.49240929021795954, "grad_norm": 1.161211681736253, "learning_rate": 2.9921193967275933e-05, "loss": 0.4686, "num_tokens": 276281429.0, "step": 46155 }, { "epoch": 0.49246263322415795, "grad_norm": 0.8140724889322979, "learning_rate": 2.9917247913765317e-05, "loss": 0.4348, "num_tokens": 276301663.0, "step": 46160 }, { "epoch": 0.4925159762303564, "grad_norm": 0.8767488878974844, "learning_rate": 2.991330178503491e-05, "loss": 0.5116, "num_tokens": 276328267.0, "step": 46165 }, { "epoch": 0.4925693192365549, "grad_norm": 1.0733894079992476, "learning_rate": 2.990935558120751e-05, "loss": 0.4151, "num_tokens": 276361676.0, "step": 46170 }, { "epoch": 0.49262266224275336, "grad_norm": 1.4238184377849648, "learning_rate": 2.990540930240591e-05, "loss": 0.4891, "num_tokens": 276392138.0, "step": 46175 }, { "epoch": 0.49267600524895183, "grad_norm": 1.0373504966333673, "learning_rate": 2.9901462948752918e-05, "loss": 0.481, "num_tokens": 276412137.0, "step": 46180 }, { "epoch": 0.49272934825515025, "grad_norm": 0.6545138093720121, "learning_rate": 2.9897516520371327e-05, "loss": 0.4568, "num_tokens": 276433132.0, "step": 46185 }, { "epoch": 0.4927826912613487, "grad_norm": 1.0539591078644324, "learning_rate": 2.9893570017383948e-05, "loss": 0.5208, "num_tokens": 276465935.0, "step": 46190 }, { "epoch": 0.4928360342675472, "grad_norm": 0.91691859150889, "learning_rate": 2.988962343991359e-05, "loss": 0.5187, "num_tokens": 276495154.0, "step": 46195 }, { "epoch": 0.49288937727374565, "grad_norm": 0.7755756319658608, "learning_rate": 2.988567678808305e-05, "loss": 0.407, "num_tokens": 276524374.0, "step": 46200 }, { "epoch": 0.49294272027994407, "grad_norm": 0.8371990394622519, "learning_rate": 2.9881730062015166e-05, "loss": 0.5163, "num_tokens": 276547708.0, "step": 46205 }, { "epoch": 0.49299606328614254, "grad_norm": 0.8862566022161645, "learning_rate": 2.987778326183272e-05, "loss": 0.5888, "num_tokens": 276569549.0, "step": 46210 }, { "epoch": 0.493049406292341, "grad_norm": 1.237730414706843, "learning_rate": 2.9873836387658544e-05, "loss": 0.4782, "num_tokens": 276589208.0, "step": 46215 }, { "epoch": 0.4931027492985395, "grad_norm": 1.2099284452930203, "learning_rate": 2.9869889439615456e-05, "loss": 0.5544, "num_tokens": 276617051.0, "step": 46220 }, { "epoch": 0.49315609230473795, "grad_norm": 1.332288811576378, "learning_rate": 2.9865942417826286e-05, "loss": 0.456, "num_tokens": 276647797.0, "step": 46225 }, { "epoch": 0.49320943531093636, "grad_norm": 1.7537554227431837, "learning_rate": 2.9861995322413834e-05, "loss": 0.5683, "num_tokens": 276682976.0, "step": 46230 }, { "epoch": 0.49326277831713483, "grad_norm": 1.1995689397055345, "learning_rate": 2.985804815350095e-05, "loss": 0.6526, "num_tokens": 276706173.0, "step": 46235 }, { "epoch": 0.4933161213233333, "grad_norm": 1.1060643562739854, "learning_rate": 2.985410091121044e-05, "loss": 0.4776, "num_tokens": 276721551.0, "step": 46240 }, { "epoch": 0.49336946432953177, "grad_norm": 1.387927125182362, "learning_rate": 2.985015359566516e-05, "loss": 0.4896, "num_tokens": 276739349.0, "step": 46245 }, { "epoch": 0.4934228073357302, "grad_norm": 1.5033331416908218, "learning_rate": 2.984620620698792e-05, "loss": 0.5321, "num_tokens": 276764286.0, "step": 46250 }, { "epoch": 0.49347615034192865, "grad_norm": 1.1078589378386112, "learning_rate": 2.984225874530156e-05, "loss": 0.6315, "num_tokens": 276803077.0, "step": 46255 }, { "epoch": 0.4935294933481271, "grad_norm": 1.249124477829337, "learning_rate": 2.9838311210728924e-05, "loss": 0.5747, "num_tokens": 276834168.0, "step": 46260 }, { "epoch": 0.4935828363543256, "grad_norm": 0.8083751689263923, "learning_rate": 2.983436360339284e-05, "loss": 0.5686, "num_tokens": 276859676.0, "step": 46265 }, { "epoch": 0.49363617936052406, "grad_norm": 0.8372965606962065, "learning_rate": 2.9830415923416162e-05, "loss": 0.3828, "num_tokens": 276879668.0, "step": 46270 }, { "epoch": 0.4936895223667225, "grad_norm": 0.8411863007325973, "learning_rate": 2.9826468170921717e-05, "loss": 0.472, "num_tokens": 276894477.0, "step": 46275 }, { "epoch": 0.49374286537292095, "grad_norm": 0.7995749581294185, "learning_rate": 2.9822520346032372e-05, "loss": 0.5295, "num_tokens": 276925105.0, "step": 46280 }, { "epoch": 0.4937962083791194, "grad_norm": 0.9316837561780705, "learning_rate": 2.9818572448870964e-05, "loss": 0.4532, "num_tokens": 276948503.0, "step": 46285 }, { "epoch": 0.4938495513853179, "grad_norm": 0.7560622732299452, "learning_rate": 2.9814624479560334e-05, "loss": 0.5016, "num_tokens": 276985516.0, "step": 46290 }, { "epoch": 0.4939028943915163, "grad_norm": 1.2740096380121342, "learning_rate": 2.981067643822335e-05, "loss": 0.5546, "num_tokens": 277018892.0, "step": 46295 }, { "epoch": 0.49395623739771477, "grad_norm": 0.5621734351081141, "learning_rate": 2.980672832498287e-05, "loss": 0.4356, "num_tokens": 277045912.0, "step": 46300 }, { "epoch": 0.49400958040391324, "grad_norm": 1.2219822775630063, "learning_rate": 2.980278013996173e-05, "loss": 0.4845, "num_tokens": 277084645.0, "step": 46305 }, { "epoch": 0.4940629234101117, "grad_norm": 0.7655581170490621, "learning_rate": 2.9798831883282808e-05, "loss": 0.5367, "num_tokens": 277113441.0, "step": 46310 }, { "epoch": 0.4941162664163102, "grad_norm": 0.7158105970422444, "learning_rate": 2.979488355506896e-05, "loss": 0.5506, "num_tokens": 277136189.0, "step": 46315 }, { "epoch": 0.4941696094225086, "grad_norm": 0.8654343341315793, "learning_rate": 2.9790935155443043e-05, "loss": 0.5535, "num_tokens": 277166569.0, "step": 46320 }, { "epoch": 0.49422295242870706, "grad_norm": 0.789134321623998, "learning_rate": 2.9786986684527934e-05, "loss": 0.4894, "num_tokens": 277197059.0, "step": 46325 }, { "epoch": 0.49427629543490553, "grad_norm": 0.78056102494525, "learning_rate": 2.97830381424465e-05, "loss": 0.5469, "num_tokens": 277238293.0, "step": 46330 }, { "epoch": 0.494329638441104, "grad_norm": 0.7874962489844379, "learning_rate": 2.9779089529321613e-05, "loss": 0.5999, "num_tokens": 277270567.0, "step": 46335 }, { "epoch": 0.4943829814473024, "grad_norm": 0.6119572027989489, "learning_rate": 2.9775140845276128e-05, "loss": 0.5268, "num_tokens": 277299957.0, "step": 46340 }, { "epoch": 0.4944363244535009, "grad_norm": 0.8753281437224926, "learning_rate": 2.9771192090432943e-05, "loss": 0.5082, "num_tokens": 277324224.0, "step": 46345 }, { "epoch": 0.49448966745969936, "grad_norm": 1.093667107070581, "learning_rate": 2.9767243264914924e-05, "loss": 0.4135, "num_tokens": 277342242.0, "step": 46350 }, { "epoch": 0.4945430104658978, "grad_norm": 0.7897769177791092, "learning_rate": 2.9763294368844953e-05, "loss": 0.4889, "num_tokens": 277376621.0, "step": 46355 }, { "epoch": 0.4945963534720963, "grad_norm": 0.6170257427507507, "learning_rate": 2.97593454023459e-05, "loss": 0.4919, "num_tokens": 277415215.0, "step": 46360 }, { "epoch": 0.4946496964782947, "grad_norm": 0.7122186216666041, "learning_rate": 2.9755396365540665e-05, "loss": 0.5054, "num_tokens": 277458598.0, "step": 46365 }, { "epoch": 0.4947030394844932, "grad_norm": 0.621740454855991, "learning_rate": 2.9751447258552135e-05, "loss": 0.5097, "num_tokens": 277496426.0, "step": 46370 }, { "epoch": 0.49475638249069165, "grad_norm": 1.4306998193373508, "learning_rate": 2.9747498081503188e-05, "loss": 0.7625, "num_tokens": 277529041.0, "step": 46375 }, { "epoch": 0.4948097254968901, "grad_norm": 1.2213461707469877, "learning_rate": 2.9743548834516706e-05, "loss": 0.6484, "num_tokens": 277568615.0, "step": 46380 }, { "epoch": 0.49486306850308853, "grad_norm": 0.7734692775767461, "learning_rate": 2.97395995177156e-05, "loss": 0.5805, "num_tokens": 277609648.0, "step": 46385 }, { "epoch": 0.494916411509287, "grad_norm": 1.1329107934472926, "learning_rate": 2.9735650131222765e-05, "loss": 0.4441, "num_tokens": 277635335.0, "step": 46390 }, { "epoch": 0.49496975451548547, "grad_norm": 0.7484801493129907, "learning_rate": 2.9731700675161077e-05, "loss": 0.4937, "num_tokens": 277654849.0, "step": 46395 }, { "epoch": 0.49502309752168394, "grad_norm": 0.8365560494511557, "learning_rate": 2.9727751149653455e-05, "loss": 0.492, "num_tokens": 277687831.0, "step": 46400 }, { "epoch": 0.4950764405278824, "grad_norm": 0.8055668860617587, "learning_rate": 2.9723801554822794e-05, "loss": 0.5675, "num_tokens": 277713882.0, "step": 46405 }, { "epoch": 0.4951297835340808, "grad_norm": 1.4531174129635964, "learning_rate": 2.9719851890791993e-05, "loss": 0.6156, "num_tokens": 277740709.0, "step": 46410 }, { "epoch": 0.4951831265402793, "grad_norm": 0.9771280707519261, "learning_rate": 2.9715902157683962e-05, "loss": 0.4545, "num_tokens": 277761282.0, "step": 46415 }, { "epoch": 0.49523646954647776, "grad_norm": 0.7499259527524954, "learning_rate": 2.9711952355621607e-05, "loss": 0.4984, "num_tokens": 277793989.0, "step": 46420 }, { "epoch": 0.49528981255267623, "grad_norm": 0.871240016929416, "learning_rate": 2.970800248472784e-05, "loss": 0.5315, "num_tokens": 277814758.0, "step": 46425 }, { "epoch": 0.49534315555887465, "grad_norm": 0.5524738287161908, "learning_rate": 2.970405254512557e-05, "loss": 0.6925, "num_tokens": 277865112.0, "step": 46430 }, { "epoch": 0.4953964985650731, "grad_norm": 1.196528908549168, "learning_rate": 2.970010253693771e-05, "loss": 0.5126, "num_tokens": 277887735.0, "step": 46435 }, { "epoch": 0.4954498415712716, "grad_norm": 1.457625919632966, "learning_rate": 2.969615246028718e-05, "loss": 0.5415, "num_tokens": 277911355.0, "step": 46440 }, { "epoch": 0.49550318457747006, "grad_norm": 1.2049070076283819, "learning_rate": 2.96922023152969e-05, "loss": 0.5875, "num_tokens": 277940469.0, "step": 46445 }, { "epoch": 0.4955565275836685, "grad_norm": 0.9714059333589125, "learning_rate": 2.9688252102089785e-05, "loss": 0.5179, "num_tokens": 277980563.0, "step": 46450 }, { "epoch": 0.49560987058986694, "grad_norm": 1.122135766500195, "learning_rate": 2.9684301820788752e-05, "loss": 0.5685, "num_tokens": 278003929.0, "step": 46455 }, { "epoch": 0.4956632135960654, "grad_norm": 0.5602229349261071, "learning_rate": 2.9680351471516744e-05, "loss": 0.5069, "num_tokens": 278032644.0, "step": 46460 }, { "epoch": 0.4957165566022639, "grad_norm": 1.4182160451307781, "learning_rate": 2.9676401054396675e-05, "loss": 0.5534, "num_tokens": 278052784.0, "step": 46465 }, { "epoch": 0.49576989960846235, "grad_norm": 0.8595076475905655, "learning_rate": 2.967245056955147e-05, "loss": 0.5912, "num_tokens": 278083361.0, "step": 46470 }, { "epoch": 0.49582324261466076, "grad_norm": 0.9036685071767095, "learning_rate": 2.966850001710406e-05, "loss": 0.6534, "num_tokens": 278102832.0, "step": 46475 }, { "epoch": 0.49587658562085923, "grad_norm": 0.7976771178066194, "learning_rate": 2.96645493971774e-05, "loss": 0.4998, "num_tokens": 278124306.0, "step": 46480 }, { "epoch": 0.4959299286270577, "grad_norm": 0.7914739396475334, "learning_rate": 2.9660598709894393e-05, "loss": 0.5183, "num_tokens": 278164998.0, "step": 46485 }, { "epoch": 0.4959832716332562, "grad_norm": 1.6122228482209866, "learning_rate": 2.9656647955378004e-05, "loss": 0.5269, "num_tokens": 278182047.0, "step": 46490 }, { "epoch": 0.49603661463945464, "grad_norm": 1.274729055086402, "learning_rate": 2.9652697133751158e-05, "loss": 0.5212, "num_tokens": 278220573.0, "step": 46495 }, { "epoch": 0.49608995764565306, "grad_norm": 1.1528199244729551, "learning_rate": 2.96487462451368e-05, "loss": 0.6623, "num_tokens": 278256164.0, "step": 46500 }, { "epoch": 0.4961433006518515, "grad_norm": 1.451740120356067, "learning_rate": 2.964479528965787e-05, "loss": 0.5498, "num_tokens": 278276661.0, "step": 46505 }, { "epoch": 0.49619664365805, "grad_norm": 0.872639878159077, "learning_rate": 2.9640844267437314e-05, "loss": 0.5759, "num_tokens": 278304660.0, "step": 46510 }, { "epoch": 0.49624998666424847, "grad_norm": 0.9860927201327262, "learning_rate": 2.9636893178598084e-05, "loss": 0.5409, "num_tokens": 278339854.0, "step": 46515 }, { "epoch": 0.4963033296704469, "grad_norm": 1.730813522223455, "learning_rate": 2.9632942023263127e-05, "loss": 0.5055, "num_tokens": 278370124.0, "step": 46520 }, { "epoch": 0.49635667267664535, "grad_norm": 0.9208364495759377, "learning_rate": 2.9628990801555396e-05, "loss": 0.3857, "num_tokens": 278398824.0, "step": 46525 }, { "epoch": 0.4964100156828438, "grad_norm": 1.072443341366839, "learning_rate": 2.962503951359784e-05, "loss": 0.5295, "num_tokens": 278437365.0, "step": 46530 }, { "epoch": 0.4964633586890423, "grad_norm": 0.5974546452034856, "learning_rate": 2.9621088159513428e-05, "loss": 0.5354, "num_tokens": 278465152.0, "step": 46535 }, { "epoch": 0.49651670169524076, "grad_norm": 0.8537000152657372, "learning_rate": 2.9617136739425106e-05, "loss": 0.4849, "num_tokens": 278505327.0, "step": 46540 }, { "epoch": 0.4965700447014392, "grad_norm": 0.9806618778516718, "learning_rate": 2.9613185253455834e-05, "loss": 0.4576, "num_tokens": 278519351.0, "step": 46545 }, { "epoch": 0.49662338770763764, "grad_norm": 1.153313917304888, "learning_rate": 2.9609233701728577e-05, "loss": 0.5221, "num_tokens": 278546090.0, "step": 46550 }, { "epoch": 0.4966767307138361, "grad_norm": 1.7290184678751483, "learning_rate": 2.9605282084366308e-05, "loss": 0.5884, "num_tokens": 278581750.0, "step": 46555 }, { "epoch": 0.4967300737200346, "grad_norm": 1.1365233184161676, "learning_rate": 2.9601330401491973e-05, "loss": 0.6506, "num_tokens": 278609285.0, "step": 46560 }, { "epoch": 0.496783416726233, "grad_norm": 1.0635652038607861, "learning_rate": 2.959737865322856e-05, "loss": 0.3932, "num_tokens": 278638865.0, "step": 46565 }, { "epoch": 0.49683675973243147, "grad_norm": 1.2574417555703752, "learning_rate": 2.959342683969903e-05, "loss": 0.4797, "num_tokens": 278665488.0, "step": 46570 }, { "epoch": 0.49689010273862994, "grad_norm": 0.8736780509479377, "learning_rate": 2.9589474961026357e-05, "loss": 0.5858, "num_tokens": 278694383.0, "step": 46575 }, { "epoch": 0.4969434457448284, "grad_norm": 1.1989397456913573, "learning_rate": 2.9585523017333516e-05, "loss": 0.4006, "num_tokens": 278714294.0, "step": 46580 }, { "epoch": 0.4969967887510269, "grad_norm": 0.9366398393190215, "learning_rate": 2.958157100874348e-05, "loss": 0.4669, "num_tokens": 278740027.0, "step": 46585 }, { "epoch": 0.4970501317572253, "grad_norm": 0.974804376222759, "learning_rate": 2.957761893537923e-05, "loss": 0.6103, "num_tokens": 278764633.0, "step": 46590 }, { "epoch": 0.49710347476342376, "grad_norm": 1.2548935431655124, "learning_rate": 2.9573666797363746e-05, "loss": 0.6038, "num_tokens": 278791035.0, "step": 46595 }, { "epoch": 0.49715681776962223, "grad_norm": 1.1429830444514584, "learning_rate": 2.9569714594820014e-05, "loss": 0.5063, "num_tokens": 278811415.0, "step": 46600 }, { "epoch": 0.4972101607758207, "grad_norm": 0.8499706016747617, "learning_rate": 2.956576232787101e-05, "loss": 0.6345, "num_tokens": 278850602.0, "step": 46605 }, { "epoch": 0.4972635037820191, "grad_norm": 1.0425624034981507, "learning_rate": 2.956180999663974e-05, "loss": 0.5751, "num_tokens": 278888604.0, "step": 46610 }, { "epoch": 0.4973168467882176, "grad_norm": 1.2740039224513198, "learning_rate": 2.9557857601249163e-05, "loss": 0.5131, "num_tokens": 278909641.0, "step": 46615 }, { "epoch": 0.49737018979441605, "grad_norm": 0.8030094022679833, "learning_rate": 2.955390514182228e-05, "loss": 0.4848, "num_tokens": 278933721.0, "step": 46620 }, { "epoch": 0.4974235328006145, "grad_norm": 1.1421041104079557, "learning_rate": 2.9549952618482098e-05, "loss": 0.6003, "num_tokens": 278973048.0, "step": 46625 }, { "epoch": 0.497476875806813, "grad_norm": 0.6641489967668442, "learning_rate": 2.95460000313516e-05, "loss": 0.5082, "num_tokens": 279012838.0, "step": 46630 }, { "epoch": 0.4975302188130114, "grad_norm": 1.3186305057796253, "learning_rate": 2.9542047380553785e-05, "loss": 0.4776, "num_tokens": 279036926.0, "step": 46635 }, { "epoch": 0.4975835618192099, "grad_norm": 1.9350036035605538, "learning_rate": 2.9538094666211645e-05, "loss": 0.4731, "num_tokens": 279056689.0, "step": 46640 }, { "epoch": 0.49763690482540834, "grad_norm": 0.8086975695188516, "learning_rate": 2.953414188844819e-05, "loss": 0.4572, "num_tokens": 279089272.0, "step": 46645 }, { "epoch": 0.4976902478316068, "grad_norm": 1.4212136298859663, "learning_rate": 2.953018904738642e-05, "loss": 0.5548, "num_tokens": 279133963.0, "step": 46650 }, { "epoch": 0.4977435908378052, "grad_norm": 1.0430913151664356, "learning_rate": 2.9526236143149334e-05, "loss": 0.5182, "num_tokens": 279159911.0, "step": 46655 }, { "epoch": 0.4977969338440037, "grad_norm": 1.3412811291668145, "learning_rate": 2.9522283175859934e-05, "loss": 0.5282, "num_tokens": 279181933.0, "step": 46660 }, { "epoch": 0.49785027685020217, "grad_norm": 1.457533885238282, "learning_rate": 2.9518330145641244e-05, "loss": 0.5508, "num_tokens": 279203992.0, "step": 46665 }, { "epoch": 0.49790361985640064, "grad_norm": 0.9872591837730376, "learning_rate": 2.951437705261626e-05, "loss": 0.5144, "num_tokens": 279230372.0, "step": 46670 }, { "epoch": 0.4979569628625991, "grad_norm": 1.0715498046726388, "learning_rate": 2.9510423896908003e-05, "loss": 0.5433, "num_tokens": 279277084.0, "step": 46675 }, { "epoch": 0.4980103058687975, "grad_norm": 0.7838012406331109, "learning_rate": 2.9506470678639488e-05, "loss": 0.4348, "num_tokens": 279300886.0, "step": 46680 }, { "epoch": 0.498063648874996, "grad_norm": 0.8300439699312705, "learning_rate": 2.950251739793372e-05, "loss": 0.5759, "num_tokens": 279335582.0, "step": 46685 }, { "epoch": 0.49811699188119446, "grad_norm": 1.3246764501459225, "learning_rate": 2.9498564054913726e-05, "loss": 0.6523, "num_tokens": 279355438.0, "step": 46690 }, { "epoch": 0.49817033488739293, "grad_norm": 1.0491170343289156, "learning_rate": 2.949461064970252e-05, "loss": 0.4737, "num_tokens": 279376484.0, "step": 46695 }, { "epoch": 0.49822367789359134, "grad_norm": 0.7487485401551426, "learning_rate": 2.9490657182423142e-05, "loss": 0.4595, "num_tokens": 279404077.0, "step": 46700 }, { "epoch": 0.4982770208997898, "grad_norm": 1.7582745619678242, "learning_rate": 2.9486703653198583e-05, "loss": 0.5836, "num_tokens": 279430456.0, "step": 46705 }, { "epoch": 0.4983303639059883, "grad_norm": 0.7558961763556501, "learning_rate": 2.9482750062151898e-05, "loss": 0.4542, "num_tokens": 279451854.0, "step": 46710 }, { "epoch": 0.49838370691218675, "grad_norm": 1.1595393280557889, "learning_rate": 2.94787964094061e-05, "loss": 0.5478, "num_tokens": 279481548.0, "step": 46715 }, { "epoch": 0.4984370499183852, "grad_norm": 0.764193485624215, "learning_rate": 2.947484269508422e-05, "loss": 0.4417, "num_tokens": 279504484.0, "step": 46720 }, { "epoch": 0.49849039292458364, "grad_norm": 1.0402341740589507, "learning_rate": 2.9470888919309296e-05, "loss": 0.509, "num_tokens": 279544111.0, "step": 46725 }, { "epoch": 0.4985437359307821, "grad_norm": 2.459486854702245, "learning_rate": 2.946693508220436e-05, "loss": 0.6525, "num_tokens": 279569223.0, "step": 46730 }, { "epoch": 0.4985970789369806, "grad_norm": 0.8789155457809329, "learning_rate": 2.9462981183892442e-05, "loss": 0.4771, "num_tokens": 279600815.0, "step": 46735 }, { "epoch": 0.49865042194317905, "grad_norm": 1.0244543079276995, "learning_rate": 2.9459027224496576e-05, "loss": 0.6427, "num_tokens": 279634025.0, "step": 46740 }, { "epoch": 0.49870376494937746, "grad_norm": 1.3150766484785466, "learning_rate": 2.9455073204139817e-05, "loss": 0.6094, "num_tokens": 279658175.0, "step": 46745 }, { "epoch": 0.49875710795557593, "grad_norm": 1.7372907508163529, "learning_rate": 2.945111912294518e-05, "loss": 0.5737, "num_tokens": 279685852.0, "step": 46750 }, { "epoch": 0.4988104509617744, "grad_norm": 1.2385021307147697, "learning_rate": 2.944716498103574e-05, "loss": 0.4541, "num_tokens": 279725297.0, "step": 46755 }, { "epoch": 0.49886379396797287, "grad_norm": 0.8121871142731127, "learning_rate": 2.9443210778534525e-05, "loss": 0.4994, "num_tokens": 279768534.0, "step": 46760 }, { "epoch": 0.49891713697417134, "grad_norm": 1.1234055627073232, "learning_rate": 2.9439256515564568e-05, "loss": 0.6397, "num_tokens": 279794818.0, "step": 46765 }, { "epoch": 0.49897047998036975, "grad_norm": 0.5497822191113823, "learning_rate": 2.9435302192248938e-05, "loss": 0.4803, "num_tokens": 279823576.0, "step": 46770 }, { "epoch": 0.4990238229865682, "grad_norm": 1.541854227709336, "learning_rate": 2.9431347808710686e-05, "loss": 0.5703, "num_tokens": 279858847.0, "step": 46775 }, { "epoch": 0.4990771659927667, "grad_norm": 0.7475990103879554, "learning_rate": 2.9427393365072847e-05, "loss": 0.4916, "num_tokens": 279883968.0, "step": 46780 }, { "epoch": 0.49913050899896516, "grad_norm": 0.721326428853997, "learning_rate": 2.9423438861458495e-05, "loss": 0.5987, "num_tokens": 279915910.0, "step": 46785 }, { "epoch": 0.4991838520051636, "grad_norm": 0.8238082565526992, "learning_rate": 2.9419484297990668e-05, "loss": 0.4364, "num_tokens": 279952024.0, "step": 46790 }, { "epoch": 0.49923719501136204, "grad_norm": 1.2709694440487815, "learning_rate": 2.9415529674792442e-05, "loss": 0.4643, "num_tokens": 279971096.0, "step": 46795 }, { "epoch": 0.4992905380175605, "grad_norm": 0.8884479501439498, "learning_rate": 2.9411574991986858e-05, "loss": 0.6243, "num_tokens": 279994947.0, "step": 46800 }, { "epoch": 0.499343881023759, "grad_norm": 1.1562828460390568, "learning_rate": 2.940762024969699e-05, "loss": 0.5084, "num_tokens": 280032518.0, "step": 46805 }, { "epoch": 0.49939722402995745, "grad_norm": 1.2847686801062428, "learning_rate": 2.9403665448045896e-05, "loss": 0.5077, "num_tokens": 280054953.0, "step": 46810 }, { "epoch": 0.49945056703615587, "grad_norm": 0.7478469252470098, "learning_rate": 2.939971058715665e-05, "loss": 0.497, "num_tokens": 280089654.0, "step": 46815 }, { "epoch": 0.49950391004235434, "grad_norm": 1.2022396635946242, "learning_rate": 2.939575566715231e-05, "loss": 0.5774, "num_tokens": 280133463.0, "step": 46820 }, { "epoch": 0.4995572530485528, "grad_norm": 0.741925072565918, "learning_rate": 2.939180068815594e-05, "loss": 0.5492, "num_tokens": 280165339.0, "step": 46825 }, { "epoch": 0.4996105960547513, "grad_norm": 1.0945347241482146, "learning_rate": 2.938784565029063e-05, "loss": 0.6019, "num_tokens": 280209034.0, "step": 46830 }, { "epoch": 0.4996639390609497, "grad_norm": 0.5940919170184036, "learning_rate": 2.938389055367943e-05, "loss": 0.5769, "num_tokens": 280264937.0, "step": 46835 }, { "epoch": 0.49971728206714816, "grad_norm": 0.8853199119620992, "learning_rate": 2.9379935398445436e-05, "loss": 0.5094, "num_tokens": 280307255.0, "step": 46840 }, { "epoch": 0.49977062507334663, "grad_norm": 1.0429959008322265, "learning_rate": 2.9375980184711706e-05, "loss": 0.4907, "num_tokens": 280323009.0, "step": 46845 }, { "epoch": 0.4998239680795451, "grad_norm": 1.0116298020228927, "learning_rate": 2.9372024912601332e-05, "loss": 0.5831, "num_tokens": 280351343.0, "step": 46850 }, { "epoch": 0.49987731108574357, "grad_norm": 0.6285856909477279, "learning_rate": 2.9368069582237383e-05, "loss": 0.5716, "num_tokens": 280396471.0, "step": 46855 }, { "epoch": 0.499930654091942, "grad_norm": 1.174084880310114, "learning_rate": 2.9364114193742948e-05, "loss": 0.5002, "num_tokens": 280419437.0, "step": 46860 }, { "epoch": 0.49998399709814045, "grad_norm": 0.9661642448588037, "learning_rate": 2.936015874724111e-05, "loss": 0.5623, "num_tokens": 280444247.0, "step": 46865 }, { "epoch": 0.5000373401043389, "grad_norm": 0.6069628870657248, "learning_rate": 2.9356203242854948e-05, "loss": 0.5019, "num_tokens": 280488942.0, "step": 46870 }, { "epoch": 0.5000906831105374, "grad_norm": 0.8973787932714534, "learning_rate": 2.9352247680707557e-05, "loss": 0.6541, "num_tokens": 280516841.0, "step": 46875 }, { "epoch": 0.5001440261167358, "grad_norm": 0.70064942348998, "learning_rate": 2.934829206092202e-05, "loss": 0.3843, "num_tokens": 280546501.0, "step": 46880 }, { "epoch": 0.5001973691229343, "grad_norm": 0.9763875296705188, "learning_rate": 2.9344336383621433e-05, "loss": 0.4142, "num_tokens": 280568054.0, "step": 46885 }, { "epoch": 0.5002507121291327, "grad_norm": 0.7856974533486212, "learning_rate": 2.9340380648928888e-05, "loss": 0.4882, "num_tokens": 280588995.0, "step": 46890 }, { "epoch": 0.5003040551353312, "grad_norm": 0.8608017332509145, "learning_rate": 2.9336424856967476e-05, "loss": 0.4421, "num_tokens": 280614852.0, "step": 46895 }, { "epoch": 0.5003573981415297, "grad_norm": 1.1756533621894203, "learning_rate": 2.9332469007860292e-05, "loss": 0.568, "num_tokens": 280635373.0, "step": 46900 }, { "epoch": 0.5004107411477281, "grad_norm": 0.9326383989247673, "learning_rate": 2.9328513101730444e-05, "loss": 0.4653, "num_tokens": 280670193.0, "step": 46905 }, { "epoch": 0.5004640841539266, "grad_norm": 0.6170502097626824, "learning_rate": 2.9324557138701014e-05, "loss": 0.443, "num_tokens": 280700334.0, "step": 46910 }, { "epoch": 0.500517427160125, "grad_norm": 4.892005578808812, "learning_rate": 2.9320601118895112e-05, "loss": 0.6748, "num_tokens": 280748126.0, "step": 46915 }, { "epoch": 0.5005707701663235, "grad_norm": 1.191607266888927, "learning_rate": 2.931664504243586e-05, "loss": 0.4336, "num_tokens": 280767085.0, "step": 46920 }, { "epoch": 0.500624113172522, "grad_norm": 1.2870999406080441, "learning_rate": 2.9312688909446335e-05, "loss": 0.4933, "num_tokens": 280784775.0, "step": 46925 }, { "epoch": 0.5006774561787204, "grad_norm": 1.0503949766435425, "learning_rate": 2.9308732720049654e-05, "loss": 0.5214, "num_tokens": 280809905.0, "step": 46930 }, { "epoch": 0.5007307991849189, "grad_norm": 0.908659728113762, "learning_rate": 2.9304776474368922e-05, "loss": 0.5112, "num_tokens": 280828022.0, "step": 46935 }, { "epoch": 0.5007841421911173, "grad_norm": 1.4395790745046273, "learning_rate": 2.930082017252726e-05, "loss": 0.5079, "num_tokens": 280848264.0, "step": 46940 }, { "epoch": 0.5008374851973157, "grad_norm": 0.9269238297432847, "learning_rate": 2.9296863814647767e-05, "loss": 0.516, "num_tokens": 280870146.0, "step": 46945 }, { "epoch": 0.5008908282035143, "grad_norm": 1.7136234630578933, "learning_rate": 2.929290740085357e-05, "loss": 0.4776, "num_tokens": 280890488.0, "step": 46950 }, { "epoch": 0.5009441712097127, "grad_norm": 1.9007326766408492, "learning_rate": 2.928895093126778e-05, "loss": 0.5159, "num_tokens": 280920182.0, "step": 46955 }, { "epoch": 0.5009975142159111, "grad_norm": 0.7930879356709079, "learning_rate": 2.92849944060135e-05, "loss": 0.6812, "num_tokens": 280961057.0, "step": 46960 }, { "epoch": 0.5010508572221096, "grad_norm": 0.9220409317874825, "learning_rate": 2.9281037825213864e-05, "loss": 0.5965, "num_tokens": 280996757.0, "step": 46965 }, { "epoch": 0.501104200228308, "grad_norm": 1.196099635672743, "learning_rate": 2.9277081188991996e-05, "loss": 0.5677, "num_tokens": 281023856.0, "step": 46970 }, { "epoch": 0.5011575432345066, "grad_norm": 0.8878289789332716, "learning_rate": 2.9273124497471007e-05, "loss": 0.4701, "num_tokens": 281052504.0, "step": 46975 }, { "epoch": 0.501210886240705, "grad_norm": 0.8946315295385265, "learning_rate": 2.9269167750774023e-05, "loss": 0.4971, "num_tokens": 281097564.0, "step": 46980 }, { "epoch": 0.5012642292469034, "grad_norm": 0.6575283228610851, "learning_rate": 2.926521094902418e-05, "loss": 0.4697, "num_tokens": 281126105.0, "step": 46985 }, { "epoch": 0.5013175722531019, "grad_norm": 1.098841386360259, "learning_rate": 2.9261254092344594e-05, "loss": 0.4982, "num_tokens": 281159042.0, "step": 46990 }, { "epoch": 0.5013709152593003, "grad_norm": 1.3679184120114316, "learning_rate": 2.9257297180858394e-05, "loss": 0.5645, "num_tokens": 281187791.0, "step": 46995 }, { "epoch": 0.5014242582654989, "grad_norm": 0.7736117280780015, "learning_rate": 2.9253340214688723e-05, "loss": 0.5788, "num_tokens": 281219112.0, "step": 47000 }, { "epoch": 0.5014776012716973, "grad_norm": 2.27147253487788, "learning_rate": 2.9249383193958695e-05, "loss": 0.4916, "num_tokens": 281237303.0, "step": 47005 }, { "epoch": 0.5015309442778957, "grad_norm": 0.964900578010885, "learning_rate": 2.924542611879147e-05, "loss": 0.6065, "num_tokens": 281263287.0, "step": 47010 }, { "epoch": 0.5015842872840942, "grad_norm": 1.92515060633288, "learning_rate": 2.9241468989310166e-05, "loss": 0.4621, "num_tokens": 281292440.0, "step": 47015 }, { "epoch": 0.5016376302902926, "grad_norm": 0.7765066978043381, "learning_rate": 2.923751180563791e-05, "loss": 0.3764, "num_tokens": 281315983.0, "step": 47020 }, { "epoch": 0.5016909732964911, "grad_norm": 1.1121165511243158, "learning_rate": 2.923355456789787e-05, "loss": 0.4642, "num_tokens": 281347983.0, "step": 47025 }, { "epoch": 0.5017443163026896, "grad_norm": 0.739957555673074, "learning_rate": 2.9229597276213172e-05, "loss": 0.5212, "num_tokens": 281393869.0, "step": 47030 }, { "epoch": 0.501797659308888, "grad_norm": 0.792865501715635, "learning_rate": 2.9225639930706948e-05, "loss": 0.5142, "num_tokens": 281429222.0, "step": 47035 }, { "epoch": 0.5018510023150865, "grad_norm": 0.687276724697293, "learning_rate": 2.9221682531502365e-05, "loss": 0.546, "num_tokens": 281456293.0, "step": 47040 }, { "epoch": 0.5019043453212849, "grad_norm": 1.061223333886349, "learning_rate": 2.9217725078722552e-05, "loss": 0.4583, "num_tokens": 281484883.0, "step": 47045 }, { "epoch": 0.5019576883274833, "grad_norm": 0.8530326267008801, "learning_rate": 2.9213767572490668e-05, "loss": 0.519, "num_tokens": 281523600.0, "step": 47050 }, { "epoch": 0.5020110313336819, "grad_norm": 1.120197634614078, "learning_rate": 2.9209810012929856e-05, "loss": 0.5898, "num_tokens": 281551126.0, "step": 47055 }, { "epoch": 0.5020643743398803, "grad_norm": 1.243470991709154, "learning_rate": 2.920585240016327e-05, "loss": 0.4935, "num_tokens": 281566592.0, "step": 47060 }, { "epoch": 0.5021177173460788, "grad_norm": 1.0515589788088047, "learning_rate": 2.9201894734314057e-05, "loss": 0.5624, "num_tokens": 281600129.0, "step": 47065 }, { "epoch": 0.5021710603522772, "grad_norm": 0.9833319336655506, "learning_rate": 2.9197937015505377e-05, "loss": 0.5533, "num_tokens": 281627929.0, "step": 47070 }, { "epoch": 0.5022244033584756, "grad_norm": 0.9419746357654968, "learning_rate": 2.9193979243860387e-05, "loss": 0.5019, "num_tokens": 281659979.0, "step": 47075 }, { "epoch": 0.5022777463646741, "grad_norm": 0.7962291482474901, "learning_rate": 2.9190021419502233e-05, "loss": 0.421, "num_tokens": 281699594.0, "step": 47080 }, { "epoch": 0.5023310893708726, "grad_norm": 0.9003811147326922, "learning_rate": 2.9186063542554097e-05, "loss": 0.4492, "num_tokens": 281730802.0, "step": 47085 }, { "epoch": 0.5023844323770711, "grad_norm": 0.5930878813503646, "learning_rate": 2.9182105613139127e-05, "loss": 0.4627, "num_tokens": 281754517.0, "step": 47090 }, { "epoch": 0.5024377753832695, "grad_norm": 1.1939897364900656, "learning_rate": 2.917814763138047e-05, "loss": 0.6895, "num_tokens": 281799209.0, "step": 47095 }, { "epoch": 0.5024911183894679, "grad_norm": 0.9351653530898135, "learning_rate": 2.917418959740132e-05, "loss": 0.6269, "num_tokens": 281824581.0, "step": 47100 }, { "epoch": 0.5025444613956664, "grad_norm": 0.9315653734506563, "learning_rate": 2.9170231511324824e-05, "loss": 0.5907, "num_tokens": 281866732.0, "step": 47105 }, { "epoch": 0.5025978044018649, "grad_norm": 3.2976277158121743, "learning_rate": 2.9166273373274157e-05, "loss": 0.5013, "num_tokens": 281892148.0, "step": 47110 }, { "epoch": 0.5026511474080634, "grad_norm": 0.6313397449125703, "learning_rate": 2.916231518337248e-05, "loss": 0.6321, "num_tokens": 281937519.0, "step": 47115 }, { "epoch": 0.5027044904142618, "grad_norm": 0.8167680690028786, "learning_rate": 2.9158356941742976e-05, "loss": 0.4493, "num_tokens": 281961087.0, "step": 47120 }, { "epoch": 0.5027578334204602, "grad_norm": 1.0565224349974642, "learning_rate": 2.9154398648508802e-05, "loss": 0.5466, "num_tokens": 281983504.0, "step": 47125 }, { "epoch": 0.5028111764266587, "grad_norm": 0.9483294844858617, "learning_rate": 2.915044030379314e-05, "loss": 0.5228, "num_tokens": 282011446.0, "step": 47130 }, { "epoch": 0.5028645194328571, "grad_norm": 1.378866158495799, "learning_rate": 2.9146481907719176e-05, "loss": 0.6375, "num_tokens": 282040102.0, "step": 47135 }, { "epoch": 0.5029178624390556, "grad_norm": 0.7917318657386008, "learning_rate": 2.9142523460410065e-05, "loss": 0.5527, "num_tokens": 282082432.0, "step": 47140 }, { "epoch": 0.5029712054452541, "grad_norm": 0.742678635401332, "learning_rate": 2.9138564961989007e-05, "loss": 0.4196, "num_tokens": 282121610.0, "step": 47145 }, { "epoch": 0.5030245484514525, "grad_norm": 0.9098040323814133, "learning_rate": 2.9134606412579168e-05, "loss": 0.4634, "num_tokens": 282153212.0, "step": 47150 }, { "epoch": 0.503077891457651, "grad_norm": 0.979244541391328, "learning_rate": 2.913064781230374e-05, "loss": 0.4959, "num_tokens": 282185125.0, "step": 47155 }, { "epoch": 0.5031312344638494, "grad_norm": 1.0099151058233724, "learning_rate": 2.91266891612859e-05, "loss": 0.5991, "num_tokens": 282234671.0, "step": 47160 }, { "epoch": 0.5031845774700479, "grad_norm": 0.8878092426585377, "learning_rate": 2.9122730459648822e-05, "loss": 0.5916, "num_tokens": 282258834.0, "step": 47165 }, { "epoch": 0.5032379204762464, "grad_norm": 1.7338751936510468, "learning_rate": 2.9118771707515718e-05, "loss": 0.5903, "num_tokens": 282302684.0, "step": 47170 }, { "epoch": 0.5032912634824448, "grad_norm": 0.7152329519384424, "learning_rate": 2.9114812905009768e-05, "loss": 0.604, "num_tokens": 282337589.0, "step": 47175 }, { "epoch": 0.5033446064886433, "grad_norm": 1.1282766645974374, "learning_rate": 2.9110854052254144e-05, "loss": 0.6888, "num_tokens": 282384162.0, "step": 47180 }, { "epoch": 0.5033979494948417, "grad_norm": 1.0746073076828906, "learning_rate": 2.9106895149372065e-05, "loss": 0.4956, "num_tokens": 282405948.0, "step": 47185 }, { "epoch": 0.5034512925010401, "grad_norm": 0.6863963753966362, "learning_rate": 2.91029361964867e-05, "loss": 0.5513, "num_tokens": 282446818.0, "step": 47190 }, { "epoch": 0.5035046355072387, "grad_norm": 0.6880984629002966, "learning_rate": 2.9098977193721254e-05, "loss": 0.5111, "num_tokens": 282487679.0, "step": 47195 }, { "epoch": 0.5035579785134371, "grad_norm": 0.6865848310405989, "learning_rate": 2.909501814119892e-05, "loss": 0.5091, "num_tokens": 282508180.0, "step": 47200 }, { "epoch": 0.5036113215196356, "grad_norm": 1.0084623810288966, "learning_rate": 2.9091059039042908e-05, "loss": 0.4828, "num_tokens": 282540393.0, "step": 47205 }, { "epoch": 0.503664664525834, "grad_norm": 0.6219690288708091, "learning_rate": 2.9087099887376397e-05, "loss": 0.7807, "num_tokens": 282589562.0, "step": 47210 }, { "epoch": 0.5037180075320324, "grad_norm": 1.1570602728059136, "learning_rate": 2.9083140686322603e-05, "loss": 0.5349, "num_tokens": 282615247.0, "step": 47215 }, { "epoch": 0.503771350538231, "grad_norm": 0.9582537400449638, "learning_rate": 2.907918143600472e-05, "loss": 0.4141, "num_tokens": 282639224.0, "step": 47220 }, { "epoch": 0.5038246935444294, "grad_norm": 0.9915925373263742, "learning_rate": 2.907522213654595e-05, "loss": 0.5572, "num_tokens": 282666610.0, "step": 47225 }, { "epoch": 0.5038780365506278, "grad_norm": 0.6570786268649498, "learning_rate": 2.9071262788069513e-05, "loss": 0.5244, "num_tokens": 282706444.0, "step": 47230 }, { "epoch": 0.5039313795568263, "grad_norm": 0.6952316558752666, "learning_rate": 2.9067303390698602e-05, "loss": 0.5932, "num_tokens": 282735074.0, "step": 47235 }, { "epoch": 0.5039847225630247, "grad_norm": 0.9959578240125955, "learning_rate": 2.9063343944556422e-05, "loss": 0.4422, "num_tokens": 282752298.0, "step": 47240 }, { "epoch": 0.5040380655692233, "grad_norm": 0.82666240439772, "learning_rate": 2.90593844497662e-05, "loss": 0.6002, "num_tokens": 282784579.0, "step": 47245 }, { "epoch": 0.5040914085754217, "grad_norm": 0.6554899422088437, "learning_rate": 2.9055424906451135e-05, "loss": 0.5384, "num_tokens": 282818934.0, "step": 47250 }, { "epoch": 0.5041447515816201, "grad_norm": 1.529828781702679, "learning_rate": 2.9051465314734426e-05, "loss": 0.5678, "num_tokens": 282842328.0, "step": 47255 }, { "epoch": 0.5041980945878186, "grad_norm": 0.601443680641005, "learning_rate": 2.9047505674739317e-05, "loss": 0.4982, "num_tokens": 282868253.0, "step": 47260 }, { "epoch": 0.504251437594017, "grad_norm": 2.0942512376356044, "learning_rate": 2.9043545986589015e-05, "loss": 0.5176, "num_tokens": 282891085.0, "step": 47265 }, { "epoch": 0.5043047806002156, "grad_norm": 0.7342642751114175, "learning_rate": 2.9039586250406725e-05, "loss": 0.5789, "num_tokens": 282925627.0, "step": 47270 }, { "epoch": 0.504358123606414, "grad_norm": 0.9577156319672598, "learning_rate": 2.9035626466315668e-05, "loss": 0.4915, "num_tokens": 282941836.0, "step": 47275 }, { "epoch": 0.5044114666126124, "grad_norm": 1.2462139613951906, "learning_rate": 2.903166663443908e-05, "loss": 0.6538, "num_tokens": 282971910.0, "step": 47280 }, { "epoch": 0.5044648096188109, "grad_norm": 0.7115195828828969, "learning_rate": 2.902770675490017e-05, "loss": 0.4671, "num_tokens": 282998079.0, "step": 47285 }, { "epoch": 0.5045181526250093, "grad_norm": 1.2157801573372642, "learning_rate": 2.9023746827822163e-05, "loss": 0.4661, "num_tokens": 283025623.0, "step": 47290 }, { "epoch": 0.5045714956312078, "grad_norm": 0.8286074189019174, "learning_rate": 2.901978685332828e-05, "loss": 0.3769, "num_tokens": 283049679.0, "step": 47295 }, { "epoch": 0.5046248386374063, "grad_norm": 1.0133875795409972, "learning_rate": 2.901582683154176e-05, "loss": 0.4428, "num_tokens": 283071714.0, "step": 47300 }, { "epoch": 0.5046781816436047, "grad_norm": 0.672480527413315, "learning_rate": 2.9011866762585815e-05, "loss": 0.4585, "num_tokens": 283093990.0, "step": 47305 }, { "epoch": 0.5047315246498032, "grad_norm": 0.7272841998000794, "learning_rate": 2.9007906646583688e-05, "loss": 0.4829, "num_tokens": 283128351.0, "step": 47310 }, { "epoch": 0.5047848676560016, "grad_norm": 1.0413971810832088, "learning_rate": 2.9003946483658596e-05, "loss": 0.505, "num_tokens": 283162235.0, "step": 47315 }, { "epoch": 0.5048382106622, "grad_norm": 1.7707406408875916, "learning_rate": 2.899998627393378e-05, "loss": 0.4807, "num_tokens": 283183759.0, "step": 47320 }, { "epoch": 0.5048915536683986, "grad_norm": 0.6554359980996768, "learning_rate": 2.899602601753248e-05, "loss": 0.53, "num_tokens": 283217889.0, "step": 47325 }, { "epoch": 0.504944896674597, "grad_norm": 0.6544081795360677, "learning_rate": 2.8992065714577917e-05, "loss": 0.473, "num_tokens": 283260741.0, "step": 47330 }, { "epoch": 0.5049982396807955, "grad_norm": 0.7689612671267929, "learning_rate": 2.8988105365193334e-05, "loss": 0.5158, "num_tokens": 283296271.0, "step": 47335 }, { "epoch": 0.5050515826869939, "grad_norm": 0.7521632397294181, "learning_rate": 2.8984144969501975e-05, "loss": 0.5163, "num_tokens": 283329557.0, "step": 47340 }, { "epoch": 0.5051049256931923, "grad_norm": 0.8095270631505409, "learning_rate": 2.8980184527627062e-05, "loss": 0.5254, "num_tokens": 283360354.0, "step": 47345 }, { "epoch": 0.5051582686993908, "grad_norm": 4.232257346032255, "learning_rate": 2.8976224039691853e-05, "loss": 0.6291, "num_tokens": 283390461.0, "step": 47350 }, { "epoch": 0.5052116117055893, "grad_norm": 0.7841781638547799, "learning_rate": 2.8972263505819584e-05, "loss": 0.4605, "num_tokens": 283423150.0, "step": 47355 }, { "epoch": 0.5052649547117878, "grad_norm": 1.125622943872233, "learning_rate": 2.89683029261335e-05, "loss": 0.6092, "num_tokens": 283461546.0, "step": 47360 }, { "epoch": 0.5053182977179862, "grad_norm": 0.7078337935305257, "learning_rate": 2.8964342300756847e-05, "loss": 0.4746, "num_tokens": 283494631.0, "step": 47365 }, { "epoch": 0.5053716407241846, "grad_norm": 1.111306879552422, "learning_rate": 2.8960381629812865e-05, "loss": 0.4497, "num_tokens": 283532358.0, "step": 47370 }, { "epoch": 0.5054249837303831, "grad_norm": 0.9433560377280608, "learning_rate": 2.895642091342481e-05, "loss": 0.5322, "num_tokens": 283577079.0, "step": 47375 }, { "epoch": 0.5054783267365816, "grad_norm": 1.3167169378102628, "learning_rate": 2.8952460151715922e-05, "loss": 0.4763, "num_tokens": 283610665.0, "step": 47380 }, { "epoch": 0.5055316697427801, "grad_norm": 0.7924473225741343, "learning_rate": 2.894849934480946e-05, "loss": 0.4816, "num_tokens": 283632759.0, "step": 47385 }, { "epoch": 0.5055850127489785, "grad_norm": 1.03587600765357, "learning_rate": 2.8944538492828673e-05, "loss": 0.5456, "num_tokens": 283650990.0, "step": 47390 }, { "epoch": 0.5056383557551769, "grad_norm": 0.7146037702718919, "learning_rate": 2.8940577595896822e-05, "loss": 0.5542, "num_tokens": 283676748.0, "step": 47395 }, { "epoch": 0.5056916987613754, "grad_norm": 0.9669686722226981, "learning_rate": 2.893661665413715e-05, "loss": 0.5262, "num_tokens": 283718128.0, "step": 47400 }, { "epoch": 0.5057450417675738, "grad_norm": 1.3117720527468808, "learning_rate": 2.8932655667672913e-05, "loss": 0.5669, "num_tokens": 283739669.0, "step": 47405 }, { "epoch": 0.5057983847737723, "grad_norm": 0.7434158086802534, "learning_rate": 2.892869463662739e-05, "loss": 0.5723, "num_tokens": 283779682.0, "step": 47410 }, { "epoch": 0.5058517277799708, "grad_norm": 0.7130185583044688, "learning_rate": 2.892473356112381e-05, "loss": 0.7674, "num_tokens": 283795865.0, "step": 47415 }, { "epoch": 0.5059050707861692, "grad_norm": 1.2201749933071706, "learning_rate": 2.8920772441285456e-05, "loss": 0.5049, "num_tokens": 283821353.0, "step": 47420 }, { "epoch": 0.5059584137923677, "grad_norm": 0.7027960524676186, "learning_rate": 2.8916811277235572e-05, "loss": 0.4617, "num_tokens": 283840838.0, "step": 47425 }, { "epoch": 0.5060117567985661, "grad_norm": 1.2913467603278803, "learning_rate": 2.891285006909744e-05, "loss": 0.4873, "num_tokens": 283868996.0, "step": 47430 }, { "epoch": 0.5060650998047646, "grad_norm": 0.8904062575641046, "learning_rate": 2.890888881699431e-05, "loss": 0.4939, "num_tokens": 283894748.0, "step": 47435 }, { "epoch": 0.5061184428109631, "grad_norm": 0.7737253117745686, "learning_rate": 2.8904927521049464e-05, "loss": 0.3743, "num_tokens": 283933527.0, "step": 47440 }, { "epoch": 0.5061717858171615, "grad_norm": 1.367841018375766, "learning_rate": 2.8900966181386153e-05, "loss": 0.4897, "num_tokens": 283959477.0, "step": 47445 }, { "epoch": 0.50622512882336, "grad_norm": 0.8898396911560199, "learning_rate": 2.8897004798127652e-05, "loss": 0.5048, "num_tokens": 283995704.0, "step": 47450 }, { "epoch": 0.5062784718295584, "grad_norm": 0.8471452982470845, "learning_rate": 2.8893043371397225e-05, "loss": 0.4204, "num_tokens": 284020053.0, "step": 47455 }, { "epoch": 0.5063318148357568, "grad_norm": 0.8525963236225332, "learning_rate": 2.888908190131816e-05, "loss": 0.566, "num_tokens": 284053815.0, "step": 47460 }, { "epoch": 0.5063851578419554, "grad_norm": 0.7348303087772983, "learning_rate": 2.888512038801372e-05, "loss": 0.4418, "num_tokens": 284077960.0, "step": 47465 }, { "epoch": 0.5064385008481538, "grad_norm": 1.2095784136737002, "learning_rate": 2.8881158831607175e-05, "loss": 0.5274, "num_tokens": 284105661.0, "step": 47470 }, { "epoch": 0.5064918438543523, "grad_norm": 0.6910012314543855, "learning_rate": 2.8877197232221798e-05, "loss": 0.5495, "num_tokens": 284145706.0, "step": 47475 }, { "epoch": 0.5065451868605507, "grad_norm": 0.8219490381420682, "learning_rate": 2.887323558998088e-05, "loss": 0.5007, "num_tokens": 284170027.0, "step": 47480 }, { "epoch": 0.5065985298667491, "grad_norm": 1.3539931735199333, "learning_rate": 2.8869273905007695e-05, "loss": 0.547, "num_tokens": 284185078.0, "step": 47485 }, { "epoch": 0.5066518728729477, "grad_norm": 0.7742719277823498, "learning_rate": 2.8865312177425507e-05, "loss": 0.633, "num_tokens": 284226330.0, "step": 47490 }, { "epoch": 0.5067052158791461, "grad_norm": 0.762302641992206, "learning_rate": 2.8861350407357614e-05, "loss": 0.5089, "num_tokens": 284247701.0, "step": 47495 }, { "epoch": 0.5067585588853445, "grad_norm": 0.8218923905787008, "learning_rate": 2.8857388594927292e-05, "loss": 0.5911, "num_tokens": 284274644.0, "step": 47500 }, { "epoch": 0.506811901891543, "grad_norm": 1.4287197823451896, "learning_rate": 2.885342674025783e-05, "loss": 0.6378, "num_tokens": 284305233.0, "step": 47505 }, { "epoch": 0.5068652448977414, "grad_norm": 1.1704887046064658, "learning_rate": 2.8849464843472495e-05, "loss": 0.4873, "num_tokens": 284323692.0, "step": 47510 }, { "epoch": 0.50691858790394, "grad_norm": 1.2315108566566941, "learning_rate": 2.8845502904694592e-05, "loss": 0.4361, "num_tokens": 284345972.0, "step": 47515 }, { "epoch": 0.5069719309101384, "grad_norm": 0.8833096121564724, "learning_rate": 2.884154092404741e-05, "loss": 0.6086, "num_tokens": 284383940.0, "step": 47520 }, { "epoch": 0.5070252739163368, "grad_norm": 1.2091971475365122, "learning_rate": 2.8837578901654222e-05, "loss": 0.4949, "num_tokens": 284404300.0, "step": 47525 }, { "epoch": 0.5070786169225353, "grad_norm": 0.8195329001737229, "learning_rate": 2.8833616837638327e-05, "loss": 0.5887, "num_tokens": 284433843.0, "step": 47530 }, { "epoch": 0.5071319599287337, "grad_norm": 1.3053776484614712, "learning_rate": 2.8829654732123018e-05, "loss": 0.5899, "num_tokens": 284481023.0, "step": 47535 }, { "epoch": 0.5071853029349322, "grad_norm": 0.7148807068130583, "learning_rate": 2.8825692585231583e-05, "loss": 0.5341, "num_tokens": 284508138.0, "step": 47540 }, { "epoch": 0.5072386459411307, "grad_norm": 1.240053276237355, "learning_rate": 2.8821730397087325e-05, "loss": 0.5903, "num_tokens": 284556044.0, "step": 47545 }, { "epoch": 0.5072919889473291, "grad_norm": 0.6853161027150797, "learning_rate": 2.8817768167813523e-05, "loss": 0.4953, "num_tokens": 284590848.0, "step": 47550 }, { "epoch": 0.5073453319535276, "grad_norm": 0.7686140571075439, "learning_rate": 2.8813805897533484e-05, "loss": 0.5975, "num_tokens": 284625720.0, "step": 47555 }, { "epoch": 0.507398674959726, "grad_norm": 0.9602582760748886, "learning_rate": 2.8809843586370505e-05, "loss": 0.5049, "num_tokens": 284654269.0, "step": 47560 }, { "epoch": 0.5074520179659245, "grad_norm": 0.6153288866783532, "learning_rate": 2.8805881234447884e-05, "loss": 0.4362, "num_tokens": 284682329.0, "step": 47565 }, { "epoch": 0.507505360972123, "grad_norm": 0.8209669719530063, "learning_rate": 2.8801918841888918e-05, "loss": 0.5178, "num_tokens": 284711174.0, "step": 47570 }, { "epoch": 0.5075587039783214, "grad_norm": 0.6023821237017061, "learning_rate": 2.8797956408816922e-05, "loss": 0.6664, "num_tokens": 284752080.0, "step": 47575 }, { "epoch": 0.5076120469845199, "grad_norm": 0.6022881629348931, "learning_rate": 2.8793993935355183e-05, "loss": 0.4744, "num_tokens": 284791026.0, "step": 47580 }, { "epoch": 0.5076653899907183, "grad_norm": 0.9165100530737905, "learning_rate": 2.8790031421627006e-05, "loss": 0.6387, "num_tokens": 284821144.0, "step": 47585 }, { "epoch": 0.5077187329969167, "grad_norm": 1.0845008381312802, "learning_rate": 2.8786068867755704e-05, "loss": 0.6267, "num_tokens": 284850082.0, "step": 47590 }, { "epoch": 0.5077720760031152, "grad_norm": 0.9618759895812877, "learning_rate": 2.878210627386458e-05, "loss": 0.5128, "num_tokens": 284897728.0, "step": 47595 }, { "epoch": 0.5078254190093137, "grad_norm": 0.9267550091216217, "learning_rate": 2.8778143640076942e-05, "loss": 0.48, "num_tokens": 284912980.0, "step": 47600 }, { "epoch": 0.5078787620155122, "grad_norm": 1.0608632742209465, "learning_rate": 2.8774180966516108e-05, "loss": 0.6137, "num_tokens": 284938037.0, "step": 47605 }, { "epoch": 0.5079321050217106, "grad_norm": 0.9501681239462189, "learning_rate": 2.877021825330537e-05, "loss": 0.5426, "num_tokens": 284980827.0, "step": 47610 }, { "epoch": 0.507985448027909, "grad_norm": 0.8575019300110935, "learning_rate": 2.8766255500568052e-05, "loss": 0.4644, "num_tokens": 285006933.0, "step": 47615 }, { "epoch": 0.5080387910341075, "grad_norm": 0.781377204935412, "learning_rate": 2.8762292708427463e-05, "loss": 0.5723, "num_tokens": 285047029.0, "step": 47620 }, { "epoch": 0.508092134040306, "grad_norm": 1.4435575229225244, "learning_rate": 2.8758329877006917e-05, "loss": 0.5531, "num_tokens": 285066433.0, "step": 47625 }, { "epoch": 0.5081454770465045, "grad_norm": 0.8563982485674979, "learning_rate": 2.8754367006429732e-05, "loss": 0.5089, "num_tokens": 285089571.0, "step": 47630 }, { "epoch": 0.5081988200527029, "grad_norm": 0.8752501816423102, "learning_rate": 2.8750404096819223e-05, "loss": 0.5917, "num_tokens": 285137611.0, "step": 47635 }, { "epoch": 0.5082521630589013, "grad_norm": 1.3854753883598099, "learning_rate": 2.8746441148298696e-05, "loss": 0.6826, "num_tokens": 285170862.0, "step": 47640 }, { "epoch": 0.5083055060650998, "grad_norm": 0.6148204366658303, "learning_rate": 2.8742478160991494e-05, "loss": 0.5767, "num_tokens": 285191690.0, "step": 47645 }, { "epoch": 0.5083588490712982, "grad_norm": 1.2246969283829154, "learning_rate": 2.873851513502092e-05, "loss": 0.5972, "num_tokens": 285238493.0, "step": 47650 }, { "epoch": 0.5084121920774968, "grad_norm": 1.680767992963505, "learning_rate": 2.8734552070510302e-05, "loss": 0.6169, "num_tokens": 285275211.0, "step": 47655 }, { "epoch": 0.5084655350836952, "grad_norm": 1.0285174767845588, "learning_rate": 2.873058896758295e-05, "loss": 0.4185, "num_tokens": 285303970.0, "step": 47660 }, { "epoch": 0.5085188780898936, "grad_norm": 1.2036745574502066, "learning_rate": 2.87266258263622e-05, "loss": 0.6028, "num_tokens": 285332416.0, "step": 47665 }, { "epoch": 0.5085722210960921, "grad_norm": 1.4694101342971675, "learning_rate": 2.8722662646971383e-05, "loss": 0.6007, "num_tokens": 285371515.0, "step": 47670 }, { "epoch": 0.5086255641022905, "grad_norm": 0.9335798551126856, "learning_rate": 2.8718699429533806e-05, "loss": 0.4515, "num_tokens": 285403656.0, "step": 47675 }, { "epoch": 0.508678907108489, "grad_norm": 1.278087178133123, "learning_rate": 2.8714736174172813e-05, "loss": 0.4562, "num_tokens": 285433304.0, "step": 47680 }, { "epoch": 0.5087322501146875, "grad_norm": 1.1012830234387876, "learning_rate": 2.8710772881011728e-05, "loss": 0.497, "num_tokens": 285459865.0, "step": 47685 }, { "epoch": 0.5087855931208859, "grad_norm": 0.7394442483878756, "learning_rate": 2.8706809550173868e-05, "loss": 0.6109, "num_tokens": 285487977.0, "step": 47690 }, { "epoch": 0.5088389361270844, "grad_norm": 1.0812738841683809, "learning_rate": 2.870284618178258e-05, "loss": 0.5259, "num_tokens": 285521080.0, "step": 47695 }, { "epoch": 0.5088922791332828, "grad_norm": 0.9609902354896273, "learning_rate": 2.8698882775961182e-05, "loss": 0.5082, "num_tokens": 285543530.0, "step": 47700 }, { "epoch": 0.5089456221394812, "grad_norm": 0.8620581784708178, "learning_rate": 2.869491933283302e-05, "loss": 0.6221, "num_tokens": 285573963.0, "step": 47705 }, { "epoch": 0.5089989651456798, "grad_norm": 0.6139681452405878, "learning_rate": 2.869095585252143e-05, "loss": 0.4732, "num_tokens": 285602126.0, "step": 47710 }, { "epoch": 0.5090523081518782, "grad_norm": 0.9520759871255963, "learning_rate": 2.8686992335149727e-05, "loss": 0.4409, "num_tokens": 285633014.0, "step": 47715 }, { "epoch": 0.5091056511580767, "grad_norm": 0.8553567152645816, "learning_rate": 2.868302878084127e-05, "loss": 0.5518, "num_tokens": 285676482.0, "step": 47720 }, { "epoch": 0.5091589941642751, "grad_norm": 0.692136764633243, "learning_rate": 2.8679065189719384e-05, "loss": 0.4592, "num_tokens": 285700108.0, "step": 47725 }, { "epoch": 0.5092123371704735, "grad_norm": 1.1983203633240136, "learning_rate": 2.8675101561907402e-05, "loss": 0.5053, "num_tokens": 285715706.0, "step": 47730 }, { "epoch": 0.5092656801766721, "grad_norm": 0.7035469917356426, "learning_rate": 2.867113789752869e-05, "loss": 0.5235, "num_tokens": 285749769.0, "step": 47735 }, { "epoch": 0.5093190231828705, "grad_norm": 1.0671938875068552, "learning_rate": 2.866717419670657e-05, "loss": 0.7577, "num_tokens": 285780320.0, "step": 47740 }, { "epoch": 0.509372366189069, "grad_norm": 0.9794371986166281, "learning_rate": 2.866321045956437e-05, "loss": 0.5923, "num_tokens": 285824177.0, "step": 47745 }, { "epoch": 0.5094257091952674, "grad_norm": 0.8318260077879758, "learning_rate": 2.865924668622546e-05, "loss": 0.5826, "num_tokens": 285873161.0, "step": 47750 }, { "epoch": 0.5094790522014658, "grad_norm": 0.7609868102220745, "learning_rate": 2.8655282876813176e-05, "loss": 0.6242, "num_tokens": 285912627.0, "step": 47755 }, { "epoch": 0.5095323952076644, "grad_norm": 0.6053554200456265, "learning_rate": 2.8651319031450862e-05, "loss": 0.5226, "num_tokens": 285937767.0, "step": 47760 }, { "epoch": 0.5095857382138628, "grad_norm": 0.8536479114473935, "learning_rate": 2.864735515026187e-05, "loss": 0.476, "num_tokens": 285960214.0, "step": 47765 }, { "epoch": 0.5096390812200612, "grad_norm": 0.9736655743411597, "learning_rate": 2.8643391233369533e-05, "loss": 0.5247, "num_tokens": 285985640.0, "step": 47770 }, { "epoch": 0.5096924242262597, "grad_norm": 0.6369898995984106, "learning_rate": 2.863942728089721e-05, "loss": 0.5244, "num_tokens": 286019282.0, "step": 47775 }, { "epoch": 0.5097457672324581, "grad_norm": 0.9035073238507924, "learning_rate": 2.8635463292968252e-05, "loss": 0.4708, "num_tokens": 286035278.0, "step": 47780 }, { "epoch": 0.5097991102386566, "grad_norm": 0.981066295716102, "learning_rate": 2.863149926970601e-05, "loss": 0.5909, "num_tokens": 286066588.0, "step": 47785 }, { "epoch": 0.5098524532448551, "grad_norm": 0.8377664561852035, "learning_rate": 2.862753521123383e-05, "loss": 0.5472, "num_tokens": 286107418.0, "step": 47790 }, { "epoch": 0.5099057962510535, "grad_norm": 1.0374973425371905, "learning_rate": 2.862357111767508e-05, "loss": 0.5358, "num_tokens": 286128635.0, "step": 47795 }, { "epoch": 0.509959139257252, "grad_norm": 0.7121757201829917, "learning_rate": 2.8619606989153098e-05, "loss": 0.472, "num_tokens": 286160647.0, "step": 47800 }, { "epoch": 0.5100124822634504, "grad_norm": 0.6820522359679837, "learning_rate": 2.8615642825791244e-05, "loss": 0.541, "num_tokens": 286183867.0, "step": 47805 }, { "epoch": 0.5100658252696489, "grad_norm": 0.8181816136358546, "learning_rate": 2.861167862771288e-05, "loss": 0.4868, "num_tokens": 286219871.0, "step": 47810 }, { "epoch": 0.5101191682758474, "grad_norm": 1.807781396380261, "learning_rate": 2.860771439504137e-05, "loss": 0.526, "num_tokens": 286257109.0, "step": 47815 }, { "epoch": 0.5101725112820458, "grad_norm": 1.0387004203293733, "learning_rate": 2.8603750127900042e-05, "loss": 0.5118, "num_tokens": 286287174.0, "step": 47820 }, { "epoch": 0.5102258542882443, "grad_norm": 0.8585633860661185, "learning_rate": 2.8599785826412295e-05, "loss": 0.4143, "num_tokens": 286314286.0, "step": 47825 }, { "epoch": 0.5102791972944427, "grad_norm": 1.0159031960742286, "learning_rate": 2.8595821490701462e-05, "loss": 0.5204, "num_tokens": 286336836.0, "step": 47830 }, { "epoch": 0.5103325403006412, "grad_norm": 1.491567158926803, "learning_rate": 2.8591857120890926e-05, "loss": 0.5003, "num_tokens": 286356214.0, "step": 47835 }, { "epoch": 0.5103858833068396, "grad_norm": 0.7733290308986086, "learning_rate": 2.8587892717104032e-05, "loss": 0.4987, "num_tokens": 286379607.0, "step": 47840 }, { "epoch": 0.5104392263130381, "grad_norm": 0.7242191282026068, "learning_rate": 2.858392827946415e-05, "loss": 0.4086, "num_tokens": 286405447.0, "step": 47845 }, { "epoch": 0.5104925693192366, "grad_norm": 0.7603317127979148, "learning_rate": 2.857996380809465e-05, "loss": 0.5156, "num_tokens": 286428912.0, "step": 47850 }, { "epoch": 0.510545912325435, "grad_norm": 1.2550904574607742, "learning_rate": 2.8575999303118895e-05, "loss": 0.7325, "num_tokens": 286474796.0, "step": 47855 }, { "epoch": 0.5105992553316334, "grad_norm": 0.5388827471167205, "learning_rate": 2.8572034764660243e-05, "loss": 0.4892, "num_tokens": 286503868.0, "step": 47860 }, { "epoch": 0.5106525983378319, "grad_norm": 0.684938446347741, "learning_rate": 2.8568070192842083e-05, "loss": 0.5005, "num_tokens": 286533129.0, "step": 47865 }, { "epoch": 0.5107059413440304, "grad_norm": 0.8408920363472988, "learning_rate": 2.8564105587787763e-05, "loss": 0.4928, "num_tokens": 286566379.0, "step": 47870 }, { "epoch": 0.5107592843502289, "grad_norm": 0.911171385142652, "learning_rate": 2.8560140949620672e-05, "loss": 0.4353, "num_tokens": 286589548.0, "step": 47875 }, { "epoch": 0.5108126273564273, "grad_norm": 0.8119231037901136, "learning_rate": 2.8556176278464166e-05, "loss": 0.5576, "num_tokens": 286619063.0, "step": 47880 }, { "epoch": 0.5108659703626257, "grad_norm": 0.829402917406993, "learning_rate": 2.855221157444163e-05, "loss": 0.6055, "num_tokens": 286649065.0, "step": 47885 }, { "epoch": 0.5109193133688242, "grad_norm": 0.8531857117568096, "learning_rate": 2.8548246837676423e-05, "loss": 0.5548, "num_tokens": 286675996.0, "step": 47890 }, { "epoch": 0.5109726563750226, "grad_norm": 1.1734945328580717, "learning_rate": 2.8544282068291928e-05, "loss": 0.642, "num_tokens": 286702894.0, "step": 47895 }, { "epoch": 0.5110259993812212, "grad_norm": 2.4603044786950736, "learning_rate": 2.8540317266411525e-05, "loss": 0.6321, "num_tokens": 286727214.0, "step": 47900 }, { "epoch": 0.5110793423874196, "grad_norm": 1.2780826668486311, "learning_rate": 2.8536352432158587e-05, "loss": 0.6782, "num_tokens": 286755007.0, "step": 47905 }, { "epoch": 0.511132685393618, "grad_norm": 0.787331712619319, "learning_rate": 2.8532387565656482e-05, "loss": 0.4321, "num_tokens": 286775761.0, "step": 47910 }, { "epoch": 0.5111860283998165, "grad_norm": 0.9735383704001314, "learning_rate": 2.85284226670286e-05, "loss": 0.4702, "num_tokens": 286802601.0, "step": 47915 }, { "epoch": 0.5112393714060149, "grad_norm": 0.8086767439020429, "learning_rate": 2.852445773639832e-05, "loss": 0.514, "num_tokens": 286832849.0, "step": 47920 }, { "epoch": 0.5112927144122135, "grad_norm": 1.0284476024643054, "learning_rate": 2.8520492773889017e-05, "loss": 0.5896, "num_tokens": 286864985.0, "step": 47925 }, { "epoch": 0.5113460574184119, "grad_norm": 1.4477883069301274, "learning_rate": 2.851652777962408e-05, "loss": 0.6269, "num_tokens": 286881593.0, "step": 47930 }, { "epoch": 0.5113994004246103, "grad_norm": 0.94979271815829, "learning_rate": 2.8512562753726872e-05, "loss": 0.5643, "num_tokens": 286916922.0, "step": 47935 }, { "epoch": 0.5114527434308088, "grad_norm": 1.0284377631514625, "learning_rate": 2.850859769632081e-05, "loss": 0.5174, "num_tokens": 286952998.0, "step": 47940 }, { "epoch": 0.5115060864370072, "grad_norm": 1.8210882608179748, "learning_rate": 2.850463260752925e-05, "loss": 0.6066, "num_tokens": 286973466.0, "step": 47945 }, { "epoch": 0.5115594294432056, "grad_norm": 1.0925430862031538, "learning_rate": 2.8500667487475585e-05, "loss": 0.594, "num_tokens": 287010917.0, "step": 47950 }, { "epoch": 0.5116127724494042, "grad_norm": 1.1960902786977705, "learning_rate": 2.8496702336283203e-05, "loss": 0.5328, "num_tokens": 287056851.0, "step": 47955 }, { "epoch": 0.5116661154556026, "grad_norm": 0.717212789924883, "learning_rate": 2.84927371540755e-05, "loss": 0.5351, "num_tokens": 287086434.0, "step": 47960 }, { "epoch": 0.5117194584618011, "grad_norm": 0.9039507131149702, "learning_rate": 2.8488771940975845e-05, "loss": 0.5815, "num_tokens": 287123361.0, "step": 47965 }, { "epoch": 0.5117728014679995, "grad_norm": 0.593626492213064, "learning_rate": 2.848480669710764e-05, "loss": 0.4815, "num_tokens": 287163841.0, "step": 47970 }, { "epoch": 0.5118261444741979, "grad_norm": 0.9910127927318046, "learning_rate": 2.8480841422594277e-05, "loss": 0.5966, "num_tokens": 287201524.0, "step": 47975 }, { "epoch": 0.5118794874803965, "grad_norm": 1.0207869264779532, "learning_rate": 2.8476876117559153e-05, "loss": 0.5133, "num_tokens": 287238382.0, "step": 47980 }, { "epoch": 0.5119328304865949, "grad_norm": 1.3488487885987284, "learning_rate": 2.8472910782125633e-05, "loss": 0.3954, "num_tokens": 287256395.0, "step": 47985 }, { "epoch": 0.5119861734927934, "grad_norm": 0.8604095678224961, "learning_rate": 2.8468945416417136e-05, "loss": 0.6809, "num_tokens": 287299669.0, "step": 47990 }, { "epoch": 0.5120395164989918, "grad_norm": 0.911294780287243, "learning_rate": 2.8464980020557047e-05, "loss": 0.6073, "num_tokens": 287328706.0, "step": 47995 }, { "epoch": 0.5120928595051902, "grad_norm": 0.6604331818745898, "learning_rate": 2.8461014594668767e-05, "loss": 0.531, "num_tokens": 287371918.0, "step": 48000 }, { "epoch": 0.5121462025113888, "grad_norm": 1.127518094391747, "learning_rate": 2.845704913887568e-05, "loss": 0.3939, "num_tokens": 287400810.0, "step": 48005 }, { "epoch": 0.5121995455175872, "grad_norm": 0.9149254998552002, "learning_rate": 2.8453083653301195e-05, "loss": 0.4737, "num_tokens": 287432614.0, "step": 48010 }, { "epoch": 0.5122528885237857, "grad_norm": 1.087279038812275, "learning_rate": 2.8449118138068702e-05, "loss": 0.6089, "num_tokens": 287458647.0, "step": 48015 }, { "epoch": 0.5123062315299841, "grad_norm": 5.123163876186135, "learning_rate": 2.8445152593301604e-05, "loss": 0.686, "num_tokens": 287483510.0, "step": 48020 }, { "epoch": 0.5123595745361825, "grad_norm": 0.6792979150139536, "learning_rate": 2.8441187019123296e-05, "loss": 0.5017, "num_tokens": 287501299.0, "step": 48025 }, { "epoch": 0.512412917542381, "grad_norm": 1.0779124959353588, "learning_rate": 2.8437221415657177e-05, "loss": 0.4962, "num_tokens": 287535348.0, "step": 48030 }, { "epoch": 0.5124662605485795, "grad_norm": 0.7542403470976654, "learning_rate": 2.8433255783026657e-05, "loss": 0.5303, "num_tokens": 287563373.0, "step": 48035 }, { "epoch": 0.5125196035547779, "grad_norm": 1.437603976614378, "learning_rate": 2.842929012135514e-05, "loss": 0.5183, "num_tokens": 287586778.0, "step": 48040 }, { "epoch": 0.5125729465609764, "grad_norm": 1.1349308719709075, "learning_rate": 2.8425324430766008e-05, "loss": 0.4389, "num_tokens": 287611352.0, "step": 48045 }, { "epoch": 0.5126262895671748, "grad_norm": 1.0907997255028936, "learning_rate": 2.84213587113827e-05, "loss": 0.6117, "num_tokens": 287638493.0, "step": 48050 }, { "epoch": 0.5126796325733733, "grad_norm": 0.61799623353661, "learning_rate": 2.841739296332858e-05, "loss": 0.523, "num_tokens": 287683656.0, "step": 48055 }, { "epoch": 0.5127329755795718, "grad_norm": 1.1433194170676515, "learning_rate": 2.8413427186727094e-05, "loss": 0.6573, "num_tokens": 287709748.0, "step": 48060 }, { "epoch": 0.5127863185857702, "grad_norm": 0.8231544586082562, "learning_rate": 2.8409461381701618e-05, "loss": 0.5053, "num_tokens": 287735672.0, "step": 48065 }, { "epoch": 0.5128396615919687, "grad_norm": 0.7739373492122653, "learning_rate": 2.8405495548375582e-05, "loss": 0.5271, "num_tokens": 287774166.0, "step": 48070 }, { "epoch": 0.5128930045981671, "grad_norm": 0.899966395562339, "learning_rate": 2.840152968687238e-05, "loss": 0.4848, "num_tokens": 287811863.0, "step": 48075 }, { "epoch": 0.5129463476043656, "grad_norm": 0.6572487904113592, "learning_rate": 2.8397563797315423e-05, "loss": 0.6525, "num_tokens": 287841760.0, "step": 48080 }, { "epoch": 0.512999690610564, "grad_norm": 1.6514671999502422, "learning_rate": 2.8393597879828122e-05, "loss": 0.4791, "num_tokens": 287864901.0, "step": 48085 }, { "epoch": 0.5130530336167625, "grad_norm": 0.9581520960864504, "learning_rate": 2.8389631934533895e-05, "loss": 0.4087, "num_tokens": 287894077.0, "step": 48090 }, { "epoch": 0.513106376622961, "grad_norm": 0.8146468051241819, "learning_rate": 2.8385665961556158e-05, "loss": 0.4583, "num_tokens": 287919109.0, "step": 48095 }, { "epoch": 0.5131597196291594, "grad_norm": 0.8351588686542503, "learning_rate": 2.8381699961018293e-05, "loss": 0.4658, "num_tokens": 287947787.0, "step": 48100 }, { "epoch": 0.5132130626353579, "grad_norm": 1.5006920858090809, "learning_rate": 2.837773393304376e-05, "loss": 0.5976, "num_tokens": 287970278.0, "step": 48105 }, { "epoch": 0.5132664056415563, "grad_norm": 0.5327270064691205, "learning_rate": 2.8373767877755943e-05, "loss": 0.5548, "num_tokens": 288013773.0, "step": 48110 }, { "epoch": 0.5133197486477548, "grad_norm": 0.8292245726197491, "learning_rate": 2.8369801795278255e-05, "loss": 0.6262, "num_tokens": 288045171.0, "step": 48115 }, { "epoch": 0.5133730916539533, "grad_norm": 1.240248421843738, "learning_rate": 2.8365835685734128e-05, "loss": 0.5293, "num_tokens": 288064416.0, "step": 48120 }, { "epoch": 0.5134264346601517, "grad_norm": 0.6935357426548183, "learning_rate": 2.8361869549246977e-05, "loss": 0.5063, "num_tokens": 288089129.0, "step": 48125 }, { "epoch": 0.5134797776663501, "grad_norm": 2.3130198025684323, "learning_rate": 2.835790338594021e-05, "loss": 0.5201, "num_tokens": 288119998.0, "step": 48130 }, { "epoch": 0.5135331206725486, "grad_norm": 1.0774537155981074, "learning_rate": 2.835393719593725e-05, "loss": 0.4692, "num_tokens": 288130881.0, "step": 48135 }, { "epoch": 0.513586463678747, "grad_norm": 0.7372909174567405, "learning_rate": 2.834997097936153e-05, "loss": 0.5409, "num_tokens": 288173086.0, "step": 48140 }, { "epoch": 0.5136398066849456, "grad_norm": 0.7430757040872855, "learning_rate": 2.8346004736336444e-05, "loss": 0.5692, "num_tokens": 288208712.0, "step": 48145 }, { "epoch": 0.513693149691144, "grad_norm": 0.7791371333334767, "learning_rate": 2.8342038466985437e-05, "loss": 0.5442, "num_tokens": 288246752.0, "step": 48150 }, { "epoch": 0.5137464926973424, "grad_norm": 1.197105200051337, "learning_rate": 2.833807217143193e-05, "loss": 0.367, "num_tokens": 288260550.0, "step": 48155 }, { "epoch": 0.5137998357035409, "grad_norm": 0.7861013427513222, "learning_rate": 2.8334105849799324e-05, "loss": 0.5644, "num_tokens": 288295938.0, "step": 48160 }, { "epoch": 0.5138531787097393, "grad_norm": 0.6352715931560229, "learning_rate": 2.8330139502211067e-05, "loss": 0.5671, "num_tokens": 288335292.0, "step": 48165 }, { "epoch": 0.5139065217159379, "grad_norm": 3.5176526165303437, "learning_rate": 2.8326173128790566e-05, "loss": 0.4127, "num_tokens": 288352714.0, "step": 48170 }, { "epoch": 0.5139598647221363, "grad_norm": 0.8871055028932305, "learning_rate": 2.832220672966126e-05, "loss": 0.4984, "num_tokens": 288372882.0, "step": 48175 }, { "epoch": 0.5140132077283347, "grad_norm": 0.6742431896743029, "learning_rate": 2.831824030494657e-05, "loss": 0.5478, "num_tokens": 288400873.0, "step": 48180 }, { "epoch": 0.5140665507345332, "grad_norm": 0.9532231022006811, "learning_rate": 2.831427385476992e-05, "loss": 0.501, "num_tokens": 288424735.0, "step": 48185 }, { "epoch": 0.5141198937407316, "grad_norm": 1.3086370609892672, "learning_rate": 2.831030737925473e-05, "loss": 0.4523, "num_tokens": 288441312.0, "step": 48190 }, { "epoch": 0.5141732367469302, "grad_norm": 0.9634551049959412, "learning_rate": 2.8306340878524456e-05, "loss": 0.4577, "num_tokens": 288470426.0, "step": 48195 }, { "epoch": 0.5142265797531286, "grad_norm": 0.6824472498661512, "learning_rate": 2.830237435270251e-05, "loss": 0.4687, "num_tokens": 288498085.0, "step": 48200 }, { "epoch": 0.514279922759327, "grad_norm": 0.7432666593204663, "learning_rate": 2.8298407801912308e-05, "loss": 0.582, "num_tokens": 288528357.0, "step": 48205 }, { "epoch": 0.5143332657655255, "grad_norm": 1.414906252025074, "learning_rate": 2.8294441226277303e-05, "loss": 0.5728, "num_tokens": 288552709.0, "step": 48210 }, { "epoch": 0.5143866087717239, "grad_norm": 0.6755443063632386, "learning_rate": 2.829047462592092e-05, "loss": 0.4564, "num_tokens": 288597567.0, "step": 48215 }, { "epoch": 0.5144399517779223, "grad_norm": 1.2227410383218207, "learning_rate": 2.828650800096659e-05, "loss": 0.3791, "num_tokens": 288622395.0, "step": 48220 }, { "epoch": 0.5144932947841209, "grad_norm": 0.5544219701302654, "learning_rate": 2.828254135153774e-05, "loss": 0.4148, "num_tokens": 288657640.0, "step": 48225 }, { "epoch": 0.5145466377903193, "grad_norm": 0.8765899245169018, "learning_rate": 2.827857467775782e-05, "loss": 0.5143, "num_tokens": 288671461.0, "step": 48230 }, { "epoch": 0.5145999807965178, "grad_norm": 0.9146430559928055, "learning_rate": 2.827460797975025e-05, "loss": 0.6109, "num_tokens": 288711890.0, "step": 48235 }, { "epoch": 0.5146533238027162, "grad_norm": 0.7936550787412762, "learning_rate": 2.827064125763847e-05, "loss": 0.5122, "num_tokens": 288748407.0, "step": 48240 }, { "epoch": 0.5147066668089146, "grad_norm": 1.0194676639571223, "learning_rate": 2.826667451154592e-05, "loss": 0.528, "num_tokens": 288779307.0, "step": 48245 }, { "epoch": 0.5147600098151132, "grad_norm": 1.2185116264221747, "learning_rate": 2.8262707741596033e-05, "loss": 0.4436, "num_tokens": 288796247.0, "step": 48250 }, { "epoch": 0.5148133528213116, "grad_norm": 0.9299818962522269, "learning_rate": 2.8258740947912247e-05, "loss": 0.5175, "num_tokens": 288851457.0, "step": 48255 }, { "epoch": 0.5148666958275101, "grad_norm": 2.6955990546890387, "learning_rate": 2.8254774130618005e-05, "loss": 0.557, "num_tokens": 288871108.0, "step": 48260 }, { "epoch": 0.5149200388337085, "grad_norm": 0.9652920430975742, "learning_rate": 2.8250807289836734e-05, "loss": 0.5487, "num_tokens": 288899604.0, "step": 48265 }, { "epoch": 0.5149733818399069, "grad_norm": 0.8876723177307838, "learning_rate": 2.8246840425691896e-05, "loss": 0.5778, "num_tokens": 288945875.0, "step": 48270 }, { "epoch": 0.5150267248461055, "grad_norm": 1.3766106516745202, "learning_rate": 2.8242873538306907e-05, "loss": 0.6155, "num_tokens": 288976865.0, "step": 48275 }, { "epoch": 0.5150800678523039, "grad_norm": 0.7609138998910749, "learning_rate": 2.8238906627805216e-05, "loss": 0.495, "num_tokens": 289026444.0, "step": 48280 }, { "epoch": 0.5151334108585024, "grad_norm": 0.9447063641495737, "learning_rate": 2.8234939694310274e-05, "loss": 0.6965, "num_tokens": 289070070.0, "step": 48285 }, { "epoch": 0.5151867538647008, "grad_norm": 0.8348846734220872, "learning_rate": 2.8230972737945527e-05, "loss": 0.4122, "num_tokens": 289097090.0, "step": 48290 }, { "epoch": 0.5152400968708992, "grad_norm": 2.0717178073679556, "learning_rate": 2.8227005758834398e-05, "loss": 0.4522, "num_tokens": 289120891.0, "step": 48295 }, { "epoch": 0.5152934398770977, "grad_norm": 0.6409226004192246, "learning_rate": 2.8223038757100347e-05, "loss": 0.5694, "num_tokens": 289169646.0, "step": 48300 }, { "epoch": 0.5153467828832962, "grad_norm": 0.8742824759257308, "learning_rate": 2.8219071732866814e-05, "loss": 0.3919, "num_tokens": 289186081.0, "step": 48305 }, { "epoch": 0.5154001258894946, "grad_norm": 0.865324635509632, "learning_rate": 2.8215104686257242e-05, "loss": 0.4103, "num_tokens": 289203433.0, "step": 48310 }, { "epoch": 0.5154534688956931, "grad_norm": 0.845616029205352, "learning_rate": 2.8211137617395088e-05, "loss": 0.5354, "num_tokens": 289234796.0, "step": 48315 }, { "epoch": 0.5155068119018915, "grad_norm": 1.1168709777440617, "learning_rate": 2.820717052640379e-05, "loss": 0.6095, "num_tokens": 289259239.0, "step": 48320 }, { "epoch": 0.51556015490809, "grad_norm": 0.8656578382971412, "learning_rate": 2.82032034134068e-05, "loss": 0.5376, "num_tokens": 289295526.0, "step": 48325 }, { "epoch": 0.5156134979142885, "grad_norm": 1.0114824396850834, "learning_rate": 2.8199236278527558e-05, "loss": 0.4561, "num_tokens": 289309387.0, "step": 48330 }, { "epoch": 0.5156668409204869, "grad_norm": 1.298806727159507, "learning_rate": 2.8195269121889528e-05, "loss": 0.4731, "num_tokens": 289348363.0, "step": 48335 }, { "epoch": 0.5157201839266854, "grad_norm": 0.5455520453213519, "learning_rate": 2.8191301943616145e-05, "loss": 0.4815, "num_tokens": 289394114.0, "step": 48340 }, { "epoch": 0.5157735269328838, "grad_norm": 1.5453929513204085, "learning_rate": 2.8187334743830866e-05, "loss": 0.4988, "num_tokens": 289410768.0, "step": 48345 }, { "epoch": 0.5158268699390823, "grad_norm": 1.5815722848657103, "learning_rate": 2.8183367522657145e-05, "loss": 0.5371, "num_tokens": 289442624.0, "step": 48350 }, { "epoch": 0.5158802129452807, "grad_norm": 3.0946073756778274, "learning_rate": 2.817940028021842e-05, "loss": 0.5173, "num_tokens": 289475095.0, "step": 48355 }, { "epoch": 0.5159335559514792, "grad_norm": 2.73042793955392, "learning_rate": 2.8175433016638165e-05, "loss": 0.6546, "num_tokens": 289504649.0, "step": 48360 }, { "epoch": 0.5159868989576777, "grad_norm": 0.7497495942728799, "learning_rate": 2.817146573203982e-05, "loss": 0.5476, "num_tokens": 289535745.0, "step": 48365 }, { "epoch": 0.5160402419638761, "grad_norm": 1.4306456331242619, "learning_rate": 2.8167498426546834e-05, "loss": 0.4911, "num_tokens": 289557404.0, "step": 48370 }, { "epoch": 0.5160935849700746, "grad_norm": 0.5702500322139029, "learning_rate": 2.816353110028267e-05, "loss": 0.5586, "num_tokens": 289591169.0, "step": 48375 }, { "epoch": 0.516146927976273, "grad_norm": 1.6565530572359901, "learning_rate": 2.8159563753370794e-05, "loss": 0.5306, "num_tokens": 289617956.0, "step": 48380 }, { "epoch": 0.5162002709824715, "grad_norm": 0.8340421635325734, "learning_rate": 2.8155596385934636e-05, "loss": 0.4956, "num_tokens": 289644895.0, "step": 48385 }, { "epoch": 0.51625361398867, "grad_norm": 0.6736045760011274, "learning_rate": 2.815162899809766e-05, "loss": 0.437, "num_tokens": 289671630.0, "step": 48390 }, { "epoch": 0.5163069569948684, "grad_norm": 0.9468622487622452, "learning_rate": 2.8147661589983342e-05, "loss": 0.4601, "num_tokens": 289701052.0, "step": 48395 }, { "epoch": 0.5163603000010668, "grad_norm": 0.695949403299856, "learning_rate": 2.8143694161715117e-05, "loss": 0.5063, "num_tokens": 289733835.0, "step": 48400 }, { "epoch": 0.5164136430072653, "grad_norm": 0.8003748781291006, "learning_rate": 2.8139726713416453e-05, "loss": 0.5722, "num_tokens": 289762707.0, "step": 48405 }, { "epoch": 0.5164669860134637, "grad_norm": 0.7723711439276122, "learning_rate": 2.8135759245210814e-05, "loss": 0.5202, "num_tokens": 289801224.0, "step": 48410 }, { "epoch": 0.5165203290196623, "grad_norm": 0.7903534853113943, "learning_rate": 2.8131791757221643e-05, "loss": 0.6176, "num_tokens": 289834126.0, "step": 48415 }, { "epoch": 0.5165736720258607, "grad_norm": 0.7645940479951202, "learning_rate": 2.812782424957242e-05, "loss": 0.4509, "num_tokens": 289857043.0, "step": 48420 }, { "epoch": 0.5166270150320591, "grad_norm": 0.894227981727787, "learning_rate": 2.8123856722386587e-05, "loss": 0.5377, "num_tokens": 289887830.0, "step": 48425 }, { "epoch": 0.5166803580382576, "grad_norm": 1.2786817771582282, "learning_rate": 2.8119889175787615e-05, "loss": 0.4977, "num_tokens": 289914170.0, "step": 48430 }, { "epoch": 0.516733701044456, "grad_norm": 1.0040221806738023, "learning_rate": 2.8115921609898976e-05, "loss": 0.4671, "num_tokens": 289939932.0, "step": 48435 }, { "epoch": 0.5167870440506546, "grad_norm": 1.7998804934469652, "learning_rate": 2.811195402484412e-05, "loss": 0.4739, "num_tokens": 289965186.0, "step": 48440 }, { "epoch": 0.516840387056853, "grad_norm": 0.8182010108709245, "learning_rate": 2.8107986420746497e-05, "loss": 0.3902, "num_tokens": 289984550.0, "step": 48445 }, { "epoch": 0.5168937300630514, "grad_norm": 1.0457120342302095, "learning_rate": 2.81040187977296e-05, "loss": 0.439, "num_tokens": 290011552.0, "step": 48450 }, { "epoch": 0.5169470730692499, "grad_norm": 1.3423968930778647, "learning_rate": 2.8100051155916873e-05, "loss": 0.4859, "num_tokens": 290034357.0, "step": 48455 }, { "epoch": 0.5170004160754483, "grad_norm": 1.1338754293878224, "learning_rate": 2.8096083495431784e-05, "loss": 0.5413, "num_tokens": 290072500.0, "step": 48460 }, { "epoch": 0.5170537590816469, "grad_norm": 0.7793962245765723, "learning_rate": 2.80921158163978e-05, "loss": 0.442, "num_tokens": 290093352.0, "step": 48465 }, { "epoch": 0.5171071020878453, "grad_norm": 0.6885184023482339, "learning_rate": 2.8088148118938396e-05, "loss": 0.495, "num_tokens": 290124685.0, "step": 48470 }, { "epoch": 0.5171604450940437, "grad_norm": 1.031359629633746, "learning_rate": 2.8084180403177024e-05, "loss": 0.5071, "num_tokens": 290162783.0, "step": 48475 }, { "epoch": 0.5172137881002422, "grad_norm": 0.8692394224659404, "learning_rate": 2.808021266923716e-05, "loss": 0.5963, "num_tokens": 290188857.0, "step": 48480 }, { "epoch": 0.5172671311064406, "grad_norm": 1.1260947486038135, "learning_rate": 2.8076244917242273e-05, "loss": 0.5812, "num_tokens": 290222105.0, "step": 48485 }, { "epoch": 0.517320474112639, "grad_norm": 0.9680606120801999, "learning_rate": 2.8072277147315824e-05, "loss": 0.4915, "num_tokens": 290240491.0, "step": 48490 }, { "epoch": 0.5173738171188376, "grad_norm": 0.8505171123138792, "learning_rate": 2.806830935958129e-05, "loss": 0.4467, "num_tokens": 290273916.0, "step": 48495 }, { "epoch": 0.517427160125036, "grad_norm": 0.8452154313326691, "learning_rate": 2.8064341554162128e-05, "loss": 0.6298, "num_tokens": 290306080.0, "step": 48500 }, { "epoch": 0.5174805031312345, "grad_norm": 1.010359977670384, "learning_rate": 2.806037373118182e-05, "loss": 0.4283, "num_tokens": 290334202.0, "step": 48505 }, { "epoch": 0.5175338461374329, "grad_norm": 1.8692883204958075, "learning_rate": 2.8056405890763837e-05, "loss": 0.5468, "num_tokens": 290347367.0, "step": 48510 }, { "epoch": 0.5175871891436313, "grad_norm": 1.484647811686891, "learning_rate": 2.8052438033031635e-05, "loss": 0.4083, "num_tokens": 290373601.0, "step": 48515 }, { "epoch": 0.5176405321498299, "grad_norm": 1.7778006094059084, "learning_rate": 2.8048470158108704e-05, "loss": 0.5931, "num_tokens": 290394666.0, "step": 48520 }, { "epoch": 0.5176938751560283, "grad_norm": 1.6890353225427266, "learning_rate": 2.8044502266118512e-05, "loss": 0.6338, "num_tokens": 290406777.0, "step": 48525 }, { "epoch": 0.5177472181622268, "grad_norm": 0.8988215084960384, "learning_rate": 2.8040534357184517e-05, "loss": 0.4536, "num_tokens": 290432637.0, "step": 48530 }, { "epoch": 0.5178005611684252, "grad_norm": 0.7453213485254002, "learning_rate": 2.803656643143021e-05, "loss": 0.6942, "num_tokens": 290473829.0, "step": 48535 }, { "epoch": 0.5178539041746236, "grad_norm": 0.9517365749733597, "learning_rate": 2.8032598488979057e-05, "loss": 0.7355, "num_tokens": 290502449.0, "step": 48540 }, { "epoch": 0.5179072471808222, "grad_norm": 0.7088501134331913, "learning_rate": 2.802863052995453e-05, "loss": 0.4799, "num_tokens": 290545532.0, "step": 48545 }, { "epoch": 0.5179605901870206, "grad_norm": 1.1431091523093526, "learning_rate": 2.8024662554480113e-05, "loss": 0.4362, "num_tokens": 290563662.0, "step": 48550 }, { "epoch": 0.5180139331932191, "grad_norm": 0.7030602490812585, "learning_rate": 2.8020694562679272e-05, "loss": 0.4832, "num_tokens": 290580983.0, "step": 48555 }, { "epoch": 0.5180672761994175, "grad_norm": 1.322227797395396, "learning_rate": 2.8016726554675484e-05, "loss": 0.5561, "num_tokens": 290606582.0, "step": 48560 }, { "epoch": 0.5181206192056159, "grad_norm": 1.4800480119890078, "learning_rate": 2.8012758530592232e-05, "loss": 0.5396, "num_tokens": 290639839.0, "step": 48565 }, { "epoch": 0.5181739622118144, "grad_norm": 1.297708356661063, "learning_rate": 2.8008790490552983e-05, "loss": 0.5339, "num_tokens": 290654406.0, "step": 48570 }, { "epoch": 0.5182273052180129, "grad_norm": 0.8728691957992861, "learning_rate": 2.8004822434681215e-05, "loss": 0.5375, "num_tokens": 290696060.0, "step": 48575 }, { "epoch": 0.5182806482242113, "grad_norm": 0.8459348568949615, "learning_rate": 2.800085436310042e-05, "loss": 0.5058, "num_tokens": 290714526.0, "step": 48580 }, { "epoch": 0.5183339912304098, "grad_norm": 1.0421377798982776, "learning_rate": 2.799688627593406e-05, "loss": 0.4519, "num_tokens": 290739905.0, "step": 48585 }, { "epoch": 0.5183873342366082, "grad_norm": 1.2777659882069712, "learning_rate": 2.7992918173305614e-05, "loss": 0.4897, "num_tokens": 290767735.0, "step": 48590 }, { "epoch": 0.5184406772428067, "grad_norm": 0.8253640211194571, "learning_rate": 2.7988950055338576e-05, "loss": 0.5028, "num_tokens": 290790235.0, "step": 48595 }, { "epoch": 0.5184940202490051, "grad_norm": 0.8058480829006816, "learning_rate": 2.7984981922156423e-05, "loss": 0.5697, "num_tokens": 290821903.0, "step": 48600 }, { "epoch": 0.5185473632552036, "grad_norm": 0.8102753303019808, "learning_rate": 2.7981013773882607e-05, "loss": 0.4414, "num_tokens": 290847209.0, "step": 48605 }, { "epoch": 0.5186007062614021, "grad_norm": 1.5308626371756389, "learning_rate": 2.797704561064065e-05, "loss": 0.6151, "num_tokens": 290866869.0, "step": 48610 }, { "epoch": 0.5186540492676005, "grad_norm": 0.8407080278348076, "learning_rate": 2.7973077432554005e-05, "loss": 0.5671, "num_tokens": 290899094.0, "step": 48615 }, { "epoch": 0.518707392273799, "grad_norm": 0.8403155292223952, "learning_rate": 2.7969109239746165e-05, "loss": 0.4777, "num_tokens": 290934889.0, "step": 48620 }, { "epoch": 0.5187607352799974, "grad_norm": 2.3413874390006026, "learning_rate": 2.796514103234061e-05, "loss": 0.5523, "num_tokens": 290963125.0, "step": 48625 }, { "epoch": 0.5188140782861959, "grad_norm": 3.2210356771969524, "learning_rate": 2.796117281046082e-05, "loss": 0.7176, "num_tokens": 290993233.0, "step": 48630 }, { "epoch": 0.5188674212923944, "grad_norm": 0.9318974714358934, "learning_rate": 2.7957204574230274e-05, "loss": 0.4803, "num_tokens": 291024783.0, "step": 48635 }, { "epoch": 0.5189207642985928, "grad_norm": 0.805136756492032, "learning_rate": 2.795323632377247e-05, "loss": 0.4787, "num_tokens": 291057738.0, "step": 48640 }, { "epoch": 0.5189741073047913, "grad_norm": 1.7099080771435506, "learning_rate": 2.7949268059210875e-05, "loss": 0.6164, "num_tokens": 291084856.0, "step": 48645 }, { "epoch": 0.5190274503109897, "grad_norm": 0.8956022771663301, "learning_rate": 2.7945299780668982e-05, "loss": 0.5673, "num_tokens": 291107962.0, "step": 48650 }, { "epoch": 0.5190807933171881, "grad_norm": 0.9562865506547812, "learning_rate": 2.7941331488270283e-05, "loss": 0.5644, "num_tokens": 291129928.0, "step": 48655 }, { "epoch": 0.5191341363233867, "grad_norm": 0.8647369125306307, "learning_rate": 2.7937363182138243e-05, "loss": 0.6164, "num_tokens": 291163611.0, "step": 48660 }, { "epoch": 0.5191874793295851, "grad_norm": 1.4976557044730825, "learning_rate": 2.7933394862396363e-05, "loss": 0.4617, "num_tokens": 291187565.0, "step": 48665 }, { "epoch": 0.5192408223357835, "grad_norm": 1.3473823070362407, "learning_rate": 2.7929426529168128e-05, "loss": 0.6732, "num_tokens": 291213804.0, "step": 48670 }, { "epoch": 0.519294165341982, "grad_norm": 0.890306412373468, "learning_rate": 2.7925458182577024e-05, "loss": 0.6121, "num_tokens": 291247624.0, "step": 48675 }, { "epoch": 0.5193475083481804, "grad_norm": 0.7447076287793358, "learning_rate": 2.7921489822746527e-05, "loss": 0.5032, "num_tokens": 291274164.0, "step": 48680 }, { "epoch": 0.519400851354379, "grad_norm": 0.8620215334825113, "learning_rate": 2.791752144980014e-05, "loss": 0.4974, "num_tokens": 291304902.0, "step": 48685 }, { "epoch": 0.5194541943605774, "grad_norm": 1.2164850393405762, "learning_rate": 2.7913553063861335e-05, "loss": 0.6628, "num_tokens": 291344207.0, "step": 48690 }, { "epoch": 0.5195075373667758, "grad_norm": 0.7904210519063122, "learning_rate": 2.790958466505361e-05, "loss": 0.4644, "num_tokens": 291381124.0, "step": 48695 }, { "epoch": 0.5195608803729743, "grad_norm": 1.0981226378282138, "learning_rate": 2.7905616253500454e-05, "loss": 0.5147, "num_tokens": 291402465.0, "step": 48700 }, { "epoch": 0.5196142233791727, "grad_norm": 1.7711776219338005, "learning_rate": 2.7901647829325357e-05, "loss": 0.6427, "num_tokens": 291427237.0, "step": 48705 }, { "epoch": 0.5196675663853713, "grad_norm": 1.3174604820539106, "learning_rate": 2.7897679392651804e-05, "loss": 0.4557, "num_tokens": 291446838.0, "step": 48710 }, { "epoch": 0.5197209093915697, "grad_norm": 0.8039687662242714, "learning_rate": 2.789371094360328e-05, "loss": 0.4938, "num_tokens": 291472933.0, "step": 48715 }, { "epoch": 0.5197742523977681, "grad_norm": 0.71409182740777, "learning_rate": 2.7889742482303284e-05, "loss": 0.707, "num_tokens": 291515165.0, "step": 48720 }, { "epoch": 0.5198275954039666, "grad_norm": 0.7428374559518316, "learning_rate": 2.7885774008875298e-05, "loss": 0.5442, "num_tokens": 291541293.0, "step": 48725 }, { "epoch": 0.519880938410165, "grad_norm": 0.665237492144368, "learning_rate": 2.7881805523442822e-05, "loss": 0.4354, "num_tokens": 291566606.0, "step": 48730 }, { "epoch": 0.5199342814163636, "grad_norm": 0.8188982642850527, "learning_rate": 2.7877837026129344e-05, "loss": 0.549, "num_tokens": 291584749.0, "step": 48735 }, { "epoch": 0.519987624422562, "grad_norm": 0.6680656517431053, "learning_rate": 2.7873868517058337e-05, "loss": 0.7177, "num_tokens": 291627607.0, "step": 48740 }, { "epoch": 0.5200409674287604, "grad_norm": 0.92766704883682, "learning_rate": 2.7869899996353332e-05, "loss": 0.545, "num_tokens": 291660259.0, "step": 48745 }, { "epoch": 0.5200943104349589, "grad_norm": 1.1741012578622594, "learning_rate": 2.786593146413779e-05, "loss": 0.511, "num_tokens": 291696038.0, "step": 48750 }, { "epoch": 0.5201476534411573, "grad_norm": 0.8266789053652407, "learning_rate": 2.7861962920535205e-05, "loss": 0.6077, "num_tokens": 291741943.0, "step": 48755 }, { "epoch": 0.5202009964473557, "grad_norm": 1.3864133755027928, "learning_rate": 2.7857994365669087e-05, "loss": 0.5543, "num_tokens": 291783265.0, "step": 48760 }, { "epoch": 0.5202543394535543, "grad_norm": 0.7536444098241156, "learning_rate": 2.7854025799662924e-05, "loss": 0.5594, "num_tokens": 291804587.0, "step": 48765 }, { "epoch": 0.5203076824597527, "grad_norm": 1.3356182242988, "learning_rate": 2.785005722264019e-05, "loss": 0.5201, "num_tokens": 291841327.0, "step": 48770 }, { "epoch": 0.5203610254659512, "grad_norm": 1.2612460525116256, "learning_rate": 2.784608863472441e-05, "loss": 0.5666, "num_tokens": 291878128.0, "step": 48775 }, { "epoch": 0.5204143684721496, "grad_norm": 0.9692010989492539, "learning_rate": 2.784212003603906e-05, "loss": 0.5612, "num_tokens": 291906609.0, "step": 48780 }, { "epoch": 0.520467711478348, "grad_norm": 1.505130909747436, "learning_rate": 2.7838151426707626e-05, "loss": 0.4411, "num_tokens": 291944681.0, "step": 48785 }, { "epoch": 0.5205210544845466, "grad_norm": 0.697155371689273, "learning_rate": 2.783418280685362e-05, "loss": 0.5587, "num_tokens": 291982988.0, "step": 48790 }, { "epoch": 0.520574397490745, "grad_norm": 1.5564174686897985, "learning_rate": 2.7830214176600533e-05, "loss": 0.5167, "num_tokens": 292007037.0, "step": 48795 }, { "epoch": 0.5206277404969435, "grad_norm": 1.0350137780011557, "learning_rate": 2.7826245536071866e-05, "loss": 0.5543, "num_tokens": 292041941.0, "step": 48800 }, { "epoch": 0.5206810835031419, "grad_norm": 1.1734349587682182, "learning_rate": 2.7822276885391096e-05, "loss": 0.4973, "num_tokens": 292057931.0, "step": 48805 }, { "epoch": 0.5207344265093403, "grad_norm": 2.462811636658214, "learning_rate": 2.781830822468174e-05, "loss": 0.5465, "num_tokens": 292085390.0, "step": 48810 }, { "epoch": 0.5207877695155388, "grad_norm": 0.9684180873020743, "learning_rate": 2.7814339554067282e-05, "loss": 0.4351, "num_tokens": 292117587.0, "step": 48815 }, { "epoch": 0.5208411125217373, "grad_norm": 0.7971404167334567, "learning_rate": 2.781037087367122e-05, "loss": 0.5374, "num_tokens": 292150411.0, "step": 48820 }, { "epoch": 0.5208944555279358, "grad_norm": 0.6504158009775798, "learning_rate": 2.780640218361706e-05, "loss": 0.5669, "num_tokens": 292198268.0, "step": 48825 }, { "epoch": 0.5209477985341342, "grad_norm": 0.7110010624055912, "learning_rate": 2.7802433484028284e-05, "loss": 0.4718, "num_tokens": 292221530.0, "step": 48830 }, { "epoch": 0.5210011415403326, "grad_norm": 0.7586372085185681, "learning_rate": 2.779846477502841e-05, "loss": 0.5413, "num_tokens": 292245419.0, "step": 48835 }, { "epoch": 0.5210544845465311, "grad_norm": 0.8695440047353702, "learning_rate": 2.779449605674092e-05, "loss": 0.4843, "num_tokens": 292270044.0, "step": 48840 }, { "epoch": 0.5211078275527296, "grad_norm": 0.6486345398951799, "learning_rate": 2.779052732928931e-05, "loss": 0.5008, "num_tokens": 292296982.0, "step": 48845 }, { "epoch": 0.521161170558928, "grad_norm": 1.1172996313540349, "learning_rate": 2.77865585927971e-05, "loss": 0.4124, "num_tokens": 292321928.0, "step": 48850 }, { "epoch": 0.5212145135651265, "grad_norm": 1.1892908773679398, "learning_rate": 2.7782589847387773e-05, "loss": 0.5916, "num_tokens": 292360616.0, "step": 48855 }, { "epoch": 0.5212678565713249, "grad_norm": 1.317564643098439, "learning_rate": 2.777862109318482e-05, "loss": 0.5146, "num_tokens": 292394183.0, "step": 48860 }, { "epoch": 0.5213211995775234, "grad_norm": 0.5802284806889618, "learning_rate": 2.7774652330311762e-05, "loss": 0.6367, "num_tokens": 292463934.0, "step": 48865 }, { "epoch": 0.5213745425837218, "grad_norm": 0.7635083310989023, "learning_rate": 2.777068355889208e-05, "loss": 0.3816, "num_tokens": 292486578.0, "step": 48870 }, { "epoch": 0.5214278855899203, "grad_norm": 4.071113128158745, "learning_rate": 2.7766714779049285e-05, "loss": 0.5461, "num_tokens": 292507269.0, "step": 48875 }, { "epoch": 0.5214812285961188, "grad_norm": 0.9794493052762907, "learning_rate": 2.776274599090688e-05, "loss": 0.5539, "num_tokens": 292527658.0, "step": 48880 }, { "epoch": 0.5215345716023172, "grad_norm": 0.657618056228052, "learning_rate": 2.7758777194588347e-05, "loss": 0.4461, "num_tokens": 292554213.0, "step": 48885 }, { "epoch": 0.5215879146085157, "grad_norm": 1.1197217409774989, "learning_rate": 2.775480839021721e-05, "loss": 0.5956, "num_tokens": 292595253.0, "step": 48890 }, { "epoch": 0.5216412576147141, "grad_norm": 0.8340362292823424, "learning_rate": 2.7750839577916955e-05, "loss": 0.4478, "num_tokens": 292626631.0, "step": 48895 }, { "epoch": 0.5216946006209126, "grad_norm": 0.6493967313591833, "learning_rate": 2.7746870757811082e-05, "loss": 0.3865, "num_tokens": 292650031.0, "step": 48900 }, { "epoch": 0.5217479436271111, "grad_norm": 1.190002724810478, "learning_rate": 2.774290193002311e-05, "loss": 0.594, "num_tokens": 292670138.0, "step": 48905 }, { "epoch": 0.5218012866333095, "grad_norm": 1.0708614471523714, "learning_rate": 2.773893309467652e-05, "loss": 0.451, "num_tokens": 292689376.0, "step": 48910 }, { "epoch": 0.521854629639508, "grad_norm": 0.6869922158374396, "learning_rate": 2.7734964251894828e-05, "loss": 0.6422, "num_tokens": 292730834.0, "step": 48915 }, { "epoch": 0.5219079726457064, "grad_norm": 0.7754347341019449, "learning_rate": 2.7730995401801523e-05, "loss": 0.476, "num_tokens": 292749731.0, "step": 48920 }, { "epoch": 0.5219613156519048, "grad_norm": 0.8314626839414219, "learning_rate": 2.772702654452013e-05, "loss": 0.6194, "num_tokens": 292806596.0, "step": 48925 }, { "epoch": 0.5220146586581034, "grad_norm": 0.5460510120494416, "learning_rate": 2.7723057680174126e-05, "loss": 0.4734, "num_tokens": 292842487.0, "step": 48930 }, { "epoch": 0.5220680016643018, "grad_norm": 0.8095295831178996, "learning_rate": 2.7719088808887023e-05, "loss": 0.5685, "num_tokens": 292871548.0, "step": 48935 }, { "epoch": 0.5221213446705002, "grad_norm": 0.8718152264822553, "learning_rate": 2.771511993078233e-05, "loss": 0.4835, "num_tokens": 292902201.0, "step": 48940 }, { "epoch": 0.5221746876766987, "grad_norm": 0.8729548913179601, "learning_rate": 2.7711151045983558e-05, "loss": 0.4177, "num_tokens": 292922919.0, "step": 48945 }, { "epoch": 0.5222280306828971, "grad_norm": 0.949161305194524, "learning_rate": 2.770718215461418e-05, "loss": 0.4892, "num_tokens": 292963758.0, "step": 48950 }, { "epoch": 0.5222813736890957, "grad_norm": 1.1987591661659793, "learning_rate": 2.7703213256797728e-05, "loss": 0.5143, "num_tokens": 292992648.0, "step": 48955 }, { "epoch": 0.5223347166952941, "grad_norm": 0.9626977508480974, "learning_rate": 2.7699244352657693e-05, "loss": 0.5483, "num_tokens": 293034663.0, "step": 48960 }, { "epoch": 0.5223880597014925, "grad_norm": 1.060125927697671, "learning_rate": 2.7695275442317594e-05, "loss": 0.502, "num_tokens": 293071675.0, "step": 48965 }, { "epoch": 0.522441402707691, "grad_norm": 1.1737774628986974, "learning_rate": 2.769130652590091e-05, "loss": 0.4992, "num_tokens": 293087939.0, "step": 48970 }, { "epoch": 0.5224947457138894, "grad_norm": 0.9681014905169805, "learning_rate": 2.768733760353117e-05, "loss": 0.5505, "num_tokens": 293125302.0, "step": 48975 }, { "epoch": 0.522548088720088, "grad_norm": 1.207114348313601, "learning_rate": 2.7683368675331867e-05, "loss": 0.4947, "num_tokens": 293141623.0, "step": 48980 }, { "epoch": 0.5226014317262864, "grad_norm": 1.1736653108561972, "learning_rate": 2.7679399741426504e-05, "loss": 0.611, "num_tokens": 293175955.0, "step": 48985 }, { "epoch": 0.5226547747324848, "grad_norm": 1.9015228351975533, "learning_rate": 2.7675430801938585e-05, "loss": 0.6592, "num_tokens": 293197391.0, "step": 48990 }, { "epoch": 0.5227081177386833, "grad_norm": 0.6791821954591705, "learning_rate": 2.7671461856991633e-05, "loss": 0.5259, "num_tokens": 293232007.0, "step": 48995 }, { "epoch": 0.5227614607448817, "grad_norm": 1.0460656855697514, "learning_rate": 2.7667492906709136e-05, "loss": 0.4843, "num_tokens": 293251717.0, "step": 49000 }, { "epoch": 0.5228148037510802, "grad_norm": 0.8101942006756866, "learning_rate": 2.7663523951214598e-05, "loss": 0.5507, "num_tokens": 293297754.0, "step": 49005 }, { "epoch": 0.5228681467572787, "grad_norm": 0.9588955098769245, "learning_rate": 2.765955499063153e-05, "loss": 0.5191, "num_tokens": 293333561.0, "step": 49010 }, { "epoch": 0.5229214897634771, "grad_norm": 1.1795527995084147, "learning_rate": 2.7655586025083442e-05, "loss": 0.6287, "num_tokens": 293370622.0, "step": 49015 }, { "epoch": 0.5229748327696756, "grad_norm": 1.1519656550283945, "learning_rate": 2.765161705469384e-05, "loss": 0.6135, "num_tokens": 293401398.0, "step": 49020 }, { "epoch": 0.523028175775874, "grad_norm": 0.9314909972789922, "learning_rate": 2.7647648079586224e-05, "loss": 0.4681, "num_tokens": 293417429.0, "step": 49025 }, { "epoch": 0.5230815187820724, "grad_norm": 0.7582156796673963, "learning_rate": 2.76436790998841e-05, "loss": 0.5334, "num_tokens": 293452705.0, "step": 49030 }, { "epoch": 0.523134861788271, "grad_norm": 0.7572902622723066, "learning_rate": 2.7639710115710975e-05, "loss": 0.4479, "num_tokens": 293485820.0, "step": 49035 }, { "epoch": 0.5231882047944694, "grad_norm": 0.9447999276035786, "learning_rate": 2.7635741127190368e-05, "loss": 0.4731, "num_tokens": 293503591.0, "step": 49040 }, { "epoch": 0.5232415478006679, "grad_norm": 0.6395995892309427, "learning_rate": 2.763177213444577e-05, "loss": 0.4541, "num_tokens": 293534585.0, "step": 49045 }, { "epoch": 0.5232948908068663, "grad_norm": 1.339861319962377, "learning_rate": 2.762780313760069e-05, "loss": 0.4336, "num_tokens": 293551509.0, "step": 49050 }, { "epoch": 0.5233482338130647, "grad_norm": 1.0071299251452013, "learning_rate": 2.7623834136778648e-05, "loss": 0.4431, "num_tokens": 293566783.0, "step": 49055 }, { "epoch": 0.5234015768192632, "grad_norm": 0.8843201679731734, "learning_rate": 2.761986513210314e-05, "loss": 0.3959, "num_tokens": 293582553.0, "step": 49060 }, { "epoch": 0.5234549198254617, "grad_norm": 1.478296895780196, "learning_rate": 2.7615896123697666e-05, "loss": 0.5151, "num_tokens": 293607340.0, "step": 49065 }, { "epoch": 0.5235082628316602, "grad_norm": 0.7614456782092833, "learning_rate": 2.7611927111685752e-05, "loss": 0.602, "num_tokens": 293638380.0, "step": 49070 }, { "epoch": 0.5235616058378586, "grad_norm": 0.8116542628003587, "learning_rate": 2.76079580961909e-05, "loss": 0.5886, "num_tokens": 293669350.0, "step": 49075 }, { "epoch": 0.523614948844057, "grad_norm": 0.898538856313361, "learning_rate": 2.76039890773366e-05, "loss": 0.6038, "num_tokens": 293706566.0, "step": 49080 }, { "epoch": 0.5236682918502555, "grad_norm": 0.8308515829661858, "learning_rate": 2.7600020055246384e-05, "loss": 0.5853, "num_tokens": 293723346.0, "step": 49085 }, { "epoch": 0.523721634856454, "grad_norm": 1.687546087773076, "learning_rate": 2.759605103004375e-05, "loss": 0.5495, "num_tokens": 293742684.0, "step": 49090 }, { "epoch": 0.5237749778626525, "grad_norm": 0.8887546364268748, "learning_rate": 2.7592082001852197e-05, "loss": 0.5225, "num_tokens": 293765119.0, "step": 49095 }, { "epoch": 0.5238283208688509, "grad_norm": 1.0876748238472218, "learning_rate": 2.758811297079525e-05, "loss": 0.535, "num_tokens": 293797832.0, "step": 49100 }, { "epoch": 0.5238816638750493, "grad_norm": 0.8251817913462128, "learning_rate": 2.7584143936996398e-05, "loss": 0.4447, "num_tokens": 293828846.0, "step": 49105 }, { "epoch": 0.5239350068812478, "grad_norm": 0.9360522553979441, "learning_rate": 2.7580174900579165e-05, "loss": 0.4988, "num_tokens": 293859723.0, "step": 49110 }, { "epoch": 0.5239883498874462, "grad_norm": 1.0593872611001498, "learning_rate": 2.757620586166706e-05, "loss": 0.414, "num_tokens": 293880830.0, "step": 49115 }, { "epoch": 0.5240416928936447, "grad_norm": 1.101211247558833, "learning_rate": 2.7572236820383578e-05, "loss": 0.6088, "num_tokens": 293908762.0, "step": 49120 }, { "epoch": 0.5240950358998432, "grad_norm": 0.7499727577824626, "learning_rate": 2.7568267776852237e-05, "loss": 0.4103, "num_tokens": 293933433.0, "step": 49125 }, { "epoch": 0.5241483789060416, "grad_norm": 0.6193557918714709, "learning_rate": 2.756429873119654e-05, "loss": 0.4921, "num_tokens": 293965398.0, "step": 49130 }, { "epoch": 0.5242017219122401, "grad_norm": 0.9352471107971757, "learning_rate": 2.7560329683540003e-05, "loss": 0.5088, "num_tokens": 293996137.0, "step": 49135 }, { "epoch": 0.5242550649184385, "grad_norm": 0.7248926313680384, "learning_rate": 2.7556360634006123e-05, "loss": 0.5165, "num_tokens": 294050419.0, "step": 49140 }, { "epoch": 0.524308407924637, "grad_norm": 0.7183316555165106, "learning_rate": 2.7552391582718423e-05, "loss": 0.6854, "num_tokens": 294088247.0, "step": 49145 }, { "epoch": 0.5243617509308355, "grad_norm": 0.8514540853673541, "learning_rate": 2.7548422529800405e-05, "loss": 0.6315, "num_tokens": 294116401.0, "step": 49150 }, { "epoch": 0.5244150939370339, "grad_norm": 0.7669692422017542, "learning_rate": 2.754445347537557e-05, "loss": 0.5369, "num_tokens": 294141378.0, "step": 49155 }, { "epoch": 0.5244684369432324, "grad_norm": 1.1780721811596102, "learning_rate": 2.7540484419567434e-05, "loss": 0.5266, "num_tokens": 294169600.0, "step": 49160 }, { "epoch": 0.5245217799494308, "grad_norm": 0.8967775886782983, "learning_rate": 2.7536515362499528e-05, "loss": 0.4914, "num_tokens": 294201325.0, "step": 49165 }, { "epoch": 0.5245751229556292, "grad_norm": 0.7247452280356396, "learning_rate": 2.753254630429531e-05, "loss": 0.4771, "num_tokens": 294245964.0, "step": 49170 }, { "epoch": 0.5246284659618278, "grad_norm": 0.6909859731964633, "learning_rate": 2.7528577245078334e-05, "loss": 0.5408, "num_tokens": 294276116.0, "step": 49175 }, { "epoch": 0.5246818089680262, "grad_norm": 0.643838993793595, "learning_rate": 2.7524608184972083e-05, "loss": 0.4659, "num_tokens": 294300850.0, "step": 49180 }, { "epoch": 0.5247351519742247, "grad_norm": 0.8333287272622418, "learning_rate": 2.7520639124100083e-05, "loss": 0.438, "num_tokens": 294333430.0, "step": 49185 }, { "epoch": 0.5247884949804231, "grad_norm": 0.9460410220424588, "learning_rate": 2.7516670062585836e-05, "loss": 0.5461, "num_tokens": 294363627.0, "step": 49190 }, { "epoch": 0.5248418379866215, "grad_norm": 1.1078010852603737, "learning_rate": 2.751270100055285e-05, "loss": 0.5418, "num_tokens": 294396008.0, "step": 49195 }, { "epoch": 0.5248951809928201, "grad_norm": 1.0585402495944063, "learning_rate": 2.7508731938124633e-05, "loss": 0.4867, "num_tokens": 294414550.0, "step": 49200 }, { "epoch": 0.5249485239990185, "grad_norm": 0.7167210704222485, "learning_rate": 2.7504762875424693e-05, "loss": 0.5173, "num_tokens": 294444980.0, "step": 49205 }, { "epoch": 0.5250018670052169, "grad_norm": 0.8184659713572247, "learning_rate": 2.750079381257655e-05, "loss": 0.5035, "num_tokens": 294468092.0, "step": 49210 }, { "epoch": 0.5250552100114154, "grad_norm": 1.0302755489753541, "learning_rate": 2.7496824749703705e-05, "loss": 0.6142, "num_tokens": 294523904.0, "step": 49215 }, { "epoch": 0.5251085530176138, "grad_norm": 2.0100901737184005, "learning_rate": 2.749285568692966e-05, "loss": 0.6794, "num_tokens": 294547206.0, "step": 49220 }, { "epoch": 0.5251618960238124, "grad_norm": 1.987471232168037, "learning_rate": 2.748888662437793e-05, "loss": 0.4723, "num_tokens": 294571514.0, "step": 49225 }, { "epoch": 0.5252152390300108, "grad_norm": 0.9127354449761873, "learning_rate": 2.7484917562172035e-05, "loss": 0.6145, "num_tokens": 294595796.0, "step": 49230 }, { "epoch": 0.5252685820362092, "grad_norm": 0.924910492085543, "learning_rate": 2.7480948500435472e-05, "loss": 0.4924, "num_tokens": 294623536.0, "step": 49235 }, { "epoch": 0.5253219250424077, "grad_norm": 0.7434145799053989, "learning_rate": 2.7476979439291745e-05, "loss": 0.472, "num_tokens": 294662250.0, "step": 49240 }, { "epoch": 0.5253752680486061, "grad_norm": 0.7045551282709136, "learning_rate": 2.7473010378864376e-05, "loss": 0.4723, "num_tokens": 294693846.0, "step": 49245 }, { "epoch": 0.5254286110548047, "grad_norm": 1.7716661116922254, "learning_rate": 2.746904131927687e-05, "loss": 0.4904, "num_tokens": 294721626.0, "step": 49250 }, { "epoch": 0.5254819540610031, "grad_norm": 2.691582130908759, "learning_rate": 2.746507226065273e-05, "loss": 0.5464, "num_tokens": 294745029.0, "step": 49255 }, { "epoch": 0.5255352970672015, "grad_norm": 0.7303493388674128, "learning_rate": 2.746110320311548e-05, "loss": 0.4539, "num_tokens": 294768674.0, "step": 49260 }, { "epoch": 0.5255886400734, "grad_norm": 0.9442196924754253, "learning_rate": 2.7457134146788606e-05, "loss": 0.5713, "num_tokens": 294791161.0, "step": 49265 }, { "epoch": 0.5256419830795984, "grad_norm": 0.917763030025058, "learning_rate": 2.7453165091795635e-05, "loss": 0.4703, "num_tokens": 294822140.0, "step": 49270 }, { "epoch": 0.5256953260857969, "grad_norm": 1.071615408861719, "learning_rate": 2.744919603826008e-05, "loss": 0.4532, "num_tokens": 294840860.0, "step": 49275 }, { "epoch": 0.5257486690919954, "grad_norm": 1.4518678540470962, "learning_rate": 2.7445226986305415e-05, "loss": 0.7056, "num_tokens": 294881963.0, "step": 49280 }, { "epoch": 0.5258020120981938, "grad_norm": 0.9098750035850323, "learning_rate": 2.744125793605519e-05, "loss": 0.5216, "num_tokens": 294918930.0, "step": 49285 }, { "epoch": 0.5258553551043923, "grad_norm": 1.1841999168678146, "learning_rate": 2.7437288887632896e-05, "loss": 0.4571, "num_tokens": 294940767.0, "step": 49290 }, { "epoch": 0.5259086981105907, "grad_norm": 0.6315067974476152, "learning_rate": 2.7433319841162046e-05, "loss": 0.7665, "num_tokens": 294991946.0, "step": 49295 }, { "epoch": 0.5259620411167891, "grad_norm": 1.1706777825810306, "learning_rate": 2.7429350796766135e-05, "loss": 0.665, "num_tokens": 295025130.0, "step": 49300 }, { "epoch": 0.5260153841229877, "grad_norm": 0.6798925942899503, "learning_rate": 2.7425381754568698e-05, "loss": 0.4008, "num_tokens": 295054448.0, "step": 49305 }, { "epoch": 0.5260687271291861, "grad_norm": 0.9335913669364571, "learning_rate": 2.742141271469322e-05, "loss": 0.5503, "num_tokens": 295085169.0, "step": 49310 }, { "epoch": 0.5261220701353846, "grad_norm": 2.0015114675782795, "learning_rate": 2.7417443677263205e-05, "loss": 0.4942, "num_tokens": 295110259.0, "step": 49315 }, { "epoch": 0.526175413141583, "grad_norm": 0.8980483923049175, "learning_rate": 2.741347464240219e-05, "loss": 0.6686, "num_tokens": 295169264.0, "step": 49320 }, { "epoch": 0.5262287561477814, "grad_norm": 0.90715077482718, "learning_rate": 2.7409505610233655e-05, "loss": 0.4548, "num_tokens": 295197148.0, "step": 49325 }, { "epoch": 0.5262820991539799, "grad_norm": 1.0848213036592746, "learning_rate": 2.7405536580881123e-05, "loss": 0.5045, "num_tokens": 295217633.0, "step": 49330 }, { "epoch": 0.5263354421601784, "grad_norm": 0.8147428249864924, "learning_rate": 2.740156755446811e-05, "loss": 0.4877, "num_tokens": 295238894.0, "step": 49335 }, { "epoch": 0.5263887851663769, "grad_norm": 0.760403982244185, "learning_rate": 2.7397598531118096e-05, "loss": 0.5454, "num_tokens": 295266336.0, "step": 49340 }, { "epoch": 0.5264421281725753, "grad_norm": 1.338461429821658, "learning_rate": 2.739362951095461e-05, "loss": 0.4607, "num_tokens": 295296745.0, "step": 49345 }, { "epoch": 0.5264954711787737, "grad_norm": 1.3223653688685961, "learning_rate": 2.7389660494101166e-05, "loss": 0.4252, "num_tokens": 295318136.0, "step": 49350 }, { "epoch": 0.5265488141849722, "grad_norm": 0.6687535403430293, "learning_rate": 2.7385691480681246e-05, "loss": 0.5638, "num_tokens": 295346432.0, "step": 49355 }, { "epoch": 0.5266021571911707, "grad_norm": 0.8407158352356932, "learning_rate": 2.738172247081837e-05, "loss": 0.6377, "num_tokens": 295383066.0, "step": 49360 }, { "epoch": 0.5266555001973692, "grad_norm": 1.0999566324637018, "learning_rate": 2.7377753464636063e-05, "loss": 0.5077, "num_tokens": 295418601.0, "step": 49365 }, { "epoch": 0.5267088432035676, "grad_norm": 0.6625296737291593, "learning_rate": 2.737378446225781e-05, "loss": 0.5907, "num_tokens": 295449015.0, "step": 49370 }, { "epoch": 0.526762186209766, "grad_norm": 0.8582147286500684, "learning_rate": 2.7369815463807125e-05, "loss": 0.5641, "num_tokens": 295472867.0, "step": 49375 }, { "epoch": 0.5268155292159645, "grad_norm": 1.7307232221224638, "learning_rate": 2.736584646940752e-05, "loss": 0.5157, "num_tokens": 295497962.0, "step": 49380 }, { "epoch": 0.5268688722221629, "grad_norm": 0.889612841888398, "learning_rate": 2.736187747918249e-05, "loss": 0.6098, "num_tokens": 295533008.0, "step": 49385 }, { "epoch": 0.5269222152283614, "grad_norm": 0.9063412685188743, "learning_rate": 2.7357908493255552e-05, "loss": 0.5044, "num_tokens": 295557733.0, "step": 49390 }, { "epoch": 0.5269755582345599, "grad_norm": 1.2967112543919515, "learning_rate": 2.7353939511750214e-05, "loss": 0.5745, "num_tokens": 295581078.0, "step": 49395 }, { "epoch": 0.5270289012407583, "grad_norm": 0.8147216479004398, "learning_rate": 2.7349970534789978e-05, "loss": 0.5204, "num_tokens": 295622962.0, "step": 49400 }, { "epoch": 0.5270822442469568, "grad_norm": 0.8543127811163878, "learning_rate": 2.7346001562498336e-05, "loss": 0.4855, "num_tokens": 295648036.0, "step": 49405 }, { "epoch": 0.5271355872531552, "grad_norm": 1.0217644798816892, "learning_rate": 2.734203259499883e-05, "loss": 0.5278, "num_tokens": 295668223.0, "step": 49410 }, { "epoch": 0.5271889302593536, "grad_norm": 0.853925091929553, "learning_rate": 2.7338063632414928e-05, "loss": 0.5363, "num_tokens": 295697594.0, "step": 49415 }, { "epoch": 0.5272422732655522, "grad_norm": 0.659652772538854, "learning_rate": 2.733409467487016e-05, "loss": 0.5359, "num_tokens": 295727621.0, "step": 49420 }, { "epoch": 0.5272956162717506, "grad_norm": 0.572380122522096, "learning_rate": 2.733012572248803e-05, "loss": 0.4941, "num_tokens": 295766704.0, "step": 49425 }, { "epoch": 0.5273489592779491, "grad_norm": 0.8488409757384012, "learning_rate": 2.732615677539203e-05, "loss": 0.5568, "num_tokens": 295809354.0, "step": 49430 }, { "epoch": 0.5274023022841475, "grad_norm": 0.7536727052357157, "learning_rate": 2.7322187833705682e-05, "loss": 0.5054, "num_tokens": 295830922.0, "step": 49435 }, { "epoch": 0.5274556452903459, "grad_norm": 1.1755998679394024, "learning_rate": 2.7318218897552484e-05, "loss": 0.5866, "num_tokens": 295849815.0, "step": 49440 }, { "epoch": 0.5275089882965445, "grad_norm": 0.9130723968193449, "learning_rate": 2.7314249967055928e-05, "loss": 0.6628, "num_tokens": 295863643.0, "step": 49445 }, { "epoch": 0.5275623313027429, "grad_norm": 1.5193379996302978, "learning_rate": 2.7310281042339535e-05, "loss": 0.4669, "num_tokens": 295885586.0, "step": 49450 }, { "epoch": 0.5276156743089414, "grad_norm": 0.7606716386038394, "learning_rate": 2.730631212352682e-05, "loss": 0.4843, "num_tokens": 295908907.0, "step": 49455 }, { "epoch": 0.5276690173151398, "grad_norm": 0.9017574960200498, "learning_rate": 2.730234321074126e-05, "loss": 0.5022, "num_tokens": 295949150.0, "step": 49460 }, { "epoch": 0.5277223603213382, "grad_norm": 1.1882054762091705, "learning_rate": 2.729837430410637e-05, "loss": 0.5272, "num_tokens": 295969174.0, "step": 49465 }, { "epoch": 0.5277757033275368, "grad_norm": 1.3463824188240756, "learning_rate": 2.7294405403745675e-05, "loss": 0.4742, "num_tokens": 295996746.0, "step": 49470 }, { "epoch": 0.5278290463337352, "grad_norm": 0.9147586281092773, "learning_rate": 2.7290436509782653e-05, "loss": 0.4719, "num_tokens": 296015496.0, "step": 49475 }, { "epoch": 0.5278823893399336, "grad_norm": 1.136683295226984, "learning_rate": 2.7286467622340812e-05, "loss": 0.5261, "num_tokens": 296031399.0, "step": 49480 }, { "epoch": 0.5279357323461321, "grad_norm": 0.673081143522691, "learning_rate": 2.7282498741543667e-05, "loss": 0.4367, "num_tokens": 296071427.0, "step": 49485 }, { "epoch": 0.5279890753523305, "grad_norm": 0.9947814082163099, "learning_rate": 2.7278529867514708e-05, "loss": 0.6345, "num_tokens": 296103863.0, "step": 49490 }, { "epoch": 0.528042418358529, "grad_norm": 0.8792361425830774, "learning_rate": 2.7274561000377446e-05, "loss": 0.5325, "num_tokens": 296131477.0, "step": 49495 }, { "epoch": 0.5280957613647275, "grad_norm": 0.5834050902400186, "learning_rate": 2.7270592140255392e-05, "loss": 0.4103, "num_tokens": 296162831.0, "step": 49500 }, { "epoch": 0.5281491043709259, "grad_norm": 0.867529923058777, "learning_rate": 2.7266623287272024e-05, "loss": 0.5615, "num_tokens": 296200467.0, "step": 49505 }, { "epoch": 0.5282024473771244, "grad_norm": 0.7550818433356699, "learning_rate": 2.7262654441550865e-05, "loss": 0.5844, "num_tokens": 296233241.0, "step": 49510 }, { "epoch": 0.5282557903833228, "grad_norm": 0.6213065173746112, "learning_rate": 2.7258685603215424e-05, "loss": 0.4667, "num_tokens": 296266751.0, "step": 49515 }, { "epoch": 0.5283091333895213, "grad_norm": 1.1395202382197556, "learning_rate": 2.7254716772389177e-05, "loss": 0.5539, "num_tokens": 296305106.0, "step": 49520 }, { "epoch": 0.5283624763957198, "grad_norm": 1.242448341605352, "learning_rate": 2.7250747949195636e-05, "loss": 0.5799, "num_tokens": 296329297.0, "step": 49525 }, { "epoch": 0.5284158194019182, "grad_norm": 1.2106728663588842, "learning_rate": 2.7246779133758328e-05, "loss": 0.6192, "num_tokens": 296356846.0, "step": 49530 }, { "epoch": 0.5284691624081167, "grad_norm": 0.9025504952902406, "learning_rate": 2.724281032620072e-05, "loss": 0.4748, "num_tokens": 296388495.0, "step": 49535 }, { "epoch": 0.5285225054143151, "grad_norm": 1.7737143179103463, "learning_rate": 2.723884152664632e-05, "loss": 0.6394, "num_tokens": 296418559.0, "step": 49540 }, { "epoch": 0.5285758484205136, "grad_norm": 0.617683210785768, "learning_rate": 2.7234872735218648e-05, "loss": 0.505, "num_tokens": 296443070.0, "step": 49545 }, { "epoch": 0.528629191426712, "grad_norm": 0.9595027939824835, "learning_rate": 2.7230903952041186e-05, "loss": 0.5529, "num_tokens": 296470856.0, "step": 49550 }, { "epoch": 0.5286825344329105, "grad_norm": 1.1947026904155291, "learning_rate": 2.722693517723744e-05, "loss": 0.5218, "num_tokens": 296504265.0, "step": 49555 }, { "epoch": 0.528735877439109, "grad_norm": 0.6666715889943045, "learning_rate": 2.7222966410930916e-05, "loss": 0.5531, "num_tokens": 296545072.0, "step": 49560 }, { "epoch": 0.5287892204453074, "grad_norm": 1.102094710828288, "learning_rate": 2.7218997653245104e-05, "loss": 0.5464, "num_tokens": 296578026.0, "step": 49565 }, { "epoch": 0.5288425634515058, "grad_norm": 0.8241633980531963, "learning_rate": 2.7215028904303497e-05, "loss": 0.5627, "num_tokens": 296605612.0, "step": 49570 }, { "epoch": 0.5288959064577043, "grad_norm": 1.1305177573596257, "learning_rate": 2.7211060164229624e-05, "loss": 0.4424, "num_tokens": 296618004.0, "step": 49575 }, { "epoch": 0.5289492494639028, "grad_norm": 0.7976103643946695, "learning_rate": 2.720709143314695e-05, "loss": 0.6166, "num_tokens": 296651029.0, "step": 49580 }, { "epoch": 0.5290025924701013, "grad_norm": 0.6497553029633277, "learning_rate": 2.7203122711178997e-05, "loss": 0.4943, "num_tokens": 296692403.0, "step": 49585 }, { "epoch": 0.5290559354762997, "grad_norm": 0.9409175617467989, "learning_rate": 2.7199153998449262e-05, "loss": 0.5585, "num_tokens": 296724149.0, "step": 49590 }, { "epoch": 0.5291092784824981, "grad_norm": 0.7695130888745505, "learning_rate": 2.7195185295081223e-05, "loss": 0.5406, "num_tokens": 296757872.0, "step": 49595 }, { "epoch": 0.5291626214886966, "grad_norm": 1.3588063938399442, "learning_rate": 2.7191216601198394e-05, "loss": 0.6098, "num_tokens": 296794020.0, "step": 49600 }, { "epoch": 0.529215964494895, "grad_norm": 0.7814770158487983, "learning_rate": 2.718724791692428e-05, "loss": 0.4439, "num_tokens": 296819536.0, "step": 49605 }, { "epoch": 0.5292693075010936, "grad_norm": 0.8752462935701648, "learning_rate": 2.7183279242382358e-05, "loss": 0.497, "num_tokens": 296853764.0, "step": 49610 }, { "epoch": 0.529322650507292, "grad_norm": 1.0166019496738723, "learning_rate": 2.7179310577696138e-05, "loss": 0.6883, "num_tokens": 296887945.0, "step": 49615 }, { "epoch": 0.5293759935134904, "grad_norm": 0.7398241888831396, "learning_rate": 2.717534192298912e-05, "loss": 0.4873, "num_tokens": 296913252.0, "step": 49620 }, { "epoch": 0.5294293365196889, "grad_norm": 0.7733369693290725, "learning_rate": 2.7171373278384786e-05, "loss": 0.5114, "num_tokens": 296951836.0, "step": 49625 }, { "epoch": 0.5294826795258873, "grad_norm": 1.1123157603725675, "learning_rate": 2.716740464400664e-05, "loss": 0.5225, "num_tokens": 296977594.0, "step": 49630 }, { "epoch": 0.5295360225320859, "grad_norm": 0.736387187058185, "learning_rate": 2.716343601997819e-05, "loss": 0.4716, "num_tokens": 297003062.0, "step": 49635 }, { "epoch": 0.5295893655382843, "grad_norm": 0.8507679995708646, "learning_rate": 2.715946740642291e-05, "loss": 0.6738, "num_tokens": 297045928.0, "step": 49640 }, { "epoch": 0.5296427085444827, "grad_norm": 0.7748769056229965, "learning_rate": 2.715549880346431e-05, "loss": 0.6555, "num_tokens": 297078833.0, "step": 49645 }, { "epoch": 0.5296960515506812, "grad_norm": 1.311341186675088, "learning_rate": 2.7151530211225874e-05, "loss": 0.4719, "num_tokens": 297109502.0, "step": 49650 }, { "epoch": 0.5297493945568796, "grad_norm": 0.8662372434721627, "learning_rate": 2.71475616298311e-05, "loss": 0.5823, "num_tokens": 297145609.0, "step": 49655 }, { "epoch": 0.529802737563078, "grad_norm": 1.1476031897012222, "learning_rate": 2.7143593059403494e-05, "loss": 0.4649, "num_tokens": 297171094.0, "step": 49660 }, { "epoch": 0.5298560805692766, "grad_norm": 0.5689889712422427, "learning_rate": 2.7139624500066537e-05, "loss": 0.4093, "num_tokens": 297207112.0, "step": 49665 }, { "epoch": 0.529909423575475, "grad_norm": 0.7446934212732754, "learning_rate": 2.7135655951943716e-05, "loss": 0.7567, "num_tokens": 297251844.0, "step": 49670 }, { "epoch": 0.5299627665816735, "grad_norm": 0.8055274047766902, "learning_rate": 2.713168741515854e-05, "loss": 0.5622, "num_tokens": 297296818.0, "step": 49675 }, { "epoch": 0.5300161095878719, "grad_norm": 0.7500932905373537, "learning_rate": 2.7127718889834498e-05, "loss": 0.4481, "num_tokens": 297329114.0, "step": 49680 }, { "epoch": 0.5300694525940703, "grad_norm": 0.910858954635906, "learning_rate": 2.712375037609508e-05, "loss": 0.6091, "num_tokens": 297365786.0, "step": 49685 }, { "epoch": 0.5301227956002689, "grad_norm": 0.6968363949740333, "learning_rate": 2.7119781874063777e-05, "loss": 0.4561, "num_tokens": 297396495.0, "step": 49690 }, { "epoch": 0.5301761386064673, "grad_norm": 0.796844494588883, "learning_rate": 2.7115813383864074e-05, "loss": 0.5609, "num_tokens": 297433874.0, "step": 49695 }, { "epoch": 0.5302294816126658, "grad_norm": 1.4488255000370966, "learning_rate": 2.7111844905619476e-05, "loss": 0.632, "num_tokens": 297453302.0, "step": 49700 }, { "epoch": 0.5302828246188642, "grad_norm": 1.1163548550623301, "learning_rate": 2.7107876439453462e-05, "loss": 0.484, "num_tokens": 297487231.0, "step": 49705 }, { "epoch": 0.5303361676250626, "grad_norm": 0.8111750613763034, "learning_rate": 2.710390798548953e-05, "loss": 0.4733, "num_tokens": 297517850.0, "step": 49710 }, { "epoch": 0.5303895106312612, "grad_norm": 0.9927063724800239, "learning_rate": 2.7099939543851176e-05, "loss": 0.5014, "num_tokens": 297533902.0, "step": 49715 }, { "epoch": 0.5304428536374596, "grad_norm": 1.4066409515676883, "learning_rate": 2.7095971114661868e-05, "loss": 0.5286, "num_tokens": 297566832.0, "step": 49720 }, { "epoch": 0.5304961966436581, "grad_norm": 4.279168078315803, "learning_rate": 2.7092002698045117e-05, "loss": 0.5712, "num_tokens": 297593392.0, "step": 49725 }, { "epoch": 0.5305495396498565, "grad_norm": 1.1211920537206665, "learning_rate": 2.708803429412441e-05, "loss": 0.5756, "num_tokens": 297640022.0, "step": 49730 }, { "epoch": 0.5306028826560549, "grad_norm": 0.661869400605549, "learning_rate": 2.7084065903023216e-05, "loss": 0.5722, "num_tokens": 297660660.0, "step": 49735 }, { "epoch": 0.5306562256622535, "grad_norm": 1.0608064869384612, "learning_rate": 2.708009752486504e-05, "loss": 0.5372, "num_tokens": 297700510.0, "step": 49740 }, { "epoch": 0.5307095686684519, "grad_norm": 1.8296710808245618, "learning_rate": 2.707612915977337e-05, "loss": 0.5349, "num_tokens": 297722510.0, "step": 49745 }, { "epoch": 0.5307629116746503, "grad_norm": 0.794967402908368, "learning_rate": 2.7072160807871692e-05, "loss": 0.4885, "num_tokens": 297760696.0, "step": 49750 }, { "epoch": 0.5308162546808488, "grad_norm": 1.1222629554258021, "learning_rate": 2.706819246928348e-05, "loss": 0.5259, "num_tokens": 297785399.0, "step": 49755 }, { "epoch": 0.5308695976870472, "grad_norm": 0.823429468442654, "learning_rate": 2.706422414413225e-05, "loss": 0.4742, "num_tokens": 297825868.0, "step": 49760 }, { "epoch": 0.5309229406932457, "grad_norm": 1.444685935334969, "learning_rate": 2.706025583254146e-05, "loss": 0.493, "num_tokens": 297856423.0, "step": 49765 }, { "epoch": 0.5309762836994442, "grad_norm": 0.9255248194543436, "learning_rate": 2.70562875346346e-05, "loss": 0.5266, "num_tokens": 297874135.0, "step": 49770 }, { "epoch": 0.5310296267056426, "grad_norm": 0.771168023108676, "learning_rate": 2.705231925053517e-05, "loss": 0.4072, "num_tokens": 297891642.0, "step": 49775 }, { "epoch": 0.5310829697118411, "grad_norm": 0.830066370360461, "learning_rate": 2.7048350980366633e-05, "loss": 0.48, "num_tokens": 297913314.0, "step": 49780 }, { "epoch": 0.5311363127180395, "grad_norm": 0.6820772084455266, "learning_rate": 2.704438272425249e-05, "loss": 0.4723, "num_tokens": 297939221.0, "step": 49785 }, { "epoch": 0.531189655724238, "grad_norm": 0.9839007922830968, "learning_rate": 2.7040414482316235e-05, "loss": 0.489, "num_tokens": 297972821.0, "step": 49790 }, { "epoch": 0.5312429987304365, "grad_norm": 1.3394831591700993, "learning_rate": 2.703644625468132e-05, "loss": 0.6249, "num_tokens": 297988787.0, "step": 49795 }, { "epoch": 0.5312963417366349, "grad_norm": 0.8092573072761075, "learning_rate": 2.7032478041471254e-05, "loss": 0.5457, "num_tokens": 298022098.0, "step": 49800 }, { "epoch": 0.5313496847428334, "grad_norm": 3.030502883875251, "learning_rate": 2.7028509842809514e-05, "loss": 0.6179, "num_tokens": 298046937.0, "step": 49805 }, { "epoch": 0.5314030277490318, "grad_norm": 1.0303767409563171, "learning_rate": 2.7024541658819564e-05, "loss": 0.5293, "num_tokens": 298068629.0, "step": 49810 }, { "epoch": 0.5314563707552303, "grad_norm": 1.1237847129019154, "learning_rate": 2.7020573489624908e-05, "loss": 0.5236, "num_tokens": 298101673.0, "step": 49815 }, { "epoch": 0.5315097137614287, "grad_norm": 1.5352166177081519, "learning_rate": 2.7016605335349026e-05, "loss": 0.5877, "num_tokens": 298125074.0, "step": 49820 }, { "epoch": 0.5315630567676272, "grad_norm": 0.6427947064729034, "learning_rate": 2.7012637196115392e-05, "loss": 0.5401, "num_tokens": 298161485.0, "step": 49825 }, { "epoch": 0.5316163997738257, "grad_norm": 0.7504729034521223, "learning_rate": 2.7008669072047484e-05, "loss": 0.4335, "num_tokens": 298196128.0, "step": 49830 }, { "epoch": 0.5316697427800241, "grad_norm": 0.6582346517796193, "learning_rate": 2.700470096326879e-05, "loss": 0.5261, "num_tokens": 298226991.0, "step": 49835 }, { "epoch": 0.5317230857862225, "grad_norm": 0.7539531387511903, "learning_rate": 2.7000732869902777e-05, "loss": 0.4334, "num_tokens": 298248890.0, "step": 49840 }, { "epoch": 0.531776428792421, "grad_norm": 0.7827221085994938, "learning_rate": 2.699676479207293e-05, "loss": 0.4091, "num_tokens": 298276210.0, "step": 49845 }, { "epoch": 0.5318297717986195, "grad_norm": 0.6919259203691218, "learning_rate": 2.699279672990274e-05, "loss": 0.6527, "num_tokens": 298322583.0, "step": 49850 }, { "epoch": 0.531883114804818, "grad_norm": 0.7028001990298484, "learning_rate": 2.698882868351567e-05, "loss": 0.504, "num_tokens": 298341098.0, "step": 49855 }, { "epoch": 0.5319364578110164, "grad_norm": 1.0707118964654596, "learning_rate": 2.69848606530352e-05, "loss": 0.5203, "num_tokens": 298362941.0, "step": 49860 }, { "epoch": 0.5319898008172148, "grad_norm": 0.6708629913690405, "learning_rate": 2.6980892638584816e-05, "loss": 0.4913, "num_tokens": 298389546.0, "step": 49865 }, { "epoch": 0.5320431438234133, "grad_norm": 0.9639535287187183, "learning_rate": 2.697692464028797e-05, "loss": 0.4289, "num_tokens": 298410687.0, "step": 49870 }, { "epoch": 0.5320964868296117, "grad_norm": 0.9191182856810616, "learning_rate": 2.6972956658268166e-05, "loss": 0.5553, "num_tokens": 298423967.0, "step": 49875 }, { "epoch": 0.5321498298358103, "grad_norm": 1.0775787782978157, "learning_rate": 2.6968988692648873e-05, "loss": 0.464, "num_tokens": 298453552.0, "step": 49880 }, { "epoch": 0.5322031728420087, "grad_norm": 1.2303551011621858, "learning_rate": 2.696502074355355e-05, "loss": 0.6382, "num_tokens": 298480315.0, "step": 49885 }, { "epoch": 0.5322565158482071, "grad_norm": 0.884617521480254, "learning_rate": 2.6961052811105686e-05, "loss": 0.5722, "num_tokens": 298511601.0, "step": 49890 }, { "epoch": 0.5323098588544056, "grad_norm": 1.4995960235870716, "learning_rate": 2.6957084895428757e-05, "loss": 0.6061, "num_tokens": 298538441.0, "step": 49895 }, { "epoch": 0.532363201860604, "grad_norm": 0.817488467704771, "learning_rate": 2.695311699664622e-05, "loss": 0.4577, "num_tokens": 298569068.0, "step": 49900 }, { "epoch": 0.5324165448668026, "grad_norm": 1.3942261965387641, "learning_rate": 2.694914911488156e-05, "loss": 0.5626, "num_tokens": 298599477.0, "step": 49905 }, { "epoch": 0.532469887873001, "grad_norm": 1.0159919682062553, "learning_rate": 2.694518125025826e-05, "loss": 0.4942, "num_tokens": 298612971.0, "step": 49910 }, { "epoch": 0.5325232308791994, "grad_norm": 0.6814634922796844, "learning_rate": 2.6941213402899774e-05, "loss": 0.5889, "num_tokens": 298650571.0, "step": 49915 }, { "epoch": 0.5325765738853979, "grad_norm": 0.9227401374853558, "learning_rate": 2.6937245572929575e-05, "loss": 0.5193, "num_tokens": 298677895.0, "step": 49920 }, { "epoch": 0.5326299168915963, "grad_norm": 0.7183407915573532, "learning_rate": 2.6933277760471143e-05, "loss": 0.4911, "num_tokens": 298721641.0, "step": 49925 }, { "epoch": 0.5326832598977947, "grad_norm": 0.9891674413950221, "learning_rate": 2.6929309965647942e-05, "loss": 0.4289, "num_tokens": 298746875.0, "step": 49930 }, { "epoch": 0.5327366029039933, "grad_norm": 0.9677482518042765, "learning_rate": 2.6925342188583435e-05, "loss": 0.4397, "num_tokens": 298767342.0, "step": 49935 }, { "epoch": 0.5327899459101917, "grad_norm": 0.4874119321540588, "learning_rate": 2.6921374429401115e-05, "loss": 0.5488, "num_tokens": 298808263.0, "step": 49940 }, { "epoch": 0.5328432889163902, "grad_norm": 1.9407527676970877, "learning_rate": 2.6917406688224418e-05, "loss": 0.5389, "num_tokens": 298827905.0, "step": 49945 }, { "epoch": 0.5328966319225886, "grad_norm": 1.0714454428071774, "learning_rate": 2.6913438965176835e-05, "loss": 0.5401, "num_tokens": 298859684.0, "step": 49950 }, { "epoch": 0.532949974928787, "grad_norm": 0.8686819937157341, "learning_rate": 2.690947126038183e-05, "loss": 0.4349, "num_tokens": 298903370.0, "step": 49955 }, { "epoch": 0.5330033179349856, "grad_norm": 0.910562748517181, "learning_rate": 2.690550357396286e-05, "loss": 0.57, "num_tokens": 298933870.0, "step": 49960 }, { "epoch": 0.533056660941184, "grad_norm": 1.500846383037602, "learning_rate": 2.69015359060434e-05, "loss": 0.5666, "num_tokens": 298966235.0, "step": 49965 }, { "epoch": 0.5331100039473825, "grad_norm": 0.6551434502179772, "learning_rate": 2.689756825674692e-05, "loss": 0.4788, "num_tokens": 299003439.0, "step": 49970 }, { "epoch": 0.5331633469535809, "grad_norm": 0.8100945093422446, "learning_rate": 2.6893600626196868e-05, "loss": 0.4504, "num_tokens": 299023900.0, "step": 49975 }, { "epoch": 0.5332166899597793, "grad_norm": 0.8224377259795771, "learning_rate": 2.6889633014516723e-05, "loss": 0.6099, "num_tokens": 299054825.0, "step": 49980 }, { "epoch": 0.5332700329659779, "grad_norm": 0.7355030065388566, "learning_rate": 2.6885665421829943e-05, "loss": 0.5411, "num_tokens": 299086355.0, "step": 49985 }, { "epoch": 0.5333233759721763, "grad_norm": 1.0328662164561453, "learning_rate": 2.6881697848259995e-05, "loss": 0.6193, "num_tokens": 299111464.0, "step": 49990 }, { "epoch": 0.5333767189783748, "grad_norm": 1.4601889564990957, "learning_rate": 2.6877730293930337e-05, "loss": 0.5136, "num_tokens": 299148417.0, "step": 49995 }, { "epoch": 0.5334300619845732, "grad_norm": 0.7405942435994123, "learning_rate": 2.6873762758964444e-05, "loss": 0.4266, "num_tokens": 299182539.0, "step": 50000 }, { "epoch": 0.5334834049907716, "grad_norm": 1.3288300880212771, "learning_rate": 2.686979524348576e-05, "loss": 0.539, "num_tokens": 299222868.0, "step": 50005 }, { "epoch": 0.5335367479969702, "grad_norm": 0.9986755417650066, "learning_rate": 2.686582774761775e-05, "loss": 0.4623, "num_tokens": 299238794.0, "step": 50010 }, { "epoch": 0.5335900910031686, "grad_norm": 1.0436646635959361, "learning_rate": 2.6861860271483883e-05, "loss": 0.5643, "num_tokens": 299254580.0, "step": 50015 }, { "epoch": 0.533643434009367, "grad_norm": 0.7772336579850515, "learning_rate": 2.6857892815207613e-05, "loss": 0.5464, "num_tokens": 299298592.0, "step": 50020 }, { "epoch": 0.5336967770155655, "grad_norm": 0.8437254099250975, "learning_rate": 2.68539253789124e-05, "loss": 0.4593, "num_tokens": 299328381.0, "step": 50025 }, { "epoch": 0.5337501200217639, "grad_norm": 1.5648489055453205, "learning_rate": 2.6849957962721704e-05, "loss": 0.5456, "num_tokens": 299357788.0, "step": 50030 }, { "epoch": 0.5338034630279624, "grad_norm": 1.217940254949371, "learning_rate": 2.6845990566758977e-05, "loss": 0.5323, "num_tokens": 299385600.0, "step": 50035 }, { "epoch": 0.5338568060341609, "grad_norm": 0.7030729789269369, "learning_rate": 2.684202319114768e-05, "loss": 0.5209, "num_tokens": 299421349.0, "step": 50040 }, { "epoch": 0.5339101490403593, "grad_norm": 0.8939030394117026, "learning_rate": 2.6838055836011277e-05, "loss": 0.5206, "num_tokens": 299436788.0, "step": 50045 }, { "epoch": 0.5339634920465578, "grad_norm": 1.969918867491398, "learning_rate": 2.683408850147321e-05, "loss": 0.7683, "num_tokens": 299478619.0, "step": 50050 }, { "epoch": 0.5340168350527562, "grad_norm": 0.819584168337063, "learning_rate": 2.6830121187656937e-05, "loss": 0.498, "num_tokens": 299526685.0, "step": 50055 }, { "epoch": 0.5340701780589547, "grad_norm": 1.524447417476621, "learning_rate": 2.682615389468593e-05, "loss": 0.4836, "num_tokens": 299545744.0, "step": 50060 }, { "epoch": 0.5341235210651532, "grad_norm": 1.3651092449659408, "learning_rate": 2.6822186622683614e-05, "loss": 0.5697, "num_tokens": 299563707.0, "step": 50065 }, { "epoch": 0.5341768640713516, "grad_norm": 0.8535302268225402, "learning_rate": 2.6818219371773462e-05, "loss": 0.5719, "num_tokens": 299611777.0, "step": 50070 }, { "epoch": 0.5342302070775501, "grad_norm": 0.9377845450813509, "learning_rate": 2.6814252142078932e-05, "loss": 0.4425, "num_tokens": 299642173.0, "step": 50075 }, { "epoch": 0.5342835500837485, "grad_norm": 1.3033231737957052, "learning_rate": 2.6810284933723462e-05, "loss": 0.5732, "num_tokens": 299674523.0, "step": 50080 }, { "epoch": 0.534336893089947, "grad_norm": 0.8346366199592112, "learning_rate": 2.68063177468305e-05, "loss": 0.6318, "num_tokens": 299720872.0, "step": 50085 }, { "epoch": 0.5343902360961454, "grad_norm": 0.8002113651822769, "learning_rate": 2.6802350581523524e-05, "loss": 0.5814, "num_tokens": 299754528.0, "step": 50090 }, { "epoch": 0.5344435791023439, "grad_norm": 0.900864923428139, "learning_rate": 2.6798383437925952e-05, "loss": 0.5192, "num_tokens": 299785522.0, "step": 50095 }, { "epoch": 0.5344969221085424, "grad_norm": 1.9211523722435986, "learning_rate": 2.679441631616124e-05, "loss": 0.5524, "num_tokens": 299817077.0, "step": 50100 }, { "epoch": 0.5345502651147408, "grad_norm": 0.5333265179925097, "learning_rate": 2.6790449216352853e-05, "loss": 0.5088, "num_tokens": 299857094.0, "step": 50105 }, { "epoch": 0.5346036081209392, "grad_norm": 1.673756393175619, "learning_rate": 2.6786482138624225e-05, "loss": 0.7286, "num_tokens": 299895323.0, "step": 50110 }, { "epoch": 0.5346569511271377, "grad_norm": 0.7682764627007604, "learning_rate": 2.678251508309881e-05, "loss": 0.5193, "num_tokens": 299917900.0, "step": 50115 }, { "epoch": 0.5347102941333362, "grad_norm": 0.5733155444251232, "learning_rate": 2.6778548049900055e-05, "loss": 0.4178, "num_tokens": 299941733.0, "step": 50120 }, { "epoch": 0.5347636371395347, "grad_norm": 0.7790692438506645, "learning_rate": 2.677458103915139e-05, "loss": 0.6029, "num_tokens": 299972718.0, "step": 50125 }, { "epoch": 0.5348169801457331, "grad_norm": 0.8759641389545891, "learning_rate": 2.6770614050976285e-05, "loss": 0.5429, "num_tokens": 300019201.0, "step": 50130 }, { "epoch": 0.5348703231519315, "grad_norm": 0.8118929845892109, "learning_rate": 2.676664708549817e-05, "loss": 0.5064, "num_tokens": 300037547.0, "step": 50135 }, { "epoch": 0.53492366615813, "grad_norm": 1.21056606421678, "learning_rate": 2.6762680142840484e-05, "loss": 0.6422, "num_tokens": 300064310.0, "step": 50140 }, { "epoch": 0.5349770091643284, "grad_norm": 1.3146212455693778, "learning_rate": 2.6758713223126687e-05, "loss": 0.3689, "num_tokens": 300093692.0, "step": 50145 }, { "epoch": 0.535030352170527, "grad_norm": 1.4029130641453647, "learning_rate": 2.6754746326480212e-05, "loss": 0.5762, "num_tokens": 300107655.0, "step": 50150 }, { "epoch": 0.5350836951767254, "grad_norm": 0.8658957748914397, "learning_rate": 2.6750779453024493e-05, "loss": 0.5292, "num_tokens": 300134797.0, "step": 50155 }, { "epoch": 0.5351370381829238, "grad_norm": 0.6032229295314736, "learning_rate": 2.6746812602882977e-05, "loss": 0.411, "num_tokens": 300155732.0, "step": 50160 }, { "epoch": 0.5351903811891223, "grad_norm": 1.451543175470174, "learning_rate": 2.6742845776179116e-05, "loss": 0.5121, "num_tokens": 300183870.0, "step": 50165 }, { "epoch": 0.5352437241953207, "grad_norm": 0.7371301230462473, "learning_rate": 2.6738878973036334e-05, "loss": 0.5536, "num_tokens": 300209417.0, "step": 50170 }, { "epoch": 0.5352970672015193, "grad_norm": 1.1711184605308345, "learning_rate": 2.673491219357807e-05, "loss": 0.5429, "num_tokens": 300236172.0, "step": 50175 }, { "epoch": 0.5353504102077177, "grad_norm": 0.52677936945264, "learning_rate": 2.673094543792778e-05, "loss": 0.457, "num_tokens": 300273231.0, "step": 50180 }, { "epoch": 0.5354037532139161, "grad_norm": 0.6564476478579986, "learning_rate": 2.6726978706208878e-05, "loss": 0.5584, "num_tokens": 300295848.0, "step": 50185 }, { "epoch": 0.5354570962201146, "grad_norm": 0.9746323318051507, "learning_rate": 2.6723011998544805e-05, "loss": 0.4817, "num_tokens": 300317008.0, "step": 50190 }, { "epoch": 0.535510439226313, "grad_norm": 1.0467950408526607, "learning_rate": 2.671904531505902e-05, "loss": 0.7295, "num_tokens": 300337610.0, "step": 50195 }, { "epoch": 0.5355637822325114, "grad_norm": 0.9592137144883311, "learning_rate": 2.6715078655874925e-05, "loss": 0.5511, "num_tokens": 300369322.0, "step": 50200 }, { "epoch": 0.53561712523871, "grad_norm": 0.5695603329075216, "learning_rate": 2.6711112021115974e-05, "loss": 0.443, "num_tokens": 300406385.0, "step": 50205 }, { "epoch": 0.5356704682449084, "grad_norm": 0.8142523765735459, "learning_rate": 2.670714541090561e-05, "loss": 0.4922, "num_tokens": 300428771.0, "step": 50210 }, { "epoch": 0.5357238112511069, "grad_norm": 0.8197677057420011, "learning_rate": 2.6703178825367236e-05, "loss": 0.4951, "num_tokens": 300465262.0, "step": 50215 }, { "epoch": 0.5357771542573053, "grad_norm": 0.9907893769536369, "learning_rate": 2.66992122646243e-05, "loss": 0.459, "num_tokens": 300502996.0, "step": 50220 }, { "epoch": 0.5358304972635037, "grad_norm": 0.7082219413756388, "learning_rate": 2.6695245728800244e-05, "loss": 0.4265, "num_tokens": 300528193.0, "step": 50225 }, { "epoch": 0.5358838402697023, "grad_norm": 1.1841060003147414, "learning_rate": 2.6691279218018483e-05, "loss": 0.5822, "num_tokens": 300556736.0, "step": 50230 }, { "epoch": 0.5359371832759007, "grad_norm": 0.9238880089363147, "learning_rate": 2.6687312732402448e-05, "loss": 0.5002, "num_tokens": 300587504.0, "step": 50235 }, { "epoch": 0.5359905262820992, "grad_norm": 1.5251419852664427, "learning_rate": 2.6683346272075577e-05, "loss": 0.4214, "num_tokens": 300610709.0, "step": 50240 }, { "epoch": 0.5360438692882976, "grad_norm": 0.6873823531392338, "learning_rate": 2.667937983716129e-05, "loss": 0.495, "num_tokens": 300634943.0, "step": 50245 }, { "epoch": 0.536097212294496, "grad_norm": 1.020808401689187, "learning_rate": 2.6675413427783013e-05, "loss": 0.6766, "num_tokens": 300666932.0, "step": 50250 }, { "epoch": 0.5361505553006946, "grad_norm": 0.6722601006869515, "learning_rate": 2.6671447044064184e-05, "loss": 0.5069, "num_tokens": 300696193.0, "step": 50255 }, { "epoch": 0.536203898306893, "grad_norm": 1.2212767409254999, "learning_rate": 2.666748068612822e-05, "loss": 0.4791, "num_tokens": 300710983.0, "step": 50260 }, { "epoch": 0.5362572413130915, "grad_norm": 8.919088588103815, "learning_rate": 2.666351435409854e-05, "loss": 0.5344, "num_tokens": 300729903.0, "step": 50265 }, { "epoch": 0.5363105843192899, "grad_norm": 0.8700172477424465, "learning_rate": 2.6659548048098585e-05, "loss": 0.5013, "num_tokens": 300747906.0, "step": 50270 }, { "epoch": 0.5363639273254883, "grad_norm": 0.7247249791151642, "learning_rate": 2.665558176825176e-05, "loss": 0.5974, "num_tokens": 300776555.0, "step": 50275 }, { "epoch": 0.5364172703316868, "grad_norm": 2.1962590636648436, "learning_rate": 2.66516155146815e-05, "loss": 0.6886, "num_tokens": 300813468.0, "step": 50280 }, { "epoch": 0.5364706133378853, "grad_norm": 1.2071141163781833, "learning_rate": 2.664764928751123e-05, "loss": 0.6659, "num_tokens": 300842102.0, "step": 50285 }, { "epoch": 0.5365239563440837, "grad_norm": 1.441700815762645, "learning_rate": 2.6643683086864347e-05, "loss": 0.5484, "num_tokens": 300869585.0, "step": 50290 }, { "epoch": 0.5365772993502822, "grad_norm": 0.5436178176265396, "learning_rate": 2.6639716912864293e-05, "loss": 0.5155, "num_tokens": 300897370.0, "step": 50295 }, { "epoch": 0.5366306423564806, "grad_norm": 1.105654354570042, "learning_rate": 2.6635750765634494e-05, "loss": 0.492, "num_tokens": 300928285.0, "step": 50300 }, { "epoch": 0.5366839853626791, "grad_norm": 1.1029860934238687, "learning_rate": 2.6631784645298337e-05, "loss": 0.4364, "num_tokens": 300953151.0, "step": 50305 }, { "epoch": 0.5367373283688776, "grad_norm": 1.2054231010466043, "learning_rate": 2.6627818551979268e-05, "loss": 0.3816, "num_tokens": 300973628.0, "step": 50310 }, { "epoch": 0.536790671375076, "grad_norm": 0.7682379651175418, "learning_rate": 2.66238524858007e-05, "loss": 0.4257, "num_tokens": 301000940.0, "step": 50315 }, { "epoch": 0.5368440143812745, "grad_norm": 0.9794657203593341, "learning_rate": 2.6619886446886032e-05, "loss": 0.5261, "num_tokens": 301016365.0, "step": 50320 }, { "epoch": 0.5368973573874729, "grad_norm": 0.6571320607417956, "learning_rate": 2.6615920435358687e-05, "loss": 0.4607, "num_tokens": 301039088.0, "step": 50325 }, { "epoch": 0.5369507003936714, "grad_norm": 0.8201175564270047, "learning_rate": 2.66119544513421e-05, "loss": 0.4657, "num_tokens": 301061871.0, "step": 50330 }, { "epoch": 0.5370040433998698, "grad_norm": 1.1569311065679948, "learning_rate": 2.660798849495965e-05, "loss": 0.5414, "num_tokens": 301108167.0, "step": 50335 }, { "epoch": 0.5370573864060683, "grad_norm": 1.1381367849086665, "learning_rate": 2.6604022566334768e-05, "loss": 0.4396, "num_tokens": 301126241.0, "step": 50340 }, { "epoch": 0.5371107294122668, "grad_norm": 0.9679599708595671, "learning_rate": 2.660005666559088e-05, "loss": 0.4542, "num_tokens": 301146722.0, "step": 50345 }, { "epoch": 0.5371640724184652, "grad_norm": 0.8520023918202646, "learning_rate": 2.6596090792851364e-05, "loss": 0.5517, "num_tokens": 301174004.0, "step": 50350 }, { "epoch": 0.5372174154246637, "grad_norm": 1.0410123980031494, "learning_rate": 2.6592124948239644e-05, "loss": 0.4559, "num_tokens": 301195433.0, "step": 50355 }, { "epoch": 0.5372707584308621, "grad_norm": 1.2299133329768162, "learning_rate": 2.6588159131879135e-05, "loss": 0.6369, "num_tokens": 301238453.0, "step": 50360 }, { "epoch": 0.5373241014370606, "grad_norm": 2.6364279342579686, "learning_rate": 2.6584193343893245e-05, "loss": 0.607, "num_tokens": 301267005.0, "step": 50365 }, { "epoch": 0.5373774444432591, "grad_norm": 0.9775111422688911, "learning_rate": 2.658022758440537e-05, "loss": 0.5044, "num_tokens": 301287902.0, "step": 50370 }, { "epoch": 0.5374307874494575, "grad_norm": 1.3380197774369618, "learning_rate": 2.657626185353893e-05, "loss": 0.5032, "num_tokens": 301311143.0, "step": 50375 }, { "epoch": 0.5374841304556559, "grad_norm": 1.4890638839118011, "learning_rate": 2.657229615141732e-05, "loss": 0.424, "num_tokens": 301330038.0, "step": 50380 }, { "epoch": 0.5375374734618544, "grad_norm": 1.0058240993459047, "learning_rate": 2.656833047816395e-05, "loss": 0.5038, "num_tokens": 301364874.0, "step": 50385 }, { "epoch": 0.5375908164680528, "grad_norm": 2.5501636303953217, "learning_rate": 2.6564364833902223e-05, "loss": 0.572, "num_tokens": 301381471.0, "step": 50390 }, { "epoch": 0.5376441594742514, "grad_norm": 1.630071386445858, "learning_rate": 2.6560399218755533e-05, "loss": 0.4535, "num_tokens": 301403612.0, "step": 50395 }, { "epoch": 0.5376975024804498, "grad_norm": 0.9954848070641245, "learning_rate": 2.6556433632847293e-05, "loss": 0.4923, "num_tokens": 301439996.0, "step": 50400 }, { "epoch": 0.5377508454866482, "grad_norm": 1.189709925569064, "learning_rate": 2.6552468076300907e-05, "loss": 0.5716, "num_tokens": 301468972.0, "step": 50405 }, { "epoch": 0.5378041884928467, "grad_norm": 0.7956812692615461, "learning_rate": 2.6548502549239762e-05, "loss": 0.4727, "num_tokens": 301496270.0, "step": 50410 }, { "epoch": 0.5378575314990451, "grad_norm": 0.8501667377772718, "learning_rate": 2.654453705178726e-05, "loss": 0.509, "num_tokens": 301523918.0, "step": 50415 }, { "epoch": 0.5379108745052437, "grad_norm": 0.819900398635677, "learning_rate": 2.654057158406681e-05, "loss": 0.5576, "num_tokens": 301561608.0, "step": 50420 }, { "epoch": 0.5379642175114421, "grad_norm": 1.1237853862821792, "learning_rate": 2.65366061462018e-05, "loss": 0.506, "num_tokens": 301614433.0, "step": 50425 }, { "epoch": 0.5380175605176405, "grad_norm": 0.5648015587506666, "learning_rate": 2.653264073831562e-05, "loss": 0.5337, "num_tokens": 301647294.0, "step": 50430 }, { "epoch": 0.538070903523839, "grad_norm": 0.798002137280734, "learning_rate": 2.6528675360531684e-05, "loss": 0.501, "num_tokens": 301686064.0, "step": 50435 }, { "epoch": 0.5381242465300374, "grad_norm": 0.8032216055850813, "learning_rate": 2.652471001297337e-05, "loss": 0.4175, "num_tokens": 301707959.0, "step": 50440 }, { "epoch": 0.538177589536236, "grad_norm": 0.5906795040108518, "learning_rate": 2.6520744695764076e-05, "loss": 0.542, "num_tokens": 301741377.0, "step": 50445 }, { "epoch": 0.5382309325424344, "grad_norm": 0.7157618128608791, "learning_rate": 2.6516779409027205e-05, "loss": 0.4338, "num_tokens": 301762634.0, "step": 50450 }, { "epoch": 0.5382842755486328, "grad_norm": 0.8566356938513566, "learning_rate": 2.6512814152886123e-05, "loss": 0.3822, "num_tokens": 301786032.0, "step": 50455 }, { "epoch": 0.5383376185548313, "grad_norm": 1.6711188173105394, "learning_rate": 2.6508848927464246e-05, "loss": 0.5615, "num_tokens": 301805637.0, "step": 50460 }, { "epoch": 0.5383909615610297, "grad_norm": 0.6406866639903401, "learning_rate": 2.6504883732884962e-05, "loss": 0.5586, "num_tokens": 301831839.0, "step": 50465 }, { "epoch": 0.5384443045672281, "grad_norm": 0.62934685457707, "learning_rate": 2.6500918569271638e-05, "loss": 0.503, "num_tokens": 301885673.0, "step": 50470 }, { "epoch": 0.5384976475734267, "grad_norm": 1.2191878291219889, "learning_rate": 2.6496953436747686e-05, "loss": 0.5374, "num_tokens": 301918232.0, "step": 50475 }, { "epoch": 0.5385509905796251, "grad_norm": 0.9602102351871155, "learning_rate": 2.649298833543648e-05, "loss": 0.4341, "num_tokens": 301948560.0, "step": 50480 }, { "epoch": 0.5386043335858236, "grad_norm": 0.8130023873574711, "learning_rate": 2.6489023265461406e-05, "loss": 0.4961, "num_tokens": 301971963.0, "step": 50485 }, { "epoch": 0.538657676592022, "grad_norm": 1.3520970336090163, "learning_rate": 2.6485058226945846e-05, "loss": 0.4252, "num_tokens": 301998210.0, "step": 50490 }, { "epoch": 0.5387110195982204, "grad_norm": 0.9774678233491653, "learning_rate": 2.6481093220013204e-05, "loss": 0.5321, "num_tokens": 302017305.0, "step": 50495 }, { "epoch": 0.538764362604419, "grad_norm": 0.9623872428451272, "learning_rate": 2.6477128244786837e-05, "loss": 0.502, "num_tokens": 302038298.0, "step": 50500 }, { "epoch": 0.5388177056106174, "grad_norm": 1.3941933458217528, "learning_rate": 2.6473163301390136e-05, "loss": 0.5779, "num_tokens": 302060554.0, "step": 50505 }, { "epoch": 0.5388710486168159, "grad_norm": 0.668796244029081, "learning_rate": 2.6469198389946496e-05, "loss": 0.6233, "num_tokens": 302090723.0, "step": 50510 }, { "epoch": 0.5389243916230143, "grad_norm": 0.6682795536821479, "learning_rate": 2.646523351057928e-05, "loss": 0.4508, "num_tokens": 302121107.0, "step": 50515 }, { "epoch": 0.5389777346292127, "grad_norm": 0.8443441131806751, "learning_rate": 2.6461268663411864e-05, "loss": 0.465, "num_tokens": 302151188.0, "step": 50520 }, { "epoch": 0.5390310776354112, "grad_norm": 1.9384505634368128, "learning_rate": 2.6457303848567645e-05, "loss": 0.5222, "num_tokens": 302174412.0, "step": 50525 }, { "epoch": 0.5390844206416097, "grad_norm": 1.8674952879050843, "learning_rate": 2.6453339066169973e-05, "loss": 0.7689, "num_tokens": 302204740.0, "step": 50530 }, { "epoch": 0.5391377636478082, "grad_norm": 1.6643419031815974, "learning_rate": 2.6449374316342252e-05, "loss": 0.4327, "num_tokens": 302218994.0, "step": 50535 }, { "epoch": 0.5391911066540066, "grad_norm": 0.8759839609609283, "learning_rate": 2.6445409599207848e-05, "loss": 0.4716, "num_tokens": 302260190.0, "step": 50540 }, { "epoch": 0.539244449660205, "grad_norm": 1.0258255839400237, "learning_rate": 2.6441444914890116e-05, "loss": 0.5324, "num_tokens": 302292756.0, "step": 50545 }, { "epoch": 0.5392977926664035, "grad_norm": 0.6426180243200915, "learning_rate": 2.6437480263512456e-05, "loss": 0.5076, "num_tokens": 302323546.0, "step": 50550 }, { "epoch": 0.539351135672602, "grad_norm": 1.2694294018113124, "learning_rate": 2.6433515645198225e-05, "loss": 0.5426, "num_tokens": 302355827.0, "step": 50555 }, { "epoch": 0.5394044786788004, "grad_norm": 0.7267255807391529, "learning_rate": 2.642955106007079e-05, "loss": 0.517, "num_tokens": 302387985.0, "step": 50560 }, { "epoch": 0.5394578216849989, "grad_norm": 0.8097511165009273, "learning_rate": 2.642558650825353e-05, "loss": 0.4569, "num_tokens": 302428393.0, "step": 50565 }, { "epoch": 0.5395111646911973, "grad_norm": 0.770714593409334, "learning_rate": 2.6421621989869823e-05, "loss": 0.5084, "num_tokens": 302458835.0, "step": 50570 }, { "epoch": 0.5395645076973958, "grad_norm": 1.1819720321069977, "learning_rate": 2.6417657505043014e-05, "loss": 0.57, "num_tokens": 302481439.0, "step": 50575 }, { "epoch": 0.5396178507035942, "grad_norm": 0.8716048007614464, "learning_rate": 2.6413693053896478e-05, "loss": 0.5897, "num_tokens": 302517421.0, "step": 50580 }, { "epoch": 0.5396711937097927, "grad_norm": 1.0089850728633811, "learning_rate": 2.6409728636553587e-05, "loss": 0.4797, "num_tokens": 302562375.0, "step": 50585 }, { "epoch": 0.5397245367159912, "grad_norm": 0.9693332623581206, "learning_rate": 2.6405764253137706e-05, "loss": 0.5047, "num_tokens": 302592049.0, "step": 50590 }, { "epoch": 0.5397778797221896, "grad_norm": 0.605833923745814, "learning_rate": 2.640179990377218e-05, "loss": 0.5339, "num_tokens": 302624436.0, "step": 50595 }, { "epoch": 0.5398312227283881, "grad_norm": 1.0147286828627995, "learning_rate": 2.63978355885804e-05, "loss": 0.4851, "num_tokens": 302654751.0, "step": 50600 }, { "epoch": 0.5398845657345865, "grad_norm": 1.0237946130138034, "learning_rate": 2.639387130768571e-05, "loss": 0.6426, "num_tokens": 302676507.0, "step": 50605 }, { "epoch": 0.539937908740785, "grad_norm": 0.9187880388868148, "learning_rate": 2.638990706121146e-05, "loss": 0.5207, "num_tokens": 302708850.0, "step": 50610 }, { "epoch": 0.5399912517469835, "grad_norm": 0.8749445381090445, "learning_rate": 2.6385942849281026e-05, "loss": 0.8269, "num_tokens": 302730721.0, "step": 50615 }, { "epoch": 0.5400445947531819, "grad_norm": 1.067092347738362, "learning_rate": 2.6381978672017776e-05, "loss": 0.5246, "num_tokens": 302757964.0, "step": 50620 }, { "epoch": 0.5400979377593804, "grad_norm": 1.419979161721222, "learning_rate": 2.637801452954504e-05, "loss": 0.5846, "num_tokens": 302788534.0, "step": 50625 }, { "epoch": 0.5401512807655788, "grad_norm": 0.8642833004101295, "learning_rate": 2.6374050421986192e-05, "loss": 0.6594, "num_tokens": 302826048.0, "step": 50630 }, { "epoch": 0.5402046237717772, "grad_norm": 0.6948499182445367, "learning_rate": 2.6370086349464583e-05, "loss": 0.4835, "num_tokens": 302859688.0, "step": 50635 }, { "epoch": 0.5402579667779758, "grad_norm": 0.6561733177405525, "learning_rate": 2.636612231210357e-05, "loss": 0.5353, "num_tokens": 302889563.0, "step": 50640 }, { "epoch": 0.5403113097841742, "grad_norm": 0.9396109951039919, "learning_rate": 2.636215831002649e-05, "loss": 0.5345, "num_tokens": 302910399.0, "step": 50645 }, { "epoch": 0.5403646527903726, "grad_norm": 1.364431281323229, "learning_rate": 2.6358194343356712e-05, "loss": 0.6086, "num_tokens": 302924581.0, "step": 50650 }, { "epoch": 0.5404179957965711, "grad_norm": 0.6829852484523846, "learning_rate": 2.6354230412217577e-05, "loss": 0.4406, "num_tokens": 302944213.0, "step": 50655 }, { "epoch": 0.5404713388027695, "grad_norm": 1.9297259791539674, "learning_rate": 2.6350266516732447e-05, "loss": 0.6695, "num_tokens": 302977336.0, "step": 50660 }, { "epoch": 0.5405246818089681, "grad_norm": 1.042620397652965, "learning_rate": 2.6346302657024664e-05, "loss": 0.5081, "num_tokens": 303012155.0, "step": 50665 }, { "epoch": 0.5405780248151665, "grad_norm": 0.7831089633897688, "learning_rate": 2.6342338833217556e-05, "loss": 0.5836, "num_tokens": 303053080.0, "step": 50670 }, { "epoch": 0.5406313678213649, "grad_norm": 0.8341501966086678, "learning_rate": 2.63383750454345e-05, "loss": 0.4542, "num_tokens": 303073595.0, "step": 50675 }, { "epoch": 0.5406847108275634, "grad_norm": 1.1582640395915718, "learning_rate": 2.6334411293798822e-05, "loss": 0.5515, "num_tokens": 303099168.0, "step": 50680 }, { "epoch": 0.5407380538337618, "grad_norm": 0.8698382419283529, "learning_rate": 2.6330447578433863e-05, "loss": 0.5619, "num_tokens": 303149201.0, "step": 50685 }, { "epoch": 0.5407913968399604, "grad_norm": 1.6824515536461329, "learning_rate": 2.632648389946298e-05, "loss": 0.5313, "num_tokens": 303187951.0, "step": 50690 }, { "epoch": 0.5408447398461588, "grad_norm": 0.9910047335696485, "learning_rate": 2.6322520257009514e-05, "loss": 0.7308, "num_tokens": 303224827.0, "step": 50695 }, { "epoch": 0.5408980828523572, "grad_norm": 0.9460908775176561, "learning_rate": 2.631855665119679e-05, "loss": 0.5495, "num_tokens": 303267879.0, "step": 50700 }, { "epoch": 0.5409514258585557, "grad_norm": 2.0221714967568647, "learning_rate": 2.6314593082148153e-05, "loss": 0.5878, "num_tokens": 303304252.0, "step": 50705 }, { "epoch": 0.5410047688647541, "grad_norm": 1.6196376223840134, "learning_rate": 2.6310629549986954e-05, "loss": 0.5468, "num_tokens": 303334728.0, "step": 50710 }, { "epoch": 0.5410581118709527, "grad_norm": 0.7016430366615622, "learning_rate": 2.630666605483652e-05, "loss": 0.5398, "num_tokens": 303377337.0, "step": 50715 }, { "epoch": 0.5411114548771511, "grad_norm": 0.8597082902981658, "learning_rate": 2.6302702596820177e-05, "loss": 0.6244, "num_tokens": 303413878.0, "step": 50720 }, { "epoch": 0.5411647978833495, "grad_norm": 1.0047896494458366, "learning_rate": 2.6298739176061283e-05, "loss": 0.4764, "num_tokens": 303448064.0, "step": 50725 }, { "epoch": 0.541218140889548, "grad_norm": 0.9775223360463068, "learning_rate": 2.6294775792683145e-05, "loss": 0.4758, "num_tokens": 303469691.0, "step": 50730 }, { "epoch": 0.5412714838957464, "grad_norm": 1.415235016691298, "learning_rate": 2.6290812446809116e-05, "loss": 0.482, "num_tokens": 303498953.0, "step": 50735 }, { "epoch": 0.5413248269019448, "grad_norm": 0.8855301114312358, "learning_rate": 2.6286849138562526e-05, "loss": 0.531, "num_tokens": 303536751.0, "step": 50740 }, { "epoch": 0.5413781699081434, "grad_norm": 1.1254069523290633, "learning_rate": 2.6282885868066687e-05, "loss": 0.6254, "num_tokens": 303571537.0, "step": 50745 }, { "epoch": 0.5414315129143418, "grad_norm": 0.9374566814784862, "learning_rate": 2.6278922635444947e-05, "loss": 0.5314, "num_tokens": 303596819.0, "step": 50750 }, { "epoch": 0.5414848559205403, "grad_norm": 0.8169211524870421, "learning_rate": 2.6274959440820628e-05, "loss": 0.4721, "num_tokens": 303627286.0, "step": 50755 }, { "epoch": 0.5415381989267387, "grad_norm": 1.0967245262612806, "learning_rate": 2.6270996284317046e-05, "loss": 0.5558, "num_tokens": 303651755.0, "step": 50760 }, { "epoch": 0.5415915419329371, "grad_norm": 0.6767303854700408, "learning_rate": 2.626703316605754e-05, "loss": 0.5421, "num_tokens": 303687741.0, "step": 50765 }, { "epoch": 0.5416448849391357, "grad_norm": 1.0720857365155838, "learning_rate": 2.6263070086165437e-05, "loss": 0.4271, "num_tokens": 303709279.0, "step": 50770 }, { "epoch": 0.5416982279453341, "grad_norm": 1.4795551894489518, "learning_rate": 2.625910704476404e-05, "loss": 0.5636, "num_tokens": 303722991.0, "step": 50775 }, { "epoch": 0.5417515709515326, "grad_norm": 0.9518255475410452, "learning_rate": 2.6255144041976685e-05, "loss": 0.5496, "num_tokens": 303756786.0, "step": 50780 }, { "epoch": 0.541804913957731, "grad_norm": 0.866893404478996, "learning_rate": 2.62511810779267e-05, "loss": 0.4331, "num_tokens": 303777224.0, "step": 50785 }, { "epoch": 0.5418582569639294, "grad_norm": 1.2497264244549302, "learning_rate": 2.6247218152737385e-05, "loss": 0.5078, "num_tokens": 303798021.0, "step": 50790 }, { "epoch": 0.5419115999701279, "grad_norm": 0.8626241414795742, "learning_rate": 2.624325526653207e-05, "loss": 0.5113, "num_tokens": 303827743.0, "step": 50795 }, { "epoch": 0.5419649429763264, "grad_norm": 1.0240665242383833, "learning_rate": 2.6239292419434076e-05, "loss": 0.5774, "num_tokens": 303863263.0, "step": 50800 }, { "epoch": 0.5420182859825249, "grad_norm": 0.9917309041782917, "learning_rate": 2.6235329611566704e-05, "loss": 0.6473, "num_tokens": 303881249.0, "step": 50805 }, { "epoch": 0.5420716289887233, "grad_norm": 0.9358167438233232, "learning_rate": 2.623136684305328e-05, "loss": 0.7226, "num_tokens": 303903367.0, "step": 50810 }, { "epoch": 0.5421249719949217, "grad_norm": 1.662219952395328, "learning_rate": 2.622740411401712e-05, "loss": 0.5204, "num_tokens": 303921971.0, "step": 50815 }, { "epoch": 0.5421783150011202, "grad_norm": 0.573572541761667, "learning_rate": 2.622344142458151e-05, "loss": 0.4543, "num_tokens": 303947526.0, "step": 50820 }, { "epoch": 0.5422316580073187, "grad_norm": 0.9055625065357387, "learning_rate": 2.6219478774869798e-05, "loss": 0.4828, "num_tokens": 303978223.0, "step": 50825 }, { "epoch": 0.5422850010135171, "grad_norm": 0.6472224172310578, "learning_rate": 2.6215516165005278e-05, "loss": 0.4604, "num_tokens": 304016043.0, "step": 50830 }, { "epoch": 0.5423383440197156, "grad_norm": 0.6943717033740395, "learning_rate": 2.621155359511125e-05, "loss": 0.4636, "num_tokens": 304031003.0, "step": 50835 }, { "epoch": 0.542391687025914, "grad_norm": 0.8345907777156957, "learning_rate": 2.6207591065311026e-05, "loss": 0.4669, "num_tokens": 304057507.0, "step": 50840 }, { "epoch": 0.5424450300321125, "grad_norm": 0.8735016939515247, "learning_rate": 2.6203628575727922e-05, "loss": 0.4476, "num_tokens": 304086488.0, "step": 50845 }, { "epoch": 0.5424983730383109, "grad_norm": 0.8249017807467754, "learning_rate": 2.6199666126485224e-05, "loss": 0.63, "num_tokens": 304130659.0, "step": 50850 }, { "epoch": 0.5425517160445094, "grad_norm": 0.5792007050677461, "learning_rate": 2.6195703717706245e-05, "loss": 0.5078, "num_tokens": 304161547.0, "step": 50855 }, { "epoch": 0.5426050590507079, "grad_norm": 1.3896219443611684, "learning_rate": 2.61917413495143e-05, "loss": 0.4638, "num_tokens": 304175044.0, "step": 50860 }, { "epoch": 0.5426584020569063, "grad_norm": 0.8679104556920308, "learning_rate": 2.6187779022032665e-05, "loss": 0.4514, "num_tokens": 304204240.0, "step": 50865 }, { "epoch": 0.5427117450631048, "grad_norm": 0.9191931179451985, "learning_rate": 2.6183816735384652e-05, "loss": 0.4869, "num_tokens": 304238344.0, "step": 50870 }, { "epoch": 0.5427650880693032, "grad_norm": 0.754112958096883, "learning_rate": 2.6179854489693566e-05, "loss": 0.4997, "num_tokens": 304273120.0, "step": 50875 }, { "epoch": 0.5428184310755017, "grad_norm": 2.0746508612321466, "learning_rate": 2.6175892285082694e-05, "loss": 0.5243, "num_tokens": 304293467.0, "step": 50880 }, { "epoch": 0.5428717740817002, "grad_norm": 1.4582874478368957, "learning_rate": 2.6171930121675325e-05, "loss": 0.5268, "num_tokens": 304325630.0, "step": 50885 }, { "epoch": 0.5429251170878986, "grad_norm": 1.0656590700291484, "learning_rate": 2.616796799959478e-05, "loss": 0.4772, "num_tokens": 304361879.0, "step": 50890 }, { "epoch": 0.5429784600940971, "grad_norm": 0.7442040710619425, "learning_rate": 2.616400591896432e-05, "loss": 0.5451, "num_tokens": 304399743.0, "step": 50895 }, { "epoch": 0.5430318031002955, "grad_norm": 1.4879657365474495, "learning_rate": 2.6160043879907253e-05, "loss": 0.6408, "num_tokens": 304448599.0, "step": 50900 }, { "epoch": 0.5430851461064939, "grad_norm": 1.5058572218820994, "learning_rate": 2.615608188254688e-05, "loss": 0.6369, "num_tokens": 304473333.0, "step": 50905 }, { "epoch": 0.5431384891126925, "grad_norm": 0.8921419510426054, "learning_rate": 2.6152119927006463e-05, "loss": 0.5301, "num_tokens": 304496483.0, "step": 50910 }, { "epoch": 0.5431918321188909, "grad_norm": 0.639239743974156, "learning_rate": 2.6148158013409314e-05, "loss": 0.4728, "num_tokens": 304519443.0, "step": 50915 }, { "epoch": 0.5432451751250893, "grad_norm": 0.7184719197445117, "learning_rate": 2.6144196141878712e-05, "loss": 0.557, "num_tokens": 304555120.0, "step": 50920 }, { "epoch": 0.5432985181312878, "grad_norm": 0.8475571490248882, "learning_rate": 2.6140234312537936e-05, "loss": 0.4734, "num_tokens": 304573461.0, "step": 50925 }, { "epoch": 0.5433518611374862, "grad_norm": 0.9898164502192746, "learning_rate": 2.613627252551028e-05, "loss": 0.3975, "num_tokens": 304600607.0, "step": 50930 }, { "epoch": 0.5434052041436848, "grad_norm": 1.2863054656972732, "learning_rate": 2.613231078091902e-05, "loss": 0.5532, "num_tokens": 304620395.0, "step": 50935 }, { "epoch": 0.5434585471498832, "grad_norm": 1.1507697845643754, "learning_rate": 2.6128349078887437e-05, "loss": 0.415, "num_tokens": 304633737.0, "step": 50940 }, { "epoch": 0.5435118901560816, "grad_norm": 1.016988652978228, "learning_rate": 2.6124387419538808e-05, "loss": 0.6065, "num_tokens": 304662014.0, "step": 50945 }, { "epoch": 0.5435652331622801, "grad_norm": 0.9250012422275549, "learning_rate": 2.612042580299643e-05, "loss": 0.4363, "num_tokens": 304697690.0, "step": 50950 }, { "epoch": 0.5436185761684785, "grad_norm": 0.8033588926593678, "learning_rate": 2.6116464229383557e-05, "loss": 0.5525, "num_tokens": 304736996.0, "step": 50955 }, { "epoch": 0.543671919174677, "grad_norm": 0.7651781853197303, "learning_rate": 2.6112502698823476e-05, "loss": 0.4559, "num_tokens": 304766295.0, "step": 50960 }, { "epoch": 0.5437252621808755, "grad_norm": 0.9825209149080569, "learning_rate": 2.610854121143947e-05, "loss": 0.6778, "num_tokens": 304793683.0, "step": 50965 }, { "epoch": 0.5437786051870739, "grad_norm": 1.2785801693047811, "learning_rate": 2.6104579767354797e-05, "loss": 0.5596, "num_tokens": 304825047.0, "step": 50970 }, { "epoch": 0.5438319481932724, "grad_norm": 0.6065214004534363, "learning_rate": 2.6100618366692738e-05, "loss": 0.4386, "num_tokens": 304870600.0, "step": 50975 }, { "epoch": 0.5438852911994708, "grad_norm": 0.9050525741940122, "learning_rate": 2.6096657009576557e-05, "loss": 0.5023, "num_tokens": 304895866.0, "step": 50980 }, { "epoch": 0.5439386342056693, "grad_norm": 0.8470854412763121, "learning_rate": 2.6092695696129526e-05, "loss": 0.5508, "num_tokens": 304931148.0, "step": 50985 }, { "epoch": 0.5439919772118678, "grad_norm": 0.8333408615818144, "learning_rate": 2.608873442647492e-05, "loss": 0.548, "num_tokens": 304969808.0, "step": 50990 }, { "epoch": 0.5440453202180662, "grad_norm": 1.0450546309900688, "learning_rate": 2.6084773200736e-05, "loss": 0.4595, "num_tokens": 304992483.0, "step": 50995 }, { "epoch": 0.5440986632242647, "grad_norm": 0.9110214124535455, "learning_rate": 2.608081201903602e-05, "loss": 0.6468, "num_tokens": 305019974.0, "step": 51000 }, { "epoch": 0.5441520062304631, "grad_norm": 0.8289281553604827, "learning_rate": 2.6076850881498265e-05, "loss": 0.4673, "num_tokens": 305049102.0, "step": 51005 }, { "epoch": 0.5442053492366615, "grad_norm": 0.6973376965653515, "learning_rate": 2.607288978824599e-05, "loss": 0.5769, "num_tokens": 305073856.0, "step": 51010 }, { "epoch": 0.54425869224286, "grad_norm": 2.3473001895519436, "learning_rate": 2.606892873940245e-05, "loss": 0.4769, "num_tokens": 305093359.0, "step": 51015 }, { "epoch": 0.5443120352490585, "grad_norm": 1.3144840580908235, "learning_rate": 2.60649677350909e-05, "loss": 0.5295, "num_tokens": 305119604.0, "step": 51020 }, { "epoch": 0.544365378255257, "grad_norm": 0.9114359300397546, "learning_rate": 2.606100677543462e-05, "loss": 0.4971, "num_tokens": 305148435.0, "step": 51025 }, { "epoch": 0.5444187212614554, "grad_norm": 1.5056087048926825, "learning_rate": 2.605704586055685e-05, "loss": 0.5131, "num_tokens": 305162568.0, "step": 51030 }, { "epoch": 0.5444720642676538, "grad_norm": 0.8821552767094035, "learning_rate": 2.605308499058084e-05, "loss": 0.5534, "num_tokens": 305200375.0, "step": 51035 }, { "epoch": 0.5445254072738523, "grad_norm": 1.371040314290297, "learning_rate": 2.6049124165629863e-05, "loss": 0.4738, "num_tokens": 305220447.0, "step": 51040 }, { "epoch": 0.5445787502800508, "grad_norm": 1.7313298960119183, "learning_rate": 2.6045163385827158e-05, "loss": 0.6227, "num_tokens": 305256872.0, "step": 51045 }, { "epoch": 0.5446320932862493, "grad_norm": 0.7886084786036955, "learning_rate": 2.6041202651295976e-05, "loss": 0.5309, "num_tokens": 305285165.0, "step": 51050 }, { "epoch": 0.5446854362924477, "grad_norm": 0.7546973767562171, "learning_rate": 2.603724196215958e-05, "loss": 0.6266, "num_tokens": 305321565.0, "step": 51055 }, { "epoch": 0.5447387792986461, "grad_norm": 1.2643463659980099, "learning_rate": 2.6033281318541202e-05, "loss": 0.5372, "num_tokens": 305341334.0, "step": 51060 }, { "epoch": 0.5447921223048446, "grad_norm": 1.3205596707443497, "learning_rate": 2.6029320720564094e-05, "loss": 0.4579, "num_tokens": 305357953.0, "step": 51065 }, { "epoch": 0.544845465311043, "grad_norm": 1.7076636591616268, "learning_rate": 2.6025360168351516e-05, "loss": 0.6472, "num_tokens": 305387596.0, "step": 51070 }, { "epoch": 0.5448988083172416, "grad_norm": 0.6510529593835752, "learning_rate": 2.602139966202669e-05, "loss": 0.4215, "num_tokens": 305409653.0, "step": 51075 }, { "epoch": 0.54495215132344, "grad_norm": 0.8740547590336076, "learning_rate": 2.6017439201712873e-05, "loss": 0.6429, "num_tokens": 305448193.0, "step": 51080 }, { "epoch": 0.5450054943296384, "grad_norm": 1.0069773105898092, "learning_rate": 2.601347878753331e-05, "loss": 0.5236, "num_tokens": 305480133.0, "step": 51085 }, { "epoch": 0.5450588373358369, "grad_norm": 1.482820905330503, "learning_rate": 2.6009518419611223e-05, "loss": 0.443, "num_tokens": 305505541.0, "step": 51090 }, { "epoch": 0.5451121803420353, "grad_norm": 0.5726545980861157, "learning_rate": 2.6005558098069867e-05, "loss": 0.5256, "num_tokens": 305533674.0, "step": 51095 }, { "epoch": 0.5451655233482338, "grad_norm": 0.7963579770051491, "learning_rate": 2.600159782303247e-05, "loss": 0.6021, "num_tokens": 305556528.0, "step": 51100 }, { "epoch": 0.5452188663544323, "grad_norm": 3.015898439016021, "learning_rate": 2.599763759462227e-05, "loss": 0.5712, "num_tokens": 305597634.0, "step": 51105 }, { "epoch": 0.5452722093606307, "grad_norm": 0.7476895277449109, "learning_rate": 2.5993677412962503e-05, "loss": 0.5571, "num_tokens": 305649310.0, "step": 51110 }, { "epoch": 0.5453255523668292, "grad_norm": 0.6862921076541774, "learning_rate": 2.5989717278176407e-05, "loss": 0.5416, "num_tokens": 305703063.0, "step": 51115 }, { "epoch": 0.5453788953730276, "grad_norm": 0.6372409531179309, "learning_rate": 2.59857571903872e-05, "loss": 0.4915, "num_tokens": 305733918.0, "step": 51120 }, { "epoch": 0.545432238379226, "grad_norm": 1.113581249901557, "learning_rate": 2.5981797149718113e-05, "loss": 0.5643, "num_tokens": 305757749.0, "step": 51125 }, { "epoch": 0.5454855813854246, "grad_norm": 0.9987326774249744, "learning_rate": 2.5977837156292393e-05, "loss": 0.613, "num_tokens": 305781463.0, "step": 51130 }, { "epoch": 0.545538924391623, "grad_norm": 0.8738438588808751, "learning_rate": 2.5973877210233255e-05, "loss": 0.4815, "num_tokens": 305812750.0, "step": 51135 }, { "epoch": 0.5455922673978215, "grad_norm": 1.5807588162107278, "learning_rate": 2.596991731166391e-05, "loss": 0.5132, "num_tokens": 305831671.0, "step": 51140 }, { "epoch": 0.5456456104040199, "grad_norm": 0.9065310639521239, "learning_rate": 2.5965957460707614e-05, "loss": 0.5048, "num_tokens": 305867441.0, "step": 51145 }, { "epoch": 0.5456989534102183, "grad_norm": 1.5238444433431335, "learning_rate": 2.596199765748755e-05, "loss": 0.4379, "num_tokens": 305881598.0, "step": 51150 }, { "epoch": 0.5457522964164169, "grad_norm": 0.9921482503272409, "learning_rate": 2.5958037902126968e-05, "loss": 0.6041, "num_tokens": 305909398.0, "step": 51155 }, { "epoch": 0.5458056394226153, "grad_norm": 0.696007133838533, "learning_rate": 2.5954078194749093e-05, "loss": 0.4668, "num_tokens": 305929440.0, "step": 51160 }, { "epoch": 0.5458589824288138, "grad_norm": 0.5105522407801892, "learning_rate": 2.595011853547711e-05, "loss": 0.5539, "num_tokens": 305965574.0, "step": 51165 }, { "epoch": 0.5459123254350122, "grad_norm": 1.0500698684754526, "learning_rate": 2.594615892443426e-05, "loss": 0.4894, "num_tokens": 305983485.0, "step": 51170 }, { "epoch": 0.5459656684412106, "grad_norm": 0.8917865136357785, "learning_rate": 2.5942199361743764e-05, "loss": 0.4886, "num_tokens": 306007292.0, "step": 51175 }, { "epoch": 0.5460190114474092, "grad_norm": 0.8372404448716676, "learning_rate": 2.5938239847528812e-05, "loss": 0.4022, "num_tokens": 306026231.0, "step": 51180 }, { "epoch": 0.5460723544536076, "grad_norm": 0.975182948717123, "learning_rate": 2.5934280381912623e-05, "loss": 0.4946, "num_tokens": 306054721.0, "step": 51185 }, { "epoch": 0.546125697459806, "grad_norm": 0.7499243883045748, "learning_rate": 2.5930320965018422e-05, "loss": 0.5386, "num_tokens": 306080567.0, "step": 51190 }, { "epoch": 0.5461790404660045, "grad_norm": 1.0463979939008476, "learning_rate": 2.592636159696941e-05, "loss": 0.5061, "num_tokens": 306105928.0, "step": 51195 }, { "epoch": 0.5462323834722029, "grad_norm": 1.054308332703677, "learning_rate": 2.5922402277888786e-05, "loss": 0.4252, "num_tokens": 306130593.0, "step": 51200 }, { "epoch": 0.5462857264784015, "grad_norm": 1.3956810077917718, "learning_rate": 2.5918443007899768e-05, "loss": 0.5695, "num_tokens": 306157940.0, "step": 51205 }, { "epoch": 0.5463390694845999, "grad_norm": 0.5693525945550351, "learning_rate": 2.5914483787125554e-05, "loss": 0.581, "num_tokens": 306196721.0, "step": 51210 }, { "epoch": 0.5463924124907983, "grad_norm": 1.4503268941200091, "learning_rate": 2.591052461568934e-05, "loss": 0.5591, "num_tokens": 306213999.0, "step": 51215 }, { "epoch": 0.5464457554969968, "grad_norm": 3.4550479744135125, "learning_rate": 2.5906565493714347e-05, "loss": 0.597, "num_tokens": 306234056.0, "step": 51220 }, { "epoch": 0.5464990985031952, "grad_norm": 0.6569265975940632, "learning_rate": 2.590260642132376e-05, "loss": 0.4752, "num_tokens": 306277315.0, "step": 51225 }, { "epoch": 0.5465524415093937, "grad_norm": 0.6362974695859835, "learning_rate": 2.5898647398640774e-05, "loss": 0.5714, "num_tokens": 306320238.0, "step": 51230 }, { "epoch": 0.5466057845155922, "grad_norm": 0.7648890540246192, "learning_rate": 2.58946884257886e-05, "loss": 0.504, "num_tokens": 306363719.0, "step": 51235 }, { "epoch": 0.5466591275217906, "grad_norm": 0.5551243826556578, "learning_rate": 2.5890729502890415e-05, "loss": 0.3741, "num_tokens": 306393555.0, "step": 51240 }, { "epoch": 0.5467124705279891, "grad_norm": 0.8929304494120546, "learning_rate": 2.5886770630069424e-05, "loss": 0.537, "num_tokens": 306426442.0, "step": 51245 }, { "epoch": 0.5467658135341875, "grad_norm": 0.9164411839575385, "learning_rate": 2.5882811807448827e-05, "loss": 0.6006, "num_tokens": 306445499.0, "step": 51250 }, { "epoch": 0.546819156540386, "grad_norm": 1.4491331420100646, "learning_rate": 2.5878853035151795e-05, "loss": 0.4386, "num_tokens": 306463113.0, "step": 51255 }, { "epoch": 0.5468724995465845, "grad_norm": 0.8258451794031392, "learning_rate": 2.5874894313301528e-05, "loss": 0.554, "num_tokens": 306501242.0, "step": 51260 }, { "epoch": 0.5469258425527829, "grad_norm": 1.0292104136492342, "learning_rate": 2.5870935642021222e-05, "loss": 0.61, "num_tokens": 306534470.0, "step": 51265 }, { "epoch": 0.5469791855589814, "grad_norm": 0.7211827632291236, "learning_rate": 2.5866977021434035e-05, "loss": 0.5051, "num_tokens": 306563973.0, "step": 51270 }, { "epoch": 0.5470325285651798, "grad_norm": 0.9827328373251256, "learning_rate": 2.586301845166318e-05, "loss": 0.4647, "num_tokens": 306593008.0, "step": 51275 }, { "epoch": 0.5470858715713782, "grad_norm": 0.7444981595640294, "learning_rate": 2.585905993283183e-05, "loss": 0.5044, "num_tokens": 306618673.0, "step": 51280 }, { "epoch": 0.5471392145775767, "grad_norm": 0.5829523778319196, "learning_rate": 2.5855101465063157e-05, "loss": 0.5765, "num_tokens": 306666305.0, "step": 51285 }, { "epoch": 0.5471925575837752, "grad_norm": 0.956746889066334, "learning_rate": 2.585114304848035e-05, "loss": 0.6263, "num_tokens": 306701121.0, "step": 51290 }, { "epoch": 0.5472459005899737, "grad_norm": 0.7058700718846783, "learning_rate": 2.5847184683206592e-05, "loss": 0.5647, "num_tokens": 306735327.0, "step": 51295 }, { "epoch": 0.5472992435961721, "grad_norm": 0.9492318359084153, "learning_rate": 2.584322636936505e-05, "loss": 0.5747, "num_tokens": 306763799.0, "step": 51300 }, { "epoch": 0.5473525866023705, "grad_norm": 0.8374091104578107, "learning_rate": 2.5839268107078884e-05, "loss": 0.5586, "num_tokens": 306789768.0, "step": 51305 }, { "epoch": 0.547405929608569, "grad_norm": 1.4084502762453215, "learning_rate": 2.5835309896471304e-05, "loss": 0.5319, "num_tokens": 306825315.0, "step": 51310 }, { "epoch": 0.5474592726147675, "grad_norm": 0.6433599875754232, "learning_rate": 2.5831351737665443e-05, "loss": 0.7786, "num_tokens": 306858378.0, "step": 51315 }, { "epoch": 0.547512615620966, "grad_norm": 1.266889178858642, "learning_rate": 2.58273936307845e-05, "loss": 0.647, "num_tokens": 306883359.0, "step": 51320 }, { "epoch": 0.5475659586271644, "grad_norm": 0.9519103887548359, "learning_rate": 2.5823435575951633e-05, "loss": 0.4954, "num_tokens": 306907199.0, "step": 51325 }, { "epoch": 0.5476193016333628, "grad_norm": 1.0196071154823887, "learning_rate": 2.581947757329e-05, "loss": 0.5094, "num_tokens": 306944107.0, "step": 51330 }, { "epoch": 0.5476726446395613, "grad_norm": 0.9453659833453857, "learning_rate": 2.581551962292278e-05, "loss": 0.6349, "num_tokens": 306969409.0, "step": 51335 }, { "epoch": 0.5477259876457597, "grad_norm": 0.9334862236890423, "learning_rate": 2.5811561724973126e-05, "loss": 0.615, "num_tokens": 306991829.0, "step": 51340 }, { "epoch": 0.5477793306519583, "grad_norm": 0.8874557997600631, "learning_rate": 2.58076038795642e-05, "loss": 0.4993, "num_tokens": 307019716.0, "step": 51345 }, { "epoch": 0.5478326736581567, "grad_norm": 0.7735569353413754, "learning_rate": 2.5803646086819167e-05, "loss": 0.6011, "num_tokens": 307047232.0, "step": 51350 }, { "epoch": 0.5478860166643551, "grad_norm": 1.2421415349387355, "learning_rate": 2.5799688346861185e-05, "loss": 0.5071, "num_tokens": 307069734.0, "step": 51355 }, { "epoch": 0.5479393596705536, "grad_norm": 0.6768266897062851, "learning_rate": 2.5795730659813404e-05, "loss": 0.5061, "num_tokens": 307101894.0, "step": 51360 }, { "epoch": 0.547992702676752, "grad_norm": 0.8542093197652255, "learning_rate": 2.579177302579899e-05, "loss": 0.605, "num_tokens": 307124365.0, "step": 51365 }, { "epoch": 0.5480460456829505, "grad_norm": 0.8823447706273031, "learning_rate": 2.578781544494109e-05, "loss": 0.6004, "num_tokens": 307157849.0, "step": 51370 }, { "epoch": 0.548099388689149, "grad_norm": 1.0159534749162533, "learning_rate": 2.5783857917362857e-05, "loss": 0.541, "num_tokens": 307190812.0, "step": 51375 }, { "epoch": 0.5481527316953474, "grad_norm": 0.8972864410770094, "learning_rate": 2.5779900443187432e-05, "loss": 0.4959, "num_tokens": 307218077.0, "step": 51380 }, { "epoch": 0.5482060747015459, "grad_norm": 0.7394292552824969, "learning_rate": 2.5775943022537984e-05, "loss": 0.6114, "num_tokens": 307252483.0, "step": 51385 }, { "epoch": 0.5482594177077443, "grad_norm": 0.8341861314893988, "learning_rate": 2.5771985655537645e-05, "loss": 0.4592, "num_tokens": 307276861.0, "step": 51390 }, { "epoch": 0.5483127607139427, "grad_norm": 0.8180845232556615, "learning_rate": 2.576802834230956e-05, "loss": 0.5653, "num_tokens": 307308057.0, "step": 51395 }, { "epoch": 0.5483661037201413, "grad_norm": 0.9187820263455307, "learning_rate": 2.5764071082976876e-05, "loss": 0.5125, "num_tokens": 307326767.0, "step": 51400 }, { "epoch": 0.5484194467263397, "grad_norm": 3.719486115915732, "learning_rate": 2.576011387766273e-05, "loss": 0.6695, "num_tokens": 307353938.0, "step": 51405 }, { "epoch": 0.5484727897325382, "grad_norm": 0.795487017112998, "learning_rate": 2.5756156726490264e-05, "loss": 0.5072, "num_tokens": 307385978.0, "step": 51410 }, { "epoch": 0.5485261327387366, "grad_norm": 0.8430356326820945, "learning_rate": 2.5752199629582637e-05, "loss": 0.4362, "num_tokens": 307409550.0, "step": 51415 }, { "epoch": 0.548579475744935, "grad_norm": 1.2525493021793566, "learning_rate": 2.5748242587062947e-05, "loss": 0.501, "num_tokens": 307432387.0, "step": 51420 }, { "epoch": 0.5486328187511336, "grad_norm": 0.8529931949306808, "learning_rate": 2.5744285599054358e-05, "loss": 0.5318, "num_tokens": 307458943.0, "step": 51425 }, { "epoch": 0.548686161757332, "grad_norm": 0.8014487589572659, "learning_rate": 2.5740328665680003e-05, "loss": 0.6152, "num_tokens": 307507430.0, "step": 51430 }, { "epoch": 0.5487395047635305, "grad_norm": 0.7213519665817728, "learning_rate": 2.573637178706299e-05, "loss": 0.4507, "num_tokens": 307526411.0, "step": 51435 }, { "epoch": 0.5487928477697289, "grad_norm": 0.9599984246222153, "learning_rate": 2.5732414963326474e-05, "loss": 0.5399, "num_tokens": 307555820.0, "step": 51440 }, { "epoch": 0.5488461907759273, "grad_norm": 0.7792444946604081, "learning_rate": 2.572845819459357e-05, "loss": 0.469, "num_tokens": 307586571.0, "step": 51445 }, { "epoch": 0.5488995337821259, "grad_norm": 0.6556287141500563, "learning_rate": 2.5724501480987412e-05, "loss": 0.4517, "num_tokens": 307606821.0, "step": 51450 }, { "epoch": 0.5489528767883243, "grad_norm": 1.1071313286483127, "learning_rate": 2.5720544822631116e-05, "loss": 0.4864, "num_tokens": 307637485.0, "step": 51455 }, { "epoch": 0.5490062197945227, "grad_norm": 1.2687843897171924, "learning_rate": 2.5716588219647814e-05, "loss": 0.524, "num_tokens": 307666258.0, "step": 51460 }, { "epoch": 0.5490595628007212, "grad_norm": 1.1047503023218381, "learning_rate": 2.571263167216062e-05, "loss": 0.5186, "num_tokens": 307697840.0, "step": 51465 }, { "epoch": 0.5491129058069196, "grad_norm": 1.0894480850579258, "learning_rate": 2.570867518029266e-05, "loss": 0.4976, "num_tokens": 307731685.0, "step": 51470 }, { "epoch": 0.5491662488131182, "grad_norm": 0.93327293016258, "learning_rate": 2.570471874416705e-05, "loss": 0.498, "num_tokens": 307755293.0, "step": 51475 }, { "epoch": 0.5492195918193166, "grad_norm": 1.7300642349877855, "learning_rate": 2.5700762363906898e-05, "loss": 0.5948, "num_tokens": 307789135.0, "step": 51480 }, { "epoch": 0.549272934825515, "grad_norm": 0.9179297270192546, "learning_rate": 2.569680603963533e-05, "loss": 0.464, "num_tokens": 307823454.0, "step": 51485 }, { "epoch": 0.5493262778317135, "grad_norm": 0.8892214338527227, "learning_rate": 2.5692849771475457e-05, "loss": 0.3644, "num_tokens": 307848673.0, "step": 51490 }, { "epoch": 0.5493796208379119, "grad_norm": 0.5989483865996669, "learning_rate": 2.5688893559550387e-05, "loss": 0.5358, "num_tokens": 307898617.0, "step": 51495 }, { "epoch": 0.5494329638441104, "grad_norm": 1.6744337021402114, "learning_rate": 2.5684937403983223e-05, "loss": 0.4075, "num_tokens": 307907689.0, "step": 51500 }, { "epoch": 0.5494863068503089, "grad_norm": 0.7808254554511311, "learning_rate": 2.568098130489709e-05, "loss": 0.4988, "num_tokens": 307930316.0, "step": 51505 }, { "epoch": 0.5495396498565073, "grad_norm": 0.8218460178148559, "learning_rate": 2.5677025262415066e-05, "loss": 0.7424, "num_tokens": 307952452.0, "step": 51510 }, { "epoch": 0.5495929928627058, "grad_norm": 0.9856914855572448, "learning_rate": 2.567306927666028e-05, "loss": 0.6357, "num_tokens": 307981327.0, "step": 51515 }, { "epoch": 0.5496463358689042, "grad_norm": 0.6471690992623764, "learning_rate": 2.5669113347755834e-05, "loss": 0.5005, "num_tokens": 308025370.0, "step": 51520 }, { "epoch": 0.5496996788751027, "grad_norm": 1.9672472398005934, "learning_rate": 2.566515747582481e-05, "loss": 0.5624, "num_tokens": 308049839.0, "step": 51525 }, { "epoch": 0.5497530218813012, "grad_norm": 0.8201207385985357, "learning_rate": 2.5661201660990313e-05, "loss": 0.4517, "num_tokens": 308077599.0, "step": 51530 }, { "epoch": 0.5498063648874996, "grad_norm": 1.3794663637330011, "learning_rate": 2.5657245903375443e-05, "loss": 0.5881, "num_tokens": 308130152.0, "step": 51535 }, { "epoch": 0.5498597078936981, "grad_norm": 1.1859326763179736, "learning_rate": 2.5653290203103308e-05, "loss": 0.5973, "num_tokens": 308148624.0, "step": 51540 }, { "epoch": 0.5499130508998965, "grad_norm": 0.6458711247919141, "learning_rate": 2.564933456029698e-05, "loss": 0.4989, "num_tokens": 308193686.0, "step": 51545 }, { "epoch": 0.5499663939060949, "grad_norm": 1.0211604557428813, "learning_rate": 2.5645378975079558e-05, "loss": 0.4651, "num_tokens": 308219029.0, "step": 51550 }, { "epoch": 0.5500197369122934, "grad_norm": 2.5667995182127274, "learning_rate": 2.564142344757414e-05, "loss": 0.7917, "num_tokens": 308257308.0, "step": 51555 }, { "epoch": 0.5500730799184919, "grad_norm": 1.698454537143119, "learning_rate": 2.56374679779038e-05, "loss": 0.5656, "num_tokens": 308295004.0, "step": 51560 }, { "epoch": 0.5501264229246904, "grad_norm": 1.159713048336377, "learning_rate": 2.5633512566191625e-05, "loss": 0.5738, "num_tokens": 308314734.0, "step": 51565 }, { "epoch": 0.5501797659308888, "grad_norm": 0.9436680835842981, "learning_rate": 2.5629557212560718e-05, "loss": 0.4554, "num_tokens": 308328688.0, "step": 51570 }, { "epoch": 0.5502331089370872, "grad_norm": 1.066567124909503, "learning_rate": 2.5625601917134146e-05, "loss": 0.6616, "num_tokens": 308350867.0, "step": 51575 }, { "epoch": 0.5502864519432857, "grad_norm": 1.1636987890869495, "learning_rate": 2.5621646680034982e-05, "loss": 0.5371, "num_tokens": 308377147.0, "step": 51580 }, { "epoch": 0.5503397949494842, "grad_norm": 0.8521489144526249, "learning_rate": 2.5617691501386333e-05, "loss": 0.5255, "num_tokens": 308414439.0, "step": 51585 }, { "epoch": 0.5503931379556827, "grad_norm": 2.0306863327341325, "learning_rate": 2.5613736381311245e-05, "loss": 0.4663, "num_tokens": 308437370.0, "step": 51590 }, { "epoch": 0.5504464809618811, "grad_norm": 1.071139623393641, "learning_rate": 2.5609781319932806e-05, "loss": 0.4574, "num_tokens": 308461263.0, "step": 51595 }, { "epoch": 0.5504998239680795, "grad_norm": 0.7850457026975141, "learning_rate": 2.56058263173741e-05, "loss": 0.4661, "num_tokens": 308503184.0, "step": 51600 }, { "epoch": 0.550553166974278, "grad_norm": 1.8536126643449562, "learning_rate": 2.5601871373758174e-05, "loss": 0.5919, "num_tokens": 308521437.0, "step": 51605 }, { "epoch": 0.5506065099804764, "grad_norm": 0.6341300949111454, "learning_rate": 2.559791648920812e-05, "loss": 0.6387, "num_tokens": 308550097.0, "step": 51610 }, { "epoch": 0.550659852986675, "grad_norm": 0.6896187623796569, "learning_rate": 2.5593961663846998e-05, "loss": 0.524, "num_tokens": 308592260.0, "step": 51615 }, { "epoch": 0.5507131959928734, "grad_norm": 0.8837541945552088, "learning_rate": 2.5590006897797875e-05, "loss": 0.4847, "num_tokens": 308616218.0, "step": 51620 }, { "epoch": 0.5507665389990718, "grad_norm": 0.7612066643994709, "learning_rate": 2.5586052191183807e-05, "loss": 0.4883, "num_tokens": 308665017.0, "step": 51625 }, { "epoch": 0.5508198820052703, "grad_norm": 1.6765276717137942, "learning_rate": 2.5582097544127876e-05, "loss": 0.5671, "num_tokens": 308685008.0, "step": 51630 }, { "epoch": 0.5508732250114687, "grad_norm": 0.7362201569214505, "learning_rate": 2.5578142956753116e-05, "loss": 0.5753, "num_tokens": 308714531.0, "step": 51635 }, { "epoch": 0.5509265680176672, "grad_norm": 0.740585101052779, "learning_rate": 2.55741884291826e-05, "loss": 0.4564, "num_tokens": 308737469.0, "step": 51640 }, { "epoch": 0.5509799110238657, "grad_norm": 1.1211021644398473, "learning_rate": 2.5570233961539396e-05, "loss": 0.4934, "num_tokens": 308757390.0, "step": 51645 }, { "epoch": 0.5510332540300641, "grad_norm": 0.7457811061099435, "learning_rate": 2.5566279553946543e-05, "loss": 0.5121, "num_tokens": 308790695.0, "step": 51650 }, { "epoch": 0.5510865970362626, "grad_norm": 1.0781317808102377, "learning_rate": 2.5562325206527093e-05, "loss": 0.373, "num_tokens": 308809717.0, "step": 51655 }, { "epoch": 0.551139940042461, "grad_norm": 1.3722538702199547, "learning_rate": 2.5558370919404114e-05, "loss": 0.5318, "num_tokens": 308836026.0, "step": 51660 }, { "epoch": 0.5511932830486594, "grad_norm": 0.7730363563884638, "learning_rate": 2.5554416692700635e-05, "loss": 0.4917, "num_tokens": 308880678.0, "step": 51665 }, { "epoch": 0.551246626054858, "grad_norm": 0.8366477925960809, "learning_rate": 2.5550462526539703e-05, "loss": 0.5407, "num_tokens": 308911494.0, "step": 51670 }, { "epoch": 0.5512999690610564, "grad_norm": 0.7810156234985309, "learning_rate": 2.554650842104439e-05, "loss": 0.5338, "num_tokens": 308946146.0, "step": 51675 }, { "epoch": 0.5513533120672549, "grad_norm": 1.570253985093806, "learning_rate": 2.5542554376337717e-05, "loss": 0.5281, "num_tokens": 308978936.0, "step": 51680 }, { "epoch": 0.5514066550734533, "grad_norm": 1.822153154489375, "learning_rate": 2.5538600392542728e-05, "loss": 0.5653, "num_tokens": 309013664.0, "step": 51685 }, { "epoch": 0.5514599980796517, "grad_norm": 0.7488343080996421, "learning_rate": 2.553464646978247e-05, "loss": 0.4598, "num_tokens": 309040030.0, "step": 51690 }, { "epoch": 0.5515133410858503, "grad_norm": 0.7467728037779037, "learning_rate": 2.5530692608179967e-05, "loss": 0.5178, "num_tokens": 309071597.0, "step": 51695 }, { "epoch": 0.5515666840920487, "grad_norm": 0.7759221748101602, "learning_rate": 2.5526738807858275e-05, "loss": 0.5143, "num_tokens": 309098262.0, "step": 51700 }, { "epoch": 0.5516200270982472, "grad_norm": 0.8464967902094588, "learning_rate": 2.552278506894042e-05, "loss": 0.4429, "num_tokens": 309126606.0, "step": 51705 }, { "epoch": 0.5516733701044456, "grad_norm": 0.5913675751742897, "learning_rate": 2.5518831391549425e-05, "loss": 0.5739, "num_tokens": 309173500.0, "step": 51710 }, { "epoch": 0.551726713110644, "grad_norm": 0.6203822353506572, "learning_rate": 2.551487777580833e-05, "loss": 0.5147, "num_tokens": 309204244.0, "step": 51715 }, { "epoch": 0.5517800561168426, "grad_norm": 0.7575149017000908, "learning_rate": 2.5510924221840164e-05, "loss": 0.5128, "num_tokens": 309232038.0, "step": 51720 }, { "epoch": 0.551833399123041, "grad_norm": 0.5161054017028662, "learning_rate": 2.5506970729767944e-05, "loss": 0.4835, "num_tokens": 309282286.0, "step": 51725 }, { "epoch": 0.5518867421292394, "grad_norm": 0.7799012956571176, "learning_rate": 2.5503017299714703e-05, "loss": 0.4906, "num_tokens": 309321499.0, "step": 51730 }, { "epoch": 0.5519400851354379, "grad_norm": 0.9157133887015758, "learning_rate": 2.549906393180347e-05, "loss": 0.5744, "num_tokens": 309346293.0, "step": 51735 }, { "epoch": 0.5519934281416363, "grad_norm": 0.8014730853610296, "learning_rate": 2.5495110626157248e-05, "loss": 0.5608, "num_tokens": 309369403.0, "step": 51740 }, { "epoch": 0.5520467711478348, "grad_norm": 0.9077212330085326, "learning_rate": 2.5491157382899062e-05, "loss": 0.465, "num_tokens": 309400503.0, "step": 51745 }, { "epoch": 0.5521001141540333, "grad_norm": 0.8359994823663669, "learning_rate": 2.5487204202151948e-05, "loss": 0.5648, "num_tokens": 309420712.0, "step": 51750 }, { "epoch": 0.5521534571602317, "grad_norm": 1.3143646857234055, "learning_rate": 2.5483251084038895e-05, "loss": 0.4991, "num_tokens": 309449644.0, "step": 51755 }, { "epoch": 0.5522068001664302, "grad_norm": 0.6614283107006178, "learning_rate": 2.5479298028682917e-05, "loss": 0.5968, "num_tokens": 309488172.0, "step": 51760 }, { "epoch": 0.5522601431726286, "grad_norm": 0.7537745824974935, "learning_rate": 2.547534503620705e-05, "loss": 0.5837, "num_tokens": 309531083.0, "step": 51765 }, { "epoch": 0.5523134861788271, "grad_norm": 0.5765431257602115, "learning_rate": 2.5471392106734276e-05, "loss": 0.4235, "num_tokens": 309569843.0, "step": 51770 }, { "epoch": 0.5523668291850256, "grad_norm": 0.9460786956475085, "learning_rate": 2.5467439240387614e-05, "loss": 0.7208, "num_tokens": 309609302.0, "step": 51775 }, { "epoch": 0.552420172191224, "grad_norm": 1.3111103763838348, "learning_rate": 2.546348643729008e-05, "loss": 0.5074, "num_tokens": 309631807.0, "step": 51780 }, { "epoch": 0.5524735151974225, "grad_norm": 0.9026708652348663, "learning_rate": 2.5459533697564645e-05, "loss": 0.449, "num_tokens": 309661094.0, "step": 51785 }, { "epoch": 0.5525268582036209, "grad_norm": 0.6314939778879166, "learning_rate": 2.545558102133434e-05, "loss": 0.5412, "num_tokens": 309690550.0, "step": 51790 }, { "epoch": 0.5525802012098194, "grad_norm": 1.2456467241834919, "learning_rate": 2.545162840872216e-05, "loss": 0.5428, "num_tokens": 309715633.0, "step": 51795 }, { "epoch": 0.5526335442160178, "grad_norm": 0.7839656527860454, "learning_rate": 2.544767585985109e-05, "loss": 0.4707, "num_tokens": 309735839.0, "step": 51800 }, { "epoch": 0.5526868872222163, "grad_norm": 0.9552846581829247, "learning_rate": 2.5443723374844132e-05, "loss": 0.5672, "num_tokens": 309760633.0, "step": 51805 }, { "epoch": 0.5527402302284148, "grad_norm": 0.8718473644476121, "learning_rate": 2.5439770953824277e-05, "loss": 0.6008, "num_tokens": 309800188.0, "step": 51810 }, { "epoch": 0.5527935732346132, "grad_norm": 0.6726647098788607, "learning_rate": 2.5435818596914523e-05, "loss": 0.4533, "num_tokens": 309816688.0, "step": 51815 }, { "epoch": 0.5528469162408116, "grad_norm": 1.3992203886081032, "learning_rate": 2.5431866304237846e-05, "loss": 0.5159, "num_tokens": 309833880.0, "step": 51820 }, { "epoch": 0.5529002592470101, "grad_norm": 0.7489743699001874, "learning_rate": 2.542791407591725e-05, "loss": 0.3972, "num_tokens": 309866235.0, "step": 51825 }, { "epoch": 0.5529536022532086, "grad_norm": 1.0591836728966058, "learning_rate": 2.5423961912075712e-05, "loss": 0.5124, "num_tokens": 309893732.0, "step": 51830 }, { "epoch": 0.5530069452594071, "grad_norm": 1.0507009512790366, "learning_rate": 2.5420009812836203e-05, "loss": 0.483, "num_tokens": 309933493.0, "step": 51835 }, { "epoch": 0.5530602882656055, "grad_norm": 1.1858319112158677, "learning_rate": 2.5416057778321734e-05, "loss": 0.4774, "num_tokens": 309952008.0, "step": 51840 }, { "epoch": 0.5531136312718039, "grad_norm": 0.7595876013339015, "learning_rate": 2.5412105808655257e-05, "loss": 0.5174, "num_tokens": 309982861.0, "step": 51845 }, { "epoch": 0.5531669742780024, "grad_norm": 0.715587597329581, "learning_rate": 2.540815390395975e-05, "loss": 0.568, "num_tokens": 310028005.0, "step": 51850 }, { "epoch": 0.5532203172842008, "grad_norm": 0.6406361584821724, "learning_rate": 2.5404202064358212e-05, "loss": 0.4154, "num_tokens": 310056908.0, "step": 51855 }, { "epoch": 0.5532736602903994, "grad_norm": 0.6957356822888208, "learning_rate": 2.5400250289973593e-05, "loss": 0.4722, "num_tokens": 310087790.0, "step": 51860 }, { "epoch": 0.5533270032965978, "grad_norm": 0.8599394167385332, "learning_rate": 2.5396298580928874e-05, "loss": 0.4186, "num_tokens": 310117692.0, "step": 51865 }, { "epoch": 0.5533803463027962, "grad_norm": 0.8331407501796965, "learning_rate": 2.5392346937347022e-05, "loss": 0.5043, "num_tokens": 310154061.0, "step": 51870 }, { "epoch": 0.5534336893089947, "grad_norm": 5.662874478215817, "learning_rate": 2.5388395359351003e-05, "loss": 0.67, "num_tokens": 310169751.0, "step": 51875 }, { "epoch": 0.5534870323151931, "grad_norm": 1.1952637107049462, "learning_rate": 2.5384443847063784e-05, "loss": 0.3796, "num_tokens": 310193083.0, "step": 51880 }, { "epoch": 0.5535403753213917, "grad_norm": 0.6706012153208308, "learning_rate": 2.538049240060833e-05, "loss": 0.4652, "num_tokens": 310220104.0, "step": 51885 }, { "epoch": 0.5535937183275901, "grad_norm": 1.0944697018649412, "learning_rate": 2.5376541020107592e-05, "loss": 0.4198, "num_tokens": 310240190.0, "step": 51890 }, { "epoch": 0.5536470613337885, "grad_norm": 1.9364416170576486, "learning_rate": 2.5372589705684536e-05, "loss": 0.542, "num_tokens": 310281704.0, "step": 51895 }, { "epoch": 0.553700404339987, "grad_norm": 0.8100143058058775, "learning_rate": 2.536863845746213e-05, "loss": 0.5409, "num_tokens": 310321160.0, "step": 51900 }, { "epoch": 0.5537537473461854, "grad_norm": 1.4317315431602324, "learning_rate": 2.5364687275563303e-05, "loss": 0.4806, "num_tokens": 310346709.0, "step": 51905 }, { "epoch": 0.5538070903523838, "grad_norm": 0.9161660399243478, "learning_rate": 2.5360736160111027e-05, "loss": 0.5396, "num_tokens": 310375048.0, "step": 51910 }, { "epoch": 0.5538604333585824, "grad_norm": 0.9699014224695768, "learning_rate": 2.5356785111228253e-05, "loss": 0.5218, "num_tokens": 310411582.0, "step": 51915 }, { "epoch": 0.5539137763647808, "grad_norm": 0.7219903185732848, "learning_rate": 2.5352834129037923e-05, "loss": 0.5433, "num_tokens": 310442359.0, "step": 51920 }, { "epoch": 0.5539671193709793, "grad_norm": 1.0574084380942368, "learning_rate": 2.534888321366297e-05, "loss": 0.4762, "num_tokens": 310473235.0, "step": 51925 }, { "epoch": 0.5540204623771777, "grad_norm": 1.0049113556494254, "learning_rate": 2.5344932365226376e-05, "loss": 0.5134, "num_tokens": 310508316.0, "step": 51930 }, { "epoch": 0.5540738053833761, "grad_norm": 1.4392054657328328, "learning_rate": 2.5340981583851044e-05, "loss": 0.5914, "num_tokens": 310532434.0, "step": 51935 }, { "epoch": 0.5541271483895747, "grad_norm": 1.3089950845229477, "learning_rate": 2.5337030869659935e-05, "loss": 0.4797, "num_tokens": 310563574.0, "step": 51940 }, { "epoch": 0.5541804913957731, "grad_norm": 0.7865799951770083, "learning_rate": 2.5333080222775986e-05, "loss": 0.4686, "num_tokens": 310588853.0, "step": 51945 }, { "epoch": 0.5542338344019716, "grad_norm": 0.8288794430146108, "learning_rate": 2.532912964332212e-05, "loss": 0.5158, "num_tokens": 310612270.0, "step": 51950 }, { "epoch": 0.55428717740817, "grad_norm": 1.3981829903883807, "learning_rate": 2.5325179131421284e-05, "loss": 0.4357, "num_tokens": 310657484.0, "step": 51955 }, { "epoch": 0.5543405204143684, "grad_norm": 1.459856401530927, "learning_rate": 2.5321228687196415e-05, "loss": 0.4993, "num_tokens": 310679914.0, "step": 51960 }, { "epoch": 0.554393863420567, "grad_norm": 1.229943292452677, "learning_rate": 2.531727831077042e-05, "loss": 0.6283, "num_tokens": 310700588.0, "step": 51965 }, { "epoch": 0.5544472064267654, "grad_norm": 1.2861886474388706, "learning_rate": 2.5313328002266247e-05, "loss": 0.6334, "num_tokens": 310739873.0, "step": 51970 }, { "epoch": 0.5545005494329639, "grad_norm": 0.8282040232429863, "learning_rate": 2.5309377761806826e-05, "loss": 0.6018, "num_tokens": 310792042.0, "step": 51975 }, { "epoch": 0.5545538924391623, "grad_norm": 0.9196184548031242, "learning_rate": 2.530542758951505e-05, "loss": 0.3313, "num_tokens": 310807024.0, "step": 51980 }, { "epoch": 0.5546072354453607, "grad_norm": 0.7389053058954858, "learning_rate": 2.5301477485513863e-05, "loss": 0.472, "num_tokens": 310829028.0, "step": 51985 }, { "epoch": 0.5546605784515592, "grad_norm": 1.4818114921762289, "learning_rate": 2.5297527449926195e-05, "loss": 0.5651, "num_tokens": 310853577.0, "step": 51990 }, { "epoch": 0.5547139214577577, "grad_norm": 1.7616472015091542, "learning_rate": 2.5293577482874935e-05, "loss": 0.4957, "num_tokens": 310870516.0, "step": 51995 }, { "epoch": 0.5547672644639561, "grad_norm": 1.0820352085339802, "learning_rate": 2.5289627584483016e-05, "loss": 0.5036, "num_tokens": 310895725.0, "step": 52000 }, { "epoch": 0.5548206074701546, "grad_norm": 1.1959822015902744, "learning_rate": 2.5285677754873355e-05, "loss": 0.5184, "num_tokens": 310914716.0, "step": 52005 }, { "epoch": 0.554873950476353, "grad_norm": 1.0009165010912218, "learning_rate": 2.528172799416884e-05, "loss": 0.5962, "num_tokens": 310933986.0, "step": 52010 }, { "epoch": 0.5549272934825515, "grad_norm": 0.8726836921152515, "learning_rate": 2.52777783024924e-05, "loss": 0.5691, "num_tokens": 310965415.0, "step": 52015 }, { "epoch": 0.55498063648875, "grad_norm": 0.5990063055449534, "learning_rate": 2.527382867996694e-05, "loss": 0.5377, "num_tokens": 311005124.0, "step": 52020 }, { "epoch": 0.5550339794949484, "grad_norm": 0.7939480355072221, "learning_rate": 2.5269879126715346e-05, "loss": 0.4879, "num_tokens": 311032131.0, "step": 52025 }, { "epoch": 0.5550873225011469, "grad_norm": 1.6558314515373898, "learning_rate": 2.5265929642860542e-05, "loss": 0.6169, "num_tokens": 311067109.0, "step": 52030 }, { "epoch": 0.5551406655073453, "grad_norm": 1.8170029514670876, "learning_rate": 2.526198022852542e-05, "loss": 0.5487, "num_tokens": 311096209.0, "step": 52035 }, { "epoch": 0.5551940085135438, "grad_norm": 0.6820640706690294, "learning_rate": 2.5258030883832866e-05, "loss": 0.508, "num_tokens": 311117740.0, "step": 52040 }, { "epoch": 0.5552473515197422, "grad_norm": 0.8540851249069034, "learning_rate": 2.5254081608905793e-05, "loss": 0.5047, "num_tokens": 311160167.0, "step": 52045 }, { "epoch": 0.5553006945259407, "grad_norm": 0.8452063705750147, "learning_rate": 2.5250132403867093e-05, "loss": 0.4163, "num_tokens": 311189829.0, "step": 52050 }, { "epoch": 0.5553540375321392, "grad_norm": 0.780479876185404, "learning_rate": 2.524618326883964e-05, "loss": 0.5166, "num_tokens": 311219170.0, "step": 52055 }, { "epoch": 0.5554073805383376, "grad_norm": 1.0969227924056655, "learning_rate": 2.5242234203946337e-05, "loss": 0.4554, "num_tokens": 311242180.0, "step": 52060 }, { "epoch": 0.5554607235445361, "grad_norm": 2.274433488956225, "learning_rate": 2.523828520931007e-05, "loss": 0.6351, "num_tokens": 311274006.0, "step": 52065 }, { "epoch": 0.5555140665507345, "grad_norm": 1.0293292092277027, "learning_rate": 2.523433628505372e-05, "loss": 0.5406, "num_tokens": 311296754.0, "step": 52070 }, { "epoch": 0.555567409556933, "grad_norm": 0.9116801904824893, "learning_rate": 2.5230387431300174e-05, "loss": 0.6229, "num_tokens": 311338068.0, "step": 52075 }, { "epoch": 0.5556207525631315, "grad_norm": 0.7499374559959535, "learning_rate": 2.522643864817231e-05, "loss": 0.5168, "num_tokens": 311381277.0, "step": 52080 }, { "epoch": 0.5556740955693299, "grad_norm": 1.2025359789610282, "learning_rate": 2.5222489935793002e-05, "loss": 0.5822, "num_tokens": 311410464.0, "step": 52085 }, { "epoch": 0.5557274385755283, "grad_norm": 0.7318257509343669, "learning_rate": 2.5218541294285126e-05, "loss": 0.4945, "num_tokens": 311460963.0, "step": 52090 }, { "epoch": 0.5557807815817268, "grad_norm": 1.4601319735901008, "learning_rate": 2.521459272377157e-05, "loss": 0.5054, "num_tokens": 311503445.0, "step": 52095 }, { "epoch": 0.5558341245879252, "grad_norm": 0.8134223007522521, "learning_rate": 2.5210644224375178e-05, "loss": 0.5076, "num_tokens": 311534686.0, "step": 52100 }, { "epoch": 0.5558874675941238, "grad_norm": 0.7868901115020431, "learning_rate": 2.5206695796218845e-05, "loss": 0.5374, "num_tokens": 311558452.0, "step": 52105 }, { "epoch": 0.5559408106003222, "grad_norm": 0.6724642813186773, "learning_rate": 2.5202747439425433e-05, "loss": 0.4877, "num_tokens": 311601757.0, "step": 52110 }, { "epoch": 0.5559941536065206, "grad_norm": 0.6432486824469646, "learning_rate": 2.519879915411779e-05, "loss": 0.5985, "num_tokens": 311632161.0, "step": 52115 }, { "epoch": 0.5560474966127191, "grad_norm": 1.5326514839853242, "learning_rate": 2.5194850940418795e-05, "loss": 0.5026, "num_tokens": 311649999.0, "step": 52120 }, { "epoch": 0.5561008396189175, "grad_norm": 0.7283081559337804, "learning_rate": 2.5190902798451317e-05, "loss": 0.4895, "num_tokens": 311681868.0, "step": 52125 }, { "epoch": 0.5561541826251161, "grad_norm": 1.45701694877958, "learning_rate": 2.5186954728338182e-05, "loss": 0.412, "num_tokens": 311709971.0, "step": 52130 }, { "epoch": 0.5562075256313145, "grad_norm": 1.3272311992593022, "learning_rate": 2.5183006730202268e-05, "loss": 0.5238, "num_tokens": 311734572.0, "step": 52135 }, { "epoch": 0.5562608686375129, "grad_norm": 0.7764367931764842, "learning_rate": 2.517905880416644e-05, "loss": 0.516, "num_tokens": 311768069.0, "step": 52140 }, { "epoch": 0.5563142116437114, "grad_norm": 0.9608424343184188, "learning_rate": 2.517511095035352e-05, "loss": 0.4267, "num_tokens": 311782419.0, "step": 52145 }, { "epoch": 0.5563675546499098, "grad_norm": 1.4359691399825327, "learning_rate": 2.5171163168886368e-05, "loss": 0.4286, "num_tokens": 311804864.0, "step": 52150 }, { "epoch": 0.5564208976561084, "grad_norm": 0.8574948471104081, "learning_rate": 2.516721545988785e-05, "loss": 0.5563, "num_tokens": 311842850.0, "step": 52155 }, { "epoch": 0.5564742406623068, "grad_norm": 1.1178547022918226, "learning_rate": 2.5163267823480786e-05, "loss": 0.4441, "num_tokens": 311856787.0, "step": 52160 }, { "epoch": 0.5565275836685052, "grad_norm": 0.7262946319254109, "learning_rate": 2.5159320259788027e-05, "loss": 0.4977, "num_tokens": 311890559.0, "step": 52165 }, { "epoch": 0.5565809266747037, "grad_norm": 4.608719791839794, "learning_rate": 2.5155372768932416e-05, "loss": 0.4933, "num_tokens": 311913333.0, "step": 52170 }, { "epoch": 0.5566342696809021, "grad_norm": 1.0588080324673304, "learning_rate": 2.515142535103679e-05, "loss": 0.5195, "num_tokens": 311935801.0, "step": 52175 }, { "epoch": 0.5566876126871005, "grad_norm": 0.8226657841133388, "learning_rate": 2.514747800622398e-05, "loss": 0.4305, "num_tokens": 311955944.0, "step": 52180 }, { "epoch": 0.5567409556932991, "grad_norm": 1.1132966105676838, "learning_rate": 2.5143530734616828e-05, "loss": 0.5785, "num_tokens": 311986388.0, "step": 52185 }, { "epoch": 0.5567942986994975, "grad_norm": 0.8034702969336727, "learning_rate": 2.5139583536338148e-05, "loss": 0.4931, "num_tokens": 312019050.0, "step": 52190 }, { "epoch": 0.556847641705696, "grad_norm": 0.5683449790439797, "learning_rate": 2.5135636411510787e-05, "loss": 0.615, "num_tokens": 312058588.0, "step": 52195 }, { "epoch": 0.5569009847118944, "grad_norm": 0.7445051640906696, "learning_rate": 2.5131689360257565e-05, "loss": 0.5852, "num_tokens": 312097214.0, "step": 52200 }, { "epoch": 0.5569543277180928, "grad_norm": 0.9781236542121349, "learning_rate": 2.51277423827013e-05, "loss": 0.509, "num_tokens": 312146756.0, "step": 52205 }, { "epoch": 0.5570076707242914, "grad_norm": 0.8497033284438378, "learning_rate": 2.512379547896483e-05, "loss": 0.5867, "num_tokens": 312182832.0, "step": 52210 }, { "epoch": 0.5570610137304898, "grad_norm": 1.2574835530382642, "learning_rate": 2.5119848649170965e-05, "loss": 0.4848, "num_tokens": 312210927.0, "step": 52215 }, { "epoch": 0.5571143567366883, "grad_norm": 1.2528814592374644, "learning_rate": 2.5115901893442506e-05, "loss": 0.5221, "num_tokens": 312234964.0, "step": 52220 }, { "epoch": 0.5571676997428867, "grad_norm": 0.8490509531356113, "learning_rate": 2.5111955211902283e-05, "loss": 0.5318, "num_tokens": 312265107.0, "step": 52225 }, { "epoch": 0.5572210427490851, "grad_norm": 1.2787000819563572, "learning_rate": 2.5108008604673124e-05, "loss": 0.6641, "num_tokens": 312286259.0, "step": 52230 }, { "epoch": 0.5572743857552837, "grad_norm": 1.0376209349694914, "learning_rate": 2.5104062071877815e-05, "loss": 0.5328, "num_tokens": 312316577.0, "step": 52235 }, { "epoch": 0.5573277287614821, "grad_norm": 1.5334034719660028, "learning_rate": 2.510011561363917e-05, "loss": 0.5216, "num_tokens": 312360418.0, "step": 52240 }, { "epoch": 0.5573810717676806, "grad_norm": 0.7307963610653252, "learning_rate": 2.5096169230080004e-05, "loss": 0.6513, "num_tokens": 312376883.0, "step": 52245 }, { "epoch": 0.557434414773879, "grad_norm": 0.8883308171619438, "learning_rate": 2.509222292132311e-05, "loss": 0.4455, "num_tokens": 312394745.0, "step": 52250 }, { "epoch": 0.5574877577800774, "grad_norm": 1.0760745543960095, "learning_rate": 2.5088276687491292e-05, "loss": 0.5079, "num_tokens": 312431601.0, "step": 52255 }, { "epoch": 0.557541100786276, "grad_norm": 0.955178600091085, "learning_rate": 2.5084330528707356e-05, "loss": 0.4855, "num_tokens": 312465858.0, "step": 52260 }, { "epoch": 0.5575944437924744, "grad_norm": 1.2176594218769057, "learning_rate": 2.5080384445094087e-05, "loss": 0.3962, "num_tokens": 312486193.0, "step": 52265 }, { "epoch": 0.5576477867986728, "grad_norm": 0.9410328959723261, "learning_rate": 2.5076438436774284e-05, "loss": 0.6773, "num_tokens": 312521776.0, "step": 52270 }, { "epoch": 0.5577011298048713, "grad_norm": 0.8995846668594013, "learning_rate": 2.5072492503870748e-05, "loss": 0.5494, "num_tokens": 312538237.0, "step": 52275 }, { "epoch": 0.5577544728110697, "grad_norm": 1.3286194836559804, "learning_rate": 2.506854664650624e-05, "loss": 0.621, "num_tokens": 312567608.0, "step": 52280 }, { "epoch": 0.5578078158172682, "grad_norm": 1.1779568498540791, "learning_rate": 2.5064600864803577e-05, "loss": 0.3971, "num_tokens": 312584825.0, "step": 52285 }, { "epoch": 0.5578611588234667, "grad_norm": 1.1841336190459812, "learning_rate": 2.5060655158885545e-05, "loss": 0.4233, "num_tokens": 312605987.0, "step": 52290 }, { "epoch": 0.5579145018296651, "grad_norm": 0.7188143070209335, "learning_rate": 2.5056709528874895e-05, "loss": 0.4559, "num_tokens": 312631782.0, "step": 52295 }, { "epoch": 0.5579678448358636, "grad_norm": 0.9638211635531542, "learning_rate": 2.5052763974894435e-05, "loss": 0.5111, "num_tokens": 312654771.0, "step": 52300 }, { "epoch": 0.558021187842062, "grad_norm": 0.8411406346485307, "learning_rate": 2.5048818497066935e-05, "loss": 0.4631, "num_tokens": 312674989.0, "step": 52305 }, { "epoch": 0.5580745308482605, "grad_norm": 1.8596021180722695, "learning_rate": 2.504487309551516e-05, "loss": 0.5041, "num_tokens": 312701464.0, "step": 52310 }, { "epoch": 0.558127873854459, "grad_norm": 0.8031708672011548, "learning_rate": 2.504092777036189e-05, "loss": 0.5746, "num_tokens": 312732200.0, "step": 52315 }, { "epoch": 0.5581812168606574, "grad_norm": 1.770541138321745, "learning_rate": 2.503698252172991e-05, "loss": 0.6295, "num_tokens": 312757412.0, "step": 52320 }, { "epoch": 0.5582345598668559, "grad_norm": 0.834348135427546, "learning_rate": 2.503303734974196e-05, "loss": 0.5938, "num_tokens": 312790942.0, "step": 52325 }, { "epoch": 0.5582879028730543, "grad_norm": 0.6800993507105006, "learning_rate": 2.5029092254520826e-05, "loss": 0.5231, "num_tokens": 312821803.0, "step": 52330 }, { "epoch": 0.5583412458792528, "grad_norm": 1.0228997127452055, "learning_rate": 2.5025147236189273e-05, "loss": 0.4761, "num_tokens": 312846875.0, "step": 52335 }, { "epoch": 0.5583945888854512, "grad_norm": 0.7258591762647699, "learning_rate": 2.5021202294870044e-05, "loss": 0.4422, "num_tokens": 312871544.0, "step": 52340 }, { "epoch": 0.5584479318916497, "grad_norm": 1.4158511650422132, "learning_rate": 2.5017257430685907e-05, "loss": 0.4705, "num_tokens": 312906129.0, "step": 52345 }, { "epoch": 0.5585012748978482, "grad_norm": 1.2490366396359542, "learning_rate": 2.5013312643759635e-05, "loss": 0.4947, "num_tokens": 312926975.0, "step": 52350 }, { "epoch": 0.5585546179040466, "grad_norm": 0.8042285609500065, "learning_rate": 2.500936793421395e-05, "loss": 0.4231, "num_tokens": 312952019.0, "step": 52355 }, { "epoch": 0.558607960910245, "grad_norm": 1.2768924377041597, "learning_rate": 2.500542330217162e-05, "loss": 0.4948, "num_tokens": 312980228.0, "step": 52360 }, { "epoch": 0.5586613039164435, "grad_norm": 1.4876529750334813, "learning_rate": 2.5001478747755408e-05, "loss": 0.5631, "num_tokens": 313006823.0, "step": 52365 }, { "epoch": 0.5587146469226419, "grad_norm": 0.8542283688757496, "learning_rate": 2.4997534271088025e-05, "loss": 0.4419, "num_tokens": 313027969.0, "step": 52370 }, { "epoch": 0.5587679899288405, "grad_norm": 0.789552324323691, "learning_rate": 2.4993589872292246e-05, "loss": 0.4991, "num_tokens": 313062726.0, "step": 52375 }, { "epoch": 0.5588213329350389, "grad_norm": 0.8104940872686137, "learning_rate": 2.4989645551490807e-05, "loss": 0.3641, "num_tokens": 313087954.0, "step": 52380 }, { "epoch": 0.5588746759412373, "grad_norm": 4.630628476405275, "learning_rate": 2.498570130880643e-05, "loss": 0.527, "num_tokens": 313102920.0, "step": 52385 }, { "epoch": 0.5589280189474358, "grad_norm": 0.8205988531603744, "learning_rate": 2.4981757144361866e-05, "loss": 0.6135, "num_tokens": 313146292.0, "step": 52390 }, { "epoch": 0.5589813619536342, "grad_norm": 0.7018429920796385, "learning_rate": 2.4977813058279853e-05, "loss": 0.4653, "num_tokens": 313170602.0, "step": 52395 }, { "epoch": 0.5590347049598328, "grad_norm": 0.9358849227541319, "learning_rate": 2.4973869050683114e-05, "loss": 0.6171, "num_tokens": 313193752.0, "step": 52400 }, { "epoch": 0.5590880479660312, "grad_norm": 1.2294557404769324, "learning_rate": 2.4969925121694377e-05, "loss": 0.4654, "num_tokens": 313224655.0, "step": 52405 }, { "epoch": 0.5591413909722296, "grad_norm": 0.8643546163210312, "learning_rate": 2.4965981271436383e-05, "loss": 0.6113, "num_tokens": 313259889.0, "step": 52410 }, { "epoch": 0.5591947339784281, "grad_norm": 0.6202902786639031, "learning_rate": 2.4962037500031843e-05, "loss": 0.5183, "num_tokens": 313309808.0, "step": 52415 }, { "epoch": 0.5592480769846265, "grad_norm": 1.2484847929854894, "learning_rate": 2.4958093807603477e-05, "loss": 0.5364, "num_tokens": 313347636.0, "step": 52420 }, { "epoch": 0.559301419990825, "grad_norm": 2.125537251553075, "learning_rate": 2.495415019427402e-05, "loss": 0.5446, "num_tokens": 313384242.0, "step": 52425 }, { "epoch": 0.5593547629970235, "grad_norm": 0.9200321099345004, "learning_rate": 2.4950206660166176e-05, "loss": 0.3996, "num_tokens": 313407771.0, "step": 52430 }, { "epoch": 0.5594081060032219, "grad_norm": 0.8119297638990343, "learning_rate": 2.4946263205402658e-05, "loss": 0.4842, "num_tokens": 313441182.0, "step": 52435 }, { "epoch": 0.5594614490094204, "grad_norm": 0.7282790336611629, "learning_rate": 2.4942319830106192e-05, "loss": 0.5014, "num_tokens": 313469871.0, "step": 52440 }, { "epoch": 0.5595147920156188, "grad_norm": 1.7836977351643102, "learning_rate": 2.4938376534399472e-05, "loss": 0.5277, "num_tokens": 313489090.0, "step": 52445 }, { "epoch": 0.5595681350218172, "grad_norm": 0.6963386401121391, "learning_rate": 2.4934433318405214e-05, "loss": 0.6506, "num_tokens": 313537256.0, "step": 52450 }, { "epoch": 0.5596214780280158, "grad_norm": 0.6962785919913995, "learning_rate": 2.4930490182246126e-05, "loss": 0.4718, "num_tokens": 313558538.0, "step": 52455 }, { "epoch": 0.5596748210342142, "grad_norm": 1.0212087169724242, "learning_rate": 2.4926547126044897e-05, "loss": 0.5551, "num_tokens": 313597994.0, "step": 52460 }, { "epoch": 0.5597281640404127, "grad_norm": 0.7886847141455312, "learning_rate": 2.4922604149924244e-05, "loss": 0.5749, "num_tokens": 313629263.0, "step": 52465 }, { "epoch": 0.5597815070466111, "grad_norm": 1.0057483699370091, "learning_rate": 2.4918661254006843e-05, "loss": 0.5462, "num_tokens": 313655673.0, "step": 52470 }, { "epoch": 0.5598348500528095, "grad_norm": 1.7313362036529614, "learning_rate": 2.4914718438415417e-05, "loss": 0.6378, "num_tokens": 313685883.0, "step": 52475 }, { "epoch": 0.559888193059008, "grad_norm": 0.8251974400172045, "learning_rate": 2.4910775703272632e-05, "loss": 0.4601, "num_tokens": 313725489.0, "step": 52480 }, { "epoch": 0.5599415360652065, "grad_norm": 0.8739280011402174, "learning_rate": 2.4906833048701193e-05, "loss": 0.5254, "num_tokens": 313750975.0, "step": 52485 }, { "epoch": 0.559994879071405, "grad_norm": 0.8721144043219505, "learning_rate": 2.490289047482379e-05, "loss": 0.4416, "num_tokens": 313776085.0, "step": 52490 }, { "epoch": 0.5600482220776034, "grad_norm": 0.6526038530300782, "learning_rate": 2.4898947981763094e-05, "loss": 0.5621, "num_tokens": 313818997.0, "step": 52495 }, { "epoch": 0.5601015650838018, "grad_norm": 0.8350470412172765, "learning_rate": 2.4895005569641788e-05, "loss": 0.597, "num_tokens": 313855957.0, "step": 52500 }, { "epoch": 0.5601549080900003, "grad_norm": 1.8513093157443288, "learning_rate": 2.4891063238582573e-05, "loss": 0.5316, "num_tokens": 313870874.0, "step": 52505 }, { "epoch": 0.5602082510961988, "grad_norm": 1.1991450686329082, "learning_rate": 2.4887120988708097e-05, "loss": 0.4505, "num_tokens": 313907650.0, "step": 52510 }, { "epoch": 0.5602615941023973, "grad_norm": 0.8666316728187602, "learning_rate": 2.488317882014105e-05, "loss": 0.5487, "num_tokens": 313954709.0, "step": 52515 }, { "epoch": 0.5603149371085957, "grad_norm": 0.6312346629400631, "learning_rate": 2.4879236733004114e-05, "loss": 0.4273, "num_tokens": 313995636.0, "step": 52520 }, { "epoch": 0.5603682801147941, "grad_norm": 0.691840308821475, "learning_rate": 2.487529472741994e-05, "loss": 0.4622, "num_tokens": 314023196.0, "step": 52525 }, { "epoch": 0.5604216231209926, "grad_norm": 0.7130343733124508, "learning_rate": 2.48713528035112e-05, "loss": 0.5115, "num_tokens": 314058396.0, "step": 52530 }, { "epoch": 0.560474966127191, "grad_norm": 1.2675536895933217, "learning_rate": 2.4867410961400568e-05, "loss": 0.6208, "num_tokens": 314102187.0, "step": 52535 }, { "epoch": 0.5605283091333895, "grad_norm": 0.8915841380497436, "learning_rate": 2.48634692012107e-05, "loss": 0.4882, "num_tokens": 314125211.0, "step": 52540 }, { "epoch": 0.560581652139588, "grad_norm": 1.6168310558060708, "learning_rate": 2.485952752306424e-05, "loss": 0.5497, "num_tokens": 314156411.0, "step": 52545 }, { "epoch": 0.5606349951457864, "grad_norm": 0.7504578113691321, "learning_rate": 2.4855585927083878e-05, "loss": 0.4996, "num_tokens": 314188517.0, "step": 52550 }, { "epoch": 0.5606883381519849, "grad_norm": 0.8572378193043534, "learning_rate": 2.485164441339224e-05, "loss": 0.4145, "num_tokens": 314205519.0, "step": 52555 }, { "epoch": 0.5607416811581833, "grad_norm": 0.6561453863491314, "learning_rate": 2.4847702982111993e-05, "loss": 0.5088, "num_tokens": 314240646.0, "step": 52560 }, { "epoch": 0.5607950241643818, "grad_norm": 0.9579266770609268, "learning_rate": 2.484376163336578e-05, "loss": 0.5892, "num_tokens": 314268023.0, "step": 52565 }, { "epoch": 0.5608483671705803, "grad_norm": 0.7945494996106137, "learning_rate": 2.4839820367276244e-05, "loss": 0.7293, "num_tokens": 314304808.0, "step": 52570 }, { "epoch": 0.5609017101767787, "grad_norm": 0.9885940182219946, "learning_rate": 2.4835879183966042e-05, "loss": 0.4795, "num_tokens": 314323224.0, "step": 52575 }, { "epoch": 0.5609550531829772, "grad_norm": 0.7374820468244211, "learning_rate": 2.4831938083557804e-05, "loss": 0.481, "num_tokens": 314351075.0, "step": 52580 }, { "epoch": 0.5610083961891756, "grad_norm": 0.7536805682234115, "learning_rate": 2.482799706617417e-05, "loss": 0.4052, "num_tokens": 314371977.0, "step": 52585 }, { "epoch": 0.561061739195374, "grad_norm": 0.7030868480234639, "learning_rate": 2.4824056131937783e-05, "loss": 0.5125, "num_tokens": 314403264.0, "step": 52590 }, { "epoch": 0.5611150822015726, "grad_norm": 1.6179265538935759, "learning_rate": 2.4820115280971275e-05, "loss": 0.602, "num_tokens": 314437199.0, "step": 52595 }, { "epoch": 0.561168425207771, "grad_norm": 0.6363310335283202, "learning_rate": 2.4816174513397268e-05, "loss": 0.5475, "num_tokens": 314478587.0, "step": 52600 }, { "epoch": 0.5612217682139695, "grad_norm": 1.253896815200559, "learning_rate": 2.4812233829338395e-05, "loss": 0.5966, "num_tokens": 314510222.0, "step": 52605 }, { "epoch": 0.5612751112201679, "grad_norm": 1.0123602497502384, "learning_rate": 2.480829322891729e-05, "loss": 0.4877, "num_tokens": 314536919.0, "step": 52610 }, { "epoch": 0.5613284542263663, "grad_norm": 0.6644407654391677, "learning_rate": 2.4804352712256573e-05, "loss": 0.5334, "num_tokens": 314562266.0, "step": 52615 }, { "epoch": 0.5613817972325649, "grad_norm": 1.419188341459513, "learning_rate": 2.4800412279478856e-05, "loss": 0.3887, "num_tokens": 314579642.0, "step": 52620 }, { "epoch": 0.5614351402387633, "grad_norm": 0.7447502394836879, "learning_rate": 2.479647193070677e-05, "loss": 0.5492, "num_tokens": 314610540.0, "step": 52625 }, { "epoch": 0.5614884832449617, "grad_norm": 0.931081458633299, "learning_rate": 2.4792531666062923e-05, "loss": 0.5523, "num_tokens": 314651045.0, "step": 52630 }, { "epoch": 0.5615418262511602, "grad_norm": 1.5852955829116988, "learning_rate": 2.4788591485669926e-05, "loss": 0.5867, "num_tokens": 314669303.0, "step": 52635 }, { "epoch": 0.5615951692573586, "grad_norm": 0.9958150434539367, "learning_rate": 2.4784651389650398e-05, "loss": 0.4941, "num_tokens": 314687264.0, "step": 52640 }, { "epoch": 0.5616485122635572, "grad_norm": 2.7601030260508814, "learning_rate": 2.4780711378126937e-05, "loss": 0.7577, "num_tokens": 314727457.0, "step": 52645 }, { "epoch": 0.5617018552697556, "grad_norm": 0.6960462191283548, "learning_rate": 2.4776771451222153e-05, "loss": 0.5043, "num_tokens": 314761483.0, "step": 52650 }, { "epoch": 0.561755198275954, "grad_norm": 0.8547499638095526, "learning_rate": 2.477283160905865e-05, "loss": 0.482, "num_tokens": 314805209.0, "step": 52655 }, { "epoch": 0.5618085412821525, "grad_norm": 1.4172560609665208, "learning_rate": 2.476889185175902e-05, "loss": 0.427, "num_tokens": 314823181.0, "step": 52660 }, { "epoch": 0.5618618842883509, "grad_norm": 1.1103960592571822, "learning_rate": 2.4764952179445867e-05, "loss": 0.5007, "num_tokens": 314860111.0, "step": 52665 }, { "epoch": 0.5619152272945495, "grad_norm": 0.7519086241725671, "learning_rate": 2.4761012592241796e-05, "loss": 0.5138, "num_tokens": 314889773.0, "step": 52670 }, { "epoch": 0.5619685703007479, "grad_norm": 0.7854810734321851, "learning_rate": 2.475707309026937e-05, "loss": 0.37, "num_tokens": 314921180.0, "step": 52675 }, { "epoch": 0.5620219133069463, "grad_norm": 0.9101922112592141, "learning_rate": 2.4753133673651197e-05, "loss": 0.472, "num_tokens": 314964921.0, "step": 52680 }, { "epoch": 0.5620752563131448, "grad_norm": 1.2964684926666128, "learning_rate": 2.4749194342509875e-05, "loss": 0.4546, "num_tokens": 314995992.0, "step": 52685 }, { "epoch": 0.5621285993193432, "grad_norm": 0.6632748476259177, "learning_rate": 2.4745255096967968e-05, "loss": 0.4639, "num_tokens": 315033856.0, "step": 52690 }, { "epoch": 0.5621819423255418, "grad_norm": 1.345849227406775, "learning_rate": 2.4741315937148058e-05, "loss": 0.4759, "num_tokens": 315063432.0, "step": 52695 }, { "epoch": 0.5622352853317402, "grad_norm": 0.681635739754422, "learning_rate": 2.473737686317274e-05, "loss": 0.4219, "num_tokens": 315086650.0, "step": 52700 }, { "epoch": 0.5622886283379386, "grad_norm": 0.9332213379306279, "learning_rate": 2.4733437875164572e-05, "loss": 0.4523, "num_tokens": 315112064.0, "step": 52705 }, { "epoch": 0.5623419713441371, "grad_norm": 1.0260614766368465, "learning_rate": 2.4729498973246134e-05, "loss": 0.5087, "num_tokens": 315135896.0, "step": 52710 }, { "epoch": 0.5623953143503355, "grad_norm": 1.1194381245020493, "learning_rate": 2.4725560157540007e-05, "loss": 0.5383, "num_tokens": 315157730.0, "step": 52715 }, { "epoch": 0.5624486573565339, "grad_norm": 0.9564154542298111, "learning_rate": 2.472162142816874e-05, "loss": 0.475, "num_tokens": 315185877.0, "step": 52720 }, { "epoch": 0.5625020003627325, "grad_norm": 0.8887307284988917, "learning_rate": 2.4717682785254904e-05, "loss": 0.5317, "num_tokens": 315228771.0, "step": 52725 }, { "epoch": 0.5625553433689309, "grad_norm": 0.8215972633145167, "learning_rate": 2.4713744228921076e-05, "loss": 0.5213, "num_tokens": 315263570.0, "step": 52730 }, { "epoch": 0.5626086863751294, "grad_norm": 1.201625968927451, "learning_rate": 2.4709805759289796e-05, "loss": 0.5469, "num_tokens": 315285138.0, "step": 52735 }, { "epoch": 0.5626620293813278, "grad_norm": 0.917896479167703, "learning_rate": 2.470586737648363e-05, "loss": 0.4547, "num_tokens": 315315662.0, "step": 52740 }, { "epoch": 0.5627153723875262, "grad_norm": 1.9980290282036919, "learning_rate": 2.470192908062514e-05, "loss": 0.5094, "num_tokens": 315347100.0, "step": 52745 }, { "epoch": 0.5627687153937247, "grad_norm": 1.0893815122022443, "learning_rate": 2.4697990871836863e-05, "loss": 0.6164, "num_tokens": 315384615.0, "step": 52750 }, { "epoch": 0.5628220583999232, "grad_norm": 1.0861394885446514, "learning_rate": 2.4694052750241354e-05, "loss": 0.5306, "num_tokens": 315411488.0, "step": 52755 }, { "epoch": 0.5628754014061217, "grad_norm": 0.916741566474303, "learning_rate": 2.4690114715961166e-05, "loss": 0.5439, "num_tokens": 315450432.0, "step": 52760 }, { "epoch": 0.5629287444123201, "grad_norm": 0.7431607285904459, "learning_rate": 2.4686176769118823e-05, "loss": 0.4303, "num_tokens": 315490275.0, "step": 52765 }, { "epoch": 0.5629820874185185, "grad_norm": 0.8741330984834567, "learning_rate": 2.4682238909836886e-05, "loss": 0.4223, "num_tokens": 315508376.0, "step": 52770 }, { "epoch": 0.563035430424717, "grad_norm": 1.775410130719839, "learning_rate": 2.467830113823789e-05, "loss": 0.4707, "num_tokens": 315529421.0, "step": 52775 }, { "epoch": 0.5630887734309155, "grad_norm": 1.1381868737413259, "learning_rate": 2.4674363454444365e-05, "loss": 0.5231, "num_tokens": 315561286.0, "step": 52780 }, { "epoch": 0.563142116437114, "grad_norm": 0.7575712255509989, "learning_rate": 2.4670425858578845e-05, "loss": 0.4983, "num_tokens": 315596760.0, "step": 52785 }, { "epoch": 0.5631954594433124, "grad_norm": 1.0427141043915675, "learning_rate": 2.466648835076386e-05, "loss": 0.4767, "num_tokens": 315627659.0, "step": 52790 }, { "epoch": 0.5632488024495108, "grad_norm": 1.172813955314415, "learning_rate": 2.4662550931121943e-05, "loss": 0.5065, "num_tokens": 315663811.0, "step": 52795 }, { "epoch": 0.5633021454557093, "grad_norm": 0.9091815313196588, "learning_rate": 2.4658613599775597e-05, "loss": 0.5261, "num_tokens": 315690477.0, "step": 52800 }, { "epoch": 0.5633554884619077, "grad_norm": 1.313535687879558, "learning_rate": 2.465467635684738e-05, "loss": 0.4309, "num_tokens": 315706146.0, "step": 52805 }, { "epoch": 0.5634088314681062, "grad_norm": 1.1269632339500586, "learning_rate": 2.465073920245977e-05, "loss": 0.7215, "num_tokens": 315757723.0, "step": 52810 }, { "epoch": 0.5634621744743047, "grad_norm": 0.9680514653431964, "learning_rate": 2.4646802136735314e-05, "loss": 0.5439, "num_tokens": 315814543.0, "step": 52815 }, { "epoch": 0.5635155174805031, "grad_norm": 1.2872083263326644, "learning_rate": 2.4642865159796525e-05, "loss": 0.5322, "num_tokens": 315826995.0, "step": 52820 }, { "epoch": 0.5635688604867016, "grad_norm": 0.8375081850333852, "learning_rate": 2.463892827176588e-05, "loss": 0.486, "num_tokens": 315845078.0, "step": 52825 }, { "epoch": 0.5636222034929, "grad_norm": 0.7382396657115696, "learning_rate": 2.463499147276593e-05, "loss": 0.4833, "num_tokens": 315880356.0, "step": 52830 }, { "epoch": 0.5636755464990985, "grad_norm": 1.0120611840893468, "learning_rate": 2.4631054762919153e-05, "loss": 0.6202, "num_tokens": 315904360.0, "step": 52835 }, { "epoch": 0.563728889505297, "grad_norm": 0.8795249987683111, "learning_rate": 2.462711814234806e-05, "loss": 0.4954, "num_tokens": 315930455.0, "step": 52840 }, { "epoch": 0.5637822325114954, "grad_norm": 0.5718854209063451, "learning_rate": 2.4623181611175146e-05, "loss": 0.5065, "num_tokens": 315963526.0, "step": 52845 }, { "epoch": 0.5638355755176939, "grad_norm": 0.9585744901792653, "learning_rate": 2.4619245169522914e-05, "loss": 0.571, "num_tokens": 315984239.0, "step": 52850 }, { "epoch": 0.5638889185238923, "grad_norm": 0.9227345362084027, "learning_rate": 2.461530881751386e-05, "loss": 0.5672, "num_tokens": 316009186.0, "step": 52855 }, { "epoch": 0.5639422615300907, "grad_norm": 0.7213785420335522, "learning_rate": 2.4611372555270456e-05, "loss": 0.5585, "num_tokens": 316041498.0, "step": 52860 }, { "epoch": 0.5639956045362893, "grad_norm": 0.7130812750920895, "learning_rate": 2.4607436382915223e-05, "loss": 0.4234, "num_tokens": 316064239.0, "step": 52865 }, { "epoch": 0.5640489475424877, "grad_norm": 0.7278657912506088, "learning_rate": 2.4603500300570613e-05, "loss": 0.4838, "num_tokens": 316089478.0, "step": 52870 }, { "epoch": 0.5641022905486862, "grad_norm": 1.30519799124895, "learning_rate": 2.459956430835913e-05, "loss": 0.4951, "num_tokens": 316116745.0, "step": 52875 }, { "epoch": 0.5641556335548846, "grad_norm": 1.4927557404837624, "learning_rate": 2.4595628406403252e-05, "loss": 0.4678, "num_tokens": 316137669.0, "step": 52880 }, { "epoch": 0.564208976561083, "grad_norm": 0.8948550361105915, "learning_rate": 2.459169259482545e-05, "loss": 0.6445, "num_tokens": 316167558.0, "step": 52885 }, { "epoch": 0.5642623195672816, "grad_norm": 1.9664227624507855, "learning_rate": 2.4587756873748192e-05, "loss": 0.5955, "num_tokens": 316213923.0, "step": 52890 }, { "epoch": 0.56431566257348, "grad_norm": 1.3842798269302263, "learning_rate": 2.458382124329397e-05, "loss": 0.5974, "num_tokens": 316258407.0, "step": 52895 }, { "epoch": 0.5643690055796784, "grad_norm": 0.6841521856131215, "learning_rate": 2.457988570358523e-05, "loss": 0.3797, "num_tokens": 316282941.0, "step": 52900 }, { "epoch": 0.5644223485858769, "grad_norm": 0.5831564034868653, "learning_rate": 2.4575950254744457e-05, "loss": 0.4982, "num_tokens": 316339088.0, "step": 52905 }, { "epoch": 0.5644756915920753, "grad_norm": 1.1676360012735332, "learning_rate": 2.4572014896894107e-05, "loss": 0.5389, "num_tokens": 316373978.0, "step": 52910 }, { "epoch": 0.5645290345982739, "grad_norm": 0.830006959780894, "learning_rate": 2.456807963015663e-05, "loss": 0.5257, "num_tokens": 316402118.0, "step": 52915 }, { "epoch": 0.5645823776044723, "grad_norm": 1.0221201191594764, "learning_rate": 2.4564144454654504e-05, "loss": 0.6736, "num_tokens": 316426659.0, "step": 52920 }, { "epoch": 0.5646357206106707, "grad_norm": 0.8822415421315761, "learning_rate": 2.456020937051017e-05, "loss": 0.4781, "num_tokens": 316455824.0, "step": 52925 }, { "epoch": 0.5646890636168692, "grad_norm": 0.6525488695851136, "learning_rate": 2.455627437784608e-05, "loss": 0.5516, "num_tokens": 316495273.0, "step": 52930 }, { "epoch": 0.5647424066230676, "grad_norm": 1.231930144957833, "learning_rate": 2.4552339476784674e-05, "loss": 0.5477, "num_tokens": 316524479.0, "step": 52935 }, { "epoch": 0.5647957496292662, "grad_norm": 0.5763069809721334, "learning_rate": 2.454840466744842e-05, "loss": 0.5304, "num_tokens": 316568227.0, "step": 52940 }, { "epoch": 0.5648490926354646, "grad_norm": 0.9903002888082432, "learning_rate": 2.4544469949959753e-05, "loss": 0.511, "num_tokens": 316601247.0, "step": 52945 }, { "epoch": 0.564902435641663, "grad_norm": 0.8202590857211056, "learning_rate": 2.45405353244411e-05, "loss": 0.4235, "num_tokens": 316623515.0, "step": 52950 }, { "epoch": 0.5649557786478615, "grad_norm": 0.8247457640058548, "learning_rate": 2.453660079101492e-05, "loss": 0.4325, "num_tokens": 316654045.0, "step": 52955 }, { "epoch": 0.5650091216540599, "grad_norm": 0.7681659880871717, "learning_rate": 2.4532666349803628e-05, "loss": 0.528, "num_tokens": 316684894.0, "step": 52960 }, { "epoch": 0.5650624646602584, "grad_norm": 1.5373267306382814, "learning_rate": 2.4528732000929665e-05, "loss": 0.5226, "num_tokens": 316714577.0, "step": 52965 }, { "epoch": 0.5651158076664569, "grad_norm": 6.067215269655033, "learning_rate": 2.4524797744515467e-05, "loss": 0.6144, "num_tokens": 316746334.0, "step": 52970 }, { "epoch": 0.5651691506726553, "grad_norm": 0.9501508702259039, "learning_rate": 2.452086358068344e-05, "loss": 0.542, "num_tokens": 316768200.0, "step": 52975 }, { "epoch": 0.5652224936788538, "grad_norm": 0.6811842115519201, "learning_rate": 2.4516929509556026e-05, "loss": 0.4646, "num_tokens": 316798536.0, "step": 52980 }, { "epoch": 0.5652758366850522, "grad_norm": 0.7095424508775464, "learning_rate": 2.451299553125564e-05, "loss": 0.5548, "num_tokens": 316828160.0, "step": 52985 }, { "epoch": 0.5653291796912506, "grad_norm": 1.3428976716622678, "learning_rate": 2.450906164590469e-05, "loss": 0.4402, "num_tokens": 316846566.0, "step": 52990 }, { "epoch": 0.5653825226974492, "grad_norm": 0.6870402511039894, "learning_rate": 2.4505127853625602e-05, "loss": 0.4709, "num_tokens": 316879016.0, "step": 52995 }, { "epoch": 0.5654358657036476, "grad_norm": 1.7748791853037715, "learning_rate": 2.450119415454079e-05, "loss": 0.5108, "num_tokens": 316915659.0, "step": 53000 }, { "epoch": 0.5654892087098461, "grad_norm": 1.2457569786244111, "learning_rate": 2.4497260548772644e-05, "loss": 0.6209, "num_tokens": 316942090.0, "step": 53005 }, { "epoch": 0.5655425517160445, "grad_norm": 1.0199918190942667, "learning_rate": 2.4493327036443588e-05, "loss": 0.5563, "num_tokens": 316965019.0, "step": 53010 }, { "epoch": 0.5655958947222429, "grad_norm": 1.037969171164359, "learning_rate": 2.448939361767602e-05, "loss": 0.5732, "num_tokens": 316995549.0, "step": 53015 }, { "epoch": 0.5656492377284414, "grad_norm": 0.8076671258066606, "learning_rate": 2.4485460292592338e-05, "loss": 0.4148, "num_tokens": 317029320.0, "step": 53020 }, { "epoch": 0.5657025807346399, "grad_norm": 1.348636711600001, "learning_rate": 2.4481527061314936e-05, "loss": 0.4249, "num_tokens": 317047552.0, "step": 53025 }, { "epoch": 0.5657559237408384, "grad_norm": 1.009561642853471, "learning_rate": 2.4477593923966217e-05, "loss": 0.4578, "num_tokens": 317071625.0, "step": 53030 }, { "epoch": 0.5658092667470368, "grad_norm": 0.9417554422462694, "learning_rate": 2.447366088066857e-05, "loss": 0.4447, "num_tokens": 317091980.0, "step": 53035 }, { "epoch": 0.5658626097532352, "grad_norm": 1.2440506394866833, "learning_rate": 2.4469727931544366e-05, "loss": 0.5657, "num_tokens": 317116993.0, "step": 53040 }, { "epoch": 0.5659159527594337, "grad_norm": 0.7233510068128829, "learning_rate": 2.4465795076716027e-05, "loss": 0.5, "num_tokens": 317138336.0, "step": 53045 }, { "epoch": 0.5659692957656322, "grad_norm": 1.2535305544625353, "learning_rate": 2.4461862316305894e-05, "loss": 0.5288, "num_tokens": 317166001.0, "step": 53050 }, { "epoch": 0.5660226387718307, "grad_norm": 1.949738197335798, "learning_rate": 2.4457929650436367e-05, "loss": 0.56, "num_tokens": 317179482.0, "step": 53055 }, { "epoch": 0.5660759817780291, "grad_norm": 1.488521611760535, "learning_rate": 2.445399707922983e-05, "loss": 0.7314, "num_tokens": 317209410.0, "step": 53060 }, { "epoch": 0.5661293247842275, "grad_norm": 0.7275364839649785, "learning_rate": 2.4450064602808635e-05, "loss": 0.4684, "num_tokens": 317243225.0, "step": 53065 }, { "epoch": 0.566182667790426, "grad_norm": 0.777084035975824, "learning_rate": 2.444613222129517e-05, "loss": 0.4744, "num_tokens": 317275276.0, "step": 53070 }, { "epoch": 0.5662360107966244, "grad_norm": 1.519916675641026, "learning_rate": 2.4442199934811803e-05, "loss": 0.4792, "num_tokens": 317297429.0, "step": 53075 }, { "epoch": 0.5662893538028229, "grad_norm": 2.716612235691127, "learning_rate": 2.4438267743480885e-05, "loss": 0.6391, "num_tokens": 317328300.0, "step": 53080 }, { "epoch": 0.5663426968090214, "grad_norm": 1.3783248235354104, "learning_rate": 2.4434335647424788e-05, "loss": 0.6228, "num_tokens": 317359762.0, "step": 53085 }, { "epoch": 0.5663960398152198, "grad_norm": 1.122709294927409, "learning_rate": 2.4430403646765875e-05, "loss": 0.4805, "num_tokens": 317385523.0, "step": 53090 }, { "epoch": 0.5664493828214183, "grad_norm": 1.3478147970215584, "learning_rate": 2.4426471741626488e-05, "loss": 0.3916, "num_tokens": 317404348.0, "step": 53095 }, { "epoch": 0.5665027258276167, "grad_norm": 0.711526827869668, "learning_rate": 2.442253993212899e-05, "loss": 0.4432, "num_tokens": 317429400.0, "step": 53100 }, { "epoch": 0.5665560688338152, "grad_norm": 1.6146823528769982, "learning_rate": 2.4418608218395728e-05, "loss": 0.5509, "num_tokens": 317459888.0, "step": 53105 }, { "epoch": 0.5666094118400137, "grad_norm": 0.937011303890791, "learning_rate": 2.4414676600549053e-05, "loss": 0.5437, "num_tokens": 317475902.0, "step": 53110 }, { "epoch": 0.5666627548462121, "grad_norm": 0.832661754204374, "learning_rate": 2.4410745078711295e-05, "loss": 0.349, "num_tokens": 317493288.0, "step": 53115 }, { "epoch": 0.5667160978524106, "grad_norm": 1.1764157775699091, "learning_rate": 2.440681365300481e-05, "loss": 0.5179, "num_tokens": 317525148.0, "step": 53120 }, { "epoch": 0.566769440858609, "grad_norm": 0.6367865658298233, "learning_rate": 2.4402882323551933e-05, "loss": 0.6276, "num_tokens": 317580731.0, "step": 53125 }, { "epoch": 0.5668227838648074, "grad_norm": 1.1024252598675799, "learning_rate": 2.439895109047499e-05, "loss": 0.7259, "num_tokens": 317620918.0, "step": 53130 }, { "epoch": 0.566876126871006, "grad_norm": 1.110457026657306, "learning_rate": 2.439501995389633e-05, "loss": 0.5346, "num_tokens": 317646837.0, "step": 53135 }, { "epoch": 0.5669294698772044, "grad_norm": 1.3337220688265, "learning_rate": 2.439108891393826e-05, "loss": 0.5333, "num_tokens": 317675904.0, "step": 53140 }, { "epoch": 0.5669828128834029, "grad_norm": 0.8576416884189646, "learning_rate": 2.4387157970723124e-05, "loss": 0.5327, "num_tokens": 317716426.0, "step": 53145 }, { "epoch": 0.5670361558896013, "grad_norm": 2.849560616503273, "learning_rate": 2.4383227124373237e-05, "loss": 0.6567, "num_tokens": 317736814.0, "step": 53150 }, { "epoch": 0.5670894988957997, "grad_norm": 0.7164182132233913, "learning_rate": 2.4379296375010913e-05, "loss": 0.582, "num_tokens": 317769988.0, "step": 53155 }, { "epoch": 0.5671428419019983, "grad_norm": 1.0805048592592192, "learning_rate": 2.437536572275848e-05, "loss": 0.4732, "num_tokens": 317793394.0, "step": 53160 }, { "epoch": 0.5671961849081967, "grad_norm": 0.8809590024254577, "learning_rate": 2.4371435167738254e-05, "loss": 0.4594, "num_tokens": 317820175.0, "step": 53165 }, { "epoch": 0.5672495279143951, "grad_norm": 1.0443808339318816, "learning_rate": 2.4367504710072532e-05, "loss": 0.6257, "num_tokens": 317844614.0, "step": 53170 }, { "epoch": 0.5673028709205936, "grad_norm": 1.1494284545746902, "learning_rate": 2.4363574349883632e-05, "loss": 0.6463, "num_tokens": 317882979.0, "step": 53175 }, { "epoch": 0.567356213926792, "grad_norm": 0.86183333315175, "learning_rate": 2.4359644087293854e-05, "loss": 0.4969, "num_tokens": 317904018.0, "step": 53180 }, { "epoch": 0.5674095569329906, "grad_norm": 1.7332841406358903, "learning_rate": 2.4355713922425504e-05, "loss": 0.5317, "num_tokens": 317933791.0, "step": 53185 }, { "epoch": 0.567462899939189, "grad_norm": 0.9821697137130448, "learning_rate": 2.4351783855400874e-05, "loss": 0.4034, "num_tokens": 317956008.0, "step": 53190 }, { "epoch": 0.5675162429453874, "grad_norm": 1.2542552474450828, "learning_rate": 2.434785388634227e-05, "loss": 0.507, "num_tokens": 317977884.0, "step": 53195 }, { "epoch": 0.5675695859515859, "grad_norm": 16.813116147593526, "learning_rate": 2.4343924015371976e-05, "loss": 0.9106, "num_tokens": 317997194.0, "step": 53200 }, { "epoch": 0.5676229289577843, "grad_norm": 0.996760748421597, "learning_rate": 2.433999424261228e-05, "loss": 0.471, "num_tokens": 318033441.0, "step": 53205 }, { "epoch": 0.5676762719639828, "grad_norm": 0.5268399589358818, "learning_rate": 2.433606456818548e-05, "loss": 0.4356, "num_tokens": 318081546.0, "step": 53210 }, { "epoch": 0.5677296149701813, "grad_norm": 1.8259340474310788, "learning_rate": 2.4332134992213846e-05, "loss": 0.5536, "num_tokens": 318104893.0, "step": 53215 }, { "epoch": 0.5677829579763797, "grad_norm": 0.7387264694935998, "learning_rate": 2.4328205514819658e-05, "loss": 0.5573, "num_tokens": 318146291.0, "step": 53220 }, { "epoch": 0.5678363009825782, "grad_norm": 0.6020942255021824, "learning_rate": 2.4324276136125213e-05, "loss": 0.4409, "num_tokens": 318169836.0, "step": 53225 }, { "epoch": 0.5678896439887766, "grad_norm": 0.5480070577149767, "learning_rate": 2.4320346856252756e-05, "loss": 0.4302, "num_tokens": 318195922.0, "step": 53230 }, { "epoch": 0.5679429869949751, "grad_norm": 1.4863289025376452, "learning_rate": 2.4316417675324586e-05, "loss": 0.5029, "num_tokens": 318224028.0, "step": 53235 }, { "epoch": 0.5679963300011736, "grad_norm": 0.8174296146479539, "learning_rate": 2.431248859346296e-05, "loss": 0.5563, "num_tokens": 318255123.0, "step": 53240 }, { "epoch": 0.568049673007372, "grad_norm": 0.5494796873223389, "learning_rate": 2.4308559610790133e-05, "loss": 0.4576, "num_tokens": 318286695.0, "step": 53245 }, { "epoch": 0.5681030160135705, "grad_norm": 0.7208048247361084, "learning_rate": 2.4304630727428378e-05, "loss": 0.5683, "num_tokens": 318323302.0, "step": 53250 }, { "epoch": 0.5681563590197689, "grad_norm": 1.017022203453304, "learning_rate": 2.430070194349996e-05, "loss": 0.4692, "num_tokens": 318349438.0, "step": 53255 }, { "epoch": 0.5682097020259673, "grad_norm": 0.7519416061173685, "learning_rate": 2.4296773259127108e-05, "loss": 0.4785, "num_tokens": 318383749.0, "step": 53260 }, { "epoch": 0.5682630450321658, "grad_norm": 0.6054566253785121, "learning_rate": 2.42928446744321e-05, "loss": 0.481, "num_tokens": 318413740.0, "step": 53265 }, { "epoch": 0.5683163880383643, "grad_norm": 0.5600791417634859, "learning_rate": 2.4288916189537192e-05, "loss": 0.4619, "num_tokens": 318457111.0, "step": 53270 }, { "epoch": 0.5683697310445628, "grad_norm": 1.1228770588041095, "learning_rate": 2.4284987804564602e-05, "loss": 0.5535, "num_tokens": 318498261.0, "step": 53275 }, { "epoch": 0.5684230740507612, "grad_norm": 1.9452737848483275, "learning_rate": 2.4281059519636585e-05, "loss": 0.5376, "num_tokens": 318525249.0, "step": 53280 }, { "epoch": 0.5684764170569596, "grad_norm": 0.7771881352069856, "learning_rate": 2.4277131334875397e-05, "loss": 0.4781, "num_tokens": 318571741.0, "step": 53285 }, { "epoch": 0.5685297600631581, "grad_norm": 0.8088853276534759, "learning_rate": 2.427320325040326e-05, "loss": 0.449, "num_tokens": 318601256.0, "step": 53290 }, { "epoch": 0.5685831030693566, "grad_norm": 0.8755959479664233, "learning_rate": 2.4269275266342395e-05, "loss": 0.5462, "num_tokens": 318625347.0, "step": 53295 }, { "epoch": 0.5686364460755551, "grad_norm": 0.7900411952654166, "learning_rate": 2.426534738281506e-05, "loss": 0.609, "num_tokens": 318657468.0, "step": 53300 }, { "epoch": 0.5686897890817535, "grad_norm": 0.5498197765318867, "learning_rate": 2.426141959994347e-05, "loss": 0.4469, "num_tokens": 318709233.0, "step": 53305 }, { "epoch": 0.5687431320879519, "grad_norm": 0.8419332263801484, "learning_rate": 2.4257491917849846e-05, "loss": 0.6038, "num_tokens": 318745259.0, "step": 53310 }, { "epoch": 0.5687964750941504, "grad_norm": 1.081224417109527, "learning_rate": 2.425356433665642e-05, "loss": 0.4797, "num_tokens": 318763795.0, "step": 53315 }, { "epoch": 0.5688498181003488, "grad_norm": 1.0235093855397344, "learning_rate": 2.4249636856485392e-05, "loss": 0.5548, "num_tokens": 318806291.0, "step": 53320 }, { "epoch": 0.5689031611065474, "grad_norm": 1.1642909552100846, "learning_rate": 2.4245709477458993e-05, "loss": 0.5238, "num_tokens": 318824285.0, "step": 53325 }, { "epoch": 0.5689565041127458, "grad_norm": 0.8564820695325587, "learning_rate": 2.4241782199699435e-05, "loss": 0.5301, "num_tokens": 318854553.0, "step": 53330 }, { "epoch": 0.5690098471189442, "grad_norm": 1.2889731048911877, "learning_rate": 2.423785502332892e-05, "loss": 0.5258, "num_tokens": 318879096.0, "step": 53335 }, { "epoch": 0.5690631901251427, "grad_norm": 1.4147422801079326, "learning_rate": 2.4233927948469655e-05, "loss": 0.4991, "num_tokens": 318895439.0, "step": 53340 }, { "epoch": 0.5691165331313411, "grad_norm": 0.91732615459288, "learning_rate": 2.423000097524385e-05, "loss": 0.4705, "num_tokens": 318923234.0, "step": 53345 }, { "epoch": 0.5691698761375396, "grad_norm": 1.2670672787680148, "learning_rate": 2.422607410377369e-05, "loss": 0.5342, "num_tokens": 318965379.0, "step": 53350 }, { "epoch": 0.5692232191437381, "grad_norm": 1.0843291119573282, "learning_rate": 2.422214733418137e-05, "loss": 0.4187, "num_tokens": 318994734.0, "step": 53355 }, { "epoch": 0.5692765621499365, "grad_norm": 1.842545024872392, "learning_rate": 2.4218220666589115e-05, "loss": 0.6275, "num_tokens": 319043964.0, "step": 53360 }, { "epoch": 0.569329905156135, "grad_norm": 0.6508047565564978, "learning_rate": 2.4214294101119078e-05, "loss": 0.5345, "num_tokens": 319072327.0, "step": 53365 }, { "epoch": 0.5693832481623334, "grad_norm": 1.832106111036204, "learning_rate": 2.4210367637893456e-05, "loss": 0.5473, "num_tokens": 319089464.0, "step": 53370 }, { "epoch": 0.5694365911685318, "grad_norm": 0.8662074883938399, "learning_rate": 2.4206441277034446e-05, "loss": 0.5597, "num_tokens": 319139624.0, "step": 53375 }, { "epoch": 0.5694899341747304, "grad_norm": 0.6931243563034225, "learning_rate": 2.4202515018664214e-05, "loss": 0.4948, "num_tokens": 319172229.0, "step": 53380 }, { "epoch": 0.5695432771809288, "grad_norm": 0.7942937340284798, "learning_rate": 2.4198588862904935e-05, "loss": 0.4534, "num_tokens": 319206666.0, "step": 53385 }, { "epoch": 0.5695966201871273, "grad_norm": 0.6358961979364569, "learning_rate": 2.4194662809878792e-05, "loss": 0.5022, "num_tokens": 319240760.0, "step": 53390 }, { "epoch": 0.5696499631933257, "grad_norm": 0.6572749174634871, "learning_rate": 2.4190736859707962e-05, "loss": 0.4948, "num_tokens": 319274111.0, "step": 53395 }, { "epoch": 0.5697033061995241, "grad_norm": 0.9027060679659473, "learning_rate": 2.4186811012514597e-05, "loss": 0.3803, "num_tokens": 319292963.0, "step": 53400 }, { "epoch": 0.5697566492057227, "grad_norm": 1.0224302082700194, "learning_rate": 2.418288526842087e-05, "loss": 0.5415, "num_tokens": 319316057.0, "step": 53405 }, { "epoch": 0.5698099922119211, "grad_norm": 0.7086668856323349, "learning_rate": 2.417895962754894e-05, "loss": 0.5888, "num_tokens": 319348681.0, "step": 53410 }, { "epoch": 0.5698633352181196, "grad_norm": 1.2500466645524504, "learning_rate": 2.4175034090020965e-05, "loss": 0.549, "num_tokens": 319375617.0, "step": 53415 }, { "epoch": 0.569916678224318, "grad_norm": 0.7872495221836612, "learning_rate": 2.417110865595909e-05, "loss": 0.5197, "num_tokens": 319404233.0, "step": 53420 }, { "epoch": 0.5699700212305164, "grad_norm": 0.7121655164698909, "learning_rate": 2.4167183325485493e-05, "loss": 0.391, "num_tokens": 319430588.0, "step": 53425 }, { "epoch": 0.570023364236715, "grad_norm": 2.343163492313967, "learning_rate": 2.416325809872229e-05, "loss": 0.5885, "num_tokens": 319449275.0, "step": 53430 }, { "epoch": 0.5700767072429134, "grad_norm": 0.7584700157939578, "learning_rate": 2.4159332975791647e-05, "loss": 0.4609, "num_tokens": 319472099.0, "step": 53435 }, { "epoch": 0.5701300502491118, "grad_norm": 0.7236475896321365, "learning_rate": 2.4155407956815707e-05, "loss": 0.5247, "num_tokens": 319505322.0, "step": 53440 }, { "epoch": 0.5701833932553103, "grad_norm": 0.7372535859899572, "learning_rate": 2.415148304191659e-05, "loss": 0.6671, "num_tokens": 319527324.0, "step": 53445 }, { "epoch": 0.5702367362615087, "grad_norm": 1.2883356141713072, "learning_rate": 2.4147558231216448e-05, "loss": 0.5548, "num_tokens": 319563505.0, "step": 53450 }, { "epoch": 0.5702900792677073, "grad_norm": 1.3397053331850508, "learning_rate": 2.414363352483741e-05, "loss": 0.4126, "num_tokens": 319577916.0, "step": 53455 }, { "epoch": 0.5703434222739057, "grad_norm": 0.7850423269494136, "learning_rate": 2.4139708922901594e-05, "loss": 0.481, "num_tokens": 319606569.0, "step": 53460 }, { "epoch": 0.5703967652801041, "grad_norm": 1.24748520565553, "learning_rate": 2.4135784425531138e-05, "loss": 0.4494, "num_tokens": 319625382.0, "step": 53465 }, { "epoch": 0.5704501082863026, "grad_norm": 1.107745832324519, "learning_rate": 2.4131860032848164e-05, "loss": 0.4663, "num_tokens": 319642131.0, "step": 53470 }, { "epoch": 0.570503451292501, "grad_norm": 0.8482998218369494, "learning_rate": 2.412793574497479e-05, "loss": 0.5115, "num_tokens": 319664791.0, "step": 53475 }, { "epoch": 0.5705567942986995, "grad_norm": 0.654670437788485, "learning_rate": 2.4124011562033115e-05, "loss": 0.5615, "num_tokens": 319687342.0, "step": 53480 }, { "epoch": 0.570610137304898, "grad_norm": 0.7990727076680987, "learning_rate": 2.412008748414528e-05, "loss": 0.4825, "num_tokens": 319715424.0, "step": 53485 }, { "epoch": 0.5706634803110964, "grad_norm": 1.4368428422700719, "learning_rate": 2.4116163511433378e-05, "loss": 0.6182, "num_tokens": 319745208.0, "step": 53490 }, { "epoch": 0.5707168233172949, "grad_norm": 0.8474144132313239, "learning_rate": 2.411223964401951e-05, "loss": 0.5429, "num_tokens": 319766130.0, "step": 53495 }, { "epoch": 0.5707701663234933, "grad_norm": 0.7130170408696196, "learning_rate": 2.4108315882025795e-05, "loss": 0.5663, "num_tokens": 319787767.0, "step": 53500 }, { "epoch": 0.5708235093296918, "grad_norm": 0.7347369542199066, "learning_rate": 2.4104392225574317e-05, "loss": 0.4861, "num_tokens": 319825267.0, "step": 53505 }, { "epoch": 0.5708768523358903, "grad_norm": 1.3014079722616456, "learning_rate": 2.4100468674787174e-05, "loss": 0.5293, "num_tokens": 319852687.0, "step": 53510 }, { "epoch": 0.5709301953420887, "grad_norm": 1.1680251803078243, "learning_rate": 2.409654522978647e-05, "loss": 0.5407, "num_tokens": 319892210.0, "step": 53515 }, { "epoch": 0.5709835383482872, "grad_norm": 1.198213892490425, "learning_rate": 2.4092621890694285e-05, "loss": 0.5433, "num_tokens": 319919730.0, "step": 53520 }, { "epoch": 0.5710368813544856, "grad_norm": 0.6706718077195949, "learning_rate": 2.4088698657632707e-05, "loss": 0.5272, "num_tokens": 319970221.0, "step": 53525 }, { "epoch": 0.571090224360684, "grad_norm": 0.8951413873611774, "learning_rate": 2.408477553072383e-05, "loss": 0.5571, "num_tokens": 320021070.0, "step": 53530 }, { "epoch": 0.5711435673668825, "grad_norm": 0.7711586521679211, "learning_rate": 2.4080852510089706e-05, "loss": 0.4646, "num_tokens": 320041518.0, "step": 53535 }, { "epoch": 0.571196910373081, "grad_norm": 0.8331311966015057, "learning_rate": 2.4076929595852438e-05, "loss": 0.5331, "num_tokens": 320071674.0, "step": 53540 }, { "epoch": 0.5712502533792795, "grad_norm": 1.2130831364653216, "learning_rate": 2.4073006788134096e-05, "loss": 0.4829, "num_tokens": 320102068.0, "step": 53545 }, { "epoch": 0.5713035963854779, "grad_norm": 0.827752046484848, "learning_rate": 2.406908408705673e-05, "loss": 0.4722, "num_tokens": 320135411.0, "step": 53550 }, { "epoch": 0.5713569393916763, "grad_norm": 1.2922504737284408, "learning_rate": 2.406516149274242e-05, "loss": 0.4467, "num_tokens": 320164878.0, "step": 53555 }, { "epoch": 0.5714102823978748, "grad_norm": 1.0419072124673363, "learning_rate": 2.406123900531324e-05, "loss": 0.5025, "num_tokens": 320203321.0, "step": 53560 }, { "epoch": 0.5714636254040732, "grad_norm": 0.906444664981707, "learning_rate": 2.405731662489124e-05, "loss": 0.5383, "num_tokens": 320233862.0, "step": 53565 }, { "epoch": 0.5715169684102718, "grad_norm": 1.1653109303267613, "learning_rate": 2.4053394351598463e-05, "loss": 0.5034, "num_tokens": 320268527.0, "step": 53570 }, { "epoch": 0.5715703114164702, "grad_norm": 0.9525672685798301, "learning_rate": 2.4049472185556988e-05, "loss": 0.552, "num_tokens": 320301357.0, "step": 53575 }, { "epoch": 0.5716236544226686, "grad_norm": 0.5813572284701848, "learning_rate": 2.4045550126888838e-05, "loss": 0.5215, "num_tokens": 320333748.0, "step": 53580 }, { "epoch": 0.5716769974288671, "grad_norm": 0.9953599778349929, "learning_rate": 2.4041628175716074e-05, "loss": 0.4552, "num_tokens": 320357303.0, "step": 53585 }, { "epoch": 0.5717303404350655, "grad_norm": 0.930714754692919, "learning_rate": 2.4037706332160746e-05, "loss": 0.5248, "num_tokens": 320384446.0, "step": 53590 }, { "epoch": 0.5717836834412641, "grad_norm": 0.5995594716826054, "learning_rate": 2.4033784596344876e-05, "loss": 0.4468, "num_tokens": 320421623.0, "step": 53595 }, { "epoch": 0.5718370264474625, "grad_norm": 0.7294513279287509, "learning_rate": 2.4029862968390517e-05, "loss": 0.5307, "num_tokens": 320459069.0, "step": 53600 }, { "epoch": 0.5718903694536609, "grad_norm": 0.784119877604367, "learning_rate": 2.4025941448419698e-05, "loss": 0.6539, "num_tokens": 320487811.0, "step": 53605 }, { "epoch": 0.5719437124598594, "grad_norm": 0.8520342506938543, "learning_rate": 2.402202003655443e-05, "loss": 0.6572, "num_tokens": 320519858.0, "step": 53610 }, { "epoch": 0.5719970554660578, "grad_norm": 0.8147138999444634, "learning_rate": 2.4018098732916766e-05, "loss": 0.5372, "num_tokens": 320559050.0, "step": 53615 }, { "epoch": 0.5720503984722562, "grad_norm": 1.0261151215329334, "learning_rate": 2.4014177537628717e-05, "loss": 0.6417, "num_tokens": 320578994.0, "step": 53620 }, { "epoch": 0.5721037414784548, "grad_norm": 0.9075437124750634, "learning_rate": 2.4010256450812303e-05, "loss": 0.5924, "num_tokens": 320619356.0, "step": 53625 }, { "epoch": 0.5721570844846532, "grad_norm": 1.5797448550946296, "learning_rate": 2.4006335472589537e-05, "loss": 0.5531, "num_tokens": 320635494.0, "step": 53630 }, { "epoch": 0.5722104274908517, "grad_norm": 0.9430850570175794, "learning_rate": 2.4002414603082435e-05, "loss": 0.501, "num_tokens": 320668157.0, "step": 53635 }, { "epoch": 0.5722637704970501, "grad_norm": 0.8542230621605386, "learning_rate": 2.3998493842413004e-05, "loss": 0.5516, "num_tokens": 320706331.0, "step": 53640 }, { "epoch": 0.5723171135032485, "grad_norm": 0.9590747839303465, "learning_rate": 2.3994573190703253e-05, "loss": 0.4636, "num_tokens": 320732470.0, "step": 53645 }, { "epoch": 0.5723704565094471, "grad_norm": 0.7683274862637293, "learning_rate": 2.399065264807519e-05, "loss": 0.5858, "num_tokens": 320756653.0, "step": 53650 }, { "epoch": 0.5724237995156455, "grad_norm": 0.82321303809625, "learning_rate": 2.398673221465081e-05, "loss": 0.5992, "num_tokens": 320793104.0, "step": 53655 }, { "epoch": 0.572477142521844, "grad_norm": 0.9311678116111051, "learning_rate": 2.3982811890552094e-05, "loss": 0.3957, "num_tokens": 320821308.0, "step": 53660 }, { "epoch": 0.5725304855280424, "grad_norm": 1.2110255464643944, "learning_rate": 2.397889167590106e-05, "loss": 0.5214, "num_tokens": 320846679.0, "step": 53665 }, { "epoch": 0.5725838285342408, "grad_norm": 1.1944235984321712, "learning_rate": 2.3974971570819678e-05, "loss": 0.4214, "num_tokens": 320861071.0, "step": 53670 }, { "epoch": 0.5726371715404394, "grad_norm": 0.7349123385449061, "learning_rate": 2.3971051575429936e-05, "loss": 0.5151, "num_tokens": 320883428.0, "step": 53675 }, { "epoch": 0.5726905145466378, "grad_norm": 1.8626731625395039, "learning_rate": 2.3967131689853832e-05, "loss": 0.4356, "num_tokens": 320914450.0, "step": 53680 }, { "epoch": 0.5727438575528363, "grad_norm": 0.6776303000186124, "learning_rate": 2.3963211914213324e-05, "loss": 0.5546, "num_tokens": 320976810.0, "step": 53685 }, { "epoch": 0.5727972005590347, "grad_norm": 0.9360702485549005, "learning_rate": 2.39592922486304e-05, "loss": 0.5389, "num_tokens": 320997075.0, "step": 53690 }, { "epoch": 0.5728505435652331, "grad_norm": 0.8396404038868486, "learning_rate": 2.395537269322703e-05, "loss": 0.5856, "num_tokens": 321036335.0, "step": 53695 }, { "epoch": 0.5729038865714317, "grad_norm": 1.0681198269867005, "learning_rate": 2.3951453248125177e-05, "loss": 0.4284, "num_tokens": 321057907.0, "step": 53700 }, { "epoch": 0.5729572295776301, "grad_norm": 0.9902091108780237, "learning_rate": 2.3947533913446813e-05, "loss": 0.4841, "num_tokens": 321096730.0, "step": 53705 }, { "epoch": 0.5730105725838285, "grad_norm": 0.7417444331463847, "learning_rate": 2.39436146893139e-05, "loss": 0.4475, "num_tokens": 321129878.0, "step": 53710 }, { "epoch": 0.573063915590027, "grad_norm": 1.0518968207819501, "learning_rate": 2.393969557584838e-05, "loss": 0.5123, "num_tokens": 321161246.0, "step": 53715 }, { "epoch": 0.5731172585962254, "grad_norm": 1.043110222304481, "learning_rate": 2.3935776573172226e-05, "loss": 0.5621, "num_tokens": 321193647.0, "step": 53720 }, { "epoch": 0.573170601602424, "grad_norm": 0.6688854969668547, "learning_rate": 2.3931857681407394e-05, "loss": 0.4884, "num_tokens": 321230462.0, "step": 53725 }, { "epoch": 0.5732239446086224, "grad_norm": 1.295165117993861, "learning_rate": 2.392793890067581e-05, "loss": 0.4692, "num_tokens": 321251206.0, "step": 53730 }, { "epoch": 0.5732772876148208, "grad_norm": 0.44311627067000975, "learning_rate": 2.3924020231099433e-05, "loss": 0.5224, "num_tokens": 321297060.0, "step": 53735 }, { "epoch": 0.5733306306210193, "grad_norm": 2.543839791340267, "learning_rate": 2.392010167280021e-05, "loss": 0.566, "num_tokens": 321314302.0, "step": 53740 }, { "epoch": 0.5733839736272177, "grad_norm": 0.8067527933358293, "learning_rate": 2.3916183225900062e-05, "loss": 0.3916, "num_tokens": 321340657.0, "step": 53745 }, { "epoch": 0.5734373166334162, "grad_norm": 1.1058681651457192, "learning_rate": 2.3912264890520926e-05, "loss": 0.5071, "num_tokens": 321378355.0, "step": 53750 }, { "epoch": 0.5734906596396147, "grad_norm": 0.8478745572617027, "learning_rate": 2.3908346666784748e-05, "loss": 0.4072, "num_tokens": 321394429.0, "step": 53755 }, { "epoch": 0.5735440026458131, "grad_norm": 1.1593658396577569, "learning_rate": 2.390442855481343e-05, "loss": 0.4183, "num_tokens": 321410101.0, "step": 53760 }, { "epoch": 0.5735973456520116, "grad_norm": 0.9684814928435503, "learning_rate": 2.390051055472892e-05, "loss": 0.4768, "num_tokens": 321432897.0, "step": 53765 }, { "epoch": 0.57365068865821, "grad_norm": 1.126320630840373, "learning_rate": 2.3896592666653133e-05, "loss": 0.4965, "num_tokens": 321475462.0, "step": 53770 }, { "epoch": 0.5737040316644085, "grad_norm": 0.7465620585930021, "learning_rate": 2.3892674890707973e-05, "loss": 0.5043, "num_tokens": 321502657.0, "step": 53775 }, { "epoch": 0.573757374670607, "grad_norm": 1.243215356327937, "learning_rate": 2.3888757227015357e-05, "loss": 0.5599, "num_tokens": 321520923.0, "step": 53780 }, { "epoch": 0.5738107176768054, "grad_norm": 0.9912804152271026, "learning_rate": 2.388483967569721e-05, "loss": 0.5088, "num_tokens": 321553709.0, "step": 53785 }, { "epoch": 0.5738640606830039, "grad_norm": 0.7968030336942651, "learning_rate": 2.3880922236875414e-05, "loss": 0.6113, "num_tokens": 321583950.0, "step": 53790 }, { "epoch": 0.5739174036892023, "grad_norm": 0.8119044145027596, "learning_rate": 2.387700491067189e-05, "loss": 0.4887, "num_tokens": 321607591.0, "step": 53795 }, { "epoch": 0.5739707466954007, "grad_norm": 0.8090328240079614, "learning_rate": 2.3873087697208534e-05, "loss": 0.4621, "num_tokens": 321646129.0, "step": 53800 }, { "epoch": 0.5740240897015992, "grad_norm": 0.6770530235716384, "learning_rate": 2.3869170596607236e-05, "loss": 0.4918, "num_tokens": 321677355.0, "step": 53805 }, { "epoch": 0.5740774327077977, "grad_norm": 0.9740307263938486, "learning_rate": 2.3865253608989884e-05, "loss": 0.4367, "num_tokens": 321700845.0, "step": 53810 }, { "epoch": 0.5741307757139962, "grad_norm": 0.8742247087241566, "learning_rate": 2.386133673447839e-05, "loss": 0.4431, "num_tokens": 321738256.0, "step": 53815 }, { "epoch": 0.5741841187201946, "grad_norm": 1.3399828786033572, "learning_rate": 2.385741997319461e-05, "loss": 0.52, "num_tokens": 321753754.0, "step": 53820 }, { "epoch": 0.574237461726393, "grad_norm": 0.907544461680688, "learning_rate": 2.385350332526044e-05, "loss": 0.4502, "num_tokens": 321783988.0, "step": 53825 }, { "epoch": 0.5742908047325915, "grad_norm": 1.2979497623446445, "learning_rate": 2.3849586790797764e-05, "loss": 0.5083, "num_tokens": 321811417.0, "step": 53830 }, { "epoch": 0.57434414773879, "grad_norm": 0.5721464381465665, "learning_rate": 2.3845670369928442e-05, "loss": 0.5619, "num_tokens": 321848443.0, "step": 53835 }, { "epoch": 0.5743974907449885, "grad_norm": 0.8632788124750878, "learning_rate": 2.3841754062774347e-05, "loss": 0.5699, "num_tokens": 321880478.0, "step": 53840 }, { "epoch": 0.5744508337511869, "grad_norm": 1.0137274616789487, "learning_rate": 2.3837837869457364e-05, "loss": 0.501, "num_tokens": 321909010.0, "step": 53845 }, { "epoch": 0.5745041767573853, "grad_norm": 0.8441174044397044, "learning_rate": 2.3833921790099333e-05, "loss": 0.4514, "num_tokens": 321932133.0, "step": 53850 }, { "epoch": 0.5745575197635838, "grad_norm": 0.6183577209126613, "learning_rate": 2.383000582482213e-05, "loss": 0.554, "num_tokens": 321965566.0, "step": 53855 }, { "epoch": 0.5746108627697822, "grad_norm": 0.7268816190118148, "learning_rate": 2.3826089973747618e-05, "loss": 0.4167, "num_tokens": 321997426.0, "step": 53860 }, { "epoch": 0.5746642057759808, "grad_norm": 1.665450479084483, "learning_rate": 2.3822174236997626e-05, "loss": 0.5822, "num_tokens": 322029788.0, "step": 53865 }, { "epoch": 0.5747175487821792, "grad_norm": 0.987088221723959, "learning_rate": 2.3818258614694016e-05, "loss": 0.4118, "num_tokens": 322046571.0, "step": 53870 }, { "epoch": 0.5747708917883776, "grad_norm": 0.8850843566505443, "learning_rate": 2.3814343106958643e-05, "loss": 0.5266, "num_tokens": 322070499.0, "step": 53875 }, { "epoch": 0.5748242347945761, "grad_norm": 0.6035548588870144, "learning_rate": 2.3810427713913336e-05, "loss": 0.5043, "num_tokens": 322099869.0, "step": 53880 }, { "epoch": 0.5748775778007745, "grad_norm": 1.8161573479689883, "learning_rate": 2.380651243567994e-05, "loss": 0.5691, "num_tokens": 322125155.0, "step": 53885 }, { "epoch": 0.574930920806973, "grad_norm": 0.8944580349298776, "learning_rate": 2.3802597272380293e-05, "loss": 0.4818, "num_tokens": 322153199.0, "step": 53890 }, { "epoch": 0.5749842638131715, "grad_norm": 0.9434139694971614, "learning_rate": 2.3798682224136224e-05, "loss": 0.5833, "num_tokens": 322180096.0, "step": 53895 }, { "epoch": 0.5750376068193699, "grad_norm": 1.2005189377233834, "learning_rate": 2.3794767291069565e-05, "loss": 0.5008, "num_tokens": 322199510.0, "step": 53900 }, { "epoch": 0.5750909498255684, "grad_norm": 1.1815487000265783, "learning_rate": 2.3790852473302138e-05, "loss": 0.5566, "num_tokens": 322239126.0, "step": 53905 }, { "epoch": 0.5751442928317668, "grad_norm": 0.5250193234336918, "learning_rate": 2.3786937770955757e-05, "loss": 0.4978, "num_tokens": 322271082.0, "step": 53910 }, { "epoch": 0.5751976358379652, "grad_norm": 0.8267626970959264, "learning_rate": 2.3783023184152243e-05, "loss": 0.5655, "num_tokens": 322304268.0, "step": 53915 }, { "epoch": 0.5752509788441638, "grad_norm": 1.1351456782143656, "learning_rate": 2.3779108713013425e-05, "loss": 0.4302, "num_tokens": 322327379.0, "step": 53920 }, { "epoch": 0.5753043218503622, "grad_norm": 0.9287909936174907, "learning_rate": 2.377519435766109e-05, "loss": 0.4083, "num_tokens": 322358335.0, "step": 53925 }, { "epoch": 0.5753576648565607, "grad_norm": 0.8820483464817038, "learning_rate": 2.377128011821706e-05, "loss": 0.4838, "num_tokens": 322385421.0, "step": 53930 }, { "epoch": 0.5754110078627591, "grad_norm": 1.5085275605523176, "learning_rate": 2.3767365994803137e-05, "loss": 0.5436, "num_tokens": 322408743.0, "step": 53935 }, { "epoch": 0.5754643508689575, "grad_norm": 1.678394186415192, "learning_rate": 2.3763451987541107e-05, "loss": 0.6356, "num_tokens": 322429292.0, "step": 53940 }, { "epoch": 0.5755176938751561, "grad_norm": 0.5685671287085591, "learning_rate": 2.375953809655278e-05, "loss": 0.4676, "num_tokens": 322458918.0, "step": 53945 }, { "epoch": 0.5755710368813545, "grad_norm": 0.77751366170554, "learning_rate": 2.3755624321959953e-05, "loss": 0.5126, "num_tokens": 322487216.0, "step": 53950 }, { "epoch": 0.575624379887553, "grad_norm": 1.2149146046222359, "learning_rate": 2.3751710663884396e-05, "loss": 0.597, "num_tokens": 322511140.0, "step": 53955 }, { "epoch": 0.5756777228937514, "grad_norm": 1.4204645238131748, "learning_rate": 2.3747797122447908e-05, "loss": 0.477, "num_tokens": 322552308.0, "step": 53960 }, { "epoch": 0.5757310658999498, "grad_norm": 0.7220543171105863, "learning_rate": 2.374388369777227e-05, "loss": 0.5582, "num_tokens": 322582541.0, "step": 53965 }, { "epoch": 0.5757844089061483, "grad_norm": 1.0426061006750424, "learning_rate": 2.373997038997925e-05, "loss": 0.4058, "num_tokens": 322604823.0, "step": 53970 }, { "epoch": 0.5758377519123468, "grad_norm": 1.243525330816755, "learning_rate": 2.373605719919062e-05, "loss": 0.5476, "num_tokens": 322643702.0, "step": 53975 }, { "epoch": 0.5758910949185452, "grad_norm": 0.8918006552373348, "learning_rate": 2.373214412552818e-05, "loss": 0.5597, "num_tokens": 322668466.0, "step": 53980 }, { "epoch": 0.5759444379247437, "grad_norm": 0.761800046112912, "learning_rate": 2.3728231169113657e-05, "loss": 0.4512, "num_tokens": 322714793.0, "step": 53985 }, { "epoch": 0.5759977809309421, "grad_norm": 1.1383856883294936, "learning_rate": 2.3724318330068833e-05, "loss": 0.4881, "num_tokens": 322731644.0, "step": 53990 }, { "epoch": 0.5760511239371406, "grad_norm": 0.7851449421065005, "learning_rate": 2.3720405608515484e-05, "loss": 0.523, "num_tokens": 322769832.0, "step": 53995 }, { "epoch": 0.576104466943339, "grad_norm": 1.5779121478432387, "learning_rate": 2.371649300457534e-05, "loss": 0.6007, "num_tokens": 322800384.0, "step": 54000 }, { "epoch": 0.5761578099495375, "grad_norm": 1.174586933099158, "learning_rate": 2.3712580518370153e-05, "loss": 0.4606, "num_tokens": 322827072.0, "step": 54005 }, { "epoch": 0.576211152955736, "grad_norm": 1.3131262630132434, "learning_rate": 2.3708668150021696e-05, "loss": 0.6214, "num_tokens": 322850364.0, "step": 54010 }, { "epoch": 0.5762644959619344, "grad_norm": 0.6966172763356382, "learning_rate": 2.370475589965169e-05, "loss": 0.5326, "num_tokens": 322897515.0, "step": 54015 }, { "epoch": 0.5763178389681329, "grad_norm": 0.7181500808343079, "learning_rate": 2.370084376738188e-05, "loss": 0.5956, "num_tokens": 322950332.0, "step": 54020 }, { "epoch": 0.5763711819743313, "grad_norm": 1.1956822806126586, "learning_rate": 2.369693175333402e-05, "loss": 0.456, "num_tokens": 322973602.0, "step": 54025 }, { "epoch": 0.5764245249805298, "grad_norm": 1.1843189982921472, "learning_rate": 2.369301985762982e-05, "loss": 0.6075, "num_tokens": 323002377.0, "step": 54030 }, { "epoch": 0.5764778679867283, "grad_norm": 3.2783523320842125, "learning_rate": 2.368910808039103e-05, "loss": 0.4734, "num_tokens": 323023222.0, "step": 54035 }, { "epoch": 0.5765312109929267, "grad_norm": 1.2941975948698015, "learning_rate": 2.3685196421739375e-05, "loss": 0.5493, "num_tokens": 323045663.0, "step": 54040 }, { "epoch": 0.5765845539991252, "grad_norm": 0.8840143555040981, "learning_rate": 2.3681284881796558e-05, "loss": 0.5482, "num_tokens": 323100207.0, "step": 54045 }, { "epoch": 0.5766378970053236, "grad_norm": 1.0125837051139603, "learning_rate": 2.367737346068431e-05, "loss": 0.6142, "num_tokens": 323134180.0, "step": 54050 }, { "epoch": 0.576691240011522, "grad_norm": 0.7288721488001999, "learning_rate": 2.3673462158524363e-05, "loss": 0.5199, "num_tokens": 323165104.0, "step": 54055 }, { "epoch": 0.5767445830177206, "grad_norm": 0.6163370275206991, "learning_rate": 2.3669550975438403e-05, "loss": 0.3951, "num_tokens": 323190971.0, "step": 54060 }, { "epoch": 0.576797926023919, "grad_norm": 0.9203016733474888, "learning_rate": 2.366563991154815e-05, "loss": 0.4351, "num_tokens": 323222896.0, "step": 54065 }, { "epoch": 0.5768512690301174, "grad_norm": 0.6381024353050385, "learning_rate": 2.366172896697531e-05, "loss": 0.4144, "num_tokens": 323244198.0, "step": 54070 }, { "epoch": 0.5769046120363159, "grad_norm": 0.931821547745161, "learning_rate": 2.365781814184158e-05, "loss": 0.5369, "num_tokens": 323271373.0, "step": 54075 }, { "epoch": 0.5769579550425143, "grad_norm": 0.718410727498938, "learning_rate": 2.3653907436268653e-05, "loss": 0.5702, "num_tokens": 323302156.0, "step": 54080 }, { "epoch": 0.5770112980487129, "grad_norm": 1.1634894882300741, "learning_rate": 2.364999685037823e-05, "loss": 0.5149, "num_tokens": 323329122.0, "step": 54085 }, { "epoch": 0.5770646410549113, "grad_norm": 0.7617484703304109, "learning_rate": 2.3646086384292e-05, "loss": 0.5572, "num_tokens": 323357089.0, "step": 54090 }, { "epoch": 0.5771179840611097, "grad_norm": 2.526768371625042, "learning_rate": 2.364217603813164e-05, "loss": 0.5425, "num_tokens": 323380345.0, "step": 54095 }, { "epoch": 0.5771713270673082, "grad_norm": 0.8995870353006451, "learning_rate": 2.363826581201884e-05, "loss": 0.5134, "num_tokens": 323399661.0, "step": 54100 }, { "epoch": 0.5772246700735066, "grad_norm": 0.8260822018400038, "learning_rate": 2.3634355706075273e-05, "loss": 0.4755, "num_tokens": 323422872.0, "step": 54105 }, { "epoch": 0.5772780130797052, "grad_norm": 0.7319166697595939, "learning_rate": 2.3630445720422616e-05, "loss": 0.4637, "num_tokens": 323467785.0, "step": 54110 }, { "epoch": 0.5773313560859036, "grad_norm": 0.8457586012484245, "learning_rate": 2.3626535855182553e-05, "loss": 0.4351, "num_tokens": 323491680.0, "step": 54115 }, { "epoch": 0.577384699092102, "grad_norm": 0.6180630297448236, "learning_rate": 2.362262611047672e-05, "loss": 0.4861, "num_tokens": 323521276.0, "step": 54120 }, { "epoch": 0.5774380420983005, "grad_norm": 0.7342858463346122, "learning_rate": 2.3618716486426805e-05, "loss": 0.5597, "num_tokens": 323548678.0, "step": 54125 }, { "epoch": 0.5774913851044989, "grad_norm": 1.45890687495271, "learning_rate": 2.361480698315447e-05, "loss": 0.4768, "num_tokens": 323574308.0, "step": 54130 }, { "epoch": 0.5775447281106975, "grad_norm": 0.7169445011573915, "learning_rate": 2.3610897600781347e-05, "loss": 0.5692, "num_tokens": 323602455.0, "step": 54135 }, { "epoch": 0.5775980711168959, "grad_norm": 1.5790726274288762, "learning_rate": 2.3606988339429104e-05, "loss": 0.5451, "num_tokens": 323635026.0, "step": 54140 }, { "epoch": 0.5776514141230943, "grad_norm": 1.5653481396651123, "learning_rate": 2.36030791992194e-05, "loss": 0.4557, "num_tokens": 323654152.0, "step": 54145 }, { "epoch": 0.5777047571292928, "grad_norm": 0.8845020503043207, "learning_rate": 2.359917018027385e-05, "loss": 0.495, "num_tokens": 323689748.0, "step": 54150 }, { "epoch": 0.5777581001354912, "grad_norm": 0.7360929533313522, "learning_rate": 2.3595261282714117e-05, "loss": 0.4987, "num_tokens": 323735740.0, "step": 54155 }, { "epoch": 0.5778114431416896, "grad_norm": 0.949954051316848, "learning_rate": 2.359135250666184e-05, "loss": 0.5871, "num_tokens": 323758899.0, "step": 54160 }, { "epoch": 0.5778647861478882, "grad_norm": 0.672076485680284, "learning_rate": 2.3587443852238637e-05, "loss": 0.5207, "num_tokens": 323788646.0, "step": 54165 }, { "epoch": 0.5779181291540866, "grad_norm": 1.483887671484994, "learning_rate": 2.3583535319566142e-05, "loss": 0.5103, "num_tokens": 323810853.0, "step": 54170 }, { "epoch": 0.5779714721602851, "grad_norm": 1.5153914967604034, "learning_rate": 2.3579626908765994e-05, "loss": 0.6557, "num_tokens": 323843835.0, "step": 54175 }, { "epoch": 0.5780248151664835, "grad_norm": 0.8245688777873639, "learning_rate": 2.357571861995979e-05, "loss": 0.4711, "num_tokens": 323867572.0, "step": 54180 }, { "epoch": 0.5780781581726819, "grad_norm": 1.2513712404128663, "learning_rate": 2.357181045326917e-05, "loss": 0.5868, "num_tokens": 323898301.0, "step": 54185 }, { "epoch": 0.5781315011788805, "grad_norm": 0.5687205578052192, "learning_rate": 2.356790240881575e-05, "loss": 0.6104, "num_tokens": 323932322.0, "step": 54190 }, { "epoch": 0.5781848441850789, "grad_norm": 0.8561269578712587, "learning_rate": 2.3563994486721114e-05, "loss": 0.5045, "num_tokens": 323960078.0, "step": 54195 }, { "epoch": 0.5782381871912774, "grad_norm": 1.2468180723121067, "learning_rate": 2.3560086687106893e-05, "loss": 0.5624, "num_tokens": 323977389.0, "step": 54200 }, { "epoch": 0.5782915301974758, "grad_norm": 0.9173141399425561, "learning_rate": 2.355617901009468e-05, "loss": 0.409, "num_tokens": 323996928.0, "step": 54205 }, { "epoch": 0.5783448732036742, "grad_norm": 0.8911379634296897, "learning_rate": 2.355227145580607e-05, "loss": 0.6025, "num_tokens": 324041349.0, "step": 54210 }, { "epoch": 0.5783982162098728, "grad_norm": 0.9471013137526838, "learning_rate": 2.354836402436266e-05, "loss": 0.5226, "num_tokens": 324066846.0, "step": 54215 }, { "epoch": 0.5784515592160712, "grad_norm": 0.8362228242535109, "learning_rate": 2.354445671588606e-05, "loss": 0.5297, "num_tokens": 324107926.0, "step": 54220 }, { "epoch": 0.5785049022222697, "grad_norm": 0.6757642268964521, "learning_rate": 2.3540549530497836e-05, "loss": 0.443, "num_tokens": 324140975.0, "step": 54225 }, { "epoch": 0.5785582452284681, "grad_norm": 0.8415716708032454, "learning_rate": 2.353664246831957e-05, "loss": 0.4414, "num_tokens": 324165258.0, "step": 54230 }, { "epoch": 0.5786115882346665, "grad_norm": 1.4946366067567727, "learning_rate": 2.353273552947286e-05, "loss": 0.545, "num_tokens": 324186758.0, "step": 54235 }, { "epoch": 0.578664931240865, "grad_norm": 0.8139495481471265, "learning_rate": 2.3528828714079272e-05, "loss": 0.6354, "num_tokens": 324223484.0, "step": 54240 }, { "epoch": 0.5787182742470635, "grad_norm": 0.6895175268128152, "learning_rate": 2.3524922022260364e-05, "loss": 0.457, "num_tokens": 324263066.0, "step": 54245 }, { "epoch": 0.5787716172532619, "grad_norm": 1.2629411921182696, "learning_rate": 2.3521015454137736e-05, "loss": 0.5973, "num_tokens": 324293587.0, "step": 54250 }, { "epoch": 0.5788249602594604, "grad_norm": 0.9972767896634376, "learning_rate": 2.351710900983292e-05, "loss": 0.4688, "num_tokens": 324318971.0, "step": 54255 }, { "epoch": 0.5788783032656588, "grad_norm": 0.7325160960807718, "learning_rate": 2.3513202689467488e-05, "loss": 0.6474, "num_tokens": 324353801.0, "step": 54260 }, { "epoch": 0.5789316462718573, "grad_norm": 0.9176000603177012, "learning_rate": 2.3509296493163013e-05, "loss": 0.5065, "num_tokens": 324382475.0, "step": 54265 }, { "epoch": 0.5789849892780558, "grad_norm": 0.8227098993351503, "learning_rate": 2.3505390421041023e-05, "loss": 0.6533, "num_tokens": 324416457.0, "step": 54270 }, { "epoch": 0.5790383322842542, "grad_norm": 1.0872514406570664, "learning_rate": 2.3501484473223086e-05, "loss": 0.5204, "num_tokens": 324433867.0, "step": 54275 }, { "epoch": 0.5790916752904527, "grad_norm": 0.7184486912171828, "learning_rate": 2.3497578649830738e-05, "loss": 0.4699, "num_tokens": 324468404.0, "step": 54280 }, { "epoch": 0.5791450182966511, "grad_norm": 0.9419259001248232, "learning_rate": 2.349367295098551e-05, "loss": 0.4385, "num_tokens": 324493636.0, "step": 54285 }, { "epoch": 0.5791983613028496, "grad_norm": 0.8265353451935594, "learning_rate": 2.3489767376808962e-05, "loss": 0.6394, "num_tokens": 324523045.0, "step": 54290 }, { "epoch": 0.579251704309048, "grad_norm": 0.94751660114936, "learning_rate": 2.3485861927422613e-05, "loss": 0.6706, "num_tokens": 324560020.0, "step": 54295 }, { "epoch": 0.5793050473152465, "grad_norm": 0.6379199200301942, "learning_rate": 2.3481956602947992e-05, "loss": 0.4467, "num_tokens": 324595865.0, "step": 54300 }, { "epoch": 0.579358390321445, "grad_norm": 1.0205683442759568, "learning_rate": 2.347805140350663e-05, "loss": 0.4841, "num_tokens": 324610920.0, "step": 54305 }, { "epoch": 0.5794117333276434, "grad_norm": 1.2649631322034227, "learning_rate": 2.3474146329220055e-05, "loss": 0.5704, "num_tokens": 324650078.0, "step": 54310 }, { "epoch": 0.5794650763338419, "grad_norm": 1.1779990031992453, "learning_rate": 2.3470241380209763e-05, "loss": 0.5814, "num_tokens": 324665273.0, "step": 54315 }, { "epoch": 0.5795184193400403, "grad_norm": 1.0767964762272255, "learning_rate": 2.3466336556597284e-05, "loss": 0.5319, "num_tokens": 324700430.0, "step": 54320 }, { "epoch": 0.5795717623462388, "grad_norm": 0.9463212451816475, "learning_rate": 2.3462431858504137e-05, "loss": 0.465, "num_tokens": 324720969.0, "step": 54325 }, { "epoch": 0.5796251053524373, "grad_norm": 0.5841986135382037, "learning_rate": 2.345852728605181e-05, "loss": 0.4541, "num_tokens": 324742011.0, "step": 54330 }, { "epoch": 0.5796784483586357, "grad_norm": 0.718664964883907, "learning_rate": 2.345462283936181e-05, "loss": 0.4353, "num_tokens": 324768053.0, "step": 54335 }, { "epoch": 0.5797317913648341, "grad_norm": 1.0635680409337906, "learning_rate": 2.3450718518555635e-05, "loss": 0.3247, "num_tokens": 324788927.0, "step": 54340 }, { "epoch": 0.5797851343710326, "grad_norm": 1.013110044721633, "learning_rate": 2.3446814323754795e-05, "loss": 0.5963, "num_tokens": 324842029.0, "step": 54345 }, { "epoch": 0.579838477377231, "grad_norm": 0.9736425446505652, "learning_rate": 2.3442910255080763e-05, "loss": 0.5505, "num_tokens": 324859062.0, "step": 54350 }, { "epoch": 0.5798918203834296, "grad_norm": 1.3198732648012703, "learning_rate": 2.3439006312655026e-05, "loss": 0.5504, "num_tokens": 324890359.0, "step": 54355 }, { "epoch": 0.579945163389628, "grad_norm": 1.1501162757731256, "learning_rate": 2.3435102496599077e-05, "loss": 0.3142, "num_tokens": 324901314.0, "step": 54360 }, { "epoch": 0.5799985063958264, "grad_norm": 0.9736753909119523, "learning_rate": 2.343119880703439e-05, "loss": 0.4528, "num_tokens": 324922430.0, "step": 54365 }, { "epoch": 0.5800518494020249, "grad_norm": 0.9900954653456141, "learning_rate": 2.3427295244082425e-05, "loss": 0.5193, "num_tokens": 324940408.0, "step": 54370 }, { "epoch": 0.5801051924082233, "grad_norm": 0.4987948925212511, "learning_rate": 2.3423391807864682e-05, "loss": 0.4899, "num_tokens": 324981569.0, "step": 54375 }, { "epoch": 0.5801585354144219, "grad_norm": 1.1581155427937901, "learning_rate": 2.3419488498502602e-05, "loss": 0.4268, "num_tokens": 325008704.0, "step": 54380 }, { "epoch": 0.5802118784206203, "grad_norm": 0.8083130689039633, "learning_rate": 2.3415585316117662e-05, "loss": 0.4889, "num_tokens": 325035483.0, "step": 54385 }, { "epoch": 0.5802652214268187, "grad_norm": 0.9989233017414397, "learning_rate": 2.3411682260831323e-05, "loss": 0.5259, "num_tokens": 325061493.0, "step": 54390 }, { "epoch": 0.5803185644330172, "grad_norm": 1.1677244751693878, "learning_rate": 2.3407779332765024e-05, "loss": 0.4504, "num_tokens": 325076710.0, "step": 54395 }, { "epoch": 0.5803719074392156, "grad_norm": 0.798186872890773, "learning_rate": 2.340387653204023e-05, "loss": 0.5659, "num_tokens": 325102278.0, "step": 54400 }, { "epoch": 0.5804252504454142, "grad_norm": 0.8610987246229603, "learning_rate": 2.3399973858778396e-05, "loss": 0.4778, "num_tokens": 325123266.0, "step": 54405 }, { "epoch": 0.5804785934516126, "grad_norm": 1.8405426143134798, "learning_rate": 2.339607131310093e-05, "loss": 0.4653, "num_tokens": 325140538.0, "step": 54410 }, { "epoch": 0.580531936457811, "grad_norm": 0.9116939299217756, "learning_rate": 2.3392168895129313e-05, "loss": 0.3661, "num_tokens": 325168460.0, "step": 54415 }, { "epoch": 0.5805852794640095, "grad_norm": 0.9047929920604767, "learning_rate": 2.3388266604984966e-05, "loss": 0.5627, "num_tokens": 325196549.0, "step": 54420 }, { "epoch": 0.5806386224702079, "grad_norm": 0.9644434509752083, "learning_rate": 2.3384364442789303e-05, "loss": 0.4705, "num_tokens": 325222311.0, "step": 54425 }, { "epoch": 0.5806919654764063, "grad_norm": 0.8612944591310498, "learning_rate": 2.3380462408663768e-05, "loss": 0.6064, "num_tokens": 325249419.0, "step": 54430 }, { "epoch": 0.5807453084826049, "grad_norm": 0.7193489536012501, "learning_rate": 2.337656050272979e-05, "loss": 0.4857, "num_tokens": 325274304.0, "step": 54435 }, { "epoch": 0.5807986514888033, "grad_norm": 0.8173804608703104, "learning_rate": 2.337265872510877e-05, "loss": 0.4572, "num_tokens": 325308057.0, "step": 54440 }, { "epoch": 0.5808519944950018, "grad_norm": 0.7211364473547641, "learning_rate": 2.3368757075922126e-05, "loss": 0.4335, "num_tokens": 325336811.0, "step": 54445 }, { "epoch": 0.5809053375012002, "grad_norm": 1.0256805809719958, "learning_rate": 2.3364855555291294e-05, "loss": 0.4693, "num_tokens": 325361630.0, "step": 54450 }, { "epoch": 0.5809586805073986, "grad_norm": 0.5704652090609968, "learning_rate": 2.3360954163337656e-05, "loss": 0.4725, "num_tokens": 325410612.0, "step": 54455 }, { "epoch": 0.5810120235135972, "grad_norm": 1.0653855264521368, "learning_rate": 2.335705290018262e-05, "loss": 0.4877, "num_tokens": 325437760.0, "step": 54460 }, { "epoch": 0.5810653665197956, "grad_norm": 1.0904255480933678, "learning_rate": 2.335315176594759e-05, "loss": 0.4886, "num_tokens": 325463413.0, "step": 54465 }, { "epoch": 0.5811187095259941, "grad_norm": 1.2621255672502993, "learning_rate": 2.3349250760753955e-05, "loss": 0.508, "num_tokens": 325487110.0, "step": 54470 }, { "epoch": 0.5811720525321925, "grad_norm": 0.9687295489587515, "learning_rate": 2.3345349884723117e-05, "loss": 0.4829, "num_tokens": 325518352.0, "step": 54475 }, { "epoch": 0.5812253955383909, "grad_norm": 0.8877568948268952, "learning_rate": 2.3341449137976457e-05, "loss": 0.445, "num_tokens": 325542109.0, "step": 54480 }, { "epoch": 0.5812787385445894, "grad_norm": 0.6730526046453279, "learning_rate": 2.333754852063535e-05, "loss": 0.5161, "num_tokens": 325570183.0, "step": 54485 }, { "epoch": 0.5813320815507879, "grad_norm": 0.8041509827866083, "learning_rate": 2.3333648032821186e-05, "loss": 0.4545, "num_tokens": 325587332.0, "step": 54490 }, { "epoch": 0.5813854245569864, "grad_norm": 0.9769885250621642, "learning_rate": 2.3329747674655346e-05, "loss": 0.4105, "num_tokens": 325611245.0, "step": 54495 }, { "epoch": 0.5814387675631848, "grad_norm": 0.8194877592569982, "learning_rate": 2.332584744625918e-05, "loss": 0.4602, "num_tokens": 325645470.0, "step": 54500 }, { "epoch": 0.5814921105693832, "grad_norm": 1.3946310413204666, "learning_rate": 2.332194734775407e-05, "loss": 0.5277, "num_tokens": 325662395.0, "step": 54505 }, { "epoch": 0.5815454535755817, "grad_norm": 0.7461467012677211, "learning_rate": 2.3318047379261382e-05, "loss": 0.4958, "num_tokens": 325692778.0, "step": 54510 }, { "epoch": 0.5815987965817802, "grad_norm": 1.118342909479092, "learning_rate": 2.3314147540902463e-05, "loss": 0.5377, "num_tokens": 325716828.0, "step": 54515 }, { "epoch": 0.5816521395879786, "grad_norm": 1.0182204797962586, "learning_rate": 2.3310247832798675e-05, "loss": 0.5516, "num_tokens": 325741543.0, "step": 54520 }, { "epoch": 0.5817054825941771, "grad_norm": 5.71764149499111, "learning_rate": 2.330634825507138e-05, "loss": 0.5787, "num_tokens": 325765548.0, "step": 54525 }, { "epoch": 0.5817588256003755, "grad_norm": 1.8320550790491432, "learning_rate": 2.3302448807841902e-05, "loss": 0.453, "num_tokens": 325791188.0, "step": 54530 }, { "epoch": 0.581812168606574, "grad_norm": 0.9284523322517478, "learning_rate": 2.3298549491231596e-05, "loss": 0.4803, "num_tokens": 325817300.0, "step": 54535 }, { "epoch": 0.5818655116127724, "grad_norm": 0.46554447811656774, "learning_rate": 2.329465030536181e-05, "loss": 0.4177, "num_tokens": 325845528.0, "step": 54540 }, { "epoch": 0.5819188546189709, "grad_norm": 1.8926839747244926, "learning_rate": 2.329075125035386e-05, "loss": 0.5917, "num_tokens": 325858080.0, "step": 54545 }, { "epoch": 0.5819721976251694, "grad_norm": 0.7982316515077584, "learning_rate": 2.328685232632908e-05, "loss": 0.5272, "num_tokens": 325879833.0, "step": 54550 }, { "epoch": 0.5820255406313678, "grad_norm": 1.1929172151046403, "learning_rate": 2.3282953533408812e-05, "loss": 0.5913, "num_tokens": 325901519.0, "step": 54555 }, { "epoch": 0.5820788836375663, "grad_norm": 0.7260615738162666, "learning_rate": 2.3279054871714362e-05, "loss": 0.5815, "num_tokens": 325942720.0, "step": 54560 }, { "epoch": 0.5821322266437647, "grad_norm": 0.9874475732635671, "learning_rate": 2.3275156341367054e-05, "loss": 0.5185, "num_tokens": 325973925.0, "step": 54565 }, { "epoch": 0.5821855696499632, "grad_norm": 0.6094237982423706, "learning_rate": 2.3271257942488205e-05, "loss": 0.5714, "num_tokens": 326029360.0, "step": 54570 }, { "epoch": 0.5822389126561617, "grad_norm": 0.6307029731363675, "learning_rate": 2.3267359675199125e-05, "loss": 0.4973, "num_tokens": 326056383.0, "step": 54575 }, { "epoch": 0.5822922556623601, "grad_norm": 0.7867519967383173, "learning_rate": 2.326346153962111e-05, "loss": 0.5271, "num_tokens": 326094652.0, "step": 54580 }, { "epoch": 0.5823455986685586, "grad_norm": 1.039616600788167, "learning_rate": 2.3259563535875478e-05, "loss": 0.5238, "num_tokens": 326117276.0, "step": 54585 }, { "epoch": 0.582398941674757, "grad_norm": 0.6860756797182361, "learning_rate": 2.3255665664083513e-05, "loss": 0.5168, "num_tokens": 326148072.0, "step": 54590 }, { "epoch": 0.5824522846809554, "grad_norm": 0.6349746977297749, "learning_rate": 2.3251767924366513e-05, "loss": 0.6234, "num_tokens": 326180202.0, "step": 54595 }, { "epoch": 0.582505627687154, "grad_norm": 0.676635305222831, "learning_rate": 2.3247870316845775e-05, "loss": 0.4994, "num_tokens": 326223837.0, "step": 54600 }, { "epoch": 0.5825589706933524, "grad_norm": 0.7825452709935179, "learning_rate": 2.3243972841642582e-05, "loss": 0.4791, "num_tokens": 326254030.0, "step": 54605 }, { "epoch": 0.5826123136995508, "grad_norm": 1.4998421216309217, "learning_rate": 2.32400754988782e-05, "loss": 0.5792, "num_tokens": 326282055.0, "step": 54610 }, { "epoch": 0.5826656567057493, "grad_norm": 0.6973756997599957, "learning_rate": 2.3236178288673927e-05, "loss": 0.5026, "num_tokens": 326309165.0, "step": 54615 }, { "epoch": 0.5827189997119477, "grad_norm": 0.8459773076604854, "learning_rate": 2.3232281211151025e-05, "loss": 0.5113, "num_tokens": 326335806.0, "step": 54620 }, { "epoch": 0.5827723427181463, "grad_norm": 1.0947518373537375, "learning_rate": 2.3228384266430763e-05, "loss": 0.4564, "num_tokens": 326355276.0, "step": 54625 }, { "epoch": 0.5828256857243447, "grad_norm": 1.2345129491021172, "learning_rate": 2.3224487454634413e-05, "loss": 0.4942, "num_tokens": 326381466.0, "step": 54630 }, { "epoch": 0.5828790287305431, "grad_norm": 0.922075759642215, "learning_rate": 2.322059077588323e-05, "loss": 0.5382, "num_tokens": 326423718.0, "step": 54635 }, { "epoch": 0.5829323717367416, "grad_norm": 1.0858355296392088, "learning_rate": 2.3216694230298468e-05, "loss": 0.396, "num_tokens": 326443825.0, "step": 54640 }, { "epoch": 0.58298571474294, "grad_norm": 0.8251127421213044, "learning_rate": 2.3212797818001392e-05, "loss": 0.4972, "num_tokens": 326470442.0, "step": 54645 }, { "epoch": 0.5830390577491386, "grad_norm": 1.9483142589390343, "learning_rate": 2.3208901539113232e-05, "loss": 0.5049, "num_tokens": 326484936.0, "step": 54650 }, { "epoch": 0.583092400755337, "grad_norm": 1.0705542963851735, "learning_rate": 2.320500539375525e-05, "loss": 0.7014, "num_tokens": 326514011.0, "step": 54655 }, { "epoch": 0.5831457437615354, "grad_norm": 1.1901277819533536, "learning_rate": 2.3201109382048673e-05, "loss": 0.6463, "num_tokens": 326538293.0, "step": 54660 }, { "epoch": 0.5831990867677339, "grad_norm": 0.5790847180460189, "learning_rate": 2.319721350411474e-05, "loss": 0.4207, "num_tokens": 326566132.0, "step": 54665 }, { "epoch": 0.5832524297739323, "grad_norm": 0.637385900950817, "learning_rate": 2.3193317760074685e-05, "loss": 0.4796, "num_tokens": 326607378.0, "step": 54670 }, { "epoch": 0.5833057727801308, "grad_norm": 0.7832223373087243, "learning_rate": 2.3189422150049744e-05, "loss": 0.4805, "num_tokens": 326640167.0, "step": 54675 }, { "epoch": 0.5833591157863293, "grad_norm": 0.8486974926675902, "learning_rate": 2.3185526674161124e-05, "loss": 0.5966, "num_tokens": 326674379.0, "step": 54680 }, { "epoch": 0.5834124587925277, "grad_norm": 0.9058293774241228, "learning_rate": 2.318163133253005e-05, "loss": 0.445, "num_tokens": 326697507.0, "step": 54685 }, { "epoch": 0.5834658017987262, "grad_norm": 1.01724111066993, "learning_rate": 2.317773612527775e-05, "loss": 0.5071, "num_tokens": 326728560.0, "step": 54690 }, { "epoch": 0.5835191448049246, "grad_norm": 1.19551722018293, "learning_rate": 2.3173841052525415e-05, "loss": 0.4582, "num_tokens": 326742688.0, "step": 54695 }, { "epoch": 0.583572487811123, "grad_norm": 1.5382944563908798, "learning_rate": 2.316994611439425e-05, "loss": 0.5172, "num_tokens": 326766398.0, "step": 54700 }, { "epoch": 0.5836258308173216, "grad_norm": 1.2669293184819792, "learning_rate": 2.3166051311005488e-05, "loss": 0.6354, "num_tokens": 326801894.0, "step": 54705 }, { "epoch": 0.58367917382352, "grad_norm": 1.411575480723412, "learning_rate": 2.3162156642480297e-05, "loss": 0.5646, "num_tokens": 326834308.0, "step": 54710 }, { "epoch": 0.5837325168297185, "grad_norm": 0.907128458149903, "learning_rate": 2.3158262108939876e-05, "loss": 0.4366, "num_tokens": 326879378.0, "step": 54715 }, { "epoch": 0.5837858598359169, "grad_norm": 1.078431207731564, "learning_rate": 2.3154367710505432e-05, "loss": 0.387, "num_tokens": 326903105.0, "step": 54720 }, { "epoch": 0.5838392028421153, "grad_norm": 1.1057389597834686, "learning_rate": 2.3150473447298127e-05, "loss": 0.5441, "num_tokens": 326940225.0, "step": 54725 }, { "epoch": 0.5838925458483138, "grad_norm": 2.7343974036767453, "learning_rate": 2.314657931943916e-05, "loss": 0.4969, "num_tokens": 326977687.0, "step": 54730 }, { "epoch": 0.5839458888545123, "grad_norm": 0.9637352339596105, "learning_rate": 2.3142685327049707e-05, "loss": 0.3589, "num_tokens": 327006380.0, "step": 54735 }, { "epoch": 0.5839992318607108, "grad_norm": 0.735165734176347, "learning_rate": 2.3138791470250925e-05, "loss": 0.5392, "num_tokens": 327034220.0, "step": 54740 }, { "epoch": 0.5840525748669092, "grad_norm": 0.762601604023289, "learning_rate": 2.3134897749164002e-05, "loss": 0.5432, "num_tokens": 327082851.0, "step": 54745 }, { "epoch": 0.5841059178731076, "grad_norm": 1.2366467833815857, "learning_rate": 2.3131004163910098e-05, "loss": 0.5413, "num_tokens": 327112291.0, "step": 54750 }, { "epoch": 0.5841592608793061, "grad_norm": 0.9861725423901535, "learning_rate": 2.3127110714610362e-05, "loss": 0.4909, "num_tokens": 327135757.0, "step": 54755 }, { "epoch": 0.5842126038855046, "grad_norm": 0.7147738830410959, "learning_rate": 2.312321740138596e-05, "loss": 0.5049, "num_tokens": 327175245.0, "step": 54760 }, { "epoch": 0.5842659468917031, "grad_norm": 0.4924899596327738, "learning_rate": 2.3119324224358048e-05, "loss": 0.4086, "num_tokens": 327213651.0, "step": 54765 }, { "epoch": 0.5843192898979015, "grad_norm": 0.51037592374971, "learning_rate": 2.311543118364776e-05, "loss": 0.4508, "num_tokens": 327260362.0, "step": 54770 }, { "epoch": 0.5843726329040999, "grad_norm": 0.8294357540098466, "learning_rate": 2.3111538279376248e-05, "loss": 0.5654, "num_tokens": 327295566.0, "step": 54775 }, { "epoch": 0.5844259759102984, "grad_norm": 0.7498010929528428, "learning_rate": 2.310764551166466e-05, "loss": 0.471, "num_tokens": 327315719.0, "step": 54780 }, { "epoch": 0.5844793189164968, "grad_norm": 1.0122639948893264, "learning_rate": 2.3103752880634124e-05, "loss": 0.5378, "num_tokens": 327339811.0, "step": 54785 }, { "epoch": 0.5845326619226953, "grad_norm": 1.1678587455574208, "learning_rate": 2.3099860386405754e-05, "loss": 0.4445, "num_tokens": 327369527.0, "step": 54790 }, { "epoch": 0.5845860049288938, "grad_norm": 0.6134462462103478, "learning_rate": 2.3095968029100694e-05, "loss": 0.5221, "num_tokens": 327405539.0, "step": 54795 }, { "epoch": 0.5846393479350922, "grad_norm": 0.9560545505849601, "learning_rate": 2.3092075808840063e-05, "loss": 0.5346, "num_tokens": 327432278.0, "step": 54800 }, { "epoch": 0.5846926909412907, "grad_norm": 1.1286871111958245, "learning_rate": 2.3088183725744982e-05, "loss": 0.5304, "num_tokens": 327472564.0, "step": 54805 }, { "epoch": 0.5847460339474891, "grad_norm": 0.738367187553323, "learning_rate": 2.3084291779936568e-05, "loss": 0.7439, "num_tokens": 327521770.0, "step": 54810 }, { "epoch": 0.5847993769536876, "grad_norm": 1.036102476762232, "learning_rate": 2.308039997153591e-05, "loss": 0.7609, "num_tokens": 327563439.0, "step": 54815 }, { "epoch": 0.5848527199598861, "grad_norm": 1.1643778235986333, "learning_rate": 2.3076508300664133e-05, "loss": 0.7712, "num_tokens": 327591568.0, "step": 54820 }, { "epoch": 0.5849060629660845, "grad_norm": 1.4102869167147714, "learning_rate": 2.3072616767442334e-05, "loss": 0.4067, "num_tokens": 327610235.0, "step": 54825 }, { "epoch": 0.584959405972283, "grad_norm": 0.6207144145676555, "learning_rate": 2.30687253719916e-05, "loss": 0.4347, "num_tokens": 327648043.0, "step": 54830 }, { "epoch": 0.5850127489784814, "grad_norm": 0.8118129655999186, "learning_rate": 2.3064834114433033e-05, "loss": 0.4931, "num_tokens": 327684090.0, "step": 54835 }, { "epoch": 0.5850660919846798, "grad_norm": 0.8260357832469374, "learning_rate": 2.3060942994887725e-05, "loss": 0.3899, "num_tokens": 327702906.0, "step": 54840 }, { "epoch": 0.5851194349908784, "grad_norm": 1.2398095846957513, "learning_rate": 2.305705201347675e-05, "loss": 0.6562, "num_tokens": 327738509.0, "step": 54845 }, { "epoch": 0.5851727779970768, "grad_norm": 1.3353160601448546, "learning_rate": 2.305316117032118e-05, "loss": 0.4912, "num_tokens": 327768259.0, "step": 54850 }, { "epoch": 0.5852261210032753, "grad_norm": 0.7547191755783831, "learning_rate": 2.3049270465542116e-05, "loss": 0.4172, "num_tokens": 327793641.0, "step": 54855 }, { "epoch": 0.5852794640094737, "grad_norm": 0.9168027130067532, "learning_rate": 2.3045379899260606e-05, "loss": 0.4683, "num_tokens": 327825529.0, "step": 54860 }, { "epoch": 0.5853328070156721, "grad_norm": 1.5339447599335154, "learning_rate": 2.3041489471597716e-05, "loss": 0.5056, "num_tokens": 327846232.0, "step": 54865 }, { "epoch": 0.5853861500218707, "grad_norm": 0.8791377769981671, "learning_rate": 2.303759918267453e-05, "loss": 0.5361, "num_tokens": 327872504.0, "step": 54870 }, { "epoch": 0.5854394930280691, "grad_norm": 0.8950205599944421, "learning_rate": 2.3033709032612084e-05, "loss": 0.4836, "num_tokens": 327897270.0, "step": 54875 }, { "epoch": 0.5854928360342675, "grad_norm": 1.2674745173579096, "learning_rate": 2.3029819021531435e-05, "loss": 0.5827, "num_tokens": 327931126.0, "step": 54880 }, { "epoch": 0.585546179040466, "grad_norm": 0.9354420349154269, "learning_rate": 2.3025929149553643e-05, "loss": 0.4751, "num_tokens": 327950694.0, "step": 54885 }, { "epoch": 0.5855995220466644, "grad_norm": 1.3194644500108597, "learning_rate": 2.302203941679974e-05, "loss": 0.4816, "num_tokens": 327983166.0, "step": 54890 }, { "epoch": 0.585652865052863, "grad_norm": 0.7683791692849642, "learning_rate": 2.3018149823390773e-05, "loss": 0.5932, "num_tokens": 328011895.0, "step": 54895 }, { "epoch": 0.5857062080590614, "grad_norm": 0.8180286582816152, "learning_rate": 2.3014260369447787e-05, "loss": 0.5243, "num_tokens": 328058100.0, "step": 54900 }, { "epoch": 0.5857595510652598, "grad_norm": 0.8400307975363732, "learning_rate": 2.3010371055091795e-05, "loss": 0.3796, "num_tokens": 328084417.0, "step": 54905 }, { "epoch": 0.5858128940714583, "grad_norm": 0.7649621838140552, "learning_rate": 2.3006481880443835e-05, "loss": 0.5629, "num_tokens": 328124622.0, "step": 54910 }, { "epoch": 0.5858662370776567, "grad_norm": 0.719987521262296, "learning_rate": 2.300259284562494e-05, "loss": 0.5669, "num_tokens": 328158656.0, "step": 54915 }, { "epoch": 0.5859195800838553, "grad_norm": 0.9422093742442802, "learning_rate": 2.2998703950756094e-05, "loss": 0.4037, "num_tokens": 328191792.0, "step": 54920 }, { "epoch": 0.5859729230900537, "grad_norm": 1.034935888561338, "learning_rate": 2.2994815195958348e-05, "loss": 0.3867, "num_tokens": 328211060.0, "step": 54925 }, { "epoch": 0.5860262660962521, "grad_norm": 0.7519667057221258, "learning_rate": 2.2990926581352706e-05, "loss": 0.5897, "num_tokens": 328238303.0, "step": 54930 }, { "epoch": 0.5860796091024506, "grad_norm": 0.9328884788273469, "learning_rate": 2.298703810706016e-05, "loss": 0.5293, "num_tokens": 328271353.0, "step": 54935 }, { "epoch": 0.586132952108649, "grad_norm": 0.7859267852121037, "learning_rate": 2.298314977320171e-05, "loss": 0.5498, "num_tokens": 328303907.0, "step": 54940 }, { "epoch": 0.5861862951148475, "grad_norm": 2.535047141184404, "learning_rate": 2.2979261579898382e-05, "loss": 0.5724, "num_tokens": 328325801.0, "step": 54945 }, { "epoch": 0.586239638121046, "grad_norm": 1.4337105742674623, "learning_rate": 2.297537352727113e-05, "loss": 0.4472, "num_tokens": 328356274.0, "step": 54950 }, { "epoch": 0.5862929811272444, "grad_norm": 1.359761818255867, "learning_rate": 2.2971485615440964e-05, "loss": 0.4774, "num_tokens": 328380763.0, "step": 54955 }, { "epoch": 0.5863463241334429, "grad_norm": 0.8185233789250422, "learning_rate": 2.2967597844528876e-05, "loss": 0.4614, "num_tokens": 328412100.0, "step": 54960 }, { "epoch": 0.5863996671396413, "grad_norm": 0.7186439834172101, "learning_rate": 2.2963710214655814e-05, "loss": 0.3868, "num_tokens": 328438357.0, "step": 54965 }, { "epoch": 0.5864530101458397, "grad_norm": 1.1444494123336186, "learning_rate": 2.295982272594278e-05, "loss": 0.5022, "num_tokens": 328458124.0, "step": 54970 }, { "epoch": 0.5865063531520383, "grad_norm": 2.1646491986821426, "learning_rate": 2.2955935378510744e-05, "loss": 0.4735, "num_tokens": 328482901.0, "step": 54975 }, { "epoch": 0.5865596961582367, "grad_norm": 0.8643568402321268, "learning_rate": 2.2952048172480656e-05, "loss": 0.539, "num_tokens": 328503975.0, "step": 54980 }, { "epoch": 0.5866130391644352, "grad_norm": 0.9991128864102932, "learning_rate": 2.2948161107973494e-05, "loss": 0.5278, "num_tokens": 328536441.0, "step": 54985 }, { "epoch": 0.5866663821706336, "grad_norm": 0.8631909552138946, "learning_rate": 2.294427418511021e-05, "loss": 0.5008, "num_tokens": 328558531.0, "step": 54990 }, { "epoch": 0.586719725176832, "grad_norm": 1.0012461656394882, "learning_rate": 2.2940387404011744e-05, "loss": 0.3987, "num_tokens": 328573985.0, "step": 54995 }, { "epoch": 0.5867730681830305, "grad_norm": 0.7318014464308423, "learning_rate": 2.293650076479906e-05, "loss": 0.4167, "num_tokens": 328602135.0, "step": 55000 }, { "epoch": 0.586826411189229, "grad_norm": 0.9565343946365693, "learning_rate": 2.2932614267593107e-05, "loss": 0.3735, "num_tokens": 328628248.0, "step": 55005 }, { "epoch": 0.5868797541954275, "grad_norm": 0.7852482490058137, "learning_rate": 2.2928727912514808e-05, "loss": 0.448, "num_tokens": 328660195.0, "step": 55010 }, { "epoch": 0.5869330972016259, "grad_norm": 0.7682993223695855, "learning_rate": 2.2924841699685108e-05, "loss": 0.6018, "num_tokens": 328694726.0, "step": 55015 }, { "epoch": 0.5869864402078243, "grad_norm": 1.2541770695521155, "learning_rate": 2.2920955629224937e-05, "loss": 0.5464, "num_tokens": 328709843.0, "step": 55020 }, { "epoch": 0.5870397832140228, "grad_norm": 1.1810800536664154, "learning_rate": 2.291706970125523e-05, "loss": 0.6392, "num_tokens": 328733070.0, "step": 55025 }, { "epoch": 0.5870931262202213, "grad_norm": 1.3703512487391794, "learning_rate": 2.2913183915896885e-05, "loss": 0.4722, "num_tokens": 328766229.0, "step": 55030 }, { "epoch": 0.5871464692264198, "grad_norm": 1.1187496915815562, "learning_rate": 2.2909298273270846e-05, "loss": 0.5916, "num_tokens": 328798229.0, "step": 55035 }, { "epoch": 0.5871998122326182, "grad_norm": 0.9486164882427875, "learning_rate": 2.2905412773498018e-05, "loss": 0.6795, "num_tokens": 328831071.0, "step": 55040 }, { "epoch": 0.5872531552388166, "grad_norm": 0.8046747259268094, "learning_rate": 2.2901527416699293e-05, "loss": 0.597, "num_tokens": 328884539.0, "step": 55045 }, { "epoch": 0.5873064982450151, "grad_norm": 1.1992714918003677, "learning_rate": 2.28976422029956e-05, "loss": 0.4612, "num_tokens": 328909607.0, "step": 55050 }, { "epoch": 0.5873598412512135, "grad_norm": 1.1035334416105775, "learning_rate": 2.289375713250782e-05, "loss": 0.5733, "num_tokens": 328945286.0, "step": 55055 }, { "epoch": 0.587413184257412, "grad_norm": 1.0710397817245905, "learning_rate": 2.2889872205356866e-05, "loss": 0.5855, "num_tokens": 328986489.0, "step": 55060 }, { "epoch": 0.5874665272636105, "grad_norm": 1.2982943644327933, "learning_rate": 2.2885987421663618e-05, "loss": 0.4115, "num_tokens": 329007703.0, "step": 55065 }, { "epoch": 0.5875198702698089, "grad_norm": 1.9972315630071917, "learning_rate": 2.288210278154896e-05, "loss": 0.6404, "num_tokens": 329040119.0, "step": 55070 }, { "epoch": 0.5875732132760074, "grad_norm": 1.3399447191193414, "learning_rate": 2.287821828513378e-05, "loss": 0.5319, "num_tokens": 329060752.0, "step": 55075 }, { "epoch": 0.5876265562822058, "grad_norm": 0.8166602129189198, "learning_rate": 2.2874333932538954e-05, "loss": 0.7154, "num_tokens": 329090759.0, "step": 55080 }, { "epoch": 0.5876798992884043, "grad_norm": 1.3120610025416215, "learning_rate": 2.2870449723885352e-05, "loss": 0.4968, "num_tokens": 329129148.0, "step": 55085 }, { "epoch": 0.5877332422946028, "grad_norm": 0.7915733801224784, "learning_rate": 2.2866565659293837e-05, "loss": 0.4979, "num_tokens": 329151747.0, "step": 55090 }, { "epoch": 0.5877865853008012, "grad_norm": 0.9851273257555547, "learning_rate": 2.28626817388853e-05, "loss": 0.4529, "num_tokens": 329186041.0, "step": 55095 }, { "epoch": 0.5878399283069997, "grad_norm": 0.7755909050602726, "learning_rate": 2.2858797962780576e-05, "loss": 0.5208, "num_tokens": 329204467.0, "step": 55100 }, { "epoch": 0.5878932713131981, "grad_norm": 0.8200071734127471, "learning_rate": 2.2854914331100512e-05, "loss": 0.5814, "num_tokens": 329238836.0, "step": 55105 }, { "epoch": 0.5879466143193965, "grad_norm": 1.2805332392476978, "learning_rate": 2.2851030843965994e-05, "loss": 0.5238, "num_tokens": 329259508.0, "step": 55110 }, { "epoch": 0.5879999573255951, "grad_norm": 0.9424049728343543, "learning_rate": 2.2847147501497836e-05, "loss": 0.5228, "num_tokens": 329291177.0, "step": 55115 }, { "epoch": 0.5880533003317935, "grad_norm": 0.8917558505275351, "learning_rate": 2.2843264303816885e-05, "loss": 0.5737, "num_tokens": 329330520.0, "step": 55120 }, { "epoch": 0.588106643337992, "grad_norm": 0.9359141183913099, "learning_rate": 2.2839381251043996e-05, "loss": 0.532, "num_tokens": 329368022.0, "step": 55125 }, { "epoch": 0.5881599863441904, "grad_norm": 0.7168886352164612, "learning_rate": 2.2835498343299976e-05, "loss": 0.5568, "num_tokens": 329414468.0, "step": 55130 }, { "epoch": 0.5882133293503888, "grad_norm": 1.1438563830581534, "learning_rate": 2.2831615580705678e-05, "loss": 0.4864, "num_tokens": 329452319.0, "step": 55135 }, { "epoch": 0.5882666723565874, "grad_norm": 1.6599822850192871, "learning_rate": 2.2827732963381914e-05, "loss": 0.4385, "num_tokens": 329473940.0, "step": 55140 }, { "epoch": 0.5883200153627858, "grad_norm": 1.31178572596393, "learning_rate": 2.2823850491449495e-05, "loss": 0.4785, "num_tokens": 329511628.0, "step": 55145 }, { "epoch": 0.5883733583689842, "grad_norm": 0.7680746331289269, "learning_rate": 2.2819968165029243e-05, "loss": 0.5059, "num_tokens": 329542751.0, "step": 55150 }, { "epoch": 0.5884267013751827, "grad_norm": 0.7915954142070045, "learning_rate": 2.281608598424198e-05, "loss": 0.6406, "num_tokens": 329578488.0, "step": 55155 }, { "epoch": 0.5884800443813811, "grad_norm": 0.9583939651594962, "learning_rate": 2.281220394920849e-05, "loss": 0.4754, "num_tokens": 329609349.0, "step": 55160 }, { "epoch": 0.5885333873875797, "grad_norm": 0.9438149784982143, "learning_rate": 2.2808322060049588e-05, "loss": 0.5625, "num_tokens": 329635541.0, "step": 55165 }, { "epoch": 0.5885867303937781, "grad_norm": 0.8010288312223449, "learning_rate": 2.2804440316886072e-05, "loss": 0.4645, "num_tokens": 329688590.0, "step": 55170 }, { "epoch": 0.5886400733999765, "grad_norm": 1.075666814987457, "learning_rate": 2.2800558719838717e-05, "loss": 0.4022, "num_tokens": 329711260.0, "step": 55175 }, { "epoch": 0.588693416406175, "grad_norm": 0.6759730590005188, "learning_rate": 2.279667726902832e-05, "loss": 0.5249, "num_tokens": 329741877.0, "step": 55180 }, { "epoch": 0.5887467594123734, "grad_norm": 0.5552181746903855, "learning_rate": 2.2792795964575675e-05, "loss": 0.4166, "num_tokens": 329781695.0, "step": 55185 }, { "epoch": 0.588800102418572, "grad_norm": 0.9307742173381923, "learning_rate": 2.2788914806601554e-05, "loss": 0.5161, "num_tokens": 329826597.0, "step": 55190 }, { "epoch": 0.5888534454247704, "grad_norm": 0.9187841678920643, "learning_rate": 2.278503379522671e-05, "loss": 0.418, "num_tokens": 329844353.0, "step": 55195 }, { "epoch": 0.5889067884309688, "grad_norm": 1.1716553284959876, "learning_rate": 2.2781152930571948e-05, "loss": 0.666, "num_tokens": 329868872.0, "step": 55200 }, { "epoch": 0.5889601314371673, "grad_norm": 0.6439034572890797, "learning_rate": 2.2777272212758006e-05, "loss": 0.4258, "num_tokens": 329895061.0, "step": 55205 }, { "epoch": 0.5890134744433657, "grad_norm": 1.348549028167279, "learning_rate": 2.277339164190565e-05, "loss": 0.4623, "num_tokens": 329926014.0, "step": 55210 }, { "epoch": 0.5890668174495642, "grad_norm": 1.7605207595113865, "learning_rate": 2.276951121813565e-05, "loss": 0.5505, "num_tokens": 329944394.0, "step": 55215 }, { "epoch": 0.5891201604557627, "grad_norm": 0.7119653011530735, "learning_rate": 2.276563094156873e-05, "loss": 0.4433, "num_tokens": 329983186.0, "step": 55220 }, { "epoch": 0.5891735034619611, "grad_norm": 0.7571916269387152, "learning_rate": 2.276175081232565e-05, "loss": 0.5886, "num_tokens": 330016582.0, "step": 55225 }, { "epoch": 0.5892268464681596, "grad_norm": 0.8209752875876856, "learning_rate": 2.275787083052716e-05, "loss": 0.5824, "num_tokens": 330055962.0, "step": 55230 }, { "epoch": 0.589280189474358, "grad_norm": 1.1732141913548206, "learning_rate": 2.2753990996293985e-05, "loss": 0.4688, "num_tokens": 330080368.0, "step": 55235 }, { "epoch": 0.5893335324805564, "grad_norm": 0.6469566402077367, "learning_rate": 2.2750111309746865e-05, "loss": 0.4424, "num_tokens": 330109817.0, "step": 55240 }, { "epoch": 0.589386875486755, "grad_norm": 0.7094317080007839, "learning_rate": 2.2746231771006516e-05, "loss": 0.4568, "num_tokens": 330135007.0, "step": 55245 }, { "epoch": 0.5894402184929534, "grad_norm": 0.8950528558139795, "learning_rate": 2.2742352380193676e-05, "loss": 0.6858, "num_tokens": 330168493.0, "step": 55250 }, { "epoch": 0.5894935614991519, "grad_norm": 1.6019573026644116, "learning_rate": 2.2738473137429055e-05, "loss": 0.5468, "num_tokens": 330194816.0, "step": 55255 }, { "epoch": 0.5895469045053503, "grad_norm": 0.9328381681894267, "learning_rate": 2.2734594042833373e-05, "loss": 0.5096, "num_tokens": 330219582.0, "step": 55260 }, { "epoch": 0.5896002475115487, "grad_norm": 1.0166873863326311, "learning_rate": 2.273071509652734e-05, "loss": 0.4716, "num_tokens": 330247900.0, "step": 55265 }, { "epoch": 0.5896535905177472, "grad_norm": 1.2172032647385953, "learning_rate": 2.272683629863165e-05, "loss": 0.4757, "num_tokens": 330267337.0, "step": 55270 }, { "epoch": 0.5897069335239457, "grad_norm": 2.2913158430704663, "learning_rate": 2.272295764926701e-05, "loss": 0.5239, "num_tokens": 330286357.0, "step": 55275 }, { "epoch": 0.5897602765301442, "grad_norm": 0.7606343526799801, "learning_rate": 2.2719079148554122e-05, "loss": 0.5186, "num_tokens": 330316368.0, "step": 55280 }, { "epoch": 0.5898136195363426, "grad_norm": 1.0385581206996721, "learning_rate": 2.2715200796613662e-05, "loss": 0.4765, "num_tokens": 330344615.0, "step": 55285 }, { "epoch": 0.589866962542541, "grad_norm": 0.914274210915146, "learning_rate": 2.2711322593566324e-05, "loss": 0.5207, "num_tokens": 330377724.0, "step": 55290 }, { "epoch": 0.5899203055487395, "grad_norm": 1.0757222049314978, "learning_rate": 2.2707444539532797e-05, "loss": 0.4572, "num_tokens": 330406836.0, "step": 55295 }, { "epoch": 0.589973648554938, "grad_norm": 0.7685030667182614, "learning_rate": 2.2703566634633748e-05, "loss": 0.4909, "num_tokens": 330440537.0, "step": 55300 }, { "epoch": 0.5900269915611365, "grad_norm": 1.047412140242798, "learning_rate": 2.2699688878989856e-05, "loss": 0.459, "num_tokens": 330459020.0, "step": 55305 }, { "epoch": 0.5900803345673349, "grad_norm": 1.1069061688271773, "learning_rate": 2.269581127272179e-05, "loss": 0.6113, "num_tokens": 330484993.0, "step": 55310 }, { "epoch": 0.5901336775735333, "grad_norm": 1.0284476048582745, "learning_rate": 2.26919338159502e-05, "loss": 0.5197, "num_tokens": 330519834.0, "step": 55315 }, { "epoch": 0.5901870205797318, "grad_norm": 1.4014890519570893, "learning_rate": 2.2688056508795758e-05, "loss": 0.5375, "num_tokens": 330561937.0, "step": 55320 }, { "epoch": 0.5902403635859302, "grad_norm": 0.6169056490379365, "learning_rate": 2.2684179351379114e-05, "loss": 0.4983, "num_tokens": 330610300.0, "step": 55325 }, { "epoch": 0.5902937065921287, "grad_norm": 2.3779886043624225, "learning_rate": 2.2680302343820918e-05, "loss": 0.72, "num_tokens": 330633796.0, "step": 55330 }, { "epoch": 0.5903470495983272, "grad_norm": 0.9799846374719701, "learning_rate": 2.2676425486241808e-05, "loss": 0.4019, "num_tokens": 330662762.0, "step": 55335 }, { "epoch": 0.5904003926045256, "grad_norm": 1.5472662385625737, "learning_rate": 2.2672548778762435e-05, "loss": 0.6861, "num_tokens": 330701195.0, "step": 55340 }, { "epoch": 0.5904537356107241, "grad_norm": 0.5622586728266965, "learning_rate": 2.2668672221503424e-05, "loss": 0.4231, "num_tokens": 330747994.0, "step": 55345 }, { "epoch": 0.5905070786169225, "grad_norm": 1.8792551128520463, "learning_rate": 2.266479581458541e-05, "loss": 0.5099, "num_tokens": 330771803.0, "step": 55350 }, { "epoch": 0.590560421623121, "grad_norm": 1.4547866797845033, "learning_rate": 2.2660919558129024e-05, "loss": 0.4533, "num_tokens": 330801215.0, "step": 55355 }, { "epoch": 0.5906137646293195, "grad_norm": 0.7489684120361721, "learning_rate": 2.2657043452254873e-05, "loss": 0.4493, "num_tokens": 330823718.0, "step": 55360 }, { "epoch": 0.5906671076355179, "grad_norm": 0.885894081328216, "learning_rate": 2.2653167497083587e-05, "loss": 0.4455, "num_tokens": 330844962.0, "step": 55365 }, { "epoch": 0.5907204506417164, "grad_norm": 1.3897661998337412, "learning_rate": 2.2649291692735774e-05, "loss": 0.5456, "num_tokens": 330882595.0, "step": 55370 }, { "epoch": 0.5907737936479148, "grad_norm": 1.0275371406755653, "learning_rate": 2.2645416039332035e-05, "loss": 0.453, "num_tokens": 330919477.0, "step": 55375 }, { "epoch": 0.5908271366541132, "grad_norm": 0.7262672358675956, "learning_rate": 2.2641540536992972e-05, "loss": 0.4463, "num_tokens": 330953628.0, "step": 55380 }, { "epoch": 0.5908804796603118, "grad_norm": 1.4250166940843951, "learning_rate": 2.26376651858392e-05, "loss": 0.4593, "num_tokens": 330995577.0, "step": 55385 }, { "epoch": 0.5909338226665102, "grad_norm": 0.9684901425386322, "learning_rate": 2.26337899859913e-05, "loss": 0.4669, "num_tokens": 331034585.0, "step": 55390 }, { "epoch": 0.5909871656727087, "grad_norm": 0.7049230116357237, "learning_rate": 2.2629914937569853e-05, "loss": 0.4043, "num_tokens": 331060348.0, "step": 55395 }, { "epoch": 0.5910405086789071, "grad_norm": 1.273796769035742, "learning_rate": 2.2626040040695457e-05, "loss": 0.472, "num_tokens": 331096793.0, "step": 55400 }, { "epoch": 0.5910938516851055, "grad_norm": 0.9717627071702386, "learning_rate": 2.262216529548868e-05, "loss": 0.5859, "num_tokens": 331126447.0, "step": 55405 }, { "epoch": 0.5911471946913041, "grad_norm": 1.8501289921064221, "learning_rate": 2.2618290702070095e-05, "loss": 0.4768, "num_tokens": 331153877.0, "step": 55410 }, { "epoch": 0.5912005376975025, "grad_norm": 1.1636943506948045, "learning_rate": 2.2614416260560283e-05, "loss": 0.5035, "num_tokens": 331183603.0, "step": 55415 }, { "epoch": 0.5912538807037009, "grad_norm": 0.9724649083686846, "learning_rate": 2.261054197107979e-05, "loss": 0.4771, "num_tokens": 331220011.0, "step": 55420 }, { "epoch": 0.5913072237098994, "grad_norm": 0.6535171987425676, "learning_rate": 2.2606667833749202e-05, "loss": 0.5539, "num_tokens": 331259976.0, "step": 55425 }, { "epoch": 0.5913605667160978, "grad_norm": 1.3882484496649423, "learning_rate": 2.2602793848689057e-05, "loss": 0.4602, "num_tokens": 331281374.0, "step": 55430 }, { "epoch": 0.5914139097222963, "grad_norm": 1.5825619044548325, "learning_rate": 2.2598920016019896e-05, "loss": 0.5365, "num_tokens": 331298718.0, "step": 55435 }, { "epoch": 0.5914672527284948, "grad_norm": 0.9604228891217997, "learning_rate": 2.259504633586229e-05, "loss": 0.4055, "num_tokens": 331334112.0, "step": 55440 }, { "epoch": 0.5915205957346932, "grad_norm": 1.05028952563828, "learning_rate": 2.259117280833677e-05, "loss": 0.417, "num_tokens": 331355310.0, "step": 55445 }, { "epoch": 0.5915739387408917, "grad_norm": 1.2520332777800964, "learning_rate": 2.2587299433563857e-05, "loss": 0.5024, "num_tokens": 331366684.0, "step": 55450 }, { "epoch": 0.5916272817470901, "grad_norm": 0.8463114936034349, "learning_rate": 2.25834262116641e-05, "loss": 0.3846, "num_tokens": 331390261.0, "step": 55455 }, { "epoch": 0.5916806247532886, "grad_norm": 1.142123980225777, "learning_rate": 2.2579553142758026e-05, "loss": 0.4783, "num_tokens": 331412427.0, "step": 55460 }, { "epoch": 0.5917339677594871, "grad_norm": 0.8333122417351781, "learning_rate": 2.257568022696614e-05, "loss": 0.4365, "num_tokens": 331449328.0, "step": 55465 }, { "epoch": 0.5917873107656855, "grad_norm": 0.9026745804074563, "learning_rate": 2.2571807464408973e-05, "loss": 0.5813, "num_tokens": 331484235.0, "step": 55470 }, { "epoch": 0.591840653771884, "grad_norm": 2.142255069830072, "learning_rate": 2.256793485520704e-05, "loss": 0.4126, "num_tokens": 331501087.0, "step": 55475 }, { "epoch": 0.5918939967780824, "grad_norm": 0.8623503039835639, "learning_rate": 2.2564062399480846e-05, "loss": 0.5646, "num_tokens": 331533931.0, "step": 55480 }, { "epoch": 0.5919473397842809, "grad_norm": 0.9273494183559505, "learning_rate": 2.256019009735088e-05, "loss": 0.4072, "num_tokens": 331561903.0, "step": 55485 }, { "epoch": 0.5920006827904793, "grad_norm": 1.0557019448840526, "learning_rate": 2.2556317948937668e-05, "loss": 0.4472, "num_tokens": 331582192.0, "step": 55490 }, { "epoch": 0.5920540257966778, "grad_norm": 1.641832134509418, "learning_rate": 2.2552445954361672e-05, "loss": 0.5465, "num_tokens": 331623683.0, "step": 55495 }, { "epoch": 0.5921073688028763, "grad_norm": 0.9155265074379372, "learning_rate": 2.2548574113743398e-05, "loss": 0.3905, "num_tokens": 331642550.0, "step": 55500 }, { "epoch": 0.5921607118090747, "grad_norm": 0.7111725032574916, "learning_rate": 2.2544702427203334e-05, "loss": 0.5342, "num_tokens": 331685736.0, "step": 55505 }, { "epoch": 0.5922140548152731, "grad_norm": 1.170639263816537, "learning_rate": 2.2540830894861948e-05, "loss": 0.6141, "num_tokens": 331738858.0, "step": 55510 }, { "epoch": 0.5922673978214716, "grad_norm": 0.7550409761440324, "learning_rate": 2.2536959516839717e-05, "loss": 0.5422, "num_tokens": 331774438.0, "step": 55515 }, { "epoch": 0.5923207408276701, "grad_norm": 1.0706103803698503, "learning_rate": 2.2533088293257114e-05, "loss": 0.4923, "num_tokens": 331795148.0, "step": 55520 }, { "epoch": 0.5923740838338686, "grad_norm": 0.7932599857332472, "learning_rate": 2.2529217224234596e-05, "loss": 0.4511, "num_tokens": 331824355.0, "step": 55525 }, { "epoch": 0.592427426840067, "grad_norm": 0.9429238754204236, "learning_rate": 2.252534630989263e-05, "loss": 0.4964, "num_tokens": 331857889.0, "step": 55530 }, { "epoch": 0.5924807698462654, "grad_norm": 0.8937969145950294, "learning_rate": 2.2521475550351678e-05, "loss": 0.4931, "num_tokens": 331888179.0, "step": 55535 }, { "epoch": 0.5925341128524639, "grad_norm": 0.7968364955380349, "learning_rate": 2.2517604945732167e-05, "loss": 0.4133, "num_tokens": 331913737.0, "step": 55540 }, { "epoch": 0.5925874558586623, "grad_norm": 1.0257390306752714, "learning_rate": 2.251373449615456e-05, "loss": 0.4784, "num_tokens": 331945643.0, "step": 55545 }, { "epoch": 0.5926407988648609, "grad_norm": 0.6064574837940202, "learning_rate": 2.2509864201739295e-05, "loss": 0.4314, "num_tokens": 331989684.0, "step": 55550 }, { "epoch": 0.5926941418710593, "grad_norm": 0.957757333193241, "learning_rate": 2.2505994062606805e-05, "loss": 0.5366, "num_tokens": 332015597.0, "step": 55555 }, { "epoch": 0.5927474848772577, "grad_norm": 0.669744052736513, "learning_rate": 2.250212407887752e-05, "loss": 0.4518, "num_tokens": 332048023.0, "step": 55560 }, { "epoch": 0.5928008278834562, "grad_norm": 0.7665487711749148, "learning_rate": 2.2498254250671874e-05, "loss": 0.5276, "num_tokens": 332080047.0, "step": 55565 }, { "epoch": 0.5928541708896546, "grad_norm": 0.8261560568421416, "learning_rate": 2.249438457811028e-05, "loss": 0.4289, "num_tokens": 332119661.0, "step": 55570 }, { "epoch": 0.5929075138958532, "grad_norm": 0.8047849269722394, "learning_rate": 2.249051506131315e-05, "loss": 0.4357, "num_tokens": 332137361.0, "step": 55575 }, { "epoch": 0.5929608569020516, "grad_norm": 0.7733254089183459, "learning_rate": 2.248664570040091e-05, "loss": 0.4982, "num_tokens": 332166869.0, "step": 55580 }, { "epoch": 0.59301419990825, "grad_norm": 0.869219632206452, "learning_rate": 2.248277649549395e-05, "loss": 0.4894, "num_tokens": 332197521.0, "step": 55585 }, { "epoch": 0.5930675429144485, "grad_norm": 0.7604867705468, "learning_rate": 2.2478907446712683e-05, "loss": 0.4856, "num_tokens": 332226950.0, "step": 55590 }, { "epoch": 0.5931208859206469, "grad_norm": 1.9742901997068105, "learning_rate": 2.2475038554177507e-05, "loss": 0.4734, "num_tokens": 332237934.0, "step": 55595 }, { "epoch": 0.5931742289268453, "grad_norm": 1.7850645707977997, "learning_rate": 2.2471169818008802e-05, "loss": 0.5186, "num_tokens": 332251807.0, "step": 55600 }, { "epoch": 0.5932275719330439, "grad_norm": 1.4570415020385077, "learning_rate": 2.246730123832697e-05, "loss": 0.5639, "num_tokens": 332275664.0, "step": 55605 }, { "epoch": 0.5932809149392423, "grad_norm": 1.501214055345673, "learning_rate": 2.2463432815252383e-05, "loss": 0.5975, "num_tokens": 332298691.0, "step": 55610 }, { "epoch": 0.5933342579454408, "grad_norm": 1.3782699945989405, "learning_rate": 2.245956454890542e-05, "loss": 0.5453, "num_tokens": 332321069.0, "step": 55615 }, { "epoch": 0.5933876009516392, "grad_norm": 0.818139314325032, "learning_rate": 2.2455696439406454e-05, "loss": 0.5046, "num_tokens": 332353550.0, "step": 55620 }, { "epoch": 0.5934409439578376, "grad_norm": 0.6360053271520735, "learning_rate": 2.2451828486875864e-05, "loss": 0.5244, "num_tokens": 332404645.0, "step": 55625 }, { "epoch": 0.5934942869640362, "grad_norm": 1.1938704186020417, "learning_rate": 2.2447960691433987e-05, "loss": 0.5534, "num_tokens": 332441013.0, "step": 55630 }, { "epoch": 0.5935476299702346, "grad_norm": 0.7269065494009348, "learning_rate": 2.24440930532012e-05, "loss": 0.4383, "num_tokens": 332470325.0, "step": 55635 }, { "epoch": 0.5936009729764331, "grad_norm": 1.2444048404782864, "learning_rate": 2.2440225572297856e-05, "loss": 0.4701, "num_tokens": 332503776.0, "step": 55640 }, { "epoch": 0.5936543159826315, "grad_norm": 0.8209643864343094, "learning_rate": 2.2436358248844303e-05, "loss": 0.5098, "num_tokens": 332539820.0, "step": 55645 }, { "epoch": 0.5937076589888299, "grad_norm": 0.6887486064074245, "learning_rate": 2.2432491082960864e-05, "loss": 0.4658, "num_tokens": 332565614.0, "step": 55650 }, { "epoch": 0.5937610019950285, "grad_norm": 0.9507486573030123, "learning_rate": 2.2428624074767913e-05, "loss": 0.6253, "num_tokens": 332618420.0, "step": 55655 }, { "epoch": 0.5938143450012269, "grad_norm": 2.641033632902416, "learning_rate": 2.2424757224385755e-05, "loss": 0.5867, "num_tokens": 332652355.0, "step": 55660 }, { "epoch": 0.5938676880074254, "grad_norm": 1.1867346515528079, "learning_rate": 2.2420890531934722e-05, "loss": 0.5833, "num_tokens": 332666921.0, "step": 55665 }, { "epoch": 0.5939210310136238, "grad_norm": 0.8107575981912348, "learning_rate": 2.241702399753516e-05, "loss": 0.6246, "num_tokens": 332697153.0, "step": 55670 }, { "epoch": 0.5939743740198222, "grad_norm": 0.7848050397927557, "learning_rate": 2.241315762130735e-05, "loss": 0.6317, "num_tokens": 332742642.0, "step": 55675 }, { "epoch": 0.5940277170260208, "grad_norm": 0.6372187997708036, "learning_rate": 2.240929140337164e-05, "loss": 0.476, "num_tokens": 332767044.0, "step": 55680 }, { "epoch": 0.5940810600322192, "grad_norm": 0.6059618147765394, "learning_rate": 2.2405425343848325e-05, "loss": 0.5373, "num_tokens": 332808125.0, "step": 55685 }, { "epoch": 0.5941344030384176, "grad_norm": 1.2904765327682592, "learning_rate": 2.2401559442857695e-05, "loss": 0.5564, "num_tokens": 332826537.0, "step": 55690 }, { "epoch": 0.5941877460446161, "grad_norm": 0.7000819734455881, "learning_rate": 2.2397693700520074e-05, "loss": 0.418, "num_tokens": 332862982.0, "step": 55695 }, { "epoch": 0.5942410890508145, "grad_norm": 1.2968899304998835, "learning_rate": 2.2393828116955747e-05, "loss": 0.4975, "num_tokens": 332890859.0, "step": 55700 }, { "epoch": 0.594294432057013, "grad_norm": 1.5004171017043666, "learning_rate": 2.2389962692284995e-05, "loss": 0.4532, "num_tokens": 332913087.0, "step": 55705 }, { "epoch": 0.5943477750632115, "grad_norm": 0.7663977550571938, "learning_rate": 2.23860974266281e-05, "loss": 0.4627, "num_tokens": 332946166.0, "step": 55710 }, { "epoch": 0.5944011180694099, "grad_norm": 0.901340473295351, "learning_rate": 2.2382232320105363e-05, "loss": 0.729, "num_tokens": 332966676.0, "step": 55715 }, { "epoch": 0.5944544610756084, "grad_norm": 0.7110597725574012, "learning_rate": 2.2378367372837038e-05, "loss": 0.5892, "num_tokens": 332994983.0, "step": 55720 }, { "epoch": 0.5945078040818068, "grad_norm": 1.2390052530737592, "learning_rate": 2.2374502584943396e-05, "loss": 0.5029, "num_tokens": 333021200.0, "step": 55725 }, { "epoch": 0.5945611470880053, "grad_norm": 0.5679182926773031, "learning_rate": 2.2370637956544716e-05, "loss": 0.5165, "num_tokens": 333067916.0, "step": 55730 }, { "epoch": 0.5946144900942038, "grad_norm": 0.7658530593591701, "learning_rate": 2.2366773487761243e-05, "loss": 0.4424, "num_tokens": 333091313.0, "step": 55735 }, { "epoch": 0.5946678331004022, "grad_norm": 1.066025986796067, "learning_rate": 2.2362909178713225e-05, "loss": 0.5182, "num_tokens": 333128364.0, "step": 55740 }, { "epoch": 0.5947211761066007, "grad_norm": 0.6168021242553094, "learning_rate": 2.2359045029520935e-05, "loss": 0.5031, "num_tokens": 333163916.0, "step": 55745 }, { "epoch": 0.5947745191127991, "grad_norm": 1.1010540169863676, "learning_rate": 2.2355181040304596e-05, "loss": 0.4721, "num_tokens": 333185456.0, "step": 55750 }, { "epoch": 0.5948278621189976, "grad_norm": 1.356361986258823, "learning_rate": 2.2351317211184457e-05, "loss": 0.6034, "num_tokens": 333205708.0, "step": 55755 }, { "epoch": 0.594881205125196, "grad_norm": 1.1898748569480746, "learning_rate": 2.234745354228076e-05, "loss": 0.3914, "num_tokens": 333235869.0, "step": 55760 }, { "epoch": 0.5949345481313945, "grad_norm": 1.5017248351787262, "learning_rate": 2.2343590033713707e-05, "loss": 0.5226, "num_tokens": 333262273.0, "step": 55765 }, { "epoch": 0.594987891137593, "grad_norm": 1.0186608579263918, "learning_rate": 2.233972668560355e-05, "loss": 0.5714, "num_tokens": 333286923.0, "step": 55770 }, { "epoch": 0.5950412341437914, "grad_norm": 0.7964202310539265, "learning_rate": 2.2335863498070507e-05, "loss": 0.4604, "num_tokens": 333306364.0, "step": 55775 }, { "epoch": 0.5950945771499898, "grad_norm": 0.8948245114684763, "learning_rate": 2.233200047123477e-05, "loss": 0.4142, "num_tokens": 333327729.0, "step": 55780 }, { "epoch": 0.5951479201561883, "grad_norm": 1.8448659142659873, "learning_rate": 2.232813760521657e-05, "loss": 0.6522, "num_tokens": 333363424.0, "step": 55785 }, { "epoch": 0.5952012631623868, "grad_norm": 0.8408197421585597, "learning_rate": 2.232427490013611e-05, "loss": 0.633, "num_tokens": 333400358.0, "step": 55790 }, { "epoch": 0.5952546061685853, "grad_norm": 0.7655809545336751, "learning_rate": 2.2320412356113573e-05, "loss": 0.5132, "num_tokens": 333447313.0, "step": 55795 }, { "epoch": 0.5953079491747837, "grad_norm": 0.8428565725601564, "learning_rate": 2.2316549973269164e-05, "loss": 0.4946, "num_tokens": 333475862.0, "step": 55800 }, { "epoch": 0.5953612921809821, "grad_norm": 0.6224669156966215, "learning_rate": 2.2312687751723084e-05, "loss": 0.5891, "num_tokens": 333542896.0, "step": 55805 }, { "epoch": 0.5954146351871806, "grad_norm": 1.4160149870448897, "learning_rate": 2.2308825691595504e-05, "loss": 0.4761, "num_tokens": 333576803.0, "step": 55810 }, { "epoch": 0.595467978193379, "grad_norm": 0.9403013678539803, "learning_rate": 2.2304963793006593e-05, "loss": 0.6047, "num_tokens": 333608324.0, "step": 55815 }, { "epoch": 0.5955213211995776, "grad_norm": 1.384194766240682, "learning_rate": 2.230110205607655e-05, "loss": 0.4856, "num_tokens": 333630888.0, "step": 55820 }, { "epoch": 0.595574664205776, "grad_norm": 2.9925501507217565, "learning_rate": 2.229724048092553e-05, "loss": 0.6117, "num_tokens": 333652453.0, "step": 55825 }, { "epoch": 0.5956280072119744, "grad_norm": 0.8906758898643496, "learning_rate": 2.2293379067673692e-05, "loss": 0.5223, "num_tokens": 333681609.0, "step": 55830 }, { "epoch": 0.5956813502181729, "grad_norm": 0.8316739462897775, "learning_rate": 2.2289517816441218e-05, "loss": 0.5092, "num_tokens": 333709691.0, "step": 55835 }, { "epoch": 0.5957346932243713, "grad_norm": 1.6352681483465832, "learning_rate": 2.228565672734823e-05, "loss": 0.589, "num_tokens": 333739832.0, "step": 55840 }, { "epoch": 0.5957880362305699, "grad_norm": 0.8919233771919729, "learning_rate": 2.2281795800514904e-05, "loss": 0.5002, "num_tokens": 333776640.0, "step": 55845 }, { "epoch": 0.5958413792367683, "grad_norm": 0.712304218769923, "learning_rate": 2.2277935036061375e-05, "loss": 0.5104, "num_tokens": 333808042.0, "step": 55850 }, { "epoch": 0.5958947222429667, "grad_norm": 0.7771426783156876, "learning_rate": 2.2274074434107777e-05, "loss": 0.4576, "num_tokens": 333840324.0, "step": 55855 }, { "epoch": 0.5959480652491652, "grad_norm": 1.008466308185627, "learning_rate": 2.2270213994774248e-05, "loss": 0.4478, "num_tokens": 333866994.0, "step": 55860 }, { "epoch": 0.5960014082553636, "grad_norm": 0.8067177535645101, "learning_rate": 2.2266353718180922e-05, "loss": 0.3986, "num_tokens": 333897517.0, "step": 55865 }, { "epoch": 0.596054751261562, "grad_norm": 0.8008921546760355, "learning_rate": 2.226249360444791e-05, "loss": 0.4962, "num_tokens": 333930941.0, "step": 55870 }, { "epoch": 0.5961080942677606, "grad_norm": 1.2479696617812475, "learning_rate": 2.2258633653695337e-05, "loss": 0.4023, "num_tokens": 333951237.0, "step": 55875 }, { "epoch": 0.596161437273959, "grad_norm": 0.6909931215777845, "learning_rate": 2.2254773866043333e-05, "loss": 0.4209, "num_tokens": 333977037.0, "step": 55880 }, { "epoch": 0.5962147802801575, "grad_norm": 0.9782672069188106, "learning_rate": 2.2250914241611987e-05, "loss": 0.603, "num_tokens": 334006479.0, "step": 55885 }, { "epoch": 0.5962681232863559, "grad_norm": 0.6796004258724005, "learning_rate": 2.22470547805214e-05, "loss": 0.467, "num_tokens": 334030828.0, "step": 55890 }, { "epoch": 0.5963214662925543, "grad_norm": 1.2169491914293737, "learning_rate": 2.2243195482891688e-05, "loss": 0.6409, "num_tokens": 334065827.0, "step": 55895 }, { "epoch": 0.5963748092987529, "grad_norm": 0.5391477689375347, "learning_rate": 2.223933634884293e-05, "loss": 0.4816, "num_tokens": 334120547.0, "step": 55900 }, { "epoch": 0.5964281523049513, "grad_norm": 1.5443506465905044, "learning_rate": 2.2235477378495217e-05, "loss": 0.4426, "num_tokens": 334137339.0, "step": 55905 }, { "epoch": 0.5964814953111498, "grad_norm": 0.5651998085376762, "learning_rate": 2.223161857196864e-05, "loss": 0.5891, "num_tokens": 334164986.0, "step": 55910 }, { "epoch": 0.5965348383173482, "grad_norm": 1.443983480261204, "learning_rate": 2.2227759929383268e-05, "loss": 0.4798, "num_tokens": 334184782.0, "step": 55915 }, { "epoch": 0.5965881813235466, "grad_norm": 1.3621166720911884, "learning_rate": 2.2223901450859173e-05, "loss": 0.6109, "num_tokens": 334217974.0, "step": 55920 }, { "epoch": 0.5966415243297452, "grad_norm": 1.1002124052597524, "learning_rate": 2.2220043136516437e-05, "loss": 0.5312, "num_tokens": 334257488.0, "step": 55925 }, { "epoch": 0.5966948673359436, "grad_norm": 1.288777918100938, "learning_rate": 2.2216184986475108e-05, "loss": 0.5026, "num_tokens": 334293274.0, "step": 55930 }, { "epoch": 0.5967482103421421, "grad_norm": 0.8123225410104068, "learning_rate": 2.2212327000855247e-05, "loss": 0.3996, "num_tokens": 334318555.0, "step": 55935 }, { "epoch": 0.5968015533483405, "grad_norm": 0.7725347017714755, "learning_rate": 2.2208469179776913e-05, "loss": 0.4589, "num_tokens": 334359702.0, "step": 55940 }, { "epoch": 0.5968548963545389, "grad_norm": 0.6898902369191802, "learning_rate": 2.2204611523360148e-05, "loss": 0.5501, "num_tokens": 334397020.0, "step": 55945 }, { "epoch": 0.5969082393607374, "grad_norm": 0.6774512429699302, "learning_rate": 2.2200754031724992e-05, "loss": 0.4579, "num_tokens": 334440315.0, "step": 55950 }, { "epoch": 0.5969615823669359, "grad_norm": 1.0487933475634283, "learning_rate": 2.2196896704991492e-05, "loss": 0.562, "num_tokens": 334476610.0, "step": 55955 }, { "epoch": 0.5970149253731343, "grad_norm": 1.3278828884332494, "learning_rate": 2.219303954327967e-05, "loss": 0.5154, "num_tokens": 334494945.0, "step": 55960 }, { "epoch": 0.5970682683793328, "grad_norm": 1.228320915089011, "learning_rate": 2.2189182546709547e-05, "loss": 0.5261, "num_tokens": 334517759.0, "step": 55965 }, { "epoch": 0.5971216113855312, "grad_norm": 0.6352994474223997, "learning_rate": 2.218532571540117e-05, "loss": 0.566, "num_tokens": 334561063.0, "step": 55970 }, { "epoch": 0.5971749543917297, "grad_norm": 0.8495656746622295, "learning_rate": 2.2181469049474533e-05, "loss": 0.4471, "num_tokens": 334588793.0, "step": 55975 }, { "epoch": 0.5972282973979282, "grad_norm": 0.7958721238446724, "learning_rate": 2.2177612549049652e-05, "loss": 0.4681, "num_tokens": 334622846.0, "step": 55980 }, { "epoch": 0.5972816404041266, "grad_norm": 0.8395269204616095, "learning_rate": 2.2173756214246542e-05, "loss": 0.4634, "num_tokens": 334650665.0, "step": 55985 }, { "epoch": 0.5973349834103251, "grad_norm": 0.9281665717663922, "learning_rate": 2.21699000451852e-05, "loss": 0.63, "num_tokens": 334690451.0, "step": 55990 }, { "epoch": 0.5973883264165235, "grad_norm": 1.287325999380112, "learning_rate": 2.2166044041985605e-05, "loss": 0.4802, "num_tokens": 334714850.0, "step": 55995 }, { "epoch": 0.597441669422722, "grad_norm": 0.7593964942154094, "learning_rate": 2.2162188204767786e-05, "loss": 0.611, "num_tokens": 334743310.0, "step": 56000 }, { "epoch": 0.5974950124289204, "grad_norm": 3.048290180544815, "learning_rate": 2.2158332533651687e-05, "loss": 0.4742, "num_tokens": 334767735.0, "step": 56005 }, { "epoch": 0.5975483554351189, "grad_norm": 1.1060834034372902, "learning_rate": 2.2154477028757314e-05, "loss": 0.4325, "num_tokens": 334788348.0, "step": 56010 }, { "epoch": 0.5976016984413174, "grad_norm": 1.037821063796739, "learning_rate": 2.2150621690204643e-05, "loss": 0.5772, "num_tokens": 334812553.0, "step": 56015 }, { "epoch": 0.5976550414475158, "grad_norm": 0.7573488049515438, "learning_rate": 2.2146766518113628e-05, "loss": 0.5229, "num_tokens": 334845827.0, "step": 56020 }, { "epoch": 0.5977083844537143, "grad_norm": 0.714304182953395, "learning_rate": 2.2142911512604242e-05, "loss": 0.4302, "num_tokens": 334869803.0, "step": 56025 }, { "epoch": 0.5977617274599127, "grad_norm": 1.8039149850136653, "learning_rate": 2.2139056673796453e-05, "loss": 0.4667, "num_tokens": 334898554.0, "step": 56030 }, { "epoch": 0.5978150704661112, "grad_norm": 1.586648125073733, "learning_rate": 2.21352020018102e-05, "loss": 0.6634, "num_tokens": 334924917.0, "step": 56035 }, { "epoch": 0.5978684134723097, "grad_norm": 1.1608692629889181, "learning_rate": 2.213134749676544e-05, "loss": 0.4814, "num_tokens": 334956974.0, "step": 56040 }, { "epoch": 0.5979217564785081, "grad_norm": 1.2355662022425324, "learning_rate": 2.2127493158782132e-05, "loss": 0.4803, "num_tokens": 334980529.0, "step": 56045 }, { "epoch": 0.5979750994847065, "grad_norm": 1.3984609357843842, "learning_rate": 2.2123638987980195e-05, "loss": 0.5045, "num_tokens": 335004096.0, "step": 56050 }, { "epoch": 0.598028442490905, "grad_norm": 1.013936738367818, "learning_rate": 2.2119784984479565e-05, "loss": 0.3911, "num_tokens": 335026043.0, "step": 56055 }, { "epoch": 0.5980817854971034, "grad_norm": 1.094936132698223, "learning_rate": 2.2115931148400183e-05, "loss": 0.4771, "num_tokens": 335054641.0, "step": 56060 }, { "epoch": 0.598135128503302, "grad_norm": 0.6690375156971117, "learning_rate": 2.2112077479861957e-05, "loss": 0.4545, "num_tokens": 335092914.0, "step": 56065 }, { "epoch": 0.5981884715095004, "grad_norm": 1.2761595049906358, "learning_rate": 2.210822397898481e-05, "loss": 0.5548, "num_tokens": 335124714.0, "step": 56070 }, { "epoch": 0.5982418145156988, "grad_norm": 0.6645743325495469, "learning_rate": 2.2104370645888666e-05, "loss": 0.5387, "num_tokens": 335151962.0, "step": 56075 }, { "epoch": 0.5982951575218973, "grad_norm": 1.0582695566583948, "learning_rate": 2.2100517480693426e-05, "loss": 0.5485, "num_tokens": 335187641.0, "step": 56080 }, { "epoch": 0.5983485005280957, "grad_norm": 1.1288389192945372, "learning_rate": 2.209666448351898e-05, "loss": 0.5697, "num_tokens": 335215455.0, "step": 56085 }, { "epoch": 0.5984018435342943, "grad_norm": 1.2471225576195542, "learning_rate": 2.209281165448525e-05, "loss": 0.6039, "num_tokens": 335242372.0, "step": 56090 }, { "epoch": 0.5984551865404927, "grad_norm": 1.1229539971374758, "learning_rate": 2.2088958993712104e-05, "loss": 0.5361, "num_tokens": 335272034.0, "step": 56095 }, { "epoch": 0.5985085295466911, "grad_norm": 0.9991842349025135, "learning_rate": 2.208510650131944e-05, "loss": 0.4842, "num_tokens": 335301967.0, "step": 56100 }, { "epoch": 0.5985618725528896, "grad_norm": 0.9452161956565392, "learning_rate": 2.2081254177427154e-05, "loss": 0.4837, "num_tokens": 335335765.0, "step": 56105 }, { "epoch": 0.598615215559088, "grad_norm": 0.8592779728378939, "learning_rate": 2.2077402022155087e-05, "loss": 0.3637, "num_tokens": 335355980.0, "step": 56110 }, { "epoch": 0.5986685585652866, "grad_norm": 0.6158727290274237, "learning_rate": 2.207355003562314e-05, "loss": 0.6281, "num_tokens": 335397949.0, "step": 56115 }, { "epoch": 0.598721901571485, "grad_norm": 1.0364713341194085, "learning_rate": 2.206969821795118e-05, "loss": 0.4505, "num_tokens": 335419883.0, "step": 56120 }, { "epoch": 0.5987752445776834, "grad_norm": 0.7285153714059158, "learning_rate": 2.206584656925904e-05, "loss": 0.4169, "num_tokens": 335439273.0, "step": 56125 }, { "epoch": 0.5988285875838819, "grad_norm": 0.8899738647754878, "learning_rate": 2.2061995089666592e-05, "loss": 0.4629, "num_tokens": 335462520.0, "step": 56130 }, { "epoch": 0.5988819305900803, "grad_norm": 0.5345163738226403, "learning_rate": 2.2058143779293706e-05, "loss": 0.4981, "num_tokens": 335511417.0, "step": 56135 }, { "epoch": 0.5989352735962787, "grad_norm": 1.0074419195997517, "learning_rate": 2.2054292638260195e-05, "loss": 0.4483, "num_tokens": 335526293.0, "step": 56140 }, { "epoch": 0.5989886166024773, "grad_norm": 1.2519790046075845, "learning_rate": 2.2050441666685904e-05, "loss": 0.3952, "num_tokens": 335537150.0, "step": 56145 }, { "epoch": 0.5990419596086757, "grad_norm": 1.3622276824404045, "learning_rate": 2.2046590864690687e-05, "loss": 0.5187, "num_tokens": 335557856.0, "step": 56150 }, { "epoch": 0.5990953026148742, "grad_norm": 0.9321665296909186, "learning_rate": 2.204274023239436e-05, "loss": 0.4948, "num_tokens": 335603800.0, "step": 56155 }, { "epoch": 0.5991486456210726, "grad_norm": 0.9033624630933637, "learning_rate": 2.2038889769916737e-05, "loss": 0.544, "num_tokens": 335631960.0, "step": 56160 }, { "epoch": 0.599201988627271, "grad_norm": 0.9023454735224316, "learning_rate": 2.203503947737766e-05, "loss": 0.5106, "num_tokens": 335653177.0, "step": 56165 }, { "epoch": 0.5992553316334696, "grad_norm": 0.6629222549896074, "learning_rate": 2.203118935489692e-05, "loss": 0.4464, "num_tokens": 335700617.0, "step": 56170 }, { "epoch": 0.599308674639668, "grad_norm": 0.7870957271556235, "learning_rate": 2.202733940259433e-05, "loss": 0.4746, "num_tokens": 335728547.0, "step": 56175 }, { "epoch": 0.5993620176458665, "grad_norm": 1.2588115588506414, "learning_rate": 2.2023489620589704e-05, "loss": 0.4947, "num_tokens": 335768148.0, "step": 56180 }, { "epoch": 0.5994153606520649, "grad_norm": 0.8129718501153901, "learning_rate": 2.201964000900284e-05, "loss": 0.4685, "num_tokens": 335809233.0, "step": 56185 }, { "epoch": 0.5994687036582633, "grad_norm": 0.803600195532565, "learning_rate": 2.201579056795351e-05, "loss": 0.441, "num_tokens": 335844866.0, "step": 56190 }, { "epoch": 0.5995220466644618, "grad_norm": 0.7814037463373018, "learning_rate": 2.2011941297561516e-05, "loss": 0.548, "num_tokens": 335872845.0, "step": 56195 }, { "epoch": 0.5995753896706603, "grad_norm": 0.8432000765781796, "learning_rate": 2.2008092197946638e-05, "loss": 0.4746, "num_tokens": 335901545.0, "step": 56200 }, { "epoch": 0.5996287326768588, "grad_norm": 0.9095795877228174, "learning_rate": 2.2004243269228642e-05, "loss": 0.4749, "num_tokens": 335926417.0, "step": 56205 }, { "epoch": 0.5996820756830572, "grad_norm": 0.7117385182421004, "learning_rate": 2.2000394511527317e-05, "loss": 0.4386, "num_tokens": 335959949.0, "step": 56210 }, { "epoch": 0.5997354186892556, "grad_norm": 1.0463230566933217, "learning_rate": 2.199654592496242e-05, "loss": 0.4749, "num_tokens": 335982444.0, "step": 56215 }, { "epoch": 0.5997887616954541, "grad_norm": 1.2071106930911908, "learning_rate": 2.19926975096537e-05, "loss": 0.5189, "num_tokens": 336021046.0, "step": 56220 }, { "epoch": 0.5998421047016526, "grad_norm": 0.9037068893414056, "learning_rate": 2.1988849265720923e-05, "loss": 0.4302, "num_tokens": 336043125.0, "step": 56225 }, { "epoch": 0.599895447707851, "grad_norm": 0.7131164198741192, "learning_rate": 2.1985001193283845e-05, "loss": 0.4999, "num_tokens": 336069567.0, "step": 56230 }, { "epoch": 0.5999487907140495, "grad_norm": 0.7709691283338459, "learning_rate": 2.198115329246219e-05, "loss": 0.5281, "num_tokens": 336108426.0, "step": 56235 }, { "epoch": 0.6000021337202479, "grad_norm": 0.9664268822725094, "learning_rate": 2.1977305563375715e-05, "loss": 0.517, "num_tokens": 336136147.0, "step": 56240 }, { "epoch": 0.6000554767264464, "grad_norm": 1.0023533554206665, "learning_rate": 2.1973458006144147e-05, "loss": 0.4618, "num_tokens": 336171616.0, "step": 56245 }, { "epoch": 0.6001088197326448, "grad_norm": 1.5212227946478503, "learning_rate": 2.196961062088721e-05, "loss": 0.4298, "num_tokens": 336204333.0, "step": 56250 }, { "epoch": 0.6001621627388433, "grad_norm": 0.8973227719451069, "learning_rate": 2.1965763407724633e-05, "loss": 0.4746, "num_tokens": 336231911.0, "step": 56255 }, { "epoch": 0.6002155057450418, "grad_norm": 1.0998750549430516, "learning_rate": 2.1961916366776136e-05, "loss": 0.4764, "num_tokens": 336266476.0, "step": 56260 }, { "epoch": 0.6002688487512402, "grad_norm": 0.7553356815145783, "learning_rate": 2.1958069498161422e-05, "loss": 0.4714, "num_tokens": 336296438.0, "step": 56265 }, { "epoch": 0.6003221917574387, "grad_norm": 1.8389464414166896, "learning_rate": 2.1954222802000197e-05, "loss": 0.4951, "num_tokens": 336313907.0, "step": 56270 }, { "epoch": 0.6003755347636371, "grad_norm": 1.1734484901861415, "learning_rate": 2.1950376278412178e-05, "loss": 0.5169, "num_tokens": 336338006.0, "step": 56275 }, { "epoch": 0.6004288777698356, "grad_norm": 0.7676181006560902, "learning_rate": 2.194652992751704e-05, "loss": 0.428, "num_tokens": 336364891.0, "step": 56280 }, { "epoch": 0.6004822207760341, "grad_norm": 1.6923552616699395, "learning_rate": 2.1942683749434483e-05, "loss": 0.4676, "num_tokens": 336393989.0, "step": 56285 }, { "epoch": 0.6005355637822325, "grad_norm": 0.7707212624239376, "learning_rate": 2.19388377442842e-05, "loss": 0.4133, "num_tokens": 336430430.0, "step": 56290 }, { "epoch": 0.600588906788431, "grad_norm": 0.8637715061798181, "learning_rate": 2.193499191218586e-05, "loss": 0.4288, "num_tokens": 336450603.0, "step": 56295 }, { "epoch": 0.6006422497946294, "grad_norm": 1.0392911681804666, "learning_rate": 2.1931146253259138e-05, "loss": 0.5725, "num_tokens": 336492604.0, "step": 56300 }, { "epoch": 0.6006955928008278, "grad_norm": 0.7738321685840155, "learning_rate": 2.1927300767623716e-05, "loss": 0.4608, "num_tokens": 336517429.0, "step": 56305 }, { "epoch": 0.6007489358070264, "grad_norm": 0.7794360018677783, "learning_rate": 2.192345545539924e-05, "loss": 0.559, "num_tokens": 336545481.0, "step": 56310 }, { "epoch": 0.6008022788132248, "grad_norm": 0.8017771052973766, "learning_rate": 2.1919610316705368e-05, "loss": 0.4128, "num_tokens": 336568885.0, "step": 56315 }, { "epoch": 0.6008556218194232, "grad_norm": 0.8034672470155683, "learning_rate": 2.1915765351661776e-05, "loss": 0.4464, "num_tokens": 336595638.0, "step": 56320 }, { "epoch": 0.6009089648256217, "grad_norm": 0.870384918295443, "learning_rate": 2.1911920560388088e-05, "loss": 0.3702, "num_tokens": 336622426.0, "step": 56325 }, { "epoch": 0.6009623078318201, "grad_norm": 1.1419870518305615, "learning_rate": 2.1908075943003948e-05, "loss": 0.4884, "num_tokens": 336645940.0, "step": 56330 }, { "epoch": 0.6010156508380187, "grad_norm": 0.8364544801391539, "learning_rate": 2.190423149962901e-05, "loss": 0.4067, "num_tokens": 336691600.0, "step": 56335 }, { "epoch": 0.6010689938442171, "grad_norm": 0.7055878941280362, "learning_rate": 2.190038723038289e-05, "loss": 0.4587, "num_tokens": 336710183.0, "step": 56340 }, { "epoch": 0.6011223368504155, "grad_norm": 0.891858577385152, "learning_rate": 2.189654313538521e-05, "loss": 0.6368, "num_tokens": 336739887.0, "step": 56345 }, { "epoch": 0.601175679856614, "grad_norm": 1.00671844477393, "learning_rate": 2.1892699214755607e-05, "loss": 0.5604, "num_tokens": 336774063.0, "step": 56350 }, { "epoch": 0.6012290228628124, "grad_norm": 0.6995165434841609, "learning_rate": 2.1888855468613683e-05, "loss": 0.4684, "num_tokens": 336789258.0, "step": 56355 }, { "epoch": 0.601282365869011, "grad_norm": 0.8823456026118922, "learning_rate": 2.188501189707905e-05, "loss": 0.412, "num_tokens": 336818453.0, "step": 56360 }, { "epoch": 0.6013357088752094, "grad_norm": 1.1091055273348258, "learning_rate": 2.1881168500271322e-05, "loss": 0.374, "num_tokens": 336833753.0, "step": 56365 }, { "epoch": 0.6013890518814078, "grad_norm": 1.0848117265527035, "learning_rate": 2.187732527831008e-05, "loss": 0.4559, "num_tokens": 336855492.0, "step": 56370 }, { "epoch": 0.6014423948876063, "grad_norm": 0.5880036681845214, "learning_rate": 2.1873482231314924e-05, "loss": 0.4218, "num_tokens": 336880909.0, "step": 56375 }, { "epoch": 0.6014957378938047, "grad_norm": 1.249219261154673, "learning_rate": 2.1869639359405453e-05, "loss": 0.5493, "num_tokens": 336908561.0, "step": 56380 }, { "epoch": 0.6015490809000033, "grad_norm": 0.7954506124835328, "learning_rate": 2.1865796662701226e-05, "loss": 0.6642, "num_tokens": 336944614.0, "step": 56385 }, { "epoch": 0.6016024239062017, "grad_norm": 0.6200986268209525, "learning_rate": 2.1861954141321846e-05, "loss": 0.486, "num_tokens": 336973016.0, "step": 56390 }, { "epoch": 0.6016557669124001, "grad_norm": 0.7398711144418925, "learning_rate": 2.1858111795386872e-05, "loss": 0.5355, "num_tokens": 336992058.0, "step": 56395 }, { "epoch": 0.6017091099185986, "grad_norm": 0.7400180394983134, "learning_rate": 2.185426962501586e-05, "loss": 0.4878, "num_tokens": 337027727.0, "step": 56400 }, { "epoch": 0.601762452924797, "grad_norm": 0.6662407758010996, "learning_rate": 2.185042763032839e-05, "loss": 0.5257, "num_tokens": 337062434.0, "step": 56405 }, { "epoch": 0.6018157959309954, "grad_norm": 1.0304743319919216, "learning_rate": 2.1846585811444015e-05, "loss": 0.5611, "num_tokens": 337091547.0, "step": 56410 }, { "epoch": 0.601869138937194, "grad_norm": 1.5326397088322565, "learning_rate": 2.184274416848226e-05, "loss": 0.5424, "num_tokens": 337114289.0, "step": 56415 }, { "epoch": 0.6019224819433924, "grad_norm": 0.5057738174786898, "learning_rate": 2.183890270156269e-05, "loss": 0.4649, "num_tokens": 337144692.0, "step": 56420 }, { "epoch": 0.6019758249495909, "grad_norm": 0.7338792392367459, "learning_rate": 2.1835061410804847e-05, "loss": 0.4766, "num_tokens": 337162679.0, "step": 56425 }, { "epoch": 0.6020291679557893, "grad_norm": 0.7373926838097739, "learning_rate": 2.1831220296328253e-05, "loss": 0.4727, "num_tokens": 337182722.0, "step": 56430 }, { "epoch": 0.6020825109619877, "grad_norm": 0.7861597018188982, "learning_rate": 2.1827379358252432e-05, "loss": 0.3882, "num_tokens": 337203740.0, "step": 56435 }, { "epoch": 0.6021358539681863, "grad_norm": 0.7416349093587729, "learning_rate": 2.182353859669693e-05, "loss": 0.4756, "num_tokens": 337236189.0, "step": 56440 }, { "epoch": 0.6021891969743847, "grad_norm": 1.1477277864397173, "learning_rate": 2.1819698011781237e-05, "loss": 0.4676, "num_tokens": 337261259.0, "step": 56445 }, { "epoch": 0.6022425399805832, "grad_norm": 0.8701924605987814, "learning_rate": 2.181585760362487e-05, "loss": 0.4971, "num_tokens": 337297054.0, "step": 56450 }, { "epoch": 0.6022958829867816, "grad_norm": 0.7322419711965547, "learning_rate": 2.181201737234735e-05, "loss": 0.4868, "num_tokens": 337319494.0, "step": 56455 }, { "epoch": 0.60234922599298, "grad_norm": 0.8580932188391656, "learning_rate": 2.1808177318068156e-05, "loss": 0.5661, "num_tokens": 337343155.0, "step": 56460 }, { "epoch": 0.6024025689991785, "grad_norm": 0.9944278859833064, "learning_rate": 2.1804337440906797e-05, "loss": 0.3912, "num_tokens": 337358838.0, "step": 56465 }, { "epoch": 0.602455912005377, "grad_norm": 1.0907947115281742, "learning_rate": 2.1800497740982763e-05, "loss": 0.4512, "num_tokens": 337399634.0, "step": 56470 }, { "epoch": 0.6025092550115755, "grad_norm": 8.11861616193583, "learning_rate": 2.1796658218415515e-05, "loss": 0.5701, "num_tokens": 337440380.0, "step": 56475 }, { "epoch": 0.6025625980177739, "grad_norm": 0.8379933613325713, "learning_rate": 2.179281887332456e-05, "loss": 0.386, "num_tokens": 337463503.0, "step": 56480 }, { "epoch": 0.6026159410239723, "grad_norm": 1.9591529673041532, "learning_rate": 2.1788979705829367e-05, "loss": 0.6171, "num_tokens": 337499684.0, "step": 56485 }, { "epoch": 0.6026692840301708, "grad_norm": 0.7208336944646184, "learning_rate": 2.178514071604938e-05, "loss": 0.6198, "num_tokens": 337538226.0, "step": 56490 }, { "epoch": 0.6027226270363693, "grad_norm": 0.9062933853012205, "learning_rate": 2.178130190410408e-05, "loss": 0.399, "num_tokens": 337561741.0, "step": 56495 }, { "epoch": 0.6027759700425677, "grad_norm": 0.7806228020049041, "learning_rate": 2.177746327011292e-05, "loss": 0.6272, "num_tokens": 337610066.0, "step": 56500 }, { "epoch": 0.6028293130487662, "grad_norm": 1.3109928976761804, "learning_rate": 2.1773624814195347e-05, "loss": 0.5813, "num_tokens": 337629805.0, "step": 56505 }, { "epoch": 0.6028826560549646, "grad_norm": 0.6617110353101805, "learning_rate": 2.1769786536470805e-05, "loss": 0.3552, "num_tokens": 337659527.0, "step": 56510 }, { "epoch": 0.6029359990611631, "grad_norm": 1.001492095305689, "learning_rate": 2.1765948437058747e-05, "loss": 0.4502, "num_tokens": 337687805.0, "step": 56515 }, { "epoch": 0.6029893420673615, "grad_norm": 1.0299017637330286, "learning_rate": 2.1762110516078588e-05, "loss": 0.58, "num_tokens": 337733070.0, "step": 56520 }, { "epoch": 0.60304268507356, "grad_norm": 1.0535592970150198, "learning_rate": 2.1758272773649758e-05, "loss": 0.4743, "num_tokens": 337758071.0, "step": 56525 }, { "epoch": 0.6030960280797585, "grad_norm": 0.8996779192662233, "learning_rate": 2.17544352098917e-05, "loss": 0.6043, "num_tokens": 337790357.0, "step": 56530 }, { "epoch": 0.6031493710859569, "grad_norm": 0.8136275204604139, "learning_rate": 2.17505978249238e-05, "loss": 0.498, "num_tokens": 337821919.0, "step": 56535 }, { "epoch": 0.6032027140921554, "grad_norm": 0.8285307043692652, "learning_rate": 2.174676061886549e-05, "loss": 0.4774, "num_tokens": 337835339.0, "step": 56540 }, { "epoch": 0.6032560570983538, "grad_norm": 0.6137620067530587, "learning_rate": 2.1742923591836185e-05, "loss": 0.4453, "num_tokens": 337870292.0, "step": 56545 }, { "epoch": 0.6033094001045523, "grad_norm": 1.0094240948591393, "learning_rate": 2.173908674395526e-05, "loss": 0.4203, "num_tokens": 337886224.0, "step": 56550 }, { "epoch": 0.6033627431107508, "grad_norm": 1.2055350535766771, "learning_rate": 2.1735250075342122e-05, "loss": 0.5403, "num_tokens": 337908707.0, "step": 56555 }, { "epoch": 0.6034160861169492, "grad_norm": 0.7577302568111027, "learning_rate": 2.1731413586116166e-05, "loss": 0.6502, "num_tokens": 337947016.0, "step": 56560 }, { "epoch": 0.6034694291231477, "grad_norm": 1.1181559897797284, "learning_rate": 2.1727577276396767e-05, "loss": 0.4818, "num_tokens": 337981153.0, "step": 56565 }, { "epoch": 0.6035227721293461, "grad_norm": 0.5613613286447916, "learning_rate": 2.172374114630331e-05, "loss": 0.5137, "num_tokens": 338019468.0, "step": 56570 }, { "epoch": 0.6035761151355445, "grad_norm": 0.7120300243965652, "learning_rate": 2.1719905195955166e-05, "loss": 0.5437, "num_tokens": 338040735.0, "step": 56575 }, { "epoch": 0.6036294581417431, "grad_norm": 1.0433515680748744, "learning_rate": 2.1716069425471685e-05, "loss": 0.3911, "num_tokens": 338059956.0, "step": 56580 }, { "epoch": 0.6036828011479415, "grad_norm": 0.9584933135544702, "learning_rate": 2.171223383497225e-05, "loss": 0.5591, "num_tokens": 338079555.0, "step": 56585 }, { "epoch": 0.6037361441541399, "grad_norm": 1.181461368971221, "learning_rate": 2.1708398424576222e-05, "loss": 0.5687, "num_tokens": 338101237.0, "step": 56590 }, { "epoch": 0.6037894871603384, "grad_norm": 1.0185625208833389, "learning_rate": 2.1704563194402926e-05, "loss": 0.4991, "num_tokens": 338137228.0, "step": 56595 }, { "epoch": 0.6038428301665368, "grad_norm": 0.8083019692149844, "learning_rate": 2.170072814457172e-05, "loss": 0.5307, "num_tokens": 338173302.0, "step": 56600 }, { "epoch": 0.6038961731727354, "grad_norm": 0.99620675937529, "learning_rate": 2.1696893275201946e-05, "loss": 0.4649, "num_tokens": 338202296.0, "step": 56605 }, { "epoch": 0.6039495161789338, "grad_norm": 0.6889104604542354, "learning_rate": 2.1693058586412933e-05, "loss": 0.4019, "num_tokens": 338224759.0, "step": 56610 }, { "epoch": 0.6040028591851322, "grad_norm": 1.9995935272224046, "learning_rate": 2.1689224078324006e-05, "loss": 0.52, "num_tokens": 338246921.0, "step": 56615 }, { "epoch": 0.6040562021913307, "grad_norm": 0.9625431325403638, "learning_rate": 2.1685389751054496e-05, "loss": 0.6107, "num_tokens": 338277378.0, "step": 56620 }, { "epoch": 0.6041095451975291, "grad_norm": 0.8992916444317033, "learning_rate": 2.1681555604723702e-05, "loss": 0.5729, "num_tokens": 338310751.0, "step": 56625 }, { "epoch": 0.6041628882037277, "grad_norm": 1.0613812925854613, "learning_rate": 2.1677721639450954e-05, "loss": 0.427, "num_tokens": 338331844.0, "step": 56630 }, { "epoch": 0.6042162312099261, "grad_norm": 0.794802194217838, "learning_rate": 2.167388785535555e-05, "loss": 0.4731, "num_tokens": 338355705.0, "step": 56635 }, { "epoch": 0.6042695742161245, "grad_norm": 1.3285706641384836, "learning_rate": 2.1670054252556787e-05, "loss": 0.5479, "num_tokens": 338382273.0, "step": 56640 }, { "epoch": 0.604322917222323, "grad_norm": 0.7709933384761596, "learning_rate": 2.166622083117396e-05, "loss": 0.5736, "num_tokens": 338428609.0, "step": 56645 }, { "epoch": 0.6043762602285214, "grad_norm": 0.5884243806613164, "learning_rate": 2.1662387591326368e-05, "loss": 0.4651, "num_tokens": 338456167.0, "step": 56650 }, { "epoch": 0.60442960323472, "grad_norm": 0.6925437390669718, "learning_rate": 2.1658554533133268e-05, "loss": 0.4999, "num_tokens": 338487228.0, "step": 56655 }, { "epoch": 0.6044829462409184, "grad_norm": 0.7918994471104847, "learning_rate": 2.165472165671396e-05, "loss": 0.5453, "num_tokens": 338525315.0, "step": 56660 }, { "epoch": 0.6045362892471168, "grad_norm": 0.8362429740099887, "learning_rate": 2.1650888962187703e-05, "loss": 0.5126, "num_tokens": 338550602.0, "step": 56665 }, { "epoch": 0.6045896322533153, "grad_norm": 0.955942951772306, "learning_rate": 2.1647056449673774e-05, "loss": 0.574, "num_tokens": 338580252.0, "step": 56670 }, { "epoch": 0.6046429752595137, "grad_norm": 0.7697861882362989, "learning_rate": 2.1643224119291416e-05, "loss": 0.6618, "num_tokens": 338621712.0, "step": 56675 }, { "epoch": 0.6046963182657121, "grad_norm": 0.8702642688632396, "learning_rate": 2.1639391971159907e-05, "loss": 0.4983, "num_tokens": 338657264.0, "step": 56680 }, { "epoch": 0.6047496612719107, "grad_norm": 0.7036612537235221, "learning_rate": 2.163556000539847e-05, "loss": 0.463, "num_tokens": 338692861.0, "step": 56685 }, { "epoch": 0.6048030042781091, "grad_norm": 1.011425367332286, "learning_rate": 2.163172822212636e-05, "loss": 0.4982, "num_tokens": 338718318.0, "step": 56690 }, { "epoch": 0.6048563472843076, "grad_norm": 0.8905108064628161, "learning_rate": 2.1627896621462824e-05, "loss": 0.5855, "num_tokens": 338754246.0, "step": 56695 }, { "epoch": 0.604909690290506, "grad_norm": 2.268132093981826, "learning_rate": 2.162406520352708e-05, "loss": 0.5467, "num_tokens": 338776935.0, "step": 56700 }, { "epoch": 0.6049630332967044, "grad_norm": 0.7427335455499277, "learning_rate": 2.1620233968438346e-05, "loss": 0.5571, "num_tokens": 338830262.0, "step": 56705 }, { "epoch": 0.605016376302903, "grad_norm": 1.228615734085131, "learning_rate": 2.1616402916315866e-05, "loss": 0.3895, "num_tokens": 338849278.0, "step": 56710 }, { "epoch": 0.6050697193091014, "grad_norm": 0.9034505040733343, "learning_rate": 2.1612572047278835e-05, "loss": 0.5909, "num_tokens": 338874298.0, "step": 56715 }, { "epoch": 0.6051230623152999, "grad_norm": 0.7852345292304065, "learning_rate": 2.1608741361446473e-05, "loss": 0.4462, "num_tokens": 338898924.0, "step": 56720 }, { "epoch": 0.6051764053214983, "grad_norm": 1.7255957117635734, "learning_rate": 2.1604910858937983e-05, "loss": 0.4835, "num_tokens": 338931199.0, "step": 56725 }, { "epoch": 0.6052297483276967, "grad_norm": 0.6240909700207259, "learning_rate": 2.1601080539872547e-05, "loss": 0.4616, "num_tokens": 338972732.0, "step": 56730 }, { "epoch": 0.6052830913338952, "grad_norm": 1.0627306836655879, "learning_rate": 2.1597250404369372e-05, "loss": 0.6342, "num_tokens": 339014212.0, "step": 56735 }, { "epoch": 0.6053364343400937, "grad_norm": 0.7748906971757983, "learning_rate": 2.1593420452547647e-05, "loss": 0.4173, "num_tokens": 339042774.0, "step": 56740 }, { "epoch": 0.6053897773462922, "grad_norm": 0.689860226636309, "learning_rate": 2.158959068452654e-05, "loss": 0.56, "num_tokens": 339078711.0, "step": 56745 }, { "epoch": 0.6054431203524906, "grad_norm": 0.8427737630591032, "learning_rate": 2.158576110042522e-05, "loss": 0.4374, "num_tokens": 339104446.0, "step": 56750 }, { "epoch": 0.605496463358689, "grad_norm": 1.0449968876112894, "learning_rate": 2.1581931700362883e-05, "loss": 0.4893, "num_tokens": 339131045.0, "step": 56755 }, { "epoch": 0.6055498063648875, "grad_norm": 1.0413307137504952, "learning_rate": 2.1578102484458666e-05, "loss": 0.4398, "num_tokens": 339178586.0, "step": 56760 }, { "epoch": 0.605603149371086, "grad_norm": 0.7837424735687571, "learning_rate": 2.157427345283174e-05, "loss": 0.4009, "num_tokens": 339205935.0, "step": 56765 }, { "epoch": 0.6056564923772844, "grad_norm": 0.9841296374758253, "learning_rate": 2.1570444605601252e-05, "loss": 0.391, "num_tokens": 339223690.0, "step": 56770 }, { "epoch": 0.6057098353834829, "grad_norm": 0.9232128147195533, "learning_rate": 2.1566615942886352e-05, "loss": 0.6467, "num_tokens": 339279888.0, "step": 56775 }, { "epoch": 0.6057631783896813, "grad_norm": 1.0970718412581575, "learning_rate": 2.1562787464806166e-05, "loss": 0.5565, "num_tokens": 339301466.0, "step": 56780 }, { "epoch": 0.6058165213958798, "grad_norm": 0.7170148267853065, "learning_rate": 2.1558959171479848e-05, "loss": 0.4959, "num_tokens": 339329209.0, "step": 56785 }, { "epoch": 0.6058698644020782, "grad_norm": 0.8303895645408514, "learning_rate": 2.1555131063026513e-05, "loss": 0.5527, "num_tokens": 339365863.0, "step": 56790 }, { "epoch": 0.6059232074082767, "grad_norm": 0.7294885194005956, "learning_rate": 2.1551303139565286e-05, "loss": 0.4737, "num_tokens": 339416004.0, "step": 56795 }, { "epoch": 0.6059765504144752, "grad_norm": 1.0831653651903435, "learning_rate": 2.1547475401215294e-05, "loss": 0.4358, "num_tokens": 339450350.0, "step": 56800 }, { "epoch": 0.6060298934206736, "grad_norm": 1.9143148569363975, "learning_rate": 2.1543647848095628e-05, "loss": 0.5379, "num_tokens": 339477599.0, "step": 56805 }, { "epoch": 0.6060832364268721, "grad_norm": 0.9122639535173256, "learning_rate": 2.1539820480325416e-05, "loss": 0.4958, "num_tokens": 339496499.0, "step": 56810 }, { "epoch": 0.6061365794330705, "grad_norm": 3.5398473587095265, "learning_rate": 2.1535993298023754e-05, "loss": 0.6948, "num_tokens": 339517488.0, "step": 56815 }, { "epoch": 0.606189922439269, "grad_norm": 1.226848607851954, "learning_rate": 2.1532166301309715e-05, "loss": 0.4854, "num_tokens": 339543975.0, "step": 56820 }, { "epoch": 0.6062432654454675, "grad_norm": 1.3222629741988494, "learning_rate": 2.152833949030241e-05, "loss": 0.5186, "num_tokens": 339563816.0, "step": 56825 }, { "epoch": 0.6062966084516659, "grad_norm": 0.8227476206003258, "learning_rate": 2.1524512865120922e-05, "loss": 0.5022, "num_tokens": 339596715.0, "step": 56830 }, { "epoch": 0.6063499514578644, "grad_norm": 1.0291724385694867, "learning_rate": 2.1520686425884307e-05, "loss": 0.3615, "num_tokens": 339615544.0, "step": 56835 }, { "epoch": 0.6064032944640628, "grad_norm": 1.1068520521065028, "learning_rate": 2.1516860172711645e-05, "loss": 0.536, "num_tokens": 339642318.0, "step": 56840 }, { "epoch": 0.6064566374702612, "grad_norm": 1.41008674605059, "learning_rate": 2.151303410572202e-05, "loss": 0.4279, "num_tokens": 339663066.0, "step": 56845 }, { "epoch": 0.6065099804764598, "grad_norm": 1.2051486554909663, "learning_rate": 2.150920822503447e-05, "loss": 0.4928, "num_tokens": 339690395.0, "step": 56850 }, { "epoch": 0.6065633234826582, "grad_norm": 0.6990882776345531, "learning_rate": 2.1505382530768046e-05, "loss": 0.5751, "num_tokens": 339721414.0, "step": 56855 }, { "epoch": 0.6066166664888566, "grad_norm": 1.0752448692575034, "learning_rate": 2.1501557023041817e-05, "loss": 0.3877, "num_tokens": 339737563.0, "step": 56860 }, { "epoch": 0.6066700094950551, "grad_norm": 1.6501653179032336, "learning_rate": 2.1497731701974812e-05, "loss": 0.4333, "num_tokens": 339751745.0, "step": 56865 }, { "epoch": 0.6067233525012535, "grad_norm": 1.0761225574202464, "learning_rate": 2.149390656768605e-05, "loss": 0.5758, "num_tokens": 339774741.0, "step": 56870 }, { "epoch": 0.6067766955074521, "grad_norm": 1.2932189845852127, "learning_rate": 2.1490081620294598e-05, "loss": 0.5764, "num_tokens": 339794339.0, "step": 56875 }, { "epoch": 0.6068300385136505, "grad_norm": 1.2512230046589017, "learning_rate": 2.148625685991945e-05, "loss": 0.4372, "num_tokens": 339817793.0, "step": 56880 }, { "epoch": 0.6068833815198489, "grad_norm": 0.8133585925352051, "learning_rate": 2.1482432286679643e-05, "loss": 0.5645, "num_tokens": 339864236.0, "step": 56885 }, { "epoch": 0.6069367245260474, "grad_norm": 0.7111015630368022, "learning_rate": 2.1478607900694186e-05, "loss": 0.5415, "num_tokens": 339906909.0, "step": 56890 }, { "epoch": 0.6069900675322458, "grad_norm": 1.691772966754628, "learning_rate": 2.1474783702082073e-05, "loss": 0.5683, "num_tokens": 339927426.0, "step": 56895 }, { "epoch": 0.6070434105384444, "grad_norm": 1.0868929714651698, "learning_rate": 2.147095969096232e-05, "loss": 0.5099, "num_tokens": 339965549.0, "step": 56900 }, { "epoch": 0.6070967535446428, "grad_norm": 1.1404584416191434, "learning_rate": 2.1467135867453918e-05, "loss": 0.4535, "num_tokens": 340000379.0, "step": 56905 }, { "epoch": 0.6071500965508412, "grad_norm": 0.9893769863986448, "learning_rate": 2.146331223167585e-05, "loss": 0.4079, "num_tokens": 340028440.0, "step": 56910 }, { "epoch": 0.6072034395570397, "grad_norm": 1.0390280041419007, "learning_rate": 2.1459488783747105e-05, "loss": 0.5123, "num_tokens": 340055826.0, "step": 56915 }, { "epoch": 0.6072567825632381, "grad_norm": 0.7164309759431375, "learning_rate": 2.145566552378667e-05, "loss": 0.4317, "num_tokens": 340102191.0, "step": 56920 }, { "epoch": 0.6073101255694366, "grad_norm": 0.9993609896109314, "learning_rate": 2.1451842451913506e-05, "loss": 0.5029, "num_tokens": 340133606.0, "step": 56925 }, { "epoch": 0.6073634685756351, "grad_norm": 0.8121620397006493, "learning_rate": 2.144801956824658e-05, "loss": 0.5058, "num_tokens": 340162128.0, "step": 56930 }, { "epoch": 0.6074168115818335, "grad_norm": 0.7869949080924384, "learning_rate": 2.144419687290486e-05, "loss": 0.5262, "num_tokens": 340193447.0, "step": 56935 }, { "epoch": 0.607470154588032, "grad_norm": 0.700087918908586, "learning_rate": 2.1440374366007288e-05, "loss": 0.4239, "num_tokens": 340226163.0, "step": 56940 }, { "epoch": 0.6075234975942304, "grad_norm": 0.8313967837246682, "learning_rate": 2.1436552047672813e-05, "loss": 0.5561, "num_tokens": 340259174.0, "step": 56945 }, { "epoch": 0.6075768406004288, "grad_norm": 0.95571075051229, "learning_rate": 2.14327299180204e-05, "loss": 0.486, "num_tokens": 340291434.0, "step": 56950 }, { "epoch": 0.6076301836066273, "grad_norm": 0.6501284787491639, "learning_rate": 2.1428907977168955e-05, "loss": 0.5172, "num_tokens": 340325020.0, "step": 56955 }, { "epoch": 0.6076835266128258, "grad_norm": 0.8965877523046827, "learning_rate": 2.142508622523743e-05, "loss": 0.5949, "num_tokens": 340358925.0, "step": 56960 }, { "epoch": 0.6077368696190243, "grad_norm": 0.9190609116775389, "learning_rate": 2.142126466234474e-05, "loss": 0.6497, "num_tokens": 340399445.0, "step": 56965 }, { "epoch": 0.6077902126252227, "grad_norm": 0.6940319553546497, "learning_rate": 2.1417443288609807e-05, "loss": 0.5501, "num_tokens": 340426567.0, "step": 56970 }, { "epoch": 0.6078435556314211, "grad_norm": 0.7235803727030126, "learning_rate": 2.141362210415155e-05, "loss": 0.4794, "num_tokens": 340472844.0, "step": 56975 }, { "epoch": 0.6078968986376196, "grad_norm": 0.8412099353020732, "learning_rate": 2.1409801109088867e-05, "loss": 0.5765, "num_tokens": 340492105.0, "step": 56980 }, { "epoch": 0.6079502416438181, "grad_norm": 1.338945438445377, "learning_rate": 2.1405980303540664e-05, "loss": 0.4634, "num_tokens": 340529349.0, "step": 56985 }, { "epoch": 0.6080035846500166, "grad_norm": 0.887004104968397, "learning_rate": 2.140215968762584e-05, "loss": 0.5907, "num_tokens": 340564192.0, "step": 56990 }, { "epoch": 0.608056927656215, "grad_norm": 0.8862867803311112, "learning_rate": 2.139833926146328e-05, "loss": 0.4518, "num_tokens": 340608716.0, "step": 56995 }, { "epoch": 0.6081102706624134, "grad_norm": 0.794386743101271, "learning_rate": 2.1394519025171866e-05, "loss": 0.441, "num_tokens": 340639333.0, "step": 57000 }, { "epoch": 0.6081636136686119, "grad_norm": 1.2449266928525797, "learning_rate": 2.1390698978870477e-05, "loss": 0.6013, "num_tokens": 340680041.0, "step": 57005 }, { "epoch": 0.6082169566748103, "grad_norm": 0.9967062527694989, "learning_rate": 2.1386879122677994e-05, "loss": 0.4074, "num_tokens": 340692375.0, "step": 57010 }, { "epoch": 0.6082702996810089, "grad_norm": 1.1044542188715403, "learning_rate": 2.1383059456713274e-05, "loss": 0.4328, "num_tokens": 340705323.0, "step": 57015 }, { "epoch": 0.6083236426872073, "grad_norm": 1.4468934888241705, "learning_rate": 2.1379239981095173e-05, "loss": 0.6964, "num_tokens": 340738617.0, "step": 57020 }, { "epoch": 0.6083769856934057, "grad_norm": 0.9072759914121632, "learning_rate": 2.137542069594256e-05, "loss": 0.5424, "num_tokens": 340760367.0, "step": 57025 }, { "epoch": 0.6084303286996042, "grad_norm": 1.0458075262629305, "learning_rate": 2.1371601601374273e-05, "loss": 0.5434, "num_tokens": 340780766.0, "step": 57030 }, { "epoch": 0.6084836717058026, "grad_norm": 0.8250825679107353, "learning_rate": 2.1367782697509155e-05, "loss": 0.4531, "num_tokens": 340808175.0, "step": 57035 }, { "epoch": 0.6085370147120011, "grad_norm": 1.4226637822674637, "learning_rate": 2.136396398446604e-05, "loss": 0.4928, "num_tokens": 340838582.0, "step": 57040 }, { "epoch": 0.6085903577181996, "grad_norm": 1.303194243304863, "learning_rate": 2.136014546236376e-05, "loss": 0.4623, "num_tokens": 340854526.0, "step": 57045 }, { "epoch": 0.608643700724398, "grad_norm": 0.9327906922357022, "learning_rate": 2.1356327131321154e-05, "loss": 0.4736, "num_tokens": 340872663.0, "step": 57050 }, { "epoch": 0.6086970437305965, "grad_norm": 0.8239485573961416, "learning_rate": 2.135250899145702e-05, "loss": 0.5056, "num_tokens": 340895236.0, "step": 57055 }, { "epoch": 0.6087503867367949, "grad_norm": 0.8893802167861087, "learning_rate": 2.1348691042890177e-05, "loss": 0.4729, "num_tokens": 340920697.0, "step": 57060 }, { "epoch": 0.6088037297429933, "grad_norm": 3.9108461904901892, "learning_rate": 2.1344873285739435e-05, "loss": 0.5337, "num_tokens": 340949554.0, "step": 57065 }, { "epoch": 0.6088570727491919, "grad_norm": 0.6853631593958079, "learning_rate": 2.1341055720123598e-05, "loss": 0.6034, "num_tokens": 340998917.0, "step": 57070 }, { "epoch": 0.6089104157553903, "grad_norm": 1.2280814156433613, "learning_rate": 2.1337238346161447e-05, "loss": 0.6388, "num_tokens": 341033077.0, "step": 57075 }, { "epoch": 0.6089637587615888, "grad_norm": 1.5037689725291976, "learning_rate": 2.1333421163971784e-05, "loss": 0.5289, "num_tokens": 341049818.0, "step": 57080 }, { "epoch": 0.6090171017677872, "grad_norm": 0.7260965846251297, "learning_rate": 2.1329604173673397e-05, "loss": 0.5102, "num_tokens": 341090765.0, "step": 57085 }, { "epoch": 0.6090704447739856, "grad_norm": 0.8225053978978822, "learning_rate": 2.1325787375385042e-05, "loss": 0.5586, "num_tokens": 341123999.0, "step": 57090 }, { "epoch": 0.6091237877801842, "grad_norm": 0.6224009400544022, "learning_rate": 2.13219707692255e-05, "loss": 0.5455, "num_tokens": 341173929.0, "step": 57095 }, { "epoch": 0.6091771307863826, "grad_norm": 1.2556224073462128, "learning_rate": 2.1318154355313546e-05, "loss": 0.448, "num_tokens": 341201457.0, "step": 57100 }, { "epoch": 0.6092304737925811, "grad_norm": 0.9554507419321948, "learning_rate": 2.1314338133767937e-05, "loss": 0.5674, "num_tokens": 341233616.0, "step": 57105 }, { "epoch": 0.6092838167987795, "grad_norm": 0.7596667826665591, "learning_rate": 2.1310522104707396e-05, "loss": 0.5476, "num_tokens": 341259498.0, "step": 57110 }, { "epoch": 0.6093371598049779, "grad_norm": 1.2600802944024514, "learning_rate": 2.1306706268250713e-05, "loss": 0.444, "num_tokens": 341272531.0, "step": 57115 }, { "epoch": 0.6093905028111765, "grad_norm": 0.900004495964643, "learning_rate": 2.1302890624516608e-05, "loss": 0.5636, "num_tokens": 341292117.0, "step": 57120 }, { "epoch": 0.6094438458173749, "grad_norm": 0.9270128097144203, "learning_rate": 2.1299075173623813e-05, "loss": 0.5057, "num_tokens": 341314936.0, "step": 57125 }, { "epoch": 0.6094971888235733, "grad_norm": 1.205659299435948, "learning_rate": 2.1295259915691057e-05, "loss": 0.607, "num_tokens": 341348223.0, "step": 57130 }, { "epoch": 0.6095505318297718, "grad_norm": 1.6327112399172026, "learning_rate": 2.129144485083708e-05, "loss": 0.4638, "num_tokens": 341371538.0, "step": 57135 }, { "epoch": 0.6096038748359702, "grad_norm": 1.1941427300983176, "learning_rate": 2.128762997918058e-05, "loss": 0.5925, "num_tokens": 341396046.0, "step": 57140 }, { "epoch": 0.6096572178421688, "grad_norm": 2.3225883654207684, "learning_rate": 2.128381530084027e-05, "loss": 0.5418, "num_tokens": 341415559.0, "step": 57145 }, { "epoch": 0.6097105608483672, "grad_norm": 0.6175626215554627, "learning_rate": 2.128000081593487e-05, "loss": 0.595, "num_tokens": 341450953.0, "step": 57150 }, { "epoch": 0.6097639038545656, "grad_norm": 0.7126494120342886, "learning_rate": 2.127618652458306e-05, "loss": 0.4163, "num_tokens": 341485392.0, "step": 57155 }, { "epoch": 0.6098172468607641, "grad_norm": 0.678421919312397, "learning_rate": 2.127237242690354e-05, "loss": 0.5258, "num_tokens": 341511478.0, "step": 57160 }, { "epoch": 0.6098705898669625, "grad_norm": 1.509497748238017, "learning_rate": 2.1268558523015005e-05, "loss": 0.4752, "num_tokens": 341533239.0, "step": 57165 }, { "epoch": 0.609923932873161, "grad_norm": 0.6827890040344253, "learning_rate": 2.1264744813036125e-05, "loss": 0.4051, "num_tokens": 341565005.0, "step": 57170 }, { "epoch": 0.6099772758793595, "grad_norm": 0.7119872460381563, "learning_rate": 2.1260931297085574e-05, "loss": 0.5753, "num_tokens": 341591623.0, "step": 57175 }, { "epoch": 0.6100306188855579, "grad_norm": 3.5525463722125594, "learning_rate": 2.1257117975282036e-05, "loss": 0.5011, "num_tokens": 341627038.0, "step": 57180 }, { "epoch": 0.6100839618917564, "grad_norm": 1.1651088805784147, "learning_rate": 2.1253304847744153e-05, "loss": 0.5246, "num_tokens": 341654440.0, "step": 57185 }, { "epoch": 0.6101373048979548, "grad_norm": 1.1723091757671726, "learning_rate": 2.1249491914590597e-05, "loss": 0.4615, "num_tokens": 341683991.0, "step": 57190 }, { "epoch": 0.6101906479041533, "grad_norm": 2.5303051639879532, "learning_rate": 2.124567917594002e-05, "loss": 0.6045, "num_tokens": 341714896.0, "step": 57195 }, { "epoch": 0.6102439909103518, "grad_norm": 0.7339790192080174, "learning_rate": 2.124186663191105e-05, "loss": 0.5846, "num_tokens": 341764459.0, "step": 57200 }, { "epoch": 0.6102973339165502, "grad_norm": 0.8528001521811818, "learning_rate": 2.1238054282622338e-05, "loss": 0.5522, "num_tokens": 341783098.0, "step": 57205 }, { "epoch": 0.6103506769227487, "grad_norm": 0.6362571924161566, "learning_rate": 2.1234242128192523e-05, "loss": 0.4041, "num_tokens": 341805462.0, "step": 57210 }, { "epoch": 0.6104040199289471, "grad_norm": 0.6978230811191742, "learning_rate": 2.1230430168740213e-05, "loss": 0.5473, "num_tokens": 341845515.0, "step": 57215 }, { "epoch": 0.6104573629351455, "grad_norm": 0.9617034887929453, "learning_rate": 2.1226618404384036e-05, "loss": 0.4496, "num_tokens": 341866090.0, "step": 57220 }, { "epoch": 0.610510705941344, "grad_norm": 0.8561475187941219, "learning_rate": 2.122280683524262e-05, "loss": 0.4837, "num_tokens": 341892946.0, "step": 57225 }, { "epoch": 0.6105640489475425, "grad_norm": 0.8761981411725149, "learning_rate": 2.121899546143456e-05, "loss": 0.4491, "num_tokens": 341926892.0, "step": 57230 }, { "epoch": 0.610617391953741, "grad_norm": 1.1707141802440284, "learning_rate": 2.1215184283078448e-05, "loss": 0.4886, "num_tokens": 341956897.0, "step": 57235 }, { "epoch": 0.6106707349599394, "grad_norm": 1.0415136275417785, "learning_rate": 2.1211373300292903e-05, "loss": 0.464, "num_tokens": 341977811.0, "step": 57240 }, { "epoch": 0.6107240779661378, "grad_norm": 1.1896115272170549, "learning_rate": 2.1207562513196493e-05, "loss": 0.3894, "num_tokens": 341991137.0, "step": 57245 }, { "epoch": 0.6107774209723363, "grad_norm": 0.7505912564921863, "learning_rate": 2.120375192190782e-05, "loss": 0.6093, "num_tokens": 342021988.0, "step": 57250 }, { "epoch": 0.6108307639785348, "grad_norm": 1.3734928983655867, "learning_rate": 2.1199941526545457e-05, "loss": 0.4927, "num_tokens": 342047782.0, "step": 57255 }, { "epoch": 0.6108841069847333, "grad_norm": 1.5087371621779653, "learning_rate": 2.119613132722797e-05, "loss": 0.3853, "num_tokens": 342075123.0, "step": 57260 }, { "epoch": 0.6109374499909317, "grad_norm": 1.7304525123386005, "learning_rate": 2.1192321324073922e-05, "loss": 0.5168, "num_tokens": 342091861.0, "step": 57265 }, { "epoch": 0.6109907929971301, "grad_norm": 0.6803195266630332, "learning_rate": 2.1188511517201888e-05, "loss": 0.4988, "num_tokens": 342127994.0, "step": 57270 }, { "epoch": 0.6110441360033286, "grad_norm": 1.5710114163137996, "learning_rate": 2.1184701906730403e-05, "loss": 0.4956, "num_tokens": 342169505.0, "step": 57275 }, { "epoch": 0.611097479009527, "grad_norm": 0.8113855016864866, "learning_rate": 2.1180892492778026e-05, "loss": 0.4443, "num_tokens": 342188299.0, "step": 57280 }, { "epoch": 0.6111508220157256, "grad_norm": 1.546474510912708, "learning_rate": 2.11770832754633e-05, "loss": 0.4977, "num_tokens": 342223018.0, "step": 57285 }, { "epoch": 0.611204165021924, "grad_norm": 0.9830193698048878, "learning_rate": 2.1173274254904745e-05, "loss": 0.4415, "num_tokens": 342251848.0, "step": 57290 }, { "epoch": 0.6112575080281224, "grad_norm": 1.0451194566084558, "learning_rate": 2.1169465431220904e-05, "loss": 0.5129, "num_tokens": 342270279.0, "step": 57295 }, { "epoch": 0.6113108510343209, "grad_norm": 0.8333124630652269, "learning_rate": 2.1165656804530297e-05, "loss": 0.5695, "num_tokens": 342299665.0, "step": 57300 }, { "epoch": 0.6113641940405193, "grad_norm": 1.5108907650918026, "learning_rate": 2.116184837495144e-05, "loss": 0.5598, "num_tokens": 342330493.0, "step": 57305 }, { "epoch": 0.6114175370467178, "grad_norm": 0.7873749295630346, "learning_rate": 2.115804014260283e-05, "loss": 0.4272, "num_tokens": 342363858.0, "step": 57310 }, { "epoch": 0.6114708800529163, "grad_norm": 1.4103324973482374, "learning_rate": 2.1154232107603e-05, "loss": 0.5495, "num_tokens": 342391384.0, "step": 57315 }, { "epoch": 0.6115242230591147, "grad_norm": 0.850383819458804, "learning_rate": 2.115042427007043e-05, "loss": 0.5296, "num_tokens": 342411437.0, "step": 57320 }, { "epoch": 0.6115775660653132, "grad_norm": 0.6916532173275366, "learning_rate": 2.114661663012361e-05, "loss": 0.4877, "num_tokens": 342442810.0, "step": 57325 }, { "epoch": 0.6116309090715116, "grad_norm": 0.6679336556650404, "learning_rate": 2.1142809187881037e-05, "loss": 0.5525, "num_tokens": 342481399.0, "step": 57330 }, { "epoch": 0.61168425207771, "grad_norm": 0.9582034856268857, "learning_rate": 2.113900194346117e-05, "loss": 0.5591, "num_tokens": 342510245.0, "step": 57335 }, { "epoch": 0.6117375950839086, "grad_norm": 0.8156477707851265, "learning_rate": 2.1135194896982508e-05, "loss": 0.5618, "num_tokens": 342542876.0, "step": 57340 }, { "epoch": 0.611790938090107, "grad_norm": 0.6840601205606188, "learning_rate": 2.1131388048563505e-05, "loss": 0.4385, "num_tokens": 342580992.0, "step": 57345 }, { "epoch": 0.6118442810963055, "grad_norm": 0.7821107905150988, "learning_rate": 2.1127581398322623e-05, "loss": 0.45, "num_tokens": 342608645.0, "step": 57350 }, { "epoch": 0.6118976241025039, "grad_norm": 1.332125439429158, "learning_rate": 2.1123774946378323e-05, "loss": 0.413, "num_tokens": 342636616.0, "step": 57355 }, { "epoch": 0.6119509671087023, "grad_norm": 1.0136593227292958, "learning_rate": 2.1119968692849044e-05, "loss": 0.5181, "num_tokens": 342665229.0, "step": 57360 }, { "epoch": 0.6120043101149009, "grad_norm": 0.8902156479920331, "learning_rate": 2.1116162637853233e-05, "loss": 0.4467, "num_tokens": 342687293.0, "step": 57365 }, { "epoch": 0.6120576531210993, "grad_norm": 1.1503303707608687, "learning_rate": 2.1112356781509322e-05, "loss": 0.4548, "num_tokens": 342714587.0, "step": 57370 }, { "epoch": 0.6121109961272978, "grad_norm": 0.6739723650719491, "learning_rate": 2.1108551123935766e-05, "loss": 0.6414, "num_tokens": 342746400.0, "step": 57375 }, { "epoch": 0.6121643391334962, "grad_norm": 1.0458763907051254, "learning_rate": 2.1104745665250964e-05, "loss": 0.3855, "num_tokens": 342775045.0, "step": 57380 }, { "epoch": 0.6122176821396946, "grad_norm": 0.5601896729806537, "learning_rate": 2.1100940405573327e-05, "loss": 0.503, "num_tokens": 342813975.0, "step": 57385 }, { "epoch": 0.6122710251458932, "grad_norm": 1.1558127257495632, "learning_rate": 2.1097135345021298e-05, "loss": 0.4425, "num_tokens": 342847655.0, "step": 57390 }, { "epoch": 0.6123243681520916, "grad_norm": 2.3246013742357894, "learning_rate": 2.1093330483713257e-05, "loss": 0.4562, "num_tokens": 342885185.0, "step": 57395 }, { "epoch": 0.61237771115829, "grad_norm": 0.9658724033176682, "learning_rate": 2.1089525821767608e-05, "loss": 0.5347, "num_tokens": 342915469.0, "step": 57400 }, { "epoch": 0.6124310541644885, "grad_norm": 0.8935209739917163, "learning_rate": 2.108572135930276e-05, "loss": 0.5218, "num_tokens": 342941504.0, "step": 57405 }, { "epoch": 0.6124843971706869, "grad_norm": 0.9617256184495379, "learning_rate": 2.1081917096437075e-05, "loss": 0.5599, "num_tokens": 342973827.0, "step": 57410 }, { "epoch": 0.6125377401768854, "grad_norm": 0.5621862179876452, "learning_rate": 2.1078113033288953e-05, "loss": 0.4864, "num_tokens": 343019348.0, "step": 57415 }, { "epoch": 0.6125910831830839, "grad_norm": 0.8862182610484798, "learning_rate": 2.107430916997677e-05, "loss": 0.4457, "num_tokens": 343054186.0, "step": 57420 }, { "epoch": 0.6126444261892823, "grad_norm": 1.4178019252387632, "learning_rate": 2.107050550661887e-05, "loss": 0.4614, "num_tokens": 343090268.0, "step": 57425 }, { "epoch": 0.6126977691954808, "grad_norm": 0.9417824136682048, "learning_rate": 2.1066702043333648e-05, "loss": 0.5321, "num_tokens": 343135176.0, "step": 57430 }, { "epoch": 0.6127511122016792, "grad_norm": 0.845694399187059, "learning_rate": 2.1062898780239438e-05, "loss": 0.5236, "num_tokens": 343170304.0, "step": 57435 }, { "epoch": 0.6128044552078777, "grad_norm": 1.513246500815581, "learning_rate": 2.1059095717454595e-05, "loss": 0.5573, "num_tokens": 343188382.0, "step": 57440 }, { "epoch": 0.6128577982140762, "grad_norm": 1.2455418978196198, "learning_rate": 2.1055292855097463e-05, "loss": 0.4938, "num_tokens": 343223053.0, "step": 57445 }, { "epoch": 0.6129111412202746, "grad_norm": 0.8384816165141864, "learning_rate": 2.1051490193286382e-05, "loss": 0.516, "num_tokens": 343250956.0, "step": 57450 }, { "epoch": 0.6129644842264731, "grad_norm": 0.8402482259156269, "learning_rate": 2.1047687732139677e-05, "loss": 0.4642, "num_tokens": 343288812.0, "step": 57455 }, { "epoch": 0.6130178272326715, "grad_norm": 0.5899649403943557, "learning_rate": 2.104388547177567e-05, "loss": 0.4535, "num_tokens": 343319292.0, "step": 57460 }, { "epoch": 0.61307117023887, "grad_norm": 0.827083048565252, "learning_rate": 2.10400834123127e-05, "loss": 0.4931, "num_tokens": 343341113.0, "step": 57465 }, { "epoch": 0.6131245132450684, "grad_norm": 1.3895216845466776, "learning_rate": 2.103628155386906e-05, "loss": 0.6053, "num_tokens": 343380606.0, "step": 57470 }, { "epoch": 0.6131778562512669, "grad_norm": 0.9612757576841748, "learning_rate": 2.103247989656305e-05, "loss": 0.4847, "num_tokens": 343412324.0, "step": 57475 }, { "epoch": 0.6132311992574654, "grad_norm": 0.9899526916369765, "learning_rate": 2.1028678440513e-05, "loss": 0.4892, "num_tokens": 343452851.0, "step": 57480 }, { "epoch": 0.6132845422636638, "grad_norm": 0.7163664022965333, "learning_rate": 2.102487718583717e-05, "loss": 0.425, "num_tokens": 343476250.0, "step": 57485 }, { "epoch": 0.6133378852698622, "grad_norm": 0.6681757599018835, "learning_rate": 2.1021076132653866e-05, "loss": 0.5726, "num_tokens": 343509451.0, "step": 57490 }, { "epoch": 0.6133912282760607, "grad_norm": 0.5918727977930714, "learning_rate": 2.1017275281081373e-05, "loss": 0.5302, "num_tokens": 343544877.0, "step": 57495 }, { "epoch": 0.6134445712822592, "grad_norm": 0.7434026563208213, "learning_rate": 2.1013474631237945e-05, "loss": 0.5557, "num_tokens": 343590153.0, "step": 57500 }, { "epoch": 0.6134979142884577, "grad_norm": 0.8576604687039275, "learning_rate": 2.100967418324187e-05, "loss": 0.4347, "num_tokens": 343614825.0, "step": 57505 }, { "epoch": 0.6135512572946561, "grad_norm": 0.7741246715210566, "learning_rate": 2.1005873937211406e-05, "loss": 0.5862, "num_tokens": 343646193.0, "step": 57510 }, { "epoch": 0.6136046003008545, "grad_norm": 0.7821686483453192, "learning_rate": 2.1002073893264794e-05, "loss": 0.4289, "num_tokens": 343677211.0, "step": 57515 }, { "epoch": 0.613657943307053, "grad_norm": 1.0370882681149314, "learning_rate": 2.0998274051520305e-05, "loss": 0.5705, "num_tokens": 343706920.0, "step": 57520 }, { "epoch": 0.6137112863132514, "grad_norm": 0.7058636618655265, "learning_rate": 2.099447441209617e-05, "loss": 0.4567, "num_tokens": 343735814.0, "step": 57525 }, { "epoch": 0.61376462931945, "grad_norm": 0.923041775160892, "learning_rate": 2.0990674975110625e-05, "loss": 0.6119, "num_tokens": 343764950.0, "step": 57530 }, { "epoch": 0.6138179723256484, "grad_norm": 0.949116836578035, "learning_rate": 2.0986875740681905e-05, "loss": 0.4174, "num_tokens": 343791937.0, "step": 57535 }, { "epoch": 0.6138713153318468, "grad_norm": 1.4068839467372574, "learning_rate": 2.098307670892824e-05, "loss": 0.4643, "num_tokens": 343820614.0, "step": 57540 }, { "epoch": 0.6139246583380453, "grad_norm": 0.6196864604364103, "learning_rate": 2.097927787996784e-05, "loss": 0.4227, "num_tokens": 343853891.0, "step": 57545 }, { "epoch": 0.6139780013442437, "grad_norm": 0.7068168822287987, "learning_rate": 2.0975479253918907e-05, "loss": 0.5581, "num_tokens": 343887185.0, "step": 57550 }, { "epoch": 0.6140313443504423, "grad_norm": 0.7425506957192585, "learning_rate": 2.097168083089967e-05, "loss": 0.4954, "num_tokens": 343915765.0, "step": 57555 }, { "epoch": 0.6140846873566407, "grad_norm": 0.6672282077727274, "learning_rate": 2.0967882611028318e-05, "loss": 0.3804, "num_tokens": 343951189.0, "step": 57560 }, { "epoch": 0.6141380303628391, "grad_norm": 1.0583912384207006, "learning_rate": 2.0964084594423027e-05, "loss": 0.7402, "num_tokens": 343995258.0, "step": 57565 }, { "epoch": 0.6141913733690376, "grad_norm": 0.6962261124795486, "learning_rate": 2.0960286781202023e-05, "loss": 0.4948, "num_tokens": 344026452.0, "step": 57570 }, { "epoch": 0.614244716375236, "grad_norm": 0.7610365757964688, "learning_rate": 2.0956489171483435e-05, "loss": 0.4973, "num_tokens": 344048704.0, "step": 57575 }, { "epoch": 0.6142980593814344, "grad_norm": 0.6212567841072545, "learning_rate": 2.0952691765385475e-05, "loss": 0.5697, "num_tokens": 344094326.0, "step": 57580 }, { "epoch": 0.614351402387633, "grad_norm": 1.22666392263503, "learning_rate": 2.0948894563026306e-05, "loss": 0.6155, "num_tokens": 344116880.0, "step": 57585 }, { "epoch": 0.6144047453938314, "grad_norm": 1.413126289518577, "learning_rate": 2.094509756452407e-05, "loss": 0.5725, "num_tokens": 344164002.0, "step": 57590 }, { "epoch": 0.6144580884000299, "grad_norm": 4.057804481770022, "learning_rate": 2.0941300769996936e-05, "loss": 0.6784, "num_tokens": 344187461.0, "step": 57595 }, { "epoch": 0.6145114314062283, "grad_norm": 0.7080655068888214, "learning_rate": 2.0937504179563055e-05, "loss": 0.5743, "num_tokens": 344239058.0, "step": 57600 }, { "epoch": 0.6145647744124267, "grad_norm": 1.0073646517707455, "learning_rate": 2.0933707793340557e-05, "loss": 0.4324, "num_tokens": 344258585.0, "step": 57605 }, { "epoch": 0.6146181174186253, "grad_norm": 0.6478590577674739, "learning_rate": 2.092991161144759e-05, "loss": 0.4916, "num_tokens": 344298191.0, "step": 57610 }, { "epoch": 0.6146714604248237, "grad_norm": 1.0545559213354778, "learning_rate": 2.0926115634002284e-05, "loss": 0.4797, "num_tokens": 344333271.0, "step": 57615 }, { "epoch": 0.6147248034310222, "grad_norm": 1.0479496196935634, "learning_rate": 2.092231986112274e-05, "loss": 0.6286, "num_tokens": 344360454.0, "step": 57620 }, { "epoch": 0.6147781464372206, "grad_norm": 1.3526594241267877, "learning_rate": 2.09185242929271e-05, "loss": 0.4105, "num_tokens": 344379698.0, "step": 57625 }, { "epoch": 0.614831489443419, "grad_norm": 1.224023340605194, "learning_rate": 2.0914728929533466e-05, "loss": 0.5394, "num_tokens": 344429453.0, "step": 57630 }, { "epoch": 0.6148848324496176, "grad_norm": 1.0553706918878747, "learning_rate": 2.0910933771059943e-05, "loss": 0.5333, "num_tokens": 344448273.0, "step": 57635 }, { "epoch": 0.614938175455816, "grad_norm": 0.870818581724486, "learning_rate": 2.0907138817624623e-05, "loss": 0.5006, "num_tokens": 344475631.0, "step": 57640 }, { "epoch": 0.6149915184620145, "grad_norm": 2.298195431810659, "learning_rate": 2.0903344069345605e-05, "loss": 0.6058, "num_tokens": 344484782.0, "step": 57645 }, { "epoch": 0.6150448614682129, "grad_norm": 1.4680145602606955, "learning_rate": 2.0899549526340967e-05, "loss": 0.5728, "num_tokens": 344529630.0, "step": 57650 }, { "epoch": 0.6150982044744113, "grad_norm": 1.0432969041073465, "learning_rate": 2.0895755188728788e-05, "loss": 0.5561, "num_tokens": 344554623.0, "step": 57655 }, { "epoch": 0.6151515474806099, "grad_norm": 0.7957038401635759, "learning_rate": 2.089196105662715e-05, "loss": 0.4367, "num_tokens": 344570227.0, "step": 57660 }, { "epoch": 0.6152048904868083, "grad_norm": 0.610263310239601, "learning_rate": 2.08881671301541e-05, "loss": 0.4519, "num_tokens": 344595559.0, "step": 57665 }, { "epoch": 0.6152582334930067, "grad_norm": 0.7774353452056953, "learning_rate": 2.0884373409427716e-05, "loss": 0.5201, "num_tokens": 344635709.0, "step": 57670 }, { "epoch": 0.6153115764992052, "grad_norm": 0.7566523909844014, "learning_rate": 2.0880579894566038e-05, "loss": 0.5005, "num_tokens": 344667015.0, "step": 57675 }, { "epoch": 0.6153649195054036, "grad_norm": 1.111842621044026, "learning_rate": 2.087678658568712e-05, "loss": 0.5431, "num_tokens": 344689502.0, "step": 57680 }, { "epoch": 0.6154182625116021, "grad_norm": 3.5880875790142235, "learning_rate": 2.0872993482908993e-05, "loss": 0.4646, "num_tokens": 344719851.0, "step": 57685 }, { "epoch": 0.6154716055178006, "grad_norm": 0.9421654692398118, "learning_rate": 2.0869200586349708e-05, "loss": 0.5228, "num_tokens": 344751477.0, "step": 57690 }, { "epoch": 0.615524948523999, "grad_norm": 0.7633124536893164, "learning_rate": 2.0865407896127266e-05, "loss": 0.4467, "num_tokens": 344768597.0, "step": 57695 }, { "epoch": 0.6155782915301975, "grad_norm": 0.7375328077577638, "learning_rate": 2.086161541235971e-05, "loss": 0.4954, "num_tokens": 344792488.0, "step": 57700 }, { "epoch": 0.6156316345363959, "grad_norm": 1.8287792474408298, "learning_rate": 2.0857823135165044e-05, "loss": 0.5035, "num_tokens": 344822263.0, "step": 57705 }, { "epoch": 0.6156849775425944, "grad_norm": 0.776678240519604, "learning_rate": 2.0854031064661284e-05, "loss": 0.5813, "num_tokens": 344851729.0, "step": 57710 }, { "epoch": 0.6157383205487929, "grad_norm": 2.463723488685697, "learning_rate": 2.085023920096642e-05, "loss": 0.6002, "num_tokens": 344896360.0, "step": 57715 }, { "epoch": 0.6157916635549913, "grad_norm": 0.6281922620564829, "learning_rate": 2.084644754419846e-05, "loss": 0.5006, "num_tokens": 344938262.0, "step": 57720 }, { "epoch": 0.6158450065611898, "grad_norm": 0.8775421947164531, "learning_rate": 2.084265609447538e-05, "loss": 0.544, "num_tokens": 344980952.0, "step": 57725 }, { "epoch": 0.6158983495673882, "grad_norm": 0.7030611226193862, "learning_rate": 2.083886485191517e-05, "loss": 0.4376, "num_tokens": 345008118.0, "step": 57730 }, { "epoch": 0.6159516925735867, "grad_norm": 0.7022189315718427, "learning_rate": 2.0835073816635807e-05, "loss": 0.4854, "num_tokens": 345040446.0, "step": 57735 }, { "epoch": 0.6160050355797851, "grad_norm": 1.406027258127442, "learning_rate": 2.0831282988755253e-05, "loss": 0.5594, "num_tokens": 345068172.0, "step": 57740 }, { "epoch": 0.6160583785859836, "grad_norm": 0.553380688796011, "learning_rate": 2.0827492368391473e-05, "loss": 0.5819, "num_tokens": 345119422.0, "step": 57745 }, { "epoch": 0.6161117215921821, "grad_norm": 0.7373434111765075, "learning_rate": 2.0823701955662427e-05, "loss": 0.5625, "num_tokens": 345160427.0, "step": 57750 }, { "epoch": 0.6161650645983805, "grad_norm": 0.6826633877503795, "learning_rate": 2.081991175068606e-05, "loss": 0.4496, "num_tokens": 345196627.0, "step": 57755 }, { "epoch": 0.6162184076045789, "grad_norm": 0.638111492809077, "learning_rate": 2.081612175358032e-05, "loss": 0.4974, "num_tokens": 345256030.0, "step": 57760 }, { "epoch": 0.6162717506107774, "grad_norm": 0.6583158939070024, "learning_rate": 2.0812331964463144e-05, "loss": 0.5343, "num_tokens": 345294425.0, "step": 57765 }, { "epoch": 0.6163250936169758, "grad_norm": 1.0871887802259481, "learning_rate": 2.0808542383452456e-05, "loss": 0.5856, "num_tokens": 345326410.0, "step": 57770 }, { "epoch": 0.6163784366231744, "grad_norm": 0.7046234853974545, "learning_rate": 2.0804753010666184e-05, "loss": 0.5411, "num_tokens": 345357987.0, "step": 57775 }, { "epoch": 0.6164317796293728, "grad_norm": 1.587696007382968, "learning_rate": 2.0800963846222254e-05, "loss": 0.5117, "num_tokens": 345382129.0, "step": 57780 }, { "epoch": 0.6164851226355712, "grad_norm": 2.487031900926212, "learning_rate": 2.0797174890238557e-05, "loss": 0.7135, "num_tokens": 345406391.0, "step": 57785 }, { "epoch": 0.6165384656417697, "grad_norm": 1.5773998473027917, "learning_rate": 2.0793386142833016e-05, "loss": 0.5259, "num_tokens": 345427710.0, "step": 57790 }, { "epoch": 0.6165918086479681, "grad_norm": 0.8852185387334897, "learning_rate": 2.0789597604123522e-05, "loss": 0.6949, "num_tokens": 345448321.0, "step": 57795 }, { "epoch": 0.6166451516541667, "grad_norm": 0.7219864835281189, "learning_rate": 2.078580927422797e-05, "loss": 0.5496, "num_tokens": 345486697.0, "step": 57800 }, { "epoch": 0.6166984946603651, "grad_norm": 0.8506551032583374, "learning_rate": 2.0782021153264235e-05, "loss": 0.4251, "num_tokens": 345505714.0, "step": 57805 }, { "epoch": 0.6167518376665635, "grad_norm": 0.8863046775950689, "learning_rate": 2.0778233241350214e-05, "loss": 0.6505, "num_tokens": 345552822.0, "step": 57810 }, { "epoch": 0.616805180672762, "grad_norm": 0.8170313764032134, "learning_rate": 2.077444553860376e-05, "loss": 0.5182, "num_tokens": 345598345.0, "step": 57815 }, { "epoch": 0.6168585236789604, "grad_norm": 1.2019765855820417, "learning_rate": 2.0770658045142742e-05, "loss": 0.4475, "num_tokens": 345624675.0, "step": 57820 }, { "epoch": 0.616911866685159, "grad_norm": 2.468227640639188, "learning_rate": 2.0766870761085033e-05, "loss": 0.6226, "num_tokens": 345646045.0, "step": 57825 }, { "epoch": 0.6169652096913574, "grad_norm": 0.5822785841117235, "learning_rate": 2.076308368654847e-05, "loss": 0.4824, "num_tokens": 345695436.0, "step": 57830 }, { "epoch": 0.6170185526975558, "grad_norm": 0.884637192817625, "learning_rate": 2.07592968216509e-05, "loss": 0.5488, "num_tokens": 345720627.0, "step": 57835 }, { "epoch": 0.6170718957037543, "grad_norm": 0.8425130949937405, "learning_rate": 2.075551016651018e-05, "loss": 0.3912, "num_tokens": 345743548.0, "step": 57840 }, { "epoch": 0.6171252387099527, "grad_norm": 0.7885168818751813, "learning_rate": 2.0751723721244116e-05, "loss": 0.4998, "num_tokens": 345774859.0, "step": 57845 }, { "epoch": 0.6171785817161511, "grad_norm": 1.1368784736280406, "learning_rate": 2.0747937485970554e-05, "loss": 0.5066, "num_tokens": 345800483.0, "step": 57850 }, { "epoch": 0.6172319247223497, "grad_norm": 0.7519910799327405, "learning_rate": 2.0744151460807316e-05, "loss": 0.6706, "num_tokens": 345832875.0, "step": 57855 }, { "epoch": 0.6172852677285481, "grad_norm": 0.6711754650171198, "learning_rate": 2.0740365645872194e-05, "loss": 0.5071, "num_tokens": 345868587.0, "step": 57860 }, { "epoch": 0.6173386107347466, "grad_norm": 1.1355904862382917, "learning_rate": 2.073658004128301e-05, "loss": 0.4266, "num_tokens": 345899703.0, "step": 57865 }, { "epoch": 0.617391953740945, "grad_norm": 1.0532192474333963, "learning_rate": 2.0732794647157572e-05, "loss": 0.576, "num_tokens": 345918330.0, "step": 57870 }, { "epoch": 0.6174452967471434, "grad_norm": 0.7886163940929679, "learning_rate": 2.0729009463613664e-05, "loss": 0.5886, "num_tokens": 345942281.0, "step": 57875 }, { "epoch": 0.617498639753342, "grad_norm": 0.8518645453813377, "learning_rate": 2.0725224490769062e-05, "loss": 0.4578, "num_tokens": 345981373.0, "step": 57880 }, { "epoch": 0.6175519827595404, "grad_norm": 1.4860498277640182, "learning_rate": 2.0721439728741572e-05, "loss": 0.5098, "num_tokens": 346010947.0, "step": 57885 }, { "epoch": 0.6176053257657389, "grad_norm": 1.0042595953073414, "learning_rate": 2.071765517764895e-05, "loss": 0.4656, "num_tokens": 346035064.0, "step": 57890 }, { "epoch": 0.6176586687719373, "grad_norm": 0.9164848004057781, "learning_rate": 2.0713870837608957e-05, "loss": 0.5147, "num_tokens": 346073007.0, "step": 57895 }, { "epoch": 0.6177120117781357, "grad_norm": 0.8582507102890484, "learning_rate": 2.0710086708739377e-05, "loss": 0.5025, "num_tokens": 346110424.0, "step": 57900 }, { "epoch": 0.6177653547843343, "grad_norm": 1.3011931511926595, "learning_rate": 2.070630279115795e-05, "loss": 0.496, "num_tokens": 346146702.0, "step": 57905 }, { "epoch": 0.6178186977905327, "grad_norm": 1.4800615378821953, "learning_rate": 2.0702519084982418e-05, "loss": 0.4632, "num_tokens": 346161755.0, "step": 57910 }, { "epoch": 0.6178720407967312, "grad_norm": 1.5789614734637327, "learning_rate": 2.0698735590330537e-05, "loss": 0.5637, "num_tokens": 346187129.0, "step": 57915 }, { "epoch": 0.6179253838029296, "grad_norm": 1.4075253014662847, "learning_rate": 2.0694952307320033e-05, "loss": 0.5429, "num_tokens": 346206452.0, "step": 57920 }, { "epoch": 0.617978726809128, "grad_norm": 0.9282301208801155, "learning_rate": 2.069116923606863e-05, "loss": 0.471, "num_tokens": 346236153.0, "step": 57925 }, { "epoch": 0.6180320698153265, "grad_norm": 5.386034377803866, "learning_rate": 2.0687386376694064e-05, "loss": 0.6693, "num_tokens": 346259472.0, "step": 57930 }, { "epoch": 0.618085412821525, "grad_norm": 1.1728141495599729, "learning_rate": 2.0683603729314034e-05, "loss": 0.6109, "num_tokens": 346292763.0, "step": 57935 }, { "epoch": 0.6181387558277234, "grad_norm": 1.188489929226086, "learning_rate": 2.0679821294046253e-05, "loss": 0.5008, "num_tokens": 346320204.0, "step": 57940 }, { "epoch": 0.6181920988339219, "grad_norm": 0.9700517169333845, "learning_rate": 2.067603907100843e-05, "loss": 0.5023, "num_tokens": 346340742.0, "step": 57945 }, { "epoch": 0.6182454418401203, "grad_norm": 0.9142678800200377, "learning_rate": 2.067225706031825e-05, "loss": 0.5509, "num_tokens": 346369657.0, "step": 57950 }, { "epoch": 0.6182987848463188, "grad_norm": 1.2371569758179803, "learning_rate": 2.0668475262093402e-05, "loss": 0.528, "num_tokens": 346389026.0, "step": 57955 }, { "epoch": 0.6183521278525173, "grad_norm": 0.7710938185900604, "learning_rate": 2.066469367645158e-05, "loss": 0.5306, "num_tokens": 346418466.0, "step": 57960 }, { "epoch": 0.6184054708587157, "grad_norm": 1.1746262101365186, "learning_rate": 2.066091230351045e-05, "loss": 0.4371, "num_tokens": 346454706.0, "step": 57965 }, { "epoch": 0.6184588138649142, "grad_norm": 1.5501237847167075, "learning_rate": 2.065713114338767e-05, "loss": 0.493, "num_tokens": 346471567.0, "step": 57970 }, { "epoch": 0.6185121568711126, "grad_norm": 0.6977220035250532, "learning_rate": 2.0653350196200926e-05, "loss": 0.6532, "num_tokens": 346521046.0, "step": 57975 }, { "epoch": 0.6185654998773111, "grad_norm": 0.7171948252080449, "learning_rate": 2.064956946206786e-05, "loss": 0.5031, "num_tokens": 346554136.0, "step": 57980 }, { "epoch": 0.6186188428835095, "grad_norm": 0.6374069785811232, "learning_rate": 2.0645788941106116e-05, "loss": 0.5385, "num_tokens": 346589875.0, "step": 57985 }, { "epoch": 0.618672185889708, "grad_norm": 0.914423821468804, "learning_rate": 2.064200863343334e-05, "loss": 0.5159, "num_tokens": 346614680.0, "step": 57990 }, { "epoch": 0.6187255288959065, "grad_norm": 0.774113902791776, "learning_rate": 2.0638228539167166e-05, "loss": 0.6332, "num_tokens": 346663768.0, "step": 57995 }, { "epoch": 0.6187788719021049, "grad_norm": 0.7277500034715718, "learning_rate": 2.063444865842523e-05, "loss": 0.5745, "num_tokens": 346706502.0, "step": 58000 }, { "epoch": 0.6188322149083034, "grad_norm": 1.2705570562935102, "learning_rate": 2.0630668991325157e-05, "loss": 0.531, "num_tokens": 346732456.0, "step": 58005 }, { "epoch": 0.6188855579145018, "grad_norm": 1.0564615078543471, "learning_rate": 2.0626889537984544e-05, "loss": 0.5117, "num_tokens": 346760585.0, "step": 58010 }, { "epoch": 0.6189389009207003, "grad_norm": 1.149930948905121, "learning_rate": 2.0623110298521014e-05, "loss": 0.4837, "num_tokens": 346778898.0, "step": 58015 }, { "epoch": 0.6189922439268988, "grad_norm": 0.8272039463946851, "learning_rate": 2.0619331273052172e-05, "loss": 0.4519, "num_tokens": 346828056.0, "step": 58020 }, { "epoch": 0.6190455869330972, "grad_norm": 1.2568251588569246, "learning_rate": 2.0615552461695598e-05, "loss": 0.4601, "num_tokens": 346849645.0, "step": 58025 }, { "epoch": 0.6190989299392956, "grad_norm": 2.408824454306369, "learning_rate": 2.0611773864568895e-05, "loss": 0.5519, "num_tokens": 346885514.0, "step": 58030 }, { "epoch": 0.6191522729454941, "grad_norm": 0.6819858196208617, "learning_rate": 2.0607995481789633e-05, "loss": 0.4851, "num_tokens": 346907527.0, "step": 58035 }, { "epoch": 0.6192056159516925, "grad_norm": 1.1392752617318231, "learning_rate": 2.060421731347541e-05, "loss": 0.5594, "num_tokens": 346936809.0, "step": 58040 }, { "epoch": 0.6192589589578911, "grad_norm": 0.6309275667484986, "learning_rate": 2.0600439359743766e-05, "loss": 0.3842, "num_tokens": 346959924.0, "step": 58045 }, { "epoch": 0.6193123019640895, "grad_norm": 0.8363764931678822, "learning_rate": 2.059666162071228e-05, "loss": 0.4864, "num_tokens": 346981743.0, "step": 58050 }, { "epoch": 0.6193656449702879, "grad_norm": 0.7048304934995016, "learning_rate": 2.0592884096498517e-05, "loss": 0.4221, "num_tokens": 347009255.0, "step": 58055 }, { "epoch": 0.6194189879764864, "grad_norm": 0.5984901882109737, "learning_rate": 2.0589106787219996e-05, "loss": 0.5147, "num_tokens": 347047867.0, "step": 58060 }, { "epoch": 0.6194723309826848, "grad_norm": 0.7400419796837099, "learning_rate": 2.0585329692994287e-05, "loss": 0.4348, "num_tokens": 347075470.0, "step": 58065 }, { "epoch": 0.6195256739888834, "grad_norm": 0.8625357225609215, "learning_rate": 2.058155281393892e-05, "loss": 0.4782, "num_tokens": 347102549.0, "step": 58070 }, { "epoch": 0.6195790169950818, "grad_norm": 0.7801924364196953, "learning_rate": 2.0577776150171402e-05, "loss": 0.4912, "num_tokens": 347137543.0, "step": 58075 }, { "epoch": 0.6196323600012802, "grad_norm": 1.0092336018133352, "learning_rate": 2.0573999701809278e-05, "loss": 0.552, "num_tokens": 347162272.0, "step": 58080 }, { "epoch": 0.6196857030074787, "grad_norm": 0.757015110670826, "learning_rate": 2.0570223468970062e-05, "loss": 0.4123, "num_tokens": 347181783.0, "step": 58085 }, { "epoch": 0.6197390460136771, "grad_norm": 1.0038561770675958, "learning_rate": 2.0566447451771252e-05, "loss": 0.5111, "num_tokens": 347213031.0, "step": 58090 }, { "epoch": 0.6197923890198757, "grad_norm": 0.7744850782152751, "learning_rate": 2.0562671650330355e-05, "loss": 0.5497, "num_tokens": 347241503.0, "step": 58095 }, { "epoch": 0.6198457320260741, "grad_norm": 0.6799079819334755, "learning_rate": 2.0558896064764877e-05, "loss": 0.5283, "num_tokens": 347276556.0, "step": 58100 }, { "epoch": 0.6198990750322725, "grad_norm": 0.7798242883240937, "learning_rate": 2.0555120695192287e-05, "loss": 0.4569, "num_tokens": 347301858.0, "step": 58105 }, { "epoch": 0.619952418038471, "grad_norm": 1.0464409480099817, "learning_rate": 2.0551345541730073e-05, "loss": 0.3992, "num_tokens": 347328356.0, "step": 58110 }, { "epoch": 0.6200057610446694, "grad_norm": 0.9651291899705312, "learning_rate": 2.054757060449572e-05, "loss": 0.6486, "num_tokens": 347371231.0, "step": 58115 }, { "epoch": 0.6200591040508678, "grad_norm": 1.2504531008638502, "learning_rate": 2.0543795883606682e-05, "loss": 0.4946, "num_tokens": 347385992.0, "step": 58120 }, { "epoch": 0.6201124470570664, "grad_norm": 0.7106607410220247, "learning_rate": 2.054002137918043e-05, "loss": 0.5222, "num_tokens": 347420172.0, "step": 58125 }, { "epoch": 0.6201657900632648, "grad_norm": 0.9055064081764311, "learning_rate": 2.0536247091334428e-05, "loss": 0.6712, "num_tokens": 347442595.0, "step": 58130 }, { "epoch": 0.6202191330694633, "grad_norm": 0.8570817457311014, "learning_rate": 2.0532473020186093e-05, "loss": 0.5444, "num_tokens": 347463600.0, "step": 58135 }, { "epoch": 0.6202724760756617, "grad_norm": 0.8067772673133101, "learning_rate": 2.05286991658529e-05, "loss": 0.4863, "num_tokens": 347499441.0, "step": 58140 }, { "epoch": 0.6203258190818601, "grad_norm": 0.8109685860075888, "learning_rate": 2.0524925528452267e-05, "loss": 0.4499, "num_tokens": 347522120.0, "step": 58145 }, { "epoch": 0.6203791620880587, "grad_norm": 0.9972856272971402, "learning_rate": 2.0521152108101622e-05, "loss": 0.5032, "num_tokens": 347541083.0, "step": 58150 }, { "epoch": 0.6204325050942571, "grad_norm": 0.6100341829736007, "learning_rate": 2.0517378904918377e-05, "loss": 0.3937, "num_tokens": 347567749.0, "step": 58155 }, { "epoch": 0.6204858481004556, "grad_norm": 0.8223450659813976, "learning_rate": 2.051360591901998e-05, "loss": 0.5974, "num_tokens": 347608560.0, "step": 58160 }, { "epoch": 0.620539191106654, "grad_norm": 1.9822179370083022, "learning_rate": 2.0509833150523804e-05, "loss": 0.607, "num_tokens": 347639986.0, "step": 58165 }, { "epoch": 0.6205925341128524, "grad_norm": 0.9346077832961984, "learning_rate": 2.050606059954726e-05, "loss": 0.5299, "num_tokens": 347676460.0, "step": 58170 }, { "epoch": 0.620645877119051, "grad_norm": 0.8604026168867895, "learning_rate": 2.0502288266207753e-05, "loss": 0.3827, "num_tokens": 347704854.0, "step": 58175 }, { "epoch": 0.6206992201252494, "grad_norm": 0.9732923362646297, "learning_rate": 2.0498516150622655e-05, "loss": 0.4712, "num_tokens": 347739871.0, "step": 58180 }, { "epoch": 0.6207525631314479, "grad_norm": 1.0429054016713304, "learning_rate": 2.0494744252909353e-05, "loss": 0.5555, "num_tokens": 347768527.0, "step": 58185 }, { "epoch": 0.6208059061376463, "grad_norm": 0.7872858306577757, "learning_rate": 2.0490972573185224e-05, "loss": 0.5527, "num_tokens": 347796317.0, "step": 58190 }, { "epoch": 0.6208592491438447, "grad_norm": 1.0632044916751775, "learning_rate": 2.0487201111567634e-05, "loss": 0.5269, "num_tokens": 347821383.0, "step": 58195 }, { "epoch": 0.6209125921500432, "grad_norm": 1.012828532605244, "learning_rate": 2.048342986817393e-05, "loss": 0.436, "num_tokens": 347853841.0, "step": 58200 }, { "epoch": 0.6209659351562417, "grad_norm": 0.8759361831214184, "learning_rate": 2.047965884312149e-05, "loss": 0.4859, "num_tokens": 347877956.0, "step": 58205 }, { "epoch": 0.6210192781624401, "grad_norm": 0.7982339489418081, "learning_rate": 2.047588803652763e-05, "loss": 0.4537, "num_tokens": 347904837.0, "step": 58210 }, { "epoch": 0.6210726211686386, "grad_norm": 0.5980716186780312, "learning_rate": 2.047211744850972e-05, "loss": 0.445, "num_tokens": 347948435.0, "step": 58215 }, { "epoch": 0.621125964174837, "grad_norm": 1.0780386099209982, "learning_rate": 2.046834707918508e-05, "loss": 0.4962, "num_tokens": 347964864.0, "step": 58220 }, { "epoch": 0.6211793071810355, "grad_norm": 1.3868080478267937, "learning_rate": 2.046457692867102e-05, "loss": 0.5798, "num_tokens": 347982535.0, "step": 58225 }, { "epoch": 0.621232650187234, "grad_norm": 0.6983482194619983, "learning_rate": 2.0460806997084887e-05, "loss": 0.3951, "num_tokens": 348012768.0, "step": 58230 }, { "epoch": 0.6212859931934324, "grad_norm": 1.0748681223976373, "learning_rate": 2.045703728454399e-05, "loss": 0.5578, "num_tokens": 348042878.0, "step": 58235 }, { "epoch": 0.6213393361996309, "grad_norm": 0.8749085822176957, "learning_rate": 2.0453267791165604e-05, "loss": 0.6258, "num_tokens": 348080585.0, "step": 58240 }, { "epoch": 0.6213926792058293, "grad_norm": 0.6922900682623654, "learning_rate": 2.044949851706706e-05, "loss": 0.6326, "num_tokens": 348134141.0, "step": 58245 }, { "epoch": 0.6214460222120278, "grad_norm": 0.8252677383276086, "learning_rate": 2.044572946236565e-05, "loss": 0.492, "num_tokens": 348169779.0, "step": 58250 }, { "epoch": 0.6214993652182262, "grad_norm": 1.0517054391457121, "learning_rate": 2.0441960627178636e-05, "loss": 0.5554, "num_tokens": 348187301.0, "step": 58255 }, { "epoch": 0.6215527082244247, "grad_norm": 0.9325905625963531, "learning_rate": 2.0438192011623313e-05, "loss": 0.4965, "num_tokens": 348220664.0, "step": 58260 }, { "epoch": 0.6216060512306232, "grad_norm": 1.135960581147002, "learning_rate": 2.0434423615816956e-05, "loss": 0.6421, "num_tokens": 348244575.0, "step": 58265 }, { "epoch": 0.6216593942368216, "grad_norm": 0.9113746497730194, "learning_rate": 2.0430655439876818e-05, "loss": 0.524, "num_tokens": 348269964.0, "step": 58270 }, { "epoch": 0.6217127372430201, "grad_norm": 1.5713767005805392, "learning_rate": 2.0426887483920155e-05, "loss": 0.6217, "num_tokens": 348296354.0, "step": 58275 }, { "epoch": 0.6217660802492185, "grad_norm": 0.4891032022219844, "learning_rate": 2.0423119748064235e-05, "loss": 0.5641, "num_tokens": 348322299.0, "step": 58280 }, { "epoch": 0.621819423255417, "grad_norm": 1.3304770505171961, "learning_rate": 2.0419352232426286e-05, "loss": 0.4529, "num_tokens": 348349976.0, "step": 58285 }, { "epoch": 0.6218727662616155, "grad_norm": 0.8758006077544926, "learning_rate": 2.041558493712355e-05, "loss": 0.4733, "num_tokens": 348380130.0, "step": 58290 }, { "epoch": 0.6219261092678139, "grad_norm": 0.8106048913629734, "learning_rate": 2.041181786227327e-05, "loss": 0.3706, "num_tokens": 348403029.0, "step": 58295 }, { "epoch": 0.6219794522740123, "grad_norm": 1.1649161889382278, "learning_rate": 2.0408051007992645e-05, "loss": 0.4988, "num_tokens": 348425633.0, "step": 58300 }, { "epoch": 0.6220327952802108, "grad_norm": 0.6281732603441217, "learning_rate": 2.040428437439892e-05, "loss": 0.5935, "num_tokens": 348473096.0, "step": 58305 }, { "epoch": 0.6220861382864092, "grad_norm": 0.9550390215761487, "learning_rate": 2.0400517961609284e-05, "loss": 0.4844, "num_tokens": 348493648.0, "step": 58310 }, { "epoch": 0.6221394812926078, "grad_norm": 1.2397771332185028, "learning_rate": 2.039675176974094e-05, "loss": 0.4227, "num_tokens": 348508001.0, "step": 58315 }, { "epoch": 0.6221928242988062, "grad_norm": 0.7567457395078239, "learning_rate": 2.0392985798911086e-05, "loss": 0.554, "num_tokens": 348546634.0, "step": 58320 }, { "epoch": 0.6222461673050046, "grad_norm": 0.6233263366229861, "learning_rate": 2.038922004923693e-05, "loss": 0.429, "num_tokens": 348588267.0, "step": 58325 }, { "epoch": 0.6222995103112031, "grad_norm": 0.7138397342165136, "learning_rate": 2.0385454520835634e-05, "loss": 0.6393, "num_tokens": 348622251.0, "step": 58330 }, { "epoch": 0.6223528533174015, "grad_norm": 1.1769134153666452, "learning_rate": 2.038168921382438e-05, "loss": 0.6249, "num_tokens": 348665090.0, "step": 58335 }, { "epoch": 0.6224061963236001, "grad_norm": 0.7053046176359982, "learning_rate": 2.0377924128320337e-05, "loss": 0.4962, "num_tokens": 348702098.0, "step": 58340 }, { "epoch": 0.6224595393297985, "grad_norm": 0.9083112214895778, "learning_rate": 2.0374159264440667e-05, "loss": 0.4452, "num_tokens": 348724114.0, "step": 58345 }, { "epoch": 0.6225128823359969, "grad_norm": 1.7994653273568655, "learning_rate": 2.037039462230252e-05, "loss": 0.5781, "num_tokens": 348753943.0, "step": 58350 }, { "epoch": 0.6225662253421954, "grad_norm": 1.2040804138043997, "learning_rate": 2.0366630202023058e-05, "loss": 0.4906, "num_tokens": 348780508.0, "step": 58355 }, { "epoch": 0.6226195683483938, "grad_norm": 0.8560750188100689, "learning_rate": 2.03628660037194e-05, "loss": 0.5418, "num_tokens": 348809179.0, "step": 58360 }, { "epoch": 0.6226729113545924, "grad_norm": 0.9136454335634824, "learning_rate": 2.0359102027508688e-05, "loss": 0.5178, "num_tokens": 348849326.0, "step": 58365 }, { "epoch": 0.6227262543607908, "grad_norm": 1.2884463047515173, "learning_rate": 2.035533827350807e-05, "loss": 0.6844, "num_tokens": 348873629.0, "step": 58370 }, { "epoch": 0.6227795973669892, "grad_norm": 0.6912462013889047, "learning_rate": 2.0351574741834632e-05, "loss": 0.5904, "num_tokens": 348911108.0, "step": 58375 }, { "epoch": 0.6228329403731877, "grad_norm": 1.220753753746279, "learning_rate": 2.0347811432605512e-05, "loss": 0.5853, "num_tokens": 348923807.0, "step": 58380 }, { "epoch": 0.6228862833793861, "grad_norm": 0.785458565213849, "learning_rate": 2.0344048345937815e-05, "loss": 0.4819, "num_tokens": 348948928.0, "step": 58385 }, { "epoch": 0.6229396263855845, "grad_norm": 1.0807813647000526, "learning_rate": 2.0340285481948623e-05, "loss": 0.3862, "num_tokens": 348972358.0, "step": 58390 }, { "epoch": 0.6229929693917831, "grad_norm": 2.8493661298157957, "learning_rate": 2.0336522840755052e-05, "loss": 0.4775, "num_tokens": 348990513.0, "step": 58395 }, { "epoch": 0.6230463123979815, "grad_norm": 1.0570068764921854, "learning_rate": 2.0332760422474173e-05, "loss": 0.5306, "num_tokens": 349006748.0, "step": 58400 }, { "epoch": 0.62309965540418, "grad_norm": 1.0436606229688679, "learning_rate": 2.0328998227223062e-05, "loss": 0.5648, "num_tokens": 349034682.0, "step": 58405 }, { "epoch": 0.6231529984103784, "grad_norm": 0.8838042612382242, "learning_rate": 2.0325236255118797e-05, "loss": 0.4034, "num_tokens": 349058720.0, "step": 58410 }, { "epoch": 0.6232063414165768, "grad_norm": 0.9847859648952897, "learning_rate": 2.0321474506278447e-05, "loss": 0.4607, "num_tokens": 349080136.0, "step": 58415 }, { "epoch": 0.6232596844227754, "grad_norm": 1.0273367382971248, "learning_rate": 2.0317712980819063e-05, "loss": 0.4945, "num_tokens": 349112301.0, "step": 58420 }, { "epoch": 0.6233130274289738, "grad_norm": 1.1119555611777425, "learning_rate": 2.03139516788577e-05, "loss": 0.5486, "num_tokens": 349162532.0, "step": 58425 }, { "epoch": 0.6233663704351723, "grad_norm": 1.0256512199196608, "learning_rate": 2.0310190600511404e-05, "loss": 0.4889, "num_tokens": 349185680.0, "step": 58430 }, { "epoch": 0.6234197134413707, "grad_norm": 0.8532479201812729, "learning_rate": 2.0306429745897205e-05, "loss": 0.3936, "num_tokens": 349209237.0, "step": 58435 }, { "epoch": 0.6234730564475691, "grad_norm": 0.8677386147723634, "learning_rate": 2.0302669115132126e-05, "loss": 0.6097, "num_tokens": 349238169.0, "step": 58440 }, { "epoch": 0.6235263994537676, "grad_norm": 0.8975005253365598, "learning_rate": 2.0298908708333215e-05, "loss": 0.5436, "num_tokens": 349262658.0, "step": 58445 }, { "epoch": 0.6235797424599661, "grad_norm": 1.2073620409782966, "learning_rate": 2.0295148525617462e-05, "loss": 0.5646, "num_tokens": 349283625.0, "step": 58450 }, { "epoch": 0.6236330854661646, "grad_norm": 0.8179686941465998, "learning_rate": 2.0291388567101895e-05, "loss": 0.6029, "num_tokens": 349339000.0, "step": 58455 }, { "epoch": 0.623686428472363, "grad_norm": 0.8217556815723528, "learning_rate": 2.0287628832903515e-05, "loss": 0.4842, "num_tokens": 349356063.0, "step": 58460 }, { "epoch": 0.6237397714785614, "grad_norm": 1.0987750429678402, "learning_rate": 2.0283869323139298e-05, "loss": 0.4051, "num_tokens": 349381214.0, "step": 58465 }, { "epoch": 0.6237931144847599, "grad_norm": 0.8361865233060534, "learning_rate": 2.028011003792625e-05, "loss": 0.3806, "num_tokens": 349412118.0, "step": 58470 }, { "epoch": 0.6238464574909584, "grad_norm": 0.9079988336607456, "learning_rate": 2.0276350977381354e-05, "loss": 0.5045, "num_tokens": 349449562.0, "step": 58475 }, { "epoch": 0.6238998004971568, "grad_norm": 1.3001251131276421, "learning_rate": 2.0272592141621565e-05, "loss": 0.5413, "num_tokens": 349463816.0, "step": 58480 }, { "epoch": 0.6239531435033553, "grad_norm": 0.8126868610278415, "learning_rate": 2.026883353076387e-05, "loss": 0.3827, "num_tokens": 349483928.0, "step": 58485 }, { "epoch": 0.6240064865095537, "grad_norm": 0.8788272701707711, "learning_rate": 2.026507514492522e-05, "loss": 0.4832, "num_tokens": 349511349.0, "step": 58490 }, { "epoch": 0.6240598295157522, "grad_norm": 0.6615844516750277, "learning_rate": 2.0261316984222573e-05, "loss": 0.5224, "num_tokens": 349539019.0, "step": 58495 }, { "epoch": 0.6241131725219506, "grad_norm": 1.5901395448326332, "learning_rate": 2.0257559048772874e-05, "loss": 0.5026, "num_tokens": 349560694.0, "step": 58500 }, { "epoch": 0.6241665155281491, "grad_norm": 0.7190694524701798, "learning_rate": 2.025380133869306e-05, "loss": 0.4353, "num_tokens": 349594654.0, "step": 58505 }, { "epoch": 0.6242198585343476, "grad_norm": 1.4627700502186274, "learning_rate": 2.0250043854100064e-05, "loss": 0.5649, "num_tokens": 349643071.0, "step": 58510 }, { "epoch": 0.624273201540546, "grad_norm": 0.8842683243418393, "learning_rate": 2.0246286595110808e-05, "loss": 0.3809, "num_tokens": 349672700.0, "step": 58515 }, { "epoch": 0.6243265445467445, "grad_norm": 0.9943603873924046, "learning_rate": 2.0242529561842223e-05, "loss": 0.368, "num_tokens": 349697661.0, "step": 58520 }, { "epoch": 0.6243798875529429, "grad_norm": 1.3404989662602786, "learning_rate": 2.0238772754411206e-05, "loss": 0.6246, "num_tokens": 349717628.0, "step": 58525 }, { "epoch": 0.6244332305591414, "grad_norm": 2.3321239890356207, "learning_rate": 2.0235016172934657e-05, "loss": 0.5785, "num_tokens": 349751510.0, "step": 58530 }, { "epoch": 0.6244865735653399, "grad_norm": 0.8094504916075487, "learning_rate": 2.0231259817529497e-05, "loss": 0.4614, "num_tokens": 349774984.0, "step": 58535 }, { "epoch": 0.6245399165715383, "grad_norm": 0.9077245623897854, "learning_rate": 2.0227503688312587e-05, "loss": 0.5012, "num_tokens": 349794924.0, "step": 58540 }, { "epoch": 0.6245932595777368, "grad_norm": 0.7619667933584489, "learning_rate": 2.022374778540083e-05, "loss": 0.6773, "num_tokens": 349835756.0, "step": 58545 }, { "epoch": 0.6246466025839352, "grad_norm": 2.33044870037451, "learning_rate": 2.02199921089111e-05, "loss": 0.5184, "num_tokens": 349876777.0, "step": 58550 }, { "epoch": 0.6246999455901336, "grad_norm": 0.985606496202633, "learning_rate": 2.021623665896026e-05, "loss": 0.5592, "num_tokens": 349903560.0, "step": 58555 }, { "epoch": 0.6247532885963322, "grad_norm": 1.149326338701251, "learning_rate": 2.021248143566517e-05, "loss": 0.523, "num_tokens": 349930176.0, "step": 58560 }, { "epoch": 0.6248066316025306, "grad_norm": 1.278180833434273, "learning_rate": 2.0208726439142693e-05, "loss": 0.5141, "num_tokens": 349955118.0, "step": 58565 }, { "epoch": 0.624859974608729, "grad_norm": 1.3521909531490968, "learning_rate": 2.020497166950967e-05, "loss": 0.6131, "num_tokens": 349967860.0, "step": 58570 }, { "epoch": 0.6249133176149275, "grad_norm": 0.794911247484259, "learning_rate": 2.020121712688294e-05, "loss": 0.5214, "num_tokens": 349990479.0, "step": 58575 }, { "epoch": 0.6249666606211259, "grad_norm": 0.973590174797354, "learning_rate": 2.0197462811379352e-05, "loss": 0.5675, "num_tokens": 350024414.0, "step": 58580 }, { "epoch": 0.6250200036273245, "grad_norm": 0.9705349562916561, "learning_rate": 2.019370872311571e-05, "loss": 0.4613, "num_tokens": 350053503.0, "step": 58585 }, { "epoch": 0.6250733466335229, "grad_norm": 0.7632062187560552, "learning_rate": 2.018995486220885e-05, "loss": 0.4557, "num_tokens": 350069647.0, "step": 58590 }, { "epoch": 0.6251266896397213, "grad_norm": 0.5943552069814233, "learning_rate": 2.0186201228775585e-05, "loss": 0.3907, "num_tokens": 350092671.0, "step": 58595 }, { "epoch": 0.6251800326459198, "grad_norm": 1.0399946493255623, "learning_rate": 2.018244782293271e-05, "loss": 0.4933, "num_tokens": 350131481.0, "step": 58600 }, { "epoch": 0.6252333756521182, "grad_norm": 0.7278626699075654, "learning_rate": 2.0178694644797025e-05, "loss": 0.5194, "num_tokens": 350157269.0, "step": 58605 }, { "epoch": 0.6252867186583168, "grad_norm": 4.956319407282532, "learning_rate": 2.0174941694485327e-05, "loss": 0.6875, "num_tokens": 350181304.0, "step": 58610 }, { "epoch": 0.6253400616645152, "grad_norm": 1.1587265109089386, "learning_rate": 2.0171188972114396e-05, "loss": 0.3927, "num_tokens": 350213526.0, "step": 58615 }, { "epoch": 0.6253934046707136, "grad_norm": 0.9727453050421, "learning_rate": 2.016743647780101e-05, "loss": 0.4989, "num_tokens": 350239465.0, "step": 58620 }, { "epoch": 0.6254467476769121, "grad_norm": 0.7601150596131268, "learning_rate": 2.0163684211661947e-05, "loss": 0.402, "num_tokens": 350287319.0, "step": 58625 }, { "epoch": 0.6255000906831105, "grad_norm": 0.7212075439639177, "learning_rate": 2.015993217381395e-05, "loss": 0.5063, "num_tokens": 350326080.0, "step": 58630 }, { "epoch": 0.625553433689309, "grad_norm": 0.78874267669776, "learning_rate": 2.0156180364373795e-05, "loss": 0.5241, "num_tokens": 350364217.0, "step": 58635 }, { "epoch": 0.6256067766955075, "grad_norm": 0.6458427735926192, "learning_rate": 2.0152428783458226e-05, "loss": 0.6021, "num_tokens": 350405856.0, "step": 58640 }, { "epoch": 0.6256601197017059, "grad_norm": 1.1740636019628643, "learning_rate": 2.014867743118397e-05, "loss": 0.5695, "num_tokens": 350434666.0, "step": 58645 }, { "epoch": 0.6257134627079044, "grad_norm": 1.2438005286426561, "learning_rate": 2.0144926307667776e-05, "loss": 0.5877, "num_tokens": 350460426.0, "step": 58650 }, { "epoch": 0.6257668057141028, "grad_norm": 1.004877237834645, "learning_rate": 2.0141175413026375e-05, "loss": 0.4897, "num_tokens": 350487435.0, "step": 58655 }, { "epoch": 0.6258201487203012, "grad_norm": 1.1507889867018735, "learning_rate": 2.0137424747376472e-05, "loss": 0.3975, "num_tokens": 350512440.0, "step": 58660 }, { "epoch": 0.6258734917264998, "grad_norm": 0.9148360180079985, "learning_rate": 2.013367431083478e-05, "loss": 0.4904, "num_tokens": 350540567.0, "step": 58665 }, { "epoch": 0.6259268347326982, "grad_norm": 0.8734972065624613, "learning_rate": 2.0129924103518032e-05, "loss": 0.5885, "num_tokens": 350575861.0, "step": 58670 }, { "epoch": 0.6259801777388967, "grad_norm": 0.7570796995331788, "learning_rate": 2.0126174125542896e-05, "loss": 0.561, "num_tokens": 350624390.0, "step": 58675 }, { "epoch": 0.6260335207450951, "grad_norm": 0.8403659759558947, "learning_rate": 2.0122424377026072e-05, "loss": 0.4746, "num_tokens": 350656491.0, "step": 58680 }, { "epoch": 0.6260868637512935, "grad_norm": 0.6027787919157832, "learning_rate": 2.0118674858084257e-05, "loss": 0.5177, "num_tokens": 350691607.0, "step": 58685 }, { "epoch": 0.626140206757492, "grad_norm": 1.2068493223486334, "learning_rate": 2.0114925568834115e-05, "loss": 0.5579, "num_tokens": 350727792.0, "step": 58690 }, { "epoch": 0.6261935497636905, "grad_norm": 0.9289139786260671, "learning_rate": 2.0111176509392315e-05, "loss": 0.5606, "num_tokens": 350765093.0, "step": 58695 }, { "epoch": 0.626246892769889, "grad_norm": 1.907477635062656, "learning_rate": 2.010742767987553e-05, "loss": 0.5438, "num_tokens": 350786467.0, "step": 58700 }, { "epoch": 0.6263002357760874, "grad_norm": 0.6291198111802213, "learning_rate": 2.0103679080400406e-05, "loss": 0.5729, "num_tokens": 350816164.0, "step": 58705 }, { "epoch": 0.6263535787822858, "grad_norm": 1.539915294927224, "learning_rate": 2.00999307110836e-05, "loss": 0.4013, "num_tokens": 350841538.0, "step": 58710 }, { "epoch": 0.6264069217884843, "grad_norm": 1.0149933240356777, "learning_rate": 2.0096182572041756e-05, "loss": 0.5511, "num_tokens": 350876968.0, "step": 58715 }, { "epoch": 0.6264602647946828, "grad_norm": 0.9765505330635827, "learning_rate": 2.0092434663391492e-05, "loss": 0.5267, "num_tokens": 350905911.0, "step": 58720 }, { "epoch": 0.6265136078008813, "grad_norm": 1.675566417377253, "learning_rate": 2.008868698524945e-05, "loss": 0.5646, "num_tokens": 350936760.0, "step": 58725 }, { "epoch": 0.6265669508070797, "grad_norm": 0.9574601316530025, "learning_rate": 2.008493953773225e-05, "loss": 0.488, "num_tokens": 350956629.0, "step": 58730 }, { "epoch": 0.6266202938132781, "grad_norm": 0.9358767232085597, "learning_rate": 2.008119232095649e-05, "loss": 0.483, "num_tokens": 350987414.0, "step": 58735 }, { "epoch": 0.6266736368194766, "grad_norm": 0.7917258343198305, "learning_rate": 2.007744533503879e-05, "loss": 0.5367, "num_tokens": 351030818.0, "step": 58740 }, { "epoch": 0.626726979825675, "grad_norm": 0.8435270064254834, "learning_rate": 2.007369858009575e-05, "loss": 0.4282, "num_tokens": 351052596.0, "step": 58745 }, { "epoch": 0.6267803228318735, "grad_norm": 0.9282984952795845, "learning_rate": 2.0069952056243958e-05, "loss": 0.572, "num_tokens": 351075347.0, "step": 58750 }, { "epoch": 0.626833665838072, "grad_norm": 0.7421805325422137, "learning_rate": 2.0066205763599983e-05, "loss": 0.5337, "num_tokens": 351101253.0, "step": 58755 }, { "epoch": 0.6268870088442704, "grad_norm": 1.0906422007278105, "learning_rate": 2.006245970228043e-05, "loss": 0.536, "num_tokens": 351136279.0, "step": 58760 }, { "epoch": 0.6269403518504689, "grad_norm": 1.01996902861386, "learning_rate": 2.0058713872401845e-05, "loss": 0.4541, "num_tokens": 351161430.0, "step": 58765 }, { "epoch": 0.6269936948566673, "grad_norm": 0.7807420688092245, "learning_rate": 2.0054968274080803e-05, "loss": 0.5136, "num_tokens": 351189781.0, "step": 58770 }, { "epoch": 0.6270470378628658, "grad_norm": 0.9173859604516863, "learning_rate": 2.005122290743386e-05, "loss": 0.4231, "num_tokens": 351224822.0, "step": 58775 }, { "epoch": 0.6271003808690643, "grad_norm": 0.9903946892709748, "learning_rate": 2.004747777257755e-05, "loss": 0.5032, "num_tokens": 351247292.0, "step": 58780 }, { "epoch": 0.6271537238752627, "grad_norm": 1.1614542620146922, "learning_rate": 2.004373286962843e-05, "loss": 0.5215, "num_tokens": 351276916.0, "step": 58785 }, { "epoch": 0.6272070668814612, "grad_norm": 1.0315310270340983, "learning_rate": 2.003998819870303e-05, "loss": 0.5663, "num_tokens": 351299364.0, "step": 58790 }, { "epoch": 0.6272604098876596, "grad_norm": 1.0111974703870596, "learning_rate": 2.0036243759917866e-05, "loss": 0.4763, "num_tokens": 351329282.0, "step": 58795 }, { "epoch": 0.627313752893858, "grad_norm": 1.2422809547795055, "learning_rate": 2.0032499553389466e-05, "loss": 0.4655, "num_tokens": 351357678.0, "step": 58800 }, { "epoch": 0.6273670959000566, "grad_norm": 0.8891457428305055, "learning_rate": 2.0028755579234354e-05, "loss": 0.4096, "num_tokens": 351383157.0, "step": 58805 }, { "epoch": 0.627420438906255, "grad_norm": 0.867154843243579, "learning_rate": 2.0025011837569006e-05, "loss": 0.4452, "num_tokens": 351414149.0, "step": 58810 }, { "epoch": 0.6274737819124535, "grad_norm": 0.7603783522409081, "learning_rate": 2.002126832850994e-05, "loss": 0.4024, "num_tokens": 351448896.0, "step": 58815 }, { "epoch": 0.6275271249186519, "grad_norm": 0.9633675539721477, "learning_rate": 2.0017525052173653e-05, "loss": 0.5675, "num_tokens": 351479195.0, "step": 58820 }, { "epoch": 0.6275804679248503, "grad_norm": 1.4392024861179196, "learning_rate": 2.00137820086766e-05, "loss": 0.554, "num_tokens": 351512154.0, "step": 58825 }, { "epoch": 0.6276338109310489, "grad_norm": 0.6883653228245588, "learning_rate": 2.0010039198135277e-05, "loss": 0.5513, "num_tokens": 351536607.0, "step": 58830 }, { "epoch": 0.6276871539372473, "grad_norm": 0.7751528198390698, "learning_rate": 2.000629662066616e-05, "loss": 0.5339, "num_tokens": 351579152.0, "step": 58835 }, { "epoch": 0.6277404969434457, "grad_norm": 0.6798511074486205, "learning_rate": 2.0002554276385693e-05, "loss": 0.4811, "num_tokens": 351623175.0, "step": 58840 }, { "epoch": 0.6277938399496442, "grad_norm": 0.6163876336024768, "learning_rate": 1.9998812165410334e-05, "loss": 0.4211, "num_tokens": 351646582.0, "step": 58845 }, { "epoch": 0.6278471829558426, "grad_norm": 0.6579070965902227, "learning_rate": 1.9995070287856543e-05, "loss": 0.451, "num_tokens": 351677158.0, "step": 58850 }, { "epoch": 0.6279005259620412, "grad_norm": 0.7670328306294723, "learning_rate": 1.999132864384074e-05, "loss": 0.3867, "num_tokens": 351703283.0, "step": 58855 }, { "epoch": 0.6279538689682396, "grad_norm": 0.9115173320396806, "learning_rate": 1.9987587233479366e-05, "loss": 0.4348, "num_tokens": 351719106.0, "step": 58860 }, { "epoch": 0.628007211974438, "grad_norm": 1.01915314876929, "learning_rate": 1.9983846056888856e-05, "loss": 0.4129, "num_tokens": 351747874.0, "step": 58865 }, { "epoch": 0.6280605549806365, "grad_norm": 0.8550479612965745, "learning_rate": 1.9980105114185604e-05, "loss": 0.3454, "num_tokens": 351773889.0, "step": 58870 }, { "epoch": 0.6281138979868349, "grad_norm": 0.6711142952920306, "learning_rate": 1.997636440548604e-05, "loss": 0.4608, "num_tokens": 351800490.0, "step": 58875 }, { "epoch": 0.6281672409930334, "grad_norm": 1.0956624531455266, "learning_rate": 1.997262393090657e-05, "loss": 0.5781, "num_tokens": 351817695.0, "step": 58880 }, { "epoch": 0.6282205839992319, "grad_norm": 0.8206682290648244, "learning_rate": 1.996888369056357e-05, "loss": 0.5215, "num_tokens": 351843804.0, "step": 58885 }, { "epoch": 0.6282739270054303, "grad_norm": 0.9734737156261458, "learning_rate": 1.9965143684573445e-05, "loss": 0.4448, "num_tokens": 351863538.0, "step": 58890 }, { "epoch": 0.6283272700116288, "grad_norm": 0.5926176993933888, "learning_rate": 1.996140391305258e-05, "loss": 0.5057, "num_tokens": 351890478.0, "step": 58895 }, { "epoch": 0.6283806130178272, "grad_norm": 0.6992749515695634, "learning_rate": 1.9957664376117325e-05, "loss": 0.5056, "num_tokens": 351921894.0, "step": 58900 }, { "epoch": 0.6284339560240257, "grad_norm": 1.9464991794848883, "learning_rate": 1.9953925073884066e-05, "loss": 0.5233, "num_tokens": 351948359.0, "step": 58905 }, { "epoch": 0.6284872990302242, "grad_norm": 1.292746662946364, "learning_rate": 1.9950186006469163e-05, "loss": 0.5132, "num_tokens": 351985225.0, "step": 58910 }, { "epoch": 0.6285406420364226, "grad_norm": 0.8288201905751458, "learning_rate": 1.9946447173988964e-05, "loss": 0.4428, "num_tokens": 352015540.0, "step": 58915 }, { "epoch": 0.6285939850426211, "grad_norm": 0.6846315823866017, "learning_rate": 1.994270857655981e-05, "loss": 0.5548, "num_tokens": 352057557.0, "step": 58920 }, { "epoch": 0.6286473280488195, "grad_norm": 0.694451067658817, "learning_rate": 1.9938970214298046e-05, "loss": 0.4487, "num_tokens": 352091766.0, "step": 58925 }, { "epoch": 0.6287006710550179, "grad_norm": 1.2028551168962147, "learning_rate": 1.993523208732e-05, "loss": 0.5127, "num_tokens": 352109685.0, "step": 58930 }, { "epoch": 0.6287540140612164, "grad_norm": 0.5579299266898107, "learning_rate": 1.9931494195741983e-05, "loss": 0.4261, "num_tokens": 352142484.0, "step": 58935 }, { "epoch": 0.6288073570674149, "grad_norm": 1.2403222448113067, "learning_rate": 1.9927756539680333e-05, "loss": 0.484, "num_tokens": 352161007.0, "step": 58940 }, { "epoch": 0.6288607000736134, "grad_norm": 0.775517267692477, "learning_rate": 1.992401911925133e-05, "loss": 0.4117, "num_tokens": 352201539.0, "step": 58945 }, { "epoch": 0.6289140430798118, "grad_norm": 0.5702847999979113, "learning_rate": 1.9920281934571306e-05, "loss": 0.4629, "num_tokens": 352239749.0, "step": 58950 }, { "epoch": 0.6289673860860102, "grad_norm": 0.6535809156245549, "learning_rate": 1.9916544985756526e-05, "loss": 0.4356, "num_tokens": 352260453.0, "step": 58955 }, { "epoch": 0.6290207290922087, "grad_norm": 1.0384097582482097, "learning_rate": 1.99128082729233e-05, "loss": 0.5203, "num_tokens": 352284016.0, "step": 58960 }, { "epoch": 0.6290740720984072, "grad_norm": 0.9747931820082226, "learning_rate": 1.990907179618789e-05, "loss": 0.5557, "num_tokens": 352330414.0, "step": 58965 }, { "epoch": 0.6291274151046057, "grad_norm": 0.8368459416102734, "learning_rate": 1.9905335555666573e-05, "loss": 0.3699, "num_tokens": 352363076.0, "step": 58970 }, { "epoch": 0.6291807581108041, "grad_norm": 2.276161077511307, "learning_rate": 1.990159955147562e-05, "loss": 0.5316, "num_tokens": 352381301.0, "step": 58975 }, { "epoch": 0.6292341011170025, "grad_norm": 1.2163980005467983, "learning_rate": 1.989786378373128e-05, "loss": 0.5404, "num_tokens": 352398811.0, "step": 58980 }, { "epoch": 0.629287444123201, "grad_norm": 0.5920800090261831, "learning_rate": 1.989412825254979e-05, "loss": 0.5208, "num_tokens": 352439667.0, "step": 58985 }, { "epoch": 0.6293407871293994, "grad_norm": 0.9912254039165626, "learning_rate": 1.9890392958047426e-05, "loss": 0.4613, "num_tokens": 352458409.0, "step": 58990 }, { "epoch": 0.629394130135598, "grad_norm": 0.7295433982724077, "learning_rate": 1.9886657900340393e-05, "loss": 0.5485, "num_tokens": 352495894.0, "step": 58995 }, { "epoch": 0.6294474731417964, "grad_norm": 0.7857522667725833, "learning_rate": 1.9882923079544924e-05, "loss": 0.638, "num_tokens": 352555188.0, "step": 59000 }, { "epoch": 0.6295008161479948, "grad_norm": 0.7677971817371878, "learning_rate": 1.9879188495777256e-05, "loss": 0.4857, "num_tokens": 352591819.0, "step": 59005 }, { "epoch": 0.6295541591541933, "grad_norm": 0.9969724492810119, "learning_rate": 1.987545414915357e-05, "loss": 0.6476, "num_tokens": 352628562.0, "step": 59010 }, { "epoch": 0.6296075021603917, "grad_norm": 1.1117478887873427, "learning_rate": 1.9871720039790104e-05, "loss": 0.5415, "num_tokens": 352658125.0, "step": 59015 }, { "epoch": 0.6296608451665902, "grad_norm": 0.5812610133756468, "learning_rate": 1.9867986167803036e-05, "loss": 0.4833, "num_tokens": 352691777.0, "step": 59020 }, { "epoch": 0.6297141881727887, "grad_norm": 0.7023611048238885, "learning_rate": 1.9864252533308563e-05, "loss": 0.748, "num_tokens": 352712500.0, "step": 59025 }, { "epoch": 0.6297675311789871, "grad_norm": 0.7789821890940815, "learning_rate": 1.986051913642286e-05, "loss": 0.4502, "num_tokens": 352738179.0, "step": 59030 }, { "epoch": 0.6298208741851856, "grad_norm": 0.8065157643192451, "learning_rate": 1.985678597726212e-05, "loss": 0.538, "num_tokens": 352752217.0, "step": 59035 }, { "epoch": 0.629874217191384, "grad_norm": 1.2802594707740993, "learning_rate": 1.98530530559425e-05, "loss": 0.545, "num_tokens": 352776042.0, "step": 59040 }, { "epoch": 0.6299275601975824, "grad_norm": 1.3275337506162574, "learning_rate": 1.9849320372580155e-05, "loss": 0.5826, "num_tokens": 352810699.0, "step": 59045 }, { "epoch": 0.629980903203781, "grad_norm": 0.8768300470947711, "learning_rate": 1.9845587927291253e-05, "loss": 0.4776, "num_tokens": 352838411.0, "step": 59050 }, { "epoch": 0.6300342462099794, "grad_norm": 0.9716301166027072, "learning_rate": 1.9841855720191926e-05, "loss": 0.4748, "num_tokens": 352854238.0, "step": 59055 }, { "epoch": 0.6300875892161779, "grad_norm": 1.1354335980244792, "learning_rate": 1.9838123751398318e-05, "loss": 0.3894, "num_tokens": 352881541.0, "step": 59060 }, { "epoch": 0.6301409322223763, "grad_norm": 0.7218679907417435, "learning_rate": 1.9834392021026572e-05, "loss": 0.5539, "num_tokens": 352914681.0, "step": 59065 }, { "epoch": 0.6301942752285747, "grad_norm": 0.7961894679127628, "learning_rate": 1.9830660529192786e-05, "loss": 0.3891, "num_tokens": 352949998.0, "step": 59070 }, { "epoch": 0.6302476182347733, "grad_norm": 1.0453617770784045, "learning_rate": 1.9826929276013097e-05, "loss": 0.5166, "num_tokens": 352983205.0, "step": 59075 }, { "epoch": 0.6303009612409717, "grad_norm": 0.7327578686943566, "learning_rate": 1.9823198261603617e-05, "loss": 0.4741, "num_tokens": 353014622.0, "step": 59080 }, { "epoch": 0.6303543042471702, "grad_norm": 1.10099856598695, "learning_rate": 1.9819467486080416e-05, "loss": 0.4914, "num_tokens": 353045886.0, "step": 59085 }, { "epoch": 0.6304076472533686, "grad_norm": 0.8359530136295876, "learning_rate": 1.9815736949559627e-05, "loss": 0.5272, "num_tokens": 353073366.0, "step": 59090 }, { "epoch": 0.630460990259567, "grad_norm": 2.4801294365047117, "learning_rate": 1.9812006652157323e-05, "loss": 0.5124, "num_tokens": 353097260.0, "step": 59095 }, { "epoch": 0.6305143332657656, "grad_norm": 0.5319488947113864, "learning_rate": 1.980827659398957e-05, "loss": 0.4615, "num_tokens": 353130805.0, "step": 59100 }, { "epoch": 0.630567676271964, "grad_norm": 0.8276249859822115, "learning_rate": 1.9804546775172457e-05, "loss": 0.4137, "num_tokens": 353164224.0, "step": 59105 }, { "epoch": 0.6306210192781624, "grad_norm": 1.1658810384216811, "learning_rate": 1.9800817195822042e-05, "loss": 0.6428, "num_tokens": 353195713.0, "step": 59110 }, { "epoch": 0.6306743622843609, "grad_norm": 0.8147998787787789, "learning_rate": 1.9797087856054375e-05, "loss": 0.4636, "num_tokens": 353227933.0, "step": 59115 }, { "epoch": 0.6307277052905593, "grad_norm": 1.1653059815079314, "learning_rate": 1.979335875598551e-05, "loss": 0.579, "num_tokens": 353251884.0, "step": 59120 }, { "epoch": 0.6307810482967579, "grad_norm": 0.703358821423745, "learning_rate": 1.9789629895731504e-05, "loss": 0.557, "num_tokens": 353300810.0, "step": 59125 }, { "epoch": 0.6308343913029563, "grad_norm": 0.8901233976925298, "learning_rate": 1.978590127540837e-05, "loss": 0.4497, "num_tokens": 353328402.0, "step": 59130 }, { "epoch": 0.6308877343091547, "grad_norm": 0.9136789668005506, "learning_rate": 1.9782172895132135e-05, "loss": 0.5085, "num_tokens": 353354278.0, "step": 59135 }, { "epoch": 0.6309410773153532, "grad_norm": 1.1522293185880754, "learning_rate": 1.9778444755018844e-05, "loss": 0.4169, "num_tokens": 353376908.0, "step": 59140 }, { "epoch": 0.6309944203215516, "grad_norm": 0.8469168302693718, "learning_rate": 1.9774716855184477e-05, "loss": 0.5327, "num_tokens": 353408465.0, "step": 59145 }, { "epoch": 0.6310477633277501, "grad_norm": 1.2285752066129598, "learning_rate": 1.9770989195745053e-05, "loss": 0.4719, "num_tokens": 353430737.0, "step": 59150 }, { "epoch": 0.6311011063339486, "grad_norm": 1.9947633049474742, "learning_rate": 1.9767261776816585e-05, "loss": 0.6168, "num_tokens": 353460033.0, "step": 59155 }, { "epoch": 0.631154449340147, "grad_norm": 1.0937556146978389, "learning_rate": 1.9763534598515033e-05, "loss": 0.58, "num_tokens": 353497480.0, "step": 59160 }, { "epoch": 0.6312077923463455, "grad_norm": 0.8545901665688206, "learning_rate": 1.9759807660956396e-05, "loss": 0.5654, "num_tokens": 353529688.0, "step": 59165 }, { "epoch": 0.6312611353525439, "grad_norm": 1.607456418511495, "learning_rate": 1.975608096425665e-05, "loss": 0.5196, "num_tokens": 353555065.0, "step": 59170 }, { "epoch": 0.6313144783587424, "grad_norm": 1.010139081642031, "learning_rate": 1.975235450853175e-05, "loss": 0.4678, "num_tokens": 353592049.0, "step": 59175 }, { "epoch": 0.6313678213649409, "grad_norm": 0.670783912073137, "learning_rate": 1.974862829389767e-05, "loss": 0.4563, "num_tokens": 353625680.0, "step": 59180 }, { "epoch": 0.6314211643711393, "grad_norm": 0.804111945304895, "learning_rate": 1.974490232047036e-05, "loss": 0.3795, "num_tokens": 353656983.0, "step": 59185 }, { "epoch": 0.6314745073773378, "grad_norm": 1.4808469200703733, "learning_rate": 1.974117658836575e-05, "loss": 0.5645, "num_tokens": 353699312.0, "step": 59190 }, { "epoch": 0.6315278503835362, "grad_norm": 0.8416720529268359, "learning_rate": 1.9737451097699787e-05, "loss": 0.4421, "num_tokens": 353723563.0, "step": 59195 }, { "epoch": 0.6315811933897346, "grad_norm": 1.2363652568178913, "learning_rate": 1.9733725848588414e-05, "loss": 0.3895, "num_tokens": 353737820.0, "step": 59200 }, { "epoch": 0.6316345363959331, "grad_norm": 0.8050108982792605, "learning_rate": 1.9730000841147528e-05, "loss": 0.5283, "num_tokens": 353776423.0, "step": 59205 }, { "epoch": 0.6316878794021316, "grad_norm": 0.546331537870528, "learning_rate": 1.972627607549306e-05, "loss": 0.4742, "num_tokens": 353799778.0, "step": 59210 }, { "epoch": 0.6317412224083301, "grad_norm": 0.8864446454278484, "learning_rate": 1.972255155174092e-05, "loss": 0.365, "num_tokens": 353821767.0, "step": 59215 }, { "epoch": 0.6317945654145285, "grad_norm": 0.8554549152470019, "learning_rate": 1.971882727000699e-05, "loss": 0.5863, "num_tokens": 353854490.0, "step": 59220 }, { "epoch": 0.6318479084207269, "grad_norm": 1.0167710855959597, "learning_rate": 1.9715103230407173e-05, "loss": 0.5199, "num_tokens": 353872611.0, "step": 59225 }, { "epoch": 0.6319012514269254, "grad_norm": 1.0366873126088414, "learning_rate": 1.971137943305736e-05, "loss": 0.5105, "num_tokens": 353901355.0, "step": 59230 }, { "epoch": 0.6319545944331239, "grad_norm": 0.5459537806320962, "learning_rate": 1.970765587807341e-05, "loss": 0.5619, "num_tokens": 353938678.0, "step": 59235 }, { "epoch": 0.6320079374393224, "grad_norm": 1.7734778803489046, "learning_rate": 1.970393256557121e-05, "loss": 0.4885, "num_tokens": 353960963.0, "step": 59240 }, { "epoch": 0.6320612804455208, "grad_norm": 1.0666611659594072, "learning_rate": 1.970020949566662e-05, "loss": 0.5326, "num_tokens": 353996591.0, "step": 59245 }, { "epoch": 0.6321146234517192, "grad_norm": 0.758365278414071, "learning_rate": 1.9696486668475477e-05, "loss": 0.5449, "num_tokens": 354031985.0, "step": 59250 }, { "epoch": 0.6321679664579177, "grad_norm": 0.9239756596784687, "learning_rate": 1.9692764084113652e-05, "loss": 0.4239, "num_tokens": 354053914.0, "step": 59255 }, { "epoch": 0.6322213094641161, "grad_norm": 0.6547652672306521, "learning_rate": 1.9689041742696967e-05, "loss": 0.4874, "num_tokens": 354078198.0, "step": 59260 }, { "epoch": 0.6322746524703147, "grad_norm": 0.890238935530885, "learning_rate": 1.968531964434126e-05, "loss": 0.5556, "num_tokens": 354113646.0, "step": 59265 }, { "epoch": 0.6323279954765131, "grad_norm": 0.907048130200415, "learning_rate": 1.968159778916235e-05, "loss": 0.5188, "num_tokens": 354156838.0, "step": 59270 }, { "epoch": 0.6323813384827115, "grad_norm": 0.967973485550072, "learning_rate": 1.9677876177276062e-05, "loss": 0.5514, "num_tokens": 354198837.0, "step": 59275 }, { "epoch": 0.63243468148891, "grad_norm": 1.074088498794166, "learning_rate": 1.9674154808798195e-05, "loss": 0.4508, "num_tokens": 354221560.0, "step": 59280 }, { "epoch": 0.6324880244951084, "grad_norm": 1.3956653179746956, "learning_rate": 1.967043368384456e-05, "loss": 0.5212, "num_tokens": 354253189.0, "step": 59285 }, { "epoch": 0.6325413675013069, "grad_norm": 1.053464506107488, "learning_rate": 1.9666712802530946e-05, "loss": 0.4418, "num_tokens": 354276148.0, "step": 59290 }, { "epoch": 0.6325947105075054, "grad_norm": 1.1446547003055427, "learning_rate": 1.9662992164973137e-05, "loss": 0.4145, "num_tokens": 354305438.0, "step": 59295 }, { "epoch": 0.6326480535137038, "grad_norm": 0.9210283735490643, "learning_rate": 1.9659271771286915e-05, "loss": 0.3551, "num_tokens": 354328911.0, "step": 59300 }, { "epoch": 0.6327013965199023, "grad_norm": 0.7036270146966433, "learning_rate": 1.9655551621588052e-05, "loss": 0.5314, "num_tokens": 354370092.0, "step": 59305 }, { "epoch": 0.6327547395261007, "grad_norm": 0.6624176434363783, "learning_rate": 1.9651831715992314e-05, "loss": 0.545, "num_tokens": 354406859.0, "step": 59310 }, { "epoch": 0.6328080825322991, "grad_norm": 0.8467310857095676, "learning_rate": 1.9648112054615443e-05, "loss": 0.4818, "num_tokens": 354440173.0, "step": 59315 }, { "epoch": 0.6328614255384977, "grad_norm": 0.7182515673494315, "learning_rate": 1.9644392637573205e-05, "loss": 0.469, "num_tokens": 354458767.0, "step": 59320 }, { "epoch": 0.6329147685446961, "grad_norm": 0.8706292883331578, "learning_rate": 1.9640673464981317e-05, "loss": 0.4576, "num_tokens": 354482714.0, "step": 59325 }, { "epoch": 0.6329681115508946, "grad_norm": 1.0757446379450597, "learning_rate": 1.9636954536955543e-05, "loss": 0.5457, "num_tokens": 354513156.0, "step": 59330 }, { "epoch": 0.633021454557093, "grad_norm": 1.2374833059211872, "learning_rate": 1.963323585361159e-05, "loss": 0.4314, "num_tokens": 354532835.0, "step": 59335 }, { "epoch": 0.6330747975632914, "grad_norm": 0.8320255557594538, "learning_rate": 1.9629517415065174e-05, "loss": 0.5834, "num_tokens": 354557168.0, "step": 59340 }, { "epoch": 0.63312814056949, "grad_norm": 0.688014729296613, "learning_rate": 1.9625799221432012e-05, "loss": 0.4412, "num_tokens": 354606681.0, "step": 59345 }, { "epoch": 0.6331814835756884, "grad_norm": 0.9891189501030792, "learning_rate": 1.962208127282781e-05, "loss": 0.3747, "num_tokens": 354622695.0, "step": 59350 }, { "epoch": 0.6332348265818869, "grad_norm": 1.3161718445450084, "learning_rate": 1.9618363569368246e-05, "loss": 0.4919, "num_tokens": 354661202.0, "step": 59355 }, { "epoch": 0.6332881695880853, "grad_norm": 0.7645573866688229, "learning_rate": 1.961464611116902e-05, "loss": 0.4725, "num_tokens": 354694378.0, "step": 59360 }, { "epoch": 0.6333415125942837, "grad_norm": 0.6977693285398825, "learning_rate": 1.961092889834582e-05, "loss": 0.5535, "num_tokens": 354740933.0, "step": 59365 }, { "epoch": 0.6333948556004823, "grad_norm": 0.7607685825967685, "learning_rate": 1.9607211931014303e-05, "loss": 0.4858, "num_tokens": 354783181.0, "step": 59370 }, { "epoch": 0.6334481986066807, "grad_norm": 1.2393335125529783, "learning_rate": 1.9603495209290128e-05, "loss": 0.4412, "num_tokens": 354798472.0, "step": 59375 }, { "epoch": 0.6335015416128791, "grad_norm": 1.7855034112244679, "learning_rate": 1.9599778733288977e-05, "loss": 0.4715, "num_tokens": 354814863.0, "step": 59380 }, { "epoch": 0.6335548846190776, "grad_norm": 1.313347944345267, "learning_rate": 1.9596062503126478e-05, "loss": 0.4623, "num_tokens": 354837817.0, "step": 59385 }, { "epoch": 0.633608227625276, "grad_norm": 1.2934215775960245, "learning_rate": 1.9592346518918277e-05, "loss": 0.5924, "num_tokens": 354863363.0, "step": 59390 }, { "epoch": 0.6336615706314745, "grad_norm": 1.6618008777640905, "learning_rate": 1.9588630780780015e-05, "loss": 0.4762, "num_tokens": 354890230.0, "step": 59395 }, { "epoch": 0.633714913637673, "grad_norm": 0.6568897120752512, "learning_rate": 1.9584915288827305e-05, "loss": 0.5365, "num_tokens": 354926670.0, "step": 59400 }, { "epoch": 0.6337682566438714, "grad_norm": 0.8939210862869001, "learning_rate": 1.9581200043175778e-05, "loss": 0.4577, "num_tokens": 354954351.0, "step": 59405 }, { "epoch": 0.6338215996500699, "grad_norm": 3.509923124858594, "learning_rate": 1.9577485043941046e-05, "loss": 0.5574, "num_tokens": 354987246.0, "step": 59410 }, { "epoch": 0.6338749426562683, "grad_norm": 1.1218962528020155, "learning_rate": 1.9573770291238693e-05, "loss": 0.5444, "num_tokens": 355011309.0, "step": 59415 }, { "epoch": 0.6339282856624668, "grad_norm": 1.2118377740875512, "learning_rate": 1.9570055785184337e-05, "loss": 0.4845, "num_tokens": 355030447.0, "step": 59420 }, { "epoch": 0.6339816286686653, "grad_norm": 0.7184789924331995, "learning_rate": 1.9566341525893556e-05, "loss": 0.5688, "num_tokens": 355057835.0, "step": 59425 }, { "epoch": 0.6340349716748637, "grad_norm": 0.9301316880960874, "learning_rate": 1.9562627513481925e-05, "loss": 0.4593, "num_tokens": 355083016.0, "step": 59430 }, { "epoch": 0.6340883146810622, "grad_norm": 0.8590854521149094, "learning_rate": 1.9558913748065027e-05, "loss": 0.4393, "num_tokens": 355114445.0, "step": 59435 }, { "epoch": 0.6341416576872606, "grad_norm": 0.7614552588436752, "learning_rate": 1.9555200229758424e-05, "loss": 0.5797, "num_tokens": 355160670.0, "step": 59440 }, { "epoch": 0.6341950006934591, "grad_norm": 0.9781352877684185, "learning_rate": 1.9551486958677662e-05, "loss": 0.4727, "num_tokens": 355181378.0, "step": 59445 }, { "epoch": 0.6342483436996575, "grad_norm": 0.7037781658029376, "learning_rate": 1.9547773934938303e-05, "loss": 0.5595, "num_tokens": 355203675.0, "step": 59450 }, { "epoch": 0.634301686705856, "grad_norm": 1.0840651023847934, "learning_rate": 1.9544061158655886e-05, "loss": 0.4711, "num_tokens": 355220480.0, "step": 59455 }, { "epoch": 0.6343550297120545, "grad_norm": 0.7794409442535737, "learning_rate": 1.9540348629945943e-05, "loss": 0.4842, "num_tokens": 355258532.0, "step": 59460 }, { "epoch": 0.6344083727182529, "grad_norm": 0.8596411257547292, "learning_rate": 1.9536636348923998e-05, "loss": 0.5958, "num_tokens": 355305978.0, "step": 59465 }, { "epoch": 0.6344617157244513, "grad_norm": 0.8414196999116106, "learning_rate": 1.953292431570558e-05, "loss": 0.4368, "num_tokens": 355325493.0, "step": 59470 }, { "epoch": 0.6345150587306498, "grad_norm": 1.00481425062121, "learning_rate": 1.952921253040619e-05, "loss": 0.577, "num_tokens": 355353875.0, "step": 59475 }, { "epoch": 0.6345684017368483, "grad_norm": 0.8191775682566287, "learning_rate": 1.9525500993141328e-05, "loss": 0.4798, "num_tokens": 355391345.0, "step": 59480 }, { "epoch": 0.6346217447430468, "grad_norm": 0.5676216302465756, "learning_rate": 1.9521789704026504e-05, "loss": 0.5688, "num_tokens": 355440235.0, "step": 59485 }, { "epoch": 0.6346750877492452, "grad_norm": 0.7294138681801291, "learning_rate": 1.9518078663177187e-05, "loss": 0.4886, "num_tokens": 355467791.0, "step": 59490 }, { "epoch": 0.6347284307554436, "grad_norm": 0.5571925465859625, "learning_rate": 1.951436787070887e-05, "loss": 0.3763, "num_tokens": 355498739.0, "step": 59495 }, { "epoch": 0.6347817737616421, "grad_norm": 1.8412183128952095, "learning_rate": 1.9510657326737032e-05, "loss": 0.5302, "num_tokens": 355528089.0, "step": 59500 }, { "epoch": 0.6348351167678405, "grad_norm": 1.031133327778037, "learning_rate": 1.9506947031377116e-05, "loss": 0.482, "num_tokens": 355543152.0, "step": 59505 }, { "epoch": 0.6348884597740391, "grad_norm": 1.2928505998250797, "learning_rate": 1.950323698474459e-05, "loss": 0.4911, "num_tokens": 355573078.0, "step": 59510 }, { "epoch": 0.6349418027802375, "grad_norm": 0.6141172246462788, "learning_rate": 1.949952718695491e-05, "loss": 0.4912, "num_tokens": 355612381.0, "step": 59515 }, { "epoch": 0.6349951457864359, "grad_norm": 0.8857967141384535, "learning_rate": 1.9495817638123503e-05, "loss": 0.453, "num_tokens": 355639183.0, "step": 59520 }, { "epoch": 0.6350484887926344, "grad_norm": 0.9620405132557924, "learning_rate": 1.949210833836581e-05, "loss": 0.5071, "num_tokens": 355672137.0, "step": 59525 }, { "epoch": 0.6351018317988328, "grad_norm": 1.063942557011769, "learning_rate": 1.948839928779726e-05, "loss": 0.5216, "num_tokens": 355718567.0, "step": 59530 }, { "epoch": 0.6351551748050314, "grad_norm": 0.8996125157747263, "learning_rate": 1.9484690486533275e-05, "loss": 0.4713, "num_tokens": 355753390.0, "step": 59535 }, { "epoch": 0.6352085178112298, "grad_norm": 0.8622005898642402, "learning_rate": 1.948098193468924e-05, "loss": 0.3897, "num_tokens": 355783392.0, "step": 59540 }, { "epoch": 0.6352618608174282, "grad_norm": 1.1257584555551268, "learning_rate": 1.94772736323806e-05, "loss": 0.6408, "num_tokens": 355805095.0, "step": 59545 }, { "epoch": 0.6353152038236267, "grad_norm": 1.0471653357773785, "learning_rate": 1.947356557972271e-05, "loss": 0.4848, "num_tokens": 355829793.0, "step": 59550 }, { "epoch": 0.6353685468298251, "grad_norm": 1.1617546908604206, "learning_rate": 1.9469857776830976e-05, "loss": 0.4742, "num_tokens": 355849905.0, "step": 59555 }, { "epoch": 0.6354218898360235, "grad_norm": 0.6134127686952059, "learning_rate": 1.9466150223820772e-05, "loss": 0.4631, "num_tokens": 355885991.0, "step": 59560 }, { "epoch": 0.6354752328422221, "grad_norm": 0.6816098431976749, "learning_rate": 1.946244292080747e-05, "loss": 0.4432, "num_tokens": 355916967.0, "step": 59565 }, { "epoch": 0.6355285758484205, "grad_norm": 1.0077942816540062, "learning_rate": 1.9458735867906437e-05, "loss": 0.5066, "num_tokens": 355956219.0, "step": 59570 }, { "epoch": 0.635581918854619, "grad_norm": 1.3000811452485783, "learning_rate": 1.9455029065233028e-05, "loss": 0.5051, "num_tokens": 355979777.0, "step": 59575 }, { "epoch": 0.6356352618608174, "grad_norm": 0.7042108643512909, "learning_rate": 1.945132251290258e-05, "loss": 0.4172, "num_tokens": 356029317.0, "step": 59580 }, { "epoch": 0.6356886048670158, "grad_norm": 0.686169627020449, "learning_rate": 1.9447616211030456e-05, "loss": 0.455, "num_tokens": 356068630.0, "step": 59585 }, { "epoch": 0.6357419478732144, "grad_norm": 1.0179609247835313, "learning_rate": 1.944391015973197e-05, "loss": 0.5562, "num_tokens": 356112710.0, "step": 59590 }, { "epoch": 0.6357952908794128, "grad_norm": 1.734222639696425, "learning_rate": 1.944020435912245e-05, "loss": 0.5661, "num_tokens": 356134163.0, "step": 59595 }, { "epoch": 0.6358486338856113, "grad_norm": 0.9147813897483539, "learning_rate": 1.9436498809317217e-05, "loss": 0.4985, "num_tokens": 356171935.0, "step": 59600 }, { "epoch": 0.6359019768918097, "grad_norm": 3.624905024332164, "learning_rate": 1.943279351043158e-05, "loss": 0.617, "num_tokens": 356195342.0, "step": 59605 }, { "epoch": 0.6359553198980081, "grad_norm": 1.074645829791318, "learning_rate": 1.9429088462580834e-05, "loss": 0.4383, "num_tokens": 356216250.0, "step": 59610 }, { "epoch": 0.6360086629042067, "grad_norm": 0.7655923151576076, "learning_rate": 1.9425383665880276e-05, "loss": 0.6287, "num_tokens": 356254352.0, "step": 59615 }, { "epoch": 0.6360620059104051, "grad_norm": 1.0750811804702867, "learning_rate": 1.9421679120445202e-05, "loss": 0.459, "num_tokens": 356289888.0, "step": 59620 }, { "epoch": 0.6361153489166036, "grad_norm": 0.7202627613682452, "learning_rate": 1.9417974826390878e-05, "loss": 0.5278, "num_tokens": 356322077.0, "step": 59625 }, { "epoch": 0.636168691922802, "grad_norm": 0.8819930958310749, "learning_rate": 1.9414270783832566e-05, "loss": 0.4355, "num_tokens": 356353404.0, "step": 59630 }, { "epoch": 0.6362220349290004, "grad_norm": 0.8207469212348055, "learning_rate": 1.941056699288555e-05, "loss": 0.5113, "num_tokens": 356377527.0, "step": 59635 }, { "epoch": 0.636275377935199, "grad_norm": 0.9796169698017326, "learning_rate": 1.940686345366507e-05, "loss": 0.4637, "num_tokens": 356399967.0, "step": 59640 }, { "epoch": 0.6363287209413974, "grad_norm": 0.672806690599217, "learning_rate": 1.9403160166286365e-05, "loss": 0.4318, "num_tokens": 356425502.0, "step": 59645 }, { "epoch": 0.6363820639475958, "grad_norm": 0.7608944693012735, "learning_rate": 1.9399457130864702e-05, "loss": 0.4829, "num_tokens": 356453272.0, "step": 59650 }, { "epoch": 0.6364354069537943, "grad_norm": 0.969470290023077, "learning_rate": 1.9395754347515276e-05, "loss": 0.6164, "num_tokens": 356486168.0, "step": 59655 }, { "epoch": 0.6364887499599927, "grad_norm": 1.0401789526449343, "learning_rate": 1.939205181635334e-05, "loss": 0.6602, "num_tokens": 356518227.0, "step": 59660 }, { "epoch": 0.6365420929661912, "grad_norm": 0.686419053500125, "learning_rate": 1.9388349537494104e-05, "loss": 0.3818, "num_tokens": 356548186.0, "step": 59665 }, { "epoch": 0.6365954359723897, "grad_norm": 0.9642873070276468, "learning_rate": 1.9384647511052757e-05, "loss": 0.5017, "num_tokens": 356578076.0, "step": 59670 }, { "epoch": 0.6366487789785881, "grad_norm": 0.933669529022143, "learning_rate": 1.9380945737144513e-05, "loss": 0.4451, "num_tokens": 356624474.0, "step": 59675 }, { "epoch": 0.6367021219847866, "grad_norm": 0.7006352796101828, "learning_rate": 1.9377244215884566e-05, "loss": 0.5386, "num_tokens": 356649255.0, "step": 59680 }, { "epoch": 0.636755464990985, "grad_norm": 0.9948462586830646, "learning_rate": 1.9373542947388078e-05, "loss": 0.4429, "num_tokens": 356665043.0, "step": 59685 }, { "epoch": 0.6368088079971835, "grad_norm": 1.430836486677778, "learning_rate": 1.936984193177025e-05, "loss": 0.5419, "num_tokens": 356689523.0, "step": 59690 }, { "epoch": 0.636862151003382, "grad_norm": 1.0495875273113664, "learning_rate": 1.9366141169146252e-05, "loss": 0.6634, "num_tokens": 356723371.0, "step": 59695 }, { "epoch": 0.6369154940095804, "grad_norm": 1.0990995052465278, "learning_rate": 1.936244065963122e-05, "loss": 0.5564, "num_tokens": 356748990.0, "step": 59700 }, { "epoch": 0.6369688370157789, "grad_norm": 1.979381978751482, "learning_rate": 1.935874040334032e-05, "loss": 0.533, "num_tokens": 356772399.0, "step": 59705 }, { "epoch": 0.6370221800219773, "grad_norm": 0.7529911767717479, "learning_rate": 1.9355040400388706e-05, "loss": 0.4814, "num_tokens": 356803358.0, "step": 59710 }, { "epoch": 0.6370755230281758, "grad_norm": 0.8584784451943375, "learning_rate": 1.9351340650891496e-05, "loss": 0.5162, "num_tokens": 356829447.0, "step": 59715 }, { "epoch": 0.6371288660343742, "grad_norm": 1.2536591833250916, "learning_rate": 1.934764115496383e-05, "loss": 0.5078, "num_tokens": 356845371.0, "step": 59720 }, { "epoch": 0.6371822090405727, "grad_norm": 0.720907241474812, "learning_rate": 1.9343941912720832e-05, "loss": 0.5095, "num_tokens": 356866502.0, "step": 59725 }, { "epoch": 0.6372355520467712, "grad_norm": 1.4023435568388658, "learning_rate": 1.9340242924277602e-05, "loss": 0.4514, "num_tokens": 356886502.0, "step": 59730 }, { "epoch": 0.6372888950529696, "grad_norm": 1.7285955905070132, "learning_rate": 1.9336544189749245e-05, "loss": 0.614, "num_tokens": 356912293.0, "step": 59735 }, { "epoch": 0.637342238059168, "grad_norm": 1.3486394451704249, "learning_rate": 1.933284570925088e-05, "loss": 0.3992, "num_tokens": 356928252.0, "step": 59740 }, { "epoch": 0.6373955810653665, "grad_norm": 1.1534646446110324, "learning_rate": 1.9329147482897565e-05, "loss": 0.4831, "num_tokens": 356948958.0, "step": 59745 }, { "epoch": 0.637448924071565, "grad_norm": 1.2692692132302876, "learning_rate": 1.9325449510804405e-05, "loss": 0.5735, "num_tokens": 356982947.0, "step": 59750 }, { "epoch": 0.6375022670777635, "grad_norm": 1.0886238670179602, "learning_rate": 1.9321751793086467e-05, "loss": 0.4679, "num_tokens": 357007985.0, "step": 59755 }, { "epoch": 0.6375556100839619, "grad_norm": 1.4016559118858112, "learning_rate": 1.931805432985881e-05, "loss": 0.5342, "num_tokens": 357029839.0, "step": 59760 }, { "epoch": 0.6376089530901603, "grad_norm": 0.7598604471110054, "learning_rate": 1.9314357121236498e-05, "loss": 0.4136, "num_tokens": 357051846.0, "step": 59765 }, { "epoch": 0.6376622960963588, "grad_norm": 1.3339032672269606, "learning_rate": 1.9310660167334583e-05, "loss": 0.4862, "num_tokens": 357089947.0, "step": 59770 }, { "epoch": 0.6377156391025572, "grad_norm": 0.5877722590519552, "learning_rate": 1.9306963468268093e-05, "loss": 0.4477, "num_tokens": 357113964.0, "step": 59775 }, { "epoch": 0.6377689821087558, "grad_norm": 0.9561636438214338, "learning_rate": 1.9303267024152072e-05, "loss": 0.4664, "num_tokens": 357141074.0, "step": 59780 }, { "epoch": 0.6378223251149542, "grad_norm": 0.7446022656925284, "learning_rate": 1.9299570835101555e-05, "loss": 0.5829, "num_tokens": 357178890.0, "step": 59785 }, { "epoch": 0.6378756681211526, "grad_norm": 0.864597025680618, "learning_rate": 1.9295874901231538e-05, "loss": 0.5511, "num_tokens": 357219185.0, "step": 59790 }, { "epoch": 0.6379290111273511, "grad_norm": 1.0151674222319234, "learning_rate": 1.9292179222657048e-05, "loss": 0.6333, "num_tokens": 357244521.0, "step": 59795 }, { "epoch": 0.6379823541335495, "grad_norm": 1.5017833911056597, "learning_rate": 1.9288483799493084e-05, "loss": 0.546, "num_tokens": 357274923.0, "step": 59800 }, { "epoch": 0.6380356971397481, "grad_norm": 1.2578451989853126, "learning_rate": 1.9284788631854635e-05, "loss": 0.6, "num_tokens": 357320384.0, "step": 59805 }, { "epoch": 0.6380890401459465, "grad_norm": 0.9257194006521989, "learning_rate": 1.928109371985668e-05, "loss": 0.5433, "num_tokens": 357335998.0, "step": 59810 }, { "epoch": 0.6381423831521449, "grad_norm": 1.5943671713259246, "learning_rate": 1.927739906361422e-05, "loss": 0.5815, "num_tokens": 357367211.0, "step": 59815 }, { "epoch": 0.6381957261583434, "grad_norm": 1.181723780688807, "learning_rate": 1.9273704663242203e-05, "loss": 0.5455, "num_tokens": 357395502.0, "step": 59820 }, { "epoch": 0.6382490691645418, "grad_norm": 0.9743569703146133, "learning_rate": 1.9270010518855596e-05, "loss": 0.5035, "num_tokens": 357435114.0, "step": 59825 }, { "epoch": 0.6383024121707402, "grad_norm": 0.9432978683053288, "learning_rate": 1.926631663056937e-05, "loss": 0.6013, "num_tokens": 357474384.0, "step": 59830 }, { "epoch": 0.6383557551769388, "grad_norm": 1.0485821829020943, "learning_rate": 1.9262622998498448e-05, "loss": 0.6025, "num_tokens": 357510733.0, "step": 59835 }, { "epoch": 0.6384090981831372, "grad_norm": 0.7880367129012906, "learning_rate": 1.925892962275778e-05, "loss": 0.5517, "num_tokens": 357548627.0, "step": 59840 }, { "epoch": 0.6384624411893357, "grad_norm": 1.2843138569407515, "learning_rate": 1.9255236503462303e-05, "loss": 0.4038, "num_tokens": 357562977.0, "step": 59845 }, { "epoch": 0.6385157841955341, "grad_norm": 1.30839003358303, "learning_rate": 1.9251543640726917e-05, "loss": 0.5675, "num_tokens": 357586204.0, "step": 59850 }, { "epoch": 0.6385691272017325, "grad_norm": 1.540735662568076, "learning_rate": 1.924785103466656e-05, "loss": 0.4434, "num_tokens": 357615824.0, "step": 59855 }, { "epoch": 0.6386224702079311, "grad_norm": 1.0760184108800623, "learning_rate": 1.9244158685396123e-05, "loss": 0.5153, "num_tokens": 357652407.0, "step": 59860 }, { "epoch": 0.6386758132141295, "grad_norm": 0.718634559639301, "learning_rate": 1.9240466593030514e-05, "loss": 0.5747, "num_tokens": 357685128.0, "step": 59865 }, { "epoch": 0.638729156220328, "grad_norm": 0.6772199725347416, "learning_rate": 1.9236774757684613e-05, "loss": 0.4499, "num_tokens": 357710965.0, "step": 59870 }, { "epoch": 0.6387824992265264, "grad_norm": 0.6024243098663786, "learning_rate": 1.9233083179473316e-05, "loss": 0.4937, "num_tokens": 357749268.0, "step": 59875 }, { "epoch": 0.6388358422327248, "grad_norm": 1.4944920949503568, "learning_rate": 1.9229391858511485e-05, "loss": 0.5453, "num_tokens": 357783224.0, "step": 59880 }, { "epoch": 0.6388891852389234, "grad_norm": 0.8555450753081846, "learning_rate": 1.9225700794913988e-05, "loss": 0.4277, "num_tokens": 357811022.0, "step": 59885 }, { "epoch": 0.6389425282451218, "grad_norm": 0.9535376721796764, "learning_rate": 1.9222009988795686e-05, "loss": 0.5145, "num_tokens": 357830655.0, "step": 59890 }, { "epoch": 0.6389958712513203, "grad_norm": 1.0475450291424468, "learning_rate": 1.9218319440271443e-05, "loss": 0.4755, "num_tokens": 357861143.0, "step": 59895 }, { "epoch": 0.6390492142575187, "grad_norm": 1.3401761297476629, "learning_rate": 1.921462914945607e-05, "loss": 0.5474, "num_tokens": 357885584.0, "step": 59900 }, { "epoch": 0.6391025572637171, "grad_norm": 0.6697619497121649, "learning_rate": 1.9210939116464427e-05, "loss": 0.5154, "num_tokens": 357928855.0, "step": 59905 }, { "epoch": 0.6391559002699156, "grad_norm": 0.7315503092426894, "learning_rate": 1.9207249341411336e-05, "loss": 0.4601, "num_tokens": 357962232.0, "step": 59910 }, { "epoch": 0.6392092432761141, "grad_norm": 0.8599852061511735, "learning_rate": 1.9203559824411616e-05, "loss": 0.4644, "num_tokens": 357996195.0, "step": 59915 }, { "epoch": 0.6392625862823125, "grad_norm": 0.9201364376270801, "learning_rate": 1.9199870565580057e-05, "loss": 0.5662, "num_tokens": 358020766.0, "step": 59920 }, { "epoch": 0.639315929288511, "grad_norm": 1.1141298827786366, "learning_rate": 1.919618156503149e-05, "loss": 0.4253, "num_tokens": 358044740.0, "step": 59925 }, { "epoch": 0.6393692722947094, "grad_norm": 1.727234448678568, "learning_rate": 1.91924928228807e-05, "loss": 0.4975, "num_tokens": 358061234.0, "step": 59930 }, { "epoch": 0.6394226153009079, "grad_norm": 1.2364801446919313, "learning_rate": 1.918880433924245e-05, "loss": 0.6428, "num_tokens": 358097581.0, "step": 59935 }, { "epoch": 0.6394759583071064, "grad_norm": 0.7049380342990238, "learning_rate": 1.9185116114231555e-05, "loss": 0.4239, "num_tokens": 358121673.0, "step": 59940 }, { "epoch": 0.6395293013133048, "grad_norm": 0.9512592086128965, "learning_rate": 1.9181428147962753e-05, "loss": 0.4909, "num_tokens": 358134862.0, "step": 59945 }, { "epoch": 0.6395826443195033, "grad_norm": 0.824637057229578, "learning_rate": 1.9177740440550835e-05, "loss": 0.4867, "num_tokens": 358164437.0, "step": 59950 }, { "epoch": 0.6396359873257017, "grad_norm": 1.0843179430403542, "learning_rate": 1.9174052992110537e-05, "loss": 0.498, "num_tokens": 358194661.0, "step": 59955 }, { "epoch": 0.6396893303319002, "grad_norm": 1.1666539292260811, "learning_rate": 1.91703658027566e-05, "loss": 0.4949, "num_tokens": 358216195.0, "step": 59960 }, { "epoch": 0.6397426733380986, "grad_norm": 0.557229985107147, "learning_rate": 1.9166678872603778e-05, "loss": 0.5021, "num_tokens": 358249258.0, "step": 59965 }, { "epoch": 0.6397960163442971, "grad_norm": 1.0983889509746603, "learning_rate": 1.9162992201766793e-05, "loss": 0.5577, "num_tokens": 358284249.0, "step": 59970 }, { "epoch": 0.6398493593504956, "grad_norm": 1.5142235177675532, "learning_rate": 1.9159305790360353e-05, "loss": 0.6167, "num_tokens": 358319044.0, "step": 59975 }, { "epoch": 0.639902702356694, "grad_norm": 1.528804351635955, "learning_rate": 1.915561963849919e-05, "loss": 0.4377, "num_tokens": 358347624.0, "step": 59980 }, { "epoch": 0.6399560453628925, "grad_norm": 1.3248596393410086, "learning_rate": 1.915193374629801e-05, "loss": 0.565, "num_tokens": 358373881.0, "step": 59985 }, { "epoch": 0.6400093883690909, "grad_norm": 0.9618130614031241, "learning_rate": 1.9148248113871503e-05, "loss": 0.4727, "num_tokens": 358412216.0, "step": 59990 }, { "epoch": 0.6400627313752894, "grad_norm": 0.8020562973987622, "learning_rate": 1.9144562741334354e-05, "loss": 0.4931, "num_tokens": 358443335.0, "step": 59995 }, { "epoch": 0.6401160743814879, "grad_norm": 1.0390889014893747, "learning_rate": 1.9140877628801256e-05, "loss": 0.6298, "num_tokens": 358490723.0, "step": 60000 }, { "epoch": 0.6401694173876863, "grad_norm": 1.0976680592838313, "learning_rate": 1.9137192776386874e-05, "loss": 0.4332, "num_tokens": 358525566.0, "step": 60005 }, { "epoch": 0.6402227603938847, "grad_norm": 1.3418987006518428, "learning_rate": 1.9133508184205872e-05, "loss": 0.5744, "num_tokens": 358565152.0, "step": 60010 }, { "epoch": 0.6402761034000832, "grad_norm": 0.9584024565694242, "learning_rate": 1.9129823852372918e-05, "loss": 0.5797, "num_tokens": 358595730.0, "step": 60015 }, { "epoch": 0.6403294464062816, "grad_norm": 0.782412445147411, "learning_rate": 1.912613978100265e-05, "loss": 0.5999, "num_tokens": 358623866.0, "step": 60020 }, { "epoch": 0.6403827894124802, "grad_norm": 1.105634308457003, "learning_rate": 1.91224559702097e-05, "loss": 0.5535, "num_tokens": 358637809.0, "step": 60025 }, { "epoch": 0.6404361324186786, "grad_norm": 0.9481352321468137, "learning_rate": 1.9118772420108732e-05, "loss": 0.5125, "num_tokens": 358667133.0, "step": 60030 }, { "epoch": 0.640489475424877, "grad_norm": 1.1016153839929443, "learning_rate": 1.9115089130814334e-05, "loss": 0.5059, "num_tokens": 358680829.0, "step": 60035 }, { "epoch": 0.6405428184310755, "grad_norm": 0.7577075410682229, "learning_rate": 1.911140610244115e-05, "loss": 0.5653, "num_tokens": 358698819.0, "step": 60040 }, { "epoch": 0.6405961614372739, "grad_norm": 1.8150734429579753, "learning_rate": 1.910772333510377e-05, "loss": 0.5133, "num_tokens": 358712638.0, "step": 60045 }, { "epoch": 0.6406495044434725, "grad_norm": 0.6644920183431474, "learning_rate": 1.9104040828916808e-05, "loss": 0.498, "num_tokens": 358751490.0, "step": 60050 }, { "epoch": 0.6407028474496709, "grad_norm": 1.0735410281271873, "learning_rate": 1.9100358583994844e-05, "loss": 0.4748, "num_tokens": 358776562.0, "step": 60055 }, { "epoch": 0.6407561904558693, "grad_norm": 1.4135831142974875, "learning_rate": 1.909667660045248e-05, "loss": 0.5309, "num_tokens": 358806635.0, "step": 60060 }, { "epoch": 0.6408095334620678, "grad_norm": 1.056717720004997, "learning_rate": 1.9092994878404258e-05, "loss": 0.4719, "num_tokens": 358841920.0, "step": 60065 }, { "epoch": 0.6408628764682662, "grad_norm": 1.710910445092928, "learning_rate": 1.908931341796478e-05, "loss": 0.4483, "num_tokens": 358858800.0, "step": 60070 }, { "epoch": 0.6409162194744648, "grad_norm": 1.0284253199006081, "learning_rate": 1.9085632219248593e-05, "loss": 0.4751, "num_tokens": 358897157.0, "step": 60075 }, { "epoch": 0.6409695624806632, "grad_norm": 1.9632285406771235, "learning_rate": 1.908195128237024e-05, "loss": 0.5538, "num_tokens": 358909989.0, "step": 60080 }, { "epoch": 0.6410229054868616, "grad_norm": 1.2792844431701775, "learning_rate": 1.9078270607444275e-05, "loss": 0.5677, "num_tokens": 358942165.0, "step": 60085 }, { "epoch": 0.6410762484930601, "grad_norm": 0.8980213944675678, "learning_rate": 1.9074590194585235e-05, "loss": 0.7131, "num_tokens": 358993305.0, "step": 60090 }, { "epoch": 0.6411295914992585, "grad_norm": 0.6908543133314277, "learning_rate": 1.907091004390764e-05, "loss": 0.4874, "num_tokens": 359022061.0, "step": 60095 }, { "epoch": 0.6411829345054569, "grad_norm": 0.844957947659122, "learning_rate": 1.9067230155526004e-05, "loss": 0.4473, "num_tokens": 359040720.0, "step": 60100 }, { "epoch": 0.6412362775116555, "grad_norm": 0.9373576587974157, "learning_rate": 1.906355052955486e-05, "loss": 0.4917, "num_tokens": 359079571.0, "step": 60105 }, { "epoch": 0.6412896205178539, "grad_norm": 0.8590955149383892, "learning_rate": 1.9059871166108678e-05, "loss": 0.4255, "num_tokens": 359104011.0, "step": 60110 }, { "epoch": 0.6413429635240524, "grad_norm": 0.9651460489905523, "learning_rate": 1.9056192065301975e-05, "loss": 0.5215, "num_tokens": 359136699.0, "step": 60115 }, { "epoch": 0.6413963065302508, "grad_norm": 0.848577298649639, "learning_rate": 1.9052513227249236e-05, "loss": 0.3619, "num_tokens": 359159275.0, "step": 60120 }, { "epoch": 0.6414496495364492, "grad_norm": 1.3846024280196803, "learning_rate": 1.9048834652064922e-05, "loss": 0.6298, "num_tokens": 359191809.0, "step": 60125 }, { "epoch": 0.6415029925426478, "grad_norm": 0.7922791316782614, "learning_rate": 1.9045156339863525e-05, "loss": 0.5014, "num_tokens": 359224343.0, "step": 60130 }, { "epoch": 0.6415563355488462, "grad_norm": 0.5848605595161624, "learning_rate": 1.9041478290759496e-05, "loss": 0.5821, "num_tokens": 359263038.0, "step": 60135 }, { "epoch": 0.6416096785550447, "grad_norm": 0.8013474306140753, "learning_rate": 1.9037800504867276e-05, "loss": 0.5364, "num_tokens": 359298572.0, "step": 60140 }, { "epoch": 0.6416630215612431, "grad_norm": 0.6651773354247067, "learning_rate": 1.903412298230133e-05, "loss": 0.4892, "num_tokens": 359342994.0, "step": 60145 }, { "epoch": 0.6417163645674415, "grad_norm": 0.8938917552178711, "learning_rate": 1.9030445723176093e-05, "loss": 0.4037, "num_tokens": 359361778.0, "step": 60150 }, { "epoch": 0.64176970757364, "grad_norm": 1.2293838973537394, "learning_rate": 1.9026768727605982e-05, "loss": 0.7753, "num_tokens": 359416571.0, "step": 60155 }, { "epoch": 0.6418230505798385, "grad_norm": 0.7765628462059342, "learning_rate": 1.9023091995705423e-05, "loss": 0.4724, "num_tokens": 359437581.0, "step": 60160 }, { "epoch": 0.641876393586037, "grad_norm": 1.0397675737538445, "learning_rate": 1.9019415527588834e-05, "loss": 0.4471, "num_tokens": 359459305.0, "step": 60165 }, { "epoch": 0.6419297365922354, "grad_norm": 0.9730415756939327, "learning_rate": 1.9015739323370608e-05, "loss": 0.5053, "num_tokens": 359482147.0, "step": 60170 }, { "epoch": 0.6419830795984338, "grad_norm": 1.2083859272318822, "learning_rate": 1.9012063383165145e-05, "loss": 0.4817, "num_tokens": 359508634.0, "step": 60175 }, { "epoch": 0.6420364226046323, "grad_norm": 0.8802250540109041, "learning_rate": 1.900838770708685e-05, "loss": 0.4899, "num_tokens": 359544852.0, "step": 60180 }, { "epoch": 0.6420897656108308, "grad_norm": 0.8699374025367892, "learning_rate": 1.9004712295250075e-05, "loss": 0.5434, "num_tokens": 359583758.0, "step": 60185 }, { "epoch": 0.6421431086170292, "grad_norm": 0.5480631383296748, "learning_rate": 1.90010371477692e-05, "loss": 0.8045, "num_tokens": 359625536.0, "step": 60190 }, { "epoch": 0.6421964516232277, "grad_norm": 0.6878004264263077, "learning_rate": 1.8997362264758604e-05, "loss": 0.4409, "num_tokens": 359662959.0, "step": 60195 }, { "epoch": 0.6422497946294261, "grad_norm": 0.6856947190065669, "learning_rate": 1.899368764633262e-05, "loss": 0.4634, "num_tokens": 359691715.0, "step": 60200 }, { "epoch": 0.6423031376356246, "grad_norm": 0.8593047174101233, "learning_rate": 1.899001329260561e-05, "loss": 0.4385, "num_tokens": 359720707.0, "step": 60205 }, { "epoch": 0.642356480641823, "grad_norm": 0.5798621031551745, "learning_rate": 1.8986339203691906e-05, "loss": 0.4332, "num_tokens": 359765489.0, "step": 60210 }, { "epoch": 0.6424098236480215, "grad_norm": 0.6834988128228913, "learning_rate": 1.8982665379705827e-05, "loss": 0.6085, "num_tokens": 359785129.0, "step": 60215 }, { "epoch": 0.64246316665422, "grad_norm": 0.7397957883089812, "learning_rate": 1.8978991820761717e-05, "loss": 0.4204, "num_tokens": 359811678.0, "step": 60220 }, { "epoch": 0.6425165096604184, "grad_norm": 0.7693201165954506, "learning_rate": 1.8975318526973885e-05, "loss": 0.5313, "num_tokens": 359854992.0, "step": 60225 }, { "epoch": 0.6425698526666169, "grad_norm": 0.7967955162697649, "learning_rate": 1.8971645498456615e-05, "loss": 0.3914, "num_tokens": 359880463.0, "step": 60230 }, { "epoch": 0.6426231956728153, "grad_norm": 0.6883394478010872, "learning_rate": 1.8967972735324218e-05, "loss": 0.4437, "num_tokens": 359908147.0, "step": 60235 }, { "epoch": 0.6426765386790138, "grad_norm": 0.606278046293547, "learning_rate": 1.8964300237691e-05, "loss": 0.5007, "num_tokens": 359939876.0, "step": 60240 }, { "epoch": 0.6427298816852123, "grad_norm": 1.304765821351131, "learning_rate": 1.896062800567122e-05, "loss": 0.4794, "num_tokens": 359972476.0, "step": 60245 }, { "epoch": 0.6427832246914107, "grad_norm": 0.7830637421579271, "learning_rate": 1.895695603937915e-05, "loss": 0.4712, "num_tokens": 359998944.0, "step": 60250 }, { "epoch": 0.6428365676976092, "grad_norm": 0.9506473567083903, "learning_rate": 1.8953284338929073e-05, "loss": 0.4704, "num_tokens": 360022484.0, "step": 60255 }, { "epoch": 0.6428899107038076, "grad_norm": 0.8596325555555672, "learning_rate": 1.894961290443522e-05, "loss": 0.4061, "num_tokens": 360046315.0, "step": 60260 }, { "epoch": 0.642943253710006, "grad_norm": 0.5805674918421356, "learning_rate": 1.8945941736011847e-05, "loss": 0.5527, "num_tokens": 360076982.0, "step": 60265 }, { "epoch": 0.6429965967162046, "grad_norm": 0.7778145743247972, "learning_rate": 1.8942270833773213e-05, "loss": 0.4499, "num_tokens": 360110011.0, "step": 60270 }, { "epoch": 0.643049939722403, "grad_norm": 0.8869597799786421, "learning_rate": 1.893860019783352e-05, "loss": 0.5929, "num_tokens": 360143561.0, "step": 60275 }, { "epoch": 0.6431032827286014, "grad_norm": 0.9832566684846565, "learning_rate": 1.8934929828307004e-05, "loss": 0.4205, "num_tokens": 360162024.0, "step": 60280 }, { "epoch": 0.6431566257347999, "grad_norm": 1.4709726776361758, "learning_rate": 1.8931259725307886e-05, "loss": 0.4924, "num_tokens": 360178396.0, "step": 60285 }, { "epoch": 0.6432099687409983, "grad_norm": 0.7481087223579685, "learning_rate": 1.8927589888950353e-05, "loss": 0.4413, "num_tokens": 360218175.0, "step": 60290 }, { "epoch": 0.6432633117471969, "grad_norm": 0.5447496904856642, "learning_rate": 1.892392031934862e-05, "loss": 0.4402, "num_tokens": 360253147.0, "step": 60295 }, { "epoch": 0.6433166547533953, "grad_norm": 0.7895508888611058, "learning_rate": 1.892025101661688e-05, "loss": 0.6132, "num_tokens": 360289052.0, "step": 60300 }, { "epoch": 0.6433699977595937, "grad_norm": 1.1303696743573155, "learning_rate": 1.8916581980869292e-05, "loss": 0.597, "num_tokens": 360310863.0, "step": 60305 }, { "epoch": 0.6434233407657922, "grad_norm": 1.1046332652089654, "learning_rate": 1.8912913212220045e-05, "loss": 0.407, "num_tokens": 360332815.0, "step": 60310 }, { "epoch": 0.6434766837719906, "grad_norm": 0.7135500350458955, "learning_rate": 1.8909244710783302e-05, "loss": 0.3824, "num_tokens": 360358967.0, "step": 60315 }, { "epoch": 0.6435300267781892, "grad_norm": 1.7922096170990922, "learning_rate": 1.890557647667322e-05, "loss": 0.5354, "num_tokens": 360390133.0, "step": 60320 }, { "epoch": 0.6435833697843876, "grad_norm": 0.8053519147014756, "learning_rate": 1.8901908510003936e-05, "loss": 0.4826, "num_tokens": 360425842.0, "step": 60325 }, { "epoch": 0.643636712790586, "grad_norm": 0.8013652564327822, "learning_rate": 1.8898240810889612e-05, "loss": 0.4349, "num_tokens": 360448673.0, "step": 60330 }, { "epoch": 0.6436900557967845, "grad_norm": 0.9170535356091216, "learning_rate": 1.8894573379444356e-05, "loss": 0.6576, "num_tokens": 360473574.0, "step": 60335 }, { "epoch": 0.6437433988029829, "grad_norm": 0.5938588970821934, "learning_rate": 1.88909062157823e-05, "loss": 0.47, "num_tokens": 360511499.0, "step": 60340 }, { "epoch": 0.6437967418091814, "grad_norm": 1.3331115917105196, "learning_rate": 1.8887239320017563e-05, "loss": 0.5707, "num_tokens": 360548697.0, "step": 60345 }, { "epoch": 0.6438500848153799, "grad_norm": 2.807422208419328, "learning_rate": 1.888357269226425e-05, "loss": 0.5934, "num_tokens": 360583542.0, "step": 60350 }, { "epoch": 0.6439034278215783, "grad_norm": 0.8657202822588099, "learning_rate": 1.8879906332636444e-05, "loss": 0.4643, "num_tokens": 360625402.0, "step": 60355 }, { "epoch": 0.6439567708277768, "grad_norm": 0.6835556474752519, "learning_rate": 1.887624024124826e-05, "loss": 0.4809, "num_tokens": 360649737.0, "step": 60360 }, { "epoch": 0.6440101138339752, "grad_norm": 0.9018517228928816, "learning_rate": 1.8872574418213758e-05, "loss": 0.375, "num_tokens": 360688917.0, "step": 60365 }, { "epoch": 0.6440634568401736, "grad_norm": 1.2902745928086605, "learning_rate": 1.886890886364702e-05, "loss": 0.5099, "num_tokens": 360709317.0, "step": 60370 }, { "epoch": 0.6441167998463722, "grad_norm": 1.5466942875962, "learning_rate": 1.8865243577662116e-05, "loss": 0.5309, "num_tokens": 360734110.0, "step": 60375 }, { "epoch": 0.6441701428525706, "grad_norm": 0.8540122881970067, "learning_rate": 1.886157856037309e-05, "loss": 0.5267, "num_tokens": 360779267.0, "step": 60380 }, { "epoch": 0.6442234858587691, "grad_norm": 1.484436674260309, "learning_rate": 1.8857913811893996e-05, "loss": 0.5367, "num_tokens": 360800226.0, "step": 60385 }, { "epoch": 0.6442768288649675, "grad_norm": 0.9454239518976165, "learning_rate": 1.8854249332338876e-05, "loss": 0.4896, "num_tokens": 360836953.0, "step": 60390 }, { "epoch": 0.6443301718711659, "grad_norm": 0.8144428804173024, "learning_rate": 1.8850585121821747e-05, "loss": 0.4647, "num_tokens": 360856447.0, "step": 60395 }, { "epoch": 0.6443835148773644, "grad_norm": 1.1797959897405303, "learning_rate": 1.8846921180456644e-05, "loss": 0.4762, "num_tokens": 360872400.0, "step": 60400 }, { "epoch": 0.6444368578835629, "grad_norm": 0.9866656845721558, "learning_rate": 1.8843257508357593e-05, "loss": 0.4294, "num_tokens": 360897385.0, "step": 60405 }, { "epoch": 0.6444902008897614, "grad_norm": 0.971276025440007, "learning_rate": 1.883959410563858e-05, "loss": 0.5044, "num_tokens": 360924398.0, "step": 60410 }, { "epoch": 0.6445435438959598, "grad_norm": 1.0004160733532155, "learning_rate": 1.8835930972413606e-05, "loss": 0.553, "num_tokens": 360967007.0, "step": 60415 }, { "epoch": 0.6445968869021582, "grad_norm": 0.859997651559126, "learning_rate": 1.8832268108796674e-05, "loss": 0.4953, "num_tokens": 360995635.0, "step": 60420 }, { "epoch": 0.6446502299083567, "grad_norm": 0.7100143354276164, "learning_rate": 1.882860551490175e-05, "loss": 0.4212, "num_tokens": 361038081.0, "step": 60425 }, { "epoch": 0.6447035729145552, "grad_norm": 0.7397000617357018, "learning_rate": 1.8824943190842802e-05, "loss": 0.519, "num_tokens": 361060968.0, "step": 60430 }, { "epoch": 0.6447569159207537, "grad_norm": 1.120202262931092, "learning_rate": 1.8821281136733808e-05, "loss": 0.555, "num_tokens": 361082305.0, "step": 60435 }, { "epoch": 0.6448102589269521, "grad_norm": 1.2424394119019826, "learning_rate": 1.881761935268872e-05, "loss": 0.5788, "num_tokens": 361102392.0, "step": 60440 }, { "epoch": 0.6448636019331505, "grad_norm": 1.9290308009389756, "learning_rate": 1.8813957838821483e-05, "loss": 0.5484, "num_tokens": 361119300.0, "step": 60445 }, { "epoch": 0.644916944939349, "grad_norm": 1.3257103790944955, "learning_rate": 1.881029659524604e-05, "loss": 0.5346, "num_tokens": 361158831.0, "step": 60450 }, { "epoch": 0.6449702879455474, "grad_norm": 0.75782696312657, "learning_rate": 1.8806635622076314e-05, "loss": 0.5104, "num_tokens": 361187903.0, "step": 60455 }, { "epoch": 0.6450236309517459, "grad_norm": 0.9635112418737486, "learning_rate": 1.880297491942623e-05, "loss": 0.5666, "num_tokens": 361206795.0, "step": 60460 }, { "epoch": 0.6450769739579444, "grad_norm": 1.1155852171051108, "learning_rate": 1.8799314487409707e-05, "loss": 0.4353, "num_tokens": 361243101.0, "step": 60465 }, { "epoch": 0.6451303169641428, "grad_norm": 3.2813669420319833, "learning_rate": 1.879565432614064e-05, "loss": 0.7022, "num_tokens": 361274926.0, "step": 60470 }, { "epoch": 0.6451836599703413, "grad_norm": 1.0768505909576946, "learning_rate": 1.8791994435732928e-05, "loss": 0.4251, "num_tokens": 361302473.0, "step": 60475 }, { "epoch": 0.6452370029765397, "grad_norm": 0.8020884275387689, "learning_rate": 1.878833481630048e-05, "loss": 0.4899, "num_tokens": 361329513.0, "step": 60480 }, { "epoch": 0.6452903459827382, "grad_norm": 1.2843263687455397, "learning_rate": 1.8784675467957136e-05, "loss": 0.5376, "num_tokens": 361348774.0, "step": 60485 }, { "epoch": 0.6453436889889367, "grad_norm": 1.4940172195498116, "learning_rate": 1.8781016390816796e-05, "loss": 0.416, "num_tokens": 361372061.0, "step": 60490 }, { "epoch": 0.6453970319951351, "grad_norm": 1.0438669516879386, "learning_rate": 1.8777357584993327e-05, "loss": 0.5514, "num_tokens": 361406385.0, "step": 60495 }, { "epoch": 0.6454503750013336, "grad_norm": 1.4188200487086946, "learning_rate": 1.8773699050600563e-05, "loss": 0.3983, "num_tokens": 361426438.0, "step": 60500 }, { "epoch": 0.645503718007532, "grad_norm": 0.7539921254176624, "learning_rate": 1.8770040787752358e-05, "loss": 0.4334, "num_tokens": 361453417.0, "step": 60505 }, { "epoch": 0.6455570610137304, "grad_norm": 0.8315004492543586, "learning_rate": 1.8766382796562565e-05, "loss": 0.5687, "num_tokens": 361498687.0, "step": 60510 }, { "epoch": 0.645610404019929, "grad_norm": 1.1126947732283459, "learning_rate": 1.8762725077144994e-05, "loss": 0.3815, "num_tokens": 361526790.0, "step": 60515 }, { "epoch": 0.6456637470261274, "grad_norm": 2.26366341857229, "learning_rate": 1.8759067629613465e-05, "loss": 0.4323, "num_tokens": 361552336.0, "step": 60520 }, { "epoch": 0.6457170900323259, "grad_norm": 0.7551559904394658, "learning_rate": 1.87554104540818e-05, "loss": 0.5769, "num_tokens": 361585256.0, "step": 60525 }, { "epoch": 0.6457704330385243, "grad_norm": 1.0091838448555233, "learning_rate": 1.8751753550663804e-05, "loss": 0.3601, "num_tokens": 361599605.0, "step": 60530 }, { "epoch": 0.6458237760447227, "grad_norm": 1.276232350362567, "learning_rate": 1.874809691947326e-05, "loss": 0.5597, "num_tokens": 361623770.0, "step": 60535 }, { "epoch": 0.6458771190509213, "grad_norm": 0.9867347498989808, "learning_rate": 1.8744440560623978e-05, "loss": 0.4924, "num_tokens": 361655534.0, "step": 60540 }, { "epoch": 0.6459304620571197, "grad_norm": 1.0630052714775617, "learning_rate": 1.8740784474229706e-05, "loss": 0.6279, "num_tokens": 361676302.0, "step": 60545 }, { "epoch": 0.6459838050633181, "grad_norm": 0.634098083123774, "learning_rate": 1.873712866040424e-05, "loss": 0.5709, "num_tokens": 361717600.0, "step": 60550 }, { "epoch": 0.6460371480695166, "grad_norm": 0.9116265203535386, "learning_rate": 1.8733473119261323e-05, "loss": 0.7117, "num_tokens": 361747714.0, "step": 60555 }, { "epoch": 0.646090491075715, "grad_norm": 0.6932675429344307, "learning_rate": 1.8729817850914718e-05, "loss": 0.4851, "num_tokens": 361786395.0, "step": 60560 }, { "epoch": 0.6461438340819136, "grad_norm": 0.49288338750215954, "learning_rate": 1.8726162855478164e-05, "loss": 0.4053, "num_tokens": 361819847.0, "step": 60565 }, { "epoch": 0.646197177088112, "grad_norm": 1.914878256909905, "learning_rate": 1.8722508133065408e-05, "loss": 0.4903, "num_tokens": 361844561.0, "step": 60570 }, { "epoch": 0.6462505200943104, "grad_norm": 1.6064715568993293, "learning_rate": 1.8718853683790165e-05, "loss": 0.396, "num_tokens": 361860398.0, "step": 60575 }, { "epoch": 0.6463038631005089, "grad_norm": 0.6609503575841791, "learning_rate": 1.8715199507766152e-05, "loss": 0.4047, "num_tokens": 361893000.0, "step": 60580 }, { "epoch": 0.6463572061067073, "grad_norm": 1.2044166601285824, "learning_rate": 1.8711545605107095e-05, "loss": 0.51, "num_tokens": 361917308.0, "step": 60585 }, { "epoch": 0.6464105491129059, "grad_norm": 1.1427985748632687, "learning_rate": 1.8707891975926682e-05, "loss": 0.5993, "num_tokens": 361937749.0, "step": 60590 }, { "epoch": 0.6464638921191043, "grad_norm": 0.8148422276852327, "learning_rate": 1.8704238620338616e-05, "loss": 0.6002, "num_tokens": 361985139.0, "step": 60595 }, { "epoch": 0.6465172351253027, "grad_norm": 0.8346968027087408, "learning_rate": 1.870058553845658e-05, "loss": 0.4712, "num_tokens": 362005534.0, "step": 60600 }, { "epoch": 0.6465705781315012, "grad_norm": 0.8588087617531323, "learning_rate": 1.8696932730394235e-05, "loss": 0.4185, "num_tokens": 362032026.0, "step": 60605 }, { "epoch": 0.6466239211376996, "grad_norm": 0.7193745342458328, "learning_rate": 1.8693280196265267e-05, "loss": 0.4927, "num_tokens": 362068002.0, "step": 60610 }, { "epoch": 0.6466772641438981, "grad_norm": 0.6014002468028949, "learning_rate": 1.8689627936183336e-05, "loss": 0.4795, "num_tokens": 362097345.0, "step": 60615 }, { "epoch": 0.6467306071500966, "grad_norm": 1.1762455155384977, "learning_rate": 1.8685975950262074e-05, "loss": 0.4803, "num_tokens": 362134783.0, "step": 60620 }, { "epoch": 0.646783950156295, "grad_norm": 0.7195418922229054, "learning_rate": 1.8682324238615146e-05, "loss": 0.4903, "num_tokens": 362171107.0, "step": 60625 }, { "epoch": 0.6468372931624935, "grad_norm": 1.0698385606511727, "learning_rate": 1.867867280135618e-05, "loss": 0.4165, "num_tokens": 362195653.0, "step": 60630 }, { "epoch": 0.6468906361686919, "grad_norm": 1.3837091609300238, "learning_rate": 1.8675021638598784e-05, "loss": 0.3929, "num_tokens": 362213862.0, "step": 60635 }, { "epoch": 0.6469439791748903, "grad_norm": 0.8785984862309315, "learning_rate": 1.8671370750456592e-05, "loss": 0.5193, "num_tokens": 362239443.0, "step": 60640 }, { "epoch": 0.6469973221810889, "grad_norm": 0.9045170265938215, "learning_rate": 1.8667720137043214e-05, "loss": 0.6613, "num_tokens": 362263905.0, "step": 60645 }, { "epoch": 0.6470506651872873, "grad_norm": 1.7103709903601862, "learning_rate": 1.8664069798472235e-05, "loss": 0.5012, "num_tokens": 362302703.0, "step": 60650 }, { "epoch": 0.6471040081934858, "grad_norm": 0.6786026480291975, "learning_rate": 1.8660419734857254e-05, "loss": 0.5127, "num_tokens": 362338214.0, "step": 60655 }, { "epoch": 0.6471573511996842, "grad_norm": 1.5478273829116915, "learning_rate": 1.865676994631186e-05, "loss": 0.5321, "num_tokens": 362376772.0, "step": 60660 }, { "epoch": 0.6472106942058826, "grad_norm": 1.1562853969514728, "learning_rate": 1.8653120432949623e-05, "loss": 0.6795, "num_tokens": 362405284.0, "step": 60665 }, { "epoch": 0.6472640372120811, "grad_norm": 0.7444278137115131, "learning_rate": 1.8649471194884093e-05, "loss": 0.4764, "num_tokens": 362430489.0, "step": 60670 }, { "epoch": 0.6473173802182796, "grad_norm": 0.5486540622798803, "learning_rate": 1.8645822232228855e-05, "loss": 0.4212, "num_tokens": 362459715.0, "step": 60675 }, { "epoch": 0.6473707232244781, "grad_norm": 3.6720231946045345, "learning_rate": 1.8642173545097437e-05, "loss": 0.4991, "num_tokens": 362478102.0, "step": 60680 }, { "epoch": 0.6474240662306765, "grad_norm": 0.9708349309137602, "learning_rate": 1.8638525133603374e-05, "loss": 0.549, "num_tokens": 362513215.0, "step": 60685 }, { "epoch": 0.6474774092368749, "grad_norm": 1.1211898983974704, "learning_rate": 1.8634876997860222e-05, "loss": 0.4323, "num_tokens": 362534829.0, "step": 60690 }, { "epoch": 0.6475307522430734, "grad_norm": 0.5525205175104676, "learning_rate": 1.8631229137981475e-05, "loss": 0.5747, "num_tokens": 362567413.0, "step": 60695 }, { "epoch": 0.6475840952492719, "grad_norm": 0.8804115780563309, "learning_rate": 1.862758155408067e-05, "loss": 0.4372, "num_tokens": 362579887.0, "step": 60700 }, { "epoch": 0.6476374382554704, "grad_norm": 1.0775939273944044, "learning_rate": 1.862393424627131e-05, "loss": 0.5107, "num_tokens": 362615675.0, "step": 60705 }, { "epoch": 0.6476907812616688, "grad_norm": 1.258670899132495, "learning_rate": 1.8620287214666866e-05, "loss": 0.4746, "num_tokens": 362637857.0, "step": 60710 }, { "epoch": 0.6477441242678672, "grad_norm": 1.1904390560921352, "learning_rate": 1.8616640459380845e-05, "loss": 0.5935, "num_tokens": 362676047.0, "step": 60715 }, { "epoch": 0.6477974672740657, "grad_norm": 2.257268237586115, "learning_rate": 1.8612993980526743e-05, "loss": 0.4357, "num_tokens": 362696180.0, "step": 60720 }, { "epoch": 0.6478508102802641, "grad_norm": 0.7771479446178339, "learning_rate": 1.8609347778217995e-05, "loss": 0.4235, "num_tokens": 362716057.0, "step": 60725 }, { "epoch": 0.6479041532864626, "grad_norm": 0.9283871786421173, "learning_rate": 1.860570185256809e-05, "loss": 0.4498, "num_tokens": 362746447.0, "step": 60730 }, { "epoch": 0.6479574962926611, "grad_norm": 1.387389417422124, "learning_rate": 1.8602056203690477e-05, "loss": 0.4782, "num_tokens": 362777688.0, "step": 60735 }, { "epoch": 0.6480108392988595, "grad_norm": 0.5647988603297656, "learning_rate": 1.8598410831698597e-05, "loss": 0.4946, "num_tokens": 362808911.0, "step": 60740 }, { "epoch": 0.648064182305058, "grad_norm": 0.6321194420923052, "learning_rate": 1.8594765736705884e-05, "loss": 0.4591, "num_tokens": 362838746.0, "step": 60745 }, { "epoch": 0.6481175253112564, "grad_norm": 1.1086341585370516, "learning_rate": 1.8591120918825776e-05, "loss": 0.4639, "num_tokens": 362862265.0, "step": 60750 }, { "epoch": 0.6481708683174549, "grad_norm": 0.6365691398711134, "learning_rate": 1.8587476378171685e-05, "loss": 0.4104, "num_tokens": 362893328.0, "step": 60755 }, { "epoch": 0.6482242113236534, "grad_norm": 1.2479367865933937, "learning_rate": 1.8583832114857014e-05, "loss": 0.4045, "num_tokens": 362915902.0, "step": 60760 }, { "epoch": 0.6482775543298518, "grad_norm": 1.5540975331738154, "learning_rate": 1.8580188128995185e-05, "loss": 0.6019, "num_tokens": 362954641.0, "step": 60765 }, { "epoch": 0.6483308973360503, "grad_norm": 1.4148886226942694, "learning_rate": 1.8576544420699565e-05, "loss": 0.6441, "num_tokens": 362982440.0, "step": 60770 }, { "epoch": 0.6483842403422487, "grad_norm": 1.0017310756037625, "learning_rate": 1.8572900990083564e-05, "loss": 0.4316, "num_tokens": 363005658.0, "step": 60775 }, { "epoch": 0.6484375833484471, "grad_norm": 1.055916147091096, "learning_rate": 1.856925783726055e-05, "loss": 0.5264, "num_tokens": 363033980.0, "step": 60780 }, { "epoch": 0.6484909263546457, "grad_norm": 0.5792068451279869, "learning_rate": 1.8565614962343875e-05, "loss": 0.4755, "num_tokens": 363075998.0, "step": 60785 }, { "epoch": 0.6485442693608441, "grad_norm": 0.8129367604986824, "learning_rate": 1.8561972365446917e-05, "loss": 0.4161, "num_tokens": 363101132.0, "step": 60790 }, { "epoch": 0.6485976123670426, "grad_norm": 2.054049135610705, "learning_rate": 1.8558330046683025e-05, "loss": 0.6569, "num_tokens": 363152487.0, "step": 60795 }, { "epoch": 0.648650955373241, "grad_norm": 1.0237749624279908, "learning_rate": 1.8554688006165527e-05, "loss": 0.4888, "num_tokens": 363189983.0, "step": 60800 }, { "epoch": 0.6487042983794394, "grad_norm": 1.640682220416763, "learning_rate": 1.8551046244007768e-05, "loss": 0.5305, "num_tokens": 363219693.0, "step": 60805 }, { "epoch": 0.648757641385638, "grad_norm": 1.500025892488743, "learning_rate": 1.8547404760323068e-05, "loss": 0.4684, "num_tokens": 363242525.0, "step": 60810 }, { "epoch": 0.6488109843918364, "grad_norm": 1.0156487589609162, "learning_rate": 1.8543763555224746e-05, "loss": 0.4928, "num_tokens": 363261159.0, "step": 60815 }, { "epoch": 0.6488643273980348, "grad_norm": 1.1349165272199646, "learning_rate": 1.8540122628826102e-05, "loss": 0.6403, "num_tokens": 363288062.0, "step": 60820 }, { "epoch": 0.6489176704042333, "grad_norm": 1.2457731442494755, "learning_rate": 1.8536481981240435e-05, "loss": 0.4856, "num_tokens": 363312710.0, "step": 60825 }, { "epoch": 0.6489710134104317, "grad_norm": 1.2236101520578193, "learning_rate": 1.8532841612581043e-05, "loss": 0.4716, "num_tokens": 363328273.0, "step": 60830 }, { "epoch": 0.6490243564166303, "grad_norm": 0.7542152029073461, "learning_rate": 1.8529201522961192e-05, "loss": 0.6002, "num_tokens": 363360091.0, "step": 60835 }, { "epoch": 0.6490776994228287, "grad_norm": 1.396187054930647, "learning_rate": 1.8525561712494172e-05, "loss": 0.5229, "num_tokens": 363379984.0, "step": 60840 }, { "epoch": 0.6491310424290271, "grad_norm": 0.9035946952415942, "learning_rate": 1.852192218129324e-05, "loss": 0.52, "num_tokens": 363405646.0, "step": 60845 }, { "epoch": 0.6491843854352256, "grad_norm": 1.836041405922316, "learning_rate": 1.8518282929471638e-05, "loss": 0.5608, "num_tokens": 363441282.0, "step": 60850 }, { "epoch": 0.649237728441424, "grad_norm": 1.4524602393118162, "learning_rate": 1.8514643957142624e-05, "loss": 0.41, "num_tokens": 363457350.0, "step": 60855 }, { "epoch": 0.6492910714476225, "grad_norm": 1.458054467351796, "learning_rate": 1.851100526441944e-05, "loss": 0.4504, "num_tokens": 363486645.0, "step": 60860 }, { "epoch": 0.649344414453821, "grad_norm": 1.0109154576730004, "learning_rate": 1.8507366851415308e-05, "loss": 0.5284, "num_tokens": 363520123.0, "step": 60865 }, { "epoch": 0.6493977574600194, "grad_norm": 1.4378421819608096, "learning_rate": 1.850372871824344e-05, "loss": 0.5004, "num_tokens": 363556799.0, "step": 60870 }, { "epoch": 0.6494511004662179, "grad_norm": 0.9323236210407461, "learning_rate": 1.8500090865017068e-05, "loss": 0.3283, "num_tokens": 363586465.0, "step": 60875 }, { "epoch": 0.6495044434724163, "grad_norm": 0.7435853376550288, "learning_rate": 1.8496453291849376e-05, "loss": 0.5449, "num_tokens": 363615175.0, "step": 60880 }, { "epoch": 0.6495577864786148, "grad_norm": 1.6540727265199437, "learning_rate": 1.8492815998853552e-05, "loss": 0.5211, "num_tokens": 363629975.0, "step": 60885 }, { "epoch": 0.6496111294848133, "grad_norm": 0.7728560697435896, "learning_rate": 1.8489178986142814e-05, "loss": 0.4788, "num_tokens": 363657609.0, "step": 60890 }, { "epoch": 0.6496644724910117, "grad_norm": 1.3257862334741437, "learning_rate": 1.8485542253830295e-05, "loss": 0.5093, "num_tokens": 363710056.0, "step": 60895 }, { "epoch": 0.6497178154972102, "grad_norm": 0.9186448426424396, "learning_rate": 1.8481905802029203e-05, "loss": 0.5465, "num_tokens": 363744324.0, "step": 60900 }, { "epoch": 0.6497711585034086, "grad_norm": 0.6605273910410644, "learning_rate": 1.8478269630852674e-05, "loss": 0.4996, "num_tokens": 363784888.0, "step": 60905 }, { "epoch": 0.649824501509607, "grad_norm": 0.9970595567198121, "learning_rate": 1.8474633740413855e-05, "loss": 0.5101, "num_tokens": 363823979.0, "step": 60910 }, { "epoch": 0.6498778445158055, "grad_norm": 0.7822667300349413, "learning_rate": 1.84709981308259e-05, "loss": 0.4666, "num_tokens": 363856219.0, "step": 60915 }, { "epoch": 0.649931187522004, "grad_norm": 1.8434362929543453, "learning_rate": 1.8467362802201948e-05, "loss": 0.4771, "num_tokens": 363880231.0, "step": 60920 }, { "epoch": 0.6499845305282025, "grad_norm": 1.312554340184523, "learning_rate": 1.8463727754655098e-05, "loss": 0.647, "num_tokens": 363914802.0, "step": 60925 }, { "epoch": 0.6500378735344009, "grad_norm": 0.6459218146318458, "learning_rate": 1.8460092988298484e-05, "loss": 0.4162, "num_tokens": 363942259.0, "step": 60930 }, { "epoch": 0.6500912165405993, "grad_norm": 0.9720278216480783, "learning_rate": 1.8456458503245212e-05, "loss": 0.5179, "num_tokens": 363977942.0, "step": 60935 }, { "epoch": 0.6501445595467978, "grad_norm": 0.7229543225778982, "learning_rate": 1.8452824299608364e-05, "loss": 0.3956, "num_tokens": 364004779.0, "step": 60940 }, { "epoch": 0.6501979025529963, "grad_norm": 0.8597787154687174, "learning_rate": 1.844919037750104e-05, "loss": 0.452, "num_tokens": 364034419.0, "step": 60945 }, { "epoch": 0.6502512455591948, "grad_norm": 0.9682904934358512, "learning_rate": 1.8445556737036335e-05, "loss": 0.4992, "num_tokens": 364056247.0, "step": 60950 }, { "epoch": 0.6503045885653932, "grad_norm": 1.0567999607249443, "learning_rate": 1.8441923378327303e-05, "loss": 0.5779, "num_tokens": 364089562.0, "step": 60955 }, { "epoch": 0.6503579315715916, "grad_norm": 0.804019155570868, "learning_rate": 1.8438290301487e-05, "loss": 0.4685, "num_tokens": 364110130.0, "step": 60960 }, { "epoch": 0.6504112745777901, "grad_norm": 0.7962169857621821, "learning_rate": 1.84346575066285e-05, "loss": 0.4362, "num_tokens": 364154716.0, "step": 60965 }, { "epoch": 0.6504646175839885, "grad_norm": 0.6202226208232391, "learning_rate": 1.843102499386483e-05, "loss": 0.3992, "num_tokens": 364185518.0, "step": 60970 }, { "epoch": 0.6505179605901871, "grad_norm": 2.2858152160177427, "learning_rate": 1.842739276330903e-05, "loss": 0.5289, "num_tokens": 364213054.0, "step": 60975 }, { "epoch": 0.6505713035963855, "grad_norm": 1.067179655897574, "learning_rate": 1.8423760815074142e-05, "loss": 0.4171, "num_tokens": 364234717.0, "step": 60980 }, { "epoch": 0.6506246466025839, "grad_norm": 1.1958839038847544, "learning_rate": 1.8420129149273168e-05, "loss": 0.449, "num_tokens": 364251380.0, "step": 60985 }, { "epoch": 0.6506779896087824, "grad_norm": 1.0368226083793572, "learning_rate": 1.8416497766019132e-05, "loss": 0.4816, "num_tokens": 364280511.0, "step": 60990 }, { "epoch": 0.6507313326149808, "grad_norm": 0.613052372251285, "learning_rate": 1.8412866665425023e-05, "loss": 0.545, "num_tokens": 364331540.0, "step": 60995 }, { "epoch": 0.6507846756211793, "grad_norm": 1.422329364433048, "learning_rate": 1.8409235847603833e-05, "loss": 0.5705, "num_tokens": 364365342.0, "step": 61000 }, { "epoch": 0.6508380186273778, "grad_norm": 0.8212418897798897, "learning_rate": 1.8405605312668554e-05, "loss": 0.5274, "num_tokens": 364396729.0, "step": 61005 }, { "epoch": 0.6508913616335762, "grad_norm": 0.8437875743132053, "learning_rate": 1.8401975060732163e-05, "loss": 0.4981, "num_tokens": 364418761.0, "step": 61010 }, { "epoch": 0.6509447046397747, "grad_norm": 0.6960750940656901, "learning_rate": 1.839834509190761e-05, "loss": 0.538, "num_tokens": 364451175.0, "step": 61015 }, { "epoch": 0.6509980476459731, "grad_norm": 0.9061019540627706, "learning_rate": 1.839471540630786e-05, "loss": 0.5771, "num_tokens": 364484218.0, "step": 61020 }, { "epoch": 0.6510513906521715, "grad_norm": 1.2920893479376532, "learning_rate": 1.8391086004045876e-05, "loss": 0.494, "num_tokens": 364504459.0, "step": 61025 }, { "epoch": 0.6511047336583701, "grad_norm": 1.2550731134411668, "learning_rate": 1.8387456885234583e-05, "loss": 0.4648, "num_tokens": 364533951.0, "step": 61030 }, { "epoch": 0.6511580766645685, "grad_norm": 1.2479037547404883, "learning_rate": 1.8383828049986906e-05, "loss": 0.5436, "num_tokens": 364550216.0, "step": 61035 }, { "epoch": 0.651211419670767, "grad_norm": 0.8067563759325006, "learning_rate": 1.8380199498415783e-05, "loss": 0.5823, "num_tokens": 364587447.0, "step": 61040 }, { "epoch": 0.6512647626769654, "grad_norm": 0.9478605334808311, "learning_rate": 1.8376571230634122e-05, "loss": 0.51, "num_tokens": 364629546.0, "step": 61045 }, { "epoch": 0.6513181056831638, "grad_norm": 0.6292193662460581, "learning_rate": 1.8372943246754815e-05, "loss": 0.4401, "num_tokens": 364666600.0, "step": 61050 }, { "epoch": 0.6513714486893624, "grad_norm": 0.8464606743493566, "learning_rate": 1.836931554689077e-05, "loss": 0.4328, "num_tokens": 364696007.0, "step": 61055 }, { "epoch": 0.6514247916955608, "grad_norm": 1.4575586275036692, "learning_rate": 1.836568813115487e-05, "loss": 0.4546, "num_tokens": 364726690.0, "step": 61060 }, { "epoch": 0.6514781347017593, "grad_norm": 0.9294798840567138, "learning_rate": 1.8362060999659992e-05, "loss": 0.4581, "num_tokens": 364767317.0, "step": 61065 }, { "epoch": 0.6515314777079577, "grad_norm": 1.5430281738015894, "learning_rate": 1.8358434152519012e-05, "loss": 0.5048, "num_tokens": 364788017.0, "step": 61070 }, { "epoch": 0.6515848207141561, "grad_norm": 0.6086005992067275, "learning_rate": 1.8354807589844774e-05, "loss": 0.4804, "num_tokens": 364817395.0, "step": 61075 }, { "epoch": 0.6516381637203547, "grad_norm": 0.5915516110104451, "learning_rate": 1.8351181311750144e-05, "loss": 0.3267, "num_tokens": 364845635.0, "step": 61080 }, { "epoch": 0.6516915067265531, "grad_norm": 1.2390451743787616, "learning_rate": 1.8347555318347966e-05, "loss": 0.4218, "num_tokens": 364865165.0, "step": 61085 }, { "epoch": 0.6517448497327515, "grad_norm": 0.8157952758675153, "learning_rate": 1.8343929609751055e-05, "loss": 0.5505, "num_tokens": 364887461.0, "step": 61090 }, { "epoch": 0.65179819273895, "grad_norm": 0.8751173491852934, "learning_rate": 1.8340304186072256e-05, "loss": 0.528, "num_tokens": 364921410.0, "step": 61095 }, { "epoch": 0.6518515357451484, "grad_norm": 1.9577915814002673, "learning_rate": 1.8336679047424378e-05, "loss": 0.4789, "num_tokens": 364941601.0, "step": 61100 }, { "epoch": 0.651904878751347, "grad_norm": 2.630183297556367, "learning_rate": 1.8333054193920214e-05, "loss": 0.6355, "num_tokens": 364958173.0, "step": 61105 }, { "epoch": 0.6519582217575454, "grad_norm": 0.8500670196755241, "learning_rate": 1.8329429625672573e-05, "loss": 0.4428, "num_tokens": 364975620.0, "step": 61110 }, { "epoch": 0.6520115647637438, "grad_norm": 0.9067981057494976, "learning_rate": 1.832580534279426e-05, "loss": 0.4938, "num_tokens": 364998207.0, "step": 61115 }, { "epoch": 0.6520649077699423, "grad_norm": 0.9032034475619082, "learning_rate": 1.8322181345398037e-05, "loss": 0.3671, "num_tokens": 365024705.0, "step": 61120 }, { "epoch": 0.6521182507761407, "grad_norm": 0.7035241200111079, "learning_rate": 1.8318557633596667e-05, "loss": 0.553, "num_tokens": 365056254.0, "step": 61125 }, { "epoch": 0.6521715937823392, "grad_norm": 1.2169452780361307, "learning_rate": 1.8314934207502943e-05, "loss": 0.5457, "num_tokens": 365090038.0, "step": 61130 }, { "epoch": 0.6522249367885377, "grad_norm": 1.2921558341295565, "learning_rate": 1.8311311067229587e-05, "loss": 0.5132, "num_tokens": 365127656.0, "step": 61135 }, { "epoch": 0.6522782797947361, "grad_norm": 0.7271613645210793, "learning_rate": 1.8307688212889356e-05, "loss": 0.4255, "num_tokens": 365146107.0, "step": 61140 }, { "epoch": 0.6523316228009346, "grad_norm": 0.8986861984396747, "learning_rate": 1.830406564459499e-05, "loss": 0.4141, "num_tokens": 365174298.0, "step": 61145 }, { "epoch": 0.652384965807133, "grad_norm": 0.7982819074577093, "learning_rate": 1.8300443362459208e-05, "loss": 0.5522, "num_tokens": 365203354.0, "step": 61150 }, { "epoch": 0.6524383088133315, "grad_norm": 1.0843190447898112, "learning_rate": 1.8296821366594736e-05, "loss": 0.4719, "num_tokens": 365231841.0, "step": 61155 }, { "epoch": 0.65249165181953, "grad_norm": 0.7480077001687973, "learning_rate": 1.8293199657114286e-05, "loss": 0.581, "num_tokens": 365279221.0, "step": 61160 }, { "epoch": 0.6525449948257284, "grad_norm": 0.8323470493769324, "learning_rate": 1.828957823413054e-05, "loss": 0.5269, "num_tokens": 365299288.0, "step": 61165 }, { "epoch": 0.6525983378319269, "grad_norm": 0.7538192470673216, "learning_rate": 1.82859570977562e-05, "loss": 0.5137, "num_tokens": 365332774.0, "step": 61170 }, { "epoch": 0.6526516808381253, "grad_norm": 1.3774933069189497, "learning_rate": 1.828233624810396e-05, "loss": 0.3995, "num_tokens": 365359716.0, "step": 61175 }, { "epoch": 0.6527050238443237, "grad_norm": 0.691211290376222, "learning_rate": 1.8278715685286473e-05, "loss": 0.4924, "num_tokens": 365392262.0, "step": 61180 }, { "epoch": 0.6527583668505222, "grad_norm": 0.9335004792709898, "learning_rate": 1.827509540941641e-05, "loss": 0.5527, "num_tokens": 365413938.0, "step": 61185 }, { "epoch": 0.6528117098567207, "grad_norm": 0.9711361380622896, "learning_rate": 1.827147542060644e-05, "loss": 0.4905, "num_tokens": 365447748.0, "step": 61190 }, { "epoch": 0.6528650528629192, "grad_norm": 0.842075840620148, "learning_rate": 1.8267855718969194e-05, "loss": 0.5476, "num_tokens": 365485119.0, "step": 61195 }, { "epoch": 0.6529183958691176, "grad_norm": 0.6844359786328787, "learning_rate": 1.826423630461731e-05, "loss": 0.4675, "num_tokens": 365514096.0, "step": 61200 }, { "epoch": 0.652971738875316, "grad_norm": 0.6458079078341505, "learning_rate": 1.8260617177663432e-05, "loss": 0.4074, "num_tokens": 365534722.0, "step": 61205 }, { "epoch": 0.6530250818815145, "grad_norm": 0.9241389365120648, "learning_rate": 1.825699833822016e-05, "loss": 0.5188, "num_tokens": 365558416.0, "step": 61210 }, { "epoch": 0.653078424887713, "grad_norm": 1.3643578264809735, "learning_rate": 1.8253379786400116e-05, "loss": 0.4386, "num_tokens": 365577584.0, "step": 61215 }, { "epoch": 0.6531317678939115, "grad_norm": 0.7754589687123001, "learning_rate": 1.8249761522315907e-05, "loss": 0.4338, "num_tokens": 365595841.0, "step": 61220 }, { "epoch": 0.6531851109001099, "grad_norm": 1.0646427649110277, "learning_rate": 1.8246143546080114e-05, "loss": 0.438, "num_tokens": 365618763.0, "step": 61225 }, { "epoch": 0.6532384539063083, "grad_norm": 3.9316786798177445, "learning_rate": 1.8242525857805314e-05, "loss": 0.8628, "num_tokens": 365640204.0, "step": 61230 }, { "epoch": 0.6532917969125068, "grad_norm": 1.4367542700952367, "learning_rate": 1.8238908457604116e-05, "loss": 0.5182, "num_tokens": 365663454.0, "step": 61235 }, { "epoch": 0.6533451399187052, "grad_norm": 1.1320933534819786, "learning_rate": 1.8235291345589046e-05, "loss": 0.4846, "num_tokens": 365686587.0, "step": 61240 }, { "epoch": 0.6533984829249038, "grad_norm": 1.4017878551164502, "learning_rate": 1.823167452187269e-05, "loss": 0.5023, "num_tokens": 365700635.0, "step": 61245 }, { "epoch": 0.6534518259311022, "grad_norm": 0.8302713424579774, "learning_rate": 1.8228057986567583e-05, "loss": 0.5671, "num_tokens": 365740089.0, "step": 61250 }, { "epoch": 0.6535051689373006, "grad_norm": 0.6353495765471289, "learning_rate": 1.8224441739786257e-05, "loss": 0.4276, "num_tokens": 365771738.0, "step": 61255 }, { "epoch": 0.6535585119434991, "grad_norm": 0.6850705605631625, "learning_rate": 1.822082578164126e-05, "loss": 0.5717, "num_tokens": 365805427.0, "step": 61260 }, { "epoch": 0.6536118549496975, "grad_norm": 1.522559096960764, "learning_rate": 1.821721011224511e-05, "loss": 0.5585, "num_tokens": 365839059.0, "step": 61265 }, { "epoch": 0.653665197955896, "grad_norm": 1.4572407983245599, "learning_rate": 1.8213594731710304e-05, "loss": 0.6412, "num_tokens": 365871801.0, "step": 61270 }, { "epoch": 0.6537185409620945, "grad_norm": 0.5994350855310089, "learning_rate": 1.8209979640149354e-05, "loss": 0.4462, "num_tokens": 365922388.0, "step": 61275 }, { "epoch": 0.6537718839682929, "grad_norm": 0.851923049681388, "learning_rate": 1.8206364837674765e-05, "loss": 0.5665, "num_tokens": 365937174.0, "step": 61280 }, { "epoch": 0.6538252269744914, "grad_norm": 1.4076266211971304, "learning_rate": 1.820275032439901e-05, "loss": 0.4592, "num_tokens": 365958560.0, "step": 61285 }, { "epoch": 0.6538785699806898, "grad_norm": 1.4772977393418782, "learning_rate": 1.8199136100434555e-05, "loss": 0.4978, "num_tokens": 366005683.0, "step": 61290 }, { "epoch": 0.6539319129868882, "grad_norm": 0.6288132384680835, "learning_rate": 1.8195522165893895e-05, "loss": 0.4898, "num_tokens": 366023969.0, "step": 61295 }, { "epoch": 0.6539852559930868, "grad_norm": 0.8892390700895856, "learning_rate": 1.8191908520889473e-05, "loss": 0.4347, "num_tokens": 366042805.0, "step": 61300 }, { "epoch": 0.6540385989992852, "grad_norm": 0.9106487737273928, "learning_rate": 1.818829516553373e-05, "loss": 0.5202, "num_tokens": 366080421.0, "step": 61305 }, { "epoch": 0.6540919420054837, "grad_norm": 0.8412933097906807, "learning_rate": 1.818468209993912e-05, "loss": 0.4781, "num_tokens": 366103695.0, "step": 61310 }, { "epoch": 0.6541452850116821, "grad_norm": 1.2048453796322998, "learning_rate": 1.818106932421807e-05, "loss": 0.5611, "num_tokens": 366122189.0, "step": 61315 }, { "epoch": 0.6541986280178805, "grad_norm": 1.2744076782474532, "learning_rate": 1.8177456838482996e-05, "loss": 0.3539, "num_tokens": 366148299.0, "step": 61320 }, { "epoch": 0.6542519710240791, "grad_norm": 0.7366966588641046, "learning_rate": 1.8173844642846327e-05, "loss": 0.414, "num_tokens": 366189884.0, "step": 61325 }, { "epoch": 0.6543053140302775, "grad_norm": 1.4577537274522214, "learning_rate": 1.8170232737420438e-05, "loss": 0.4664, "num_tokens": 366218915.0, "step": 61330 }, { "epoch": 0.654358657036476, "grad_norm": 0.8562467402354306, "learning_rate": 1.8166621122317755e-05, "loss": 0.5113, "num_tokens": 366252222.0, "step": 61335 }, { "epoch": 0.6544120000426744, "grad_norm": 2.2000168305784578, "learning_rate": 1.8163009797650655e-05, "loss": 0.4461, "num_tokens": 366270517.0, "step": 61340 }, { "epoch": 0.6544653430488728, "grad_norm": 0.7561707093267712, "learning_rate": 1.81593987635315e-05, "loss": 0.4398, "num_tokens": 366293784.0, "step": 61345 }, { "epoch": 0.6545186860550714, "grad_norm": 0.7591186316781767, "learning_rate": 1.815578802007267e-05, "loss": 0.5106, "num_tokens": 366320769.0, "step": 61350 }, { "epoch": 0.6545720290612698, "grad_norm": 0.8806545434305071, "learning_rate": 1.815217756738653e-05, "loss": 0.4092, "num_tokens": 366343416.0, "step": 61355 }, { "epoch": 0.6546253720674682, "grad_norm": 1.6737403167462068, "learning_rate": 1.814856740558542e-05, "loss": 0.4149, "num_tokens": 366363326.0, "step": 61360 }, { "epoch": 0.6546787150736667, "grad_norm": 0.7943098003140897, "learning_rate": 1.8144957534781687e-05, "loss": 0.5212, "num_tokens": 366402170.0, "step": 61365 }, { "epoch": 0.6547320580798651, "grad_norm": 0.6409824717327708, "learning_rate": 1.8141347955087657e-05, "loss": 0.4023, "num_tokens": 366443360.0, "step": 61370 }, { "epoch": 0.6547854010860636, "grad_norm": 0.9494366699172265, "learning_rate": 1.8137738666615656e-05, "loss": 0.4473, "num_tokens": 366472069.0, "step": 61375 }, { "epoch": 0.6548387440922621, "grad_norm": 1.183322529266322, "learning_rate": 1.8134129669477995e-05, "loss": 0.464, "num_tokens": 366507423.0, "step": 61380 }, { "epoch": 0.6548920870984605, "grad_norm": 0.716134629220748, "learning_rate": 1.813052096378699e-05, "loss": 0.3751, "num_tokens": 366534606.0, "step": 61385 }, { "epoch": 0.654945430104659, "grad_norm": 1.124445566902775, "learning_rate": 1.8126912549654913e-05, "loss": 0.4987, "num_tokens": 366551776.0, "step": 61390 }, { "epoch": 0.6549987731108574, "grad_norm": 2.1510727160881293, "learning_rate": 1.8123304427194064e-05, "loss": 0.533, "num_tokens": 366581318.0, "step": 61395 }, { "epoch": 0.6550521161170559, "grad_norm": 0.8906379569059985, "learning_rate": 1.8119696596516734e-05, "loss": 0.5349, "num_tokens": 366624795.0, "step": 61400 }, { "epoch": 0.6551054591232544, "grad_norm": 1.0532707861189652, "learning_rate": 1.811608905773518e-05, "loss": 0.5614, "num_tokens": 366654091.0, "step": 61405 }, { "epoch": 0.6551588021294528, "grad_norm": 0.7329038759212165, "learning_rate": 1.8112481810961647e-05, "loss": 0.4052, "num_tokens": 366680035.0, "step": 61410 }, { "epoch": 0.6552121451356513, "grad_norm": 0.7812080964263042, "learning_rate": 1.8108874856308406e-05, "loss": 0.4764, "num_tokens": 366724885.0, "step": 61415 }, { "epoch": 0.6552654881418497, "grad_norm": 0.8357526531540348, "learning_rate": 1.810526819388768e-05, "loss": 0.4846, "num_tokens": 366766959.0, "step": 61420 }, { "epoch": 0.6553188311480482, "grad_norm": 0.8095119019081456, "learning_rate": 1.8101661823811715e-05, "loss": 0.479, "num_tokens": 366791348.0, "step": 61425 }, { "epoch": 0.6553721741542466, "grad_norm": 12.133133990600783, "learning_rate": 1.8098055746192732e-05, "loss": 0.4811, "num_tokens": 366809989.0, "step": 61430 }, { "epoch": 0.6554255171604451, "grad_norm": 1.3332899553719073, "learning_rate": 1.809444996114294e-05, "loss": 0.4803, "num_tokens": 366834283.0, "step": 61435 }, { "epoch": 0.6554788601666436, "grad_norm": 1.4174062562645282, "learning_rate": 1.809084446877455e-05, "loss": 0.5195, "num_tokens": 366863209.0, "step": 61440 }, { "epoch": 0.655532203172842, "grad_norm": 1.0475025901270467, "learning_rate": 1.808723926919975e-05, "loss": 0.4561, "num_tokens": 366892273.0, "step": 61445 }, { "epoch": 0.6555855461790404, "grad_norm": 1.9025746901162373, "learning_rate": 1.8083634362530725e-05, "loss": 0.4506, "num_tokens": 366918683.0, "step": 61450 }, { "epoch": 0.6556388891852389, "grad_norm": 0.7729050370408826, "learning_rate": 1.8080029748879663e-05, "loss": 0.4973, "num_tokens": 366968123.0, "step": 61455 }, { "epoch": 0.6556922321914374, "grad_norm": 0.7693662537911242, "learning_rate": 1.8076425428358728e-05, "loss": 0.5185, "num_tokens": 367007405.0, "step": 61460 }, { "epoch": 0.6557455751976359, "grad_norm": 1.918682545569719, "learning_rate": 1.807282140108007e-05, "loss": 0.6445, "num_tokens": 367039624.0, "step": 61465 }, { "epoch": 0.6557989182038343, "grad_norm": 0.8141984512371777, "learning_rate": 1.806921766715585e-05, "loss": 0.5703, "num_tokens": 367064810.0, "step": 61470 }, { "epoch": 0.6558522612100327, "grad_norm": 0.7056375920278875, "learning_rate": 1.8065614226698214e-05, "loss": 0.4243, "num_tokens": 367104916.0, "step": 61475 }, { "epoch": 0.6559056042162312, "grad_norm": 0.960368198715174, "learning_rate": 1.806201107981927e-05, "loss": 0.5709, "num_tokens": 367136287.0, "step": 61480 }, { "epoch": 0.6559589472224296, "grad_norm": 0.761451303513053, "learning_rate": 1.8058408226631158e-05, "loss": 0.6575, "num_tokens": 367177532.0, "step": 61485 }, { "epoch": 0.6560122902286282, "grad_norm": 0.7164308964253027, "learning_rate": 1.8054805667245995e-05, "loss": 0.4199, "num_tokens": 367210068.0, "step": 61490 }, { "epoch": 0.6560656332348266, "grad_norm": 0.7482571608896748, "learning_rate": 1.805120340177586e-05, "loss": 0.5304, "num_tokens": 367248650.0, "step": 61495 }, { "epoch": 0.656118976241025, "grad_norm": 0.9078208829791361, "learning_rate": 1.804760143033288e-05, "loss": 0.4503, "num_tokens": 367269287.0, "step": 61500 }, { "epoch": 0.6561723192472235, "grad_norm": 0.6597444060861128, "learning_rate": 1.8043999753029135e-05, "loss": 0.5304, "num_tokens": 367296754.0, "step": 61505 }, { "epoch": 0.6562256622534219, "grad_norm": 0.9919094195327538, "learning_rate": 1.8040398369976692e-05, "loss": 0.4614, "num_tokens": 367344600.0, "step": 61510 }, { "epoch": 0.6562790052596205, "grad_norm": 0.9296089987588764, "learning_rate": 1.803679728128761e-05, "loss": 0.4035, "num_tokens": 367372748.0, "step": 61515 }, { "epoch": 0.6563323482658189, "grad_norm": 0.8668345329810742, "learning_rate": 1.803319648707397e-05, "loss": 0.4243, "num_tokens": 367394896.0, "step": 61520 }, { "epoch": 0.6563856912720173, "grad_norm": 0.9988283831027143, "learning_rate": 1.8029595987447805e-05, "loss": 0.564, "num_tokens": 367428413.0, "step": 61525 }, { "epoch": 0.6564390342782158, "grad_norm": 0.8725642521079201, "learning_rate": 1.8025995782521156e-05, "loss": 0.4987, "num_tokens": 367457512.0, "step": 61530 }, { "epoch": 0.6564923772844142, "grad_norm": 0.6844218997659086, "learning_rate": 1.802239587240607e-05, "loss": 0.4809, "num_tokens": 367493707.0, "step": 61535 }, { "epoch": 0.6565457202906126, "grad_norm": 1.501152284813157, "learning_rate": 1.8018796257214545e-05, "loss": 0.486, "num_tokens": 367509032.0, "step": 61540 }, { "epoch": 0.6565990632968112, "grad_norm": 0.8998110060535448, "learning_rate": 1.801519693705861e-05, "loss": 0.4865, "num_tokens": 367535763.0, "step": 61545 }, { "epoch": 0.6566524063030096, "grad_norm": 1.0029195245892317, "learning_rate": 1.8011597912050272e-05, "loss": 0.4128, "num_tokens": 367560352.0, "step": 61550 }, { "epoch": 0.6567057493092081, "grad_norm": 0.8095995361112647, "learning_rate": 1.80079991823015e-05, "loss": 0.4835, "num_tokens": 367597346.0, "step": 61555 }, { "epoch": 0.6567590923154065, "grad_norm": 0.8373362654469553, "learning_rate": 1.80044007479243e-05, "loss": 0.65, "num_tokens": 367635684.0, "step": 61560 }, { "epoch": 0.6568124353216049, "grad_norm": 1.1413716075332254, "learning_rate": 1.800080260903066e-05, "loss": 0.5726, "num_tokens": 367663860.0, "step": 61565 }, { "epoch": 0.6568657783278035, "grad_norm": 1.4306080067637406, "learning_rate": 1.799720476573251e-05, "loss": 0.4944, "num_tokens": 367686239.0, "step": 61570 }, { "epoch": 0.6569191213340019, "grad_norm": 0.9903958560723127, "learning_rate": 1.799360721814184e-05, "loss": 0.488, "num_tokens": 367707538.0, "step": 61575 }, { "epoch": 0.6569724643402004, "grad_norm": 1.1018671294936724, "learning_rate": 1.7990009966370593e-05, "loss": 0.5848, "num_tokens": 367750780.0, "step": 61580 }, { "epoch": 0.6570258073463988, "grad_norm": 1.017290919526217, "learning_rate": 1.7986413010530696e-05, "loss": 0.4463, "num_tokens": 367783463.0, "step": 61585 }, { "epoch": 0.6570791503525972, "grad_norm": 0.7866055776224925, "learning_rate": 1.7982816350734077e-05, "loss": 0.4368, "num_tokens": 367813304.0, "step": 61590 }, { "epoch": 0.6571324933587958, "grad_norm": 1.0720451495388053, "learning_rate": 1.797921998709268e-05, "loss": 0.6047, "num_tokens": 367856118.0, "step": 61595 }, { "epoch": 0.6571858363649942, "grad_norm": 0.6779074964293155, "learning_rate": 1.7975623919718383e-05, "loss": 0.6216, "num_tokens": 367898076.0, "step": 61600 }, { "epoch": 0.6572391793711927, "grad_norm": 1.6362931913905487, "learning_rate": 1.797202814872311e-05, "loss": 0.6706, "num_tokens": 367933684.0, "step": 61605 }, { "epoch": 0.6572925223773911, "grad_norm": 0.8371760447666534, "learning_rate": 1.796843267421876e-05, "loss": 0.3966, "num_tokens": 367961695.0, "step": 61610 }, { "epoch": 0.6573458653835895, "grad_norm": 1.3781383359390469, "learning_rate": 1.7964837496317193e-05, "loss": 0.5414, "num_tokens": 367990495.0, "step": 61615 }, { "epoch": 0.657399208389788, "grad_norm": 0.7175393637837547, "learning_rate": 1.7961242615130307e-05, "loss": 0.4999, "num_tokens": 368034094.0, "step": 61620 }, { "epoch": 0.6574525513959865, "grad_norm": 0.8566941626498362, "learning_rate": 1.7957648030769963e-05, "loss": 0.4585, "num_tokens": 368053972.0, "step": 61625 }, { "epoch": 0.6575058944021849, "grad_norm": 1.903399499251674, "learning_rate": 1.7954053743348003e-05, "loss": 0.4881, "num_tokens": 368080710.0, "step": 61630 }, { "epoch": 0.6575592374083834, "grad_norm": 1.875567587333235, "learning_rate": 1.795045975297628e-05, "loss": 0.5259, "num_tokens": 368104529.0, "step": 61635 }, { "epoch": 0.6576125804145818, "grad_norm": 0.668075600277308, "learning_rate": 1.7946866059766644e-05, "loss": 0.4831, "num_tokens": 368144825.0, "step": 61640 }, { "epoch": 0.6576659234207803, "grad_norm": 0.9376586818661167, "learning_rate": 1.79432726638309e-05, "loss": 0.5163, "num_tokens": 368167415.0, "step": 61645 }, { "epoch": 0.6577192664269788, "grad_norm": 0.730223076169812, "learning_rate": 1.7939679565280888e-05, "loss": 0.3942, "num_tokens": 368195700.0, "step": 61650 }, { "epoch": 0.6577726094331772, "grad_norm": 1.0842456675784524, "learning_rate": 1.793608676422841e-05, "loss": 0.5323, "num_tokens": 368215483.0, "step": 61655 }, { "epoch": 0.6578259524393757, "grad_norm": 0.9280138711466757, "learning_rate": 1.7932494260785278e-05, "loss": 0.4547, "num_tokens": 368236184.0, "step": 61660 }, { "epoch": 0.6578792954455741, "grad_norm": 2.8610461659308686, "learning_rate": 1.7928902055063256e-05, "loss": 0.479, "num_tokens": 368255395.0, "step": 61665 }, { "epoch": 0.6579326384517726, "grad_norm": 1.296269402293091, "learning_rate": 1.7925310147174157e-05, "loss": 0.4776, "num_tokens": 368283726.0, "step": 61670 }, { "epoch": 0.657985981457971, "grad_norm": 0.8308828093482314, "learning_rate": 1.7921718537229726e-05, "loss": 0.5297, "num_tokens": 368320482.0, "step": 61675 }, { "epoch": 0.6580393244641695, "grad_norm": 0.789034179786063, "learning_rate": 1.791812722534174e-05, "loss": 0.5029, "num_tokens": 368362600.0, "step": 61680 }, { "epoch": 0.658092667470368, "grad_norm": 0.9779198849802004, "learning_rate": 1.7914536211621964e-05, "loss": 0.6531, "num_tokens": 368398261.0, "step": 61685 }, { "epoch": 0.6581460104765664, "grad_norm": 1.0382817349592677, "learning_rate": 1.791094549618212e-05, "loss": 0.6379, "num_tokens": 368420907.0, "step": 61690 }, { "epoch": 0.6581993534827649, "grad_norm": 1.3114266607886704, "learning_rate": 1.7907355079133963e-05, "loss": 0.4805, "num_tokens": 368445722.0, "step": 61695 }, { "epoch": 0.6582526964889633, "grad_norm": 1.7941107490230344, "learning_rate": 1.7903764960589214e-05, "loss": 0.54, "num_tokens": 368469345.0, "step": 61700 }, { "epoch": 0.6583060394951618, "grad_norm": 0.8307656788542838, "learning_rate": 1.7900175140659586e-05, "loss": 0.5273, "num_tokens": 368504597.0, "step": 61705 }, { "epoch": 0.6583593825013603, "grad_norm": 1.825625748294436, "learning_rate": 1.789658561945678e-05, "loss": 0.6448, "num_tokens": 368532399.0, "step": 61710 }, { "epoch": 0.6584127255075587, "grad_norm": 0.8513956667761923, "learning_rate": 1.7892996397092514e-05, "loss": 0.575, "num_tokens": 368570477.0, "step": 61715 }, { "epoch": 0.6584660685137571, "grad_norm": 0.9504381378146395, "learning_rate": 1.7889407473678467e-05, "loss": 0.5281, "num_tokens": 368594533.0, "step": 61720 }, { "epoch": 0.6585194115199556, "grad_norm": 0.8736045137388541, "learning_rate": 1.788581884932631e-05, "loss": 0.5678, "num_tokens": 368624531.0, "step": 61725 }, { "epoch": 0.658572754526154, "grad_norm": 1.0875855458407386, "learning_rate": 1.788223052414773e-05, "loss": 0.3422, "num_tokens": 368653479.0, "step": 61730 }, { "epoch": 0.6586260975323526, "grad_norm": 1.1879199636186029, "learning_rate": 1.7878642498254382e-05, "loss": 0.5067, "num_tokens": 368687564.0, "step": 61735 }, { "epoch": 0.658679440538551, "grad_norm": 0.7747557269982066, "learning_rate": 1.787505477175791e-05, "loss": 0.5905, "num_tokens": 368719812.0, "step": 61740 }, { "epoch": 0.6587327835447494, "grad_norm": 1.3978651351120737, "learning_rate": 1.7871467344769965e-05, "loss": 0.5664, "num_tokens": 368747754.0, "step": 61745 }, { "epoch": 0.6587861265509479, "grad_norm": 0.8623666125095828, "learning_rate": 1.7867880217402184e-05, "loss": 0.5349, "num_tokens": 368782631.0, "step": 61750 }, { "epoch": 0.6588394695571463, "grad_norm": 0.8014122449683363, "learning_rate": 1.786429338976618e-05, "loss": 0.47, "num_tokens": 368806742.0, "step": 61755 }, { "epoch": 0.6588928125633449, "grad_norm": 1.2777249815060083, "learning_rate": 1.786070686197358e-05, "loss": 0.5208, "num_tokens": 368837047.0, "step": 61760 }, { "epoch": 0.6589461555695433, "grad_norm": 0.9549316725293879, "learning_rate": 1.7857120634135983e-05, "loss": 0.463, "num_tokens": 368864850.0, "step": 61765 }, { "epoch": 0.6589994985757417, "grad_norm": 0.7213141518992011, "learning_rate": 1.785353470636497e-05, "loss": 0.4769, "num_tokens": 368897814.0, "step": 61770 }, { "epoch": 0.6590528415819402, "grad_norm": 0.8918621245822653, "learning_rate": 1.7849949078772154e-05, "loss": 0.5177, "num_tokens": 368926467.0, "step": 61775 }, { "epoch": 0.6591061845881386, "grad_norm": 0.9733288302525577, "learning_rate": 1.7846363751469102e-05, "loss": 0.4198, "num_tokens": 368946949.0, "step": 61780 }, { "epoch": 0.6591595275943372, "grad_norm": 0.7826141364183204, "learning_rate": 1.7842778724567373e-05, "loss": 0.4698, "num_tokens": 368977397.0, "step": 61785 }, { "epoch": 0.6592128706005356, "grad_norm": 1.0599861327269484, "learning_rate": 1.7839193998178537e-05, "loss": 0.5301, "num_tokens": 369010658.0, "step": 61790 }, { "epoch": 0.659266213606734, "grad_norm": 0.6691611351957091, "learning_rate": 1.7835609572414146e-05, "loss": 0.3939, "num_tokens": 369035598.0, "step": 61795 }, { "epoch": 0.6593195566129325, "grad_norm": 0.76956547947558, "learning_rate": 1.7832025447385736e-05, "loss": 0.533, "num_tokens": 369059491.0, "step": 61800 }, { "epoch": 0.6593728996191309, "grad_norm": 0.7919242543621386, "learning_rate": 1.7828441623204822e-05, "loss": 0.539, "num_tokens": 369097813.0, "step": 61805 }, { "epoch": 0.6594262426253293, "grad_norm": 0.5921040536145529, "learning_rate": 1.782485809998295e-05, "loss": 0.4155, "num_tokens": 369116212.0, "step": 61810 }, { "epoch": 0.6594795856315279, "grad_norm": 1.082333763472494, "learning_rate": 1.7821274877831618e-05, "loss": 0.4565, "num_tokens": 369148965.0, "step": 61815 }, { "epoch": 0.6595329286377263, "grad_norm": 1.4069486683608368, "learning_rate": 1.7817691956862325e-05, "loss": 0.4775, "num_tokens": 369176262.0, "step": 61820 }, { "epoch": 0.6595862716439248, "grad_norm": 0.9465398598173851, "learning_rate": 1.7814109337186578e-05, "loss": 0.4119, "num_tokens": 369192817.0, "step": 61825 }, { "epoch": 0.6596396146501232, "grad_norm": 2.330956648609198, "learning_rate": 1.7810527018915847e-05, "loss": 0.5467, "num_tokens": 369212664.0, "step": 61830 }, { "epoch": 0.6596929576563216, "grad_norm": 0.9719912027216211, "learning_rate": 1.7806945002161618e-05, "loss": 0.5185, "num_tokens": 369243280.0, "step": 61835 }, { "epoch": 0.6597463006625202, "grad_norm": 2.3343426250203207, "learning_rate": 1.780336328703535e-05, "loss": 0.6194, "num_tokens": 369271905.0, "step": 61840 }, { "epoch": 0.6597996436687186, "grad_norm": 1.2628929677752758, "learning_rate": 1.7799781873648498e-05, "loss": 0.4646, "num_tokens": 369295956.0, "step": 61845 }, { "epoch": 0.6598529866749171, "grad_norm": 1.2102898166312894, "learning_rate": 1.77962007621125e-05, "loss": 0.6258, "num_tokens": 369332194.0, "step": 61850 }, { "epoch": 0.6599063296811155, "grad_norm": 0.8620244356556089, "learning_rate": 1.779261995253882e-05, "loss": 0.4743, "num_tokens": 369356466.0, "step": 61855 }, { "epoch": 0.6599596726873139, "grad_norm": 0.8609054365518672, "learning_rate": 1.778903944503885e-05, "loss": 0.6285, "num_tokens": 369390007.0, "step": 61860 }, { "epoch": 0.6600130156935125, "grad_norm": 0.8119290973624547, "learning_rate": 1.7785459239724028e-05, "loss": 0.5085, "num_tokens": 369421450.0, "step": 61865 }, { "epoch": 0.6600663586997109, "grad_norm": 0.5783207104129874, "learning_rate": 1.7781879336705777e-05, "loss": 0.5, "num_tokens": 369469688.0, "step": 61870 }, { "epoch": 0.6601197017059094, "grad_norm": 1.2530222246026403, "learning_rate": 1.7778299736095466e-05, "loss": 0.5051, "num_tokens": 369495979.0, "step": 61875 }, { "epoch": 0.6601730447121078, "grad_norm": 1.125476157173974, "learning_rate": 1.77747204380045e-05, "loss": 0.5399, "num_tokens": 369517908.0, "step": 61880 }, { "epoch": 0.6602263877183062, "grad_norm": 1.2558541033915298, "learning_rate": 1.7771141442544258e-05, "loss": 0.368, "num_tokens": 369535815.0, "step": 61885 }, { "epoch": 0.6602797307245047, "grad_norm": 0.906522919827241, "learning_rate": 1.776756274982611e-05, "loss": 0.5496, "num_tokens": 369573823.0, "step": 61890 }, { "epoch": 0.6603330737307032, "grad_norm": 0.9840263420718313, "learning_rate": 1.7763984359961417e-05, "loss": 0.5518, "num_tokens": 369611405.0, "step": 61895 }, { "epoch": 0.6603864167369016, "grad_norm": 5.17910452249856, "learning_rate": 1.7760406273061535e-05, "loss": 0.3622, "num_tokens": 369642030.0, "step": 61900 }, { "epoch": 0.6604397597431001, "grad_norm": 1.1580062517398055, "learning_rate": 1.7756828489237796e-05, "loss": 0.5183, "num_tokens": 369667960.0, "step": 61905 }, { "epoch": 0.6604931027492985, "grad_norm": 0.6836588727729332, "learning_rate": 1.7753251008601563e-05, "loss": 0.4315, "num_tokens": 369691308.0, "step": 61910 }, { "epoch": 0.660546445755497, "grad_norm": 1.1083742728075432, "learning_rate": 1.7749673831264124e-05, "loss": 0.5693, "num_tokens": 369732159.0, "step": 61915 }, { "epoch": 0.6605997887616955, "grad_norm": 1.1294791092390943, "learning_rate": 1.7746096957336805e-05, "loss": 0.4093, "num_tokens": 369747920.0, "step": 61920 }, { "epoch": 0.6606531317678939, "grad_norm": 0.8474262857767212, "learning_rate": 1.774252038693091e-05, "loss": 0.4848, "num_tokens": 369797045.0, "step": 61925 }, { "epoch": 0.6607064747740924, "grad_norm": 1.0652421144088853, "learning_rate": 1.7738944120157754e-05, "loss": 0.4843, "num_tokens": 369830974.0, "step": 61930 }, { "epoch": 0.6607598177802908, "grad_norm": 0.8422127500400596, "learning_rate": 1.773536815712859e-05, "loss": 0.4719, "num_tokens": 369859408.0, "step": 61935 }, { "epoch": 0.6608131607864893, "grad_norm": 0.6663837225776894, "learning_rate": 1.7731792497954715e-05, "loss": 0.4561, "num_tokens": 369886568.0, "step": 61940 }, { "epoch": 0.6608665037926877, "grad_norm": 0.7725510284317274, "learning_rate": 1.77282171427474e-05, "loss": 0.4755, "num_tokens": 369904975.0, "step": 61945 }, { "epoch": 0.6609198467988862, "grad_norm": 1.4867029753324688, "learning_rate": 1.77246420916179e-05, "loss": 0.6539, "num_tokens": 369927612.0, "step": 61950 }, { "epoch": 0.6609731898050847, "grad_norm": 0.9103345343527527, "learning_rate": 1.772106734467745e-05, "loss": 0.4852, "num_tokens": 369960501.0, "step": 61955 }, { "epoch": 0.6610265328112831, "grad_norm": 0.9266175490198442, "learning_rate": 1.7717492902037304e-05, "loss": 0.4461, "num_tokens": 369972964.0, "step": 61960 }, { "epoch": 0.6610798758174816, "grad_norm": 0.9852721868063311, "learning_rate": 1.771391876380868e-05, "loss": 0.4447, "num_tokens": 370016741.0, "step": 61965 }, { "epoch": 0.66113321882368, "grad_norm": 0.9370417845702681, "learning_rate": 1.7710344930102796e-05, "loss": 0.4491, "num_tokens": 370052506.0, "step": 61970 }, { "epoch": 0.6611865618298784, "grad_norm": 0.889187725030147, "learning_rate": 1.770677140103088e-05, "loss": 0.4494, "num_tokens": 370084221.0, "step": 61975 }, { "epoch": 0.661239904836077, "grad_norm": 2.0337422082403265, "learning_rate": 1.7703198176704115e-05, "loss": 0.4382, "num_tokens": 370125828.0, "step": 61980 }, { "epoch": 0.6612932478422754, "grad_norm": 0.9523364496410128, "learning_rate": 1.769962525723371e-05, "loss": 0.4093, "num_tokens": 370157078.0, "step": 61985 }, { "epoch": 0.6613465908484738, "grad_norm": 0.9031766683873448, "learning_rate": 1.769605264273083e-05, "loss": 0.5694, "num_tokens": 370184078.0, "step": 61990 }, { "epoch": 0.6613999338546723, "grad_norm": 0.8184390392647771, "learning_rate": 1.7692480333306654e-05, "loss": 0.5235, "num_tokens": 370217702.0, "step": 61995 }, { "epoch": 0.6614532768608707, "grad_norm": 1.018583955567246, "learning_rate": 1.768890832907234e-05, "loss": 0.4749, "num_tokens": 370233596.0, "step": 62000 }, { "epoch": 0.6615066198670693, "grad_norm": 1.939561149562295, "learning_rate": 1.7685336630139055e-05, "loss": 0.587, "num_tokens": 370276937.0, "step": 62005 }, { "epoch": 0.6615599628732677, "grad_norm": 0.8086506255696772, "learning_rate": 1.7681765236617927e-05, "loss": 0.4443, "num_tokens": 370301058.0, "step": 62010 }, { "epoch": 0.6616133058794661, "grad_norm": 1.9298916182641126, "learning_rate": 1.7678194148620096e-05, "loss": 0.575, "num_tokens": 370328072.0, "step": 62015 }, { "epoch": 0.6616666488856646, "grad_norm": 0.8058885101329918, "learning_rate": 1.76746233662567e-05, "loss": 0.3545, "num_tokens": 370346518.0, "step": 62020 }, { "epoch": 0.661719991891863, "grad_norm": 1.007456481317329, "learning_rate": 1.767105288963884e-05, "loss": 0.5667, "num_tokens": 370366503.0, "step": 62025 }, { "epoch": 0.6617733348980616, "grad_norm": 0.6645971078839398, "learning_rate": 1.7667482718877615e-05, "loss": 0.4923, "num_tokens": 370392567.0, "step": 62030 }, { "epoch": 0.66182667790426, "grad_norm": 0.695194710481536, "learning_rate": 1.7663912854084142e-05, "loss": 0.5265, "num_tokens": 370438611.0, "step": 62035 }, { "epoch": 0.6618800209104584, "grad_norm": 0.8009079177941466, "learning_rate": 1.7660343295369484e-05, "loss": 0.5526, "num_tokens": 370466080.0, "step": 62040 }, { "epoch": 0.6619333639166569, "grad_norm": 0.7343997081255745, "learning_rate": 1.765677404284474e-05, "loss": 0.4725, "num_tokens": 370506027.0, "step": 62045 }, { "epoch": 0.6619867069228553, "grad_norm": 0.8321354377308546, "learning_rate": 1.7653205096620973e-05, "loss": 0.5426, "num_tokens": 370549361.0, "step": 62050 }, { "epoch": 0.6620400499290539, "grad_norm": 0.592566222551183, "learning_rate": 1.7649636456809232e-05, "loss": 0.5549, "num_tokens": 370582483.0, "step": 62055 }, { "epoch": 0.6620933929352523, "grad_norm": 0.7210746025986892, "learning_rate": 1.7646068123520575e-05, "loss": 0.559, "num_tokens": 370615285.0, "step": 62060 }, { "epoch": 0.6621467359414507, "grad_norm": 0.6757655414679056, "learning_rate": 1.7642500096866043e-05, "loss": 0.3671, "num_tokens": 370645062.0, "step": 62065 }, { "epoch": 0.6622000789476492, "grad_norm": 1.3005190041837043, "learning_rate": 1.7638932376956647e-05, "loss": 0.5022, "num_tokens": 370679974.0, "step": 62070 }, { "epoch": 0.6622534219538476, "grad_norm": 0.6189682249474815, "learning_rate": 1.763536496390342e-05, "loss": 0.4666, "num_tokens": 370705560.0, "step": 62075 }, { "epoch": 0.662306764960046, "grad_norm": 1.920422288488274, "learning_rate": 1.7631797857817382e-05, "loss": 0.715, "num_tokens": 370725860.0, "step": 62080 }, { "epoch": 0.6623601079662446, "grad_norm": 0.5438905075913838, "learning_rate": 1.7628231058809518e-05, "loss": 0.4196, "num_tokens": 370754450.0, "step": 62085 }, { "epoch": 0.662413450972443, "grad_norm": 0.643605428710196, "learning_rate": 1.7624664566990833e-05, "loss": 0.5003, "num_tokens": 370782329.0, "step": 62090 }, { "epoch": 0.6624667939786415, "grad_norm": 0.6271580483575272, "learning_rate": 1.7621098382472307e-05, "loss": 0.5065, "num_tokens": 370817088.0, "step": 62095 }, { "epoch": 0.6625201369848399, "grad_norm": 0.7823939758163397, "learning_rate": 1.761753250536489e-05, "loss": 0.4622, "num_tokens": 370848417.0, "step": 62100 }, { "epoch": 0.6625734799910383, "grad_norm": 0.994587895641307, "learning_rate": 1.761396693577957e-05, "loss": 0.5429, "num_tokens": 370885209.0, "step": 62105 }, { "epoch": 0.6626268229972369, "grad_norm": 1.3400194112397907, "learning_rate": 1.76104016738273e-05, "loss": 0.4204, "num_tokens": 370907705.0, "step": 62110 }, { "epoch": 0.6626801660034353, "grad_norm": 1.4679362456758784, "learning_rate": 1.7606836719619003e-05, "loss": 0.4919, "num_tokens": 370936059.0, "step": 62115 }, { "epoch": 0.6627335090096338, "grad_norm": 1.0658877807982317, "learning_rate": 1.760327207326563e-05, "loss": 0.4336, "num_tokens": 370969132.0, "step": 62120 }, { "epoch": 0.6627868520158322, "grad_norm": 0.9951519408378049, "learning_rate": 1.7599707734878107e-05, "loss": 0.5214, "num_tokens": 370989640.0, "step": 62125 }, { "epoch": 0.6628401950220306, "grad_norm": 0.9383071033387457, "learning_rate": 1.759614370456735e-05, "loss": 0.5358, "num_tokens": 371006121.0, "step": 62130 }, { "epoch": 0.6628935380282291, "grad_norm": 1.4583274589434239, "learning_rate": 1.759257998244424e-05, "loss": 0.521, "num_tokens": 371021635.0, "step": 62135 }, { "epoch": 0.6629468810344276, "grad_norm": 1.11585653410335, "learning_rate": 1.758901656861971e-05, "loss": 0.5414, "num_tokens": 371051236.0, "step": 62140 }, { "epoch": 0.6630002240406261, "grad_norm": 2.433882754451322, "learning_rate": 1.758545346320461e-05, "loss": 0.5191, "num_tokens": 371083433.0, "step": 62145 }, { "epoch": 0.6630535670468245, "grad_norm": 1.0934417897236062, "learning_rate": 1.7581890666309836e-05, "loss": 0.4152, "num_tokens": 371102271.0, "step": 62150 }, { "epoch": 0.6631069100530229, "grad_norm": 1.4774016698887336, "learning_rate": 1.7578328178046255e-05, "loss": 0.468, "num_tokens": 371119011.0, "step": 62155 }, { "epoch": 0.6631602530592214, "grad_norm": 0.5599804975909524, "learning_rate": 1.7574765998524716e-05, "loss": 0.4376, "num_tokens": 371157438.0, "step": 62160 }, { "epoch": 0.6632135960654199, "grad_norm": 0.9916959501320076, "learning_rate": 1.7571204127856082e-05, "loss": 0.3588, "num_tokens": 371174035.0, "step": 62165 }, { "epoch": 0.6632669390716183, "grad_norm": 1.844485638476189, "learning_rate": 1.7567642566151183e-05, "loss": 0.6726, "num_tokens": 371196768.0, "step": 62170 }, { "epoch": 0.6633202820778168, "grad_norm": 0.9366588093148178, "learning_rate": 1.7564081313520838e-05, "loss": 0.4192, "num_tokens": 371228775.0, "step": 62175 }, { "epoch": 0.6633736250840152, "grad_norm": 0.8755078665659023, "learning_rate": 1.756052037007587e-05, "loss": 0.4857, "num_tokens": 371254493.0, "step": 62180 }, { "epoch": 0.6634269680902137, "grad_norm": 1.1052424475587714, "learning_rate": 1.7556959735927103e-05, "loss": 0.4813, "num_tokens": 371280717.0, "step": 62185 }, { "epoch": 0.6634803110964121, "grad_norm": 0.95148559937438, "learning_rate": 1.7553399411185318e-05, "loss": 0.4358, "num_tokens": 371301074.0, "step": 62190 }, { "epoch": 0.6635336541026106, "grad_norm": 1.1498893419396994, "learning_rate": 1.754983939596131e-05, "loss": 0.5176, "num_tokens": 371321181.0, "step": 62195 }, { "epoch": 0.6635869971088091, "grad_norm": 0.7144856439086579, "learning_rate": 1.754627969036587e-05, "loss": 0.4602, "num_tokens": 371350726.0, "step": 62200 }, { "epoch": 0.6636403401150075, "grad_norm": 0.9138291941151924, "learning_rate": 1.7542720294509763e-05, "loss": 0.4606, "num_tokens": 371382256.0, "step": 62205 }, { "epoch": 0.663693683121206, "grad_norm": 1.0086193283687075, "learning_rate": 1.753916120850373e-05, "loss": 0.5988, "num_tokens": 371419959.0, "step": 62210 }, { "epoch": 0.6637470261274044, "grad_norm": 0.8740152578927746, "learning_rate": 1.7535602432458557e-05, "loss": 0.4712, "num_tokens": 371439289.0, "step": 62215 }, { "epoch": 0.6638003691336029, "grad_norm": 1.2214113461609504, "learning_rate": 1.753204396648496e-05, "loss": 0.4484, "num_tokens": 371457354.0, "step": 62220 }, { "epoch": 0.6638537121398014, "grad_norm": 1.0639288558032165, "learning_rate": 1.7528485810693678e-05, "loss": 0.4725, "num_tokens": 371503401.0, "step": 62225 }, { "epoch": 0.6639070551459998, "grad_norm": 1.0768473430177432, "learning_rate": 1.7524927965195442e-05, "loss": 0.4193, "num_tokens": 371529331.0, "step": 62230 }, { "epoch": 0.6639603981521983, "grad_norm": 0.6266341187316651, "learning_rate": 1.752137043010095e-05, "loss": 0.4041, "num_tokens": 371559160.0, "step": 62235 }, { "epoch": 0.6640137411583967, "grad_norm": 0.6857328784393049, "learning_rate": 1.7517813205520933e-05, "loss": 0.5202, "num_tokens": 371596623.0, "step": 62240 }, { "epoch": 0.6640670841645951, "grad_norm": 0.6454806219148204, "learning_rate": 1.7514256291566056e-05, "loss": 0.4226, "num_tokens": 371619079.0, "step": 62245 }, { "epoch": 0.6641204271707937, "grad_norm": 0.8411433141839749, "learning_rate": 1.7510699688347e-05, "loss": 0.6241, "num_tokens": 371646503.0, "step": 62250 }, { "epoch": 0.6641737701769921, "grad_norm": 1.1973197156571749, "learning_rate": 1.7507143395974457e-05, "loss": 0.4583, "num_tokens": 371673096.0, "step": 62255 }, { "epoch": 0.6642271131831905, "grad_norm": 0.9235319562270426, "learning_rate": 1.750358741455909e-05, "loss": 0.4785, "num_tokens": 371696039.0, "step": 62260 }, { "epoch": 0.664280456189389, "grad_norm": 2.1854730998603733, "learning_rate": 1.7500031744211543e-05, "loss": 0.6029, "num_tokens": 371723559.0, "step": 62265 }, { "epoch": 0.6643337991955874, "grad_norm": 1.9444982894761715, "learning_rate": 1.749647638504247e-05, "loss": 0.5417, "num_tokens": 371741557.0, "step": 62270 }, { "epoch": 0.664387142201786, "grad_norm": 0.710181969758639, "learning_rate": 1.749292133716251e-05, "loss": 0.5323, "num_tokens": 371799050.0, "step": 62275 }, { "epoch": 0.6644404852079844, "grad_norm": 0.9624567152171536, "learning_rate": 1.7489366600682284e-05, "loss": 0.5423, "num_tokens": 371831653.0, "step": 62280 }, { "epoch": 0.6644938282141828, "grad_norm": 0.8201753150654568, "learning_rate": 1.7485812175712395e-05, "loss": 0.4466, "num_tokens": 371852864.0, "step": 62285 }, { "epoch": 0.6645471712203813, "grad_norm": 1.1069085939461434, "learning_rate": 1.748225806236347e-05, "loss": 0.4771, "num_tokens": 371890677.0, "step": 62290 }, { "epoch": 0.6646005142265797, "grad_norm": 2.2373409449884356, "learning_rate": 1.7478704260746093e-05, "loss": 0.5405, "num_tokens": 371918229.0, "step": 62295 }, { "epoch": 0.6646538572327783, "grad_norm": 0.7575931223789453, "learning_rate": 1.7475150770970854e-05, "loss": 0.5359, "num_tokens": 371950612.0, "step": 62300 }, { "epoch": 0.6647072002389767, "grad_norm": 0.8367418809171429, "learning_rate": 1.7471597593148342e-05, "loss": 0.4801, "num_tokens": 371988261.0, "step": 62305 }, { "epoch": 0.6647605432451751, "grad_norm": 0.6325447766621161, "learning_rate": 1.74680447273891e-05, "loss": 0.4879, "num_tokens": 372021696.0, "step": 62310 }, { "epoch": 0.6648138862513736, "grad_norm": 0.8247238818115985, "learning_rate": 1.7464492173803714e-05, "loss": 0.326, "num_tokens": 372039168.0, "step": 62315 }, { "epoch": 0.664867229257572, "grad_norm": 0.7670847744315821, "learning_rate": 1.7460939932502713e-05, "loss": 0.461, "num_tokens": 372062795.0, "step": 62320 }, { "epoch": 0.6649205722637705, "grad_norm": 0.6864381265662973, "learning_rate": 1.745738800359663e-05, "loss": 0.4882, "num_tokens": 372093619.0, "step": 62325 }, { "epoch": 0.664973915269969, "grad_norm": 0.9628856428442153, "learning_rate": 1.745383638719601e-05, "loss": 0.4459, "num_tokens": 372123369.0, "step": 62330 }, { "epoch": 0.6650272582761674, "grad_norm": 0.6972685001807744, "learning_rate": 1.7450285083411373e-05, "loss": 0.5697, "num_tokens": 372153129.0, "step": 62335 }, { "epoch": 0.6650806012823659, "grad_norm": 0.6777032198664338, "learning_rate": 1.744673409235321e-05, "loss": 0.4646, "num_tokens": 372188330.0, "step": 62340 }, { "epoch": 0.6651339442885643, "grad_norm": 1.7068356843554027, "learning_rate": 1.7443183414132036e-05, "loss": 0.5395, "num_tokens": 372223677.0, "step": 62345 }, { "epoch": 0.6651872872947627, "grad_norm": 0.7927048365208991, "learning_rate": 1.7439633048858346e-05, "loss": 0.509, "num_tokens": 372253266.0, "step": 62350 }, { "epoch": 0.6652406303009613, "grad_norm": 1.070142484105565, "learning_rate": 1.743608299664261e-05, "loss": 0.5213, "num_tokens": 372278870.0, "step": 62355 }, { "epoch": 0.6652939733071597, "grad_norm": 1.0030457723735597, "learning_rate": 1.743253325759529e-05, "loss": 0.6733, "num_tokens": 372325140.0, "step": 62360 }, { "epoch": 0.6653473163133582, "grad_norm": 1.148591840104171, "learning_rate": 1.7428983831826868e-05, "loss": 0.4887, "num_tokens": 372343257.0, "step": 62365 }, { "epoch": 0.6654006593195566, "grad_norm": 2.719636090963952, "learning_rate": 1.7425434719447767e-05, "loss": 0.5054, "num_tokens": 372382764.0, "step": 62370 }, { "epoch": 0.665454002325755, "grad_norm": 0.9399201545991335, "learning_rate": 1.7421885920568447e-05, "loss": 0.429, "num_tokens": 372402038.0, "step": 62375 }, { "epoch": 0.6655073453319535, "grad_norm": 0.6994678136055045, "learning_rate": 1.7418337435299342e-05, "loss": 0.3675, "num_tokens": 372433843.0, "step": 62380 }, { "epoch": 0.665560688338152, "grad_norm": 0.7282425745744391, "learning_rate": 1.7414789263750875e-05, "loss": 0.4044, "num_tokens": 372469478.0, "step": 62385 }, { "epoch": 0.6656140313443505, "grad_norm": 0.5273143419249765, "learning_rate": 1.7411241406033435e-05, "loss": 0.4989, "num_tokens": 372503628.0, "step": 62390 }, { "epoch": 0.6656673743505489, "grad_norm": 0.736857628876861, "learning_rate": 1.740769386225745e-05, "loss": 0.4557, "num_tokens": 372539201.0, "step": 62395 }, { "epoch": 0.6657207173567473, "grad_norm": 0.7640041364746023, "learning_rate": 1.7404146632533296e-05, "loss": 0.378, "num_tokens": 372569301.0, "step": 62400 }, { "epoch": 0.6657740603629458, "grad_norm": 0.8658528395710635, "learning_rate": 1.740059971697136e-05, "loss": 0.516, "num_tokens": 372611968.0, "step": 62405 }, { "epoch": 0.6658274033691443, "grad_norm": 0.7438222250498345, "learning_rate": 1.7397053115682022e-05, "loss": 0.4589, "num_tokens": 372632204.0, "step": 62410 }, { "epoch": 0.6658807463753428, "grad_norm": 1.3675833872972492, "learning_rate": 1.7393506828775635e-05, "loss": 0.3901, "num_tokens": 372661322.0, "step": 62415 }, { "epoch": 0.6659340893815412, "grad_norm": 0.9724328639823211, "learning_rate": 1.738996085636256e-05, "loss": 0.3638, "num_tokens": 372679552.0, "step": 62420 }, { "epoch": 0.6659874323877396, "grad_norm": 0.6284130069377907, "learning_rate": 1.7386415198553137e-05, "loss": 0.5535, "num_tokens": 372700825.0, "step": 62425 }, { "epoch": 0.6660407753939381, "grad_norm": 0.6932691396723982, "learning_rate": 1.7382869855457694e-05, "loss": 0.4952, "num_tokens": 372731010.0, "step": 62430 }, { "epoch": 0.6660941184001365, "grad_norm": 0.7508937671153794, "learning_rate": 1.737932482718656e-05, "loss": 0.5265, "num_tokens": 372764599.0, "step": 62435 }, { "epoch": 0.666147461406335, "grad_norm": 1.8277880131605286, "learning_rate": 1.737578011385005e-05, "loss": 0.5014, "num_tokens": 372780738.0, "step": 62440 }, { "epoch": 0.6662008044125335, "grad_norm": 0.6857146915378397, "learning_rate": 1.7372235715558467e-05, "loss": 0.4582, "num_tokens": 372817608.0, "step": 62445 }, { "epoch": 0.6662541474187319, "grad_norm": 1.275092856399991, "learning_rate": 1.73686916324221e-05, "loss": 0.5599, "num_tokens": 372850362.0, "step": 62450 }, { "epoch": 0.6663074904249304, "grad_norm": 0.7028457584954197, "learning_rate": 1.736514786455125e-05, "loss": 0.49, "num_tokens": 372882748.0, "step": 62455 }, { "epoch": 0.6663608334311288, "grad_norm": 1.3058473144963318, "learning_rate": 1.7361604412056183e-05, "loss": 0.5857, "num_tokens": 372918202.0, "step": 62460 }, { "epoch": 0.6664141764373273, "grad_norm": 0.947768838950271, "learning_rate": 1.7358061275047152e-05, "loss": 0.4752, "num_tokens": 372942682.0, "step": 62465 }, { "epoch": 0.6664675194435258, "grad_norm": 0.9002764514183627, "learning_rate": 1.7354518453634428e-05, "loss": 0.5468, "num_tokens": 372975466.0, "step": 62470 }, { "epoch": 0.6665208624497242, "grad_norm": 0.5277637829821364, "learning_rate": 1.7350975947928244e-05, "loss": 0.4764, "num_tokens": 373012173.0, "step": 62475 }, { "epoch": 0.6665742054559227, "grad_norm": 0.850057428985588, "learning_rate": 1.734743375803884e-05, "loss": 0.5941, "num_tokens": 373037230.0, "step": 62480 }, { "epoch": 0.6666275484621211, "grad_norm": 0.9933323696669067, "learning_rate": 1.7343891884076453e-05, "loss": 0.576, "num_tokens": 373079533.0, "step": 62485 }, { "epoch": 0.6666808914683195, "grad_norm": 1.2170573592957499, "learning_rate": 1.7340350326151284e-05, "loss": 0.5723, "num_tokens": 373111140.0, "step": 62490 }, { "epoch": 0.6667342344745181, "grad_norm": 0.841162463890697, "learning_rate": 1.733680908437355e-05, "loss": 0.436, "num_tokens": 373140722.0, "step": 62495 }, { "epoch": 0.6667875774807165, "grad_norm": 0.9481863381994234, "learning_rate": 1.7333268158853445e-05, "loss": 0.5092, "num_tokens": 373178408.0, "step": 62500 }, { "epoch": 0.666840920486915, "grad_norm": 0.8097416412469955, "learning_rate": 1.7329727549701135e-05, "loss": 0.4606, "num_tokens": 373218744.0, "step": 62505 }, { "epoch": 0.6668942634931134, "grad_norm": 0.6552464002200865, "learning_rate": 1.732618725702682e-05, "loss": 0.6069, "num_tokens": 373261409.0, "step": 62510 }, { "epoch": 0.6669476064993118, "grad_norm": 0.88836662204335, "learning_rate": 1.7322647280940667e-05, "loss": 0.6202, "num_tokens": 373289720.0, "step": 62515 }, { "epoch": 0.6670009495055104, "grad_norm": 0.4918512168398928, "learning_rate": 1.7319107621552815e-05, "loss": 0.4891, "num_tokens": 373332689.0, "step": 62520 }, { "epoch": 0.6670542925117088, "grad_norm": 0.9719658904798754, "learning_rate": 1.7315568278973425e-05, "loss": 0.5186, "num_tokens": 373346798.0, "step": 62525 }, { "epoch": 0.6671076355179072, "grad_norm": 0.7747788658038509, "learning_rate": 1.7312029253312635e-05, "loss": 0.4619, "num_tokens": 373385394.0, "step": 62530 }, { "epoch": 0.6671609785241057, "grad_norm": 0.9679821476070468, "learning_rate": 1.730849054468057e-05, "loss": 0.4198, "num_tokens": 373407017.0, "step": 62535 }, { "epoch": 0.6672143215303041, "grad_norm": 0.7303845811159285, "learning_rate": 1.730495215318734e-05, "loss": 0.4991, "num_tokens": 373450162.0, "step": 62540 }, { "epoch": 0.6672676645365027, "grad_norm": 0.6746806523798521, "learning_rate": 1.730141407894307e-05, "loss": 0.6115, "num_tokens": 373508101.0, "step": 62545 }, { "epoch": 0.6673210075427011, "grad_norm": 1.3003550997196966, "learning_rate": 1.7297876322057827e-05, "loss": 0.3702, "num_tokens": 373532795.0, "step": 62550 }, { "epoch": 0.6673743505488995, "grad_norm": 1.1665460139255521, "learning_rate": 1.729433888264172e-05, "loss": 0.5368, "num_tokens": 373569574.0, "step": 62555 }, { "epoch": 0.667427693555098, "grad_norm": 0.6642385442352028, "learning_rate": 1.729080176080483e-05, "loss": 0.4139, "num_tokens": 373589189.0, "step": 62560 }, { "epoch": 0.6674810365612964, "grad_norm": 2.741473174470398, "learning_rate": 1.7287264956657216e-05, "loss": 0.5872, "num_tokens": 373610767.0, "step": 62565 }, { "epoch": 0.667534379567495, "grad_norm": 0.653709345769628, "learning_rate": 1.7283728470308944e-05, "loss": 0.5039, "num_tokens": 373646923.0, "step": 62570 }, { "epoch": 0.6675877225736934, "grad_norm": 0.8081878240986738, "learning_rate": 1.728019230187006e-05, "loss": 0.4739, "num_tokens": 373676936.0, "step": 62575 }, { "epoch": 0.6676410655798918, "grad_norm": 0.8150460730101291, "learning_rate": 1.727665645145059e-05, "loss": 0.5217, "num_tokens": 373697079.0, "step": 62580 }, { "epoch": 0.6676944085860903, "grad_norm": 1.4066793149429024, "learning_rate": 1.7273120919160568e-05, "loss": 0.4277, "num_tokens": 373718606.0, "step": 62585 }, { "epoch": 0.6677477515922887, "grad_norm": 0.7566023183964186, "learning_rate": 1.726958570511003e-05, "loss": 0.4795, "num_tokens": 373763280.0, "step": 62590 }, { "epoch": 0.6678010945984872, "grad_norm": 1.0224539196595568, "learning_rate": 1.7266050809408964e-05, "loss": 0.3964, "num_tokens": 373789827.0, "step": 62595 }, { "epoch": 0.6678544376046857, "grad_norm": 1.4292815893108415, "learning_rate": 1.726251623216737e-05, "loss": 0.5906, "num_tokens": 373811527.0, "step": 62600 }, { "epoch": 0.6679077806108841, "grad_norm": 0.6251149005109472, "learning_rate": 1.7258981973495254e-05, "loss": 0.4673, "num_tokens": 373849798.0, "step": 62605 }, { "epoch": 0.6679611236170826, "grad_norm": 0.6641227907300923, "learning_rate": 1.725544803350258e-05, "loss": 0.4537, "num_tokens": 373875394.0, "step": 62610 }, { "epoch": 0.668014466623281, "grad_norm": 1.0231040087849048, "learning_rate": 1.7251914412299313e-05, "loss": 0.4985, "num_tokens": 373919955.0, "step": 62615 }, { "epoch": 0.6680678096294794, "grad_norm": 0.8289446366404156, "learning_rate": 1.724838110999543e-05, "loss": 0.496, "num_tokens": 373952017.0, "step": 62620 }, { "epoch": 0.668121152635678, "grad_norm": 1.2910174488458561, "learning_rate": 1.724484812670086e-05, "loss": 0.441, "num_tokens": 373969631.0, "step": 62625 }, { "epoch": 0.6681744956418764, "grad_norm": 0.9867735204703025, "learning_rate": 1.724131546252555e-05, "loss": 0.4287, "num_tokens": 373986515.0, "step": 62630 }, { "epoch": 0.6682278386480749, "grad_norm": 0.9469706819887435, "learning_rate": 1.723778311757944e-05, "loss": 0.5259, "num_tokens": 374006653.0, "step": 62635 }, { "epoch": 0.6682811816542733, "grad_norm": 1.227336223308933, "learning_rate": 1.7234251091972438e-05, "loss": 0.6698, "num_tokens": 374038949.0, "step": 62640 }, { "epoch": 0.6683345246604717, "grad_norm": 0.5560866653059634, "learning_rate": 1.7230719385814457e-05, "loss": 0.3956, "num_tokens": 374090566.0, "step": 62645 }, { "epoch": 0.6683878676666702, "grad_norm": 0.6896806388323259, "learning_rate": 1.7227187999215397e-05, "loss": 0.4315, "num_tokens": 374130179.0, "step": 62650 }, { "epoch": 0.6684412106728687, "grad_norm": 0.66524962845577, "learning_rate": 1.722365693228514e-05, "loss": 0.4816, "num_tokens": 374165862.0, "step": 62655 }, { "epoch": 0.6684945536790672, "grad_norm": 1.3919277384498998, "learning_rate": 1.722012618513356e-05, "loss": 0.5122, "num_tokens": 374198498.0, "step": 62660 }, { "epoch": 0.6685478966852656, "grad_norm": 1.3921815181549666, "learning_rate": 1.7216595757870553e-05, "loss": 0.4278, "num_tokens": 374217149.0, "step": 62665 }, { "epoch": 0.668601239691464, "grad_norm": 1.6111282768536643, "learning_rate": 1.721306565060596e-05, "loss": 0.4389, "num_tokens": 374235668.0, "step": 62670 }, { "epoch": 0.6686545826976625, "grad_norm": 1.6420312332232136, "learning_rate": 1.720953586344964e-05, "loss": 0.5639, "num_tokens": 374259893.0, "step": 62675 }, { "epoch": 0.668707925703861, "grad_norm": 1.2021992038021845, "learning_rate": 1.7206006396511414e-05, "loss": 0.4999, "num_tokens": 374284503.0, "step": 62680 }, { "epoch": 0.6687612687100595, "grad_norm": 0.9929916536784409, "learning_rate": 1.7202477249901137e-05, "loss": 0.6394, "num_tokens": 374318591.0, "step": 62685 }, { "epoch": 0.6688146117162579, "grad_norm": 3.9201562668274246, "learning_rate": 1.7198948423728605e-05, "loss": 0.5708, "num_tokens": 374342494.0, "step": 62690 }, { "epoch": 0.6688679547224563, "grad_norm": 1.8801830389470953, "learning_rate": 1.7195419918103643e-05, "loss": 0.5007, "num_tokens": 374361851.0, "step": 62695 }, { "epoch": 0.6689212977286548, "grad_norm": 0.4826165001261366, "learning_rate": 1.719189173313605e-05, "loss": 0.3999, "num_tokens": 374420467.0, "step": 62700 }, { "epoch": 0.6689746407348532, "grad_norm": 1.8576068261675376, "learning_rate": 1.7188363868935608e-05, "loss": 0.5783, "num_tokens": 374446922.0, "step": 62705 }, { "epoch": 0.6690279837410517, "grad_norm": 0.7123105358639833, "learning_rate": 1.718483632561211e-05, "loss": 0.5753, "num_tokens": 374492919.0, "step": 62710 }, { "epoch": 0.6690813267472502, "grad_norm": 0.8690190126147552, "learning_rate": 1.7181309103275318e-05, "loss": 0.5086, "num_tokens": 374531033.0, "step": 62715 }, { "epoch": 0.6691346697534486, "grad_norm": 0.9366447405026823, "learning_rate": 1.717778220203498e-05, "loss": 0.4565, "num_tokens": 374566515.0, "step": 62720 }, { "epoch": 0.6691880127596471, "grad_norm": 0.6876277489138907, "learning_rate": 1.7174255622000863e-05, "loss": 0.5223, "num_tokens": 374596290.0, "step": 62725 }, { "epoch": 0.6692413557658455, "grad_norm": 1.5168725370069602, "learning_rate": 1.7170729363282705e-05, "loss": 0.4816, "num_tokens": 374624383.0, "step": 62730 }, { "epoch": 0.669294698772044, "grad_norm": 0.9990905283614127, "learning_rate": 1.7167203425990222e-05, "loss": 0.6126, "num_tokens": 374663474.0, "step": 62735 }, { "epoch": 0.6693480417782425, "grad_norm": 1.0688109215304258, "learning_rate": 1.7163677810233147e-05, "loss": 0.5159, "num_tokens": 374685431.0, "step": 62740 }, { "epoch": 0.6694013847844409, "grad_norm": 0.6164042842220852, "learning_rate": 1.7160152516121194e-05, "loss": 0.4648, "num_tokens": 374724467.0, "step": 62745 }, { "epoch": 0.6694547277906394, "grad_norm": 1.2190712087753457, "learning_rate": 1.7156627543764057e-05, "loss": 0.4223, "num_tokens": 374741981.0, "step": 62750 }, { "epoch": 0.6695080707968378, "grad_norm": 1.206174290684317, "learning_rate": 1.715310289327142e-05, "loss": 0.4744, "num_tokens": 374760655.0, "step": 62755 }, { "epoch": 0.6695614138030362, "grad_norm": 1.7129585354090067, "learning_rate": 1.7149578564752976e-05, "loss": 0.4854, "num_tokens": 374781008.0, "step": 62760 }, { "epoch": 0.6696147568092348, "grad_norm": 1.0323437305902141, "learning_rate": 1.7146054558318375e-05, "loss": 0.4201, "num_tokens": 374820123.0, "step": 62765 }, { "epoch": 0.6696680998154332, "grad_norm": 1.2269697708699887, "learning_rate": 1.714253087407729e-05, "loss": 0.4413, "num_tokens": 374854893.0, "step": 62770 }, { "epoch": 0.6697214428216317, "grad_norm": 0.9935257656407548, "learning_rate": 1.7139007512139378e-05, "loss": 0.4072, "num_tokens": 374884914.0, "step": 62775 }, { "epoch": 0.6697747858278301, "grad_norm": 1.348801344992972, "learning_rate": 1.713548447261426e-05, "loss": 0.5903, "num_tokens": 374923315.0, "step": 62780 }, { "epoch": 0.6698281288340285, "grad_norm": 0.9739711591243323, "learning_rate": 1.7131961755611585e-05, "loss": 0.5062, "num_tokens": 374936799.0, "step": 62785 }, { "epoch": 0.6698814718402271, "grad_norm": 0.5959900053686715, "learning_rate": 1.712843936124096e-05, "loss": 0.5125, "num_tokens": 374980210.0, "step": 62790 }, { "epoch": 0.6699348148464255, "grad_norm": 1.117424072500261, "learning_rate": 1.7124917289611995e-05, "loss": 0.5661, "num_tokens": 375009080.0, "step": 62795 }, { "epoch": 0.6699881578526239, "grad_norm": 0.9105703043900941, "learning_rate": 1.7121395540834292e-05, "loss": 0.4546, "num_tokens": 375030462.0, "step": 62800 }, { "epoch": 0.6700415008588224, "grad_norm": 1.0738026653985795, "learning_rate": 1.7117874115017448e-05, "loss": 0.4868, "num_tokens": 375057258.0, "step": 62805 }, { "epoch": 0.6700948438650208, "grad_norm": 2.186713208790054, "learning_rate": 1.7114353012271032e-05, "loss": 0.4682, "num_tokens": 375092708.0, "step": 62810 }, { "epoch": 0.6701481868712194, "grad_norm": 0.8868876011225064, "learning_rate": 1.7110832232704613e-05, "loss": 0.4842, "num_tokens": 375120436.0, "step": 62815 }, { "epoch": 0.6702015298774178, "grad_norm": 0.9349507493300915, "learning_rate": 1.7107311776427765e-05, "loss": 0.5411, "num_tokens": 375144898.0, "step": 62820 }, { "epoch": 0.6702548728836162, "grad_norm": 0.6129301872496773, "learning_rate": 1.710379164355003e-05, "loss": 0.5738, "num_tokens": 375192878.0, "step": 62825 }, { "epoch": 0.6703082158898147, "grad_norm": 0.6166310213400783, "learning_rate": 1.710027183418093e-05, "loss": 0.4657, "num_tokens": 375231092.0, "step": 62830 }, { "epoch": 0.6703615588960131, "grad_norm": 0.5874098205413903, "learning_rate": 1.7096752348430022e-05, "loss": 0.5088, "num_tokens": 375269689.0, "step": 62835 }, { "epoch": 0.6704149019022116, "grad_norm": 1.2013524611226745, "learning_rate": 1.7093233186406803e-05, "loss": 0.533, "num_tokens": 375298711.0, "step": 62840 }, { "epoch": 0.6704682449084101, "grad_norm": 1.4418620236592072, "learning_rate": 1.7089714348220786e-05, "loss": 0.5372, "num_tokens": 375330580.0, "step": 62845 }, { "epoch": 0.6705215879146085, "grad_norm": 3.095069526914688, "learning_rate": 1.7086195833981493e-05, "loss": 0.5647, "num_tokens": 375366720.0, "step": 62850 }, { "epoch": 0.670574930920807, "grad_norm": 1.2961802834133995, "learning_rate": 1.708267764379838e-05, "loss": 0.3499, "num_tokens": 375380647.0, "step": 62855 }, { "epoch": 0.6706282739270054, "grad_norm": 0.6685138946495274, "learning_rate": 1.707915977778095e-05, "loss": 0.5089, "num_tokens": 375403191.0, "step": 62860 }, { "epoch": 0.6706816169332039, "grad_norm": 0.9671525919530469, "learning_rate": 1.7075642236038668e-05, "loss": 0.456, "num_tokens": 375438848.0, "step": 62865 }, { "epoch": 0.6707349599394024, "grad_norm": 1.118367619371188, "learning_rate": 1.7072125018680973e-05, "loss": 0.3718, "num_tokens": 375462585.0, "step": 62870 }, { "epoch": 0.6707883029456008, "grad_norm": 1.1111144050049435, "learning_rate": 1.7068608125817325e-05, "loss": 0.6285, "num_tokens": 375489577.0, "step": 62875 }, { "epoch": 0.6708416459517993, "grad_norm": 1.1763521110874116, "learning_rate": 1.7065091557557183e-05, "loss": 0.5356, "num_tokens": 375512046.0, "step": 62880 }, { "epoch": 0.6708949889579977, "grad_norm": 0.6328577980967525, "learning_rate": 1.7061575314009944e-05, "loss": 0.4074, "num_tokens": 375548231.0, "step": 62885 }, { "epoch": 0.6709483319641961, "grad_norm": 0.9577323113204353, "learning_rate": 1.705805939528504e-05, "loss": 0.4292, "num_tokens": 375572797.0, "step": 62890 }, { "epoch": 0.6710016749703946, "grad_norm": 0.7415273282442212, "learning_rate": 1.705454380149189e-05, "loss": 0.4467, "num_tokens": 375609701.0, "step": 62895 }, { "epoch": 0.6710550179765931, "grad_norm": 0.9628904303625456, "learning_rate": 1.705102853273988e-05, "loss": 0.4416, "num_tokens": 375633598.0, "step": 62900 }, { "epoch": 0.6711083609827916, "grad_norm": 0.5611921076220961, "learning_rate": 1.704751358913839e-05, "loss": 0.4848, "num_tokens": 375666852.0, "step": 62905 }, { "epoch": 0.67116170398899, "grad_norm": 1.0001055927737081, "learning_rate": 1.704399897079682e-05, "loss": 0.4285, "num_tokens": 375679365.0, "step": 62910 }, { "epoch": 0.6712150469951884, "grad_norm": 1.1839545192750778, "learning_rate": 1.7040484677824513e-05, "loss": 0.4249, "num_tokens": 375693990.0, "step": 62915 }, { "epoch": 0.6712683900013869, "grad_norm": 0.5715307043619744, "learning_rate": 1.7036970710330836e-05, "loss": 0.4057, "num_tokens": 375729530.0, "step": 62920 }, { "epoch": 0.6713217330075854, "grad_norm": 0.8174452839793922, "learning_rate": 1.703345706842515e-05, "loss": 0.4227, "num_tokens": 375761682.0, "step": 62925 }, { "epoch": 0.6713750760137839, "grad_norm": 0.7298569596460724, "learning_rate": 1.702994375221677e-05, "loss": 0.4349, "num_tokens": 375795073.0, "step": 62930 }, { "epoch": 0.6714284190199823, "grad_norm": 0.7017895008180633, "learning_rate": 1.702643076181505e-05, "loss": 0.4679, "num_tokens": 375818194.0, "step": 62935 }, { "epoch": 0.6714817620261807, "grad_norm": 0.9068570228615587, "learning_rate": 1.702291809732928e-05, "loss": 0.53, "num_tokens": 375845819.0, "step": 62940 }, { "epoch": 0.6715351050323792, "grad_norm": 0.8393658358583925, "learning_rate": 1.701940575886878e-05, "loss": 0.4518, "num_tokens": 375873305.0, "step": 62945 }, { "epoch": 0.6715884480385776, "grad_norm": 1.359246287445778, "learning_rate": 1.701589374654284e-05, "loss": 0.6325, "num_tokens": 375909374.0, "step": 62950 }, { "epoch": 0.6716417910447762, "grad_norm": 0.5896015502291834, "learning_rate": 1.7012382060460762e-05, "loss": 0.5229, "num_tokens": 375949485.0, "step": 62955 }, { "epoch": 0.6716951340509746, "grad_norm": 0.8970523309642433, "learning_rate": 1.70088707007318e-05, "loss": 0.4517, "num_tokens": 375965036.0, "step": 62960 }, { "epoch": 0.671748477057173, "grad_norm": 0.7158051467392935, "learning_rate": 1.700535966746524e-05, "loss": 0.4725, "num_tokens": 375999835.0, "step": 62965 }, { "epoch": 0.6718018200633715, "grad_norm": 1.2640539099910164, "learning_rate": 1.700184896077033e-05, "loss": 0.5876, "num_tokens": 376017292.0, "step": 62970 }, { "epoch": 0.6718551630695699, "grad_norm": 0.6295795824158349, "learning_rate": 1.6998338580756323e-05, "loss": 0.4577, "num_tokens": 376050083.0, "step": 62975 }, { "epoch": 0.6719085060757684, "grad_norm": 1.6046556700571024, "learning_rate": 1.6994828527532437e-05, "loss": 0.4772, "num_tokens": 376076405.0, "step": 62980 }, { "epoch": 0.6719618490819669, "grad_norm": 1.6647276739083665, "learning_rate": 1.6991318801207916e-05, "loss": 0.3741, "num_tokens": 376096422.0, "step": 62985 }, { "epoch": 0.6720151920881653, "grad_norm": 1.0336055425997661, "learning_rate": 1.6987809401891965e-05, "loss": 0.4229, "num_tokens": 376118545.0, "step": 62990 }, { "epoch": 0.6720685350943638, "grad_norm": 1.0649995870430404, "learning_rate": 1.6984300329693788e-05, "loss": 0.4619, "num_tokens": 376146566.0, "step": 62995 }, { "epoch": 0.6721218781005622, "grad_norm": 0.7452623325384486, "learning_rate": 1.6980791584722595e-05, "loss": 0.4919, "num_tokens": 376176789.0, "step": 63000 }, { "epoch": 0.6721752211067606, "grad_norm": 1.2092930723703899, "learning_rate": 1.697728316708756e-05, "loss": 0.5045, "num_tokens": 376215690.0, "step": 63005 }, { "epoch": 0.6722285641129592, "grad_norm": 1.914798428961851, "learning_rate": 1.697377507689785e-05, "loss": 0.4668, "num_tokens": 376246494.0, "step": 63010 }, { "epoch": 0.6722819071191576, "grad_norm": 0.6322209174136887, "learning_rate": 1.697026731426265e-05, "loss": 0.4591, "num_tokens": 376286742.0, "step": 63015 }, { "epoch": 0.6723352501253561, "grad_norm": 0.9271847536248488, "learning_rate": 1.6966759879291092e-05, "loss": 0.4517, "num_tokens": 376319999.0, "step": 63020 }, { "epoch": 0.6723885931315545, "grad_norm": 0.8371094668170298, "learning_rate": 1.6963252772092327e-05, "loss": 0.4328, "num_tokens": 376337955.0, "step": 63025 }, { "epoch": 0.6724419361377529, "grad_norm": 1.1761086046155163, "learning_rate": 1.695974599277551e-05, "loss": 0.4402, "num_tokens": 376360208.0, "step": 63030 }, { "epoch": 0.6724952791439515, "grad_norm": 0.8298106454072487, "learning_rate": 1.695623954144973e-05, "loss": 0.512, "num_tokens": 376387299.0, "step": 63035 }, { "epoch": 0.6725486221501499, "grad_norm": 0.6677253629006317, "learning_rate": 1.6952733418224132e-05, "loss": 0.4751, "num_tokens": 376431969.0, "step": 63040 }, { "epoch": 0.6726019651563484, "grad_norm": 0.7970498518164678, "learning_rate": 1.6949227623207802e-05, "loss": 0.5165, "num_tokens": 376461000.0, "step": 63045 }, { "epoch": 0.6726553081625468, "grad_norm": 2.8417089292434143, "learning_rate": 1.694572215650983e-05, "loss": 0.5156, "num_tokens": 376486895.0, "step": 63050 }, { "epoch": 0.6727086511687452, "grad_norm": 0.6927292279972207, "learning_rate": 1.6942217018239304e-05, "loss": 0.5072, "num_tokens": 376522336.0, "step": 63055 }, { "epoch": 0.6727619941749438, "grad_norm": 1.2030685240938965, "learning_rate": 1.6938712208505305e-05, "loss": 0.4943, "num_tokens": 376548871.0, "step": 63060 }, { "epoch": 0.6728153371811422, "grad_norm": 1.0038324572332824, "learning_rate": 1.693520772741688e-05, "loss": 0.4401, "num_tokens": 376599731.0, "step": 63065 }, { "epoch": 0.6728686801873406, "grad_norm": 1.0740950185518872, "learning_rate": 1.6931703575083096e-05, "loss": 0.438, "num_tokens": 376638400.0, "step": 63070 }, { "epoch": 0.6729220231935391, "grad_norm": 1.298574393577777, "learning_rate": 1.692819975161299e-05, "loss": 0.5228, "num_tokens": 376663805.0, "step": 63075 }, { "epoch": 0.6729753661997375, "grad_norm": 0.6458467122878002, "learning_rate": 1.6924696257115597e-05, "loss": 0.4445, "num_tokens": 376689719.0, "step": 63080 }, { "epoch": 0.673028709205936, "grad_norm": 0.9454852667676016, "learning_rate": 1.6921193091699923e-05, "loss": 0.4853, "num_tokens": 376729014.0, "step": 63085 }, { "epoch": 0.6730820522121345, "grad_norm": 1.2275511289938341, "learning_rate": 1.6917690255475e-05, "loss": 0.5054, "num_tokens": 376769817.0, "step": 63090 }, { "epoch": 0.6731353952183329, "grad_norm": 0.5151600124338616, "learning_rate": 1.6914187748549815e-05, "loss": 0.4574, "num_tokens": 376800048.0, "step": 63095 }, { "epoch": 0.6731887382245314, "grad_norm": 1.2054070378231363, "learning_rate": 1.6910685571033356e-05, "loss": 0.4889, "num_tokens": 376822493.0, "step": 63100 }, { "epoch": 0.6732420812307298, "grad_norm": 0.7880756823091006, "learning_rate": 1.6907183723034625e-05, "loss": 0.4983, "num_tokens": 376850930.0, "step": 63105 }, { "epoch": 0.6732954242369283, "grad_norm": 1.128337698501479, "learning_rate": 1.690368220466257e-05, "loss": 0.5214, "num_tokens": 376869256.0, "step": 63110 }, { "epoch": 0.6733487672431268, "grad_norm": 0.7993317638961849, "learning_rate": 1.6900181016026168e-05, "loss": 0.4506, "num_tokens": 376894206.0, "step": 63115 }, { "epoch": 0.6734021102493252, "grad_norm": 1.1695808802080974, "learning_rate": 1.6896680157234356e-05, "loss": 0.4011, "num_tokens": 376925423.0, "step": 63120 }, { "epoch": 0.6734554532555237, "grad_norm": 0.9339410224461607, "learning_rate": 1.689317962839607e-05, "loss": 0.4156, "num_tokens": 376952956.0, "step": 63125 }, { "epoch": 0.6735087962617221, "grad_norm": 0.6765489573547463, "learning_rate": 1.6889679429620252e-05, "loss": 0.4918, "num_tokens": 376972984.0, "step": 63130 }, { "epoch": 0.6735621392679206, "grad_norm": 0.6072221562402119, "learning_rate": 1.688617956101582e-05, "loss": 0.5566, "num_tokens": 377013856.0, "step": 63135 }, { "epoch": 0.673615482274119, "grad_norm": 0.6229453382449422, "learning_rate": 1.6882680022691673e-05, "loss": 0.5097, "num_tokens": 377047052.0, "step": 63140 }, { "epoch": 0.6736688252803175, "grad_norm": 0.8770687328509215, "learning_rate": 1.6879180814756707e-05, "loss": 0.3927, "num_tokens": 377077463.0, "step": 63145 }, { "epoch": 0.673722168286516, "grad_norm": 1.5786984231162526, "learning_rate": 1.6875681937319835e-05, "loss": 0.5348, "num_tokens": 377117784.0, "step": 63150 }, { "epoch": 0.6737755112927144, "grad_norm": 1.092124421862955, "learning_rate": 1.6872183390489915e-05, "loss": 0.4065, "num_tokens": 377145858.0, "step": 63155 }, { "epoch": 0.6738288542989128, "grad_norm": 1.3187918851720692, "learning_rate": 1.686868517437581e-05, "loss": 0.5274, "num_tokens": 377187836.0, "step": 63160 }, { "epoch": 0.6738821973051113, "grad_norm": 1.0119965322202116, "learning_rate": 1.6865187289086392e-05, "loss": 0.5147, "num_tokens": 377212592.0, "step": 63165 }, { "epoch": 0.6739355403113098, "grad_norm": 1.6360420303182421, "learning_rate": 1.6861689734730495e-05, "loss": 0.4938, "num_tokens": 377230418.0, "step": 63170 }, { "epoch": 0.6739888833175083, "grad_norm": 0.9052805398691005, "learning_rate": 1.6858192511416964e-05, "loss": 0.4353, "num_tokens": 377271712.0, "step": 63175 }, { "epoch": 0.6740422263237067, "grad_norm": 1.007687070876365, "learning_rate": 1.685469561925463e-05, "loss": 0.5254, "num_tokens": 377295121.0, "step": 63180 }, { "epoch": 0.6740955693299051, "grad_norm": 1.094910642881413, "learning_rate": 1.685119905835229e-05, "loss": 0.4895, "num_tokens": 377317216.0, "step": 63185 }, { "epoch": 0.6741489123361036, "grad_norm": 0.8627335184552447, "learning_rate": 1.6847702828818774e-05, "loss": 0.4671, "num_tokens": 377350366.0, "step": 63190 }, { "epoch": 0.674202255342302, "grad_norm": 0.7900645662158217, "learning_rate": 1.6844206930762862e-05, "loss": 0.3916, "num_tokens": 377380366.0, "step": 63195 }, { "epoch": 0.6742555983485006, "grad_norm": 0.8830375363601349, "learning_rate": 1.6840711364293336e-05, "loss": 0.5884, "num_tokens": 377417628.0, "step": 63200 }, { "epoch": 0.674308941354699, "grad_norm": 0.8837441217234452, "learning_rate": 1.683721612951898e-05, "loss": 0.4067, "num_tokens": 377441014.0, "step": 63205 }, { "epoch": 0.6743622843608974, "grad_norm": 1.44814887615906, "learning_rate": 1.6833721226548562e-05, "loss": 0.373, "num_tokens": 377463862.0, "step": 63210 }, { "epoch": 0.6744156273670959, "grad_norm": 0.5559490302860729, "learning_rate": 1.683022665549082e-05, "loss": 0.59, "num_tokens": 377495629.0, "step": 63215 }, { "epoch": 0.6744689703732943, "grad_norm": 1.3504135696851753, "learning_rate": 1.6826732416454513e-05, "loss": 0.4726, "num_tokens": 377522807.0, "step": 63220 }, { "epoch": 0.6745223133794929, "grad_norm": 1.3273873745786133, "learning_rate": 1.6823238509548376e-05, "loss": 0.4742, "num_tokens": 377546396.0, "step": 63225 }, { "epoch": 0.6745756563856913, "grad_norm": 0.7319490897561296, "learning_rate": 1.6819744934881128e-05, "loss": 0.4401, "num_tokens": 377586624.0, "step": 63230 }, { "epoch": 0.6746289993918897, "grad_norm": 1.0438401362247822, "learning_rate": 1.6816251692561462e-05, "loss": 0.5025, "num_tokens": 377607607.0, "step": 63235 }, { "epoch": 0.6746823423980882, "grad_norm": 1.1332338225201743, "learning_rate": 1.681275878269812e-05, "loss": 0.3968, "num_tokens": 377619558.0, "step": 63240 }, { "epoch": 0.6747356854042866, "grad_norm": 1.047917186711497, "learning_rate": 1.6809266205399752e-05, "loss": 0.4007, "num_tokens": 377641302.0, "step": 63245 }, { "epoch": 0.674789028410485, "grad_norm": 1.3005616841103949, "learning_rate": 1.6805773960775066e-05, "loss": 0.4612, "num_tokens": 377661750.0, "step": 63250 }, { "epoch": 0.6748423714166836, "grad_norm": 0.8506380121809177, "learning_rate": 1.680228204893274e-05, "loss": 0.508, "num_tokens": 377682548.0, "step": 63255 }, { "epoch": 0.674895714422882, "grad_norm": 0.4978581999146263, "learning_rate": 1.679879046998141e-05, "loss": 0.5797, "num_tokens": 377724181.0, "step": 63260 }, { "epoch": 0.6749490574290805, "grad_norm": 1.6679533488993659, "learning_rate": 1.6795299224029747e-05, "loss": 0.767, "num_tokens": 377767199.0, "step": 63265 }, { "epoch": 0.6750024004352789, "grad_norm": 0.6714565507945887, "learning_rate": 1.679180831118639e-05, "loss": 0.5102, "num_tokens": 377820610.0, "step": 63270 }, { "epoch": 0.6750557434414773, "grad_norm": 1.4351983439151896, "learning_rate": 1.6788317731559947e-05, "loss": 0.4941, "num_tokens": 377848170.0, "step": 63275 }, { "epoch": 0.6751090864476759, "grad_norm": 0.726604893518456, "learning_rate": 1.678482748525906e-05, "loss": 0.5444, "num_tokens": 377885901.0, "step": 63280 }, { "epoch": 0.6751624294538743, "grad_norm": 0.7056353501570829, "learning_rate": 1.6781337572392336e-05, "loss": 0.5917, "num_tokens": 377928731.0, "step": 63285 }, { "epoch": 0.6752157724600728, "grad_norm": 0.8198846542985367, "learning_rate": 1.6777847993068362e-05, "loss": 0.5174, "num_tokens": 377961742.0, "step": 63290 }, { "epoch": 0.6752691154662712, "grad_norm": 0.8204119377552389, "learning_rate": 1.6774358747395745e-05, "loss": 0.5068, "num_tokens": 377993275.0, "step": 63295 }, { "epoch": 0.6753224584724696, "grad_norm": 0.8424390665805, "learning_rate": 1.677086983548305e-05, "loss": 0.4739, "num_tokens": 378038826.0, "step": 63300 }, { "epoch": 0.6753758014786682, "grad_norm": 0.9412721328195466, "learning_rate": 1.676738125743884e-05, "loss": 0.4358, "num_tokens": 378062838.0, "step": 63305 }, { "epoch": 0.6754291444848666, "grad_norm": 0.8205511717970464, "learning_rate": 1.6763893013371684e-05, "loss": 0.4936, "num_tokens": 378081842.0, "step": 63310 }, { "epoch": 0.6754824874910651, "grad_norm": 0.9610074949318455, "learning_rate": 1.676040510339013e-05, "loss": 0.4766, "num_tokens": 378115048.0, "step": 63315 }, { "epoch": 0.6755358304972635, "grad_norm": 1.4180518352957092, "learning_rate": 1.67569175276027e-05, "loss": 0.6932, "num_tokens": 378134220.0, "step": 63320 }, { "epoch": 0.6755891735034619, "grad_norm": 1.2275107217350634, "learning_rate": 1.675343028611793e-05, "loss": 0.4403, "num_tokens": 378162266.0, "step": 63325 }, { "epoch": 0.6756425165096605, "grad_norm": 0.9922044621067935, "learning_rate": 1.674994337904435e-05, "loss": 0.4206, "num_tokens": 378179682.0, "step": 63330 }, { "epoch": 0.6756958595158589, "grad_norm": 0.5650215645848214, "learning_rate": 1.6746456806490443e-05, "loss": 0.5392, "num_tokens": 378199395.0, "step": 63335 }, { "epoch": 0.6757492025220573, "grad_norm": 0.639478098153246, "learning_rate": 1.6742970568564703e-05, "loss": 0.4512, "num_tokens": 378228502.0, "step": 63340 }, { "epoch": 0.6758025455282558, "grad_norm": 1.3022401856024906, "learning_rate": 1.6739484665375636e-05, "loss": 0.5041, "num_tokens": 378255013.0, "step": 63345 }, { "epoch": 0.6758558885344542, "grad_norm": 1.2073025522469036, "learning_rate": 1.6735999097031694e-05, "loss": 0.5877, "num_tokens": 378269376.0, "step": 63350 }, { "epoch": 0.6759092315406527, "grad_norm": 2.9272364584943724, "learning_rate": 1.673251386364135e-05, "loss": 0.5575, "num_tokens": 378299249.0, "step": 63355 }, { "epoch": 0.6759625745468512, "grad_norm": 1.007208532585479, "learning_rate": 1.6729028965313064e-05, "loss": 0.5321, "num_tokens": 378330489.0, "step": 63360 }, { "epoch": 0.6760159175530496, "grad_norm": 0.8302246188618919, "learning_rate": 1.6725544402155266e-05, "loss": 0.5708, "num_tokens": 378355935.0, "step": 63365 }, { "epoch": 0.6760692605592481, "grad_norm": 0.891677711363168, "learning_rate": 1.6722060174276403e-05, "loss": 0.5559, "num_tokens": 378389592.0, "step": 63370 }, { "epoch": 0.6761226035654465, "grad_norm": 1.151481158408584, "learning_rate": 1.6718576281784887e-05, "loss": 0.503, "num_tokens": 378400806.0, "step": 63375 }, { "epoch": 0.676175946571645, "grad_norm": 0.9660427588137326, "learning_rate": 1.671509272478913e-05, "loss": 0.5044, "num_tokens": 378427852.0, "step": 63380 }, { "epoch": 0.6762292895778435, "grad_norm": 0.8351597279103569, "learning_rate": 1.6711609503397524e-05, "loss": 0.4266, "num_tokens": 378456621.0, "step": 63385 }, { "epoch": 0.6762826325840419, "grad_norm": 0.8371961324858702, "learning_rate": 1.6708126617718483e-05, "loss": 0.4633, "num_tokens": 378498945.0, "step": 63390 }, { "epoch": 0.6763359755902404, "grad_norm": 0.6086644981029948, "learning_rate": 1.6704644067860366e-05, "loss": 0.4654, "num_tokens": 378532349.0, "step": 63395 }, { "epoch": 0.6763893185964388, "grad_norm": 0.5922895498242942, "learning_rate": 1.6701161853931558e-05, "loss": 0.4428, "num_tokens": 378582020.0, "step": 63400 }, { "epoch": 0.6764426616026373, "grad_norm": 0.6537132771298717, "learning_rate": 1.6697679976040412e-05, "loss": 0.458, "num_tokens": 378614631.0, "step": 63405 }, { "epoch": 0.6764960046088357, "grad_norm": 0.8515225648415398, "learning_rate": 1.6694198434295278e-05, "loss": 0.4375, "num_tokens": 378644459.0, "step": 63410 }, { "epoch": 0.6765493476150342, "grad_norm": 1.0248643922240481, "learning_rate": 1.6690717228804483e-05, "loss": 0.5686, "num_tokens": 378684618.0, "step": 63415 }, { "epoch": 0.6766026906212327, "grad_norm": 1.1172394557588754, "learning_rate": 1.6687236359676377e-05, "loss": 0.4286, "num_tokens": 378715932.0, "step": 63420 }, { "epoch": 0.6766560336274311, "grad_norm": 0.9781037665502206, "learning_rate": 1.6683755827019258e-05, "loss": 0.4489, "num_tokens": 378735160.0, "step": 63425 }, { "epoch": 0.6767093766336295, "grad_norm": 0.573911711847266, "learning_rate": 1.6680275630941437e-05, "loss": 0.5614, "num_tokens": 378769004.0, "step": 63430 }, { "epoch": 0.676762719639828, "grad_norm": 0.8547398299953277, "learning_rate": 1.6676795771551225e-05, "loss": 0.4818, "num_tokens": 378801850.0, "step": 63435 }, { "epoch": 0.6768160626460265, "grad_norm": 0.9513574070108037, "learning_rate": 1.6673316248956887e-05, "loss": 0.5878, "num_tokens": 378832006.0, "step": 63440 }, { "epoch": 0.676869405652225, "grad_norm": 1.1274602223734094, "learning_rate": 1.666983706326672e-05, "loss": 0.5679, "num_tokens": 378878034.0, "step": 63445 }, { "epoch": 0.6769227486584234, "grad_norm": 0.954052999831003, "learning_rate": 1.6666358214588972e-05, "loss": 0.5035, "num_tokens": 378902732.0, "step": 63450 }, { "epoch": 0.6769760916646218, "grad_norm": 0.73151351729943, "learning_rate": 1.66628797030319e-05, "loss": 0.4003, "num_tokens": 378937337.0, "step": 63455 }, { "epoch": 0.6770294346708203, "grad_norm": 0.9544699020437288, "learning_rate": 1.665940152870375e-05, "loss": 0.5268, "num_tokens": 378969937.0, "step": 63460 }, { "epoch": 0.6770827776770187, "grad_norm": 1.1508496555770504, "learning_rate": 1.6655923691712767e-05, "loss": 0.5887, "num_tokens": 379001133.0, "step": 63465 }, { "epoch": 0.6771361206832173, "grad_norm": 0.6277584740756533, "learning_rate": 1.665244619216715e-05, "loss": 0.4902, "num_tokens": 379032511.0, "step": 63470 }, { "epoch": 0.6771894636894157, "grad_norm": 1.0119223875216081, "learning_rate": 1.6648969030175133e-05, "loss": 0.5144, "num_tokens": 379053402.0, "step": 63475 }, { "epoch": 0.6772428066956141, "grad_norm": 1.2799902224077775, "learning_rate": 1.6645492205844917e-05, "loss": 0.4197, "num_tokens": 379081957.0, "step": 63480 }, { "epoch": 0.6772961497018126, "grad_norm": 0.7843318837535103, "learning_rate": 1.6642015719284687e-05, "loss": 0.4047, "num_tokens": 379101162.0, "step": 63485 }, { "epoch": 0.677349492708011, "grad_norm": 0.9748168516189071, "learning_rate": 1.6638539570602617e-05, "loss": 0.4085, "num_tokens": 379116041.0, "step": 63490 }, { "epoch": 0.6774028357142096, "grad_norm": 0.8753754816338208, "learning_rate": 1.6635063759906892e-05, "loss": 0.5749, "num_tokens": 379150896.0, "step": 63495 }, { "epoch": 0.677456178720408, "grad_norm": 0.9099372520452259, "learning_rate": 1.663158828730566e-05, "loss": 0.4146, "num_tokens": 379175456.0, "step": 63500 }, { "epoch": 0.6775095217266064, "grad_norm": 1.0968461227856423, "learning_rate": 1.662811315290708e-05, "loss": 0.4496, "num_tokens": 379202501.0, "step": 63505 }, { "epoch": 0.6775628647328049, "grad_norm": 0.8882968269877825, "learning_rate": 1.6624638356819287e-05, "loss": 0.3936, "num_tokens": 379220352.0, "step": 63510 }, { "epoch": 0.6776162077390033, "grad_norm": 0.781823723063951, "learning_rate": 1.6621163899150405e-05, "loss": 0.4201, "num_tokens": 379240796.0, "step": 63515 }, { "epoch": 0.6776695507452017, "grad_norm": 0.7433876877419942, "learning_rate": 1.6617689780008567e-05, "loss": 0.3668, "num_tokens": 379265743.0, "step": 63520 }, { "epoch": 0.6777228937514003, "grad_norm": 0.9052243893420763, "learning_rate": 1.6614215999501868e-05, "loss": 0.726, "num_tokens": 379286323.0, "step": 63525 }, { "epoch": 0.6777762367575987, "grad_norm": 0.7231443464259717, "learning_rate": 1.66107425577384e-05, "loss": 0.4401, "num_tokens": 379321464.0, "step": 63530 }, { "epoch": 0.6778295797637972, "grad_norm": 0.9321361510613642, "learning_rate": 1.660726945482625e-05, "loss": 0.5143, "num_tokens": 379349786.0, "step": 63535 }, { "epoch": 0.6778829227699956, "grad_norm": 1.4268283294680049, "learning_rate": 1.660379669087352e-05, "loss": 0.4733, "num_tokens": 379366781.0, "step": 63540 }, { "epoch": 0.677936265776194, "grad_norm": 0.9778776571104766, "learning_rate": 1.6600324265988244e-05, "loss": 0.4201, "num_tokens": 379391933.0, "step": 63545 }, { "epoch": 0.6779896087823926, "grad_norm": 0.6168096661145492, "learning_rate": 1.6596852180278483e-05, "loss": 0.4642, "num_tokens": 379440904.0, "step": 63550 }, { "epoch": 0.678042951788591, "grad_norm": 1.8747232581801794, "learning_rate": 1.6593380433852296e-05, "loss": 0.5814, "num_tokens": 379472733.0, "step": 63555 }, { "epoch": 0.6780962947947895, "grad_norm": 0.6881404904752214, "learning_rate": 1.6589909026817707e-05, "loss": 0.4096, "num_tokens": 379514643.0, "step": 63560 }, { "epoch": 0.6781496378009879, "grad_norm": 0.8594974530516704, "learning_rate": 1.6586437959282735e-05, "loss": 0.517, "num_tokens": 379551426.0, "step": 63565 }, { "epoch": 0.6782029808071863, "grad_norm": 0.7605260268754216, "learning_rate": 1.65829672313554e-05, "loss": 0.3824, "num_tokens": 379572045.0, "step": 63570 }, { "epoch": 0.6782563238133849, "grad_norm": 3.651451230484951, "learning_rate": 1.6579496843143692e-05, "loss": 0.416, "num_tokens": 379600302.0, "step": 63575 }, { "epoch": 0.6783096668195833, "grad_norm": 0.7694781950569243, "learning_rate": 1.657602679475562e-05, "loss": 0.4598, "num_tokens": 379633833.0, "step": 63580 }, { "epoch": 0.6783630098257818, "grad_norm": 1.5113007253193926, "learning_rate": 1.6572557086299156e-05, "loss": 0.6336, "num_tokens": 379662398.0, "step": 63585 }, { "epoch": 0.6784163528319802, "grad_norm": 2.269754797645446, "learning_rate": 1.656908771788227e-05, "loss": 0.48, "num_tokens": 379691910.0, "step": 63590 }, { "epoch": 0.6784696958381786, "grad_norm": 0.5104123027682727, "learning_rate": 1.6565618689612916e-05, "loss": 0.4167, "num_tokens": 379729209.0, "step": 63595 }, { "epoch": 0.6785230388443771, "grad_norm": 0.8277149258744818, "learning_rate": 1.6562150001599048e-05, "loss": 0.4626, "num_tokens": 379761945.0, "step": 63600 }, { "epoch": 0.6785763818505756, "grad_norm": 0.8864287061428476, "learning_rate": 1.655868165394861e-05, "loss": 0.4556, "num_tokens": 379789346.0, "step": 63605 }, { "epoch": 0.678629724856774, "grad_norm": 0.9309115797022663, "learning_rate": 1.655521364676952e-05, "loss": 0.3699, "num_tokens": 379815250.0, "step": 63610 }, { "epoch": 0.6786830678629725, "grad_norm": 1.3731986956673023, "learning_rate": 1.6551745980169697e-05, "loss": 0.3644, "num_tokens": 379837468.0, "step": 63615 }, { "epoch": 0.6787364108691709, "grad_norm": 0.5029834087275158, "learning_rate": 1.654827865425706e-05, "loss": 0.4752, "num_tokens": 379890354.0, "step": 63620 }, { "epoch": 0.6787897538753694, "grad_norm": 0.7027552537935753, "learning_rate": 1.65448116691395e-05, "loss": 0.3899, "num_tokens": 379908444.0, "step": 63625 }, { "epoch": 0.6788430968815679, "grad_norm": 0.7072240355606737, "learning_rate": 1.6541345024924883e-05, "loss": 0.4724, "num_tokens": 379948162.0, "step": 63630 }, { "epoch": 0.6788964398877663, "grad_norm": 0.9999283724657474, "learning_rate": 1.653787872172111e-05, "loss": 0.508, "num_tokens": 379973026.0, "step": 63635 }, { "epoch": 0.6789497828939648, "grad_norm": 1.0022630276268873, "learning_rate": 1.653441275963603e-05, "loss": 0.4177, "num_tokens": 379997776.0, "step": 63640 }, { "epoch": 0.6790031259001632, "grad_norm": 0.8898016907846189, "learning_rate": 1.65309471387775e-05, "loss": 0.5328, "num_tokens": 380031176.0, "step": 63645 }, { "epoch": 0.6790564689063617, "grad_norm": 0.7924953060741721, "learning_rate": 1.6527481859253368e-05, "loss": 0.5895, "num_tokens": 380067599.0, "step": 63650 }, { "epoch": 0.6791098119125601, "grad_norm": 0.6950872893661638, "learning_rate": 1.6524016921171458e-05, "loss": 0.5365, "num_tokens": 380098813.0, "step": 63655 }, { "epoch": 0.6791631549187586, "grad_norm": 1.3822577937176, "learning_rate": 1.65205523246396e-05, "loss": 0.6233, "num_tokens": 380136295.0, "step": 63660 }, { "epoch": 0.6792164979249571, "grad_norm": 0.7984993055108173, "learning_rate": 1.6517088069765603e-05, "loss": 0.587, "num_tokens": 380166977.0, "step": 63665 }, { "epoch": 0.6792698409311555, "grad_norm": 1.0254279591022708, "learning_rate": 1.651362415665726e-05, "loss": 0.5977, "num_tokens": 380184391.0, "step": 63670 }, { "epoch": 0.679323183937354, "grad_norm": 0.8989885482077354, "learning_rate": 1.6510160585422367e-05, "loss": 0.4496, "num_tokens": 380213427.0, "step": 63675 }, { "epoch": 0.6793765269435524, "grad_norm": 1.6095452331915097, "learning_rate": 1.6506697356168705e-05, "loss": 0.4749, "num_tokens": 380245892.0, "step": 63680 }, { "epoch": 0.6794298699497509, "grad_norm": 0.9914730540288197, "learning_rate": 1.6503234469004038e-05, "loss": 0.6236, "num_tokens": 380279096.0, "step": 63685 }, { "epoch": 0.6794832129559494, "grad_norm": 0.9627379441039922, "learning_rate": 1.6499771924036124e-05, "loss": 0.4703, "num_tokens": 380302577.0, "step": 63690 }, { "epoch": 0.6795365559621478, "grad_norm": 1.3237800770598205, "learning_rate": 1.649630972137272e-05, "loss": 0.4703, "num_tokens": 380325157.0, "step": 63695 }, { "epoch": 0.6795898989683462, "grad_norm": 1.153248736361724, "learning_rate": 1.649284786112156e-05, "loss": 0.5218, "num_tokens": 380361709.0, "step": 63700 }, { "epoch": 0.6796432419745447, "grad_norm": 1.0005817139211926, "learning_rate": 1.6489386343390352e-05, "loss": 0.5213, "num_tokens": 380386648.0, "step": 63705 }, { "epoch": 0.6796965849807431, "grad_norm": 0.9756584170335012, "learning_rate": 1.6485925168286838e-05, "loss": 0.5344, "num_tokens": 380408433.0, "step": 63710 }, { "epoch": 0.6797499279869417, "grad_norm": 0.83328047494199, "learning_rate": 1.6482464335918693e-05, "loss": 0.4161, "num_tokens": 380454830.0, "step": 63715 }, { "epoch": 0.6798032709931401, "grad_norm": 1.3599079944080927, "learning_rate": 1.647900384639363e-05, "loss": 0.4497, "num_tokens": 380473299.0, "step": 63720 }, { "epoch": 0.6798566139993385, "grad_norm": 1.03397406066587, "learning_rate": 1.6475543699819342e-05, "loss": 0.4288, "num_tokens": 380496226.0, "step": 63725 }, { "epoch": 0.679909957005537, "grad_norm": 0.6499865258707833, "learning_rate": 1.6472083896303476e-05, "loss": 0.5629, "num_tokens": 380513349.0, "step": 63730 }, { "epoch": 0.6799633000117354, "grad_norm": 0.5812198051013984, "learning_rate": 1.646862443595372e-05, "loss": 0.4834, "num_tokens": 380555527.0, "step": 63735 }, { "epoch": 0.680016643017934, "grad_norm": 1.0507877145846114, "learning_rate": 1.6465165318877707e-05, "loss": 0.5162, "num_tokens": 380579703.0, "step": 63740 }, { "epoch": 0.6800699860241324, "grad_norm": 1.160653373556731, "learning_rate": 1.6461706545183082e-05, "loss": 0.6376, "num_tokens": 380601387.0, "step": 63745 }, { "epoch": 0.6801233290303308, "grad_norm": 0.8842387452066738, "learning_rate": 1.645824811497747e-05, "loss": 0.6502, "num_tokens": 380642739.0, "step": 63750 }, { "epoch": 0.6801766720365293, "grad_norm": 0.8473577002106892, "learning_rate": 1.6454790028368505e-05, "loss": 0.5645, "num_tokens": 380685219.0, "step": 63755 }, { "epoch": 0.6802300150427277, "grad_norm": 1.2202751393666018, "learning_rate": 1.645133228546378e-05, "loss": 0.4302, "num_tokens": 380704577.0, "step": 63760 }, { "epoch": 0.6802833580489263, "grad_norm": 1.1610940058588857, "learning_rate": 1.64478748863709e-05, "loss": 0.517, "num_tokens": 380732101.0, "step": 63765 }, { "epoch": 0.6803367010551247, "grad_norm": 1.0649236077669937, "learning_rate": 1.6444417831197457e-05, "loss": 0.3943, "num_tokens": 380753229.0, "step": 63770 }, { "epoch": 0.6803900440613231, "grad_norm": 0.8095169954064686, "learning_rate": 1.644096112005103e-05, "loss": 0.558, "num_tokens": 380798827.0, "step": 63775 }, { "epoch": 0.6804433870675216, "grad_norm": 0.797861525371921, "learning_rate": 1.6437504753039162e-05, "loss": 0.5334, "num_tokens": 380822519.0, "step": 63780 }, { "epoch": 0.68049673007372, "grad_norm": 1.254217771348348, "learning_rate": 1.6434048730269432e-05, "loss": 0.4782, "num_tokens": 380851217.0, "step": 63785 }, { "epoch": 0.6805500730799184, "grad_norm": 0.7923821681483161, "learning_rate": 1.643059305184937e-05, "loss": 0.6638, "num_tokens": 380882284.0, "step": 63790 }, { "epoch": 0.680603416086117, "grad_norm": 2.0151949419554342, "learning_rate": 1.6427137717886513e-05, "loss": 0.6265, "num_tokens": 380906563.0, "step": 63795 }, { "epoch": 0.6806567590923154, "grad_norm": 0.9580917368170696, "learning_rate": 1.6423682728488393e-05, "loss": 0.503, "num_tokens": 380932241.0, "step": 63800 }, { "epoch": 0.6807101020985139, "grad_norm": 0.8089650349271399, "learning_rate": 1.6420228083762508e-05, "loss": 0.3694, "num_tokens": 380946554.0, "step": 63805 }, { "epoch": 0.6807634451047123, "grad_norm": 0.7619435105436559, "learning_rate": 1.6416773783816376e-05, "loss": 0.4899, "num_tokens": 380968036.0, "step": 63810 }, { "epoch": 0.6808167881109107, "grad_norm": 1.0343257292326793, "learning_rate": 1.641331982875748e-05, "loss": 0.4857, "num_tokens": 380989099.0, "step": 63815 }, { "epoch": 0.6808701311171093, "grad_norm": 1.0716896771893212, "learning_rate": 1.6409866218693286e-05, "loss": 0.7583, "num_tokens": 381014939.0, "step": 63820 }, { "epoch": 0.6809234741233077, "grad_norm": 1.1354300431891586, "learning_rate": 1.6406412953731277e-05, "loss": 0.414, "num_tokens": 381033223.0, "step": 63825 }, { "epoch": 0.6809768171295062, "grad_norm": 0.6331597139535133, "learning_rate": 1.640296003397892e-05, "loss": 0.4969, "num_tokens": 381076228.0, "step": 63830 }, { "epoch": 0.6810301601357046, "grad_norm": 1.0792577935665242, "learning_rate": 1.6399507459543638e-05, "loss": 0.4192, "num_tokens": 381122145.0, "step": 63835 }, { "epoch": 0.681083503141903, "grad_norm": 0.8632965478798118, "learning_rate": 1.6396055230532885e-05, "loss": 0.4344, "num_tokens": 381147994.0, "step": 63840 }, { "epoch": 0.6811368461481015, "grad_norm": 1.0396490693604925, "learning_rate": 1.63926033470541e-05, "loss": 0.6888, "num_tokens": 381183485.0, "step": 63845 }, { "epoch": 0.6811901891543, "grad_norm": 0.7073890252767143, "learning_rate": 1.6389151809214676e-05, "loss": 0.4737, "num_tokens": 381210182.0, "step": 63850 }, { "epoch": 0.6812435321604985, "grad_norm": 0.8836660053921326, "learning_rate": 1.6385700617122023e-05, "loss": 0.5134, "num_tokens": 381245742.0, "step": 63855 }, { "epoch": 0.6812968751666969, "grad_norm": 0.9007889963832009, "learning_rate": 1.638224977088354e-05, "loss": 0.5573, "num_tokens": 381284473.0, "step": 63860 }, { "epoch": 0.6813502181728953, "grad_norm": 0.8786706710908239, "learning_rate": 1.6378799270606603e-05, "loss": 0.5041, "num_tokens": 381316803.0, "step": 63865 }, { "epoch": 0.6814035611790938, "grad_norm": 1.078738619820492, "learning_rate": 1.6375349116398593e-05, "loss": 0.4536, "num_tokens": 381350869.0, "step": 63870 }, { "epoch": 0.6814569041852923, "grad_norm": 0.7762383794508372, "learning_rate": 1.637189930836687e-05, "loss": 0.6451, "num_tokens": 381388075.0, "step": 63875 }, { "epoch": 0.6815102471914907, "grad_norm": 0.8224885967654572, "learning_rate": 1.6368449846618783e-05, "loss": 0.5441, "num_tokens": 381407196.0, "step": 63880 }, { "epoch": 0.6815635901976892, "grad_norm": 1.0838145329874755, "learning_rate": 1.6365000731261666e-05, "loss": 0.5025, "num_tokens": 381436126.0, "step": 63885 }, { "epoch": 0.6816169332038876, "grad_norm": 1.4918709933330827, "learning_rate": 1.6361551962402862e-05, "loss": 0.4812, "num_tokens": 381457393.0, "step": 63890 }, { "epoch": 0.6816702762100861, "grad_norm": 0.8749569313871333, "learning_rate": 1.635810354014967e-05, "loss": 0.4738, "num_tokens": 381477646.0, "step": 63895 }, { "epoch": 0.6817236192162845, "grad_norm": 0.9770023323328177, "learning_rate": 1.6354655464609414e-05, "loss": 0.4941, "num_tokens": 381508169.0, "step": 63900 }, { "epoch": 0.681776962222483, "grad_norm": 0.5517680528654761, "learning_rate": 1.6351207735889396e-05, "loss": 0.4822, "num_tokens": 381533534.0, "step": 63905 }, { "epoch": 0.6818303052286815, "grad_norm": 1.2928555176716248, "learning_rate": 1.634776035409688e-05, "loss": 0.4501, "num_tokens": 381559473.0, "step": 63910 }, { "epoch": 0.6818836482348799, "grad_norm": 1.8816647912835136, "learning_rate": 1.6344313319339167e-05, "loss": 0.4028, "num_tokens": 381581902.0, "step": 63915 }, { "epoch": 0.6819369912410784, "grad_norm": 0.7341901696168107, "learning_rate": 1.6340866631723506e-05, "loss": 0.4081, "num_tokens": 381608242.0, "step": 63920 }, { "epoch": 0.6819903342472768, "grad_norm": 1.0774756926292393, "learning_rate": 1.6337420291357147e-05, "loss": 0.4763, "num_tokens": 381640901.0, "step": 63925 }, { "epoch": 0.6820436772534753, "grad_norm": 1.103075751428307, "learning_rate": 1.633397429834734e-05, "loss": 0.4515, "num_tokens": 381662946.0, "step": 63930 }, { "epoch": 0.6820970202596738, "grad_norm": 0.9803671436969816, "learning_rate": 1.6330528652801325e-05, "loss": 0.5332, "num_tokens": 381692270.0, "step": 63935 }, { "epoch": 0.6821503632658722, "grad_norm": 0.9886946539510166, "learning_rate": 1.6327083354826305e-05, "loss": 0.4706, "num_tokens": 381729725.0, "step": 63940 }, { "epoch": 0.6822037062720707, "grad_norm": 0.7867112252318681, "learning_rate": 1.6323638404529506e-05, "loss": 0.4764, "num_tokens": 381758092.0, "step": 63945 }, { "epoch": 0.6822570492782691, "grad_norm": 1.2017492186820837, "learning_rate": 1.632019380201813e-05, "loss": 0.4501, "num_tokens": 381788480.0, "step": 63950 }, { "epoch": 0.6823103922844675, "grad_norm": 0.8874621046097905, "learning_rate": 1.631674954739936e-05, "loss": 0.4011, "num_tokens": 381809993.0, "step": 63955 }, { "epoch": 0.6823637352906661, "grad_norm": 0.9418266004721824, "learning_rate": 1.631330564078036e-05, "loss": 0.5092, "num_tokens": 381852201.0, "step": 63960 }, { "epoch": 0.6824170782968645, "grad_norm": 0.8850398193038864, "learning_rate": 1.630986208226832e-05, "loss": 0.5337, "num_tokens": 381885461.0, "step": 63965 }, { "epoch": 0.6824704213030629, "grad_norm": 0.5780914804641154, "learning_rate": 1.6306418871970383e-05, "loss": 0.5825, "num_tokens": 381919490.0, "step": 63970 }, { "epoch": 0.6825237643092614, "grad_norm": 0.7316879480224436, "learning_rate": 1.6302976009993692e-05, "loss": 0.3477, "num_tokens": 381944724.0, "step": 63975 }, { "epoch": 0.6825771073154598, "grad_norm": 0.5614352814922087, "learning_rate": 1.6299533496445403e-05, "loss": 0.5579, "num_tokens": 382001952.0, "step": 63980 }, { "epoch": 0.6826304503216584, "grad_norm": 0.7965637653012506, "learning_rate": 1.629609133143261e-05, "loss": 0.4388, "num_tokens": 382031325.0, "step": 63985 }, { "epoch": 0.6826837933278568, "grad_norm": 0.8476051748653153, "learning_rate": 1.6292649515062454e-05, "loss": 0.4706, "num_tokens": 382059588.0, "step": 63990 }, { "epoch": 0.6827371363340552, "grad_norm": 0.8722558708128116, "learning_rate": 1.6289208047442026e-05, "loss": 0.4415, "num_tokens": 382079850.0, "step": 63995 }, { "epoch": 0.6827904793402537, "grad_norm": 0.8854337455051577, "learning_rate": 1.6285766928678402e-05, "loss": 0.5905, "num_tokens": 382103468.0, "step": 64000 }, { "epoch": 0.6828438223464521, "grad_norm": 0.6720646175716468, "learning_rate": 1.628232615887868e-05, "loss": 0.4429, "num_tokens": 382141377.0, "step": 64005 }, { "epoch": 0.6828971653526507, "grad_norm": 1.4556643000337806, "learning_rate": 1.6278885738149935e-05, "loss": 0.5911, "num_tokens": 382188927.0, "step": 64010 }, { "epoch": 0.6829505083588491, "grad_norm": 0.6741274229002868, "learning_rate": 1.627544566659921e-05, "loss": 0.4968, "num_tokens": 382223451.0, "step": 64015 }, { "epoch": 0.6830038513650475, "grad_norm": 0.9036408089544066, "learning_rate": 1.6272005944333556e-05, "loss": 0.5179, "num_tokens": 382269120.0, "step": 64020 }, { "epoch": 0.683057194371246, "grad_norm": 1.3675062929914514, "learning_rate": 1.6268566571460027e-05, "loss": 0.6684, "num_tokens": 382307417.0, "step": 64025 }, { "epoch": 0.6831105373774444, "grad_norm": 1.1818785051669973, "learning_rate": 1.6265127548085633e-05, "loss": 0.5107, "num_tokens": 382338215.0, "step": 64030 }, { "epoch": 0.683163880383643, "grad_norm": 0.6664191492282213, "learning_rate": 1.6261688874317384e-05, "loss": 0.5665, "num_tokens": 382384480.0, "step": 64035 }, { "epoch": 0.6832172233898414, "grad_norm": 1.4025653282350514, "learning_rate": 1.62582505502623e-05, "loss": 0.4477, "num_tokens": 382399872.0, "step": 64040 }, { "epoch": 0.6832705663960398, "grad_norm": 1.414400208894372, "learning_rate": 1.6254812576027363e-05, "loss": 0.5053, "num_tokens": 382428428.0, "step": 64045 }, { "epoch": 0.6833239094022383, "grad_norm": 0.8262074339613364, "learning_rate": 1.6251374951719562e-05, "loss": 0.3551, "num_tokens": 382453760.0, "step": 64050 }, { "epoch": 0.6833772524084367, "grad_norm": 1.406562223398269, "learning_rate": 1.624793767744587e-05, "loss": 0.6152, "num_tokens": 382481927.0, "step": 64055 }, { "epoch": 0.6834305954146351, "grad_norm": 0.864072837431602, "learning_rate": 1.624450075331324e-05, "loss": 0.3391, "num_tokens": 382511037.0, "step": 64060 }, { "epoch": 0.6834839384208337, "grad_norm": 0.7850405772603741, "learning_rate": 1.6241064179428633e-05, "loss": 0.5246, "num_tokens": 382547821.0, "step": 64065 }, { "epoch": 0.6835372814270321, "grad_norm": 0.6774471698680392, "learning_rate": 1.6237627955898987e-05, "loss": 0.5039, "num_tokens": 382585788.0, "step": 64070 }, { "epoch": 0.6835906244332306, "grad_norm": 2.1435324622707994, "learning_rate": 1.6234192082831212e-05, "loss": 0.5179, "num_tokens": 382605202.0, "step": 64075 }, { "epoch": 0.683643967439429, "grad_norm": 0.679690798268447, "learning_rate": 1.6230756560332237e-05, "loss": 0.5185, "num_tokens": 382656408.0, "step": 64080 }, { "epoch": 0.6836973104456274, "grad_norm": 0.9459686204206429, "learning_rate": 1.622732138850899e-05, "loss": 0.4807, "num_tokens": 382682290.0, "step": 64085 }, { "epoch": 0.683750653451826, "grad_norm": 1.1784530270170916, "learning_rate": 1.6223886567468328e-05, "loss": 0.426, "num_tokens": 382701447.0, "step": 64090 }, { "epoch": 0.6838039964580244, "grad_norm": 0.7452327861527096, "learning_rate": 1.6220452097317157e-05, "loss": 0.4791, "num_tokens": 382733935.0, "step": 64095 }, { "epoch": 0.6838573394642229, "grad_norm": 1.3139847987216962, "learning_rate": 1.6217017978162352e-05, "loss": 0.4022, "num_tokens": 382751476.0, "step": 64100 }, { "epoch": 0.6839106824704213, "grad_norm": 0.6663387650293684, "learning_rate": 1.6213584210110778e-05, "loss": 0.3453, "num_tokens": 382780856.0, "step": 64105 }, { "epoch": 0.6839640254766197, "grad_norm": 0.7288756488663775, "learning_rate": 1.621015079326927e-05, "loss": 0.4591, "num_tokens": 382804839.0, "step": 64110 }, { "epoch": 0.6840173684828182, "grad_norm": 0.6287226198514488, "learning_rate": 1.6206717727744686e-05, "loss": 0.6132, "num_tokens": 382835699.0, "step": 64115 }, { "epoch": 0.6840707114890167, "grad_norm": 0.773460454831515, "learning_rate": 1.6203285013643844e-05, "loss": 0.4464, "num_tokens": 382864120.0, "step": 64120 }, { "epoch": 0.6841240544952152, "grad_norm": 0.6701529028888761, "learning_rate": 1.6199852651073565e-05, "loss": 0.3836, "num_tokens": 382891842.0, "step": 64125 }, { "epoch": 0.6841773975014136, "grad_norm": 0.8295895550398996, "learning_rate": 1.619642064014067e-05, "loss": 0.6279, "num_tokens": 382925690.0, "step": 64130 }, { "epoch": 0.684230740507612, "grad_norm": 1.0373758000441287, "learning_rate": 1.619298898095194e-05, "loss": 0.5679, "num_tokens": 382967001.0, "step": 64135 }, { "epoch": 0.6842840835138105, "grad_norm": 1.0129900834122791, "learning_rate": 1.618955767361417e-05, "loss": 0.4505, "num_tokens": 382992522.0, "step": 64140 }, { "epoch": 0.684337426520009, "grad_norm": 1.2337778100672034, "learning_rate": 1.618612671823414e-05, "loss": 0.4909, "num_tokens": 383022258.0, "step": 64145 }, { "epoch": 0.6843907695262074, "grad_norm": 0.9934451578463593, "learning_rate": 1.6182696114918596e-05, "loss": 0.5031, "num_tokens": 383038512.0, "step": 64150 }, { "epoch": 0.6844441125324059, "grad_norm": 0.6993336111798562, "learning_rate": 1.61792658637743e-05, "loss": 0.5825, "num_tokens": 383073440.0, "step": 64155 }, { "epoch": 0.6844974555386043, "grad_norm": 1.4296163506484865, "learning_rate": 1.6175835964908008e-05, "loss": 0.4536, "num_tokens": 383115939.0, "step": 64160 }, { "epoch": 0.6845507985448028, "grad_norm": 1.098457606411567, "learning_rate": 1.6172406418426433e-05, "loss": 0.5386, "num_tokens": 383149131.0, "step": 64165 }, { "epoch": 0.6846041415510012, "grad_norm": 0.6498938919701942, "learning_rate": 1.6168977224436305e-05, "loss": 0.4627, "num_tokens": 383178050.0, "step": 64170 }, { "epoch": 0.6846574845571997, "grad_norm": 1.6999596172970826, "learning_rate": 1.6165548383044332e-05, "loss": 0.5272, "num_tokens": 383191093.0, "step": 64175 }, { "epoch": 0.6847108275633982, "grad_norm": 1.348666261918192, "learning_rate": 1.6162119894357218e-05, "loss": 0.5518, "num_tokens": 383211166.0, "step": 64180 }, { "epoch": 0.6847641705695966, "grad_norm": 1.0629798415505747, "learning_rate": 1.615869175848163e-05, "loss": 0.6016, "num_tokens": 383246351.0, "step": 64185 }, { "epoch": 0.6848175135757951, "grad_norm": 0.7162084801247777, "learning_rate": 1.6155263975524274e-05, "loss": 0.4747, "num_tokens": 383287251.0, "step": 64190 }, { "epoch": 0.6848708565819935, "grad_norm": 0.8198430242566548, "learning_rate": 1.6151836545591785e-05, "loss": 0.3841, "num_tokens": 383308931.0, "step": 64195 }, { "epoch": 0.684924199588192, "grad_norm": 0.8247002379291803, "learning_rate": 1.6148409468790836e-05, "loss": 0.438, "num_tokens": 383346505.0, "step": 64200 }, { "epoch": 0.6849775425943905, "grad_norm": 1.9426397810580294, "learning_rate": 1.614498274522808e-05, "loss": 0.6275, "num_tokens": 383383369.0, "step": 64205 }, { "epoch": 0.6850308856005889, "grad_norm": 0.7569823855906448, "learning_rate": 1.614155637501013e-05, "loss": 0.3287, "num_tokens": 383408003.0, "step": 64210 }, { "epoch": 0.6850842286067874, "grad_norm": 1.1604875503390648, "learning_rate": 1.6138130358243613e-05, "loss": 0.6269, "num_tokens": 383451206.0, "step": 64215 }, { "epoch": 0.6851375716129858, "grad_norm": 0.6259522280132376, "learning_rate": 1.6134704695035146e-05, "loss": 0.497, "num_tokens": 383479694.0, "step": 64220 }, { "epoch": 0.6851909146191842, "grad_norm": 1.6978874601801635, "learning_rate": 1.6131279385491316e-05, "loss": 0.4639, "num_tokens": 383492469.0, "step": 64225 }, { "epoch": 0.6852442576253828, "grad_norm": 0.9816951850247705, "learning_rate": 1.6127854429718716e-05, "loss": 0.4762, "num_tokens": 383515268.0, "step": 64230 }, { "epoch": 0.6852976006315812, "grad_norm": 0.8390107470377768, "learning_rate": 1.6124429827823938e-05, "loss": 0.448, "num_tokens": 383551075.0, "step": 64235 }, { "epoch": 0.6853509436377796, "grad_norm": 0.8513804992028383, "learning_rate": 1.6121005579913532e-05, "loss": 0.489, "num_tokens": 383576990.0, "step": 64240 }, { "epoch": 0.6854042866439781, "grad_norm": 1.5414508985369577, "learning_rate": 1.6117581686094066e-05, "loss": 0.4526, "num_tokens": 383594161.0, "step": 64245 }, { "epoch": 0.6854576296501765, "grad_norm": 0.5304855294298715, "learning_rate": 1.611415814647208e-05, "loss": 0.45, "num_tokens": 383621721.0, "step": 64250 }, { "epoch": 0.6855109726563751, "grad_norm": 0.9624536282885201, "learning_rate": 1.611073496115409e-05, "loss": 0.5505, "num_tokens": 383650538.0, "step": 64255 }, { "epoch": 0.6855643156625735, "grad_norm": 1.20175190610064, "learning_rate": 1.610731213024664e-05, "loss": 0.58, "num_tokens": 383677188.0, "step": 64260 }, { "epoch": 0.6856176586687719, "grad_norm": 1.4066196984592747, "learning_rate": 1.6103889653856245e-05, "loss": 0.4278, "num_tokens": 383706925.0, "step": 64265 }, { "epoch": 0.6856710016749704, "grad_norm": 1.2470869893340786, "learning_rate": 1.610046753208938e-05, "loss": 0.4119, "num_tokens": 383724521.0, "step": 64270 }, { "epoch": 0.6857243446811688, "grad_norm": 0.8384925820613234, "learning_rate": 1.6097045765052553e-05, "loss": 0.4534, "num_tokens": 383752337.0, "step": 64275 }, { "epoch": 0.6857776876873674, "grad_norm": 1.3310571306332957, "learning_rate": 1.6093624352852256e-05, "loss": 0.6082, "num_tokens": 383784745.0, "step": 64280 }, { "epoch": 0.6858310306935658, "grad_norm": 0.6869519532642228, "learning_rate": 1.609020329559493e-05, "loss": 0.5815, "num_tokens": 383804283.0, "step": 64285 }, { "epoch": 0.6858843736997642, "grad_norm": 0.9388336210496503, "learning_rate": 1.6086782593387034e-05, "loss": 0.4354, "num_tokens": 383832047.0, "step": 64290 }, { "epoch": 0.6859377167059627, "grad_norm": 1.2229878787240764, "learning_rate": 1.608336224633503e-05, "loss": 0.563, "num_tokens": 383867321.0, "step": 64295 }, { "epoch": 0.6859910597121611, "grad_norm": 1.0894122023538884, "learning_rate": 1.6079942254545337e-05, "loss": 0.4955, "num_tokens": 383897598.0, "step": 64300 }, { "epoch": 0.6860444027183596, "grad_norm": 1.3043576759779516, "learning_rate": 1.6076522618124378e-05, "loss": 0.4331, "num_tokens": 383923486.0, "step": 64305 }, { "epoch": 0.6860977457245581, "grad_norm": 1.18267621750551, "learning_rate": 1.6073103337178583e-05, "loss": 0.5305, "num_tokens": 383954734.0, "step": 64310 }, { "epoch": 0.6861510887307565, "grad_norm": 0.7437478873806377, "learning_rate": 1.606968441181433e-05, "loss": 0.5222, "num_tokens": 383983104.0, "step": 64315 }, { "epoch": 0.686204431736955, "grad_norm": 0.7997256093572607, "learning_rate": 1.606626584213803e-05, "loss": 0.5216, "num_tokens": 384011945.0, "step": 64320 }, { "epoch": 0.6862577747431534, "grad_norm": 0.7925659385927613, "learning_rate": 1.606284762825605e-05, "loss": 0.5578, "num_tokens": 384035206.0, "step": 64325 }, { "epoch": 0.6863111177493518, "grad_norm": 0.8563651795481202, "learning_rate": 1.6059429770274754e-05, "loss": 0.4578, "num_tokens": 384053058.0, "step": 64330 }, { "epoch": 0.6863644607555504, "grad_norm": 0.8332170879103995, "learning_rate": 1.6056012268300498e-05, "loss": 0.3773, "num_tokens": 384075762.0, "step": 64335 }, { "epoch": 0.6864178037617488, "grad_norm": 1.002628789501686, "learning_rate": 1.6052595122439645e-05, "loss": 0.4935, "num_tokens": 384116965.0, "step": 64340 }, { "epoch": 0.6864711467679473, "grad_norm": 0.8348546046438486, "learning_rate": 1.604917833279851e-05, "loss": 0.5068, "num_tokens": 384157067.0, "step": 64345 }, { "epoch": 0.6865244897741457, "grad_norm": 1.2765202362852401, "learning_rate": 1.6045761899483424e-05, "loss": 0.386, "num_tokens": 384183538.0, "step": 64350 }, { "epoch": 0.6865778327803441, "grad_norm": 1.020664858188358, "learning_rate": 1.6042345822600712e-05, "loss": 0.4349, "num_tokens": 384206215.0, "step": 64355 }, { "epoch": 0.6866311757865426, "grad_norm": 0.9581429895505489, "learning_rate": 1.6038930102256662e-05, "loss": 0.5166, "num_tokens": 384226921.0, "step": 64360 }, { "epoch": 0.6866845187927411, "grad_norm": 0.9063062480040543, "learning_rate": 1.603551473855755e-05, "loss": 0.4481, "num_tokens": 384250758.0, "step": 64365 }, { "epoch": 0.6867378617989396, "grad_norm": 0.8139622948788751, "learning_rate": 1.6032099731609688e-05, "loss": 0.5256, "num_tokens": 384277096.0, "step": 64370 }, { "epoch": 0.686791204805138, "grad_norm": 0.917968475430627, "learning_rate": 1.6028685081519315e-05, "loss": 0.4674, "num_tokens": 384315961.0, "step": 64375 }, { "epoch": 0.6868445478113364, "grad_norm": 0.7579848416476934, "learning_rate": 1.60252707883927e-05, "loss": 0.4292, "num_tokens": 384340486.0, "step": 64380 }, { "epoch": 0.6868978908175349, "grad_norm": 0.9247912099545498, "learning_rate": 1.602185685233609e-05, "loss": 0.48, "num_tokens": 384374089.0, "step": 64385 }, { "epoch": 0.6869512338237334, "grad_norm": 1.008192180021215, "learning_rate": 1.601844327345572e-05, "loss": 0.4822, "num_tokens": 384402779.0, "step": 64390 }, { "epoch": 0.6870045768299319, "grad_norm": 0.8327427003511508, "learning_rate": 1.6015030051857817e-05, "loss": 0.416, "num_tokens": 384421382.0, "step": 64395 }, { "epoch": 0.6870579198361303, "grad_norm": 1.0974200979462632, "learning_rate": 1.6011617187648587e-05, "loss": 0.5509, "num_tokens": 384458245.0, "step": 64400 }, { "epoch": 0.6871112628423287, "grad_norm": 0.635014775095794, "learning_rate": 1.6008204680934223e-05, "loss": 0.4872, "num_tokens": 384478652.0, "step": 64405 }, { "epoch": 0.6871646058485272, "grad_norm": 0.8945152676267555, "learning_rate": 1.6004792531820923e-05, "loss": 0.5203, "num_tokens": 384517841.0, "step": 64410 }, { "epoch": 0.6872179488547256, "grad_norm": 1.082418974354456, "learning_rate": 1.6001380740414878e-05, "loss": 0.5939, "num_tokens": 384541990.0, "step": 64415 }, { "epoch": 0.6872712918609241, "grad_norm": 0.7835941921201877, "learning_rate": 1.5997969306822235e-05, "loss": 0.4712, "num_tokens": 384564460.0, "step": 64420 }, { "epoch": 0.6873246348671226, "grad_norm": 0.7238202013705362, "learning_rate": 1.5994558231149165e-05, "loss": 0.447, "num_tokens": 384598739.0, "step": 64425 }, { "epoch": 0.687377977873321, "grad_norm": 0.8011509534966538, "learning_rate": 1.5991147513501817e-05, "loss": 0.4563, "num_tokens": 384628731.0, "step": 64430 }, { "epoch": 0.6874313208795195, "grad_norm": 0.6631743297738948, "learning_rate": 1.5987737153986315e-05, "loss": 0.4612, "num_tokens": 384675377.0, "step": 64435 }, { "epoch": 0.6874846638857179, "grad_norm": 0.7907804563164587, "learning_rate": 1.5984327152708784e-05, "loss": 0.5062, "num_tokens": 384703278.0, "step": 64440 }, { "epoch": 0.6875380068919164, "grad_norm": 0.8719488760340393, "learning_rate": 1.5980917509775342e-05, "loss": 0.4346, "num_tokens": 384739347.0, "step": 64445 }, { "epoch": 0.6875913498981149, "grad_norm": 0.9328390551433503, "learning_rate": 1.597750822529208e-05, "loss": 0.4752, "num_tokens": 384766036.0, "step": 64450 }, { "epoch": 0.6876446929043133, "grad_norm": 0.9214293037352443, "learning_rate": 1.5974099299365093e-05, "loss": 0.5421, "num_tokens": 384780688.0, "step": 64455 }, { "epoch": 0.6876980359105118, "grad_norm": 0.8045792912401307, "learning_rate": 1.597069073210047e-05, "loss": 0.3749, "num_tokens": 384811821.0, "step": 64460 }, { "epoch": 0.6877513789167102, "grad_norm": 0.8379221808060392, "learning_rate": 1.596728252360426e-05, "loss": 0.4879, "num_tokens": 384840688.0, "step": 64465 }, { "epoch": 0.6878047219229086, "grad_norm": 0.5338286697191242, "learning_rate": 1.5963874673982538e-05, "loss": 0.4781, "num_tokens": 384872566.0, "step": 64470 }, { "epoch": 0.6878580649291072, "grad_norm": 1.088338515456457, "learning_rate": 1.596046718334134e-05, "loss": 0.4944, "num_tokens": 384910162.0, "step": 64475 }, { "epoch": 0.6879114079353056, "grad_norm": 0.8972567418072256, "learning_rate": 1.5957060051786694e-05, "loss": 0.4301, "num_tokens": 384936518.0, "step": 64480 }, { "epoch": 0.6879647509415041, "grad_norm": 0.8372144551957867, "learning_rate": 1.5953653279424623e-05, "loss": 0.5586, "num_tokens": 384975167.0, "step": 64485 }, { "epoch": 0.6880180939477025, "grad_norm": 0.6194817725522203, "learning_rate": 1.595024686636116e-05, "loss": 0.3985, "num_tokens": 385012017.0, "step": 64490 }, { "epoch": 0.6880714369539009, "grad_norm": 1.188571597865724, "learning_rate": 1.594684081270228e-05, "loss": 0.4766, "num_tokens": 385047123.0, "step": 64495 }, { "epoch": 0.6881247799600995, "grad_norm": 0.9765826739882771, "learning_rate": 1.594343511855399e-05, "loss": 0.5228, "num_tokens": 385076823.0, "step": 64500 }, { "epoch": 0.6881781229662979, "grad_norm": 0.6075529808592315, "learning_rate": 1.5940029784022264e-05, "loss": 0.5563, "num_tokens": 385119354.0, "step": 64505 }, { "epoch": 0.6882314659724963, "grad_norm": 1.2862722187102125, "learning_rate": 1.5936624809213056e-05, "loss": 0.5045, "num_tokens": 385162224.0, "step": 64510 }, { "epoch": 0.6882848089786948, "grad_norm": 0.8239438104384775, "learning_rate": 1.5933220194232336e-05, "loss": 0.3262, "num_tokens": 385178138.0, "step": 64515 }, { "epoch": 0.6883381519848932, "grad_norm": 0.8318222447331188, "learning_rate": 1.592981593918604e-05, "loss": 0.5105, "num_tokens": 385216249.0, "step": 64520 }, { "epoch": 0.6883914949910918, "grad_norm": 0.7414382196494126, "learning_rate": 1.5926412044180117e-05, "loss": 0.3995, "num_tokens": 385238272.0, "step": 64525 }, { "epoch": 0.6884448379972902, "grad_norm": 0.8098538898260668, "learning_rate": 1.592300850932047e-05, "loss": 0.43, "num_tokens": 385261694.0, "step": 64530 }, { "epoch": 0.6884981810034886, "grad_norm": 1.1830651484061658, "learning_rate": 1.5919605334713024e-05, "loss": 0.3973, "num_tokens": 385283483.0, "step": 64535 }, { "epoch": 0.6885515240096871, "grad_norm": 1.1971517470106823, "learning_rate": 1.5916202520463674e-05, "loss": 0.4839, "num_tokens": 385305508.0, "step": 64540 }, { "epoch": 0.6886048670158855, "grad_norm": 0.7600567891495256, "learning_rate": 1.5912800066678303e-05, "loss": 0.495, "num_tokens": 385328939.0, "step": 64545 }, { "epoch": 0.688658210022084, "grad_norm": 1.469286194840878, "learning_rate": 1.590939797346279e-05, "loss": 0.4154, "num_tokens": 385343282.0, "step": 64550 }, { "epoch": 0.6887115530282825, "grad_norm": 0.8759639683899096, "learning_rate": 1.590599624092301e-05, "loss": 0.4286, "num_tokens": 385365860.0, "step": 64555 }, { "epoch": 0.6887648960344809, "grad_norm": 0.6290938682612065, "learning_rate": 1.590259486916481e-05, "loss": 0.5695, "num_tokens": 385410611.0, "step": 64560 }, { "epoch": 0.6888182390406794, "grad_norm": 1.4706402981657545, "learning_rate": 1.5899193858294033e-05, "loss": 0.5448, "num_tokens": 385426586.0, "step": 64565 }, { "epoch": 0.6888715820468778, "grad_norm": 0.7632318392909353, "learning_rate": 1.589579320841652e-05, "loss": 0.5411, "num_tokens": 385458369.0, "step": 64570 }, { "epoch": 0.6889249250530763, "grad_norm": 0.8303351289903441, "learning_rate": 1.5892392919638093e-05, "loss": 0.4611, "num_tokens": 385481485.0, "step": 64575 }, { "epoch": 0.6889782680592748, "grad_norm": 0.8611431077714297, "learning_rate": 1.5888992992064545e-05, "loss": 0.4439, "num_tokens": 385513568.0, "step": 64580 }, { "epoch": 0.6890316110654732, "grad_norm": 0.8766531621933901, "learning_rate": 1.5885593425801687e-05, "loss": 0.3823, "num_tokens": 385536797.0, "step": 64585 }, { "epoch": 0.6890849540716717, "grad_norm": 2.237760905130457, "learning_rate": 1.5882194220955306e-05, "loss": 0.4871, "num_tokens": 385564728.0, "step": 64590 }, { "epoch": 0.6891382970778701, "grad_norm": 0.8027972745554476, "learning_rate": 1.587879537763117e-05, "loss": 0.4686, "num_tokens": 385589047.0, "step": 64595 }, { "epoch": 0.6891916400840685, "grad_norm": 0.698909811844006, "learning_rate": 1.5875396895935066e-05, "loss": 0.4976, "num_tokens": 385617796.0, "step": 64600 }, { "epoch": 0.689244983090267, "grad_norm": 0.8146327393646529, "learning_rate": 1.587199877597272e-05, "loss": 0.4846, "num_tokens": 385646582.0, "step": 64605 }, { "epoch": 0.6892983260964655, "grad_norm": 0.6818824094200825, "learning_rate": 1.58686010178499e-05, "loss": 0.6453, "num_tokens": 385699515.0, "step": 64610 }, { "epoch": 0.689351669102664, "grad_norm": 0.9848045282642794, "learning_rate": 1.586520362167232e-05, "loss": 0.4632, "num_tokens": 385725228.0, "step": 64615 }, { "epoch": 0.6894050121088624, "grad_norm": 1.4639635602508043, "learning_rate": 1.5861806587545696e-05, "loss": 0.458, "num_tokens": 385737335.0, "step": 64620 }, { "epoch": 0.6894583551150608, "grad_norm": 0.9972734204820538, "learning_rate": 1.585840991557575e-05, "loss": 0.5753, "num_tokens": 385767172.0, "step": 64625 }, { "epoch": 0.6895116981212593, "grad_norm": 1.0068753706324236, "learning_rate": 1.5855013605868178e-05, "loss": 0.5422, "num_tokens": 385787589.0, "step": 64630 }, { "epoch": 0.6895650411274578, "grad_norm": 0.8282439170641279, "learning_rate": 1.5851617658528657e-05, "loss": 0.4334, "num_tokens": 385816700.0, "step": 64635 }, { "epoch": 0.6896183841336563, "grad_norm": 0.8242378876540785, "learning_rate": 1.5848222073662873e-05, "loss": 0.4698, "num_tokens": 385837297.0, "step": 64640 }, { "epoch": 0.6896717271398547, "grad_norm": 1.667429338402921, "learning_rate": 1.5844826851376487e-05, "loss": 0.4963, "num_tokens": 385859805.0, "step": 64645 }, { "epoch": 0.6897250701460531, "grad_norm": 0.5974860752955696, "learning_rate": 1.5841431991775152e-05, "loss": 0.4063, "num_tokens": 385892230.0, "step": 64650 }, { "epoch": 0.6897784131522516, "grad_norm": 1.169859766664847, "learning_rate": 1.5838037494964497e-05, "loss": 0.5266, "num_tokens": 385912124.0, "step": 64655 }, { "epoch": 0.68983175615845, "grad_norm": 0.49331258879577244, "learning_rate": 1.5834643361050166e-05, "loss": 0.3817, "num_tokens": 385942286.0, "step": 64660 }, { "epoch": 0.6898850991646486, "grad_norm": 0.7359638627175861, "learning_rate": 1.5831249590137767e-05, "loss": 0.338, "num_tokens": 385960112.0, "step": 64665 }, { "epoch": 0.689938442170847, "grad_norm": 0.7446793692645741, "learning_rate": 1.5827856182332913e-05, "loss": 0.4699, "num_tokens": 385987520.0, "step": 64670 }, { "epoch": 0.6899917851770454, "grad_norm": 2.14917872831539, "learning_rate": 1.5824463137741207e-05, "loss": 0.4916, "num_tokens": 386007030.0, "step": 64675 }, { "epoch": 0.6900451281832439, "grad_norm": 1.0595617542713518, "learning_rate": 1.5821070456468218e-05, "loss": 0.4389, "num_tokens": 386050963.0, "step": 64680 }, { "epoch": 0.6900984711894423, "grad_norm": 0.606742774860143, "learning_rate": 1.5817678138619536e-05, "loss": 0.4581, "num_tokens": 386087862.0, "step": 64685 }, { "epoch": 0.6901518141956408, "grad_norm": 0.6883504621318178, "learning_rate": 1.581428618430071e-05, "loss": 0.5475, "num_tokens": 386134803.0, "step": 64690 }, { "epoch": 0.6902051572018393, "grad_norm": 0.6304502968232671, "learning_rate": 1.5810894593617286e-05, "loss": 0.4129, "num_tokens": 386160215.0, "step": 64695 }, { "epoch": 0.6902585002080377, "grad_norm": 0.995446719493563, "learning_rate": 1.580750336667482e-05, "loss": 0.5874, "num_tokens": 386186084.0, "step": 64700 }, { "epoch": 0.6903118432142362, "grad_norm": 0.766216051766411, "learning_rate": 1.5804112503578837e-05, "loss": 0.4622, "num_tokens": 386217716.0, "step": 64705 }, { "epoch": 0.6903651862204346, "grad_norm": 0.7013317797376388, "learning_rate": 1.5800722004434837e-05, "loss": 0.4153, "num_tokens": 386252657.0, "step": 64710 }, { "epoch": 0.690418529226633, "grad_norm": 0.8666406637943361, "learning_rate": 1.579733186934834e-05, "loss": 0.4952, "num_tokens": 386289107.0, "step": 64715 }, { "epoch": 0.6904718722328316, "grad_norm": 0.7281656032192986, "learning_rate": 1.5793942098424845e-05, "loss": 0.563, "num_tokens": 386311498.0, "step": 64720 }, { "epoch": 0.69052521523903, "grad_norm": 0.6091305342359683, "learning_rate": 1.579055269176983e-05, "loss": 0.4324, "num_tokens": 386352233.0, "step": 64725 }, { "epoch": 0.6905785582452285, "grad_norm": 0.9042390554579969, "learning_rate": 1.578716364948875e-05, "loss": 0.4838, "num_tokens": 386373148.0, "step": 64730 }, { "epoch": 0.6906319012514269, "grad_norm": 1.2163225321415378, "learning_rate": 1.5783774971687088e-05, "loss": 0.5873, "num_tokens": 386411225.0, "step": 64735 }, { "epoch": 0.6906852442576253, "grad_norm": 0.5173154348132748, "learning_rate": 1.5780386658470275e-05, "loss": 0.5047, "num_tokens": 386456981.0, "step": 64740 }, { "epoch": 0.6907385872638239, "grad_norm": 0.750926949910115, "learning_rate": 1.5776998709943758e-05, "loss": 0.5013, "num_tokens": 386498093.0, "step": 64745 }, { "epoch": 0.6907919302700223, "grad_norm": 1.6219463894095487, "learning_rate": 1.577361112621297e-05, "loss": 0.4628, "num_tokens": 386507673.0, "step": 64750 }, { "epoch": 0.6908452732762208, "grad_norm": 0.6278539235552112, "learning_rate": 1.577022390738331e-05, "loss": 0.434, "num_tokens": 386537999.0, "step": 64755 }, { "epoch": 0.6908986162824192, "grad_norm": 1.5274627299665855, "learning_rate": 1.576683705356019e-05, "loss": 0.5034, "num_tokens": 386572006.0, "step": 64760 }, { "epoch": 0.6909519592886176, "grad_norm": 3.315429262347815, "learning_rate": 1.576345056484901e-05, "loss": 0.6183, "num_tokens": 386604213.0, "step": 64765 }, { "epoch": 0.6910053022948162, "grad_norm": 1.4549725613829987, "learning_rate": 1.576006444135512e-05, "loss": 0.5021, "num_tokens": 386626049.0, "step": 64770 }, { "epoch": 0.6910586453010146, "grad_norm": 1.1550695935375161, "learning_rate": 1.575667868318392e-05, "loss": 0.5366, "num_tokens": 386647062.0, "step": 64775 }, { "epoch": 0.691111988307213, "grad_norm": 0.6286856246469704, "learning_rate": 1.575329329044076e-05, "loss": 0.4621, "num_tokens": 386676508.0, "step": 64780 }, { "epoch": 0.6911653313134115, "grad_norm": 1.0351794625053936, "learning_rate": 1.5749908263230984e-05, "loss": 0.515, "num_tokens": 386709803.0, "step": 64785 }, { "epoch": 0.6912186743196099, "grad_norm": 0.708758187803154, "learning_rate": 1.574652360165993e-05, "loss": 0.5129, "num_tokens": 386749071.0, "step": 64790 }, { "epoch": 0.6912720173258085, "grad_norm": 0.8138596635480929, "learning_rate": 1.574313930583291e-05, "loss": 0.4355, "num_tokens": 386779741.0, "step": 64795 }, { "epoch": 0.6913253603320069, "grad_norm": 0.6272981460366914, "learning_rate": 1.573975537585526e-05, "loss": 0.5378, "num_tokens": 386806367.0, "step": 64800 }, { "epoch": 0.6913787033382053, "grad_norm": 0.8643454685761168, "learning_rate": 1.573637181183225e-05, "loss": 0.5016, "num_tokens": 386840184.0, "step": 64805 }, { "epoch": 0.6914320463444038, "grad_norm": 0.9598006527203871, "learning_rate": 1.5732988613869202e-05, "loss": 0.5175, "num_tokens": 386858347.0, "step": 64810 }, { "epoch": 0.6914853893506022, "grad_norm": 0.8670960446969065, "learning_rate": 1.5729605782071364e-05, "loss": 0.4912, "num_tokens": 386897793.0, "step": 64815 }, { "epoch": 0.6915387323568007, "grad_norm": 0.8661235288537008, "learning_rate": 1.572622331654402e-05, "loss": 0.5019, "num_tokens": 386927960.0, "step": 64820 }, { "epoch": 0.6915920753629992, "grad_norm": 0.6453149462960055, "learning_rate": 1.572284121739243e-05, "loss": 0.4567, "num_tokens": 386953894.0, "step": 64825 }, { "epoch": 0.6916454183691976, "grad_norm": 0.7964344606762153, "learning_rate": 1.5719459484721833e-05, "loss": 0.4661, "num_tokens": 386984523.0, "step": 64830 }, { "epoch": 0.6916987613753961, "grad_norm": 0.8003610102583063, "learning_rate": 1.5716078118637444e-05, "loss": 0.5344, "num_tokens": 387013589.0, "step": 64835 }, { "epoch": 0.6917521043815945, "grad_norm": 0.857128926242234, "learning_rate": 1.5712697119244514e-05, "loss": 0.4452, "num_tokens": 387048444.0, "step": 64840 }, { "epoch": 0.691805447387793, "grad_norm": 0.9945713089279158, "learning_rate": 1.5709316486648224e-05, "loss": 0.4659, "num_tokens": 387068584.0, "step": 64845 }, { "epoch": 0.6918587903939915, "grad_norm": 0.7271113567950573, "learning_rate": 1.570593622095379e-05, "loss": 0.4766, "num_tokens": 387106905.0, "step": 64850 }, { "epoch": 0.6919121334001899, "grad_norm": 0.8042674647629134, "learning_rate": 1.5702556322266405e-05, "loss": 0.4861, "num_tokens": 387133371.0, "step": 64855 }, { "epoch": 0.6919654764063884, "grad_norm": 1.0880904238001745, "learning_rate": 1.5699176790691224e-05, "loss": 0.4485, "num_tokens": 387154273.0, "step": 64860 }, { "epoch": 0.6920188194125868, "grad_norm": 0.778520321347236, "learning_rate": 1.5695797626333425e-05, "loss": 0.5469, "num_tokens": 387201601.0, "step": 64865 }, { "epoch": 0.6920721624187852, "grad_norm": 0.8153102242249362, "learning_rate": 1.5692418829298163e-05, "loss": 0.5365, "num_tokens": 387235043.0, "step": 64870 }, { "epoch": 0.6921255054249837, "grad_norm": 0.793493536922967, "learning_rate": 1.5689040399690566e-05, "loss": 0.571, "num_tokens": 387260702.0, "step": 64875 }, { "epoch": 0.6921788484311822, "grad_norm": 3.012936713808447, "learning_rate": 1.568566233761577e-05, "loss": 0.4902, "num_tokens": 387296986.0, "step": 64880 }, { "epoch": 0.6922321914373807, "grad_norm": 0.8249313399922509, "learning_rate": 1.56822846431789e-05, "loss": 0.5717, "num_tokens": 387330417.0, "step": 64885 }, { "epoch": 0.6922855344435791, "grad_norm": 0.8192368257678793, "learning_rate": 1.5678907316485054e-05, "loss": 0.5273, "num_tokens": 387370254.0, "step": 64890 }, { "epoch": 0.6923388774497775, "grad_norm": 0.9659187490503065, "learning_rate": 1.5675530357639328e-05, "loss": 0.54, "num_tokens": 387398680.0, "step": 64895 }, { "epoch": 0.692392220455976, "grad_norm": 0.994344208665864, "learning_rate": 1.5672153766746818e-05, "loss": 0.4684, "num_tokens": 387420108.0, "step": 64900 }, { "epoch": 0.6924455634621745, "grad_norm": 1.1393100661416722, "learning_rate": 1.566877754391259e-05, "loss": 0.5058, "num_tokens": 387446813.0, "step": 64905 }, { "epoch": 0.692498906468373, "grad_norm": 1.164329611715064, "learning_rate": 1.5665401689241694e-05, "loss": 0.5294, "num_tokens": 387483216.0, "step": 64910 }, { "epoch": 0.6925522494745714, "grad_norm": 1.4643896340777975, "learning_rate": 1.5662026202839195e-05, "loss": 0.4941, "num_tokens": 387505144.0, "step": 64915 }, { "epoch": 0.6926055924807698, "grad_norm": 0.8768669962943675, "learning_rate": 1.5658651084810118e-05, "loss": 0.5009, "num_tokens": 387530432.0, "step": 64920 }, { "epoch": 0.6926589354869683, "grad_norm": 1.1289684587204172, "learning_rate": 1.5655276335259493e-05, "loss": 0.3891, "num_tokens": 387555257.0, "step": 64925 }, { "epoch": 0.6927122784931667, "grad_norm": 0.7534967408463228, "learning_rate": 1.565190195429235e-05, "loss": 0.3788, "num_tokens": 387578907.0, "step": 64930 }, { "epoch": 0.6927656214993653, "grad_norm": 0.9427415919250588, "learning_rate": 1.5648527942013674e-05, "loss": 0.5121, "num_tokens": 387600547.0, "step": 64935 }, { "epoch": 0.6928189645055637, "grad_norm": 0.8923872304921685, "learning_rate": 1.564515429852847e-05, "loss": 0.566, "num_tokens": 387627070.0, "step": 64940 }, { "epoch": 0.6928723075117621, "grad_norm": 1.063402693086085, "learning_rate": 1.5641781023941716e-05, "loss": 0.3731, "num_tokens": 387644578.0, "step": 64945 }, { "epoch": 0.6929256505179606, "grad_norm": 0.5192346113386573, "learning_rate": 1.5638408118358368e-05, "loss": 0.3832, "num_tokens": 387668467.0, "step": 64950 }, { "epoch": 0.692978993524159, "grad_norm": 3.6529545591506176, "learning_rate": 1.56350355818834e-05, "loss": 0.5738, "num_tokens": 387693424.0, "step": 64955 }, { "epoch": 0.6930323365303575, "grad_norm": 0.9494208405390563, "learning_rate": 1.5631663414621757e-05, "loss": 0.4717, "num_tokens": 387718762.0, "step": 64960 }, { "epoch": 0.693085679536556, "grad_norm": 1.2420708633138364, "learning_rate": 1.5628291616678366e-05, "loss": 0.5573, "num_tokens": 387757152.0, "step": 64965 }, { "epoch": 0.6931390225427544, "grad_norm": 1.0379263044037552, "learning_rate": 1.562492018815815e-05, "loss": 0.5306, "num_tokens": 387782087.0, "step": 64970 }, { "epoch": 0.6931923655489529, "grad_norm": 0.8346312000341916, "learning_rate": 1.5621549129166036e-05, "loss": 0.4432, "num_tokens": 387815529.0, "step": 64975 }, { "epoch": 0.6932457085551513, "grad_norm": 0.7884785946851999, "learning_rate": 1.561817843980691e-05, "loss": 0.3854, "num_tokens": 387835092.0, "step": 64980 }, { "epoch": 0.6932990515613497, "grad_norm": 0.5119004666617267, "learning_rate": 1.5614808120185664e-05, "loss": 0.4357, "num_tokens": 387874332.0, "step": 64985 }, { "epoch": 0.6933523945675483, "grad_norm": 2.2466735707626233, "learning_rate": 1.5611438170407184e-05, "loss": 0.5796, "num_tokens": 387888260.0, "step": 64990 }, { "epoch": 0.6934057375737467, "grad_norm": 0.7641287175621122, "learning_rate": 1.5608068590576317e-05, "loss": 0.4746, "num_tokens": 387923324.0, "step": 64995 }, { "epoch": 0.6934590805799452, "grad_norm": 1.036800109724976, "learning_rate": 1.5604699380797926e-05, "loss": 0.5243, "num_tokens": 387951166.0, "step": 65000 }, { "epoch": 0.6935124235861436, "grad_norm": 0.8664276329519455, "learning_rate": 1.560133054117687e-05, "loss": 0.4597, "num_tokens": 387972145.0, "step": 65005 }, { "epoch": 0.693565766592342, "grad_norm": 1.1023283201400833, "learning_rate": 1.559796207181796e-05, "loss": 0.4591, "num_tokens": 387999194.0, "step": 65010 }, { "epoch": 0.6936191095985406, "grad_norm": 0.9953530964729926, "learning_rate": 1.5594593972826026e-05, "loss": 0.537, "num_tokens": 388022457.0, "step": 65015 }, { "epoch": 0.693672452604739, "grad_norm": 1.1014323608984546, "learning_rate": 1.5591226244305876e-05, "loss": 0.476, "num_tokens": 388044812.0, "step": 65020 }, { "epoch": 0.6937257956109375, "grad_norm": 0.9422469484580002, "learning_rate": 1.5587858886362295e-05, "loss": 0.4369, "num_tokens": 388065664.0, "step": 65025 }, { "epoch": 0.6937791386171359, "grad_norm": 1.1704937004932816, "learning_rate": 1.5584491899100078e-05, "loss": 0.5325, "num_tokens": 388109583.0, "step": 65030 }, { "epoch": 0.6938324816233343, "grad_norm": 0.6581753027207492, "learning_rate": 1.5581125282624006e-05, "loss": 0.4812, "num_tokens": 388141149.0, "step": 65035 }, { "epoch": 0.6938858246295329, "grad_norm": 0.9360330448361676, "learning_rate": 1.5577759037038826e-05, "loss": 0.4408, "num_tokens": 388162723.0, "step": 65040 }, { "epoch": 0.6939391676357313, "grad_norm": 0.6627322685828727, "learning_rate": 1.557439316244929e-05, "loss": 0.6091, "num_tokens": 388206363.0, "step": 65045 }, { "epoch": 0.6939925106419297, "grad_norm": 0.7514529968694664, "learning_rate": 1.5571027658960158e-05, "loss": 0.4384, "num_tokens": 388241125.0, "step": 65050 }, { "epoch": 0.6940458536481282, "grad_norm": 0.7477690606262858, "learning_rate": 1.5567662526676138e-05, "loss": 0.53, "num_tokens": 388273018.0, "step": 65055 }, { "epoch": 0.6940991966543266, "grad_norm": 0.8640868660569901, "learning_rate": 1.5564297765701943e-05, "loss": 0.4575, "num_tokens": 388303086.0, "step": 65060 }, { "epoch": 0.6941525396605251, "grad_norm": 1.072155780460685, "learning_rate": 1.5560933376142296e-05, "loss": 0.4123, "num_tokens": 388334289.0, "step": 65065 }, { "epoch": 0.6942058826667236, "grad_norm": 1.6341986558594925, "learning_rate": 1.5557569358101868e-05, "loss": 0.5196, "num_tokens": 388358312.0, "step": 65070 }, { "epoch": 0.694259225672922, "grad_norm": 1.1128367322496107, "learning_rate": 1.555420571168535e-05, "loss": 0.4296, "num_tokens": 388384863.0, "step": 65075 }, { "epoch": 0.6943125686791205, "grad_norm": 0.6620960368112385, "learning_rate": 1.5550842436997425e-05, "loss": 0.4891, "num_tokens": 388424151.0, "step": 65080 }, { "epoch": 0.6943659116853189, "grad_norm": 0.7712637828885552, "learning_rate": 1.554747953414273e-05, "loss": 0.5083, "num_tokens": 388450753.0, "step": 65085 }, { "epoch": 0.6944192546915174, "grad_norm": 1.1661930649713794, "learning_rate": 1.5544117003225924e-05, "loss": 0.5917, "num_tokens": 388477370.0, "step": 65090 }, { "epoch": 0.6944725976977159, "grad_norm": 2.0168902032382383, "learning_rate": 1.5540754844351647e-05, "loss": 0.6084, "num_tokens": 388520970.0, "step": 65095 }, { "epoch": 0.6945259407039143, "grad_norm": 0.838508858732102, "learning_rate": 1.55373930576245e-05, "loss": 0.3914, "num_tokens": 388554811.0, "step": 65100 }, { "epoch": 0.6945792837101128, "grad_norm": 1.3424037272414664, "learning_rate": 1.553403164314911e-05, "loss": 0.4296, "num_tokens": 388569151.0, "step": 65105 }, { "epoch": 0.6946326267163112, "grad_norm": 1.10202931271356, "learning_rate": 1.5530670601030085e-05, "loss": 0.5943, "num_tokens": 388584587.0, "step": 65110 }, { "epoch": 0.6946859697225097, "grad_norm": 0.955033741680779, "learning_rate": 1.5527309931372e-05, "loss": 0.4817, "num_tokens": 388612207.0, "step": 65115 }, { "epoch": 0.6947393127287081, "grad_norm": 0.8407434550138031, "learning_rate": 1.552394963427944e-05, "loss": 0.5389, "num_tokens": 388651899.0, "step": 65120 }, { "epoch": 0.6947926557349066, "grad_norm": 0.7775128137297765, "learning_rate": 1.552058970985697e-05, "loss": 0.5322, "num_tokens": 388682324.0, "step": 65125 }, { "epoch": 0.6948459987411051, "grad_norm": 0.6746747087145097, "learning_rate": 1.5517230158209136e-05, "loss": 0.4202, "num_tokens": 388717030.0, "step": 65130 }, { "epoch": 0.6948993417473035, "grad_norm": 0.7359496934217016, "learning_rate": 1.5513870979440486e-05, "loss": 0.5341, "num_tokens": 388753979.0, "step": 65135 }, { "epoch": 0.6949526847535019, "grad_norm": 1.1537542558214018, "learning_rate": 1.5510512173655557e-05, "loss": 0.441, "num_tokens": 388780981.0, "step": 65140 }, { "epoch": 0.6950060277597004, "grad_norm": 0.664852460394834, "learning_rate": 1.5507153740958853e-05, "loss": 0.5127, "num_tokens": 388817277.0, "step": 65145 }, { "epoch": 0.6950593707658989, "grad_norm": 0.7681216703949677, "learning_rate": 1.550379568145489e-05, "loss": 0.3949, "num_tokens": 388844303.0, "step": 65150 }, { "epoch": 0.6951127137720974, "grad_norm": 1.072762458921268, "learning_rate": 1.5500437995248178e-05, "loss": 0.4633, "num_tokens": 388861071.0, "step": 65155 }, { "epoch": 0.6951660567782958, "grad_norm": 0.8729264977177265, "learning_rate": 1.5497080682443183e-05, "loss": 0.4274, "num_tokens": 388884711.0, "step": 65160 }, { "epoch": 0.6952193997844942, "grad_norm": 1.4867238044009987, "learning_rate": 1.5493723743144377e-05, "loss": 0.4296, "num_tokens": 388919079.0, "step": 65165 }, { "epoch": 0.6952727427906927, "grad_norm": 0.9173126123577141, "learning_rate": 1.5490367177456235e-05, "loss": 0.4745, "num_tokens": 388950512.0, "step": 65170 }, { "epoch": 0.6953260857968911, "grad_norm": 1.002149244049923, "learning_rate": 1.5487010985483186e-05, "loss": 0.4909, "num_tokens": 388981349.0, "step": 65175 }, { "epoch": 0.6953794288030897, "grad_norm": 0.891964180009766, "learning_rate": 1.548365516732968e-05, "loss": 0.4833, "num_tokens": 389027842.0, "step": 65180 }, { "epoch": 0.6954327718092881, "grad_norm": 1.4411257055279991, "learning_rate": 1.5480299723100157e-05, "loss": 0.3629, "num_tokens": 389040759.0, "step": 65185 }, { "epoch": 0.6954861148154865, "grad_norm": 1.4321293916342883, "learning_rate": 1.5476944652899004e-05, "loss": 0.5815, "num_tokens": 389082074.0, "step": 65190 }, { "epoch": 0.695539457821685, "grad_norm": 0.8039402226797536, "learning_rate": 1.5473589956830644e-05, "loss": 0.489, "num_tokens": 389104297.0, "step": 65195 }, { "epoch": 0.6955928008278834, "grad_norm": 1.2037587365421145, "learning_rate": 1.547023563499947e-05, "loss": 0.4423, "num_tokens": 389128799.0, "step": 65200 }, { "epoch": 0.695646143834082, "grad_norm": 0.9085194039174578, "learning_rate": 1.5466881687509834e-05, "loss": 0.4148, "num_tokens": 389146139.0, "step": 65205 }, { "epoch": 0.6956994868402804, "grad_norm": 1.4125899383653149, "learning_rate": 1.546352811446613e-05, "loss": 0.5439, "num_tokens": 389165938.0, "step": 65210 }, { "epoch": 0.6957528298464788, "grad_norm": 0.7755360790028883, "learning_rate": 1.5460174915972715e-05, "loss": 0.4445, "num_tokens": 389185800.0, "step": 65215 }, { "epoch": 0.6958061728526773, "grad_norm": 1.066095094466799, "learning_rate": 1.5456822092133916e-05, "loss": 0.5562, "num_tokens": 389209602.0, "step": 65220 }, { "epoch": 0.6958595158588757, "grad_norm": 0.8015145810218205, "learning_rate": 1.5453469643054077e-05, "loss": 0.5162, "num_tokens": 389253160.0, "step": 65225 }, { "epoch": 0.6959128588650741, "grad_norm": 0.7608163569361742, "learning_rate": 1.5450117568837528e-05, "loss": 0.4256, "num_tokens": 389284772.0, "step": 65230 }, { "epoch": 0.6959662018712727, "grad_norm": 0.8144663766495956, "learning_rate": 1.544676586958857e-05, "loss": 0.4832, "num_tokens": 389313163.0, "step": 65235 }, { "epoch": 0.6960195448774711, "grad_norm": 0.9233254775957853, "learning_rate": 1.5443414545411488e-05, "loss": 0.4154, "num_tokens": 389336458.0, "step": 65240 }, { "epoch": 0.6960728878836696, "grad_norm": 0.6388991366159887, "learning_rate": 1.5440063596410593e-05, "loss": 0.4641, "num_tokens": 389365684.0, "step": 65245 }, { "epoch": 0.696126230889868, "grad_norm": 0.7039796799288859, "learning_rate": 1.5436713022690132e-05, "loss": 0.5083, "num_tokens": 389402499.0, "step": 65250 }, { "epoch": 0.6961795738960664, "grad_norm": 1.6692768375223943, "learning_rate": 1.5433362824354385e-05, "loss": 0.5626, "num_tokens": 389430428.0, "step": 65255 }, { "epoch": 0.696232916902265, "grad_norm": 1.1646351757330806, "learning_rate": 1.5430013001507616e-05, "loss": 0.5419, "num_tokens": 389474960.0, "step": 65260 }, { "epoch": 0.6962862599084634, "grad_norm": 1.0840276907347108, "learning_rate": 1.5426663554254035e-05, "loss": 0.4676, "num_tokens": 389493533.0, "step": 65265 }, { "epoch": 0.6963396029146619, "grad_norm": 1.1648739300304602, "learning_rate": 1.5423314482697897e-05, "loss": 0.4549, "num_tokens": 389525421.0, "step": 65270 }, { "epoch": 0.6963929459208603, "grad_norm": 1.0194235148724946, "learning_rate": 1.5419965786943402e-05, "loss": 0.4964, "num_tokens": 389553979.0, "step": 65275 }, { "epoch": 0.6964462889270587, "grad_norm": 0.8262897762539245, "learning_rate": 1.5416617467094757e-05, "loss": 0.3966, "num_tokens": 389586680.0, "step": 65280 }, { "epoch": 0.6964996319332573, "grad_norm": 1.2743433420348702, "learning_rate": 1.541326952325615e-05, "loss": 0.5242, "num_tokens": 389602911.0, "step": 65285 }, { "epoch": 0.6965529749394557, "grad_norm": 0.9051042323552827, "learning_rate": 1.540992195553178e-05, "loss": 0.4529, "num_tokens": 389621660.0, "step": 65290 }, { "epoch": 0.6966063179456542, "grad_norm": 1.0560673401660428, "learning_rate": 1.5406574764025797e-05, "loss": 0.4798, "num_tokens": 389663044.0, "step": 65295 }, { "epoch": 0.6966596609518526, "grad_norm": 1.798175403587031, "learning_rate": 1.540322794884237e-05, "loss": 0.4472, "num_tokens": 389684789.0, "step": 65300 }, { "epoch": 0.696713003958051, "grad_norm": 0.9494055869662091, "learning_rate": 1.5399881510085642e-05, "loss": 0.3999, "num_tokens": 389714071.0, "step": 65305 }, { "epoch": 0.6967663469642495, "grad_norm": 0.5780179667277782, "learning_rate": 1.539653544785975e-05, "loss": 0.4778, "num_tokens": 389756919.0, "step": 65310 }, { "epoch": 0.696819689970448, "grad_norm": 1.4857120236070447, "learning_rate": 1.539318976226881e-05, "loss": 0.4304, "num_tokens": 389784899.0, "step": 65315 }, { "epoch": 0.6968730329766464, "grad_norm": 0.8175512147821318, "learning_rate": 1.538984445341694e-05, "loss": 0.4678, "num_tokens": 389806937.0, "step": 65320 }, { "epoch": 0.6969263759828449, "grad_norm": 0.9854038233515552, "learning_rate": 1.5386499521408227e-05, "loss": 0.3987, "num_tokens": 389828139.0, "step": 65325 }, { "epoch": 0.6969797189890433, "grad_norm": 0.7003240989413642, "learning_rate": 1.538315496634677e-05, "loss": 0.5102, "num_tokens": 389872236.0, "step": 65330 }, { "epoch": 0.6970330619952418, "grad_norm": 0.5735351931823517, "learning_rate": 1.5379810788336646e-05, "loss": 0.4798, "num_tokens": 389918520.0, "step": 65335 }, { "epoch": 0.6970864050014403, "grad_norm": 0.9576472093037841, "learning_rate": 1.537646698748191e-05, "loss": 0.4622, "num_tokens": 389945043.0, "step": 65340 }, { "epoch": 0.6971397480076387, "grad_norm": 1.120866545040923, "learning_rate": 1.5373123563886628e-05, "loss": 0.4974, "num_tokens": 389965359.0, "step": 65345 }, { "epoch": 0.6971930910138372, "grad_norm": 0.9140257468850599, "learning_rate": 1.5369780517654826e-05, "loss": 0.519, "num_tokens": 389990219.0, "step": 65350 }, { "epoch": 0.6972464340200356, "grad_norm": 0.5732453904974263, "learning_rate": 1.5366437848890535e-05, "loss": 0.4798, "num_tokens": 390021664.0, "step": 65355 }, { "epoch": 0.6972997770262341, "grad_norm": 1.4521136684507718, "learning_rate": 1.536309555769777e-05, "loss": 0.5431, "num_tokens": 390048054.0, "step": 65360 }, { "epoch": 0.6973531200324325, "grad_norm": 1.067371349123713, "learning_rate": 1.5359753644180557e-05, "loss": 0.4499, "num_tokens": 390069560.0, "step": 65365 }, { "epoch": 0.697406463038631, "grad_norm": 1.2268175508534536, "learning_rate": 1.535641210844286e-05, "loss": 0.4945, "num_tokens": 390095030.0, "step": 65370 }, { "epoch": 0.6974598060448295, "grad_norm": 1.0295828255723047, "learning_rate": 1.5353070950588676e-05, "loss": 0.397, "num_tokens": 390118788.0, "step": 65375 }, { "epoch": 0.6975131490510279, "grad_norm": 0.9533774247756932, "learning_rate": 1.5349730170721983e-05, "loss": 0.4822, "num_tokens": 390161810.0, "step": 65380 }, { "epoch": 0.6975664920572264, "grad_norm": 0.8639479309933531, "learning_rate": 1.5346389768946727e-05, "loss": 0.557, "num_tokens": 390195562.0, "step": 65385 }, { "epoch": 0.6976198350634248, "grad_norm": 1.4027297066153177, "learning_rate": 1.534304974536685e-05, "loss": 0.3828, "num_tokens": 390219086.0, "step": 65390 }, { "epoch": 0.6976731780696233, "grad_norm": 0.7733251925066958, "learning_rate": 1.5339710100086306e-05, "loss": 0.522, "num_tokens": 390262111.0, "step": 65395 }, { "epoch": 0.6977265210758218, "grad_norm": 1.088705438481966, "learning_rate": 1.533637083320899e-05, "loss": 0.3909, "num_tokens": 390280559.0, "step": 65400 }, { "epoch": 0.6977798640820202, "grad_norm": 0.7903031606084281, "learning_rate": 1.5333031944838834e-05, "loss": 0.4472, "num_tokens": 390302069.0, "step": 65405 }, { "epoch": 0.6978332070882186, "grad_norm": 0.7630817872949325, "learning_rate": 1.5329693435079738e-05, "loss": 0.478, "num_tokens": 390359166.0, "step": 65410 }, { "epoch": 0.6978865500944171, "grad_norm": 1.0699487249522313, "learning_rate": 1.5326355304035588e-05, "loss": 0.5268, "num_tokens": 390385778.0, "step": 65415 }, { "epoch": 0.6979398931006155, "grad_norm": 1.2171929788250997, "learning_rate": 1.5323017551810244e-05, "loss": 0.4053, "num_tokens": 390406293.0, "step": 65420 }, { "epoch": 0.6979932361068141, "grad_norm": 0.8669727729134796, "learning_rate": 1.531968017850759e-05, "loss": 0.4153, "num_tokens": 390435143.0, "step": 65425 }, { "epoch": 0.6980465791130125, "grad_norm": 2.8498576054779994, "learning_rate": 1.5316343184231464e-05, "loss": 0.4533, "num_tokens": 390458970.0, "step": 65430 }, { "epoch": 0.6980999221192109, "grad_norm": 1.135614304244527, "learning_rate": 1.531300656908571e-05, "loss": 0.7377, "num_tokens": 390516638.0, "step": 65435 }, { "epoch": 0.6981532651254094, "grad_norm": 0.907784826180761, "learning_rate": 1.5309670333174164e-05, "loss": 0.4547, "num_tokens": 390546568.0, "step": 65440 }, { "epoch": 0.6982066081316078, "grad_norm": 1.2529777730202687, "learning_rate": 1.5306334476600634e-05, "loss": 0.4552, "num_tokens": 390569593.0, "step": 65445 }, { "epoch": 0.6982599511378064, "grad_norm": 0.8652211155567676, "learning_rate": 1.5302998999468934e-05, "loss": 0.4002, "num_tokens": 390594719.0, "step": 65450 }, { "epoch": 0.6983132941440048, "grad_norm": 1.487779578774866, "learning_rate": 1.5299663901882844e-05, "loss": 0.6447, "num_tokens": 390628285.0, "step": 65455 }, { "epoch": 0.6983666371502032, "grad_norm": 1.6813296864571106, "learning_rate": 1.529632918394616e-05, "loss": 0.5657, "num_tokens": 390650588.0, "step": 65460 }, { "epoch": 0.6984199801564017, "grad_norm": 1.1119446421643537, "learning_rate": 1.5292994845762643e-05, "loss": 0.5217, "num_tokens": 390688248.0, "step": 65465 }, { "epoch": 0.6984733231626001, "grad_norm": 0.7631675835821301, "learning_rate": 1.5289660887436047e-05, "loss": 0.5324, "num_tokens": 390735558.0, "step": 65470 }, { "epoch": 0.6985266661687987, "grad_norm": 0.8188111991493164, "learning_rate": 1.5286327309070132e-05, "loss": 0.4307, "num_tokens": 390766269.0, "step": 65475 }, { "epoch": 0.6985800091749971, "grad_norm": 0.7895273258669885, "learning_rate": 1.5282994110768616e-05, "loss": 0.5522, "num_tokens": 390806941.0, "step": 65480 }, { "epoch": 0.6986333521811955, "grad_norm": 0.6872863705364661, "learning_rate": 1.527966129263524e-05, "loss": 0.4796, "num_tokens": 390838843.0, "step": 65485 }, { "epoch": 0.698686695187394, "grad_norm": 1.131561783801457, "learning_rate": 1.5276328854773698e-05, "loss": 0.4766, "num_tokens": 390871620.0, "step": 65490 }, { "epoch": 0.6987400381935924, "grad_norm": 3.221145790233946, "learning_rate": 1.5272996797287685e-05, "loss": 0.6645, "num_tokens": 390900223.0, "step": 65495 }, { "epoch": 0.6987933811997908, "grad_norm": 0.9153150459888365, "learning_rate": 1.5269665120280903e-05, "loss": 0.5213, "num_tokens": 390950846.0, "step": 65500 }, { "epoch": 0.6988467242059894, "grad_norm": 0.7928987672557768, "learning_rate": 1.5266333823857025e-05, "loss": 0.4339, "num_tokens": 390983220.0, "step": 65505 }, { "epoch": 0.6989000672121878, "grad_norm": 1.0949802551667438, "learning_rate": 1.5263002908119705e-05, "loss": 0.4006, "num_tokens": 391006162.0, "step": 65510 }, { "epoch": 0.6989534102183863, "grad_norm": 0.6837166606794202, "learning_rate": 1.525967237317259e-05, "loss": 0.5616, "num_tokens": 391057641.0, "step": 65515 }, { "epoch": 0.6990067532245847, "grad_norm": 1.2467926175111077, "learning_rate": 1.5256342219119346e-05, "loss": 0.5235, "num_tokens": 391084870.0, "step": 65520 }, { "epoch": 0.6990600962307831, "grad_norm": 5.53009133106674, "learning_rate": 1.525301244606358e-05, "loss": 0.5488, "num_tokens": 391102404.0, "step": 65525 }, { "epoch": 0.6991134392369817, "grad_norm": 0.7990043046224251, "learning_rate": 1.5249683054108904e-05, "loss": 0.4045, "num_tokens": 391126599.0, "step": 65530 }, { "epoch": 0.6991667822431801, "grad_norm": 0.8061719820396239, "learning_rate": 1.524635404335893e-05, "loss": 0.5432, "num_tokens": 391164674.0, "step": 65535 }, { "epoch": 0.6992201252493786, "grad_norm": 4.6292283066677795, "learning_rate": 1.5243025413917247e-05, "loss": 0.4393, "num_tokens": 391186555.0, "step": 65540 }, { "epoch": 0.699273468255577, "grad_norm": 0.8387790748767179, "learning_rate": 1.5239697165887434e-05, "loss": 0.5496, "num_tokens": 391223827.0, "step": 65545 }, { "epoch": 0.6993268112617754, "grad_norm": 0.8615702938748286, "learning_rate": 1.523636929937307e-05, "loss": 0.5071, "num_tokens": 391247182.0, "step": 65550 }, { "epoch": 0.699380154267974, "grad_norm": 1.1288052678223992, "learning_rate": 1.5233041814477693e-05, "loss": 0.5313, "num_tokens": 391286329.0, "step": 65555 }, { "epoch": 0.6994334972741724, "grad_norm": 0.6123737962346155, "learning_rate": 1.5229714711304873e-05, "loss": 0.4681, "num_tokens": 391322532.0, "step": 65560 }, { "epoch": 0.6994868402803709, "grad_norm": 18.630363347513825, "learning_rate": 1.5226387989958122e-05, "loss": 0.7626, "num_tokens": 391344094.0, "step": 65565 }, { "epoch": 0.6995401832865693, "grad_norm": 0.9080707240518643, "learning_rate": 1.522306165054096e-05, "loss": 0.7216, "num_tokens": 391374385.0, "step": 65570 }, { "epoch": 0.6995935262927677, "grad_norm": 1.0050693991068256, "learning_rate": 1.52197356931569e-05, "loss": 0.5419, "num_tokens": 391389583.0, "step": 65575 }, { "epoch": 0.6996468692989662, "grad_norm": 1.6557237060093855, "learning_rate": 1.5216410117909449e-05, "loss": 0.429, "num_tokens": 391415015.0, "step": 65580 }, { "epoch": 0.6997002123051647, "grad_norm": 0.6661899323051993, "learning_rate": 1.5213084924902077e-05, "loss": 0.5708, "num_tokens": 391460478.0, "step": 65585 }, { "epoch": 0.6997535553113631, "grad_norm": 0.7202360516930848, "learning_rate": 1.5209760114238263e-05, "loss": 0.4793, "num_tokens": 391489059.0, "step": 65590 }, { "epoch": 0.6998068983175616, "grad_norm": 1.007380836370105, "learning_rate": 1.5206435686021476e-05, "loss": 0.5826, "num_tokens": 391530499.0, "step": 65595 }, { "epoch": 0.69986024132376, "grad_norm": 0.6923222727362567, "learning_rate": 1.5203111640355162e-05, "loss": 0.463, "num_tokens": 391567792.0, "step": 65600 }, { "epoch": 0.6999135843299585, "grad_norm": 2.642870650195674, "learning_rate": 1.5199787977342745e-05, "loss": 0.5218, "num_tokens": 391608093.0, "step": 65605 }, { "epoch": 0.699966927336157, "grad_norm": 1.1079754923050378, "learning_rate": 1.519646469708767e-05, "loss": 0.5852, "num_tokens": 391631103.0, "step": 65610 }, { "epoch": 0.7000202703423554, "grad_norm": 1.2251588448350712, "learning_rate": 1.5193141799693334e-05, "loss": 0.4228, "num_tokens": 391665476.0, "step": 65615 }, { "epoch": 0.7000736133485539, "grad_norm": 2.4462814916470226, "learning_rate": 1.5189819285263146e-05, "loss": 0.5386, "num_tokens": 391684851.0, "step": 65620 }, { "epoch": 0.7001269563547523, "grad_norm": 1.1303429608209736, "learning_rate": 1.51864971539005e-05, "loss": 0.4809, "num_tokens": 391719024.0, "step": 65625 }, { "epoch": 0.7001802993609508, "grad_norm": 0.686150777652918, "learning_rate": 1.5183175405708767e-05, "loss": 0.4482, "num_tokens": 391756726.0, "step": 65630 }, { "epoch": 0.7002336423671492, "grad_norm": 1.2212645597815124, "learning_rate": 1.5179854040791322e-05, "loss": 0.3725, "num_tokens": 391777007.0, "step": 65635 }, { "epoch": 0.7002869853733477, "grad_norm": 0.9388649751872898, "learning_rate": 1.5176533059251513e-05, "loss": 0.475, "num_tokens": 391808881.0, "step": 65640 }, { "epoch": 0.7003403283795462, "grad_norm": 0.851144000349901, "learning_rate": 1.5173212461192674e-05, "loss": 0.4269, "num_tokens": 391834039.0, "step": 65645 }, { "epoch": 0.7003936713857446, "grad_norm": 0.8953258474358387, "learning_rate": 1.5169892246718143e-05, "loss": 0.4978, "num_tokens": 391878777.0, "step": 65650 }, { "epoch": 0.7004470143919431, "grad_norm": 0.5820869340559628, "learning_rate": 1.5166572415931246e-05, "loss": 0.5334, "num_tokens": 391922781.0, "step": 65655 }, { "epoch": 0.7005003573981415, "grad_norm": 0.8880080997641349, "learning_rate": 1.5163252968935274e-05, "loss": 0.4752, "num_tokens": 391954068.0, "step": 65660 }, { "epoch": 0.70055370040434, "grad_norm": 0.9617375420853495, "learning_rate": 1.515993390583353e-05, "loss": 0.6878, "num_tokens": 391977936.0, "step": 65665 }, { "epoch": 0.7006070434105385, "grad_norm": 1.0391815546440857, "learning_rate": 1.5156615226729305e-05, "loss": 0.4592, "num_tokens": 392016210.0, "step": 65670 }, { "epoch": 0.7006603864167369, "grad_norm": 0.9219646955513874, "learning_rate": 1.5153296931725857e-05, "loss": 0.4241, "num_tokens": 392039202.0, "step": 65675 }, { "epoch": 0.7007137294229353, "grad_norm": 0.9708080029534676, "learning_rate": 1.5149979020926442e-05, "loss": 0.3953, "num_tokens": 392058848.0, "step": 65680 }, { "epoch": 0.7007670724291338, "grad_norm": 1.196382371497564, "learning_rate": 1.514666149443432e-05, "loss": 0.5041, "num_tokens": 392074005.0, "step": 65685 }, { "epoch": 0.7008204154353322, "grad_norm": 0.9731223713211062, "learning_rate": 1.5143344352352706e-05, "loss": 0.4935, "num_tokens": 392095165.0, "step": 65690 }, { "epoch": 0.7008737584415308, "grad_norm": 0.5989292688623297, "learning_rate": 1.514002759478484e-05, "loss": 0.4824, "num_tokens": 392139860.0, "step": 65695 }, { "epoch": 0.7009271014477292, "grad_norm": 0.5676744627640802, "learning_rate": 1.5136711221833933e-05, "loss": 0.5013, "num_tokens": 392175760.0, "step": 65700 }, { "epoch": 0.7009804444539276, "grad_norm": 0.6350255495485456, "learning_rate": 1.5133395233603179e-05, "loss": 0.4975, "num_tokens": 392224782.0, "step": 65705 }, { "epoch": 0.7010337874601261, "grad_norm": 0.9889440244237816, "learning_rate": 1.5130079630195754e-05, "loss": 0.4603, "num_tokens": 392246954.0, "step": 65710 }, { "epoch": 0.7010871304663245, "grad_norm": 0.6170154875782125, "learning_rate": 1.512676441171485e-05, "loss": 0.4224, "num_tokens": 392273987.0, "step": 65715 }, { "epoch": 0.7011404734725231, "grad_norm": 0.7308327064084481, "learning_rate": 1.5123449578263615e-05, "loss": 0.4341, "num_tokens": 392316311.0, "step": 65720 }, { "epoch": 0.7011938164787215, "grad_norm": 1.8525337015673975, "learning_rate": 1.5120135129945207e-05, "loss": 0.5382, "num_tokens": 392355799.0, "step": 65725 }, { "epoch": 0.7012471594849199, "grad_norm": 0.7667864967856055, "learning_rate": 1.5116821066862771e-05, "loss": 0.368, "num_tokens": 392386272.0, "step": 65730 }, { "epoch": 0.7013005024911184, "grad_norm": 0.7036154562533005, "learning_rate": 1.5113507389119422e-05, "loss": 0.5051, "num_tokens": 392424780.0, "step": 65735 }, { "epoch": 0.7013538454973168, "grad_norm": 0.7692809796671336, "learning_rate": 1.5110194096818287e-05, "loss": 0.5246, "num_tokens": 392453943.0, "step": 65740 }, { "epoch": 0.7014071885035154, "grad_norm": 1.128232938536605, "learning_rate": 1.5106881190062461e-05, "loss": 0.5125, "num_tokens": 392483599.0, "step": 65745 }, { "epoch": 0.7014605315097138, "grad_norm": 2.3651809525447334, "learning_rate": 1.5103568668955032e-05, "loss": 0.7069, "num_tokens": 392508096.0, "step": 65750 }, { "epoch": 0.7015138745159122, "grad_norm": 0.9783940680448916, "learning_rate": 1.510025653359908e-05, "loss": 0.4902, "num_tokens": 392533048.0, "step": 65755 }, { "epoch": 0.7015672175221107, "grad_norm": 1.1079640854851165, "learning_rate": 1.5096944784097682e-05, "loss": 0.5151, "num_tokens": 392562290.0, "step": 65760 }, { "epoch": 0.7016205605283091, "grad_norm": 0.7040457912573548, "learning_rate": 1.5093633420553882e-05, "loss": 0.4895, "num_tokens": 392586239.0, "step": 65765 }, { "epoch": 0.7016739035345075, "grad_norm": 2.017355431708337, "learning_rate": 1.5090322443070726e-05, "loss": 0.5933, "num_tokens": 392607050.0, "step": 65770 }, { "epoch": 0.7017272465407061, "grad_norm": 3.1422163936828267, "learning_rate": 1.5087011851751248e-05, "loss": 0.6209, "num_tokens": 392629884.0, "step": 65775 }, { "epoch": 0.7017805895469045, "grad_norm": 0.6982565499516178, "learning_rate": 1.508370164669847e-05, "loss": 0.5163, "num_tokens": 392656934.0, "step": 65780 }, { "epoch": 0.701833932553103, "grad_norm": 0.8566949384709693, "learning_rate": 1.5080391828015383e-05, "loss": 0.5385, "num_tokens": 392677882.0, "step": 65785 }, { "epoch": 0.7018872755593014, "grad_norm": 0.6806270183460551, "learning_rate": 1.5077082395804997e-05, "loss": 0.4729, "num_tokens": 392711119.0, "step": 65790 }, { "epoch": 0.7019406185654998, "grad_norm": 0.6821780600499282, "learning_rate": 1.5073773350170287e-05, "loss": 0.3284, "num_tokens": 392736315.0, "step": 65795 }, { "epoch": 0.7019939615716984, "grad_norm": 0.8285492674074635, "learning_rate": 1.5070464691214222e-05, "loss": 0.4089, "num_tokens": 392767095.0, "step": 65800 }, { "epoch": 0.7020473045778968, "grad_norm": 1.280127124548087, "learning_rate": 1.5067156419039774e-05, "loss": 0.5005, "num_tokens": 392803524.0, "step": 65805 }, { "epoch": 0.7021006475840953, "grad_norm": 1.5262350469452521, "learning_rate": 1.506384853374987e-05, "loss": 0.5337, "num_tokens": 392833832.0, "step": 65810 }, { "epoch": 0.7021539905902937, "grad_norm": 0.7701543224318885, "learning_rate": 1.5060541035447468e-05, "loss": 0.3584, "num_tokens": 392855763.0, "step": 65815 }, { "epoch": 0.7022073335964921, "grad_norm": 0.5507146606459944, "learning_rate": 1.5057233924235475e-05, "loss": 0.4776, "num_tokens": 392893520.0, "step": 65820 }, { "epoch": 0.7022606766026906, "grad_norm": 1.2143500151638968, "learning_rate": 1.5053927200216793e-05, "loss": 0.5343, "num_tokens": 392923721.0, "step": 65825 }, { "epoch": 0.7023140196088891, "grad_norm": 0.9786541866236783, "learning_rate": 1.5050620863494336e-05, "loss": 0.4928, "num_tokens": 392940926.0, "step": 65830 }, { "epoch": 0.7023673626150876, "grad_norm": 0.9084683365348855, "learning_rate": 1.5047314914170995e-05, "loss": 0.4891, "num_tokens": 392972429.0, "step": 65835 }, { "epoch": 0.702420705621286, "grad_norm": 1.82462284286998, "learning_rate": 1.5044009352349626e-05, "loss": 0.4451, "num_tokens": 392998473.0, "step": 65840 }, { "epoch": 0.7024740486274844, "grad_norm": 0.7848807617108294, "learning_rate": 1.5040704178133096e-05, "loss": 0.5792, "num_tokens": 393016792.0, "step": 65845 }, { "epoch": 0.7025273916336829, "grad_norm": 1.1511478257392496, "learning_rate": 1.503739939162427e-05, "loss": 0.4076, "num_tokens": 393039976.0, "step": 65850 }, { "epoch": 0.7025807346398814, "grad_norm": 0.8194801771992659, "learning_rate": 1.503409499292598e-05, "loss": 0.6336, "num_tokens": 393060976.0, "step": 65855 }, { "epoch": 0.7026340776460798, "grad_norm": 0.7706456006925207, "learning_rate": 1.5030790982141036e-05, "loss": 0.5692, "num_tokens": 393096777.0, "step": 65860 }, { "epoch": 0.7026874206522783, "grad_norm": 0.9923055217274951, "learning_rate": 1.5027487359372272e-05, "loss": 0.3607, "num_tokens": 393116405.0, "step": 65865 }, { "epoch": 0.7027407636584767, "grad_norm": 1.0045494334174627, "learning_rate": 1.5024184124722476e-05, "loss": 0.4287, "num_tokens": 393131022.0, "step": 65870 }, { "epoch": 0.7027941066646752, "grad_norm": 1.7889707942286937, "learning_rate": 1.5020881278294447e-05, "loss": 0.5411, "num_tokens": 393172328.0, "step": 65875 }, { "epoch": 0.7028474496708736, "grad_norm": 1.0470519687255415, "learning_rate": 1.5017578820190964e-05, "loss": 0.403, "num_tokens": 393191945.0, "step": 65880 }, { "epoch": 0.7029007926770721, "grad_norm": 0.7414055999796959, "learning_rate": 1.501427675051478e-05, "loss": 0.4794, "num_tokens": 393235724.0, "step": 65885 }, { "epoch": 0.7029541356832706, "grad_norm": 0.5589925446224899, "learning_rate": 1.5010975069368665e-05, "loss": 0.4675, "num_tokens": 393281846.0, "step": 65890 }, { "epoch": 0.703007478689469, "grad_norm": 0.9458363092350544, "learning_rate": 1.5007673776855354e-05, "loss": 0.4401, "num_tokens": 393309610.0, "step": 65895 }, { "epoch": 0.7030608216956675, "grad_norm": 2.6382277092768267, "learning_rate": 1.5004372873077569e-05, "loss": 0.5829, "num_tokens": 393324927.0, "step": 65900 }, { "epoch": 0.7031141647018659, "grad_norm": 1.1984422542197608, "learning_rate": 1.500107235813803e-05, "loss": 0.5489, "num_tokens": 393355343.0, "step": 65905 }, { "epoch": 0.7031675077080644, "grad_norm": 0.6001918657549943, "learning_rate": 1.4997772232139456e-05, "loss": 0.3487, "num_tokens": 393383819.0, "step": 65910 }, { "epoch": 0.7032208507142629, "grad_norm": 3.284426194419134, "learning_rate": 1.499447249518452e-05, "loss": 0.4867, "num_tokens": 393403489.0, "step": 65915 }, { "epoch": 0.7032741937204613, "grad_norm": 0.5552383163528363, "learning_rate": 1.4991173147375914e-05, "loss": 0.3484, "num_tokens": 393428760.0, "step": 65920 }, { "epoch": 0.7033275367266598, "grad_norm": 0.8135141844748948, "learning_rate": 1.4987874188816314e-05, "loss": 0.4169, "num_tokens": 393449337.0, "step": 65925 }, { "epoch": 0.7033808797328582, "grad_norm": 0.8847677870554925, "learning_rate": 1.4984575619608366e-05, "loss": 0.5244, "num_tokens": 393474716.0, "step": 65930 }, { "epoch": 0.7034342227390566, "grad_norm": 1.0952718435852005, "learning_rate": 1.4981277439854713e-05, "loss": 0.5615, "num_tokens": 393508676.0, "step": 65935 }, { "epoch": 0.7034875657452552, "grad_norm": 0.9496512077813609, "learning_rate": 1.4977979649657998e-05, "loss": 0.5268, "num_tokens": 393541524.0, "step": 65940 }, { "epoch": 0.7035409087514536, "grad_norm": 0.8858027772763585, "learning_rate": 1.4974682249120824e-05, "loss": 0.4847, "num_tokens": 393563317.0, "step": 65945 }, { "epoch": 0.703594251757652, "grad_norm": 0.8395897041670188, "learning_rate": 1.4971385238345818e-05, "loss": 0.4454, "num_tokens": 393601792.0, "step": 65950 }, { "epoch": 0.7036475947638505, "grad_norm": 0.7300010366260021, "learning_rate": 1.4968088617435572e-05, "loss": 0.5164, "num_tokens": 393633730.0, "step": 65955 }, { "epoch": 0.7037009377700489, "grad_norm": 1.429101861564368, "learning_rate": 1.496479238649266e-05, "loss": 0.4768, "num_tokens": 393659897.0, "step": 65960 }, { "epoch": 0.7037542807762475, "grad_norm": 0.9315414867972875, "learning_rate": 1.496149654561967e-05, "loss": 0.3662, "num_tokens": 393685933.0, "step": 65965 }, { "epoch": 0.7038076237824459, "grad_norm": 1.917620515825963, "learning_rate": 1.495820109491915e-05, "loss": 0.6168, "num_tokens": 393698768.0, "step": 65970 }, { "epoch": 0.7038609667886443, "grad_norm": 1.403246877918967, "learning_rate": 1.4954906034493643e-05, "loss": 0.4989, "num_tokens": 393719664.0, "step": 65975 }, { "epoch": 0.7039143097948428, "grad_norm": 0.7619713220909683, "learning_rate": 1.4951611364445695e-05, "loss": 0.4844, "num_tokens": 393762357.0, "step": 65980 }, { "epoch": 0.7039676528010412, "grad_norm": 0.7238398234106678, "learning_rate": 1.4948317084877833e-05, "loss": 0.4872, "num_tokens": 393783481.0, "step": 65985 }, { "epoch": 0.7040209958072398, "grad_norm": 1.2064012760750988, "learning_rate": 1.4945023195892549e-05, "loss": 0.5393, "num_tokens": 393807544.0, "step": 65990 }, { "epoch": 0.7040743388134382, "grad_norm": 1.0880965728853509, "learning_rate": 1.494172969759236e-05, "loss": 0.5122, "num_tokens": 393836948.0, "step": 65995 }, { "epoch": 0.7041276818196366, "grad_norm": 0.929759598471849, "learning_rate": 1.4938436590079752e-05, "loss": 0.5255, "num_tokens": 393877019.0, "step": 66000 }, { "epoch": 0.7041810248258351, "grad_norm": 2.287974920828062, "learning_rate": 1.4935143873457197e-05, "loss": 0.6311, "num_tokens": 393913426.0, "step": 66005 }, { "epoch": 0.7042343678320335, "grad_norm": 1.0604156278150163, "learning_rate": 1.4931851547827147e-05, "loss": 0.4617, "num_tokens": 393929999.0, "step": 66010 }, { "epoch": 0.704287710838232, "grad_norm": 1.858144415156305, "learning_rate": 1.492855961329207e-05, "loss": 0.7077, "num_tokens": 393953431.0, "step": 66015 }, { "epoch": 0.7043410538444305, "grad_norm": 0.6262791053122102, "learning_rate": 1.4925268069954384e-05, "loss": 0.4949, "num_tokens": 393998960.0, "step": 66020 }, { "epoch": 0.7043943968506289, "grad_norm": 1.0447274346824529, "learning_rate": 1.492197691791653e-05, "loss": 0.5509, "num_tokens": 394021623.0, "step": 66025 }, { "epoch": 0.7044477398568274, "grad_norm": 0.6152305125540939, "learning_rate": 1.4918686157280925e-05, "loss": 0.5464, "num_tokens": 394055602.0, "step": 66030 }, { "epoch": 0.7045010828630258, "grad_norm": 1.0224459864110214, "learning_rate": 1.4915395788149965e-05, "loss": 0.5644, "num_tokens": 394083938.0, "step": 66035 }, { "epoch": 0.7045544258692242, "grad_norm": 0.8726982462225668, "learning_rate": 1.491210581062603e-05, "loss": 0.5206, "num_tokens": 394113149.0, "step": 66040 }, { "epoch": 0.7046077688754228, "grad_norm": 0.9441886775690491, "learning_rate": 1.4908816224811515e-05, "loss": 0.3979, "num_tokens": 394128125.0, "step": 66045 }, { "epoch": 0.7046611118816212, "grad_norm": 1.043086210914638, "learning_rate": 1.4905527030808764e-05, "loss": 0.4967, "num_tokens": 394147796.0, "step": 66050 }, { "epoch": 0.7047144548878197, "grad_norm": 0.9443164401361902, "learning_rate": 1.4902238228720144e-05, "loss": 0.3979, "num_tokens": 394167299.0, "step": 66055 }, { "epoch": 0.7047677978940181, "grad_norm": 0.9914266268297095, "learning_rate": 1.4898949818648005e-05, "loss": 0.4723, "num_tokens": 394195507.0, "step": 66060 }, { "epoch": 0.7048211409002165, "grad_norm": 0.8006638214987831, "learning_rate": 1.4895661800694655e-05, "loss": 0.4458, "num_tokens": 394219440.0, "step": 66065 }, { "epoch": 0.704874483906415, "grad_norm": 0.9990055332633425, "learning_rate": 1.4892374174962426e-05, "loss": 0.5178, "num_tokens": 394247208.0, "step": 66070 }, { "epoch": 0.7049278269126135, "grad_norm": 0.8824219962825596, "learning_rate": 1.4889086941553614e-05, "loss": 0.4988, "num_tokens": 394272300.0, "step": 66075 }, { "epoch": 0.704981169918812, "grad_norm": 1.5612049095541378, "learning_rate": 1.4885800100570508e-05, "loss": 0.5003, "num_tokens": 394306567.0, "step": 66080 }, { "epoch": 0.7050345129250104, "grad_norm": 0.930518112664106, "learning_rate": 1.4882513652115393e-05, "loss": 0.5116, "num_tokens": 394347826.0, "step": 66085 }, { "epoch": 0.7050878559312088, "grad_norm": 1.0513609375753692, "learning_rate": 1.4879227596290546e-05, "loss": 0.5466, "num_tokens": 394378776.0, "step": 66090 }, { "epoch": 0.7051411989374073, "grad_norm": 1.278850482195895, "learning_rate": 1.4875941933198199e-05, "loss": 0.4504, "num_tokens": 394397315.0, "step": 66095 }, { "epoch": 0.7051945419436058, "grad_norm": 0.8146409246512342, "learning_rate": 1.487265666294061e-05, "loss": 0.5202, "num_tokens": 394428937.0, "step": 66100 }, { "epoch": 0.7052478849498043, "grad_norm": 0.8917761704626712, "learning_rate": 1.4869371785620017e-05, "loss": 0.4427, "num_tokens": 394467291.0, "step": 66105 }, { "epoch": 0.7053012279560027, "grad_norm": 0.9382952804449296, "learning_rate": 1.4866087301338633e-05, "loss": 0.5197, "num_tokens": 394503277.0, "step": 66110 }, { "epoch": 0.7053545709622011, "grad_norm": 0.9664358489351543, "learning_rate": 1.486280321019865e-05, "loss": 0.521, "num_tokens": 394522227.0, "step": 66115 }, { "epoch": 0.7054079139683996, "grad_norm": 1.5621532623067815, "learning_rate": 1.485951951230228e-05, "loss": 0.5336, "num_tokens": 394544176.0, "step": 66120 }, { "epoch": 0.705461256974598, "grad_norm": 0.681416594820301, "learning_rate": 1.4856236207751695e-05, "loss": 0.3775, "num_tokens": 394571902.0, "step": 66125 }, { "epoch": 0.7055145999807965, "grad_norm": 0.8569436434703104, "learning_rate": 1.4852953296649064e-05, "loss": 0.4423, "num_tokens": 394607651.0, "step": 66130 }, { "epoch": 0.705567942986995, "grad_norm": 1.2576785830640458, "learning_rate": 1.4849670779096559e-05, "loss": 0.442, "num_tokens": 394636955.0, "step": 66135 }, { "epoch": 0.7056212859931934, "grad_norm": 1.2094898247431476, "learning_rate": 1.4846388655196308e-05, "loss": 0.6056, "num_tokens": 394670101.0, "step": 66140 }, { "epoch": 0.7056746289993919, "grad_norm": 0.7684675432957673, "learning_rate": 1.4843106925050453e-05, "loss": 0.5342, "num_tokens": 394695803.0, "step": 66145 }, { "epoch": 0.7057279720055903, "grad_norm": 1.017921030554964, "learning_rate": 1.4839825588761119e-05, "loss": 0.4443, "num_tokens": 394718713.0, "step": 66150 }, { "epoch": 0.7057813150117888, "grad_norm": 0.6601848922948015, "learning_rate": 1.48365446464304e-05, "loss": 0.5007, "num_tokens": 394753712.0, "step": 66155 }, { "epoch": 0.7058346580179873, "grad_norm": 0.6161838419498271, "learning_rate": 1.4833264098160396e-05, "loss": 0.5736, "num_tokens": 394788910.0, "step": 66160 }, { "epoch": 0.7058880010241857, "grad_norm": 0.9338358827838322, "learning_rate": 1.4829983944053204e-05, "loss": 0.4451, "num_tokens": 394816666.0, "step": 66165 }, { "epoch": 0.7059413440303842, "grad_norm": 0.7093174620544851, "learning_rate": 1.482670418421088e-05, "loss": 0.4391, "num_tokens": 394844848.0, "step": 66170 }, { "epoch": 0.7059946870365826, "grad_norm": 0.7260588860135561, "learning_rate": 1.482342481873549e-05, "loss": 0.5442, "num_tokens": 394875592.0, "step": 66175 }, { "epoch": 0.706048030042781, "grad_norm": 0.8421063752608303, "learning_rate": 1.4820145847729088e-05, "loss": 0.4486, "num_tokens": 394902124.0, "step": 66180 }, { "epoch": 0.7061013730489796, "grad_norm": 0.9681661698516383, "learning_rate": 1.4816867271293703e-05, "loss": 0.5576, "num_tokens": 394943069.0, "step": 66185 }, { "epoch": 0.706154716055178, "grad_norm": 0.8505635704394657, "learning_rate": 1.4813589089531348e-05, "loss": 0.5247, "num_tokens": 394964258.0, "step": 66190 }, { "epoch": 0.7062080590613765, "grad_norm": 0.7038333272882166, "learning_rate": 1.481031130254405e-05, "loss": 0.4183, "num_tokens": 394998762.0, "step": 66195 }, { "epoch": 0.7062614020675749, "grad_norm": 0.8227244138507774, "learning_rate": 1.4807033910433793e-05, "loss": 0.4641, "num_tokens": 395038423.0, "step": 66200 }, { "epoch": 0.7063147450737733, "grad_norm": 1.102442693175481, "learning_rate": 1.4803756913302564e-05, "loss": 0.4474, "num_tokens": 395062006.0, "step": 66205 }, { "epoch": 0.7063680880799719, "grad_norm": 1.6568587176457572, "learning_rate": 1.4800480311252352e-05, "loss": 0.4628, "num_tokens": 395079236.0, "step": 66210 }, { "epoch": 0.7064214310861703, "grad_norm": 0.8486412033489003, "learning_rate": 1.4797204104385098e-05, "loss": 0.4303, "num_tokens": 395109545.0, "step": 66215 }, { "epoch": 0.7064747740923687, "grad_norm": 3.942444967560313, "learning_rate": 1.479392829280277e-05, "loss": 0.4839, "num_tokens": 395139013.0, "step": 66220 }, { "epoch": 0.7065281170985672, "grad_norm": 0.7052152804621126, "learning_rate": 1.4790652876607297e-05, "loss": 0.5211, "num_tokens": 395167272.0, "step": 66225 }, { "epoch": 0.7065814601047656, "grad_norm": 0.8448212931565029, "learning_rate": 1.4787377855900587e-05, "loss": 0.4431, "num_tokens": 395190162.0, "step": 66230 }, { "epoch": 0.7066348031109642, "grad_norm": 1.1518530732706789, "learning_rate": 1.4784103230784568e-05, "loss": 0.5542, "num_tokens": 395221375.0, "step": 66235 }, { "epoch": 0.7066881461171626, "grad_norm": 1.3758383480643426, "learning_rate": 1.4780829001361143e-05, "loss": 0.4731, "num_tokens": 395264025.0, "step": 66240 }, { "epoch": 0.706741489123361, "grad_norm": 1.3674857732454861, "learning_rate": 1.4777555167732187e-05, "loss": 0.4942, "num_tokens": 395298479.0, "step": 66245 }, { "epoch": 0.7067948321295595, "grad_norm": 0.7242501528280945, "learning_rate": 1.4774281729999584e-05, "loss": 0.4285, "num_tokens": 395331004.0, "step": 66250 }, { "epoch": 0.7068481751357579, "grad_norm": 0.7631500350502026, "learning_rate": 1.4771008688265203e-05, "loss": 0.5114, "num_tokens": 395362545.0, "step": 66255 }, { "epoch": 0.7069015181419565, "grad_norm": 0.7206803440494544, "learning_rate": 1.4767736042630881e-05, "loss": 0.4256, "num_tokens": 395384185.0, "step": 66260 }, { "epoch": 0.7069548611481549, "grad_norm": 1.0648808498101432, "learning_rate": 1.4764463793198455e-05, "loss": 0.5214, "num_tokens": 395415465.0, "step": 66265 }, { "epoch": 0.7070082041543533, "grad_norm": 0.8577259198062211, "learning_rate": 1.4761191940069763e-05, "loss": 0.5733, "num_tokens": 395447874.0, "step": 66270 }, { "epoch": 0.7070615471605518, "grad_norm": 0.7164113388272493, "learning_rate": 1.4757920483346605e-05, "loss": 0.4957, "num_tokens": 395495161.0, "step": 66275 }, { "epoch": 0.7071148901667502, "grad_norm": 0.7971613957446708, "learning_rate": 1.4754649423130787e-05, "loss": 0.5423, "num_tokens": 395526335.0, "step": 66280 }, { "epoch": 0.7071682331729487, "grad_norm": 0.7583354973581058, "learning_rate": 1.4751378759524109e-05, "loss": 0.4075, "num_tokens": 395547301.0, "step": 66285 }, { "epoch": 0.7072215761791472, "grad_norm": 0.8600077350712609, "learning_rate": 1.4748108492628327e-05, "loss": 0.5009, "num_tokens": 395586248.0, "step": 66290 }, { "epoch": 0.7072749191853456, "grad_norm": 0.6352130867109852, "learning_rate": 1.4744838622545227e-05, "loss": 0.4313, "num_tokens": 395616090.0, "step": 66295 }, { "epoch": 0.7073282621915441, "grad_norm": 0.9453703878861082, "learning_rate": 1.4741569149376544e-05, "loss": 0.5376, "num_tokens": 395653057.0, "step": 66300 }, { "epoch": 0.7073816051977425, "grad_norm": 1.036939426699779, "learning_rate": 1.473830007322402e-05, "loss": 0.5755, "num_tokens": 395687032.0, "step": 66305 }, { "epoch": 0.7074349482039409, "grad_norm": 1.4680649689533103, "learning_rate": 1.4735031394189381e-05, "loss": 0.4703, "num_tokens": 395708320.0, "step": 66310 }, { "epoch": 0.7074882912101395, "grad_norm": 1.462361659627183, "learning_rate": 1.4731763112374356e-05, "loss": 0.4695, "num_tokens": 395741096.0, "step": 66315 }, { "epoch": 0.7075416342163379, "grad_norm": 2.410314881853101, "learning_rate": 1.4728495227880626e-05, "loss": 0.597, "num_tokens": 395762863.0, "step": 66320 }, { "epoch": 0.7075949772225364, "grad_norm": 4.660902977428353, "learning_rate": 1.47252277408099e-05, "loss": 0.4212, "num_tokens": 395780632.0, "step": 66325 }, { "epoch": 0.7076483202287348, "grad_norm": 0.7788669874147948, "learning_rate": 1.4721960651263844e-05, "loss": 0.4964, "num_tokens": 395815621.0, "step": 66330 }, { "epoch": 0.7077016632349332, "grad_norm": 0.6861543336944045, "learning_rate": 1.4718693959344122e-05, "loss": 0.3789, "num_tokens": 395844602.0, "step": 66335 }, { "epoch": 0.7077550062411317, "grad_norm": 0.8776814712104606, "learning_rate": 1.4715427665152387e-05, "loss": 0.5255, "num_tokens": 395874467.0, "step": 66340 }, { "epoch": 0.7078083492473302, "grad_norm": 1.140256815750207, "learning_rate": 1.4712161768790294e-05, "loss": 0.4427, "num_tokens": 395903524.0, "step": 66345 }, { "epoch": 0.7078616922535287, "grad_norm": 0.8639945544697917, "learning_rate": 1.4708896270359449e-05, "loss": 0.5427, "num_tokens": 395945914.0, "step": 66350 }, { "epoch": 0.7079150352597271, "grad_norm": 6.328093157299584, "learning_rate": 1.470563116996148e-05, "loss": 0.6814, "num_tokens": 395970884.0, "step": 66355 }, { "epoch": 0.7079683782659255, "grad_norm": 0.5485598340301656, "learning_rate": 1.4702366467697995e-05, "loss": 0.3499, "num_tokens": 396003647.0, "step": 66360 }, { "epoch": 0.708021721272124, "grad_norm": 1.4143160074807986, "learning_rate": 1.469910216367058e-05, "loss": 0.576, "num_tokens": 396026191.0, "step": 66365 }, { "epoch": 0.7080750642783225, "grad_norm": 0.7844951271647529, "learning_rate": 1.4695838257980804e-05, "loss": 0.5093, "num_tokens": 396054105.0, "step": 66370 }, { "epoch": 0.708128407284521, "grad_norm": 0.7324388216902269, "learning_rate": 1.469257475073024e-05, "loss": 0.5175, "num_tokens": 396086757.0, "step": 66375 }, { "epoch": 0.7081817502907194, "grad_norm": 0.6861111663554124, "learning_rate": 1.468931164202045e-05, "loss": 0.5429, "num_tokens": 396121145.0, "step": 66380 }, { "epoch": 0.7082350932969178, "grad_norm": 1.548685495017274, "learning_rate": 1.4686048931952961e-05, "loss": 0.4511, "num_tokens": 396151033.0, "step": 66385 }, { "epoch": 0.7082884363031163, "grad_norm": 1.3284340981634688, "learning_rate": 1.4682786620629307e-05, "loss": 0.5231, "num_tokens": 396174134.0, "step": 66390 }, { "epoch": 0.7083417793093147, "grad_norm": 1.4135914587910026, "learning_rate": 1.4679524708151016e-05, "loss": 0.4718, "num_tokens": 396202912.0, "step": 66395 }, { "epoch": 0.7083951223155132, "grad_norm": 1.1677970339456056, "learning_rate": 1.467626319461958e-05, "loss": 0.5134, "num_tokens": 396219685.0, "step": 66400 }, { "epoch": 0.7084484653217117, "grad_norm": 0.7488648756207378, "learning_rate": 1.4673002080136488e-05, "loss": 0.497, "num_tokens": 396243959.0, "step": 66405 }, { "epoch": 0.7085018083279101, "grad_norm": 0.9706271093887091, "learning_rate": 1.4669741364803228e-05, "loss": 0.4597, "num_tokens": 396288459.0, "step": 66410 }, { "epoch": 0.7085551513341086, "grad_norm": 1.1354663765168032, "learning_rate": 1.466648104872126e-05, "loss": 0.4529, "num_tokens": 396305249.0, "step": 66415 }, { "epoch": 0.708608494340307, "grad_norm": 1.2432336560305752, "learning_rate": 1.4663221131992032e-05, "loss": 0.6999, "num_tokens": 396341880.0, "step": 66420 }, { "epoch": 0.7086618373465055, "grad_norm": 1.1216211447702604, "learning_rate": 1.4659961614717011e-05, "loss": 0.4617, "num_tokens": 396380216.0, "step": 66425 }, { "epoch": 0.708715180352704, "grad_norm": 1.4596439334568991, "learning_rate": 1.4656702496997599e-05, "loss": 0.4948, "num_tokens": 396399532.0, "step": 66430 }, { "epoch": 0.7087685233589024, "grad_norm": 1.03926456871627, "learning_rate": 1.4653443778935232e-05, "loss": 0.4136, "num_tokens": 396430979.0, "step": 66435 }, { "epoch": 0.7088218663651009, "grad_norm": 0.5684628707472787, "learning_rate": 1.465018546063131e-05, "loss": 0.4593, "num_tokens": 396472393.0, "step": 66440 }, { "epoch": 0.7088752093712993, "grad_norm": 1.3208320928609503, "learning_rate": 1.4646927542187212e-05, "loss": 0.6579, "num_tokens": 396496809.0, "step": 66445 }, { "epoch": 0.7089285523774977, "grad_norm": 0.9972049623685812, "learning_rate": 1.4643670023704329e-05, "loss": 0.5151, "num_tokens": 396544584.0, "step": 66450 }, { "epoch": 0.7089818953836963, "grad_norm": 1.2422218286896551, "learning_rate": 1.4640412905284034e-05, "loss": 0.6179, "num_tokens": 396581610.0, "step": 66455 }, { "epoch": 0.7090352383898947, "grad_norm": 0.6884692954813021, "learning_rate": 1.4637156187027667e-05, "loss": 0.3945, "num_tokens": 396618751.0, "step": 66460 }, { "epoch": 0.7090885813960932, "grad_norm": 1.4112964791869362, "learning_rate": 1.4633899869036577e-05, "loss": 0.5238, "num_tokens": 396643458.0, "step": 66465 }, { "epoch": 0.7091419244022916, "grad_norm": 0.6314010952927472, "learning_rate": 1.4630643951412104e-05, "loss": 0.3326, "num_tokens": 396663403.0, "step": 66470 }, { "epoch": 0.70919526740849, "grad_norm": 1.031864799247964, "learning_rate": 1.4627388434255563e-05, "loss": 0.6493, "num_tokens": 396693656.0, "step": 66475 }, { "epoch": 0.7092486104146886, "grad_norm": 0.9072913024923333, "learning_rate": 1.4624133317668238e-05, "loss": 0.5233, "num_tokens": 396724050.0, "step": 66480 }, { "epoch": 0.709301953420887, "grad_norm": 1.1856853748024936, "learning_rate": 1.4620878601751448e-05, "loss": 0.558, "num_tokens": 396747647.0, "step": 66485 }, { "epoch": 0.7093552964270854, "grad_norm": 0.8524216449112476, "learning_rate": 1.4617624286606448e-05, "loss": 0.5812, "num_tokens": 396770674.0, "step": 66490 }, { "epoch": 0.7094086394332839, "grad_norm": 0.9045673658057825, "learning_rate": 1.4614370372334525e-05, "loss": 0.503, "num_tokens": 396785106.0, "step": 66495 }, { "epoch": 0.7094619824394823, "grad_norm": 1.8302348493518914, "learning_rate": 1.4611116859036932e-05, "loss": 0.451, "num_tokens": 396818801.0, "step": 66500 }, { "epoch": 0.7095153254456809, "grad_norm": 1.1680585134997878, "learning_rate": 1.4607863746814904e-05, "loss": 0.5665, "num_tokens": 396861211.0, "step": 66505 }, { "epoch": 0.7095686684518793, "grad_norm": 1.1480501292915373, "learning_rate": 1.4604611035769677e-05, "loss": 0.5838, "num_tokens": 396883564.0, "step": 66510 }, { "epoch": 0.7096220114580777, "grad_norm": 1.0642076431646172, "learning_rate": 1.4601358726002473e-05, "loss": 0.6641, "num_tokens": 396918238.0, "step": 66515 }, { "epoch": 0.7096753544642762, "grad_norm": 1.417203033556101, "learning_rate": 1.459810681761448e-05, "loss": 0.4634, "num_tokens": 396937143.0, "step": 66520 }, { "epoch": 0.7097286974704746, "grad_norm": 1.701232750445832, "learning_rate": 1.4594855310706901e-05, "loss": 0.5101, "num_tokens": 396951608.0, "step": 66525 }, { "epoch": 0.7097820404766731, "grad_norm": 0.7941559014462501, "learning_rate": 1.4591604205380926e-05, "loss": 0.5116, "num_tokens": 396972531.0, "step": 66530 }, { "epoch": 0.7098353834828716, "grad_norm": 0.8124733421835991, "learning_rate": 1.4588353501737705e-05, "loss": 0.5156, "num_tokens": 396998170.0, "step": 66535 }, { "epoch": 0.70988872648907, "grad_norm": 1.3177259692031498, "learning_rate": 1.4585103199878403e-05, "loss": 0.5174, "num_tokens": 397033953.0, "step": 66540 }, { "epoch": 0.7099420694952685, "grad_norm": 0.9448937268814613, "learning_rate": 1.4581853299904166e-05, "loss": 0.5056, "num_tokens": 397075027.0, "step": 66545 }, { "epoch": 0.7099954125014669, "grad_norm": 0.9812306844845261, "learning_rate": 1.4578603801916125e-05, "loss": 0.4352, "num_tokens": 397097674.0, "step": 66550 }, { "epoch": 0.7100487555076654, "grad_norm": 0.7032551019128791, "learning_rate": 1.4575354706015379e-05, "loss": 0.4551, "num_tokens": 397130521.0, "step": 66555 }, { "epoch": 0.7101020985138639, "grad_norm": 0.6531087804405943, "learning_rate": 1.4572106012303057e-05, "loss": 0.4319, "num_tokens": 397158700.0, "step": 66560 }, { "epoch": 0.7101554415200623, "grad_norm": 0.9557606867568282, "learning_rate": 1.4568857720880235e-05, "loss": 0.4144, "num_tokens": 397195256.0, "step": 66565 }, { "epoch": 0.7102087845262608, "grad_norm": 0.9870313506315577, "learning_rate": 1.4565609831847996e-05, "loss": 0.4917, "num_tokens": 397220144.0, "step": 66570 }, { "epoch": 0.7102621275324592, "grad_norm": 1.0054154044110917, "learning_rate": 1.456236234530742e-05, "loss": 0.4782, "num_tokens": 397244673.0, "step": 66575 }, { "epoch": 0.7103154705386576, "grad_norm": 1.0740118215364391, "learning_rate": 1.4559115261359546e-05, "loss": 0.5184, "num_tokens": 397268972.0, "step": 66580 }, { "epoch": 0.7103688135448561, "grad_norm": 0.5746047570083154, "learning_rate": 1.4555868580105433e-05, "loss": 0.4027, "num_tokens": 397298813.0, "step": 66585 }, { "epoch": 0.7104221565510546, "grad_norm": 0.6729630865726426, "learning_rate": 1.4552622301646102e-05, "loss": 0.3635, "num_tokens": 397320698.0, "step": 66590 }, { "epoch": 0.7104754995572531, "grad_norm": 0.7083585357790427, "learning_rate": 1.454937642608256e-05, "loss": 0.6275, "num_tokens": 397356326.0, "step": 66595 }, { "epoch": 0.7105288425634515, "grad_norm": 0.9645393559474906, "learning_rate": 1.4546130953515819e-05, "loss": 0.4716, "num_tokens": 397403202.0, "step": 66600 }, { "epoch": 0.7105821855696499, "grad_norm": 0.6969058733644214, "learning_rate": 1.4542885884046891e-05, "loss": 0.5126, "num_tokens": 397447895.0, "step": 66605 }, { "epoch": 0.7106355285758484, "grad_norm": 0.9079964392135171, "learning_rate": 1.4539641217776729e-05, "loss": 0.4517, "num_tokens": 397479952.0, "step": 66610 }, { "epoch": 0.7106888715820469, "grad_norm": 0.5743008923813145, "learning_rate": 1.4536396954806314e-05, "loss": 0.428, "num_tokens": 397511141.0, "step": 66615 }, { "epoch": 0.7107422145882454, "grad_norm": 0.8913216464455431, "learning_rate": 1.4533153095236602e-05, "loss": 0.4459, "num_tokens": 397538954.0, "step": 66620 }, { "epoch": 0.7107955575944438, "grad_norm": 1.0973845052530065, "learning_rate": 1.452990963916852e-05, "loss": 0.4573, "num_tokens": 397579674.0, "step": 66625 }, { "epoch": 0.7108489006006422, "grad_norm": 0.7220327776752634, "learning_rate": 1.4526666586703012e-05, "loss": 0.5086, "num_tokens": 397628080.0, "step": 66630 }, { "epoch": 0.7109022436068407, "grad_norm": 1.0152310242152998, "learning_rate": 1.4523423937940999e-05, "loss": 0.4699, "num_tokens": 397647175.0, "step": 66635 }, { "epoch": 0.7109555866130391, "grad_norm": 1.2719869907872994, "learning_rate": 1.4520181692983367e-05, "loss": 0.4633, "num_tokens": 397681919.0, "step": 66640 }, { "epoch": 0.7110089296192377, "grad_norm": 0.6607139422012402, "learning_rate": 1.4516939851931022e-05, "loss": 0.3709, "num_tokens": 397713166.0, "step": 66645 }, { "epoch": 0.7110622726254361, "grad_norm": 1.005864241300915, "learning_rate": 1.4513698414884851e-05, "loss": 0.501, "num_tokens": 397739531.0, "step": 66650 }, { "epoch": 0.7111156156316345, "grad_norm": 0.8274859145142396, "learning_rate": 1.4510457381945708e-05, "loss": 0.4651, "num_tokens": 397770957.0, "step": 66655 }, { "epoch": 0.711168958637833, "grad_norm": 0.9361515728676005, "learning_rate": 1.4507216753214442e-05, "loss": 0.4702, "num_tokens": 397798652.0, "step": 66660 }, { "epoch": 0.7112223016440314, "grad_norm": 0.8654577807332968, "learning_rate": 1.4503976528791913e-05, "loss": 0.3832, "num_tokens": 397824229.0, "step": 66665 }, { "epoch": 0.7112756446502299, "grad_norm": 2.0950375141987956, "learning_rate": 1.450073670877893e-05, "loss": 0.5296, "num_tokens": 397848015.0, "step": 66670 }, { "epoch": 0.7113289876564284, "grad_norm": 3.3342254528332647, "learning_rate": 1.4497497293276322e-05, "loss": 0.6834, "num_tokens": 397883363.0, "step": 66675 }, { "epoch": 0.7113823306626268, "grad_norm": 1.2576140240827178, "learning_rate": 1.4494258282384892e-05, "loss": 0.6202, "num_tokens": 397911375.0, "step": 66680 }, { "epoch": 0.7114356736688253, "grad_norm": 0.7702207350459375, "learning_rate": 1.4491019676205427e-05, "loss": 0.4155, "num_tokens": 397941953.0, "step": 66685 }, { "epoch": 0.7114890166750237, "grad_norm": 0.8427794944654844, "learning_rate": 1.4487781474838713e-05, "loss": 0.457, "num_tokens": 397961427.0, "step": 66690 }, { "epoch": 0.7115423596812221, "grad_norm": 0.827542729710062, "learning_rate": 1.4484543678385515e-05, "loss": 0.4879, "num_tokens": 398003061.0, "step": 66695 }, { "epoch": 0.7115957026874207, "grad_norm": 1.0196021739523629, "learning_rate": 1.4481306286946578e-05, "loss": 0.5529, "num_tokens": 398030778.0, "step": 66700 }, { "epoch": 0.7116490456936191, "grad_norm": 0.8979520693612806, "learning_rate": 1.4478069300622643e-05, "loss": 0.4248, "num_tokens": 398061896.0, "step": 66705 }, { "epoch": 0.7117023886998176, "grad_norm": 0.8289797414980777, "learning_rate": 1.4474832719514453e-05, "loss": 0.5151, "num_tokens": 398089093.0, "step": 66710 }, { "epoch": 0.711755731706016, "grad_norm": 1.2351527918762346, "learning_rate": 1.4471596543722705e-05, "loss": 0.4693, "num_tokens": 398114776.0, "step": 66715 }, { "epoch": 0.7118090747122144, "grad_norm": 0.6703488246169429, "learning_rate": 1.4468360773348114e-05, "loss": 0.5335, "num_tokens": 398144482.0, "step": 66720 }, { "epoch": 0.711862417718413, "grad_norm": 0.5978147048861085, "learning_rate": 1.446512540849137e-05, "loss": 0.427, "num_tokens": 398184456.0, "step": 66725 }, { "epoch": 0.7119157607246114, "grad_norm": 1.1460654869545381, "learning_rate": 1.4461890449253157e-05, "loss": 0.6436, "num_tokens": 398211369.0, "step": 66730 }, { "epoch": 0.7119691037308099, "grad_norm": 0.5889149875109622, "learning_rate": 1.445865589573412e-05, "loss": 0.3267, "num_tokens": 398235855.0, "step": 66735 }, { "epoch": 0.7120224467370083, "grad_norm": 0.8832619093777341, "learning_rate": 1.4455421748034933e-05, "loss": 0.4178, "num_tokens": 398255864.0, "step": 66740 }, { "epoch": 0.7120757897432067, "grad_norm": 0.8802895293554347, "learning_rate": 1.4452188006256218e-05, "loss": 0.419, "num_tokens": 398297912.0, "step": 66745 }, { "epoch": 0.7121291327494053, "grad_norm": 0.9169902410077384, "learning_rate": 1.444895467049861e-05, "loss": 0.6196, "num_tokens": 398337371.0, "step": 66750 }, { "epoch": 0.7121824757556037, "grad_norm": 2.2515978033744686, "learning_rate": 1.4445721740862736e-05, "loss": 0.4233, "num_tokens": 398362464.0, "step": 66755 }, { "epoch": 0.7122358187618021, "grad_norm": 0.8806934177429894, "learning_rate": 1.444248921744918e-05, "loss": 0.3738, "num_tokens": 398389542.0, "step": 66760 }, { "epoch": 0.7122891617680006, "grad_norm": 0.8706484117986601, "learning_rate": 1.4439257100358544e-05, "loss": 0.3882, "num_tokens": 398416964.0, "step": 66765 }, { "epoch": 0.712342504774199, "grad_norm": 0.5942128938280594, "learning_rate": 1.4436025389691399e-05, "loss": 0.3618, "num_tokens": 398443371.0, "step": 66770 }, { "epoch": 0.7123958477803976, "grad_norm": 0.7266752803417529, "learning_rate": 1.4432794085548302e-05, "loss": 0.4393, "num_tokens": 398475161.0, "step": 66775 }, { "epoch": 0.712449190786596, "grad_norm": 0.8667587613189044, "learning_rate": 1.4429563188029815e-05, "loss": 0.5661, "num_tokens": 398508346.0, "step": 66780 }, { "epoch": 0.7125025337927944, "grad_norm": 0.6368446340875211, "learning_rate": 1.4426332697236477e-05, "loss": 0.5121, "num_tokens": 398537585.0, "step": 66785 }, { "epoch": 0.7125558767989929, "grad_norm": 0.7437265759895659, "learning_rate": 1.4423102613268808e-05, "loss": 0.4763, "num_tokens": 398560810.0, "step": 66790 }, { "epoch": 0.7126092198051913, "grad_norm": 0.7097108962764933, "learning_rate": 1.4419872936227321e-05, "loss": 0.5112, "num_tokens": 398597676.0, "step": 66795 }, { "epoch": 0.7126625628113898, "grad_norm": 0.9613420435032767, "learning_rate": 1.4416643666212534e-05, "loss": 0.4583, "num_tokens": 398615410.0, "step": 66800 }, { "epoch": 0.7127159058175883, "grad_norm": 0.747820762565409, "learning_rate": 1.4413414803324917e-05, "loss": 0.4387, "num_tokens": 398654354.0, "step": 66805 }, { "epoch": 0.7127692488237867, "grad_norm": 1.4869532943398176, "learning_rate": 1.4410186347664944e-05, "loss": 0.4014, "num_tokens": 398683110.0, "step": 66810 }, { "epoch": 0.7128225918299852, "grad_norm": 0.7223355775642347, "learning_rate": 1.4406958299333095e-05, "loss": 0.4056, "num_tokens": 398708098.0, "step": 66815 }, { "epoch": 0.7128759348361836, "grad_norm": 0.869552795903395, "learning_rate": 1.44037306584298e-05, "loss": 0.3625, "num_tokens": 398725442.0, "step": 66820 }, { "epoch": 0.7129292778423821, "grad_norm": 0.8187309752103379, "learning_rate": 1.4400503425055509e-05, "loss": 0.5334, "num_tokens": 398758842.0, "step": 66825 }, { "epoch": 0.7129826208485806, "grad_norm": 1.443554213631616, "learning_rate": 1.439727659931065e-05, "loss": 0.4745, "num_tokens": 398789750.0, "step": 66830 }, { "epoch": 0.713035963854779, "grad_norm": 0.6993433664169436, "learning_rate": 1.439405018129562e-05, "loss": 0.4551, "num_tokens": 398828325.0, "step": 66835 }, { "epoch": 0.7130893068609775, "grad_norm": 0.9851993388063347, "learning_rate": 1.4390824171110839e-05, "loss": 0.3468, "num_tokens": 398854205.0, "step": 66840 }, { "epoch": 0.7131426498671759, "grad_norm": 1.3856349936157608, "learning_rate": 1.438759856885668e-05, "loss": 0.6353, "num_tokens": 398886883.0, "step": 66845 }, { "epoch": 0.7131959928733743, "grad_norm": 0.7992912910638265, "learning_rate": 1.4384373374633515e-05, "loss": 0.6418, "num_tokens": 398930665.0, "step": 66850 }, { "epoch": 0.7132493358795728, "grad_norm": 0.5073443839456807, "learning_rate": 1.4381148588541709e-05, "loss": 0.4429, "num_tokens": 398972261.0, "step": 66855 }, { "epoch": 0.7133026788857713, "grad_norm": 1.3280999073002635, "learning_rate": 1.437792421068162e-05, "loss": 0.544, "num_tokens": 398985055.0, "step": 66860 }, { "epoch": 0.7133560218919698, "grad_norm": 1.107150124956596, "learning_rate": 1.4374700241153568e-05, "loss": 0.4738, "num_tokens": 399006921.0, "step": 66865 }, { "epoch": 0.7134093648981682, "grad_norm": 0.5936683052156331, "learning_rate": 1.4371476680057883e-05, "loss": 0.4206, "num_tokens": 399038137.0, "step": 66870 }, { "epoch": 0.7134627079043666, "grad_norm": 0.9373517401919351, "learning_rate": 1.4368253527494888e-05, "loss": 0.5579, "num_tokens": 399072513.0, "step": 66875 }, { "epoch": 0.7135160509105651, "grad_norm": 1.1922839151058926, "learning_rate": 1.4365030783564868e-05, "loss": 0.5577, "num_tokens": 399092348.0, "step": 66880 }, { "epoch": 0.7135693939167636, "grad_norm": 1.2170500282410657, "learning_rate": 1.4361808448368097e-05, "loss": 0.7225, "num_tokens": 399107684.0, "step": 66885 }, { "epoch": 0.7136227369229621, "grad_norm": 1.2722223736119218, "learning_rate": 1.4358586522004874e-05, "loss": 0.5084, "num_tokens": 399132708.0, "step": 66890 }, { "epoch": 0.7136760799291605, "grad_norm": 0.8979318146088834, "learning_rate": 1.4355365004575439e-05, "loss": 0.3799, "num_tokens": 399152563.0, "step": 66895 }, { "epoch": 0.7137294229353589, "grad_norm": 1.2453970823600873, "learning_rate": 1.4352143896180042e-05, "loss": 0.4696, "num_tokens": 399195738.0, "step": 66900 }, { "epoch": 0.7137827659415574, "grad_norm": 0.6283694923250801, "learning_rate": 1.4348923196918928e-05, "loss": 0.4506, "num_tokens": 399226414.0, "step": 66905 }, { "epoch": 0.7138361089477558, "grad_norm": 0.8836793071381577, "learning_rate": 1.4345702906892308e-05, "loss": 0.4167, "num_tokens": 399253181.0, "step": 66910 }, { "epoch": 0.7138894519539544, "grad_norm": 0.9337199010901738, "learning_rate": 1.4342483026200398e-05, "loss": 0.4497, "num_tokens": 399282037.0, "step": 66915 }, { "epoch": 0.7139427949601528, "grad_norm": 0.8804575577170874, "learning_rate": 1.4339263554943389e-05, "loss": 0.4005, "num_tokens": 399297964.0, "step": 66920 }, { "epoch": 0.7139961379663512, "grad_norm": 2.614370353306498, "learning_rate": 1.4336044493221456e-05, "loss": 0.4818, "num_tokens": 399327421.0, "step": 66925 }, { "epoch": 0.7140494809725497, "grad_norm": 0.98396692519081, "learning_rate": 1.4332825841134784e-05, "loss": 0.4541, "num_tokens": 399352445.0, "step": 66930 }, { "epoch": 0.7141028239787481, "grad_norm": 0.8256588576917204, "learning_rate": 1.4329607598783528e-05, "loss": 0.5311, "num_tokens": 399388487.0, "step": 66935 }, { "epoch": 0.7141561669849465, "grad_norm": 0.7998058154893176, "learning_rate": 1.4326389766267828e-05, "loss": 0.5066, "num_tokens": 399409905.0, "step": 66940 }, { "epoch": 0.7142095099911451, "grad_norm": 1.304455566731839, "learning_rate": 1.4323172343687823e-05, "loss": 0.3862, "num_tokens": 399437727.0, "step": 66945 }, { "epoch": 0.7142628529973435, "grad_norm": 1.184804322567347, "learning_rate": 1.4319955331143631e-05, "loss": 0.5762, "num_tokens": 399469648.0, "step": 66950 }, { "epoch": 0.714316196003542, "grad_norm": 0.6794535138391996, "learning_rate": 1.4316738728735349e-05, "loss": 0.5201, "num_tokens": 399504406.0, "step": 66955 }, { "epoch": 0.7143695390097404, "grad_norm": 1.3544689888926187, "learning_rate": 1.431352253656308e-05, "loss": 0.45, "num_tokens": 399518681.0, "step": 66960 }, { "epoch": 0.7144228820159388, "grad_norm": 0.679554189844865, "learning_rate": 1.4310306754726907e-05, "loss": 0.3744, "num_tokens": 399544397.0, "step": 66965 }, { "epoch": 0.7144762250221374, "grad_norm": 0.880966150216956, "learning_rate": 1.4307091383326887e-05, "loss": 0.5396, "num_tokens": 399585241.0, "step": 66970 }, { "epoch": 0.7145295680283358, "grad_norm": 0.6746926118121447, "learning_rate": 1.430387642246309e-05, "loss": 0.4668, "num_tokens": 399612280.0, "step": 66975 }, { "epoch": 0.7145829110345343, "grad_norm": 0.8126220415408301, "learning_rate": 1.4300661872235557e-05, "loss": 0.4544, "num_tokens": 399650042.0, "step": 66980 }, { "epoch": 0.7146362540407327, "grad_norm": 2.7869217532612747, "learning_rate": 1.4297447732744313e-05, "loss": 0.445, "num_tokens": 399684181.0, "step": 66985 }, { "epoch": 0.7146895970469311, "grad_norm": 1.2066324520029763, "learning_rate": 1.4294234004089374e-05, "loss": 0.3773, "num_tokens": 399704710.0, "step": 66990 }, { "epoch": 0.7147429400531297, "grad_norm": 1.616712412278075, "learning_rate": 1.429102068637075e-05, "loss": 0.5528, "num_tokens": 399725951.0, "step": 66995 }, { "epoch": 0.7147962830593281, "grad_norm": 1.0481029984984838, "learning_rate": 1.4287807779688425e-05, "loss": 0.4685, "num_tokens": 399764210.0, "step": 67000 }, { "epoch": 0.7148496260655266, "grad_norm": 0.7712115587638345, "learning_rate": 1.4284595284142383e-05, "loss": 0.5028, "num_tokens": 399798014.0, "step": 67005 }, { "epoch": 0.714902969071725, "grad_norm": 0.8466262990104969, "learning_rate": 1.42813831998326e-05, "loss": 0.3685, "num_tokens": 399820600.0, "step": 67010 }, { "epoch": 0.7149563120779234, "grad_norm": 1.1146366436844755, "learning_rate": 1.4278171526859008e-05, "loss": 0.4834, "num_tokens": 399847650.0, "step": 67015 }, { "epoch": 0.715009655084122, "grad_norm": 0.786313073706712, "learning_rate": 1.4274960265321573e-05, "loss": 0.367, "num_tokens": 399872535.0, "step": 67020 }, { "epoch": 0.7150629980903204, "grad_norm": 0.9779183761601833, "learning_rate": 1.4271749415320207e-05, "loss": 0.4366, "num_tokens": 399905890.0, "step": 67025 }, { "epoch": 0.7151163410965188, "grad_norm": 0.9639803618958049, "learning_rate": 1.4268538976954818e-05, "loss": 0.5823, "num_tokens": 399946965.0, "step": 67030 }, { "epoch": 0.7151696841027173, "grad_norm": 0.7793391622891235, "learning_rate": 1.4265328950325319e-05, "loss": 0.4598, "num_tokens": 399978989.0, "step": 67035 }, { "epoch": 0.7152230271089157, "grad_norm": 1.248123238492664, "learning_rate": 1.4262119335531604e-05, "loss": 0.5981, "num_tokens": 400009189.0, "step": 67040 }, { "epoch": 0.7152763701151142, "grad_norm": 0.8287894933495458, "learning_rate": 1.425891013267354e-05, "loss": 0.5352, "num_tokens": 400036703.0, "step": 67045 }, { "epoch": 0.7153297131213127, "grad_norm": 1.0944663060655233, "learning_rate": 1.4255701341850994e-05, "loss": 0.4921, "num_tokens": 400056217.0, "step": 67050 }, { "epoch": 0.7153830561275111, "grad_norm": 0.8081261897521477, "learning_rate": 1.4252492963163822e-05, "loss": 0.4878, "num_tokens": 400091024.0, "step": 67055 }, { "epoch": 0.7154363991337096, "grad_norm": 1.4167322032579943, "learning_rate": 1.4249284996711862e-05, "loss": 0.531, "num_tokens": 400122983.0, "step": 67060 }, { "epoch": 0.715489742139908, "grad_norm": 0.9775463382393158, "learning_rate": 1.4246077442594926e-05, "loss": 0.4677, "num_tokens": 400154350.0, "step": 67065 }, { "epoch": 0.7155430851461065, "grad_norm": 0.9220118965842558, "learning_rate": 1.4242870300912842e-05, "loss": 0.5339, "num_tokens": 400188787.0, "step": 67070 }, { "epoch": 0.715596428152305, "grad_norm": 1.676197838878428, "learning_rate": 1.4239663571765397e-05, "loss": 0.5516, "num_tokens": 400210207.0, "step": 67075 }, { "epoch": 0.7156497711585034, "grad_norm": 1.1941400985759385, "learning_rate": 1.4236457255252383e-05, "loss": 0.4179, "num_tokens": 400228698.0, "step": 67080 }, { "epoch": 0.7157031141647019, "grad_norm": 1.2659969758467278, "learning_rate": 1.4233251351473585e-05, "loss": 0.5327, "num_tokens": 400244516.0, "step": 67085 }, { "epoch": 0.7157564571709003, "grad_norm": 1.6169289382422596, "learning_rate": 1.4230045860528746e-05, "loss": 0.4838, "num_tokens": 400294247.0, "step": 67090 }, { "epoch": 0.7158098001770988, "grad_norm": 1.470185316096008, "learning_rate": 1.4226840782517631e-05, "loss": 0.7042, "num_tokens": 400314889.0, "step": 67095 }, { "epoch": 0.7158631431832972, "grad_norm": 1.4388398202842156, "learning_rate": 1.4223636117539962e-05, "loss": 0.5249, "num_tokens": 400344392.0, "step": 67100 }, { "epoch": 0.7159164861894957, "grad_norm": 0.8127483075878408, "learning_rate": 1.4220431865695467e-05, "loss": 0.4552, "num_tokens": 400375202.0, "step": 67105 }, { "epoch": 0.7159698291956942, "grad_norm": 1.1660839757113828, "learning_rate": 1.4217228027083845e-05, "loss": 0.5681, "num_tokens": 400399683.0, "step": 67110 }, { "epoch": 0.7160231722018926, "grad_norm": 1.0468844429114454, "learning_rate": 1.4214024601804817e-05, "loss": 0.5768, "num_tokens": 400431283.0, "step": 67115 }, { "epoch": 0.716076515208091, "grad_norm": 0.8240071000273771, "learning_rate": 1.4210821589958045e-05, "loss": 0.6524, "num_tokens": 400469989.0, "step": 67120 }, { "epoch": 0.7161298582142895, "grad_norm": 0.60142521289334, "learning_rate": 1.4207618991643212e-05, "loss": 0.4915, "num_tokens": 400510878.0, "step": 67125 }, { "epoch": 0.716183201220488, "grad_norm": 2.0478353823886266, "learning_rate": 1.4204416806959976e-05, "loss": 0.589, "num_tokens": 400530248.0, "step": 67130 }, { "epoch": 0.7162365442266865, "grad_norm": 2.488179814305667, "learning_rate": 1.420121503600798e-05, "loss": 0.6046, "num_tokens": 400571231.0, "step": 67135 }, { "epoch": 0.7162898872328849, "grad_norm": 1.1891571161124652, "learning_rate": 1.4198013678886845e-05, "loss": 0.3793, "num_tokens": 400585535.0, "step": 67140 }, { "epoch": 0.7163432302390833, "grad_norm": 0.7594951848647178, "learning_rate": 1.4194812735696214e-05, "loss": 0.4483, "num_tokens": 400615977.0, "step": 67145 }, { "epoch": 0.7163965732452818, "grad_norm": 1.253085028140612, "learning_rate": 1.419161220653567e-05, "loss": 0.4315, "num_tokens": 400636505.0, "step": 67150 }, { "epoch": 0.7164499162514802, "grad_norm": 1.2009709123264818, "learning_rate": 1.4188412091504821e-05, "loss": 0.5538, "num_tokens": 400672856.0, "step": 67155 }, { "epoch": 0.7165032592576788, "grad_norm": 1.080698559426775, "learning_rate": 1.4185212390703251e-05, "loss": 0.4551, "num_tokens": 400697044.0, "step": 67160 }, { "epoch": 0.7165566022638772, "grad_norm": 0.5592744070672432, "learning_rate": 1.4182013104230512e-05, "loss": 0.4248, "num_tokens": 400735425.0, "step": 67165 }, { "epoch": 0.7166099452700756, "grad_norm": 0.8699831149358719, "learning_rate": 1.4178814232186177e-05, "loss": 0.5641, "num_tokens": 400762523.0, "step": 67170 }, { "epoch": 0.7166632882762741, "grad_norm": 1.1309303466057508, "learning_rate": 1.4175615774669782e-05, "loss": 0.5733, "num_tokens": 400789512.0, "step": 67175 }, { "epoch": 0.7167166312824725, "grad_norm": 0.8896799442438822, "learning_rate": 1.4172417731780852e-05, "loss": 0.4005, "num_tokens": 400804567.0, "step": 67180 }, { "epoch": 0.7167699742886711, "grad_norm": 0.9037576189993405, "learning_rate": 1.4169220103618902e-05, "loss": 0.4008, "num_tokens": 400832451.0, "step": 67185 }, { "epoch": 0.7168233172948695, "grad_norm": 0.7324881371491883, "learning_rate": 1.4166022890283449e-05, "loss": 0.4199, "num_tokens": 400880794.0, "step": 67190 }, { "epoch": 0.7168766603010679, "grad_norm": 0.7159674123043426, "learning_rate": 1.4162826091873963e-05, "loss": 0.4304, "num_tokens": 400912369.0, "step": 67195 }, { "epoch": 0.7169300033072664, "grad_norm": 1.9814374804834736, "learning_rate": 1.4159629708489938e-05, "loss": 0.4486, "num_tokens": 400923938.0, "step": 67200 }, { "epoch": 0.7169833463134648, "grad_norm": 2.4669621067558545, "learning_rate": 1.415643374023084e-05, "loss": 0.6509, "num_tokens": 400941601.0, "step": 67205 }, { "epoch": 0.7170366893196632, "grad_norm": 0.6716817387821177, "learning_rate": 1.4153238187196119e-05, "loss": 0.4916, "num_tokens": 400974733.0, "step": 67210 }, { "epoch": 0.7170900323258618, "grad_norm": 1.0365290040936908, "learning_rate": 1.41500430494852e-05, "loss": 0.409, "num_tokens": 400999761.0, "step": 67215 }, { "epoch": 0.7171433753320602, "grad_norm": 0.8003652955032147, "learning_rate": 1.4146848327197526e-05, "loss": 0.4791, "num_tokens": 401033258.0, "step": 67220 }, { "epoch": 0.7171967183382587, "grad_norm": 0.6507675247527557, "learning_rate": 1.41436540204325e-05, "loss": 0.5093, "num_tokens": 401075292.0, "step": 67225 }, { "epoch": 0.7172500613444571, "grad_norm": 0.7408232842638739, "learning_rate": 1.4140460129289524e-05, "loss": 0.4969, "num_tokens": 401101642.0, "step": 67230 }, { "epoch": 0.7173034043506555, "grad_norm": 1.959127807777904, "learning_rate": 1.4137266653867998e-05, "loss": 0.4614, "num_tokens": 401120352.0, "step": 67235 }, { "epoch": 0.7173567473568541, "grad_norm": 0.8211287271277933, "learning_rate": 1.4134073594267283e-05, "loss": 0.5224, "num_tokens": 401152046.0, "step": 67240 }, { "epoch": 0.7174100903630525, "grad_norm": 1.5978263410123967, "learning_rate": 1.4130880950586736e-05, "loss": 0.5665, "num_tokens": 401174480.0, "step": 67245 }, { "epoch": 0.717463433369251, "grad_norm": 1.547355262748635, "learning_rate": 1.412768872292572e-05, "loss": 0.5304, "num_tokens": 401193508.0, "step": 67250 }, { "epoch": 0.7175167763754494, "grad_norm": 0.9847339435312236, "learning_rate": 1.4124496911383559e-05, "loss": 0.3887, "num_tokens": 401216570.0, "step": 67255 }, { "epoch": 0.7175701193816478, "grad_norm": 1.446632909070886, "learning_rate": 1.4121305516059573e-05, "loss": 0.595, "num_tokens": 401252630.0, "step": 67260 }, { "epoch": 0.7176234623878464, "grad_norm": 1.2543973629781522, "learning_rate": 1.4118114537053095e-05, "loss": 0.3509, "num_tokens": 401272676.0, "step": 67265 }, { "epoch": 0.7176768053940448, "grad_norm": 0.966171836425538, "learning_rate": 1.4114923974463393e-05, "loss": 0.4604, "num_tokens": 401290241.0, "step": 67270 }, { "epoch": 0.7177301484002433, "grad_norm": 0.6171052669049728, "learning_rate": 1.4111733828389773e-05, "loss": 0.6218, "num_tokens": 401352547.0, "step": 67275 }, { "epoch": 0.7177834914064417, "grad_norm": 0.7581232721374243, "learning_rate": 1.4108544098931492e-05, "loss": 0.4564, "num_tokens": 401378435.0, "step": 67280 }, { "epoch": 0.7178368344126401, "grad_norm": 0.9713071711215258, "learning_rate": 1.4105354786187807e-05, "loss": 0.459, "num_tokens": 401402670.0, "step": 67285 }, { "epoch": 0.7178901774188386, "grad_norm": 0.7273444670475443, "learning_rate": 1.4102165890257968e-05, "loss": 0.4629, "num_tokens": 401430942.0, "step": 67290 }, { "epoch": 0.7179435204250371, "grad_norm": 0.6038126011205014, "learning_rate": 1.4098977411241215e-05, "loss": 0.5183, "num_tokens": 401472214.0, "step": 67295 }, { "epoch": 0.7179968634312355, "grad_norm": 1.0086127100971698, "learning_rate": 1.4095789349236749e-05, "loss": 0.4257, "num_tokens": 401497183.0, "step": 67300 }, { "epoch": 0.718050206437434, "grad_norm": 1.121024634307989, "learning_rate": 1.4092601704343783e-05, "loss": 0.4903, "num_tokens": 401532550.0, "step": 67305 }, { "epoch": 0.7181035494436324, "grad_norm": 0.7532647312023518, "learning_rate": 1.4089414476661526e-05, "loss": 0.386, "num_tokens": 401565446.0, "step": 67310 }, { "epoch": 0.7181568924498309, "grad_norm": 0.8812546339951016, "learning_rate": 1.408622766628914e-05, "loss": 0.4459, "num_tokens": 401587546.0, "step": 67315 }, { "epoch": 0.7182102354560294, "grad_norm": 0.8866864495952849, "learning_rate": 1.4083041273325792e-05, "loss": 0.4162, "num_tokens": 401617162.0, "step": 67320 }, { "epoch": 0.7182635784622278, "grad_norm": 1.2509517449153087, "learning_rate": 1.4079855297870636e-05, "loss": 0.4254, "num_tokens": 401649754.0, "step": 67325 }, { "epoch": 0.7183169214684263, "grad_norm": 1.4687661493159163, "learning_rate": 1.407666974002283e-05, "loss": 0.4338, "num_tokens": 401665911.0, "step": 67330 }, { "epoch": 0.7183702644746247, "grad_norm": 0.5952278708680376, "learning_rate": 1.4073484599881476e-05, "loss": 0.456, "num_tokens": 401692333.0, "step": 67335 }, { "epoch": 0.7184236074808232, "grad_norm": 0.9003687465454941, "learning_rate": 1.4070299877545707e-05, "loss": 0.392, "num_tokens": 401711379.0, "step": 67340 }, { "epoch": 0.7184769504870216, "grad_norm": 0.5847987097158398, "learning_rate": 1.4067115573114626e-05, "loss": 0.4779, "num_tokens": 401745150.0, "step": 67345 }, { "epoch": 0.7185302934932201, "grad_norm": 0.7366384969456488, "learning_rate": 1.4063931686687317e-05, "loss": 0.4425, "num_tokens": 401772515.0, "step": 67350 }, { "epoch": 0.7185836364994186, "grad_norm": 1.1045141816484814, "learning_rate": 1.4060748218362846e-05, "loss": 0.4759, "num_tokens": 401811239.0, "step": 67355 }, { "epoch": 0.718636979505617, "grad_norm": 0.5903243627883565, "learning_rate": 1.4057565168240295e-05, "loss": 0.5552, "num_tokens": 401846176.0, "step": 67360 }, { "epoch": 0.7186903225118155, "grad_norm": 1.30496511059065, "learning_rate": 1.4054382536418698e-05, "loss": 0.5938, "num_tokens": 401891692.0, "step": 67365 }, { "epoch": 0.7187436655180139, "grad_norm": 0.9458764420148977, "learning_rate": 1.4051200322997097e-05, "loss": 0.4955, "num_tokens": 401909527.0, "step": 67370 }, { "epoch": 0.7187970085242124, "grad_norm": 0.7964459123440781, "learning_rate": 1.4048018528074525e-05, "loss": 0.453, "num_tokens": 401945605.0, "step": 67375 }, { "epoch": 0.7188503515304109, "grad_norm": 0.772023288852706, "learning_rate": 1.4044837151749979e-05, "loss": 0.5409, "num_tokens": 401976745.0, "step": 67380 }, { "epoch": 0.7189036945366093, "grad_norm": 1.5138034352794638, "learning_rate": 1.4041656194122465e-05, "loss": 0.3841, "num_tokens": 402000872.0, "step": 67385 }, { "epoch": 0.7189570375428077, "grad_norm": 0.752318278715144, "learning_rate": 1.4038475655290973e-05, "loss": 0.4823, "num_tokens": 402030627.0, "step": 67390 }, { "epoch": 0.7190103805490062, "grad_norm": 1.0584778751675583, "learning_rate": 1.403529553535446e-05, "loss": 0.503, "num_tokens": 402050859.0, "step": 67395 }, { "epoch": 0.7190637235552046, "grad_norm": 0.7899488157064107, "learning_rate": 1.4032115834411885e-05, "loss": 0.5051, "num_tokens": 402080331.0, "step": 67400 }, { "epoch": 0.7191170665614032, "grad_norm": 1.0502036282988512, "learning_rate": 1.4028936552562217e-05, "loss": 0.411, "num_tokens": 402092164.0, "step": 67405 }, { "epoch": 0.7191704095676016, "grad_norm": 1.19806339621082, "learning_rate": 1.4025757689904362e-05, "loss": 0.476, "num_tokens": 402125607.0, "step": 67410 }, { "epoch": 0.7192237525738, "grad_norm": 1.0869727843866608, "learning_rate": 1.4022579246537252e-05, "loss": 0.4597, "num_tokens": 402138981.0, "step": 67415 }, { "epoch": 0.7192770955799985, "grad_norm": 0.9946606226557352, "learning_rate": 1.40194012225598e-05, "loss": 0.4884, "num_tokens": 402169705.0, "step": 67420 }, { "epoch": 0.7193304385861969, "grad_norm": 0.784643104857514, "learning_rate": 1.4016223618070893e-05, "loss": 0.4043, "num_tokens": 402188343.0, "step": 67425 }, { "epoch": 0.7193837815923955, "grad_norm": 1.337883866034912, "learning_rate": 1.4013046433169399e-05, "loss": 0.4707, "num_tokens": 402213823.0, "step": 67430 }, { "epoch": 0.7194371245985939, "grad_norm": 0.8921778266681392, "learning_rate": 1.4009869667954207e-05, "loss": 0.4668, "num_tokens": 402246257.0, "step": 67435 }, { "epoch": 0.7194904676047923, "grad_norm": 0.76570580489498, "learning_rate": 1.4006693322524153e-05, "loss": 0.4591, "num_tokens": 402276977.0, "step": 67440 }, { "epoch": 0.7195438106109908, "grad_norm": 0.882041921826067, "learning_rate": 1.4003517396978088e-05, "loss": 0.443, "num_tokens": 402312356.0, "step": 67445 }, { "epoch": 0.7195971536171892, "grad_norm": 0.654214009505571, "learning_rate": 1.4000341891414847e-05, "loss": 0.4469, "num_tokens": 402357977.0, "step": 67450 }, { "epoch": 0.7196504966233878, "grad_norm": 0.6463953309136323, "learning_rate": 1.3997166805933226e-05, "loss": 0.4699, "num_tokens": 402397260.0, "step": 67455 }, { "epoch": 0.7197038396295862, "grad_norm": 1.2647034145019322, "learning_rate": 1.399399214063205e-05, "loss": 0.4855, "num_tokens": 402429660.0, "step": 67460 }, { "epoch": 0.7197571826357846, "grad_norm": 0.6033990295191322, "learning_rate": 1.3990817895610099e-05, "loss": 0.4967, "num_tokens": 402456020.0, "step": 67465 }, { "epoch": 0.7198105256419831, "grad_norm": 0.5852503670978723, "learning_rate": 1.3987644070966133e-05, "loss": 0.51, "num_tokens": 402493204.0, "step": 67470 }, { "epoch": 0.7198638686481815, "grad_norm": 0.681029895589129, "learning_rate": 1.3984470666798931e-05, "loss": 0.4873, "num_tokens": 402516920.0, "step": 67475 }, { "epoch": 0.7199172116543799, "grad_norm": 1.0164105824068828, "learning_rate": 1.3981297683207246e-05, "loss": 0.3695, "num_tokens": 402542822.0, "step": 67480 }, { "epoch": 0.7199705546605785, "grad_norm": 1.2766630468976905, "learning_rate": 1.3978125120289803e-05, "loss": 0.4928, "num_tokens": 402582470.0, "step": 67485 }, { "epoch": 0.7200238976667769, "grad_norm": 0.7360871405733115, "learning_rate": 1.3974952978145334e-05, "loss": 0.5014, "num_tokens": 402618509.0, "step": 67490 }, { "epoch": 0.7200772406729754, "grad_norm": 1.278675780340516, "learning_rate": 1.3971781256872549e-05, "loss": 0.5501, "num_tokens": 402651969.0, "step": 67495 }, { "epoch": 0.7201305836791738, "grad_norm": 1.5189682625530658, "learning_rate": 1.3968609956570147e-05, "loss": 0.3875, "num_tokens": 402673314.0, "step": 67500 }, { "epoch": 0.7201839266853722, "grad_norm": 0.9868949602784748, "learning_rate": 1.39654390773368e-05, "loss": 0.4296, "num_tokens": 402692481.0, "step": 67505 }, { "epoch": 0.7202372696915708, "grad_norm": 0.8644338805616437, "learning_rate": 1.3962268619271196e-05, "loss": 0.4916, "num_tokens": 402722815.0, "step": 67510 }, { "epoch": 0.7202906126977692, "grad_norm": 1.027360451319872, "learning_rate": 1.395909858247198e-05, "loss": 0.5266, "num_tokens": 402749382.0, "step": 67515 }, { "epoch": 0.7203439557039677, "grad_norm": 0.6465130898619984, "learning_rate": 1.3955928967037798e-05, "loss": 0.466, "num_tokens": 402794748.0, "step": 67520 }, { "epoch": 0.7203972987101661, "grad_norm": 0.905052201530911, "learning_rate": 1.3952759773067297e-05, "loss": 0.4337, "num_tokens": 402814487.0, "step": 67525 }, { "epoch": 0.7204506417163645, "grad_norm": 1.085715561511236, "learning_rate": 1.3949591000659085e-05, "loss": 0.4998, "num_tokens": 402851647.0, "step": 67530 }, { "epoch": 0.720503984722563, "grad_norm": 1.0237545855123262, "learning_rate": 1.3946422649911758e-05, "loss": 0.8061, "num_tokens": 402886303.0, "step": 67535 }, { "epoch": 0.7205573277287615, "grad_norm": 0.6569113759348126, "learning_rate": 1.394325472092393e-05, "loss": 0.5248, "num_tokens": 402922128.0, "step": 67540 }, { "epoch": 0.72061067073496, "grad_norm": 1.12936367139519, "learning_rate": 1.3940087213794157e-05, "loss": 0.4802, "num_tokens": 402947249.0, "step": 67545 }, { "epoch": 0.7206640137411584, "grad_norm": 0.7281763731933413, "learning_rate": 1.3936920128621018e-05, "loss": 0.4836, "num_tokens": 402973504.0, "step": 67550 }, { "epoch": 0.7207173567473568, "grad_norm": 1.0197462068432543, "learning_rate": 1.3933753465503074e-05, "loss": 0.474, "num_tokens": 402996646.0, "step": 67555 }, { "epoch": 0.7207706997535553, "grad_norm": 1.0038139279296696, "learning_rate": 1.3930587224538849e-05, "loss": 0.5107, "num_tokens": 403031009.0, "step": 67560 }, { "epoch": 0.7208240427597538, "grad_norm": 1.033420063866276, "learning_rate": 1.3927421405826882e-05, "loss": 0.4905, "num_tokens": 403066367.0, "step": 67565 }, { "epoch": 0.7208773857659522, "grad_norm": 1.0413222717004422, "learning_rate": 1.3924256009465686e-05, "loss": 0.4304, "num_tokens": 403083901.0, "step": 67570 }, { "epoch": 0.7209307287721507, "grad_norm": 1.5333718549503634, "learning_rate": 1.3921091035553745e-05, "loss": 0.6138, "num_tokens": 403115885.0, "step": 67575 }, { "epoch": 0.7209840717783491, "grad_norm": 1.1277887950472287, "learning_rate": 1.3917926484189564e-05, "loss": 0.4246, "num_tokens": 403133495.0, "step": 67580 }, { "epoch": 0.7210374147845476, "grad_norm": 0.9484187473293273, "learning_rate": 1.3914762355471617e-05, "loss": 0.4771, "num_tokens": 403167358.0, "step": 67585 }, { "epoch": 0.721090757790746, "grad_norm": 0.9758605673707569, "learning_rate": 1.3911598649498352e-05, "loss": 0.3991, "num_tokens": 403194001.0, "step": 67590 }, { "epoch": 0.7211441007969445, "grad_norm": 0.6883284913488735, "learning_rate": 1.3908435366368228e-05, "loss": 0.399, "num_tokens": 403215734.0, "step": 67595 }, { "epoch": 0.721197443803143, "grad_norm": 2.2693752583372913, "learning_rate": 1.3905272506179683e-05, "loss": 0.5464, "num_tokens": 403235656.0, "step": 67600 }, { "epoch": 0.7212507868093414, "grad_norm": 0.9042339026720431, "learning_rate": 1.3902110069031138e-05, "loss": 0.4087, "num_tokens": 403272305.0, "step": 67605 }, { "epoch": 0.7213041298155399, "grad_norm": 0.6662629605853548, "learning_rate": 1.3898948055020988e-05, "loss": 0.5474, "num_tokens": 403299272.0, "step": 67610 }, { "epoch": 0.7213574728217383, "grad_norm": 0.9341263504549352, "learning_rate": 1.389578646424764e-05, "loss": 0.5015, "num_tokens": 403326662.0, "step": 67615 }, { "epoch": 0.7214108158279368, "grad_norm": 0.9345431695823135, "learning_rate": 1.3892625296809469e-05, "loss": 0.4183, "num_tokens": 403352854.0, "step": 67620 }, { "epoch": 0.7214641588341353, "grad_norm": 1.111626627408147, "learning_rate": 1.3889464552804848e-05, "loss": 0.4705, "num_tokens": 403378437.0, "step": 67625 }, { "epoch": 0.7215175018403337, "grad_norm": 1.584350460111938, "learning_rate": 1.3886304232332142e-05, "loss": 0.495, "num_tokens": 403401742.0, "step": 67630 }, { "epoch": 0.7215708448465322, "grad_norm": 0.553542078476847, "learning_rate": 1.3883144335489674e-05, "loss": 0.461, "num_tokens": 403451749.0, "step": 67635 }, { "epoch": 0.7216241878527306, "grad_norm": 0.8456090288685953, "learning_rate": 1.3879984862375794e-05, "loss": 0.593, "num_tokens": 403491543.0, "step": 67640 }, { "epoch": 0.721677530858929, "grad_norm": 1.3870069715868272, "learning_rate": 1.3876825813088812e-05, "loss": 0.479, "num_tokens": 403515096.0, "step": 67645 }, { "epoch": 0.7217308738651276, "grad_norm": 1.0968667262003446, "learning_rate": 1.3873667187727013e-05, "loss": 0.4946, "num_tokens": 403532590.0, "step": 67650 }, { "epoch": 0.721784216871326, "grad_norm": 0.8262059965247375, "learning_rate": 1.3870508986388709e-05, "loss": 0.5019, "num_tokens": 403560740.0, "step": 67655 }, { "epoch": 0.7218375598775244, "grad_norm": 0.7003112810007113, "learning_rate": 1.3867351209172175e-05, "loss": 0.4396, "num_tokens": 403588303.0, "step": 67660 }, { "epoch": 0.7218909028837229, "grad_norm": 1.6771977166364476, "learning_rate": 1.3864193856175661e-05, "loss": 0.4641, "num_tokens": 403611694.0, "step": 67665 }, { "epoch": 0.7219442458899213, "grad_norm": 0.7315008523806864, "learning_rate": 1.3861036927497425e-05, "loss": 0.4541, "num_tokens": 403644952.0, "step": 67670 }, { "epoch": 0.7219975888961199, "grad_norm": 1.6350448304127556, "learning_rate": 1.3857880423235715e-05, "loss": 0.5995, "num_tokens": 403666719.0, "step": 67675 }, { "epoch": 0.7220509319023183, "grad_norm": 1.9929619693707534, "learning_rate": 1.385472434348874e-05, "loss": 0.491, "num_tokens": 403697414.0, "step": 67680 }, { "epoch": 0.7221042749085167, "grad_norm": 0.7045181281538576, "learning_rate": 1.385156868835471e-05, "loss": 0.5773, "num_tokens": 403744213.0, "step": 67685 }, { "epoch": 0.7221576179147152, "grad_norm": 0.8763648989413146, "learning_rate": 1.3848413457931836e-05, "loss": 0.5091, "num_tokens": 403779815.0, "step": 67690 }, { "epoch": 0.7222109609209136, "grad_norm": 0.9581203920256762, "learning_rate": 1.3845258652318283e-05, "loss": 0.4846, "num_tokens": 403816518.0, "step": 67695 }, { "epoch": 0.7222643039271122, "grad_norm": 0.6883849593223185, "learning_rate": 1.3842104271612236e-05, "loss": 0.464, "num_tokens": 403862590.0, "step": 67700 }, { "epoch": 0.7223176469333106, "grad_norm": 0.9723077552381206, "learning_rate": 1.3838950315911858e-05, "loss": 0.4014, "num_tokens": 403888253.0, "step": 67705 }, { "epoch": 0.722370989939509, "grad_norm": 0.6514414300116737, "learning_rate": 1.3835796785315275e-05, "loss": 0.4938, "num_tokens": 403921567.0, "step": 67710 }, { "epoch": 0.7224243329457075, "grad_norm": 1.4774472997492676, "learning_rate": 1.383264367992064e-05, "loss": 0.555, "num_tokens": 403948024.0, "step": 67715 }, { "epoch": 0.7224776759519059, "grad_norm": 0.9611580651437519, "learning_rate": 1.3829490999826056e-05, "loss": 0.4936, "num_tokens": 403989941.0, "step": 67720 }, { "epoch": 0.7225310189581045, "grad_norm": 1.0890067044665965, "learning_rate": 1.382633874512963e-05, "loss": 0.5191, "num_tokens": 404016116.0, "step": 67725 }, { "epoch": 0.7225843619643029, "grad_norm": 1.959568377654715, "learning_rate": 1.3823186915929454e-05, "loss": 0.5991, "num_tokens": 404040961.0, "step": 67730 }, { "epoch": 0.7226377049705013, "grad_norm": 1.6413206561908125, "learning_rate": 1.3820035512323615e-05, "loss": 0.4566, "num_tokens": 404069389.0, "step": 67735 }, { "epoch": 0.7226910479766998, "grad_norm": 1.2961929555023832, "learning_rate": 1.3816884534410162e-05, "loss": 0.5946, "num_tokens": 404094676.0, "step": 67740 }, { "epoch": 0.7227443909828982, "grad_norm": 1.1216088926565704, "learning_rate": 1.3813733982287158e-05, "loss": 0.5042, "num_tokens": 404116033.0, "step": 67745 }, { "epoch": 0.7227977339890966, "grad_norm": 0.6392256007324882, "learning_rate": 1.381058385605265e-05, "loss": 0.3656, "num_tokens": 404136451.0, "step": 67750 }, { "epoch": 0.7228510769952952, "grad_norm": 1.3270791609359531, "learning_rate": 1.3807434155804649e-05, "loss": 0.4456, "num_tokens": 404162528.0, "step": 67755 }, { "epoch": 0.7229044200014936, "grad_norm": 0.6511402029002756, "learning_rate": 1.3804284881641166e-05, "loss": 0.4397, "num_tokens": 404195513.0, "step": 67760 }, { "epoch": 0.7229577630076921, "grad_norm": 0.8290016554984013, "learning_rate": 1.3801136033660211e-05, "loss": 0.517, "num_tokens": 404229759.0, "step": 67765 }, { "epoch": 0.7230111060138905, "grad_norm": 0.96618534098466, "learning_rate": 1.3797987611959761e-05, "loss": 0.5593, "num_tokens": 404251660.0, "step": 67770 }, { "epoch": 0.7230644490200889, "grad_norm": 0.5911587326309005, "learning_rate": 1.3794839616637792e-05, "loss": 0.4545, "num_tokens": 404275885.0, "step": 67775 }, { "epoch": 0.7231177920262875, "grad_norm": 0.7945317916901895, "learning_rate": 1.379169204779227e-05, "loss": 0.4895, "num_tokens": 404324664.0, "step": 67780 }, { "epoch": 0.7231711350324859, "grad_norm": 0.7959053015271812, "learning_rate": 1.3788544905521122e-05, "loss": 0.463, "num_tokens": 404350862.0, "step": 67785 }, { "epoch": 0.7232244780386844, "grad_norm": 0.9738672221953979, "learning_rate": 1.3785398189922305e-05, "loss": 0.4453, "num_tokens": 404366704.0, "step": 67790 }, { "epoch": 0.7232778210448828, "grad_norm": 0.5945698249142478, "learning_rate": 1.3782251901093723e-05, "loss": 0.4666, "num_tokens": 404407005.0, "step": 67795 }, { "epoch": 0.7233311640510812, "grad_norm": 0.6688456218818217, "learning_rate": 1.3779106039133278e-05, "loss": 0.5264, "num_tokens": 404446783.0, "step": 67800 }, { "epoch": 0.7233845070572797, "grad_norm": 4.512014442428533, "learning_rate": 1.3775960604138866e-05, "loss": 0.4795, "num_tokens": 404474557.0, "step": 67805 }, { "epoch": 0.7234378500634782, "grad_norm": 0.9121954701528943, "learning_rate": 1.3772815596208383e-05, "loss": 0.5026, "num_tokens": 404511329.0, "step": 67810 }, { "epoch": 0.7234911930696767, "grad_norm": 1.1323962881093186, "learning_rate": 1.3769671015439673e-05, "loss": 0.4957, "num_tokens": 404544538.0, "step": 67815 }, { "epoch": 0.7235445360758751, "grad_norm": 0.8136370742083087, "learning_rate": 1.3766526861930595e-05, "loss": 0.4159, "num_tokens": 404571129.0, "step": 67820 }, { "epoch": 0.7235978790820735, "grad_norm": 0.6931665634820483, "learning_rate": 1.3763383135779003e-05, "loss": 0.3483, "num_tokens": 404589829.0, "step": 67825 }, { "epoch": 0.723651222088272, "grad_norm": 1.3273836978331905, "learning_rate": 1.3760239837082711e-05, "loss": 0.6128, "num_tokens": 404637440.0, "step": 67830 }, { "epoch": 0.7237045650944705, "grad_norm": 1.3959666327774267, "learning_rate": 1.3757096965939525e-05, "loss": 0.5205, "num_tokens": 404659033.0, "step": 67835 }, { "epoch": 0.7237579081006689, "grad_norm": 0.9185122655927667, "learning_rate": 1.3753954522447262e-05, "loss": 0.494, "num_tokens": 404685655.0, "step": 67840 }, { "epoch": 0.7238112511068674, "grad_norm": 0.9145980301542332, "learning_rate": 1.3750812506703691e-05, "loss": 0.6467, "num_tokens": 404738555.0, "step": 67845 }, { "epoch": 0.7238645941130658, "grad_norm": 1.1225160453270038, "learning_rate": 1.3747670918806592e-05, "loss": 0.4959, "num_tokens": 404778272.0, "step": 67850 }, { "epoch": 0.7239179371192643, "grad_norm": 0.9466124238637358, "learning_rate": 1.3744529758853734e-05, "loss": 0.4695, "num_tokens": 404817305.0, "step": 67855 }, { "epoch": 0.7239712801254627, "grad_norm": 1.0977905977742328, "learning_rate": 1.3741389026942853e-05, "loss": 0.3834, "num_tokens": 404845997.0, "step": 67860 }, { "epoch": 0.7240246231316612, "grad_norm": 1.0919663102324786, "learning_rate": 1.3738248723171682e-05, "loss": 0.4704, "num_tokens": 404874216.0, "step": 67865 }, { "epoch": 0.7240779661378597, "grad_norm": 0.8187214657839326, "learning_rate": 1.3735108847637946e-05, "loss": 0.446, "num_tokens": 404904808.0, "step": 67870 }, { "epoch": 0.7241313091440581, "grad_norm": 1.1009335497138018, "learning_rate": 1.3731969400439342e-05, "loss": 0.4948, "num_tokens": 404931670.0, "step": 67875 }, { "epoch": 0.7241846521502566, "grad_norm": 1.1692587292639975, "learning_rate": 1.3728830381673568e-05, "loss": 0.4769, "num_tokens": 404969548.0, "step": 67880 }, { "epoch": 0.724237995156455, "grad_norm": 0.6153386550540236, "learning_rate": 1.3725691791438323e-05, "loss": 0.4658, "num_tokens": 404997950.0, "step": 67885 }, { "epoch": 0.7242913381626535, "grad_norm": 0.9194595108924958, "learning_rate": 1.3722553629831236e-05, "loss": 0.472, "num_tokens": 405022873.0, "step": 67890 }, { "epoch": 0.724344681168852, "grad_norm": 1.179005688705223, "learning_rate": 1.3719415896949994e-05, "loss": 0.5003, "num_tokens": 405041159.0, "step": 67895 }, { "epoch": 0.7243980241750504, "grad_norm": 1.1294969698977926, "learning_rate": 1.3716278592892224e-05, "loss": 0.5239, "num_tokens": 405064621.0, "step": 67900 }, { "epoch": 0.7244513671812489, "grad_norm": 0.7962243367693133, "learning_rate": 1.3713141717755543e-05, "loss": 0.4953, "num_tokens": 405089615.0, "step": 67905 }, { "epoch": 0.7245047101874473, "grad_norm": 0.898184957801021, "learning_rate": 1.3710005271637574e-05, "loss": 0.3744, "num_tokens": 405113493.0, "step": 67910 }, { "epoch": 0.7245580531936457, "grad_norm": 1.201754048614394, "learning_rate": 1.3706869254635923e-05, "loss": 0.3594, "num_tokens": 405147714.0, "step": 67915 }, { "epoch": 0.7246113961998443, "grad_norm": 1.0486606734029758, "learning_rate": 1.3703733666848156e-05, "loss": 0.4806, "num_tokens": 405184791.0, "step": 67920 }, { "epoch": 0.7246647392060427, "grad_norm": 0.8271149938388788, "learning_rate": 1.3700598508371865e-05, "loss": 0.4062, "num_tokens": 405216694.0, "step": 67925 }, { "epoch": 0.7247180822122411, "grad_norm": 1.7074236184826495, "learning_rate": 1.3697463779304609e-05, "loss": 0.5681, "num_tokens": 405242099.0, "step": 67930 }, { "epoch": 0.7247714252184396, "grad_norm": 0.5884169372230285, "learning_rate": 1.3694329479743931e-05, "loss": 0.4689, "num_tokens": 405278741.0, "step": 67935 }, { "epoch": 0.724824768224638, "grad_norm": 0.7942069998293313, "learning_rate": 1.369119560978735e-05, "loss": 0.5174, "num_tokens": 405297485.0, "step": 67940 }, { "epoch": 0.7248781112308366, "grad_norm": 0.953933515432354, "learning_rate": 1.3688062169532412e-05, "loss": 0.4422, "num_tokens": 405318199.0, "step": 67945 }, { "epoch": 0.724931454237035, "grad_norm": 2.2635870141237957, "learning_rate": 1.3684929159076593e-05, "loss": 0.5054, "num_tokens": 405343685.0, "step": 67950 }, { "epoch": 0.7249847972432334, "grad_norm": 0.894429347230457, "learning_rate": 1.3681796578517405e-05, "loss": 0.5179, "num_tokens": 405383215.0, "step": 67955 }, { "epoch": 0.7250381402494319, "grad_norm": 0.9160307749105135, "learning_rate": 1.3678664427952338e-05, "loss": 0.4115, "num_tokens": 405402994.0, "step": 67960 }, { "epoch": 0.7250914832556303, "grad_norm": 1.0196093819666756, "learning_rate": 1.3675532707478827e-05, "loss": 0.4815, "num_tokens": 405438030.0, "step": 67965 }, { "epoch": 0.7251448262618289, "grad_norm": 1.2521623146312044, "learning_rate": 1.3672401417194353e-05, "loss": 0.4044, "num_tokens": 405475632.0, "step": 67970 }, { "epoch": 0.7251981692680273, "grad_norm": 1.4228574882303016, "learning_rate": 1.3669270557196346e-05, "loss": 0.4821, "num_tokens": 405496040.0, "step": 67975 }, { "epoch": 0.7252515122742257, "grad_norm": 0.8736563875376273, "learning_rate": 1.3666140127582219e-05, "loss": 0.4676, "num_tokens": 405516528.0, "step": 67980 }, { "epoch": 0.7253048552804242, "grad_norm": 0.624899418465933, "learning_rate": 1.3663010128449399e-05, "loss": 0.546, "num_tokens": 405541090.0, "step": 67985 }, { "epoch": 0.7253581982866226, "grad_norm": 0.7020938557731605, "learning_rate": 1.3659880559895285e-05, "loss": 0.4958, "num_tokens": 405576404.0, "step": 67990 }, { "epoch": 0.7254115412928211, "grad_norm": 0.8946768490643078, "learning_rate": 1.3656751422017258e-05, "loss": 0.4895, "num_tokens": 405604612.0, "step": 67995 }, { "epoch": 0.7254648842990196, "grad_norm": 1.1312579390678252, "learning_rate": 1.3653622714912687e-05, "loss": 0.5316, "num_tokens": 405624664.0, "step": 68000 }, { "epoch": 0.725518227305218, "grad_norm": 0.600173634758874, "learning_rate": 1.3650494438678946e-05, "loss": 0.4623, "num_tokens": 405655707.0, "step": 68005 }, { "epoch": 0.7255715703114165, "grad_norm": 0.8177441137194318, "learning_rate": 1.364736659341337e-05, "loss": 0.5794, "num_tokens": 405693247.0, "step": 68010 }, { "epoch": 0.7256249133176149, "grad_norm": 0.782111207441085, "learning_rate": 1.364423917921328e-05, "loss": 0.5064, "num_tokens": 405734823.0, "step": 68015 }, { "epoch": 0.7256782563238133, "grad_norm": 1.718461031771875, "learning_rate": 1.364111219617602e-05, "loss": 0.4804, "num_tokens": 405766032.0, "step": 68020 }, { "epoch": 0.7257315993300119, "grad_norm": 1.4605988263426428, "learning_rate": 1.3637985644398871e-05, "loss": 0.4343, "num_tokens": 405790997.0, "step": 68025 }, { "epoch": 0.7257849423362103, "grad_norm": 0.7405458299945868, "learning_rate": 1.3634859523979135e-05, "loss": 0.5028, "num_tokens": 405822825.0, "step": 68030 }, { "epoch": 0.7258382853424088, "grad_norm": 0.691531299117754, "learning_rate": 1.36317338350141e-05, "loss": 0.5485, "num_tokens": 405854189.0, "step": 68035 }, { "epoch": 0.7258916283486072, "grad_norm": 0.6664857625950646, "learning_rate": 1.3628608577601015e-05, "loss": 0.4736, "num_tokens": 405883658.0, "step": 68040 }, { "epoch": 0.7259449713548056, "grad_norm": 1.0874332592694838, "learning_rate": 1.3625483751837142e-05, "loss": 0.4957, "num_tokens": 405908344.0, "step": 68045 }, { "epoch": 0.7259983143610041, "grad_norm": 0.8395556115111225, "learning_rate": 1.3622359357819717e-05, "loss": 0.3848, "num_tokens": 405927741.0, "step": 68050 }, { "epoch": 0.7260516573672026, "grad_norm": 0.9082766570612059, "learning_rate": 1.3619235395645958e-05, "loss": 0.4977, "num_tokens": 405952373.0, "step": 68055 }, { "epoch": 0.7261050003734011, "grad_norm": 0.7947859662122168, "learning_rate": 1.3616111865413078e-05, "loss": 0.4826, "num_tokens": 405976606.0, "step": 68060 }, { "epoch": 0.7261583433795995, "grad_norm": 0.6922639371903903, "learning_rate": 1.3612988767218288e-05, "loss": 0.5488, "num_tokens": 406006579.0, "step": 68065 }, { "epoch": 0.7262116863857979, "grad_norm": 0.9050974749343399, "learning_rate": 1.3609866101158758e-05, "loss": 0.3967, "num_tokens": 406030318.0, "step": 68070 }, { "epoch": 0.7262650293919964, "grad_norm": 0.9565596308106606, "learning_rate": 1.3606743867331662e-05, "loss": 0.434, "num_tokens": 406045328.0, "step": 68075 }, { "epoch": 0.7263183723981949, "grad_norm": 1.49521822102118, "learning_rate": 1.3603622065834165e-05, "loss": 0.5017, "num_tokens": 406064900.0, "step": 68080 }, { "epoch": 0.7263717154043934, "grad_norm": 1.0215889362302844, "learning_rate": 1.3600500696763407e-05, "loss": 0.4816, "num_tokens": 406103007.0, "step": 68085 }, { "epoch": 0.7264250584105918, "grad_norm": 0.6065514435230771, "learning_rate": 1.3597379760216507e-05, "loss": 0.5682, "num_tokens": 406137728.0, "step": 68090 }, { "epoch": 0.7264784014167902, "grad_norm": 0.78294314609398, "learning_rate": 1.35942592562906e-05, "loss": 0.3647, "num_tokens": 406159713.0, "step": 68095 }, { "epoch": 0.7265317444229887, "grad_norm": 0.587724244109321, "learning_rate": 1.3591139185082777e-05, "loss": 0.4204, "num_tokens": 406189809.0, "step": 68100 }, { "epoch": 0.7265850874291871, "grad_norm": 0.8938687839100725, "learning_rate": 1.3588019546690134e-05, "loss": 0.464, "num_tokens": 406215913.0, "step": 68105 }, { "epoch": 0.7266384304353856, "grad_norm": 0.916041860391003, "learning_rate": 1.358490034120975e-05, "loss": 0.5286, "num_tokens": 406242923.0, "step": 68110 }, { "epoch": 0.7266917734415841, "grad_norm": 1.4517646828721744, "learning_rate": 1.3581781568738677e-05, "loss": 0.5915, "num_tokens": 406299025.0, "step": 68115 }, { "epoch": 0.7267451164477825, "grad_norm": 1.0928761881266684, "learning_rate": 1.3578663229373984e-05, "loss": 0.5489, "num_tokens": 406342250.0, "step": 68120 }, { "epoch": 0.726798459453981, "grad_norm": 1.1444607930530666, "learning_rate": 1.3575545323212693e-05, "loss": 0.6285, "num_tokens": 406387428.0, "step": 68125 }, { "epoch": 0.7268518024601794, "grad_norm": 0.708463379737393, "learning_rate": 1.3572427850351827e-05, "loss": 0.4407, "num_tokens": 406422217.0, "step": 68130 }, { "epoch": 0.7269051454663779, "grad_norm": 1.0355586138887496, "learning_rate": 1.3569310810888391e-05, "loss": 0.3923, "num_tokens": 406450092.0, "step": 68135 }, { "epoch": 0.7269584884725764, "grad_norm": 0.7177217575119988, "learning_rate": 1.3566194204919402e-05, "loss": 0.4107, "num_tokens": 406468400.0, "step": 68140 }, { "epoch": 0.7270118314787748, "grad_norm": 0.7630111475297999, "learning_rate": 1.3563078032541817e-05, "loss": 0.4604, "num_tokens": 406501308.0, "step": 68145 }, { "epoch": 0.7270651744849733, "grad_norm": 1.0091257970656946, "learning_rate": 1.3559962293852624e-05, "loss": 0.6075, "num_tokens": 406543454.0, "step": 68150 }, { "epoch": 0.7271185174911717, "grad_norm": 0.7635738035427204, "learning_rate": 1.3556846988948774e-05, "loss": 0.5516, "num_tokens": 406584433.0, "step": 68155 }, { "epoch": 0.7271718604973701, "grad_norm": 1.402719312602388, "learning_rate": 1.3553732117927196e-05, "loss": 0.656, "num_tokens": 406613744.0, "step": 68160 }, { "epoch": 0.7272252035035687, "grad_norm": 1.0235634391420325, "learning_rate": 1.3550617680884831e-05, "loss": 0.4565, "num_tokens": 406628911.0, "step": 68165 }, { "epoch": 0.7272785465097671, "grad_norm": 0.7122650274340762, "learning_rate": 1.3547503677918595e-05, "loss": 0.6011, "num_tokens": 406683296.0, "step": 68170 }, { "epoch": 0.7273318895159656, "grad_norm": 0.6722693286723521, "learning_rate": 1.3544390109125377e-05, "loss": 0.6184, "num_tokens": 406707333.0, "step": 68175 }, { "epoch": 0.727385232522164, "grad_norm": 0.6248809964212197, "learning_rate": 1.3541276974602074e-05, "loss": 0.4996, "num_tokens": 406739800.0, "step": 68180 }, { "epoch": 0.7274385755283624, "grad_norm": 0.991949127566155, "learning_rate": 1.353816427444557e-05, "loss": 0.3892, "num_tokens": 406761713.0, "step": 68185 }, { "epoch": 0.727491918534561, "grad_norm": 0.8198407236869879, "learning_rate": 1.3535052008752714e-05, "loss": 0.4783, "num_tokens": 406795027.0, "step": 68190 }, { "epoch": 0.7275452615407594, "grad_norm": 0.594452556743171, "learning_rate": 1.3531940177620345e-05, "loss": 0.4647, "num_tokens": 406825544.0, "step": 68195 }, { "epoch": 0.7275986045469578, "grad_norm": 0.9687339015705253, "learning_rate": 1.3528828781145314e-05, "loss": 0.4063, "num_tokens": 406851724.0, "step": 68200 }, { "epoch": 0.7276519475531563, "grad_norm": 0.9860608989327763, "learning_rate": 1.3525717819424427e-05, "loss": 0.4307, "num_tokens": 406873307.0, "step": 68205 }, { "epoch": 0.7277052905593547, "grad_norm": 0.8298415396742438, "learning_rate": 1.3522607292554501e-05, "loss": 0.4422, "num_tokens": 406893599.0, "step": 68210 }, { "epoch": 0.7277586335655533, "grad_norm": 1.2982434838460788, "learning_rate": 1.351949720063233e-05, "loss": 0.5488, "num_tokens": 406925309.0, "step": 68215 }, { "epoch": 0.7278119765717517, "grad_norm": 0.6253725216020114, "learning_rate": 1.3516387543754682e-05, "loss": 0.5154, "num_tokens": 406959083.0, "step": 68220 }, { "epoch": 0.7278653195779501, "grad_norm": 0.88070677170757, "learning_rate": 1.3513278322018336e-05, "loss": 0.4991, "num_tokens": 406985708.0, "step": 68225 }, { "epoch": 0.7279186625841486, "grad_norm": 0.7647153577003185, "learning_rate": 1.3510169535520035e-05, "loss": 0.4506, "num_tokens": 407010703.0, "step": 68230 }, { "epoch": 0.727972005590347, "grad_norm": 0.7188363085637499, "learning_rate": 1.350706118435653e-05, "loss": 0.4313, "num_tokens": 407051140.0, "step": 68235 }, { "epoch": 0.7280253485965456, "grad_norm": 1.0157942367104107, "learning_rate": 1.3503953268624525e-05, "loss": 0.4337, "num_tokens": 407072135.0, "step": 68240 }, { "epoch": 0.728078691602744, "grad_norm": 0.5421188589785159, "learning_rate": 1.3500845788420752e-05, "loss": 0.5727, "num_tokens": 407125741.0, "step": 68245 }, { "epoch": 0.7281320346089424, "grad_norm": 0.7563361463240001, "learning_rate": 1.3497738743841908e-05, "loss": 0.4716, "num_tokens": 407162327.0, "step": 68250 }, { "epoch": 0.7281853776151409, "grad_norm": 1.0906290254070092, "learning_rate": 1.3494632134984663e-05, "loss": 0.3434, "num_tokens": 407184709.0, "step": 68255 }, { "epoch": 0.7282387206213393, "grad_norm": 0.5332876781048259, "learning_rate": 1.349152596194571e-05, "loss": 0.4531, "num_tokens": 407218592.0, "step": 68260 }, { "epoch": 0.7282920636275378, "grad_norm": 0.7137633864602696, "learning_rate": 1.3488420224821691e-05, "loss": 0.6043, "num_tokens": 407279030.0, "step": 68265 }, { "epoch": 0.7283454066337363, "grad_norm": 0.6483275843632768, "learning_rate": 1.3485314923709252e-05, "loss": 0.4298, "num_tokens": 407324664.0, "step": 68270 }, { "epoch": 0.7283987496399347, "grad_norm": 1.884774801337928, "learning_rate": 1.348221005870502e-05, "loss": 0.5185, "num_tokens": 407348445.0, "step": 68275 }, { "epoch": 0.7284520926461332, "grad_norm": 0.6350532962916364, "learning_rate": 1.3479105629905628e-05, "loss": 0.4703, "num_tokens": 407381254.0, "step": 68280 }, { "epoch": 0.7285054356523316, "grad_norm": 1.317263903339903, "learning_rate": 1.3476001637407658e-05, "loss": 0.4974, "num_tokens": 407419603.0, "step": 68285 }, { "epoch": 0.72855877865853, "grad_norm": 1.082827066927214, "learning_rate": 1.3472898081307716e-05, "loss": 0.522, "num_tokens": 407450815.0, "step": 68290 }, { "epoch": 0.7286121216647286, "grad_norm": 0.8308930751634063, "learning_rate": 1.3469794961702378e-05, "loss": 0.5341, "num_tokens": 407488153.0, "step": 68295 }, { "epoch": 0.728665464670927, "grad_norm": 2.3850049671996048, "learning_rate": 1.3466692278688203e-05, "loss": 0.5591, "num_tokens": 407517272.0, "step": 68300 }, { "epoch": 0.7287188076771255, "grad_norm": 0.9949382883210651, "learning_rate": 1.3463590032361734e-05, "loss": 0.5091, "num_tokens": 407545620.0, "step": 68305 }, { "epoch": 0.7287721506833239, "grad_norm": 0.714850508907725, "learning_rate": 1.3460488222819511e-05, "loss": 0.423, "num_tokens": 407575085.0, "step": 68310 }, { "epoch": 0.7288254936895223, "grad_norm": 2.1977042272124243, "learning_rate": 1.3457386850158054e-05, "loss": 0.4406, "num_tokens": 407602365.0, "step": 68315 }, { "epoch": 0.7288788366957208, "grad_norm": 1.3836581703065491, "learning_rate": 1.3454285914473875e-05, "loss": 0.3967, "num_tokens": 407616178.0, "step": 68320 }, { "epoch": 0.7289321797019193, "grad_norm": 0.888122390022648, "learning_rate": 1.3451185415863477e-05, "loss": 0.4947, "num_tokens": 407645789.0, "step": 68325 }, { "epoch": 0.7289855227081178, "grad_norm": 1.4992468894322073, "learning_rate": 1.3448085354423318e-05, "loss": 0.5402, "num_tokens": 407659678.0, "step": 68330 }, { "epoch": 0.7290388657143162, "grad_norm": 0.8378490786054738, "learning_rate": 1.3444985730249892e-05, "loss": 0.4309, "num_tokens": 407693296.0, "step": 68335 }, { "epoch": 0.7290922087205146, "grad_norm": 0.5286488173417755, "learning_rate": 1.3441886543439638e-05, "loss": 0.4551, "num_tokens": 407725206.0, "step": 68340 }, { "epoch": 0.7291455517267131, "grad_norm": 0.6472147469891202, "learning_rate": 1.3438787794088992e-05, "loss": 0.4763, "num_tokens": 407750226.0, "step": 68345 }, { "epoch": 0.7291988947329116, "grad_norm": 0.7636470392133371, "learning_rate": 1.3435689482294384e-05, "loss": 0.447, "num_tokens": 407782415.0, "step": 68350 }, { "epoch": 0.7292522377391101, "grad_norm": 1.1193866714584038, "learning_rate": 1.3432591608152242e-05, "loss": 0.4186, "num_tokens": 407810448.0, "step": 68355 }, { "epoch": 0.7293055807453085, "grad_norm": 0.6874642065768203, "learning_rate": 1.3429494171758947e-05, "loss": 0.515, "num_tokens": 407852021.0, "step": 68360 }, { "epoch": 0.7293589237515069, "grad_norm": 0.7971807039612354, "learning_rate": 1.3426397173210886e-05, "loss": 0.4414, "num_tokens": 407873767.0, "step": 68365 }, { "epoch": 0.7294122667577054, "grad_norm": 0.8097700269201025, "learning_rate": 1.342330061260445e-05, "loss": 0.4904, "num_tokens": 407916798.0, "step": 68370 }, { "epoch": 0.7294656097639038, "grad_norm": 1.2188270871355014, "learning_rate": 1.3420204490035982e-05, "loss": 0.586, "num_tokens": 407951389.0, "step": 68375 }, { "epoch": 0.7295189527701023, "grad_norm": 0.8091520305544947, "learning_rate": 1.3417108805601824e-05, "loss": 0.4451, "num_tokens": 407988086.0, "step": 68380 }, { "epoch": 0.7295722957763008, "grad_norm": 1.0866162884570543, "learning_rate": 1.341401355939832e-05, "loss": 0.4565, "num_tokens": 408022130.0, "step": 68385 }, { "epoch": 0.7296256387824992, "grad_norm": 0.8179819878333795, "learning_rate": 1.3410918751521773e-05, "loss": 0.4313, "num_tokens": 408050776.0, "step": 68390 }, { "epoch": 0.7296789817886977, "grad_norm": 0.818851523364026, "learning_rate": 1.3407824382068493e-05, "loss": 0.4516, "num_tokens": 408081934.0, "step": 68395 }, { "epoch": 0.7297323247948961, "grad_norm": 0.708963393967983, "learning_rate": 1.3404730451134778e-05, "loss": 0.4859, "num_tokens": 408108512.0, "step": 68400 }, { "epoch": 0.7297856678010946, "grad_norm": 1.426104883749244, "learning_rate": 1.3401636958816894e-05, "loss": 0.4494, "num_tokens": 408128032.0, "step": 68405 }, { "epoch": 0.7298390108072931, "grad_norm": 0.7613257627543594, "learning_rate": 1.3398543905211119e-05, "loss": 0.4613, "num_tokens": 408158323.0, "step": 68410 }, { "epoch": 0.7298923538134915, "grad_norm": 0.8827062184449773, "learning_rate": 1.3395451290413691e-05, "loss": 0.4942, "num_tokens": 408186552.0, "step": 68415 }, { "epoch": 0.72994569681969, "grad_norm": 1.009389795248803, "learning_rate": 1.3392359114520838e-05, "loss": 0.5447, "num_tokens": 408221206.0, "step": 68420 }, { "epoch": 0.7299990398258884, "grad_norm": 0.6871645007190774, "learning_rate": 1.338926737762879e-05, "loss": 0.4328, "num_tokens": 408246981.0, "step": 68425 }, { "epoch": 0.7300523828320868, "grad_norm": 0.709569136856365, "learning_rate": 1.3386176079833768e-05, "loss": 0.5083, "num_tokens": 408272275.0, "step": 68430 }, { "epoch": 0.7301057258382854, "grad_norm": 0.8797653091322042, "learning_rate": 1.3383085221231944e-05, "loss": 0.5352, "num_tokens": 408313147.0, "step": 68435 }, { "epoch": 0.7301590688444838, "grad_norm": 0.8606090931614007, "learning_rate": 1.3379994801919524e-05, "loss": 0.5353, "num_tokens": 408358816.0, "step": 68440 }, { "epoch": 0.7302124118506823, "grad_norm": 1.3015799306937497, "learning_rate": 1.337690482199266e-05, "loss": 0.638, "num_tokens": 408389981.0, "step": 68445 }, { "epoch": 0.7302657548568807, "grad_norm": 0.6396579639420622, "learning_rate": 1.3373815281547497e-05, "loss": 0.4913, "num_tokens": 408427221.0, "step": 68450 }, { "epoch": 0.7303190978630791, "grad_norm": 1.3721707417197893, "learning_rate": 1.3370726180680193e-05, "loss": 0.5051, "num_tokens": 408446542.0, "step": 68455 }, { "epoch": 0.7303724408692777, "grad_norm": 0.6178154498658223, "learning_rate": 1.336763751948687e-05, "loss": 0.3683, "num_tokens": 408474619.0, "step": 68460 }, { "epoch": 0.7304257838754761, "grad_norm": 0.7024995378680079, "learning_rate": 1.3364549298063633e-05, "loss": 0.5069, "num_tokens": 408528376.0, "step": 68465 }, { "epoch": 0.7304791268816745, "grad_norm": 1.0544350042958648, "learning_rate": 1.336146151650659e-05, "loss": 0.5635, "num_tokens": 408544829.0, "step": 68470 }, { "epoch": 0.730532469887873, "grad_norm": 0.8864134947194777, "learning_rate": 1.3358374174911825e-05, "loss": 0.406, "num_tokens": 408561864.0, "step": 68475 }, { "epoch": 0.7305858128940714, "grad_norm": 1.0956663845987256, "learning_rate": 1.3355287273375413e-05, "loss": 0.3803, "num_tokens": 408582799.0, "step": 68480 }, { "epoch": 0.73063915590027, "grad_norm": 0.69457530987303, "learning_rate": 1.3352200811993399e-05, "loss": 0.5728, "num_tokens": 408623458.0, "step": 68485 }, { "epoch": 0.7306924989064684, "grad_norm": 0.7535175440330822, "learning_rate": 1.334911479086184e-05, "loss": 0.4719, "num_tokens": 408657609.0, "step": 68490 }, { "epoch": 0.7307458419126668, "grad_norm": 0.9182098457784652, "learning_rate": 1.3346029210076754e-05, "loss": 0.4614, "num_tokens": 408689205.0, "step": 68495 }, { "epoch": 0.7307991849188653, "grad_norm": 0.6210225166596137, "learning_rate": 1.3342944069734167e-05, "loss": 0.5233, "num_tokens": 408719086.0, "step": 68500 }, { "epoch": 0.7308525279250637, "grad_norm": 0.758168535459316, "learning_rate": 1.3339859369930092e-05, "loss": 0.4278, "num_tokens": 408748497.0, "step": 68505 }, { "epoch": 0.7309058709312622, "grad_norm": 0.8106636847492559, "learning_rate": 1.3336775110760494e-05, "loss": 0.4185, "num_tokens": 408789531.0, "step": 68510 }, { "epoch": 0.7309592139374607, "grad_norm": 1.0607804317139073, "learning_rate": 1.3333691292321376e-05, "loss": 0.3231, "num_tokens": 408803211.0, "step": 68515 }, { "epoch": 0.7310125569436591, "grad_norm": 1.2896827956634456, "learning_rate": 1.333060791470868e-05, "loss": 0.6651, "num_tokens": 408843608.0, "step": 68520 }, { "epoch": 0.7310658999498576, "grad_norm": 0.8483846978495114, "learning_rate": 1.3327524978018357e-05, "loss": 0.3914, "num_tokens": 408860669.0, "step": 68525 }, { "epoch": 0.731119242956056, "grad_norm": 0.7935632509673058, "learning_rate": 1.332444248234635e-05, "loss": 0.4858, "num_tokens": 408883764.0, "step": 68530 }, { "epoch": 0.7311725859622545, "grad_norm": 1.1158411133592772, "learning_rate": 1.3321360427788576e-05, "loss": 0.4537, "num_tokens": 408918587.0, "step": 68535 }, { "epoch": 0.731225928968453, "grad_norm": 0.5857361933297041, "learning_rate": 1.3318278814440938e-05, "loss": 0.4193, "num_tokens": 408945200.0, "step": 68540 }, { "epoch": 0.7312792719746514, "grad_norm": 2.088037347647472, "learning_rate": 1.3315197642399333e-05, "loss": 0.5627, "num_tokens": 408969989.0, "step": 68545 }, { "epoch": 0.7313326149808499, "grad_norm": 1.6406234046854538, "learning_rate": 1.3312116911759647e-05, "loss": 0.4985, "num_tokens": 408997748.0, "step": 68550 }, { "epoch": 0.7313859579870483, "grad_norm": 0.9085823745409995, "learning_rate": 1.3309036622617737e-05, "loss": 0.4106, "num_tokens": 409019377.0, "step": 68555 }, { "epoch": 0.7314393009932467, "grad_norm": 1.0464708827739146, "learning_rate": 1.3305956775069456e-05, "loss": 0.4818, "num_tokens": 409034121.0, "step": 68560 }, { "epoch": 0.7314926439994452, "grad_norm": 0.9789920563349777, "learning_rate": 1.330287736921065e-05, "loss": 0.5793, "num_tokens": 409064133.0, "step": 68565 }, { "epoch": 0.7315459870056437, "grad_norm": 1.2735372770724047, "learning_rate": 1.3299798405137135e-05, "loss": 0.4668, "num_tokens": 409100536.0, "step": 68570 }, { "epoch": 0.7315993300118422, "grad_norm": 0.7526026798091092, "learning_rate": 1.329671988294472e-05, "loss": 0.5176, "num_tokens": 409131269.0, "step": 68575 }, { "epoch": 0.7316526730180406, "grad_norm": 0.7772341332962517, "learning_rate": 1.3293641802729217e-05, "loss": 0.4668, "num_tokens": 409160049.0, "step": 68580 }, { "epoch": 0.731706016024239, "grad_norm": 1.0461655834374355, "learning_rate": 1.3290564164586394e-05, "loss": 0.4118, "num_tokens": 409196904.0, "step": 68585 }, { "epoch": 0.7317593590304375, "grad_norm": 1.0118054978213993, "learning_rate": 1.3287486968612038e-05, "loss": 0.4486, "num_tokens": 409217928.0, "step": 68590 }, { "epoch": 0.731812702036636, "grad_norm": 0.856087917036979, "learning_rate": 1.3284410214901888e-05, "loss": 0.5649, "num_tokens": 409244805.0, "step": 68595 }, { "epoch": 0.7318660450428345, "grad_norm": 0.7753866555438154, "learning_rate": 1.3281333903551688e-05, "loss": 0.539, "num_tokens": 409271833.0, "step": 68600 }, { "epoch": 0.7319193880490329, "grad_norm": 0.9330107504227066, "learning_rate": 1.3278258034657171e-05, "loss": 0.5474, "num_tokens": 409290896.0, "step": 68605 }, { "epoch": 0.7319727310552313, "grad_norm": 0.833211171874957, "learning_rate": 1.3275182608314057e-05, "loss": 0.5065, "num_tokens": 409319265.0, "step": 68610 }, { "epoch": 0.7320260740614298, "grad_norm": 1.0508143332116582, "learning_rate": 1.3272107624618035e-05, "loss": 0.3992, "num_tokens": 409346164.0, "step": 68615 }, { "epoch": 0.7320794170676282, "grad_norm": 1.0872684732891056, "learning_rate": 1.32690330836648e-05, "loss": 0.5629, "num_tokens": 409385100.0, "step": 68620 }, { "epoch": 0.7321327600738268, "grad_norm": 0.7785942759964459, "learning_rate": 1.326595898555003e-05, "loss": 0.4731, "num_tokens": 409407581.0, "step": 68625 }, { "epoch": 0.7321861030800252, "grad_norm": 0.5920138646316694, "learning_rate": 1.3262885330369382e-05, "loss": 0.4555, "num_tokens": 409441458.0, "step": 68630 }, { "epoch": 0.7322394460862236, "grad_norm": 0.9677047956907554, "learning_rate": 1.3259812118218487e-05, "loss": 0.4964, "num_tokens": 409464401.0, "step": 68635 }, { "epoch": 0.7322927890924221, "grad_norm": 1.2015326393531547, "learning_rate": 1.3256739349192998e-05, "loss": 0.5828, "num_tokens": 409481975.0, "step": 68640 }, { "epoch": 0.7323461320986205, "grad_norm": 0.8221155690797316, "learning_rate": 1.3253667023388516e-05, "loss": 0.5537, "num_tokens": 409507685.0, "step": 68645 }, { "epoch": 0.732399475104819, "grad_norm": 0.9941044362780384, "learning_rate": 1.3250595140900657e-05, "loss": 0.5557, "num_tokens": 409539706.0, "step": 68650 }, { "epoch": 0.7324528181110175, "grad_norm": 1.024322027740417, "learning_rate": 1.324752370182501e-05, "loss": 0.4088, "num_tokens": 409578105.0, "step": 68655 }, { "epoch": 0.7325061611172159, "grad_norm": 1.0358543219691405, "learning_rate": 1.3244452706257146e-05, "loss": 0.4699, "num_tokens": 409630562.0, "step": 68660 }, { "epoch": 0.7325595041234144, "grad_norm": 0.8744675038964325, "learning_rate": 1.3241382154292639e-05, "loss": 0.4641, "num_tokens": 409654843.0, "step": 68665 }, { "epoch": 0.7326128471296128, "grad_norm": 1.0148058715302226, "learning_rate": 1.323831204602703e-05, "loss": 0.5073, "num_tokens": 409678215.0, "step": 68670 }, { "epoch": 0.7326661901358112, "grad_norm": 0.7705931780611236, "learning_rate": 1.3235242381555852e-05, "loss": 0.5654, "num_tokens": 409707290.0, "step": 68675 }, { "epoch": 0.7327195331420098, "grad_norm": 1.3538395726493648, "learning_rate": 1.3232173160974628e-05, "loss": 0.4261, "num_tokens": 409728304.0, "step": 68680 }, { "epoch": 0.7327728761482082, "grad_norm": 0.9338473680470734, "learning_rate": 1.3229104384378877e-05, "loss": 0.5124, "num_tokens": 409753088.0, "step": 68685 }, { "epoch": 0.7328262191544067, "grad_norm": 0.9488288087677935, "learning_rate": 1.3226036051864075e-05, "loss": 0.4663, "num_tokens": 409782677.0, "step": 68690 }, { "epoch": 0.7328795621606051, "grad_norm": 0.6594256784324087, "learning_rate": 1.3222968163525712e-05, "loss": 0.3995, "num_tokens": 409809594.0, "step": 68695 }, { "epoch": 0.7329329051668035, "grad_norm": 1.0656060894490051, "learning_rate": 1.321990071945926e-05, "loss": 0.3836, "num_tokens": 409830743.0, "step": 68700 }, { "epoch": 0.7329862481730021, "grad_norm": 1.10137572266859, "learning_rate": 1.3216833719760166e-05, "loss": 0.4276, "num_tokens": 409856113.0, "step": 68705 }, { "epoch": 0.7330395911792005, "grad_norm": 1.3345166144365368, "learning_rate": 1.321376716452386e-05, "loss": 0.5984, "num_tokens": 409906444.0, "step": 68710 }, { "epoch": 0.733092934185399, "grad_norm": 0.9748474606437273, "learning_rate": 1.3210701053845786e-05, "loss": 0.4362, "num_tokens": 409932355.0, "step": 68715 }, { "epoch": 0.7331462771915974, "grad_norm": 0.9613782273471524, "learning_rate": 1.3207635387821334e-05, "loss": 0.4995, "num_tokens": 409967114.0, "step": 68720 }, { "epoch": 0.7331996201977958, "grad_norm": 0.6428839924788398, "learning_rate": 1.3204570166545912e-05, "loss": 0.4332, "num_tokens": 410017110.0, "step": 68725 }, { "epoch": 0.7332529632039944, "grad_norm": 0.9558849084086602, "learning_rate": 1.320150539011491e-05, "loss": 0.6575, "num_tokens": 410051507.0, "step": 68730 }, { "epoch": 0.7333063062101928, "grad_norm": 1.5359295303263631, "learning_rate": 1.3198441058623683e-05, "loss": 0.5307, "num_tokens": 410085502.0, "step": 68735 }, { "epoch": 0.7333596492163912, "grad_norm": 0.9567874742824467, "learning_rate": 1.31953771721676e-05, "loss": 0.5823, "num_tokens": 410113619.0, "step": 68740 }, { "epoch": 0.7334129922225897, "grad_norm": 1.1426457720042462, "learning_rate": 1.3192313730841999e-05, "loss": 0.4644, "num_tokens": 410135834.0, "step": 68745 }, { "epoch": 0.7334663352287881, "grad_norm": 1.4553396519603354, "learning_rate": 1.3189250734742199e-05, "loss": 0.4783, "num_tokens": 410167905.0, "step": 68750 }, { "epoch": 0.7335196782349866, "grad_norm": 0.7087512068975331, "learning_rate": 1.318618818396352e-05, "loss": 0.417, "num_tokens": 410200806.0, "step": 68755 }, { "epoch": 0.7335730212411851, "grad_norm": 1.2622992266815294, "learning_rate": 1.3183126078601271e-05, "loss": 0.4913, "num_tokens": 410233558.0, "step": 68760 }, { "epoch": 0.7336263642473835, "grad_norm": 0.7662665713404134, "learning_rate": 1.318006441875072e-05, "loss": 0.4928, "num_tokens": 410270234.0, "step": 68765 }, { "epoch": 0.733679707253582, "grad_norm": 1.0085930584700429, "learning_rate": 1.3177003204507163e-05, "loss": 0.5524, "num_tokens": 410301884.0, "step": 68770 }, { "epoch": 0.7337330502597804, "grad_norm": 1.3537663170549852, "learning_rate": 1.3173942435965845e-05, "loss": 0.5178, "num_tokens": 410331671.0, "step": 68775 }, { "epoch": 0.7337863932659789, "grad_norm": 2.505538382200729, "learning_rate": 1.3170882113222002e-05, "loss": 0.5363, "num_tokens": 410354067.0, "step": 68780 }, { "epoch": 0.7338397362721774, "grad_norm": 1.3372624675248612, "learning_rate": 1.3167822236370874e-05, "loss": 0.4588, "num_tokens": 410373371.0, "step": 68785 }, { "epoch": 0.7338930792783758, "grad_norm": 0.8038845121173085, "learning_rate": 1.3164762805507691e-05, "loss": 0.4001, "num_tokens": 410398451.0, "step": 68790 }, { "epoch": 0.7339464222845743, "grad_norm": 1.3490706631162057, "learning_rate": 1.3161703820727634e-05, "loss": 0.5484, "num_tokens": 410426917.0, "step": 68795 }, { "epoch": 0.7339997652907727, "grad_norm": 0.9627266612568027, "learning_rate": 1.3158645282125898e-05, "loss": 0.5062, "num_tokens": 410442926.0, "step": 68800 }, { "epoch": 0.7340531082969712, "grad_norm": 0.9681103403430865, "learning_rate": 1.3155587189797675e-05, "loss": 0.5267, "num_tokens": 410485339.0, "step": 68805 }, { "epoch": 0.7341064513031696, "grad_norm": 1.5258423830810224, "learning_rate": 1.3152529543838116e-05, "loss": 0.4646, "num_tokens": 410507254.0, "step": 68810 }, { "epoch": 0.7341597943093681, "grad_norm": 1.0501765593979604, "learning_rate": 1.3149472344342356e-05, "loss": 0.4521, "num_tokens": 410534960.0, "step": 68815 }, { "epoch": 0.7342131373155666, "grad_norm": 0.7674942184322353, "learning_rate": 1.3146415591405547e-05, "loss": 0.5932, "num_tokens": 410581857.0, "step": 68820 }, { "epoch": 0.734266480321765, "grad_norm": 0.669386922480519, "learning_rate": 1.3143359285122798e-05, "loss": 0.4618, "num_tokens": 410617756.0, "step": 68825 }, { "epoch": 0.7343198233279634, "grad_norm": 0.9950123333757744, "learning_rate": 1.3140303425589218e-05, "loss": 0.4445, "num_tokens": 410644764.0, "step": 68830 }, { "epoch": 0.7343731663341619, "grad_norm": 0.7318928472852939, "learning_rate": 1.3137248012899905e-05, "loss": 0.6017, "num_tokens": 410692040.0, "step": 68835 }, { "epoch": 0.7344265093403604, "grad_norm": 0.8941648000588824, "learning_rate": 1.3134193047149923e-05, "loss": 0.3699, "num_tokens": 410732749.0, "step": 68840 }, { "epoch": 0.7344798523465589, "grad_norm": 1.1471039450886342, "learning_rate": 1.3131138528434356e-05, "loss": 0.3638, "num_tokens": 410745658.0, "step": 68845 }, { "epoch": 0.7345331953527573, "grad_norm": 0.8724112048394776, "learning_rate": 1.3128084456848242e-05, "loss": 0.4542, "num_tokens": 410772939.0, "step": 68850 }, { "epoch": 0.7345865383589557, "grad_norm": 0.7593966776539516, "learning_rate": 1.3125030832486613e-05, "loss": 0.5148, "num_tokens": 410810556.0, "step": 68855 }, { "epoch": 0.7346398813651542, "grad_norm": 0.8896969648273375, "learning_rate": 1.3121977655444496e-05, "loss": 0.4275, "num_tokens": 410846817.0, "step": 68860 }, { "epoch": 0.7346932243713526, "grad_norm": 1.1138991996968184, "learning_rate": 1.3118924925816908e-05, "loss": 0.4522, "num_tokens": 410867847.0, "step": 68865 }, { "epoch": 0.7347465673775512, "grad_norm": 0.8553814196806386, "learning_rate": 1.3115872643698828e-05, "loss": 0.3856, "num_tokens": 410887974.0, "step": 68870 }, { "epoch": 0.7347999103837496, "grad_norm": 1.4632036733079006, "learning_rate": 1.311282080918525e-05, "loss": 0.4478, "num_tokens": 410908313.0, "step": 68875 }, { "epoch": 0.734853253389948, "grad_norm": 1.4778695705852027, "learning_rate": 1.3109769422371142e-05, "loss": 0.5437, "num_tokens": 410936746.0, "step": 68880 }, { "epoch": 0.7349065963961465, "grad_norm": 2.1570468235250853, "learning_rate": 1.3106718483351449e-05, "loss": 0.6677, "num_tokens": 410957918.0, "step": 68885 }, { "epoch": 0.7349599394023449, "grad_norm": 0.7110748089652911, "learning_rate": 1.3103667992221107e-05, "loss": 0.4807, "num_tokens": 411001914.0, "step": 68890 }, { "epoch": 0.7350132824085435, "grad_norm": 0.7697037067732538, "learning_rate": 1.3100617949075053e-05, "loss": 0.5283, "num_tokens": 411035247.0, "step": 68895 }, { "epoch": 0.7350666254147419, "grad_norm": 0.8527358795058947, "learning_rate": 1.3097568354008183e-05, "loss": 0.4978, "num_tokens": 411066945.0, "step": 68900 }, { "epoch": 0.7351199684209403, "grad_norm": 0.5636570425140305, "learning_rate": 1.3094519207115402e-05, "loss": 0.5122, "num_tokens": 411117268.0, "step": 68905 }, { "epoch": 0.7351733114271388, "grad_norm": 1.0501661331480325, "learning_rate": 1.3091470508491604e-05, "loss": 0.4302, "num_tokens": 411132906.0, "step": 68910 }, { "epoch": 0.7352266544333372, "grad_norm": 0.5267771172437113, "learning_rate": 1.3088422258231636e-05, "loss": 0.4051, "num_tokens": 411162407.0, "step": 68915 }, { "epoch": 0.7352799974395356, "grad_norm": 0.6106127407885776, "learning_rate": 1.3085374456430377e-05, "loss": 0.4049, "num_tokens": 411195408.0, "step": 68920 }, { "epoch": 0.7353333404457342, "grad_norm": 0.9341074524581161, "learning_rate": 1.3082327103182657e-05, "loss": 0.3864, "num_tokens": 411216687.0, "step": 68925 }, { "epoch": 0.7353866834519326, "grad_norm": 0.6554993988049508, "learning_rate": 1.307928019858329e-05, "loss": 0.4802, "num_tokens": 411242589.0, "step": 68930 }, { "epoch": 0.7354400264581311, "grad_norm": 0.9172123444856498, "learning_rate": 1.3076233742727107e-05, "loss": 0.5239, "num_tokens": 411274266.0, "step": 68935 }, { "epoch": 0.7354933694643295, "grad_norm": 0.8763095803582005, "learning_rate": 1.3073187735708908e-05, "loss": 0.5966, "num_tokens": 411319750.0, "step": 68940 }, { "epoch": 0.7355467124705279, "grad_norm": 1.6580904894243644, "learning_rate": 1.3070142177623462e-05, "loss": 0.4143, "num_tokens": 411334908.0, "step": 68945 }, { "epoch": 0.7356000554767265, "grad_norm": 1.7167233099618144, "learning_rate": 1.306709706856556e-05, "loss": 0.4713, "num_tokens": 411363487.0, "step": 68950 }, { "epoch": 0.7356533984829249, "grad_norm": 0.7717258600190744, "learning_rate": 1.306405240862995e-05, "loss": 0.6367, "num_tokens": 411398974.0, "step": 68955 }, { "epoch": 0.7357067414891234, "grad_norm": 1.1113774637070681, "learning_rate": 1.3061008197911384e-05, "loss": 0.5077, "num_tokens": 411425070.0, "step": 68960 }, { "epoch": 0.7357600844953218, "grad_norm": 1.1561758457759317, "learning_rate": 1.3057964436504571e-05, "loss": 0.3884, "num_tokens": 411441768.0, "step": 68965 }, { "epoch": 0.7358134275015202, "grad_norm": 1.2615732440901546, "learning_rate": 1.305492112450425e-05, "loss": 0.4615, "num_tokens": 411472011.0, "step": 68970 }, { "epoch": 0.7358667705077188, "grad_norm": 0.6103949067581945, "learning_rate": 1.3051878262005106e-05, "loss": 0.5928, "num_tokens": 411513883.0, "step": 68975 }, { "epoch": 0.7359201135139172, "grad_norm": 0.9050134494392149, "learning_rate": 1.3048835849101832e-05, "loss": 0.4353, "num_tokens": 411542385.0, "step": 68980 }, { "epoch": 0.7359734565201157, "grad_norm": 1.2472041629926698, "learning_rate": 1.304579388588911e-05, "loss": 0.4424, "num_tokens": 411566220.0, "step": 68985 }, { "epoch": 0.7360267995263141, "grad_norm": 1.2554308159275118, "learning_rate": 1.3042752372461587e-05, "loss": 0.5252, "num_tokens": 411581320.0, "step": 68990 }, { "epoch": 0.7360801425325125, "grad_norm": 1.131740511269136, "learning_rate": 1.303971130891392e-05, "loss": 0.3912, "num_tokens": 411596584.0, "step": 68995 }, { "epoch": 0.736133485538711, "grad_norm": 0.9739923643540953, "learning_rate": 1.3036670695340735e-05, "loss": 0.476, "num_tokens": 411614268.0, "step": 69000 }, { "epoch": 0.7361868285449095, "grad_norm": 1.0360227127983959, "learning_rate": 1.3033630531836643e-05, "loss": 0.4096, "num_tokens": 411644717.0, "step": 69005 }, { "epoch": 0.7362401715511079, "grad_norm": 0.7355607147653433, "learning_rate": 1.3030590818496253e-05, "loss": 0.5163, "num_tokens": 411673590.0, "step": 69010 }, { "epoch": 0.7362935145573064, "grad_norm": 1.7975975016488384, "learning_rate": 1.3027551555414164e-05, "loss": 0.4214, "num_tokens": 411712006.0, "step": 69015 }, { "epoch": 0.7363468575635048, "grad_norm": 0.7397406868927116, "learning_rate": 1.3024512742684932e-05, "loss": 0.507, "num_tokens": 411745408.0, "step": 69020 }, { "epoch": 0.7364002005697033, "grad_norm": 0.6773104161648912, "learning_rate": 1.3021474380403135e-05, "loss": 0.5672, "num_tokens": 411774309.0, "step": 69025 }, { "epoch": 0.7364535435759018, "grad_norm": 1.00835597986469, "learning_rate": 1.3018436468663322e-05, "loss": 0.4883, "num_tokens": 411792139.0, "step": 69030 }, { "epoch": 0.7365068865821002, "grad_norm": 0.9271230236505369, "learning_rate": 1.301539900756002e-05, "loss": 0.5405, "num_tokens": 411832919.0, "step": 69035 }, { "epoch": 0.7365602295882987, "grad_norm": 0.8103528226986256, "learning_rate": 1.301236199718774e-05, "loss": 0.4484, "num_tokens": 411857021.0, "step": 69040 }, { "epoch": 0.7366135725944971, "grad_norm": 0.8646558524681953, "learning_rate": 1.3009325437641001e-05, "loss": 0.5225, "num_tokens": 411894218.0, "step": 69045 }, { "epoch": 0.7366669156006956, "grad_norm": 0.9058488541687699, "learning_rate": 1.3006289329014288e-05, "loss": 0.3847, "num_tokens": 411917286.0, "step": 69050 }, { "epoch": 0.736720258606894, "grad_norm": 0.8790018868135201, "learning_rate": 1.3003253671402076e-05, "loss": 0.5034, "num_tokens": 411946781.0, "step": 69055 }, { "epoch": 0.7367736016130925, "grad_norm": 0.9031274692771012, "learning_rate": 1.3000218464898841e-05, "loss": 0.4509, "num_tokens": 411978360.0, "step": 69060 }, { "epoch": 0.736826944619291, "grad_norm": 0.7380259050506619, "learning_rate": 1.2997183709599026e-05, "loss": 0.4811, "num_tokens": 412019294.0, "step": 69065 }, { "epoch": 0.7368802876254894, "grad_norm": 0.7360806777562741, "learning_rate": 1.2994149405597055e-05, "loss": 0.5005, "num_tokens": 412045731.0, "step": 69070 }, { "epoch": 0.7369336306316879, "grad_norm": 0.6802528454299009, "learning_rate": 1.2991115552987368e-05, "loss": 0.5605, "num_tokens": 412087402.0, "step": 69075 }, { "epoch": 0.7369869736378863, "grad_norm": 1.1516226019457492, "learning_rate": 1.2988082151864353e-05, "loss": 0.3999, "num_tokens": 412114895.0, "step": 69080 }, { "epoch": 0.7370403166440848, "grad_norm": 0.8723198794092456, "learning_rate": 1.2985049202322414e-05, "loss": 0.5227, "num_tokens": 412154062.0, "step": 69085 }, { "epoch": 0.7370936596502833, "grad_norm": 0.7659233249484595, "learning_rate": 1.2982016704455934e-05, "loss": 0.5154, "num_tokens": 412190980.0, "step": 69090 }, { "epoch": 0.7371470026564817, "grad_norm": 0.8091070670612747, "learning_rate": 1.2978984658359269e-05, "loss": 0.4227, "num_tokens": 412224463.0, "step": 69095 }, { "epoch": 0.7372003456626801, "grad_norm": 0.6184782809724516, "learning_rate": 1.2975953064126783e-05, "loss": 0.4726, "num_tokens": 412262436.0, "step": 69100 }, { "epoch": 0.7372536886688786, "grad_norm": 0.6118797230529622, "learning_rate": 1.2972921921852804e-05, "loss": 0.492, "num_tokens": 412301028.0, "step": 69105 }, { "epoch": 0.737307031675077, "grad_norm": 0.7881529373114742, "learning_rate": 1.2969891231631647e-05, "loss": 0.535, "num_tokens": 412330616.0, "step": 69110 }, { "epoch": 0.7373603746812756, "grad_norm": 0.8595704850183234, "learning_rate": 1.2966860993557628e-05, "loss": 0.407, "num_tokens": 412357059.0, "step": 69115 }, { "epoch": 0.737413717687474, "grad_norm": 0.9918089361378656, "learning_rate": 1.2963831207725053e-05, "loss": 0.4916, "num_tokens": 412386009.0, "step": 69120 }, { "epoch": 0.7374670606936724, "grad_norm": 1.0715292200485644, "learning_rate": 1.2960801874228179e-05, "loss": 0.5024, "num_tokens": 412417712.0, "step": 69125 }, { "epoch": 0.7375204036998709, "grad_norm": 0.900526621897721, "learning_rate": 1.2957772993161294e-05, "loss": 0.4309, "num_tokens": 412457445.0, "step": 69130 }, { "epoch": 0.7375737467060693, "grad_norm": 0.8154978735777799, "learning_rate": 1.2954744564618646e-05, "loss": 0.609, "num_tokens": 412490291.0, "step": 69135 }, { "epoch": 0.7376270897122679, "grad_norm": 0.7442775146782199, "learning_rate": 1.2951716588694473e-05, "loss": 0.6368, "num_tokens": 412527407.0, "step": 69140 }, { "epoch": 0.7376804327184663, "grad_norm": 0.8938690126800359, "learning_rate": 1.2948689065482989e-05, "loss": 0.5038, "num_tokens": 412569707.0, "step": 69145 }, { "epoch": 0.7377337757246647, "grad_norm": 1.0757282049646169, "learning_rate": 1.2945661995078418e-05, "loss": 0.4938, "num_tokens": 412608947.0, "step": 69150 }, { "epoch": 0.7377871187308632, "grad_norm": 0.7543204768506441, "learning_rate": 1.294263537757494e-05, "loss": 0.5872, "num_tokens": 412646758.0, "step": 69155 }, { "epoch": 0.7378404617370616, "grad_norm": 1.2047122666892605, "learning_rate": 1.293960921306675e-05, "loss": 0.5804, "num_tokens": 412679892.0, "step": 69160 }, { "epoch": 0.7378938047432602, "grad_norm": 1.1241232987401404, "learning_rate": 1.2936583501648013e-05, "loss": 0.4194, "num_tokens": 412699105.0, "step": 69165 }, { "epoch": 0.7379471477494586, "grad_norm": 1.3987417629108176, "learning_rate": 1.2933558243412894e-05, "loss": 0.4511, "num_tokens": 412732095.0, "step": 69170 }, { "epoch": 0.738000490755657, "grad_norm": 0.9874851091603788, "learning_rate": 1.2930533438455519e-05, "loss": 0.5802, "num_tokens": 412762829.0, "step": 69175 }, { "epoch": 0.7380538337618555, "grad_norm": 1.1864468983012226, "learning_rate": 1.292750908687001e-05, "loss": 0.5259, "num_tokens": 412781525.0, "step": 69180 }, { "epoch": 0.7381071767680539, "grad_norm": 0.6937659264258353, "learning_rate": 1.2924485188750493e-05, "loss": 0.419, "num_tokens": 412816005.0, "step": 69185 }, { "epoch": 0.7381605197742523, "grad_norm": 0.7187138355652645, "learning_rate": 1.2921461744191052e-05, "loss": 0.5195, "num_tokens": 412839381.0, "step": 69190 }, { "epoch": 0.7382138627804509, "grad_norm": 1.0798726633507132, "learning_rate": 1.2918438753285772e-05, "loss": 0.6045, "num_tokens": 412864818.0, "step": 69195 }, { "epoch": 0.7382672057866493, "grad_norm": 0.5865744528581746, "learning_rate": 1.291541621612874e-05, "loss": 0.4833, "num_tokens": 412898144.0, "step": 69200 }, { "epoch": 0.7383205487928478, "grad_norm": 1.2105393570478953, "learning_rate": 1.2912394132813987e-05, "loss": 0.5189, "num_tokens": 412934094.0, "step": 69205 }, { "epoch": 0.7383738917990462, "grad_norm": 0.6361909557550096, "learning_rate": 1.2909372503435571e-05, "loss": 0.3763, "num_tokens": 412966400.0, "step": 69210 }, { "epoch": 0.7384272348052446, "grad_norm": 2.599040163093357, "learning_rate": 1.2906351328087517e-05, "loss": 0.5953, "num_tokens": 413003984.0, "step": 69215 }, { "epoch": 0.7384805778114432, "grad_norm": 0.8528970086769941, "learning_rate": 1.2903330606863822e-05, "loss": 0.3946, "num_tokens": 413021552.0, "step": 69220 }, { "epoch": 0.7385339208176416, "grad_norm": 1.09894175873847, "learning_rate": 1.2900310339858495e-05, "loss": 0.5308, "num_tokens": 413047402.0, "step": 69225 }, { "epoch": 0.7385872638238401, "grad_norm": 0.7620132580850414, "learning_rate": 1.2897290527165534e-05, "loss": 0.5345, "num_tokens": 413079049.0, "step": 69230 }, { "epoch": 0.7386406068300385, "grad_norm": 0.8759985502324279, "learning_rate": 1.2894271168878885e-05, "loss": 0.4663, "num_tokens": 413116516.0, "step": 69235 }, { "epoch": 0.7386939498362369, "grad_norm": 0.7837163093850256, "learning_rate": 1.2891252265092519e-05, "loss": 0.4708, "num_tokens": 413149054.0, "step": 69240 }, { "epoch": 0.7387472928424355, "grad_norm": 0.8335407467885427, "learning_rate": 1.288823381590038e-05, "loss": 0.4463, "num_tokens": 413179461.0, "step": 69245 }, { "epoch": 0.7388006358486339, "grad_norm": 1.1504033656911414, "learning_rate": 1.2885215821396397e-05, "loss": 0.3667, "num_tokens": 413208388.0, "step": 69250 }, { "epoch": 0.7388539788548324, "grad_norm": 0.7515939819558543, "learning_rate": 1.2882198281674462e-05, "loss": 0.4175, "num_tokens": 413230651.0, "step": 69255 }, { "epoch": 0.7389073218610308, "grad_norm": 1.169041548928391, "learning_rate": 1.2879181196828505e-05, "loss": 0.5426, "num_tokens": 413253285.0, "step": 69260 }, { "epoch": 0.7389606648672292, "grad_norm": 1.0856038431915371, "learning_rate": 1.2876164566952386e-05, "loss": 0.498, "num_tokens": 413280111.0, "step": 69265 }, { "epoch": 0.7390140078734277, "grad_norm": 1.086061033704871, "learning_rate": 1.2873148392139992e-05, "loss": 0.5966, "num_tokens": 413302017.0, "step": 69270 }, { "epoch": 0.7390673508796262, "grad_norm": 0.9229418027749037, "learning_rate": 1.287013267248518e-05, "loss": 0.4527, "num_tokens": 413325924.0, "step": 69275 }, { "epoch": 0.7391206938858246, "grad_norm": 1.9218583814269294, "learning_rate": 1.286711740808178e-05, "loss": 0.5372, "num_tokens": 413353038.0, "step": 69280 }, { "epoch": 0.7391740368920231, "grad_norm": 0.5998208771660454, "learning_rate": 1.2864102599023636e-05, "loss": 0.5151, "num_tokens": 413392377.0, "step": 69285 }, { "epoch": 0.7392273798982215, "grad_norm": 1.4340407457372415, "learning_rate": 1.2861088245404559e-05, "loss": 0.4231, "num_tokens": 413412401.0, "step": 69290 }, { "epoch": 0.73928072290442, "grad_norm": 0.807163307604711, "learning_rate": 1.2858074347318339e-05, "loss": 0.492, "num_tokens": 413440538.0, "step": 69295 }, { "epoch": 0.7393340659106185, "grad_norm": 1.6778604819312335, "learning_rate": 1.2855060904858767e-05, "loss": 0.5394, "num_tokens": 413479167.0, "step": 69300 }, { "epoch": 0.7393874089168169, "grad_norm": 0.8068403016870411, "learning_rate": 1.285204791811963e-05, "loss": 0.4385, "num_tokens": 413520530.0, "step": 69305 }, { "epoch": 0.7394407519230154, "grad_norm": 0.8871814782517486, "learning_rate": 1.2849035387194663e-05, "loss": 0.508, "num_tokens": 413557191.0, "step": 69310 }, { "epoch": 0.7394940949292138, "grad_norm": 1.0086995744875427, "learning_rate": 1.2846023312177621e-05, "loss": 0.5366, "num_tokens": 413579376.0, "step": 69315 }, { "epoch": 0.7395474379354123, "grad_norm": 0.8337332129208818, "learning_rate": 1.2843011693162244e-05, "loss": 0.5876, "num_tokens": 413612298.0, "step": 69320 }, { "epoch": 0.7396007809416107, "grad_norm": 2.1050112854241516, "learning_rate": 1.2840000530242236e-05, "loss": 0.5317, "num_tokens": 413649265.0, "step": 69325 }, { "epoch": 0.7396541239478092, "grad_norm": 0.6970593763450953, "learning_rate": 1.2836989823511292e-05, "loss": 0.4771, "num_tokens": 413687398.0, "step": 69330 }, { "epoch": 0.7397074669540077, "grad_norm": 1.1381158014977173, "learning_rate": 1.2833979573063107e-05, "loss": 0.4553, "num_tokens": 413722568.0, "step": 69335 }, { "epoch": 0.7397608099602061, "grad_norm": 0.7909290453558949, "learning_rate": 1.2830969778991353e-05, "loss": 0.4764, "num_tokens": 413743235.0, "step": 69340 }, { "epoch": 0.7398141529664046, "grad_norm": 1.0820058389874398, "learning_rate": 1.2827960441389686e-05, "loss": 0.5693, "num_tokens": 413773609.0, "step": 69345 }, { "epoch": 0.739867495972603, "grad_norm": 0.847422636800115, "learning_rate": 1.2824951560351759e-05, "loss": 0.4816, "num_tokens": 413808041.0, "step": 69350 }, { "epoch": 0.7399208389788015, "grad_norm": 0.7088978605649547, "learning_rate": 1.2821943135971195e-05, "loss": 0.5604, "num_tokens": 413841220.0, "step": 69355 }, { "epoch": 0.739974181985, "grad_norm": 0.8294417110747008, "learning_rate": 1.2818935168341606e-05, "loss": 0.5368, "num_tokens": 413894931.0, "step": 69360 }, { "epoch": 0.7400275249911984, "grad_norm": 1.4941350229654677, "learning_rate": 1.2815927657556606e-05, "loss": 0.5739, "num_tokens": 413927578.0, "step": 69365 }, { "epoch": 0.7400808679973968, "grad_norm": 0.7850418056154892, "learning_rate": 1.2812920603709765e-05, "loss": 0.5048, "num_tokens": 413953347.0, "step": 69370 }, { "epoch": 0.7401342110035953, "grad_norm": 0.7099354596265514, "learning_rate": 1.280991400689467e-05, "loss": 0.4803, "num_tokens": 413977250.0, "step": 69375 }, { "epoch": 0.7401875540097937, "grad_norm": 1.8304047354490525, "learning_rate": 1.2806907867204885e-05, "loss": 0.4975, "num_tokens": 414013636.0, "step": 69380 }, { "epoch": 0.7402408970159923, "grad_norm": 0.8200972192142194, "learning_rate": 1.280390218473394e-05, "loss": 0.4515, "num_tokens": 414033941.0, "step": 69385 }, { "epoch": 0.7402942400221907, "grad_norm": 0.945392870472867, "learning_rate": 1.2800896959575376e-05, "loss": 0.4084, "num_tokens": 414068976.0, "step": 69390 }, { "epoch": 0.7403475830283891, "grad_norm": 1.4587348636067086, "learning_rate": 1.2797892191822708e-05, "loss": 0.5208, "num_tokens": 414093025.0, "step": 69395 }, { "epoch": 0.7404009260345876, "grad_norm": 0.6522208405434613, "learning_rate": 1.2794887881569428e-05, "loss": 0.4923, "num_tokens": 414120101.0, "step": 69400 }, { "epoch": 0.740454269040786, "grad_norm": 0.7170074145326857, "learning_rate": 1.279188402890903e-05, "loss": 0.4102, "num_tokens": 414147889.0, "step": 69405 }, { "epoch": 0.7405076120469846, "grad_norm": 1.5089552330761078, "learning_rate": 1.2788880633935e-05, "loss": 0.6906, "num_tokens": 414173243.0, "step": 69410 }, { "epoch": 0.740560955053183, "grad_norm": 0.5515099663483605, "learning_rate": 1.2785877696740777e-05, "loss": 0.6281, "num_tokens": 414222166.0, "step": 69415 }, { "epoch": 0.7406142980593814, "grad_norm": 1.406515658069268, "learning_rate": 1.2782875217419821e-05, "loss": 0.4858, "num_tokens": 414251150.0, "step": 69420 }, { "epoch": 0.7406676410655799, "grad_norm": 3.076272977153778, "learning_rate": 1.2779873196065561e-05, "loss": 0.4277, "num_tokens": 414269962.0, "step": 69425 }, { "epoch": 0.7407209840717783, "grad_norm": 1.5074576512534201, "learning_rate": 1.2776871632771415e-05, "loss": 0.5261, "num_tokens": 414296354.0, "step": 69430 }, { "epoch": 0.7407743270779769, "grad_norm": 0.6012117236137782, "learning_rate": 1.2773870527630771e-05, "loss": 0.3967, "num_tokens": 414337612.0, "step": 69435 }, { "epoch": 0.7408276700841753, "grad_norm": 0.8331594196752541, "learning_rate": 1.2770869880737036e-05, "loss": 0.3986, "num_tokens": 414357432.0, "step": 69440 }, { "epoch": 0.7408810130903737, "grad_norm": 1.76464313357977, "learning_rate": 1.276786969218357e-05, "loss": 0.4871, "num_tokens": 414381965.0, "step": 69445 }, { "epoch": 0.7409343560965722, "grad_norm": 1.2123540224966594, "learning_rate": 1.2764869962063739e-05, "loss": 0.456, "num_tokens": 414402696.0, "step": 69450 }, { "epoch": 0.7409876991027706, "grad_norm": 0.8999778020575969, "learning_rate": 1.2761870690470893e-05, "loss": 0.5012, "num_tokens": 414431775.0, "step": 69455 }, { "epoch": 0.741041042108969, "grad_norm": 0.6729109939562754, "learning_rate": 1.2758871877498349e-05, "loss": 0.416, "num_tokens": 414459748.0, "step": 69460 }, { "epoch": 0.7410943851151676, "grad_norm": 0.7743752836875826, "learning_rate": 1.2755873523239448e-05, "loss": 0.4978, "num_tokens": 414488909.0, "step": 69465 }, { "epoch": 0.741147728121366, "grad_norm": 1.1458271329948733, "learning_rate": 1.2752875627787469e-05, "loss": 0.5694, "num_tokens": 414536036.0, "step": 69470 }, { "epoch": 0.7412010711275645, "grad_norm": 1.0004773295126652, "learning_rate": 1.2749878191235705e-05, "loss": 0.5232, "num_tokens": 414562922.0, "step": 69475 }, { "epoch": 0.7412544141337629, "grad_norm": 2.257527541344619, "learning_rate": 1.2746881213677437e-05, "loss": 0.4319, "num_tokens": 414581422.0, "step": 69480 }, { "epoch": 0.7413077571399613, "grad_norm": 0.836393718671809, "learning_rate": 1.2743884695205923e-05, "loss": 0.4816, "num_tokens": 414613516.0, "step": 69485 }, { "epoch": 0.7413611001461599, "grad_norm": 0.9619488789112641, "learning_rate": 1.2740888635914406e-05, "loss": 0.572, "num_tokens": 414645571.0, "step": 69490 }, { "epoch": 0.7414144431523583, "grad_norm": 0.873866467093941, "learning_rate": 1.2737893035896114e-05, "loss": 0.4685, "num_tokens": 414672627.0, "step": 69495 }, { "epoch": 0.7414677861585568, "grad_norm": 1.6856395184592043, "learning_rate": 1.273489789524428e-05, "loss": 0.4848, "num_tokens": 414698260.0, "step": 69500 }, { "epoch": 0.7415211291647552, "grad_norm": 0.8774121352128909, "learning_rate": 1.2731903214052093e-05, "loss": 0.4189, "num_tokens": 414724058.0, "step": 69505 }, { "epoch": 0.7415744721709536, "grad_norm": 0.8547438965970224, "learning_rate": 1.2728908992412735e-05, "loss": 0.5858, "num_tokens": 414764796.0, "step": 69510 }, { "epoch": 0.7416278151771521, "grad_norm": 2.2856650580989233, "learning_rate": 1.27259152304194e-05, "loss": 0.5538, "num_tokens": 414795316.0, "step": 69515 }, { "epoch": 0.7416811581833506, "grad_norm": 0.9781118452061228, "learning_rate": 1.2722921928165224e-05, "loss": 0.4733, "num_tokens": 414818874.0, "step": 69520 }, { "epoch": 0.7417345011895491, "grad_norm": 0.7387453216457531, "learning_rate": 1.2719929085743366e-05, "loss": 0.492, "num_tokens": 414855914.0, "step": 69525 }, { "epoch": 0.7417878441957475, "grad_norm": 0.9670711594520254, "learning_rate": 1.2716936703246962e-05, "loss": 0.4221, "num_tokens": 414888759.0, "step": 69530 }, { "epoch": 0.7418411872019459, "grad_norm": 1.520114383828145, "learning_rate": 1.2713944780769117e-05, "loss": 0.4274, "num_tokens": 414903038.0, "step": 69535 }, { "epoch": 0.7418945302081444, "grad_norm": 0.7890902108788005, "learning_rate": 1.2710953318402946e-05, "loss": 0.4192, "num_tokens": 414934113.0, "step": 69540 }, { "epoch": 0.7419478732143429, "grad_norm": 2.2200969510152198, "learning_rate": 1.2707962316241533e-05, "loss": 0.5297, "num_tokens": 414951219.0, "step": 69545 }, { "epoch": 0.7420012162205413, "grad_norm": 0.7301808769470038, "learning_rate": 1.2704971774377939e-05, "loss": 0.4005, "num_tokens": 414979885.0, "step": 69550 }, { "epoch": 0.7420545592267398, "grad_norm": 0.6443614838874278, "learning_rate": 1.2701981692905229e-05, "loss": 0.4066, "num_tokens": 414999843.0, "step": 69555 }, { "epoch": 0.7421079022329382, "grad_norm": 0.8692498032452997, "learning_rate": 1.2698992071916466e-05, "loss": 0.5088, "num_tokens": 415037532.0, "step": 69560 }, { "epoch": 0.7421612452391367, "grad_norm": 0.6777524120582907, "learning_rate": 1.2696002911504659e-05, "loss": 0.3856, "num_tokens": 415064213.0, "step": 69565 }, { "epoch": 0.7422145882453351, "grad_norm": 0.8955757678470997, "learning_rate": 1.2693014211762833e-05, "loss": 0.4094, "num_tokens": 415086662.0, "step": 69570 }, { "epoch": 0.7422679312515336, "grad_norm": 0.833813586132536, "learning_rate": 1.2690025972783998e-05, "loss": 0.3289, "num_tokens": 415110911.0, "step": 69575 }, { "epoch": 0.7423212742577321, "grad_norm": 0.6576179489533629, "learning_rate": 1.2687038194661132e-05, "loss": 0.5189, "num_tokens": 415163051.0, "step": 69580 }, { "epoch": 0.7423746172639305, "grad_norm": 1.0290918007023244, "learning_rate": 1.2684050877487208e-05, "loss": 0.3979, "num_tokens": 415180364.0, "step": 69585 }, { "epoch": 0.742427960270129, "grad_norm": 1.1509084929611595, "learning_rate": 1.268106402135519e-05, "loss": 0.4477, "num_tokens": 415212567.0, "step": 69590 }, { "epoch": 0.7424813032763274, "grad_norm": 1.3561359569142264, "learning_rate": 1.2678077626358015e-05, "loss": 0.4379, "num_tokens": 415240164.0, "step": 69595 }, { "epoch": 0.7425346462825259, "grad_norm": 1.2909130459281983, "learning_rate": 1.267509169258862e-05, "loss": 0.4817, "num_tokens": 415276073.0, "step": 69600 }, { "epoch": 0.7425879892887244, "grad_norm": 2.0744166031781455, "learning_rate": 1.267210622013993e-05, "loss": 0.4645, "num_tokens": 415292233.0, "step": 69605 }, { "epoch": 0.7426413322949228, "grad_norm": 1.064007247436262, "learning_rate": 1.2669121209104826e-05, "loss": 0.5318, "num_tokens": 415320604.0, "step": 69610 }, { "epoch": 0.7426946753011213, "grad_norm": 0.8609385267542898, "learning_rate": 1.2666136659576213e-05, "loss": 0.3913, "num_tokens": 415339054.0, "step": 69615 }, { "epoch": 0.7427480183073197, "grad_norm": 0.8841456726727714, "learning_rate": 1.2663152571646957e-05, "loss": 0.6779, "num_tokens": 415392994.0, "step": 69620 }, { "epoch": 0.7428013613135181, "grad_norm": 0.9788048639673677, "learning_rate": 1.2660168945409917e-05, "loss": 0.4659, "num_tokens": 415415512.0, "step": 69625 }, { "epoch": 0.7428547043197167, "grad_norm": 0.8730531570516621, "learning_rate": 1.265718578095793e-05, "loss": 0.495, "num_tokens": 415448531.0, "step": 69630 }, { "epoch": 0.7429080473259151, "grad_norm": 0.797566557508317, "learning_rate": 1.2654203078383848e-05, "loss": 0.4255, "num_tokens": 415485870.0, "step": 69635 }, { "epoch": 0.7429613903321135, "grad_norm": 1.4723901707778022, "learning_rate": 1.2651220837780459e-05, "loss": 0.528, "num_tokens": 415520343.0, "step": 69640 }, { "epoch": 0.743014733338312, "grad_norm": 0.7835654179362352, "learning_rate": 1.2648239059240582e-05, "loss": 0.616, "num_tokens": 415566697.0, "step": 69645 }, { "epoch": 0.7430680763445104, "grad_norm": 1.1969325677113156, "learning_rate": 1.2645257742856997e-05, "loss": 0.5788, "num_tokens": 415607990.0, "step": 69650 }, { "epoch": 0.743121419350709, "grad_norm": 0.5707927234571886, "learning_rate": 1.2642276888722488e-05, "loss": 0.4813, "num_tokens": 415642840.0, "step": 69655 }, { "epoch": 0.7431747623569074, "grad_norm": 0.8351683785370144, "learning_rate": 1.263929649692979e-05, "loss": 0.6332, "num_tokens": 415695575.0, "step": 69660 }, { "epoch": 0.7432281053631058, "grad_norm": 1.482839001443644, "learning_rate": 1.263631656757167e-05, "loss": 0.5019, "num_tokens": 415742160.0, "step": 69665 }, { "epoch": 0.7432814483693043, "grad_norm": 0.688539487989116, "learning_rate": 1.2633337100740838e-05, "loss": 0.4777, "num_tokens": 415771197.0, "step": 69670 }, { "epoch": 0.7433347913755027, "grad_norm": 0.8962041584553052, "learning_rate": 1.2630358096530023e-05, "loss": 0.3983, "num_tokens": 415803034.0, "step": 69675 }, { "epoch": 0.7433881343817013, "grad_norm": 1.2129046600151154, "learning_rate": 1.2627379555031926e-05, "loss": 0.5917, "num_tokens": 415852101.0, "step": 69680 }, { "epoch": 0.7434414773878997, "grad_norm": 0.8004271475452653, "learning_rate": 1.2624401476339229e-05, "loss": 0.581, "num_tokens": 415886008.0, "step": 69685 }, { "epoch": 0.7434948203940981, "grad_norm": 2.8660276735416144, "learning_rate": 1.2621423860544595e-05, "loss": 0.6063, "num_tokens": 415912465.0, "step": 69690 }, { "epoch": 0.7435481634002966, "grad_norm": 0.7071791512695852, "learning_rate": 1.2618446707740695e-05, "loss": 0.5698, "num_tokens": 415942063.0, "step": 69695 }, { "epoch": 0.743601506406495, "grad_norm": 0.6597948681313983, "learning_rate": 1.261547001802016e-05, "loss": 0.4866, "num_tokens": 415980748.0, "step": 69700 }, { "epoch": 0.7436548494126936, "grad_norm": 1.781975377092883, "learning_rate": 1.2612493791475627e-05, "loss": 0.4154, "num_tokens": 416007680.0, "step": 69705 }, { "epoch": 0.743708192418892, "grad_norm": 0.7938175886077866, "learning_rate": 1.2609518028199707e-05, "loss": 0.4603, "num_tokens": 416040859.0, "step": 69710 }, { "epoch": 0.7437615354250904, "grad_norm": 0.9648326614483067, "learning_rate": 1.2606542728285002e-05, "loss": 0.4553, "num_tokens": 416077940.0, "step": 69715 }, { "epoch": 0.7438148784312889, "grad_norm": 1.2877974783403563, "learning_rate": 1.2603567891824097e-05, "loss": 0.5138, "num_tokens": 416123547.0, "step": 69720 }, { "epoch": 0.7438682214374873, "grad_norm": 0.6511125131808331, "learning_rate": 1.260059351890956e-05, "loss": 0.3817, "num_tokens": 416146382.0, "step": 69725 }, { "epoch": 0.7439215644436857, "grad_norm": 0.7861561858198319, "learning_rate": 1.2597619609633942e-05, "loss": 0.4081, "num_tokens": 416161145.0, "step": 69730 }, { "epoch": 0.7439749074498843, "grad_norm": 0.9265327999757875, "learning_rate": 1.2594646164089793e-05, "loss": 0.4451, "num_tokens": 416191500.0, "step": 69735 }, { "epoch": 0.7440282504560827, "grad_norm": 1.150003314123215, "learning_rate": 1.2591673182369646e-05, "loss": 0.5574, "num_tokens": 416225827.0, "step": 69740 }, { "epoch": 0.7440815934622812, "grad_norm": 0.8571549700169058, "learning_rate": 1.2588700664566e-05, "loss": 0.411, "num_tokens": 416262605.0, "step": 69745 }, { "epoch": 0.7441349364684796, "grad_norm": 1.308610975777958, "learning_rate": 1.2585728610771357e-05, "loss": 0.4221, "num_tokens": 416292634.0, "step": 69750 }, { "epoch": 0.744188279474678, "grad_norm": 0.698001790614998, "learning_rate": 1.2582757021078218e-05, "loss": 0.5606, "num_tokens": 416335854.0, "step": 69755 }, { "epoch": 0.7442416224808766, "grad_norm": 0.5390185551176456, "learning_rate": 1.2579785895579038e-05, "loss": 0.4491, "num_tokens": 416372039.0, "step": 69760 }, { "epoch": 0.744294965487075, "grad_norm": 1.1798226451643845, "learning_rate": 1.2576815234366263e-05, "loss": 0.4352, "num_tokens": 416390376.0, "step": 69765 }, { "epoch": 0.7443483084932735, "grad_norm": 0.6700681670289856, "learning_rate": 1.2573845037532356e-05, "loss": 0.5581, "num_tokens": 416432990.0, "step": 69770 }, { "epoch": 0.7444016514994719, "grad_norm": 1.031577274675182, "learning_rate": 1.2570875305169725e-05, "loss": 0.4905, "num_tokens": 416467758.0, "step": 69775 }, { "epoch": 0.7444549945056703, "grad_norm": 1.1142966491592687, "learning_rate": 1.2567906037370785e-05, "loss": 0.4294, "num_tokens": 416495669.0, "step": 69780 }, { "epoch": 0.7445083375118688, "grad_norm": 1.325418242272922, "learning_rate": 1.2564937234227948e-05, "loss": 0.5632, "num_tokens": 416516244.0, "step": 69785 }, { "epoch": 0.7445616805180673, "grad_norm": 3.4506860144188414, "learning_rate": 1.2561968895833578e-05, "loss": 0.5517, "num_tokens": 416546852.0, "step": 69790 }, { "epoch": 0.7446150235242658, "grad_norm": 1.0617885024718856, "learning_rate": 1.2559001022280062e-05, "loss": 0.4164, "num_tokens": 416585340.0, "step": 69795 }, { "epoch": 0.7446683665304642, "grad_norm": 1.0065209782700275, "learning_rate": 1.2556033613659743e-05, "loss": 0.5012, "num_tokens": 416619244.0, "step": 69800 }, { "epoch": 0.7447217095366626, "grad_norm": 0.5920828219717725, "learning_rate": 1.2553066670064956e-05, "loss": 0.512, "num_tokens": 416657476.0, "step": 69805 }, { "epoch": 0.7447750525428611, "grad_norm": 1.017166625423483, "learning_rate": 1.2550100191588033e-05, "loss": 0.4566, "num_tokens": 416685218.0, "step": 69810 }, { "epoch": 0.7448283955490596, "grad_norm": 1.778083421041355, "learning_rate": 1.2547134178321284e-05, "loss": 0.5004, "num_tokens": 416710226.0, "step": 69815 }, { "epoch": 0.744881738555258, "grad_norm": 0.7386763384836975, "learning_rate": 1.2544168630357007e-05, "loss": 0.5283, "num_tokens": 416746263.0, "step": 69820 }, { "epoch": 0.7449350815614565, "grad_norm": 1.4334676473526728, "learning_rate": 1.2541203547787479e-05, "loss": 0.5734, "num_tokens": 416774400.0, "step": 69825 }, { "epoch": 0.7449884245676549, "grad_norm": 1.0922276598049965, "learning_rate": 1.2538238930704976e-05, "loss": 0.5107, "num_tokens": 416797924.0, "step": 69830 }, { "epoch": 0.7450417675738534, "grad_norm": 0.7771415647300383, "learning_rate": 1.253527477920175e-05, "loss": 0.4615, "num_tokens": 416822521.0, "step": 69835 }, { "epoch": 0.7450951105800518, "grad_norm": 0.8516335174893094, "learning_rate": 1.253231109337002e-05, "loss": 0.5334, "num_tokens": 416854522.0, "step": 69840 }, { "epoch": 0.7451484535862503, "grad_norm": 0.6175342100455414, "learning_rate": 1.2529347873302038e-05, "loss": 0.4573, "num_tokens": 416888434.0, "step": 69845 }, { "epoch": 0.7452017965924488, "grad_norm": 1.3214513960254877, "learning_rate": 1.252638511908999e-05, "loss": 0.4417, "num_tokens": 416917533.0, "step": 69850 }, { "epoch": 0.7452551395986472, "grad_norm": 0.757612788514014, "learning_rate": 1.2523422830826076e-05, "loss": 0.4962, "num_tokens": 416937683.0, "step": 69855 }, { "epoch": 0.7453084826048457, "grad_norm": 0.5740454580960743, "learning_rate": 1.2520461008602497e-05, "loss": 0.4636, "num_tokens": 416968098.0, "step": 69860 }, { "epoch": 0.7453618256110441, "grad_norm": 1.6995178331827658, "learning_rate": 1.251749965251139e-05, "loss": 0.5124, "num_tokens": 417006703.0, "step": 69865 }, { "epoch": 0.7454151686172426, "grad_norm": 0.9504256674747555, "learning_rate": 1.2514538762644926e-05, "loss": 0.5939, "num_tokens": 417026680.0, "step": 69870 }, { "epoch": 0.7454685116234411, "grad_norm": 0.7851614893474808, "learning_rate": 1.2511578339095231e-05, "loss": 0.3801, "num_tokens": 417048228.0, "step": 69875 }, { "epoch": 0.7455218546296395, "grad_norm": 0.723550587350241, "learning_rate": 1.2508618381954432e-05, "loss": 0.578, "num_tokens": 417067045.0, "step": 69880 }, { "epoch": 0.745575197635838, "grad_norm": 0.8362189159882042, "learning_rate": 1.2505658891314632e-05, "loss": 0.4573, "num_tokens": 417096750.0, "step": 69885 }, { "epoch": 0.7456285406420364, "grad_norm": 1.3730380578934118, "learning_rate": 1.2502699867267936e-05, "loss": 0.5475, "num_tokens": 417111776.0, "step": 69890 }, { "epoch": 0.7456818836482348, "grad_norm": 1.2673255200350706, "learning_rate": 1.2499741309906403e-05, "loss": 0.3801, "num_tokens": 417134565.0, "step": 69895 }, { "epoch": 0.7457352266544334, "grad_norm": 0.7058086331216352, "learning_rate": 1.2496783219322115e-05, "loss": 0.4099, "num_tokens": 417164760.0, "step": 69900 }, { "epoch": 0.7457885696606318, "grad_norm": 0.8274555017799156, "learning_rate": 1.249382559560712e-05, "loss": 0.444, "num_tokens": 417192935.0, "step": 69905 }, { "epoch": 0.7458419126668302, "grad_norm": 1.848530231918647, "learning_rate": 1.2490868438853449e-05, "loss": 0.5165, "num_tokens": 417222204.0, "step": 69910 }, { "epoch": 0.7458952556730287, "grad_norm": 0.7985039648311046, "learning_rate": 1.2487911749153116e-05, "loss": 0.4524, "num_tokens": 417253111.0, "step": 69915 }, { "epoch": 0.7459485986792271, "grad_norm": 0.8023844996111468, "learning_rate": 1.248495552659814e-05, "loss": 0.4755, "num_tokens": 417291607.0, "step": 69920 }, { "epoch": 0.7460019416854257, "grad_norm": 0.5694831318587436, "learning_rate": 1.2481999771280501e-05, "loss": 0.3993, "num_tokens": 417336175.0, "step": 69925 }, { "epoch": 0.7460552846916241, "grad_norm": 0.7526056523672278, "learning_rate": 1.2479044483292179e-05, "loss": 0.5292, "num_tokens": 417369375.0, "step": 69930 }, { "epoch": 0.7461086276978225, "grad_norm": 0.6436942804942307, "learning_rate": 1.2476089662725146e-05, "loss": 0.4664, "num_tokens": 417390708.0, "step": 69935 }, { "epoch": 0.746161970704021, "grad_norm": 0.6839347124262737, "learning_rate": 1.2473135309671337e-05, "loss": 0.5234, "num_tokens": 417439161.0, "step": 69940 }, { "epoch": 0.7462153137102194, "grad_norm": 0.6956086902439119, "learning_rate": 1.2470181424222697e-05, "loss": 0.5823, "num_tokens": 417469701.0, "step": 69945 }, { "epoch": 0.746268656716418, "grad_norm": 2.034054642118379, "learning_rate": 1.2467228006471138e-05, "loss": 0.5481, "num_tokens": 417488937.0, "step": 69950 }, { "epoch": 0.7463219997226164, "grad_norm": 2.260157682931886, "learning_rate": 1.2464275056508563e-05, "loss": 0.5098, "num_tokens": 417519557.0, "step": 69955 }, { "epoch": 0.7463753427288148, "grad_norm": 0.9424294718719547, "learning_rate": 1.246132257442686e-05, "loss": 0.3827, "num_tokens": 417533156.0, "step": 69960 }, { "epoch": 0.7464286857350133, "grad_norm": 1.2223926428941472, "learning_rate": 1.2458370560317914e-05, "loss": 0.5292, "num_tokens": 417567742.0, "step": 69965 }, { "epoch": 0.7464820287412117, "grad_norm": 0.6397591777684387, "learning_rate": 1.2455419014273575e-05, "loss": 0.4291, "num_tokens": 417600118.0, "step": 69970 }, { "epoch": 0.7465353717474102, "grad_norm": 1.0507068000991262, "learning_rate": 1.2452467936385702e-05, "loss": 0.4298, "num_tokens": 417623761.0, "step": 69975 }, { "epoch": 0.7465887147536087, "grad_norm": 0.49323083492520964, "learning_rate": 1.2449517326746115e-05, "loss": 0.3591, "num_tokens": 417654743.0, "step": 69980 }, { "epoch": 0.7466420577598071, "grad_norm": 0.8276616617715022, "learning_rate": 1.2446567185446629e-05, "loss": 0.5268, "num_tokens": 417673291.0, "step": 69985 }, { "epoch": 0.7466954007660056, "grad_norm": 1.1892514219558534, "learning_rate": 1.2443617512579054e-05, "loss": 0.4529, "num_tokens": 417703038.0, "step": 69990 }, { "epoch": 0.746748743772204, "grad_norm": 0.7823570256354213, "learning_rate": 1.244066830823518e-05, "loss": 0.4519, "num_tokens": 417742066.0, "step": 69995 }, { "epoch": 0.7468020867784024, "grad_norm": 0.8666029757198058, "learning_rate": 1.2437719572506767e-05, "loss": 0.569, "num_tokens": 417786283.0, "step": 70000 }, { "epoch": 0.746855429784601, "grad_norm": 0.8786914683961179, "learning_rate": 1.2434771305485582e-05, "loss": 0.4339, "num_tokens": 417815921.0, "step": 70005 }, { "epoch": 0.7469087727907994, "grad_norm": 0.9328471454708871, "learning_rate": 1.2431823507263378e-05, "loss": 0.4479, "num_tokens": 417841007.0, "step": 70010 }, { "epoch": 0.7469621157969979, "grad_norm": 1.075320751216069, "learning_rate": 1.2428876177931878e-05, "loss": 0.4385, "num_tokens": 417867962.0, "step": 70015 }, { "epoch": 0.7470154588031963, "grad_norm": 1.7775471525714297, "learning_rate": 1.2425929317582783e-05, "loss": 0.4336, "num_tokens": 417903558.0, "step": 70020 }, { "epoch": 0.7470688018093947, "grad_norm": 0.5084239753266409, "learning_rate": 1.2422982926307811e-05, "loss": 0.4586, "num_tokens": 417947010.0, "step": 70025 }, { "epoch": 0.7471221448155932, "grad_norm": 1.1786639611455771, "learning_rate": 1.2420037004198638e-05, "loss": 0.5557, "num_tokens": 417983635.0, "step": 70030 }, { "epoch": 0.7471754878217917, "grad_norm": 1.3984225761295817, "learning_rate": 1.2417091551346936e-05, "loss": 0.4861, "num_tokens": 418005723.0, "step": 70035 }, { "epoch": 0.7472288308279902, "grad_norm": 0.924584884820822, "learning_rate": 1.2414146567844372e-05, "loss": 0.5687, "num_tokens": 418040539.0, "step": 70040 }, { "epoch": 0.7472821738341886, "grad_norm": 0.5956308868235265, "learning_rate": 1.2411202053782572e-05, "loss": 0.4808, "num_tokens": 418082184.0, "step": 70045 }, { "epoch": 0.747335516840387, "grad_norm": 0.8425415666373333, "learning_rate": 1.2408258009253179e-05, "loss": 0.5547, "num_tokens": 418108489.0, "step": 70050 }, { "epoch": 0.7473888598465855, "grad_norm": 0.8460482862452121, "learning_rate": 1.2405314434347795e-05, "loss": 0.4117, "num_tokens": 418132610.0, "step": 70055 }, { "epoch": 0.747442202852784, "grad_norm": 0.7187409705374072, "learning_rate": 1.2402371329158014e-05, "loss": 0.439, "num_tokens": 418165168.0, "step": 70060 }, { "epoch": 0.7474955458589825, "grad_norm": 1.747342049324641, "learning_rate": 1.2399428693775427e-05, "loss": 0.4614, "num_tokens": 418189948.0, "step": 70065 }, { "epoch": 0.7475488888651809, "grad_norm": 0.7139657407003914, "learning_rate": 1.2396486528291607e-05, "loss": 0.5412, "num_tokens": 418224668.0, "step": 70070 }, { "epoch": 0.7476022318713793, "grad_norm": 1.1396832109875392, "learning_rate": 1.2393544832798097e-05, "loss": 0.5741, "num_tokens": 418246191.0, "step": 70075 }, { "epoch": 0.7476555748775778, "grad_norm": 0.6561894911568007, "learning_rate": 1.2390603607386441e-05, "loss": 0.4035, "num_tokens": 418265973.0, "step": 70080 }, { "epoch": 0.7477089178837762, "grad_norm": 0.6338208547969452, "learning_rate": 1.2387662852148175e-05, "loss": 0.5732, "num_tokens": 418312896.0, "step": 70085 }, { "epoch": 0.7477622608899747, "grad_norm": 0.8925007968278489, "learning_rate": 1.2384722567174797e-05, "loss": 0.3501, "num_tokens": 418348759.0, "step": 70090 }, { "epoch": 0.7478156038961732, "grad_norm": 0.9608405317834972, "learning_rate": 1.2381782752557799e-05, "loss": 0.3891, "num_tokens": 418363856.0, "step": 70095 }, { "epoch": 0.7478689469023716, "grad_norm": 0.6805503097506401, "learning_rate": 1.2378843408388669e-05, "loss": 0.4347, "num_tokens": 418391810.0, "step": 70100 }, { "epoch": 0.7479222899085701, "grad_norm": 0.9606897367225483, "learning_rate": 1.2375904534758876e-05, "loss": 0.432, "num_tokens": 418416999.0, "step": 70105 }, { "epoch": 0.7479756329147685, "grad_norm": 1.0307818826611652, "learning_rate": 1.2372966131759863e-05, "loss": 0.3791, "num_tokens": 418429371.0, "step": 70110 }, { "epoch": 0.748028975920967, "grad_norm": 1.7544746046606856, "learning_rate": 1.2370028199483073e-05, "loss": 0.4548, "num_tokens": 418462307.0, "step": 70115 }, { "epoch": 0.7480823189271655, "grad_norm": 1.378768509656046, "learning_rate": 1.2367090738019934e-05, "loss": 0.3732, "num_tokens": 418479137.0, "step": 70120 }, { "epoch": 0.7481356619333639, "grad_norm": 2.8448476615552645, "learning_rate": 1.2364153747461847e-05, "loss": 0.4592, "num_tokens": 418495125.0, "step": 70125 }, { "epoch": 0.7481890049395624, "grad_norm": 0.7020000235701916, "learning_rate": 1.2361217227900199e-05, "loss": 0.4625, "num_tokens": 418527676.0, "step": 70130 }, { "epoch": 0.7482423479457608, "grad_norm": 0.7789659957810325, "learning_rate": 1.235828117942638e-05, "loss": 0.4412, "num_tokens": 418561806.0, "step": 70135 }, { "epoch": 0.7482956909519592, "grad_norm": 0.9089851314804185, "learning_rate": 1.2355345602131744e-05, "loss": 0.4608, "num_tokens": 418585562.0, "step": 70140 }, { "epoch": 0.7483490339581578, "grad_norm": 0.8967993910302197, "learning_rate": 1.2352410496107644e-05, "loss": 0.3789, "num_tokens": 418619610.0, "step": 70145 }, { "epoch": 0.7484023769643562, "grad_norm": 0.717974044594542, "learning_rate": 1.2349475861445422e-05, "loss": 0.4843, "num_tokens": 418643759.0, "step": 70150 }, { "epoch": 0.7484557199705547, "grad_norm": 1.1074341636294356, "learning_rate": 1.2346541698236387e-05, "loss": 0.5682, "num_tokens": 418662886.0, "step": 70155 }, { "epoch": 0.7485090629767531, "grad_norm": 0.870397079471397, "learning_rate": 1.2343608006571853e-05, "loss": 0.4886, "num_tokens": 418688428.0, "step": 70160 }, { "epoch": 0.7485624059829515, "grad_norm": 1.1980841346047804, "learning_rate": 1.2340674786543105e-05, "loss": 0.4783, "num_tokens": 418714876.0, "step": 70165 }, { "epoch": 0.7486157489891501, "grad_norm": 0.9575868168061482, "learning_rate": 1.2337742038241414e-05, "loss": 0.403, "num_tokens": 418744975.0, "step": 70170 }, { "epoch": 0.7486690919953485, "grad_norm": 1.0332854805038387, "learning_rate": 1.2334809761758045e-05, "loss": 0.4637, "num_tokens": 418775100.0, "step": 70175 }, { "epoch": 0.7487224350015469, "grad_norm": 0.9249885454640073, "learning_rate": 1.2331877957184254e-05, "loss": 0.4628, "num_tokens": 418808001.0, "step": 70180 }, { "epoch": 0.7487757780077454, "grad_norm": 1.5445530280488466, "learning_rate": 1.2328946624611257e-05, "loss": 0.3969, "num_tokens": 418823924.0, "step": 70185 }, { "epoch": 0.7488291210139438, "grad_norm": 0.7775259764199909, "learning_rate": 1.232601576413028e-05, "loss": 0.4828, "num_tokens": 418871492.0, "step": 70190 }, { "epoch": 0.7488824640201424, "grad_norm": 1.2357806948861925, "learning_rate": 1.232308537583253e-05, "loss": 0.4018, "num_tokens": 418894658.0, "step": 70195 }, { "epoch": 0.7489358070263408, "grad_norm": 1.1988539950180168, "learning_rate": 1.232015545980919e-05, "loss": 0.4283, "num_tokens": 418912253.0, "step": 70200 }, { "epoch": 0.7489891500325392, "grad_norm": 0.6537231533316951, "learning_rate": 1.2317226016151425e-05, "loss": 0.4536, "num_tokens": 418951024.0, "step": 70205 }, { "epoch": 0.7490424930387377, "grad_norm": 0.6925753665554445, "learning_rate": 1.2314297044950404e-05, "loss": 0.3926, "num_tokens": 418970810.0, "step": 70210 }, { "epoch": 0.7490958360449361, "grad_norm": 1.0296569957104806, "learning_rate": 1.2311368546297263e-05, "loss": 0.5246, "num_tokens": 418983895.0, "step": 70215 }, { "epoch": 0.7491491790511347, "grad_norm": 0.7772263488754496, "learning_rate": 1.2308440520283132e-05, "loss": 0.5115, "num_tokens": 419004853.0, "step": 70220 }, { "epoch": 0.7492025220573331, "grad_norm": 1.2921264104374808, "learning_rate": 1.2305512966999135e-05, "loss": 0.4557, "num_tokens": 419027007.0, "step": 70225 }, { "epoch": 0.7492558650635315, "grad_norm": 0.7963962209067367, "learning_rate": 1.2302585886536359e-05, "loss": 0.5072, "num_tokens": 419063325.0, "step": 70230 }, { "epoch": 0.74930920806973, "grad_norm": 0.764528206119958, "learning_rate": 1.22996592789859e-05, "loss": 0.4936, "num_tokens": 419104464.0, "step": 70235 }, { "epoch": 0.7493625510759284, "grad_norm": 0.9974065932480373, "learning_rate": 1.2296733144438822e-05, "loss": 0.5036, "num_tokens": 419126968.0, "step": 70240 }, { "epoch": 0.7494158940821269, "grad_norm": 0.7247016913773286, "learning_rate": 1.2293807482986174e-05, "loss": 0.5661, "num_tokens": 419149326.0, "step": 70245 }, { "epoch": 0.7494692370883254, "grad_norm": 1.0336210423539318, "learning_rate": 1.2290882294719e-05, "loss": 0.4946, "num_tokens": 419174642.0, "step": 70250 }, { "epoch": 0.7495225800945238, "grad_norm": 0.9683617978795687, "learning_rate": 1.2287957579728337e-05, "loss": 0.5247, "num_tokens": 419201428.0, "step": 70255 }, { "epoch": 0.7495759231007223, "grad_norm": 1.097443882810692, "learning_rate": 1.2285033338105182e-05, "loss": 0.3895, "num_tokens": 419226327.0, "step": 70260 }, { "epoch": 0.7496292661069207, "grad_norm": 0.9526901724867266, "learning_rate": 1.228210956994054e-05, "loss": 0.4564, "num_tokens": 419255142.0, "step": 70265 }, { "epoch": 0.7496826091131191, "grad_norm": 0.85702940843664, "learning_rate": 1.2279186275325396e-05, "loss": 0.4291, "num_tokens": 419288921.0, "step": 70270 }, { "epoch": 0.7497359521193177, "grad_norm": 0.7777180630227366, "learning_rate": 1.2276263454350699e-05, "loss": 0.4961, "num_tokens": 419313740.0, "step": 70275 }, { "epoch": 0.7497892951255161, "grad_norm": 0.5593092338681835, "learning_rate": 1.2273341107107413e-05, "loss": 0.5632, "num_tokens": 419360389.0, "step": 70280 }, { "epoch": 0.7498426381317146, "grad_norm": 1.12848338674048, "learning_rate": 1.2270419233686486e-05, "loss": 0.6626, "num_tokens": 419405273.0, "step": 70285 }, { "epoch": 0.749895981137913, "grad_norm": 0.9007708855716889, "learning_rate": 1.2267497834178818e-05, "loss": 0.4612, "num_tokens": 419426908.0, "step": 70290 }, { "epoch": 0.7499493241441114, "grad_norm": 0.8154214393272736, "learning_rate": 1.226457690867533e-05, "loss": 0.5107, "num_tokens": 419448569.0, "step": 70295 }, { "epoch": 0.7500026671503099, "grad_norm": 1.2354360102685686, "learning_rate": 1.2261656457266924e-05, "loss": 0.3966, "num_tokens": 419488511.0, "step": 70300 }, { "epoch": 0.7500560101565084, "grad_norm": 1.3313874636232814, "learning_rate": 1.2258736480044468e-05, "loss": 0.5292, "num_tokens": 419511283.0, "step": 70305 }, { "epoch": 0.7501093531627069, "grad_norm": 0.5666698776121128, "learning_rate": 1.2255816977098818e-05, "loss": 0.392, "num_tokens": 419540846.0, "step": 70310 }, { "epoch": 0.7501626961689053, "grad_norm": 1.0874282283835062, "learning_rate": 1.225289794852084e-05, "loss": 0.4807, "num_tokens": 419561614.0, "step": 70315 }, { "epoch": 0.7502160391751037, "grad_norm": 1.862018810263557, "learning_rate": 1.2249979394401351e-05, "loss": 0.5409, "num_tokens": 419579047.0, "step": 70320 }, { "epoch": 0.7502693821813022, "grad_norm": 0.9411902760484951, "learning_rate": 1.2247061314831177e-05, "loss": 0.4072, "num_tokens": 419609749.0, "step": 70325 }, { "epoch": 0.7503227251875006, "grad_norm": 0.8913053518960176, "learning_rate": 1.2244143709901135e-05, "loss": 0.5694, "num_tokens": 419652020.0, "step": 70330 }, { "epoch": 0.7503760681936992, "grad_norm": 0.6101870330944851, "learning_rate": 1.2241226579701995e-05, "loss": 0.5431, "num_tokens": 419678035.0, "step": 70335 }, { "epoch": 0.7504294111998976, "grad_norm": 0.5879989339231354, "learning_rate": 1.2238309924324549e-05, "loss": 0.5834, "num_tokens": 419721056.0, "step": 70340 }, { "epoch": 0.750482754206096, "grad_norm": 0.6757850768847697, "learning_rate": 1.223539374385955e-05, "loss": 0.4624, "num_tokens": 419754615.0, "step": 70345 }, { "epoch": 0.7505360972122945, "grad_norm": 1.2795975046588375, "learning_rate": 1.2232478038397737e-05, "loss": 0.4727, "num_tokens": 419770284.0, "step": 70350 }, { "epoch": 0.7505894402184929, "grad_norm": 0.7625215348013953, "learning_rate": 1.2229562808029846e-05, "loss": 0.4707, "num_tokens": 419806289.0, "step": 70355 }, { "epoch": 0.7506427832246914, "grad_norm": 5.989195329138194, "learning_rate": 1.2226648052846601e-05, "loss": 0.5736, "num_tokens": 419822814.0, "step": 70360 }, { "epoch": 0.7506961262308899, "grad_norm": 0.9774159116816907, "learning_rate": 1.222373377293869e-05, "loss": 0.5404, "num_tokens": 419858163.0, "step": 70365 }, { "epoch": 0.7507494692370883, "grad_norm": 1.5555196199228822, "learning_rate": 1.2220819968396802e-05, "loss": 0.4778, "num_tokens": 419877564.0, "step": 70370 }, { "epoch": 0.7508028122432868, "grad_norm": 0.7878252882904911, "learning_rate": 1.2217906639311622e-05, "loss": 0.4089, "num_tokens": 419912133.0, "step": 70375 }, { "epoch": 0.7508561552494852, "grad_norm": 0.6868826262922719, "learning_rate": 1.22149937857738e-05, "loss": 0.4063, "num_tokens": 419939670.0, "step": 70380 }, { "epoch": 0.7509094982556836, "grad_norm": 1.458884531215922, "learning_rate": 1.2212081407873965e-05, "loss": 0.4567, "num_tokens": 419970404.0, "step": 70385 }, { "epoch": 0.7509628412618822, "grad_norm": 0.8032746063917796, "learning_rate": 1.2209169505702761e-05, "loss": 0.5456, "num_tokens": 419999705.0, "step": 70390 }, { "epoch": 0.7510161842680806, "grad_norm": 0.7655736367451723, "learning_rate": 1.2206258079350787e-05, "loss": 0.5358, "num_tokens": 420038212.0, "step": 70395 }, { "epoch": 0.7510695272742791, "grad_norm": 1.6098966332154934, "learning_rate": 1.220334712890865e-05, "loss": 0.527, "num_tokens": 420051975.0, "step": 70400 }, { "epoch": 0.7511228702804775, "grad_norm": 0.9873427870720434, "learning_rate": 1.2200436654466935e-05, "loss": 0.4745, "num_tokens": 420095454.0, "step": 70405 }, { "epoch": 0.7511762132866759, "grad_norm": 0.6877365476957773, "learning_rate": 1.2197526656116196e-05, "loss": 0.4241, "num_tokens": 420123239.0, "step": 70410 }, { "epoch": 0.7512295562928745, "grad_norm": 1.020972983749717, "learning_rate": 1.2194617133947007e-05, "loss": 0.3854, "num_tokens": 420156054.0, "step": 70415 }, { "epoch": 0.7512828992990729, "grad_norm": 0.8324252161141352, "learning_rate": 1.219170808804989e-05, "loss": 0.3755, "num_tokens": 420185213.0, "step": 70420 }, { "epoch": 0.7513362423052714, "grad_norm": 1.0636112733653527, "learning_rate": 1.2188799518515369e-05, "loss": 0.5685, "num_tokens": 420207711.0, "step": 70425 }, { "epoch": 0.7513895853114698, "grad_norm": 1.0087718171746984, "learning_rate": 1.2185891425433955e-05, "loss": 0.5481, "num_tokens": 420233934.0, "step": 70430 }, { "epoch": 0.7514429283176682, "grad_norm": 1.3868305538990526, "learning_rate": 1.2182983808896151e-05, "loss": 0.423, "num_tokens": 420251280.0, "step": 70435 }, { "epoch": 0.7514962713238668, "grad_norm": 1.2939378681453206, "learning_rate": 1.2180076668992424e-05, "loss": 0.4096, "num_tokens": 420265246.0, "step": 70440 }, { "epoch": 0.7515496143300652, "grad_norm": 2.323399171947211, "learning_rate": 1.2177170005813242e-05, "loss": 0.4975, "num_tokens": 420286687.0, "step": 70445 }, { "epoch": 0.7516029573362636, "grad_norm": 0.6871015823981774, "learning_rate": 1.217426381944906e-05, "loss": 0.4981, "num_tokens": 420310142.0, "step": 70450 }, { "epoch": 0.7516563003424621, "grad_norm": 1.0126120058589487, "learning_rate": 1.2171358109990312e-05, "loss": 0.4861, "num_tokens": 420335996.0, "step": 70455 }, { "epoch": 0.7517096433486605, "grad_norm": 1.1522654781681814, "learning_rate": 1.2168452877527405e-05, "loss": 0.4158, "num_tokens": 420364258.0, "step": 70460 }, { "epoch": 0.751762986354859, "grad_norm": 0.8579757654723682, "learning_rate": 1.2165548122150757e-05, "loss": 0.5538, "num_tokens": 420396435.0, "step": 70465 }, { "epoch": 0.7518163293610575, "grad_norm": 1.0143663458039667, "learning_rate": 1.2162643843950749e-05, "loss": 0.4158, "num_tokens": 420411326.0, "step": 70470 }, { "epoch": 0.7518696723672559, "grad_norm": 1.1011754152414128, "learning_rate": 1.2159740043017763e-05, "loss": 0.4554, "num_tokens": 420441946.0, "step": 70475 }, { "epoch": 0.7519230153734544, "grad_norm": 0.8550590605630892, "learning_rate": 1.215683671944216e-05, "loss": 0.5816, "num_tokens": 420484727.0, "step": 70480 }, { "epoch": 0.7519763583796528, "grad_norm": 0.9757502290185683, "learning_rate": 1.2153933873314276e-05, "loss": 0.4138, "num_tokens": 420501928.0, "step": 70485 }, { "epoch": 0.7520297013858513, "grad_norm": 0.9089942963237244, "learning_rate": 1.2151031504724459e-05, "loss": 0.5477, "num_tokens": 420532805.0, "step": 70490 }, { "epoch": 0.7520830443920498, "grad_norm": 0.6600074497392632, "learning_rate": 1.214812961376301e-05, "loss": 0.5146, "num_tokens": 420568904.0, "step": 70495 }, { "epoch": 0.7521363873982482, "grad_norm": 0.7483005485125531, "learning_rate": 1.2145228200520227e-05, "loss": 0.4876, "num_tokens": 420597817.0, "step": 70500 }, { "epoch": 0.7521897304044467, "grad_norm": 1.034818118722201, "learning_rate": 1.2142327265086404e-05, "loss": 0.3965, "num_tokens": 420615677.0, "step": 70505 }, { "epoch": 0.7522430734106451, "grad_norm": 0.9440780930724378, "learning_rate": 1.2139426807551819e-05, "loss": 0.4, "num_tokens": 420644121.0, "step": 70510 }, { "epoch": 0.7522964164168436, "grad_norm": 0.9199492957583084, "learning_rate": 1.2136526828006713e-05, "loss": 0.3908, "num_tokens": 420690494.0, "step": 70515 }, { "epoch": 0.752349759423042, "grad_norm": 0.7961135044255432, "learning_rate": 1.2133627326541332e-05, "loss": 0.3397, "num_tokens": 420709911.0, "step": 70520 }, { "epoch": 0.7524031024292405, "grad_norm": 0.7565857689670402, "learning_rate": 1.2130728303245912e-05, "loss": 0.5508, "num_tokens": 420770649.0, "step": 70525 }, { "epoch": 0.752456445435439, "grad_norm": 0.8178603107550767, "learning_rate": 1.2127829758210662e-05, "loss": 0.3598, "num_tokens": 420796642.0, "step": 70530 }, { "epoch": 0.7525097884416374, "grad_norm": 0.689004470218739, "learning_rate": 1.2124931691525763e-05, "loss": 0.5907, "num_tokens": 420843068.0, "step": 70535 }, { "epoch": 0.7525631314478358, "grad_norm": 1.112285195588145, "learning_rate": 1.2122034103281419e-05, "loss": 0.4109, "num_tokens": 420865338.0, "step": 70540 }, { "epoch": 0.7526164744540343, "grad_norm": 0.611579787201688, "learning_rate": 1.2119136993567778e-05, "loss": 0.5378, "num_tokens": 420903898.0, "step": 70545 }, { "epoch": 0.7526698174602328, "grad_norm": 0.9251079337073689, "learning_rate": 1.2116240362475e-05, "loss": 0.455, "num_tokens": 420925336.0, "step": 70550 }, { "epoch": 0.7527231604664313, "grad_norm": 0.7533418091947333, "learning_rate": 1.2113344210093231e-05, "loss": 0.4684, "num_tokens": 420944023.0, "step": 70555 }, { "epoch": 0.7527765034726297, "grad_norm": 0.644106250069467, "learning_rate": 1.2110448536512576e-05, "loss": 0.51, "num_tokens": 420993188.0, "step": 70560 }, { "epoch": 0.7528298464788281, "grad_norm": 2.195069801342866, "learning_rate": 1.2107553341823162e-05, "loss": 0.4732, "num_tokens": 421014283.0, "step": 70565 }, { "epoch": 0.7528831894850266, "grad_norm": 0.8691700823184834, "learning_rate": 1.210465862611507e-05, "loss": 0.5037, "num_tokens": 421061393.0, "step": 70570 }, { "epoch": 0.752936532491225, "grad_norm": 0.9632405723987476, "learning_rate": 1.210176438947837e-05, "loss": 0.5067, "num_tokens": 421089505.0, "step": 70575 }, { "epoch": 0.7529898754974236, "grad_norm": 0.8173903078170682, "learning_rate": 1.2098870632003132e-05, "loss": 0.4909, "num_tokens": 421112052.0, "step": 70580 }, { "epoch": 0.753043218503622, "grad_norm": 1.1102522102810972, "learning_rate": 1.2095977353779414e-05, "loss": 0.357, "num_tokens": 421133758.0, "step": 70585 }, { "epoch": 0.7530965615098204, "grad_norm": 1.0855463937318544, "learning_rate": 1.2093084554897236e-05, "loss": 0.4146, "num_tokens": 421164850.0, "step": 70590 }, { "epoch": 0.7531499045160189, "grad_norm": 1.3752245049768101, "learning_rate": 1.2090192235446622e-05, "loss": 0.385, "num_tokens": 421178902.0, "step": 70595 }, { "epoch": 0.7532032475222173, "grad_norm": 1.1087717284233194, "learning_rate": 1.2087300395517575e-05, "loss": 0.3827, "num_tokens": 421206926.0, "step": 70600 }, { "epoch": 0.7532565905284159, "grad_norm": 1.0323041251475693, "learning_rate": 1.2084409035200076e-05, "loss": 0.5551, "num_tokens": 421250372.0, "step": 70605 }, { "epoch": 0.7533099335346143, "grad_norm": 1.0890259384212666, "learning_rate": 1.20815181545841e-05, "loss": 0.483, "num_tokens": 421272902.0, "step": 70610 }, { "epoch": 0.7533632765408127, "grad_norm": 0.7450491959954352, "learning_rate": 1.2078627753759616e-05, "loss": 0.4068, "num_tokens": 421304773.0, "step": 70615 }, { "epoch": 0.7534166195470112, "grad_norm": 0.6601835167691447, "learning_rate": 1.2075737832816554e-05, "loss": 0.3831, "num_tokens": 421328615.0, "step": 70620 }, { "epoch": 0.7534699625532096, "grad_norm": 0.821360801889032, "learning_rate": 1.2072848391844848e-05, "loss": 0.4372, "num_tokens": 421349373.0, "step": 70625 }, { "epoch": 0.753523305559408, "grad_norm": 0.840222691474192, "learning_rate": 1.2069959430934418e-05, "loss": 0.4244, "num_tokens": 421371290.0, "step": 70630 }, { "epoch": 0.7535766485656066, "grad_norm": 0.9487090985737047, "learning_rate": 1.2067070950175158e-05, "loss": 0.4794, "num_tokens": 421390025.0, "step": 70635 }, { "epoch": 0.753629991571805, "grad_norm": 0.6144641700603649, "learning_rate": 1.2064182949656943e-05, "loss": 0.4426, "num_tokens": 421424450.0, "step": 70640 }, { "epoch": 0.7536833345780035, "grad_norm": 0.7994616837201075, "learning_rate": 1.2061295429469654e-05, "loss": 0.4897, "num_tokens": 421443346.0, "step": 70645 }, { "epoch": 0.7537366775842019, "grad_norm": 1.097907363146221, "learning_rate": 1.2058408389703133e-05, "loss": 0.4677, "num_tokens": 421472247.0, "step": 70650 }, { "epoch": 0.7537900205904003, "grad_norm": 0.6437355822109273, "learning_rate": 1.2055521830447225e-05, "loss": 0.4622, "num_tokens": 421506481.0, "step": 70655 }, { "epoch": 0.7538433635965989, "grad_norm": 0.7375291310627781, "learning_rate": 1.2052635751791761e-05, "loss": 0.436, "num_tokens": 421544831.0, "step": 70660 }, { "epoch": 0.7538967066027973, "grad_norm": 0.8179210085473038, "learning_rate": 1.2049750153826534e-05, "loss": 0.3981, "num_tokens": 421585071.0, "step": 70665 }, { "epoch": 0.7539500496089958, "grad_norm": 0.8701930358270225, "learning_rate": 1.2046865036641355e-05, "loss": 0.5724, "num_tokens": 421605044.0, "step": 70670 }, { "epoch": 0.7540033926151942, "grad_norm": 0.9753400597743103, "learning_rate": 1.2043980400325996e-05, "loss": 0.6912, "num_tokens": 421647561.0, "step": 70675 }, { "epoch": 0.7540567356213926, "grad_norm": 2.0685713004302784, "learning_rate": 1.2041096244970209e-05, "loss": 0.3904, "num_tokens": 421662556.0, "step": 70680 }, { "epoch": 0.7541100786275912, "grad_norm": 0.872259198935629, "learning_rate": 1.2038212570663754e-05, "loss": 0.5977, "num_tokens": 421715268.0, "step": 70685 }, { "epoch": 0.7541634216337896, "grad_norm": 1.8546248708131878, "learning_rate": 1.2035329377496373e-05, "loss": 0.5118, "num_tokens": 421742776.0, "step": 70690 }, { "epoch": 0.7542167646399881, "grad_norm": 0.8256246355624586, "learning_rate": 1.2032446665557769e-05, "loss": 0.5929, "num_tokens": 421773693.0, "step": 70695 }, { "epoch": 0.7542701076461865, "grad_norm": 1.0319262294269544, "learning_rate": 1.2029564434937653e-05, "loss": 0.4089, "num_tokens": 421790462.0, "step": 70700 }, { "epoch": 0.7543234506523849, "grad_norm": 0.553634645121051, "learning_rate": 1.2026682685725723e-05, "loss": 0.4458, "num_tokens": 421830414.0, "step": 70705 }, { "epoch": 0.7543767936585835, "grad_norm": 0.6379162795342791, "learning_rate": 1.2023801418011643e-05, "loss": 0.3763, "num_tokens": 421852938.0, "step": 70710 }, { "epoch": 0.7544301366647819, "grad_norm": 2.366915384184738, "learning_rate": 1.2020920631885066e-05, "loss": 0.4645, "num_tokens": 421872201.0, "step": 70715 }, { "epoch": 0.7544834796709803, "grad_norm": 0.7094766644126067, "learning_rate": 1.2018040327435651e-05, "loss": 0.4063, "num_tokens": 421905923.0, "step": 70720 }, { "epoch": 0.7545368226771788, "grad_norm": 0.855091710894274, "learning_rate": 1.2015160504753015e-05, "loss": 0.5348, "num_tokens": 421930895.0, "step": 70725 }, { "epoch": 0.7545901656833772, "grad_norm": 1.027258171981359, "learning_rate": 1.2012281163926777e-05, "loss": 0.345, "num_tokens": 421949552.0, "step": 70730 }, { "epoch": 0.7546435086895757, "grad_norm": 0.8523845703359398, "learning_rate": 1.2009402305046544e-05, "loss": 0.4246, "num_tokens": 421966907.0, "step": 70735 }, { "epoch": 0.7546968516957742, "grad_norm": 0.7308262614748403, "learning_rate": 1.2006523928201886e-05, "loss": 0.5225, "num_tokens": 421992579.0, "step": 70740 }, { "epoch": 0.7547501947019726, "grad_norm": 3.088529785765214, "learning_rate": 1.2003646033482385e-05, "loss": 0.5279, "num_tokens": 422010100.0, "step": 70745 }, { "epoch": 0.7548035377081711, "grad_norm": 1.214660976154668, "learning_rate": 1.2000768620977588e-05, "loss": 0.4511, "num_tokens": 422021416.0, "step": 70750 }, { "epoch": 0.7548568807143695, "grad_norm": 0.9807224426324552, "learning_rate": 1.1997891690777027e-05, "loss": 0.5531, "num_tokens": 422041364.0, "step": 70755 }, { "epoch": 0.754910223720568, "grad_norm": 1.1988641607801018, "learning_rate": 1.1995015242970236e-05, "loss": 0.5462, "num_tokens": 422064487.0, "step": 70760 }, { "epoch": 0.7549635667267665, "grad_norm": 0.7956222849472231, "learning_rate": 1.199213927764673e-05, "loss": 0.4228, "num_tokens": 422094663.0, "step": 70765 }, { "epoch": 0.7550169097329649, "grad_norm": 0.9935923163649638, "learning_rate": 1.1989263794895992e-05, "loss": 0.5568, "num_tokens": 422121797.0, "step": 70770 }, { "epoch": 0.7550702527391634, "grad_norm": 0.748813587195583, "learning_rate": 1.19863887948075e-05, "loss": 0.5348, "num_tokens": 422161338.0, "step": 70775 }, { "epoch": 0.7551235957453618, "grad_norm": 1.033017973952219, "learning_rate": 1.198351427747073e-05, "loss": 0.4358, "num_tokens": 422180542.0, "step": 70780 }, { "epoch": 0.7551769387515603, "grad_norm": 0.6821262314877342, "learning_rate": 1.1980640242975126e-05, "loss": 0.5501, "num_tokens": 422217065.0, "step": 70785 }, { "epoch": 0.7552302817577587, "grad_norm": 0.9258842657170877, "learning_rate": 1.1977766691410112e-05, "loss": 0.3795, "num_tokens": 422254482.0, "step": 70790 }, { "epoch": 0.7552836247639572, "grad_norm": 0.5505065533867017, "learning_rate": 1.197489362286512e-05, "loss": 0.6296, "num_tokens": 422288959.0, "step": 70795 }, { "epoch": 0.7553369677701557, "grad_norm": 0.7653313599528206, "learning_rate": 1.1972021037429545e-05, "loss": 0.3983, "num_tokens": 422319491.0, "step": 70800 }, { "epoch": 0.7553903107763541, "grad_norm": 0.8260724479716908, "learning_rate": 1.196914893519278e-05, "loss": 0.4967, "num_tokens": 422340178.0, "step": 70805 }, { "epoch": 0.7554436537825525, "grad_norm": 1.1445244828874055, "learning_rate": 1.1966277316244204e-05, "loss": 0.5095, "num_tokens": 422360105.0, "step": 70810 }, { "epoch": 0.755496996788751, "grad_norm": 0.6155571932561427, "learning_rate": 1.1963406180673164e-05, "loss": 0.5063, "num_tokens": 422392148.0, "step": 70815 }, { "epoch": 0.7555503397949495, "grad_norm": 1.9998741722280073, "learning_rate": 1.196053552856902e-05, "loss": 0.5803, "num_tokens": 422406981.0, "step": 70820 }, { "epoch": 0.755603682801148, "grad_norm": 0.7502011696740358, "learning_rate": 1.1957665360021086e-05, "loss": 0.5666, "num_tokens": 422447519.0, "step": 70825 }, { "epoch": 0.7556570258073464, "grad_norm": 0.8299954488201606, "learning_rate": 1.195479567511868e-05, "loss": 0.5253, "num_tokens": 422477076.0, "step": 70830 }, { "epoch": 0.7557103688135448, "grad_norm": 0.7969906528484998, "learning_rate": 1.1951926473951097e-05, "loss": 0.3352, "num_tokens": 422508301.0, "step": 70835 }, { "epoch": 0.7557637118197433, "grad_norm": 0.9875501788864511, "learning_rate": 1.1949057756607636e-05, "loss": 0.5113, "num_tokens": 422526947.0, "step": 70840 }, { "epoch": 0.7558170548259417, "grad_norm": 1.1181221858692452, "learning_rate": 1.1946189523177546e-05, "loss": 0.4787, "num_tokens": 422559557.0, "step": 70845 }, { "epoch": 0.7558703978321403, "grad_norm": 1.1134016406234264, "learning_rate": 1.194332177375009e-05, "loss": 0.4491, "num_tokens": 422588571.0, "step": 70850 }, { "epoch": 0.7559237408383387, "grad_norm": 0.5921282255398247, "learning_rate": 1.1940454508414516e-05, "loss": 0.331, "num_tokens": 422612294.0, "step": 70855 }, { "epoch": 0.7559770838445371, "grad_norm": 0.6825125820616749, "learning_rate": 1.1937587727260032e-05, "loss": 0.5041, "num_tokens": 422641982.0, "step": 70860 }, { "epoch": 0.7560304268507356, "grad_norm": 0.6578612633737286, "learning_rate": 1.1934721430375848e-05, "loss": 0.5554, "num_tokens": 422671752.0, "step": 70865 }, { "epoch": 0.756083769856934, "grad_norm": 1.000480705588711, "learning_rate": 1.1931855617851168e-05, "loss": 0.4466, "num_tokens": 422702731.0, "step": 70870 }, { "epoch": 0.7561371128631326, "grad_norm": 1.338576481310573, "learning_rate": 1.1928990289775157e-05, "loss": 0.4812, "num_tokens": 422720726.0, "step": 70875 }, { "epoch": 0.756190455869331, "grad_norm": 0.9207805753944202, "learning_rate": 1.1926125446236985e-05, "loss": 0.467, "num_tokens": 422751130.0, "step": 70880 }, { "epoch": 0.7562437988755294, "grad_norm": 0.9179476193415856, "learning_rate": 1.1923261087325803e-05, "loss": 0.4281, "num_tokens": 422768637.0, "step": 70885 }, { "epoch": 0.7562971418817279, "grad_norm": 0.9921053461298172, "learning_rate": 1.1920397213130744e-05, "loss": 0.6105, "num_tokens": 422804019.0, "step": 70890 }, { "epoch": 0.7563504848879263, "grad_norm": 0.5039169717874302, "learning_rate": 1.1917533823740913e-05, "loss": 0.461, "num_tokens": 422843998.0, "step": 70895 }, { "epoch": 0.7564038278941247, "grad_norm": 0.9094176933172851, "learning_rate": 1.191467091924543e-05, "loss": 0.37, "num_tokens": 422862429.0, "step": 70900 }, { "epoch": 0.7564571709003233, "grad_norm": 0.8764589254863621, "learning_rate": 1.1911808499733368e-05, "loss": 0.5511, "num_tokens": 422893052.0, "step": 70905 }, { "epoch": 0.7565105139065217, "grad_norm": 0.8544900838533221, "learning_rate": 1.1908946565293805e-05, "loss": 0.5245, "num_tokens": 422913177.0, "step": 70910 }, { "epoch": 0.7565638569127202, "grad_norm": 0.7993968807753596, "learning_rate": 1.1906085116015809e-05, "loss": 0.4989, "num_tokens": 422951588.0, "step": 70915 }, { "epoch": 0.7566171999189186, "grad_norm": 0.8158591954595046, "learning_rate": 1.1903224151988406e-05, "loss": 0.4331, "num_tokens": 422980777.0, "step": 70920 }, { "epoch": 0.756670542925117, "grad_norm": 2.0256961221291374, "learning_rate": 1.1900363673300636e-05, "loss": 0.5379, "num_tokens": 423014837.0, "step": 70925 }, { "epoch": 0.7567238859313156, "grad_norm": 0.9807627925149333, "learning_rate": 1.1897503680041509e-05, "loss": 0.4998, "num_tokens": 423056491.0, "step": 70930 }, { "epoch": 0.756777228937514, "grad_norm": 1.025736491889067, "learning_rate": 1.1894644172300008e-05, "loss": 0.4967, "num_tokens": 423080759.0, "step": 70935 }, { "epoch": 0.7568305719437125, "grad_norm": 0.8652544608068733, "learning_rate": 1.1891785150165127e-05, "loss": 0.5241, "num_tokens": 423108336.0, "step": 70940 }, { "epoch": 0.7568839149499109, "grad_norm": 1.0132325256999113, "learning_rate": 1.1888926613725842e-05, "loss": 0.4051, "num_tokens": 423134076.0, "step": 70945 }, { "epoch": 0.7569372579561093, "grad_norm": 0.9144063498915336, "learning_rate": 1.1886068563071085e-05, "loss": 0.3874, "num_tokens": 423175418.0, "step": 70950 }, { "epoch": 0.7569906009623079, "grad_norm": 1.5030816210090294, "learning_rate": 1.1883210998289803e-05, "loss": 0.4402, "num_tokens": 423192921.0, "step": 70955 }, { "epoch": 0.7570439439685063, "grad_norm": 0.5976680750722395, "learning_rate": 1.1880353919470924e-05, "loss": 0.4486, "num_tokens": 423220256.0, "step": 70960 }, { "epoch": 0.7570972869747048, "grad_norm": 0.9067911178884996, "learning_rate": 1.1877497326703348e-05, "loss": 0.5044, "num_tokens": 423247596.0, "step": 70965 }, { "epoch": 0.7571506299809032, "grad_norm": 1.394856483163349, "learning_rate": 1.1874641220075958e-05, "loss": 0.5615, "num_tokens": 423270651.0, "step": 70970 }, { "epoch": 0.7572039729871016, "grad_norm": 0.9943828726076854, "learning_rate": 1.1871785599677645e-05, "loss": 0.3976, "num_tokens": 423292649.0, "step": 70975 }, { "epoch": 0.7572573159933002, "grad_norm": 0.8175985162708458, "learning_rate": 1.1868930465597256e-05, "loss": 0.438, "num_tokens": 423317898.0, "step": 70980 }, { "epoch": 0.7573106589994986, "grad_norm": 1.0831125933072006, "learning_rate": 1.1866075817923645e-05, "loss": 0.4677, "num_tokens": 423342583.0, "step": 70985 }, { "epoch": 0.757364002005697, "grad_norm": 1.0695862320993503, "learning_rate": 1.1863221656745646e-05, "loss": 0.5077, "num_tokens": 423379459.0, "step": 70990 }, { "epoch": 0.7574173450118955, "grad_norm": 0.8757848910710746, "learning_rate": 1.1860367982152062e-05, "loss": 0.5126, "num_tokens": 423419192.0, "step": 70995 }, { "epoch": 0.7574706880180939, "grad_norm": 0.6112248568931076, "learning_rate": 1.1857514794231713e-05, "loss": 0.478, "num_tokens": 423463126.0, "step": 71000 }, { "epoch": 0.7575240310242924, "grad_norm": 1.081843125173517, "learning_rate": 1.185466209307337e-05, "loss": 0.672, "num_tokens": 423478578.0, "step": 71005 }, { "epoch": 0.7575773740304909, "grad_norm": 0.6799786346379887, "learning_rate": 1.1851809878765804e-05, "loss": 0.4387, "num_tokens": 423521266.0, "step": 71010 }, { "epoch": 0.7576307170366893, "grad_norm": 0.9028858999960522, "learning_rate": 1.1848958151397766e-05, "loss": 0.5049, "num_tokens": 423549432.0, "step": 71015 }, { "epoch": 0.7576840600428878, "grad_norm": 0.9409387004621278, "learning_rate": 1.1846106911058006e-05, "loss": 0.4838, "num_tokens": 423574207.0, "step": 71020 }, { "epoch": 0.7577374030490862, "grad_norm": 0.8699316443400744, "learning_rate": 1.184325615783525e-05, "loss": 0.3627, "num_tokens": 423593134.0, "step": 71025 }, { "epoch": 0.7577907460552847, "grad_norm": 1.0628648068024096, "learning_rate": 1.1840405891818196e-05, "loss": 0.4877, "num_tokens": 423621852.0, "step": 71030 }, { "epoch": 0.7578440890614832, "grad_norm": 0.8122001147177782, "learning_rate": 1.183755611309555e-05, "loss": 0.4827, "num_tokens": 423659745.0, "step": 71035 }, { "epoch": 0.7578974320676816, "grad_norm": 0.6274083758630093, "learning_rate": 1.183470682175599e-05, "loss": 0.4531, "num_tokens": 423685709.0, "step": 71040 }, { "epoch": 0.7579507750738801, "grad_norm": 0.6411852811608624, "learning_rate": 1.1831858017888166e-05, "loss": 0.4545, "num_tokens": 423712459.0, "step": 71045 }, { "epoch": 0.7580041180800785, "grad_norm": 0.7803556788350345, "learning_rate": 1.1829009701580739e-05, "loss": 0.4563, "num_tokens": 423743440.0, "step": 71050 }, { "epoch": 0.758057461086277, "grad_norm": 0.7684512168731505, "learning_rate": 1.1826161872922347e-05, "loss": 0.4893, "num_tokens": 423781891.0, "step": 71055 }, { "epoch": 0.7581108040924754, "grad_norm": 0.8784427751576896, "learning_rate": 1.1823314532001598e-05, "loss": 0.476, "num_tokens": 423804640.0, "step": 71060 }, { "epoch": 0.7581641470986739, "grad_norm": 1.0171516387394783, "learning_rate": 1.1820467678907098e-05, "loss": 0.4344, "num_tokens": 423836442.0, "step": 71065 }, { "epoch": 0.7582174901048724, "grad_norm": 1.2909526679419436, "learning_rate": 1.1817621313727444e-05, "loss": 0.495, "num_tokens": 423865539.0, "step": 71070 }, { "epoch": 0.7582708331110708, "grad_norm": 1.9281332951309083, "learning_rate": 1.1814775436551202e-05, "loss": 0.4675, "num_tokens": 423899487.0, "step": 71075 }, { "epoch": 0.7583241761172692, "grad_norm": 0.6436725034770019, "learning_rate": 1.1811930047466922e-05, "loss": 0.4118, "num_tokens": 423934070.0, "step": 71080 }, { "epoch": 0.7583775191234677, "grad_norm": 0.5368818322305859, "learning_rate": 1.1809085146563165e-05, "loss": 0.4797, "num_tokens": 423971538.0, "step": 71085 }, { "epoch": 0.7584308621296662, "grad_norm": 1.1332060319330264, "learning_rate": 1.1806240733928438e-05, "loss": 0.5228, "num_tokens": 424003355.0, "step": 71090 }, { "epoch": 0.7584842051358647, "grad_norm": 0.9313555485680299, "learning_rate": 1.1803396809651264e-05, "loss": 0.6022, "num_tokens": 424026450.0, "step": 71095 }, { "epoch": 0.7585375481420631, "grad_norm": 0.8887602099011971, "learning_rate": 1.180055337382015e-05, "loss": 0.6547, "num_tokens": 424061895.0, "step": 71100 }, { "epoch": 0.7585908911482615, "grad_norm": 0.8439005293770783, "learning_rate": 1.1797710426523557e-05, "loss": 0.5113, "num_tokens": 424098617.0, "step": 71105 }, { "epoch": 0.75864423415446, "grad_norm": 0.7947245493413496, "learning_rate": 1.1794867967849969e-05, "loss": 0.449, "num_tokens": 424127041.0, "step": 71110 }, { "epoch": 0.7586975771606584, "grad_norm": 0.8749182503191358, "learning_rate": 1.1792025997887833e-05, "loss": 0.3641, "num_tokens": 424162226.0, "step": 71115 }, { "epoch": 0.758750920166857, "grad_norm": 0.8198767844823663, "learning_rate": 1.1789184516725572e-05, "loss": 0.3993, "num_tokens": 424187923.0, "step": 71120 }, { "epoch": 0.7588042631730554, "grad_norm": 1.5536567074719443, "learning_rate": 1.178634352445162e-05, "loss": 0.5336, "num_tokens": 424213065.0, "step": 71125 }, { "epoch": 0.7588576061792538, "grad_norm": 0.875708192837621, "learning_rate": 1.1783503021154388e-05, "loss": 0.4373, "num_tokens": 424234291.0, "step": 71130 }, { "epoch": 0.7589109491854523, "grad_norm": 0.7476307406615222, "learning_rate": 1.1780663006922252e-05, "loss": 0.5197, "num_tokens": 424262382.0, "step": 71135 }, { "epoch": 0.7589642921916507, "grad_norm": 1.132366324462737, "learning_rate": 1.1777823481843597e-05, "loss": 0.5345, "num_tokens": 424293681.0, "step": 71140 }, { "epoch": 0.7590176351978493, "grad_norm": 1.217862806706926, "learning_rate": 1.1774984446006785e-05, "loss": 0.4392, "num_tokens": 424332619.0, "step": 71145 }, { "epoch": 0.7590709782040477, "grad_norm": 1.1557522529573683, "learning_rate": 1.1772145899500157e-05, "loss": 0.4057, "num_tokens": 424359989.0, "step": 71150 }, { "epoch": 0.7591243212102461, "grad_norm": 1.2617577511890923, "learning_rate": 1.1769307842412039e-05, "loss": 0.5363, "num_tokens": 424385154.0, "step": 71155 }, { "epoch": 0.7591776642164446, "grad_norm": 0.8424757582220929, "learning_rate": 1.176647027483075e-05, "loss": 0.5125, "num_tokens": 424420347.0, "step": 71160 }, { "epoch": 0.759231007222643, "grad_norm": 1.0171289389008107, "learning_rate": 1.1763633196844586e-05, "loss": 0.5031, "num_tokens": 424446005.0, "step": 71165 }, { "epoch": 0.7592843502288414, "grad_norm": 2.095687495363237, "learning_rate": 1.1760796608541834e-05, "loss": 0.4025, "num_tokens": 424463566.0, "step": 71170 }, { "epoch": 0.75933769323504, "grad_norm": 1.8212287900529849, "learning_rate": 1.1757960510010768e-05, "loss": 0.4438, "num_tokens": 424477885.0, "step": 71175 }, { "epoch": 0.7593910362412384, "grad_norm": 1.4417491008870533, "learning_rate": 1.1755124901339636e-05, "loss": 0.4867, "num_tokens": 424500081.0, "step": 71180 }, { "epoch": 0.7594443792474369, "grad_norm": 0.6608261540649822, "learning_rate": 1.175228978261667e-05, "loss": 0.531, "num_tokens": 424527179.0, "step": 71185 }, { "epoch": 0.7594977222536353, "grad_norm": 1.044637683351198, "learning_rate": 1.1749455153930105e-05, "loss": 0.4832, "num_tokens": 424568195.0, "step": 71190 }, { "epoch": 0.7595510652598337, "grad_norm": 0.8336303988703492, "learning_rate": 1.1746621015368135e-05, "loss": 0.4103, "num_tokens": 424591673.0, "step": 71195 }, { "epoch": 0.7596044082660323, "grad_norm": 0.8374010740371394, "learning_rate": 1.1743787367018963e-05, "loss": 0.453, "num_tokens": 424618783.0, "step": 71200 }, { "epoch": 0.7596577512722307, "grad_norm": 0.9111030530187745, "learning_rate": 1.1740954208970769e-05, "loss": 0.3984, "num_tokens": 424648241.0, "step": 71205 }, { "epoch": 0.7597110942784292, "grad_norm": 0.9125554382504824, "learning_rate": 1.1738121541311705e-05, "loss": 0.3655, "num_tokens": 424672468.0, "step": 71210 }, { "epoch": 0.7597644372846276, "grad_norm": 0.8413793276585108, "learning_rate": 1.1735289364129929e-05, "loss": 0.5738, "num_tokens": 424706239.0, "step": 71215 }, { "epoch": 0.759817780290826, "grad_norm": 1.0793323696805641, "learning_rate": 1.1732457677513568e-05, "loss": 0.403, "num_tokens": 424738204.0, "step": 71220 }, { "epoch": 0.7598711232970246, "grad_norm": 1.082066940201174, "learning_rate": 1.1729626481550726e-05, "loss": 0.429, "num_tokens": 424757954.0, "step": 71225 }, { "epoch": 0.759924466303223, "grad_norm": 0.7048201439589001, "learning_rate": 1.1726795776329515e-05, "loss": 0.5001, "num_tokens": 424787613.0, "step": 71230 }, { "epoch": 0.7599778093094215, "grad_norm": 1.4378009811217811, "learning_rate": 1.172396556193803e-05, "loss": 0.556, "num_tokens": 424822545.0, "step": 71235 }, { "epoch": 0.7600311523156199, "grad_norm": 0.951479253320897, "learning_rate": 1.1721135838464324e-05, "loss": 0.3751, "num_tokens": 424857475.0, "step": 71240 }, { "epoch": 0.7600844953218183, "grad_norm": 0.7269994315177547, "learning_rate": 1.171830660599646e-05, "loss": 0.4999, "num_tokens": 424884112.0, "step": 71245 }, { "epoch": 0.7601378383280168, "grad_norm": 0.8668233263144511, "learning_rate": 1.1715477864622483e-05, "loss": 0.4266, "num_tokens": 424906603.0, "step": 71250 }, { "epoch": 0.7601911813342153, "grad_norm": 0.6100971802808424, "learning_rate": 1.1712649614430415e-05, "loss": 0.4213, "num_tokens": 424948446.0, "step": 71255 }, { "epoch": 0.7602445243404137, "grad_norm": 0.6564963278236388, "learning_rate": 1.1709821855508254e-05, "loss": 0.4511, "num_tokens": 424974037.0, "step": 71260 }, { "epoch": 0.7602978673466122, "grad_norm": 1.5406807231405388, "learning_rate": 1.1706994587944012e-05, "loss": 0.4112, "num_tokens": 425003461.0, "step": 71265 }, { "epoch": 0.7603512103528106, "grad_norm": 0.7308273868801728, "learning_rate": 1.1704167811825649e-05, "loss": 0.4039, "num_tokens": 425035919.0, "step": 71270 }, { "epoch": 0.7604045533590091, "grad_norm": 0.9750168444379723, "learning_rate": 1.1701341527241138e-05, "loss": 0.4335, "num_tokens": 425066822.0, "step": 71275 }, { "epoch": 0.7604578963652076, "grad_norm": 1.327459885016734, "learning_rate": 1.1698515734278436e-05, "loss": 0.5617, "num_tokens": 425094824.0, "step": 71280 }, { "epoch": 0.760511239371406, "grad_norm": 1.222416285526362, "learning_rate": 1.169569043302546e-05, "loss": 0.526, "num_tokens": 425111226.0, "step": 71285 }, { "epoch": 0.7605645823776045, "grad_norm": 0.6597904159034486, "learning_rate": 1.1692865623570144e-05, "loss": 0.451, "num_tokens": 425139840.0, "step": 71290 }, { "epoch": 0.7606179253838029, "grad_norm": 0.7175181958257567, "learning_rate": 1.1690041306000377e-05, "loss": 0.4473, "num_tokens": 425171294.0, "step": 71295 }, { "epoch": 0.7606712683900014, "grad_norm": 1.0512902765987444, "learning_rate": 1.1687217480404045e-05, "loss": 0.5165, "num_tokens": 425197393.0, "step": 71300 }, { "epoch": 0.7607246113961998, "grad_norm": 1.5116851053128462, "learning_rate": 1.1684394146869025e-05, "loss": 0.3888, "num_tokens": 425211581.0, "step": 71305 }, { "epoch": 0.7607779544023983, "grad_norm": 1.4567736477019226, "learning_rate": 1.1681571305483179e-05, "loss": 0.4185, "num_tokens": 425232184.0, "step": 71310 }, { "epoch": 0.7608312974085968, "grad_norm": 1.0330296544970619, "learning_rate": 1.1678748956334336e-05, "loss": 0.4843, "num_tokens": 425265027.0, "step": 71315 }, { "epoch": 0.7608846404147952, "grad_norm": 0.7420111732869324, "learning_rate": 1.1675927099510327e-05, "loss": 0.5103, "num_tokens": 425296448.0, "step": 71320 }, { "epoch": 0.7609379834209937, "grad_norm": 1.5098046780945484, "learning_rate": 1.1673105735098968e-05, "loss": 0.4769, "num_tokens": 425318526.0, "step": 71325 }, { "epoch": 0.7609913264271921, "grad_norm": 1.0368311996754123, "learning_rate": 1.1670284863188055e-05, "loss": 0.408, "num_tokens": 425337109.0, "step": 71330 }, { "epoch": 0.7610446694333906, "grad_norm": 0.8367817703058829, "learning_rate": 1.1667464483865348e-05, "loss": 0.496, "num_tokens": 425365528.0, "step": 71335 }, { "epoch": 0.7610980124395891, "grad_norm": 2.609872578371459, "learning_rate": 1.1664644597218635e-05, "loss": 0.549, "num_tokens": 425386587.0, "step": 71340 }, { "epoch": 0.7611513554457875, "grad_norm": 0.8512924400666718, "learning_rate": 1.166182520333565e-05, "loss": 0.5495, "num_tokens": 425429230.0, "step": 71345 }, { "epoch": 0.7612046984519859, "grad_norm": 1.196337335411111, "learning_rate": 1.1659006302304132e-05, "loss": 0.5044, "num_tokens": 425459443.0, "step": 71350 }, { "epoch": 0.7612580414581844, "grad_norm": 0.749670694968958, "learning_rate": 1.1656187894211803e-05, "loss": 0.4356, "num_tokens": 425484557.0, "step": 71355 }, { "epoch": 0.7613113844643828, "grad_norm": 0.7476641827574854, "learning_rate": 1.1653369979146358e-05, "loss": 0.542, "num_tokens": 425515443.0, "step": 71360 }, { "epoch": 0.7613647274705814, "grad_norm": 0.6230489997869718, "learning_rate": 1.1650552557195497e-05, "loss": 0.6682, "num_tokens": 425540131.0, "step": 71365 }, { "epoch": 0.7614180704767798, "grad_norm": 0.8956596531860516, "learning_rate": 1.1647735628446884e-05, "loss": 0.4779, "num_tokens": 425563166.0, "step": 71370 }, { "epoch": 0.7614714134829782, "grad_norm": 0.7936607696485577, "learning_rate": 1.164491919298817e-05, "loss": 0.4904, "num_tokens": 425602248.0, "step": 71375 }, { "epoch": 0.7615247564891767, "grad_norm": 0.8739053315295259, "learning_rate": 1.1642103250907003e-05, "loss": 0.5739, "num_tokens": 425635845.0, "step": 71380 }, { "epoch": 0.7615780994953751, "grad_norm": 0.864023845467864, "learning_rate": 1.1639287802291019e-05, "loss": 0.5325, "num_tokens": 425672262.0, "step": 71385 }, { "epoch": 0.7616314425015737, "grad_norm": 1.573921254389537, "learning_rate": 1.163647284722781e-05, "loss": 0.4257, "num_tokens": 425698399.0, "step": 71390 }, { "epoch": 0.7616847855077721, "grad_norm": 0.821352174376596, "learning_rate": 1.1633658385804983e-05, "loss": 0.5162, "num_tokens": 425726794.0, "step": 71395 }, { "epoch": 0.7617381285139705, "grad_norm": 0.7033015075244046, "learning_rate": 1.163084441811012e-05, "loss": 0.4238, "num_tokens": 425760724.0, "step": 71400 }, { "epoch": 0.761791471520169, "grad_norm": 1.069510936345973, "learning_rate": 1.1628030944230788e-05, "loss": 0.4025, "num_tokens": 425787937.0, "step": 71405 }, { "epoch": 0.7618448145263674, "grad_norm": 0.8751611754806149, "learning_rate": 1.162521796425452e-05, "loss": 0.3972, "num_tokens": 425807888.0, "step": 71410 }, { "epoch": 0.761898157532566, "grad_norm": 0.8565988378309239, "learning_rate": 1.1622405478268869e-05, "loss": 0.5195, "num_tokens": 425829818.0, "step": 71415 }, { "epoch": 0.7619515005387644, "grad_norm": 1.012380469449272, "learning_rate": 1.1619593486361342e-05, "loss": 0.4768, "num_tokens": 425857285.0, "step": 71420 }, { "epoch": 0.7620048435449628, "grad_norm": 0.8401031619614766, "learning_rate": 1.1616781988619443e-05, "loss": 0.3716, "num_tokens": 425886325.0, "step": 71425 }, { "epoch": 0.7620581865511613, "grad_norm": 0.7739434245533438, "learning_rate": 1.161397098513067e-05, "loss": 0.4685, "num_tokens": 425916875.0, "step": 71430 }, { "epoch": 0.7621115295573597, "grad_norm": 0.7737405858869392, "learning_rate": 1.1611160475982486e-05, "loss": 0.5895, "num_tokens": 425949640.0, "step": 71435 }, { "epoch": 0.7621648725635581, "grad_norm": 0.9010277299277442, "learning_rate": 1.1608350461262354e-05, "loss": 0.3585, "num_tokens": 425970581.0, "step": 71440 }, { "epoch": 0.7622182155697567, "grad_norm": 0.5574983981958412, "learning_rate": 1.1605540941057716e-05, "loss": 0.4053, "num_tokens": 426007716.0, "step": 71445 }, { "epoch": 0.7622715585759551, "grad_norm": 3.546240178497918, "learning_rate": 1.1602731915455989e-05, "loss": 0.5743, "num_tokens": 426038294.0, "step": 71450 }, { "epoch": 0.7623249015821536, "grad_norm": 2.589250521526576, "learning_rate": 1.159992338454459e-05, "loss": 0.4974, "num_tokens": 426063781.0, "step": 71455 }, { "epoch": 0.762378244588352, "grad_norm": 0.602783139253355, "learning_rate": 1.1597115348410922e-05, "loss": 0.4296, "num_tokens": 426100845.0, "step": 71460 }, { "epoch": 0.7624315875945504, "grad_norm": 0.8599591179350761, "learning_rate": 1.1594307807142352e-05, "loss": 0.4879, "num_tokens": 426143154.0, "step": 71465 }, { "epoch": 0.762484930600749, "grad_norm": 0.5851413589448291, "learning_rate": 1.159150076082626e-05, "loss": 0.3883, "num_tokens": 426176799.0, "step": 71470 }, { "epoch": 0.7625382736069474, "grad_norm": 0.5546931606435453, "learning_rate": 1.158869420954998e-05, "loss": 0.5234, "num_tokens": 426217619.0, "step": 71475 }, { "epoch": 0.7625916166131459, "grad_norm": 0.7401625171046856, "learning_rate": 1.158588815340086e-05, "loss": 0.4322, "num_tokens": 426242073.0, "step": 71480 }, { "epoch": 0.7626449596193443, "grad_norm": 0.888190536429352, "learning_rate": 1.1583082592466202e-05, "loss": 0.6051, "num_tokens": 426268109.0, "step": 71485 }, { "epoch": 0.7626983026255427, "grad_norm": 0.557275390975777, "learning_rate": 1.1580277526833331e-05, "loss": 0.431, "num_tokens": 426296852.0, "step": 71490 }, { "epoch": 0.7627516456317412, "grad_norm": 0.8292874703849535, "learning_rate": 1.1577472956589514e-05, "loss": 0.513, "num_tokens": 426319101.0, "step": 71495 }, { "epoch": 0.7628049886379397, "grad_norm": 1.1805433369725533, "learning_rate": 1.1574668881822036e-05, "loss": 0.5088, "num_tokens": 426347548.0, "step": 71500 }, { "epoch": 0.7628583316441382, "grad_norm": 1.0910469321396314, "learning_rate": 1.1571865302618154e-05, "loss": 0.4872, "num_tokens": 426370950.0, "step": 71505 }, { "epoch": 0.7629116746503366, "grad_norm": 0.74595998797023, "learning_rate": 1.1569062219065107e-05, "loss": 0.4078, "num_tokens": 426401297.0, "step": 71510 }, { "epoch": 0.762965017656535, "grad_norm": 0.8652425390213941, "learning_rate": 1.1566259631250117e-05, "loss": 0.4999, "num_tokens": 426439961.0, "step": 71515 }, { "epoch": 0.7630183606627335, "grad_norm": 0.6308911686366165, "learning_rate": 1.1563457539260403e-05, "loss": 0.4726, "num_tokens": 426477121.0, "step": 71520 }, { "epoch": 0.763071703668932, "grad_norm": 0.8479387447166478, "learning_rate": 1.156065594318315e-05, "loss": 0.4969, "num_tokens": 426503017.0, "step": 71525 }, { "epoch": 0.7631250466751304, "grad_norm": 0.7615320703994531, "learning_rate": 1.155785484310554e-05, "loss": 0.456, "num_tokens": 426545489.0, "step": 71530 }, { "epoch": 0.7631783896813289, "grad_norm": 0.835981449698338, "learning_rate": 1.155505423911475e-05, "loss": 0.4598, "num_tokens": 426576098.0, "step": 71535 }, { "epoch": 0.7632317326875273, "grad_norm": 0.7489142454867569, "learning_rate": 1.1552254131297917e-05, "loss": 0.4843, "num_tokens": 426627553.0, "step": 71540 }, { "epoch": 0.7632850756937258, "grad_norm": 0.9633519622798083, "learning_rate": 1.154945451974218e-05, "loss": 0.4846, "num_tokens": 426643791.0, "step": 71545 }, { "epoch": 0.7633384186999242, "grad_norm": 0.8036014692620126, "learning_rate": 1.1546655404534656e-05, "loss": 0.4392, "num_tokens": 426667199.0, "step": 71550 }, { "epoch": 0.7633917617061227, "grad_norm": 0.6869814079696914, "learning_rate": 1.1543856785762442e-05, "loss": 0.4686, "num_tokens": 426721464.0, "step": 71555 }, { "epoch": 0.7634451047123212, "grad_norm": 0.6554734073113816, "learning_rate": 1.154105866351263e-05, "loss": 0.4302, "num_tokens": 426746953.0, "step": 71560 }, { "epoch": 0.7634984477185196, "grad_norm": 0.6661875774252571, "learning_rate": 1.1538261037872294e-05, "loss": 0.4789, "num_tokens": 426764456.0, "step": 71565 }, { "epoch": 0.7635517907247181, "grad_norm": 1.2455156010715727, "learning_rate": 1.1535463908928488e-05, "loss": 0.4463, "num_tokens": 426799418.0, "step": 71570 }, { "epoch": 0.7636051337309165, "grad_norm": 0.9623768329319267, "learning_rate": 1.1532667276768248e-05, "loss": 0.6257, "num_tokens": 426834486.0, "step": 71575 }, { "epoch": 0.763658476737115, "grad_norm": 2.573051178584097, "learning_rate": 1.152987114147861e-05, "loss": 0.5107, "num_tokens": 426860134.0, "step": 71580 }, { "epoch": 0.7637118197433135, "grad_norm": 0.9310115439751295, "learning_rate": 1.1527075503146583e-05, "loss": 0.4883, "num_tokens": 426887029.0, "step": 71585 }, { "epoch": 0.7637651627495119, "grad_norm": 0.8831459001018621, "learning_rate": 1.1524280361859149e-05, "loss": 0.4605, "num_tokens": 426924648.0, "step": 71590 }, { "epoch": 0.7638185057557104, "grad_norm": 1.2156705349866412, "learning_rate": 1.15214857177033e-05, "loss": 0.4402, "num_tokens": 426943632.0, "step": 71595 }, { "epoch": 0.7638718487619088, "grad_norm": 1.0030720034884797, "learning_rate": 1.151869157076599e-05, "loss": 0.5731, "num_tokens": 426974864.0, "step": 71600 }, { "epoch": 0.7639251917681072, "grad_norm": 1.0521114669466423, "learning_rate": 1.1515897921134172e-05, "loss": 0.5667, "num_tokens": 427012361.0, "step": 71605 }, { "epoch": 0.7639785347743058, "grad_norm": 0.7346851564841975, "learning_rate": 1.1513104768894784e-05, "loss": 0.5082, "num_tokens": 427033494.0, "step": 71610 }, { "epoch": 0.7640318777805042, "grad_norm": 0.843237204305416, "learning_rate": 1.151031211413473e-05, "loss": 0.4467, "num_tokens": 427062964.0, "step": 71615 }, { "epoch": 0.7640852207867026, "grad_norm": 1.2255334128053073, "learning_rate": 1.1507519956940929e-05, "loss": 0.4803, "num_tokens": 427092579.0, "step": 71620 }, { "epoch": 0.7641385637929011, "grad_norm": 1.1422830136325381, "learning_rate": 1.1504728297400254e-05, "loss": 0.3989, "num_tokens": 427112283.0, "step": 71625 }, { "epoch": 0.7641919067990995, "grad_norm": 0.6509147648313858, "learning_rate": 1.1501937135599575e-05, "loss": 0.4467, "num_tokens": 427144282.0, "step": 71630 }, { "epoch": 0.7642452498052981, "grad_norm": 1.198882416950077, "learning_rate": 1.1499146471625748e-05, "loss": 0.4902, "num_tokens": 427165074.0, "step": 71635 }, { "epoch": 0.7642985928114965, "grad_norm": 0.8575314799013929, "learning_rate": 1.1496356305565627e-05, "loss": 0.4624, "num_tokens": 427184396.0, "step": 71640 }, { "epoch": 0.7643519358176949, "grad_norm": 1.3425504281403737, "learning_rate": 1.1493566637506015e-05, "loss": 0.4528, "num_tokens": 427200930.0, "step": 71645 }, { "epoch": 0.7644052788238934, "grad_norm": 0.77546536948448, "learning_rate": 1.1490777467533736e-05, "loss": 0.3485, "num_tokens": 427227008.0, "step": 71650 }, { "epoch": 0.7644586218300918, "grad_norm": 0.9428533865592251, "learning_rate": 1.1487988795735581e-05, "loss": 0.4587, "num_tokens": 427255439.0, "step": 71655 }, { "epoch": 0.7645119648362904, "grad_norm": 1.658452841216057, "learning_rate": 1.1485200622198326e-05, "loss": 0.4062, "num_tokens": 427282840.0, "step": 71660 }, { "epoch": 0.7645653078424888, "grad_norm": 1.9099261324452426, "learning_rate": 1.1482412947008725e-05, "loss": 0.5178, "num_tokens": 427298199.0, "step": 71665 }, { "epoch": 0.7646186508486872, "grad_norm": 0.7442314807951823, "learning_rate": 1.147962577025354e-05, "loss": 0.3646, "num_tokens": 427347257.0, "step": 71670 }, { "epoch": 0.7646719938548857, "grad_norm": 1.2558372512950835, "learning_rate": 1.1476839092019486e-05, "loss": 0.4935, "num_tokens": 427372310.0, "step": 71675 }, { "epoch": 0.7647253368610841, "grad_norm": 0.7583636304991204, "learning_rate": 1.1474052912393287e-05, "loss": 0.4455, "num_tokens": 427405904.0, "step": 71680 }, { "epoch": 0.7647786798672827, "grad_norm": 1.0424689637979851, "learning_rate": 1.1471267231461652e-05, "loss": 0.5317, "num_tokens": 427440058.0, "step": 71685 }, { "epoch": 0.7648320228734811, "grad_norm": 0.639117085359861, "learning_rate": 1.1468482049311247e-05, "loss": 0.4279, "num_tokens": 427467791.0, "step": 71690 }, { "epoch": 0.7648853658796795, "grad_norm": 1.2283826196378878, "learning_rate": 1.1465697366028759e-05, "loss": 0.5417, "num_tokens": 427501576.0, "step": 71695 }, { "epoch": 0.764938708885878, "grad_norm": 1.1298651735562455, "learning_rate": 1.1462913181700834e-05, "loss": 0.4558, "num_tokens": 427522670.0, "step": 71700 }, { "epoch": 0.7649920518920764, "grad_norm": 0.6117880385950636, "learning_rate": 1.1460129496414106e-05, "loss": 0.4126, "num_tokens": 427546388.0, "step": 71705 }, { "epoch": 0.7650453948982748, "grad_norm": 0.963678979410199, "learning_rate": 1.1457346310255196e-05, "loss": 0.5729, "num_tokens": 427569067.0, "step": 71710 }, { "epoch": 0.7650987379044734, "grad_norm": 0.761316344235629, "learning_rate": 1.1454563623310723e-05, "loss": 0.4474, "num_tokens": 427602858.0, "step": 71715 }, { "epoch": 0.7651520809106718, "grad_norm": 1.1078191080807323, "learning_rate": 1.1451781435667267e-05, "loss": 0.425, "num_tokens": 427628389.0, "step": 71720 }, { "epoch": 0.7652054239168703, "grad_norm": 0.7048799732137732, "learning_rate": 1.144899974741141e-05, "loss": 0.4802, "num_tokens": 427650415.0, "step": 71725 }, { "epoch": 0.7652587669230687, "grad_norm": 0.7912599521532716, "learning_rate": 1.1446218558629718e-05, "loss": 0.5403, "num_tokens": 427699177.0, "step": 71730 }, { "epoch": 0.7653121099292671, "grad_norm": 1.4503474585921785, "learning_rate": 1.1443437869408728e-05, "loss": 0.3991, "num_tokens": 427710862.0, "step": 71735 }, { "epoch": 0.7653654529354657, "grad_norm": 1.0118349311865082, "learning_rate": 1.1440657679834963e-05, "loss": 0.5202, "num_tokens": 427735662.0, "step": 71740 }, { "epoch": 0.7654187959416641, "grad_norm": 1.404195690847474, "learning_rate": 1.1437877989994953e-05, "loss": 0.6012, "num_tokens": 427761996.0, "step": 71745 }, { "epoch": 0.7654721389478626, "grad_norm": 1.3197149359457216, "learning_rate": 1.1435098799975178e-05, "loss": 0.4914, "num_tokens": 427786544.0, "step": 71750 }, { "epoch": 0.765525481954061, "grad_norm": 0.8843942445995163, "learning_rate": 1.143232010986213e-05, "loss": 0.4109, "num_tokens": 427810593.0, "step": 71755 }, { "epoch": 0.7655788249602594, "grad_norm": 0.7707936127442379, "learning_rate": 1.1429541919742286e-05, "loss": 0.3816, "num_tokens": 427829811.0, "step": 71760 }, { "epoch": 0.7656321679664579, "grad_norm": 0.6114272916039082, "learning_rate": 1.1426764229702076e-05, "loss": 0.4489, "num_tokens": 427873168.0, "step": 71765 }, { "epoch": 0.7656855109726564, "grad_norm": 0.8295203939177697, "learning_rate": 1.1423987039827959e-05, "loss": 0.4391, "num_tokens": 427911933.0, "step": 71770 }, { "epoch": 0.7657388539788549, "grad_norm": 1.2414120229705792, "learning_rate": 1.1421210350206344e-05, "loss": 0.5865, "num_tokens": 427933331.0, "step": 71775 }, { "epoch": 0.7657921969850533, "grad_norm": 1.49846839207492, "learning_rate": 1.1418434160923628e-05, "loss": 0.5418, "num_tokens": 427954665.0, "step": 71780 }, { "epoch": 0.7658455399912517, "grad_norm": 0.6726135389170004, "learning_rate": 1.1415658472066208e-05, "loss": 0.465, "num_tokens": 427999226.0, "step": 71785 }, { "epoch": 0.7658988829974502, "grad_norm": 0.8351228782285307, "learning_rate": 1.1412883283720466e-05, "loss": 0.4587, "num_tokens": 428029347.0, "step": 71790 }, { "epoch": 0.7659522260036487, "grad_norm": 1.7295038629689048, "learning_rate": 1.1410108595972744e-05, "loss": 0.4562, "num_tokens": 428066164.0, "step": 71795 }, { "epoch": 0.7660055690098471, "grad_norm": 1.3181426074479636, "learning_rate": 1.1407334408909402e-05, "loss": 0.43, "num_tokens": 428092126.0, "step": 71800 }, { "epoch": 0.7660589120160456, "grad_norm": 0.6574129541762241, "learning_rate": 1.1404560722616757e-05, "loss": 0.4655, "num_tokens": 428114919.0, "step": 71805 }, { "epoch": 0.766112255022244, "grad_norm": 1.0953284277652495, "learning_rate": 1.1401787537181115e-05, "loss": 0.4925, "num_tokens": 428142767.0, "step": 71810 }, { "epoch": 0.7661655980284425, "grad_norm": 1.4484790767608255, "learning_rate": 1.1399014852688778e-05, "loss": 0.4893, "num_tokens": 428170410.0, "step": 71815 }, { "epoch": 0.7662189410346409, "grad_norm": 1.1053884474482794, "learning_rate": 1.1396242669226033e-05, "loss": 0.417, "num_tokens": 428188336.0, "step": 71820 }, { "epoch": 0.7662722840408394, "grad_norm": 2.5884134078126584, "learning_rate": 1.1393470986879129e-05, "loss": 0.5242, "num_tokens": 428217312.0, "step": 71825 }, { "epoch": 0.7663256270470379, "grad_norm": 1.1563939161469277, "learning_rate": 1.1390699805734328e-05, "loss": 0.5011, "num_tokens": 428261100.0, "step": 71830 }, { "epoch": 0.7663789700532363, "grad_norm": 0.973062734042477, "learning_rate": 1.1387929125877862e-05, "loss": 0.3767, "num_tokens": 428295831.0, "step": 71835 }, { "epoch": 0.7664323130594348, "grad_norm": 1.982584330203988, "learning_rate": 1.1385158947395949e-05, "loss": 0.6108, "num_tokens": 428335150.0, "step": 71840 }, { "epoch": 0.7664856560656332, "grad_norm": 1.0309209532373866, "learning_rate": 1.1382389270374783e-05, "loss": 0.5194, "num_tokens": 428353684.0, "step": 71845 }, { "epoch": 0.7665389990718317, "grad_norm": 0.8339544003200905, "learning_rate": 1.1379620094900562e-05, "loss": 0.4964, "num_tokens": 428383438.0, "step": 71850 }, { "epoch": 0.7665923420780302, "grad_norm": 0.6893006896613229, "learning_rate": 1.1376851421059445e-05, "loss": 0.4709, "num_tokens": 428425775.0, "step": 71855 }, { "epoch": 0.7666456850842286, "grad_norm": 0.9411778410986172, "learning_rate": 1.1374083248937593e-05, "loss": 0.4421, "num_tokens": 428446245.0, "step": 71860 }, { "epoch": 0.7666990280904271, "grad_norm": 1.065082706538239, "learning_rate": 1.1371315578621154e-05, "loss": 0.4879, "num_tokens": 428473029.0, "step": 71865 }, { "epoch": 0.7667523710966255, "grad_norm": 0.9239239346095275, "learning_rate": 1.1368548410196241e-05, "loss": 0.4216, "num_tokens": 428494362.0, "step": 71870 }, { "epoch": 0.7668057141028239, "grad_norm": 1.0461237912378172, "learning_rate": 1.136578174374897e-05, "loss": 0.3947, "num_tokens": 428512023.0, "step": 71875 }, { "epoch": 0.7668590571090225, "grad_norm": 1.4294467948603056, "learning_rate": 1.136301557936543e-05, "loss": 0.4724, "num_tokens": 428545719.0, "step": 71880 }, { "epoch": 0.7669124001152209, "grad_norm": 1.310771892813433, "learning_rate": 1.1360249917131692e-05, "loss": 0.4694, "num_tokens": 428560384.0, "step": 71885 }, { "epoch": 0.7669657431214193, "grad_norm": 0.6900077580821914, "learning_rate": 1.1357484757133826e-05, "loss": 0.4191, "num_tokens": 428576751.0, "step": 71890 }, { "epoch": 0.7670190861276178, "grad_norm": 0.6906008506945215, "learning_rate": 1.1354720099457883e-05, "loss": 0.5689, "num_tokens": 428619724.0, "step": 71895 }, { "epoch": 0.7670724291338162, "grad_norm": 0.7672807827721292, "learning_rate": 1.135195594418988e-05, "loss": 0.4682, "num_tokens": 428655403.0, "step": 71900 }, { "epoch": 0.7671257721400148, "grad_norm": 0.7876488986925262, "learning_rate": 1.134919229141584e-05, "loss": 0.4478, "num_tokens": 428694372.0, "step": 71905 }, { "epoch": 0.7671791151462132, "grad_norm": 0.920982988945178, "learning_rate": 1.134642914122177e-05, "loss": 0.4882, "num_tokens": 428717287.0, "step": 71910 }, { "epoch": 0.7672324581524116, "grad_norm": 0.7925386010950042, "learning_rate": 1.1343666493693641e-05, "loss": 0.3923, "num_tokens": 428749683.0, "step": 71915 }, { "epoch": 0.7672858011586101, "grad_norm": 0.924176139935715, "learning_rate": 1.1340904348917417e-05, "loss": 0.561, "num_tokens": 428791015.0, "step": 71920 }, { "epoch": 0.7673391441648085, "grad_norm": 0.9117023849499585, "learning_rate": 1.133814270697907e-05, "loss": 0.482, "num_tokens": 428814110.0, "step": 71925 }, { "epoch": 0.767392487171007, "grad_norm": 1.035484565143742, "learning_rate": 1.1335381567964514e-05, "loss": 0.5679, "num_tokens": 428836495.0, "step": 71930 }, { "epoch": 0.7674458301772055, "grad_norm": 0.5342130026619191, "learning_rate": 1.1332620931959681e-05, "loss": 0.431, "num_tokens": 428882402.0, "step": 71935 }, { "epoch": 0.7674991731834039, "grad_norm": 0.8171085591724786, "learning_rate": 1.1329860799050476e-05, "loss": 0.4026, "num_tokens": 428909676.0, "step": 71940 }, { "epoch": 0.7675525161896024, "grad_norm": 1.0237341858660214, "learning_rate": 1.1327101169322796e-05, "loss": 0.4711, "num_tokens": 428946811.0, "step": 71945 }, { "epoch": 0.7676058591958008, "grad_norm": 1.1543793780443579, "learning_rate": 1.1324342042862506e-05, "loss": 0.5307, "num_tokens": 428974601.0, "step": 71950 }, { "epoch": 0.7676592022019993, "grad_norm": 0.8382522612246178, "learning_rate": 1.132158341975546e-05, "loss": 0.4034, "num_tokens": 429004306.0, "step": 71955 }, { "epoch": 0.7677125452081978, "grad_norm": 0.7522860569158804, "learning_rate": 1.1318825300087513e-05, "loss": 0.4539, "num_tokens": 429048169.0, "step": 71960 }, { "epoch": 0.7677658882143962, "grad_norm": 2.703396605215795, "learning_rate": 1.1316067683944478e-05, "loss": 0.5295, "num_tokens": 429082178.0, "step": 71965 }, { "epoch": 0.7678192312205947, "grad_norm": 1.4794178021912578, "learning_rate": 1.1313310571412175e-05, "loss": 0.4514, "num_tokens": 429101278.0, "step": 71970 }, { "epoch": 0.7678725742267931, "grad_norm": 1.4253902465912676, "learning_rate": 1.1310553962576404e-05, "loss": 0.477, "num_tokens": 429142022.0, "step": 71975 }, { "epoch": 0.7679259172329915, "grad_norm": 0.7802346095464404, "learning_rate": 1.1307797857522936e-05, "loss": 0.3757, "num_tokens": 429180728.0, "step": 71980 }, { "epoch": 0.76797926023919, "grad_norm": 1.3166957331023088, "learning_rate": 1.1305042256337543e-05, "loss": 0.499, "num_tokens": 429218928.0, "step": 71985 }, { "epoch": 0.7680326032453885, "grad_norm": 1.0322398596562967, "learning_rate": 1.1302287159105972e-05, "loss": 0.564, "num_tokens": 429262369.0, "step": 71990 }, { "epoch": 0.768085946251587, "grad_norm": 0.738671806406671, "learning_rate": 1.1299532565913944e-05, "loss": 0.3503, "num_tokens": 429292032.0, "step": 71995 }, { "epoch": 0.7681392892577854, "grad_norm": 1.6117877952082564, "learning_rate": 1.1296778476847187e-05, "loss": 0.4986, "num_tokens": 429329969.0, "step": 72000 }, { "epoch": 0.7681926322639838, "grad_norm": 0.8121348270128168, "learning_rate": 1.1294024891991411e-05, "loss": 0.47, "num_tokens": 429362604.0, "step": 72005 }, { "epoch": 0.7682459752701823, "grad_norm": 1.0002978250449182, "learning_rate": 1.1291271811432282e-05, "loss": 0.4456, "num_tokens": 429398515.0, "step": 72010 }, { "epoch": 0.7682993182763808, "grad_norm": 1.0544711781981586, "learning_rate": 1.1288519235255479e-05, "loss": 0.4219, "num_tokens": 429418303.0, "step": 72015 }, { "epoch": 0.7683526612825793, "grad_norm": 1.1453762829794785, "learning_rate": 1.1285767163546669e-05, "loss": 0.5248, "num_tokens": 429452318.0, "step": 72020 }, { "epoch": 0.7684060042887777, "grad_norm": 0.654351557149768, "learning_rate": 1.128301559639148e-05, "loss": 0.5347, "num_tokens": 429489704.0, "step": 72025 }, { "epoch": 0.7684593472949761, "grad_norm": 0.9124854467989498, "learning_rate": 1.1280264533875527e-05, "loss": 0.411, "num_tokens": 429524308.0, "step": 72030 }, { "epoch": 0.7685126903011746, "grad_norm": 0.9149701716338257, "learning_rate": 1.127751397608443e-05, "loss": 0.4357, "num_tokens": 429561051.0, "step": 72035 }, { "epoch": 0.768566033307373, "grad_norm": 1.0428911341020828, "learning_rate": 1.127476392310377e-05, "loss": 0.4538, "num_tokens": 429578777.0, "step": 72040 }, { "epoch": 0.7686193763135716, "grad_norm": 1.0303174893041513, "learning_rate": 1.1272014375019131e-05, "loss": 0.4647, "num_tokens": 429603618.0, "step": 72045 }, { "epoch": 0.76867271931977, "grad_norm": 0.9504170064225942, "learning_rate": 1.1269265331916076e-05, "loss": 0.5128, "num_tokens": 429645333.0, "step": 72050 }, { "epoch": 0.7687260623259684, "grad_norm": 1.3596270295900355, "learning_rate": 1.126651679388014e-05, "loss": 0.4922, "num_tokens": 429677410.0, "step": 72055 }, { "epoch": 0.7687794053321669, "grad_norm": 0.6767830048791513, "learning_rate": 1.1263768760996863e-05, "loss": 0.441, "num_tokens": 429722956.0, "step": 72060 }, { "epoch": 0.7688327483383653, "grad_norm": 0.9579920977638906, "learning_rate": 1.1261021233351753e-05, "loss": 0.4613, "num_tokens": 429750756.0, "step": 72065 }, { "epoch": 0.7688860913445638, "grad_norm": 0.6098746506170939, "learning_rate": 1.1258274211030298e-05, "loss": 0.4577, "num_tokens": 429784597.0, "step": 72070 }, { "epoch": 0.7689394343507623, "grad_norm": 0.9931391612288791, "learning_rate": 1.1255527694117989e-05, "loss": 0.6252, "num_tokens": 429813697.0, "step": 72075 }, { "epoch": 0.7689927773569607, "grad_norm": 0.5171094963016699, "learning_rate": 1.1252781682700297e-05, "loss": 0.609, "num_tokens": 429864097.0, "step": 72080 }, { "epoch": 0.7690461203631592, "grad_norm": 0.7034874164602831, "learning_rate": 1.1250036176862659e-05, "loss": 0.4763, "num_tokens": 429892540.0, "step": 72085 }, { "epoch": 0.7690994633693576, "grad_norm": 0.9117283517018814, "learning_rate": 1.1247291176690524e-05, "loss": 0.5775, "num_tokens": 429934844.0, "step": 72090 }, { "epoch": 0.769152806375556, "grad_norm": 0.8053836223703671, "learning_rate": 1.1244546682269306e-05, "loss": 0.4573, "num_tokens": 429959415.0, "step": 72095 }, { "epoch": 0.7692061493817546, "grad_norm": 1.3167073027870524, "learning_rate": 1.1241802693684397e-05, "loss": 0.4074, "num_tokens": 429980464.0, "step": 72100 }, { "epoch": 0.769259492387953, "grad_norm": 0.9540236820742527, "learning_rate": 1.1239059211021193e-05, "loss": 0.5256, "num_tokens": 430002658.0, "step": 72105 }, { "epoch": 0.7693128353941515, "grad_norm": 0.8946067419135769, "learning_rate": 1.1236316234365072e-05, "loss": 0.5005, "num_tokens": 430024999.0, "step": 72110 }, { "epoch": 0.7693661784003499, "grad_norm": 0.6573278286348605, "learning_rate": 1.1233573763801377e-05, "loss": 0.3517, "num_tokens": 430054677.0, "step": 72115 }, { "epoch": 0.7694195214065483, "grad_norm": 0.7054529817642565, "learning_rate": 1.1230831799415453e-05, "loss": 0.4224, "num_tokens": 430082445.0, "step": 72120 }, { "epoch": 0.7694728644127469, "grad_norm": 0.8554169919889733, "learning_rate": 1.1228090341292633e-05, "loss": 0.3799, "num_tokens": 430102113.0, "step": 72125 }, { "epoch": 0.7695262074189453, "grad_norm": 1.4251561533798793, "learning_rate": 1.122534938951822e-05, "loss": 0.4512, "num_tokens": 430121873.0, "step": 72130 }, { "epoch": 0.7695795504251438, "grad_norm": 0.8836703393830333, "learning_rate": 1.1222608944177496e-05, "loss": 0.4976, "num_tokens": 430150416.0, "step": 72135 }, { "epoch": 0.7696328934313422, "grad_norm": 0.7195442528943174, "learning_rate": 1.1219869005355755e-05, "loss": 0.4174, "num_tokens": 430178539.0, "step": 72140 }, { "epoch": 0.7696862364375406, "grad_norm": 0.7919264288992404, "learning_rate": 1.1217129573138241e-05, "loss": 0.3685, "num_tokens": 430213909.0, "step": 72145 }, { "epoch": 0.7697395794437392, "grad_norm": 0.585008218513133, "learning_rate": 1.1214390647610209e-05, "loss": 0.5038, "num_tokens": 430247157.0, "step": 72150 }, { "epoch": 0.7697929224499376, "grad_norm": 1.1458773879386812, "learning_rate": 1.12116522288569e-05, "loss": 0.4415, "num_tokens": 430270102.0, "step": 72155 }, { "epoch": 0.769846265456136, "grad_norm": 0.6031763897070158, "learning_rate": 1.1208914316963504e-05, "loss": 0.5894, "num_tokens": 430321709.0, "step": 72160 }, { "epoch": 0.7698996084623345, "grad_norm": 0.6036919183472266, "learning_rate": 1.1206176912015242e-05, "loss": 0.4317, "num_tokens": 430351014.0, "step": 72165 }, { "epoch": 0.7699529514685329, "grad_norm": 0.9485986636808185, "learning_rate": 1.1203440014097282e-05, "loss": 0.5557, "num_tokens": 430378628.0, "step": 72170 }, { "epoch": 0.7700062944747315, "grad_norm": 0.7929200623762639, "learning_rate": 1.1200703623294792e-05, "loss": 0.5149, "num_tokens": 430405648.0, "step": 72175 }, { "epoch": 0.7700596374809299, "grad_norm": 0.6066508463580171, "learning_rate": 1.1197967739692924e-05, "loss": 0.4283, "num_tokens": 430438882.0, "step": 72180 }, { "epoch": 0.7701129804871283, "grad_norm": 0.595257506169715, "learning_rate": 1.1195232363376823e-05, "loss": 0.3011, "num_tokens": 430463852.0, "step": 72185 }, { "epoch": 0.7701663234933268, "grad_norm": 2.376807607295113, "learning_rate": 1.1192497494431592e-05, "loss": 0.4901, "num_tokens": 430493640.0, "step": 72190 }, { "epoch": 0.7702196664995252, "grad_norm": 5.9744519960764535, "learning_rate": 1.118976313294234e-05, "loss": 0.4485, "num_tokens": 430513940.0, "step": 72195 }, { "epoch": 0.7702730095057237, "grad_norm": 0.7022524095423834, "learning_rate": 1.1187029278994168e-05, "loss": 0.4838, "num_tokens": 430545923.0, "step": 72200 }, { "epoch": 0.7703263525119222, "grad_norm": 0.8107937780431391, "learning_rate": 1.1184295932672134e-05, "loss": 0.5864, "num_tokens": 430583213.0, "step": 72205 }, { "epoch": 0.7703796955181206, "grad_norm": 1.2166682149040116, "learning_rate": 1.118156309406129e-05, "loss": 0.3982, "num_tokens": 430613166.0, "step": 72210 }, { "epoch": 0.7704330385243191, "grad_norm": 0.6880318692230192, "learning_rate": 1.1178830763246692e-05, "loss": 0.4655, "num_tokens": 430642589.0, "step": 72215 }, { "epoch": 0.7704863815305175, "grad_norm": 0.6391035421787548, "learning_rate": 1.1176098940313348e-05, "loss": 0.4876, "num_tokens": 430678418.0, "step": 72220 }, { "epoch": 0.770539724536716, "grad_norm": 0.7476105741858957, "learning_rate": 1.1173367625346277e-05, "loss": 0.5284, "num_tokens": 430725334.0, "step": 72225 }, { "epoch": 0.7705930675429145, "grad_norm": 1.1322139302487617, "learning_rate": 1.1170636818430474e-05, "loss": 0.4048, "num_tokens": 430751369.0, "step": 72230 }, { "epoch": 0.7706464105491129, "grad_norm": 1.4528156878003131, "learning_rate": 1.1167906519650907e-05, "loss": 0.499, "num_tokens": 430786491.0, "step": 72235 }, { "epoch": 0.7706997535553114, "grad_norm": 0.7023457060467477, "learning_rate": 1.1165176729092548e-05, "loss": 0.4422, "num_tokens": 430812616.0, "step": 72240 }, { "epoch": 0.7707530965615098, "grad_norm": 0.9478326020393155, "learning_rate": 1.1162447446840336e-05, "loss": 0.5117, "num_tokens": 430844643.0, "step": 72245 }, { "epoch": 0.7708064395677082, "grad_norm": 1.0446624148434818, "learning_rate": 1.1159718672979195e-05, "loss": 0.5255, "num_tokens": 430872764.0, "step": 72250 }, { "epoch": 0.7708597825739067, "grad_norm": 0.5868729656113686, "learning_rate": 1.1156990407594043e-05, "loss": 0.5028, "num_tokens": 430925291.0, "step": 72255 }, { "epoch": 0.7709131255801052, "grad_norm": 0.9108867891023683, "learning_rate": 1.1154262650769786e-05, "loss": 0.384, "num_tokens": 430949381.0, "step": 72260 }, { "epoch": 0.7709664685863037, "grad_norm": 1.0217966474410205, "learning_rate": 1.1151535402591298e-05, "loss": 0.4077, "num_tokens": 430972433.0, "step": 72265 }, { "epoch": 0.7710198115925021, "grad_norm": 0.8802105229149878, "learning_rate": 1.1148808663143446e-05, "loss": 0.345, "num_tokens": 430986250.0, "step": 72270 }, { "epoch": 0.7710731545987005, "grad_norm": 0.8279505143543544, "learning_rate": 1.1146082432511087e-05, "loss": 0.3469, "num_tokens": 431005175.0, "step": 72275 }, { "epoch": 0.771126497604899, "grad_norm": 0.7393964970319671, "learning_rate": 1.1143356710779052e-05, "loss": 0.5384, "num_tokens": 431045911.0, "step": 72280 }, { "epoch": 0.7711798406110975, "grad_norm": 0.7123810341079491, "learning_rate": 1.1140631498032152e-05, "loss": 0.4074, "num_tokens": 431083468.0, "step": 72285 }, { "epoch": 0.771233183617296, "grad_norm": 0.724169521551831, "learning_rate": 1.1137906794355205e-05, "loss": 0.4726, "num_tokens": 431118775.0, "step": 72290 }, { "epoch": 0.7712865266234944, "grad_norm": 1.2401784611802877, "learning_rate": 1.1135182599832982e-05, "loss": 0.5, "num_tokens": 431144514.0, "step": 72295 }, { "epoch": 0.7713398696296928, "grad_norm": 0.7174700221475893, "learning_rate": 1.113245891455026e-05, "loss": 0.5035, "num_tokens": 431179650.0, "step": 72300 }, { "epoch": 0.7713932126358913, "grad_norm": 0.9158936350726997, "learning_rate": 1.1129735738591807e-05, "loss": 0.4669, "num_tokens": 431203475.0, "step": 72305 }, { "epoch": 0.7714465556420897, "grad_norm": 0.8442298695989445, "learning_rate": 1.1127013072042342e-05, "loss": 0.4688, "num_tokens": 431224923.0, "step": 72310 }, { "epoch": 0.7714998986482883, "grad_norm": 1.187426201889923, "learning_rate": 1.1124290914986606e-05, "loss": 0.4908, "num_tokens": 431247922.0, "step": 72315 }, { "epoch": 0.7715532416544867, "grad_norm": 0.6396068274586366, "learning_rate": 1.1121569267509302e-05, "loss": 0.4619, "num_tokens": 431288378.0, "step": 72320 }, { "epoch": 0.7716065846606851, "grad_norm": 0.7444383139879567, "learning_rate": 1.1118848129695112e-05, "loss": 0.5349, "num_tokens": 431308419.0, "step": 72325 }, { "epoch": 0.7716599276668836, "grad_norm": 0.8647206834374371, "learning_rate": 1.1116127501628723e-05, "loss": 0.4281, "num_tokens": 431331561.0, "step": 72330 }, { "epoch": 0.771713270673082, "grad_norm": 0.677949360048008, "learning_rate": 1.1113407383394798e-05, "loss": 0.4319, "num_tokens": 431378297.0, "step": 72335 }, { "epoch": 0.7717666136792805, "grad_norm": 0.636869683737109, "learning_rate": 1.1110687775077969e-05, "loss": 0.4126, "num_tokens": 431410280.0, "step": 72340 }, { "epoch": 0.771819956685479, "grad_norm": 0.8461760216797327, "learning_rate": 1.110796867676287e-05, "loss": 0.3823, "num_tokens": 431440979.0, "step": 72345 }, { "epoch": 0.7718732996916774, "grad_norm": 1.267555054898832, "learning_rate": 1.1105250088534128e-05, "loss": 0.3994, "num_tokens": 431458357.0, "step": 72350 }, { "epoch": 0.7719266426978759, "grad_norm": 0.7906132351597156, "learning_rate": 1.1102532010476322e-05, "loss": 0.4094, "num_tokens": 431472143.0, "step": 72355 }, { "epoch": 0.7719799857040743, "grad_norm": 0.789385082779821, "learning_rate": 1.1099814442674033e-05, "loss": 0.435, "num_tokens": 431493275.0, "step": 72360 }, { "epoch": 0.7720333287102727, "grad_norm": 1.0811377278566279, "learning_rate": 1.109709738521184e-05, "loss": 0.488, "num_tokens": 431526570.0, "step": 72365 }, { "epoch": 0.7720866717164713, "grad_norm": 0.8193324298823977, "learning_rate": 1.1094380838174276e-05, "loss": 0.4664, "num_tokens": 431554183.0, "step": 72370 }, { "epoch": 0.7721400147226697, "grad_norm": 0.8865069079195604, "learning_rate": 1.1091664801645882e-05, "loss": 0.5472, "num_tokens": 431600462.0, "step": 72375 }, { "epoch": 0.7721933577288682, "grad_norm": 2.2620635750872156, "learning_rate": 1.1088949275711182e-05, "loss": 0.4849, "num_tokens": 431618405.0, "step": 72380 }, { "epoch": 0.7722467007350666, "grad_norm": 1.0403629764091316, "learning_rate": 1.1086234260454673e-05, "loss": 0.4163, "num_tokens": 431637984.0, "step": 72385 }, { "epoch": 0.772300043741265, "grad_norm": 0.7961563929504056, "learning_rate": 1.1083519755960829e-05, "loss": 0.5145, "num_tokens": 431679365.0, "step": 72390 }, { "epoch": 0.7723533867474636, "grad_norm": 0.913629171756033, "learning_rate": 1.108080576231414e-05, "loss": 0.527, "num_tokens": 431702156.0, "step": 72395 }, { "epoch": 0.772406729753662, "grad_norm": 1.014146219698355, "learning_rate": 1.1078092279599042e-05, "loss": 0.5133, "num_tokens": 431741961.0, "step": 72400 }, { "epoch": 0.7724600727598605, "grad_norm": 0.9196180482284284, "learning_rate": 1.107537930789998e-05, "loss": 0.5655, "num_tokens": 431778324.0, "step": 72405 }, { "epoch": 0.7725134157660589, "grad_norm": 0.9232941122596053, "learning_rate": 1.1072666847301386e-05, "loss": 0.5432, "num_tokens": 431804984.0, "step": 72410 }, { "epoch": 0.7725667587722573, "grad_norm": 0.8619917790231745, "learning_rate": 1.1069954897887647e-05, "loss": 0.355, "num_tokens": 431827991.0, "step": 72415 }, { "epoch": 0.7726201017784559, "grad_norm": 0.9002615321021187, "learning_rate": 1.1067243459743169e-05, "loss": 0.4386, "num_tokens": 431852935.0, "step": 72420 }, { "epoch": 0.7726734447846543, "grad_norm": 0.9106391946727392, "learning_rate": 1.1064532532952324e-05, "loss": 0.4102, "num_tokens": 431891928.0, "step": 72425 }, { "epoch": 0.7727267877908527, "grad_norm": 1.3521044805836757, "learning_rate": 1.106182211759946e-05, "loss": 0.4476, "num_tokens": 431909362.0, "step": 72430 }, { "epoch": 0.7727801307970512, "grad_norm": 0.7987411760911307, "learning_rate": 1.1059112213768927e-05, "loss": 0.4391, "num_tokens": 431935123.0, "step": 72435 }, { "epoch": 0.7728334738032496, "grad_norm": 1.4085485107655453, "learning_rate": 1.1056402821545055e-05, "loss": 0.5519, "num_tokens": 431968225.0, "step": 72440 }, { "epoch": 0.7728868168094482, "grad_norm": 0.646317363931661, "learning_rate": 1.1053693941012147e-05, "loss": 0.4382, "num_tokens": 432010135.0, "step": 72445 }, { "epoch": 0.7729401598156466, "grad_norm": 1.0857999682947372, "learning_rate": 1.10509855722545e-05, "loss": 0.4902, "num_tokens": 432036762.0, "step": 72450 }, { "epoch": 0.772993502821845, "grad_norm": 0.9372950149597067, "learning_rate": 1.1048277715356403e-05, "loss": 0.5645, "num_tokens": 432075538.0, "step": 72455 }, { "epoch": 0.7730468458280435, "grad_norm": 1.0226037890757425, "learning_rate": 1.1045570370402112e-05, "loss": 0.5259, "num_tokens": 432092281.0, "step": 72460 }, { "epoch": 0.7731001888342419, "grad_norm": 0.5973962957457671, "learning_rate": 1.1042863537475864e-05, "loss": 0.511, "num_tokens": 432136485.0, "step": 72465 }, { "epoch": 0.7731535318404404, "grad_norm": 0.7185552552181378, "learning_rate": 1.1040157216661906e-05, "loss": 0.4627, "num_tokens": 432170537.0, "step": 72470 }, { "epoch": 0.7732068748466389, "grad_norm": 0.9647188390286724, "learning_rate": 1.103745140804444e-05, "loss": 0.5911, "num_tokens": 432199062.0, "step": 72475 }, { "epoch": 0.7732602178528373, "grad_norm": 0.9693299239243556, "learning_rate": 1.103474611170767e-05, "loss": 0.6064, "num_tokens": 432223616.0, "step": 72480 }, { "epoch": 0.7733135608590358, "grad_norm": 1.1717396052745463, "learning_rate": 1.1032041327735786e-05, "loss": 0.4837, "num_tokens": 432255875.0, "step": 72485 }, { "epoch": 0.7733669038652342, "grad_norm": 1.0252853020510122, "learning_rate": 1.1029337056212944e-05, "loss": 0.5282, "num_tokens": 432290015.0, "step": 72490 }, { "epoch": 0.7734202468714327, "grad_norm": 1.8770080488174894, "learning_rate": 1.102663329722331e-05, "loss": 0.5267, "num_tokens": 432317062.0, "step": 72495 }, { "epoch": 0.7734735898776312, "grad_norm": 0.9724953928632045, "learning_rate": 1.1023930050851008e-05, "loss": 0.4633, "num_tokens": 432351694.0, "step": 72500 }, { "epoch": 0.7735269328838296, "grad_norm": 1.6014824701010935, "learning_rate": 1.1021227317180155e-05, "loss": 0.4399, "num_tokens": 432381893.0, "step": 72505 }, { "epoch": 0.7735802758900281, "grad_norm": 1.253315269427529, "learning_rate": 1.1018525096294857e-05, "loss": 0.4776, "num_tokens": 432410873.0, "step": 72510 }, { "epoch": 0.7736336188962265, "grad_norm": 0.6781141895392528, "learning_rate": 1.1015823388279215e-05, "loss": 0.4533, "num_tokens": 432449817.0, "step": 72515 }, { "epoch": 0.7736869619024249, "grad_norm": 1.0614849203595298, "learning_rate": 1.1013122193217278e-05, "loss": 0.4723, "num_tokens": 432481649.0, "step": 72520 }, { "epoch": 0.7737403049086234, "grad_norm": 1.2602168994662817, "learning_rate": 1.1010421511193116e-05, "loss": 0.6248, "num_tokens": 432531068.0, "step": 72525 }, { "epoch": 0.7737936479148219, "grad_norm": 0.724753328844374, "learning_rate": 1.1007721342290771e-05, "loss": 0.4192, "num_tokens": 432559736.0, "step": 72530 }, { "epoch": 0.7738469909210204, "grad_norm": 1.0592653482815062, "learning_rate": 1.1005021686594266e-05, "loss": 0.4585, "num_tokens": 432578985.0, "step": 72535 }, { "epoch": 0.7739003339272188, "grad_norm": 0.8752544383940963, "learning_rate": 1.1002322544187593e-05, "loss": 0.4812, "num_tokens": 432613278.0, "step": 72540 }, { "epoch": 0.7739536769334172, "grad_norm": 0.7719674943652549, "learning_rate": 1.0999623915154766e-05, "loss": 0.4013, "num_tokens": 432634981.0, "step": 72545 }, { "epoch": 0.7740070199396157, "grad_norm": 1.719635598068204, "learning_rate": 1.0996925799579739e-05, "loss": 0.4072, "num_tokens": 432688106.0, "step": 72550 }, { "epoch": 0.7740603629458142, "grad_norm": 1.1843989423082733, "learning_rate": 1.0994228197546486e-05, "loss": 0.4301, "num_tokens": 432711276.0, "step": 72555 }, { "epoch": 0.7741137059520127, "grad_norm": 2.873686332428164, "learning_rate": 1.0991531109138953e-05, "loss": 0.7565, "num_tokens": 432737984.0, "step": 72560 }, { "epoch": 0.7741670489582111, "grad_norm": 0.7718361053497189, "learning_rate": 1.098883453444106e-05, "loss": 0.4182, "num_tokens": 432775222.0, "step": 72565 }, { "epoch": 0.7742203919644095, "grad_norm": 0.6905737167241552, "learning_rate": 1.0986138473536719e-05, "loss": 0.4546, "num_tokens": 432811631.0, "step": 72570 }, { "epoch": 0.774273734970608, "grad_norm": 0.8261293123508027, "learning_rate": 1.0983442926509834e-05, "loss": 0.5152, "num_tokens": 432828990.0, "step": 72575 }, { "epoch": 0.7743270779768064, "grad_norm": 1.521926579128242, "learning_rate": 1.0980747893444274e-05, "loss": 0.4872, "num_tokens": 432854784.0, "step": 72580 }, { "epoch": 0.774380420983005, "grad_norm": 2.4301891599318814, "learning_rate": 1.0978053374423905e-05, "loss": 0.6106, "num_tokens": 432878466.0, "step": 72585 }, { "epoch": 0.7744337639892034, "grad_norm": 0.8794406850366534, "learning_rate": 1.0975359369532585e-05, "loss": 0.463, "num_tokens": 432908863.0, "step": 72590 }, { "epoch": 0.7744871069954018, "grad_norm": 0.9675662906367382, "learning_rate": 1.0972665878854135e-05, "loss": 0.4828, "num_tokens": 432935732.0, "step": 72595 }, { "epoch": 0.7745404500016003, "grad_norm": 1.1050911457670438, "learning_rate": 1.0969972902472372e-05, "loss": 0.5061, "num_tokens": 432957575.0, "step": 72600 }, { "epoch": 0.7745937930077987, "grad_norm": 0.744192629200101, "learning_rate": 1.0967280440471106e-05, "loss": 0.4764, "num_tokens": 432991963.0, "step": 72605 }, { "epoch": 0.7746471360139972, "grad_norm": 1.517900143623031, "learning_rate": 1.0964588492934112e-05, "loss": 0.5777, "num_tokens": 433024724.0, "step": 72610 }, { "epoch": 0.7747004790201957, "grad_norm": 0.7585230098935107, "learning_rate": 1.0961897059945156e-05, "loss": 0.455, "num_tokens": 433053701.0, "step": 72615 }, { "epoch": 0.7747538220263941, "grad_norm": 2.075309342765069, "learning_rate": 1.0959206141587998e-05, "loss": 0.5014, "num_tokens": 433089663.0, "step": 72620 }, { "epoch": 0.7748071650325926, "grad_norm": 1.0963809815543797, "learning_rate": 1.095651573794636e-05, "loss": 0.3843, "num_tokens": 433112391.0, "step": 72625 }, { "epoch": 0.774860508038791, "grad_norm": 1.0044773252477717, "learning_rate": 1.0953825849103973e-05, "loss": 0.5031, "num_tokens": 433150214.0, "step": 72630 }, { "epoch": 0.7749138510449894, "grad_norm": 0.7208775483715751, "learning_rate": 1.0951136475144547e-05, "loss": 0.3596, "num_tokens": 433191798.0, "step": 72635 }, { "epoch": 0.774967194051188, "grad_norm": 1.2313504450199995, "learning_rate": 1.0948447616151754e-05, "loss": 0.4826, "num_tokens": 433213317.0, "step": 72640 }, { "epoch": 0.7750205370573864, "grad_norm": 0.7805644006787615, "learning_rate": 1.094575927220928e-05, "loss": 0.4587, "num_tokens": 433234013.0, "step": 72645 }, { "epoch": 0.7750738800635849, "grad_norm": 1.0585065769869255, "learning_rate": 1.0943071443400773e-05, "loss": 0.483, "num_tokens": 433274813.0, "step": 72650 }, { "epoch": 0.7751272230697833, "grad_norm": 0.5508422357375738, "learning_rate": 1.0940384129809868e-05, "loss": 0.457, "num_tokens": 433315486.0, "step": 72655 }, { "epoch": 0.7751805660759817, "grad_norm": 0.9052433409291234, "learning_rate": 1.0937697331520193e-05, "loss": 0.5315, "num_tokens": 433351921.0, "step": 72660 }, { "epoch": 0.7752339090821803, "grad_norm": 1.0277852471884845, "learning_rate": 1.0935011048615366e-05, "loss": 0.5089, "num_tokens": 433374132.0, "step": 72665 }, { "epoch": 0.7752872520883787, "grad_norm": 0.7280746029142603, "learning_rate": 1.0932325281178964e-05, "loss": 0.3628, "num_tokens": 433405011.0, "step": 72670 }, { "epoch": 0.7753405950945772, "grad_norm": 1.0085238267959873, "learning_rate": 1.0929640029294564e-05, "loss": 0.4754, "num_tokens": 433428527.0, "step": 72675 }, { "epoch": 0.7753939381007756, "grad_norm": 1.4501129143198446, "learning_rate": 1.092695529304574e-05, "loss": 0.578, "num_tokens": 433456371.0, "step": 72680 }, { "epoch": 0.775447281106974, "grad_norm": 0.9664552698532713, "learning_rate": 1.0924271072516024e-05, "loss": 0.399, "num_tokens": 433473010.0, "step": 72685 }, { "epoch": 0.7755006241131726, "grad_norm": 1.3274904101230616, "learning_rate": 1.0921587367788938e-05, "loss": 0.549, "num_tokens": 433493493.0, "step": 72690 }, { "epoch": 0.775553967119371, "grad_norm": 0.6444452751481198, "learning_rate": 1.0918904178948008e-05, "loss": 0.5158, "num_tokens": 433526877.0, "step": 72695 }, { "epoch": 0.7756073101255694, "grad_norm": 1.4497898044799014, "learning_rate": 1.0916221506076712e-05, "loss": 0.5665, "num_tokens": 433582284.0, "step": 72700 }, { "epoch": 0.7756606531317679, "grad_norm": 1.4466404875699814, "learning_rate": 1.0913539349258542e-05, "loss": 0.5353, "num_tokens": 433599804.0, "step": 72705 }, { "epoch": 0.7757139961379663, "grad_norm": 1.4301779278035918, "learning_rate": 1.0910857708576962e-05, "loss": 0.576, "num_tokens": 433620407.0, "step": 72710 }, { "epoch": 0.7757673391441648, "grad_norm": 1.3507169244898067, "learning_rate": 1.0908176584115416e-05, "loss": 0.4898, "num_tokens": 433638831.0, "step": 72715 }, { "epoch": 0.7758206821503633, "grad_norm": 0.6054184083483609, "learning_rate": 1.0905495975957327e-05, "loss": 0.5413, "num_tokens": 433695672.0, "step": 72720 }, { "epoch": 0.7758740251565617, "grad_norm": 0.5360729741063872, "learning_rate": 1.0902815884186124e-05, "loss": 0.4921, "num_tokens": 433746742.0, "step": 72725 }, { "epoch": 0.7759273681627602, "grad_norm": 1.2073126933308043, "learning_rate": 1.0900136308885192e-05, "loss": 0.4846, "num_tokens": 433761613.0, "step": 72730 }, { "epoch": 0.7759807111689586, "grad_norm": 1.0150155322482437, "learning_rate": 1.089745725013792e-05, "loss": 0.5164, "num_tokens": 433794960.0, "step": 72735 }, { "epoch": 0.7760340541751571, "grad_norm": 1.0138649120962244, "learning_rate": 1.0894778708027686e-05, "loss": 0.3921, "num_tokens": 433824028.0, "step": 72740 }, { "epoch": 0.7760873971813556, "grad_norm": 0.9120510875018906, "learning_rate": 1.0892100682637823e-05, "loss": 0.5284, "num_tokens": 433861751.0, "step": 72745 }, { "epoch": 0.776140740187554, "grad_norm": 1.929007886234718, "learning_rate": 1.088942317405168e-05, "loss": 0.5444, "num_tokens": 433893810.0, "step": 72750 }, { "epoch": 0.7761940831937525, "grad_norm": 0.8864257342688922, "learning_rate": 1.0886746182352568e-05, "loss": 0.5423, "num_tokens": 433934363.0, "step": 72755 }, { "epoch": 0.7762474261999509, "grad_norm": 1.9111110214331863, "learning_rate": 1.088406970762378e-05, "loss": 0.5584, "num_tokens": 433964232.0, "step": 72760 }, { "epoch": 0.7763007692061494, "grad_norm": 0.9749752610518861, "learning_rate": 1.0881393749948616e-05, "loss": 0.4229, "num_tokens": 433991497.0, "step": 72765 }, { "epoch": 0.7763541122123478, "grad_norm": 0.7536237154555656, "learning_rate": 1.0878718309410348e-05, "loss": 0.4736, "num_tokens": 434022130.0, "step": 72770 }, { "epoch": 0.7764074552185463, "grad_norm": 1.4126807781927118, "learning_rate": 1.087604338609222e-05, "loss": 0.4443, "num_tokens": 434054921.0, "step": 72775 }, { "epoch": 0.7764607982247448, "grad_norm": 0.9036253304908012, "learning_rate": 1.0873368980077477e-05, "loss": 0.4138, "num_tokens": 434092820.0, "step": 72780 }, { "epoch": 0.7765141412309432, "grad_norm": 0.6684500863876855, "learning_rate": 1.0870695091449343e-05, "loss": 0.4438, "num_tokens": 434128721.0, "step": 72785 }, { "epoch": 0.7765674842371416, "grad_norm": 0.7177316696922579, "learning_rate": 1.0868021720291018e-05, "loss": 0.4979, "num_tokens": 434157869.0, "step": 72790 }, { "epoch": 0.7766208272433401, "grad_norm": 0.6230126221546788, "learning_rate": 1.0865348866685693e-05, "loss": 0.3452, "num_tokens": 434187362.0, "step": 72795 }, { "epoch": 0.7766741702495386, "grad_norm": 0.5385942971608547, "learning_rate": 1.0862676530716548e-05, "loss": 0.3993, "num_tokens": 434212981.0, "step": 72800 }, { "epoch": 0.7767275132557371, "grad_norm": 1.1417510207708466, "learning_rate": 1.0860004712466726e-05, "loss": 0.497, "num_tokens": 434240632.0, "step": 72805 }, { "epoch": 0.7767808562619355, "grad_norm": 0.9468220315391875, "learning_rate": 1.0857333412019379e-05, "loss": 0.579, "num_tokens": 434259724.0, "step": 72810 }, { "epoch": 0.7768341992681339, "grad_norm": 1.4732816435427405, "learning_rate": 1.085466262945764e-05, "loss": 0.4857, "num_tokens": 434279086.0, "step": 72815 }, { "epoch": 0.7768875422743324, "grad_norm": 0.5618304628458799, "learning_rate": 1.0851992364864597e-05, "loss": 0.4513, "num_tokens": 434315377.0, "step": 72820 }, { "epoch": 0.7769408852805308, "grad_norm": 0.8805229704594839, "learning_rate": 1.0849322618323369e-05, "loss": 0.5381, "num_tokens": 434344142.0, "step": 72825 }, { "epoch": 0.7769942282867294, "grad_norm": 0.6819162674876831, "learning_rate": 1.0846653389917017e-05, "loss": 0.5494, "num_tokens": 434368472.0, "step": 72830 }, { "epoch": 0.7770475712929278, "grad_norm": 0.8527100833350446, "learning_rate": 1.0843984679728595e-05, "loss": 0.4237, "num_tokens": 434393506.0, "step": 72835 }, { "epoch": 0.7771009142991262, "grad_norm": 1.1800830766935537, "learning_rate": 1.084131648784116e-05, "loss": 0.4947, "num_tokens": 434410418.0, "step": 72840 }, { "epoch": 0.7771542573053247, "grad_norm": 1.4542718891072444, "learning_rate": 1.0838648814337746e-05, "loss": 0.3933, "num_tokens": 434427609.0, "step": 72845 }, { "epoch": 0.7772076003115231, "grad_norm": 4.1766176488266105, "learning_rate": 1.083598165930135e-05, "loss": 0.3526, "num_tokens": 434448279.0, "step": 72850 }, { "epoch": 0.7772609433177217, "grad_norm": 0.8300264437845161, "learning_rate": 1.0833315022814974e-05, "loss": 0.4507, "num_tokens": 434485751.0, "step": 72855 }, { "epoch": 0.7773142863239201, "grad_norm": 0.7520879122547162, "learning_rate": 1.083064890496161e-05, "loss": 0.4375, "num_tokens": 434506713.0, "step": 72860 }, { "epoch": 0.7773676293301185, "grad_norm": 1.285413106777611, "learning_rate": 1.082798330582421e-05, "loss": 0.5196, "num_tokens": 434536881.0, "step": 72865 }, { "epoch": 0.777420972336317, "grad_norm": 0.7402337602900892, "learning_rate": 1.0825318225485717e-05, "loss": 0.3996, "num_tokens": 434565307.0, "step": 72870 }, { "epoch": 0.7774743153425154, "grad_norm": 0.807869055975519, "learning_rate": 1.0822653664029072e-05, "loss": 0.4824, "num_tokens": 434602671.0, "step": 72875 }, { "epoch": 0.7775276583487138, "grad_norm": 0.734496113496758, "learning_rate": 1.0819989621537194e-05, "loss": 0.3749, "num_tokens": 434629112.0, "step": 72880 }, { "epoch": 0.7775810013549124, "grad_norm": 0.992441075678385, "learning_rate": 1.0817326098092971e-05, "loss": 0.4109, "num_tokens": 434648513.0, "step": 72885 }, { "epoch": 0.7776343443611108, "grad_norm": 0.9745014624768374, "learning_rate": 1.0814663093779292e-05, "loss": 0.3999, "num_tokens": 434673081.0, "step": 72890 }, { "epoch": 0.7776876873673093, "grad_norm": 0.6768898610129034, "learning_rate": 1.0812000608679032e-05, "loss": 0.4379, "num_tokens": 434708663.0, "step": 72895 }, { "epoch": 0.7777410303735077, "grad_norm": 1.021261685266794, "learning_rate": 1.0809338642875033e-05, "loss": 0.4641, "num_tokens": 434734167.0, "step": 72900 }, { "epoch": 0.7777943733797061, "grad_norm": 1.3024197257106185, "learning_rate": 1.080667719645013e-05, "loss": 0.4321, "num_tokens": 434771969.0, "step": 72905 }, { "epoch": 0.7778477163859047, "grad_norm": 0.7143995577339459, "learning_rate": 1.0804016269487146e-05, "loss": 0.4108, "num_tokens": 434800857.0, "step": 72910 }, { "epoch": 0.7779010593921031, "grad_norm": 0.8384016936726861, "learning_rate": 1.0801355862068876e-05, "loss": 0.5009, "num_tokens": 434818810.0, "step": 72915 }, { "epoch": 0.7779544023983016, "grad_norm": 1.736245245751307, "learning_rate": 1.0798695974278111e-05, "loss": 0.4392, "num_tokens": 434838502.0, "step": 72920 }, { "epoch": 0.7780077454045, "grad_norm": 0.90611917284043, "learning_rate": 1.079603660619763e-05, "loss": 0.5062, "num_tokens": 434876304.0, "step": 72925 }, { "epoch": 0.7780610884106984, "grad_norm": 0.6897557190593304, "learning_rate": 1.0793377757910173e-05, "loss": 0.4875, "num_tokens": 434903046.0, "step": 72930 }, { "epoch": 0.778114431416897, "grad_norm": 2.276233641533388, "learning_rate": 1.0790719429498486e-05, "loss": 0.5706, "num_tokens": 434943171.0, "step": 72935 }, { "epoch": 0.7781677744230954, "grad_norm": 0.8872886111617677, "learning_rate": 1.0788061621045293e-05, "loss": 0.3824, "num_tokens": 434967971.0, "step": 72940 }, { "epoch": 0.7782211174292939, "grad_norm": 0.8749598900703685, "learning_rate": 1.0785404332633287e-05, "loss": 0.4499, "num_tokens": 434997744.0, "step": 72945 }, { "epoch": 0.7782744604354923, "grad_norm": 0.7922673991685127, "learning_rate": 1.0782747564345165e-05, "loss": 0.5505, "num_tokens": 435028512.0, "step": 72950 }, { "epoch": 0.7783278034416907, "grad_norm": 0.7672499781779082, "learning_rate": 1.0780091316263604e-05, "loss": 0.4407, "num_tokens": 435055313.0, "step": 72955 }, { "epoch": 0.7783811464478892, "grad_norm": 1.100941675716557, "learning_rate": 1.0777435588471258e-05, "loss": 0.5692, "num_tokens": 435077995.0, "step": 72960 }, { "epoch": 0.7784344894540877, "grad_norm": 3.3869496839710105, "learning_rate": 1.0774780381050762e-05, "loss": 0.4382, "num_tokens": 435098701.0, "step": 72965 }, { "epoch": 0.7784878324602861, "grad_norm": 0.9294802970905006, "learning_rate": 1.0772125694084757e-05, "loss": 0.4205, "num_tokens": 435117068.0, "step": 72970 }, { "epoch": 0.7785411754664846, "grad_norm": 0.8563655142853998, "learning_rate": 1.0769471527655835e-05, "loss": 0.4772, "num_tokens": 435162264.0, "step": 72975 }, { "epoch": 0.778594518472683, "grad_norm": 0.8662679249126599, "learning_rate": 1.0766817881846589e-05, "loss": 0.5575, "num_tokens": 435204305.0, "step": 72980 }, { "epoch": 0.7786478614788815, "grad_norm": 0.6735922008232401, "learning_rate": 1.0764164756739605e-05, "loss": 0.5009, "num_tokens": 435246022.0, "step": 72985 }, { "epoch": 0.77870120448508, "grad_norm": 1.0540461012989526, "learning_rate": 1.0761512152417432e-05, "loss": 0.4306, "num_tokens": 435287458.0, "step": 72990 }, { "epoch": 0.7787545474912784, "grad_norm": 1.0114563349128378, "learning_rate": 1.0758860068962622e-05, "loss": 0.5219, "num_tokens": 435326258.0, "step": 72995 }, { "epoch": 0.7788078904974769, "grad_norm": 0.6763166142795416, "learning_rate": 1.0756208506457702e-05, "loss": 0.5138, "num_tokens": 435370292.0, "step": 73000 }, { "epoch": 0.7788612335036753, "grad_norm": 1.0958154985520066, "learning_rate": 1.0753557464985185e-05, "loss": 0.4227, "num_tokens": 435394272.0, "step": 73005 }, { "epoch": 0.7789145765098738, "grad_norm": 0.810867996330097, "learning_rate": 1.0750906944627549e-05, "loss": 0.4232, "num_tokens": 435423526.0, "step": 73010 }, { "epoch": 0.7789679195160722, "grad_norm": 0.9567924664166672, "learning_rate": 1.0748256945467295e-05, "loss": 0.4121, "num_tokens": 435439032.0, "step": 73015 }, { "epoch": 0.7790212625222707, "grad_norm": 0.7252278033008918, "learning_rate": 1.0745607467586868e-05, "loss": 0.417, "num_tokens": 435475713.0, "step": 73020 }, { "epoch": 0.7790746055284692, "grad_norm": 0.7890752827461057, "learning_rate": 1.0742958511068723e-05, "loss": 0.4205, "num_tokens": 435495224.0, "step": 73025 }, { "epoch": 0.7791279485346676, "grad_norm": 0.8248319896106288, "learning_rate": 1.0740310075995296e-05, "loss": 0.4424, "num_tokens": 435539034.0, "step": 73030 }, { "epoch": 0.7791812915408661, "grad_norm": 0.7831799551188187, "learning_rate": 1.0737662162448988e-05, "loss": 0.4459, "num_tokens": 435564606.0, "step": 73035 }, { "epoch": 0.7792346345470645, "grad_norm": 0.9982370393574208, "learning_rate": 1.0735014770512209e-05, "loss": 0.4738, "num_tokens": 435592831.0, "step": 73040 }, { "epoch": 0.779287977553263, "grad_norm": 0.9022308594518661, "learning_rate": 1.0732367900267334e-05, "loss": 0.4702, "num_tokens": 435622075.0, "step": 73045 }, { "epoch": 0.7793413205594615, "grad_norm": 0.6301778445957371, "learning_rate": 1.072972155179672e-05, "loss": 0.4962, "num_tokens": 435651373.0, "step": 73050 }, { "epoch": 0.7793946635656599, "grad_norm": 0.6575924129205909, "learning_rate": 1.0727075725182727e-05, "loss": 0.4943, "num_tokens": 435680588.0, "step": 73055 }, { "epoch": 0.7794480065718583, "grad_norm": 0.9540258357462145, "learning_rate": 1.072443042050769e-05, "loss": 0.4373, "num_tokens": 435698031.0, "step": 73060 }, { "epoch": 0.7795013495780568, "grad_norm": 0.7315398043695546, "learning_rate": 1.0721785637853912e-05, "loss": 0.4962, "num_tokens": 435747506.0, "step": 73065 }, { "epoch": 0.7795546925842552, "grad_norm": 1.4826084869240033, "learning_rate": 1.0719141377303704e-05, "loss": 0.4713, "num_tokens": 435766189.0, "step": 73070 }, { "epoch": 0.7796080355904538, "grad_norm": 0.7485755238426297, "learning_rate": 1.0716497638939351e-05, "loss": 0.4876, "num_tokens": 435804181.0, "step": 73075 }, { "epoch": 0.7796613785966522, "grad_norm": 1.0681253644030269, "learning_rate": 1.071385442284312e-05, "loss": 0.5068, "num_tokens": 435834305.0, "step": 73080 }, { "epoch": 0.7797147216028506, "grad_norm": 1.0719223290359232, "learning_rate": 1.0711211729097252e-05, "loss": 0.4746, "num_tokens": 435868704.0, "step": 73085 }, { "epoch": 0.7797680646090491, "grad_norm": 0.9541700857021512, "learning_rate": 1.0708569557783999e-05, "loss": 0.6922, "num_tokens": 435897637.0, "step": 73090 }, { "epoch": 0.7798214076152475, "grad_norm": 0.8308832117604787, "learning_rate": 1.0705927908985561e-05, "loss": 0.4512, "num_tokens": 435926488.0, "step": 73095 }, { "epoch": 0.7798747506214461, "grad_norm": 1.253695233172582, "learning_rate": 1.070328678278415e-05, "loss": 0.533, "num_tokens": 435949466.0, "step": 73100 }, { "epoch": 0.7799280936276445, "grad_norm": 1.0450027781582543, "learning_rate": 1.0700646179261961e-05, "loss": 0.4305, "num_tokens": 435971096.0, "step": 73105 }, { "epoch": 0.7799814366338429, "grad_norm": 0.8235095177170726, "learning_rate": 1.0698006098501151e-05, "loss": 0.578, "num_tokens": 436014225.0, "step": 73110 }, { "epoch": 0.7800347796400414, "grad_norm": 0.9945851175788565, "learning_rate": 1.0695366540583882e-05, "loss": 0.5073, "num_tokens": 436045701.0, "step": 73115 }, { "epoch": 0.7800881226462398, "grad_norm": 1.4755597152000088, "learning_rate": 1.0692727505592291e-05, "loss": 0.4803, "num_tokens": 436086222.0, "step": 73120 }, { "epoch": 0.7801414656524384, "grad_norm": 1.0062660215108084, "learning_rate": 1.0690088993608489e-05, "loss": 0.4635, "num_tokens": 436111981.0, "step": 73125 }, { "epoch": 0.7801948086586368, "grad_norm": 2.150744912296338, "learning_rate": 1.068745100471459e-05, "loss": 0.4412, "num_tokens": 436155725.0, "step": 73130 }, { "epoch": 0.7802481516648352, "grad_norm": 0.8077920203667667, "learning_rate": 1.0684813538992689e-05, "loss": 0.4348, "num_tokens": 436181962.0, "step": 73135 }, { "epoch": 0.7803014946710337, "grad_norm": 0.43668547946794156, "learning_rate": 1.0682176596524842e-05, "loss": 0.3469, "num_tokens": 436225501.0, "step": 73140 }, { "epoch": 0.7803548376772321, "grad_norm": 1.0675524044630593, "learning_rate": 1.0679540177393119e-05, "loss": 0.4697, "num_tokens": 436269827.0, "step": 73145 }, { "epoch": 0.7804081806834305, "grad_norm": 2.0609299687016667, "learning_rate": 1.0676904281679557e-05, "loss": 0.4428, "num_tokens": 436286687.0, "step": 73150 }, { "epoch": 0.7804615236896291, "grad_norm": 0.7434805949885901, "learning_rate": 1.0674268909466182e-05, "loss": 0.426, "num_tokens": 436313039.0, "step": 73155 }, { "epoch": 0.7805148666958275, "grad_norm": 1.3007607498174139, "learning_rate": 1.067163406083499e-05, "loss": 0.4892, "num_tokens": 436352309.0, "step": 73160 }, { "epoch": 0.780568209702026, "grad_norm": 0.8047692991069357, "learning_rate": 1.0668999735867982e-05, "loss": 0.548, "num_tokens": 436373940.0, "step": 73165 }, { "epoch": 0.7806215527082244, "grad_norm": 0.8496852628886484, "learning_rate": 1.066636593464713e-05, "loss": 0.617, "num_tokens": 436401465.0, "step": 73170 }, { "epoch": 0.7806748957144228, "grad_norm": 0.8961731685603335, "learning_rate": 1.066373265725439e-05, "loss": 0.5621, "num_tokens": 436440135.0, "step": 73175 }, { "epoch": 0.7807282387206214, "grad_norm": 0.7855883838036447, "learning_rate": 1.0661099903771713e-05, "loss": 0.414, "num_tokens": 436471515.0, "step": 73180 }, { "epoch": 0.7807815817268198, "grad_norm": 0.6639873341034971, "learning_rate": 1.0658467674281014e-05, "loss": 0.5539, "num_tokens": 436498456.0, "step": 73185 }, { "epoch": 0.7808349247330183, "grad_norm": 1.0872077893228562, "learning_rate": 1.0655835968864213e-05, "loss": 0.4951, "num_tokens": 436525614.0, "step": 73190 }, { "epoch": 0.7808882677392167, "grad_norm": 1.7188116976707009, "learning_rate": 1.0653204787603197e-05, "loss": 0.4561, "num_tokens": 436559046.0, "step": 73195 }, { "epoch": 0.7809416107454151, "grad_norm": 1.2395114547081965, "learning_rate": 1.0650574130579837e-05, "loss": 0.4529, "num_tokens": 436598018.0, "step": 73200 }, { "epoch": 0.7809949537516137, "grad_norm": 0.797096814640345, "learning_rate": 1.0647943997876003e-05, "loss": 0.4226, "num_tokens": 436628016.0, "step": 73205 }, { "epoch": 0.7810482967578121, "grad_norm": 1.1244209152619662, "learning_rate": 1.064531438957354e-05, "loss": 0.419, "num_tokens": 436650279.0, "step": 73210 }, { "epoch": 0.7811016397640106, "grad_norm": 1.350399324151349, "learning_rate": 1.0642685305754269e-05, "loss": 0.5789, "num_tokens": 436686953.0, "step": 73215 }, { "epoch": 0.781154982770209, "grad_norm": 1.3948170085377067, "learning_rate": 1.0640056746500002e-05, "loss": 0.4265, "num_tokens": 436717738.0, "step": 73220 }, { "epoch": 0.7812083257764074, "grad_norm": 0.951049310797316, "learning_rate": 1.0637428711892548e-05, "loss": 0.578, "num_tokens": 436763828.0, "step": 73225 }, { "epoch": 0.781261668782606, "grad_norm": 1.354580308339185, "learning_rate": 1.0634801202013673e-05, "loss": 0.5931, "num_tokens": 436785001.0, "step": 73230 }, { "epoch": 0.7813150117888044, "grad_norm": 1.305433179083136, "learning_rate": 1.0632174216945136e-05, "loss": 0.5059, "num_tokens": 436811295.0, "step": 73235 }, { "epoch": 0.7813683547950028, "grad_norm": 1.0621286593142454, "learning_rate": 1.06295477567687e-05, "loss": 0.3878, "num_tokens": 436829653.0, "step": 73240 }, { "epoch": 0.7814216978012013, "grad_norm": 0.6785406585934329, "learning_rate": 1.0626921821566074e-05, "loss": 0.4041, "num_tokens": 436869104.0, "step": 73245 }, { "epoch": 0.7814750408073997, "grad_norm": 0.8471316709079764, "learning_rate": 1.0624296411418986e-05, "loss": 0.4815, "num_tokens": 436899079.0, "step": 73250 }, { "epoch": 0.7815283838135982, "grad_norm": 1.0490999446783256, "learning_rate": 1.0621671526409134e-05, "loss": 0.3699, "num_tokens": 436918537.0, "step": 73255 }, { "epoch": 0.7815817268197967, "grad_norm": 0.8480335616160375, "learning_rate": 1.061904716661819e-05, "loss": 0.4315, "num_tokens": 436950796.0, "step": 73260 }, { "epoch": 0.7816350698259951, "grad_norm": 1.437471868590004, "learning_rate": 1.061642333212783e-05, "loss": 0.454, "num_tokens": 436972612.0, "step": 73265 }, { "epoch": 0.7816884128321936, "grad_norm": 1.0500806637563411, "learning_rate": 1.0613800023019696e-05, "loss": 0.4722, "num_tokens": 436995627.0, "step": 73270 }, { "epoch": 0.781741755838392, "grad_norm": 0.9533788229376242, "learning_rate": 1.0611177239375414e-05, "loss": 0.4777, "num_tokens": 437024374.0, "step": 73275 }, { "epoch": 0.7817950988445905, "grad_norm": 0.5865265892817306, "learning_rate": 1.0608554981276603e-05, "loss": 0.4833, "num_tokens": 437063353.0, "step": 73280 }, { "epoch": 0.7818484418507889, "grad_norm": 0.943730094336389, "learning_rate": 1.0605933248804876e-05, "loss": 0.4355, "num_tokens": 437093052.0, "step": 73285 }, { "epoch": 0.7819017848569874, "grad_norm": 1.10510636714598, "learning_rate": 1.0603312042041794e-05, "loss": 0.4305, "num_tokens": 437102243.0, "step": 73290 }, { "epoch": 0.7819551278631859, "grad_norm": 1.0827703000721063, "learning_rate": 1.0600691361068943e-05, "loss": 0.4649, "num_tokens": 437135394.0, "step": 73295 }, { "epoch": 0.7820084708693843, "grad_norm": 0.9723981707348816, "learning_rate": 1.0598071205967857e-05, "loss": 0.5302, "num_tokens": 437165993.0, "step": 73300 }, { "epoch": 0.7820618138755828, "grad_norm": 0.7683720222852221, "learning_rate": 1.0595451576820087e-05, "loss": 0.4684, "num_tokens": 437197579.0, "step": 73305 }, { "epoch": 0.7821151568817812, "grad_norm": 0.7496875111697832, "learning_rate": 1.0592832473707132e-05, "loss": 0.5177, "num_tokens": 437232850.0, "step": 73310 }, { "epoch": 0.7821684998879797, "grad_norm": 0.5898826683037793, "learning_rate": 1.0590213896710508e-05, "loss": 0.4033, "num_tokens": 437261310.0, "step": 73315 }, { "epoch": 0.7822218428941782, "grad_norm": 1.14119207316532, "learning_rate": 1.0587595845911689e-05, "loss": 0.5108, "num_tokens": 437283664.0, "step": 73320 }, { "epoch": 0.7822751859003766, "grad_norm": 0.8569838880705738, "learning_rate": 1.0584978321392147e-05, "loss": 0.4175, "num_tokens": 437318158.0, "step": 73325 }, { "epoch": 0.782328528906575, "grad_norm": 0.8526021496326116, "learning_rate": 1.0582361323233342e-05, "loss": 0.4656, "num_tokens": 437343740.0, "step": 73330 }, { "epoch": 0.7823818719127735, "grad_norm": 0.9655617119798197, "learning_rate": 1.0579744851516701e-05, "loss": 0.5004, "num_tokens": 437366586.0, "step": 73335 }, { "epoch": 0.7824352149189719, "grad_norm": 0.8191990309237875, "learning_rate": 1.0577128906323642e-05, "loss": 0.4682, "num_tokens": 437397987.0, "step": 73340 }, { "epoch": 0.7824885579251705, "grad_norm": 1.097262452002297, "learning_rate": 1.0574513487735577e-05, "loss": 0.4346, "num_tokens": 437417406.0, "step": 73345 }, { "epoch": 0.7825419009313689, "grad_norm": 1.0839724359540563, "learning_rate": 1.0571898595833879e-05, "loss": 0.5334, "num_tokens": 437444189.0, "step": 73350 }, { "epoch": 0.7825952439375673, "grad_norm": 0.736197402485995, "learning_rate": 1.0569284230699925e-05, "loss": 0.5117, "num_tokens": 437477767.0, "step": 73355 }, { "epoch": 0.7826485869437658, "grad_norm": 0.7848662272084732, "learning_rate": 1.0566670392415075e-05, "loss": 0.4695, "num_tokens": 437511265.0, "step": 73360 }, { "epoch": 0.7827019299499642, "grad_norm": 0.6245240866145901, "learning_rate": 1.0564057081060655e-05, "loss": 0.4541, "num_tokens": 437563794.0, "step": 73365 }, { "epoch": 0.7827552729561628, "grad_norm": 1.1097228558219945, "learning_rate": 1.0561444296717998e-05, "loss": 0.4424, "num_tokens": 437582218.0, "step": 73370 }, { "epoch": 0.7828086159623612, "grad_norm": 2.440845643380705, "learning_rate": 1.05588320394684e-05, "loss": 0.4823, "num_tokens": 437598605.0, "step": 73375 }, { "epoch": 0.7828619589685596, "grad_norm": 0.9544856279987799, "learning_rate": 1.0556220309393145e-05, "loss": 0.3948, "num_tokens": 437618903.0, "step": 73380 }, { "epoch": 0.7829153019747581, "grad_norm": 0.8345315139719287, "learning_rate": 1.0553609106573512e-05, "loss": 0.4307, "num_tokens": 437657093.0, "step": 73385 }, { "epoch": 0.7829686449809565, "grad_norm": 0.8981615462831055, "learning_rate": 1.0550998431090758e-05, "loss": 0.454, "num_tokens": 437686918.0, "step": 73390 }, { "epoch": 0.783021987987155, "grad_norm": 0.6015166752336953, "learning_rate": 1.0548388283026114e-05, "loss": 0.5307, "num_tokens": 437716068.0, "step": 73395 }, { "epoch": 0.7830753309933535, "grad_norm": 1.2061992548278193, "learning_rate": 1.0545778662460809e-05, "loss": 0.4108, "num_tokens": 437731643.0, "step": 73400 }, { "epoch": 0.7831286739995519, "grad_norm": 0.5562930469998897, "learning_rate": 1.0543169569476052e-05, "loss": 0.4792, "num_tokens": 437770874.0, "step": 73405 }, { "epoch": 0.7831820170057504, "grad_norm": 0.7147772908467498, "learning_rate": 1.0540561004153027e-05, "loss": 0.509, "num_tokens": 437809775.0, "step": 73410 }, { "epoch": 0.7832353600119488, "grad_norm": 0.678108036855278, "learning_rate": 1.05379529665729e-05, "loss": 0.43, "num_tokens": 437838467.0, "step": 73415 }, { "epoch": 0.7832887030181472, "grad_norm": 1.7223314839257065, "learning_rate": 1.0535345456816844e-05, "loss": 0.4611, "num_tokens": 437870817.0, "step": 73420 }, { "epoch": 0.7833420460243458, "grad_norm": 0.9857570997253593, "learning_rate": 1.0532738474965984e-05, "loss": 0.4936, "num_tokens": 437897337.0, "step": 73425 }, { "epoch": 0.7833953890305442, "grad_norm": 1.0424144122122272, "learning_rate": 1.0530132021101453e-05, "loss": 0.3932, "num_tokens": 437926360.0, "step": 73430 }, { "epoch": 0.7834487320367427, "grad_norm": 0.8057055745905165, "learning_rate": 1.052752609530436e-05, "loss": 0.4589, "num_tokens": 437959335.0, "step": 73435 }, { "epoch": 0.7835020750429411, "grad_norm": 1.0426384207384973, "learning_rate": 1.0524920697655786e-05, "loss": 0.4647, "num_tokens": 437989065.0, "step": 73440 }, { "epoch": 0.7835554180491395, "grad_norm": 0.8356909395365442, "learning_rate": 1.0522315828236819e-05, "loss": 0.5074, "num_tokens": 438035726.0, "step": 73445 }, { "epoch": 0.783608761055338, "grad_norm": 0.8747766680092572, "learning_rate": 1.0519711487128511e-05, "loss": 0.5482, "num_tokens": 438064025.0, "step": 73450 }, { "epoch": 0.7836621040615365, "grad_norm": 0.7430744092303955, "learning_rate": 1.0517107674411897e-05, "loss": 0.4602, "num_tokens": 438093314.0, "step": 73455 }, { "epoch": 0.783715447067735, "grad_norm": 1.2002802578307525, "learning_rate": 1.0514504390168009e-05, "loss": 0.4493, "num_tokens": 438125044.0, "step": 73460 }, { "epoch": 0.7837687900739334, "grad_norm": 0.8192189183505152, "learning_rate": 1.051190163447786e-05, "loss": 0.6503, "num_tokens": 438166605.0, "step": 73465 }, { "epoch": 0.7838221330801318, "grad_norm": 0.8535530662296709, "learning_rate": 1.050929940742243e-05, "loss": 0.4726, "num_tokens": 438196614.0, "step": 73470 }, { "epoch": 0.7838754760863303, "grad_norm": 1.3800630657686825, "learning_rate": 1.0506697709082706e-05, "loss": 0.418, "num_tokens": 438222412.0, "step": 73475 }, { "epoch": 0.7839288190925288, "grad_norm": 0.7271114355506896, "learning_rate": 1.0504096539539649e-05, "loss": 0.5124, "num_tokens": 438244144.0, "step": 73480 }, { "epoch": 0.7839821620987273, "grad_norm": 1.0572929533927242, "learning_rate": 1.0501495898874195e-05, "loss": 0.4842, "num_tokens": 438259543.0, "step": 73485 }, { "epoch": 0.7840355051049257, "grad_norm": 0.6277718550373826, "learning_rate": 1.0498895787167266e-05, "loss": 0.5472, "num_tokens": 438300871.0, "step": 73490 }, { "epoch": 0.7840888481111241, "grad_norm": 0.5948472169551244, "learning_rate": 1.0496296204499788e-05, "loss": 0.4276, "num_tokens": 438329453.0, "step": 73495 }, { "epoch": 0.7841421911173226, "grad_norm": 1.972739900866766, "learning_rate": 1.0493697150952636e-05, "loss": 0.422, "num_tokens": 438346352.0, "step": 73500 }, { "epoch": 0.784195534123521, "grad_norm": 0.9896800536043883, "learning_rate": 1.0491098626606702e-05, "loss": 0.4568, "num_tokens": 438376693.0, "step": 73505 }, { "epoch": 0.7842488771297195, "grad_norm": 0.7960922491253243, "learning_rate": 1.0488500631542844e-05, "loss": 0.4901, "num_tokens": 438410296.0, "step": 73510 }, { "epoch": 0.784302220135918, "grad_norm": 0.7535794211168738, "learning_rate": 1.0485903165841898e-05, "loss": 0.3502, "num_tokens": 438443844.0, "step": 73515 }, { "epoch": 0.7843555631421164, "grad_norm": 0.6508135025701288, "learning_rate": 1.0483306229584706e-05, "loss": 0.5291, "num_tokens": 438477963.0, "step": 73520 }, { "epoch": 0.7844089061483149, "grad_norm": 0.6687237446488999, "learning_rate": 1.0480709822852067e-05, "loss": 0.4214, "num_tokens": 438512391.0, "step": 73525 }, { "epoch": 0.7844622491545133, "grad_norm": 1.5497921774374077, "learning_rate": 1.0478113945724775e-05, "loss": 0.4218, "num_tokens": 438529648.0, "step": 73530 }, { "epoch": 0.7845155921607118, "grad_norm": 1.4950206100528967, "learning_rate": 1.0475518598283614e-05, "loss": 0.4431, "num_tokens": 438558738.0, "step": 73535 }, { "epoch": 0.7845689351669103, "grad_norm": 0.8155405189791829, "learning_rate": 1.047292378060935e-05, "loss": 0.4877, "num_tokens": 438596796.0, "step": 73540 }, { "epoch": 0.7846222781731087, "grad_norm": 0.8467270443266377, "learning_rate": 1.0470329492782718e-05, "loss": 0.4557, "num_tokens": 438635959.0, "step": 73545 }, { "epoch": 0.7846756211793072, "grad_norm": 1.3326187783121144, "learning_rate": 1.046773573488445e-05, "loss": 0.5106, "num_tokens": 438663074.0, "step": 73550 }, { "epoch": 0.7847289641855056, "grad_norm": 1.4005832529006383, "learning_rate": 1.0465142506995268e-05, "loss": 0.3925, "num_tokens": 438700453.0, "step": 73555 }, { "epoch": 0.784782307191704, "grad_norm": 0.8377770250011537, "learning_rate": 1.0462549809195863e-05, "loss": 0.5152, "num_tokens": 438738674.0, "step": 73560 }, { "epoch": 0.7848356501979026, "grad_norm": 0.7949973207300772, "learning_rate": 1.0459957641566904e-05, "loss": 0.5138, "num_tokens": 438777710.0, "step": 73565 }, { "epoch": 0.784888993204101, "grad_norm": 0.9162396056082124, "learning_rate": 1.0457366004189067e-05, "loss": 0.4966, "num_tokens": 438808281.0, "step": 73570 }, { "epoch": 0.7849423362102995, "grad_norm": 0.796928783596238, "learning_rate": 1.045477489714299e-05, "loss": 0.3764, "num_tokens": 438829831.0, "step": 73575 }, { "epoch": 0.7849956792164979, "grad_norm": 0.6024020984228189, "learning_rate": 1.0452184320509304e-05, "loss": 0.5074, "num_tokens": 438873829.0, "step": 73580 }, { "epoch": 0.7850490222226963, "grad_norm": 1.0177285983611777, "learning_rate": 1.0449594274368631e-05, "loss": 0.4727, "num_tokens": 438894277.0, "step": 73585 }, { "epoch": 0.7851023652288949, "grad_norm": 0.6150285555182616, "learning_rate": 1.0447004758801556e-05, "loss": 0.4172, "num_tokens": 438928916.0, "step": 73590 }, { "epoch": 0.7851557082350933, "grad_norm": 0.6392658256937548, "learning_rate": 1.0444415773888671e-05, "loss": 0.4587, "num_tokens": 438974463.0, "step": 73595 }, { "epoch": 0.7852090512412917, "grad_norm": 0.8326732050561824, "learning_rate": 1.0441827319710537e-05, "loss": 0.6184, "num_tokens": 439006864.0, "step": 73600 }, { "epoch": 0.7852623942474902, "grad_norm": 0.5510142263422192, "learning_rate": 1.0439239396347685e-05, "loss": 0.4412, "num_tokens": 439058963.0, "step": 73605 }, { "epoch": 0.7853157372536886, "grad_norm": 3.190116639645183, "learning_rate": 1.0436652003880668e-05, "loss": 0.5626, "num_tokens": 439089103.0, "step": 73610 }, { "epoch": 0.7853690802598872, "grad_norm": 0.644602958842713, "learning_rate": 1.043406514238999e-05, "loss": 0.6096, "num_tokens": 439136307.0, "step": 73615 }, { "epoch": 0.7854224232660856, "grad_norm": 0.7658129256237497, "learning_rate": 1.0431478811956149e-05, "loss": 0.4364, "num_tokens": 439164542.0, "step": 73620 }, { "epoch": 0.785475766272284, "grad_norm": 1.3711542931383758, "learning_rate": 1.0428893012659633e-05, "loss": 0.5012, "num_tokens": 439203491.0, "step": 73625 }, { "epoch": 0.7855291092784825, "grad_norm": 0.8576508850083413, "learning_rate": 1.0426307744580898e-05, "loss": 0.509, "num_tokens": 439244586.0, "step": 73630 }, { "epoch": 0.7855824522846809, "grad_norm": 0.7518732623655258, "learning_rate": 1.0423723007800394e-05, "loss": 0.4382, "num_tokens": 439282217.0, "step": 73635 }, { "epoch": 0.7856357952908795, "grad_norm": 0.772289157977202, "learning_rate": 1.0421138802398553e-05, "loss": 0.4705, "num_tokens": 439303556.0, "step": 73640 }, { "epoch": 0.7856891382970779, "grad_norm": 1.2651982796762418, "learning_rate": 1.0418555128455798e-05, "loss": 0.525, "num_tokens": 439328202.0, "step": 73645 }, { "epoch": 0.7857424813032763, "grad_norm": 0.8469612957142595, "learning_rate": 1.0415971986052512e-05, "loss": 0.4265, "num_tokens": 439360755.0, "step": 73650 }, { "epoch": 0.7857958243094748, "grad_norm": 0.7134132269854033, "learning_rate": 1.041338937526909e-05, "loss": 0.459, "num_tokens": 439399709.0, "step": 73655 }, { "epoch": 0.7858491673156732, "grad_norm": 0.7541155138805243, "learning_rate": 1.0410807296185896e-05, "loss": 0.4443, "num_tokens": 439429682.0, "step": 73660 }, { "epoch": 0.7859025103218718, "grad_norm": 1.0099100361072388, "learning_rate": 1.040822574888328e-05, "loss": 0.5424, "num_tokens": 439464314.0, "step": 73665 }, { "epoch": 0.7859558533280702, "grad_norm": 1.5397691600923311, "learning_rate": 1.0405644733441563e-05, "loss": 0.4564, "num_tokens": 439497910.0, "step": 73670 }, { "epoch": 0.7860091963342686, "grad_norm": 0.6500020012696044, "learning_rate": 1.0403064249941078e-05, "loss": 0.4718, "num_tokens": 439551071.0, "step": 73675 }, { "epoch": 0.7860625393404671, "grad_norm": 1.2031798651057413, "learning_rate": 1.0400484298462108e-05, "loss": 0.4512, "num_tokens": 439592308.0, "step": 73680 }, { "epoch": 0.7861158823466655, "grad_norm": 1.0406651311352948, "learning_rate": 1.0397904879084942e-05, "loss": 0.5935, "num_tokens": 439638572.0, "step": 73685 }, { "epoch": 0.7861692253528639, "grad_norm": 0.794622435363836, "learning_rate": 1.0395325991889854e-05, "loss": 0.3828, "num_tokens": 439661723.0, "step": 73690 }, { "epoch": 0.7862225683590625, "grad_norm": 0.9232363790040267, "learning_rate": 1.0392747636957079e-05, "loss": 0.4101, "num_tokens": 439695278.0, "step": 73695 }, { "epoch": 0.7862759113652609, "grad_norm": 0.7171826665004707, "learning_rate": 1.0390169814366869e-05, "loss": 0.4525, "num_tokens": 439738262.0, "step": 73700 }, { "epoch": 0.7863292543714594, "grad_norm": 0.8392863799562913, "learning_rate": 1.0387592524199426e-05, "loss": 0.5079, "num_tokens": 439762380.0, "step": 73705 }, { "epoch": 0.7863825973776578, "grad_norm": 0.7129404124931576, "learning_rate": 1.038501576653495e-05, "loss": 0.4267, "num_tokens": 439788155.0, "step": 73710 }, { "epoch": 0.7864359403838562, "grad_norm": 0.6893544369187691, "learning_rate": 1.0382439541453625e-05, "loss": 0.5406, "num_tokens": 439825484.0, "step": 73715 }, { "epoch": 0.7864892833900547, "grad_norm": 1.3832017444721982, "learning_rate": 1.0379863849035629e-05, "loss": 0.5475, "num_tokens": 439852145.0, "step": 73720 }, { "epoch": 0.7865426263962532, "grad_norm": 1.114191436526612, "learning_rate": 1.0377288689361098e-05, "loss": 0.5218, "num_tokens": 439874255.0, "step": 73725 }, { "epoch": 0.7865959694024517, "grad_norm": 1.642640153986861, "learning_rate": 1.0374714062510173e-05, "loss": 0.5326, "num_tokens": 439892214.0, "step": 73730 }, { "epoch": 0.7866493124086501, "grad_norm": 0.5136745207087939, "learning_rate": 1.0372139968562977e-05, "loss": 0.5537, "num_tokens": 439936017.0, "step": 73735 }, { "epoch": 0.7867026554148485, "grad_norm": 0.6571710711211173, "learning_rate": 1.0369566407599603e-05, "loss": 0.538, "num_tokens": 439960075.0, "step": 73740 }, { "epoch": 0.786755998421047, "grad_norm": 1.108994304679242, "learning_rate": 1.0366993379700127e-05, "loss": 0.4133, "num_tokens": 439983417.0, "step": 73745 }, { "epoch": 0.7868093414272455, "grad_norm": 0.9076980434642664, "learning_rate": 1.036442088494463e-05, "loss": 0.4648, "num_tokens": 440013714.0, "step": 73750 }, { "epoch": 0.786862684433444, "grad_norm": 0.6748057944505331, "learning_rate": 1.0361848923413157e-05, "loss": 0.5781, "num_tokens": 440054132.0, "step": 73755 }, { "epoch": 0.7869160274396424, "grad_norm": 1.4525661654409583, "learning_rate": 1.0359277495185737e-05, "loss": 0.5437, "num_tokens": 440081539.0, "step": 73760 }, { "epoch": 0.7869693704458408, "grad_norm": 1.205084656915144, "learning_rate": 1.0356706600342403e-05, "loss": 0.4114, "num_tokens": 440106990.0, "step": 73765 }, { "epoch": 0.7870227134520393, "grad_norm": 0.8659733950331517, "learning_rate": 1.035413623896314e-05, "loss": 0.4485, "num_tokens": 440142644.0, "step": 73770 }, { "epoch": 0.7870760564582377, "grad_norm": 0.8875936761208164, "learning_rate": 1.0351566411127942e-05, "loss": 0.4603, "num_tokens": 440171081.0, "step": 73775 }, { "epoch": 0.7871293994644362, "grad_norm": 0.6101054871155671, "learning_rate": 1.0348997116916776e-05, "loss": 0.504, "num_tokens": 440212244.0, "step": 73780 }, { "epoch": 0.7871827424706347, "grad_norm": 1.438153307371077, "learning_rate": 1.0346428356409585e-05, "loss": 0.5349, "num_tokens": 440249404.0, "step": 73785 }, { "epoch": 0.7872360854768331, "grad_norm": 0.9432092917492483, "learning_rate": 1.0343860129686307e-05, "loss": 0.5076, "num_tokens": 440276418.0, "step": 73790 }, { "epoch": 0.7872894284830316, "grad_norm": 0.6106494194744065, "learning_rate": 1.0341292436826863e-05, "loss": 0.4734, "num_tokens": 440318351.0, "step": 73795 }, { "epoch": 0.78734277148923, "grad_norm": 1.1569343850722602, "learning_rate": 1.0338725277911157e-05, "loss": 0.4622, "num_tokens": 440346519.0, "step": 73800 }, { "epoch": 0.7873961144954285, "grad_norm": 1.1205617372643424, "learning_rate": 1.0336158653019068e-05, "loss": 0.4076, "num_tokens": 440371943.0, "step": 73805 }, { "epoch": 0.787449457501627, "grad_norm": 0.6125637655094556, "learning_rate": 1.033359256223047e-05, "loss": 0.4362, "num_tokens": 440412663.0, "step": 73810 }, { "epoch": 0.7875028005078254, "grad_norm": 1.152821139391193, "learning_rate": 1.0331027005625212e-05, "loss": 0.4375, "num_tokens": 440446189.0, "step": 73815 }, { "epoch": 0.7875561435140239, "grad_norm": 0.639414281134126, "learning_rate": 1.032846198328312e-05, "loss": 0.492, "num_tokens": 440489347.0, "step": 73820 }, { "epoch": 0.7876094865202223, "grad_norm": 1.40032926112989, "learning_rate": 1.032589749528402e-05, "loss": 0.4746, "num_tokens": 440510407.0, "step": 73825 }, { "epoch": 0.7876628295264207, "grad_norm": 0.5236441145317381, "learning_rate": 1.032333354170772e-05, "loss": 0.4541, "num_tokens": 440551332.0, "step": 73830 }, { "epoch": 0.7877161725326193, "grad_norm": 0.9946698808681468, "learning_rate": 1.0320770122633993e-05, "loss": 0.4617, "num_tokens": 440577375.0, "step": 73835 }, { "epoch": 0.7877695155388177, "grad_norm": 0.790255089793083, "learning_rate": 1.031820723814261e-05, "loss": 0.51, "num_tokens": 440623887.0, "step": 73840 }, { "epoch": 0.7878228585450162, "grad_norm": 0.9465372626421976, "learning_rate": 1.0315644888313334e-05, "loss": 0.5649, "num_tokens": 440656812.0, "step": 73845 }, { "epoch": 0.7878762015512146, "grad_norm": 1.099886403581338, "learning_rate": 1.031308307322589e-05, "loss": 0.4093, "num_tokens": 440674072.0, "step": 73850 }, { "epoch": 0.787929544557413, "grad_norm": 1.3644132943051428, "learning_rate": 1.0310521792959993e-05, "loss": 0.4491, "num_tokens": 440704497.0, "step": 73855 }, { "epoch": 0.7879828875636116, "grad_norm": 0.7039211978856527, "learning_rate": 1.0307961047595354e-05, "loss": 0.5127, "num_tokens": 440731305.0, "step": 73860 }, { "epoch": 0.78803623056981, "grad_norm": 0.6855525531148479, "learning_rate": 1.0305400837211649e-05, "loss": 0.4283, "num_tokens": 440770380.0, "step": 73865 }, { "epoch": 0.7880895735760084, "grad_norm": 0.7024733839283743, "learning_rate": 1.030284116188855e-05, "loss": 0.5912, "num_tokens": 440793191.0, "step": 73870 }, { "epoch": 0.7881429165822069, "grad_norm": 1.1324099051266223, "learning_rate": 1.0300282021705717e-05, "loss": 0.4906, "num_tokens": 440840787.0, "step": 73875 }, { "epoch": 0.7881962595884053, "grad_norm": 1.5925369314582056, "learning_rate": 1.0297723416742772e-05, "loss": 0.5053, "num_tokens": 440866814.0, "step": 73880 }, { "epoch": 0.7882496025946039, "grad_norm": 1.049781761456144, "learning_rate": 1.0295165347079345e-05, "loss": 0.4446, "num_tokens": 440896700.0, "step": 73885 }, { "epoch": 0.7883029456008023, "grad_norm": 0.671436382683929, "learning_rate": 1.0292607812795035e-05, "loss": 0.5633, "num_tokens": 440941146.0, "step": 73890 }, { "epoch": 0.7883562886070007, "grad_norm": 0.8486493551846459, "learning_rate": 1.0290050813969416e-05, "loss": 0.3803, "num_tokens": 440965689.0, "step": 73895 }, { "epoch": 0.7884096316131992, "grad_norm": 0.7742449794697923, "learning_rate": 1.0287494350682067e-05, "loss": 0.5035, "num_tokens": 441000267.0, "step": 73900 }, { "epoch": 0.7884629746193976, "grad_norm": 0.9691178676882832, "learning_rate": 1.0284938423012546e-05, "loss": 0.5327, "num_tokens": 441040464.0, "step": 73905 }, { "epoch": 0.7885163176255962, "grad_norm": 0.9862749564974004, "learning_rate": 1.0282383031040371e-05, "loss": 0.4994, "num_tokens": 441079312.0, "step": 73910 }, { "epoch": 0.7885696606317946, "grad_norm": 1.5806598600589632, "learning_rate": 1.0279828174845077e-05, "loss": 0.4184, "num_tokens": 441103241.0, "step": 73915 }, { "epoch": 0.788623003637993, "grad_norm": 1.5269524997110449, "learning_rate": 1.0277273854506162e-05, "loss": 0.4824, "num_tokens": 441123044.0, "step": 73920 }, { "epoch": 0.7886763466441915, "grad_norm": 0.9384805019377988, "learning_rate": 1.0274720070103098e-05, "loss": 0.512, "num_tokens": 441144819.0, "step": 73925 }, { "epoch": 0.7887296896503899, "grad_norm": 1.0564286251191106, "learning_rate": 1.0272166821715365e-05, "loss": 0.4185, "num_tokens": 441163475.0, "step": 73930 }, { "epoch": 0.7887830326565884, "grad_norm": 1.1897879875414454, "learning_rate": 1.026961410942242e-05, "loss": 0.4744, "num_tokens": 441190164.0, "step": 73935 }, { "epoch": 0.7888363756627869, "grad_norm": 1.1462971510311029, "learning_rate": 1.0267061933303687e-05, "loss": 0.5029, "num_tokens": 441227693.0, "step": 73940 }, { "epoch": 0.7888897186689853, "grad_norm": 1.7335553044057668, "learning_rate": 1.0264510293438587e-05, "loss": 0.5279, "num_tokens": 441258208.0, "step": 73945 }, { "epoch": 0.7889430616751838, "grad_norm": 1.4079659151773836, "learning_rate": 1.026195918990653e-05, "loss": 0.4298, "num_tokens": 441284075.0, "step": 73950 }, { "epoch": 0.7889964046813822, "grad_norm": 0.9959075660989226, "learning_rate": 1.0259408622786898e-05, "loss": 0.4622, "num_tokens": 441309806.0, "step": 73955 }, { "epoch": 0.7890497476875806, "grad_norm": 0.7593975376386218, "learning_rate": 1.025685859215905e-05, "loss": 0.3665, "num_tokens": 441336051.0, "step": 73960 }, { "epoch": 0.7891030906937792, "grad_norm": 0.9343430219377811, "learning_rate": 1.0254309098102347e-05, "loss": 0.4074, "num_tokens": 441380429.0, "step": 73965 }, { "epoch": 0.7891564336999776, "grad_norm": 1.4072617180921885, "learning_rate": 1.0251760140696116e-05, "loss": 0.5698, "num_tokens": 441413104.0, "step": 73970 }, { "epoch": 0.7892097767061761, "grad_norm": 1.4792257978020045, "learning_rate": 1.0249211720019681e-05, "loss": 0.5564, "num_tokens": 441458372.0, "step": 73975 }, { "epoch": 0.7892631197123745, "grad_norm": 0.8802312165613054, "learning_rate": 1.0246663836152348e-05, "loss": 0.4815, "num_tokens": 441492050.0, "step": 73980 }, { "epoch": 0.7893164627185729, "grad_norm": 0.8585527461606931, "learning_rate": 1.0244116489173393e-05, "loss": 0.5009, "num_tokens": 441532334.0, "step": 73985 }, { "epoch": 0.7893698057247714, "grad_norm": 1.0316529691582816, "learning_rate": 1.0241569679162093e-05, "loss": 0.5517, "num_tokens": 441558811.0, "step": 73990 }, { "epoch": 0.7894231487309699, "grad_norm": 0.6764377198949857, "learning_rate": 1.0239023406197698e-05, "loss": 0.5313, "num_tokens": 441594338.0, "step": 73995 }, { "epoch": 0.7894764917371684, "grad_norm": 1.0518309753188488, "learning_rate": 1.0236477670359431e-05, "loss": 0.362, "num_tokens": 441629741.0, "step": 74000 }, { "epoch": 0.7895298347433668, "grad_norm": 0.6676310672395913, "learning_rate": 1.0233932471726519e-05, "loss": 0.52, "num_tokens": 441661590.0, "step": 74005 }, { "epoch": 0.7895831777495652, "grad_norm": 1.8075399135332164, "learning_rate": 1.0231387810378168e-05, "loss": 0.5592, "num_tokens": 441682054.0, "step": 74010 }, { "epoch": 0.7896365207557637, "grad_norm": 0.7064430540296166, "learning_rate": 1.0228843686393554e-05, "loss": 0.4337, "num_tokens": 441710400.0, "step": 74015 }, { "epoch": 0.7896898637619622, "grad_norm": 0.9480826048337907, "learning_rate": 1.0226300099851843e-05, "loss": 0.5075, "num_tokens": 441742450.0, "step": 74020 }, { "epoch": 0.7897432067681607, "grad_norm": 1.2931541484270392, "learning_rate": 1.0223757050832203e-05, "loss": 0.3695, "num_tokens": 441771105.0, "step": 74025 }, { "epoch": 0.7897965497743591, "grad_norm": 1.3945061365397218, "learning_rate": 1.0221214539413757e-05, "loss": 0.4859, "num_tokens": 441804053.0, "step": 74030 }, { "epoch": 0.7898498927805575, "grad_norm": 0.942527447268745, "learning_rate": 1.0218672565675615e-05, "loss": 0.4665, "num_tokens": 441849240.0, "step": 74035 }, { "epoch": 0.789903235786756, "grad_norm": 1.4761197647007258, "learning_rate": 1.0216131129696894e-05, "loss": 0.5221, "num_tokens": 441872592.0, "step": 74040 }, { "epoch": 0.7899565787929544, "grad_norm": 0.7885970975144462, "learning_rate": 1.0213590231556659e-05, "loss": 0.5785, "num_tokens": 441911097.0, "step": 74045 }, { "epoch": 0.7900099217991529, "grad_norm": 0.9063398662393071, "learning_rate": 1.0211049871333994e-05, "loss": 0.3451, "num_tokens": 441926945.0, "step": 74050 }, { "epoch": 0.7900632648053514, "grad_norm": 0.8226823417024881, "learning_rate": 1.020851004910795e-05, "loss": 0.5471, "num_tokens": 441966288.0, "step": 74055 }, { "epoch": 0.7901166078115498, "grad_norm": 0.6645563302392681, "learning_rate": 1.0205970764957547e-05, "loss": 0.5227, "num_tokens": 441997412.0, "step": 74060 }, { "epoch": 0.7901699508177483, "grad_norm": 1.181975845945411, "learning_rate": 1.0203432018961819e-05, "loss": 0.5122, "num_tokens": 442026220.0, "step": 74065 }, { "epoch": 0.7902232938239467, "grad_norm": 1.1148654819296662, "learning_rate": 1.0200893811199755e-05, "loss": 0.4251, "num_tokens": 442053011.0, "step": 74070 }, { "epoch": 0.7902766368301452, "grad_norm": 1.000470883217564, "learning_rate": 1.019835614175034e-05, "loss": 0.4244, "num_tokens": 442088421.0, "step": 74075 }, { "epoch": 0.7903299798363437, "grad_norm": 0.8350797480036595, "learning_rate": 1.0195819010692543e-05, "loss": 0.465, "num_tokens": 442121508.0, "step": 74080 }, { "epoch": 0.7903833228425421, "grad_norm": 0.6236215968726033, "learning_rate": 1.0193282418105319e-05, "loss": 0.4064, "num_tokens": 442158974.0, "step": 74085 }, { "epoch": 0.7904366658487406, "grad_norm": 1.0464068674722145, "learning_rate": 1.0190746364067591e-05, "loss": 0.509, "num_tokens": 442194345.0, "step": 74090 }, { "epoch": 0.790490008854939, "grad_norm": 0.7225632089246241, "learning_rate": 1.018821084865828e-05, "loss": 0.4454, "num_tokens": 442219207.0, "step": 74095 }, { "epoch": 0.7905433518611374, "grad_norm": 1.0385150345050569, "learning_rate": 1.01856758719563e-05, "loss": 0.5592, "num_tokens": 442258383.0, "step": 74100 }, { "epoch": 0.790596694867336, "grad_norm": 0.7378731981164772, "learning_rate": 1.0183141434040515e-05, "loss": 0.5379, "num_tokens": 442293486.0, "step": 74105 }, { "epoch": 0.7906500378735344, "grad_norm": 0.767381820635245, "learning_rate": 1.01806075349898e-05, "loss": 0.4516, "num_tokens": 442322063.0, "step": 74110 }, { "epoch": 0.7907033808797329, "grad_norm": 0.7544613595565521, "learning_rate": 1.0178074174883007e-05, "loss": 0.4508, "num_tokens": 442350723.0, "step": 74115 }, { "epoch": 0.7907567238859313, "grad_norm": 1.1016185403137857, "learning_rate": 1.0175541353798957e-05, "loss": 0.4829, "num_tokens": 442392836.0, "step": 74120 }, { "epoch": 0.7908100668921297, "grad_norm": 1.4254903003837358, "learning_rate": 1.0173009071816475e-05, "loss": 0.4573, "num_tokens": 442406776.0, "step": 74125 }, { "epoch": 0.7908634098983283, "grad_norm": 1.2361317219534365, "learning_rate": 1.0170477329014367e-05, "loss": 0.419, "num_tokens": 442430436.0, "step": 74130 }, { "epoch": 0.7909167529045267, "grad_norm": 1.4522952486004763, "learning_rate": 1.0167946125471403e-05, "loss": 0.4858, "num_tokens": 442448553.0, "step": 74135 }, { "epoch": 0.7909700959107251, "grad_norm": 1.1742520231336764, "learning_rate": 1.0165415461266362e-05, "loss": 0.4658, "num_tokens": 442474354.0, "step": 74140 }, { "epoch": 0.7910234389169236, "grad_norm": 0.9426188921853501, "learning_rate": 1.0162885336477981e-05, "loss": 0.3522, "num_tokens": 442496597.0, "step": 74145 }, { "epoch": 0.791076781923122, "grad_norm": 0.9568514741183356, "learning_rate": 1.0160355751184995e-05, "loss": 0.5123, "num_tokens": 442513007.0, "step": 74150 }, { "epoch": 0.7911301249293206, "grad_norm": 0.7777552406069039, "learning_rate": 1.015782670546612e-05, "loss": 0.5133, "num_tokens": 442531859.0, "step": 74155 }, { "epoch": 0.791183467935519, "grad_norm": 1.2149588506253397, "learning_rate": 1.0155298199400062e-05, "loss": 0.7004, "num_tokens": 442556480.0, "step": 74160 }, { "epoch": 0.7912368109417174, "grad_norm": 0.7500872750382784, "learning_rate": 1.0152770233065493e-05, "loss": 0.5716, "num_tokens": 442581656.0, "step": 74165 }, { "epoch": 0.7912901539479159, "grad_norm": 0.7348481580794916, "learning_rate": 1.0150242806541079e-05, "loss": 0.4003, "num_tokens": 442605254.0, "step": 74170 }, { "epoch": 0.7913434969541143, "grad_norm": 0.8526316838858187, "learning_rate": 1.014771591990548e-05, "loss": 0.436, "num_tokens": 442638501.0, "step": 74175 }, { "epoch": 0.7913968399603128, "grad_norm": 0.7288644505760158, "learning_rate": 1.0145189573237317e-05, "loss": 0.3963, "num_tokens": 442665307.0, "step": 74180 }, { "epoch": 0.7914501829665113, "grad_norm": 1.094076015406559, "learning_rate": 1.0142663766615201e-05, "loss": 0.4368, "num_tokens": 442704963.0, "step": 74185 }, { "epoch": 0.7915035259727097, "grad_norm": 1.1215087888513773, "learning_rate": 1.0140138500117743e-05, "loss": 0.4933, "num_tokens": 442728222.0, "step": 74190 }, { "epoch": 0.7915568689789082, "grad_norm": 1.1538960555822988, "learning_rate": 1.013761377382351e-05, "loss": 0.491, "num_tokens": 442750284.0, "step": 74195 }, { "epoch": 0.7916102119851066, "grad_norm": 0.7148793388448245, "learning_rate": 1.0135089587811069e-05, "loss": 0.4908, "num_tokens": 442783623.0, "step": 74200 }, { "epoch": 0.7916635549913051, "grad_norm": 1.026456598396792, "learning_rate": 1.0132565942158984e-05, "loss": 0.4991, "num_tokens": 442811171.0, "step": 74205 }, { "epoch": 0.7917168979975036, "grad_norm": 0.6603473301945396, "learning_rate": 1.0130042836945772e-05, "loss": 0.4284, "num_tokens": 442850959.0, "step": 74210 }, { "epoch": 0.791770241003702, "grad_norm": 0.8592926901477835, "learning_rate": 1.0127520272249937e-05, "loss": 0.435, "num_tokens": 442888664.0, "step": 74215 }, { "epoch": 0.7918235840099005, "grad_norm": 1.0462774458445745, "learning_rate": 1.0124998248149998e-05, "loss": 0.4683, "num_tokens": 442916219.0, "step": 74220 }, { "epoch": 0.7918769270160989, "grad_norm": 0.9154103476492096, "learning_rate": 1.0122476764724414e-05, "loss": 0.5631, "num_tokens": 442947549.0, "step": 74225 }, { "epoch": 0.7919302700222973, "grad_norm": 4.4330373833918175, "learning_rate": 1.0119955822051664e-05, "loss": 0.5875, "num_tokens": 442984766.0, "step": 74230 }, { "epoch": 0.7919836130284958, "grad_norm": 0.9665380255088881, "learning_rate": 1.0117435420210192e-05, "loss": 0.5097, "num_tokens": 443013132.0, "step": 74235 }, { "epoch": 0.7920369560346943, "grad_norm": 0.873282086271211, "learning_rate": 1.0114915559278421e-05, "loss": 0.4747, "num_tokens": 443045688.0, "step": 74240 }, { "epoch": 0.7920902990408928, "grad_norm": 0.801604738007245, "learning_rate": 1.011239623933477e-05, "loss": 0.4242, "num_tokens": 443068469.0, "step": 74245 }, { "epoch": 0.7921436420470912, "grad_norm": 1.2991078587073706, "learning_rate": 1.0109877460457637e-05, "loss": 0.6012, "num_tokens": 443090511.0, "step": 74250 }, { "epoch": 0.7921969850532896, "grad_norm": 0.7489997253663232, "learning_rate": 1.0107359222725388e-05, "loss": 0.4721, "num_tokens": 443116183.0, "step": 74255 }, { "epoch": 0.7922503280594881, "grad_norm": 0.6220735653239516, "learning_rate": 1.0104841526216393e-05, "loss": 0.5068, "num_tokens": 443168591.0, "step": 74260 }, { "epoch": 0.7923036710656866, "grad_norm": 2.7327904227423874, "learning_rate": 1.0102324371009008e-05, "loss": 0.5653, "num_tokens": 443206294.0, "step": 74265 }, { "epoch": 0.7923570140718851, "grad_norm": 0.8140807931599254, "learning_rate": 1.0099807757181547e-05, "loss": 0.4626, "num_tokens": 443237275.0, "step": 74270 }, { "epoch": 0.7924103570780835, "grad_norm": 0.9244507795101924, "learning_rate": 1.0097291684812327e-05, "loss": 0.4789, "num_tokens": 443263262.0, "step": 74275 }, { "epoch": 0.7924637000842819, "grad_norm": 0.8340083848706794, "learning_rate": 1.009477615397965e-05, "loss": 0.479, "num_tokens": 443289873.0, "step": 74280 }, { "epoch": 0.7925170430904804, "grad_norm": 0.9651196379319299, "learning_rate": 1.0092261164761788e-05, "loss": 0.5373, "num_tokens": 443324600.0, "step": 74285 }, { "epoch": 0.7925703860966788, "grad_norm": 0.718765520769031, "learning_rate": 1.0089746717236995e-05, "loss": 0.4638, "num_tokens": 443354111.0, "step": 74290 }, { "epoch": 0.7926237291028774, "grad_norm": 0.7335005351923317, "learning_rate": 1.0087232811483527e-05, "loss": 0.4476, "num_tokens": 443399876.0, "step": 74295 }, { "epoch": 0.7926770721090758, "grad_norm": 1.1407967255190703, "learning_rate": 1.0084719447579603e-05, "loss": 0.4409, "num_tokens": 443427237.0, "step": 74300 }, { "epoch": 0.7927304151152742, "grad_norm": 0.7061826469261087, "learning_rate": 1.0082206625603439e-05, "loss": 0.5266, "num_tokens": 443462192.0, "step": 74305 }, { "epoch": 0.7927837581214727, "grad_norm": 0.8419660551224257, "learning_rate": 1.007969434563323e-05, "loss": 0.4657, "num_tokens": 443495008.0, "step": 74310 }, { "epoch": 0.7928371011276711, "grad_norm": 4.496943370451925, "learning_rate": 1.0077182607747149e-05, "loss": 0.6036, "num_tokens": 443519969.0, "step": 74315 }, { "epoch": 0.7928904441338696, "grad_norm": 2.247763305483427, "learning_rate": 1.0074671412023359e-05, "loss": 0.4806, "num_tokens": 443534726.0, "step": 74320 }, { "epoch": 0.7929437871400681, "grad_norm": 0.5821893218300059, "learning_rate": 1.0072160758540009e-05, "loss": 0.4833, "num_tokens": 443569241.0, "step": 74325 }, { "epoch": 0.7929971301462665, "grad_norm": 0.6657898367938601, "learning_rate": 1.0069650647375206e-05, "loss": 0.415, "num_tokens": 443600009.0, "step": 74330 }, { "epoch": 0.793050473152465, "grad_norm": 0.5444212792599904, "learning_rate": 1.0067141078607073e-05, "loss": 0.3903, "num_tokens": 443633884.0, "step": 74335 }, { "epoch": 0.7931038161586634, "grad_norm": 2.243991167543088, "learning_rate": 1.0064632052313708e-05, "loss": 0.4295, "num_tokens": 443652761.0, "step": 74340 }, { "epoch": 0.7931571591648618, "grad_norm": 1.327565355841071, "learning_rate": 1.0062123568573176e-05, "loss": 0.4645, "num_tokens": 443676478.0, "step": 74345 }, { "epoch": 0.7932105021710604, "grad_norm": 2.162900718842898, "learning_rate": 1.0059615627463537e-05, "loss": 0.5296, "num_tokens": 443704073.0, "step": 74350 }, { "epoch": 0.7932638451772588, "grad_norm": 0.8295900814412561, "learning_rate": 1.0057108229062843e-05, "loss": 0.4399, "num_tokens": 443726087.0, "step": 74355 }, { "epoch": 0.7933171881834573, "grad_norm": 1.4044043597711922, "learning_rate": 1.0054601373449116e-05, "loss": 0.4684, "num_tokens": 443743545.0, "step": 74360 }, { "epoch": 0.7933705311896557, "grad_norm": 0.8996004972221506, "learning_rate": 1.005209506070035e-05, "loss": 0.4436, "num_tokens": 443767286.0, "step": 74365 }, { "epoch": 0.7934238741958541, "grad_norm": 1.1465797777662619, "learning_rate": 1.0049589290894554e-05, "loss": 0.4576, "num_tokens": 443799792.0, "step": 74370 }, { "epoch": 0.7934772172020527, "grad_norm": 0.7784871550209307, "learning_rate": 1.004708406410969e-05, "loss": 0.4482, "num_tokens": 443833365.0, "step": 74375 }, { "epoch": 0.7935305602082511, "grad_norm": 2.176667860574051, "learning_rate": 1.004457938042372e-05, "loss": 0.4531, "num_tokens": 443844618.0, "step": 74380 }, { "epoch": 0.7935839032144496, "grad_norm": 1.797031526554507, "learning_rate": 1.004207523991459e-05, "loss": 0.4349, "num_tokens": 443865661.0, "step": 74385 }, { "epoch": 0.793637246220648, "grad_norm": 0.8569813554973232, "learning_rate": 1.0039571642660215e-05, "loss": 0.4482, "num_tokens": 443894710.0, "step": 74390 }, { "epoch": 0.7936905892268464, "grad_norm": 0.9328100620960345, "learning_rate": 1.003706858873851e-05, "loss": 0.585, "num_tokens": 443935094.0, "step": 74395 }, { "epoch": 0.793743932233045, "grad_norm": 0.7761950169347871, "learning_rate": 1.0034566078227361e-05, "loss": 0.5936, "num_tokens": 443975813.0, "step": 74400 }, { "epoch": 0.7937972752392434, "grad_norm": 0.690043087937554, "learning_rate": 1.0032064111204636e-05, "loss": 0.468, "num_tokens": 444008143.0, "step": 74405 }, { "epoch": 0.7938506182454418, "grad_norm": 0.6651930200643498, "learning_rate": 1.0029562687748194e-05, "loss": 0.4051, "num_tokens": 444043778.0, "step": 74410 }, { "epoch": 0.7939039612516403, "grad_norm": 0.710911203212362, "learning_rate": 1.0027061807935883e-05, "loss": 0.4342, "num_tokens": 444076814.0, "step": 74415 }, { "epoch": 0.7939573042578387, "grad_norm": 2.01856060392588, "learning_rate": 1.0024561471845511e-05, "loss": 0.6663, "num_tokens": 444106752.0, "step": 74420 }, { "epoch": 0.7940106472640373, "grad_norm": 0.8795527893440686, "learning_rate": 1.0022061679554891e-05, "loss": 0.4264, "num_tokens": 444142812.0, "step": 74425 }, { "epoch": 0.7940639902702357, "grad_norm": 0.5530281171441335, "learning_rate": 1.0019562431141817e-05, "loss": 0.3366, "num_tokens": 444190223.0, "step": 74430 }, { "epoch": 0.7941173332764341, "grad_norm": 1.5630282118088952, "learning_rate": 1.0017063726684053e-05, "loss": 0.5306, "num_tokens": 444218214.0, "step": 74435 }, { "epoch": 0.7941706762826326, "grad_norm": 1.5549042868211043, "learning_rate": 1.001456556625935e-05, "loss": 0.4884, "num_tokens": 444239975.0, "step": 74440 }, { "epoch": 0.794224019288831, "grad_norm": 0.8188919443404347, "learning_rate": 1.0012067949945456e-05, "loss": 0.5674, "num_tokens": 444275022.0, "step": 74445 }, { "epoch": 0.7942773622950295, "grad_norm": 0.6205408530544597, "learning_rate": 1.0009570877820082e-05, "loss": 0.4622, "num_tokens": 444305983.0, "step": 74450 }, { "epoch": 0.794330705301228, "grad_norm": 0.6544902791992339, "learning_rate": 1.0007074349960935e-05, "loss": 0.4826, "num_tokens": 444328304.0, "step": 74455 }, { "epoch": 0.7943840483074264, "grad_norm": 0.8231258418427976, "learning_rate": 1.0004578366445708e-05, "loss": 0.4342, "num_tokens": 444347770.0, "step": 74460 }, { "epoch": 0.7944373913136249, "grad_norm": 0.9113476572980729, "learning_rate": 1.000208292735206e-05, "loss": 0.4178, "num_tokens": 444370342.0, "step": 74465 }, { "epoch": 0.7944907343198233, "grad_norm": 1.0686620258370767, "learning_rate": 9.999588032757656e-06, "loss": 0.4202, "num_tokens": 444395692.0, "step": 74470 }, { "epoch": 0.7945440773260218, "grad_norm": 1.6220108383314202, "learning_rate": 9.997093682740125e-06, "loss": 0.5207, "num_tokens": 444418842.0, "step": 74475 }, { "epoch": 0.7945974203322203, "grad_norm": 0.7345657688037854, "learning_rate": 9.99459987737708e-06, "loss": 0.3964, "num_tokens": 444469176.0, "step": 74480 }, { "epoch": 0.7946507633384187, "grad_norm": 1.207288286262375, "learning_rate": 9.992106616746131e-06, "loss": 0.439, "num_tokens": 444495138.0, "step": 74485 }, { "epoch": 0.7947041063446172, "grad_norm": 1.1648035949063005, "learning_rate": 9.989613900924865e-06, "loss": 0.4754, "num_tokens": 444520459.0, "step": 74490 }, { "epoch": 0.7947574493508156, "grad_norm": 3.129219274150469, "learning_rate": 9.987121729990845e-06, "loss": 0.5568, "num_tokens": 444539385.0, "step": 74495 }, { "epoch": 0.794810792357014, "grad_norm": 0.8529982919542078, "learning_rate": 9.984630104021622e-06, "loss": 0.4519, "num_tokens": 444569465.0, "step": 74500 }, { "epoch": 0.7948641353632125, "grad_norm": 1.5968302351033166, "learning_rate": 9.982139023094738e-06, "loss": 0.6568, "num_tokens": 444598076.0, "step": 74505 }, { "epoch": 0.794917478369411, "grad_norm": 0.7140397899203023, "learning_rate": 9.979648487287707e-06, "loss": 0.4885, "num_tokens": 444633385.0, "step": 74510 }, { "epoch": 0.7949708213756095, "grad_norm": 0.620719513965963, "learning_rate": 9.977158496678018e-06, "loss": 0.4553, "num_tokens": 444672427.0, "step": 74515 }, { "epoch": 0.7950241643818079, "grad_norm": 0.8572138173617831, "learning_rate": 9.974669051343171e-06, "loss": 0.4426, "num_tokens": 444687846.0, "step": 74520 }, { "epoch": 0.7950775073880063, "grad_norm": 0.8927361970350731, "learning_rate": 9.972180151360621e-06, "loss": 0.6274, "num_tokens": 444726925.0, "step": 74525 }, { "epoch": 0.7951308503942048, "grad_norm": 0.8533582374624555, "learning_rate": 9.969691796807821e-06, "loss": 0.5016, "num_tokens": 444760853.0, "step": 74530 }, { "epoch": 0.7951841934004032, "grad_norm": 0.9798851387877843, "learning_rate": 9.967203987762211e-06, "loss": 0.527, "num_tokens": 444783730.0, "step": 74535 }, { "epoch": 0.7952375364066018, "grad_norm": 1.0343322556772685, "learning_rate": 9.964716724301195e-06, "loss": 0.3388, "num_tokens": 444799775.0, "step": 74540 }, { "epoch": 0.7952908794128002, "grad_norm": 1.5691522296754414, "learning_rate": 9.962230006502177e-06, "loss": 0.3968, "num_tokens": 444816274.0, "step": 74545 }, { "epoch": 0.7953442224189986, "grad_norm": 0.9406564590349575, "learning_rate": 9.959743834442536e-06, "loss": 0.4866, "num_tokens": 444837497.0, "step": 74550 }, { "epoch": 0.7953975654251971, "grad_norm": 1.1842423578801708, "learning_rate": 9.957258208199638e-06, "loss": 0.429, "num_tokens": 444851999.0, "step": 74555 }, { "epoch": 0.7954509084313955, "grad_norm": 1.4133362799959621, "learning_rate": 9.954773127850826e-06, "loss": 0.5304, "num_tokens": 444874851.0, "step": 74560 }, { "epoch": 0.7955042514375941, "grad_norm": 0.6722164317722861, "learning_rate": 9.952288593473443e-06, "loss": 0.619, "num_tokens": 444918395.0, "step": 74565 }, { "epoch": 0.7955575944437925, "grad_norm": 1.720721464015742, "learning_rate": 9.949804605144791e-06, "loss": 0.5968, "num_tokens": 444947270.0, "step": 74570 }, { "epoch": 0.7956109374499909, "grad_norm": 0.7659383336864661, "learning_rate": 9.947321162942176e-06, "loss": 0.505, "num_tokens": 444981747.0, "step": 74575 }, { "epoch": 0.7956642804561894, "grad_norm": 0.8832425470899438, "learning_rate": 9.944838266942871e-06, "loss": 0.4867, "num_tokens": 445008833.0, "step": 74580 }, { "epoch": 0.7957176234623878, "grad_norm": 0.6908069529682584, "learning_rate": 9.942355917224133e-06, "loss": 0.4169, "num_tokens": 445040400.0, "step": 74585 }, { "epoch": 0.7957709664685862, "grad_norm": 0.8556934562498827, "learning_rate": 9.939874113863217e-06, "loss": 0.5018, "num_tokens": 445069963.0, "step": 74590 }, { "epoch": 0.7958243094747848, "grad_norm": 1.3632288813531293, "learning_rate": 9.937392856937353e-06, "loss": 0.5701, "num_tokens": 445106456.0, "step": 74595 }, { "epoch": 0.7958776524809832, "grad_norm": 0.8797800340446613, "learning_rate": 9.934912146523742e-06, "loss": 0.4632, "num_tokens": 445139066.0, "step": 74600 }, { "epoch": 0.7959309954871817, "grad_norm": 0.8300084389413753, "learning_rate": 9.932431982699588e-06, "loss": 0.5658, "num_tokens": 445166521.0, "step": 74605 }, { "epoch": 0.7959843384933801, "grad_norm": 0.6720096124737187, "learning_rate": 9.929952365542071e-06, "loss": 0.4454, "num_tokens": 445215420.0, "step": 74610 }, { "epoch": 0.7960376814995785, "grad_norm": 0.6425883477736483, "learning_rate": 9.927473295128346e-06, "loss": 0.4045, "num_tokens": 445244887.0, "step": 74615 }, { "epoch": 0.7960910245057771, "grad_norm": 0.7358251500023087, "learning_rate": 9.924994771535551e-06, "loss": 0.5035, "num_tokens": 445260286.0, "step": 74620 }, { "epoch": 0.7961443675119755, "grad_norm": 0.5904268529066689, "learning_rate": 9.922516794840823e-06, "loss": 0.4895, "num_tokens": 445293022.0, "step": 74625 }, { "epoch": 0.796197710518174, "grad_norm": 0.6306932858353047, "learning_rate": 9.920039365121265e-06, "loss": 0.4833, "num_tokens": 445323297.0, "step": 74630 }, { "epoch": 0.7962510535243724, "grad_norm": 0.8756229772420688, "learning_rate": 9.917562482453969e-06, "loss": 0.4993, "num_tokens": 445364362.0, "step": 74635 }, { "epoch": 0.7963043965305708, "grad_norm": 1.4152115052136218, "learning_rate": 9.91508614691602e-06, "loss": 0.4541, "num_tokens": 445398183.0, "step": 74640 }, { "epoch": 0.7963577395367694, "grad_norm": 1.0373857478832458, "learning_rate": 9.912610358584462e-06, "loss": 0.6246, "num_tokens": 445427279.0, "step": 74645 }, { "epoch": 0.7964110825429678, "grad_norm": 1.01479389221998, "learning_rate": 9.910135117536353e-06, "loss": 0.4636, "num_tokens": 445478401.0, "step": 74650 }, { "epoch": 0.7964644255491663, "grad_norm": 1.0013688894564723, "learning_rate": 9.907660423848706e-06, "loss": 0.4952, "num_tokens": 445516134.0, "step": 74655 }, { "epoch": 0.7965177685553647, "grad_norm": 1.1920456467759581, "learning_rate": 9.905186277598528e-06, "loss": 0.5011, "num_tokens": 445536257.0, "step": 74660 }, { "epoch": 0.7965711115615631, "grad_norm": 1.0883886333719082, "learning_rate": 9.902712678862808e-06, "loss": 0.6987, "num_tokens": 445581377.0, "step": 74665 }, { "epoch": 0.7966244545677617, "grad_norm": 0.6762299743221093, "learning_rate": 9.90023962771853e-06, "loss": 0.3962, "num_tokens": 445607971.0, "step": 74670 }, { "epoch": 0.7966777975739601, "grad_norm": 1.4744294504280535, "learning_rate": 9.89776712424264e-06, "loss": 0.4436, "num_tokens": 445633507.0, "step": 74675 }, { "epoch": 0.7967311405801585, "grad_norm": 0.7884747132845737, "learning_rate": 9.895295168512082e-06, "loss": 0.4848, "num_tokens": 445658147.0, "step": 74680 }, { "epoch": 0.796784483586357, "grad_norm": 1.358020109616816, "learning_rate": 9.89282376060378e-06, "loss": 0.4115, "num_tokens": 445681656.0, "step": 74685 }, { "epoch": 0.7968378265925554, "grad_norm": 0.7459831883681538, "learning_rate": 9.890352900594638e-06, "loss": 0.4298, "num_tokens": 445716765.0, "step": 74690 }, { "epoch": 0.796891169598754, "grad_norm": 0.6491709284391558, "learning_rate": 9.887882588561536e-06, "loss": 0.4739, "num_tokens": 445754379.0, "step": 74695 }, { "epoch": 0.7969445126049524, "grad_norm": 0.7086380175873178, "learning_rate": 9.885412824581361e-06, "loss": 0.429, "num_tokens": 445799816.0, "step": 74700 }, { "epoch": 0.7969978556111508, "grad_norm": 0.42030597579404066, "learning_rate": 9.882943608730947e-06, "loss": 0.4944, "num_tokens": 445834547.0, "step": 74705 }, { "epoch": 0.7970511986173493, "grad_norm": 0.915032254314499, "learning_rate": 9.880474941087145e-06, "loss": 0.4442, "num_tokens": 445851836.0, "step": 74710 }, { "epoch": 0.7971045416235477, "grad_norm": 1.1265919754956177, "learning_rate": 9.878006821726773e-06, "loss": 0.4458, "num_tokens": 445877510.0, "step": 74715 }, { "epoch": 0.7971578846297462, "grad_norm": 0.5652132081878254, "learning_rate": 9.875539250726632e-06, "loss": 0.5021, "num_tokens": 445919506.0, "step": 74720 }, { "epoch": 0.7972112276359447, "grad_norm": 1.6303896631488333, "learning_rate": 9.873072228163507e-06, "loss": 0.4425, "num_tokens": 445948488.0, "step": 74725 }, { "epoch": 0.7972645706421431, "grad_norm": 0.9336777531612183, "learning_rate": 9.870605754114169e-06, "loss": 0.5173, "num_tokens": 445970967.0, "step": 74730 }, { "epoch": 0.7973179136483416, "grad_norm": 0.7296193088308046, "learning_rate": 9.868139828655368e-06, "loss": 0.5103, "num_tokens": 446017074.0, "step": 74735 }, { "epoch": 0.79737125665454, "grad_norm": 0.837675812929956, "learning_rate": 9.865674451863834e-06, "loss": 0.5023, "num_tokens": 446052833.0, "step": 74740 }, { "epoch": 0.7974245996607385, "grad_norm": 1.0628352598750859, "learning_rate": 9.86320962381629e-06, "loss": 0.515, "num_tokens": 446073597.0, "step": 74745 }, { "epoch": 0.797477942666937, "grad_norm": 1.1812892316870007, "learning_rate": 9.86074534458944e-06, "loss": 0.4851, "num_tokens": 446098557.0, "step": 74750 }, { "epoch": 0.7975312856731354, "grad_norm": 0.7282586347532386, "learning_rate": 9.85828161425996e-06, "loss": 0.3547, "num_tokens": 446138302.0, "step": 74755 }, { "epoch": 0.7975846286793339, "grad_norm": 1.3727918623896596, "learning_rate": 9.855818432904523e-06, "loss": 0.473, "num_tokens": 446165394.0, "step": 74760 }, { "epoch": 0.7976379716855323, "grad_norm": 0.9214191645792078, "learning_rate": 9.853355800599775e-06, "loss": 0.395, "num_tokens": 446199610.0, "step": 74765 }, { "epoch": 0.7976913146917307, "grad_norm": 1.0314585210099119, "learning_rate": 9.85089371742234e-06, "loss": 0.3868, "num_tokens": 446228563.0, "step": 74770 }, { "epoch": 0.7977446576979292, "grad_norm": 1.2275132232236599, "learning_rate": 9.84843218344884e-06, "loss": 0.5089, "num_tokens": 446262775.0, "step": 74775 }, { "epoch": 0.7977980007041277, "grad_norm": 0.7438588483808342, "learning_rate": 9.845971198755882e-06, "loss": 0.4644, "num_tokens": 446298715.0, "step": 74780 }, { "epoch": 0.7978513437103262, "grad_norm": 0.8946332356461947, "learning_rate": 9.843510763420027e-06, "loss": 0.491, "num_tokens": 446336726.0, "step": 74785 }, { "epoch": 0.7979046867165246, "grad_norm": 1.6199774667057194, "learning_rate": 9.841050877517852e-06, "loss": 0.3964, "num_tokens": 446350493.0, "step": 74790 }, { "epoch": 0.797958029722723, "grad_norm": 0.9081227937796066, "learning_rate": 9.838591541125907e-06, "loss": 0.4767, "num_tokens": 446371627.0, "step": 74795 }, { "epoch": 0.7980113727289215, "grad_norm": 1.1671550662753312, "learning_rate": 9.836132754320717e-06, "loss": 0.4924, "num_tokens": 446404989.0, "step": 74800 }, { "epoch": 0.79806471573512, "grad_norm": 0.8726604671050492, "learning_rate": 9.833674517178788e-06, "loss": 0.5287, "num_tokens": 446435391.0, "step": 74805 }, { "epoch": 0.7981180587413185, "grad_norm": 0.49409809935214416, "learning_rate": 9.831216829776623e-06, "loss": 0.4901, "num_tokens": 446469641.0, "step": 74810 }, { "epoch": 0.7981714017475169, "grad_norm": 0.7040839504491697, "learning_rate": 9.828759692190692e-06, "loss": 0.4159, "num_tokens": 446502184.0, "step": 74815 }, { "epoch": 0.7982247447537153, "grad_norm": 1.0217192372896362, "learning_rate": 9.826303104497465e-06, "loss": 0.4709, "num_tokens": 446523799.0, "step": 74820 }, { "epoch": 0.7982780877599138, "grad_norm": 0.9933665774352198, "learning_rate": 9.823847066773387e-06, "loss": 0.5367, "num_tokens": 446568540.0, "step": 74825 }, { "epoch": 0.7983314307661122, "grad_norm": 0.6291611350493116, "learning_rate": 9.82139157909488e-06, "loss": 0.409, "num_tokens": 446605629.0, "step": 74830 }, { "epoch": 0.7983847737723108, "grad_norm": 1.086468348831551, "learning_rate": 9.818936641538347e-06, "loss": 0.4997, "num_tokens": 446648552.0, "step": 74835 }, { "epoch": 0.7984381167785092, "grad_norm": 1.408912742718076, "learning_rate": 9.816482254180194e-06, "loss": 0.5369, "num_tokens": 446679497.0, "step": 74840 }, { "epoch": 0.7984914597847076, "grad_norm": 1.3011410490787145, "learning_rate": 9.814028417096785e-06, "loss": 0.4998, "num_tokens": 446700827.0, "step": 74845 }, { "epoch": 0.7985448027909061, "grad_norm": 0.9307359643056227, "learning_rate": 9.811575130364484e-06, "loss": 0.4328, "num_tokens": 446715656.0, "step": 74850 }, { "epoch": 0.7985981457971045, "grad_norm": 0.8938191096339659, "learning_rate": 9.809122394059638e-06, "loss": 0.5037, "num_tokens": 446740906.0, "step": 74855 }, { "epoch": 0.798651488803303, "grad_norm": 1.6501509302871349, "learning_rate": 9.806670208258556e-06, "loss": 0.4445, "num_tokens": 446757679.0, "step": 74860 }, { "epoch": 0.7987048318095015, "grad_norm": 0.6440335675334009, "learning_rate": 9.804218573037566e-06, "loss": 0.4112, "num_tokens": 446789384.0, "step": 74865 }, { "epoch": 0.7987581748156999, "grad_norm": 0.8330191141074184, "learning_rate": 9.80176748847294e-06, "loss": 0.3686, "num_tokens": 446806855.0, "step": 74870 }, { "epoch": 0.7988115178218984, "grad_norm": 1.6547926712265053, "learning_rate": 9.799316954640953e-06, "loss": 0.4721, "num_tokens": 446831075.0, "step": 74875 }, { "epoch": 0.7988648608280968, "grad_norm": 1.1879920886228248, "learning_rate": 9.796866971617866e-06, "loss": 0.4006, "num_tokens": 446852018.0, "step": 74880 }, { "epoch": 0.7989182038342952, "grad_norm": 0.9468901011662008, "learning_rate": 9.79441753947992e-06, "loss": 0.4166, "num_tokens": 446870508.0, "step": 74885 }, { "epoch": 0.7989715468404938, "grad_norm": 1.6942917685086627, "learning_rate": 9.791968658303325e-06, "loss": 0.5477, "num_tokens": 446900407.0, "step": 74890 }, { "epoch": 0.7990248898466922, "grad_norm": 0.8325988907150729, "learning_rate": 9.789520328164289e-06, "loss": 0.4101, "num_tokens": 446931805.0, "step": 74895 }, { "epoch": 0.7990782328528907, "grad_norm": 1.0768273215949928, "learning_rate": 9.787072549139012e-06, "loss": 0.4823, "num_tokens": 446961259.0, "step": 74900 }, { "epoch": 0.7991315758590891, "grad_norm": 0.7651872238160677, "learning_rate": 9.784625321303654e-06, "loss": 0.3955, "num_tokens": 446982363.0, "step": 74905 }, { "epoch": 0.7991849188652875, "grad_norm": 0.8293152432023707, "learning_rate": 9.782178644734362e-06, "loss": 0.348, "num_tokens": 447011873.0, "step": 74910 }, { "epoch": 0.799238261871486, "grad_norm": 1.1435358780210536, "learning_rate": 9.779732519507282e-06, "loss": 0.5503, "num_tokens": 447051931.0, "step": 74915 }, { "epoch": 0.7992916048776845, "grad_norm": 0.8112583749533396, "learning_rate": 9.777286945698522e-06, "loss": 0.4955, "num_tokens": 447082902.0, "step": 74920 }, { "epoch": 0.799344947883883, "grad_norm": 0.9932213415682049, "learning_rate": 9.774841923384186e-06, "loss": 0.4058, "num_tokens": 447106936.0, "step": 74925 }, { "epoch": 0.7993982908900814, "grad_norm": 1.2177546448464611, "learning_rate": 9.77239745264037e-06, "loss": 0.4115, "num_tokens": 447124585.0, "step": 74930 }, { "epoch": 0.7994516338962798, "grad_norm": 1.254715185033122, "learning_rate": 9.769953533543126e-06, "loss": 0.5093, "num_tokens": 447150137.0, "step": 74935 }, { "epoch": 0.7995049769024783, "grad_norm": 0.993805833920515, "learning_rate": 9.767510166168515e-06, "loss": 0.5192, "num_tokens": 447175550.0, "step": 74940 }, { "epoch": 0.7995583199086768, "grad_norm": 0.8542169924297996, "learning_rate": 9.76506735059256e-06, "loss": 0.4548, "num_tokens": 447209274.0, "step": 74945 }, { "epoch": 0.7996116629148752, "grad_norm": 1.0317289273577048, "learning_rate": 9.762625086891278e-06, "loss": 0.4494, "num_tokens": 447239412.0, "step": 74950 }, { "epoch": 0.7996650059210737, "grad_norm": 1.0531267608718495, "learning_rate": 9.760183375140672e-06, "loss": 0.3398, "num_tokens": 447261105.0, "step": 74955 }, { "epoch": 0.7997183489272721, "grad_norm": 0.5834647172257782, "learning_rate": 9.757742215416724e-06, "loss": 0.4335, "num_tokens": 447295909.0, "step": 74960 }, { "epoch": 0.7997716919334706, "grad_norm": 0.7675505607577859, "learning_rate": 9.755301607795389e-06, "loss": 0.3777, "num_tokens": 447332363.0, "step": 74965 }, { "epoch": 0.799825034939669, "grad_norm": 1.0111038257146239, "learning_rate": 9.752861552352617e-06, "loss": 0.4437, "num_tokens": 447365296.0, "step": 74970 }, { "epoch": 0.7998783779458675, "grad_norm": 1.1089294053843781, "learning_rate": 9.750422049164348e-06, "loss": 0.5129, "num_tokens": 447379608.0, "step": 74975 }, { "epoch": 0.799931720952066, "grad_norm": 1.2759949611331027, "learning_rate": 9.747983098306485e-06, "loss": 0.5301, "num_tokens": 447393394.0, "step": 74980 }, { "epoch": 0.7999850639582644, "grad_norm": 0.8573160095382522, "learning_rate": 9.745544699854922e-06, "loss": 0.587, "num_tokens": 447415485.0, "step": 74985 }, { "epoch": 0.8000384069644629, "grad_norm": 1.3201058282808373, "learning_rate": 9.743106853885542e-06, "loss": 0.5233, "num_tokens": 447442834.0, "step": 74990 }, { "epoch": 0.8000917499706613, "grad_norm": 0.9360680016086724, "learning_rate": 9.740669560474196e-06, "loss": 0.3856, "num_tokens": 447470552.0, "step": 74995 }, { "epoch": 0.8001450929768598, "grad_norm": 1.0069023102421417, "learning_rate": 9.73823281969674e-06, "loss": 0.4471, "num_tokens": 447501459.0, "step": 75000 }, { "epoch": 0.8001984359830583, "grad_norm": 0.6063788556666035, "learning_rate": 9.735796631628996e-06, "loss": 0.4195, "num_tokens": 447534315.0, "step": 75005 }, { "epoch": 0.8002517789892567, "grad_norm": 0.8860981500602696, "learning_rate": 9.733360996346768e-06, "loss": 0.4488, "num_tokens": 447560450.0, "step": 75010 }, { "epoch": 0.8003051219954552, "grad_norm": 0.899408096052307, "learning_rate": 9.730925913925857e-06, "loss": 0.5503, "num_tokens": 447593195.0, "step": 75015 }, { "epoch": 0.8003584650016536, "grad_norm": 1.1554064567619136, "learning_rate": 9.728491384442035e-06, "loss": 0.4404, "num_tokens": 447613125.0, "step": 75020 }, { "epoch": 0.800411808007852, "grad_norm": 0.7294664145039138, "learning_rate": 9.726057407971045e-06, "loss": 0.4264, "num_tokens": 447643461.0, "step": 75025 }, { "epoch": 0.8004651510140506, "grad_norm": 1.053535376925252, "learning_rate": 9.723623984588646e-06, "loss": 0.4906, "num_tokens": 447666787.0, "step": 75030 }, { "epoch": 0.800518494020249, "grad_norm": 1.4257136073740049, "learning_rate": 9.72119111437056e-06, "loss": 0.4081, "num_tokens": 447693479.0, "step": 75035 }, { "epoch": 0.8005718370264474, "grad_norm": 0.7133632895388542, "learning_rate": 9.71875879739248e-06, "loss": 0.5693, "num_tokens": 447725378.0, "step": 75040 }, { "epoch": 0.8006251800326459, "grad_norm": 0.7149916297620481, "learning_rate": 9.716327033730105e-06, "loss": 0.4319, "num_tokens": 447752906.0, "step": 75045 }, { "epoch": 0.8006785230388443, "grad_norm": 0.7819476476575838, "learning_rate": 9.713895823459107e-06, "loss": 0.3337, "num_tokens": 447773240.0, "step": 75050 }, { "epoch": 0.8007318660450429, "grad_norm": 0.6823398390463595, "learning_rate": 9.71146516665514e-06, "loss": 0.4822, "num_tokens": 447810559.0, "step": 75055 }, { "epoch": 0.8007852090512413, "grad_norm": 1.0638296311967903, "learning_rate": 9.709035063393832e-06, "loss": 0.4057, "num_tokens": 447839615.0, "step": 75060 }, { "epoch": 0.8008385520574397, "grad_norm": 0.5503505262035163, "learning_rate": 9.706605513750814e-06, "loss": 0.5834, "num_tokens": 447885797.0, "step": 75065 }, { "epoch": 0.8008918950636382, "grad_norm": 0.7981321148663563, "learning_rate": 9.704176517801678e-06, "loss": 0.5402, "num_tokens": 447908548.0, "step": 75070 }, { "epoch": 0.8009452380698366, "grad_norm": 1.3015189791666124, "learning_rate": 9.701748075622014e-06, "loss": 0.4084, "num_tokens": 447931350.0, "step": 75075 }, { "epoch": 0.8009985810760352, "grad_norm": 0.7881135996335279, "learning_rate": 9.699320187287398e-06, "loss": 0.5962, "num_tokens": 447966304.0, "step": 75080 }, { "epoch": 0.8010519240822336, "grad_norm": 0.7642253762436955, "learning_rate": 9.696892852873368e-06, "loss": 0.4153, "num_tokens": 447990357.0, "step": 75085 }, { "epoch": 0.801105267088432, "grad_norm": 1.0542409905417636, "learning_rate": 9.694466072455471e-06, "loss": 0.5705, "num_tokens": 448030677.0, "step": 75090 }, { "epoch": 0.8011586100946305, "grad_norm": 1.298538848301189, "learning_rate": 9.692039846109215e-06, "loss": 0.5952, "num_tokens": 448055439.0, "step": 75095 }, { "epoch": 0.8012119531008289, "grad_norm": 1.382946301598062, "learning_rate": 9.689614173910097e-06, "loss": 0.3981, "num_tokens": 448076750.0, "step": 75100 }, { "epoch": 0.8012652961070275, "grad_norm": 1.0892596281317213, "learning_rate": 9.687189055933598e-06, "loss": 0.5639, "num_tokens": 448104947.0, "step": 75105 }, { "epoch": 0.8013186391132259, "grad_norm": 0.7536528728591962, "learning_rate": 9.684764492255197e-06, "loss": 0.4191, "num_tokens": 448146455.0, "step": 75110 }, { "epoch": 0.8013719821194243, "grad_norm": 0.8264495745302449, "learning_rate": 9.682340482950322e-06, "loss": 0.4731, "num_tokens": 448176923.0, "step": 75115 }, { "epoch": 0.8014253251256228, "grad_norm": 1.6648262374974492, "learning_rate": 9.679917028094421e-06, "loss": 0.5482, "num_tokens": 448203015.0, "step": 75120 }, { "epoch": 0.8014786681318212, "grad_norm": 1.250614594859384, "learning_rate": 9.677494127762898e-06, "loss": 0.3792, "num_tokens": 448223919.0, "step": 75125 }, { "epoch": 0.8015320111380196, "grad_norm": 1.2423243835544155, "learning_rate": 9.675071782031145e-06, "loss": 0.5015, "num_tokens": 448251681.0, "step": 75130 }, { "epoch": 0.8015853541442182, "grad_norm": 0.5748230696980348, "learning_rate": 9.672649990974542e-06, "loss": 0.4295, "num_tokens": 448290891.0, "step": 75135 }, { "epoch": 0.8016386971504166, "grad_norm": 1.9090764285442061, "learning_rate": 9.670228754668459e-06, "loss": 0.5765, "num_tokens": 448319676.0, "step": 75140 }, { "epoch": 0.8016920401566151, "grad_norm": 0.8764101839383603, "learning_rate": 9.667808073188228e-06, "loss": 0.4418, "num_tokens": 448343099.0, "step": 75145 }, { "epoch": 0.8017453831628135, "grad_norm": 0.9832151577526143, "learning_rate": 9.66538794660918e-06, "loss": 0.5327, "num_tokens": 448372180.0, "step": 75150 }, { "epoch": 0.8017987261690119, "grad_norm": 0.5340275429661229, "learning_rate": 9.662968375006637e-06, "loss": 0.3885, "num_tokens": 448413626.0, "step": 75155 }, { "epoch": 0.8018520691752105, "grad_norm": 0.9910037701272307, "learning_rate": 9.660549358455875e-06, "loss": 0.3497, "num_tokens": 448435532.0, "step": 75160 }, { "epoch": 0.8019054121814089, "grad_norm": 1.0260775955511272, "learning_rate": 9.658130897032169e-06, "loss": 0.3715, "num_tokens": 448463945.0, "step": 75165 }, { "epoch": 0.8019587551876074, "grad_norm": 1.1803550691791556, "learning_rate": 9.655712990810787e-06, "loss": 0.4918, "num_tokens": 448488820.0, "step": 75170 }, { "epoch": 0.8020120981938058, "grad_norm": 0.8109169624136089, "learning_rate": 9.653295639866958e-06, "loss": 0.4316, "num_tokens": 448510411.0, "step": 75175 }, { "epoch": 0.8020654412000042, "grad_norm": 1.210570233312532, "learning_rate": 9.650878844275912e-06, "loss": 0.5462, "num_tokens": 448537333.0, "step": 75180 }, { "epoch": 0.8021187842062028, "grad_norm": 0.8855887628586507, "learning_rate": 9.648462604112856e-06, "loss": 0.4452, "num_tokens": 448557234.0, "step": 75185 }, { "epoch": 0.8021721272124012, "grad_norm": 0.8054802327584426, "learning_rate": 9.646046919452973e-06, "loss": 0.4528, "num_tokens": 448581751.0, "step": 75190 }, { "epoch": 0.8022254702185997, "grad_norm": 0.6506368077853877, "learning_rate": 9.64363179037144e-06, "loss": 0.4529, "num_tokens": 448619359.0, "step": 75195 }, { "epoch": 0.8022788132247981, "grad_norm": 1.1761887130301565, "learning_rate": 9.64121721694341e-06, "loss": 0.6196, "num_tokens": 448665204.0, "step": 75200 }, { "epoch": 0.8023321562309965, "grad_norm": 1.0497347382366822, "learning_rate": 9.63880319924401e-06, "loss": 0.3856, "num_tokens": 448705316.0, "step": 75205 }, { "epoch": 0.802385499237195, "grad_norm": 0.7722850826017912, "learning_rate": 9.636389737348365e-06, "loss": 0.3891, "num_tokens": 448740706.0, "step": 75210 }, { "epoch": 0.8024388422433935, "grad_norm": 1.1371722960381823, "learning_rate": 9.633976831331586e-06, "loss": 0.5349, "num_tokens": 448783959.0, "step": 75215 }, { "epoch": 0.8024921852495919, "grad_norm": 1.048253226580499, "learning_rate": 9.631564481268745e-06, "loss": 0.5014, "num_tokens": 448821571.0, "step": 75220 }, { "epoch": 0.8025455282557904, "grad_norm": 0.8169212479615316, "learning_rate": 9.629152687234913e-06, "loss": 0.4691, "num_tokens": 448852376.0, "step": 75225 }, { "epoch": 0.8025988712619888, "grad_norm": 1.4688774117372574, "learning_rate": 9.626741449305148e-06, "loss": 0.6269, "num_tokens": 448880183.0, "step": 75230 }, { "epoch": 0.8026522142681873, "grad_norm": 1.9658548928043649, "learning_rate": 9.624330767554476e-06, "loss": 0.6714, "num_tokens": 448906066.0, "step": 75235 }, { "epoch": 0.8027055572743858, "grad_norm": 1.4326438895598965, "learning_rate": 9.621920642057911e-06, "loss": 0.4974, "num_tokens": 448929595.0, "step": 75240 }, { "epoch": 0.8027589002805842, "grad_norm": 1.055608564392157, "learning_rate": 9.619511072890453e-06, "loss": 0.5051, "num_tokens": 448961841.0, "step": 75245 }, { "epoch": 0.8028122432867827, "grad_norm": 0.6924773272301117, "learning_rate": 9.617102060127078e-06, "loss": 0.3566, "num_tokens": 448988728.0, "step": 75250 }, { "epoch": 0.8028655862929811, "grad_norm": 1.320369492934772, "learning_rate": 9.614693603842758e-06, "loss": 0.3968, "num_tokens": 449015069.0, "step": 75255 }, { "epoch": 0.8029189292991796, "grad_norm": 1.7449234506187463, "learning_rate": 9.612285704112436e-06, "loss": 0.4674, "num_tokens": 449043310.0, "step": 75260 }, { "epoch": 0.802972272305378, "grad_norm": 0.673555838894655, "learning_rate": 9.60987836101104e-06, "loss": 0.4312, "num_tokens": 449085719.0, "step": 75265 }, { "epoch": 0.8030256153115765, "grad_norm": 0.6619498979573787, "learning_rate": 9.607471574613485e-06, "loss": 0.4337, "num_tokens": 449115245.0, "step": 75270 }, { "epoch": 0.803078958317775, "grad_norm": 2.1264931673897545, "learning_rate": 9.605065344994663e-06, "loss": 0.5307, "num_tokens": 449140540.0, "step": 75275 }, { "epoch": 0.8031323013239734, "grad_norm": 0.865211430214246, "learning_rate": 9.602659672229445e-06, "loss": 0.5654, "num_tokens": 449162783.0, "step": 75280 }, { "epoch": 0.8031856443301719, "grad_norm": 0.7645885538834574, "learning_rate": 9.600254556392696e-06, "loss": 0.5235, "num_tokens": 449202710.0, "step": 75285 }, { "epoch": 0.8032389873363703, "grad_norm": 1.0995749415688973, "learning_rate": 9.597849997559261e-06, "loss": 0.4905, "num_tokens": 449230953.0, "step": 75290 }, { "epoch": 0.8032923303425688, "grad_norm": 0.8773192423388502, "learning_rate": 9.595445995803959e-06, "loss": 0.5195, "num_tokens": 449253939.0, "step": 75295 }, { "epoch": 0.8033456733487673, "grad_norm": 1.4542199009936212, "learning_rate": 9.5930425512016e-06, "loss": 0.498, "num_tokens": 449294153.0, "step": 75300 }, { "epoch": 0.8033990163549657, "grad_norm": 1.198412637211744, "learning_rate": 9.590639663826979e-06, "loss": 0.4516, "num_tokens": 449322058.0, "step": 75305 }, { "epoch": 0.8034523593611641, "grad_norm": 1.6126978126430334, "learning_rate": 9.588237333754868e-06, "loss": 0.6241, "num_tokens": 449349336.0, "step": 75310 }, { "epoch": 0.8035057023673626, "grad_norm": 0.7423147504100381, "learning_rate": 9.585835561060011e-06, "loss": 0.5116, "num_tokens": 449386488.0, "step": 75315 }, { "epoch": 0.803559045373561, "grad_norm": 0.760795047601611, "learning_rate": 9.583434345817162e-06, "loss": 0.4334, "num_tokens": 449420891.0, "step": 75320 }, { "epoch": 0.8036123883797596, "grad_norm": 0.6186337858197009, "learning_rate": 9.581033688101027e-06, "loss": 0.4733, "num_tokens": 449469657.0, "step": 75325 }, { "epoch": 0.803665731385958, "grad_norm": 1.1846026928088946, "learning_rate": 9.578633587986317e-06, "loss": 0.4568, "num_tokens": 449489279.0, "step": 75330 }, { "epoch": 0.8037190743921564, "grad_norm": 0.6932232825496366, "learning_rate": 9.576234045547724e-06, "loss": 0.4677, "num_tokens": 449515272.0, "step": 75335 }, { "epoch": 0.8037724173983549, "grad_norm": 1.0987790811701519, "learning_rate": 9.573835060859909e-06, "loss": 0.4631, "num_tokens": 449547676.0, "step": 75340 }, { "epoch": 0.8038257604045533, "grad_norm": 0.820180090540221, "learning_rate": 9.571436633997528e-06, "loss": 0.5272, "num_tokens": 449588666.0, "step": 75345 }, { "epoch": 0.8038791034107519, "grad_norm": 1.051070835407203, "learning_rate": 9.569038765035215e-06, "loss": 0.4671, "num_tokens": 449623107.0, "step": 75350 }, { "epoch": 0.8039324464169503, "grad_norm": 0.7748370540369923, "learning_rate": 9.566641454047576e-06, "loss": 0.5031, "num_tokens": 449655197.0, "step": 75355 }, { "epoch": 0.8039857894231487, "grad_norm": 1.3269249932963383, "learning_rate": 9.564244701109217e-06, "loss": 0.4857, "num_tokens": 449677830.0, "step": 75360 }, { "epoch": 0.8040391324293472, "grad_norm": 0.9412611082317096, "learning_rate": 9.56184850629473e-06, "loss": 0.4894, "num_tokens": 449704853.0, "step": 75365 }, { "epoch": 0.8040924754355456, "grad_norm": 2.6988519476756005, "learning_rate": 9.559452869678667e-06, "loss": 0.4715, "num_tokens": 449739885.0, "step": 75370 }, { "epoch": 0.8041458184417442, "grad_norm": 1.0693171408816826, "learning_rate": 9.557057791335577e-06, "loss": 0.4874, "num_tokens": 449760382.0, "step": 75375 }, { "epoch": 0.8041991614479426, "grad_norm": 1.0690360877569494, "learning_rate": 9.554663271340004e-06, "loss": 0.4399, "num_tokens": 449776018.0, "step": 75380 }, { "epoch": 0.804252504454141, "grad_norm": 1.6355261919544666, "learning_rate": 9.552269309766442e-06, "loss": 0.5331, "num_tokens": 449790695.0, "step": 75385 }, { "epoch": 0.8043058474603395, "grad_norm": 2.1379480236266892, "learning_rate": 9.54987590668939e-06, "loss": 0.5509, "num_tokens": 449810854.0, "step": 75390 }, { "epoch": 0.8043591904665379, "grad_norm": 0.5972976175622449, "learning_rate": 9.547483062183338e-06, "loss": 0.5403, "num_tokens": 449851333.0, "step": 75395 }, { "epoch": 0.8044125334727363, "grad_norm": 0.816851357700564, "learning_rate": 9.545090776322729e-06, "loss": 0.3984, "num_tokens": 449883092.0, "step": 75400 }, { "epoch": 0.8044658764789349, "grad_norm": 1.535005064203846, "learning_rate": 9.542699049182016e-06, "loss": 0.5804, "num_tokens": 449904258.0, "step": 75405 }, { "epoch": 0.8045192194851333, "grad_norm": 1.1466955277938937, "learning_rate": 9.540307880835628e-06, "loss": 0.4913, "num_tokens": 449933511.0, "step": 75410 }, { "epoch": 0.8045725624913318, "grad_norm": 1.214793611559999, "learning_rate": 9.537917271357962e-06, "loss": 0.4695, "num_tokens": 449973448.0, "step": 75415 }, { "epoch": 0.8046259054975302, "grad_norm": 0.9291602106836742, "learning_rate": 9.535527220823423e-06, "loss": 0.4884, "num_tokens": 450005739.0, "step": 75420 }, { "epoch": 0.8046792485037286, "grad_norm": 0.7831977836338708, "learning_rate": 9.533137729306377e-06, "loss": 0.4445, "num_tokens": 450033154.0, "step": 75425 }, { "epoch": 0.8047325915099272, "grad_norm": 1.003706099463146, "learning_rate": 9.530748796881173e-06, "loss": 0.5048, "num_tokens": 450064160.0, "step": 75430 }, { "epoch": 0.8047859345161256, "grad_norm": 1.010445847489589, "learning_rate": 9.528360423622154e-06, "loss": 0.5606, "num_tokens": 450094994.0, "step": 75435 }, { "epoch": 0.8048392775223241, "grad_norm": 0.7024397601961196, "learning_rate": 9.525972609603652e-06, "loss": 0.5969, "num_tokens": 450126071.0, "step": 75440 }, { "epoch": 0.8048926205285225, "grad_norm": 0.8598073098179017, "learning_rate": 9.523585354899956e-06, "loss": 0.4912, "num_tokens": 450159167.0, "step": 75445 }, { "epoch": 0.8049459635347209, "grad_norm": 0.7809994906138593, "learning_rate": 9.521198659585368e-06, "loss": 0.4116, "num_tokens": 450181957.0, "step": 75450 }, { "epoch": 0.8049993065409194, "grad_norm": 0.6464053361822811, "learning_rate": 9.518812523734145e-06, "loss": 0.6414, "num_tokens": 450226301.0, "step": 75455 }, { "epoch": 0.8050526495471179, "grad_norm": 1.4263101269323728, "learning_rate": 9.516426947420536e-06, "loss": 0.5955, "num_tokens": 450273354.0, "step": 75460 }, { "epoch": 0.8051059925533164, "grad_norm": 1.5265979345358076, "learning_rate": 9.514041930718784e-06, "loss": 0.5631, "num_tokens": 450311540.0, "step": 75465 }, { "epoch": 0.8051593355595148, "grad_norm": 0.6597140919809957, "learning_rate": 9.511657473703106e-06, "loss": 0.5327, "num_tokens": 450341488.0, "step": 75470 }, { "epoch": 0.8052126785657132, "grad_norm": 0.5753408194775103, "learning_rate": 9.509273576447695e-06, "loss": 0.4344, "num_tokens": 450393255.0, "step": 75475 }, { "epoch": 0.8052660215719117, "grad_norm": 0.6320993836657915, "learning_rate": 9.506890239026733e-06, "loss": 0.3983, "num_tokens": 450417195.0, "step": 75480 }, { "epoch": 0.8053193645781102, "grad_norm": 1.3632714239082517, "learning_rate": 9.504507461514395e-06, "loss": 0.4509, "num_tokens": 450450804.0, "step": 75485 }, { "epoch": 0.8053727075843086, "grad_norm": 2.9434295375170567, "learning_rate": 9.502125243984822e-06, "loss": 0.4068, "num_tokens": 450468514.0, "step": 75490 }, { "epoch": 0.8054260505905071, "grad_norm": 1.016382527715486, "learning_rate": 9.499743586512136e-06, "loss": 0.5318, "num_tokens": 450509492.0, "step": 75495 }, { "epoch": 0.8054793935967055, "grad_norm": 1.0841022462593648, "learning_rate": 9.497362489170464e-06, "loss": 0.4878, "num_tokens": 450553626.0, "step": 75500 }, { "epoch": 0.805532736602904, "grad_norm": 0.9413110591435971, "learning_rate": 9.494981952033882e-06, "loss": 0.4642, "num_tokens": 450582531.0, "step": 75505 }, { "epoch": 0.8055860796091024, "grad_norm": 0.601354361834024, "learning_rate": 9.492601975176483e-06, "loss": 0.3939, "num_tokens": 450616145.0, "step": 75510 }, { "epoch": 0.8056394226153009, "grad_norm": 1.0348711067417835, "learning_rate": 9.490222558672327e-06, "loss": 0.4452, "num_tokens": 450647749.0, "step": 75515 }, { "epoch": 0.8056927656214994, "grad_norm": 1.0965637761148133, "learning_rate": 9.487843702595444e-06, "loss": 0.5902, "num_tokens": 450687287.0, "step": 75520 }, { "epoch": 0.8057461086276978, "grad_norm": 0.8909386466722805, "learning_rate": 9.485465407019875e-06, "loss": 0.4245, "num_tokens": 450724715.0, "step": 75525 }, { "epoch": 0.8057994516338963, "grad_norm": 0.49833384447951456, "learning_rate": 9.483087672019616e-06, "loss": 0.4182, "num_tokens": 450766937.0, "step": 75530 }, { "epoch": 0.8058527946400947, "grad_norm": 1.0383055586459093, "learning_rate": 9.48071049766866e-06, "loss": 0.4381, "num_tokens": 450803382.0, "step": 75535 }, { "epoch": 0.8059061376462932, "grad_norm": 0.5930277441190575, "learning_rate": 9.478333884040978e-06, "loss": 0.4389, "num_tokens": 450844264.0, "step": 75540 }, { "epoch": 0.8059594806524917, "grad_norm": 0.6282012231850488, "learning_rate": 9.475957831210536e-06, "loss": 0.4169, "num_tokens": 450887340.0, "step": 75545 }, { "epoch": 0.8060128236586901, "grad_norm": 0.803333865372112, "learning_rate": 9.473582339251255e-06, "loss": 0.5281, "num_tokens": 450915353.0, "step": 75550 }, { "epoch": 0.8060661666648886, "grad_norm": 0.9017175727133557, "learning_rate": 9.471207408237067e-06, "loss": 0.4813, "num_tokens": 450937200.0, "step": 75555 }, { "epoch": 0.806119509671087, "grad_norm": 1.1155186639635204, "learning_rate": 9.468833038241876e-06, "loss": 0.4928, "num_tokens": 450952619.0, "step": 75560 }, { "epoch": 0.8061728526772854, "grad_norm": 0.9077318194414746, "learning_rate": 9.466459229339565e-06, "loss": 0.4976, "num_tokens": 450980779.0, "step": 75565 }, { "epoch": 0.806226195683484, "grad_norm": 0.8533677518283445, "learning_rate": 9.464085981603993e-06, "loss": 0.4793, "num_tokens": 450998391.0, "step": 75570 }, { "epoch": 0.8062795386896824, "grad_norm": 0.802686569010488, "learning_rate": 9.461713295109027e-06, "loss": 0.5422, "num_tokens": 451018869.0, "step": 75575 }, { "epoch": 0.8063328816958808, "grad_norm": 0.8761550119430939, "learning_rate": 9.459341169928485e-06, "loss": 0.4627, "num_tokens": 451042112.0, "step": 75580 }, { "epoch": 0.8063862247020793, "grad_norm": 1.1856235724581137, "learning_rate": 9.456969606136187e-06, "loss": 0.4473, "num_tokens": 451065142.0, "step": 75585 }, { "epoch": 0.8064395677082777, "grad_norm": 1.079760954777347, "learning_rate": 9.454598603805943e-06, "loss": 0.6127, "num_tokens": 451127138.0, "step": 75590 }, { "epoch": 0.8064929107144763, "grad_norm": 1.0066166490292425, "learning_rate": 9.452228163011515e-06, "loss": 0.4793, "num_tokens": 451166056.0, "step": 75595 }, { "epoch": 0.8065462537206747, "grad_norm": 0.5693096602128135, "learning_rate": 9.449858283826682e-06, "loss": 0.4338, "num_tokens": 451198726.0, "step": 75600 }, { "epoch": 0.8065995967268731, "grad_norm": 0.8197059771035079, "learning_rate": 9.447488966325186e-06, "loss": 0.4209, "num_tokens": 451218943.0, "step": 75605 }, { "epoch": 0.8066529397330716, "grad_norm": 0.7173423348439931, "learning_rate": 9.445120210580741e-06, "loss": 0.4026, "num_tokens": 451253491.0, "step": 75610 }, { "epoch": 0.80670628273927, "grad_norm": 0.9956852532488496, "learning_rate": 9.442752016667073e-06, "loss": 0.4562, "num_tokens": 451305546.0, "step": 75615 }, { "epoch": 0.8067596257454686, "grad_norm": 0.9648342212170665, "learning_rate": 9.440384384657876e-06, "loss": 0.4469, "num_tokens": 451322250.0, "step": 75620 }, { "epoch": 0.806812968751667, "grad_norm": 1.338717255493966, "learning_rate": 9.438017314626819e-06, "loss": 0.5248, "num_tokens": 451349170.0, "step": 75625 }, { "epoch": 0.8068663117578654, "grad_norm": 0.7745911153619259, "learning_rate": 9.435650806647558e-06, "loss": 0.5767, "num_tokens": 451379957.0, "step": 75630 }, { "epoch": 0.8069196547640639, "grad_norm": 0.9269692546494814, "learning_rate": 9.433284860793747e-06, "loss": 0.4598, "num_tokens": 451413775.0, "step": 75635 }, { "epoch": 0.8069729977702623, "grad_norm": 0.7942984878439993, "learning_rate": 9.430919477139002e-06, "loss": 0.444, "num_tokens": 451439121.0, "step": 75640 }, { "epoch": 0.8070263407764608, "grad_norm": 1.5868194234410602, "learning_rate": 9.428554655756922e-06, "loss": 0.3597, "num_tokens": 451455617.0, "step": 75645 }, { "epoch": 0.8070796837826593, "grad_norm": 0.7136121772990102, "learning_rate": 9.426190396721099e-06, "loss": 0.5629, "num_tokens": 451487560.0, "step": 75650 }, { "epoch": 0.8071330267888577, "grad_norm": 0.8873311879350703, "learning_rate": 9.423826700105115e-06, "loss": 0.5563, "num_tokens": 451523794.0, "step": 75655 }, { "epoch": 0.8071863697950562, "grad_norm": 1.5411147461404022, "learning_rate": 9.421463565982506e-06, "loss": 0.4842, "num_tokens": 451561718.0, "step": 75660 }, { "epoch": 0.8072397128012546, "grad_norm": 1.2555153266887127, "learning_rate": 9.419100994426818e-06, "loss": 0.5165, "num_tokens": 451592372.0, "step": 75665 }, { "epoch": 0.807293055807453, "grad_norm": 1.4855916671694676, "learning_rate": 9.416738985511572e-06, "loss": 0.3142, "num_tokens": 451602130.0, "step": 75670 }, { "epoch": 0.8073463988136516, "grad_norm": 0.6684323211596571, "learning_rate": 9.414377539310265e-06, "loss": 0.3992, "num_tokens": 451630333.0, "step": 75675 }, { "epoch": 0.80739974181985, "grad_norm": 1.2052160513937873, "learning_rate": 9.412016655896374e-06, "loss": 0.7303, "num_tokens": 451666071.0, "step": 75680 }, { "epoch": 0.8074530848260485, "grad_norm": 0.7792697156675963, "learning_rate": 9.409656335343382e-06, "loss": 0.5008, "num_tokens": 451706082.0, "step": 75685 }, { "epoch": 0.8075064278322469, "grad_norm": 1.2235287874965926, "learning_rate": 9.407296577724713e-06, "loss": 0.4987, "num_tokens": 451739735.0, "step": 75690 }, { "epoch": 0.8075597708384453, "grad_norm": 1.0154624002560078, "learning_rate": 9.404937383113815e-06, "loss": 0.3931, "num_tokens": 451770428.0, "step": 75695 }, { "epoch": 0.8076131138446438, "grad_norm": 0.9740359808450166, "learning_rate": 9.402578751584101e-06, "loss": 0.4234, "num_tokens": 451797282.0, "step": 75700 }, { "epoch": 0.8076664568508423, "grad_norm": 1.034992879315888, "learning_rate": 9.40022068320896e-06, "loss": 0.5578, "num_tokens": 451822753.0, "step": 75705 }, { "epoch": 0.8077197998570408, "grad_norm": 0.56266514813396, "learning_rate": 9.397863178061778e-06, "loss": 0.5031, "num_tokens": 451858476.0, "step": 75710 }, { "epoch": 0.8077731428632392, "grad_norm": 1.6948705262579833, "learning_rate": 9.395506236215911e-06, "loss": 0.4568, "num_tokens": 451882543.0, "step": 75715 }, { "epoch": 0.8078264858694376, "grad_norm": 0.8033038187975987, "learning_rate": 9.393149857744696e-06, "loss": 0.4283, "num_tokens": 451899096.0, "step": 75720 }, { "epoch": 0.8078798288756361, "grad_norm": 0.8103253131426016, "learning_rate": 9.390794042721462e-06, "loss": 0.5611, "num_tokens": 451926614.0, "step": 75725 }, { "epoch": 0.8079331718818346, "grad_norm": 0.9162291047567097, "learning_rate": 9.388438791219533e-06, "loss": 0.3318, "num_tokens": 451953411.0, "step": 75730 }, { "epoch": 0.8079865148880331, "grad_norm": 0.8539414950818071, "learning_rate": 9.386084103312174e-06, "loss": 0.4387, "num_tokens": 451982190.0, "step": 75735 }, { "epoch": 0.8080398578942315, "grad_norm": 0.8385160734865509, "learning_rate": 9.383729979072679e-06, "loss": 0.5024, "num_tokens": 452020148.0, "step": 75740 }, { "epoch": 0.8080932009004299, "grad_norm": 0.803541434233784, "learning_rate": 9.381376418574298e-06, "loss": 0.5403, "num_tokens": 452058601.0, "step": 75745 }, { "epoch": 0.8081465439066284, "grad_norm": 1.508676287414367, "learning_rate": 9.379023421890258e-06, "loss": 0.5724, "num_tokens": 452072827.0, "step": 75750 }, { "epoch": 0.8081998869128268, "grad_norm": 0.9102511781564746, "learning_rate": 9.376670989093785e-06, "loss": 0.3379, "num_tokens": 452091398.0, "step": 75755 }, { "epoch": 0.8082532299190253, "grad_norm": 0.7068225212077623, "learning_rate": 9.374319120258094e-06, "loss": 0.5145, "num_tokens": 452132403.0, "step": 75760 }, { "epoch": 0.8083065729252238, "grad_norm": 1.4208409893921286, "learning_rate": 9.371967815456353e-06, "loss": 0.5336, "num_tokens": 452167836.0, "step": 75765 }, { "epoch": 0.8083599159314222, "grad_norm": 1.0620703061830596, "learning_rate": 9.369617074761738e-06, "loss": 0.4337, "num_tokens": 452183762.0, "step": 75770 }, { "epoch": 0.8084132589376207, "grad_norm": 0.8228478893683522, "learning_rate": 9.367266898247403e-06, "loss": 0.5318, "num_tokens": 452209145.0, "step": 75775 }, { "epoch": 0.8084666019438191, "grad_norm": 0.57891664338903, "learning_rate": 9.364917285986479e-06, "loss": 0.3299, "num_tokens": 452245638.0, "step": 75780 }, { "epoch": 0.8085199449500176, "grad_norm": 0.5804994630608667, "learning_rate": 9.362568238052072e-06, "loss": 0.5283, "num_tokens": 452285408.0, "step": 75785 }, { "epoch": 0.8085732879562161, "grad_norm": 1.1142643748210264, "learning_rate": 9.36021975451729e-06, "loss": 0.4008, "num_tokens": 452302275.0, "step": 75790 }, { "epoch": 0.8086266309624145, "grad_norm": 0.7262257670196375, "learning_rate": 9.357871835455206e-06, "loss": 0.3652, "num_tokens": 452324223.0, "step": 75795 }, { "epoch": 0.808679973968613, "grad_norm": 1.7239632700800585, "learning_rate": 9.355524480938883e-06, "loss": 0.5268, "num_tokens": 452345218.0, "step": 75800 }, { "epoch": 0.8087333169748114, "grad_norm": 0.8822480770852608, "learning_rate": 9.353177691041375e-06, "loss": 0.4956, "num_tokens": 452367214.0, "step": 75805 }, { "epoch": 0.8087866599810098, "grad_norm": 0.8687537574844276, "learning_rate": 9.3508314658357e-06, "loss": 0.3489, "num_tokens": 452383983.0, "step": 75810 }, { "epoch": 0.8088400029872084, "grad_norm": 0.6546311419826648, "learning_rate": 9.348485805394874e-06, "loss": 0.484, "num_tokens": 452412606.0, "step": 75815 }, { "epoch": 0.8088933459934068, "grad_norm": 0.8167903138114637, "learning_rate": 9.346140709791885e-06, "loss": 0.5219, "num_tokens": 452440591.0, "step": 75820 }, { "epoch": 0.8089466889996053, "grad_norm": 0.7977769390054756, "learning_rate": 9.3437961790997e-06, "loss": 0.5287, "num_tokens": 452465907.0, "step": 75825 }, { "epoch": 0.8090000320058037, "grad_norm": 0.9590583915032437, "learning_rate": 9.341452213391286e-06, "loss": 0.4804, "num_tokens": 452491987.0, "step": 75830 }, { "epoch": 0.8090533750120021, "grad_norm": 0.7323916947358186, "learning_rate": 9.339108812739585e-06, "loss": 0.3754, "num_tokens": 452526693.0, "step": 75835 }, { "epoch": 0.8091067180182007, "grad_norm": 0.9076149664629279, "learning_rate": 9.336765977217511e-06, "loss": 0.5019, "num_tokens": 452550699.0, "step": 75840 }, { "epoch": 0.8091600610243991, "grad_norm": 0.8637179856299395, "learning_rate": 9.334423706897968e-06, "loss": 0.3866, "num_tokens": 452580211.0, "step": 75845 }, { "epoch": 0.8092134040305975, "grad_norm": 0.8069344076185125, "learning_rate": 9.332082001853856e-06, "loss": 0.4897, "num_tokens": 452612044.0, "step": 75850 }, { "epoch": 0.809266747036796, "grad_norm": 1.1323021737044703, "learning_rate": 9.329740862158033e-06, "loss": 0.4726, "num_tokens": 452652739.0, "step": 75855 }, { "epoch": 0.8093200900429944, "grad_norm": 0.8673566188428065, "learning_rate": 9.327400287883342e-06, "loss": 0.6088, "num_tokens": 452685082.0, "step": 75860 }, { "epoch": 0.809373433049193, "grad_norm": 0.9529046908955855, "learning_rate": 9.325060279102637e-06, "loss": 0.4805, "num_tokens": 452716288.0, "step": 75865 }, { "epoch": 0.8094267760553914, "grad_norm": 1.0584613320340723, "learning_rate": 9.322720835888717e-06, "loss": 0.4413, "num_tokens": 452733680.0, "step": 75870 }, { "epoch": 0.8094801190615898, "grad_norm": 1.0005270997474869, "learning_rate": 9.320381958314384e-06, "loss": 0.4107, "num_tokens": 452766244.0, "step": 75875 }, { "epoch": 0.8095334620677883, "grad_norm": 0.7655130156365413, "learning_rate": 9.318043646452432e-06, "loss": 0.4719, "num_tokens": 452802062.0, "step": 75880 }, { "epoch": 0.8095868050739867, "grad_norm": 0.682802885945638, "learning_rate": 9.315705900375608e-06, "loss": 0.4648, "num_tokens": 452827603.0, "step": 75885 }, { "epoch": 0.8096401480801853, "grad_norm": 0.9187875186203549, "learning_rate": 9.31336872015667e-06, "loss": 0.5998, "num_tokens": 452849623.0, "step": 75890 }, { "epoch": 0.8096934910863837, "grad_norm": 1.1996384046384563, "learning_rate": 9.311032105868343e-06, "loss": 0.4392, "num_tokens": 452877944.0, "step": 75895 }, { "epoch": 0.8097468340925821, "grad_norm": 0.8141627387797619, "learning_rate": 9.308696057583328e-06, "loss": 0.497, "num_tokens": 452917584.0, "step": 75900 }, { "epoch": 0.8098001770987806, "grad_norm": 0.9031133646811991, "learning_rate": 9.306360575374323e-06, "loss": 0.3846, "num_tokens": 452949839.0, "step": 75905 }, { "epoch": 0.809853520104979, "grad_norm": 0.9330439415745629, "learning_rate": 9.304025659314016e-06, "loss": 0.395, "num_tokens": 452974942.0, "step": 75910 }, { "epoch": 0.8099068631111775, "grad_norm": 0.8271708081557166, "learning_rate": 9.301691309475047e-06, "loss": 0.4336, "num_tokens": 453009676.0, "step": 75915 }, { "epoch": 0.809960206117376, "grad_norm": 0.7364837320995177, "learning_rate": 9.299357525930067e-06, "loss": 0.4966, "num_tokens": 453039868.0, "step": 75920 }, { "epoch": 0.8100135491235744, "grad_norm": 0.7531480780327907, "learning_rate": 9.297024308751698e-06, "loss": 0.4903, "num_tokens": 453073226.0, "step": 75925 }, { "epoch": 0.8100668921297729, "grad_norm": 0.7383749506719777, "learning_rate": 9.294691658012546e-06, "loss": 0.5913, "num_tokens": 453119400.0, "step": 75930 }, { "epoch": 0.8101202351359713, "grad_norm": 1.0653795858840474, "learning_rate": 9.292359573785186e-06, "loss": 0.433, "num_tokens": 453147974.0, "step": 75935 }, { "epoch": 0.8101735781421697, "grad_norm": 0.8768178521541227, "learning_rate": 9.290028056142203e-06, "loss": 0.4708, "num_tokens": 453185399.0, "step": 75940 }, { "epoch": 0.8102269211483683, "grad_norm": 0.6307596119807497, "learning_rate": 9.287697105156136e-06, "loss": 0.4207, "num_tokens": 453231350.0, "step": 75945 }, { "epoch": 0.8102802641545667, "grad_norm": 1.1948878941639283, "learning_rate": 9.285366720899527e-06, "loss": 0.4909, "num_tokens": 453275677.0, "step": 75950 }, { "epoch": 0.8103336071607652, "grad_norm": 0.9984090831843212, "learning_rate": 9.283036903444897e-06, "loss": 0.4731, "num_tokens": 453303785.0, "step": 75955 }, { "epoch": 0.8103869501669636, "grad_norm": 1.5492026137081365, "learning_rate": 9.280707652864737e-06, "loss": 0.5966, "num_tokens": 453343420.0, "step": 75960 }, { "epoch": 0.810440293173162, "grad_norm": 1.073838982379237, "learning_rate": 9.278378969231533e-06, "loss": 0.3779, "num_tokens": 453367803.0, "step": 75965 }, { "epoch": 0.8104936361793605, "grad_norm": 1.3978626655447264, "learning_rate": 9.276050852617748e-06, "loss": 0.4609, "num_tokens": 453401680.0, "step": 75970 }, { "epoch": 0.810546979185559, "grad_norm": 0.6195225650589425, "learning_rate": 9.273723303095824e-06, "loss": 0.3352, "num_tokens": 453424460.0, "step": 75975 }, { "epoch": 0.8106003221917575, "grad_norm": 0.6910878751525183, "learning_rate": 9.27139632073819e-06, "loss": 0.46, "num_tokens": 453452191.0, "step": 75980 }, { "epoch": 0.8106536651979559, "grad_norm": 1.6858745166772897, "learning_rate": 9.269069905617267e-06, "loss": 0.3937, "num_tokens": 453490186.0, "step": 75985 }, { "epoch": 0.8107070082041543, "grad_norm": 1.0829547661512342, "learning_rate": 9.266744057805437e-06, "loss": 0.4746, "num_tokens": 453515001.0, "step": 75990 }, { "epoch": 0.8107603512103528, "grad_norm": 0.9661486837420651, "learning_rate": 9.264418777375078e-06, "loss": 0.5072, "num_tokens": 453540503.0, "step": 75995 }, { "epoch": 0.8108136942165513, "grad_norm": 1.0471149276721907, "learning_rate": 9.262094064398556e-06, "loss": 0.5178, "num_tokens": 453567263.0, "step": 76000 }, { "epoch": 0.8108670372227498, "grad_norm": 2.285391106715324, "learning_rate": 9.259769918948202e-06, "loss": 0.5622, "num_tokens": 453594060.0, "step": 76005 }, { "epoch": 0.8109203802289482, "grad_norm": 7.967306091550586, "learning_rate": 9.25744634109634e-06, "loss": 0.4012, "num_tokens": 453610638.0, "step": 76010 }, { "epoch": 0.8109737232351466, "grad_norm": 1.1304027190564632, "learning_rate": 9.255123330915281e-06, "loss": 0.3047, "num_tokens": 453641196.0, "step": 76015 }, { "epoch": 0.8110270662413451, "grad_norm": 0.7121635683297065, "learning_rate": 9.252800888477301e-06, "loss": 0.4305, "num_tokens": 453675672.0, "step": 76020 }, { "epoch": 0.8110804092475435, "grad_norm": 0.9755030133471837, "learning_rate": 9.250479013854677e-06, "loss": 0.4763, "num_tokens": 453706217.0, "step": 76025 }, { "epoch": 0.811133752253742, "grad_norm": 3.1364244203623364, "learning_rate": 9.248157707119669e-06, "loss": 0.5769, "num_tokens": 453743764.0, "step": 76030 }, { "epoch": 0.8111870952599405, "grad_norm": 2.1978931516753684, "learning_rate": 9.245836968344498e-06, "loss": 0.4764, "num_tokens": 453758273.0, "step": 76035 }, { "epoch": 0.8112404382661389, "grad_norm": 1.0041434274273706, "learning_rate": 9.243516797601383e-06, "loss": 0.4404, "num_tokens": 453787252.0, "step": 76040 }, { "epoch": 0.8112937812723374, "grad_norm": 0.8666267693947008, "learning_rate": 9.241197194962531e-06, "loss": 0.6655, "num_tokens": 453807928.0, "step": 76045 }, { "epoch": 0.8113471242785358, "grad_norm": 0.8232330300274406, "learning_rate": 9.238878160500111e-06, "loss": 0.4451, "num_tokens": 453846667.0, "step": 76050 }, { "epoch": 0.8114004672847343, "grad_norm": 1.0191629868857732, "learning_rate": 9.236559694286293e-06, "loss": 0.5516, "num_tokens": 453878350.0, "step": 76055 }, { "epoch": 0.8114538102909328, "grad_norm": 0.8193174199826364, "learning_rate": 9.23424179639323e-06, "loss": 0.4038, "num_tokens": 453920281.0, "step": 76060 }, { "epoch": 0.8115071532971312, "grad_norm": 0.6605151545798025, "learning_rate": 9.231924466893035e-06, "loss": 0.49, "num_tokens": 453954687.0, "step": 76065 }, { "epoch": 0.8115604963033297, "grad_norm": 1.1320981448477034, "learning_rate": 9.229607705857837e-06, "loss": 0.4365, "num_tokens": 453979832.0, "step": 76070 }, { "epoch": 0.8116138393095281, "grad_norm": 0.7887095257515085, "learning_rate": 9.227291513359716e-06, "loss": 0.4208, "num_tokens": 453999018.0, "step": 76075 }, { "epoch": 0.8116671823157265, "grad_norm": 1.1625406377191345, "learning_rate": 9.224975889470744e-06, "loss": 0.5337, "num_tokens": 454037549.0, "step": 76080 }, { "epoch": 0.8117205253219251, "grad_norm": 0.8660702021744398, "learning_rate": 9.222660834262987e-06, "loss": 0.4523, "num_tokens": 454063682.0, "step": 76085 }, { "epoch": 0.8117738683281235, "grad_norm": 1.2777735940794208, "learning_rate": 9.220346347808484e-06, "loss": 0.4664, "num_tokens": 454081284.0, "step": 76090 }, { "epoch": 0.811827211334322, "grad_norm": 0.7667756774499688, "learning_rate": 9.218032430179251e-06, "loss": 0.468, "num_tokens": 454132278.0, "step": 76095 }, { "epoch": 0.8118805543405204, "grad_norm": 0.8929745043956407, "learning_rate": 9.215719081447296e-06, "loss": 0.4862, "num_tokens": 454157627.0, "step": 76100 }, { "epoch": 0.8119338973467188, "grad_norm": 0.7374650692316621, "learning_rate": 9.213406301684613e-06, "loss": 0.3891, "num_tokens": 454184359.0, "step": 76105 }, { "epoch": 0.8119872403529174, "grad_norm": 0.7557204604594998, "learning_rate": 9.211094090963162e-06, "loss": 0.4616, "num_tokens": 454213395.0, "step": 76110 }, { "epoch": 0.8120405833591158, "grad_norm": 1.4484361302188897, "learning_rate": 9.208782449354893e-06, "loss": 0.5102, "num_tokens": 454233066.0, "step": 76115 }, { "epoch": 0.8120939263653142, "grad_norm": 2.3267230199149194, "learning_rate": 9.20647137693175e-06, "loss": 0.5889, "num_tokens": 454269283.0, "step": 76120 }, { "epoch": 0.8121472693715127, "grad_norm": 0.8563721605286616, "learning_rate": 9.204160873765632e-06, "loss": 0.4811, "num_tokens": 454295932.0, "step": 76125 }, { "epoch": 0.8122006123777111, "grad_norm": 1.0817535535535516, "learning_rate": 9.20185093992845e-06, "loss": 0.5832, "num_tokens": 454316455.0, "step": 76130 }, { "epoch": 0.8122539553839097, "grad_norm": 0.574805467248118, "learning_rate": 9.199541575492087e-06, "loss": 0.4595, "num_tokens": 454360844.0, "step": 76135 }, { "epoch": 0.8123072983901081, "grad_norm": 1.18616494580418, "learning_rate": 9.197232780528392e-06, "loss": 0.4416, "num_tokens": 454386540.0, "step": 76140 }, { "epoch": 0.8123606413963065, "grad_norm": 0.737072227373508, "learning_rate": 9.194924555109225e-06, "loss": 0.4136, "num_tokens": 454404605.0, "step": 76145 }, { "epoch": 0.812413984402505, "grad_norm": 1.3979493606759752, "learning_rate": 9.192616899306406e-06, "loss": 0.4491, "num_tokens": 454430809.0, "step": 76150 }, { "epoch": 0.8124673274087034, "grad_norm": 1.6939252219491567, "learning_rate": 9.190309813191738e-06, "loss": 0.5603, "num_tokens": 454452054.0, "step": 76155 }, { "epoch": 0.812520670414902, "grad_norm": 1.1797695641875756, "learning_rate": 9.18800329683702e-06, "loss": 0.5486, "num_tokens": 454483896.0, "step": 76160 }, { "epoch": 0.8125740134211004, "grad_norm": 0.7197982773739023, "learning_rate": 9.185697350314034e-06, "loss": 0.3755, "num_tokens": 454510240.0, "step": 76165 }, { "epoch": 0.8126273564272988, "grad_norm": 0.7496423321716131, "learning_rate": 9.183391973694518e-06, "loss": 0.4034, "num_tokens": 454528266.0, "step": 76170 }, { "epoch": 0.8126806994334973, "grad_norm": 1.0702448790995134, "learning_rate": 9.18108716705022e-06, "loss": 0.4938, "num_tokens": 454554885.0, "step": 76175 }, { "epoch": 0.8127340424396957, "grad_norm": 1.2606537332291299, "learning_rate": 9.17878293045287e-06, "loss": 0.5049, "num_tokens": 454579717.0, "step": 76180 }, { "epoch": 0.8127873854458942, "grad_norm": 0.5556928608379994, "learning_rate": 9.176479263974162e-06, "loss": 0.4924, "num_tokens": 454628734.0, "step": 76185 }, { "epoch": 0.8128407284520927, "grad_norm": 0.9932206580047142, "learning_rate": 9.174176167685775e-06, "loss": 0.4832, "num_tokens": 454644138.0, "step": 76190 }, { "epoch": 0.8128940714582911, "grad_norm": 0.7465646752808365, "learning_rate": 9.171873641659391e-06, "loss": 0.4304, "num_tokens": 454672044.0, "step": 76195 }, { "epoch": 0.8129474144644896, "grad_norm": 0.5614398481263835, "learning_rate": 9.169571685966644e-06, "loss": 0.3824, "num_tokens": 454699362.0, "step": 76200 }, { "epoch": 0.813000757470688, "grad_norm": 0.8623725150691871, "learning_rate": 9.167270300679175e-06, "loss": 0.506, "num_tokens": 454715093.0, "step": 76205 }, { "epoch": 0.8130541004768864, "grad_norm": 1.2025140309156777, "learning_rate": 9.164969485868605e-06, "loss": 0.4663, "num_tokens": 454748784.0, "step": 76210 }, { "epoch": 0.813107443483085, "grad_norm": 0.806022320069675, "learning_rate": 9.162669241606514e-06, "loss": 0.5375, "num_tokens": 454799662.0, "step": 76215 }, { "epoch": 0.8131607864892834, "grad_norm": 0.8019288443606707, "learning_rate": 9.1603695679645e-06, "loss": 0.4265, "num_tokens": 454832781.0, "step": 76220 }, { "epoch": 0.8132141294954819, "grad_norm": 0.7131257142102165, "learning_rate": 9.158070465014111e-06, "loss": 0.4802, "num_tokens": 454865518.0, "step": 76225 }, { "epoch": 0.8132674725016803, "grad_norm": 1.4380578543787423, "learning_rate": 9.15577193282689e-06, "loss": 0.4816, "num_tokens": 454884628.0, "step": 76230 }, { "epoch": 0.8133208155078787, "grad_norm": 0.5527956798228373, "learning_rate": 9.153473971474367e-06, "loss": 0.4097, "num_tokens": 454928194.0, "step": 76235 }, { "epoch": 0.8133741585140772, "grad_norm": 0.9401261205508844, "learning_rate": 9.151176581028053e-06, "loss": 0.3555, "num_tokens": 454944244.0, "step": 76240 }, { "epoch": 0.8134275015202757, "grad_norm": 0.9650273241576179, "learning_rate": 9.14887976155943e-06, "loss": 0.3642, "num_tokens": 454962652.0, "step": 76245 }, { "epoch": 0.8134808445264742, "grad_norm": 0.764137612066474, "learning_rate": 9.146583513139973e-06, "loss": 0.5078, "num_tokens": 454996112.0, "step": 76250 }, { "epoch": 0.8135341875326726, "grad_norm": 1.4435424574153906, "learning_rate": 9.144287835841144e-06, "loss": 0.474, "num_tokens": 455014939.0, "step": 76255 }, { "epoch": 0.813587530538871, "grad_norm": 1.1219573458649443, "learning_rate": 9.141992729734374e-06, "loss": 0.4887, "num_tokens": 455044628.0, "step": 76260 }, { "epoch": 0.8136408735450695, "grad_norm": 0.8643159030887169, "learning_rate": 9.139698194891078e-06, "loss": 0.4791, "num_tokens": 455075214.0, "step": 76265 }, { "epoch": 0.813694216551268, "grad_norm": 0.7454567759814059, "learning_rate": 9.137404231382666e-06, "loss": 0.457, "num_tokens": 455116374.0, "step": 76270 }, { "epoch": 0.8137475595574665, "grad_norm": 0.697021954878052, "learning_rate": 9.135110839280511e-06, "loss": 0.5087, "num_tokens": 455157080.0, "step": 76275 }, { "epoch": 0.8138009025636649, "grad_norm": 1.0180046841592099, "learning_rate": 9.132818018655983e-06, "loss": 0.4435, "num_tokens": 455180977.0, "step": 76280 }, { "epoch": 0.8138542455698633, "grad_norm": 0.9821001674058469, "learning_rate": 9.130525769580436e-06, "loss": 0.5455, "num_tokens": 455217060.0, "step": 76285 }, { "epoch": 0.8139075885760618, "grad_norm": 0.8089021539112418, "learning_rate": 9.12823409212519e-06, "loss": 0.5136, "num_tokens": 455249066.0, "step": 76290 }, { "epoch": 0.8139609315822602, "grad_norm": 1.1041990948958091, "learning_rate": 9.12594298636157e-06, "loss": 0.5187, "num_tokens": 455286723.0, "step": 76295 }, { "epoch": 0.8140142745884587, "grad_norm": 0.6528885986741199, "learning_rate": 9.123652452360862e-06, "loss": 0.4195, "num_tokens": 455325755.0, "step": 76300 }, { "epoch": 0.8140676175946572, "grad_norm": 1.193735023196034, "learning_rate": 9.121362490194334e-06, "loss": 0.4806, "num_tokens": 455351635.0, "step": 76305 }, { "epoch": 0.8141209606008556, "grad_norm": 1.090892146679182, "learning_rate": 9.119073099933259e-06, "loss": 0.456, "num_tokens": 455392889.0, "step": 76310 }, { "epoch": 0.8141743036070541, "grad_norm": 0.932855438464076, "learning_rate": 9.11678428164888e-06, "loss": 0.478, "num_tokens": 455423561.0, "step": 76315 }, { "epoch": 0.8142276466132525, "grad_norm": 0.872539677022638, "learning_rate": 9.114496035412404e-06, "loss": 0.5021, "num_tokens": 455448327.0, "step": 76320 }, { "epoch": 0.814280989619451, "grad_norm": 0.6238798527888768, "learning_rate": 9.112208361295049e-06, "loss": 0.3811, "num_tokens": 455468956.0, "step": 76325 }, { "epoch": 0.8143343326256495, "grad_norm": 0.8758223729881729, "learning_rate": 9.109921259368007e-06, "loss": 0.3521, "num_tokens": 455496170.0, "step": 76330 }, { "epoch": 0.8143876756318479, "grad_norm": 5.182722679273582, "learning_rate": 9.107634729702438e-06, "loss": 0.4609, "num_tokens": 455516522.0, "step": 76335 }, { "epoch": 0.8144410186380464, "grad_norm": 0.8378873648574107, "learning_rate": 9.105348772369495e-06, "loss": 0.3298, "num_tokens": 455549263.0, "step": 76340 }, { "epoch": 0.8144943616442448, "grad_norm": 0.7178533451429518, "learning_rate": 9.103063387440319e-06, "loss": 0.5523, "num_tokens": 455594796.0, "step": 76345 }, { "epoch": 0.8145477046504432, "grad_norm": 0.9212776557144204, "learning_rate": 9.100778574986015e-06, "loss": 0.582, "num_tokens": 455634696.0, "step": 76350 }, { "epoch": 0.8146010476566418, "grad_norm": 0.9121539051139941, "learning_rate": 9.09849433507769e-06, "loss": 0.4785, "num_tokens": 455667857.0, "step": 76355 }, { "epoch": 0.8146543906628402, "grad_norm": 0.8281557709665951, "learning_rate": 9.096210667786425e-06, "loss": 0.3607, "num_tokens": 455684915.0, "step": 76360 }, { "epoch": 0.8147077336690387, "grad_norm": 0.842651287088762, "learning_rate": 9.093927573183285e-06, "loss": 0.431, "num_tokens": 455722951.0, "step": 76365 }, { "epoch": 0.8147610766752371, "grad_norm": 0.9458932359482483, "learning_rate": 9.09164505133931e-06, "loss": 0.5129, "num_tokens": 455748188.0, "step": 76370 }, { "epoch": 0.8148144196814355, "grad_norm": 0.570399728739337, "learning_rate": 9.089363102325529e-06, "loss": 0.4377, "num_tokens": 455765349.0, "step": 76375 }, { "epoch": 0.8148677626876341, "grad_norm": 0.6679422422030539, "learning_rate": 9.087081726212948e-06, "loss": 0.3551, "num_tokens": 455786726.0, "step": 76380 }, { "epoch": 0.8149211056938325, "grad_norm": 1.501026360890889, "learning_rate": 9.084800923072565e-06, "loss": 0.4881, "num_tokens": 455811093.0, "step": 76385 }, { "epoch": 0.8149744487000309, "grad_norm": 0.8486188225033708, "learning_rate": 9.082520692975353e-06, "loss": 0.5027, "num_tokens": 455844167.0, "step": 76390 }, { "epoch": 0.8150277917062294, "grad_norm": 2.5815506484140975, "learning_rate": 9.080241035992262e-06, "loss": 0.5087, "num_tokens": 455871874.0, "step": 76395 }, { "epoch": 0.8150811347124278, "grad_norm": 1.6076913645359083, "learning_rate": 9.077961952194241e-06, "loss": 0.4887, "num_tokens": 455903222.0, "step": 76400 }, { "epoch": 0.8151344777186263, "grad_norm": 0.9432734781596988, "learning_rate": 9.075683441652205e-06, "loss": 0.4835, "num_tokens": 455930204.0, "step": 76405 }, { "epoch": 0.8151878207248248, "grad_norm": 0.9082587396861321, "learning_rate": 9.073405504437049e-06, "loss": 0.4136, "num_tokens": 455950655.0, "step": 76410 }, { "epoch": 0.8152411637310232, "grad_norm": 1.0472264252707328, "learning_rate": 9.071128140619663e-06, "loss": 0.4486, "num_tokens": 455981583.0, "step": 76415 }, { "epoch": 0.8152945067372217, "grad_norm": 1.1944678726369875, "learning_rate": 9.068851350270924e-06, "loss": 0.3818, "num_tokens": 456005919.0, "step": 76420 }, { "epoch": 0.8153478497434201, "grad_norm": 0.8650620695898936, "learning_rate": 9.066575133461664e-06, "loss": 0.4472, "num_tokens": 456050834.0, "step": 76425 }, { "epoch": 0.8154011927496186, "grad_norm": 0.8528769137982511, "learning_rate": 9.064299490262724e-06, "loss": 0.4452, "num_tokens": 456067761.0, "step": 76430 }, { "epoch": 0.8154545357558171, "grad_norm": 1.0306426006012734, "learning_rate": 9.062024420744919e-06, "loss": 0.4875, "num_tokens": 456110075.0, "step": 76435 }, { "epoch": 0.8155078787620155, "grad_norm": 0.8531835065965613, "learning_rate": 9.059749924979045e-06, "loss": 0.557, "num_tokens": 456134037.0, "step": 76440 }, { "epoch": 0.815561221768214, "grad_norm": 0.5596964639255473, "learning_rate": 9.057476003035866e-06, "loss": 0.4197, "num_tokens": 456167354.0, "step": 76445 }, { "epoch": 0.8156145647744124, "grad_norm": 0.811151102781339, "learning_rate": 9.055202654986161e-06, "loss": 0.4422, "num_tokens": 456203207.0, "step": 76450 }, { "epoch": 0.8156679077806109, "grad_norm": 0.9222415053221567, "learning_rate": 9.052929880900657e-06, "loss": 0.5954, "num_tokens": 456239911.0, "step": 76455 }, { "epoch": 0.8157212507868093, "grad_norm": 0.5302757212421354, "learning_rate": 9.050657680850083e-06, "loss": 0.3438, "num_tokens": 456279812.0, "step": 76460 }, { "epoch": 0.8157745937930078, "grad_norm": 1.220413632045032, "learning_rate": 9.04838605490515e-06, "loss": 0.5193, "num_tokens": 456324206.0, "step": 76465 }, { "epoch": 0.8158279367992063, "grad_norm": 0.6093825424346929, "learning_rate": 9.04611500313654e-06, "loss": 0.5294, "num_tokens": 456370218.0, "step": 76470 }, { "epoch": 0.8158812798054047, "grad_norm": 1.1175385000194398, "learning_rate": 9.043844525614928e-06, "loss": 0.4773, "num_tokens": 456391316.0, "step": 76475 }, { "epoch": 0.8159346228116031, "grad_norm": 0.9562767794377414, "learning_rate": 9.041574622410967e-06, "loss": 0.3766, "num_tokens": 456418788.0, "step": 76480 }, { "epoch": 0.8159879658178016, "grad_norm": 1.230564285904249, "learning_rate": 9.039305293595283e-06, "loss": 0.4739, "num_tokens": 456442843.0, "step": 76485 }, { "epoch": 0.8160413088240001, "grad_norm": 0.9053493752457391, "learning_rate": 9.037036539238496e-06, "loss": 0.4323, "num_tokens": 456459159.0, "step": 76490 }, { "epoch": 0.8160946518301986, "grad_norm": 1.1938439918574848, "learning_rate": 9.034768359411217e-06, "loss": 0.4175, "num_tokens": 456486875.0, "step": 76495 }, { "epoch": 0.816147994836397, "grad_norm": 3.6751792669595647, "learning_rate": 9.03250075418401e-06, "loss": 0.4356, "num_tokens": 456507625.0, "step": 76500 }, { "epoch": 0.8162013378425954, "grad_norm": 0.7280569888314212, "learning_rate": 9.030233723627446e-06, "loss": 0.389, "num_tokens": 456541618.0, "step": 76505 }, { "epoch": 0.8162546808487939, "grad_norm": 0.924692281668505, "learning_rate": 9.027967267812077e-06, "loss": 0.5934, "num_tokens": 456573442.0, "step": 76510 }, { "epoch": 0.8163080238549923, "grad_norm": 2.8037762747563355, "learning_rate": 9.025701386808426e-06, "loss": 0.4149, "num_tokens": 456603968.0, "step": 76515 }, { "epoch": 0.8163613668611909, "grad_norm": 1.341605754218566, "learning_rate": 9.023436080686992e-06, "loss": 0.4587, "num_tokens": 456637548.0, "step": 76520 }, { "epoch": 0.8164147098673893, "grad_norm": 0.9416407149417164, "learning_rate": 9.021171349518281e-06, "loss": 0.3118, "num_tokens": 456654233.0, "step": 76525 }, { "epoch": 0.8164680528735877, "grad_norm": 0.8154656037272654, "learning_rate": 9.018907193372758e-06, "loss": 0.5299, "num_tokens": 456685571.0, "step": 76530 }, { "epoch": 0.8165213958797862, "grad_norm": 1.0632782603205182, "learning_rate": 9.01664361232088e-06, "loss": 0.4899, "num_tokens": 456713087.0, "step": 76535 }, { "epoch": 0.8165747388859846, "grad_norm": 0.8470249974031103, "learning_rate": 9.014380606433093e-06, "loss": 0.6183, "num_tokens": 456739354.0, "step": 76540 }, { "epoch": 0.8166280818921832, "grad_norm": 0.7798854868857076, "learning_rate": 9.012118175779805e-06, "loss": 0.3982, "num_tokens": 456758558.0, "step": 76545 }, { "epoch": 0.8166814248983816, "grad_norm": 1.9321807672994187, "learning_rate": 9.009856320431428e-06, "loss": 0.4623, "num_tokens": 456776486.0, "step": 76550 }, { "epoch": 0.81673476790458, "grad_norm": 0.6709628886732392, "learning_rate": 9.007595040458347e-06, "loss": 0.6152, "num_tokens": 456813190.0, "step": 76555 }, { "epoch": 0.8167881109107785, "grad_norm": 24.462321004399776, "learning_rate": 9.005334335930915e-06, "loss": 0.5733, "num_tokens": 456841238.0, "step": 76560 }, { "epoch": 0.8168414539169769, "grad_norm": 1.054587801489236, "learning_rate": 9.00307420691949e-06, "loss": 0.376, "num_tokens": 456866431.0, "step": 76565 }, { "epoch": 0.8168947969231753, "grad_norm": 1.8571257274064867, "learning_rate": 9.000814653494408e-06, "loss": 0.4794, "num_tokens": 456891168.0, "step": 76570 }, { "epoch": 0.8169481399293739, "grad_norm": 0.9206634349400876, "learning_rate": 8.998555675725969e-06, "loss": 0.4174, "num_tokens": 456938959.0, "step": 76575 }, { "epoch": 0.8170014829355723, "grad_norm": 1.1854935869573497, "learning_rate": 8.996297273684472e-06, "loss": 0.4203, "num_tokens": 456961489.0, "step": 76580 }, { "epoch": 0.8170548259417708, "grad_norm": 0.8441493441271531, "learning_rate": 8.994039447440205e-06, "loss": 0.4638, "num_tokens": 457008841.0, "step": 76585 }, { "epoch": 0.8171081689479692, "grad_norm": 0.9385716392283056, "learning_rate": 8.99178219706342e-06, "loss": 0.3807, "num_tokens": 457031837.0, "step": 76590 }, { "epoch": 0.8171615119541676, "grad_norm": 1.039416969706922, "learning_rate": 8.989525522624347e-06, "loss": 0.414, "num_tokens": 457066576.0, "step": 76595 }, { "epoch": 0.8172148549603662, "grad_norm": 1.2268094652124433, "learning_rate": 8.98726942419322e-06, "loss": 0.3672, "num_tokens": 457093565.0, "step": 76600 }, { "epoch": 0.8172681979665646, "grad_norm": 1.2906594288077435, "learning_rate": 8.985013901840248e-06, "loss": 0.4383, "num_tokens": 457114725.0, "step": 76605 }, { "epoch": 0.8173215409727631, "grad_norm": 1.1340810276651565, "learning_rate": 8.982758955635603e-06, "loss": 0.6542, "num_tokens": 457152379.0, "step": 76610 }, { "epoch": 0.8173748839789615, "grad_norm": 0.9131133519571188, "learning_rate": 8.980504585649468e-06, "loss": 0.5357, "num_tokens": 457172517.0, "step": 76615 }, { "epoch": 0.8174282269851599, "grad_norm": 0.6926752614437025, "learning_rate": 8.978250791951996e-06, "loss": 0.4516, "num_tokens": 457194177.0, "step": 76620 }, { "epoch": 0.8174815699913585, "grad_norm": 0.9686201962400485, "learning_rate": 8.975997574613313e-06, "loss": 0.5885, "num_tokens": 457240565.0, "step": 76625 }, { "epoch": 0.8175349129975569, "grad_norm": 1.6832324448154528, "learning_rate": 8.973744933703529e-06, "loss": 0.447, "num_tokens": 457261454.0, "step": 76630 }, { "epoch": 0.8175882560037554, "grad_norm": 0.5981067713892512, "learning_rate": 8.971492869292758e-06, "loss": 0.5023, "num_tokens": 457290454.0, "step": 76635 }, { "epoch": 0.8176415990099538, "grad_norm": 0.7330704543631824, "learning_rate": 8.96924138145106e-06, "loss": 0.4749, "num_tokens": 457325756.0, "step": 76640 }, { "epoch": 0.8176949420161522, "grad_norm": 1.0095655630671836, "learning_rate": 8.96699047024851e-06, "loss": 0.4747, "num_tokens": 457348709.0, "step": 76645 }, { "epoch": 0.8177482850223508, "grad_norm": 0.9133770803361736, "learning_rate": 8.964740135755153e-06, "loss": 0.4598, "num_tokens": 457370335.0, "step": 76650 }, { "epoch": 0.8178016280285492, "grad_norm": 1.559042941547567, "learning_rate": 8.962490378041011e-06, "loss": 0.4428, "num_tokens": 457389372.0, "step": 76655 }, { "epoch": 0.8178549710347476, "grad_norm": 0.9587062158048338, "learning_rate": 8.960241197176087e-06, "loss": 0.4122, "num_tokens": 457429481.0, "step": 76660 }, { "epoch": 0.8179083140409461, "grad_norm": 0.8314942302367081, "learning_rate": 8.957992593230381e-06, "loss": 0.4299, "num_tokens": 457457448.0, "step": 76665 }, { "epoch": 0.8179616570471445, "grad_norm": 0.7766370648358033, "learning_rate": 8.95574456627385e-06, "loss": 0.6348, "num_tokens": 457508042.0, "step": 76670 }, { "epoch": 0.818015000053343, "grad_norm": 0.9700411803236733, "learning_rate": 8.953497116376459e-06, "loss": 0.439, "num_tokens": 457536735.0, "step": 76675 }, { "epoch": 0.8180683430595415, "grad_norm": 1.1454290192826853, "learning_rate": 8.95125024360815e-06, "loss": 0.4696, "num_tokens": 457559017.0, "step": 76680 }, { "epoch": 0.8181216860657399, "grad_norm": 1.064464743398525, "learning_rate": 8.949003948038826e-06, "loss": 0.3934, "num_tokens": 457605282.0, "step": 76685 }, { "epoch": 0.8181750290719384, "grad_norm": 1.0182606872271118, "learning_rate": 8.946758229738397e-06, "loss": 0.4637, "num_tokens": 457649544.0, "step": 76690 }, { "epoch": 0.8182283720781368, "grad_norm": 0.8438156022023865, "learning_rate": 8.944513088776748e-06, "loss": 0.4018, "num_tokens": 457673579.0, "step": 76695 }, { "epoch": 0.8182817150843353, "grad_norm": 0.5520648968611608, "learning_rate": 8.942268525223728e-06, "loss": 0.5322, "num_tokens": 457712357.0, "step": 76700 }, { "epoch": 0.8183350580905338, "grad_norm": 0.5720910437250221, "learning_rate": 8.940024539149195e-06, "loss": 0.3823, "num_tokens": 457742272.0, "step": 76705 }, { "epoch": 0.8183884010967322, "grad_norm": 0.8600601283101486, "learning_rate": 8.937781130622978e-06, "loss": 0.4238, "num_tokens": 457787340.0, "step": 76710 }, { "epoch": 0.8184417441029307, "grad_norm": 1.0823577687238197, "learning_rate": 8.93553829971488e-06, "loss": 0.4022, "num_tokens": 457806845.0, "step": 76715 }, { "epoch": 0.8184950871091291, "grad_norm": 0.7449284931768134, "learning_rate": 8.9332960464947e-06, "loss": 0.5096, "num_tokens": 457834887.0, "step": 76720 }, { "epoch": 0.8185484301153276, "grad_norm": 0.9319519028109851, "learning_rate": 8.93105437103221e-06, "loss": 0.67, "num_tokens": 457878984.0, "step": 76725 }, { "epoch": 0.818601773121526, "grad_norm": 1.2209555415158693, "learning_rate": 8.92881327339717e-06, "loss": 0.5086, "num_tokens": 457908458.0, "step": 76730 }, { "epoch": 0.8186551161277245, "grad_norm": 0.9002504738501378, "learning_rate": 8.92657275365931e-06, "loss": 0.3877, "num_tokens": 457936301.0, "step": 76735 }, { "epoch": 0.818708459133923, "grad_norm": 0.8245843938672215, "learning_rate": 8.924332811888359e-06, "loss": 0.5351, "num_tokens": 457986389.0, "step": 76740 }, { "epoch": 0.8187618021401214, "grad_norm": 1.1406307111098892, "learning_rate": 8.922093448154009e-06, "loss": 0.5348, "num_tokens": 458027152.0, "step": 76745 }, { "epoch": 0.8188151451463198, "grad_norm": 0.7366911889721189, "learning_rate": 8.919854662525954e-06, "loss": 0.4543, "num_tokens": 458048266.0, "step": 76750 }, { "epoch": 0.8188684881525183, "grad_norm": 0.9672012425534409, "learning_rate": 8.91761645507386e-06, "loss": 0.5462, "num_tokens": 458072032.0, "step": 76755 }, { "epoch": 0.8189218311587168, "grad_norm": 0.7985735773614505, "learning_rate": 8.915378825867368e-06, "loss": 0.4675, "num_tokens": 458096207.0, "step": 76760 }, { "epoch": 0.8189751741649153, "grad_norm": 1.1441497096864304, "learning_rate": 8.913141774976119e-06, "loss": 0.5038, "num_tokens": 458117364.0, "step": 76765 }, { "epoch": 0.8190285171711137, "grad_norm": 0.7419237106344024, "learning_rate": 8.91090530246972e-06, "loss": 0.4761, "num_tokens": 458141638.0, "step": 76770 }, { "epoch": 0.8190818601773121, "grad_norm": 1.1706719195800066, "learning_rate": 8.908669408417756e-06, "loss": 0.4867, "num_tokens": 458172561.0, "step": 76775 }, { "epoch": 0.8191352031835106, "grad_norm": 1.101501935760919, "learning_rate": 8.906434092889815e-06, "loss": 0.5012, "num_tokens": 458200225.0, "step": 76780 }, { "epoch": 0.819188546189709, "grad_norm": 0.8867107331671082, "learning_rate": 8.904199355955456e-06, "loss": 0.4681, "num_tokens": 458227094.0, "step": 76785 }, { "epoch": 0.8192418891959076, "grad_norm": 0.722653698558619, "learning_rate": 8.901965197684212e-06, "loss": 0.5665, "num_tokens": 458255479.0, "step": 76790 }, { "epoch": 0.819295232202106, "grad_norm": 0.5816829263111803, "learning_rate": 8.899731618145609e-06, "loss": 0.5416, "num_tokens": 458304977.0, "step": 76795 }, { "epoch": 0.8193485752083044, "grad_norm": 0.8363547953007449, "learning_rate": 8.897498617409161e-06, "loss": 0.4365, "num_tokens": 458325861.0, "step": 76800 }, { "epoch": 0.8194019182145029, "grad_norm": 1.1102546793903274, "learning_rate": 8.895266195544342e-06, "loss": 0.5651, "num_tokens": 458370763.0, "step": 76805 }, { "epoch": 0.8194552612207013, "grad_norm": 0.8519825751000891, "learning_rate": 8.89303435262062e-06, "loss": 0.5458, "num_tokens": 458410730.0, "step": 76810 }, { "epoch": 0.8195086042268999, "grad_norm": 0.86081434546841, "learning_rate": 8.890803088707453e-06, "loss": 0.4315, "num_tokens": 458444477.0, "step": 76815 }, { "epoch": 0.8195619472330983, "grad_norm": 0.6335287935767653, "learning_rate": 8.888572403874266e-06, "loss": 0.448, "num_tokens": 458484948.0, "step": 76820 }, { "epoch": 0.8196152902392967, "grad_norm": 1.050218485817564, "learning_rate": 8.886342298190475e-06, "loss": 0.5333, "num_tokens": 458508425.0, "step": 76825 }, { "epoch": 0.8196686332454952, "grad_norm": 0.9073822979292981, "learning_rate": 8.884112771725484e-06, "loss": 0.2922, "num_tokens": 458527003.0, "step": 76830 }, { "epoch": 0.8197219762516936, "grad_norm": 1.2068610647647637, "learning_rate": 8.88188382454866e-06, "loss": 0.441, "num_tokens": 458559758.0, "step": 76835 }, { "epoch": 0.819775319257892, "grad_norm": 0.8139486060039013, "learning_rate": 8.879655456729375e-06, "loss": 0.572, "num_tokens": 458597124.0, "step": 76840 }, { "epoch": 0.8198286622640906, "grad_norm": 0.6961169877476566, "learning_rate": 8.877427668336962e-06, "loss": 0.4552, "num_tokens": 458626517.0, "step": 76845 }, { "epoch": 0.819882005270289, "grad_norm": 4.164050151204855, "learning_rate": 8.875200459440745e-06, "loss": 0.561, "num_tokens": 458658945.0, "step": 76850 }, { "epoch": 0.8199353482764875, "grad_norm": 0.8625504820176471, "learning_rate": 8.872973830110034e-06, "loss": 0.4008, "num_tokens": 458688093.0, "step": 76855 }, { "epoch": 0.8199886912826859, "grad_norm": 0.9753624099463714, "learning_rate": 8.870747780414118e-06, "loss": 0.4183, "num_tokens": 458707378.0, "step": 76860 }, { "epoch": 0.8200420342888843, "grad_norm": 0.8800709067582412, "learning_rate": 8.868522310422264e-06, "loss": 0.4527, "num_tokens": 458736282.0, "step": 76865 }, { "epoch": 0.8200953772950829, "grad_norm": 0.9063338978228797, "learning_rate": 8.866297420203726e-06, "loss": 0.3963, "num_tokens": 458750315.0, "step": 76870 }, { "epoch": 0.8201487203012813, "grad_norm": 0.6414306330783219, "learning_rate": 8.864073109827742e-06, "loss": 0.4764, "num_tokens": 458790841.0, "step": 76875 }, { "epoch": 0.8202020633074798, "grad_norm": 1.1561986535309312, "learning_rate": 8.86184937936352e-06, "loss": 0.475, "num_tokens": 458829837.0, "step": 76880 }, { "epoch": 0.8202554063136782, "grad_norm": 1.8777014955688927, "learning_rate": 8.859626228880261e-06, "loss": 0.5665, "num_tokens": 458868723.0, "step": 76885 }, { "epoch": 0.8203087493198766, "grad_norm": 1.1260497366493891, "learning_rate": 8.857403658447149e-06, "loss": 0.7029, "num_tokens": 458883896.0, "step": 76890 }, { "epoch": 0.8203620923260752, "grad_norm": 1.075029667235319, "learning_rate": 8.855181668133337e-06, "loss": 0.4543, "num_tokens": 458904841.0, "step": 76895 }, { "epoch": 0.8204154353322736, "grad_norm": 0.8410478588923866, "learning_rate": 8.852960258007973e-06, "loss": 0.4101, "num_tokens": 458929894.0, "step": 76900 }, { "epoch": 0.8204687783384721, "grad_norm": 0.6551831737444858, "learning_rate": 8.850739428140189e-06, "loss": 0.449, "num_tokens": 458968764.0, "step": 76905 }, { "epoch": 0.8205221213446705, "grad_norm": 0.6582989512670814, "learning_rate": 8.848519178599083e-06, "loss": 0.3927, "num_tokens": 458992979.0, "step": 76910 }, { "epoch": 0.8205754643508689, "grad_norm": 1.2159892928116098, "learning_rate": 8.846299509453754e-06, "loss": 0.486, "num_tokens": 459010334.0, "step": 76915 }, { "epoch": 0.8206288073570674, "grad_norm": 6.582775293872474, "learning_rate": 8.844080420773269e-06, "loss": 0.601, "num_tokens": 459036180.0, "step": 76920 }, { "epoch": 0.8206821503632659, "grad_norm": 1.062961166809095, "learning_rate": 8.841861912626675e-06, "loss": 0.5225, "num_tokens": 459061097.0, "step": 76925 }, { "epoch": 0.8207354933694643, "grad_norm": 0.791427531893836, "learning_rate": 8.839643985083012e-06, "loss": 0.3948, "num_tokens": 459093958.0, "step": 76930 }, { "epoch": 0.8207888363756628, "grad_norm": 1.2922739891687451, "learning_rate": 8.837426638211305e-06, "loss": 0.5543, "num_tokens": 459124659.0, "step": 76935 }, { "epoch": 0.8208421793818612, "grad_norm": 1.018505819968292, "learning_rate": 8.835209872080541e-06, "loss": 0.4738, "num_tokens": 459157746.0, "step": 76940 }, { "epoch": 0.8208955223880597, "grad_norm": 1.2005508708172479, "learning_rate": 8.832993686759717e-06, "loss": 0.5559, "num_tokens": 459186788.0, "step": 76945 }, { "epoch": 0.8209488653942582, "grad_norm": 1.7355148607117132, "learning_rate": 8.83077808231778e-06, "loss": 0.6282, "num_tokens": 459234238.0, "step": 76950 }, { "epoch": 0.8210022084004566, "grad_norm": 0.8110395492885056, "learning_rate": 8.82856305882368e-06, "loss": 0.393, "num_tokens": 459254610.0, "step": 76955 }, { "epoch": 0.8210555514066551, "grad_norm": 1.3943001875204846, "learning_rate": 8.826348616346345e-06, "loss": 0.4837, "num_tokens": 459289820.0, "step": 76960 }, { "epoch": 0.8211088944128535, "grad_norm": 0.9715203629189341, "learning_rate": 8.824134754954688e-06, "loss": 0.5136, "num_tokens": 459339599.0, "step": 76965 }, { "epoch": 0.821162237419052, "grad_norm": 0.7138007193897811, "learning_rate": 8.82192147471759e-06, "loss": 0.414, "num_tokens": 459369773.0, "step": 76970 }, { "epoch": 0.8212155804252504, "grad_norm": 0.8627160735474859, "learning_rate": 8.819708775703933e-06, "loss": 0.4049, "num_tokens": 459395699.0, "step": 76975 }, { "epoch": 0.8212689234314489, "grad_norm": 1.3558466512934695, "learning_rate": 8.817496657982572e-06, "loss": 0.3867, "num_tokens": 459406960.0, "step": 76980 }, { "epoch": 0.8213222664376474, "grad_norm": 0.5911191982868638, "learning_rate": 8.815285121622341e-06, "loss": 0.4338, "num_tokens": 459449901.0, "step": 76985 }, { "epoch": 0.8213756094438458, "grad_norm": 0.8030787377390697, "learning_rate": 8.813074166692051e-06, "loss": 0.4643, "num_tokens": 459484010.0, "step": 76990 }, { "epoch": 0.8214289524500443, "grad_norm": 1.6061031943015518, "learning_rate": 8.810863793260515e-06, "loss": 0.4602, "num_tokens": 459532257.0, "step": 76995 }, { "epoch": 0.8214822954562427, "grad_norm": 1.1663572840907288, "learning_rate": 8.808654001396505e-06, "loss": 0.3989, "num_tokens": 459552832.0, "step": 77000 }, { "epoch": 0.8215356384624412, "grad_norm": 1.058250922133547, "learning_rate": 8.806444791168786e-06, "loss": 0.4793, "num_tokens": 459578152.0, "step": 77005 }, { "epoch": 0.8215889814686397, "grad_norm": 1.3199603085865184, "learning_rate": 8.804236162646116e-06, "loss": 0.4517, "num_tokens": 459595726.0, "step": 77010 }, { "epoch": 0.8216423244748381, "grad_norm": 0.8282246658079511, "learning_rate": 8.802028115897207e-06, "loss": 0.4316, "num_tokens": 459617092.0, "step": 77015 }, { "epoch": 0.8216956674810365, "grad_norm": 1.1775993617714922, "learning_rate": 8.799820650990781e-06, "loss": 0.4045, "num_tokens": 459631794.0, "step": 77020 }, { "epoch": 0.821749010487235, "grad_norm": 0.9684394802104003, "learning_rate": 8.797613767995528e-06, "loss": 0.57, "num_tokens": 459653719.0, "step": 77025 }, { "epoch": 0.8218023534934334, "grad_norm": 1.3001161548073887, "learning_rate": 8.795407466980112e-06, "loss": 0.41, "num_tokens": 459688609.0, "step": 77030 }, { "epoch": 0.821855696499632, "grad_norm": 1.6984122285513787, "learning_rate": 8.793201748013193e-06, "loss": 0.4086, "num_tokens": 459701149.0, "step": 77035 }, { "epoch": 0.8219090395058304, "grad_norm": 1.001453665358946, "learning_rate": 8.79099661116342e-06, "loss": 0.5467, "num_tokens": 459735693.0, "step": 77040 }, { "epoch": 0.8219623825120288, "grad_norm": 0.8719561775108073, "learning_rate": 8.788792056499398e-06, "loss": 0.5777, "num_tokens": 459773803.0, "step": 77045 }, { "epoch": 0.8220157255182273, "grad_norm": 0.8844214055054015, "learning_rate": 8.786588084089728e-06, "loss": 0.387, "num_tokens": 459795750.0, "step": 77050 }, { "epoch": 0.8220690685244257, "grad_norm": 0.7566085882396928, "learning_rate": 8.78438469400301e-06, "loss": 0.484, "num_tokens": 459830915.0, "step": 77055 }, { "epoch": 0.8221224115306243, "grad_norm": 2.759248813374944, "learning_rate": 8.782181886307792e-06, "loss": 0.5662, "num_tokens": 459873935.0, "step": 77060 }, { "epoch": 0.8221757545368227, "grad_norm": 1.498603557224351, "learning_rate": 8.779979661072623e-06, "loss": 0.506, "num_tokens": 459903142.0, "step": 77065 }, { "epoch": 0.8222290975430211, "grad_norm": 0.7337306517543604, "learning_rate": 8.777778018366042e-06, "loss": 0.3894, "num_tokens": 459927142.0, "step": 77070 }, { "epoch": 0.8222824405492196, "grad_norm": 0.8186941563855074, "learning_rate": 8.775576958256546e-06, "loss": 0.5209, "num_tokens": 459973476.0, "step": 77075 }, { "epoch": 0.822335783555418, "grad_norm": 3.4963819294577574, "learning_rate": 8.773376480812634e-06, "loss": 0.5388, "num_tokens": 460001466.0, "step": 77080 }, { "epoch": 0.8223891265616166, "grad_norm": 0.8412557016171421, "learning_rate": 8.771176586102787e-06, "loss": 0.4017, "num_tokens": 460032545.0, "step": 77085 }, { "epoch": 0.822442469567815, "grad_norm": 0.6986649046315294, "learning_rate": 8.768977274195445e-06, "loss": 0.4424, "num_tokens": 460072534.0, "step": 77090 }, { "epoch": 0.8224958125740134, "grad_norm": 0.8597980386702624, "learning_rate": 8.766778545159064e-06, "loss": 0.6148, "num_tokens": 460100303.0, "step": 77095 }, { "epoch": 0.8225491555802119, "grad_norm": 5.199103574790722, "learning_rate": 8.764580399062056e-06, "loss": 0.5862, "num_tokens": 460117329.0, "step": 77100 }, { "epoch": 0.8226024985864103, "grad_norm": 1.2194070929710945, "learning_rate": 8.762382835972815e-06, "loss": 0.4761, "num_tokens": 460134436.0, "step": 77105 }, { "epoch": 0.8226558415926087, "grad_norm": 0.8885973859060731, "learning_rate": 8.760185855959733e-06, "loss": 0.3591, "num_tokens": 460154296.0, "step": 77110 }, { "epoch": 0.8227091845988073, "grad_norm": 0.9387202946191096, "learning_rate": 8.75798945909118e-06, "loss": 0.5312, "num_tokens": 460186557.0, "step": 77115 }, { "epoch": 0.8227625276050057, "grad_norm": 0.7988324342267812, "learning_rate": 8.755793645435492e-06, "loss": 0.5316, "num_tokens": 460227692.0, "step": 77120 }, { "epoch": 0.8228158706112042, "grad_norm": 1.5544579959725637, "learning_rate": 8.753598415061004e-06, "loss": 0.4487, "num_tokens": 460257612.0, "step": 77125 }, { "epoch": 0.8228692136174026, "grad_norm": 1.2843248063606478, "learning_rate": 8.751403768036031e-06, "loss": 0.3473, "num_tokens": 460286048.0, "step": 77130 }, { "epoch": 0.822922556623601, "grad_norm": 0.8439714507920599, "learning_rate": 8.749209704428864e-06, "loss": 0.5259, "num_tokens": 460311352.0, "step": 77135 }, { "epoch": 0.8229758996297996, "grad_norm": 0.8968697328868059, "learning_rate": 8.747016224307772e-06, "loss": 0.4049, "num_tokens": 460331877.0, "step": 77140 }, { "epoch": 0.823029242635998, "grad_norm": 1.211343500320462, "learning_rate": 8.74482332774102e-06, "loss": 0.5166, "num_tokens": 460361636.0, "step": 77145 }, { "epoch": 0.8230825856421965, "grad_norm": 1.2438311687637171, "learning_rate": 8.742631014796834e-06, "loss": 0.3805, "num_tokens": 460376400.0, "step": 77150 }, { "epoch": 0.8231359286483949, "grad_norm": 1.0611672396755953, "learning_rate": 8.740439285543441e-06, "loss": 0.5, "num_tokens": 460401813.0, "step": 77155 }, { "epoch": 0.8231892716545933, "grad_norm": 3.1410129345409876, "learning_rate": 8.738248140049054e-06, "loss": 0.6549, "num_tokens": 460425892.0, "step": 77160 }, { "epoch": 0.8232426146607918, "grad_norm": 0.7356054285687778, "learning_rate": 8.73605757838184e-06, "loss": 0.4665, "num_tokens": 460450901.0, "step": 77165 }, { "epoch": 0.8232959576669903, "grad_norm": 1.1376459587312642, "learning_rate": 8.73386760060998e-06, "loss": 0.4561, "num_tokens": 460475159.0, "step": 77170 }, { "epoch": 0.8233493006731888, "grad_norm": 0.9798033044338129, "learning_rate": 8.73167820680161e-06, "loss": 0.3843, "num_tokens": 460498234.0, "step": 77175 }, { "epoch": 0.8234026436793872, "grad_norm": 0.7876788033485573, "learning_rate": 8.729489397024856e-06, "loss": 0.3869, "num_tokens": 460531542.0, "step": 77180 }, { "epoch": 0.8234559866855856, "grad_norm": 1.6755903405139057, "learning_rate": 8.72730117134784e-06, "loss": 0.4272, "num_tokens": 460548934.0, "step": 77185 }, { "epoch": 0.8235093296917841, "grad_norm": 0.7421863924941791, "learning_rate": 8.725113529838654e-06, "loss": 0.4282, "num_tokens": 460581270.0, "step": 77190 }, { "epoch": 0.8235626726979826, "grad_norm": 1.1686262836497874, "learning_rate": 8.722926472565368e-06, "loss": 0.319, "num_tokens": 460606164.0, "step": 77195 }, { "epoch": 0.823616015704181, "grad_norm": 0.728294565865667, "learning_rate": 8.720739999596037e-06, "loss": 0.4416, "num_tokens": 460645314.0, "step": 77200 }, { "epoch": 0.8236693587103795, "grad_norm": 0.8083820102358066, "learning_rate": 8.718554110998712e-06, "loss": 0.4532, "num_tokens": 460675332.0, "step": 77205 }, { "epoch": 0.8237227017165779, "grad_norm": 2.064617839095166, "learning_rate": 8.716368806841404e-06, "loss": 0.5381, "num_tokens": 460683689.0, "step": 77210 }, { "epoch": 0.8237760447227764, "grad_norm": 1.4677274886406912, "learning_rate": 8.71418408719211e-06, "loss": 0.4017, "num_tokens": 460706607.0, "step": 77215 }, { "epoch": 0.8238293877289748, "grad_norm": 1.3480190603644002, "learning_rate": 8.711999952118824e-06, "loss": 0.5712, "num_tokens": 460744516.0, "step": 77220 }, { "epoch": 0.8238827307351733, "grad_norm": 1.1651881163214384, "learning_rate": 8.709816401689505e-06, "loss": 0.4506, "num_tokens": 460757691.0, "step": 77225 }, { "epoch": 0.8239360737413718, "grad_norm": 0.7805101316786652, "learning_rate": 8.707633435972105e-06, "loss": 0.5727, "num_tokens": 460799993.0, "step": 77230 }, { "epoch": 0.8239894167475702, "grad_norm": 0.5275297178890989, "learning_rate": 8.705451055034552e-06, "loss": 0.4703, "num_tokens": 460844700.0, "step": 77235 }, { "epoch": 0.8240427597537687, "grad_norm": 1.0642975872488776, "learning_rate": 8.703269258944754e-06, "loss": 0.3972, "num_tokens": 460875239.0, "step": 77240 }, { "epoch": 0.8240961027599671, "grad_norm": 1.644732291434856, "learning_rate": 8.701088047770616e-06, "loss": 0.4213, "num_tokens": 460907803.0, "step": 77245 }, { "epoch": 0.8241494457661656, "grad_norm": 0.8089629814529978, "learning_rate": 8.69890742158e-06, "loss": 0.4543, "num_tokens": 460932077.0, "step": 77250 }, { "epoch": 0.8242027887723641, "grad_norm": 0.9330737921858095, "learning_rate": 8.696727380440762e-06, "loss": 0.4746, "num_tokens": 460954460.0, "step": 77255 }, { "epoch": 0.8242561317785625, "grad_norm": 0.8863513207855824, "learning_rate": 8.694547924420745e-06, "loss": 0.4483, "num_tokens": 460980599.0, "step": 77260 }, { "epoch": 0.824309474784761, "grad_norm": 0.8627845465650756, "learning_rate": 8.692369053587775e-06, "loss": 0.5882, "num_tokens": 461009946.0, "step": 77265 }, { "epoch": 0.8243628177909594, "grad_norm": 0.9486991902340267, "learning_rate": 8.69019076800964e-06, "loss": 0.6031, "num_tokens": 461045776.0, "step": 77270 }, { "epoch": 0.8244161607971578, "grad_norm": 0.9203063248826299, "learning_rate": 8.68801306775414e-06, "loss": 0.6802, "num_tokens": 461074564.0, "step": 77275 }, { "epoch": 0.8244695038033564, "grad_norm": 1.4287575073475125, "learning_rate": 8.685835952889031e-06, "loss": 0.5344, "num_tokens": 461096140.0, "step": 77280 }, { "epoch": 0.8245228468095548, "grad_norm": 0.9939165360015177, "learning_rate": 8.68365942348206e-06, "loss": 0.3232, "num_tokens": 461118387.0, "step": 77285 }, { "epoch": 0.8245761898157532, "grad_norm": 1.4079690476419464, "learning_rate": 8.681483479600954e-06, "loss": 0.415, "num_tokens": 461153064.0, "step": 77290 }, { "epoch": 0.8246295328219517, "grad_norm": 1.2241868672074314, "learning_rate": 8.679308121313435e-06, "loss": 0.4665, "num_tokens": 461176915.0, "step": 77295 }, { "epoch": 0.8246828758281501, "grad_norm": 0.8206578427784221, "learning_rate": 8.67713334868718e-06, "loss": 0.3435, "num_tokens": 461194954.0, "step": 77300 }, { "epoch": 0.8247362188343487, "grad_norm": 0.8374369964848802, "learning_rate": 8.674959161789875e-06, "loss": 0.4457, "num_tokens": 461227938.0, "step": 77305 }, { "epoch": 0.8247895618405471, "grad_norm": 0.8142561207246839, "learning_rate": 8.672785560689177e-06, "loss": 0.5209, "num_tokens": 461264021.0, "step": 77310 }, { "epoch": 0.8248429048467455, "grad_norm": 1.1270068593612934, "learning_rate": 8.670612545452722e-06, "loss": 0.5012, "num_tokens": 461296572.0, "step": 77315 }, { "epoch": 0.824896247852944, "grad_norm": 0.6666038367055871, "learning_rate": 8.668440116148122e-06, "loss": 0.4069, "num_tokens": 461321565.0, "step": 77320 }, { "epoch": 0.8249495908591424, "grad_norm": 1.0876524750284557, "learning_rate": 8.666268272842986e-06, "loss": 0.5167, "num_tokens": 461352744.0, "step": 77325 }, { "epoch": 0.825002933865341, "grad_norm": 0.9199543528117408, "learning_rate": 8.664097015604897e-06, "loss": 0.4779, "num_tokens": 461385247.0, "step": 77330 }, { "epoch": 0.8250562768715394, "grad_norm": 1.0335866429225338, "learning_rate": 8.661926344501414e-06, "loss": 0.4375, "num_tokens": 461434443.0, "step": 77335 }, { "epoch": 0.8251096198777378, "grad_norm": 0.5816002845565355, "learning_rate": 8.659756259600097e-06, "loss": 0.5272, "num_tokens": 461474921.0, "step": 77340 }, { "epoch": 0.8251629628839363, "grad_norm": 0.8529727487544168, "learning_rate": 8.657586760968459e-06, "loss": 0.4961, "num_tokens": 461508839.0, "step": 77345 }, { "epoch": 0.8252163058901347, "grad_norm": 0.6097619543284809, "learning_rate": 8.655417848674021e-06, "loss": 0.4516, "num_tokens": 461545849.0, "step": 77350 }, { "epoch": 0.8252696488963333, "grad_norm": 0.8414219675003496, "learning_rate": 8.653249522784276e-06, "loss": 0.4148, "num_tokens": 461570104.0, "step": 77355 }, { "epoch": 0.8253229919025317, "grad_norm": 0.9910308005851804, "learning_rate": 8.651081783366685e-06, "loss": 0.4433, "num_tokens": 461597180.0, "step": 77360 }, { "epoch": 0.8253763349087301, "grad_norm": 0.7989208183189441, "learning_rate": 8.648914630488713e-06, "loss": 0.4494, "num_tokens": 461636680.0, "step": 77365 }, { "epoch": 0.8254296779149286, "grad_norm": 1.571428180918844, "learning_rate": 8.646748064217804e-06, "loss": 0.5154, "num_tokens": 461664645.0, "step": 77370 }, { "epoch": 0.825483020921127, "grad_norm": 0.5496099135777213, "learning_rate": 8.64458208462136e-06, "loss": 0.4724, "num_tokens": 461707790.0, "step": 77375 }, { "epoch": 0.8255363639273254, "grad_norm": 1.7663095883520028, "learning_rate": 8.642416691766794e-06, "loss": 0.3205, "num_tokens": 461733486.0, "step": 77380 }, { "epoch": 0.825589706933524, "grad_norm": 1.2234920075267222, "learning_rate": 8.640251885721492e-06, "loss": 0.4396, "num_tokens": 461760618.0, "step": 77385 }, { "epoch": 0.8256430499397224, "grad_norm": 0.5754547748648634, "learning_rate": 8.63808766655281e-06, "loss": 0.3653, "num_tokens": 461788923.0, "step": 77390 }, { "epoch": 0.8256963929459209, "grad_norm": 0.6995936779270114, "learning_rate": 8.635924034328091e-06, "loss": 0.5184, "num_tokens": 461832941.0, "step": 77395 }, { "epoch": 0.8257497359521193, "grad_norm": 0.7610147360230225, "learning_rate": 8.633760989114675e-06, "loss": 0.5003, "num_tokens": 461871208.0, "step": 77400 }, { "epoch": 0.8258030789583177, "grad_norm": 1.186758972811867, "learning_rate": 8.63159853097986e-06, "loss": 0.4325, "num_tokens": 461907478.0, "step": 77405 }, { "epoch": 0.8258564219645163, "grad_norm": 1.107975656946653, "learning_rate": 8.629436659990938e-06, "loss": 0.4193, "num_tokens": 461928550.0, "step": 77410 }, { "epoch": 0.8259097649707147, "grad_norm": 0.8298207116809122, "learning_rate": 8.627275376215197e-06, "loss": 0.4996, "num_tokens": 461967513.0, "step": 77415 }, { "epoch": 0.8259631079769132, "grad_norm": 2.2374165730941655, "learning_rate": 8.625114679719872e-06, "loss": 0.4558, "num_tokens": 461984418.0, "step": 77420 }, { "epoch": 0.8260164509831116, "grad_norm": 0.5504153264670963, "learning_rate": 8.622954570572214e-06, "loss": 0.4422, "num_tokens": 462004547.0, "step": 77425 }, { "epoch": 0.82606979398931, "grad_norm": 1.2522126764224015, "learning_rate": 8.620795048839434e-06, "loss": 0.5074, "num_tokens": 462021066.0, "step": 77430 }, { "epoch": 0.8261231369955085, "grad_norm": 1.0617762821435763, "learning_rate": 8.618636114588729e-06, "loss": 0.4623, "num_tokens": 462041689.0, "step": 77435 }, { "epoch": 0.826176480001707, "grad_norm": 1.3152320669606516, "learning_rate": 8.616477767887285e-06, "loss": 0.5376, "num_tokens": 462055868.0, "step": 77440 }, { "epoch": 0.8262298230079055, "grad_norm": 0.9081505922023607, "learning_rate": 8.614320008802271e-06, "loss": 0.4604, "num_tokens": 462100468.0, "step": 77445 }, { "epoch": 0.8262831660141039, "grad_norm": 0.830324738547034, "learning_rate": 8.61216283740082e-06, "loss": 0.4714, "num_tokens": 462130636.0, "step": 77450 }, { "epoch": 0.8263365090203023, "grad_norm": 0.8447960786464143, "learning_rate": 8.610006253750062e-06, "loss": 0.4098, "num_tokens": 462171998.0, "step": 77455 }, { "epoch": 0.8263898520265008, "grad_norm": 0.9617367339160996, "learning_rate": 8.607850257917115e-06, "loss": 0.4111, "num_tokens": 462203737.0, "step": 77460 }, { "epoch": 0.8264431950326993, "grad_norm": 1.0714219733059884, "learning_rate": 8.605694849969065e-06, "loss": 0.5539, "num_tokens": 462248147.0, "step": 77465 }, { "epoch": 0.8264965380388977, "grad_norm": 0.8294020748338957, "learning_rate": 8.603540029972973e-06, "loss": 0.3749, "num_tokens": 462270697.0, "step": 77470 }, { "epoch": 0.8265498810450962, "grad_norm": 0.9949423037007776, "learning_rate": 8.601385797995909e-06, "loss": 0.4295, "num_tokens": 462294000.0, "step": 77475 }, { "epoch": 0.8266032240512946, "grad_norm": 0.6368607295483002, "learning_rate": 8.599232154104892e-06, "loss": 0.4497, "num_tokens": 462317383.0, "step": 77480 }, { "epoch": 0.8266565670574931, "grad_norm": 0.6058725798607048, "learning_rate": 8.597079098366948e-06, "loss": 0.4338, "num_tokens": 462370760.0, "step": 77485 }, { "epoch": 0.8267099100636915, "grad_norm": 0.8499348127915501, "learning_rate": 8.59492663084908e-06, "loss": 0.512, "num_tokens": 462400505.0, "step": 77490 }, { "epoch": 0.82676325306989, "grad_norm": 0.6833056000444497, "learning_rate": 8.592774751618258e-06, "loss": 0.4881, "num_tokens": 462436497.0, "step": 77495 }, { "epoch": 0.8268165960760885, "grad_norm": 0.5599234243662606, "learning_rate": 8.590623460741454e-06, "loss": 0.4109, "num_tokens": 462472119.0, "step": 77500 }, { "epoch": 0.8268699390822869, "grad_norm": 0.8959043731198472, "learning_rate": 8.588472758285601e-06, "loss": 0.4544, "num_tokens": 462504284.0, "step": 77505 }, { "epoch": 0.8269232820884854, "grad_norm": 0.8665575278597086, "learning_rate": 8.586322644317637e-06, "loss": 0.4568, "num_tokens": 462530534.0, "step": 77510 }, { "epoch": 0.8269766250946838, "grad_norm": 1.0382156956410713, "learning_rate": 8.58417311890446e-06, "loss": 0.5104, "num_tokens": 462562772.0, "step": 77515 }, { "epoch": 0.8270299681008823, "grad_norm": 0.9589061620400363, "learning_rate": 8.582024182112955e-06, "loss": 0.3701, "num_tokens": 462591927.0, "step": 77520 }, { "epoch": 0.8270833111070808, "grad_norm": 0.8027806777026721, "learning_rate": 8.579875834010008e-06, "loss": 0.5959, "num_tokens": 462636410.0, "step": 77525 }, { "epoch": 0.8271366541132792, "grad_norm": 0.5655665452496695, "learning_rate": 8.577728074662459e-06, "loss": 0.5543, "num_tokens": 462672265.0, "step": 77530 }, { "epoch": 0.8271899971194777, "grad_norm": 0.7557226380405921, "learning_rate": 8.575580904137146e-06, "loss": 0.533, "num_tokens": 462705808.0, "step": 77535 }, { "epoch": 0.8272433401256761, "grad_norm": 1.4359305756796514, "learning_rate": 8.573434322500884e-06, "loss": 0.4513, "num_tokens": 462719850.0, "step": 77540 }, { "epoch": 0.8272966831318745, "grad_norm": 0.7977337157946045, "learning_rate": 8.571288329820461e-06, "loss": 0.549, "num_tokens": 462760697.0, "step": 77545 }, { "epoch": 0.8273500261380731, "grad_norm": 1.4353098266393696, "learning_rate": 8.569142926162671e-06, "loss": 0.4208, "num_tokens": 462786792.0, "step": 77550 }, { "epoch": 0.8274033691442715, "grad_norm": 1.0168722969751103, "learning_rate": 8.56699811159427e-06, "loss": 0.4085, "num_tokens": 462820814.0, "step": 77555 }, { "epoch": 0.8274567121504699, "grad_norm": 0.7497302996829192, "learning_rate": 8.564853886181995e-06, "loss": 0.53, "num_tokens": 462861851.0, "step": 77560 }, { "epoch": 0.8275100551566684, "grad_norm": 0.7527031114833815, "learning_rate": 8.562710249992577e-06, "loss": 0.34, "num_tokens": 462888200.0, "step": 77565 }, { "epoch": 0.8275633981628668, "grad_norm": 0.7795918023160167, "learning_rate": 8.560567203092717e-06, "loss": 0.5653, "num_tokens": 462919689.0, "step": 77570 }, { "epoch": 0.8276167411690654, "grad_norm": 0.7202295252424533, "learning_rate": 8.558424745549098e-06, "loss": 0.3701, "num_tokens": 462949914.0, "step": 77575 }, { "epoch": 0.8276700841752638, "grad_norm": 1.058172341107455, "learning_rate": 8.556282877428396e-06, "loss": 0.4376, "num_tokens": 462978064.0, "step": 77580 }, { "epoch": 0.8277234271814622, "grad_norm": 1.2645313028844445, "learning_rate": 8.554141598797264e-06, "loss": 0.3374, "num_tokens": 462993205.0, "step": 77585 }, { "epoch": 0.8277767701876607, "grad_norm": 0.8208035178672979, "learning_rate": 8.552000909722322e-06, "loss": 0.4841, "num_tokens": 463040929.0, "step": 77590 }, { "epoch": 0.8278301131938591, "grad_norm": 0.5432568603972354, "learning_rate": 8.54986081027019e-06, "loss": 0.4704, "num_tokens": 463078532.0, "step": 77595 }, { "epoch": 0.8278834562000577, "grad_norm": 2.1404556113119058, "learning_rate": 8.547721300507478e-06, "loss": 0.5407, "num_tokens": 463093724.0, "step": 77600 }, { "epoch": 0.8279367992062561, "grad_norm": 0.7681160036569586, "learning_rate": 8.545582380500743e-06, "loss": 0.4764, "num_tokens": 463125410.0, "step": 77605 }, { "epoch": 0.8279901422124545, "grad_norm": 0.8833324667046669, "learning_rate": 8.543444050316548e-06, "loss": 0.4635, "num_tokens": 463159793.0, "step": 77610 }, { "epoch": 0.828043485218653, "grad_norm": 1.092482255575696, "learning_rate": 8.54130631002144e-06, "loss": 0.3917, "num_tokens": 463186126.0, "step": 77615 }, { "epoch": 0.8280968282248514, "grad_norm": 0.7270640932354181, "learning_rate": 8.539169159681934e-06, "loss": 0.4899, "num_tokens": 463220171.0, "step": 77620 }, { "epoch": 0.82815017123105, "grad_norm": 1.1797677908706292, "learning_rate": 8.537032599364534e-06, "loss": 0.5332, "num_tokens": 463245255.0, "step": 77625 }, { "epoch": 0.8282035142372484, "grad_norm": 1.4080881641880465, "learning_rate": 8.534896629135737e-06, "loss": 0.4787, "num_tokens": 463277276.0, "step": 77630 }, { "epoch": 0.8282568572434468, "grad_norm": 1.4607809027125034, "learning_rate": 8.532761249061995e-06, "loss": 0.5606, "num_tokens": 463302412.0, "step": 77635 }, { "epoch": 0.8283102002496453, "grad_norm": 0.614066207316201, "learning_rate": 8.530626459209767e-06, "loss": 0.43, "num_tokens": 463339928.0, "step": 77640 }, { "epoch": 0.8283635432558437, "grad_norm": 1.1100787449873668, "learning_rate": 8.528492259645481e-06, "loss": 0.4153, "num_tokens": 463362235.0, "step": 77645 }, { "epoch": 0.8284168862620421, "grad_norm": 0.7932870072140804, "learning_rate": 8.526358650435543e-06, "loss": 0.4147, "num_tokens": 463385568.0, "step": 77650 }, { "epoch": 0.8284702292682407, "grad_norm": 0.6296741524946436, "learning_rate": 8.52422563164635e-06, "loss": 0.3928, "num_tokens": 463420616.0, "step": 77655 }, { "epoch": 0.8285235722744391, "grad_norm": 0.7378130518287914, "learning_rate": 8.522093203344284e-06, "loss": 0.4649, "num_tokens": 463444429.0, "step": 77660 }, { "epoch": 0.8285769152806376, "grad_norm": 0.533624624402794, "learning_rate": 8.519961365595688e-06, "loss": 0.37, "num_tokens": 463473311.0, "step": 77665 }, { "epoch": 0.828630258286836, "grad_norm": 1.057187109209277, "learning_rate": 8.517830118466908e-06, "loss": 0.4342, "num_tokens": 463495862.0, "step": 77670 }, { "epoch": 0.8286836012930344, "grad_norm": 1.1268720305278042, "learning_rate": 8.515699462024273e-06, "loss": 0.4794, "num_tokens": 463528601.0, "step": 77675 }, { "epoch": 0.828736944299233, "grad_norm": 0.8960648140879296, "learning_rate": 8.513569396334073e-06, "loss": 0.3987, "num_tokens": 463563861.0, "step": 77680 }, { "epoch": 0.8287902873054314, "grad_norm": 0.9261353231869945, "learning_rate": 8.51143992146259e-06, "loss": 0.4134, "num_tokens": 463593990.0, "step": 77685 }, { "epoch": 0.8288436303116299, "grad_norm": 1.1335033879497942, "learning_rate": 8.509311037476097e-06, "loss": 0.5227, "num_tokens": 463610530.0, "step": 77690 }, { "epoch": 0.8288969733178283, "grad_norm": 0.6185647630400741, "learning_rate": 8.507182744440833e-06, "loss": 0.4598, "num_tokens": 463638732.0, "step": 77695 }, { "epoch": 0.8289503163240267, "grad_norm": 0.8359260858749471, "learning_rate": 8.50505504242303e-06, "loss": 0.4214, "num_tokens": 463667467.0, "step": 77700 }, { "epoch": 0.8290036593302252, "grad_norm": 0.908489787412042, "learning_rate": 8.502927931488902e-06, "loss": 0.3485, "num_tokens": 463694048.0, "step": 77705 }, { "epoch": 0.8290570023364237, "grad_norm": 0.7346518239036357, "learning_rate": 8.500801411704629e-06, "loss": 0.4775, "num_tokens": 463719447.0, "step": 77710 }, { "epoch": 0.8291103453426222, "grad_norm": 1.361508428581206, "learning_rate": 8.498675483136397e-06, "loss": 0.4666, "num_tokens": 463742122.0, "step": 77715 }, { "epoch": 0.8291636883488206, "grad_norm": 0.6334276528559646, "learning_rate": 8.496550145850355e-06, "loss": 0.3795, "num_tokens": 463764632.0, "step": 77720 }, { "epoch": 0.829217031355019, "grad_norm": 1.0046494584887804, "learning_rate": 8.49442539991263e-06, "loss": 0.5161, "num_tokens": 463778783.0, "step": 77725 }, { "epoch": 0.8292703743612175, "grad_norm": 1.2408225411157683, "learning_rate": 8.492301245389352e-06, "loss": 0.4888, "num_tokens": 463812303.0, "step": 77730 }, { "epoch": 0.829323717367416, "grad_norm": 0.9094955180958318, "learning_rate": 8.49017768234662e-06, "loss": 0.434, "num_tokens": 463833734.0, "step": 77735 }, { "epoch": 0.8293770603736144, "grad_norm": 1.0481280854189787, "learning_rate": 8.488054710850504e-06, "loss": 0.4264, "num_tokens": 463879408.0, "step": 77740 }, { "epoch": 0.8294304033798129, "grad_norm": 1.3876868444310861, "learning_rate": 8.485932330967076e-06, "loss": 0.4834, "num_tokens": 463908462.0, "step": 77745 }, { "epoch": 0.8294837463860113, "grad_norm": 0.7146426265702851, "learning_rate": 8.483810542762382e-06, "loss": 0.5175, "num_tokens": 463935823.0, "step": 77750 }, { "epoch": 0.8295370893922098, "grad_norm": 0.8262175982129748, "learning_rate": 8.481689346302443e-06, "loss": 0.4278, "num_tokens": 463963466.0, "step": 77755 }, { "epoch": 0.8295904323984082, "grad_norm": 0.8140224457403278, "learning_rate": 8.479568741653263e-06, "loss": 0.426, "num_tokens": 463988579.0, "step": 77760 }, { "epoch": 0.8296437754046067, "grad_norm": 0.9985271401520478, "learning_rate": 8.47744872888084e-06, "loss": 0.5946, "num_tokens": 464029390.0, "step": 77765 }, { "epoch": 0.8296971184108052, "grad_norm": 0.9291009388183286, "learning_rate": 8.475329308051134e-06, "loss": 0.4926, "num_tokens": 464049153.0, "step": 77770 }, { "epoch": 0.8297504614170036, "grad_norm": 0.6843617360315237, "learning_rate": 8.4732104792301e-06, "loss": 0.5341, "num_tokens": 464083874.0, "step": 77775 }, { "epoch": 0.8298038044232021, "grad_norm": 1.354367700204249, "learning_rate": 8.47109224248368e-06, "loss": 0.3922, "num_tokens": 464122721.0, "step": 77780 }, { "epoch": 0.8298571474294005, "grad_norm": 1.230101308950904, "learning_rate": 8.46897459787778e-06, "loss": 0.4084, "num_tokens": 464147993.0, "step": 77785 }, { "epoch": 0.829910490435599, "grad_norm": 1.0091698894557366, "learning_rate": 8.466857545478302e-06, "loss": 0.4131, "num_tokens": 464178903.0, "step": 77790 }, { "epoch": 0.8299638334417975, "grad_norm": 0.941702339422651, "learning_rate": 8.464741085351123e-06, "loss": 0.4103, "num_tokens": 464205699.0, "step": 77795 }, { "epoch": 0.8300171764479959, "grad_norm": 0.8069945024710127, "learning_rate": 8.462625217562096e-06, "loss": 0.3856, "num_tokens": 464230797.0, "step": 77800 }, { "epoch": 0.8300705194541944, "grad_norm": 1.2074780429434602, "learning_rate": 8.46050994217707e-06, "loss": 0.5582, "num_tokens": 464274798.0, "step": 77805 }, { "epoch": 0.8301238624603928, "grad_norm": 1.4589687128286826, "learning_rate": 8.45839525926187e-06, "loss": 0.439, "num_tokens": 464301301.0, "step": 77810 }, { "epoch": 0.8301772054665912, "grad_norm": 0.5635564784443858, "learning_rate": 8.45628116888229e-06, "loss": 0.4221, "num_tokens": 464326835.0, "step": 77815 }, { "epoch": 0.8302305484727898, "grad_norm": 1.4394698531485155, "learning_rate": 8.454167671104127e-06, "loss": 0.4993, "num_tokens": 464355878.0, "step": 77820 }, { "epoch": 0.8302838914789882, "grad_norm": 0.9563118249373357, "learning_rate": 8.452054765993149e-06, "loss": 0.469, "num_tokens": 464388744.0, "step": 77825 }, { "epoch": 0.8303372344851866, "grad_norm": 1.7964334970471332, "learning_rate": 8.4499424536151e-06, "loss": 0.5433, "num_tokens": 464411412.0, "step": 77830 }, { "epoch": 0.8303905774913851, "grad_norm": 0.9369110982302645, "learning_rate": 8.447830734035709e-06, "loss": 0.545, "num_tokens": 464435294.0, "step": 77835 }, { "epoch": 0.8304439204975835, "grad_norm": 1.4456639729341358, "learning_rate": 8.445719607320695e-06, "loss": 0.4256, "num_tokens": 464461599.0, "step": 77840 }, { "epoch": 0.8304972635037821, "grad_norm": 1.0661648347764023, "learning_rate": 8.44360907353574e-06, "loss": 0.4436, "num_tokens": 464502447.0, "step": 77845 }, { "epoch": 0.8305506065099805, "grad_norm": 1.1329179381178123, "learning_rate": 8.44149913274653e-06, "loss": 0.3872, "num_tokens": 464531715.0, "step": 77850 }, { "epoch": 0.8306039495161789, "grad_norm": 3.45912798813015, "learning_rate": 8.439389785018728e-06, "loss": 0.6847, "num_tokens": 464549749.0, "step": 77855 }, { "epoch": 0.8306572925223774, "grad_norm": 1.0743107934114589, "learning_rate": 8.437281030417959e-06, "loss": 0.5599, "num_tokens": 464571129.0, "step": 77860 }, { "epoch": 0.8307106355285758, "grad_norm": 0.5776892464399883, "learning_rate": 8.435172869009847e-06, "loss": 0.3496, "num_tokens": 464610863.0, "step": 77865 }, { "epoch": 0.8307639785347743, "grad_norm": 0.5519282092085055, "learning_rate": 8.433065300859999e-06, "loss": 0.3429, "num_tokens": 464643262.0, "step": 77870 }, { "epoch": 0.8308173215409728, "grad_norm": 0.5767536348751725, "learning_rate": 8.43095832603399e-06, "loss": 0.5501, "num_tokens": 464683832.0, "step": 77875 }, { "epoch": 0.8308706645471712, "grad_norm": 0.7147720088804711, "learning_rate": 8.428851944597388e-06, "loss": 0.5258, "num_tokens": 464712763.0, "step": 77880 }, { "epoch": 0.8309240075533697, "grad_norm": 0.5980491987046688, "learning_rate": 8.426746156615744e-06, "loss": 0.4766, "num_tokens": 464750631.0, "step": 77885 }, { "epoch": 0.8309773505595681, "grad_norm": 0.7961574948672036, "learning_rate": 8.42464096215458e-06, "loss": 0.4416, "num_tokens": 464788224.0, "step": 77890 }, { "epoch": 0.8310306935657666, "grad_norm": 1.1004868782182216, "learning_rate": 8.42253636127941e-06, "loss": 0.418, "num_tokens": 464814717.0, "step": 77895 }, { "epoch": 0.8310840365719651, "grad_norm": 0.7991615512382411, "learning_rate": 8.420432354055724e-06, "loss": 0.3792, "num_tokens": 464849461.0, "step": 77900 }, { "epoch": 0.8311373795781635, "grad_norm": 1.2405925297388976, "learning_rate": 8.418328940548985e-06, "loss": 0.4811, "num_tokens": 464875301.0, "step": 77905 }, { "epoch": 0.831190722584362, "grad_norm": 0.7590194160050394, "learning_rate": 8.416226120824658e-06, "loss": 0.4093, "num_tokens": 464909119.0, "step": 77910 }, { "epoch": 0.8312440655905604, "grad_norm": 0.7389788782498832, "learning_rate": 8.414123894948176e-06, "loss": 0.519, "num_tokens": 464954801.0, "step": 77915 }, { "epoch": 0.8312974085967588, "grad_norm": 1.5480888383206939, "learning_rate": 8.412022262984952e-06, "loss": 0.4635, "num_tokens": 464979667.0, "step": 77920 }, { "epoch": 0.8313507516029573, "grad_norm": 1.022666661795209, "learning_rate": 8.409921225000387e-06, "loss": 0.5435, "num_tokens": 465009356.0, "step": 77925 }, { "epoch": 0.8314040946091558, "grad_norm": 0.93490105665052, "learning_rate": 8.407820781059866e-06, "loss": 0.404, "num_tokens": 465029018.0, "step": 77930 }, { "epoch": 0.8314574376153543, "grad_norm": 0.8109804569852469, "learning_rate": 8.405720931228747e-06, "loss": 0.5121, "num_tokens": 465052437.0, "step": 77935 }, { "epoch": 0.8315107806215527, "grad_norm": 0.5805315376363079, "learning_rate": 8.403621675572365e-06, "loss": 0.9507, "num_tokens": 465082774.0, "step": 77940 }, { "epoch": 0.8315641236277511, "grad_norm": 1.2327212981475446, "learning_rate": 8.401523014156059e-06, "loss": 0.4782, "num_tokens": 465107620.0, "step": 77945 }, { "epoch": 0.8316174666339496, "grad_norm": 0.9683788958642023, "learning_rate": 8.399424947045121e-06, "loss": 0.4569, "num_tokens": 465126842.0, "step": 77950 }, { "epoch": 0.8316708096401481, "grad_norm": 0.6657974330412556, "learning_rate": 8.397327474304844e-06, "loss": 0.5285, "num_tokens": 465164729.0, "step": 77955 }, { "epoch": 0.8317241526463466, "grad_norm": 1.064615850767195, "learning_rate": 8.395230596000504e-06, "loss": 0.48, "num_tokens": 465200081.0, "step": 77960 }, { "epoch": 0.831777495652545, "grad_norm": 0.6383962394393226, "learning_rate": 8.39313431219734e-06, "loss": 0.4548, "num_tokens": 465244891.0, "step": 77965 }, { "epoch": 0.8318308386587434, "grad_norm": 0.7420529431689356, "learning_rate": 8.391038622960595e-06, "loss": 0.4355, "num_tokens": 465276281.0, "step": 77970 }, { "epoch": 0.8318841816649419, "grad_norm": 0.9278498515318268, "learning_rate": 8.388943528355477e-06, "loss": 0.462, "num_tokens": 465302318.0, "step": 77975 }, { "epoch": 0.8319375246711403, "grad_norm": 0.6857689925374807, "learning_rate": 8.386849028447176e-06, "loss": 0.4857, "num_tokens": 465351111.0, "step": 77980 }, { "epoch": 0.8319908676773389, "grad_norm": 1.0145816077662226, "learning_rate": 8.384755123300875e-06, "loss": 0.6147, "num_tokens": 465384861.0, "step": 77985 }, { "epoch": 0.8320442106835373, "grad_norm": 1.2867516025150045, "learning_rate": 8.382661812981735e-06, "loss": 0.4061, "num_tokens": 465408290.0, "step": 77990 }, { "epoch": 0.8320975536897357, "grad_norm": 0.8663615147866054, "learning_rate": 8.380569097554886e-06, "loss": 0.741, "num_tokens": 465452693.0, "step": 77995 }, { "epoch": 0.8321508966959342, "grad_norm": 0.7974859199399785, "learning_rate": 8.378476977085455e-06, "loss": 0.4716, "num_tokens": 465476544.0, "step": 78000 }, { "epoch": 0.8322042397021326, "grad_norm": 1.2140721766758857, "learning_rate": 8.376385451638546e-06, "loss": 0.6599, "num_tokens": 465507511.0, "step": 78005 }, { "epoch": 0.8322575827083311, "grad_norm": 0.5157706495061704, "learning_rate": 8.374294521279242e-06, "loss": 0.4257, "num_tokens": 465546136.0, "step": 78010 }, { "epoch": 0.8323109257145296, "grad_norm": 0.9547996733312796, "learning_rate": 8.372204186072605e-06, "loss": 0.458, "num_tokens": 465576690.0, "step": 78015 }, { "epoch": 0.832364268720728, "grad_norm": 0.721213651417013, "learning_rate": 8.370114446083686e-06, "loss": 0.4752, "num_tokens": 465616315.0, "step": 78020 }, { "epoch": 0.8324176117269265, "grad_norm": 1.1024747175670868, "learning_rate": 8.368025301377508e-06, "loss": 0.3768, "num_tokens": 465637502.0, "step": 78025 }, { "epoch": 0.8324709547331249, "grad_norm": 0.7302627673158483, "learning_rate": 8.365936752019082e-06, "loss": 0.4086, "num_tokens": 465656052.0, "step": 78030 }, { "epoch": 0.8325242977393233, "grad_norm": 0.5620951332067036, "learning_rate": 8.363848798073409e-06, "loss": 0.4095, "num_tokens": 465683552.0, "step": 78035 }, { "epoch": 0.8325776407455219, "grad_norm": 1.2143563724181896, "learning_rate": 8.361761439605451e-06, "loss": 0.4216, "num_tokens": 465711709.0, "step": 78040 }, { "epoch": 0.8326309837517203, "grad_norm": 1.0179960216023116, "learning_rate": 8.359674676680169e-06, "loss": 0.4604, "num_tokens": 465735977.0, "step": 78045 }, { "epoch": 0.8326843267579188, "grad_norm": 0.7054474847981903, "learning_rate": 8.357588509362495e-06, "loss": 0.4427, "num_tokens": 465770942.0, "step": 78050 }, { "epoch": 0.8327376697641172, "grad_norm": 0.9403113354185012, "learning_rate": 8.355502937717344e-06, "loss": 0.4734, "num_tokens": 465800679.0, "step": 78055 }, { "epoch": 0.8327910127703156, "grad_norm": 0.7801037152241906, "learning_rate": 8.353417961809617e-06, "loss": 0.5349, "num_tokens": 465829767.0, "step": 78060 }, { "epoch": 0.8328443557765142, "grad_norm": 1.1714294646229713, "learning_rate": 8.3513335817042e-06, "loss": 0.4706, "num_tokens": 465854443.0, "step": 78065 }, { "epoch": 0.8328976987827126, "grad_norm": 0.6741531747556992, "learning_rate": 8.349249797465943e-06, "loss": 0.6033, "num_tokens": 465893728.0, "step": 78070 }, { "epoch": 0.8329510417889111, "grad_norm": 1.1628543503979798, "learning_rate": 8.347166609159696e-06, "loss": 0.4666, "num_tokens": 465934696.0, "step": 78075 }, { "epoch": 0.8330043847951095, "grad_norm": 0.565722224971927, "learning_rate": 8.345084016850286e-06, "loss": 0.3608, "num_tokens": 465973876.0, "step": 78080 }, { "epoch": 0.8330577278013079, "grad_norm": 1.68002615692896, "learning_rate": 8.34300202060252e-06, "loss": 0.4918, "num_tokens": 465988853.0, "step": 78085 }, { "epoch": 0.8331110708075065, "grad_norm": 0.8147300408526343, "learning_rate": 8.340920620481175e-06, "loss": 0.4743, "num_tokens": 466016562.0, "step": 78090 }, { "epoch": 0.8331644138137049, "grad_norm": 0.952794196622649, "learning_rate": 8.338839816551034e-06, "loss": 0.4524, "num_tokens": 466038910.0, "step": 78095 }, { "epoch": 0.8332177568199033, "grad_norm": 1.3652529261763682, "learning_rate": 8.33675960887683e-06, "loss": 0.5064, "num_tokens": 466062949.0, "step": 78100 }, { "epoch": 0.8332710998261018, "grad_norm": 6.578108181423658, "learning_rate": 8.334679997523306e-06, "loss": 0.5767, "num_tokens": 466086059.0, "step": 78105 }, { "epoch": 0.8333244428323002, "grad_norm": 0.8090267350950449, "learning_rate": 8.33260098255518e-06, "loss": 0.4616, "num_tokens": 466108293.0, "step": 78110 }, { "epoch": 0.8333777858384988, "grad_norm": 0.7263768655360118, "learning_rate": 8.330522564037135e-06, "loss": 0.5487, "num_tokens": 466147163.0, "step": 78115 }, { "epoch": 0.8334311288446972, "grad_norm": 0.6143690538222413, "learning_rate": 8.328444742033859e-06, "loss": 0.4835, "num_tokens": 466179738.0, "step": 78120 }, { "epoch": 0.8334844718508956, "grad_norm": 0.6810356177508148, "learning_rate": 8.326367516610001e-06, "loss": 0.4987, "num_tokens": 466211910.0, "step": 78125 }, { "epoch": 0.8335378148570941, "grad_norm": 1.0590941329724164, "learning_rate": 8.324290887830196e-06, "loss": 0.5759, "num_tokens": 466250132.0, "step": 78130 }, { "epoch": 0.8335911578632925, "grad_norm": 0.7959780981710475, "learning_rate": 8.322214855759072e-06, "loss": 0.3725, "num_tokens": 466284677.0, "step": 78135 }, { "epoch": 0.833644500869491, "grad_norm": 1.247459322232292, "learning_rate": 8.320139420461238e-06, "loss": 0.3874, "num_tokens": 466308018.0, "step": 78140 }, { "epoch": 0.8336978438756895, "grad_norm": 0.5517481792578828, "learning_rate": 8.318064582001258e-06, "loss": 0.5901, "num_tokens": 466344457.0, "step": 78145 }, { "epoch": 0.8337511868818879, "grad_norm": 0.8656310485659554, "learning_rate": 8.315990340443715e-06, "loss": 0.4383, "num_tokens": 466378857.0, "step": 78150 }, { "epoch": 0.8338045298880864, "grad_norm": 1.0744365894922785, "learning_rate": 8.313916695853144e-06, "loss": 0.4023, "num_tokens": 466394431.0, "step": 78155 }, { "epoch": 0.8338578728942848, "grad_norm": 1.1150925363566235, "learning_rate": 8.31184364829408e-06, "loss": 0.4017, "num_tokens": 466415749.0, "step": 78160 }, { "epoch": 0.8339112159004833, "grad_norm": 0.6078984071319327, "learning_rate": 8.30977119783102e-06, "loss": 0.4381, "num_tokens": 466455471.0, "step": 78165 }, { "epoch": 0.8339645589066818, "grad_norm": 1.1247340415544034, "learning_rate": 8.30769934452847e-06, "loss": 0.5537, "num_tokens": 466484707.0, "step": 78170 }, { "epoch": 0.8340179019128802, "grad_norm": 0.911887905122938, "learning_rate": 8.30562808845089e-06, "loss": 0.4908, "num_tokens": 466533323.0, "step": 78175 }, { "epoch": 0.8340712449190787, "grad_norm": 0.8519745142995389, "learning_rate": 8.303557429662735e-06, "loss": 0.5302, "num_tokens": 466577376.0, "step": 78180 }, { "epoch": 0.8341245879252771, "grad_norm": 0.6239805605381512, "learning_rate": 8.30148736822845e-06, "loss": 0.5013, "num_tokens": 466614987.0, "step": 78185 }, { "epoch": 0.8341779309314755, "grad_norm": 1.3779285699200894, "learning_rate": 8.299417904212444e-06, "loss": 0.5248, "num_tokens": 466650563.0, "step": 78190 }, { "epoch": 0.834231273937674, "grad_norm": 1.0537270777045193, "learning_rate": 8.297349037679104e-06, "loss": 0.5297, "num_tokens": 466681555.0, "step": 78195 }, { "epoch": 0.8342846169438725, "grad_norm": 1.0104772961442263, "learning_rate": 8.295280768692827e-06, "loss": 0.5528, "num_tokens": 466724343.0, "step": 78200 }, { "epoch": 0.834337959950071, "grad_norm": 0.7927723247582422, "learning_rate": 8.293213097317961e-06, "loss": 0.4427, "num_tokens": 466754118.0, "step": 78205 }, { "epoch": 0.8343913029562694, "grad_norm": 0.8443843256099531, "learning_rate": 8.29114602361885e-06, "loss": 0.5221, "num_tokens": 466778363.0, "step": 78210 }, { "epoch": 0.8344446459624678, "grad_norm": 0.7828128399289173, "learning_rate": 8.289079547659822e-06, "loss": 0.5765, "num_tokens": 466800243.0, "step": 78215 }, { "epoch": 0.8344979889686663, "grad_norm": 0.7453149321706267, "learning_rate": 8.287013669505175e-06, "loss": 0.4096, "num_tokens": 466821984.0, "step": 78220 }, { "epoch": 0.8345513319748648, "grad_norm": 0.7087619799299976, "learning_rate": 8.284948389219202e-06, "loss": 0.4588, "num_tokens": 466866644.0, "step": 78225 }, { "epoch": 0.8346046749810633, "grad_norm": 0.9874104823676774, "learning_rate": 8.282883706866167e-06, "loss": 0.46, "num_tokens": 466906002.0, "step": 78230 }, { "epoch": 0.8346580179872617, "grad_norm": 0.8807005003172975, "learning_rate": 8.280819622510314e-06, "loss": 0.5452, "num_tokens": 466937006.0, "step": 78235 }, { "epoch": 0.8347113609934601, "grad_norm": 0.6802338799096259, "learning_rate": 8.278756136215877e-06, "loss": 0.4848, "num_tokens": 466970023.0, "step": 78240 }, { "epoch": 0.8347647039996586, "grad_norm": 1.635921297806565, "learning_rate": 8.27669324804707e-06, "loss": 0.495, "num_tokens": 467005187.0, "step": 78245 }, { "epoch": 0.834818047005857, "grad_norm": 0.650448774466608, "learning_rate": 8.27463095806808e-06, "loss": 0.5181, "num_tokens": 467043975.0, "step": 78250 }, { "epoch": 0.8348713900120556, "grad_norm": 1.038683678746646, "learning_rate": 8.272569266343083e-06, "loss": 0.428, "num_tokens": 467080333.0, "step": 78255 }, { "epoch": 0.834924733018254, "grad_norm": 1.1200110133855843, "learning_rate": 8.270508172936242e-06, "loss": 0.4683, "num_tokens": 467108902.0, "step": 78260 }, { "epoch": 0.8349780760244524, "grad_norm": 1.7196781595869235, "learning_rate": 8.26844767791169e-06, "loss": 0.4972, "num_tokens": 467133979.0, "step": 78265 }, { "epoch": 0.8350314190306509, "grad_norm": 0.9394142121360398, "learning_rate": 8.266387781333535e-06, "loss": 0.4082, "num_tokens": 467168024.0, "step": 78270 }, { "epoch": 0.8350847620368493, "grad_norm": 0.8193581422586798, "learning_rate": 8.264328483265893e-06, "loss": 0.5197, "num_tokens": 467202500.0, "step": 78275 }, { "epoch": 0.8351381050430478, "grad_norm": 0.6775025302719612, "learning_rate": 8.262269783772833e-06, "loss": 0.3783, "num_tokens": 467234683.0, "step": 78280 }, { "epoch": 0.8351914480492463, "grad_norm": 0.9689516065459376, "learning_rate": 8.260211682918419e-06, "loss": 0.4906, "num_tokens": 467270781.0, "step": 78285 }, { "epoch": 0.8352447910554447, "grad_norm": 0.7638608944996872, "learning_rate": 8.258154180766703e-06, "loss": 0.3786, "num_tokens": 467297215.0, "step": 78290 }, { "epoch": 0.8352981340616432, "grad_norm": 0.5129105825131807, "learning_rate": 8.256097277381702e-06, "loss": 0.4326, "num_tokens": 467335447.0, "step": 78295 }, { "epoch": 0.8353514770678416, "grad_norm": 1.2519335664310756, "learning_rate": 8.254040972827432e-06, "loss": 0.4258, "num_tokens": 467351671.0, "step": 78300 }, { "epoch": 0.83540482007404, "grad_norm": 1.1211531553218514, "learning_rate": 8.25198526716787e-06, "loss": 0.4307, "num_tokens": 467380782.0, "step": 78305 }, { "epoch": 0.8354581630802386, "grad_norm": 2.7656042553284768, "learning_rate": 8.249930160466988e-06, "loss": 0.5353, "num_tokens": 467406552.0, "step": 78310 }, { "epoch": 0.835511506086437, "grad_norm": 0.712742267971862, "learning_rate": 8.247875652788739e-06, "loss": 0.5256, "num_tokens": 467456243.0, "step": 78315 }, { "epoch": 0.8355648490926355, "grad_norm": 0.70436138839749, "learning_rate": 8.24582174419706e-06, "loss": 0.3646, "num_tokens": 467479567.0, "step": 78320 }, { "epoch": 0.8356181920988339, "grad_norm": 0.8801869370693257, "learning_rate": 8.24376843475585e-06, "loss": 0.5118, "num_tokens": 467503841.0, "step": 78325 }, { "epoch": 0.8356715351050323, "grad_norm": 0.5966035172984085, "learning_rate": 8.241715724529017e-06, "loss": 0.4548, "num_tokens": 467541404.0, "step": 78330 }, { "epoch": 0.8357248781112309, "grad_norm": 0.6722055532707195, "learning_rate": 8.239663613580437e-06, "loss": 0.4737, "num_tokens": 467581787.0, "step": 78335 }, { "epoch": 0.8357782211174293, "grad_norm": 1.3886556371161844, "learning_rate": 8.237612101973963e-06, "loss": 0.4793, "num_tokens": 467603010.0, "step": 78340 }, { "epoch": 0.8358315641236278, "grad_norm": 0.6544698632241124, "learning_rate": 8.23556118977343e-06, "loss": 0.4278, "num_tokens": 467635736.0, "step": 78345 }, { "epoch": 0.8358849071298262, "grad_norm": 0.6741899075478621, "learning_rate": 8.233510877042668e-06, "loss": 0.3867, "num_tokens": 467674081.0, "step": 78350 }, { "epoch": 0.8359382501360246, "grad_norm": 0.5534747551729599, "learning_rate": 8.231461163845466e-06, "loss": 0.4501, "num_tokens": 467720787.0, "step": 78355 }, { "epoch": 0.8359915931422232, "grad_norm": 0.5875431561048301, "learning_rate": 8.229412050245616e-06, "loss": 0.4735, "num_tokens": 467755354.0, "step": 78360 }, { "epoch": 0.8360449361484216, "grad_norm": 0.6262713964049031, "learning_rate": 8.227363536306883e-06, "loss": 0.4583, "num_tokens": 467787459.0, "step": 78365 }, { "epoch": 0.83609827915462, "grad_norm": 0.54511381108639, "learning_rate": 8.225315622093006e-06, "loss": 0.5231, "num_tokens": 467820813.0, "step": 78370 }, { "epoch": 0.8361516221608185, "grad_norm": 1.0715461488011373, "learning_rate": 8.22326830766772e-06, "loss": 0.4631, "num_tokens": 467834392.0, "step": 78375 }, { "epoch": 0.8362049651670169, "grad_norm": 1.0236648419879908, "learning_rate": 8.221221593094727e-06, "loss": 0.4756, "num_tokens": 467858901.0, "step": 78380 }, { "epoch": 0.8362583081732154, "grad_norm": 1.9656660343310075, "learning_rate": 8.219175478437716e-06, "loss": 0.4317, "num_tokens": 467896718.0, "step": 78385 }, { "epoch": 0.8363116511794139, "grad_norm": 0.9987562562352481, "learning_rate": 8.21712996376036e-06, "loss": 0.4221, "num_tokens": 467918849.0, "step": 78390 }, { "epoch": 0.8363649941856123, "grad_norm": 1.2299591674696349, "learning_rate": 8.215085049126318e-06, "loss": 0.5288, "num_tokens": 467945067.0, "step": 78395 }, { "epoch": 0.8364183371918108, "grad_norm": 1.0806825295284948, "learning_rate": 8.213040734599209e-06, "loss": 0.3979, "num_tokens": 467962214.0, "step": 78400 }, { "epoch": 0.8364716801980092, "grad_norm": 7.181464546419191, "learning_rate": 8.210997020242656e-06, "loss": 0.4664, "num_tokens": 467979751.0, "step": 78405 }, { "epoch": 0.8365250232042077, "grad_norm": 1.471889947895875, "learning_rate": 8.20895390612026e-06, "loss": 0.5148, "num_tokens": 467996997.0, "step": 78410 }, { "epoch": 0.8365783662104062, "grad_norm": 0.6774715074690275, "learning_rate": 8.206911392295594e-06, "loss": 0.4417, "num_tokens": 468022968.0, "step": 78415 }, { "epoch": 0.8366317092166046, "grad_norm": 1.7493030426217913, "learning_rate": 8.204869478832211e-06, "loss": 0.5167, "num_tokens": 468042521.0, "step": 78420 }, { "epoch": 0.8366850522228031, "grad_norm": 1.8358460041409683, "learning_rate": 8.202828165793662e-06, "loss": 0.4059, "num_tokens": 468063658.0, "step": 78425 }, { "epoch": 0.8367383952290015, "grad_norm": 1.4576604365283756, "learning_rate": 8.200787453243458e-06, "loss": 0.3967, "num_tokens": 468084753.0, "step": 78430 }, { "epoch": 0.8367917382352, "grad_norm": 1.0759610581859318, "learning_rate": 8.198747341245106e-06, "loss": 0.3686, "num_tokens": 468117641.0, "step": 78435 }, { "epoch": 0.8368450812413984, "grad_norm": 0.9540676317350731, "learning_rate": 8.196707829862092e-06, "loss": 0.3804, "num_tokens": 468141893.0, "step": 78440 }, { "epoch": 0.8368984242475969, "grad_norm": 0.7664325390979032, "learning_rate": 8.194668919157881e-06, "loss": 0.4497, "num_tokens": 468167559.0, "step": 78445 }, { "epoch": 0.8369517672537954, "grad_norm": 0.6819036274446273, "learning_rate": 8.192630609195922e-06, "loss": 0.3569, "num_tokens": 468190275.0, "step": 78450 }, { "epoch": 0.8370051102599938, "grad_norm": 1.2444931356587554, "learning_rate": 8.190592900039638e-06, "loss": 0.4452, "num_tokens": 468208213.0, "step": 78455 }, { "epoch": 0.8370584532661922, "grad_norm": 0.9592202597525539, "learning_rate": 8.188555791752441e-06, "loss": 0.42, "num_tokens": 468233911.0, "step": 78460 }, { "epoch": 0.8371117962723907, "grad_norm": 1.2678085792639935, "learning_rate": 8.18651928439772e-06, "loss": 0.4483, "num_tokens": 468259116.0, "step": 78465 }, { "epoch": 0.8371651392785892, "grad_norm": 1.5713332811233007, "learning_rate": 8.184483378038846e-06, "loss": 0.4719, "num_tokens": 468298145.0, "step": 78470 }, { "epoch": 0.8372184822847877, "grad_norm": 0.8924302365197242, "learning_rate": 8.182448072739177e-06, "loss": 0.4641, "num_tokens": 468326138.0, "step": 78475 }, { "epoch": 0.8372718252909861, "grad_norm": 0.7582437679550778, "learning_rate": 8.180413368562046e-06, "loss": 0.5027, "num_tokens": 468358911.0, "step": 78480 }, { "epoch": 0.8373251682971845, "grad_norm": 1.3522278594176942, "learning_rate": 8.178379265570764e-06, "loss": 0.4724, "num_tokens": 468383521.0, "step": 78485 }, { "epoch": 0.837378511303383, "grad_norm": 0.8436270269744303, "learning_rate": 8.176345763828633e-06, "loss": 0.5698, "num_tokens": 468425301.0, "step": 78490 }, { "epoch": 0.8374318543095814, "grad_norm": 0.8409388809121603, "learning_rate": 8.174312863398927e-06, "loss": 0.4468, "num_tokens": 468457496.0, "step": 78495 }, { "epoch": 0.83748519731578, "grad_norm": 0.5858204264043703, "learning_rate": 8.172280564344908e-06, "loss": 0.4046, "num_tokens": 468488351.0, "step": 78500 }, { "epoch": 0.8375385403219784, "grad_norm": 0.6100057123160405, "learning_rate": 8.170248866729824e-06, "loss": 0.3541, "num_tokens": 468518367.0, "step": 78505 }, { "epoch": 0.8375918833281768, "grad_norm": 0.730913206135337, "learning_rate": 8.168217770616886e-06, "loss": 0.4736, "num_tokens": 468556939.0, "step": 78510 }, { "epoch": 0.8376452263343753, "grad_norm": 0.5968080545051062, "learning_rate": 8.166187276069306e-06, "loss": 0.4089, "num_tokens": 468590180.0, "step": 78515 }, { "epoch": 0.8376985693405737, "grad_norm": 1.2740106074468824, "learning_rate": 8.164157383150264e-06, "loss": 0.428, "num_tokens": 468621611.0, "step": 78520 }, { "epoch": 0.8377519123467723, "grad_norm": 1.1067038706597885, "learning_rate": 8.162128091922925e-06, "loss": 0.5722, "num_tokens": 468659689.0, "step": 78525 }, { "epoch": 0.8378052553529707, "grad_norm": 0.6394790626244831, "learning_rate": 8.160099402450438e-06, "loss": 0.4308, "num_tokens": 468689966.0, "step": 78530 }, { "epoch": 0.8378585983591691, "grad_norm": 1.473259897581625, "learning_rate": 8.158071314795934e-06, "loss": 0.4106, "num_tokens": 468709190.0, "step": 78535 }, { "epoch": 0.8379119413653676, "grad_norm": 4.983018291207477, "learning_rate": 8.156043829022522e-06, "loss": 0.5123, "num_tokens": 468741197.0, "step": 78540 }, { "epoch": 0.837965284371566, "grad_norm": 0.7704873958725493, "learning_rate": 8.154016945193287e-06, "loss": 0.4345, "num_tokens": 468770349.0, "step": 78545 }, { "epoch": 0.8380186273777644, "grad_norm": 2.089947448627325, "learning_rate": 8.151990663371317e-06, "loss": 0.4561, "num_tokens": 468781417.0, "step": 78550 }, { "epoch": 0.838071970383963, "grad_norm": 1.2254048646718327, "learning_rate": 8.14996498361965e-06, "loss": 0.501, "num_tokens": 468812973.0, "step": 78555 }, { "epoch": 0.8381253133901614, "grad_norm": 0.6034554572650145, "learning_rate": 8.147939906001325e-06, "loss": 0.3902, "num_tokens": 468845105.0, "step": 78560 }, { "epoch": 0.8381786563963599, "grad_norm": 0.9109938281952619, "learning_rate": 8.145915430579365e-06, "loss": 0.5124, "num_tokens": 468886034.0, "step": 78565 }, { "epoch": 0.8382319994025583, "grad_norm": 1.0102032329636192, "learning_rate": 8.143891557416755e-06, "loss": 0.4964, "num_tokens": 468902203.0, "step": 78570 }, { "epoch": 0.8382853424087567, "grad_norm": 1.3597096008311644, "learning_rate": 8.141868286576482e-06, "loss": 0.4312, "num_tokens": 468929532.0, "step": 78575 }, { "epoch": 0.8383386854149553, "grad_norm": 0.9524666018146206, "learning_rate": 8.139845618121513e-06, "loss": 0.3437, "num_tokens": 468947298.0, "step": 78580 }, { "epoch": 0.8383920284211537, "grad_norm": 1.2231240368282763, "learning_rate": 8.137823552114774e-06, "loss": 0.5386, "num_tokens": 468971991.0, "step": 78585 }, { "epoch": 0.8384453714273522, "grad_norm": 0.7976673727402065, "learning_rate": 8.135802088619202e-06, "loss": 0.4888, "num_tokens": 469004600.0, "step": 78590 }, { "epoch": 0.8384987144335506, "grad_norm": 0.8844641353646873, "learning_rate": 8.133781227697692e-06, "loss": 0.4592, "num_tokens": 469034775.0, "step": 78595 }, { "epoch": 0.838552057439749, "grad_norm": 3.412640602642535, "learning_rate": 8.131760969413128e-06, "loss": 0.4722, "num_tokens": 469049383.0, "step": 78600 }, { "epoch": 0.8386054004459476, "grad_norm": 0.6886309795844372, "learning_rate": 8.129741313828373e-06, "loss": 0.4734, "num_tokens": 469093423.0, "step": 78605 }, { "epoch": 0.838658743452146, "grad_norm": 0.7993485490522698, "learning_rate": 8.12772226100629e-06, "loss": 0.4347, "num_tokens": 469121746.0, "step": 78610 }, { "epoch": 0.8387120864583445, "grad_norm": 0.8231421320069492, "learning_rate": 8.125703811009694e-06, "loss": 0.4108, "num_tokens": 469147881.0, "step": 78615 }, { "epoch": 0.8387654294645429, "grad_norm": 0.8800186991212183, "learning_rate": 8.1236859639014e-06, "loss": 0.4463, "num_tokens": 469182637.0, "step": 78620 }, { "epoch": 0.8388187724707413, "grad_norm": 0.8587837995021915, "learning_rate": 8.121668719744202e-06, "loss": 0.4666, "num_tokens": 469215607.0, "step": 78625 }, { "epoch": 0.8388721154769399, "grad_norm": 0.8283041248807812, "learning_rate": 8.119652078600871e-06, "loss": 0.4273, "num_tokens": 469243887.0, "step": 78630 }, { "epoch": 0.8389254584831383, "grad_norm": 1.0462366754089574, "learning_rate": 8.117636040534154e-06, "loss": 0.5186, "num_tokens": 469286017.0, "step": 78635 }, { "epoch": 0.8389788014893367, "grad_norm": 1.024202949571588, "learning_rate": 8.11562060560679e-06, "loss": 0.509, "num_tokens": 469313518.0, "step": 78640 }, { "epoch": 0.8390321444955352, "grad_norm": 0.7274114725502415, "learning_rate": 8.113605773881498e-06, "loss": 0.4076, "num_tokens": 469348937.0, "step": 78645 }, { "epoch": 0.8390854875017336, "grad_norm": 0.801882731414371, "learning_rate": 8.111591545420973e-06, "loss": 0.5564, "num_tokens": 469394663.0, "step": 78650 }, { "epoch": 0.8391388305079321, "grad_norm": 0.8474666528720669, "learning_rate": 8.109577920287895e-06, "loss": 0.4355, "num_tokens": 469428441.0, "step": 78655 }, { "epoch": 0.8391921735141306, "grad_norm": 1.0251405006617995, "learning_rate": 8.10756489854492e-06, "loss": 0.5956, "num_tokens": 469460978.0, "step": 78660 }, { "epoch": 0.839245516520329, "grad_norm": 1.686424512656794, "learning_rate": 8.105552480254699e-06, "loss": 0.4997, "num_tokens": 469480397.0, "step": 78665 }, { "epoch": 0.8392988595265275, "grad_norm": 1.533649890494014, "learning_rate": 8.103540665479847e-06, "loss": 0.4641, "num_tokens": 469505814.0, "step": 78670 }, { "epoch": 0.8393522025327259, "grad_norm": 0.7863269557056817, "learning_rate": 8.101529454282961e-06, "loss": 0.5016, "num_tokens": 469540036.0, "step": 78675 }, { "epoch": 0.8394055455389244, "grad_norm": 2.145768459285988, "learning_rate": 8.099518846726633e-06, "loss": 0.5224, "num_tokens": 469568549.0, "step": 78680 }, { "epoch": 0.8394588885451228, "grad_norm": 1.5227570865095115, "learning_rate": 8.097508842873436e-06, "loss": 0.4661, "num_tokens": 469581827.0, "step": 78685 }, { "epoch": 0.8395122315513213, "grad_norm": 1.2424396813167662, "learning_rate": 8.095499442785904e-06, "loss": 0.4746, "num_tokens": 469599561.0, "step": 78690 }, { "epoch": 0.8395655745575198, "grad_norm": 0.8587713216964641, "learning_rate": 8.09349064652657e-06, "loss": 0.4016, "num_tokens": 469632530.0, "step": 78695 }, { "epoch": 0.8396189175637182, "grad_norm": 1.0379700494146007, "learning_rate": 8.091482454157951e-06, "loss": 0.3482, "num_tokens": 469651507.0, "step": 78700 }, { "epoch": 0.8396722605699167, "grad_norm": 0.69345479337594, "learning_rate": 8.089474865742531e-06, "loss": 0.7075, "num_tokens": 469678150.0, "step": 78705 }, { "epoch": 0.8397256035761151, "grad_norm": 1.2113360587990947, "learning_rate": 8.08746788134278e-06, "loss": 0.4728, "num_tokens": 469711889.0, "step": 78710 }, { "epoch": 0.8397789465823136, "grad_norm": 0.6480405077836684, "learning_rate": 8.085461501021156e-06, "loss": 0.4297, "num_tokens": 469748677.0, "step": 78715 }, { "epoch": 0.8398322895885121, "grad_norm": 0.7565794069721666, "learning_rate": 8.08345572484009e-06, "loss": 0.4317, "num_tokens": 469791498.0, "step": 78720 }, { "epoch": 0.8398856325947105, "grad_norm": 0.6878617832134394, "learning_rate": 8.081450552861995e-06, "loss": 0.4783, "num_tokens": 469814356.0, "step": 78725 }, { "epoch": 0.8399389756009089, "grad_norm": 0.7834390979765234, "learning_rate": 8.07944598514928e-06, "loss": 0.4104, "num_tokens": 469844848.0, "step": 78730 }, { "epoch": 0.8399923186071074, "grad_norm": 1.0326577902026182, "learning_rate": 8.077442021764308e-06, "loss": 0.5731, "num_tokens": 469860389.0, "step": 78735 }, { "epoch": 0.8400456616133058, "grad_norm": 1.5255746559306826, "learning_rate": 8.075438662769452e-06, "loss": 0.5442, "num_tokens": 469881564.0, "step": 78740 }, { "epoch": 0.8400990046195044, "grad_norm": 0.7952056245190855, "learning_rate": 8.073435908227045e-06, "loss": 0.4096, "num_tokens": 469902619.0, "step": 78745 }, { "epoch": 0.8401523476257028, "grad_norm": 0.8632838615651864, "learning_rate": 8.071433758199404e-06, "loss": 0.4188, "num_tokens": 469929119.0, "step": 78750 }, { "epoch": 0.8402056906319012, "grad_norm": 1.1553819200524318, "learning_rate": 8.069432212748839e-06, "loss": 0.4501, "num_tokens": 469963774.0, "step": 78755 }, { "epoch": 0.8402590336380997, "grad_norm": 0.7125420224040918, "learning_rate": 8.067431271937634e-06, "loss": 0.351, "num_tokens": 469995503.0, "step": 78760 }, { "epoch": 0.8403123766442981, "grad_norm": 0.7951333203594103, "learning_rate": 8.06543093582805e-06, "loss": 0.4591, "num_tokens": 470012308.0, "step": 78765 }, { "epoch": 0.8403657196504967, "grad_norm": 1.071571529242667, "learning_rate": 8.063431204482335e-06, "loss": 0.3876, "num_tokens": 470040312.0, "step": 78770 }, { "epoch": 0.8404190626566951, "grad_norm": 0.7490523818761059, "learning_rate": 8.061432077962725e-06, "loss": 0.5145, "num_tokens": 470077112.0, "step": 78775 }, { "epoch": 0.8404724056628935, "grad_norm": 3.359532224377728, "learning_rate": 8.05943355633141e-06, "loss": 0.5086, "num_tokens": 470106009.0, "step": 78780 }, { "epoch": 0.840525748669092, "grad_norm": 1.1374775962009445, "learning_rate": 8.057435639650594e-06, "loss": 0.4607, "num_tokens": 470128562.0, "step": 78785 }, { "epoch": 0.8405790916752904, "grad_norm": 1.3169386591419852, "learning_rate": 8.055438327982446e-06, "loss": 0.4976, "num_tokens": 470149923.0, "step": 78790 }, { "epoch": 0.840632434681489, "grad_norm": 1.4134613785681174, "learning_rate": 8.053441621389115e-06, "loss": 0.5589, "num_tokens": 470195074.0, "step": 78795 }, { "epoch": 0.8406857776876874, "grad_norm": 0.8969857995314208, "learning_rate": 8.051445519932735e-06, "loss": 0.4872, "num_tokens": 470246562.0, "step": 78800 }, { "epoch": 0.8407391206938858, "grad_norm": 1.0237168342357865, "learning_rate": 8.049450023675428e-06, "loss": 0.4407, "num_tokens": 470263984.0, "step": 78805 }, { "epoch": 0.8407924637000843, "grad_norm": 0.6663660328824023, "learning_rate": 8.047455132679282e-06, "loss": 0.3978, "num_tokens": 470292556.0, "step": 78810 }, { "epoch": 0.8408458067062827, "grad_norm": 0.6236867618807818, "learning_rate": 8.045460847006374e-06, "loss": 0.4271, "num_tokens": 470312768.0, "step": 78815 }, { "epoch": 0.8408991497124811, "grad_norm": 0.8016768650376187, "learning_rate": 8.043467166718764e-06, "loss": 0.4333, "num_tokens": 470345407.0, "step": 78820 }, { "epoch": 0.8409524927186797, "grad_norm": 1.5880765966818404, "learning_rate": 8.04147409187849e-06, "loss": 0.4708, "num_tokens": 470371977.0, "step": 78825 }, { "epoch": 0.8410058357248781, "grad_norm": 0.664650271999128, "learning_rate": 8.039481622547572e-06, "loss": 0.5248, "num_tokens": 470397146.0, "step": 78830 }, { "epoch": 0.8410591787310766, "grad_norm": 0.6214957839254813, "learning_rate": 8.037489758788018e-06, "loss": 0.4679, "num_tokens": 470432779.0, "step": 78835 }, { "epoch": 0.841112521737275, "grad_norm": 1.853761536788065, "learning_rate": 8.0354985006618e-06, "loss": 0.4988, "num_tokens": 470455300.0, "step": 78840 }, { "epoch": 0.8411658647434734, "grad_norm": 1.0312111048131427, "learning_rate": 8.03350784823089e-06, "loss": 0.5221, "num_tokens": 470469780.0, "step": 78845 }, { "epoch": 0.841219207749672, "grad_norm": 0.8408851951755726, "learning_rate": 8.031517801557235e-06, "loss": 0.5117, "num_tokens": 470500019.0, "step": 78850 }, { "epoch": 0.8412725507558704, "grad_norm": 1.2485875350186386, "learning_rate": 8.029528360702746e-06, "loss": 0.4362, "num_tokens": 470538326.0, "step": 78855 }, { "epoch": 0.8413258937620689, "grad_norm": 1.0059342349490537, "learning_rate": 8.027539525729346e-06, "loss": 0.4187, "num_tokens": 470561200.0, "step": 78860 }, { "epoch": 0.8413792367682673, "grad_norm": 0.9962263228062694, "learning_rate": 8.025551296698924e-06, "loss": 0.5965, "num_tokens": 470598559.0, "step": 78865 }, { "epoch": 0.8414325797744657, "grad_norm": 1.2296996807848433, "learning_rate": 8.023563673673336e-06, "loss": 0.4602, "num_tokens": 470622465.0, "step": 78870 }, { "epoch": 0.8414859227806643, "grad_norm": 0.7336352931360697, "learning_rate": 8.02157665671444e-06, "loss": 0.5051, "num_tokens": 470649550.0, "step": 78875 }, { "epoch": 0.8415392657868627, "grad_norm": 1.3481800031960551, "learning_rate": 8.019590245884076e-06, "loss": 0.4999, "num_tokens": 470675286.0, "step": 78880 }, { "epoch": 0.8415926087930612, "grad_norm": 0.677735774475325, "learning_rate": 8.017604441244048e-06, "loss": 0.4375, "num_tokens": 470702234.0, "step": 78885 }, { "epoch": 0.8416459517992596, "grad_norm": 0.9316255849302797, "learning_rate": 8.015619242856149e-06, "loss": 0.3461, "num_tokens": 470719959.0, "step": 78890 }, { "epoch": 0.841699294805458, "grad_norm": 0.7572851803892444, "learning_rate": 8.013634650782161e-06, "loss": 0.5377, "num_tokens": 470766442.0, "step": 78895 }, { "epoch": 0.8417526378116565, "grad_norm": 1.1841926069110258, "learning_rate": 8.011650665083829e-06, "loss": 0.4412, "num_tokens": 470793176.0, "step": 78900 }, { "epoch": 0.841805980817855, "grad_norm": 0.9958127867044791, "learning_rate": 8.009667285822901e-06, "loss": 0.5254, "num_tokens": 470817946.0, "step": 78905 }, { "epoch": 0.8418593238240534, "grad_norm": 1.553620591030334, "learning_rate": 8.007684513061096e-06, "loss": 0.4963, "num_tokens": 470867276.0, "step": 78910 }, { "epoch": 0.8419126668302519, "grad_norm": 1.1484396827037289, "learning_rate": 8.005702346860108e-06, "loss": 0.4946, "num_tokens": 470894393.0, "step": 78915 }, { "epoch": 0.8419660098364503, "grad_norm": 1.033890143054466, "learning_rate": 8.003720787281626e-06, "loss": 0.5848, "num_tokens": 470935796.0, "step": 78920 }, { "epoch": 0.8420193528426488, "grad_norm": 1.6454060857477655, "learning_rate": 8.001739834387303e-06, "loss": 0.56, "num_tokens": 470956259.0, "step": 78925 }, { "epoch": 0.8420726958488473, "grad_norm": 1.0478218125418035, "learning_rate": 7.999759488238783e-06, "loss": 0.3646, "num_tokens": 470977120.0, "step": 78930 }, { "epoch": 0.8421260388550457, "grad_norm": 1.4151555041536594, "learning_rate": 7.997779748897693e-06, "loss": 0.5411, "num_tokens": 471012972.0, "step": 78935 }, { "epoch": 0.8421793818612442, "grad_norm": 0.7021955360185959, "learning_rate": 7.995800616425643e-06, "loss": 0.4846, "num_tokens": 471048395.0, "step": 78940 }, { "epoch": 0.8422327248674426, "grad_norm": 0.8390574708841417, "learning_rate": 7.993822090884209e-06, "loss": 0.386, "num_tokens": 471070773.0, "step": 78945 }, { "epoch": 0.8422860678736411, "grad_norm": 0.6396139667977038, "learning_rate": 7.991844172334968e-06, "loss": 0.4294, "num_tokens": 471097648.0, "step": 78950 }, { "epoch": 0.8423394108798395, "grad_norm": 0.868546660596981, "learning_rate": 7.989866860839467e-06, "loss": 0.5009, "num_tokens": 471121564.0, "step": 78955 }, { "epoch": 0.842392753886038, "grad_norm": 0.9083997209284744, "learning_rate": 7.987890156459235e-06, "loss": 0.4606, "num_tokens": 471149149.0, "step": 78960 }, { "epoch": 0.8424460968922365, "grad_norm": 0.9400755080095768, "learning_rate": 7.98591405925578e-06, "loss": 0.4318, "num_tokens": 471193175.0, "step": 78965 }, { "epoch": 0.8424994398984349, "grad_norm": 1.4090762984089997, "learning_rate": 7.983938569290599e-06, "loss": 0.595, "num_tokens": 471224192.0, "step": 78970 }, { "epoch": 0.8425527829046334, "grad_norm": 0.6906436007090828, "learning_rate": 7.981963686625158e-06, "loss": 0.3813, "num_tokens": 471260818.0, "step": 78975 }, { "epoch": 0.8426061259108318, "grad_norm": 0.6454927791479695, "learning_rate": 7.979989411320915e-06, "loss": 0.4125, "num_tokens": 471305711.0, "step": 78980 }, { "epoch": 0.8426594689170303, "grad_norm": 1.161495202844917, "learning_rate": 7.978015743439313e-06, "loss": 0.4491, "num_tokens": 471321462.0, "step": 78985 }, { "epoch": 0.8427128119232288, "grad_norm": 0.6426075473328029, "learning_rate": 7.976042683041757e-06, "loss": 0.4697, "num_tokens": 471358672.0, "step": 78990 }, { "epoch": 0.8427661549294272, "grad_norm": 1.160639028216049, "learning_rate": 7.97407023018965e-06, "loss": 0.5559, "num_tokens": 471397168.0, "step": 78995 }, { "epoch": 0.8428194979356256, "grad_norm": 0.8743186104804931, "learning_rate": 7.972098384944374e-06, "loss": 0.5045, "num_tokens": 471423861.0, "step": 79000 }, { "epoch": 0.8428728409418241, "grad_norm": 0.8759744199583747, "learning_rate": 7.97012714736728e-06, "loss": 0.5221, "num_tokens": 471464883.0, "step": 79005 }, { "epoch": 0.8429261839480225, "grad_norm": 0.5933726368832869, "learning_rate": 7.968156517519711e-06, "loss": 0.41, "num_tokens": 471489029.0, "step": 79010 }, { "epoch": 0.8429795269542211, "grad_norm": 0.7089509349202375, "learning_rate": 7.966186495463e-06, "loss": 0.3527, "num_tokens": 471508401.0, "step": 79015 }, { "epoch": 0.8430328699604195, "grad_norm": 1.8256837046805632, "learning_rate": 7.964217081258434e-06, "loss": 0.395, "num_tokens": 471519732.0, "step": 79020 }, { "epoch": 0.8430862129666179, "grad_norm": 2.1934332101494483, "learning_rate": 7.962248274967306e-06, "loss": 0.512, "num_tokens": 471546027.0, "step": 79025 }, { "epoch": 0.8431395559728164, "grad_norm": 0.8261112432813978, "learning_rate": 7.960280076650886e-06, "loss": 0.4647, "num_tokens": 471576896.0, "step": 79030 }, { "epoch": 0.8431928989790148, "grad_norm": 1.3712079132698771, "learning_rate": 7.958312486370412e-06, "loss": 0.5409, "num_tokens": 471603415.0, "step": 79035 }, { "epoch": 0.8432462419852134, "grad_norm": 1.4019735576204835, "learning_rate": 7.95634550418711e-06, "loss": 0.3822, "num_tokens": 471616902.0, "step": 79040 }, { "epoch": 0.8432995849914118, "grad_norm": 1.1425432885100995, "learning_rate": 7.954379130162198e-06, "loss": 0.6297, "num_tokens": 471650421.0, "step": 79045 }, { "epoch": 0.8433529279976102, "grad_norm": 0.6234398435873881, "learning_rate": 7.952413364356853e-06, "loss": 0.3973, "num_tokens": 471680135.0, "step": 79050 }, { "epoch": 0.8434062710038087, "grad_norm": 0.7812871166243265, "learning_rate": 7.950448206832253e-06, "loss": 0.4715, "num_tokens": 471695228.0, "step": 79055 }, { "epoch": 0.8434596140100071, "grad_norm": 0.9980033325308619, "learning_rate": 7.948483657649552e-06, "loss": 0.4224, "num_tokens": 471725739.0, "step": 79060 }, { "epoch": 0.8435129570162057, "grad_norm": 1.13937187673845, "learning_rate": 7.946519716869877e-06, "loss": 0.501, "num_tokens": 471752198.0, "step": 79065 }, { "epoch": 0.8435663000224041, "grad_norm": 0.9072899592611569, "learning_rate": 7.94455638455435e-06, "loss": 0.4533, "num_tokens": 471772770.0, "step": 79070 }, { "epoch": 0.8436196430286025, "grad_norm": 1.7826222784614918, "learning_rate": 7.942593660764058e-06, "loss": 0.393, "num_tokens": 471796346.0, "step": 79075 }, { "epoch": 0.843672986034801, "grad_norm": 1.07630951175773, "learning_rate": 7.940631545560075e-06, "loss": 0.5911, "num_tokens": 471844518.0, "step": 79080 }, { "epoch": 0.8437263290409994, "grad_norm": 1.5949439619334056, "learning_rate": 7.938670039003462e-06, "loss": 0.4317, "num_tokens": 471872942.0, "step": 79085 }, { "epoch": 0.8437796720471978, "grad_norm": 0.8129785524768266, "learning_rate": 7.936709141155263e-06, "loss": 0.4622, "num_tokens": 471900857.0, "step": 79090 }, { "epoch": 0.8438330150533964, "grad_norm": 0.6598408438793215, "learning_rate": 7.934748852076486e-06, "loss": 0.4577, "num_tokens": 471930457.0, "step": 79095 }, { "epoch": 0.8438863580595948, "grad_norm": 0.9256622761579364, "learning_rate": 7.932789171828141e-06, "loss": 0.5157, "num_tokens": 471952501.0, "step": 79100 }, { "epoch": 0.8439397010657933, "grad_norm": 0.6755763211943591, "learning_rate": 7.930830100471203e-06, "loss": 0.5293, "num_tokens": 471999998.0, "step": 79105 }, { "epoch": 0.8439930440719917, "grad_norm": 1.3218092846165634, "learning_rate": 7.928871638066635e-06, "loss": 0.4912, "num_tokens": 472029550.0, "step": 79110 }, { "epoch": 0.8440463870781901, "grad_norm": 0.7897716400947302, "learning_rate": 7.92691378467538e-06, "loss": 0.3807, "num_tokens": 472061139.0, "step": 79115 }, { "epoch": 0.8440997300843887, "grad_norm": 1.4879893945853764, "learning_rate": 7.924956540358368e-06, "loss": 0.4459, "num_tokens": 472084367.0, "step": 79120 }, { "epoch": 0.8441530730905871, "grad_norm": 0.6972248806922402, "learning_rate": 7.922999905176496e-06, "loss": 0.4935, "num_tokens": 472132644.0, "step": 79125 }, { "epoch": 0.8442064160967856, "grad_norm": 1.013322526035627, "learning_rate": 7.921043879190653e-06, "loss": 0.4765, "num_tokens": 472149412.0, "step": 79130 }, { "epoch": 0.844259759102984, "grad_norm": 0.9207590339798682, "learning_rate": 7.919088462461716e-06, "loss": 0.3555, "num_tokens": 472172204.0, "step": 79135 }, { "epoch": 0.8443131021091824, "grad_norm": 0.8768516934340806, "learning_rate": 7.917133655050524e-06, "loss": 0.4221, "num_tokens": 472201877.0, "step": 79140 }, { "epoch": 0.844366445115381, "grad_norm": 1.2699113433752494, "learning_rate": 7.915179457017905e-06, "loss": 0.4128, "num_tokens": 472232501.0, "step": 79145 }, { "epoch": 0.8444197881215794, "grad_norm": 0.8034639047733996, "learning_rate": 7.913225868424674e-06, "loss": 0.3742, "num_tokens": 472248853.0, "step": 79150 }, { "epoch": 0.8444731311277779, "grad_norm": 1.0352223471725974, "learning_rate": 7.911272889331618e-06, "loss": 0.3454, "num_tokens": 472262164.0, "step": 79155 }, { "epoch": 0.8445264741339763, "grad_norm": 1.5153825093540647, "learning_rate": 7.909320519799515e-06, "loss": 0.4751, "num_tokens": 472282063.0, "step": 79160 }, { "epoch": 0.8445798171401747, "grad_norm": 0.8588486914258211, "learning_rate": 7.907368759889123e-06, "loss": 0.4632, "num_tokens": 472316145.0, "step": 79165 }, { "epoch": 0.8446331601463732, "grad_norm": 1.060796796798225, "learning_rate": 7.905417609661161e-06, "loss": 0.4609, "num_tokens": 472342932.0, "step": 79170 }, { "epoch": 0.8446865031525717, "grad_norm": 1.2380019056323122, "learning_rate": 7.903467069176365e-06, "loss": 0.377, "num_tokens": 472359387.0, "step": 79175 }, { "epoch": 0.8447398461587701, "grad_norm": 0.6132714087396467, "learning_rate": 7.901517138495418e-06, "loss": 0.4652, "num_tokens": 472427127.0, "step": 79180 }, { "epoch": 0.8447931891649686, "grad_norm": 0.9483543962803092, "learning_rate": 7.899567817678996e-06, "loss": 0.6021, "num_tokens": 472469736.0, "step": 79185 }, { "epoch": 0.844846532171167, "grad_norm": 0.8188397255354701, "learning_rate": 7.897619106787765e-06, "loss": 0.5235, "num_tokens": 472512429.0, "step": 79190 }, { "epoch": 0.8448998751773655, "grad_norm": 0.8175585604162809, "learning_rate": 7.895671005882366e-06, "loss": 0.3425, "num_tokens": 472542707.0, "step": 79195 }, { "epoch": 0.844953218183564, "grad_norm": 0.731641217808571, "learning_rate": 7.893723515023415e-06, "loss": 0.4482, "num_tokens": 472574525.0, "step": 79200 }, { "epoch": 0.8450065611897624, "grad_norm": 0.89754181124838, "learning_rate": 7.891776634271514e-06, "loss": 0.4605, "num_tokens": 472615421.0, "step": 79205 }, { "epoch": 0.8450599041959609, "grad_norm": 1.5362170546665037, "learning_rate": 7.889830363687252e-06, "loss": 0.6001, "num_tokens": 472655970.0, "step": 79210 }, { "epoch": 0.8451132472021593, "grad_norm": 1.3561968470987547, "learning_rate": 7.88788470333119e-06, "loss": 0.6229, "num_tokens": 472696786.0, "step": 79215 }, { "epoch": 0.8451665902083578, "grad_norm": 0.9188277406579777, "learning_rate": 7.885939653263864e-06, "loss": 0.44, "num_tokens": 472722882.0, "step": 79220 }, { "epoch": 0.8452199332145562, "grad_norm": 0.7099165007139441, "learning_rate": 7.883995213545814e-06, "loss": 0.4601, "num_tokens": 472745227.0, "step": 79225 }, { "epoch": 0.8452732762207547, "grad_norm": 0.5136945874380082, "learning_rate": 7.882051384237536e-06, "loss": 0.5017, "num_tokens": 472800365.0, "step": 79230 }, { "epoch": 0.8453266192269532, "grad_norm": 0.859454299947219, "learning_rate": 7.880108165399523e-06, "loss": 0.4896, "num_tokens": 472844171.0, "step": 79235 }, { "epoch": 0.8453799622331516, "grad_norm": 1.0807723980966037, "learning_rate": 7.87816555709225e-06, "loss": 0.5733, "num_tokens": 472873370.0, "step": 79240 }, { "epoch": 0.8454333052393501, "grad_norm": 0.6598003146262482, "learning_rate": 7.876223559376151e-06, "loss": 0.4489, "num_tokens": 472915078.0, "step": 79245 }, { "epoch": 0.8454866482455485, "grad_norm": 0.8586800156176126, "learning_rate": 7.874282172311673e-06, "loss": 0.416, "num_tokens": 472951752.0, "step": 79250 }, { "epoch": 0.845539991251747, "grad_norm": 1.0920667252557177, "learning_rate": 7.872341395959224e-06, "loss": 0.4565, "num_tokens": 472981202.0, "step": 79255 }, { "epoch": 0.8455933342579455, "grad_norm": 0.7661973186415953, "learning_rate": 7.870401230379187e-06, "loss": 0.5115, "num_tokens": 473017941.0, "step": 79260 }, { "epoch": 0.8456466772641439, "grad_norm": 0.8604983941504583, "learning_rate": 7.868461675631943e-06, "loss": 0.427, "num_tokens": 473042839.0, "step": 79265 }, { "epoch": 0.8457000202703423, "grad_norm": 0.6623299664947556, "learning_rate": 7.866522731777852e-06, "loss": 0.4789, "num_tokens": 473072202.0, "step": 79270 }, { "epoch": 0.8457533632765408, "grad_norm": 1.450935788717784, "learning_rate": 7.864584398877243e-06, "loss": 0.4985, "num_tokens": 473093642.0, "step": 79275 }, { "epoch": 0.8458067062827392, "grad_norm": 1.4566091554974707, "learning_rate": 7.862646676990435e-06, "loss": 0.4117, "num_tokens": 473142223.0, "step": 79280 }, { "epoch": 0.8458600492889378, "grad_norm": 0.5227513938308876, "learning_rate": 7.860709566177729e-06, "loss": 0.3666, "num_tokens": 473166018.0, "step": 79285 }, { "epoch": 0.8459133922951362, "grad_norm": 1.516496957810895, "learning_rate": 7.8587730664994e-06, "loss": 0.4902, "num_tokens": 473182341.0, "step": 79290 }, { "epoch": 0.8459667353013346, "grad_norm": 3.2669203885062235, "learning_rate": 7.856837178015707e-06, "loss": 0.4383, "num_tokens": 473204732.0, "step": 79295 }, { "epoch": 0.8460200783075331, "grad_norm": 0.7338382229574513, "learning_rate": 7.854901900786897e-06, "loss": 0.3805, "num_tokens": 473231206.0, "step": 79300 }, { "epoch": 0.8460734213137315, "grad_norm": 0.7718199489944574, "learning_rate": 7.852967234873182e-06, "loss": 0.4711, "num_tokens": 473261794.0, "step": 79305 }, { "epoch": 0.8461267643199301, "grad_norm": 0.8761002615276908, "learning_rate": 7.85103318033477e-06, "loss": 0.3809, "num_tokens": 473281095.0, "step": 79310 }, { "epoch": 0.8461801073261285, "grad_norm": 1.1108694711209224, "learning_rate": 7.849099737231851e-06, "loss": 0.4008, "num_tokens": 473299933.0, "step": 79315 }, { "epoch": 0.8462334503323269, "grad_norm": 0.945334305179975, "learning_rate": 7.847166905624581e-06, "loss": 0.4063, "num_tokens": 473323129.0, "step": 79320 }, { "epoch": 0.8462867933385254, "grad_norm": 0.622550713602306, "learning_rate": 7.845234685573111e-06, "loss": 0.4433, "num_tokens": 473353624.0, "step": 79325 }, { "epoch": 0.8463401363447238, "grad_norm": 0.820957801838047, "learning_rate": 7.843303077137564e-06, "loss": 0.4687, "num_tokens": 473381538.0, "step": 79330 }, { "epoch": 0.8463934793509224, "grad_norm": 0.79175975864844, "learning_rate": 7.841372080378049e-06, "loss": 0.464, "num_tokens": 473406012.0, "step": 79335 }, { "epoch": 0.8464468223571208, "grad_norm": 1.2336835033505522, "learning_rate": 7.839441695354651e-06, "loss": 0.3957, "num_tokens": 473431808.0, "step": 79340 }, { "epoch": 0.8465001653633192, "grad_norm": 0.8105649457818307, "learning_rate": 7.837511922127452e-06, "loss": 0.4696, "num_tokens": 473475418.0, "step": 79345 }, { "epoch": 0.8465535083695177, "grad_norm": 0.8880015265957798, "learning_rate": 7.835582760756486e-06, "loss": 0.4577, "num_tokens": 473504203.0, "step": 79350 }, { "epoch": 0.8466068513757161, "grad_norm": 0.781672557582623, "learning_rate": 7.833654211301795e-06, "loss": 0.4558, "num_tokens": 473540621.0, "step": 79355 }, { "epoch": 0.8466601943819145, "grad_norm": 0.8803238868670457, "learning_rate": 7.831726273823391e-06, "loss": 0.3655, "num_tokens": 473570581.0, "step": 79360 }, { "epoch": 0.8467135373881131, "grad_norm": 0.7802715079951095, "learning_rate": 7.82979894838127e-06, "loss": 0.3808, "num_tokens": 473593656.0, "step": 79365 }, { "epoch": 0.8467668803943115, "grad_norm": 0.5782541228736778, "learning_rate": 7.827872235035394e-06, "loss": 0.5167, "num_tokens": 473630485.0, "step": 79370 }, { "epoch": 0.84682022340051, "grad_norm": 0.9768848154164301, "learning_rate": 7.825946133845724e-06, "loss": 0.4507, "num_tokens": 473662473.0, "step": 79375 }, { "epoch": 0.8468735664067084, "grad_norm": 0.8572680150198198, "learning_rate": 7.824020644872208e-06, "loss": 0.4343, "num_tokens": 473697500.0, "step": 79380 }, { "epoch": 0.8469269094129068, "grad_norm": 1.4260534035625738, "learning_rate": 7.82209576817475e-06, "loss": 0.4973, "num_tokens": 473721519.0, "step": 79385 }, { "epoch": 0.8469802524191054, "grad_norm": 0.7303278672327338, "learning_rate": 7.820171503813251e-06, "loss": 0.4542, "num_tokens": 473757902.0, "step": 79390 }, { "epoch": 0.8470335954253038, "grad_norm": 0.5853106417033284, "learning_rate": 7.818247851847595e-06, "loss": 0.646, "num_tokens": 473799240.0, "step": 79395 }, { "epoch": 0.8470869384315023, "grad_norm": 1.5287125431133206, "learning_rate": 7.816324812337633e-06, "loss": 0.4159, "num_tokens": 473826092.0, "step": 79400 }, { "epoch": 0.8471402814377007, "grad_norm": 1.1179567132974548, "learning_rate": 7.814402385343214e-06, "loss": 0.4016, "num_tokens": 473853414.0, "step": 79405 }, { "epoch": 0.8471936244438991, "grad_norm": 1.0323597852095443, "learning_rate": 7.812480570924158e-06, "loss": 0.4132, "num_tokens": 473876159.0, "step": 79410 }, { "epoch": 0.8472469674500976, "grad_norm": 0.6042697625420853, "learning_rate": 7.810559369140264e-06, "loss": 0.3553, "num_tokens": 473896723.0, "step": 79415 }, { "epoch": 0.8473003104562961, "grad_norm": 0.7024370793850441, "learning_rate": 7.80863878005132e-06, "loss": 0.4955, "num_tokens": 473943284.0, "step": 79420 }, { "epoch": 0.8473536534624946, "grad_norm": 0.7158919483435612, "learning_rate": 7.806718803717094e-06, "loss": 0.5624, "num_tokens": 474002322.0, "step": 79425 }, { "epoch": 0.847406996468693, "grad_norm": 1.0043328695673275, "learning_rate": 7.804799440197328e-06, "loss": 0.5747, "num_tokens": 474036218.0, "step": 79430 }, { "epoch": 0.8474603394748914, "grad_norm": 0.7184220584894531, "learning_rate": 7.802880689551745e-06, "loss": 0.4747, "num_tokens": 474075380.0, "step": 79435 }, { "epoch": 0.8475136824810899, "grad_norm": 0.751638816093435, "learning_rate": 7.800962551840057e-06, "loss": 0.4338, "num_tokens": 474105694.0, "step": 79440 }, { "epoch": 0.8475670254872884, "grad_norm": 0.9265425112017861, "learning_rate": 7.799045027121952e-06, "loss": 0.4497, "num_tokens": 474139015.0, "step": 79445 }, { "epoch": 0.8476203684934868, "grad_norm": 0.9125288640271412, "learning_rate": 7.797128115457091e-06, "loss": 0.3684, "num_tokens": 474169322.0, "step": 79450 }, { "epoch": 0.8476737114996853, "grad_norm": 0.9710144231424924, "learning_rate": 7.795211816905144e-06, "loss": 0.5282, "num_tokens": 474207388.0, "step": 79455 }, { "epoch": 0.8477270545058837, "grad_norm": 1.5775854517996093, "learning_rate": 7.793296131525724e-06, "loss": 0.5258, "num_tokens": 474224412.0, "step": 79460 }, { "epoch": 0.8477803975120822, "grad_norm": 0.7617993134366463, "learning_rate": 7.791381059378454e-06, "loss": 0.4041, "num_tokens": 474257208.0, "step": 79465 }, { "epoch": 0.8478337405182806, "grad_norm": 0.5805232120285937, "learning_rate": 7.789466600522921e-06, "loss": 0.4707, "num_tokens": 474297104.0, "step": 79470 }, { "epoch": 0.8478870835244791, "grad_norm": 0.9056916151553325, "learning_rate": 7.787552755018698e-06, "loss": 0.4286, "num_tokens": 474320521.0, "step": 79475 }, { "epoch": 0.8479404265306776, "grad_norm": 0.7785650308827875, "learning_rate": 7.785639522925342e-06, "loss": 0.4139, "num_tokens": 474358088.0, "step": 79480 }, { "epoch": 0.847993769536876, "grad_norm": 0.9521461414565595, "learning_rate": 7.783726904302396e-06, "loss": 0.4448, "num_tokens": 474374463.0, "step": 79485 }, { "epoch": 0.8480471125430745, "grad_norm": 0.90043163085611, "learning_rate": 7.781814899209364e-06, "loss": 0.4255, "num_tokens": 474407861.0, "step": 79490 }, { "epoch": 0.8481004555492729, "grad_norm": 0.8424723306188507, "learning_rate": 7.779903507705748e-06, "loss": 0.5015, "num_tokens": 474431192.0, "step": 79495 }, { "epoch": 0.8481537985554713, "grad_norm": 0.8184184314394402, "learning_rate": 7.777992729851037e-06, "loss": 0.4328, "num_tokens": 474455603.0, "step": 79500 }, { "epoch": 0.8482071415616699, "grad_norm": 0.8563214524107915, "learning_rate": 7.77608256570468e-06, "loss": 0.4498, "num_tokens": 474489358.0, "step": 79505 }, { "epoch": 0.8482604845678683, "grad_norm": 0.6395557952799237, "learning_rate": 7.774173015326115e-06, "loss": 0.4361, "num_tokens": 474530618.0, "step": 79510 }, { "epoch": 0.8483138275740668, "grad_norm": 0.799383850220091, "learning_rate": 7.772264078774772e-06, "loss": 0.5764, "num_tokens": 474572503.0, "step": 79515 }, { "epoch": 0.8483671705802652, "grad_norm": 0.9090929551346894, "learning_rate": 7.770355756110045e-06, "loss": 0.5748, "num_tokens": 474607811.0, "step": 79520 }, { "epoch": 0.8484205135864636, "grad_norm": 0.5853912277630536, "learning_rate": 7.768448047391322e-06, "loss": 0.36, "num_tokens": 474638636.0, "step": 79525 }, { "epoch": 0.8484738565926622, "grad_norm": 1.2793013780830194, "learning_rate": 7.76654095267797e-06, "loss": 0.5124, "num_tokens": 474662272.0, "step": 79530 }, { "epoch": 0.8485271995988606, "grad_norm": 0.7375453764296647, "learning_rate": 7.764634472029325e-06, "loss": 0.4787, "num_tokens": 474687825.0, "step": 79535 }, { "epoch": 0.848580542605059, "grad_norm": 1.69927804698223, "learning_rate": 7.76272860550472e-06, "loss": 0.5496, "num_tokens": 474714118.0, "step": 79540 }, { "epoch": 0.8486338856112575, "grad_norm": 0.9847164412683655, "learning_rate": 7.760823353163465e-06, "loss": 0.4722, "num_tokens": 474741160.0, "step": 79545 }, { "epoch": 0.8486872286174559, "grad_norm": 1.2301030852052213, "learning_rate": 7.758918715064832e-06, "loss": 0.4205, "num_tokens": 474768030.0, "step": 79550 }, { "epoch": 0.8487405716236545, "grad_norm": 0.6954034822892952, "learning_rate": 7.757014691268102e-06, "loss": 0.421, "num_tokens": 474798583.0, "step": 79555 }, { "epoch": 0.8487939146298529, "grad_norm": 1.0685756883461033, "learning_rate": 7.755111281832525e-06, "loss": 0.5136, "num_tokens": 474823661.0, "step": 79560 }, { "epoch": 0.8488472576360513, "grad_norm": 0.6784854435658492, "learning_rate": 7.753208486817323e-06, "loss": 0.405, "num_tokens": 474843804.0, "step": 79565 }, { "epoch": 0.8489006006422498, "grad_norm": 1.6931958667221978, "learning_rate": 7.751306306281711e-06, "loss": 0.4661, "num_tokens": 474857433.0, "step": 79570 }, { "epoch": 0.8489539436484482, "grad_norm": 0.94260365473605, "learning_rate": 7.74940474028489e-06, "loss": 0.4748, "num_tokens": 474891983.0, "step": 79575 }, { "epoch": 0.8490072866546468, "grad_norm": 0.9106642292077675, "learning_rate": 7.747503788886019e-06, "loss": 0.5092, "num_tokens": 474925208.0, "step": 79580 }, { "epoch": 0.8490606296608452, "grad_norm": 1.2799532482169362, "learning_rate": 7.745603452144258e-06, "loss": 0.4881, "num_tokens": 474958600.0, "step": 79585 }, { "epoch": 0.8491139726670436, "grad_norm": 0.8077431290293511, "learning_rate": 7.743703730118745e-06, "loss": 0.4251, "num_tokens": 474987140.0, "step": 79590 }, { "epoch": 0.8491673156732421, "grad_norm": 1.0305336186167797, "learning_rate": 7.741804622868583e-06, "loss": 0.4393, "num_tokens": 475034014.0, "step": 79595 }, { "epoch": 0.8492206586794405, "grad_norm": 0.8606757676372815, "learning_rate": 7.739906130452877e-06, "loss": 0.3942, "num_tokens": 475051209.0, "step": 79600 }, { "epoch": 0.849274001685639, "grad_norm": 0.8247031478199719, "learning_rate": 7.738008252930712e-06, "loss": 0.4601, "num_tokens": 475079691.0, "step": 79605 }, { "epoch": 0.8493273446918375, "grad_norm": 1.9265892992684195, "learning_rate": 7.736110990361131e-06, "loss": 0.4732, "num_tokens": 475104317.0, "step": 79610 }, { "epoch": 0.8493806876980359, "grad_norm": 0.6553804499131719, "learning_rate": 7.734214342803185e-06, "loss": 0.413, "num_tokens": 475130438.0, "step": 79615 }, { "epoch": 0.8494340307042344, "grad_norm": 0.7792820532007096, "learning_rate": 7.732318310315888e-06, "loss": 0.5249, "num_tokens": 475161114.0, "step": 79620 }, { "epoch": 0.8494873737104328, "grad_norm": 1.0459044049448882, "learning_rate": 7.730422892958237e-06, "loss": 0.5145, "num_tokens": 475189094.0, "step": 79625 }, { "epoch": 0.8495407167166312, "grad_norm": 0.5799445771754776, "learning_rate": 7.728528090789217e-06, "loss": 0.4888, "num_tokens": 475224095.0, "step": 79630 }, { "epoch": 0.8495940597228298, "grad_norm": 2.6144439821162595, "learning_rate": 7.726633903867796e-06, "loss": 0.5181, "num_tokens": 475249595.0, "step": 79635 }, { "epoch": 0.8496474027290282, "grad_norm": 1.3279483614494838, "learning_rate": 7.724740332252909e-06, "loss": 0.6333, "num_tokens": 475275394.0, "step": 79640 }, { "epoch": 0.8497007457352267, "grad_norm": 0.9051380307326579, "learning_rate": 7.72284737600348e-06, "loss": 0.5278, "num_tokens": 475300157.0, "step": 79645 }, { "epoch": 0.8497540887414251, "grad_norm": 0.6439314750884334, "learning_rate": 7.720955035178425e-06, "loss": 0.4766, "num_tokens": 475326064.0, "step": 79650 }, { "epoch": 0.8498074317476235, "grad_norm": 0.7467075567885975, "learning_rate": 7.719063309836621e-06, "loss": 0.425, "num_tokens": 475365821.0, "step": 79655 }, { "epoch": 0.849860774753822, "grad_norm": 0.8575325377640766, "learning_rate": 7.717172200036932e-06, "loss": 0.4193, "num_tokens": 475386120.0, "step": 79660 }, { "epoch": 0.8499141177600205, "grad_norm": 0.5609235209931605, "learning_rate": 7.715281705838213e-06, "loss": 0.4286, "num_tokens": 475425695.0, "step": 79665 }, { "epoch": 0.849967460766219, "grad_norm": 1.288003894249359, "learning_rate": 7.713391827299282e-06, "loss": 0.4846, "num_tokens": 475453984.0, "step": 79670 }, { "epoch": 0.8500208037724174, "grad_norm": 0.8591401827481644, "learning_rate": 7.711502564478954e-06, "loss": 0.425, "num_tokens": 475483385.0, "step": 79675 }, { "epoch": 0.8500741467786158, "grad_norm": 0.8849451497920254, "learning_rate": 7.709613917436027e-06, "loss": 0.4799, "num_tokens": 475518680.0, "step": 79680 }, { "epoch": 0.8501274897848143, "grad_norm": 0.8670167073161718, "learning_rate": 7.707725886229264e-06, "loss": 0.5642, "num_tokens": 475549975.0, "step": 79685 }, { "epoch": 0.8501808327910128, "grad_norm": 0.7322398038242314, "learning_rate": 7.70583847091741e-06, "loss": 0.3698, "num_tokens": 475567764.0, "step": 79690 }, { "epoch": 0.8502341757972113, "grad_norm": 0.7066097440213156, "learning_rate": 7.703951671559212e-06, "loss": 0.4551, "num_tokens": 475596571.0, "step": 79695 }, { "epoch": 0.8502875188034097, "grad_norm": 1.2544416186121814, "learning_rate": 7.702065488213371e-06, "loss": 0.4888, "num_tokens": 475622783.0, "step": 79700 }, { "epoch": 0.8503408618096081, "grad_norm": 1.4060302431571117, "learning_rate": 7.700179920938583e-06, "loss": 0.5174, "num_tokens": 475638690.0, "step": 79705 }, { "epoch": 0.8503942048158066, "grad_norm": 0.8086263539459285, "learning_rate": 7.698294969793533e-06, "loss": 0.4334, "num_tokens": 475668632.0, "step": 79710 }, { "epoch": 0.850447547822005, "grad_norm": 1.0396848327178447, "learning_rate": 7.696410634836863e-06, "loss": 0.4668, "num_tokens": 475707415.0, "step": 79715 }, { "epoch": 0.8505008908282035, "grad_norm": 0.8043663781883825, "learning_rate": 7.694526916127222e-06, "loss": 0.5688, "num_tokens": 475741012.0, "step": 79720 }, { "epoch": 0.850554233834402, "grad_norm": 0.7904131392070496, "learning_rate": 7.692643813723222e-06, "loss": 0.6151, "num_tokens": 475780463.0, "step": 79725 }, { "epoch": 0.8506075768406004, "grad_norm": 0.9949344088075708, "learning_rate": 7.690761327683457e-06, "loss": 0.404, "num_tokens": 475807820.0, "step": 79730 }, { "epoch": 0.8506609198467989, "grad_norm": 0.8369377317798552, "learning_rate": 7.688879458066508e-06, "loss": 0.5452, "num_tokens": 475859398.0, "step": 79735 }, { "epoch": 0.8507142628529973, "grad_norm": 0.797440103031601, "learning_rate": 7.686998204930945e-06, "loss": 0.4514, "num_tokens": 475887252.0, "step": 79740 }, { "epoch": 0.8507676058591958, "grad_norm": 0.813756176079519, "learning_rate": 7.685117568335293e-06, "loss": 0.4192, "num_tokens": 475907894.0, "step": 79745 }, { "epoch": 0.8508209488653943, "grad_norm": 1.1506464483817263, "learning_rate": 7.683237548338082e-06, "loss": 0.4644, "num_tokens": 475948551.0, "step": 79750 }, { "epoch": 0.8508742918715927, "grad_norm": 1.330841773671706, "learning_rate": 7.68135814499782e-06, "loss": 0.4826, "num_tokens": 475966216.0, "step": 79755 }, { "epoch": 0.8509276348777912, "grad_norm": 2.039379692693882, "learning_rate": 7.679479358372981e-06, "loss": 0.4245, "num_tokens": 475988473.0, "step": 79760 }, { "epoch": 0.8509809778839896, "grad_norm": 0.9887472917574853, "learning_rate": 7.67760118852203e-06, "loss": 0.5684, "num_tokens": 476019305.0, "step": 79765 }, { "epoch": 0.851034320890188, "grad_norm": 1.2619161842608204, "learning_rate": 7.675723635503417e-06, "loss": 0.562, "num_tokens": 476050051.0, "step": 79770 }, { "epoch": 0.8510876638963866, "grad_norm": 0.9212982395205089, "learning_rate": 7.67384669937556e-06, "loss": 0.466, "num_tokens": 476080647.0, "step": 79775 }, { "epoch": 0.851141006902585, "grad_norm": 0.998061965556065, "learning_rate": 7.67197038019687e-06, "loss": 0.408, "num_tokens": 476099995.0, "step": 79780 }, { "epoch": 0.8511943499087835, "grad_norm": 1.6093325267631748, "learning_rate": 7.670094678025739e-06, "loss": 0.4509, "num_tokens": 476121822.0, "step": 79785 }, { "epoch": 0.8512476929149819, "grad_norm": 1.3460831628541625, "learning_rate": 7.668219592920523e-06, "loss": 0.5339, "num_tokens": 476165332.0, "step": 79790 }, { "epoch": 0.8513010359211803, "grad_norm": 0.8623637709479423, "learning_rate": 7.666345124939582e-06, "loss": 0.4149, "num_tokens": 476191439.0, "step": 79795 }, { "epoch": 0.8513543789273789, "grad_norm": 0.9236912924297315, "learning_rate": 7.664471274141244e-06, "loss": 0.4749, "num_tokens": 476209957.0, "step": 79800 }, { "epoch": 0.8514077219335773, "grad_norm": 0.8022554666340546, "learning_rate": 7.662598040583811e-06, "loss": 0.6229, "num_tokens": 476231699.0, "step": 79805 }, { "epoch": 0.8514610649397757, "grad_norm": 0.6727009478882104, "learning_rate": 7.660725424325578e-06, "loss": 0.4296, "num_tokens": 476259859.0, "step": 79810 }, { "epoch": 0.8515144079459742, "grad_norm": 0.893007465430787, "learning_rate": 7.658853425424826e-06, "loss": 0.3275, "num_tokens": 476280769.0, "step": 79815 }, { "epoch": 0.8515677509521726, "grad_norm": 1.0987725718129264, "learning_rate": 7.656982043939792e-06, "loss": 0.4925, "num_tokens": 476299317.0, "step": 79820 }, { "epoch": 0.8516210939583712, "grad_norm": 0.9779400929872041, "learning_rate": 7.655111279928723e-06, "loss": 0.4242, "num_tokens": 476321844.0, "step": 79825 }, { "epoch": 0.8516744369645696, "grad_norm": 5.976996610832196, "learning_rate": 7.65324113344983e-06, "loss": 0.6584, "num_tokens": 476350160.0, "step": 79830 }, { "epoch": 0.851727779970768, "grad_norm": 1.2533121210529827, "learning_rate": 7.651371604561308e-06, "loss": 0.5123, "num_tokens": 476371497.0, "step": 79835 }, { "epoch": 0.8517811229769665, "grad_norm": 0.7740753581892991, "learning_rate": 7.649502693321325e-06, "loss": 0.4085, "num_tokens": 476402337.0, "step": 79840 }, { "epoch": 0.8518344659831649, "grad_norm": 0.6636090666480088, "learning_rate": 7.647634399788051e-06, "loss": 0.3759, "num_tokens": 476432602.0, "step": 79845 }, { "epoch": 0.8518878089893634, "grad_norm": 0.8210086249297213, "learning_rate": 7.64576672401961e-06, "loss": 0.3906, "num_tokens": 476459920.0, "step": 79850 }, { "epoch": 0.8519411519955619, "grad_norm": 1.2501739612146612, "learning_rate": 7.643899666074128e-06, "loss": 0.4799, "num_tokens": 476500341.0, "step": 79855 }, { "epoch": 0.8519944950017603, "grad_norm": 1.3418393911378697, "learning_rate": 7.642033226009706e-06, "loss": 0.4873, "num_tokens": 476531016.0, "step": 79860 }, { "epoch": 0.8520478380079588, "grad_norm": 1.3510901979647394, "learning_rate": 7.640167403884416e-06, "loss": 0.4523, "num_tokens": 476547570.0, "step": 79865 }, { "epoch": 0.8521011810141572, "grad_norm": 1.9397843622770867, "learning_rate": 7.63830219975633e-06, "loss": 0.5342, "num_tokens": 476581265.0, "step": 79870 }, { "epoch": 0.8521545240203557, "grad_norm": 0.6501332202298354, "learning_rate": 7.636437613683481e-06, "loss": 0.4301, "num_tokens": 476632307.0, "step": 79875 }, { "epoch": 0.8522078670265542, "grad_norm": 0.7830715793301902, "learning_rate": 7.63457364572389e-06, "loss": 0.5285, "num_tokens": 476676658.0, "step": 79880 }, { "epoch": 0.8522612100327526, "grad_norm": 1.8667892933669106, "learning_rate": 7.632710295935558e-06, "loss": 0.4807, "num_tokens": 476706228.0, "step": 79885 }, { "epoch": 0.8523145530389511, "grad_norm": 0.8117288300918155, "learning_rate": 7.630847564376479e-06, "loss": 0.4568, "num_tokens": 476727911.0, "step": 79890 }, { "epoch": 0.8523678960451495, "grad_norm": 0.9017493523707144, "learning_rate": 7.6289854511046086e-06, "loss": 0.542, "num_tokens": 476755504.0, "step": 79895 }, { "epoch": 0.8524212390513479, "grad_norm": 0.8414136772838361, "learning_rate": 7.627123956177893e-06, "loss": 0.4198, "num_tokens": 476792896.0, "step": 79900 }, { "epoch": 0.8524745820575464, "grad_norm": 0.9261251211813972, "learning_rate": 7.625263079654265e-06, "loss": 0.4241, "num_tokens": 476824175.0, "step": 79905 }, { "epoch": 0.8525279250637449, "grad_norm": 1.0883393405709014, "learning_rate": 7.6234028215916285e-06, "loss": 0.5123, "num_tokens": 476846780.0, "step": 79910 }, { "epoch": 0.8525812680699434, "grad_norm": 0.68991897019348, "learning_rate": 7.621543182047861e-06, "loss": 0.5323, "num_tokens": 476884750.0, "step": 79915 }, { "epoch": 0.8526346110761418, "grad_norm": 0.9418715041681311, "learning_rate": 7.619684161080842e-06, "loss": 0.5267, "num_tokens": 476914257.0, "step": 79920 }, { "epoch": 0.8526879540823402, "grad_norm": 1.0140994281971822, "learning_rate": 7.617825758748416e-06, "loss": 0.4853, "num_tokens": 476944979.0, "step": 79925 }, { "epoch": 0.8527412970885387, "grad_norm": 0.6628150698604744, "learning_rate": 7.615967975108409e-06, "loss": 0.5003, "num_tokens": 476991863.0, "step": 79930 }, { "epoch": 0.8527946400947372, "grad_norm": 0.8518396465009836, "learning_rate": 7.614110810218643e-06, "loss": 0.5985, "num_tokens": 477024972.0, "step": 79935 }, { "epoch": 0.8528479831009357, "grad_norm": 1.1841549152641584, "learning_rate": 7.612254264136897e-06, "loss": 0.4769, "num_tokens": 477052913.0, "step": 79940 }, { "epoch": 0.8529013261071341, "grad_norm": 0.6783855419897098, "learning_rate": 7.610398336920952e-06, "loss": 0.4899, "num_tokens": 477087141.0, "step": 79945 }, { "epoch": 0.8529546691133325, "grad_norm": 1.594138982826877, "learning_rate": 7.608543028628553e-06, "loss": 0.5081, "num_tokens": 477113792.0, "step": 79950 }, { "epoch": 0.853008012119531, "grad_norm": 0.7929665416735591, "learning_rate": 7.606688339317437e-06, "loss": 0.4303, "num_tokens": 477152866.0, "step": 79955 }, { "epoch": 0.8530613551257294, "grad_norm": 1.2080018133900385, "learning_rate": 7.604834269045316e-06, "loss": 0.5577, "num_tokens": 477185941.0, "step": 79960 }, { "epoch": 0.853114698131928, "grad_norm": 0.8572425051941622, "learning_rate": 7.602980817869889e-06, "loss": 0.488, "num_tokens": 477201231.0, "step": 79965 }, { "epoch": 0.8531680411381264, "grad_norm": 0.9720690055864343, "learning_rate": 7.601127985848829e-06, "loss": 0.335, "num_tokens": 477223613.0, "step": 79970 }, { "epoch": 0.8532213841443248, "grad_norm": 0.5608206886492746, "learning_rate": 7.599275773039795e-06, "loss": 0.3188, "num_tokens": 477237522.0, "step": 79975 }, { "epoch": 0.8532747271505233, "grad_norm": 0.9553512186787215, "learning_rate": 7.597424179500418e-06, "loss": 0.4856, "num_tokens": 477259639.0, "step": 79980 }, { "epoch": 0.8533280701567217, "grad_norm": 0.7988786220385069, "learning_rate": 7.595573205288321e-06, "loss": 0.493, "num_tokens": 477301081.0, "step": 79985 }, { "epoch": 0.8533814131629202, "grad_norm": 0.8638899957637434, "learning_rate": 7.593722850461099e-06, "loss": 0.5172, "num_tokens": 477339963.0, "step": 79990 }, { "epoch": 0.8534347561691187, "grad_norm": 0.9783910094116338, "learning_rate": 7.591873115076336e-06, "loss": 0.4051, "num_tokens": 477370766.0, "step": 79995 }, { "epoch": 0.8534880991753171, "grad_norm": 0.9450283066706573, "learning_rate": 7.590023999191588e-06, "loss": 0.3705, "num_tokens": 477401353.0, "step": 80000 }, { "epoch": 0.8535414421815156, "grad_norm": 0.744850890340499, "learning_rate": 7.5881755028643945e-06, "loss": 0.4162, "num_tokens": 477438176.0, "step": 80005 }, { "epoch": 0.853594785187714, "grad_norm": 0.8478107524844543, "learning_rate": 7.586327626152284e-06, "loss": 0.5515, "num_tokens": 477472946.0, "step": 80010 }, { "epoch": 0.8536481281939124, "grad_norm": 0.8123316978914232, "learning_rate": 7.584480369112755e-06, "loss": 0.4644, "num_tokens": 477492076.0, "step": 80015 }, { "epoch": 0.853701471200111, "grad_norm": 0.8400723344977015, "learning_rate": 7.582633731803285e-06, "loss": 0.5498, "num_tokens": 477524155.0, "step": 80020 }, { "epoch": 0.8537548142063094, "grad_norm": 0.626828746903069, "learning_rate": 7.580787714281344e-06, "loss": 0.4427, "num_tokens": 477563293.0, "step": 80025 }, { "epoch": 0.8538081572125079, "grad_norm": 0.7223809218447079, "learning_rate": 7.578942316604371e-06, "loss": 0.5126, "num_tokens": 477590341.0, "step": 80030 }, { "epoch": 0.8538615002187063, "grad_norm": 1.0968305351721008, "learning_rate": 7.577097538829794e-06, "loss": 0.4709, "num_tokens": 477615873.0, "step": 80035 }, { "epoch": 0.8539148432249047, "grad_norm": 0.6788845419543112, "learning_rate": 7.575253381015024e-06, "loss": 0.6258, "num_tokens": 477654619.0, "step": 80040 }, { "epoch": 0.8539681862311033, "grad_norm": 1.1761201116678368, "learning_rate": 7.573409843217437e-06, "loss": 0.4878, "num_tokens": 477669146.0, "step": 80045 }, { "epoch": 0.8540215292373017, "grad_norm": 0.7653477535288391, "learning_rate": 7.57156692549441e-06, "loss": 0.4008, "num_tokens": 477703053.0, "step": 80050 }, { "epoch": 0.8540748722435002, "grad_norm": 0.9655844882469119, "learning_rate": 7.5697246279032855e-06, "loss": 0.3803, "num_tokens": 477727864.0, "step": 80055 }, { "epoch": 0.8541282152496986, "grad_norm": 0.8554331275721259, "learning_rate": 7.567882950501387e-06, "loss": 0.6454, "num_tokens": 477753684.0, "step": 80060 }, { "epoch": 0.854181558255897, "grad_norm": 7.447992205668811, "learning_rate": 7.566041893346032e-06, "loss": 0.4849, "num_tokens": 477786420.0, "step": 80065 }, { "epoch": 0.8542349012620956, "grad_norm": 1.0372500864123917, "learning_rate": 7.56420145649451e-06, "loss": 0.403, "num_tokens": 477826555.0, "step": 80070 }, { "epoch": 0.854288244268294, "grad_norm": 0.9639290874575979, "learning_rate": 7.562361640004087e-06, "loss": 0.5782, "num_tokens": 477844305.0, "step": 80075 }, { "epoch": 0.8543415872744924, "grad_norm": 1.4333664117405078, "learning_rate": 7.560522443932014e-06, "loss": 0.4698, "num_tokens": 477871812.0, "step": 80080 }, { "epoch": 0.8543949302806909, "grad_norm": 0.781119899320275, "learning_rate": 7.558683868335532e-06, "loss": 0.4969, "num_tokens": 477904610.0, "step": 80085 }, { "epoch": 0.8544482732868893, "grad_norm": 0.9083282745511797, "learning_rate": 7.556845913271849e-06, "loss": 0.4272, "num_tokens": 477938353.0, "step": 80090 }, { "epoch": 0.8545016162930879, "grad_norm": 0.7646542782730401, "learning_rate": 7.555008578798149e-06, "loss": 0.4925, "num_tokens": 477965738.0, "step": 80095 }, { "epoch": 0.8545549592992863, "grad_norm": 0.5934509225701995, "learning_rate": 7.553171864971618e-06, "loss": 0.4022, "num_tokens": 477996142.0, "step": 80100 }, { "epoch": 0.8546083023054847, "grad_norm": 0.7863492303606239, "learning_rate": 7.551335771849407e-06, "loss": 0.4312, "num_tokens": 478021610.0, "step": 80105 }, { "epoch": 0.8546616453116832, "grad_norm": 1.8845934162495925, "learning_rate": 7.549500299488646e-06, "loss": 0.5019, "num_tokens": 478054355.0, "step": 80110 }, { "epoch": 0.8547149883178816, "grad_norm": 1.3294312063446503, "learning_rate": 7.547665447946464e-06, "loss": 0.5253, "num_tokens": 478075826.0, "step": 80115 }, { "epoch": 0.8547683313240801, "grad_norm": 4.3495578251891, "learning_rate": 7.545831217279943e-06, "loss": 0.5112, "num_tokens": 478106794.0, "step": 80120 }, { "epoch": 0.8548216743302786, "grad_norm": 0.8865756331138661, "learning_rate": 7.543997607546173e-06, "loss": 0.5138, "num_tokens": 478145101.0, "step": 80125 }, { "epoch": 0.854875017336477, "grad_norm": 2.5369579512257863, "learning_rate": 7.542164618802207e-06, "loss": 0.4802, "num_tokens": 478163239.0, "step": 80130 }, { "epoch": 0.8549283603426755, "grad_norm": 0.5896932269134326, "learning_rate": 7.5403322511050785e-06, "loss": 0.5414, "num_tokens": 478199960.0, "step": 80135 }, { "epoch": 0.8549817033488739, "grad_norm": 1.4576920514818907, "learning_rate": 7.538500504511811e-06, "loss": 0.4901, "num_tokens": 478234844.0, "step": 80140 }, { "epoch": 0.8550350463550724, "grad_norm": 1.0945606021393597, "learning_rate": 7.536669379079414e-06, "loss": 0.3948, "num_tokens": 478257408.0, "step": 80145 }, { "epoch": 0.8550883893612709, "grad_norm": 0.6095719411155986, "learning_rate": 7.5348388748648524e-06, "loss": 0.4242, "num_tokens": 478295151.0, "step": 80150 }, { "epoch": 0.8551417323674693, "grad_norm": 0.972299027071687, "learning_rate": 7.5330089919250945e-06, "loss": 0.3959, "num_tokens": 478330411.0, "step": 80155 }, { "epoch": 0.8551950753736678, "grad_norm": 0.7081330460991148, "learning_rate": 7.531179730317089e-06, "loss": 0.5205, "num_tokens": 478362887.0, "step": 80160 }, { "epoch": 0.8552484183798662, "grad_norm": 0.77215432323248, "learning_rate": 7.529351090097754e-06, "loss": 0.3863, "num_tokens": 478397898.0, "step": 80165 }, { "epoch": 0.8553017613860646, "grad_norm": 0.8847392355780727, "learning_rate": 7.527523071323988e-06, "loss": 0.4667, "num_tokens": 478435283.0, "step": 80170 }, { "epoch": 0.8553551043922631, "grad_norm": 0.8739537120979002, "learning_rate": 7.525695674052682e-06, "loss": 0.4156, "num_tokens": 478471539.0, "step": 80175 }, { "epoch": 0.8554084473984616, "grad_norm": 1.477189927078133, "learning_rate": 7.523868898340696e-06, "loss": 0.3641, "num_tokens": 478498840.0, "step": 80180 }, { "epoch": 0.8554617904046601, "grad_norm": 0.8807845406569512, "learning_rate": 7.5220427442448766e-06, "loss": 0.4057, "num_tokens": 478530877.0, "step": 80185 }, { "epoch": 0.8555151334108585, "grad_norm": 1.03107180668784, "learning_rate": 7.520217211822058e-06, "loss": 0.484, "num_tokens": 478559991.0, "step": 80190 }, { "epoch": 0.8555684764170569, "grad_norm": 1.350244946553514, "learning_rate": 7.518392301129032e-06, "loss": 0.5952, "num_tokens": 478588812.0, "step": 80195 }, { "epoch": 0.8556218194232554, "grad_norm": 0.9856147264487497, "learning_rate": 7.516568012222599e-06, "loss": 0.3905, "num_tokens": 478611936.0, "step": 80200 }, { "epoch": 0.8556751624294539, "grad_norm": 1.390068082992999, "learning_rate": 7.514744345159523e-06, "loss": 0.6134, "num_tokens": 478647789.0, "step": 80205 }, { "epoch": 0.8557285054356524, "grad_norm": 0.6899010298416711, "learning_rate": 7.512921299996548e-06, "loss": 0.3045, "num_tokens": 478674956.0, "step": 80210 }, { "epoch": 0.8557818484418508, "grad_norm": 0.8863213492713455, "learning_rate": 7.511098876790407e-06, "loss": 0.3504, "num_tokens": 478699106.0, "step": 80215 }, { "epoch": 0.8558351914480492, "grad_norm": 1.3340444504809075, "learning_rate": 7.509277075597817e-06, "loss": 0.4363, "num_tokens": 478724947.0, "step": 80220 }, { "epoch": 0.8558885344542477, "grad_norm": 1.0807601809843896, "learning_rate": 7.5074558964754555e-06, "loss": 0.3937, "num_tokens": 478752248.0, "step": 80225 }, { "epoch": 0.8559418774604461, "grad_norm": 1.5758206080419923, "learning_rate": 7.505635339480001e-06, "loss": 0.5524, "num_tokens": 478781850.0, "step": 80230 }, { "epoch": 0.8559952204666447, "grad_norm": 0.8168327686785462, "learning_rate": 7.50381540466811e-06, "loss": 0.4694, "num_tokens": 478809890.0, "step": 80235 }, { "epoch": 0.8560485634728431, "grad_norm": 1.1093303472555032, "learning_rate": 7.5019960920964094e-06, "loss": 0.4692, "num_tokens": 478845216.0, "step": 80240 }, { "epoch": 0.8561019064790415, "grad_norm": 1.0483614901153828, "learning_rate": 7.50017740182151e-06, "loss": 0.4113, "num_tokens": 478874445.0, "step": 80245 }, { "epoch": 0.85615524948524, "grad_norm": 1.0891692791155076, "learning_rate": 7.498359333900014e-06, "loss": 0.4609, "num_tokens": 478909518.0, "step": 80250 }, { "epoch": 0.8562085924914384, "grad_norm": 0.669316133803812, "learning_rate": 7.496541888388484e-06, "loss": 0.3919, "num_tokens": 478947961.0, "step": 80255 }, { "epoch": 0.8562619354976369, "grad_norm": 1.2417021683230614, "learning_rate": 7.494725065343486e-06, "loss": 0.5117, "num_tokens": 478970118.0, "step": 80260 }, { "epoch": 0.8563152785038354, "grad_norm": 0.9457496530681133, "learning_rate": 7.492908864821555e-06, "loss": 0.3956, "num_tokens": 478996256.0, "step": 80265 }, { "epoch": 0.8563686215100338, "grad_norm": 0.9032051472434284, "learning_rate": 7.491093286879197e-06, "loss": 0.4773, "num_tokens": 479021467.0, "step": 80270 }, { "epoch": 0.8564219645162323, "grad_norm": 1.1228572532517829, "learning_rate": 7.4892783315729245e-06, "loss": 0.5569, "num_tokens": 479056980.0, "step": 80275 }, { "epoch": 0.8564753075224307, "grad_norm": 0.8211814224123711, "learning_rate": 7.487463998959207e-06, "loss": 0.5072, "num_tokens": 479097289.0, "step": 80280 }, { "epoch": 0.8565286505286291, "grad_norm": 0.6388379313343481, "learning_rate": 7.4856502890944964e-06, "loss": 0.4862, "num_tokens": 479134288.0, "step": 80285 }, { "epoch": 0.8565819935348277, "grad_norm": 0.7987566626889911, "learning_rate": 7.483837202035238e-06, "loss": 0.4135, "num_tokens": 479162943.0, "step": 80290 }, { "epoch": 0.8566353365410261, "grad_norm": 0.5242251242799946, "learning_rate": 7.482024737837852e-06, "loss": 0.4023, "num_tokens": 479192322.0, "step": 80295 }, { "epoch": 0.8566886795472246, "grad_norm": 1.1723779088016526, "learning_rate": 7.480212896558743e-06, "loss": 0.579, "num_tokens": 479228095.0, "step": 80300 }, { "epoch": 0.856742022553423, "grad_norm": 0.7636130724824374, "learning_rate": 7.4784016782542875e-06, "loss": 0.4292, "num_tokens": 479264980.0, "step": 80305 }, { "epoch": 0.8567953655596214, "grad_norm": 0.8176879129025301, "learning_rate": 7.4765910829808415e-06, "loss": 0.5445, "num_tokens": 479303922.0, "step": 80310 }, { "epoch": 0.85684870856582, "grad_norm": 1.176918005432411, "learning_rate": 7.474781110794754e-06, "loss": 0.5064, "num_tokens": 479335608.0, "step": 80315 }, { "epoch": 0.8569020515720184, "grad_norm": 0.8063586266494696, "learning_rate": 7.4729717617523455e-06, "loss": 0.4284, "num_tokens": 479371988.0, "step": 80320 }, { "epoch": 0.8569553945782169, "grad_norm": 0.6397391896698943, "learning_rate": 7.4711630359099145e-06, "loss": 0.4846, "num_tokens": 479422638.0, "step": 80325 }, { "epoch": 0.8570087375844153, "grad_norm": 0.6715071941086111, "learning_rate": 7.469354933323755e-06, "loss": 0.5103, "num_tokens": 479458126.0, "step": 80330 }, { "epoch": 0.8570620805906137, "grad_norm": 0.9631747242205696, "learning_rate": 7.467547454050124e-06, "loss": 0.488, "num_tokens": 479506511.0, "step": 80335 }, { "epoch": 0.8571154235968123, "grad_norm": 1.0748028591063297, "learning_rate": 7.46574059814527e-06, "loss": 0.4372, "num_tokens": 479537576.0, "step": 80340 }, { "epoch": 0.8571687666030107, "grad_norm": 1.199298854955495, "learning_rate": 7.463934365665419e-06, "loss": 0.5167, "num_tokens": 479584284.0, "step": 80345 }, { "epoch": 0.8572221096092091, "grad_norm": 0.7423101655318967, "learning_rate": 7.462128756666768e-06, "loss": 0.5719, "num_tokens": 479625127.0, "step": 80350 }, { "epoch": 0.8572754526154076, "grad_norm": 0.7227158233735836, "learning_rate": 7.4603237712055125e-06, "loss": 0.5149, "num_tokens": 479652007.0, "step": 80355 }, { "epoch": 0.857328795621606, "grad_norm": 1.1890269150363502, "learning_rate": 7.458519409337825e-06, "loss": 0.4184, "num_tokens": 479675398.0, "step": 80360 }, { "epoch": 0.8573821386278045, "grad_norm": 0.8623160368477581, "learning_rate": 7.456715671119841e-06, "loss": 0.5446, "num_tokens": 479715236.0, "step": 80365 }, { "epoch": 0.857435481634003, "grad_norm": 0.5786703788979459, "learning_rate": 7.454912556607694e-06, "loss": 0.4195, "num_tokens": 479751944.0, "step": 80370 }, { "epoch": 0.8574888246402014, "grad_norm": 1.023388682532226, "learning_rate": 7.453110065857502e-06, "loss": 0.4261, "num_tokens": 479769964.0, "step": 80375 }, { "epoch": 0.8575421676463999, "grad_norm": 0.5853163002797492, "learning_rate": 7.451308198925344e-06, "loss": 0.4619, "num_tokens": 479806633.0, "step": 80380 }, { "epoch": 0.8575955106525983, "grad_norm": 0.7725909835961862, "learning_rate": 7.44950695586729e-06, "loss": 0.4432, "num_tokens": 479833012.0, "step": 80385 }, { "epoch": 0.8576488536587968, "grad_norm": 0.7216820345343454, "learning_rate": 7.447706336739399e-06, "loss": 0.527, "num_tokens": 479870867.0, "step": 80390 }, { "epoch": 0.8577021966649953, "grad_norm": 0.7416929727997272, "learning_rate": 7.445906341597697e-06, "loss": 0.4549, "num_tokens": 479895928.0, "step": 80395 }, { "epoch": 0.8577555396711937, "grad_norm": 1.9419856578122734, "learning_rate": 7.4441069704981935e-06, "loss": 0.6062, "num_tokens": 479928118.0, "step": 80400 }, { "epoch": 0.8578088826773922, "grad_norm": 0.5818038092509138, "learning_rate": 7.442308223496892e-06, "loss": 0.3729, "num_tokens": 479947873.0, "step": 80405 }, { "epoch": 0.8578622256835906, "grad_norm": 0.728058220405028, "learning_rate": 7.440510100649753e-06, "loss": 0.5174, "num_tokens": 479996486.0, "step": 80410 }, { "epoch": 0.8579155686897891, "grad_norm": 0.7768618722952452, "learning_rate": 7.4387126020127404e-06, "loss": 0.3708, "num_tokens": 480026660.0, "step": 80415 }, { "epoch": 0.8579689116959875, "grad_norm": 0.8706751102473268, "learning_rate": 7.436915727641787e-06, "loss": 0.5144, "num_tokens": 480067120.0, "step": 80420 }, { "epoch": 0.858022254702186, "grad_norm": 1.00679864249401, "learning_rate": 7.435119477592797e-06, "loss": 0.4918, "num_tokens": 480096119.0, "step": 80425 }, { "epoch": 0.8580755977083845, "grad_norm": 1.3144003995689912, "learning_rate": 7.4333238519216784e-06, "loss": 0.4338, "num_tokens": 480114966.0, "step": 80430 }, { "epoch": 0.8581289407145829, "grad_norm": 0.7661746175275523, "learning_rate": 7.431528850684305e-06, "loss": 0.4287, "num_tokens": 480143286.0, "step": 80435 }, { "epoch": 0.8581822837207813, "grad_norm": 1.2611130391512784, "learning_rate": 7.429734473936528e-06, "loss": 0.495, "num_tokens": 480178455.0, "step": 80440 }, { "epoch": 0.8582356267269798, "grad_norm": 0.6675512544132257, "learning_rate": 7.4279407217341915e-06, "loss": 0.3877, "num_tokens": 480209067.0, "step": 80445 }, { "epoch": 0.8582889697331783, "grad_norm": 0.6880445661159676, "learning_rate": 7.4261475941331125e-06, "loss": 0.4218, "num_tokens": 480236639.0, "step": 80450 }, { "epoch": 0.8583423127393768, "grad_norm": 1.2549475782537072, "learning_rate": 7.424355091189086e-06, "loss": 0.451, "num_tokens": 480281177.0, "step": 80455 }, { "epoch": 0.8583956557455752, "grad_norm": 0.949826651463109, "learning_rate": 7.422563212957889e-06, "loss": 0.4043, "num_tokens": 480303828.0, "step": 80460 }, { "epoch": 0.8584489987517736, "grad_norm": 1.393942084230315, "learning_rate": 7.420771959495291e-06, "loss": 0.4947, "num_tokens": 480325044.0, "step": 80465 }, { "epoch": 0.8585023417579721, "grad_norm": 1.6558061821782049, "learning_rate": 7.418981330857022e-06, "loss": 0.5137, "num_tokens": 480338430.0, "step": 80470 }, { "epoch": 0.8585556847641705, "grad_norm": 0.6502221591421256, "learning_rate": 7.417191327098805e-06, "loss": 0.393, "num_tokens": 480370211.0, "step": 80475 }, { "epoch": 0.8586090277703691, "grad_norm": 0.7421442459132667, "learning_rate": 7.4154019482763446e-06, "loss": 0.5872, "num_tokens": 480400930.0, "step": 80480 }, { "epoch": 0.8586623707765675, "grad_norm": 0.7048087405786192, "learning_rate": 7.41361319444532e-06, "loss": 0.4699, "num_tokens": 480429601.0, "step": 80485 }, { "epoch": 0.8587157137827659, "grad_norm": 0.6064999844872759, "learning_rate": 7.411825065661396e-06, "loss": 0.5846, "num_tokens": 480479150.0, "step": 80490 }, { "epoch": 0.8587690567889644, "grad_norm": 0.72601861185799, "learning_rate": 7.410037561980212e-06, "loss": 0.4811, "num_tokens": 480503632.0, "step": 80495 }, { "epoch": 0.8588223997951628, "grad_norm": 1.0817109898852404, "learning_rate": 7.408250683457393e-06, "loss": 0.4344, "num_tokens": 480526441.0, "step": 80500 }, { "epoch": 0.8588757428013614, "grad_norm": 0.7940395414956967, "learning_rate": 7.406464430148539e-06, "loss": 0.5139, "num_tokens": 480557493.0, "step": 80505 }, { "epoch": 0.8589290858075598, "grad_norm": 1.852576075901662, "learning_rate": 7.4046788021092465e-06, "loss": 0.5301, "num_tokens": 480595656.0, "step": 80510 }, { "epoch": 0.8589824288137582, "grad_norm": 1.1886783445315658, "learning_rate": 7.402893799395068e-06, "loss": 0.4324, "num_tokens": 480623421.0, "step": 80515 }, { "epoch": 0.8590357718199567, "grad_norm": 0.9721908601962546, "learning_rate": 7.401109422061551e-06, "loss": 0.5142, "num_tokens": 480647698.0, "step": 80520 }, { "epoch": 0.8590891148261551, "grad_norm": 0.9539481850042231, "learning_rate": 7.399325670164231e-06, "loss": 0.5145, "num_tokens": 480678805.0, "step": 80525 }, { "epoch": 0.8591424578323535, "grad_norm": 0.8521643892999661, "learning_rate": 7.3975425437586075e-06, "loss": 0.4532, "num_tokens": 480711098.0, "step": 80530 }, { "epoch": 0.8591958008385521, "grad_norm": 0.8012086016866666, "learning_rate": 7.395760042900166e-06, "loss": 0.3723, "num_tokens": 480737592.0, "step": 80535 }, { "epoch": 0.8592491438447505, "grad_norm": 0.95975250702325, "learning_rate": 7.3939781676443786e-06, "loss": 0.4048, "num_tokens": 480765307.0, "step": 80540 }, { "epoch": 0.859302486850949, "grad_norm": 1.0781428107629378, "learning_rate": 7.3921969180466895e-06, "loss": 0.5264, "num_tokens": 480790756.0, "step": 80545 }, { "epoch": 0.8593558298571474, "grad_norm": 0.727587868253325, "learning_rate": 7.3904162941625274e-06, "loss": 0.5646, "num_tokens": 480822862.0, "step": 80550 }, { "epoch": 0.8594091728633458, "grad_norm": 1.0874280383204635, "learning_rate": 7.388636296047309e-06, "loss": 0.4033, "num_tokens": 480851070.0, "step": 80555 }, { "epoch": 0.8594625158695444, "grad_norm": 1.3138160504190772, "learning_rate": 7.386856923756416e-06, "loss": 0.5472, "num_tokens": 480884121.0, "step": 80560 }, { "epoch": 0.8595158588757428, "grad_norm": 1.5750010755156434, "learning_rate": 7.385078177345226e-06, "loss": 0.4316, "num_tokens": 480917386.0, "step": 80565 }, { "epoch": 0.8595692018819413, "grad_norm": 0.8757515277895423, "learning_rate": 7.383300056869086e-06, "loss": 0.4679, "num_tokens": 480950631.0, "step": 80570 }, { "epoch": 0.8596225448881397, "grad_norm": 1.1586286194640034, "learning_rate": 7.381522562383322e-06, "loss": 0.5007, "num_tokens": 480968238.0, "step": 80575 }, { "epoch": 0.8596758878943381, "grad_norm": 0.8204598852254429, "learning_rate": 7.379745693943249e-06, "loss": 0.5149, "num_tokens": 481012348.0, "step": 80580 }, { "epoch": 0.8597292309005367, "grad_norm": 0.8157086559238071, "learning_rate": 7.377969451604172e-06, "loss": 0.3495, "num_tokens": 481028853.0, "step": 80585 }, { "epoch": 0.8597825739067351, "grad_norm": 0.8000473798824929, "learning_rate": 7.376193835421345e-06, "loss": 0.4744, "num_tokens": 481055993.0, "step": 80590 }, { "epoch": 0.8598359169129336, "grad_norm": 0.9233950393862602, "learning_rate": 7.374418845450036e-06, "loss": 0.4309, "num_tokens": 481074327.0, "step": 80595 }, { "epoch": 0.859889259919132, "grad_norm": 1.0874917028554612, "learning_rate": 7.372644481745473e-06, "loss": 0.397, "num_tokens": 481104752.0, "step": 80600 }, { "epoch": 0.8599426029253304, "grad_norm": 0.7089504915465044, "learning_rate": 7.370870744362868e-06, "loss": 0.5132, "num_tokens": 481138294.0, "step": 80605 }, { "epoch": 0.859995945931529, "grad_norm": 1.1590843586847346, "learning_rate": 7.369097633357416e-06, "loss": 0.5015, "num_tokens": 481168974.0, "step": 80610 }, { "epoch": 0.8600492889377274, "grad_norm": 1.316303742807988, "learning_rate": 7.367325148784304e-06, "loss": 0.4276, "num_tokens": 481191059.0, "step": 80615 }, { "epoch": 0.8601026319439258, "grad_norm": 1.1333556922654098, "learning_rate": 7.365553290698671e-06, "loss": 0.6002, "num_tokens": 481216409.0, "step": 80620 }, { "epoch": 0.8601559749501243, "grad_norm": 1.31593849959643, "learning_rate": 7.363782059155666e-06, "loss": 0.3702, "num_tokens": 481250577.0, "step": 80625 }, { "epoch": 0.8602093179563227, "grad_norm": 1.0646735991586784, "learning_rate": 7.362011454210405e-06, "loss": 0.4259, "num_tokens": 481268848.0, "step": 80630 }, { "epoch": 0.8602626609625212, "grad_norm": 2.4970662415146894, "learning_rate": 7.360241475917982e-06, "loss": 0.4578, "num_tokens": 481299235.0, "step": 80635 }, { "epoch": 0.8603160039687197, "grad_norm": 1.1399648302497143, "learning_rate": 7.3584721243334735e-06, "loss": 0.5801, "num_tokens": 481348892.0, "step": 80640 }, { "epoch": 0.8603693469749181, "grad_norm": 2.3872123854699367, "learning_rate": 7.356703399511944e-06, "loss": 0.5265, "num_tokens": 481376122.0, "step": 80645 }, { "epoch": 0.8604226899811166, "grad_norm": 0.7846867828694118, "learning_rate": 7.354935301508427e-06, "loss": 0.4744, "num_tokens": 481401989.0, "step": 80650 }, { "epoch": 0.860476032987315, "grad_norm": 1.2860693009553414, "learning_rate": 7.353167830377941e-06, "loss": 0.5231, "num_tokens": 481435318.0, "step": 80655 }, { "epoch": 0.8605293759935135, "grad_norm": 1.2792634782580163, "learning_rate": 7.351400986175497e-06, "loss": 0.5085, "num_tokens": 481467101.0, "step": 80660 }, { "epoch": 0.860582718999712, "grad_norm": 0.9746568601197965, "learning_rate": 7.3496347689560595e-06, "loss": 0.4105, "num_tokens": 481512142.0, "step": 80665 }, { "epoch": 0.8606360620059104, "grad_norm": 0.6320301045081393, "learning_rate": 7.347869178774605e-06, "loss": 0.506, "num_tokens": 481544515.0, "step": 80670 }, { "epoch": 0.8606894050121089, "grad_norm": 0.5856127410187276, "learning_rate": 7.346104215686068e-06, "loss": 0.4156, "num_tokens": 481580358.0, "step": 80675 }, { "epoch": 0.8607427480183073, "grad_norm": 0.8982062593152876, "learning_rate": 7.344339879745364e-06, "loss": 0.4224, "num_tokens": 481604575.0, "step": 80680 }, { "epoch": 0.8607960910245058, "grad_norm": 0.8826712291542893, "learning_rate": 7.342576171007406e-06, "loss": 0.4079, "num_tokens": 481631650.0, "step": 80685 }, { "epoch": 0.8608494340307042, "grad_norm": 1.728187627955598, "learning_rate": 7.340813089527075e-06, "loss": 0.3495, "num_tokens": 481666260.0, "step": 80690 }, { "epoch": 0.8609027770369027, "grad_norm": 1.266690670828478, "learning_rate": 7.339050635359226e-06, "loss": 0.4657, "num_tokens": 481700412.0, "step": 80695 }, { "epoch": 0.8609561200431012, "grad_norm": 1.018445473062665, "learning_rate": 7.337288808558713e-06, "loss": 0.3413, "num_tokens": 481719284.0, "step": 80700 }, { "epoch": 0.8610094630492996, "grad_norm": 4.738964171678717, "learning_rate": 7.33552760918036e-06, "loss": 0.4816, "num_tokens": 481759164.0, "step": 80705 }, { "epoch": 0.861062806055498, "grad_norm": 1.014884714973797, "learning_rate": 7.33376703727897e-06, "loss": 0.494, "num_tokens": 481791168.0, "step": 80710 }, { "epoch": 0.8611161490616965, "grad_norm": 0.6128606755214812, "learning_rate": 7.332007092909321e-06, "loss": 0.4481, "num_tokens": 481819550.0, "step": 80715 }, { "epoch": 0.861169492067895, "grad_norm": 1.3316470527253257, "learning_rate": 7.3302477761261895e-06, "loss": 0.3381, "num_tokens": 481849879.0, "step": 80720 }, { "epoch": 0.8612228350740935, "grad_norm": 1.0588911772573018, "learning_rate": 7.328489086984314e-06, "loss": 0.417, "num_tokens": 481881611.0, "step": 80725 }, { "epoch": 0.8612761780802919, "grad_norm": 0.8867906076169499, "learning_rate": 7.326731025538425e-06, "loss": 0.5217, "num_tokens": 481899413.0, "step": 80730 }, { "epoch": 0.8613295210864903, "grad_norm": 1.1700974567215245, "learning_rate": 7.32497359184323e-06, "loss": 0.488, "num_tokens": 481919687.0, "step": 80735 }, { "epoch": 0.8613828640926888, "grad_norm": 1.279000523948823, "learning_rate": 7.323216785953416e-06, "loss": 0.4379, "num_tokens": 481941031.0, "step": 80740 }, { "epoch": 0.8614362070988872, "grad_norm": 0.9221688828409559, "learning_rate": 7.321460607923652e-06, "loss": 0.3957, "num_tokens": 481970002.0, "step": 80745 }, { "epoch": 0.8614895501050858, "grad_norm": 2.567581425717246, "learning_rate": 7.319705057808589e-06, "loss": 0.4027, "num_tokens": 481984933.0, "step": 80750 }, { "epoch": 0.8615428931112842, "grad_norm": 1.1491574915163703, "learning_rate": 7.317950135662849e-06, "loss": 0.4366, "num_tokens": 482011772.0, "step": 80755 }, { "epoch": 0.8615962361174826, "grad_norm": 0.976517422203683, "learning_rate": 7.316195841541045e-06, "loss": 0.4775, "num_tokens": 482031715.0, "step": 80760 }, { "epoch": 0.8616495791236811, "grad_norm": 0.8144931424774292, "learning_rate": 7.314442175497771e-06, "loss": 0.5571, "num_tokens": 482062664.0, "step": 80765 }, { "epoch": 0.8617029221298795, "grad_norm": 2.6040099736278397, "learning_rate": 7.312689137587589e-06, "loss": 0.606, "num_tokens": 482092099.0, "step": 80770 }, { "epoch": 0.8617562651360781, "grad_norm": 1.2941889551613333, "learning_rate": 7.310936727865058e-06, "loss": 0.4017, "num_tokens": 482119773.0, "step": 80775 }, { "epoch": 0.8618096081422765, "grad_norm": 1.4060950750376515, "learning_rate": 7.309184946384709e-06, "loss": 0.4521, "num_tokens": 482140731.0, "step": 80780 }, { "epoch": 0.8618629511484749, "grad_norm": 0.6076807340685458, "learning_rate": 7.3074337932010515e-06, "loss": 0.4273, "num_tokens": 482180358.0, "step": 80785 }, { "epoch": 0.8619162941546734, "grad_norm": 0.5525624030768179, "learning_rate": 7.3056832683685754e-06, "loss": 0.3113, "num_tokens": 482205474.0, "step": 80790 }, { "epoch": 0.8619696371608718, "grad_norm": 1.2496073844146665, "learning_rate": 7.303933371941757e-06, "loss": 0.3932, "num_tokens": 482227975.0, "step": 80795 }, { "epoch": 0.8620229801670702, "grad_norm": 0.7339230545585171, "learning_rate": 7.302184103975046e-06, "loss": 0.5854, "num_tokens": 482254372.0, "step": 80800 }, { "epoch": 0.8620763231732688, "grad_norm": 0.8824919316440019, "learning_rate": 7.300435464522877e-06, "loss": 0.5835, "num_tokens": 482285955.0, "step": 80805 }, { "epoch": 0.8621296661794672, "grad_norm": 0.6460567845741809, "learning_rate": 7.2986874536396685e-06, "loss": 0.5198, "num_tokens": 482321966.0, "step": 80810 }, { "epoch": 0.8621830091856657, "grad_norm": 1.8187268448854461, "learning_rate": 7.296940071379809e-06, "loss": 0.3961, "num_tokens": 482342849.0, "step": 80815 }, { "epoch": 0.8622363521918641, "grad_norm": 1.4797314322683601, "learning_rate": 7.29519331779768e-06, "loss": 0.3966, "num_tokens": 482365897.0, "step": 80820 }, { "epoch": 0.8622896951980625, "grad_norm": 0.7244239405814603, "learning_rate": 7.293447192947635e-06, "loss": 0.4529, "num_tokens": 482385947.0, "step": 80825 }, { "epoch": 0.8623430382042611, "grad_norm": 1.2478377412795323, "learning_rate": 7.291701696884001e-06, "loss": 0.4938, "num_tokens": 482417669.0, "step": 80830 }, { "epoch": 0.8623963812104595, "grad_norm": 0.8508291349385825, "learning_rate": 7.289956829661101e-06, "loss": 0.3716, "num_tokens": 482441385.0, "step": 80835 }, { "epoch": 0.862449724216658, "grad_norm": 0.6450871792844398, "learning_rate": 7.288212591333239e-06, "loss": 0.4131, "num_tokens": 482475352.0, "step": 80840 }, { "epoch": 0.8625030672228564, "grad_norm": 0.8542229224164497, "learning_rate": 7.286468981954678e-06, "loss": 0.3964, "num_tokens": 482508822.0, "step": 80845 }, { "epoch": 0.8625564102290548, "grad_norm": 0.7746294120968235, "learning_rate": 7.284726001579685e-06, "loss": 0.6604, "num_tokens": 482560051.0, "step": 80850 }, { "epoch": 0.8626097532352534, "grad_norm": 1.4127481181252926, "learning_rate": 7.282983650262498e-06, "loss": 0.4337, "num_tokens": 482581969.0, "step": 80855 }, { "epoch": 0.8626630962414518, "grad_norm": 1.0391933937649789, "learning_rate": 7.281241928057331e-06, "loss": 0.4334, "num_tokens": 482601369.0, "step": 80860 }, { "epoch": 0.8627164392476503, "grad_norm": 0.4825622246027092, "learning_rate": 7.279500835018382e-06, "loss": 0.5103, "num_tokens": 482640880.0, "step": 80865 }, { "epoch": 0.8627697822538487, "grad_norm": 0.9329478681330157, "learning_rate": 7.277760371199839e-06, "loss": 0.4652, "num_tokens": 482666541.0, "step": 80870 }, { "epoch": 0.8628231252600471, "grad_norm": 0.7233265322874307, "learning_rate": 7.276020536655849e-06, "loss": 0.5178, "num_tokens": 482695784.0, "step": 80875 }, { "epoch": 0.8628764682662456, "grad_norm": 1.202881284130599, "learning_rate": 7.274281331440561e-06, "loss": 0.4653, "num_tokens": 482716247.0, "step": 80880 }, { "epoch": 0.8629298112724441, "grad_norm": 1.2760886673486083, "learning_rate": 7.272542755608095e-06, "loss": 0.6877, "num_tokens": 482771869.0, "step": 80885 }, { "epoch": 0.8629831542786425, "grad_norm": 0.8036832256434686, "learning_rate": 7.270804809212553e-06, "loss": 0.4354, "num_tokens": 482815598.0, "step": 80890 }, { "epoch": 0.863036497284841, "grad_norm": 0.9160065304976001, "learning_rate": 7.269067492308005e-06, "loss": 0.4052, "num_tokens": 482837691.0, "step": 80895 }, { "epoch": 0.8630898402910394, "grad_norm": 0.6533931204211614, "learning_rate": 7.267330804948529e-06, "loss": 0.4667, "num_tokens": 482891710.0, "step": 80900 }, { "epoch": 0.8631431832972379, "grad_norm": 1.0895116681366386, "learning_rate": 7.265594747188152e-06, "loss": 0.5321, "num_tokens": 482925791.0, "step": 80905 }, { "epoch": 0.8631965263034364, "grad_norm": 1.1024412775400023, "learning_rate": 7.2638593190809056e-06, "loss": 0.4316, "num_tokens": 482946928.0, "step": 80910 }, { "epoch": 0.8632498693096348, "grad_norm": 0.8882759924477575, "learning_rate": 7.2621245206807954e-06, "loss": 0.3783, "num_tokens": 482969981.0, "step": 80915 }, { "epoch": 0.8633032123158333, "grad_norm": 0.6021261721136336, "learning_rate": 7.260390352041796e-06, "loss": 0.431, "num_tokens": 483008242.0, "step": 80920 }, { "epoch": 0.8633565553220317, "grad_norm": 1.060554718250516, "learning_rate": 7.258656813217879e-06, "loss": 0.499, "num_tokens": 483025819.0, "step": 80925 }, { "epoch": 0.8634098983282302, "grad_norm": 1.2949046290532473, "learning_rate": 7.2569239042629845e-06, "loss": 0.3991, "num_tokens": 483042620.0, "step": 80930 }, { "epoch": 0.8634632413344286, "grad_norm": 0.6549740292150441, "learning_rate": 7.255191625231037e-06, "loss": 0.4575, "num_tokens": 483073790.0, "step": 80935 }, { "epoch": 0.8635165843406271, "grad_norm": 0.8634677660492939, "learning_rate": 7.253459976175939e-06, "loss": 0.4595, "num_tokens": 483116050.0, "step": 80940 }, { "epoch": 0.8635699273468256, "grad_norm": 0.6085354161855135, "learning_rate": 7.251728957151582e-06, "loss": 0.4171, "num_tokens": 483149484.0, "step": 80945 }, { "epoch": 0.863623270353024, "grad_norm": 1.278688924539007, "learning_rate": 7.249998568211827e-06, "loss": 0.4543, "num_tokens": 483179014.0, "step": 80950 }, { "epoch": 0.8636766133592225, "grad_norm": 0.9446629936407537, "learning_rate": 7.24826880941052e-06, "loss": 0.4044, "num_tokens": 483197677.0, "step": 80955 }, { "epoch": 0.8637299563654209, "grad_norm": 1.0346019051462396, "learning_rate": 7.2465396808014955e-06, "loss": 0.6018, "num_tokens": 483220037.0, "step": 80960 }, { "epoch": 0.8637832993716194, "grad_norm": 0.7827444206451538, "learning_rate": 7.2448111824385545e-06, "loss": 0.5044, "num_tokens": 483257196.0, "step": 80965 }, { "epoch": 0.8638366423778179, "grad_norm": 0.748638024013392, "learning_rate": 7.243083314375477e-06, "loss": 0.5732, "num_tokens": 483298906.0, "step": 80970 }, { "epoch": 0.8638899853840163, "grad_norm": 0.8116797096266376, "learning_rate": 7.241356076666043e-06, "loss": 0.4934, "num_tokens": 483331231.0, "step": 80975 }, { "epoch": 0.8639433283902147, "grad_norm": 1.0891449646155023, "learning_rate": 7.239629469363994e-06, "loss": 0.4396, "num_tokens": 483351188.0, "step": 80980 }, { "epoch": 0.8639966713964132, "grad_norm": 1.2105223136688814, "learning_rate": 7.237903492523057e-06, "loss": 0.4126, "num_tokens": 483367500.0, "step": 80985 }, { "epoch": 0.8640500144026116, "grad_norm": 1.0996552965100643, "learning_rate": 7.236178146196951e-06, "loss": 0.5879, "num_tokens": 483394376.0, "step": 80990 }, { "epoch": 0.8641033574088102, "grad_norm": 0.9520773480216714, "learning_rate": 7.23445343043935e-06, "loss": 0.4636, "num_tokens": 483424482.0, "step": 80995 }, { "epoch": 0.8641567004150086, "grad_norm": 0.9276834050214791, "learning_rate": 7.2327293453039386e-06, "loss": 0.539, "num_tokens": 483455667.0, "step": 81000 }, { "epoch": 0.864210043421207, "grad_norm": 0.8141539630743846, "learning_rate": 7.231005890844359e-06, "loss": 0.4934, "num_tokens": 483492619.0, "step": 81005 }, { "epoch": 0.8642633864274055, "grad_norm": 2.1072009329019195, "learning_rate": 7.2292830671142385e-06, "loss": 0.4084, "num_tokens": 483512856.0, "step": 81010 }, { "epoch": 0.8643167294336039, "grad_norm": 0.7049635282674507, "learning_rate": 7.22756087416719e-06, "loss": 0.4236, "num_tokens": 483541245.0, "step": 81015 }, { "epoch": 0.8643700724398025, "grad_norm": 1.0077591899668898, "learning_rate": 7.2258393120568145e-06, "loss": 0.427, "num_tokens": 483572191.0, "step": 81020 }, { "epoch": 0.8644234154460009, "grad_norm": 0.9540187356679317, "learning_rate": 7.2241183808366654e-06, "loss": 0.3369, "num_tokens": 483591687.0, "step": 81025 }, { "epoch": 0.8644767584521993, "grad_norm": 1.0451486470673212, "learning_rate": 7.222398080560309e-06, "loss": 0.5805, "num_tokens": 483627700.0, "step": 81030 }, { "epoch": 0.8645301014583978, "grad_norm": 0.8548596773039955, "learning_rate": 7.220678411281276e-06, "loss": 0.5053, "num_tokens": 483676266.0, "step": 81035 }, { "epoch": 0.8645834444645962, "grad_norm": 0.7711917122071094, "learning_rate": 7.218959373053075e-06, "loss": 0.4407, "num_tokens": 483719347.0, "step": 81040 }, { "epoch": 0.8646367874707948, "grad_norm": 4.2392984044185145, "learning_rate": 7.217240965929196e-06, "loss": 0.5964, "num_tokens": 483750187.0, "step": 81045 }, { "epoch": 0.8646901304769932, "grad_norm": 0.9280299774068681, "learning_rate": 7.215523189963122e-06, "loss": 0.5022, "num_tokens": 483771910.0, "step": 81050 }, { "epoch": 0.8647434734831916, "grad_norm": 0.9689919176640668, "learning_rate": 7.213806045208295e-06, "loss": 0.4488, "num_tokens": 483795194.0, "step": 81055 }, { "epoch": 0.8647968164893901, "grad_norm": 1.369306218642261, "learning_rate": 7.212089531718153e-06, "loss": 0.3825, "num_tokens": 483815792.0, "step": 81060 }, { "epoch": 0.8648501594955885, "grad_norm": 0.5916610682294842, "learning_rate": 7.2103736495461195e-06, "loss": 0.3908, "num_tokens": 483860332.0, "step": 81065 }, { "epoch": 0.8649035025017869, "grad_norm": 1.0698295034536827, "learning_rate": 7.2086583987455755e-06, "loss": 0.5711, "num_tokens": 483888893.0, "step": 81070 }, { "epoch": 0.8649568455079855, "grad_norm": 0.7620756064682538, "learning_rate": 7.2069437793699095e-06, "loss": 0.4259, "num_tokens": 483921367.0, "step": 81075 }, { "epoch": 0.8650101885141839, "grad_norm": 1.5933568540850898, "learning_rate": 7.205229791472468e-06, "loss": 0.4392, "num_tokens": 483941983.0, "step": 81080 }, { "epoch": 0.8650635315203824, "grad_norm": 0.727216305805455, "learning_rate": 7.203516435106583e-06, "loss": 0.4109, "num_tokens": 483978926.0, "step": 81085 }, { "epoch": 0.8651168745265808, "grad_norm": 0.69727514027294, "learning_rate": 7.20180371032558e-06, "loss": 0.5302, "num_tokens": 484020217.0, "step": 81090 }, { "epoch": 0.8651702175327792, "grad_norm": 0.9427825919961343, "learning_rate": 7.200091617182755e-06, "loss": 0.4472, "num_tokens": 484046931.0, "step": 81095 }, { "epoch": 0.8652235605389778, "grad_norm": 1.3801234053700888, "learning_rate": 7.198380155731377e-06, "loss": 0.5808, "num_tokens": 484107974.0, "step": 81100 }, { "epoch": 0.8652769035451762, "grad_norm": 0.9039119971432894, "learning_rate": 7.196669326024706e-06, "loss": 0.509, "num_tokens": 484142061.0, "step": 81105 }, { "epoch": 0.8653302465513747, "grad_norm": 0.8485627867616554, "learning_rate": 7.194959128115987e-06, "loss": 0.4355, "num_tokens": 484170016.0, "step": 81110 }, { "epoch": 0.8653835895575731, "grad_norm": 0.8807406313116406, "learning_rate": 7.193249562058433e-06, "loss": 0.437, "num_tokens": 484199979.0, "step": 81115 }, { "epoch": 0.8654369325637715, "grad_norm": 1.4491236951147803, "learning_rate": 7.191540627905237e-06, "loss": 0.5428, "num_tokens": 484233296.0, "step": 81120 }, { "epoch": 0.86549027556997, "grad_norm": 0.8193478141704748, "learning_rate": 7.1898323257095845e-06, "loss": 0.4391, "num_tokens": 484253556.0, "step": 81125 }, { "epoch": 0.8655436185761685, "grad_norm": 0.8581233559266243, "learning_rate": 7.188124655524629e-06, "loss": 0.439, "num_tokens": 484282357.0, "step": 81130 }, { "epoch": 0.865596961582367, "grad_norm": 0.7397139433524293, "learning_rate": 7.186417617403512e-06, "loss": 0.4874, "num_tokens": 484320799.0, "step": 81135 }, { "epoch": 0.8656503045885654, "grad_norm": 0.6432487144291025, "learning_rate": 7.184711211399358e-06, "loss": 0.4509, "num_tokens": 484353409.0, "step": 81140 }, { "epoch": 0.8657036475947638, "grad_norm": 0.8905832925906174, "learning_rate": 7.183005437565259e-06, "loss": 0.4038, "num_tokens": 484379988.0, "step": 81145 }, { "epoch": 0.8657569906009623, "grad_norm": 0.8895674877512887, "learning_rate": 7.1813002959543004e-06, "loss": 0.4668, "num_tokens": 484409443.0, "step": 81150 }, { "epoch": 0.8658103336071608, "grad_norm": 2.0907201888242657, "learning_rate": 7.1795957866195415e-06, "loss": 0.5022, "num_tokens": 484441426.0, "step": 81155 }, { "epoch": 0.8658636766133592, "grad_norm": 0.789523558379489, "learning_rate": 7.177891909614019e-06, "loss": 0.4689, "num_tokens": 484486593.0, "step": 81160 }, { "epoch": 0.8659170196195577, "grad_norm": 0.6903256392371051, "learning_rate": 7.176188664990757e-06, "loss": 0.4504, "num_tokens": 484525621.0, "step": 81165 }, { "epoch": 0.8659703626257561, "grad_norm": 1.5529176134495715, "learning_rate": 7.174486052802763e-06, "loss": 0.4094, "num_tokens": 484543331.0, "step": 81170 }, { "epoch": 0.8660237056319546, "grad_norm": 0.9481300209924296, "learning_rate": 7.172784073103007e-06, "loss": 0.438, "num_tokens": 484574242.0, "step": 81175 }, { "epoch": 0.866077048638153, "grad_norm": 1.51145627913454, "learning_rate": 7.171082725944457e-06, "loss": 0.45, "num_tokens": 484602409.0, "step": 81180 }, { "epoch": 0.8661303916443515, "grad_norm": 1.504562098887661, "learning_rate": 7.16938201138006e-06, "loss": 0.4466, "num_tokens": 484629541.0, "step": 81185 }, { "epoch": 0.86618373465055, "grad_norm": 1.0424708780420753, "learning_rate": 7.167681929462737e-06, "loss": 0.4736, "num_tokens": 484653871.0, "step": 81190 }, { "epoch": 0.8662370776567484, "grad_norm": 0.850726711695068, "learning_rate": 7.1659824802453825e-06, "loss": 0.742, "num_tokens": 484697242.0, "step": 81195 }, { "epoch": 0.8662904206629469, "grad_norm": 1.0542635333475476, "learning_rate": 7.1642836637808906e-06, "loss": 0.4607, "num_tokens": 484715647.0, "step": 81200 }, { "epoch": 0.8663437636691453, "grad_norm": 1.0805859126230473, "learning_rate": 7.162585480122116e-06, "loss": 0.499, "num_tokens": 484753281.0, "step": 81205 }, { "epoch": 0.8663971066753438, "grad_norm": 0.7106592086955049, "learning_rate": 7.160887929321909e-06, "loss": 0.3763, "num_tokens": 484785207.0, "step": 81210 }, { "epoch": 0.8664504496815423, "grad_norm": 1.3129140300416209, "learning_rate": 7.159191011433094e-06, "loss": 0.5218, "num_tokens": 484804045.0, "step": 81215 }, { "epoch": 0.8665037926877407, "grad_norm": 1.2662899964873653, "learning_rate": 7.157494726508473e-06, "loss": 0.4469, "num_tokens": 484816444.0, "step": 81220 }, { "epoch": 0.8665571356939392, "grad_norm": 0.8004485727229996, "learning_rate": 7.1557990746008276e-06, "loss": 0.4546, "num_tokens": 484845332.0, "step": 81225 }, { "epoch": 0.8666104787001376, "grad_norm": 0.8983018207080171, "learning_rate": 7.154104055762927e-06, "loss": 0.4837, "num_tokens": 484876983.0, "step": 81230 }, { "epoch": 0.866663821706336, "grad_norm": 0.8573144492732345, "learning_rate": 7.152409670047523e-06, "loss": 0.4325, "num_tokens": 484914926.0, "step": 81235 }, { "epoch": 0.8667171647125346, "grad_norm": 0.8877967070116496, "learning_rate": 7.1507159175073296e-06, "loss": 0.4155, "num_tokens": 484930389.0, "step": 81240 }, { "epoch": 0.866770507718733, "grad_norm": 0.8347121999079861, "learning_rate": 7.149022798195054e-06, "loss": 0.4134, "num_tokens": 484962849.0, "step": 81245 }, { "epoch": 0.8668238507249314, "grad_norm": 0.6249016240228068, "learning_rate": 7.147330312163396e-06, "loss": 0.5032, "num_tokens": 484996028.0, "step": 81250 }, { "epoch": 0.8668771937311299, "grad_norm": 1.3084781274369894, "learning_rate": 7.145638459465011e-06, "loss": 0.4382, "num_tokens": 485017529.0, "step": 81255 }, { "epoch": 0.8669305367373283, "grad_norm": 0.8454448020356806, "learning_rate": 7.1439472401525444e-06, "loss": 0.5281, "num_tokens": 485045664.0, "step": 81260 }, { "epoch": 0.8669838797435269, "grad_norm": 0.6861824884208715, "learning_rate": 7.142256654278631e-06, "loss": 0.3883, "num_tokens": 485072313.0, "step": 81265 }, { "epoch": 0.8670372227497253, "grad_norm": 2.7078669965788955, "learning_rate": 7.140566701895872e-06, "loss": 0.5429, "num_tokens": 485096377.0, "step": 81270 }, { "epoch": 0.8670905657559237, "grad_norm": 1.0718353148406223, "learning_rate": 7.138877383056856e-06, "loss": 0.5186, "num_tokens": 485141876.0, "step": 81275 }, { "epoch": 0.8671439087621222, "grad_norm": 4.830298508218105, "learning_rate": 7.137188697814157e-06, "loss": 0.5416, "num_tokens": 485171910.0, "step": 81280 }, { "epoch": 0.8671972517683206, "grad_norm": 1.0235465007583342, "learning_rate": 7.135500646220314e-06, "loss": 0.4548, "num_tokens": 485207652.0, "step": 81285 }, { "epoch": 0.8672505947745192, "grad_norm": 0.7407802739401435, "learning_rate": 7.133813228327869e-06, "loss": 0.4531, "num_tokens": 485224898.0, "step": 81290 }, { "epoch": 0.8673039377807176, "grad_norm": 1.3201089291105035, "learning_rate": 7.13212644418932e-06, "loss": 0.504, "num_tokens": 485246291.0, "step": 81295 }, { "epoch": 0.867357280786916, "grad_norm": 0.8278975206083997, "learning_rate": 7.130440293857155e-06, "loss": 0.442, "num_tokens": 485286709.0, "step": 81300 }, { "epoch": 0.8674106237931145, "grad_norm": 0.6414759706058553, "learning_rate": 7.128754777383849e-06, "loss": 0.4844, "num_tokens": 485320743.0, "step": 81305 }, { "epoch": 0.8674639667993129, "grad_norm": 0.5347489601032965, "learning_rate": 7.127069894821854e-06, "loss": 0.4523, "num_tokens": 485359376.0, "step": 81310 }, { "epoch": 0.8675173098055114, "grad_norm": 0.8367731720261405, "learning_rate": 7.125385646223594e-06, "loss": 0.4335, "num_tokens": 485384182.0, "step": 81315 }, { "epoch": 0.8675706528117099, "grad_norm": 0.8842394641013133, "learning_rate": 7.12370203164148e-06, "loss": 0.4219, "num_tokens": 485417211.0, "step": 81320 }, { "epoch": 0.8676239958179083, "grad_norm": 1.286650959364375, "learning_rate": 7.122019051127909e-06, "loss": 0.4846, "num_tokens": 485452430.0, "step": 81325 }, { "epoch": 0.8676773388241068, "grad_norm": 0.5725776677469797, "learning_rate": 7.120336704735249e-06, "loss": 0.4345, "num_tokens": 485481632.0, "step": 81330 }, { "epoch": 0.8677306818303052, "grad_norm": 1.1171107574976187, "learning_rate": 7.118654992515844e-06, "loss": 0.4276, "num_tokens": 485496677.0, "step": 81335 }, { "epoch": 0.8677840248365036, "grad_norm": 0.6927861982647736, "learning_rate": 7.116973914522037e-06, "loss": 0.4929, "num_tokens": 485534856.0, "step": 81340 }, { "epoch": 0.8678373678427022, "grad_norm": 0.7723790265135004, "learning_rate": 7.115293470806129e-06, "loss": 0.4191, "num_tokens": 485570813.0, "step": 81345 }, { "epoch": 0.8678907108489006, "grad_norm": 0.9889305840403336, "learning_rate": 7.113613661420415e-06, "loss": 0.5251, "num_tokens": 485610434.0, "step": 81350 }, { "epoch": 0.8679440538550991, "grad_norm": 0.9612404897642216, "learning_rate": 7.111934486417177e-06, "loss": 0.4952, "num_tokens": 485629487.0, "step": 81355 }, { "epoch": 0.8679973968612975, "grad_norm": 2.3848823816537488, "learning_rate": 7.1102559458486526e-06, "loss": 0.6029, "num_tokens": 485654939.0, "step": 81360 }, { "epoch": 0.8680507398674959, "grad_norm": 1.4018405542361436, "learning_rate": 7.108578039767086e-06, "loss": 0.5304, "num_tokens": 485666653.0, "step": 81365 }, { "epoch": 0.8681040828736944, "grad_norm": 0.7798011088951963, "learning_rate": 7.106900768224686e-06, "loss": 0.4704, "num_tokens": 485685899.0, "step": 81370 }, { "epoch": 0.8681574258798929, "grad_norm": 0.6757969234806276, "learning_rate": 7.10522413127364e-06, "loss": 0.436, "num_tokens": 485725357.0, "step": 81375 }, { "epoch": 0.8682107688860914, "grad_norm": 0.6300490520281699, "learning_rate": 7.10354812896613e-06, "loss": 0.4717, "num_tokens": 485752356.0, "step": 81380 }, { "epoch": 0.8682641118922898, "grad_norm": 0.6115312564555926, "learning_rate": 7.101872761354308e-06, "loss": 0.4134, "num_tokens": 485797073.0, "step": 81385 }, { "epoch": 0.8683174548984882, "grad_norm": 0.8541925077830997, "learning_rate": 7.100198028490303e-06, "loss": 0.4129, "num_tokens": 485840890.0, "step": 81390 }, { "epoch": 0.8683707979046867, "grad_norm": 0.7954680762507879, "learning_rate": 7.098523930426232e-06, "loss": 0.3694, "num_tokens": 485861603.0, "step": 81395 }, { "epoch": 0.8684241409108852, "grad_norm": 0.8777511580561879, "learning_rate": 7.096850467214198e-06, "loss": 0.4848, "num_tokens": 485892149.0, "step": 81400 }, { "epoch": 0.8684774839170837, "grad_norm": 0.9441789698251032, "learning_rate": 7.095177638906267e-06, "loss": 0.4403, "num_tokens": 485921576.0, "step": 81405 }, { "epoch": 0.8685308269232821, "grad_norm": 0.8632606685341451, "learning_rate": 7.093505445554489e-06, "loss": 0.4687, "num_tokens": 485960456.0, "step": 81410 }, { "epoch": 0.8685841699294805, "grad_norm": 0.8983781034036676, "learning_rate": 7.091833887210911e-06, "loss": 0.5065, "num_tokens": 485994608.0, "step": 81415 }, { "epoch": 0.868637512935679, "grad_norm": 0.5502335288382169, "learning_rate": 7.090162963927538e-06, "loss": 0.3283, "num_tokens": 486037904.0, "step": 81420 }, { "epoch": 0.8686908559418774, "grad_norm": 1.0470336872280552, "learning_rate": 7.088492675756372e-06, "loss": 0.4518, "num_tokens": 486064656.0, "step": 81425 }, { "epoch": 0.8687441989480759, "grad_norm": 0.9107400943995346, "learning_rate": 7.086823022749389e-06, "loss": 0.6275, "num_tokens": 486101088.0, "step": 81430 }, { "epoch": 0.8687975419542744, "grad_norm": 0.6241190708383296, "learning_rate": 7.085154004958541e-06, "loss": 0.3844, "num_tokens": 486143131.0, "step": 81435 }, { "epoch": 0.8688508849604728, "grad_norm": 1.2895872198293883, "learning_rate": 7.0834856224357745e-06, "loss": 0.4109, "num_tokens": 486166281.0, "step": 81440 }, { "epoch": 0.8689042279666713, "grad_norm": 0.8644757577497127, "learning_rate": 7.081817875232994e-06, "loss": 0.4168, "num_tokens": 486198910.0, "step": 81445 }, { "epoch": 0.8689575709728697, "grad_norm": 1.1542266683878843, "learning_rate": 7.080150763402097e-06, "loss": 0.4465, "num_tokens": 486222828.0, "step": 81450 }, { "epoch": 0.8690109139790682, "grad_norm": 1.5080768219922358, "learning_rate": 7.078484286994969e-06, "loss": 0.4504, "num_tokens": 486252913.0, "step": 81455 }, { "epoch": 0.8690642569852667, "grad_norm": 1.2923297570328607, "learning_rate": 7.076818446063464e-06, "loss": 0.4949, "num_tokens": 486270301.0, "step": 81460 }, { "epoch": 0.8691175999914651, "grad_norm": 1.2676783875924653, "learning_rate": 7.0751532406594145e-06, "loss": 0.3671, "num_tokens": 486298995.0, "step": 81465 }, { "epoch": 0.8691709429976636, "grad_norm": 0.6384588772135581, "learning_rate": 7.0734886708346424e-06, "loss": 0.4442, "num_tokens": 486328569.0, "step": 81470 }, { "epoch": 0.869224286003862, "grad_norm": 0.7574558750525092, "learning_rate": 7.07182473664095e-06, "loss": 0.478, "num_tokens": 486370041.0, "step": 81475 }, { "epoch": 0.8692776290100604, "grad_norm": 1.2670836084859087, "learning_rate": 7.070161438130112e-06, "loss": 0.5757, "num_tokens": 486401319.0, "step": 81480 }, { "epoch": 0.869330972016259, "grad_norm": 0.6618825125652741, "learning_rate": 7.068498775353881e-06, "loss": 0.3772, "num_tokens": 486425196.0, "step": 81485 }, { "epoch": 0.8693843150224574, "grad_norm": 1.1970384302923107, "learning_rate": 7.066836748364003e-06, "loss": 0.5586, "num_tokens": 486446799.0, "step": 81490 }, { "epoch": 0.8694376580286559, "grad_norm": 0.996374397593777, "learning_rate": 7.065175357212194e-06, "loss": 0.4862, "num_tokens": 486471758.0, "step": 81495 }, { "epoch": 0.8694910010348543, "grad_norm": 0.8700063189266553, "learning_rate": 7.063514601950151e-06, "loss": 0.4223, "num_tokens": 486506559.0, "step": 81500 }, { "epoch": 0.8695443440410527, "grad_norm": 0.7206733393314253, "learning_rate": 7.06185448262956e-06, "loss": 0.4841, "num_tokens": 486549099.0, "step": 81505 }, { "epoch": 0.8695976870472513, "grad_norm": 0.724205679364389, "learning_rate": 7.060194999302078e-06, "loss": 0.4022, "num_tokens": 486576234.0, "step": 81510 }, { "epoch": 0.8696510300534497, "grad_norm": 1.1733898128161517, "learning_rate": 7.058536152019335e-06, "loss": 0.4549, "num_tokens": 486610523.0, "step": 81515 }, { "epoch": 0.8697043730596481, "grad_norm": 1.1554485957143668, "learning_rate": 7.056877940832969e-06, "loss": 0.37, "num_tokens": 486646157.0, "step": 81520 }, { "epoch": 0.8697577160658466, "grad_norm": 0.7486300590126422, "learning_rate": 7.055220365794561e-06, "loss": 0.5021, "num_tokens": 486664339.0, "step": 81525 }, { "epoch": 0.869811059072045, "grad_norm": 0.7855039767457774, "learning_rate": 7.053563426955702e-06, "loss": 0.4481, "num_tokens": 486704747.0, "step": 81530 }, { "epoch": 0.8698644020782436, "grad_norm": 0.7249686718317745, "learning_rate": 7.051907124367957e-06, "loss": 0.5599, "num_tokens": 486744060.0, "step": 81535 }, { "epoch": 0.869917745084442, "grad_norm": 0.8387932748695431, "learning_rate": 7.050251458082854e-06, "loss": 0.4781, "num_tokens": 486772359.0, "step": 81540 }, { "epoch": 0.8699710880906404, "grad_norm": 0.6297727491584924, "learning_rate": 7.0485964281519254e-06, "loss": 0.4399, "num_tokens": 486792841.0, "step": 81545 }, { "epoch": 0.8700244310968389, "grad_norm": 0.7694088652183892, "learning_rate": 7.046942034626668e-06, "loss": 0.4295, "num_tokens": 486825680.0, "step": 81550 }, { "epoch": 0.8700777741030373, "grad_norm": 1.0014714541233105, "learning_rate": 7.045288277558558e-06, "loss": 0.5461, "num_tokens": 486854105.0, "step": 81555 }, { "epoch": 0.8701311171092359, "grad_norm": 0.6058808239882035, "learning_rate": 7.043635156999063e-06, "loss": 0.4579, "num_tokens": 486887938.0, "step": 81560 }, { "epoch": 0.8701844601154343, "grad_norm": 1.0973513227922436, "learning_rate": 7.041982672999626e-06, "loss": 0.4319, "num_tokens": 486913836.0, "step": 81565 }, { "epoch": 0.8702378031216327, "grad_norm": 0.8487452574902097, "learning_rate": 7.040330825611663e-06, "loss": 0.474, "num_tokens": 486940013.0, "step": 81570 }, { "epoch": 0.8702911461278312, "grad_norm": 0.7394488014580799, "learning_rate": 7.03867961488658e-06, "loss": 0.3709, "num_tokens": 486970863.0, "step": 81575 }, { "epoch": 0.8703444891340296, "grad_norm": 0.7201323865552954, "learning_rate": 7.03702904087576e-06, "loss": 0.432, "num_tokens": 487005623.0, "step": 81580 }, { "epoch": 0.8703978321402281, "grad_norm": 0.9671480794123297, "learning_rate": 7.035379103630568e-06, "loss": 0.4452, "num_tokens": 487026156.0, "step": 81585 }, { "epoch": 0.8704511751464266, "grad_norm": 0.6696790849578153, "learning_rate": 7.033729803202335e-06, "loss": 0.5137, "num_tokens": 487064937.0, "step": 81590 }, { "epoch": 0.870504518152625, "grad_norm": 1.0962118376857137, "learning_rate": 7.032081139642399e-06, "loss": 0.4285, "num_tokens": 487089822.0, "step": 81595 }, { "epoch": 0.8705578611588235, "grad_norm": 1.1172088386397352, "learning_rate": 7.030433113002048e-06, "loss": 0.3493, "num_tokens": 487118187.0, "step": 81600 }, { "epoch": 0.8706112041650219, "grad_norm": 0.7019427647453818, "learning_rate": 7.028785723332576e-06, "loss": 0.5071, "num_tokens": 487156393.0, "step": 81605 }, { "epoch": 0.8706645471712203, "grad_norm": 0.9286172607316933, "learning_rate": 7.027138970685246e-06, "loss": 0.4878, "num_tokens": 487177614.0, "step": 81610 }, { "epoch": 0.8707178901774189, "grad_norm": 1.6557366229894026, "learning_rate": 7.025492855111296e-06, "loss": 0.5065, "num_tokens": 487204923.0, "step": 81615 }, { "epoch": 0.8707712331836173, "grad_norm": 0.7174787517950167, "learning_rate": 7.023847376661953e-06, "loss": 0.5427, "num_tokens": 487230366.0, "step": 81620 }, { "epoch": 0.8708245761898158, "grad_norm": 1.1959276037204838, "learning_rate": 7.022202535388424e-06, "loss": 0.5906, "num_tokens": 487254870.0, "step": 81625 }, { "epoch": 0.8708779191960142, "grad_norm": 0.5223486642367671, "learning_rate": 7.020558331341883e-06, "loss": 0.391, "num_tokens": 487287570.0, "step": 81630 }, { "epoch": 0.8709312622022126, "grad_norm": 0.8211037110191213, "learning_rate": 7.018914764573502e-06, "loss": 0.5653, "num_tokens": 487315691.0, "step": 81635 }, { "epoch": 0.8709846052084111, "grad_norm": 0.9239463148985998, "learning_rate": 7.017271835134427e-06, "loss": 0.5169, "num_tokens": 487337254.0, "step": 81640 }, { "epoch": 0.8710379482146096, "grad_norm": 0.6805949994586019, "learning_rate": 7.015629543075778e-06, "loss": 0.433, "num_tokens": 487360955.0, "step": 81645 }, { "epoch": 0.8710912912208081, "grad_norm": 1.4904149056778324, "learning_rate": 7.013987888448658e-06, "loss": 0.517, "num_tokens": 487388308.0, "step": 81650 }, { "epoch": 0.8711446342270065, "grad_norm": 1.1489785039083975, "learning_rate": 7.012346871304165e-06, "loss": 0.4972, "num_tokens": 487399290.0, "step": 81655 }, { "epoch": 0.8711979772332049, "grad_norm": 0.9927395310512347, "learning_rate": 7.0107064916933486e-06, "loss": 0.484, "num_tokens": 487430100.0, "step": 81660 }, { "epoch": 0.8712513202394034, "grad_norm": 0.8601636951476623, "learning_rate": 7.0090667496672594e-06, "loss": 0.4535, "num_tokens": 487459279.0, "step": 81665 }, { "epoch": 0.8713046632456019, "grad_norm": 0.5631862195876034, "learning_rate": 7.0074276452769275e-06, "loss": 0.4125, "num_tokens": 487498328.0, "step": 81670 }, { "epoch": 0.8713580062518004, "grad_norm": 1.0187432518543487, "learning_rate": 7.005789178573349e-06, "loss": 0.5168, "num_tokens": 487516298.0, "step": 81675 }, { "epoch": 0.8714113492579988, "grad_norm": 0.9488620822580963, "learning_rate": 7.004151349607514e-06, "loss": 0.5125, "num_tokens": 487548979.0, "step": 81680 }, { "epoch": 0.8714646922641972, "grad_norm": 0.8937770440794767, "learning_rate": 7.0025141584303954e-06, "loss": 0.4056, "num_tokens": 487571289.0, "step": 81685 }, { "epoch": 0.8715180352703957, "grad_norm": 0.7544594958343234, "learning_rate": 7.000877605092929e-06, "loss": 0.52, "num_tokens": 487599982.0, "step": 81690 }, { "epoch": 0.8715713782765941, "grad_norm": 0.8202886447456615, "learning_rate": 6.99924168964605e-06, "loss": 0.3353, "num_tokens": 487619760.0, "step": 81695 }, { "epoch": 0.8716247212827926, "grad_norm": 0.6833817806008425, "learning_rate": 6.997606412140656e-06, "loss": 0.4892, "num_tokens": 487659005.0, "step": 81700 }, { "epoch": 0.8716780642889911, "grad_norm": 0.5306041231019972, "learning_rate": 6.995971772627638e-06, "loss": 0.4583, "num_tokens": 487713680.0, "step": 81705 }, { "epoch": 0.8717314072951895, "grad_norm": 3.256659838078207, "learning_rate": 6.994337771157858e-06, "loss": 0.3834, "num_tokens": 487746301.0, "step": 81710 }, { "epoch": 0.871784750301388, "grad_norm": 1.2105206783803002, "learning_rate": 6.992704407782172e-06, "loss": 0.4638, "num_tokens": 487783365.0, "step": 81715 }, { "epoch": 0.8718380933075864, "grad_norm": 0.5648378138346917, "learning_rate": 6.991071682551399e-06, "loss": 0.4036, "num_tokens": 487818991.0, "step": 81720 }, { "epoch": 0.8718914363137849, "grad_norm": 0.7407841739951532, "learning_rate": 6.989439595516348e-06, "loss": 0.4355, "num_tokens": 487843556.0, "step": 81725 }, { "epoch": 0.8719447793199834, "grad_norm": 0.9514314458484219, "learning_rate": 6.987808146727811e-06, "loss": 0.4986, "num_tokens": 487870108.0, "step": 81730 }, { "epoch": 0.8719981223261818, "grad_norm": 0.8576718551400736, "learning_rate": 6.986177336236549e-06, "loss": 0.4482, "num_tokens": 487908756.0, "step": 81735 }, { "epoch": 0.8720514653323803, "grad_norm": 1.0116184918329683, "learning_rate": 6.984547164093311e-06, "loss": 0.4569, "num_tokens": 487944844.0, "step": 81740 }, { "epoch": 0.8721048083385787, "grad_norm": 0.6280795340922343, "learning_rate": 6.982917630348827e-06, "loss": 0.3813, "num_tokens": 487979990.0, "step": 81745 }, { "epoch": 0.8721581513447771, "grad_norm": 0.8051183213356041, "learning_rate": 6.981288735053801e-06, "loss": 0.3545, "num_tokens": 488007829.0, "step": 81750 }, { "epoch": 0.8722114943509757, "grad_norm": 0.5699303505942306, "learning_rate": 6.9796604782589205e-06, "loss": 0.3446, "num_tokens": 488039365.0, "step": 81755 }, { "epoch": 0.8722648373571741, "grad_norm": 1.216455689155457, "learning_rate": 6.978032860014863e-06, "loss": 0.4282, "num_tokens": 488075985.0, "step": 81760 }, { "epoch": 0.8723181803633726, "grad_norm": 0.701098601356128, "learning_rate": 6.976405880372263e-06, "loss": 0.4915, "num_tokens": 488100520.0, "step": 81765 }, { "epoch": 0.872371523369571, "grad_norm": 1.008568739122436, "learning_rate": 6.97477953938176e-06, "loss": 0.6195, "num_tokens": 488146092.0, "step": 81770 }, { "epoch": 0.8724248663757694, "grad_norm": 0.5980127147599957, "learning_rate": 6.973153837093957e-06, "loss": 0.408, "num_tokens": 488176997.0, "step": 81775 }, { "epoch": 0.872478209381968, "grad_norm": 0.6489636855730582, "learning_rate": 6.9715287735594426e-06, "loss": 0.48, "num_tokens": 488213708.0, "step": 81780 }, { "epoch": 0.8725315523881664, "grad_norm": 0.8286849013687523, "learning_rate": 6.969904348828783e-06, "loss": 0.4625, "num_tokens": 488239573.0, "step": 81785 }, { "epoch": 0.8725848953943648, "grad_norm": 0.8684834842896283, "learning_rate": 6.968280562952534e-06, "loss": 0.4103, "num_tokens": 488260106.0, "step": 81790 }, { "epoch": 0.8726382384005633, "grad_norm": 0.9616107498070677, "learning_rate": 6.9666574159812165e-06, "loss": 0.3896, "num_tokens": 488287829.0, "step": 81795 }, { "epoch": 0.8726915814067617, "grad_norm": 0.8892335855021095, "learning_rate": 6.96503490796535e-06, "loss": 0.4231, "num_tokens": 488308321.0, "step": 81800 }, { "epoch": 0.8727449244129603, "grad_norm": 0.9804989601418143, "learning_rate": 6.963413038955412e-06, "loss": 0.4823, "num_tokens": 488336549.0, "step": 81805 }, { "epoch": 0.8727982674191587, "grad_norm": 0.7826568156040172, "learning_rate": 6.961791809001879e-06, "loss": 0.4014, "num_tokens": 488359688.0, "step": 81810 }, { "epoch": 0.8728516104253571, "grad_norm": 0.6806446892420126, "learning_rate": 6.960171218155195e-06, "loss": 0.4081, "num_tokens": 488395823.0, "step": 81815 }, { "epoch": 0.8729049534315556, "grad_norm": 0.8762562235414361, "learning_rate": 6.958551266465796e-06, "loss": 0.4425, "num_tokens": 488429045.0, "step": 81820 }, { "epoch": 0.872958296437754, "grad_norm": 1.2814051171140806, "learning_rate": 6.9569319539840876e-06, "loss": 0.5011, "num_tokens": 488444158.0, "step": 81825 }, { "epoch": 0.8730116394439525, "grad_norm": 0.5978106797628895, "learning_rate": 6.955313280760458e-06, "loss": 0.4245, "num_tokens": 488472673.0, "step": 81830 }, { "epoch": 0.873064982450151, "grad_norm": 0.6576637420567205, "learning_rate": 6.953695246845282e-06, "loss": 0.4657, "num_tokens": 488525284.0, "step": 81835 }, { "epoch": 0.8731183254563494, "grad_norm": 0.8222224337264527, "learning_rate": 6.952077852288907e-06, "loss": 0.4398, "num_tokens": 488555283.0, "step": 81840 }, { "epoch": 0.8731716684625479, "grad_norm": 0.8689513904737283, "learning_rate": 6.95046109714166e-06, "loss": 0.4101, "num_tokens": 488579703.0, "step": 81845 }, { "epoch": 0.8732250114687463, "grad_norm": 0.7379494539035897, "learning_rate": 6.948844981453857e-06, "loss": 0.5093, "num_tokens": 488614767.0, "step": 81850 }, { "epoch": 0.8732783544749448, "grad_norm": 0.7408125227356316, "learning_rate": 6.94722950527578e-06, "loss": 0.4461, "num_tokens": 488648813.0, "step": 81855 }, { "epoch": 0.8733316974811433, "grad_norm": 0.6792962970743119, "learning_rate": 6.945614668657706e-06, "loss": 0.4715, "num_tokens": 488684299.0, "step": 81860 }, { "epoch": 0.8733850404873417, "grad_norm": 0.7733509936959474, "learning_rate": 6.9440004716498865e-06, "loss": 0.4406, "num_tokens": 488719062.0, "step": 81865 }, { "epoch": 0.8734383834935402, "grad_norm": 0.683583854733821, "learning_rate": 6.942386914302545e-06, "loss": 0.4129, "num_tokens": 488761339.0, "step": 81870 }, { "epoch": 0.8734917264997386, "grad_norm": 1.0688030363977292, "learning_rate": 6.9407739966659e-06, "loss": 0.4897, "num_tokens": 488787544.0, "step": 81875 }, { "epoch": 0.873545069505937, "grad_norm": 0.8687195295093492, "learning_rate": 6.939161718790141e-06, "loss": 0.4713, "num_tokens": 488847877.0, "step": 81880 }, { "epoch": 0.8735984125121355, "grad_norm": 0.7842493760263131, "learning_rate": 6.9375500807254274e-06, "loss": 0.4691, "num_tokens": 488880949.0, "step": 81885 }, { "epoch": 0.873651755518334, "grad_norm": 0.6214000441771027, "learning_rate": 6.935939082521922e-06, "loss": 0.4409, "num_tokens": 488902491.0, "step": 81890 }, { "epoch": 0.8737050985245325, "grad_norm": 1.8549027162738876, "learning_rate": 6.934328724229755e-06, "loss": 0.5255, "num_tokens": 488925186.0, "step": 81895 }, { "epoch": 0.8737584415307309, "grad_norm": 1.2202594260397543, "learning_rate": 6.932719005899033e-06, "loss": 0.4273, "num_tokens": 488940816.0, "step": 81900 }, { "epoch": 0.8738117845369293, "grad_norm": 0.921607570442221, "learning_rate": 6.931109927579847e-06, "loss": 0.3877, "num_tokens": 488962749.0, "step": 81905 }, { "epoch": 0.8738651275431278, "grad_norm": 0.7172026491867706, "learning_rate": 6.929501489322277e-06, "loss": 0.3971, "num_tokens": 488986936.0, "step": 81910 }, { "epoch": 0.8739184705493263, "grad_norm": 0.8605614705101011, "learning_rate": 6.927893691176365e-06, "loss": 0.4683, "num_tokens": 489019879.0, "step": 81915 }, { "epoch": 0.8739718135555248, "grad_norm": 0.5992399954135637, "learning_rate": 6.926286533192142e-06, "loss": 0.4183, "num_tokens": 489059548.0, "step": 81920 }, { "epoch": 0.8740251565617232, "grad_norm": 1.045392929620014, "learning_rate": 6.924680015419627e-06, "loss": 0.4944, "num_tokens": 489091755.0, "step": 81925 }, { "epoch": 0.8740784995679216, "grad_norm": 0.6576852004721161, "learning_rate": 6.923074137908802e-06, "loss": 0.3744, "num_tokens": 489117200.0, "step": 81930 }, { "epoch": 0.8741318425741201, "grad_norm": 0.9576043563090166, "learning_rate": 6.921468900709643e-06, "loss": 0.3227, "num_tokens": 489136799.0, "step": 81935 }, { "epoch": 0.8741851855803185, "grad_norm": 0.6113230948331141, "learning_rate": 6.9198643038721104e-06, "loss": 0.4009, "num_tokens": 489168862.0, "step": 81940 }, { "epoch": 0.8742385285865171, "grad_norm": 0.8416633586403532, "learning_rate": 6.91826034744612e-06, "loss": 0.4385, "num_tokens": 489194678.0, "step": 81945 }, { "epoch": 0.8742918715927155, "grad_norm": 0.902063769338986, "learning_rate": 6.9166570314815965e-06, "loss": 0.4124, "num_tokens": 489215582.0, "step": 81950 }, { "epoch": 0.8743452145989139, "grad_norm": 1.3706681956036697, "learning_rate": 6.915054356028425e-06, "loss": 0.5209, "num_tokens": 489238936.0, "step": 81955 }, { "epoch": 0.8743985576051124, "grad_norm": 0.6757065292720686, "learning_rate": 6.913452321136477e-06, "loss": 0.5035, "num_tokens": 489274239.0, "step": 81960 }, { "epoch": 0.8744519006113108, "grad_norm": 0.6898650898666288, "learning_rate": 6.911850926855608e-06, "loss": 0.4528, "num_tokens": 489304834.0, "step": 81965 }, { "epoch": 0.8745052436175093, "grad_norm": 0.5602245158662442, "learning_rate": 6.910250173235651e-06, "loss": 0.3516, "num_tokens": 489336234.0, "step": 81970 }, { "epoch": 0.8745585866237078, "grad_norm": 1.1447923690130541, "learning_rate": 6.90865006032641e-06, "loss": 0.4022, "num_tokens": 489353150.0, "step": 81975 }, { "epoch": 0.8746119296299062, "grad_norm": 0.8200113880816275, "learning_rate": 6.907050588177688e-06, "loss": 0.521, "num_tokens": 489379144.0, "step": 81980 }, { "epoch": 0.8746652726361047, "grad_norm": 1.197556768217737, "learning_rate": 6.905451756839256e-06, "loss": 0.4585, "num_tokens": 489400224.0, "step": 81985 }, { "epoch": 0.8747186156423031, "grad_norm": 1.111265736667786, "learning_rate": 6.90385356636086e-06, "loss": 0.4591, "num_tokens": 489415468.0, "step": 81990 }, { "epoch": 0.8747719586485015, "grad_norm": 0.7403660739850775, "learning_rate": 6.902256016792233e-06, "loss": 0.3962, "num_tokens": 489449835.0, "step": 81995 }, { "epoch": 0.8748253016547001, "grad_norm": 0.672787225949691, "learning_rate": 6.900659108183092e-06, "loss": 0.4273, "num_tokens": 489466503.0, "step": 82000 }, { "epoch": 0.8748786446608985, "grad_norm": 0.6673273424928875, "learning_rate": 6.899062840583126e-06, "loss": 0.4703, "num_tokens": 489484887.0, "step": 82005 }, { "epoch": 0.874931987667097, "grad_norm": 1.2521992244538296, "learning_rate": 6.897467214042008e-06, "loss": 0.626, "num_tokens": 489522484.0, "step": 82010 }, { "epoch": 0.8749853306732954, "grad_norm": 0.8710413974581482, "learning_rate": 6.8958722286093944e-06, "loss": 0.5306, "num_tokens": 489570181.0, "step": 82015 }, { "epoch": 0.8750386736794938, "grad_norm": 1.0436106266165202, "learning_rate": 6.894277884334911e-06, "loss": 0.4968, "num_tokens": 489607345.0, "step": 82020 }, { "epoch": 0.8750920166856924, "grad_norm": 0.7554038686734881, "learning_rate": 6.89268418126818e-06, "loss": 0.4758, "num_tokens": 489651994.0, "step": 82025 }, { "epoch": 0.8751453596918908, "grad_norm": 0.8096239613611333, "learning_rate": 6.8910911194587866e-06, "loss": 0.4479, "num_tokens": 489689988.0, "step": 82030 }, { "epoch": 0.8751987026980893, "grad_norm": 0.8779087914335152, "learning_rate": 6.889498698956304e-06, "loss": 0.5228, "num_tokens": 489723678.0, "step": 82035 }, { "epoch": 0.8752520457042877, "grad_norm": 0.9667521509270316, "learning_rate": 6.887906919810286e-06, "loss": 0.5081, "num_tokens": 489751853.0, "step": 82040 }, { "epoch": 0.8753053887104861, "grad_norm": 1.445522773449209, "learning_rate": 6.8863157820702685e-06, "loss": 0.4635, "num_tokens": 489790395.0, "step": 82045 }, { "epoch": 0.8753587317166847, "grad_norm": 1.8225944426632072, "learning_rate": 6.884725285785761e-06, "loss": 0.4587, "num_tokens": 489829614.0, "step": 82050 }, { "epoch": 0.8754120747228831, "grad_norm": 0.8226134902301888, "learning_rate": 6.883135431006253e-06, "loss": 0.4819, "num_tokens": 489857758.0, "step": 82055 }, { "epoch": 0.8754654177290815, "grad_norm": 1.0883715277989594, "learning_rate": 6.8815462177812315e-06, "loss": 0.6022, "num_tokens": 489908028.0, "step": 82060 }, { "epoch": 0.87551876073528, "grad_norm": 1.1406325177173153, "learning_rate": 6.879957646160138e-06, "loss": 0.4576, "num_tokens": 489928075.0, "step": 82065 }, { "epoch": 0.8755721037414784, "grad_norm": 0.8331363490168209, "learning_rate": 6.878369716192403e-06, "loss": 0.481, "num_tokens": 489962983.0, "step": 82070 }, { "epoch": 0.875625446747677, "grad_norm": 1.4438149862275718, "learning_rate": 6.876782427927448e-06, "loss": 0.39, "num_tokens": 489987093.0, "step": 82075 }, { "epoch": 0.8756787897538754, "grad_norm": 0.9420706438472711, "learning_rate": 6.875195781414659e-06, "loss": 0.3685, "num_tokens": 490023831.0, "step": 82080 }, { "epoch": 0.8757321327600738, "grad_norm": 0.8276170487992216, "learning_rate": 6.873609776703415e-06, "loss": 0.4669, "num_tokens": 490048975.0, "step": 82085 }, { "epoch": 0.8757854757662723, "grad_norm": 1.9151599599788562, "learning_rate": 6.872024413843069e-06, "loss": 0.5819, "num_tokens": 490073122.0, "step": 82090 }, { "epoch": 0.8758388187724707, "grad_norm": 1.1126967078382808, "learning_rate": 6.870439692882946e-06, "loss": 0.4511, "num_tokens": 490085343.0, "step": 82095 }, { "epoch": 0.8758921617786692, "grad_norm": 0.7702559958695999, "learning_rate": 6.868855613872373e-06, "loss": 0.6335, "num_tokens": 490111431.0, "step": 82100 }, { "epoch": 0.8759455047848677, "grad_norm": 0.7305669403986679, "learning_rate": 6.8672721768606365e-06, "loss": 0.4846, "num_tokens": 490150175.0, "step": 82105 }, { "epoch": 0.8759988477910661, "grad_norm": 1.4209397483273838, "learning_rate": 6.865689381897002e-06, "loss": 0.4034, "num_tokens": 490173744.0, "step": 82110 }, { "epoch": 0.8760521907972646, "grad_norm": 1.5636361004305226, "learning_rate": 6.864107229030732e-06, "loss": 0.3969, "num_tokens": 490197085.0, "step": 82115 }, { "epoch": 0.876105533803463, "grad_norm": 0.7025420958555281, "learning_rate": 6.86252571831106e-06, "loss": 0.4463, "num_tokens": 490225375.0, "step": 82120 }, { "epoch": 0.8761588768096615, "grad_norm": 0.7752957559575435, "learning_rate": 6.860944849787193e-06, "loss": 0.3465, "num_tokens": 490248360.0, "step": 82125 }, { "epoch": 0.87621221981586, "grad_norm": 1.0053479276094874, "learning_rate": 6.8593646235083324e-06, "loss": 0.4441, "num_tokens": 490270035.0, "step": 82130 }, { "epoch": 0.8762655628220584, "grad_norm": 0.9327316121726551, "learning_rate": 6.857785039523648e-06, "loss": 0.4259, "num_tokens": 490310023.0, "step": 82135 }, { "epoch": 0.8763189058282569, "grad_norm": 0.8198497862015119, "learning_rate": 6.856206097882289e-06, "loss": 0.3937, "num_tokens": 490349942.0, "step": 82140 }, { "epoch": 0.8763722488344553, "grad_norm": 0.9566938179555051, "learning_rate": 6.854627798633392e-06, "loss": 0.4584, "num_tokens": 490371087.0, "step": 82145 }, { "epoch": 0.8764255918406537, "grad_norm": 0.7659536673376544, "learning_rate": 6.853050141826073e-06, "loss": 0.3635, "num_tokens": 490397022.0, "step": 82150 }, { "epoch": 0.8764789348468522, "grad_norm": 1.0261574526336001, "learning_rate": 6.851473127509428e-06, "loss": 0.4973, "num_tokens": 490423488.0, "step": 82155 }, { "epoch": 0.8765322778530507, "grad_norm": 0.903142968069665, "learning_rate": 6.84989675573252e-06, "loss": 0.4117, "num_tokens": 490448410.0, "step": 82160 }, { "epoch": 0.8765856208592492, "grad_norm": 0.588702018646367, "learning_rate": 6.848321026544412e-06, "loss": 0.4417, "num_tokens": 490477329.0, "step": 82165 }, { "epoch": 0.8766389638654476, "grad_norm": 0.9110463965517751, "learning_rate": 6.8467459399941345e-06, "loss": 0.5432, "num_tokens": 490527672.0, "step": 82170 }, { "epoch": 0.876692306871646, "grad_norm": 0.9098454201146915, "learning_rate": 6.845171496130696e-06, "loss": 0.483, "num_tokens": 490560885.0, "step": 82175 }, { "epoch": 0.8767456498778445, "grad_norm": 0.9271002009883073, "learning_rate": 6.843597695003096e-06, "loss": 0.4145, "num_tokens": 490596341.0, "step": 82180 }, { "epoch": 0.876798992884043, "grad_norm": 0.7192590645915857, "learning_rate": 6.842024536660309e-06, "loss": 0.4893, "num_tokens": 490636103.0, "step": 82185 }, { "epoch": 0.8768523358902415, "grad_norm": 0.9641646982109291, "learning_rate": 6.84045202115128e-06, "loss": 0.4712, "num_tokens": 490658516.0, "step": 82190 }, { "epoch": 0.8769056788964399, "grad_norm": 1.1440346942242452, "learning_rate": 6.838880148524951e-06, "loss": 0.5096, "num_tokens": 490690805.0, "step": 82195 }, { "epoch": 0.8769590219026383, "grad_norm": 1.0871740197345114, "learning_rate": 6.837308918830236e-06, "loss": 0.3732, "num_tokens": 490712407.0, "step": 82200 }, { "epoch": 0.8770123649088368, "grad_norm": 0.8105778862250653, "learning_rate": 6.835738332116025e-06, "loss": 0.4566, "num_tokens": 490743275.0, "step": 82205 }, { "epoch": 0.8770657079150352, "grad_norm": 1.1957933136108236, "learning_rate": 6.834168388431189e-06, "loss": 0.4135, "num_tokens": 490780283.0, "step": 82210 }, { "epoch": 0.8771190509212338, "grad_norm": 1.2309865306806111, "learning_rate": 6.832599087824586e-06, "loss": 0.5071, "num_tokens": 490815020.0, "step": 82215 }, { "epoch": 0.8771723939274322, "grad_norm": 1.348044686826885, "learning_rate": 6.831030430345042e-06, "loss": 0.5614, "num_tokens": 490859619.0, "step": 82220 }, { "epoch": 0.8772257369336306, "grad_norm": 0.7291323840812785, "learning_rate": 6.829462416041378e-06, "loss": 0.6183, "num_tokens": 490893340.0, "step": 82225 }, { "epoch": 0.8772790799398291, "grad_norm": 0.6176153378822072, "learning_rate": 6.8278950449623875e-06, "loss": 0.4039, "num_tokens": 490916539.0, "step": 82230 }, { "epoch": 0.8773324229460275, "grad_norm": 1.009414539635192, "learning_rate": 6.8263283171568395e-06, "loss": 0.3534, "num_tokens": 490939354.0, "step": 82235 }, { "epoch": 0.877385765952226, "grad_norm": 1.0072263637317116, "learning_rate": 6.824762232673492e-06, "loss": 0.5104, "num_tokens": 490973976.0, "step": 82240 }, { "epoch": 0.8774391089584245, "grad_norm": 0.7979119249330805, "learning_rate": 6.823196791561075e-06, "loss": 0.421, "num_tokens": 491018302.0, "step": 82245 }, { "epoch": 0.8774924519646229, "grad_norm": 0.5295748582563233, "learning_rate": 6.821631993868301e-06, "loss": 0.4275, "num_tokens": 491061450.0, "step": 82250 }, { "epoch": 0.8775457949708214, "grad_norm": 0.7343342510247245, "learning_rate": 6.820067839643861e-06, "loss": 0.5735, "num_tokens": 491098009.0, "step": 82255 }, { "epoch": 0.8775991379770198, "grad_norm": 1.0211563944177613, "learning_rate": 6.818504328936439e-06, "loss": 0.5357, "num_tokens": 491132544.0, "step": 82260 }, { "epoch": 0.8776524809832182, "grad_norm": 0.9254690692842789, "learning_rate": 6.816941461794676e-06, "loss": 0.4358, "num_tokens": 491163825.0, "step": 82265 }, { "epoch": 0.8777058239894168, "grad_norm": 1.470465825201829, "learning_rate": 6.815379238267211e-06, "loss": 0.501, "num_tokens": 491192235.0, "step": 82270 }, { "epoch": 0.8777591669956152, "grad_norm": 0.8066580884945163, "learning_rate": 6.81381765840266e-06, "loss": 0.4557, "num_tokens": 491220501.0, "step": 82275 }, { "epoch": 0.8778125100018137, "grad_norm": 0.9690820113531813, "learning_rate": 6.812256722249614e-06, "loss": 0.4438, "num_tokens": 491247063.0, "step": 82280 }, { "epoch": 0.8778658530080121, "grad_norm": 0.6236234904464656, "learning_rate": 6.810696429856642e-06, "loss": 0.4062, "num_tokens": 491279336.0, "step": 82285 }, { "epoch": 0.8779191960142105, "grad_norm": 0.8446231771915236, "learning_rate": 6.8091367812723e-06, "loss": 0.3552, "num_tokens": 491320958.0, "step": 82290 }, { "epoch": 0.8779725390204091, "grad_norm": 0.9835053835109665, "learning_rate": 6.807577776545121e-06, "loss": 0.4707, "num_tokens": 491347832.0, "step": 82295 }, { "epoch": 0.8780258820266075, "grad_norm": 1.0034855262800797, "learning_rate": 6.806019415723616e-06, "loss": 0.4044, "num_tokens": 491376053.0, "step": 82300 }, { "epoch": 0.878079225032806, "grad_norm": 0.9809953646223684, "learning_rate": 6.804461698856285e-06, "loss": 0.4339, "num_tokens": 491402281.0, "step": 82305 }, { "epoch": 0.8781325680390044, "grad_norm": 0.6440688777724455, "learning_rate": 6.802904625991591e-06, "loss": 0.4757, "num_tokens": 491440317.0, "step": 82310 }, { "epoch": 0.8781859110452028, "grad_norm": 1.0704539406268079, "learning_rate": 6.801348197177997e-06, "loss": 0.513, "num_tokens": 491458832.0, "step": 82315 }, { "epoch": 0.8782392540514014, "grad_norm": 0.9391199246287251, "learning_rate": 6.7997924124639315e-06, "loss": 0.421, "num_tokens": 491499071.0, "step": 82320 }, { "epoch": 0.8782925970575998, "grad_norm": 1.0613058834847613, "learning_rate": 6.7982372718978005e-06, "loss": 0.505, "num_tokens": 491531520.0, "step": 82325 }, { "epoch": 0.8783459400637982, "grad_norm": 1.5203382651036355, "learning_rate": 6.796682775528007e-06, "loss": 0.4072, "num_tokens": 491549332.0, "step": 82330 }, { "epoch": 0.8783992830699967, "grad_norm": 1.2311344558175983, "learning_rate": 6.79512892340292e-06, "loss": 0.4205, "num_tokens": 491577083.0, "step": 82335 }, { "epoch": 0.8784526260761951, "grad_norm": 1.4420195911398317, "learning_rate": 6.793575715570888e-06, "loss": 0.4216, "num_tokens": 491596873.0, "step": 82340 }, { "epoch": 0.8785059690823936, "grad_norm": 1.1849524599821675, "learning_rate": 6.79202315208025e-06, "loss": 0.543, "num_tokens": 491628629.0, "step": 82345 }, { "epoch": 0.8785593120885921, "grad_norm": 1.2851011657696625, "learning_rate": 6.790471232979318e-06, "loss": 0.4296, "num_tokens": 491667615.0, "step": 82350 }, { "epoch": 0.8786126550947905, "grad_norm": 0.5544797211744784, "learning_rate": 6.788919958316384e-06, "loss": 0.4281, "num_tokens": 491694093.0, "step": 82355 }, { "epoch": 0.878665998100989, "grad_norm": 0.7300309017328592, "learning_rate": 6.787369328139713e-06, "loss": 0.4459, "num_tokens": 491726369.0, "step": 82360 }, { "epoch": 0.8787193411071874, "grad_norm": 1.092951174467652, "learning_rate": 6.78581934249757e-06, "loss": 0.549, "num_tokens": 491756883.0, "step": 82365 }, { "epoch": 0.8787726841133859, "grad_norm": 0.685036679785814, "learning_rate": 6.7842700014381756e-06, "loss": 0.4985, "num_tokens": 491805345.0, "step": 82370 }, { "epoch": 0.8788260271195844, "grad_norm": 0.6812679454529146, "learning_rate": 6.7827213050097485e-06, "loss": 0.4599, "num_tokens": 491835381.0, "step": 82375 }, { "epoch": 0.8788793701257828, "grad_norm": 0.6889800297495652, "learning_rate": 6.781173253260481e-06, "loss": 0.404, "num_tokens": 491865284.0, "step": 82380 }, { "epoch": 0.8789327131319813, "grad_norm": 1.3800193346677077, "learning_rate": 6.779625846238543e-06, "loss": 0.4433, "num_tokens": 491897795.0, "step": 82385 }, { "epoch": 0.8789860561381797, "grad_norm": 1.1301353490328285, "learning_rate": 6.778079083992091e-06, "loss": 0.447, "num_tokens": 491946024.0, "step": 82390 }, { "epoch": 0.8790393991443782, "grad_norm": 0.9188760958541645, "learning_rate": 6.776532966569253e-06, "loss": 0.4718, "num_tokens": 491964811.0, "step": 82395 }, { "epoch": 0.8790927421505766, "grad_norm": 0.904763762771671, "learning_rate": 6.7749874940181385e-06, "loss": 0.5047, "num_tokens": 491997497.0, "step": 82400 }, { "epoch": 0.8791460851567751, "grad_norm": 0.5723224319863225, "learning_rate": 6.773442666386844e-06, "loss": 0.4138, "num_tokens": 492042248.0, "step": 82405 }, { "epoch": 0.8791994281629736, "grad_norm": 1.366882246773215, "learning_rate": 6.771898483723443e-06, "loss": 0.394, "num_tokens": 492068787.0, "step": 82410 }, { "epoch": 0.879252771169172, "grad_norm": 1.3528599178063216, "learning_rate": 6.7703549460759825e-06, "loss": 0.5569, "num_tokens": 492100902.0, "step": 82415 }, { "epoch": 0.8793061141753704, "grad_norm": 1.2336125606922017, "learning_rate": 6.768812053492497e-06, "loss": 0.3733, "num_tokens": 492125748.0, "step": 82420 }, { "epoch": 0.8793594571815689, "grad_norm": 0.7479264906350294, "learning_rate": 6.767269806020998e-06, "loss": 0.4707, "num_tokens": 492156017.0, "step": 82425 }, { "epoch": 0.8794128001877674, "grad_norm": 1.3797490958084122, "learning_rate": 6.765728203709473e-06, "loss": 0.5474, "num_tokens": 492181492.0, "step": 82430 }, { "epoch": 0.8794661431939659, "grad_norm": 1.03129462424557, "learning_rate": 6.764187246605896e-06, "loss": 0.4681, "num_tokens": 492207288.0, "step": 82435 }, { "epoch": 0.8795194862001643, "grad_norm": 0.9332076501199812, "learning_rate": 6.762646934758224e-06, "loss": 0.5531, "num_tokens": 492235533.0, "step": 82440 }, { "epoch": 0.8795728292063627, "grad_norm": 0.9909168051370953, "learning_rate": 6.76110726821438e-06, "loss": 0.4723, "num_tokens": 492256768.0, "step": 82445 }, { "epoch": 0.8796261722125612, "grad_norm": 1.3568068704042433, "learning_rate": 6.75956824702228e-06, "loss": 0.4317, "num_tokens": 492277564.0, "step": 82450 }, { "epoch": 0.8796795152187596, "grad_norm": 0.7283230483362056, "learning_rate": 6.758029871229816e-06, "loss": 0.4281, "num_tokens": 492316275.0, "step": 82455 }, { "epoch": 0.8797328582249582, "grad_norm": 1.2129267596691253, "learning_rate": 6.756492140884858e-06, "loss": 0.4367, "num_tokens": 492348508.0, "step": 82460 }, { "epoch": 0.8797862012311566, "grad_norm": 0.742466869887139, "learning_rate": 6.754955056035253e-06, "loss": 0.4577, "num_tokens": 492380020.0, "step": 82465 }, { "epoch": 0.879839544237355, "grad_norm": 0.6932858425708686, "learning_rate": 6.753418616728837e-06, "loss": 0.5581, "num_tokens": 492405394.0, "step": 82470 }, { "epoch": 0.8798928872435535, "grad_norm": 1.1503904924584734, "learning_rate": 6.751882823013417e-06, "loss": 0.4673, "num_tokens": 492425320.0, "step": 82475 }, { "epoch": 0.8799462302497519, "grad_norm": 0.7921903264219179, "learning_rate": 6.750347674936786e-06, "loss": 0.432, "num_tokens": 492456496.0, "step": 82480 }, { "epoch": 0.8799995732559505, "grad_norm": 1.4926211474824784, "learning_rate": 6.748813172546717e-06, "loss": 0.4543, "num_tokens": 492477401.0, "step": 82485 }, { "epoch": 0.8800529162621489, "grad_norm": 0.9721497094029157, "learning_rate": 6.747279315890953e-06, "loss": 0.4845, "num_tokens": 492509851.0, "step": 82490 }, { "epoch": 0.8801062592683473, "grad_norm": 1.4750130462946196, "learning_rate": 6.745746105017235e-06, "loss": 0.4574, "num_tokens": 492528484.0, "step": 82495 }, { "epoch": 0.8801596022745458, "grad_norm": 0.7357760188380094, "learning_rate": 6.744213539973267e-06, "loss": 0.3376, "num_tokens": 492548575.0, "step": 82500 }, { "epoch": 0.8802129452807442, "grad_norm": 0.9522034510054642, "learning_rate": 6.7426816208067375e-06, "loss": 0.4616, "num_tokens": 492579843.0, "step": 82505 }, { "epoch": 0.8802662882869426, "grad_norm": 0.9602148650036886, "learning_rate": 6.741150347565319e-06, "loss": 0.3955, "num_tokens": 492615071.0, "step": 82510 }, { "epoch": 0.8803196312931412, "grad_norm": 0.6657705330504836, "learning_rate": 6.739619720296664e-06, "loss": 0.5836, "num_tokens": 492654537.0, "step": 82515 }, { "epoch": 0.8803729742993396, "grad_norm": 1.2772771541043584, "learning_rate": 6.738089739048395e-06, "loss": 0.4968, "num_tokens": 492681620.0, "step": 82520 }, { "epoch": 0.8804263173055381, "grad_norm": 0.8231615559041437, "learning_rate": 6.7365604038681305e-06, "loss": 0.4858, "num_tokens": 492712943.0, "step": 82525 }, { "epoch": 0.8804796603117365, "grad_norm": 0.8856959376480746, "learning_rate": 6.735031714803459e-06, "loss": 0.4859, "num_tokens": 492744772.0, "step": 82530 }, { "epoch": 0.8805330033179349, "grad_norm": 0.879782350538428, "learning_rate": 6.733503671901949e-06, "loss": 0.4519, "num_tokens": 492767705.0, "step": 82535 }, { "epoch": 0.8805863463241335, "grad_norm": 0.9269844668806125, "learning_rate": 6.7319762752111455e-06, "loss": 0.4649, "num_tokens": 492792789.0, "step": 82540 }, { "epoch": 0.8806396893303319, "grad_norm": 0.872888119001005, "learning_rate": 6.730449524778584e-06, "loss": 0.3999, "num_tokens": 492823994.0, "step": 82545 }, { "epoch": 0.8806930323365304, "grad_norm": 1.1863933851896789, "learning_rate": 6.72892342065177e-06, "loss": 0.4871, "num_tokens": 492845329.0, "step": 82550 }, { "epoch": 0.8807463753427288, "grad_norm": 0.7363141116050522, "learning_rate": 6.727397962878193e-06, "loss": 0.4492, "num_tokens": 492871285.0, "step": 82555 }, { "epoch": 0.8807997183489272, "grad_norm": 1.3394561452242877, "learning_rate": 6.725873151505327e-06, "loss": 0.4116, "num_tokens": 492893029.0, "step": 82560 }, { "epoch": 0.8808530613551258, "grad_norm": 0.9195751179823695, "learning_rate": 6.72434898658061e-06, "loss": 0.4249, "num_tokens": 492919657.0, "step": 82565 }, { "epoch": 0.8809064043613242, "grad_norm": 0.7153209121125592, "learning_rate": 6.722825468151487e-06, "loss": 0.4255, "num_tokens": 492948275.0, "step": 82570 }, { "epoch": 0.8809597473675227, "grad_norm": 0.9280621573355993, "learning_rate": 6.721302596265357e-06, "loss": 0.5282, "num_tokens": 492988400.0, "step": 82575 }, { "epoch": 0.8810130903737211, "grad_norm": 0.8841435521116425, "learning_rate": 6.719780370969603e-06, "loss": 0.7451, "num_tokens": 493023323.0, "step": 82580 }, { "epoch": 0.8810664333799195, "grad_norm": 1.0149496262207531, "learning_rate": 6.7182587923116015e-06, "loss": 0.5973, "num_tokens": 493058230.0, "step": 82585 }, { "epoch": 0.881119776386118, "grad_norm": 2.2896816276231293, "learning_rate": 6.716737860338702e-06, "loss": 0.5027, "num_tokens": 493096137.0, "step": 82590 }, { "epoch": 0.8811731193923165, "grad_norm": 1.0717892354043523, "learning_rate": 6.71521757509823e-06, "loss": 0.4089, "num_tokens": 493125631.0, "step": 82595 }, { "epoch": 0.8812264623985149, "grad_norm": 1.0036553210988142, "learning_rate": 6.7136979366374905e-06, "loss": 0.3316, "num_tokens": 493149986.0, "step": 82600 }, { "epoch": 0.8812798054047134, "grad_norm": 0.7865774340216466, "learning_rate": 6.71217894500378e-06, "loss": 0.4621, "num_tokens": 493186707.0, "step": 82605 }, { "epoch": 0.8813331484109118, "grad_norm": 1.381063501753453, "learning_rate": 6.710660600244364e-06, "loss": 0.4652, "num_tokens": 493218328.0, "step": 82610 }, { "epoch": 0.8813864914171103, "grad_norm": 0.8712596551521329, "learning_rate": 6.709142902406479e-06, "loss": 0.5215, "num_tokens": 493250992.0, "step": 82615 }, { "epoch": 0.8814398344233088, "grad_norm": 0.6187381491938266, "learning_rate": 6.707625851537368e-06, "loss": 0.4654, "num_tokens": 493289265.0, "step": 82620 }, { "epoch": 0.8814931774295072, "grad_norm": 0.8000487188436982, "learning_rate": 6.7061094476842266e-06, "loss": 0.5388, "num_tokens": 493335013.0, "step": 82625 }, { "epoch": 0.8815465204357057, "grad_norm": 0.7864542941854695, "learning_rate": 6.704593690894249e-06, "loss": 0.533, "num_tokens": 493361232.0, "step": 82630 }, { "epoch": 0.8815998634419041, "grad_norm": 0.7236514209177414, "learning_rate": 6.703078581214601e-06, "loss": 0.4358, "num_tokens": 493409439.0, "step": 82635 }, { "epoch": 0.8816532064481026, "grad_norm": 1.362085567200013, "learning_rate": 6.70156411869243e-06, "loss": 0.4011, "num_tokens": 493439750.0, "step": 82640 }, { "epoch": 0.881706549454301, "grad_norm": 1.0883457968808874, "learning_rate": 6.700050303374865e-06, "loss": 0.4304, "num_tokens": 493474597.0, "step": 82645 }, { "epoch": 0.8817598924604995, "grad_norm": 0.8594072722404944, "learning_rate": 6.69853713530901e-06, "loss": 0.4797, "num_tokens": 493505160.0, "step": 82650 }, { "epoch": 0.881813235466698, "grad_norm": 0.6979248993589408, "learning_rate": 6.697024614541947e-06, "loss": 0.4624, "num_tokens": 493544107.0, "step": 82655 }, { "epoch": 0.8818665784728964, "grad_norm": 0.7781475594386652, "learning_rate": 6.695512741120748e-06, "loss": 0.3629, "num_tokens": 493577417.0, "step": 82660 }, { "epoch": 0.8819199214790949, "grad_norm": 0.827112659259728, "learning_rate": 6.6940015150924616e-06, "loss": 0.4164, "num_tokens": 493601480.0, "step": 82665 }, { "epoch": 0.8819732644852933, "grad_norm": 0.634523120992155, "learning_rate": 6.692490936504109e-06, "loss": 0.4567, "num_tokens": 493641540.0, "step": 82670 }, { "epoch": 0.8820266074914918, "grad_norm": 0.8813986795911067, "learning_rate": 6.690981005402698e-06, "loss": 0.456, "num_tokens": 493670880.0, "step": 82675 }, { "epoch": 0.8820799504976903, "grad_norm": 1.234934408399738, "learning_rate": 6.6894717218352205e-06, "loss": 0.3755, "num_tokens": 493686809.0, "step": 82680 }, { "epoch": 0.8821332935038887, "grad_norm": 1.2343294302042096, "learning_rate": 6.687963085848635e-06, "loss": 0.4422, "num_tokens": 493706695.0, "step": 82685 }, { "epoch": 0.8821866365100871, "grad_norm": 0.7904786207608545, "learning_rate": 6.686455097489885e-06, "loss": 0.3434, "num_tokens": 493728325.0, "step": 82690 }, { "epoch": 0.8822399795162856, "grad_norm": 0.6480228616744098, "learning_rate": 6.6849477568059054e-06, "loss": 0.4409, "num_tokens": 493752892.0, "step": 82695 }, { "epoch": 0.882293322522484, "grad_norm": 0.6645817028762627, "learning_rate": 6.683441063843593e-06, "loss": 0.3246, "num_tokens": 493780267.0, "step": 82700 }, { "epoch": 0.8823466655286826, "grad_norm": 0.6663104789908192, "learning_rate": 6.6819350186498345e-06, "loss": 0.5376, "num_tokens": 493829365.0, "step": 82705 }, { "epoch": 0.882400008534881, "grad_norm": 0.7909901333593007, "learning_rate": 6.680429621271501e-06, "loss": 0.4493, "num_tokens": 493860134.0, "step": 82710 }, { "epoch": 0.8824533515410794, "grad_norm": 0.8909797785281508, "learning_rate": 6.678924871755434e-06, "loss": 0.402, "num_tokens": 493903245.0, "step": 82715 }, { "epoch": 0.8825066945472779, "grad_norm": 0.8554802750258613, "learning_rate": 6.677420770148451e-06, "loss": 0.4199, "num_tokens": 493938106.0, "step": 82720 }, { "epoch": 0.8825600375534763, "grad_norm": 1.4183348644829006, "learning_rate": 6.67591731649737e-06, "loss": 0.5887, "num_tokens": 493967926.0, "step": 82725 }, { "epoch": 0.8826133805596749, "grad_norm": 1.1069997525852566, "learning_rate": 6.6744145108489645e-06, "loss": 0.504, "num_tokens": 493982601.0, "step": 82730 }, { "epoch": 0.8826667235658733, "grad_norm": 0.8088107859636707, "learning_rate": 6.6729123532499996e-06, "loss": 0.4106, "num_tokens": 494015939.0, "step": 82735 }, { "epoch": 0.8827200665720717, "grad_norm": 1.2815228326441335, "learning_rate": 6.671410843747226e-06, "loss": 0.4747, "num_tokens": 494042466.0, "step": 82740 }, { "epoch": 0.8827734095782702, "grad_norm": 0.9960582584833905, "learning_rate": 6.669909982387361e-06, "loss": 0.4793, "num_tokens": 494087625.0, "step": 82745 }, { "epoch": 0.8828267525844686, "grad_norm": 1.028374461544207, "learning_rate": 6.668409769217117e-06, "loss": 0.4534, "num_tokens": 494107071.0, "step": 82750 }, { "epoch": 0.8828800955906672, "grad_norm": 0.9787487837362799, "learning_rate": 6.666910204283168e-06, "loss": 0.5032, "num_tokens": 494128587.0, "step": 82755 }, { "epoch": 0.8829334385968656, "grad_norm": 0.9850629511156132, "learning_rate": 6.665411287632181e-06, "loss": 0.4923, "num_tokens": 494160752.0, "step": 82760 }, { "epoch": 0.882986781603064, "grad_norm": 0.9795590443501635, "learning_rate": 6.6639130193107965e-06, "loss": 0.5367, "num_tokens": 494195878.0, "step": 82765 }, { "epoch": 0.8830401246092625, "grad_norm": 1.2704222965860568, "learning_rate": 6.662415399365646e-06, "loss": 0.5813, "num_tokens": 494237046.0, "step": 82770 }, { "epoch": 0.8830934676154609, "grad_norm": 0.9853690857955547, "learning_rate": 6.660918427843321e-06, "loss": 0.5136, "num_tokens": 494287225.0, "step": 82775 }, { "epoch": 0.8831468106216593, "grad_norm": 0.9179349231068329, "learning_rate": 6.659422104790411e-06, "loss": 0.5357, "num_tokens": 494325580.0, "step": 82780 }, { "epoch": 0.8832001536278579, "grad_norm": 1.5056516038911667, "learning_rate": 6.6579264302534795e-06, "loss": 0.5189, "num_tokens": 494351173.0, "step": 82785 }, { "epoch": 0.8832534966340563, "grad_norm": 0.8055438510934565, "learning_rate": 6.656431404279068e-06, "loss": 0.5389, "num_tokens": 494369577.0, "step": 82790 }, { "epoch": 0.8833068396402548, "grad_norm": 0.6510003843139444, "learning_rate": 6.6549370269136935e-06, "loss": 0.3972, "num_tokens": 494396937.0, "step": 82795 }, { "epoch": 0.8833601826464532, "grad_norm": 1.0016366814677264, "learning_rate": 6.6534432982038654e-06, "loss": 0.5646, "num_tokens": 494428864.0, "step": 82800 }, { "epoch": 0.8834135256526516, "grad_norm": 0.908297932839341, "learning_rate": 6.651950218196058e-06, "loss": 0.4124, "num_tokens": 494448747.0, "step": 82805 }, { "epoch": 0.8834668686588502, "grad_norm": 0.688061467656703, "learning_rate": 6.650457786936737e-06, "loss": 0.4127, "num_tokens": 494471919.0, "step": 82810 }, { "epoch": 0.8835202116650486, "grad_norm": 0.7393088021676267, "learning_rate": 6.648966004472347e-06, "loss": 0.4565, "num_tokens": 494505448.0, "step": 82815 }, { "epoch": 0.8835735546712471, "grad_norm": 1.0381392149661048, "learning_rate": 6.647474870849302e-06, "loss": 0.4712, "num_tokens": 494541151.0, "step": 82820 }, { "epoch": 0.8836268976774455, "grad_norm": 2.3396048407057948, "learning_rate": 6.645984386114011e-06, "loss": 0.5527, "num_tokens": 494579073.0, "step": 82825 }, { "epoch": 0.8836802406836439, "grad_norm": 1.1320431990072102, "learning_rate": 6.6444945503128495e-06, "loss": 0.5939, "num_tokens": 494614401.0, "step": 82830 }, { "epoch": 0.8837335836898425, "grad_norm": 0.7287518593312136, "learning_rate": 6.643005363492176e-06, "loss": 0.4521, "num_tokens": 494647551.0, "step": 82835 }, { "epoch": 0.8837869266960409, "grad_norm": 0.9055118459261826, "learning_rate": 6.641516825698332e-06, "loss": 0.5141, "num_tokens": 494675033.0, "step": 82840 }, { "epoch": 0.8838402697022394, "grad_norm": 0.8600923823093973, "learning_rate": 6.640028936977648e-06, "loss": 0.4967, "num_tokens": 494727908.0, "step": 82845 }, { "epoch": 0.8838936127084378, "grad_norm": 1.0054822580552858, "learning_rate": 6.638541697376408e-06, "loss": 0.3105, "num_tokens": 494743752.0, "step": 82850 }, { "epoch": 0.8839469557146362, "grad_norm": 0.7544736420092388, "learning_rate": 6.637055106940901e-06, "loss": 0.5078, "num_tokens": 494786897.0, "step": 82855 }, { "epoch": 0.8840002987208347, "grad_norm": 1.1112520015900116, "learning_rate": 6.63556916571739e-06, "loss": 0.4015, "num_tokens": 494835304.0, "step": 82860 }, { "epoch": 0.8840536417270332, "grad_norm": 1.0708747320927634, "learning_rate": 6.63408387375211e-06, "loss": 0.5061, "num_tokens": 494873439.0, "step": 82865 }, { "epoch": 0.8841069847332316, "grad_norm": 1.045219430485559, "learning_rate": 6.632599231091273e-06, "loss": 0.5736, "num_tokens": 494911369.0, "step": 82870 }, { "epoch": 0.8841603277394301, "grad_norm": 0.6022481444776233, "learning_rate": 6.631115237781092e-06, "loss": 0.432, "num_tokens": 494953694.0, "step": 82875 }, { "epoch": 0.8842136707456285, "grad_norm": 1.1834182174765386, "learning_rate": 6.629631893867734e-06, "loss": 0.5267, "num_tokens": 494980675.0, "step": 82880 }, { "epoch": 0.884267013751827, "grad_norm": 1.8294938332200716, "learning_rate": 6.628149199397364e-06, "loss": 0.3981, "num_tokens": 494999945.0, "step": 82885 }, { "epoch": 0.8843203567580254, "grad_norm": 1.4350997822931981, "learning_rate": 6.626667154416121e-06, "loss": 0.5508, "num_tokens": 495024121.0, "step": 82890 }, { "epoch": 0.8843736997642239, "grad_norm": 0.6731081141149385, "learning_rate": 6.625185758970118e-06, "loss": 0.4412, "num_tokens": 495068796.0, "step": 82895 }, { "epoch": 0.8844270427704224, "grad_norm": 0.7248196579265256, "learning_rate": 6.623705013105459e-06, "loss": 0.4542, "num_tokens": 495110568.0, "step": 82900 }, { "epoch": 0.8844803857766208, "grad_norm": 0.5827584146216459, "learning_rate": 6.622224916868221e-06, "loss": 0.4907, "num_tokens": 495151551.0, "step": 82905 }, { "epoch": 0.8845337287828193, "grad_norm": 0.7260073588013719, "learning_rate": 6.620745470304454e-06, "loss": 0.4159, "num_tokens": 495188329.0, "step": 82910 }, { "epoch": 0.8845870717890177, "grad_norm": 1.203277149708594, "learning_rate": 6.6192666734602015e-06, "loss": 0.43, "num_tokens": 495208122.0, "step": 82915 }, { "epoch": 0.8846404147952162, "grad_norm": 0.6844862134631124, "learning_rate": 6.617788526381483e-06, "loss": 0.4482, "num_tokens": 495243350.0, "step": 82920 }, { "epoch": 0.8846937578014147, "grad_norm": 1.1599253862264474, "learning_rate": 6.616311029114287e-06, "loss": 0.5466, "num_tokens": 495265239.0, "step": 82925 }, { "epoch": 0.8847471008076131, "grad_norm": 0.6278419469752254, "learning_rate": 6.6148341817045976e-06, "loss": 0.3481, "num_tokens": 495291848.0, "step": 82930 }, { "epoch": 0.8848004438138116, "grad_norm": 1.0162506064286168, "learning_rate": 6.6133579841983735e-06, "loss": 0.4769, "num_tokens": 495325732.0, "step": 82935 }, { "epoch": 0.88485378682001, "grad_norm": 0.8878560131779564, "learning_rate": 6.611882436641543e-06, "loss": 0.4319, "num_tokens": 495349481.0, "step": 82940 }, { "epoch": 0.8849071298262084, "grad_norm": 0.7968825393932166, "learning_rate": 6.610407539080027e-06, "loss": 0.5552, "num_tokens": 495383245.0, "step": 82945 }, { "epoch": 0.884960472832407, "grad_norm": 3.932667334695763, "learning_rate": 6.608933291559721e-06, "loss": 0.4806, "num_tokens": 495412917.0, "step": 82950 }, { "epoch": 0.8850138158386054, "grad_norm": 0.9140432611476963, "learning_rate": 6.607459694126497e-06, "loss": 0.3064, "num_tokens": 495429376.0, "step": 82955 }, { "epoch": 0.8850671588448038, "grad_norm": 0.7674707465350545, "learning_rate": 6.605986746826209e-06, "loss": 0.4432, "num_tokens": 495464460.0, "step": 82960 }, { "epoch": 0.8851205018510023, "grad_norm": 1.9168672356265846, "learning_rate": 6.604514449704703e-06, "loss": 0.4819, "num_tokens": 495496007.0, "step": 82965 }, { "epoch": 0.8851738448572007, "grad_norm": 1.135050993761547, "learning_rate": 6.603042802807781e-06, "loss": 0.4033, "num_tokens": 495517819.0, "step": 82970 }, { "epoch": 0.8852271878633993, "grad_norm": 1.6602510201565368, "learning_rate": 6.601571806181249e-06, "loss": 0.3938, "num_tokens": 495535028.0, "step": 82975 }, { "epoch": 0.8852805308695977, "grad_norm": 0.612753325135655, "learning_rate": 6.600101459870876e-06, "loss": 0.4777, "num_tokens": 495571593.0, "step": 82980 }, { "epoch": 0.8853338738757961, "grad_norm": 1.1264446637231544, "learning_rate": 6.598631763922411e-06, "loss": 0.4414, "num_tokens": 495595895.0, "step": 82985 }, { "epoch": 0.8853872168819946, "grad_norm": 1.4566646524275928, "learning_rate": 6.597162718381593e-06, "loss": 0.4975, "num_tokens": 495615581.0, "step": 82990 }, { "epoch": 0.885440559888193, "grad_norm": 0.7636769875277025, "learning_rate": 6.59569432329414e-06, "loss": 0.4177, "num_tokens": 495642391.0, "step": 82995 }, { "epoch": 0.8854939028943916, "grad_norm": 0.9839799290447555, "learning_rate": 6.594226578705737e-06, "loss": 0.4157, "num_tokens": 495656504.0, "step": 83000 }, { "epoch": 0.88554724590059, "grad_norm": 0.8899135115258374, "learning_rate": 6.592759484662062e-06, "loss": 0.4306, "num_tokens": 495696208.0, "step": 83005 }, { "epoch": 0.8856005889067884, "grad_norm": 1.0116204485400457, "learning_rate": 6.591293041208768e-06, "loss": 0.4929, "num_tokens": 495730363.0, "step": 83010 }, { "epoch": 0.8856539319129869, "grad_norm": 0.6676717944737776, "learning_rate": 6.589827248391489e-06, "loss": 0.5055, "num_tokens": 495787051.0, "step": 83015 }, { "epoch": 0.8857072749191853, "grad_norm": 0.8035205890106939, "learning_rate": 6.588362106255833e-06, "loss": 0.4005, "num_tokens": 495829342.0, "step": 83020 }, { "epoch": 0.8857606179253839, "grad_norm": 0.5589540263840828, "learning_rate": 6.586897614847395e-06, "loss": 0.4044, "num_tokens": 495865635.0, "step": 83025 }, { "epoch": 0.8858139609315823, "grad_norm": 0.5684319128242538, "learning_rate": 6.585433774211745e-06, "loss": 0.4603, "num_tokens": 495906273.0, "step": 83030 }, { "epoch": 0.8858673039377807, "grad_norm": 0.8721287091361838, "learning_rate": 6.5839705843944344e-06, "loss": 0.4515, "num_tokens": 495933591.0, "step": 83035 }, { "epoch": 0.8859206469439792, "grad_norm": 0.9046030916114297, "learning_rate": 6.582508045441002e-06, "loss": 0.3708, "num_tokens": 495957666.0, "step": 83040 }, { "epoch": 0.8859739899501776, "grad_norm": 0.8245667207117253, "learning_rate": 6.581046157396952e-06, "loss": 0.4097, "num_tokens": 495991698.0, "step": 83045 }, { "epoch": 0.886027332956376, "grad_norm": 1.0795165542688703, "learning_rate": 6.5795849203077745e-06, "loss": 0.4704, "num_tokens": 496006559.0, "step": 83050 }, { "epoch": 0.8860806759625746, "grad_norm": 0.8540983490130154, "learning_rate": 6.578124334218945e-06, "loss": 0.4808, "num_tokens": 496034145.0, "step": 83055 }, { "epoch": 0.886134018968773, "grad_norm": 0.9247240069654036, "learning_rate": 6.576664399175907e-06, "loss": 0.4619, "num_tokens": 496076095.0, "step": 83060 }, { "epoch": 0.8861873619749715, "grad_norm": 1.0555061048324157, "learning_rate": 6.575205115224098e-06, "loss": 0.4556, "num_tokens": 496102329.0, "step": 83065 }, { "epoch": 0.8862407049811699, "grad_norm": 1.0539333069919157, "learning_rate": 6.573746482408922e-06, "loss": 0.4051, "num_tokens": 496134048.0, "step": 83070 }, { "epoch": 0.8862940479873683, "grad_norm": 0.7919128147063217, "learning_rate": 6.57228850077578e-06, "loss": 0.454, "num_tokens": 496163292.0, "step": 83075 }, { "epoch": 0.8863473909935669, "grad_norm": 1.1169463707202143, "learning_rate": 6.570831170370027e-06, "loss": 0.4278, "num_tokens": 496189539.0, "step": 83080 }, { "epoch": 0.8864007339997653, "grad_norm": 0.5830490689703359, "learning_rate": 6.5693744912370185e-06, "loss": 0.4676, "num_tokens": 496229816.0, "step": 83085 }, { "epoch": 0.8864540770059638, "grad_norm": 0.9870285142592298, "learning_rate": 6.5679184634220875e-06, "loss": 0.4866, "num_tokens": 496248221.0, "step": 83090 }, { "epoch": 0.8865074200121622, "grad_norm": 0.7724964131925544, "learning_rate": 6.566463086970531e-06, "loss": 0.5749, "num_tokens": 496262285.0, "step": 83095 }, { "epoch": 0.8865607630183606, "grad_norm": 0.8986913755420143, "learning_rate": 6.565008361927647e-06, "loss": 0.4309, "num_tokens": 496298592.0, "step": 83100 }, { "epoch": 0.8866141060245591, "grad_norm": 0.690369361944866, "learning_rate": 6.563554288338704e-06, "loss": 0.4358, "num_tokens": 496331138.0, "step": 83105 }, { "epoch": 0.8866674490307576, "grad_norm": 0.7224314582754895, "learning_rate": 6.562100866248942e-06, "loss": 0.4699, "num_tokens": 496375930.0, "step": 83110 }, { "epoch": 0.8867207920369561, "grad_norm": 1.3045652228768736, "learning_rate": 6.560648095703601e-06, "loss": 0.4847, "num_tokens": 496401736.0, "step": 83115 }, { "epoch": 0.8867741350431545, "grad_norm": 0.5892652650215474, "learning_rate": 6.559195976747877e-06, "loss": 0.4803, "num_tokens": 496446563.0, "step": 83120 }, { "epoch": 0.8868274780493529, "grad_norm": 0.7366079772844492, "learning_rate": 6.557744509426958e-06, "loss": 0.4404, "num_tokens": 496478049.0, "step": 83125 }, { "epoch": 0.8868808210555514, "grad_norm": 0.6489518880637735, "learning_rate": 6.556293693786011e-06, "loss": 0.3685, "num_tokens": 496512390.0, "step": 83130 }, { "epoch": 0.8869341640617499, "grad_norm": 0.6374326356290642, "learning_rate": 6.55484352987019e-06, "loss": 0.3759, "num_tokens": 496538028.0, "step": 83135 }, { "epoch": 0.8869875070679483, "grad_norm": 1.3835357929951633, "learning_rate": 6.5533940177246126e-06, "loss": 0.4503, "num_tokens": 496556888.0, "step": 83140 }, { "epoch": 0.8870408500741468, "grad_norm": 1.272988546863886, "learning_rate": 6.551945157394389e-06, "loss": 0.4569, "num_tokens": 496595318.0, "step": 83145 }, { "epoch": 0.8870941930803452, "grad_norm": 0.9685998894869525, "learning_rate": 6.550496948924606e-06, "loss": 0.5279, "num_tokens": 496621771.0, "step": 83150 }, { "epoch": 0.8871475360865437, "grad_norm": 1.2199715704016234, "learning_rate": 6.549049392360326e-06, "loss": 0.4972, "num_tokens": 496659408.0, "step": 83155 }, { "epoch": 0.8872008790927421, "grad_norm": 0.8722165551122651, "learning_rate": 6.547602487746592e-06, "loss": 0.4639, "num_tokens": 496696632.0, "step": 83160 }, { "epoch": 0.8872542220989406, "grad_norm": 0.6083554929121954, "learning_rate": 6.546156235128434e-06, "loss": 0.5195, "num_tokens": 496733558.0, "step": 83165 }, { "epoch": 0.8873075651051391, "grad_norm": 1.1096546982081377, "learning_rate": 6.544710634550848e-06, "loss": 0.5277, "num_tokens": 496754576.0, "step": 83170 }, { "epoch": 0.8873609081113375, "grad_norm": 1.065465378900807, "learning_rate": 6.543265686058826e-06, "loss": 0.482, "num_tokens": 496780618.0, "step": 83175 }, { "epoch": 0.887414251117536, "grad_norm": 1.0738383920294556, "learning_rate": 6.541821389697332e-06, "loss": 0.4554, "num_tokens": 496810545.0, "step": 83180 }, { "epoch": 0.8874675941237344, "grad_norm": 0.905794051033201, "learning_rate": 6.540377745511306e-06, "loss": 0.4914, "num_tokens": 496831187.0, "step": 83185 }, { "epoch": 0.8875209371299329, "grad_norm": 0.655048081993545, "learning_rate": 6.538934753545671e-06, "loss": 0.3538, "num_tokens": 496859574.0, "step": 83190 }, { "epoch": 0.8875742801361314, "grad_norm": 1.1995489404579665, "learning_rate": 6.537492413845336e-06, "loss": 0.5052, "num_tokens": 496883747.0, "step": 83195 }, { "epoch": 0.8876276231423298, "grad_norm": 1.1819367108093128, "learning_rate": 6.536050726455173e-06, "loss": 0.4116, "num_tokens": 496905674.0, "step": 83200 }, { "epoch": 0.8876809661485283, "grad_norm": 1.0034020148409541, "learning_rate": 6.534609691420052e-06, "loss": 0.4333, "num_tokens": 496938935.0, "step": 83205 }, { "epoch": 0.8877343091547267, "grad_norm": 0.7473445502107781, "learning_rate": 6.533169308784813e-06, "loss": 0.4158, "num_tokens": 496964686.0, "step": 83210 }, { "epoch": 0.8877876521609251, "grad_norm": 0.8029434313729074, "learning_rate": 6.531729578594277e-06, "loss": 0.5033, "num_tokens": 497017048.0, "step": 83215 }, { "epoch": 0.8878409951671237, "grad_norm": 4.325881041029927, "learning_rate": 6.530290500893248e-06, "loss": 0.6721, "num_tokens": 497039037.0, "step": 83220 }, { "epoch": 0.8878943381733221, "grad_norm": 1.1505960585732984, "learning_rate": 6.528852075726508e-06, "loss": 0.3791, "num_tokens": 497062139.0, "step": 83225 }, { "epoch": 0.8879476811795205, "grad_norm": 0.8018517914069041, "learning_rate": 6.527414303138814e-06, "loss": 0.4389, "num_tokens": 497093373.0, "step": 83230 }, { "epoch": 0.888001024185719, "grad_norm": 0.669263212662838, "learning_rate": 6.5259771831749045e-06, "loss": 0.4232, "num_tokens": 497122818.0, "step": 83235 }, { "epoch": 0.8880543671919174, "grad_norm": 0.7690768599507667, "learning_rate": 6.5245407158795086e-06, "loss": 0.432, "num_tokens": 497149050.0, "step": 83240 }, { "epoch": 0.888107710198116, "grad_norm": 0.6732830375496617, "learning_rate": 6.5231049012973155e-06, "loss": 0.3715, "num_tokens": 497183637.0, "step": 83245 }, { "epoch": 0.8881610532043144, "grad_norm": 0.8989007987384464, "learning_rate": 6.5216697394730105e-06, "loss": 0.3985, "num_tokens": 497203843.0, "step": 83250 }, { "epoch": 0.8882143962105128, "grad_norm": 0.857646362469473, "learning_rate": 6.520235230451256e-06, "loss": 0.464, "num_tokens": 497230560.0, "step": 83255 }, { "epoch": 0.8882677392167113, "grad_norm": 1.2027632300946767, "learning_rate": 6.5188013742766844e-06, "loss": 0.3356, "num_tokens": 497244752.0, "step": 83260 }, { "epoch": 0.8883210822229097, "grad_norm": 0.955412572939976, "learning_rate": 6.51736817099392e-06, "loss": 0.5407, "num_tokens": 497274798.0, "step": 83265 }, { "epoch": 0.8883744252291083, "grad_norm": 0.8407690126014041, "learning_rate": 6.515935620647561e-06, "loss": 0.4396, "num_tokens": 497319303.0, "step": 83270 }, { "epoch": 0.8884277682353067, "grad_norm": 3.080465165480232, "learning_rate": 6.514503723282176e-06, "loss": 0.5464, "num_tokens": 497351658.0, "step": 83275 }, { "epoch": 0.8884811112415051, "grad_norm": 1.194907703403335, "learning_rate": 6.513072478942331e-06, "loss": 0.5633, "num_tokens": 497373983.0, "step": 83280 }, { "epoch": 0.8885344542477036, "grad_norm": 1.0631876482006897, "learning_rate": 6.511641887672567e-06, "loss": 0.4951, "num_tokens": 497400703.0, "step": 83285 }, { "epoch": 0.888587797253902, "grad_norm": 0.9394665987345951, "learning_rate": 6.510211949517393e-06, "loss": 0.5537, "num_tokens": 497429188.0, "step": 83290 }, { "epoch": 0.8886411402601005, "grad_norm": 0.7866203349867967, "learning_rate": 6.508782664521306e-06, "loss": 0.4529, "num_tokens": 497462461.0, "step": 83295 }, { "epoch": 0.888694483266299, "grad_norm": 0.49256095444812015, "learning_rate": 6.5073540327287895e-06, "loss": 0.5083, "num_tokens": 497513254.0, "step": 83300 }, { "epoch": 0.8887478262724974, "grad_norm": 0.8788771054659601, "learning_rate": 6.505926054184297e-06, "loss": 0.425, "num_tokens": 497542741.0, "step": 83305 }, { "epoch": 0.8888011692786959, "grad_norm": 1.9027293941841361, "learning_rate": 6.504498728932258e-06, "loss": 0.5838, "num_tokens": 497568411.0, "step": 83310 }, { "epoch": 0.8888545122848943, "grad_norm": 0.6818075727274141, "learning_rate": 6.5030720570170984e-06, "loss": 0.4816, "num_tokens": 497590749.0, "step": 83315 }, { "epoch": 0.8889078552910927, "grad_norm": 1.2488289792528842, "learning_rate": 6.501646038483202e-06, "loss": 0.5058, "num_tokens": 497628077.0, "step": 83320 }, { "epoch": 0.8889611982972913, "grad_norm": 0.7880398428923304, "learning_rate": 6.500220673374948e-06, "loss": 0.4798, "num_tokens": 497669247.0, "step": 83325 }, { "epoch": 0.8890145413034897, "grad_norm": 2.5304556133266436, "learning_rate": 6.498795961736696e-06, "loss": 0.508, "num_tokens": 497692696.0, "step": 83330 }, { "epoch": 0.8890678843096882, "grad_norm": 0.9632109721878851, "learning_rate": 6.497371903612777e-06, "loss": 0.4522, "num_tokens": 497719805.0, "step": 83335 }, { "epoch": 0.8891212273158866, "grad_norm": 0.8386368644406198, "learning_rate": 6.4959484990475e-06, "loss": 0.3853, "num_tokens": 497750303.0, "step": 83340 }, { "epoch": 0.889174570322085, "grad_norm": 0.8135247557984817, "learning_rate": 6.494525748085163e-06, "loss": 0.4699, "num_tokens": 497781334.0, "step": 83345 }, { "epoch": 0.8892279133282835, "grad_norm": 1.2103783805224193, "learning_rate": 6.4931036507700385e-06, "loss": 0.5774, "num_tokens": 497815238.0, "step": 83350 }, { "epoch": 0.889281256334482, "grad_norm": 0.8556304907939756, "learning_rate": 6.491682207146375e-06, "loss": 0.6032, "num_tokens": 497841641.0, "step": 83355 }, { "epoch": 0.8893345993406805, "grad_norm": 0.7252494575900942, "learning_rate": 6.490261417258417e-06, "loss": 0.4806, "num_tokens": 497871508.0, "step": 83360 }, { "epoch": 0.8893879423468789, "grad_norm": 0.6981655845229657, "learning_rate": 6.4888412811503625e-06, "loss": 0.3678, "num_tokens": 497900450.0, "step": 83365 }, { "epoch": 0.8894412853530773, "grad_norm": 0.8133157202259502, "learning_rate": 6.487421798866413e-06, "loss": 0.5116, "num_tokens": 497945437.0, "step": 83370 }, { "epoch": 0.8894946283592758, "grad_norm": 0.7770471483133163, "learning_rate": 6.486002970450736e-06, "loss": 0.3827, "num_tokens": 497966348.0, "step": 83375 }, { "epoch": 0.8895479713654743, "grad_norm": 1.7348322094358835, "learning_rate": 6.484584795947479e-06, "loss": 0.4591, "num_tokens": 497988414.0, "step": 83380 }, { "epoch": 0.8896013143716728, "grad_norm": 0.81025207325636, "learning_rate": 6.4831672754007745e-06, "loss": 0.4623, "num_tokens": 498019902.0, "step": 83385 }, { "epoch": 0.8896546573778712, "grad_norm": 0.623101299893665, "learning_rate": 6.481750408854741e-06, "loss": 0.4085, "num_tokens": 498053206.0, "step": 83390 }, { "epoch": 0.8897080003840696, "grad_norm": 0.9405489620955335, "learning_rate": 6.480334196353457e-06, "loss": 0.493, "num_tokens": 498084586.0, "step": 83395 }, { "epoch": 0.8897613433902681, "grad_norm": 0.560527747219448, "learning_rate": 6.478918637940997e-06, "loss": 0.6233, "num_tokens": 498120181.0, "step": 83400 }, { "epoch": 0.8898146863964665, "grad_norm": 0.7771095522849188, "learning_rate": 6.477503733661415e-06, "loss": 0.4685, "num_tokens": 498152586.0, "step": 83405 }, { "epoch": 0.889868029402665, "grad_norm": 1.0128159566622306, "learning_rate": 6.476089483558735e-06, "loss": 0.3561, "num_tokens": 498179615.0, "step": 83410 }, { "epoch": 0.8899213724088635, "grad_norm": 0.5818847599105018, "learning_rate": 6.4746758876769635e-06, "loss": 0.3876, "num_tokens": 498218967.0, "step": 83415 }, { "epoch": 0.8899747154150619, "grad_norm": 1.1574439189253165, "learning_rate": 6.473262946060093e-06, "loss": 0.4618, "num_tokens": 498242230.0, "step": 83420 }, { "epoch": 0.8900280584212604, "grad_norm": 1.0633616396341223, "learning_rate": 6.471850658752087e-06, "loss": 0.5423, "num_tokens": 498289611.0, "step": 83425 }, { "epoch": 0.8900814014274588, "grad_norm": 0.6661754296763374, "learning_rate": 6.470439025796896e-06, "loss": 0.402, "num_tokens": 498324482.0, "step": 83430 }, { "epoch": 0.8901347444336573, "grad_norm": 0.8063153886463101, "learning_rate": 6.469028047238446e-06, "loss": 0.4356, "num_tokens": 498356832.0, "step": 83435 }, { "epoch": 0.8901880874398558, "grad_norm": 0.9279669253587862, "learning_rate": 6.467617723120646e-06, "loss": 0.4725, "num_tokens": 498383608.0, "step": 83440 }, { "epoch": 0.8902414304460542, "grad_norm": 1.171081841296756, "learning_rate": 6.466208053487381e-06, "loss": 0.4464, "num_tokens": 498422413.0, "step": 83445 }, { "epoch": 0.8902947734522527, "grad_norm": 1.0569462477300118, "learning_rate": 6.464799038382519e-06, "loss": 0.4462, "num_tokens": 498445784.0, "step": 83450 }, { "epoch": 0.8903481164584511, "grad_norm": 0.9795718146176515, "learning_rate": 6.463390677849898e-06, "loss": 0.4837, "num_tokens": 498482096.0, "step": 83455 }, { "epoch": 0.8904014594646495, "grad_norm": 0.8277967667815298, "learning_rate": 6.4619829719333484e-06, "loss": 0.681, "num_tokens": 498528970.0, "step": 83460 }, { "epoch": 0.8904548024708481, "grad_norm": 1.3446299087162366, "learning_rate": 6.460575920676679e-06, "loss": 0.4342, "num_tokens": 498550752.0, "step": 83465 }, { "epoch": 0.8905081454770465, "grad_norm": 1.0375853450850403, "learning_rate": 6.45916952412367e-06, "loss": 0.4744, "num_tokens": 498568011.0, "step": 83470 }, { "epoch": 0.890561488483245, "grad_norm": 1.0582166336012526, "learning_rate": 6.457763782318082e-06, "loss": 0.3206, "num_tokens": 498597435.0, "step": 83475 }, { "epoch": 0.8906148314894434, "grad_norm": 0.585034365260072, "learning_rate": 6.456358695303672e-06, "loss": 0.4037, "num_tokens": 498626741.0, "step": 83480 }, { "epoch": 0.8906681744956418, "grad_norm": 0.6687986782842148, "learning_rate": 6.454954263124151e-06, "loss": 0.3962, "num_tokens": 498655950.0, "step": 83485 }, { "epoch": 0.8907215175018404, "grad_norm": 1.091966472854537, "learning_rate": 6.453550485823222e-06, "loss": 0.4393, "num_tokens": 498691614.0, "step": 83490 }, { "epoch": 0.8907748605080388, "grad_norm": 1.2534363219347655, "learning_rate": 6.452147363444574e-06, "loss": 0.4336, "num_tokens": 498712523.0, "step": 83495 }, { "epoch": 0.8908282035142372, "grad_norm": 0.6453791080098576, "learning_rate": 6.450744896031864e-06, "loss": 0.4233, "num_tokens": 498744900.0, "step": 83500 }, { "epoch": 0.8908815465204357, "grad_norm": 0.7235547681980601, "learning_rate": 6.449343083628738e-06, "loss": 0.3699, "num_tokens": 498784743.0, "step": 83505 }, { "epoch": 0.8909348895266341, "grad_norm": 0.7552635646492807, "learning_rate": 6.447941926278818e-06, "loss": 0.5751, "num_tokens": 498840001.0, "step": 83510 }, { "epoch": 0.8909882325328327, "grad_norm": 0.7545263977796683, "learning_rate": 6.446541424025699e-06, "loss": 0.4171, "num_tokens": 498860092.0, "step": 83515 }, { "epoch": 0.8910415755390311, "grad_norm": 0.5949570273583971, "learning_rate": 6.445141576912971e-06, "loss": 0.3559, "num_tokens": 498889766.0, "step": 83520 }, { "epoch": 0.8910949185452295, "grad_norm": 0.7248122045241696, "learning_rate": 6.443742384984189e-06, "loss": 0.4147, "num_tokens": 498947962.0, "step": 83525 }, { "epoch": 0.891148261551428, "grad_norm": 1.424731688025127, "learning_rate": 6.442343848282886e-06, "loss": 0.5032, "num_tokens": 498966507.0, "step": 83530 }, { "epoch": 0.8912016045576264, "grad_norm": 1.080594751956632, "learning_rate": 6.440945966852595e-06, "loss": 0.4722, "num_tokens": 498995446.0, "step": 83535 }, { "epoch": 0.891254947563825, "grad_norm": 0.7945830149768685, "learning_rate": 6.439548740736808e-06, "loss": 0.4224, "num_tokens": 499025201.0, "step": 83540 }, { "epoch": 0.8913082905700234, "grad_norm": 1.0801186132344738, "learning_rate": 6.438152169979002e-06, "loss": 0.3619, "num_tokens": 499049201.0, "step": 83545 }, { "epoch": 0.8913616335762218, "grad_norm": 0.6349821136284689, "learning_rate": 6.436756254622638e-06, "loss": 0.4369, "num_tokens": 499095444.0, "step": 83550 }, { "epoch": 0.8914149765824203, "grad_norm": 0.857681786831297, "learning_rate": 6.43536099471116e-06, "loss": 0.5264, "num_tokens": 499128693.0, "step": 83555 }, { "epoch": 0.8914683195886187, "grad_norm": 0.8004271270783878, "learning_rate": 6.433966390287977e-06, "loss": 0.3512, "num_tokens": 499151387.0, "step": 83560 }, { "epoch": 0.8915216625948172, "grad_norm": 0.8289288914879569, "learning_rate": 6.432572441396486e-06, "loss": 0.542, "num_tokens": 499184561.0, "step": 83565 }, { "epoch": 0.8915750056010157, "grad_norm": 1.512051921446642, "learning_rate": 6.431179148080073e-06, "loss": 0.3952, "num_tokens": 499206645.0, "step": 83570 }, { "epoch": 0.8916283486072141, "grad_norm": 0.7311469958775297, "learning_rate": 6.429786510382082e-06, "loss": 0.4708, "num_tokens": 499242293.0, "step": 83575 }, { "epoch": 0.8916816916134126, "grad_norm": 0.9182579382268208, "learning_rate": 6.428394528345856e-06, "loss": 0.5073, "num_tokens": 499286021.0, "step": 83580 }, { "epoch": 0.891735034619611, "grad_norm": 0.9945743127192362, "learning_rate": 6.4270032020147155e-06, "loss": 0.4246, "num_tokens": 499316036.0, "step": 83585 }, { "epoch": 0.8917883776258094, "grad_norm": 1.054774829464044, "learning_rate": 6.425612531431944e-06, "loss": 0.5444, "num_tokens": 499336760.0, "step": 83590 }, { "epoch": 0.891841720632008, "grad_norm": 0.810709153222891, "learning_rate": 6.424222516640828e-06, "loss": 0.5281, "num_tokens": 499372743.0, "step": 83595 }, { "epoch": 0.8918950636382064, "grad_norm": 1.0007634026211365, "learning_rate": 6.422833157684614e-06, "loss": 0.625, "num_tokens": 499403683.0, "step": 83600 }, { "epoch": 0.8919484066444049, "grad_norm": 0.6729305605073949, "learning_rate": 6.421444454606539e-06, "loss": 0.4, "num_tokens": 499437430.0, "step": 83605 }, { "epoch": 0.8920017496506033, "grad_norm": 0.6760818625037126, "learning_rate": 6.420056407449812e-06, "loss": 0.4147, "num_tokens": 499474256.0, "step": 83610 }, { "epoch": 0.8920550926568017, "grad_norm": 1.5061751901613483, "learning_rate": 6.418669016257635e-06, "loss": 0.4403, "num_tokens": 499503965.0, "step": 83615 }, { "epoch": 0.8921084356630002, "grad_norm": 0.7907602860562618, "learning_rate": 6.417282281073173e-06, "loss": 0.4595, "num_tokens": 499525802.0, "step": 83620 }, { "epoch": 0.8921617786691987, "grad_norm": 0.7769775938792248, "learning_rate": 6.415896201939582e-06, "loss": 0.4081, "num_tokens": 499549827.0, "step": 83625 }, { "epoch": 0.8922151216753972, "grad_norm": 1.2105281974038749, "learning_rate": 6.414510778899997e-06, "loss": 0.5826, "num_tokens": 499576826.0, "step": 83630 }, { "epoch": 0.8922684646815956, "grad_norm": 1.0410929753958613, "learning_rate": 6.4131260119975194e-06, "loss": 0.4815, "num_tokens": 499606225.0, "step": 83635 }, { "epoch": 0.892321807687794, "grad_norm": 0.5855914092428767, "learning_rate": 6.411741901275248e-06, "loss": 0.3341, "num_tokens": 499636546.0, "step": 83640 }, { "epoch": 0.8923751506939925, "grad_norm": 0.7085905928060916, "learning_rate": 6.410358446776256e-06, "loss": 0.4297, "num_tokens": 499679035.0, "step": 83645 }, { "epoch": 0.892428493700191, "grad_norm": 1.4169414446840851, "learning_rate": 6.408975648543585e-06, "loss": 0.5249, "num_tokens": 499698605.0, "step": 83650 }, { "epoch": 0.8924818367063895, "grad_norm": 0.9921970617353323, "learning_rate": 6.40759350662027e-06, "loss": 0.3956, "num_tokens": 499727150.0, "step": 83655 }, { "epoch": 0.8925351797125879, "grad_norm": 0.48581743845130043, "learning_rate": 6.406212021049324e-06, "loss": 0.4686, "num_tokens": 499771926.0, "step": 83660 }, { "epoch": 0.8925885227187863, "grad_norm": 0.760108745403659, "learning_rate": 6.4048311918737325e-06, "loss": 0.4849, "num_tokens": 499798429.0, "step": 83665 }, { "epoch": 0.8926418657249848, "grad_norm": 0.9186726548035877, "learning_rate": 6.40345101913646e-06, "loss": 0.4452, "num_tokens": 499826363.0, "step": 83670 }, { "epoch": 0.8926952087311832, "grad_norm": 0.8777911537512876, "learning_rate": 6.40207150288046e-06, "loss": 0.3298, "num_tokens": 499849866.0, "step": 83675 }, { "epoch": 0.8927485517373817, "grad_norm": 1.7045626439851143, "learning_rate": 6.400692643148656e-06, "loss": 0.5608, "num_tokens": 499877155.0, "step": 83680 }, { "epoch": 0.8928018947435802, "grad_norm": 0.7429530007949715, "learning_rate": 6.399314439983959e-06, "loss": 0.5433, "num_tokens": 499909993.0, "step": 83685 }, { "epoch": 0.8928552377497786, "grad_norm": 0.8611171705283928, "learning_rate": 6.397936893429254e-06, "loss": 0.4744, "num_tokens": 499940172.0, "step": 83690 }, { "epoch": 0.8929085807559771, "grad_norm": 2.1440385572094978, "learning_rate": 6.396560003527409e-06, "loss": 0.518, "num_tokens": 499985052.0, "step": 83695 }, { "epoch": 0.8929619237621755, "grad_norm": 0.6705927117584182, "learning_rate": 6.395183770321272e-06, "loss": 0.4573, "num_tokens": 500030187.0, "step": 83700 }, { "epoch": 0.893015266768374, "grad_norm": 0.9468219638725268, "learning_rate": 6.3938081938536644e-06, "loss": 0.3916, "num_tokens": 500051678.0, "step": 83705 }, { "epoch": 0.8930686097745725, "grad_norm": 0.7200742773896784, "learning_rate": 6.392433274167389e-06, "loss": 0.5174, "num_tokens": 500081326.0, "step": 83710 }, { "epoch": 0.8931219527807709, "grad_norm": 1.0459013978977865, "learning_rate": 6.391059011305233e-06, "loss": 0.3878, "num_tokens": 500094197.0, "step": 83715 }, { "epoch": 0.8931752957869694, "grad_norm": 0.8472042350526985, "learning_rate": 6.389685405309965e-06, "loss": 0.6265, "num_tokens": 500118853.0, "step": 83720 }, { "epoch": 0.8932286387931678, "grad_norm": 0.7825440370707798, "learning_rate": 6.388312456224325e-06, "loss": 0.4042, "num_tokens": 500169378.0, "step": 83725 }, { "epoch": 0.8932819817993662, "grad_norm": 1.61129025757633, "learning_rate": 6.386940164091035e-06, "loss": 0.4767, "num_tokens": 500196738.0, "step": 83730 }, { "epoch": 0.8933353248055648, "grad_norm": 2.4434331453793052, "learning_rate": 6.3855685289528025e-06, "loss": 0.4532, "num_tokens": 500218933.0, "step": 83735 }, { "epoch": 0.8933886678117632, "grad_norm": 0.6936643882709691, "learning_rate": 6.384197550852307e-06, "loss": 0.4468, "num_tokens": 500264451.0, "step": 83740 }, { "epoch": 0.8934420108179617, "grad_norm": 0.9882429072851753, "learning_rate": 6.382827229832205e-06, "loss": 0.5257, "num_tokens": 500303080.0, "step": 83745 }, { "epoch": 0.8934953538241601, "grad_norm": 0.9755974928193969, "learning_rate": 6.381457565935152e-06, "loss": 0.3958, "num_tokens": 500332666.0, "step": 83750 }, { "epoch": 0.8935486968303585, "grad_norm": 1.0539009961021069, "learning_rate": 6.380088559203754e-06, "loss": 0.4265, "num_tokens": 500358157.0, "step": 83755 }, { "epoch": 0.8936020398365571, "grad_norm": 1.1628849081753447, "learning_rate": 6.378720209680619e-06, "loss": 0.3772, "num_tokens": 500381376.0, "step": 83760 }, { "epoch": 0.8936553828427555, "grad_norm": 0.9675054747458243, "learning_rate": 6.377352517408331e-06, "loss": 0.5622, "num_tokens": 500412632.0, "step": 83765 }, { "epoch": 0.8937087258489539, "grad_norm": 0.7464175409077094, "learning_rate": 6.3759854824294416e-06, "loss": 0.4981, "num_tokens": 500457504.0, "step": 83770 }, { "epoch": 0.8937620688551524, "grad_norm": 0.6140550991166968, "learning_rate": 6.374619104786499e-06, "loss": 0.4139, "num_tokens": 500493461.0, "step": 83775 }, { "epoch": 0.8938154118613508, "grad_norm": 0.8965156407868936, "learning_rate": 6.3732533845220145e-06, "loss": 0.5491, "num_tokens": 500528180.0, "step": 83780 }, { "epoch": 0.8938687548675494, "grad_norm": 0.5652063623009961, "learning_rate": 6.371888321678486e-06, "loss": 0.352, "num_tokens": 500555320.0, "step": 83785 }, { "epoch": 0.8939220978737478, "grad_norm": 0.7036718742344834, "learning_rate": 6.370523916298396e-06, "loss": 0.5998, "num_tokens": 500598830.0, "step": 83790 }, { "epoch": 0.8939754408799462, "grad_norm": 1.2943477779640635, "learning_rate": 6.369160168424203e-06, "loss": 0.4555, "num_tokens": 500624628.0, "step": 83795 }, { "epoch": 0.8940287838861447, "grad_norm": 0.6573793608971534, "learning_rate": 6.367797078098338e-06, "loss": 0.4585, "num_tokens": 500660509.0, "step": 83800 }, { "epoch": 0.8940821268923431, "grad_norm": 0.7468633887534714, "learning_rate": 6.366434645363223e-06, "loss": 0.4471, "num_tokens": 500684358.0, "step": 83805 }, { "epoch": 0.8941354698985416, "grad_norm": 0.8790205393324665, "learning_rate": 6.365072870261253e-06, "loss": 0.3992, "num_tokens": 500703637.0, "step": 83810 }, { "epoch": 0.8941888129047401, "grad_norm": 1.4937743095128977, "learning_rate": 6.363711752834804e-06, "loss": 0.4345, "num_tokens": 500734472.0, "step": 83815 }, { "epoch": 0.8942421559109385, "grad_norm": 0.7656953635717468, "learning_rate": 6.362351293126226e-06, "loss": 0.3609, "num_tokens": 500754586.0, "step": 83820 }, { "epoch": 0.894295498917137, "grad_norm": 0.8421699104266731, "learning_rate": 6.360991491177862e-06, "loss": 0.4027, "num_tokens": 500779744.0, "step": 83825 }, { "epoch": 0.8943488419233354, "grad_norm": 0.9447499224252678, "learning_rate": 6.35963234703202e-06, "loss": 0.4589, "num_tokens": 500808376.0, "step": 83830 }, { "epoch": 0.8944021849295339, "grad_norm": 0.9363876205242055, "learning_rate": 6.358273860730994e-06, "loss": 0.4318, "num_tokens": 500834777.0, "step": 83835 }, { "epoch": 0.8944555279357324, "grad_norm": 1.1128985004210792, "learning_rate": 6.356916032317063e-06, "loss": 0.3836, "num_tokens": 500864542.0, "step": 83840 }, { "epoch": 0.8945088709419308, "grad_norm": 0.8104631626780633, "learning_rate": 6.355558861832474e-06, "loss": 0.5096, "num_tokens": 500896572.0, "step": 83845 }, { "epoch": 0.8945622139481293, "grad_norm": 1.2439629711502718, "learning_rate": 6.35420234931946e-06, "loss": 0.7265, "num_tokens": 500922142.0, "step": 83850 }, { "epoch": 0.8946155569543277, "grad_norm": 0.6998740458189938, "learning_rate": 6.352846494820239e-06, "loss": 0.3989, "num_tokens": 500950695.0, "step": 83855 }, { "epoch": 0.8946688999605261, "grad_norm": 0.7785365162017231, "learning_rate": 6.351491298376992e-06, "loss": 0.5381, "num_tokens": 500992134.0, "step": 83860 }, { "epoch": 0.8947222429667246, "grad_norm": 0.9748346360911965, "learning_rate": 6.350136760031895e-06, "loss": 0.4289, "num_tokens": 501022524.0, "step": 83865 }, { "epoch": 0.8947755859729231, "grad_norm": 1.214732139119884, "learning_rate": 6.348782879827104e-06, "loss": 0.4475, "num_tokens": 501048961.0, "step": 83870 }, { "epoch": 0.8948289289791216, "grad_norm": 0.7428720995805829, "learning_rate": 6.347429657804742e-06, "loss": 0.4639, "num_tokens": 501096057.0, "step": 83875 }, { "epoch": 0.89488227198532, "grad_norm": 0.6555837159180482, "learning_rate": 6.346077094006916e-06, "loss": 0.4819, "num_tokens": 501129227.0, "step": 83880 }, { "epoch": 0.8949356149915184, "grad_norm": 0.8637142227235508, "learning_rate": 6.344725188475727e-06, "loss": 0.4346, "num_tokens": 501157674.0, "step": 83885 }, { "epoch": 0.8949889579977169, "grad_norm": 0.907915119628963, "learning_rate": 6.3433739412532336e-06, "loss": 0.5367, "num_tokens": 501190279.0, "step": 83890 }, { "epoch": 0.8950423010039154, "grad_norm": 0.6665255530316745, "learning_rate": 6.342023352381484e-06, "loss": 0.4931, "num_tokens": 501235078.0, "step": 83895 }, { "epoch": 0.8950956440101139, "grad_norm": 0.6943614361711257, "learning_rate": 6.3406734219025095e-06, "loss": 0.3777, "num_tokens": 501278088.0, "step": 83900 }, { "epoch": 0.8951489870163123, "grad_norm": 0.545653724827556, "learning_rate": 6.339324149858315e-06, "loss": 0.5692, "num_tokens": 501335575.0, "step": 83905 }, { "epoch": 0.8952023300225107, "grad_norm": 0.7935312157269302, "learning_rate": 6.337975536290884e-06, "loss": 0.4121, "num_tokens": 501373732.0, "step": 83910 }, { "epoch": 0.8952556730287092, "grad_norm": 0.6336342114467663, "learning_rate": 6.336627581242191e-06, "loss": 0.4906, "num_tokens": 501408301.0, "step": 83915 }, { "epoch": 0.8953090160349076, "grad_norm": 2.114031028719803, "learning_rate": 6.335280284754177e-06, "loss": 0.4719, "num_tokens": 501429269.0, "step": 83920 }, { "epoch": 0.8953623590411062, "grad_norm": 0.7443705039514943, "learning_rate": 6.333933646868767e-06, "loss": 0.443, "num_tokens": 501455169.0, "step": 83925 }, { "epoch": 0.8954157020473046, "grad_norm": 0.6512749080383459, "learning_rate": 6.332587667627866e-06, "loss": 0.4364, "num_tokens": 501481102.0, "step": 83930 }, { "epoch": 0.895469045053503, "grad_norm": 0.6952930416811246, "learning_rate": 6.331242347073355e-06, "loss": 0.4218, "num_tokens": 501519747.0, "step": 83935 }, { "epoch": 0.8955223880597015, "grad_norm": 0.8853434941126709, "learning_rate": 6.329897685247098e-06, "loss": 0.2955, "num_tokens": 501542759.0, "step": 83940 }, { "epoch": 0.8955757310658999, "grad_norm": 0.7787557825433002, "learning_rate": 6.328553682190946e-06, "loss": 0.4701, "num_tokens": 501579182.0, "step": 83945 }, { "epoch": 0.8956290740720984, "grad_norm": 0.775951644315261, "learning_rate": 6.327210337946713e-06, "loss": 0.4701, "num_tokens": 501613321.0, "step": 83950 }, { "epoch": 0.8956824170782969, "grad_norm": 0.7815214430683778, "learning_rate": 6.325867652556206e-06, "loss": 0.5052, "num_tokens": 501650290.0, "step": 83955 }, { "epoch": 0.8957357600844953, "grad_norm": 2.6454451340963554, "learning_rate": 6.324525626061205e-06, "loss": 0.694, "num_tokens": 501685104.0, "step": 83960 }, { "epoch": 0.8957891030906938, "grad_norm": 1.4081632269005546, "learning_rate": 6.323184258503467e-06, "loss": 0.4004, "num_tokens": 501707152.0, "step": 83965 }, { "epoch": 0.8958424460968922, "grad_norm": 1.5215115750352204, "learning_rate": 6.3218435499247386e-06, "loss": 0.4787, "num_tokens": 501732191.0, "step": 83970 }, { "epoch": 0.8958957891030906, "grad_norm": 0.8443808830263325, "learning_rate": 6.320503500366739e-06, "loss": 0.4475, "num_tokens": 501766268.0, "step": 83975 }, { "epoch": 0.8959491321092892, "grad_norm": 1.5157272723060873, "learning_rate": 6.319164109871163e-06, "loss": 0.4751, "num_tokens": 501794386.0, "step": 83980 }, { "epoch": 0.8960024751154876, "grad_norm": 1.6509931768639925, "learning_rate": 6.317825378479695e-06, "loss": 0.6186, "num_tokens": 501822618.0, "step": 83985 }, { "epoch": 0.8960558181216861, "grad_norm": 0.6764893458047723, "learning_rate": 6.316487306233997e-06, "loss": 0.295, "num_tokens": 501841599.0, "step": 83990 }, { "epoch": 0.8961091611278845, "grad_norm": 0.6879468519291578, "learning_rate": 6.315149893175697e-06, "loss": 0.4517, "num_tokens": 501865604.0, "step": 83995 }, { "epoch": 0.8961625041340829, "grad_norm": 1.1708584677162182, "learning_rate": 6.313813139346418e-06, "loss": 0.4231, "num_tokens": 501890304.0, "step": 84000 }, { "epoch": 0.8962158471402815, "grad_norm": 0.7094454647286739, "learning_rate": 6.312477044787753e-06, "loss": 0.5373, "num_tokens": 501915190.0, "step": 84005 }, { "epoch": 0.8962691901464799, "grad_norm": 0.8509672901617725, "learning_rate": 6.311141609541286e-06, "loss": 0.5268, "num_tokens": 501946725.0, "step": 84010 }, { "epoch": 0.8963225331526784, "grad_norm": 0.7885225957666661, "learning_rate": 6.309806833648568e-06, "loss": 0.4001, "num_tokens": 501968636.0, "step": 84015 }, { "epoch": 0.8963758761588768, "grad_norm": 0.571714615596995, "learning_rate": 6.308472717151134e-06, "loss": 0.4499, "num_tokens": 501998839.0, "step": 84020 }, { "epoch": 0.8964292191650752, "grad_norm": 0.6289286803849395, "learning_rate": 6.3071392600905045e-06, "loss": 0.4863, "num_tokens": 502040464.0, "step": 84025 }, { "epoch": 0.8964825621712738, "grad_norm": 0.815701870962705, "learning_rate": 6.305806462508168e-06, "loss": 0.5118, "num_tokens": 502080641.0, "step": 84030 }, { "epoch": 0.8965359051774722, "grad_norm": 0.882099134297752, "learning_rate": 6.304474324445599e-06, "loss": 0.3897, "num_tokens": 502108224.0, "step": 84035 }, { "epoch": 0.8965892481836706, "grad_norm": 0.663351985963152, "learning_rate": 6.303142845944255e-06, "loss": 0.4088, "num_tokens": 502133303.0, "step": 84040 }, { "epoch": 0.8966425911898691, "grad_norm": 1.7905993446568365, "learning_rate": 6.30181202704556e-06, "loss": 0.5231, "num_tokens": 502167236.0, "step": 84045 }, { "epoch": 0.8966959341960675, "grad_norm": 0.8671473294540496, "learning_rate": 6.300481867790936e-06, "loss": 0.4687, "num_tokens": 502194121.0, "step": 84050 }, { "epoch": 0.896749277202266, "grad_norm": 0.9738110495749609, "learning_rate": 6.2991523682217725e-06, "loss": 0.5038, "num_tokens": 502224606.0, "step": 84055 }, { "epoch": 0.8968026202084645, "grad_norm": 1.052525678042913, "learning_rate": 6.297823528379438e-06, "loss": 0.3701, "num_tokens": 502239802.0, "step": 84060 }, { "epoch": 0.8968559632146629, "grad_norm": 0.6613528719506588, "learning_rate": 6.296495348305287e-06, "loss": 0.5137, "num_tokens": 502289804.0, "step": 84065 }, { "epoch": 0.8969093062208614, "grad_norm": 0.7122743561376935, "learning_rate": 6.295167828040646e-06, "loss": 0.4344, "num_tokens": 502324309.0, "step": 84070 }, { "epoch": 0.8969626492270598, "grad_norm": 0.829479819588374, "learning_rate": 6.293840967626824e-06, "loss": 0.3594, "num_tokens": 502351191.0, "step": 84075 }, { "epoch": 0.8970159922332583, "grad_norm": 1.0209340865611893, "learning_rate": 6.292514767105114e-06, "loss": 0.5299, "num_tokens": 502391512.0, "step": 84080 }, { "epoch": 0.8970693352394568, "grad_norm": 1.3208030852333146, "learning_rate": 6.291189226516786e-06, "loss": 0.4269, "num_tokens": 502406236.0, "step": 84085 }, { "epoch": 0.8971226782456552, "grad_norm": 0.9946381371834495, "learning_rate": 6.2898643459030805e-06, "loss": 0.4696, "num_tokens": 502433057.0, "step": 84090 }, { "epoch": 0.8971760212518537, "grad_norm": 0.9507563104692366, "learning_rate": 6.28854012530523e-06, "loss": 0.4497, "num_tokens": 502459597.0, "step": 84095 }, { "epoch": 0.8972293642580521, "grad_norm": 1.056678940416685, "learning_rate": 6.287216564764445e-06, "loss": 0.416, "num_tokens": 502491756.0, "step": 84100 }, { "epoch": 0.8972827072642506, "grad_norm": 1.0430128313619162, "learning_rate": 6.2858936643219065e-06, "loss": 0.3882, "num_tokens": 502526569.0, "step": 84105 }, { "epoch": 0.897336050270449, "grad_norm": 0.8900455620560003, "learning_rate": 6.284571424018782e-06, "loss": 0.4023, "num_tokens": 502572225.0, "step": 84110 }, { "epoch": 0.8973893932766475, "grad_norm": 1.038198522748706, "learning_rate": 6.283249843896216e-06, "loss": 0.4649, "num_tokens": 502602848.0, "step": 84115 }, { "epoch": 0.897442736282846, "grad_norm": 1.0611794114861333, "learning_rate": 6.281928923995334e-06, "loss": 0.4458, "num_tokens": 502632711.0, "step": 84120 }, { "epoch": 0.8974960792890444, "grad_norm": 0.706624699987681, "learning_rate": 6.28060866435724e-06, "loss": 0.5354, "num_tokens": 502671707.0, "step": 84125 }, { "epoch": 0.8975494222952428, "grad_norm": 0.5687276696070046, "learning_rate": 6.279289065023024e-06, "loss": 0.5517, "num_tokens": 502719467.0, "step": 84130 }, { "epoch": 0.8976027653014413, "grad_norm": 0.882891965309086, "learning_rate": 6.277970126033738e-06, "loss": 0.5776, "num_tokens": 502743540.0, "step": 84135 }, { "epoch": 0.8976561083076398, "grad_norm": 0.9731336143831942, "learning_rate": 6.276651847430434e-06, "loss": 0.4222, "num_tokens": 502772855.0, "step": 84140 }, { "epoch": 0.8977094513138383, "grad_norm": 1.8212734482451323, "learning_rate": 6.2753342292541305e-06, "loss": 0.4059, "num_tokens": 502789909.0, "step": 84145 }, { "epoch": 0.8977627943200367, "grad_norm": 1.5789743414175113, "learning_rate": 6.274017271545827e-06, "loss": 0.5569, "num_tokens": 502819920.0, "step": 84150 }, { "epoch": 0.8978161373262351, "grad_norm": 1.6611660653311378, "learning_rate": 6.2727009743465055e-06, "loss": 0.5882, "num_tokens": 502847730.0, "step": 84155 }, { "epoch": 0.8978694803324336, "grad_norm": 1.5875786118297295, "learning_rate": 6.271385337697129e-06, "loss": 0.4676, "num_tokens": 502876203.0, "step": 84160 }, { "epoch": 0.897922823338632, "grad_norm": 1.0509130268841265, "learning_rate": 6.270070361638636e-06, "loss": 0.4139, "num_tokens": 502904606.0, "step": 84165 }, { "epoch": 0.8979761663448306, "grad_norm": 0.6990505381855241, "learning_rate": 6.268756046211945e-06, "loss": 0.3868, "num_tokens": 502943480.0, "step": 84170 }, { "epoch": 0.898029509351029, "grad_norm": 0.849675145768871, "learning_rate": 6.267442391457959e-06, "loss": 0.4281, "num_tokens": 502978729.0, "step": 84175 }, { "epoch": 0.8980828523572274, "grad_norm": 1.3149647125308155, "learning_rate": 6.2661293974175515e-06, "loss": 0.4255, "num_tokens": 503009465.0, "step": 84180 }, { "epoch": 0.8981361953634259, "grad_norm": 0.6778755638248474, "learning_rate": 6.264817064131579e-06, "loss": 0.4384, "num_tokens": 503041890.0, "step": 84185 }, { "epoch": 0.8981895383696243, "grad_norm": 0.6461557886744003, "learning_rate": 6.263505391640884e-06, "loss": 0.5677, "num_tokens": 503075390.0, "step": 84190 }, { "epoch": 0.8982428813758229, "grad_norm": 0.9707858173282414, "learning_rate": 6.262194379986276e-06, "loss": 0.4945, "num_tokens": 503126253.0, "step": 84195 }, { "epoch": 0.8982962243820213, "grad_norm": 0.7871417568120455, "learning_rate": 6.260884029208558e-06, "loss": 0.4996, "num_tokens": 503167228.0, "step": 84200 }, { "epoch": 0.8983495673882197, "grad_norm": 1.950496107446053, "learning_rate": 6.2595743393485045e-06, "loss": 0.5256, "num_tokens": 503202239.0, "step": 84205 }, { "epoch": 0.8984029103944182, "grad_norm": 1.027125780436016, "learning_rate": 6.258265310446866e-06, "loss": 0.4332, "num_tokens": 503226705.0, "step": 84210 }, { "epoch": 0.8984562534006166, "grad_norm": 0.5975327505131887, "learning_rate": 6.2569569425443816e-06, "loss": 0.3697, "num_tokens": 503265783.0, "step": 84215 }, { "epoch": 0.898509596406815, "grad_norm": 0.9624081027242118, "learning_rate": 6.255649235681762e-06, "loss": 0.4483, "num_tokens": 503293294.0, "step": 84220 }, { "epoch": 0.8985629394130136, "grad_norm": 1.5172799668753139, "learning_rate": 6.254342189899698e-06, "loss": 0.4255, "num_tokens": 503326266.0, "step": 84225 }, { "epoch": 0.898616282419212, "grad_norm": 0.7291818246008493, "learning_rate": 6.253035805238868e-06, "loss": 0.4273, "num_tokens": 503362764.0, "step": 84230 }, { "epoch": 0.8986696254254105, "grad_norm": 1.0740498448294284, "learning_rate": 6.251730081739922e-06, "loss": 0.5634, "num_tokens": 503389048.0, "step": 84235 }, { "epoch": 0.8987229684316089, "grad_norm": 1.285170765326244, "learning_rate": 6.250425019443486e-06, "loss": 0.539, "num_tokens": 503426170.0, "step": 84240 }, { "epoch": 0.8987763114378073, "grad_norm": 1.2074260708329136, "learning_rate": 6.249120618390181e-06, "loss": 0.5123, "num_tokens": 503452866.0, "step": 84245 }, { "epoch": 0.8988296544440059, "grad_norm": 1.0840758852183712, "learning_rate": 6.24781687862059e-06, "loss": 0.422, "num_tokens": 503480751.0, "step": 84250 }, { "epoch": 0.8988829974502043, "grad_norm": 0.8700668852739853, "learning_rate": 6.246513800175284e-06, "loss": 0.3862, "num_tokens": 503502133.0, "step": 84255 }, { "epoch": 0.8989363404564028, "grad_norm": 2.2193729213882136, "learning_rate": 6.245211383094811e-06, "loss": 0.541, "num_tokens": 503528423.0, "step": 84260 }, { "epoch": 0.8989896834626012, "grad_norm": 0.6855549252904598, "learning_rate": 6.243909627419705e-06, "loss": 0.4602, "num_tokens": 503569291.0, "step": 84265 }, { "epoch": 0.8990430264687996, "grad_norm": 0.743986221519964, "learning_rate": 6.242608533190464e-06, "loss": 0.3582, "num_tokens": 503590243.0, "step": 84270 }, { "epoch": 0.8990963694749982, "grad_norm": 1.332910613456078, "learning_rate": 6.241308100447584e-06, "loss": 0.3787, "num_tokens": 503613285.0, "step": 84275 }, { "epoch": 0.8991497124811966, "grad_norm": 0.7814920158708776, "learning_rate": 6.240008329231535e-06, "loss": 0.4483, "num_tokens": 503645242.0, "step": 84280 }, { "epoch": 0.8992030554873951, "grad_norm": 1.0412453684184828, "learning_rate": 6.238709219582754e-06, "loss": 0.505, "num_tokens": 503663728.0, "step": 84285 }, { "epoch": 0.8992563984935935, "grad_norm": 1.0627606363576008, "learning_rate": 6.237410771541667e-06, "loss": 0.5062, "num_tokens": 503697814.0, "step": 84290 }, { "epoch": 0.8993097414997919, "grad_norm": 1.405651489540444, "learning_rate": 6.236112985148687e-06, "loss": 0.5814, "num_tokens": 503719063.0, "step": 84295 }, { "epoch": 0.8993630845059905, "grad_norm": 1.3707552014785067, "learning_rate": 6.2348158604441895e-06, "loss": 0.4253, "num_tokens": 503737840.0, "step": 84300 }, { "epoch": 0.8994164275121889, "grad_norm": 1.4080361843356535, "learning_rate": 6.233519397468542e-06, "loss": 0.3316, "num_tokens": 503758965.0, "step": 84305 }, { "epoch": 0.8994697705183873, "grad_norm": 0.734976707765068, "learning_rate": 6.232223596262093e-06, "loss": 0.429, "num_tokens": 503804992.0, "step": 84310 }, { "epoch": 0.8995231135245858, "grad_norm": 0.7063462740875777, "learning_rate": 6.2309284568651576e-06, "loss": 0.5232, "num_tokens": 503833989.0, "step": 84315 }, { "epoch": 0.8995764565307842, "grad_norm": 0.7594092645808196, "learning_rate": 6.2296339793180415e-06, "loss": 0.5395, "num_tokens": 503863826.0, "step": 84320 }, { "epoch": 0.8996297995369827, "grad_norm": 0.8029188788522948, "learning_rate": 6.228340163661026e-06, "loss": 0.5099, "num_tokens": 503898026.0, "step": 84325 }, { "epoch": 0.8996831425431812, "grad_norm": 1.82792824684803, "learning_rate": 6.22704700993437e-06, "loss": 0.4229, "num_tokens": 503920293.0, "step": 84330 }, { "epoch": 0.8997364855493796, "grad_norm": 1.679707108897884, "learning_rate": 6.225754518178314e-06, "loss": 0.4954, "num_tokens": 503950993.0, "step": 84335 }, { "epoch": 0.8997898285555781, "grad_norm": 0.8997075727350156, "learning_rate": 6.22446268843308e-06, "loss": 0.4418, "num_tokens": 503989977.0, "step": 84340 }, { "epoch": 0.8998431715617765, "grad_norm": 1.5418017592145714, "learning_rate": 6.223171520738866e-06, "loss": 0.4758, "num_tokens": 504017505.0, "step": 84345 }, { "epoch": 0.899896514567975, "grad_norm": 0.9868284312177008, "learning_rate": 6.221881015135849e-06, "loss": 0.3698, "num_tokens": 504039159.0, "step": 84350 }, { "epoch": 0.8999498575741735, "grad_norm": 1.1560599419864106, "learning_rate": 6.220591171664191e-06, "loss": 0.4476, "num_tokens": 504070769.0, "step": 84355 }, { "epoch": 0.9000032005803719, "grad_norm": 1.702646091864894, "learning_rate": 6.219301990364028e-06, "loss": 0.5122, "num_tokens": 504104862.0, "step": 84360 }, { "epoch": 0.9000565435865704, "grad_norm": 1.032748582876354, "learning_rate": 6.218013471275472e-06, "loss": 0.3128, "num_tokens": 504119934.0, "step": 84365 }, { "epoch": 0.9001098865927688, "grad_norm": 2.4966295728195025, "learning_rate": 6.216725614438623e-06, "loss": 0.459, "num_tokens": 504143992.0, "step": 84370 }, { "epoch": 0.9001632295989673, "grad_norm": 1.2195921415585858, "learning_rate": 6.215438419893556e-06, "loss": 0.4555, "num_tokens": 504175034.0, "step": 84375 }, { "epoch": 0.9002165726051657, "grad_norm": 0.8875195035725397, "learning_rate": 6.214151887680323e-06, "loss": 0.4635, "num_tokens": 504211457.0, "step": 84380 }, { "epoch": 0.9002699156113642, "grad_norm": 1.3652784943420255, "learning_rate": 6.212866017838966e-06, "loss": 0.5046, "num_tokens": 504247829.0, "step": 84385 }, { "epoch": 0.9003232586175627, "grad_norm": 0.9270958160573157, "learning_rate": 6.2115808104094875e-06, "loss": 0.3885, "num_tokens": 504273209.0, "step": 84390 }, { "epoch": 0.9003766016237611, "grad_norm": 0.6338728219422239, "learning_rate": 6.210296265431894e-06, "loss": 0.4433, "num_tokens": 504303005.0, "step": 84395 }, { "epoch": 0.9004299446299595, "grad_norm": 1.0466985819328465, "learning_rate": 6.2090123829461455e-06, "loss": 0.4492, "num_tokens": 504332936.0, "step": 84400 }, { "epoch": 0.900483287636158, "grad_norm": 1.5541915403109512, "learning_rate": 6.2077291629921996e-06, "loss": 0.6006, "num_tokens": 504364844.0, "step": 84405 }, { "epoch": 0.9005366306423565, "grad_norm": 0.8411197705346197, "learning_rate": 6.206446605609984e-06, "loss": 0.4748, "num_tokens": 504403340.0, "step": 84410 }, { "epoch": 0.900589973648555, "grad_norm": 0.678784584187161, "learning_rate": 6.205164710839416e-06, "loss": 0.3193, "num_tokens": 504424558.0, "step": 84415 }, { "epoch": 0.9006433166547534, "grad_norm": 1.7441249876188538, "learning_rate": 6.203883478720379e-06, "loss": 0.3791, "num_tokens": 504442764.0, "step": 84420 }, { "epoch": 0.9006966596609518, "grad_norm": 1.4582600222305395, "learning_rate": 6.202602909292744e-06, "loss": 0.5341, "num_tokens": 504479218.0, "step": 84425 }, { "epoch": 0.9007500026671503, "grad_norm": 1.3954356005359698, "learning_rate": 6.201323002596362e-06, "loss": 0.4217, "num_tokens": 504498985.0, "step": 84430 }, { "epoch": 0.9008033456733487, "grad_norm": 0.5770320075422842, "learning_rate": 6.200043758671062e-06, "loss": 0.4416, "num_tokens": 504528282.0, "step": 84435 }, { "epoch": 0.9008566886795473, "grad_norm": 0.9357523115185606, "learning_rate": 6.198765177556644e-06, "loss": 0.4617, "num_tokens": 504548005.0, "step": 84440 }, { "epoch": 0.9009100316857457, "grad_norm": 0.8273501235007148, "learning_rate": 6.197487259292903e-06, "loss": 0.5719, "num_tokens": 504578611.0, "step": 84445 }, { "epoch": 0.9009633746919441, "grad_norm": 0.9666822448334264, "learning_rate": 6.196210003919599e-06, "loss": 0.7713, "num_tokens": 504604556.0, "step": 84450 }, { "epoch": 0.9010167176981426, "grad_norm": 1.136194010239817, "learning_rate": 6.1949334114764805e-06, "loss": 0.4615, "num_tokens": 504644162.0, "step": 84455 }, { "epoch": 0.901070060704341, "grad_norm": 0.7486113661101648, "learning_rate": 6.193657482003276e-06, "loss": 0.4588, "num_tokens": 504672971.0, "step": 84460 }, { "epoch": 0.9011234037105396, "grad_norm": 0.7047108545295573, "learning_rate": 6.192382215539682e-06, "loss": 0.3859, "num_tokens": 504720367.0, "step": 84465 }, { "epoch": 0.901176746716738, "grad_norm": 1.5197608428171232, "learning_rate": 6.1911076121253905e-06, "loss": 0.3868, "num_tokens": 504744209.0, "step": 84470 }, { "epoch": 0.9012300897229364, "grad_norm": 0.6760655047706415, "learning_rate": 6.18983367180006e-06, "loss": 0.4834, "num_tokens": 504770130.0, "step": 84475 }, { "epoch": 0.9012834327291349, "grad_norm": 0.9147844554043932, "learning_rate": 6.1885603946033285e-06, "loss": 0.48, "num_tokens": 504810366.0, "step": 84480 }, { "epoch": 0.9013367757353333, "grad_norm": 1.5198418173102892, "learning_rate": 6.1872877805748255e-06, "loss": 0.506, "num_tokens": 504840880.0, "step": 84485 }, { "epoch": 0.9013901187415317, "grad_norm": 1.557586334006336, "learning_rate": 6.186015829754151e-06, "loss": 0.3796, "num_tokens": 504861377.0, "step": 84490 }, { "epoch": 0.9014434617477303, "grad_norm": 0.7329542341849968, "learning_rate": 6.184744542180882e-06, "loss": 0.4598, "num_tokens": 504885389.0, "step": 84495 }, { "epoch": 0.9014968047539287, "grad_norm": 1.2059275884843634, "learning_rate": 6.183473917894577e-06, "loss": 0.4817, "num_tokens": 504909200.0, "step": 84500 }, { "epoch": 0.9015501477601272, "grad_norm": 0.7029296719146183, "learning_rate": 6.182203956934784e-06, "loss": 0.3618, "num_tokens": 504935356.0, "step": 84505 }, { "epoch": 0.9016034907663256, "grad_norm": 0.629318761672787, "learning_rate": 6.1809346593410155e-06, "loss": 0.4474, "num_tokens": 504964958.0, "step": 84510 }, { "epoch": 0.901656833772524, "grad_norm": 1.00477016577085, "learning_rate": 6.179666025152764e-06, "loss": 0.5797, "num_tokens": 504995243.0, "step": 84515 }, { "epoch": 0.9017101767787226, "grad_norm": 0.6381847920003758, "learning_rate": 6.1783980544095175e-06, "loss": 0.3812, "num_tokens": 505030864.0, "step": 84520 }, { "epoch": 0.901763519784921, "grad_norm": 0.6444562645513223, "learning_rate": 6.1771307471507265e-06, "loss": 0.4286, "num_tokens": 505060052.0, "step": 84525 }, { "epoch": 0.9018168627911195, "grad_norm": 1.0557319385943762, "learning_rate": 6.175864103415825e-06, "loss": 0.4261, "num_tokens": 505096204.0, "step": 84530 }, { "epoch": 0.9018702057973179, "grad_norm": 0.5699840966272551, "learning_rate": 6.174598123244236e-06, "loss": 0.4196, "num_tokens": 505137443.0, "step": 84535 }, { "epoch": 0.9019235488035163, "grad_norm": 0.7903528099276402, "learning_rate": 6.173332806675352e-06, "loss": 0.3773, "num_tokens": 505169401.0, "step": 84540 }, { "epoch": 0.9019768918097149, "grad_norm": 0.6636270300181208, "learning_rate": 6.172068153748539e-06, "loss": 0.4395, "num_tokens": 505207857.0, "step": 84545 }, { "epoch": 0.9020302348159133, "grad_norm": 0.9574065259356098, "learning_rate": 6.170804164503159e-06, "loss": 0.4558, "num_tokens": 505248495.0, "step": 84550 }, { "epoch": 0.9020835778221118, "grad_norm": 0.5802151032789045, "learning_rate": 6.1695408389785425e-06, "loss": 0.5734, "num_tokens": 505280608.0, "step": 84555 }, { "epoch": 0.9021369208283102, "grad_norm": 0.8855935686041955, "learning_rate": 6.168278177213998e-06, "loss": 0.5416, "num_tokens": 505325513.0, "step": 84560 }, { "epoch": 0.9021902638345086, "grad_norm": 2.9090266613833293, "learning_rate": 6.167016179248823e-06, "loss": 0.5086, "num_tokens": 505355847.0, "step": 84565 }, { "epoch": 0.9022436068407071, "grad_norm": 0.9574637022198175, "learning_rate": 6.165754845122282e-06, "loss": 0.5821, "num_tokens": 505391215.0, "step": 84570 }, { "epoch": 0.9022969498469056, "grad_norm": 0.7967435455184102, "learning_rate": 6.164494174873632e-06, "loss": 0.3959, "num_tokens": 505424658.0, "step": 84575 }, { "epoch": 0.902350292853104, "grad_norm": 0.8425961027841693, "learning_rate": 6.1632341685421e-06, "loss": 0.3929, "num_tokens": 505466831.0, "step": 84580 }, { "epoch": 0.9024036358593025, "grad_norm": 1.3060533379413208, "learning_rate": 6.161974826166891e-06, "loss": 0.4406, "num_tokens": 505486832.0, "step": 84585 }, { "epoch": 0.9024569788655009, "grad_norm": 0.9309843617233766, "learning_rate": 6.160716147787193e-06, "loss": 0.3247, "num_tokens": 505520358.0, "step": 84590 }, { "epoch": 0.9025103218716994, "grad_norm": 0.9150071232598689, "learning_rate": 6.159458133442182e-06, "loss": 0.4353, "num_tokens": 505542837.0, "step": 84595 }, { "epoch": 0.9025636648778979, "grad_norm": 1.0890064283938703, "learning_rate": 6.1582007831709945e-06, "loss": 0.3787, "num_tokens": 505582791.0, "step": 84600 }, { "epoch": 0.9026170078840963, "grad_norm": 1.038592362370817, "learning_rate": 6.156944097012763e-06, "loss": 0.4467, "num_tokens": 505615418.0, "step": 84605 }, { "epoch": 0.9026703508902948, "grad_norm": 1.3017376742024511, "learning_rate": 6.155688075006593e-06, "loss": 0.4369, "num_tokens": 505641306.0, "step": 84610 }, { "epoch": 0.9027236938964932, "grad_norm": 1.4234373140795902, "learning_rate": 6.154432717191567e-06, "loss": 0.496, "num_tokens": 505672809.0, "step": 84615 }, { "epoch": 0.9027770369026917, "grad_norm": 1.1183176699659947, "learning_rate": 6.1531780236067486e-06, "loss": 0.4236, "num_tokens": 505701524.0, "step": 84620 }, { "epoch": 0.9028303799088901, "grad_norm": 0.8509624915923774, "learning_rate": 6.1519239942911844e-06, "loss": 0.5084, "num_tokens": 505733591.0, "step": 84625 }, { "epoch": 0.9028837229150886, "grad_norm": 0.9025319011409584, "learning_rate": 6.150670629283893e-06, "loss": 0.5216, "num_tokens": 505761921.0, "step": 84630 }, { "epoch": 0.9029370659212871, "grad_norm": 1.261960871465668, "learning_rate": 6.149417928623879e-06, "loss": 0.4772, "num_tokens": 505779552.0, "step": 84635 }, { "epoch": 0.9029904089274855, "grad_norm": 0.5898980156982229, "learning_rate": 6.148165892350126e-06, "loss": 0.4371, "num_tokens": 505815922.0, "step": 84640 }, { "epoch": 0.903043751933684, "grad_norm": 1.5854964763073662, "learning_rate": 6.146914520501589e-06, "loss": 0.5676, "num_tokens": 505848868.0, "step": 84645 }, { "epoch": 0.9030970949398824, "grad_norm": 0.9440156980186764, "learning_rate": 6.145663813117217e-06, "loss": 0.3981, "num_tokens": 505880934.0, "step": 84650 }, { "epoch": 0.9031504379460809, "grad_norm": 0.9377462940001886, "learning_rate": 6.1444137702359205e-06, "loss": 0.4357, "num_tokens": 505913817.0, "step": 84655 }, { "epoch": 0.9032037809522794, "grad_norm": 0.995483030517103, "learning_rate": 6.143164391896602e-06, "loss": 0.4955, "num_tokens": 505937680.0, "step": 84660 }, { "epoch": 0.9032571239584778, "grad_norm": 1.3781237939462831, "learning_rate": 6.1419156781381374e-06, "loss": 0.5016, "num_tokens": 505957460.0, "step": 84665 }, { "epoch": 0.9033104669646762, "grad_norm": 0.7686966353447798, "learning_rate": 6.140667628999389e-06, "loss": 0.5361, "num_tokens": 505998725.0, "step": 84670 }, { "epoch": 0.9033638099708747, "grad_norm": 0.926787015913435, "learning_rate": 6.13942024451919e-06, "loss": 0.3977, "num_tokens": 506023767.0, "step": 84675 }, { "epoch": 0.9034171529770731, "grad_norm": 0.7930584343900825, "learning_rate": 6.138173524736355e-06, "loss": 0.4456, "num_tokens": 506043390.0, "step": 84680 }, { "epoch": 0.9034704959832717, "grad_norm": 0.7071748827340226, "learning_rate": 6.136927469689685e-06, "loss": 0.4384, "num_tokens": 506068799.0, "step": 84685 }, { "epoch": 0.9035238389894701, "grad_norm": 0.8011628185267394, "learning_rate": 6.135682079417951e-06, "loss": 0.4628, "num_tokens": 506099531.0, "step": 84690 }, { "epoch": 0.9035771819956685, "grad_norm": 1.0214218130817185, "learning_rate": 6.1344373539599055e-06, "loss": 0.5063, "num_tokens": 506126123.0, "step": 84695 }, { "epoch": 0.903630525001867, "grad_norm": 0.6939435155235962, "learning_rate": 6.133193293354284e-06, "loss": 0.3559, "num_tokens": 506150769.0, "step": 84700 }, { "epoch": 0.9036838680080654, "grad_norm": 0.9182676432869803, "learning_rate": 6.131949897639797e-06, "loss": 0.5268, "num_tokens": 506199576.0, "step": 84705 }, { "epoch": 0.903737211014264, "grad_norm": 1.5072090263021611, "learning_rate": 6.130707166855138e-06, "loss": 0.5039, "num_tokens": 506224433.0, "step": 84710 }, { "epoch": 0.9037905540204624, "grad_norm": 1.0779767016783943, "learning_rate": 6.129465101038982e-06, "loss": 0.4621, "num_tokens": 506245125.0, "step": 84715 }, { "epoch": 0.9038438970266608, "grad_norm": 1.066334796533699, "learning_rate": 6.128223700229971e-06, "loss": 0.4658, "num_tokens": 506278240.0, "step": 84720 }, { "epoch": 0.9038972400328593, "grad_norm": 0.7008456298060215, "learning_rate": 6.1269829644667435e-06, "loss": 0.4352, "num_tokens": 506313230.0, "step": 84725 }, { "epoch": 0.9039505830390577, "grad_norm": 0.6673490846837179, "learning_rate": 6.125742893787905e-06, "loss": 0.4245, "num_tokens": 506348036.0, "step": 84730 }, { "epoch": 0.9040039260452563, "grad_norm": 2.154650633617164, "learning_rate": 6.124503488232039e-06, "loss": 0.509, "num_tokens": 506362540.0, "step": 84735 }, { "epoch": 0.9040572690514547, "grad_norm": 0.7386751405602203, "learning_rate": 6.1232647478377186e-06, "loss": 0.4883, "num_tokens": 506391234.0, "step": 84740 }, { "epoch": 0.9041106120576531, "grad_norm": 1.5330975103973563, "learning_rate": 6.122026672643493e-06, "loss": 0.4393, "num_tokens": 506423316.0, "step": 84745 }, { "epoch": 0.9041639550638516, "grad_norm": 1.0271915701673973, "learning_rate": 6.120789262687884e-06, "loss": 0.549, "num_tokens": 506466721.0, "step": 84750 }, { "epoch": 0.90421729807005, "grad_norm": 0.805124930280379, "learning_rate": 6.119552518009399e-06, "loss": 0.4174, "num_tokens": 506498477.0, "step": 84755 }, { "epoch": 0.9042706410762484, "grad_norm": 0.7255059087651158, "learning_rate": 6.118316438646524e-06, "loss": 0.4223, "num_tokens": 506523183.0, "step": 84760 }, { "epoch": 0.904323984082447, "grad_norm": 0.775356692389031, "learning_rate": 6.117081024637726e-06, "loss": 0.4472, "num_tokens": 506568461.0, "step": 84765 }, { "epoch": 0.9043773270886454, "grad_norm": 0.7305999010814425, "learning_rate": 6.115846276021438e-06, "loss": 0.3874, "num_tokens": 506593637.0, "step": 84770 }, { "epoch": 0.9044306700948439, "grad_norm": 0.7132381863071342, "learning_rate": 6.114612192836094e-06, "loss": 0.3742, "num_tokens": 506626715.0, "step": 84775 }, { "epoch": 0.9044840131010423, "grad_norm": 1.0872140564858335, "learning_rate": 6.113378775120089e-06, "loss": 0.4455, "num_tokens": 506651564.0, "step": 84780 }, { "epoch": 0.9045373561072407, "grad_norm": 0.8219473671434683, "learning_rate": 6.112146022911806e-06, "loss": 0.5361, "num_tokens": 506688385.0, "step": 84785 }, { "epoch": 0.9045906991134393, "grad_norm": 1.0597420199382444, "learning_rate": 6.110913936249611e-06, "loss": 0.3936, "num_tokens": 506719784.0, "step": 84790 }, { "epoch": 0.9046440421196377, "grad_norm": 0.8297727518219483, "learning_rate": 6.109682515171835e-06, "loss": 0.3862, "num_tokens": 506747308.0, "step": 84795 }, { "epoch": 0.9046973851258362, "grad_norm": 0.7314121780691749, "learning_rate": 6.108451759716808e-06, "loss": 0.4483, "num_tokens": 506777983.0, "step": 84800 }, { "epoch": 0.9047507281320346, "grad_norm": 1.3074305300879023, "learning_rate": 6.1072216699228215e-06, "loss": 0.4931, "num_tokens": 506807473.0, "step": 84805 }, { "epoch": 0.904804071138233, "grad_norm": 1.0200585007033338, "learning_rate": 6.10599224582815e-06, "loss": 0.489, "num_tokens": 506838182.0, "step": 84810 }, { "epoch": 0.9048574141444315, "grad_norm": 0.9035829333447278, "learning_rate": 6.104763487471056e-06, "loss": 0.5314, "num_tokens": 506867057.0, "step": 84815 }, { "epoch": 0.90491075715063, "grad_norm": 2.4582688247219173, "learning_rate": 6.10353539488978e-06, "loss": 0.5276, "num_tokens": 506888965.0, "step": 84820 }, { "epoch": 0.9049641001568285, "grad_norm": 0.8903157618969281, "learning_rate": 6.102307968122529e-06, "loss": 0.3952, "num_tokens": 506928851.0, "step": 84825 }, { "epoch": 0.9050174431630269, "grad_norm": 0.551803985655242, "learning_rate": 6.101081207207503e-06, "loss": 0.4985, "num_tokens": 506953491.0, "step": 84830 }, { "epoch": 0.9050707861692253, "grad_norm": 1.2087229263667445, "learning_rate": 6.0998551121828766e-06, "loss": 0.5606, "num_tokens": 506978917.0, "step": 84835 }, { "epoch": 0.9051241291754238, "grad_norm": 0.5366372355462846, "learning_rate": 6.098629683086802e-06, "loss": 0.5864, "num_tokens": 507019882.0, "step": 84840 }, { "epoch": 0.9051774721816223, "grad_norm": 1.0878206830356292, "learning_rate": 6.097404919957407e-06, "loss": 0.4992, "num_tokens": 507042941.0, "step": 84845 }, { "epoch": 0.9052308151878207, "grad_norm": 0.9470594192654258, "learning_rate": 6.096180822832816e-06, "loss": 0.3835, "num_tokens": 507074292.0, "step": 84850 }, { "epoch": 0.9052841581940192, "grad_norm": 0.7001343387627894, "learning_rate": 6.094957391751108e-06, "loss": 0.4297, "num_tokens": 507096663.0, "step": 84855 }, { "epoch": 0.9053375012002176, "grad_norm": 1.8174119737555783, "learning_rate": 6.093734626750358e-06, "loss": 0.3737, "num_tokens": 507121272.0, "step": 84860 }, { "epoch": 0.9053908442064161, "grad_norm": 1.2496561654552185, "learning_rate": 6.092512527868621e-06, "loss": 0.558, "num_tokens": 507148412.0, "step": 84865 }, { "epoch": 0.9054441872126145, "grad_norm": 1.8495500674982281, "learning_rate": 6.091291095143921e-06, "loss": 0.5139, "num_tokens": 507179755.0, "step": 84870 }, { "epoch": 0.905497530218813, "grad_norm": 0.8698182632920858, "learning_rate": 6.090070328614264e-06, "loss": 0.4788, "num_tokens": 507214102.0, "step": 84875 }, { "epoch": 0.9055508732250115, "grad_norm": 0.8666223253577549, "learning_rate": 6.088850228317644e-06, "loss": 0.4102, "num_tokens": 507242454.0, "step": 84880 }, { "epoch": 0.9056042162312099, "grad_norm": 1.001891264031291, "learning_rate": 6.087630794292025e-06, "loss": 0.4118, "num_tokens": 507284278.0, "step": 84885 }, { "epoch": 0.9056575592374084, "grad_norm": 1.0579687495147498, "learning_rate": 6.0864120265753514e-06, "loss": 0.5042, "num_tokens": 507314144.0, "step": 84890 }, { "epoch": 0.9057109022436068, "grad_norm": 1.2301922254798543, "learning_rate": 6.085193925205553e-06, "loss": 0.5166, "num_tokens": 507348674.0, "step": 84895 }, { "epoch": 0.9057642452498053, "grad_norm": 1.4533284314668198, "learning_rate": 6.08397649022053e-06, "loss": 0.4221, "num_tokens": 507380219.0, "step": 84900 }, { "epoch": 0.9058175882560038, "grad_norm": 0.9532749592521648, "learning_rate": 6.082759721658173e-06, "loss": 0.4072, "num_tokens": 507391342.0, "step": 84905 }, { "epoch": 0.9058709312622022, "grad_norm": 1.645832402160367, "learning_rate": 6.081543619556338e-06, "loss": 0.4291, "num_tokens": 507425327.0, "step": 84910 }, { "epoch": 0.9059242742684007, "grad_norm": 0.6892589234991263, "learning_rate": 6.0803281839528726e-06, "loss": 0.4254, "num_tokens": 507461551.0, "step": 84915 }, { "epoch": 0.9059776172745991, "grad_norm": 0.8488801277514803, "learning_rate": 6.079113414885593e-06, "loss": 0.3891, "num_tokens": 507485254.0, "step": 84920 }, { "epoch": 0.9060309602807975, "grad_norm": 0.8066737702838033, "learning_rate": 6.077899312392304e-06, "loss": 0.5164, "num_tokens": 507515136.0, "step": 84925 }, { "epoch": 0.9060843032869961, "grad_norm": 1.0415511088799467, "learning_rate": 6.076685876510792e-06, "loss": 0.4937, "num_tokens": 507553302.0, "step": 84930 }, { "epoch": 0.9061376462931945, "grad_norm": 0.6232972876256544, "learning_rate": 6.075473107278807e-06, "loss": 0.3778, "num_tokens": 507588966.0, "step": 84935 }, { "epoch": 0.9061909892993929, "grad_norm": 1.1320937883163786, "learning_rate": 6.074261004734093e-06, "loss": 0.4534, "num_tokens": 507611963.0, "step": 84940 }, { "epoch": 0.9062443323055914, "grad_norm": 0.588277639310309, "learning_rate": 6.073049568914368e-06, "loss": 0.4558, "num_tokens": 507654663.0, "step": 84945 }, { "epoch": 0.9062976753117898, "grad_norm": 1.0602379498400916, "learning_rate": 6.071838799857324e-06, "loss": 0.4347, "num_tokens": 507676158.0, "step": 84950 }, { "epoch": 0.9063510183179884, "grad_norm": 1.0388379649668333, "learning_rate": 6.070628697600643e-06, "loss": 0.4859, "num_tokens": 507707463.0, "step": 84955 }, { "epoch": 0.9064043613241868, "grad_norm": 0.8429339850381654, "learning_rate": 6.069419262181985e-06, "loss": 0.3896, "num_tokens": 507734020.0, "step": 84960 }, { "epoch": 0.9064577043303852, "grad_norm": 1.20780393938856, "learning_rate": 6.068210493638972e-06, "loss": 0.503, "num_tokens": 507765264.0, "step": 84965 }, { "epoch": 0.9065110473365837, "grad_norm": 1.1642467742036808, "learning_rate": 6.067002392009229e-06, "loss": 0.5445, "num_tokens": 507790850.0, "step": 84970 }, { "epoch": 0.9065643903427821, "grad_norm": 0.768128290083185, "learning_rate": 6.0657949573303495e-06, "loss": 0.3708, "num_tokens": 507813733.0, "step": 84975 }, { "epoch": 0.9066177333489807, "grad_norm": 1.2725621938216214, "learning_rate": 6.064588189639905e-06, "loss": 0.4001, "num_tokens": 507831362.0, "step": 84980 }, { "epoch": 0.9066710763551791, "grad_norm": 0.7508542507869053, "learning_rate": 6.063382088975442e-06, "loss": 0.4414, "num_tokens": 507872609.0, "step": 84985 }, { "epoch": 0.9067244193613775, "grad_norm": 0.8059731385460677, "learning_rate": 6.062176655374499e-06, "loss": 0.3585, "num_tokens": 507891879.0, "step": 84990 }, { "epoch": 0.906777762367576, "grad_norm": 0.7286827194157033, "learning_rate": 6.0609718888745824e-06, "loss": 0.4387, "num_tokens": 507921344.0, "step": 84995 }, { "epoch": 0.9068311053737744, "grad_norm": 0.8517723257476169, "learning_rate": 6.059767789513183e-06, "loss": 0.4732, "num_tokens": 507950462.0, "step": 85000 }, { "epoch": 0.906884448379973, "grad_norm": 0.6844514509247421, "learning_rate": 6.058564357327773e-06, "loss": 0.4218, "num_tokens": 507980360.0, "step": 85005 }, { "epoch": 0.9069377913861714, "grad_norm": 0.8670644253563325, "learning_rate": 6.057361592355796e-06, "loss": 0.509, "num_tokens": 508011651.0, "step": 85010 }, { "epoch": 0.9069911343923698, "grad_norm": 1.7121925371270672, "learning_rate": 6.056159494634683e-06, "loss": 0.5785, "num_tokens": 508052531.0, "step": 85015 }, { "epoch": 0.9070444773985683, "grad_norm": 1.3253225648257394, "learning_rate": 6.054958064201841e-06, "loss": 0.483, "num_tokens": 508071438.0, "step": 85020 }, { "epoch": 0.9070978204047667, "grad_norm": 0.8891369705334836, "learning_rate": 6.053757301094654e-06, "loss": 0.4355, "num_tokens": 508098629.0, "step": 85025 }, { "epoch": 0.9071511634109651, "grad_norm": 0.8362398279429505, "learning_rate": 6.052557205350485e-06, "loss": 0.3591, "num_tokens": 508116461.0, "step": 85030 }, { "epoch": 0.9072045064171637, "grad_norm": 0.7286174148109397, "learning_rate": 6.051357777006685e-06, "loss": 0.4698, "num_tokens": 508155189.0, "step": 85035 }, { "epoch": 0.9072578494233621, "grad_norm": 0.9310057126579121, "learning_rate": 6.050159016100572e-06, "loss": 0.436, "num_tokens": 508184799.0, "step": 85040 }, { "epoch": 0.9073111924295606, "grad_norm": 1.8165795675607013, "learning_rate": 6.0489609226694495e-06, "loss": 0.3928, "num_tokens": 508200024.0, "step": 85045 }, { "epoch": 0.907364535435759, "grad_norm": 1.1009403779123481, "learning_rate": 6.047763496750605e-06, "loss": 0.3981, "num_tokens": 508220599.0, "step": 85050 }, { "epoch": 0.9074178784419574, "grad_norm": 1.0010132558163372, "learning_rate": 6.046566738381295e-06, "loss": 0.4141, "num_tokens": 508242030.0, "step": 85055 }, { "epoch": 0.907471221448156, "grad_norm": 0.6894126816927618, "learning_rate": 6.045370647598762e-06, "loss": 0.4204, "num_tokens": 508267372.0, "step": 85060 }, { "epoch": 0.9075245644543544, "grad_norm": 0.6634291925716506, "learning_rate": 6.0441752244402255e-06, "loss": 0.4201, "num_tokens": 508300730.0, "step": 85065 }, { "epoch": 0.9075779074605529, "grad_norm": 1.4403276379355754, "learning_rate": 6.042980468942884e-06, "loss": 0.5124, "num_tokens": 508333175.0, "step": 85070 }, { "epoch": 0.9076312504667513, "grad_norm": 0.9160823847960234, "learning_rate": 6.041786381143916e-06, "loss": 0.468, "num_tokens": 508363681.0, "step": 85075 }, { "epoch": 0.9076845934729497, "grad_norm": 0.8578555939509562, "learning_rate": 6.040592961080481e-06, "loss": 0.4866, "num_tokens": 508392068.0, "step": 85080 }, { "epoch": 0.9077379364791482, "grad_norm": 0.622213734427481, "learning_rate": 6.039400208789711e-06, "loss": 0.4939, "num_tokens": 508415900.0, "step": 85085 }, { "epoch": 0.9077912794853467, "grad_norm": 1.5360502205703324, "learning_rate": 6.038208124308728e-06, "loss": 0.5539, "num_tokens": 508445543.0, "step": 85090 }, { "epoch": 0.9078446224915452, "grad_norm": 1.0200454893838407, "learning_rate": 6.037016707674626e-06, "loss": 0.3764, "num_tokens": 508473622.0, "step": 85095 }, { "epoch": 0.9078979654977436, "grad_norm": 2.390373806676195, "learning_rate": 6.0358259589244715e-06, "loss": 0.416, "num_tokens": 508505315.0, "step": 85100 }, { "epoch": 0.907951308503942, "grad_norm": 1.6794711223296848, "learning_rate": 6.034635878095329e-06, "loss": 0.5284, "num_tokens": 508541370.0, "step": 85105 }, { "epoch": 0.9080046515101405, "grad_norm": 1.1049162365111396, "learning_rate": 6.0334464652242266e-06, "loss": 0.4167, "num_tokens": 508551773.0, "step": 85110 }, { "epoch": 0.908057994516339, "grad_norm": 0.9322304260686466, "learning_rate": 6.032257720348174e-06, "loss": 0.4491, "num_tokens": 508576150.0, "step": 85115 }, { "epoch": 0.9081113375225374, "grad_norm": 0.9856688052234021, "learning_rate": 6.0310696435041666e-06, "loss": 0.4419, "num_tokens": 508607232.0, "step": 85120 }, { "epoch": 0.9081646805287359, "grad_norm": 0.7673473810333559, "learning_rate": 6.029882234729176e-06, "loss": 0.4676, "num_tokens": 508632774.0, "step": 85125 }, { "epoch": 0.9082180235349343, "grad_norm": 3.524584367641562, "learning_rate": 6.028695494060149e-06, "loss": 0.5342, "num_tokens": 508662434.0, "step": 85130 }, { "epoch": 0.9082713665411328, "grad_norm": 0.7309572002985872, "learning_rate": 6.027509421534012e-06, "loss": 0.5182, "num_tokens": 508705496.0, "step": 85135 }, { "epoch": 0.9083247095473312, "grad_norm": 1.2575283057409223, "learning_rate": 6.026324017187678e-06, "loss": 0.4754, "num_tokens": 508735112.0, "step": 85140 }, { "epoch": 0.9083780525535297, "grad_norm": 2.1027972171276197, "learning_rate": 6.02513928105803e-06, "loss": 0.423, "num_tokens": 508771983.0, "step": 85145 }, { "epoch": 0.9084313955597282, "grad_norm": 0.6113923222311614, "learning_rate": 6.023955213181938e-06, "loss": 0.3834, "num_tokens": 508804417.0, "step": 85150 }, { "epoch": 0.9084847385659266, "grad_norm": 0.8687041582092718, "learning_rate": 6.0227718135962505e-06, "loss": 0.4732, "num_tokens": 508830581.0, "step": 85155 }, { "epoch": 0.9085380815721251, "grad_norm": 1.3237815405913413, "learning_rate": 6.021589082337787e-06, "loss": 0.3697, "num_tokens": 508845272.0, "step": 85160 }, { "epoch": 0.9085914245783235, "grad_norm": 1.0245167739349066, "learning_rate": 6.02040701944335e-06, "loss": 0.2752, "num_tokens": 508859384.0, "step": 85165 }, { "epoch": 0.908644767584522, "grad_norm": 0.9678939944056908, "learning_rate": 6.01922562494973e-06, "loss": 0.5049, "num_tokens": 508885567.0, "step": 85170 }, { "epoch": 0.9086981105907205, "grad_norm": 1.2777298591286514, "learning_rate": 6.018044898893683e-06, "loss": 0.3224, "num_tokens": 508901473.0, "step": 85175 }, { "epoch": 0.9087514535969189, "grad_norm": 1.0735711274371995, "learning_rate": 6.016864841311952e-06, "loss": 0.5178, "num_tokens": 508941017.0, "step": 85180 }, { "epoch": 0.9088047966031174, "grad_norm": 0.8625165902115491, "learning_rate": 6.015685452241265e-06, "loss": 0.4328, "num_tokens": 508967467.0, "step": 85185 }, { "epoch": 0.9088581396093158, "grad_norm": 1.4680892173459679, "learning_rate": 6.01450673171831e-06, "loss": 0.4349, "num_tokens": 509000301.0, "step": 85190 }, { "epoch": 0.9089114826155142, "grad_norm": 1.1096028055973286, "learning_rate": 6.01332867977978e-06, "loss": 0.4874, "num_tokens": 509028859.0, "step": 85195 }, { "epoch": 0.9089648256217128, "grad_norm": 0.6793210018277847, "learning_rate": 6.012151296462324e-06, "loss": 0.6857, "num_tokens": 509060196.0, "step": 85200 }, { "epoch": 0.9090181686279112, "grad_norm": 0.9520949732101919, "learning_rate": 6.0109745818025795e-06, "loss": 0.3979, "num_tokens": 509091649.0, "step": 85205 }, { "epoch": 0.9090715116341096, "grad_norm": 0.7360494187454276, "learning_rate": 6.0097985358371675e-06, "loss": 0.487, "num_tokens": 509140623.0, "step": 85210 }, { "epoch": 0.9091248546403081, "grad_norm": 1.1752526462290669, "learning_rate": 6.008623158602687e-06, "loss": 0.3709, "num_tokens": 509159199.0, "step": 85215 }, { "epoch": 0.9091781976465065, "grad_norm": 3.362381796090777, "learning_rate": 6.007448450135704e-06, "loss": 0.4367, "num_tokens": 509185313.0, "step": 85220 }, { "epoch": 0.9092315406527051, "grad_norm": 2.001662271029061, "learning_rate": 6.006274410472779e-06, "loss": 0.418, "num_tokens": 509208541.0, "step": 85225 }, { "epoch": 0.9092848836589035, "grad_norm": 5.490339083031113, "learning_rate": 6.005101039650449e-06, "loss": 0.4511, "num_tokens": 509224992.0, "step": 85230 }, { "epoch": 0.9093382266651019, "grad_norm": 0.7640127655684024, "learning_rate": 6.003928337705219e-06, "loss": 0.3599, "num_tokens": 509251880.0, "step": 85235 }, { "epoch": 0.9093915696713004, "grad_norm": 1.6878296563675557, "learning_rate": 6.002756304673586e-06, "loss": 0.5143, "num_tokens": 509282176.0, "step": 85240 }, { "epoch": 0.9094449126774988, "grad_norm": 1.4081655800027693, "learning_rate": 6.001584940592022e-06, "loss": 0.4103, "num_tokens": 509317632.0, "step": 85245 }, { "epoch": 0.9094982556836974, "grad_norm": 1.4524973490246276, "learning_rate": 6.000414245496974e-06, "loss": 0.5024, "num_tokens": 509345260.0, "step": 85250 }, { "epoch": 0.9095515986898958, "grad_norm": 0.9588367998557128, "learning_rate": 5.999244219424871e-06, "loss": 0.457, "num_tokens": 509380596.0, "step": 85255 }, { "epoch": 0.9096049416960942, "grad_norm": 1.6772494021638136, "learning_rate": 5.998074862412129e-06, "loss": 0.5055, "num_tokens": 509413390.0, "step": 85260 }, { "epoch": 0.9096582847022927, "grad_norm": 1.2814956786608327, "learning_rate": 5.996906174495127e-06, "loss": 0.5375, "num_tokens": 509462252.0, "step": 85265 }, { "epoch": 0.9097116277084911, "grad_norm": 0.6430595621489754, "learning_rate": 5.995738155710238e-06, "loss": 0.4527, "num_tokens": 509498864.0, "step": 85270 }, { "epoch": 0.9097649707146896, "grad_norm": 0.759474630459851, "learning_rate": 5.994570806093809e-06, "loss": 0.406, "num_tokens": 509522881.0, "step": 85275 }, { "epoch": 0.9098183137208881, "grad_norm": 0.5846845913749128, "learning_rate": 5.993404125682158e-06, "loss": 0.4924, "num_tokens": 509565351.0, "step": 85280 }, { "epoch": 0.9098716567270865, "grad_norm": 2.2296691739333996, "learning_rate": 5.992238114511595e-06, "loss": 0.4807, "num_tokens": 509584767.0, "step": 85285 }, { "epoch": 0.909924999733285, "grad_norm": 0.6944382281813314, "learning_rate": 5.9910727726184095e-06, "loss": 0.4161, "num_tokens": 509606603.0, "step": 85290 }, { "epoch": 0.9099783427394834, "grad_norm": 1.1227394474840557, "learning_rate": 5.989908100038854e-06, "loss": 0.5037, "num_tokens": 509656476.0, "step": 85295 }, { "epoch": 0.9100316857456818, "grad_norm": 0.856494003564999, "learning_rate": 5.988744096809175e-06, "loss": 0.3823, "num_tokens": 509690629.0, "step": 85300 }, { "epoch": 0.9100850287518804, "grad_norm": 0.9486986397479741, "learning_rate": 5.987580762965595e-06, "loss": 0.4432, "num_tokens": 509722065.0, "step": 85305 }, { "epoch": 0.9101383717580788, "grad_norm": 0.8713115598849067, "learning_rate": 5.986418098544316e-06, "loss": 0.513, "num_tokens": 509753597.0, "step": 85310 }, { "epoch": 0.9101917147642773, "grad_norm": 0.8452406297430217, "learning_rate": 5.985256103581513e-06, "loss": 0.4958, "num_tokens": 509778690.0, "step": 85315 }, { "epoch": 0.9102450577704757, "grad_norm": 1.4529825392531963, "learning_rate": 5.984094778113352e-06, "loss": 0.3885, "num_tokens": 509796861.0, "step": 85320 }, { "epoch": 0.9102984007766741, "grad_norm": 1.1260203532739683, "learning_rate": 5.9829341221759624e-06, "loss": 0.4227, "num_tokens": 509822494.0, "step": 85325 }, { "epoch": 0.9103517437828726, "grad_norm": 0.9537677268947857, "learning_rate": 5.981774135805464e-06, "loss": 0.5224, "num_tokens": 509859160.0, "step": 85330 }, { "epoch": 0.9104050867890711, "grad_norm": 1.348044279865132, "learning_rate": 5.980614819037959e-06, "loss": 0.556, "num_tokens": 509888254.0, "step": 85335 }, { "epoch": 0.9104584297952696, "grad_norm": 1.2889440991259962, "learning_rate": 5.979456171909516e-06, "loss": 0.4344, "num_tokens": 509912425.0, "step": 85340 }, { "epoch": 0.910511772801468, "grad_norm": 2.255578479399088, "learning_rate": 5.978298194456195e-06, "loss": 0.4159, "num_tokens": 509924225.0, "step": 85345 }, { "epoch": 0.9105651158076664, "grad_norm": 1.3773394526553557, "learning_rate": 5.977140886714026e-06, "loss": 0.4401, "num_tokens": 509953636.0, "step": 85350 }, { "epoch": 0.9106184588138649, "grad_norm": 0.5608181534661512, "learning_rate": 5.975984248719023e-06, "loss": 0.4257, "num_tokens": 509997152.0, "step": 85355 }, { "epoch": 0.9106718018200634, "grad_norm": 1.0226015566655906, "learning_rate": 5.974828280507178e-06, "loss": 0.4959, "num_tokens": 510032318.0, "step": 85360 }, { "epoch": 0.9107251448262619, "grad_norm": 1.139773618043088, "learning_rate": 5.973672982114466e-06, "loss": 0.4403, "num_tokens": 510047219.0, "step": 85365 }, { "epoch": 0.9107784878324603, "grad_norm": 0.9507558810192298, "learning_rate": 5.97251835357683e-06, "loss": 0.3976, "num_tokens": 510081732.0, "step": 85370 }, { "epoch": 0.9108318308386587, "grad_norm": 0.8339139732821024, "learning_rate": 5.971364394930204e-06, "loss": 0.5525, "num_tokens": 510125567.0, "step": 85375 }, { "epoch": 0.9108851738448572, "grad_norm": 0.6921710814396633, "learning_rate": 5.970211106210502e-06, "loss": 0.4086, "num_tokens": 510147515.0, "step": 85380 }, { "epoch": 0.9109385168510556, "grad_norm": 1.0291412265216207, "learning_rate": 5.9690584874536065e-06, "loss": 0.4384, "num_tokens": 510172313.0, "step": 85385 }, { "epoch": 0.9109918598572541, "grad_norm": 0.8839684598819731, "learning_rate": 5.967906538695382e-06, "loss": 0.482, "num_tokens": 510207921.0, "step": 85390 }, { "epoch": 0.9110452028634526, "grad_norm": 0.6167021901548957, "learning_rate": 5.9667552599716796e-06, "loss": 0.45, "num_tokens": 510238427.0, "step": 85395 }, { "epoch": 0.911098545869651, "grad_norm": 1.24418564370293, "learning_rate": 5.965604651318319e-06, "loss": 0.4042, "num_tokens": 510255830.0, "step": 85400 }, { "epoch": 0.9111518888758495, "grad_norm": 1.4546616806631414, "learning_rate": 5.964454712771112e-06, "loss": 0.5403, "num_tokens": 510289751.0, "step": 85405 }, { "epoch": 0.9112052318820479, "grad_norm": 0.828897177789501, "learning_rate": 5.9633054443658394e-06, "loss": 0.4669, "num_tokens": 510330384.0, "step": 85410 }, { "epoch": 0.9112585748882464, "grad_norm": 1.851100488184622, "learning_rate": 5.962156846138263e-06, "loss": 0.3997, "num_tokens": 510360464.0, "step": 85415 }, { "epoch": 0.9113119178944449, "grad_norm": 0.8176755902732242, "learning_rate": 5.961008918124128e-06, "loss": 0.4816, "num_tokens": 510414371.0, "step": 85420 }, { "epoch": 0.9113652609006433, "grad_norm": 0.7330113865595237, "learning_rate": 5.959861660359152e-06, "loss": 0.4279, "num_tokens": 510444459.0, "step": 85425 }, { "epoch": 0.9114186039068418, "grad_norm": 1.2493539486890215, "learning_rate": 5.958715072879034e-06, "loss": 0.6038, "num_tokens": 510468822.0, "step": 85430 }, { "epoch": 0.9114719469130402, "grad_norm": 0.8842146961367678, "learning_rate": 5.957569155719454e-06, "loss": 0.554, "num_tokens": 510506409.0, "step": 85435 }, { "epoch": 0.9115252899192386, "grad_norm": 0.9891200716648678, "learning_rate": 5.956423908916078e-06, "loss": 0.5033, "num_tokens": 510543906.0, "step": 85440 }, { "epoch": 0.9115786329254372, "grad_norm": 0.9452633590740407, "learning_rate": 5.955279332504534e-06, "loss": 0.4015, "num_tokens": 510568359.0, "step": 85445 }, { "epoch": 0.9116319759316356, "grad_norm": 0.864251301108444, "learning_rate": 5.954135426520446e-06, "loss": 0.3793, "num_tokens": 510585923.0, "step": 85450 }, { "epoch": 0.9116853189378341, "grad_norm": 0.7796310344882538, "learning_rate": 5.952992190999408e-06, "loss": 0.4256, "num_tokens": 510610281.0, "step": 85455 }, { "epoch": 0.9117386619440325, "grad_norm": 0.9295178111044522, "learning_rate": 5.951849625976992e-06, "loss": 0.4296, "num_tokens": 510627514.0, "step": 85460 }, { "epoch": 0.9117920049502309, "grad_norm": 1.481585372535835, "learning_rate": 5.950707731488753e-06, "loss": 0.4296, "num_tokens": 510660383.0, "step": 85465 }, { "epoch": 0.9118453479564295, "grad_norm": 0.614776832420518, "learning_rate": 5.949566507570227e-06, "loss": 0.5305, "num_tokens": 510709593.0, "step": 85470 }, { "epoch": 0.9118986909626279, "grad_norm": 0.7888361142735284, "learning_rate": 5.948425954256925e-06, "loss": 0.5018, "num_tokens": 510758273.0, "step": 85475 }, { "epoch": 0.9119520339688263, "grad_norm": 0.8607001209192505, "learning_rate": 5.947286071584338e-06, "loss": 0.3999, "num_tokens": 510779529.0, "step": 85480 }, { "epoch": 0.9120053769750248, "grad_norm": 0.8205487159461773, "learning_rate": 5.946146859587944e-06, "loss": 0.4426, "num_tokens": 510801560.0, "step": 85485 }, { "epoch": 0.9120587199812232, "grad_norm": 0.8039486454840667, "learning_rate": 5.945008318303183e-06, "loss": 0.5185, "num_tokens": 510839600.0, "step": 85490 }, { "epoch": 0.9121120629874218, "grad_norm": 1.74463182247374, "learning_rate": 5.943870447765484e-06, "loss": 0.4884, "num_tokens": 510860531.0, "step": 85495 }, { "epoch": 0.9121654059936202, "grad_norm": 1.698197402978185, "learning_rate": 5.942733248010266e-06, "loss": 0.4823, "num_tokens": 510882412.0, "step": 85500 }, { "epoch": 0.9122187489998186, "grad_norm": 0.7117757846017503, "learning_rate": 5.941596719072904e-06, "loss": 0.46, "num_tokens": 510919311.0, "step": 85505 }, { "epoch": 0.9122720920060171, "grad_norm": 1.2553620976516513, "learning_rate": 5.940460860988772e-06, "loss": 0.3234, "num_tokens": 510937137.0, "step": 85510 }, { "epoch": 0.9123254350122155, "grad_norm": 0.7182939895642014, "learning_rate": 5.939325673793215e-06, "loss": 0.3929, "num_tokens": 510962393.0, "step": 85515 }, { "epoch": 0.912378778018414, "grad_norm": 0.8183584558483089, "learning_rate": 5.938191157521552e-06, "loss": 0.3904, "num_tokens": 510992245.0, "step": 85520 }, { "epoch": 0.9124321210246125, "grad_norm": 0.7256909064289006, "learning_rate": 5.937057312209095e-06, "loss": 0.4527, "num_tokens": 511036902.0, "step": 85525 }, { "epoch": 0.9124854640308109, "grad_norm": 0.8894843684849095, "learning_rate": 5.935924137891125e-06, "loss": 0.4494, "num_tokens": 511073303.0, "step": 85530 }, { "epoch": 0.9125388070370094, "grad_norm": 0.9448179992094388, "learning_rate": 5.934791634602897e-06, "loss": 0.4233, "num_tokens": 511105120.0, "step": 85535 }, { "epoch": 0.9125921500432078, "grad_norm": 0.760670509474197, "learning_rate": 5.933659802379657e-06, "loss": 0.4564, "num_tokens": 511142419.0, "step": 85540 }, { "epoch": 0.9126454930494063, "grad_norm": 5.5149068110925175, "learning_rate": 5.932528641256628e-06, "loss": 0.5548, "num_tokens": 511168343.0, "step": 85545 }, { "epoch": 0.9126988360556048, "grad_norm": 0.811410161482646, "learning_rate": 5.931398151269004e-06, "loss": 0.3517, "num_tokens": 511185191.0, "step": 85550 }, { "epoch": 0.9127521790618032, "grad_norm": 0.6066316416427237, "learning_rate": 5.930268332451966e-06, "loss": 0.497, "num_tokens": 511212466.0, "step": 85555 }, { "epoch": 0.9128055220680017, "grad_norm": 0.6829724160484212, "learning_rate": 5.929139184840677e-06, "loss": 0.328, "num_tokens": 511238360.0, "step": 85560 }, { "epoch": 0.9128588650742001, "grad_norm": 1.4545729822512936, "learning_rate": 5.928010708470268e-06, "loss": 0.4742, "num_tokens": 511258924.0, "step": 85565 }, { "epoch": 0.9129122080803985, "grad_norm": 0.6467650279806457, "learning_rate": 5.926882903375852e-06, "loss": 0.5303, "num_tokens": 511287456.0, "step": 85570 }, { "epoch": 0.912965551086597, "grad_norm": 1.3526247730910188, "learning_rate": 5.925755769592528e-06, "loss": 0.5993, "num_tokens": 511325399.0, "step": 85575 }, { "epoch": 0.9130188940927955, "grad_norm": 1.1855121388323981, "learning_rate": 5.92462930715537e-06, "loss": 0.4524, "num_tokens": 511354786.0, "step": 85580 }, { "epoch": 0.913072237098994, "grad_norm": 0.7633529245890122, "learning_rate": 5.923503516099432e-06, "loss": 0.5433, "num_tokens": 511402703.0, "step": 85585 }, { "epoch": 0.9131255801051924, "grad_norm": 0.8178072751263412, "learning_rate": 5.922378396459746e-06, "loss": 0.5197, "num_tokens": 511446697.0, "step": 85590 }, { "epoch": 0.9131789231113908, "grad_norm": 0.8311417830679525, "learning_rate": 5.9212539482713205e-06, "loss": 0.4029, "num_tokens": 511475816.0, "step": 85595 }, { "epoch": 0.9132322661175893, "grad_norm": 0.9057972855460418, "learning_rate": 5.920130171569152e-06, "loss": 0.4098, "num_tokens": 511507212.0, "step": 85600 }, { "epoch": 0.9132856091237878, "grad_norm": 0.8901731347981059, "learning_rate": 5.919007066388203e-06, "loss": 0.4577, "num_tokens": 511539255.0, "step": 85605 }, { "epoch": 0.9133389521299863, "grad_norm": 0.6349946331995315, "learning_rate": 5.9178846327634256e-06, "loss": 0.4164, "num_tokens": 511582094.0, "step": 85610 }, { "epoch": 0.9133922951361847, "grad_norm": 0.9014294682259202, "learning_rate": 5.916762870729746e-06, "loss": 0.5791, "num_tokens": 511610875.0, "step": 85615 }, { "epoch": 0.9134456381423831, "grad_norm": 2.633990049784913, "learning_rate": 5.915641780322076e-06, "loss": 0.4769, "num_tokens": 511644403.0, "step": 85620 }, { "epoch": 0.9134989811485816, "grad_norm": 0.9085479808543808, "learning_rate": 5.914521361575295e-06, "loss": 0.4122, "num_tokens": 511665864.0, "step": 85625 }, { "epoch": 0.91355232415478, "grad_norm": 0.8155237304905342, "learning_rate": 5.91340161452427e-06, "loss": 0.4265, "num_tokens": 511688879.0, "step": 85630 }, { "epoch": 0.9136056671609786, "grad_norm": 1.0412317879813349, "learning_rate": 5.912282539203853e-06, "loss": 0.4657, "num_tokens": 511708699.0, "step": 85635 }, { "epoch": 0.913659010167177, "grad_norm": 0.7380436151997741, "learning_rate": 5.911164135648858e-06, "loss": 0.5018, "num_tokens": 511756954.0, "step": 85640 }, { "epoch": 0.9137123531733754, "grad_norm": 0.7220464601197607, "learning_rate": 5.910046403894089e-06, "loss": 0.4612, "num_tokens": 511793396.0, "step": 85645 }, { "epoch": 0.9137656961795739, "grad_norm": 0.6751560114229338, "learning_rate": 5.90892934397433e-06, "loss": 0.322, "num_tokens": 511814871.0, "step": 85650 }, { "epoch": 0.9138190391857723, "grad_norm": 1.3019327864135832, "learning_rate": 5.907812955924341e-06, "loss": 0.4602, "num_tokens": 511838311.0, "step": 85655 }, { "epoch": 0.9138723821919708, "grad_norm": 1.0220005681172257, "learning_rate": 5.906697239778858e-06, "loss": 0.4876, "num_tokens": 511864269.0, "step": 85660 }, { "epoch": 0.9139257251981693, "grad_norm": 0.9250469203144842, "learning_rate": 5.905582195572606e-06, "loss": 0.5239, "num_tokens": 511896295.0, "step": 85665 }, { "epoch": 0.9139790682043677, "grad_norm": 0.9657516124792046, "learning_rate": 5.904467823340279e-06, "loss": 0.664, "num_tokens": 511936764.0, "step": 85670 }, { "epoch": 0.9140324112105662, "grad_norm": 0.8721699850436767, "learning_rate": 5.903354123116557e-06, "loss": 0.4623, "num_tokens": 511969684.0, "step": 85675 }, { "epoch": 0.9140857542167646, "grad_norm": 0.9520944971796975, "learning_rate": 5.902241094936093e-06, "loss": 0.4726, "num_tokens": 512004574.0, "step": 85680 }, { "epoch": 0.914139097222963, "grad_norm": 1.6644992900593503, "learning_rate": 5.901128738833522e-06, "loss": 0.4232, "num_tokens": 512028323.0, "step": 85685 }, { "epoch": 0.9141924402291616, "grad_norm": 1.746467575151894, "learning_rate": 5.9000170548434564e-06, "loss": 0.5376, "num_tokens": 512051755.0, "step": 85690 }, { "epoch": 0.91424578323536, "grad_norm": 0.7036989219267037, "learning_rate": 5.898906043000497e-06, "loss": 0.4779, "num_tokens": 512091369.0, "step": 85695 }, { "epoch": 0.9142991262415585, "grad_norm": 0.9042109180861805, "learning_rate": 5.8977957033392095e-06, "loss": 0.4026, "num_tokens": 512126562.0, "step": 85700 }, { "epoch": 0.9143524692477569, "grad_norm": 0.7465678825920741, "learning_rate": 5.896686035894146e-06, "loss": 0.4846, "num_tokens": 512148111.0, "step": 85705 }, { "epoch": 0.9144058122539553, "grad_norm": 0.8537038298237069, "learning_rate": 5.895577040699841e-06, "loss": 0.4444, "num_tokens": 512175910.0, "step": 85710 }, { "epoch": 0.9144591552601539, "grad_norm": 1.1952709572837088, "learning_rate": 5.894468717790805e-06, "loss": 0.4151, "num_tokens": 512194227.0, "step": 85715 }, { "epoch": 0.9145124982663523, "grad_norm": 2.119010075722365, "learning_rate": 5.893361067201518e-06, "loss": 0.4702, "num_tokens": 512204760.0, "step": 85720 }, { "epoch": 0.9145658412725508, "grad_norm": 1.0077702720528525, "learning_rate": 5.892254088966456e-06, "loss": 0.4788, "num_tokens": 512237209.0, "step": 85725 }, { "epoch": 0.9146191842787492, "grad_norm": 0.6385728467795883, "learning_rate": 5.8911477831200614e-06, "loss": 0.4563, "num_tokens": 512274477.0, "step": 85730 }, { "epoch": 0.9146725272849476, "grad_norm": 1.1604232782611368, "learning_rate": 5.890042149696761e-06, "loss": 0.5643, "num_tokens": 512306232.0, "step": 85735 }, { "epoch": 0.9147258702911462, "grad_norm": 1.8564381520420057, "learning_rate": 5.8889371887309635e-06, "loss": 0.5427, "num_tokens": 512337873.0, "step": 85740 }, { "epoch": 0.9147792132973446, "grad_norm": 0.7903336597409844, "learning_rate": 5.88783290025705e-06, "loss": 0.5257, "num_tokens": 512373589.0, "step": 85745 }, { "epoch": 0.914832556303543, "grad_norm": 0.7527891591707901, "learning_rate": 5.8867292843093845e-06, "loss": 0.5198, "num_tokens": 512416217.0, "step": 85750 }, { "epoch": 0.9148858993097415, "grad_norm": 1.4767877205603646, "learning_rate": 5.885626340922308e-06, "loss": 0.6008, "num_tokens": 512444192.0, "step": 85755 }, { "epoch": 0.9149392423159399, "grad_norm": 1.5527725896112892, "learning_rate": 5.884524070130142e-06, "loss": 0.5301, "num_tokens": 512474084.0, "step": 85760 }, { "epoch": 0.9149925853221385, "grad_norm": 0.8237527177106881, "learning_rate": 5.883422471967185e-06, "loss": 0.3887, "num_tokens": 512501802.0, "step": 85765 }, { "epoch": 0.9150459283283369, "grad_norm": 0.5511207972466752, "learning_rate": 5.882321546467723e-06, "loss": 0.4365, "num_tokens": 512533409.0, "step": 85770 }, { "epoch": 0.9150992713345353, "grad_norm": 0.6213144034338005, "learning_rate": 5.881221293666009e-06, "loss": 0.4141, "num_tokens": 512568660.0, "step": 85775 }, { "epoch": 0.9151526143407338, "grad_norm": 0.8077684842508174, "learning_rate": 5.880121713596284e-06, "loss": 0.4561, "num_tokens": 512589544.0, "step": 85780 }, { "epoch": 0.9152059573469322, "grad_norm": 2.3427831195019544, "learning_rate": 5.879022806292763e-06, "loss": 0.4585, "num_tokens": 512609169.0, "step": 85785 }, { "epoch": 0.9152593003531307, "grad_norm": 0.6993971793439892, "learning_rate": 5.877924571789637e-06, "loss": 0.5347, "num_tokens": 512636653.0, "step": 85790 }, { "epoch": 0.9153126433593292, "grad_norm": 1.1953071108800353, "learning_rate": 5.8768270101210865e-06, "loss": 0.5681, "num_tokens": 512662676.0, "step": 85795 }, { "epoch": 0.9153659863655276, "grad_norm": 1.3316779506482153, "learning_rate": 5.875730121321267e-06, "loss": 0.4534, "num_tokens": 512684358.0, "step": 85800 }, { "epoch": 0.9154193293717261, "grad_norm": 1.0287585980381786, "learning_rate": 5.874633905424305e-06, "loss": 0.3988, "num_tokens": 512697651.0, "step": 85805 }, { "epoch": 0.9154726723779245, "grad_norm": 1.0261313707813624, "learning_rate": 5.873538362464318e-06, "loss": 0.4741, "num_tokens": 512740406.0, "step": 85810 }, { "epoch": 0.915526015384123, "grad_norm": 1.1783410554371168, "learning_rate": 5.872443492475396e-06, "loss": 0.4679, "num_tokens": 512761391.0, "step": 85815 }, { "epoch": 0.9155793583903215, "grad_norm": 0.9336354347371587, "learning_rate": 5.871349295491609e-06, "loss": 0.386, "num_tokens": 512798117.0, "step": 85820 }, { "epoch": 0.9156327013965199, "grad_norm": 1.1998020477914682, "learning_rate": 5.870255771547005e-06, "loss": 0.4419, "num_tokens": 512817002.0, "step": 85825 }, { "epoch": 0.9156860444027184, "grad_norm": 1.5765768780157, "learning_rate": 5.869162920675611e-06, "loss": 0.4832, "num_tokens": 512859558.0, "step": 85830 }, { "epoch": 0.9157393874089168, "grad_norm": 0.7746756948828829, "learning_rate": 5.868070742911436e-06, "loss": 0.4297, "num_tokens": 512893273.0, "step": 85835 }, { "epoch": 0.9157927304151152, "grad_norm": 1.239257193647467, "learning_rate": 5.866979238288465e-06, "loss": 0.3895, "num_tokens": 512906754.0, "step": 85840 }, { "epoch": 0.9158460734213137, "grad_norm": 0.9594341718534076, "learning_rate": 5.865888406840668e-06, "loss": 0.4658, "num_tokens": 512937520.0, "step": 85845 }, { "epoch": 0.9158994164275122, "grad_norm": 0.5616003709625859, "learning_rate": 5.864798248601984e-06, "loss": 0.4584, "num_tokens": 512971465.0, "step": 85850 }, { "epoch": 0.9159527594337107, "grad_norm": 0.9458818362400933, "learning_rate": 5.863708763606339e-06, "loss": 0.5923, "num_tokens": 512999506.0, "step": 85855 }, { "epoch": 0.9160061024399091, "grad_norm": 0.8887269186911856, "learning_rate": 5.862619951887633e-06, "loss": 0.5549, "num_tokens": 513035378.0, "step": 85860 }, { "epoch": 0.9160594454461075, "grad_norm": 1.3026629772692073, "learning_rate": 5.861531813479754e-06, "loss": 0.4533, "num_tokens": 513067597.0, "step": 85865 }, { "epoch": 0.916112788452306, "grad_norm": 0.6817582274372992, "learning_rate": 5.860444348416553e-06, "loss": 0.4043, "num_tokens": 513092412.0, "step": 85870 }, { "epoch": 0.9161661314585045, "grad_norm": 1.0081294823692961, "learning_rate": 5.859357556731877e-06, "loss": 0.5159, "num_tokens": 513132155.0, "step": 85875 }, { "epoch": 0.916219474464703, "grad_norm": 0.9043845379016529, "learning_rate": 5.858271438459545e-06, "loss": 0.3482, "num_tokens": 513153621.0, "step": 85880 }, { "epoch": 0.9162728174709014, "grad_norm": 1.2895015252336526, "learning_rate": 5.857185993633352e-06, "loss": 0.5292, "num_tokens": 513174463.0, "step": 85885 }, { "epoch": 0.9163261604770998, "grad_norm": 1.5431136531393952, "learning_rate": 5.856101222287075e-06, "loss": 0.3714, "num_tokens": 513201666.0, "step": 85890 }, { "epoch": 0.9163795034832983, "grad_norm": 0.7659317861914462, "learning_rate": 5.85501712445447e-06, "loss": 0.4013, "num_tokens": 513236707.0, "step": 85895 }, { "epoch": 0.9164328464894967, "grad_norm": 0.973994532467183, "learning_rate": 5.853933700169269e-06, "loss": 0.4613, "num_tokens": 513274619.0, "step": 85900 }, { "epoch": 0.9164861894956953, "grad_norm": 0.9339995192596874, "learning_rate": 5.8528509494651915e-06, "loss": 0.3759, "num_tokens": 513294631.0, "step": 85905 }, { "epoch": 0.9165395325018937, "grad_norm": 1.9886560006354428, "learning_rate": 5.8517688723759295e-06, "loss": 0.5828, "num_tokens": 513324409.0, "step": 85910 }, { "epoch": 0.9165928755080921, "grad_norm": 0.7806430265608488, "learning_rate": 5.850687468935149e-06, "loss": 0.4319, "num_tokens": 513351478.0, "step": 85915 }, { "epoch": 0.9166462185142906, "grad_norm": 1.2897041329859462, "learning_rate": 5.849606739176508e-06, "loss": 0.3914, "num_tokens": 513390253.0, "step": 85920 }, { "epoch": 0.916699561520489, "grad_norm": 0.8629152046340876, "learning_rate": 5.848526683133637e-06, "loss": 0.3635, "num_tokens": 513408611.0, "step": 85925 }, { "epoch": 0.9167529045266875, "grad_norm": 0.8119037519422282, "learning_rate": 5.847447300840142e-06, "loss": 0.3237, "num_tokens": 513427215.0, "step": 85930 }, { "epoch": 0.916806247532886, "grad_norm": 1.0193487039013422, "learning_rate": 5.846368592329605e-06, "loss": 0.5215, "num_tokens": 513451910.0, "step": 85935 }, { "epoch": 0.9168595905390844, "grad_norm": 0.7144776722704576, "learning_rate": 5.845290557635605e-06, "loss": 0.4224, "num_tokens": 513485263.0, "step": 85940 }, { "epoch": 0.9169129335452829, "grad_norm": 0.6277060285145589, "learning_rate": 5.84421319679168e-06, "loss": 0.5039, "num_tokens": 513524125.0, "step": 85945 }, { "epoch": 0.9169662765514813, "grad_norm": 1.1203912590255618, "learning_rate": 5.843136509831359e-06, "loss": 0.4782, "num_tokens": 513549804.0, "step": 85950 }, { "epoch": 0.9170196195576797, "grad_norm": 0.764536424431513, "learning_rate": 5.8420604967881474e-06, "loss": 0.3743, "num_tokens": 513590498.0, "step": 85955 }, { "epoch": 0.9170729625638783, "grad_norm": 0.8701593381966534, "learning_rate": 5.840985157695524e-06, "loss": 0.4383, "num_tokens": 513610183.0, "step": 85960 }, { "epoch": 0.9171263055700767, "grad_norm": 1.384131914758096, "learning_rate": 5.839910492586954e-06, "loss": 0.3807, "num_tokens": 513642255.0, "step": 85965 }, { "epoch": 0.9171796485762752, "grad_norm": 1.097756196594573, "learning_rate": 5.838836501495881e-06, "loss": 0.4363, "num_tokens": 513669004.0, "step": 85970 }, { "epoch": 0.9172329915824736, "grad_norm": 0.8543811930525227, "learning_rate": 5.83776318445572e-06, "loss": 0.4359, "num_tokens": 513694080.0, "step": 85975 }, { "epoch": 0.917286334588672, "grad_norm": 0.7362438174972988, "learning_rate": 5.836690541499871e-06, "loss": 0.4308, "num_tokens": 513729226.0, "step": 85980 }, { "epoch": 0.9173396775948706, "grad_norm": 1.699920081305974, "learning_rate": 5.8356185726617205e-06, "loss": 0.4348, "num_tokens": 513749545.0, "step": 85985 }, { "epoch": 0.917393020601069, "grad_norm": 0.7273231089923073, "learning_rate": 5.834547277974615e-06, "loss": 0.4123, "num_tokens": 513798414.0, "step": 85990 }, { "epoch": 0.9174463636072675, "grad_norm": 0.7552361362218133, "learning_rate": 5.833476657471897e-06, "loss": 0.4371, "num_tokens": 513830902.0, "step": 85995 }, { "epoch": 0.9174997066134659, "grad_norm": 1.1837234327070374, "learning_rate": 5.832406711186884e-06, "loss": 0.5085, "num_tokens": 513854890.0, "step": 86000 }, { "epoch": 0.9175530496196643, "grad_norm": 0.7257093960463377, "learning_rate": 5.831337439152866e-06, "loss": 0.3743, "num_tokens": 513887872.0, "step": 86005 }, { "epoch": 0.9176063926258629, "grad_norm": 0.8696325565932612, "learning_rate": 5.830268841403116e-06, "loss": 0.4507, "num_tokens": 513918619.0, "step": 86010 }, { "epoch": 0.9176597356320613, "grad_norm": 1.0167433217066921, "learning_rate": 5.829200917970894e-06, "loss": 0.3772, "num_tokens": 513948514.0, "step": 86015 }, { "epoch": 0.9177130786382597, "grad_norm": 0.8147302523669346, "learning_rate": 5.828133668889421e-06, "loss": 0.4639, "num_tokens": 513977462.0, "step": 86020 }, { "epoch": 0.9177664216444582, "grad_norm": 0.586475491765442, "learning_rate": 5.8270670941919156e-06, "loss": 0.4008, "num_tokens": 514014384.0, "step": 86025 }, { "epoch": 0.9178197646506566, "grad_norm": 1.1362695120085071, "learning_rate": 5.8260011939115635e-06, "loss": 0.4778, "num_tokens": 514041215.0, "step": 86030 }, { "epoch": 0.9178731076568551, "grad_norm": 0.6969200307940272, "learning_rate": 5.8249359680815345e-06, "loss": 0.3296, "num_tokens": 514064533.0, "step": 86035 }, { "epoch": 0.9179264506630536, "grad_norm": 1.1147140934816429, "learning_rate": 5.823871416734977e-06, "loss": 0.348, "num_tokens": 514088825.0, "step": 86040 }, { "epoch": 0.917979793669252, "grad_norm": 0.8439849027037721, "learning_rate": 5.82280753990502e-06, "loss": 0.4308, "num_tokens": 514119208.0, "step": 86045 }, { "epoch": 0.9180331366754505, "grad_norm": 0.6722598981872401, "learning_rate": 5.821744337624762e-06, "loss": 0.5799, "num_tokens": 514156510.0, "step": 86050 }, { "epoch": 0.9180864796816489, "grad_norm": 1.299640525903949, "learning_rate": 5.820681809927291e-06, "loss": 0.5871, "num_tokens": 514189806.0, "step": 86055 }, { "epoch": 0.9181398226878474, "grad_norm": 0.7050334941587307, "learning_rate": 5.819619956845675e-06, "loss": 0.474, "num_tokens": 514218934.0, "step": 86060 }, { "epoch": 0.9181931656940459, "grad_norm": 1.0129602999451135, "learning_rate": 5.818558778412951e-06, "loss": 0.4756, "num_tokens": 514237464.0, "step": 86065 }, { "epoch": 0.9182465087002443, "grad_norm": 1.4064083073833493, "learning_rate": 5.817498274662145e-06, "loss": 0.5366, "num_tokens": 514266016.0, "step": 86070 }, { "epoch": 0.9182998517064428, "grad_norm": 1.161097920571995, "learning_rate": 5.816438445626256e-06, "loss": 0.478, "num_tokens": 514300610.0, "step": 86075 }, { "epoch": 0.9183531947126412, "grad_norm": 1.6511586380310677, "learning_rate": 5.815379291338259e-06, "loss": 0.4868, "num_tokens": 514322576.0, "step": 86080 }, { "epoch": 0.9184065377188397, "grad_norm": 0.6202666578347781, "learning_rate": 5.814320811831118e-06, "loss": 0.4698, "num_tokens": 514355959.0, "step": 86085 }, { "epoch": 0.9184598807250381, "grad_norm": 0.6704564674940995, "learning_rate": 5.813263007137772e-06, "loss": 0.3306, "num_tokens": 514383791.0, "step": 86090 }, { "epoch": 0.9185132237312366, "grad_norm": 0.6539353480162323, "learning_rate": 5.812205877291135e-06, "loss": 0.354, "num_tokens": 514401413.0, "step": 86095 }, { "epoch": 0.9185665667374351, "grad_norm": 1.6761814681032008, "learning_rate": 5.8111494223240994e-06, "loss": 0.4461, "num_tokens": 514451638.0, "step": 86100 }, { "epoch": 0.9186199097436335, "grad_norm": 1.3429768620649984, "learning_rate": 5.810093642269547e-06, "loss": 0.5629, "num_tokens": 514470895.0, "step": 86105 }, { "epoch": 0.9186732527498319, "grad_norm": 1.160797173437733, "learning_rate": 5.80903853716033e-06, "loss": 0.3505, "num_tokens": 514496994.0, "step": 86110 }, { "epoch": 0.9187265957560304, "grad_norm": 0.730118564260048, "learning_rate": 5.807984107029276e-06, "loss": 0.4012, "num_tokens": 514521698.0, "step": 86115 }, { "epoch": 0.9187799387622289, "grad_norm": 0.9294270338644148, "learning_rate": 5.806930351909202e-06, "loss": 0.4073, "num_tokens": 514536338.0, "step": 86120 }, { "epoch": 0.9188332817684274, "grad_norm": 0.7745833079708278, "learning_rate": 5.805877271832896e-06, "loss": 0.4641, "num_tokens": 514583897.0, "step": 86125 }, { "epoch": 0.9188866247746258, "grad_norm": 0.7038352597836978, "learning_rate": 5.804824866833125e-06, "loss": 0.4288, "num_tokens": 514616417.0, "step": 86130 }, { "epoch": 0.9189399677808242, "grad_norm": 0.9571411099076313, "learning_rate": 5.8037731369426445e-06, "loss": 0.3573, "num_tokens": 514647387.0, "step": 86135 }, { "epoch": 0.9189933107870227, "grad_norm": 1.176320541269689, "learning_rate": 5.802722082194176e-06, "loss": 0.488, "num_tokens": 514692622.0, "step": 86140 }, { "epoch": 0.9190466537932211, "grad_norm": 0.7926661999532251, "learning_rate": 5.801671702620435e-06, "loss": 0.4942, "num_tokens": 514722895.0, "step": 86145 }, { "epoch": 0.9190999967994197, "grad_norm": 0.6910457209882844, "learning_rate": 5.8006219982540976e-06, "loss": 0.4918, "num_tokens": 514748297.0, "step": 86150 }, { "epoch": 0.9191533398056181, "grad_norm": 1.5567837951322758, "learning_rate": 5.79957296912783e-06, "loss": 0.4089, "num_tokens": 514778146.0, "step": 86155 }, { "epoch": 0.9192066828118165, "grad_norm": 1.0837235802364689, "learning_rate": 5.798524615274277e-06, "loss": 0.4573, "num_tokens": 514805282.0, "step": 86160 }, { "epoch": 0.919260025818015, "grad_norm": 1.290917506806076, "learning_rate": 5.797476936726064e-06, "loss": 0.5474, "num_tokens": 514838148.0, "step": 86165 }, { "epoch": 0.9193133688242134, "grad_norm": 0.8387732431127317, "learning_rate": 5.796429933515788e-06, "loss": 0.4385, "num_tokens": 514873141.0, "step": 86170 }, { "epoch": 0.919366711830412, "grad_norm": 0.9438001764727346, "learning_rate": 5.795383605676034e-06, "loss": 0.6382, "num_tokens": 514894500.0, "step": 86175 }, { "epoch": 0.9194200548366104, "grad_norm": 0.7255603219565244, "learning_rate": 5.794337953239359e-06, "loss": 0.4745, "num_tokens": 514930450.0, "step": 86180 }, { "epoch": 0.9194733978428088, "grad_norm": 1.424115689672472, "learning_rate": 5.793292976238304e-06, "loss": 0.4834, "num_tokens": 514960888.0, "step": 86185 }, { "epoch": 0.9195267408490073, "grad_norm": 1.5435152558894183, "learning_rate": 5.792248674705383e-06, "loss": 0.4082, "num_tokens": 514985101.0, "step": 86190 }, { "epoch": 0.9195800838552057, "grad_norm": 1.0403267455546714, "learning_rate": 5.7912050486730975e-06, "loss": 0.5093, "num_tokens": 515005217.0, "step": 86195 }, { "epoch": 0.9196334268614041, "grad_norm": 1.006930969615051, "learning_rate": 5.790162098173917e-06, "loss": 0.4236, "num_tokens": 515021979.0, "step": 86200 }, { "epoch": 0.9196867698676027, "grad_norm": 1.0025279455488942, "learning_rate": 5.789119823240296e-06, "loss": 0.3763, "num_tokens": 515048772.0, "step": 86205 }, { "epoch": 0.9197401128738011, "grad_norm": 0.7288476282082715, "learning_rate": 5.788078223904675e-06, "loss": 0.585, "num_tokens": 515079963.0, "step": 86210 }, { "epoch": 0.9197934558799996, "grad_norm": 1.169036652044783, "learning_rate": 5.787037300199459e-06, "loss": 0.3998, "num_tokens": 515110684.0, "step": 86215 }, { "epoch": 0.919846798886198, "grad_norm": 0.805827149455554, "learning_rate": 5.785997052157044e-06, "loss": 0.4671, "num_tokens": 515140002.0, "step": 86220 }, { "epoch": 0.9199001418923964, "grad_norm": 2.4331967549325006, "learning_rate": 5.784957479809801e-06, "loss": 0.4781, "num_tokens": 515165191.0, "step": 86225 }, { "epoch": 0.919953484898595, "grad_norm": 1.111505207550121, "learning_rate": 5.783918583190075e-06, "loss": 0.6694, "num_tokens": 515184405.0, "step": 86230 }, { "epoch": 0.9200068279047934, "grad_norm": 0.6807828311712971, "learning_rate": 5.782880362330196e-06, "loss": 0.4131, "num_tokens": 515211439.0, "step": 86235 }, { "epoch": 0.9200601709109919, "grad_norm": 0.6856462230158921, "learning_rate": 5.781842817262474e-06, "loss": 0.4142, "num_tokens": 515252229.0, "step": 86240 }, { "epoch": 0.9201135139171903, "grad_norm": 0.8442051010517837, "learning_rate": 5.78080594801919e-06, "loss": 0.4343, "num_tokens": 515280765.0, "step": 86245 }, { "epoch": 0.9201668569233887, "grad_norm": 0.9863568071569526, "learning_rate": 5.779769754632613e-06, "loss": 0.472, "num_tokens": 515311960.0, "step": 86250 }, { "epoch": 0.9202201999295873, "grad_norm": 1.2272319302506542, "learning_rate": 5.778734237134988e-06, "loss": 0.471, "num_tokens": 515340068.0, "step": 86255 }, { "epoch": 0.9202735429357857, "grad_norm": 0.6167256432305922, "learning_rate": 5.7776993955585405e-06, "loss": 0.3795, "num_tokens": 515364568.0, "step": 86260 }, { "epoch": 0.9203268859419842, "grad_norm": 1.292568529701259, "learning_rate": 5.776665229935463e-06, "loss": 0.3956, "num_tokens": 515385459.0, "step": 86265 }, { "epoch": 0.9203802289481826, "grad_norm": 1.2531745134699002, "learning_rate": 5.775631740297946e-06, "loss": 0.3967, "num_tokens": 515412116.0, "step": 86270 }, { "epoch": 0.920433571954381, "grad_norm": 1.1115392729500595, "learning_rate": 5.774598926678143e-06, "loss": 0.5135, "num_tokens": 515449964.0, "step": 86275 }, { "epoch": 0.9204869149605795, "grad_norm": 0.7471204133088618, "learning_rate": 5.7735667891081955e-06, "loss": 0.5153, "num_tokens": 515495116.0, "step": 86280 }, { "epoch": 0.920540257966778, "grad_norm": 0.8602445630270398, "learning_rate": 5.772535327620227e-06, "loss": 0.4835, "num_tokens": 515542550.0, "step": 86285 }, { "epoch": 0.9205936009729764, "grad_norm": 1.152255809265067, "learning_rate": 5.771504542246325e-06, "loss": 0.5194, "num_tokens": 515559501.0, "step": 86290 }, { "epoch": 0.9206469439791749, "grad_norm": 1.0362119952579159, "learning_rate": 5.770474433018573e-06, "loss": 0.4619, "num_tokens": 515586377.0, "step": 86295 }, { "epoch": 0.9207002869853733, "grad_norm": 1.3723846991136406, "learning_rate": 5.769444999969024e-06, "loss": 0.4695, "num_tokens": 515622230.0, "step": 86300 }, { "epoch": 0.9207536299915718, "grad_norm": 0.8481266610684315, "learning_rate": 5.768416243129707e-06, "loss": 0.4084, "num_tokens": 515646213.0, "step": 86305 }, { "epoch": 0.9208069729977703, "grad_norm": 1.0116387408857008, "learning_rate": 5.767388162532641e-06, "loss": 0.4216, "num_tokens": 515670924.0, "step": 86310 }, { "epoch": 0.9208603160039687, "grad_norm": 1.0143995020820846, "learning_rate": 5.766360758209816e-06, "loss": 0.5256, "num_tokens": 515699083.0, "step": 86315 }, { "epoch": 0.9209136590101672, "grad_norm": 0.7383889957188497, "learning_rate": 5.765334030193199e-06, "loss": 0.4851, "num_tokens": 515732327.0, "step": 86320 }, { "epoch": 0.9209670020163656, "grad_norm": 0.6847789400927802, "learning_rate": 5.764307978514743e-06, "loss": 0.4594, "num_tokens": 515769812.0, "step": 86325 }, { "epoch": 0.9210203450225641, "grad_norm": 1.0665605718819564, "learning_rate": 5.76328260320638e-06, "loss": 0.4067, "num_tokens": 515796404.0, "step": 86330 }, { "epoch": 0.9210736880287625, "grad_norm": 0.6814515907730067, "learning_rate": 5.762257904300013e-06, "loss": 0.4808, "num_tokens": 515838747.0, "step": 86335 }, { "epoch": 0.921127031034961, "grad_norm": 1.0871218556162179, "learning_rate": 5.7612338818275245e-06, "loss": 0.547, "num_tokens": 515881768.0, "step": 86340 }, { "epoch": 0.9211803740411595, "grad_norm": 0.9636726246164237, "learning_rate": 5.76021053582079e-06, "loss": 0.6162, "num_tokens": 515908898.0, "step": 86345 }, { "epoch": 0.9212337170473579, "grad_norm": 0.9015235772196283, "learning_rate": 5.759187866311647e-06, "loss": 0.3592, "num_tokens": 515924044.0, "step": 86350 }, { "epoch": 0.9212870600535564, "grad_norm": 0.7379238161699196, "learning_rate": 5.75816587333192e-06, "loss": 0.4401, "num_tokens": 515947072.0, "step": 86355 }, { "epoch": 0.9213404030597548, "grad_norm": 0.9566427195546285, "learning_rate": 5.757144556913413e-06, "loss": 0.3762, "num_tokens": 515974496.0, "step": 86360 }, { "epoch": 0.9213937460659533, "grad_norm": 1.072796911426347, "learning_rate": 5.756123917087908e-06, "loss": 0.576, "num_tokens": 516001619.0, "step": 86365 }, { "epoch": 0.9214470890721518, "grad_norm": 1.2000262375858013, "learning_rate": 5.7551039538871616e-06, "loss": 0.5508, "num_tokens": 516035837.0, "step": 86370 }, { "epoch": 0.9215004320783502, "grad_norm": 1.0240007841253014, "learning_rate": 5.7540846673429154e-06, "loss": 0.487, "num_tokens": 516073607.0, "step": 86375 }, { "epoch": 0.9215537750845486, "grad_norm": 0.7949436263844072, "learning_rate": 5.753066057486886e-06, "loss": 0.4487, "num_tokens": 516107062.0, "step": 86380 }, { "epoch": 0.9216071180907471, "grad_norm": 1.02886409887526, "learning_rate": 5.75204812435077e-06, "loss": 0.5653, "num_tokens": 516135196.0, "step": 86385 }, { "epoch": 0.9216604610969455, "grad_norm": 1.2803101621972126, "learning_rate": 5.75103086796625e-06, "loss": 0.3486, "num_tokens": 516154274.0, "step": 86390 }, { "epoch": 0.9217138041031441, "grad_norm": 0.7179101228189505, "learning_rate": 5.750014288364971e-06, "loss": 0.5507, "num_tokens": 516195543.0, "step": 86395 }, { "epoch": 0.9217671471093425, "grad_norm": 1.0510303194515147, "learning_rate": 5.748998385578574e-06, "loss": 0.604, "num_tokens": 516216104.0, "step": 86400 }, { "epoch": 0.9218204901155409, "grad_norm": 2.0323873262951597, "learning_rate": 5.74798315963867e-06, "loss": 0.4901, "num_tokens": 516237368.0, "step": 86405 }, { "epoch": 0.9218738331217394, "grad_norm": 0.9350919605168833, "learning_rate": 5.746968610576847e-06, "loss": 0.4496, "num_tokens": 516264206.0, "step": 86410 }, { "epoch": 0.9219271761279378, "grad_norm": 0.7644457064770785, "learning_rate": 5.745954738424679e-06, "loss": 0.3779, "num_tokens": 516305565.0, "step": 86415 }, { "epoch": 0.9219805191341364, "grad_norm": 1.0444902413264239, "learning_rate": 5.7449415432137186e-06, "loss": 0.4645, "num_tokens": 516320776.0, "step": 86420 }, { "epoch": 0.9220338621403348, "grad_norm": 1.0007202475767387, "learning_rate": 5.7439290249754885e-06, "loss": 0.4083, "num_tokens": 516341510.0, "step": 86425 }, { "epoch": 0.9220872051465332, "grad_norm": 0.7270961355212787, "learning_rate": 5.7429171837414984e-06, "loss": 0.3687, "num_tokens": 516377122.0, "step": 86430 }, { "epoch": 0.9221405481527317, "grad_norm": 0.7082371354830032, "learning_rate": 5.741906019543239e-06, "loss": 0.4607, "num_tokens": 516411707.0, "step": 86435 }, { "epoch": 0.9221938911589301, "grad_norm": 0.7813230496917023, "learning_rate": 5.740895532412171e-06, "loss": 0.3767, "num_tokens": 516428806.0, "step": 86440 }, { "epoch": 0.9222472341651287, "grad_norm": 0.8279845058619042, "learning_rate": 5.739885722379738e-06, "loss": 0.4328, "num_tokens": 516458261.0, "step": 86445 }, { "epoch": 0.9223005771713271, "grad_norm": 1.2363311373342531, "learning_rate": 5.738876589477365e-06, "loss": 0.4277, "num_tokens": 516484257.0, "step": 86450 }, { "epoch": 0.9223539201775255, "grad_norm": 0.7594249977894715, "learning_rate": 5.737868133736453e-06, "loss": 0.4761, "num_tokens": 516520103.0, "step": 86455 }, { "epoch": 0.922407263183724, "grad_norm": 1.2682791203953052, "learning_rate": 5.736860355188384e-06, "loss": 0.4065, "num_tokens": 516548913.0, "step": 86460 }, { "epoch": 0.9224606061899224, "grad_norm": 0.7179651490102913, "learning_rate": 5.73585325386452e-06, "loss": 0.5434, "num_tokens": 516575921.0, "step": 86465 }, { "epoch": 0.9225139491961208, "grad_norm": 0.7209134091687672, "learning_rate": 5.734846829796197e-06, "loss": 0.4583, "num_tokens": 516608520.0, "step": 86470 }, { "epoch": 0.9225672922023194, "grad_norm": 3.74760167451327, "learning_rate": 5.733841083014734e-06, "loss": 0.5627, "num_tokens": 516633865.0, "step": 86475 }, { "epoch": 0.9226206352085178, "grad_norm": 0.7427641779968158, "learning_rate": 5.732836013551428e-06, "loss": 0.4345, "num_tokens": 516659025.0, "step": 86480 }, { "epoch": 0.9226739782147163, "grad_norm": 0.9118277574081551, "learning_rate": 5.731831621437552e-06, "loss": 0.3856, "num_tokens": 516698937.0, "step": 86485 }, { "epoch": 0.9227273212209147, "grad_norm": 0.7500907478758391, "learning_rate": 5.730827906704362e-06, "loss": 0.4511, "num_tokens": 516736333.0, "step": 86490 }, { "epoch": 0.9227806642271131, "grad_norm": 0.9182815791095789, "learning_rate": 5.729824869383095e-06, "loss": 0.546, "num_tokens": 516790626.0, "step": 86495 }, { "epoch": 0.9228340072333117, "grad_norm": 0.9123928594447485, "learning_rate": 5.7288225095049616e-06, "loss": 0.4084, "num_tokens": 516810382.0, "step": 86500 }, { "epoch": 0.9228873502395101, "grad_norm": 0.8723463185339438, "learning_rate": 5.727820827101148e-06, "loss": 0.3921, "num_tokens": 516839460.0, "step": 86505 }, { "epoch": 0.9229406932457086, "grad_norm": 0.8663041257083813, "learning_rate": 5.726819822202835e-06, "loss": 0.6219, "num_tokens": 516875492.0, "step": 86510 }, { "epoch": 0.922994036251907, "grad_norm": 1.1689881135667624, "learning_rate": 5.725819494841163e-06, "loss": 0.5504, "num_tokens": 516916468.0, "step": 86515 }, { "epoch": 0.9230473792581054, "grad_norm": 1.3097681787069704, "learning_rate": 5.724819845047263e-06, "loss": 0.4028, "num_tokens": 516937715.0, "step": 86520 }, { "epoch": 0.923100722264304, "grad_norm": 0.8716759702758989, "learning_rate": 5.723820872852243e-06, "loss": 0.45, "num_tokens": 516963220.0, "step": 86525 }, { "epoch": 0.9231540652705024, "grad_norm": 0.8106609009034111, "learning_rate": 5.722822578287185e-06, "loss": 0.4278, "num_tokens": 516992583.0, "step": 86530 }, { "epoch": 0.9232074082767009, "grad_norm": 0.8608885733427244, "learning_rate": 5.721824961383156e-06, "loss": 0.4588, "num_tokens": 517037450.0, "step": 86535 }, { "epoch": 0.9232607512828993, "grad_norm": 1.1888790295484644, "learning_rate": 5.7208280221712046e-06, "loss": 0.5088, "num_tokens": 517071269.0, "step": 86540 }, { "epoch": 0.9233140942890977, "grad_norm": 1.0475164978171339, "learning_rate": 5.719831760682347e-06, "loss": 0.5268, "num_tokens": 517099392.0, "step": 86545 }, { "epoch": 0.9233674372952962, "grad_norm": 3.6034386724976386, "learning_rate": 5.718836176947588e-06, "loss": 0.5173, "num_tokens": 517127584.0, "step": 86550 }, { "epoch": 0.9234207803014947, "grad_norm": 0.9965222580463128, "learning_rate": 5.717841270997909e-06, "loss": 0.4935, "num_tokens": 517146564.0, "step": 86555 }, { "epoch": 0.9234741233076931, "grad_norm": 1.0002332069310014, "learning_rate": 5.716847042864264e-06, "loss": 0.39, "num_tokens": 517172988.0, "step": 86560 }, { "epoch": 0.9235274663138916, "grad_norm": 1.0099043059235213, "learning_rate": 5.715853492577599e-06, "loss": 0.3888, "num_tokens": 517197954.0, "step": 86565 }, { "epoch": 0.92358080932009, "grad_norm": 0.7404876782039044, "learning_rate": 5.714860620168825e-06, "loss": 0.5459, "num_tokens": 517252764.0, "step": 86570 }, { "epoch": 0.9236341523262885, "grad_norm": 1.6267445066470358, "learning_rate": 5.7138684256688415e-06, "loss": 0.4579, "num_tokens": 517283160.0, "step": 86575 }, { "epoch": 0.923687495332487, "grad_norm": 0.6762176288825461, "learning_rate": 5.712876909108521e-06, "loss": 0.3747, "num_tokens": 517309531.0, "step": 86580 }, { "epoch": 0.9237408383386854, "grad_norm": 0.807976459894937, "learning_rate": 5.7118860705187196e-06, "loss": 0.4445, "num_tokens": 517327206.0, "step": 86585 }, { "epoch": 0.9237941813448839, "grad_norm": 0.9661195903749826, "learning_rate": 5.7108959099302735e-06, "loss": 0.4839, "num_tokens": 517361266.0, "step": 86590 }, { "epoch": 0.9238475243510823, "grad_norm": 1.7971435663251578, "learning_rate": 5.709906427373986e-06, "loss": 0.5052, "num_tokens": 517391565.0, "step": 86595 }, { "epoch": 0.9239008673572808, "grad_norm": 0.80518527080188, "learning_rate": 5.708917622880656e-06, "loss": 0.5195, "num_tokens": 517408426.0, "step": 86600 }, { "epoch": 0.9239542103634792, "grad_norm": 1.0368696322890172, "learning_rate": 5.707929496481045e-06, "loss": 0.5924, "num_tokens": 517440248.0, "step": 86605 }, { "epoch": 0.9240075533696777, "grad_norm": 0.9064817405145602, "learning_rate": 5.706942048205907e-06, "loss": 0.4339, "num_tokens": 517464316.0, "step": 86610 }, { "epoch": 0.9240608963758762, "grad_norm": 1.3519990260787909, "learning_rate": 5.7059552780859695e-06, "loss": 0.4489, "num_tokens": 517486999.0, "step": 86615 }, { "epoch": 0.9241142393820746, "grad_norm": 1.4041157744177735, "learning_rate": 5.704969186151937e-06, "loss": 0.5991, "num_tokens": 517518956.0, "step": 86620 }, { "epoch": 0.9241675823882731, "grad_norm": 1.6911732684663785, "learning_rate": 5.703983772434497e-06, "loss": 0.6931, "num_tokens": 517542639.0, "step": 86625 }, { "epoch": 0.9242209253944715, "grad_norm": 1.2530508792658057, "learning_rate": 5.702999036964311e-06, "loss": 0.4639, "num_tokens": 517571955.0, "step": 86630 }, { "epoch": 0.92427426840067, "grad_norm": 0.9951253155252671, "learning_rate": 5.702014979772021e-06, "loss": 0.4313, "num_tokens": 517593673.0, "step": 86635 }, { "epoch": 0.9243276114068685, "grad_norm": 0.8799403046429306, "learning_rate": 5.70103160088825e-06, "loss": 0.3962, "num_tokens": 517626797.0, "step": 86640 }, { "epoch": 0.9243809544130669, "grad_norm": 0.7106734268734773, "learning_rate": 5.700048900343602e-06, "loss": 0.507, "num_tokens": 517657515.0, "step": 86645 }, { "epoch": 0.9244342974192653, "grad_norm": 1.3270607136269688, "learning_rate": 5.699066878168652e-06, "loss": 0.4361, "num_tokens": 517676344.0, "step": 86650 }, { "epoch": 0.9244876404254638, "grad_norm": 1.081732365055731, "learning_rate": 5.698085534393962e-06, "loss": 0.5252, "num_tokens": 517722271.0, "step": 86655 }, { "epoch": 0.9245409834316622, "grad_norm": 1.0019242875555203, "learning_rate": 5.6971048690500646e-06, "loss": 0.5163, "num_tokens": 517757727.0, "step": 86660 }, { "epoch": 0.9245943264378608, "grad_norm": 0.7160521103018507, "learning_rate": 5.696124882167484e-06, "loss": 0.3712, "num_tokens": 517794092.0, "step": 86665 }, { "epoch": 0.9246476694440592, "grad_norm": 0.8677233871947333, "learning_rate": 5.6951455737767054e-06, "loss": 0.4713, "num_tokens": 517815140.0, "step": 86670 }, { "epoch": 0.9247010124502576, "grad_norm": 1.6950132171815995, "learning_rate": 5.69416694390821e-06, "loss": 0.4554, "num_tokens": 517833902.0, "step": 86675 }, { "epoch": 0.9247543554564561, "grad_norm": 1.1229843376188373, "learning_rate": 5.69318899259245e-06, "loss": 0.4017, "num_tokens": 517863105.0, "step": 86680 }, { "epoch": 0.9248076984626545, "grad_norm": 1.2517903364888563, "learning_rate": 5.692211719859854e-06, "loss": 0.4162, "num_tokens": 517902025.0, "step": 86685 }, { "epoch": 0.9248610414688531, "grad_norm": 0.5385925900467744, "learning_rate": 5.691235125740838e-06, "loss": 0.4997, "num_tokens": 517960736.0, "step": 86690 }, { "epoch": 0.9249143844750515, "grad_norm": 0.8909055802022933, "learning_rate": 5.690259210265786e-06, "loss": 0.3853, "num_tokens": 517987730.0, "step": 86695 }, { "epoch": 0.9249677274812499, "grad_norm": 0.9697572038476459, "learning_rate": 5.689283973465069e-06, "loss": 0.532, "num_tokens": 518017156.0, "step": 86700 }, { "epoch": 0.9250210704874484, "grad_norm": 2.015343294641904, "learning_rate": 5.688309415369035e-06, "loss": 0.4615, "num_tokens": 518040006.0, "step": 86705 }, { "epoch": 0.9250744134936468, "grad_norm": 0.9251876803423271, "learning_rate": 5.687335536008011e-06, "loss": 0.5053, "num_tokens": 518092287.0, "step": 86710 }, { "epoch": 0.9251277564998454, "grad_norm": 0.8614818644817359, "learning_rate": 5.686362335412297e-06, "loss": 0.422, "num_tokens": 518118019.0, "step": 86715 }, { "epoch": 0.9251810995060438, "grad_norm": 0.9968641541514706, "learning_rate": 5.685389813612184e-06, "loss": 0.4251, "num_tokens": 518137999.0, "step": 86720 }, { "epoch": 0.9252344425122422, "grad_norm": 0.8187312623854269, "learning_rate": 5.6844179706379275e-06, "loss": 0.5447, "num_tokens": 518177006.0, "step": 86725 }, { "epoch": 0.9252877855184407, "grad_norm": 0.7111966317832094, "learning_rate": 5.683446806519777e-06, "loss": 0.4238, "num_tokens": 518211562.0, "step": 86730 }, { "epoch": 0.9253411285246391, "grad_norm": 0.7305810230864913, "learning_rate": 5.68247632128795e-06, "loss": 0.4697, "num_tokens": 518235940.0, "step": 86735 }, { "epoch": 0.9253944715308375, "grad_norm": 0.8288326161113801, "learning_rate": 5.681506514972642e-06, "loss": 0.4589, "num_tokens": 518266591.0, "step": 86740 }, { "epoch": 0.9254478145370361, "grad_norm": 1.159096524246849, "learning_rate": 5.680537387604035e-06, "loss": 0.4656, "num_tokens": 518297265.0, "step": 86745 }, { "epoch": 0.9255011575432345, "grad_norm": 0.7247655899728309, "learning_rate": 5.679568939212289e-06, "loss": 0.446, "num_tokens": 518319840.0, "step": 86750 }, { "epoch": 0.925554500549433, "grad_norm": 1.2243601690266126, "learning_rate": 5.678601169827535e-06, "loss": 0.4061, "num_tokens": 518340855.0, "step": 86755 }, { "epoch": 0.9256078435556314, "grad_norm": 0.6996454895606206, "learning_rate": 5.677634079479889e-06, "loss": 0.4013, "num_tokens": 518369840.0, "step": 86760 }, { "epoch": 0.9256611865618298, "grad_norm": 1.0617895364625067, "learning_rate": 5.676667668199448e-06, "loss": 0.4223, "num_tokens": 518392553.0, "step": 86765 }, { "epoch": 0.9257145295680284, "grad_norm": 1.2642493103425245, "learning_rate": 5.675701936016285e-06, "loss": 0.5249, "num_tokens": 518412452.0, "step": 86770 }, { "epoch": 0.9257678725742268, "grad_norm": 0.9370135084036851, "learning_rate": 5.674736882960445e-06, "loss": 0.5461, "num_tokens": 518442004.0, "step": 86775 }, { "epoch": 0.9258212155804253, "grad_norm": 0.9165569818577209, "learning_rate": 5.673772509061965e-06, "loss": 0.4101, "num_tokens": 518469007.0, "step": 86780 }, { "epoch": 0.9258745585866237, "grad_norm": 1.01684824765112, "learning_rate": 5.672808814350854e-06, "loss": 0.4321, "num_tokens": 518502405.0, "step": 86785 }, { "epoch": 0.9259279015928221, "grad_norm": 0.6642267975967194, "learning_rate": 5.671845798857094e-06, "loss": 0.4283, "num_tokens": 518529947.0, "step": 86790 }, { "epoch": 0.9259812445990206, "grad_norm": 0.8680727184369651, "learning_rate": 5.670883462610656e-06, "loss": 0.3356, "num_tokens": 518557137.0, "step": 86795 }, { "epoch": 0.9260345876052191, "grad_norm": 0.6263777273623489, "learning_rate": 5.66992180564149e-06, "loss": 0.4344, "num_tokens": 518600120.0, "step": 86800 }, { "epoch": 0.9260879306114176, "grad_norm": 0.9191196504532734, "learning_rate": 5.668960827979519e-06, "loss": 0.5304, "num_tokens": 518645088.0, "step": 86805 }, { "epoch": 0.926141273617616, "grad_norm": 2.017058601115713, "learning_rate": 5.668000529654641e-06, "loss": 0.4237, "num_tokens": 518670623.0, "step": 86810 }, { "epoch": 0.9261946166238144, "grad_norm": 1.159908602134657, "learning_rate": 5.667040910696744e-06, "loss": 0.4029, "num_tokens": 518685238.0, "step": 86815 }, { "epoch": 0.9262479596300129, "grad_norm": 0.6936408098086322, "learning_rate": 5.666081971135687e-06, "loss": 0.4772, "num_tokens": 518708068.0, "step": 86820 }, { "epoch": 0.9263013026362114, "grad_norm": 0.9791338062958853, "learning_rate": 5.665123711001308e-06, "loss": 0.4322, "num_tokens": 518733052.0, "step": 86825 }, { "epoch": 0.9263546456424098, "grad_norm": 0.820054396396401, "learning_rate": 5.664166130323435e-06, "loss": 0.3944, "num_tokens": 518760104.0, "step": 86830 }, { "epoch": 0.9264079886486083, "grad_norm": 1.207365188916617, "learning_rate": 5.663209229131855e-06, "loss": 0.4679, "num_tokens": 518790600.0, "step": 86835 }, { "epoch": 0.9264613316548067, "grad_norm": 0.9958370878727655, "learning_rate": 5.662253007456351e-06, "loss": 0.4906, "num_tokens": 518815106.0, "step": 86840 }, { "epoch": 0.9265146746610052, "grad_norm": 0.7736886403016695, "learning_rate": 5.66129746532668e-06, "loss": 0.5137, "num_tokens": 518862442.0, "step": 86845 }, { "epoch": 0.9265680176672036, "grad_norm": 0.6568160577231754, "learning_rate": 5.6603426027725694e-06, "loss": 0.3831, "num_tokens": 518884052.0, "step": 86850 }, { "epoch": 0.9266213606734021, "grad_norm": 1.5082168164988294, "learning_rate": 5.659388419823739e-06, "loss": 0.4395, "num_tokens": 518901872.0, "step": 86855 }, { "epoch": 0.9266747036796006, "grad_norm": 0.9796901297183156, "learning_rate": 5.658434916509881e-06, "loss": 0.4426, "num_tokens": 518933462.0, "step": 86860 }, { "epoch": 0.926728046685799, "grad_norm": 0.6964373706147894, "learning_rate": 5.657482092860662e-06, "loss": 0.3898, "num_tokens": 518950964.0, "step": 86865 }, { "epoch": 0.9267813896919975, "grad_norm": 0.5923085896051591, "learning_rate": 5.6565299489057355e-06, "loss": 0.5229, "num_tokens": 518981991.0, "step": 86870 }, { "epoch": 0.9268347326981959, "grad_norm": 1.0256394140026943, "learning_rate": 5.6555784846747295e-06, "loss": 0.4664, "num_tokens": 519020617.0, "step": 86875 }, { "epoch": 0.9268880757043944, "grad_norm": 1.111895405366324, "learning_rate": 5.654627700197254e-06, "loss": 0.4299, "num_tokens": 519045526.0, "step": 86880 }, { "epoch": 0.9269414187105929, "grad_norm": 0.9018126431324358, "learning_rate": 5.653677595502886e-06, "loss": 0.4368, "num_tokens": 519074606.0, "step": 86885 }, { "epoch": 0.9269947617167913, "grad_norm": 0.7333535608966202, "learning_rate": 5.652728170621203e-06, "loss": 0.4132, "num_tokens": 519099743.0, "step": 86890 }, { "epoch": 0.9270481047229898, "grad_norm": 1.2449436269706609, "learning_rate": 5.651779425581742e-06, "loss": 0.4163, "num_tokens": 519121680.0, "step": 86895 }, { "epoch": 0.9271014477291882, "grad_norm": 0.8129883865712815, "learning_rate": 5.650831360414026e-06, "loss": 0.5246, "num_tokens": 519169434.0, "step": 86900 }, { "epoch": 0.9271547907353866, "grad_norm": 0.9297640112003521, "learning_rate": 5.6498839751475615e-06, "loss": 0.382, "num_tokens": 519195616.0, "step": 86905 }, { "epoch": 0.9272081337415852, "grad_norm": 0.8832739085439575, "learning_rate": 5.648937269811824e-06, "loss": 0.4321, "num_tokens": 519211842.0, "step": 86910 }, { "epoch": 0.9272614767477836, "grad_norm": 1.8652872481318763, "learning_rate": 5.6479912444362795e-06, "loss": 0.3388, "num_tokens": 519221646.0, "step": 86915 }, { "epoch": 0.927314819753982, "grad_norm": 1.1397654975839056, "learning_rate": 5.64704589905036e-06, "loss": 0.4765, "num_tokens": 519242670.0, "step": 86920 }, { "epoch": 0.9273681627601805, "grad_norm": 0.6082501150398021, "learning_rate": 5.646101233683482e-06, "loss": 0.3431, "num_tokens": 519273817.0, "step": 86925 }, { "epoch": 0.9274215057663789, "grad_norm": 0.8122013381716005, "learning_rate": 5.645157248365046e-06, "loss": 0.4896, "num_tokens": 519294157.0, "step": 86930 }, { "epoch": 0.9274748487725775, "grad_norm": 1.240067451540644, "learning_rate": 5.644213943124427e-06, "loss": 0.454, "num_tokens": 519313911.0, "step": 86935 }, { "epoch": 0.9275281917787759, "grad_norm": 0.8173224900917037, "learning_rate": 5.643271317990975e-06, "loss": 0.513, "num_tokens": 519344640.0, "step": 86940 }, { "epoch": 0.9275815347849743, "grad_norm": 0.5710851127927775, "learning_rate": 5.642329372994023e-06, "loss": 0.5323, "num_tokens": 519385640.0, "step": 86945 }, { "epoch": 0.9276348777911728, "grad_norm": 1.60967898550644, "learning_rate": 5.641388108162888e-06, "loss": 0.5057, "num_tokens": 519408281.0, "step": 86950 }, { "epoch": 0.9276882207973712, "grad_norm": 0.7635264137178466, "learning_rate": 5.640447523526858e-06, "loss": 0.5822, "num_tokens": 519457947.0, "step": 86955 }, { "epoch": 0.9277415638035698, "grad_norm": 1.992377150196392, "learning_rate": 5.6395076191151945e-06, "loss": 0.5882, "num_tokens": 519497103.0, "step": 86960 }, { "epoch": 0.9277949068097682, "grad_norm": 0.667412493311124, "learning_rate": 5.638568394957155e-06, "loss": 0.3991, "num_tokens": 519532445.0, "step": 86965 }, { "epoch": 0.9278482498159666, "grad_norm": 1.3332285811289848, "learning_rate": 5.63762985108196e-06, "loss": 0.4487, "num_tokens": 519556535.0, "step": 86970 }, { "epoch": 0.9279015928221651, "grad_norm": 1.629449575751152, "learning_rate": 5.636691987518817e-06, "loss": 0.3997, "num_tokens": 519581323.0, "step": 86975 }, { "epoch": 0.9279549358283635, "grad_norm": 0.6856033816915671, "learning_rate": 5.635754804296914e-06, "loss": 0.5234, "num_tokens": 519614860.0, "step": 86980 }, { "epoch": 0.928008278834562, "grad_norm": 0.9121668743009056, "learning_rate": 5.634818301445409e-06, "loss": 0.4789, "num_tokens": 519648518.0, "step": 86985 }, { "epoch": 0.9280616218407605, "grad_norm": 0.6453835518778986, "learning_rate": 5.6338824789934465e-06, "loss": 0.4624, "num_tokens": 519685289.0, "step": 86990 }, { "epoch": 0.9281149648469589, "grad_norm": 1.0077139430923323, "learning_rate": 5.632947336970149e-06, "loss": 0.5702, "num_tokens": 519735161.0, "step": 86995 }, { "epoch": 0.9281683078531574, "grad_norm": 1.100748060113172, "learning_rate": 5.632012875404609e-06, "loss": 0.3457, "num_tokens": 519749203.0, "step": 87000 }, { "epoch": 0.9282216508593558, "grad_norm": 0.9555441946905451, "learning_rate": 5.631079094325914e-06, "loss": 0.5579, "num_tokens": 519777511.0, "step": 87005 }, { "epoch": 0.9282749938655542, "grad_norm": 0.7419401143459686, "learning_rate": 5.630145993763117e-06, "loss": 0.3625, "num_tokens": 519799879.0, "step": 87010 }, { "epoch": 0.9283283368717528, "grad_norm": 1.21331802171946, "learning_rate": 5.629213573745254e-06, "loss": 0.4542, "num_tokens": 519817170.0, "step": 87015 }, { "epoch": 0.9283816798779512, "grad_norm": 0.7951886409064222, "learning_rate": 5.628281834301342e-06, "loss": 0.4335, "num_tokens": 519848829.0, "step": 87020 }, { "epoch": 0.9284350228841497, "grad_norm": 2.116934917316771, "learning_rate": 5.627350775460372e-06, "loss": 0.4486, "num_tokens": 519874904.0, "step": 87025 }, { "epoch": 0.9284883658903481, "grad_norm": 0.7589248334733673, "learning_rate": 5.626420397251318e-06, "loss": 0.453, "num_tokens": 519900030.0, "step": 87030 }, { "epoch": 0.9285417088965465, "grad_norm": 0.914389365707155, "learning_rate": 5.625490699703131e-06, "loss": 0.5456, "num_tokens": 519938116.0, "step": 87035 }, { "epoch": 0.928595051902745, "grad_norm": 0.7949317545524843, "learning_rate": 5.624561682844747e-06, "loss": 0.4158, "num_tokens": 519966345.0, "step": 87040 }, { "epoch": 0.9286483949089435, "grad_norm": 0.8446374914940873, "learning_rate": 5.623633346705064e-06, "loss": 0.4222, "num_tokens": 519997297.0, "step": 87045 }, { "epoch": 0.928701737915142, "grad_norm": 1.0120561617367, "learning_rate": 5.622705691312977e-06, "loss": 0.4236, "num_tokens": 520021718.0, "step": 87050 }, { "epoch": 0.9287550809213404, "grad_norm": 0.8316206000042778, "learning_rate": 5.621778716697355e-06, "loss": 0.4713, "num_tokens": 520048592.0, "step": 87055 }, { "epoch": 0.9288084239275388, "grad_norm": 1.8117997227550973, "learning_rate": 5.620852422887039e-06, "loss": 0.3752, "num_tokens": 520071588.0, "step": 87060 }, { "epoch": 0.9288617669337373, "grad_norm": 0.7642804585268369, "learning_rate": 5.619926809910851e-06, "loss": 0.3832, "num_tokens": 520099237.0, "step": 87065 }, { "epoch": 0.9289151099399358, "grad_norm": 1.5619020793373881, "learning_rate": 5.619001877797602e-06, "loss": 0.5031, "num_tokens": 520133088.0, "step": 87070 }, { "epoch": 0.9289684529461343, "grad_norm": 1.0496811302203766, "learning_rate": 5.618077626576067e-06, "loss": 0.4518, "num_tokens": 520162290.0, "step": 87075 }, { "epoch": 0.9290217959523327, "grad_norm": 1.5426940527325914, "learning_rate": 5.617154056275011e-06, "loss": 0.4265, "num_tokens": 520202422.0, "step": 87080 }, { "epoch": 0.9290751389585311, "grad_norm": 0.9813750212345915, "learning_rate": 5.6162311669231705e-06, "loss": 0.4474, "num_tokens": 520246393.0, "step": 87085 }, { "epoch": 0.9291284819647296, "grad_norm": 0.8516342866460075, "learning_rate": 5.615308958549268e-06, "loss": 0.4306, "num_tokens": 520274164.0, "step": 87090 }, { "epoch": 0.929181824970928, "grad_norm": 1.1411716872575743, "learning_rate": 5.6143874311819975e-06, "loss": 0.4534, "num_tokens": 520288298.0, "step": 87095 }, { "epoch": 0.9292351679771265, "grad_norm": 1.1320403951738591, "learning_rate": 5.613466584850035e-06, "loss": 0.4183, "num_tokens": 520306732.0, "step": 87100 }, { "epoch": 0.929288510983325, "grad_norm": 0.7458440040501512, "learning_rate": 5.612546419582037e-06, "loss": 0.415, "num_tokens": 520331702.0, "step": 87105 }, { "epoch": 0.9293418539895234, "grad_norm": 0.6941049858723536, "learning_rate": 5.611626935406633e-06, "loss": 0.3803, "num_tokens": 520358931.0, "step": 87110 }, { "epoch": 0.9293951969957219, "grad_norm": 0.9379956439457073, "learning_rate": 5.610708132352443e-06, "loss": 0.4637, "num_tokens": 520382867.0, "step": 87115 }, { "epoch": 0.9294485400019203, "grad_norm": 1.182580112099842, "learning_rate": 5.60979001044805e-06, "loss": 0.5655, "num_tokens": 520409227.0, "step": 87120 }, { "epoch": 0.9295018830081188, "grad_norm": 0.7229665281873587, "learning_rate": 5.608872569722031e-06, "loss": 0.4689, "num_tokens": 520431139.0, "step": 87125 }, { "epoch": 0.9295552260143173, "grad_norm": 1.3876267402679094, "learning_rate": 5.607955810202933e-06, "loss": 0.4962, "num_tokens": 520448108.0, "step": 87130 }, { "epoch": 0.9296085690205157, "grad_norm": 1.094723949095572, "learning_rate": 5.607039731919282e-06, "loss": 0.491, "num_tokens": 520492643.0, "step": 87135 }, { "epoch": 0.9296619120267142, "grad_norm": 0.8483164881201358, "learning_rate": 5.606124334899583e-06, "loss": 0.451, "num_tokens": 520518905.0, "step": 87140 }, { "epoch": 0.9297152550329126, "grad_norm": 1.1952068479247036, "learning_rate": 5.6052096191723276e-06, "loss": 0.3995, "num_tokens": 520537746.0, "step": 87145 }, { "epoch": 0.929768598039111, "grad_norm": 0.8400537896500568, "learning_rate": 5.604295584765969e-06, "loss": 0.4944, "num_tokens": 520566956.0, "step": 87150 }, { "epoch": 0.9298219410453096, "grad_norm": 1.0616643088611386, "learning_rate": 5.603382231708961e-06, "loss": 0.4565, "num_tokens": 520591940.0, "step": 87155 }, { "epoch": 0.929875284051508, "grad_norm": 0.5050963838167052, "learning_rate": 5.602469560029721e-06, "loss": 0.386, "num_tokens": 520636167.0, "step": 87160 }, { "epoch": 0.9299286270577065, "grad_norm": 1.3862068078518839, "learning_rate": 5.601557569756648e-06, "loss": 0.379, "num_tokens": 520656649.0, "step": 87165 }, { "epoch": 0.9299819700639049, "grad_norm": 0.9265107124075097, "learning_rate": 5.600646260918124e-06, "loss": 0.4345, "num_tokens": 520691825.0, "step": 87170 }, { "epoch": 0.9300353130701033, "grad_norm": 2.0306781120002237, "learning_rate": 5.599735633542509e-06, "loss": 0.472, "num_tokens": 520712240.0, "step": 87175 }, { "epoch": 0.9300886560763019, "grad_norm": 0.8430291836504948, "learning_rate": 5.598825687658132e-06, "loss": 0.3344, "num_tokens": 520734988.0, "step": 87180 }, { "epoch": 0.9301419990825003, "grad_norm": 0.9084152735526098, "learning_rate": 5.597916423293313e-06, "loss": 0.464, "num_tokens": 520769010.0, "step": 87185 }, { "epoch": 0.9301953420886987, "grad_norm": 0.6805209809918201, "learning_rate": 5.597007840476348e-06, "loss": 0.4346, "num_tokens": 520792546.0, "step": 87190 }, { "epoch": 0.9302486850948972, "grad_norm": 1.3335001745290234, "learning_rate": 5.596099939235508e-06, "loss": 0.6055, "num_tokens": 520820484.0, "step": 87195 }, { "epoch": 0.9303020281010956, "grad_norm": 1.031853852999738, "learning_rate": 5.5951927195990486e-06, "loss": 0.4268, "num_tokens": 520848672.0, "step": 87200 }, { "epoch": 0.9303553711072942, "grad_norm": 0.5650560555310078, "learning_rate": 5.594286181595196e-06, "loss": 0.486, "num_tokens": 520890653.0, "step": 87205 }, { "epoch": 0.9304087141134926, "grad_norm": 0.7634442310990316, "learning_rate": 5.593380325252165e-06, "loss": 0.5013, "num_tokens": 520936546.0, "step": 87210 }, { "epoch": 0.930462057119691, "grad_norm": 0.8393406702063996, "learning_rate": 5.592475150598137e-06, "loss": 0.4261, "num_tokens": 520964499.0, "step": 87215 }, { "epoch": 0.9305154001258895, "grad_norm": 0.8148430477001091, "learning_rate": 5.591570657661285e-06, "loss": 0.4154, "num_tokens": 520987375.0, "step": 87220 }, { "epoch": 0.9305687431320879, "grad_norm": 0.8220545090839754, "learning_rate": 5.59066684646975e-06, "loss": 0.4312, "num_tokens": 521007400.0, "step": 87225 }, { "epoch": 0.9306220861382865, "grad_norm": 1.2291288342456306, "learning_rate": 5.589763717051662e-06, "loss": 0.4318, "num_tokens": 521037533.0, "step": 87230 }, { "epoch": 0.9306754291444849, "grad_norm": 1.013481510649224, "learning_rate": 5.588861269435122e-06, "loss": 0.4137, "num_tokens": 521053406.0, "step": 87235 }, { "epoch": 0.9307287721506833, "grad_norm": 1.2546967786801886, "learning_rate": 5.587959503648211e-06, "loss": 0.5007, "num_tokens": 521102772.0, "step": 87240 }, { "epoch": 0.9307821151568818, "grad_norm": 1.0262841836308902, "learning_rate": 5.587058419718994e-06, "loss": 0.4562, "num_tokens": 521118449.0, "step": 87245 }, { "epoch": 0.9308354581630802, "grad_norm": 0.8948217123332292, "learning_rate": 5.586158017675509e-06, "loss": 0.3595, "num_tokens": 521158148.0, "step": 87250 }, { "epoch": 0.9308888011692787, "grad_norm": 1.080687055396815, "learning_rate": 5.5852582975457725e-06, "loss": 0.5827, "num_tokens": 521191125.0, "step": 87255 }, { "epoch": 0.9309421441754772, "grad_norm": 1.2424600005791502, "learning_rate": 5.5843592593577825e-06, "loss": 0.4905, "num_tokens": 521224522.0, "step": 87260 }, { "epoch": 0.9309954871816756, "grad_norm": 0.614303198696486, "learning_rate": 5.583460903139519e-06, "loss": 0.4637, "num_tokens": 521265296.0, "step": 87265 }, { "epoch": 0.9310488301878741, "grad_norm": 4.013905877598475, "learning_rate": 5.582563228918933e-06, "loss": 0.5676, "num_tokens": 521286241.0, "step": 87270 }, { "epoch": 0.9311021731940725, "grad_norm": 0.48171961708837674, "learning_rate": 5.581666236723959e-06, "loss": 0.48, "num_tokens": 521320102.0, "step": 87275 }, { "epoch": 0.9311555162002709, "grad_norm": 0.8916330325842514, "learning_rate": 5.580769926582514e-06, "loss": 0.4253, "num_tokens": 521354358.0, "step": 87280 }, { "epoch": 0.9312088592064695, "grad_norm": 0.9368481892984732, "learning_rate": 5.5798742985224816e-06, "loss": 0.5162, "num_tokens": 521384818.0, "step": 87285 }, { "epoch": 0.9312622022126679, "grad_norm": 1.1730514447746978, "learning_rate": 5.5789793525717345e-06, "loss": 0.4819, "num_tokens": 521418760.0, "step": 87290 }, { "epoch": 0.9313155452188664, "grad_norm": 1.0146928585810204, "learning_rate": 5.578085088758127e-06, "loss": 0.4407, "num_tokens": 521437839.0, "step": 87295 }, { "epoch": 0.9313688882250648, "grad_norm": 0.8751353376602127, "learning_rate": 5.577191507109479e-06, "loss": 0.4491, "num_tokens": 521468549.0, "step": 87300 }, { "epoch": 0.9314222312312632, "grad_norm": 0.7840463232431915, "learning_rate": 5.576298607653601e-06, "loss": 0.4107, "num_tokens": 521494688.0, "step": 87305 }, { "epoch": 0.9314755742374617, "grad_norm": 1.023980329297715, "learning_rate": 5.57540639041828e-06, "loss": 0.4039, "num_tokens": 521521205.0, "step": 87310 }, { "epoch": 0.9315289172436602, "grad_norm": 0.7501315855431037, "learning_rate": 5.574514855431277e-06, "loss": 0.4497, "num_tokens": 521575583.0, "step": 87315 }, { "epoch": 0.9315822602498587, "grad_norm": 0.9876832639302964, "learning_rate": 5.573624002720335e-06, "loss": 0.4078, "num_tokens": 521602278.0, "step": 87320 }, { "epoch": 0.9316356032560571, "grad_norm": 1.1324217287574752, "learning_rate": 5.572733832313176e-06, "loss": 0.4456, "num_tokens": 521623018.0, "step": 87325 }, { "epoch": 0.9316889462622555, "grad_norm": 1.5436874276545751, "learning_rate": 5.571844344237502e-06, "loss": 0.3391, "num_tokens": 521649077.0, "step": 87330 }, { "epoch": 0.931742289268454, "grad_norm": 0.7425782280197961, "learning_rate": 5.570955538520986e-06, "loss": 0.4709, "num_tokens": 521676108.0, "step": 87335 }, { "epoch": 0.9317956322746525, "grad_norm": 0.6346915253470199, "learning_rate": 5.570067415191295e-06, "loss": 0.367, "num_tokens": 521705761.0, "step": 87340 }, { "epoch": 0.931848975280851, "grad_norm": 0.8659485874349109, "learning_rate": 5.569179974276056e-06, "loss": 0.3856, "num_tokens": 521735387.0, "step": 87345 }, { "epoch": 0.9319023182870494, "grad_norm": 1.3175111077573807, "learning_rate": 5.5682932158028925e-06, "loss": 0.4685, "num_tokens": 521761221.0, "step": 87350 }, { "epoch": 0.9319556612932478, "grad_norm": 1.1322047474372814, "learning_rate": 5.567407139799395e-06, "loss": 0.3579, "num_tokens": 521786876.0, "step": 87355 }, { "epoch": 0.9320090042994463, "grad_norm": 0.7021701828336095, "learning_rate": 5.566521746293136e-06, "loss": 0.5764, "num_tokens": 521824255.0, "step": 87360 }, { "epoch": 0.9320623473056447, "grad_norm": 0.8867909508276883, "learning_rate": 5.5656370353116636e-06, "loss": 0.4299, "num_tokens": 521855757.0, "step": 87365 }, { "epoch": 0.9321156903118432, "grad_norm": 3.0130758029590528, "learning_rate": 5.564753006882518e-06, "loss": 0.4694, "num_tokens": 521874320.0, "step": 87370 }, { "epoch": 0.9321690333180417, "grad_norm": 0.6137735284338954, "learning_rate": 5.563869661033199e-06, "loss": 0.6222, "num_tokens": 521919774.0, "step": 87375 }, { "epoch": 0.9322223763242401, "grad_norm": 0.8999479588984444, "learning_rate": 5.562986997791199e-06, "loss": 0.3337, "num_tokens": 521940804.0, "step": 87380 }, { "epoch": 0.9322757193304386, "grad_norm": 1.137358469334505, "learning_rate": 5.562105017183984e-06, "loss": 0.3999, "num_tokens": 521964110.0, "step": 87385 }, { "epoch": 0.932329062336637, "grad_norm": 0.7809749517624042, "learning_rate": 5.561223719239e-06, "loss": 0.3771, "num_tokens": 521996943.0, "step": 87390 }, { "epoch": 0.9323824053428355, "grad_norm": 0.7434912874504707, "learning_rate": 5.560343103983669e-06, "loss": 0.4223, "num_tokens": 522021643.0, "step": 87395 }, { "epoch": 0.932435748349034, "grad_norm": 1.242426401359015, "learning_rate": 5.559463171445397e-06, "loss": 0.4862, "num_tokens": 522047876.0, "step": 87400 }, { "epoch": 0.9324890913552324, "grad_norm": 0.630580978428828, "learning_rate": 5.558583921651562e-06, "loss": 0.4288, "num_tokens": 522075367.0, "step": 87405 }, { "epoch": 0.9325424343614309, "grad_norm": 1.715616251033327, "learning_rate": 5.557705354629527e-06, "loss": 0.4605, "num_tokens": 522095210.0, "step": 87410 }, { "epoch": 0.9325957773676293, "grad_norm": 0.6982274320948945, "learning_rate": 5.556827470406631e-06, "loss": 0.449, "num_tokens": 522138334.0, "step": 87415 }, { "epoch": 0.9326491203738277, "grad_norm": 0.9018646616936774, "learning_rate": 5.5559502690101895e-06, "loss": 0.4606, "num_tokens": 522165695.0, "step": 87420 }, { "epoch": 0.9327024633800263, "grad_norm": 1.1363807341498904, "learning_rate": 5.555073750467505e-06, "loss": 0.4737, "num_tokens": 522195461.0, "step": 87425 }, { "epoch": 0.9327558063862247, "grad_norm": 2.1626115890933915, "learning_rate": 5.554197914805847e-06, "loss": 0.4467, "num_tokens": 522227716.0, "step": 87430 }, { "epoch": 0.9328091493924232, "grad_norm": 0.7850178431133658, "learning_rate": 5.553322762052471e-06, "loss": 0.4062, "num_tokens": 522259857.0, "step": 87435 }, { "epoch": 0.9328624923986216, "grad_norm": 1.032668755086598, "learning_rate": 5.552448292234611e-06, "loss": 0.4353, "num_tokens": 522293840.0, "step": 87440 }, { "epoch": 0.93291583540482, "grad_norm": 0.8855101251440589, "learning_rate": 5.551574505379482e-06, "loss": 0.3863, "num_tokens": 522316259.0, "step": 87445 }, { "epoch": 0.9329691784110186, "grad_norm": 0.9225292919756982, "learning_rate": 5.550701401514266e-06, "loss": 0.406, "num_tokens": 522354002.0, "step": 87450 }, { "epoch": 0.933022521417217, "grad_norm": 1.0847090521688652, "learning_rate": 5.54982898066614e-06, "loss": 0.6283, "num_tokens": 522381506.0, "step": 87455 }, { "epoch": 0.9330758644234154, "grad_norm": 0.953375875316013, "learning_rate": 5.548957242862249e-06, "loss": 0.4868, "num_tokens": 522410689.0, "step": 87460 }, { "epoch": 0.9331292074296139, "grad_norm": 1.2480809824924926, "learning_rate": 5.548086188129722e-06, "loss": 0.5503, "num_tokens": 522454182.0, "step": 87465 }, { "epoch": 0.9331825504358123, "grad_norm": 1.952043053304451, "learning_rate": 5.547215816495659e-06, "loss": 0.4643, "num_tokens": 522483075.0, "step": 87470 }, { "epoch": 0.9332358934420109, "grad_norm": 1.9664469238528641, "learning_rate": 5.54634612798715e-06, "loss": 0.4949, "num_tokens": 522516250.0, "step": 87475 }, { "epoch": 0.9332892364482093, "grad_norm": 0.9113867827752835, "learning_rate": 5.5454771226312525e-06, "loss": 0.4253, "num_tokens": 522535983.0, "step": 87480 }, { "epoch": 0.9333425794544077, "grad_norm": 0.6343910579379759, "learning_rate": 5.544608800455011e-06, "loss": 0.5053, "num_tokens": 522562453.0, "step": 87485 }, { "epoch": 0.9333959224606062, "grad_norm": 0.6954900797930967, "learning_rate": 5.54374116148545e-06, "loss": 0.3965, "num_tokens": 522594770.0, "step": 87490 }, { "epoch": 0.9334492654668046, "grad_norm": 1.1693504960097736, "learning_rate": 5.542874205749562e-06, "loss": 0.4671, "num_tokens": 522625408.0, "step": 87495 }, { "epoch": 0.9335026084730031, "grad_norm": 1.115795142462056, "learning_rate": 5.542007933274326e-06, "loss": 0.4165, "num_tokens": 522663567.0, "step": 87500 }, { "epoch": 0.9335559514792016, "grad_norm": 0.6683546535922452, "learning_rate": 5.541142344086705e-06, "loss": 0.3657, "num_tokens": 522715923.0, "step": 87505 }, { "epoch": 0.9336092944854, "grad_norm": 0.9222838707176537, "learning_rate": 5.540277438213624e-06, "loss": 0.4064, "num_tokens": 522738681.0, "step": 87510 }, { "epoch": 0.9336626374915985, "grad_norm": 0.8140610116977628, "learning_rate": 5.5394132156820056e-06, "loss": 0.3841, "num_tokens": 522768210.0, "step": 87515 }, { "epoch": 0.9337159804977969, "grad_norm": 0.8405165556673019, "learning_rate": 5.53854967651874e-06, "loss": 0.3722, "num_tokens": 522790794.0, "step": 87520 }, { "epoch": 0.9337693235039954, "grad_norm": 0.4945069556613727, "learning_rate": 5.537686820750697e-06, "loss": 0.3756, "num_tokens": 522828562.0, "step": 87525 }, { "epoch": 0.9338226665101939, "grad_norm": 1.7010777438364693, "learning_rate": 5.536824648404725e-06, "loss": 0.3904, "num_tokens": 522845029.0, "step": 87530 }, { "epoch": 0.9338760095163923, "grad_norm": 1.1940026895743572, "learning_rate": 5.535963159507661e-06, "loss": 0.4958, "num_tokens": 522867423.0, "step": 87535 }, { "epoch": 0.9339293525225908, "grad_norm": 1.3542472280753026, "learning_rate": 5.53510235408631e-06, "loss": 0.5137, "num_tokens": 522899052.0, "step": 87540 }, { "epoch": 0.9339826955287892, "grad_norm": 0.7065694414986893, "learning_rate": 5.534242232167451e-06, "loss": 0.4094, "num_tokens": 522929464.0, "step": 87545 }, { "epoch": 0.9340360385349876, "grad_norm": 0.9466158136225937, "learning_rate": 5.533382793777858e-06, "loss": 0.3586, "num_tokens": 522951237.0, "step": 87550 }, { "epoch": 0.9340893815411861, "grad_norm": 0.7122698412857973, "learning_rate": 5.532524038944269e-06, "loss": 0.4317, "num_tokens": 523005599.0, "step": 87555 }, { "epoch": 0.9341427245473846, "grad_norm": 1.4145535939952933, "learning_rate": 5.5316659676934115e-06, "loss": 0.3777, "num_tokens": 523024036.0, "step": 87560 }, { "epoch": 0.9341960675535831, "grad_norm": 0.8260633067840497, "learning_rate": 5.530808580051985e-06, "loss": 0.5274, "num_tokens": 523070635.0, "step": 87565 }, { "epoch": 0.9342494105597815, "grad_norm": 1.0990143015708165, "learning_rate": 5.529951876046668e-06, "loss": 0.5177, "num_tokens": 523088620.0, "step": 87570 }, { "epoch": 0.9343027535659799, "grad_norm": 1.0800333941851985, "learning_rate": 5.529095855704123e-06, "loss": 0.3398, "num_tokens": 523112490.0, "step": 87575 }, { "epoch": 0.9343560965721784, "grad_norm": 0.9332082910210647, "learning_rate": 5.5282405190509854e-06, "loss": 0.5292, "num_tokens": 523152961.0, "step": 87580 }, { "epoch": 0.9344094395783769, "grad_norm": 2.2269713580850015, "learning_rate": 5.52738586611387e-06, "loss": 0.5034, "num_tokens": 523186449.0, "step": 87585 }, { "epoch": 0.9344627825845754, "grad_norm": 0.800709915084222, "learning_rate": 5.526531896919374e-06, "loss": 0.4676, "num_tokens": 523224118.0, "step": 87590 }, { "epoch": 0.9345161255907738, "grad_norm": 1.173198415247499, "learning_rate": 5.525678611494071e-06, "loss": 0.4572, "num_tokens": 523239687.0, "step": 87595 }, { "epoch": 0.9345694685969722, "grad_norm": 0.700456726975675, "learning_rate": 5.524826009864511e-06, "loss": 0.4529, "num_tokens": 523275977.0, "step": 87600 }, { "epoch": 0.9346228116031707, "grad_norm": 0.9691212509587303, "learning_rate": 5.523974092057229e-06, "loss": 0.5307, "num_tokens": 523308989.0, "step": 87605 }, { "epoch": 0.9346761546093691, "grad_norm": 0.8697818614502133, "learning_rate": 5.523122858098736e-06, "loss": 0.5201, "num_tokens": 523348332.0, "step": 87610 }, { "epoch": 0.9347294976155677, "grad_norm": 1.4995820407553093, "learning_rate": 5.522272308015515e-06, "loss": 0.4274, "num_tokens": 523370100.0, "step": 87615 }, { "epoch": 0.9347828406217661, "grad_norm": 1.1139416143407477, "learning_rate": 5.521422441834033e-06, "loss": 0.4471, "num_tokens": 523412503.0, "step": 87620 }, { "epoch": 0.9348361836279645, "grad_norm": 1.4787965720162177, "learning_rate": 5.520573259580745e-06, "loss": 0.4965, "num_tokens": 523445943.0, "step": 87625 }, { "epoch": 0.934889526634163, "grad_norm": 0.5004477637039917, "learning_rate": 5.519724761282065e-06, "loss": 0.5571, "num_tokens": 523493649.0, "step": 87630 }, { "epoch": 0.9349428696403614, "grad_norm": 1.262276054141312, "learning_rate": 5.518876946964404e-06, "loss": 0.5174, "num_tokens": 523522105.0, "step": 87635 }, { "epoch": 0.9349962126465599, "grad_norm": 0.8961860585644681, "learning_rate": 5.5180298166541425e-06, "loss": 0.5778, "num_tokens": 523547741.0, "step": 87640 }, { "epoch": 0.9350495556527584, "grad_norm": 0.871997891102331, "learning_rate": 5.517183370377643e-06, "loss": 0.4721, "num_tokens": 523579876.0, "step": 87645 }, { "epoch": 0.9351028986589568, "grad_norm": 0.7395996491519727, "learning_rate": 5.516337608161239e-06, "loss": 0.4621, "num_tokens": 523605680.0, "step": 87650 }, { "epoch": 0.9351562416651553, "grad_norm": 0.9499103529519456, "learning_rate": 5.5154925300312544e-06, "loss": 0.5686, "num_tokens": 523633755.0, "step": 87655 }, { "epoch": 0.9352095846713537, "grad_norm": 1.1372755403712682, "learning_rate": 5.514648136013984e-06, "loss": 0.453, "num_tokens": 523661359.0, "step": 87660 }, { "epoch": 0.9352629276775521, "grad_norm": 1.0617941899326142, "learning_rate": 5.513804426135705e-06, "loss": 0.5741, "num_tokens": 523687839.0, "step": 87665 }, { "epoch": 0.9353162706837507, "grad_norm": 1.011354862169899, "learning_rate": 5.512961400422672e-06, "loss": 0.5232, "num_tokens": 523719477.0, "step": 87670 }, { "epoch": 0.9353696136899491, "grad_norm": 0.8249108940630558, "learning_rate": 5.512119058901116e-06, "loss": 0.5797, "num_tokens": 523761108.0, "step": 87675 }, { "epoch": 0.9354229566961476, "grad_norm": 1.027375974859876, "learning_rate": 5.511277401597254e-06, "loss": 0.5738, "num_tokens": 523793837.0, "step": 87680 }, { "epoch": 0.935476299702346, "grad_norm": 1.1572487664324749, "learning_rate": 5.510436428537271e-06, "loss": 0.4324, "num_tokens": 523828587.0, "step": 87685 }, { "epoch": 0.9355296427085444, "grad_norm": 1.1997619303646105, "learning_rate": 5.5095961397473366e-06, "loss": 0.4468, "num_tokens": 523857218.0, "step": 87690 }, { "epoch": 0.935582985714743, "grad_norm": 0.8521009837618932, "learning_rate": 5.508756535253603e-06, "loss": 0.4904, "num_tokens": 523897641.0, "step": 87695 }, { "epoch": 0.9356363287209414, "grad_norm": 0.6693900283056369, "learning_rate": 5.507917615082194e-06, "loss": 0.3654, "num_tokens": 523930878.0, "step": 87700 }, { "epoch": 0.9356896717271399, "grad_norm": 0.6831147848862652, "learning_rate": 5.507079379259216e-06, "loss": 0.4446, "num_tokens": 523966905.0, "step": 87705 }, { "epoch": 0.9357430147333383, "grad_norm": 0.8580387925738173, "learning_rate": 5.5062418278107496e-06, "loss": 0.415, "num_tokens": 524002393.0, "step": 87710 }, { "epoch": 0.9357963577395367, "grad_norm": 0.7752508675734813, "learning_rate": 5.5054049607628676e-06, "loss": 0.4165, "num_tokens": 524025737.0, "step": 87715 }, { "epoch": 0.9358497007457353, "grad_norm": 0.8893864990389445, "learning_rate": 5.5045687781416025e-06, "loss": 0.4507, "num_tokens": 524059147.0, "step": 87720 }, { "epoch": 0.9359030437519337, "grad_norm": 1.0800357718615334, "learning_rate": 5.503733279972975e-06, "loss": 0.5123, "num_tokens": 524079283.0, "step": 87725 }, { "epoch": 0.9359563867581321, "grad_norm": 1.1054268187734015, "learning_rate": 5.5028984662829865e-06, "loss": 0.4788, "num_tokens": 524115373.0, "step": 87730 }, { "epoch": 0.9360097297643306, "grad_norm": 0.8130941046024834, "learning_rate": 5.502064337097616e-06, "loss": 0.4188, "num_tokens": 524145168.0, "step": 87735 }, { "epoch": 0.936063072770529, "grad_norm": 0.8860037052212597, "learning_rate": 5.501230892442816e-06, "loss": 0.4935, "num_tokens": 524170273.0, "step": 87740 }, { "epoch": 0.9361164157767276, "grad_norm": 0.6692489573117515, "learning_rate": 5.500398132344526e-06, "loss": 0.4567, "num_tokens": 524201522.0, "step": 87745 }, { "epoch": 0.936169758782926, "grad_norm": 1.6735310801644143, "learning_rate": 5.499566056828658e-06, "loss": 0.5178, "num_tokens": 524227088.0, "step": 87750 }, { "epoch": 0.9362231017891244, "grad_norm": 1.1155392886516284, "learning_rate": 5.4987346659211045e-06, "loss": 0.4467, "num_tokens": 524248780.0, "step": 87755 }, { "epoch": 0.9362764447953229, "grad_norm": 0.8502971068020034, "learning_rate": 5.497903959647732e-06, "loss": 0.3352, "num_tokens": 524262652.0, "step": 87760 }, { "epoch": 0.9363297878015213, "grad_norm": 0.9289051163602574, "learning_rate": 5.497073938034399e-06, "loss": 0.5516, "num_tokens": 524296821.0, "step": 87765 }, { "epoch": 0.9363831308077198, "grad_norm": 0.7475551055863976, "learning_rate": 5.496244601106929e-06, "loss": 0.4563, "num_tokens": 524324969.0, "step": 87770 }, { "epoch": 0.9364364738139183, "grad_norm": 1.018064667372601, "learning_rate": 5.495415948891129e-06, "loss": 0.5025, "num_tokens": 524353130.0, "step": 87775 }, { "epoch": 0.9364898168201167, "grad_norm": 0.8992349648406148, "learning_rate": 5.494587981412788e-06, "loss": 0.477, "num_tokens": 524382585.0, "step": 87780 }, { "epoch": 0.9365431598263152, "grad_norm": 0.8855222356581497, "learning_rate": 5.493760698697666e-06, "loss": 0.5081, "num_tokens": 524421442.0, "step": 87785 }, { "epoch": 0.9365965028325136, "grad_norm": 1.1349042780357674, "learning_rate": 5.4929341007715115e-06, "loss": 0.4567, "num_tokens": 524441713.0, "step": 87790 }, { "epoch": 0.9366498458387121, "grad_norm": 1.4400409691426592, "learning_rate": 5.492108187660042e-06, "loss": 0.5316, "num_tokens": 524472321.0, "step": 87795 }, { "epoch": 0.9367031888449106, "grad_norm": 0.827877268227042, "learning_rate": 5.49128295938896e-06, "loss": 0.4349, "num_tokens": 524506334.0, "step": 87800 }, { "epoch": 0.936756531851109, "grad_norm": 0.9783688682034225, "learning_rate": 5.4904584159839455e-06, "loss": 0.3237, "num_tokens": 524526339.0, "step": 87805 }, { "epoch": 0.9368098748573075, "grad_norm": 1.2558768293021798, "learning_rate": 5.489634557470658e-06, "loss": 0.4542, "num_tokens": 524549433.0, "step": 87810 }, { "epoch": 0.9368632178635059, "grad_norm": 0.8204920235168814, "learning_rate": 5.4888113838747286e-06, "loss": 0.4837, "num_tokens": 524582142.0, "step": 87815 }, { "epoch": 0.9369165608697043, "grad_norm": 1.1573907346716918, "learning_rate": 5.4879888952217785e-06, "loss": 0.4613, "num_tokens": 524598190.0, "step": 87820 }, { "epoch": 0.9369699038759028, "grad_norm": 0.8035801895924117, "learning_rate": 5.4871670915374025e-06, "loss": 0.5214, "num_tokens": 524623985.0, "step": 87825 }, { "epoch": 0.9370232468821013, "grad_norm": 1.1053948551173893, "learning_rate": 5.486345972847167e-06, "loss": 0.4631, "num_tokens": 524659113.0, "step": 87830 }, { "epoch": 0.9370765898882998, "grad_norm": 0.8476962715433665, "learning_rate": 5.485525539176629e-06, "loss": 0.3255, "num_tokens": 524674847.0, "step": 87835 }, { "epoch": 0.9371299328944982, "grad_norm": 1.704549024202183, "learning_rate": 5.4847057905513196e-06, "loss": 0.5045, "num_tokens": 524701946.0, "step": 87840 }, { "epoch": 0.9371832759006966, "grad_norm": 0.9134428704796094, "learning_rate": 5.483886726996744e-06, "loss": 0.4573, "num_tokens": 524725886.0, "step": 87845 }, { "epoch": 0.9372366189068951, "grad_norm": 1.6293354822545234, "learning_rate": 5.4830683485383886e-06, "loss": 0.5182, "num_tokens": 524750538.0, "step": 87850 }, { "epoch": 0.9372899619130936, "grad_norm": 1.2116329667485144, "learning_rate": 5.482250655201725e-06, "loss": 0.5615, "num_tokens": 524783225.0, "step": 87855 }, { "epoch": 0.9373433049192921, "grad_norm": 0.9995415424229581, "learning_rate": 5.481433647012193e-06, "loss": 0.4315, "num_tokens": 524804448.0, "step": 87860 }, { "epoch": 0.9373966479254905, "grad_norm": 0.7236518133603308, "learning_rate": 5.480617323995223e-06, "loss": 0.513, "num_tokens": 524858231.0, "step": 87865 }, { "epoch": 0.9374499909316889, "grad_norm": 1.1631335041263728, "learning_rate": 5.47980168617621e-06, "loss": 0.5203, "num_tokens": 524884008.0, "step": 87870 }, { "epoch": 0.9375033339378874, "grad_norm": 1.1925082155580637, "learning_rate": 5.478986733580536e-06, "loss": 0.4701, "num_tokens": 524910318.0, "step": 87875 }, { "epoch": 0.9375566769440858, "grad_norm": 0.9726239281214204, "learning_rate": 5.478172466233562e-06, "loss": 0.6804, "num_tokens": 524969858.0, "step": 87880 }, { "epoch": 0.9376100199502844, "grad_norm": 0.7140763825979074, "learning_rate": 5.47735888416063e-06, "loss": 0.4647, "num_tokens": 525014092.0, "step": 87885 }, { "epoch": 0.9376633629564828, "grad_norm": 0.6322227524053426, "learning_rate": 5.476545987387051e-06, "loss": 0.487, "num_tokens": 525051095.0, "step": 87890 }, { "epoch": 0.9377167059626812, "grad_norm": 0.7572821263461416, "learning_rate": 5.475733775938126e-06, "loss": 0.4793, "num_tokens": 525086378.0, "step": 87895 }, { "epoch": 0.9377700489688797, "grad_norm": 0.6108805443891983, "learning_rate": 5.4749222498391255e-06, "loss": 0.4232, "num_tokens": 525129105.0, "step": 87900 }, { "epoch": 0.9378233919750781, "grad_norm": 0.9250154859109024, "learning_rate": 5.4741114091153015e-06, "loss": 0.4835, "num_tokens": 525158442.0, "step": 87905 }, { "epoch": 0.9378767349812765, "grad_norm": 0.9944950613794583, "learning_rate": 5.473301253791889e-06, "loss": 0.558, "num_tokens": 525207367.0, "step": 87910 }, { "epoch": 0.9379300779874751, "grad_norm": 0.742396808955061, "learning_rate": 5.4724917838941e-06, "loss": 0.425, "num_tokens": 525240441.0, "step": 87915 }, { "epoch": 0.9379834209936735, "grad_norm": 1.0436280070211437, "learning_rate": 5.471682999447118e-06, "loss": 0.3861, "num_tokens": 525276497.0, "step": 87920 }, { "epoch": 0.938036763999872, "grad_norm": 0.8958151657743949, "learning_rate": 5.470874900476114e-06, "loss": 0.4076, "num_tokens": 525294877.0, "step": 87925 }, { "epoch": 0.9380901070060704, "grad_norm": 0.6975843938711989, "learning_rate": 5.470067487006237e-06, "loss": 0.3737, "num_tokens": 525321595.0, "step": 87930 }, { "epoch": 0.9381434500122688, "grad_norm": 0.8310905917762715, "learning_rate": 5.469260759062608e-06, "loss": 0.4712, "num_tokens": 525344958.0, "step": 87935 }, { "epoch": 0.9381967930184674, "grad_norm": 0.7562408567166646, "learning_rate": 5.468454716670328e-06, "loss": 0.5176, "num_tokens": 525374962.0, "step": 87940 }, { "epoch": 0.9382501360246658, "grad_norm": 2.0241058912807968, "learning_rate": 5.467649359854488e-06, "loss": 0.416, "num_tokens": 525408204.0, "step": 87945 }, { "epoch": 0.9383034790308643, "grad_norm": 1.0326727952979058, "learning_rate": 5.466844688640142e-06, "loss": 0.398, "num_tokens": 525435075.0, "step": 87950 }, { "epoch": 0.9383568220370627, "grad_norm": 0.7050355480468746, "learning_rate": 5.4660407030523295e-06, "loss": 0.4278, "num_tokens": 525474097.0, "step": 87955 }, { "epoch": 0.9384101650432611, "grad_norm": 0.9182265567473258, "learning_rate": 5.465237403116075e-06, "loss": 0.4547, "num_tokens": 525485814.0, "step": 87960 }, { "epoch": 0.9384635080494597, "grad_norm": 1.1208524497968295, "learning_rate": 5.464434788856368e-06, "loss": 0.4058, "num_tokens": 525518307.0, "step": 87965 }, { "epoch": 0.9385168510556581, "grad_norm": 0.8389256460269636, "learning_rate": 5.463632860298193e-06, "loss": 0.4592, "num_tokens": 525552115.0, "step": 87970 }, { "epoch": 0.9385701940618566, "grad_norm": 0.9207078677023517, "learning_rate": 5.462831617466498e-06, "loss": 0.526, "num_tokens": 525573589.0, "step": 87975 }, { "epoch": 0.938623537068055, "grad_norm": 0.9155668735057954, "learning_rate": 5.462031060386215e-06, "loss": 0.4474, "num_tokens": 525606628.0, "step": 87980 }, { "epoch": 0.9386768800742534, "grad_norm": 0.898783711853342, "learning_rate": 5.461231189082259e-06, "loss": 0.5301, "num_tokens": 525643077.0, "step": 87985 }, { "epoch": 0.938730223080452, "grad_norm": 0.5893471947950882, "learning_rate": 5.460432003579521e-06, "loss": 0.3728, "num_tokens": 525686105.0, "step": 87990 }, { "epoch": 0.9387835660866504, "grad_norm": 0.7803115533720557, "learning_rate": 5.459633503902866e-06, "loss": 0.4105, "num_tokens": 525719348.0, "step": 87995 }, { "epoch": 0.9388369090928488, "grad_norm": 0.966067055727473, "learning_rate": 5.458835690077145e-06, "loss": 0.4674, "num_tokens": 525746360.0, "step": 88000 }, { "epoch": 0.9388902520990473, "grad_norm": 0.8466675052886885, "learning_rate": 5.458038562127185e-06, "loss": 0.5266, "num_tokens": 525792184.0, "step": 88005 }, { "epoch": 0.9389435951052457, "grad_norm": 0.9231877828411514, "learning_rate": 5.4572421200777885e-06, "loss": 0.4134, "num_tokens": 525832665.0, "step": 88010 }, { "epoch": 0.9389969381114442, "grad_norm": 1.6065283419044591, "learning_rate": 5.456446363953739e-06, "loss": 0.5729, "num_tokens": 525851717.0, "step": 88015 }, { "epoch": 0.9390502811176427, "grad_norm": 0.8913600465914907, "learning_rate": 5.455651293779801e-06, "loss": 0.3811, "num_tokens": 525878945.0, "step": 88020 }, { "epoch": 0.9391036241238411, "grad_norm": 0.9198181467197065, "learning_rate": 5.454856909580715e-06, "loss": 0.4696, "num_tokens": 525916646.0, "step": 88025 }, { "epoch": 0.9391569671300396, "grad_norm": 2.0680967347685053, "learning_rate": 5.454063211381199e-06, "loss": 0.3988, "num_tokens": 525935827.0, "step": 88030 }, { "epoch": 0.939210310136238, "grad_norm": 0.9873937752022676, "learning_rate": 5.453270199205953e-06, "loss": 0.4184, "num_tokens": 525967213.0, "step": 88035 }, { "epoch": 0.9392636531424365, "grad_norm": 0.7724854661346443, "learning_rate": 5.452477873079651e-06, "loss": 0.4934, "num_tokens": 525996117.0, "step": 88040 }, { "epoch": 0.939316996148635, "grad_norm": 0.6644103810060665, "learning_rate": 5.451686233026953e-06, "loss": 0.3885, "num_tokens": 526028409.0, "step": 88045 }, { "epoch": 0.9393703391548334, "grad_norm": 1.1337692817758558, "learning_rate": 5.45089527907249e-06, "loss": 0.5381, "num_tokens": 526072482.0, "step": 88050 }, { "epoch": 0.9394236821610319, "grad_norm": 0.8933251020458837, "learning_rate": 5.450105011240876e-06, "loss": 0.592, "num_tokens": 526096757.0, "step": 88055 }, { "epoch": 0.9394770251672303, "grad_norm": 0.7045392699286395, "learning_rate": 5.449315429556701e-06, "loss": 0.4617, "num_tokens": 526146922.0, "step": 88060 }, { "epoch": 0.9395303681734288, "grad_norm": 0.9400621902570767, "learning_rate": 5.44852653404454e-06, "loss": 0.4572, "num_tokens": 526172596.0, "step": 88065 }, { "epoch": 0.9395837111796272, "grad_norm": 0.8494440314771872, "learning_rate": 5.447738324728934e-06, "loss": 0.479, "num_tokens": 526210702.0, "step": 88070 }, { "epoch": 0.9396370541858257, "grad_norm": 1.6371558213878399, "learning_rate": 5.446950801634415e-06, "loss": 0.5013, "num_tokens": 526229946.0, "step": 88075 }, { "epoch": 0.9396903971920242, "grad_norm": 1.416313405576468, "learning_rate": 5.446163964785491e-06, "loss": 0.3873, "num_tokens": 526258803.0, "step": 88080 }, { "epoch": 0.9397437401982226, "grad_norm": 1.3083079550334606, "learning_rate": 5.445377814206646e-06, "loss": 0.4786, "num_tokens": 526274285.0, "step": 88085 }, { "epoch": 0.939797083204421, "grad_norm": 0.8200758999913969, "learning_rate": 5.44459234992234e-06, "loss": 0.47, "num_tokens": 526292300.0, "step": 88090 }, { "epoch": 0.9398504262106195, "grad_norm": 0.92745426281342, "learning_rate": 5.443807571957017e-06, "loss": 0.4357, "num_tokens": 526315756.0, "step": 88095 }, { "epoch": 0.939903769216818, "grad_norm": 0.8635530798589134, "learning_rate": 5.443023480335096e-06, "loss": 0.5164, "num_tokens": 526371009.0, "step": 88100 }, { "epoch": 0.9399571122230165, "grad_norm": 0.7957766367493467, "learning_rate": 5.442240075080979e-06, "loss": 0.4006, "num_tokens": 526404484.0, "step": 88105 }, { "epoch": 0.9400104552292149, "grad_norm": 2.229301701041198, "learning_rate": 5.441457356219044e-06, "loss": 0.4814, "num_tokens": 526447134.0, "step": 88110 }, { "epoch": 0.9400637982354133, "grad_norm": 0.880167989296378, "learning_rate": 5.440675323773645e-06, "loss": 0.3392, "num_tokens": 526472103.0, "step": 88115 }, { "epoch": 0.9401171412416118, "grad_norm": 1.6809952985918475, "learning_rate": 5.439893977769121e-06, "loss": 0.4753, "num_tokens": 526505099.0, "step": 88120 }, { "epoch": 0.9401704842478102, "grad_norm": 1.0589254801222734, "learning_rate": 5.4391133182297835e-06, "loss": 0.49, "num_tokens": 526534217.0, "step": 88125 }, { "epoch": 0.9402238272540088, "grad_norm": 1.532910494697283, "learning_rate": 5.438333345179922e-06, "loss": 0.6193, "num_tokens": 526558129.0, "step": 88130 }, { "epoch": 0.9402771702602072, "grad_norm": 0.8452578235218102, "learning_rate": 5.437554058643813e-06, "loss": 0.524, "num_tokens": 526606151.0, "step": 88135 }, { "epoch": 0.9403305132664056, "grad_norm": 1.0642160942525898, "learning_rate": 5.436775458645703e-06, "loss": 0.3806, "num_tokens": 526629491.0, "step": 88140 }, { "epoch": 0.9403838562726041, "grad_norm": 0.7763791092993073, "learning_rate": 5.435997545209823e-06, "loss": 0.4699, "num_tokens": 526661848.0, "step": 88145 }, { "epoch": 0.9404371992788025, "grad_norm": 0.8614185194127758, "learning_rate": 5.4352203183603755e-06, "loss": 0.4461, "num_tokens": 526688051.0, "step": 88150 }, { "epoch": 0.9404905422850011, "grad_norm": 0.9323955895577619, "learning_rate": 5.4344437781215545e-06, "loss": 0.4104, "num_tokens": 526720583.0, "step": 88155 }, { "epoch": 0.9405438852911995, "grad_norm": 0.5158354492562129, "learning_rate": 5.433667924517516e-06, "loss": 0.5234, "num_tokens": 526758625.0, "step": 88160 }, { "epoch": 0.9405972282973979, "grad_norm": 0.7102543844588651, "learning_rate": 5.432892757572406e-06, "loss": 0.3762, "num_tokens": 526775917.0, "step": 88165 }, { "epoch": 0.9406505713035964, "grad_norm": 0.9779065355408845, "learning_rate": 5.432118277310349e-06, "loss": 0.4555, "num_tokens": 526803943.0, "step": 88170 }, { "epoch": 0.9407039143097948, "grad_norm": 0.6346853312535761, "learning_rate": 5.4313444837554396e-06, "loss": 0.472, "num_tokens": 526834570.0, "step": 88175 }, { "epoch": 0.9407572573159932, "grad_norm": 0.9745812946331098, "learning_rate": 5.430571376931758e-06, "loss": 0.4513, "num_tokens": 526858377.0, "step": 88180 }, { "epoch": 0.9408106003221918, "grad_norm": 1.022424244003322, "learning_rate": 5.429798956863369e-06, "loss": 0.4406, "num_tokens": 526890790.0, "step": 88185 }, { "epoch": 0.9408639433283902, "grad_norm": 0.5608244946347413, "learning_rate": 5.4290272235743e-06, "loss": 0.3889, "num_tokens": 526932522.0, "step": 88190 }, { "epoch": 0.9409172863345887, "grad_norm": 0.7575473628554036, "learning_rate": 5.4282561770885665e-06, "loss": 0.6068, "num_tokens": 526953883.0, "step": 88195 }, { "epoch": 0.9409706293407871, "grad_norm": 0.7682297392895697, "learning_rate": 5.427485817430167e-06, "loss": 0.4478, "num_tokens": 526982097.0, "step": 88200 }, { "epoch": 0.9410239723469855, "grad_norm": 2.3259048287084214, "learning_rate": 5.426716144623069e-06, "loss": 0.5376, "num_tokens": 527011140.0, "step": 88205 }, { "epoch": 0.9410773153531841, "grad_norm": 0.8801672101816375, "learning_rate": 5.425947158691225e-06, "loss": 0.458, "num_tokens": 527040401.0, "step": 88210 }, { "epoch": 0.9411306583593825, "grad_norm": 1.1052441896856842, "learning_rate": 5.425178859658566e-06, "loss": 0.4875, "num_tokens": 527076609.0, "step": 88215 }, { "epoch": 0.941184001365581, "grad_norm": 0.8171173389385002, "learning_rate": 5.424411247548995e-06, "loss": 0.4032, "num_tokens": 527109689.0, "step": 88220 }, { "epoch": 0.9412373443717794, "grad_norm": 0.5537124412335158, "learning_rate": 5.423644322386403e-06, "loss": 0.3976, "num_tokens": 527143725.0, "step": 88225 }, { "epoch": 0.9412906873779778, "grad_norm": 0.8068163547899109, "learning_rate": 5.422878084194656e-06, "loss": 0.3902, "num_tokens": 527164890.0, "step": 88230 }, { "epoch": 0.9413440303841764, "grad_norm": 0.8080643070060128, "learning_rate": 5.422112532997591e-06, "loss": 0.3714, "num_tokens": 527202979.0, "step": 88235 }, { "epoch": 0.9413973733903748, "grad_norm": 0.7302912248707312, "learning_rate": 5.421347668819035e-06, "loss": 0.3759, "num_tokens": 527226930.0, "step": 88240 }, { "epoch": 0.9414507163965733, "grad_norm": 0.8292059323746592, "learning_rate": 5.4205834916827905e-06, "loss": 0.4804, "num_tokens": 527262733.0, "step": 88245 }, { "epoch": 0.9415040594027717, "grad_norm": 1.731571249623424, "learning_rate": 5.419820001612634e-06, "loss": 0.5468, "num_tokens": 527288422.0, "step": 88250 }, { "epoch": 0.9415574024089701, "grad_norm": 0.7511965493261844, "learning_rate": 5.419057198632326e-06, "loss": 0.5374, "num_tokens": 527310713.0, "step": 88255 }, { "epoch": 0.9416107454151686, "grad_norm": 0.7821961403029869, "learning_rate": 5.4182950827656035e-06, "loss": 0.4209, "num_tokens": 527336581.0, "step": 88260 }, { "epoch": 0.9416640884213671, "grad_norm": 0.9785976971081104, "learning_rate": 5.417533654036181e-06, "loss": 0.5025, "num_tokens": 527360686.0, "step": 88265 }, { "epoch": 0.9417174314275655, "grad_norm": 1.0394919225769208, "learning_rate": 5.416772912467748e-06, "loss": 0.424, "num_tokens": 527390058.0, "step": 88270 }, { "epoch": 0.941770774433764, "grad_norm": 1.296714643540632, "learning_rate": 5.416012858083985e-06, "loss": 0.4952, "num_tokens": 527432399.0, "step": 88275 }, { "epoch": 0.9418241174399624, "grad_norm": 1.3741064666820026, "learning_rate": 5.41525349090854e-06, "loss": 0.5568, "num_tokens": 527444651.0, "step": 88280 }, { "epoch": 0.9418774604461609, "grad_norm": 0.9313321522027865, "learning_rate": 5.414494810965044e-06, "loss": 0.4586, "num_tokens": 527466832.0, "step": 88285 }, { "epoch": 0.9419308034523594, "grad_norm": 1.1838673283027563, "learning_rate": 5.4137368182771025e-06, "loss": 0.4707, "num_tokens": 527492198.0, "step": 88290 }, { "epoch": 0.9419841464585578, "grad_norm": 0.7598701748166111, "learning_rate": 5.412979512868304e-06, "loss": 0.3992, "num_tokens": 527518239.0, "step": 88295 }, { "epoch": 0.9420374894647563, "grad_norm": 0.9188800897390195, "learning_rate": 5.412222894762219e-06, "loss": 0.48, "num_tokens": 527546328.0, "step": 88300 }, { "epoch": 0.9420908324709547, "grad_norm": 2.482358286448307, "learning_rate": 5.411466963982387e-06, "loss": 0.5136, "num_tokens": 527573084.0, "step": 88305 }, { "epoch": 0.9421441754771532, "grad_norm": 1.2106063130884073, "learning_rate": 5.410711720552329e-06, "loss": 0.477, "num_tokens": 527610140.0, "step": 88310 }, { "epoch": 0.9421975184833516, "grad_norm": 0.7456273460095584, "learning_rate": 5.40995716449555e-06, "loss": 0.5323, "num_tokens": 527642802.0, "step": 88315 }, { "epoch": 0.9422508614895501, "grad_norm": 1.0698801300551164, "learning_rate": 5.409203295835532e-06, "loss": 0.507, "num_tokens": 527666864.0, "step": 88320 }, { "epoch": 0.9423042044957486, "grad_norm": 1.3716145515090223, "learning_rate": 5.408450114595731e-06, "loss": 0.3549, "num_tokens": 527685604.0, "step": 88325 }, { "epoch": 0.942357547501947, "grad_norm": 0.7379794566429774, "learning_rate": 5.407697620799584e-06, "loss": 0.3988, "num_tokens": 527715949.0, "step": 88330 }, { "epoch": 0.9424108905081455, "grad_norm": 1.228168338378694, "learning_rate": 5.406945814470511e-06, "loss": 0.5023, "num_tokens": 527753897.0, "step": 88335 }, { "epoch": 0.9424642335143439, "grad_norm": 0.7376969640556711, "learning_rate": 5.406194695631901e-06, "loss": 0.497, "num_tokens": 527790944.0, "step": 88340 }, { "epoch": 0.9425175765205424, "grad_norm": 0.9287850725200963, "learning_rate": 5.405444264307131e-06, "loss": 0.4867, "num_tokens": 527818880.0, "step": 88345 }, { "epoch": 0.9425709195267409, "grad_norm": 1.0969178755999152, "learning_rate": 5.404694520519552e-06, "loss": 0.4913, "num_tokens": 527858545.0, "step": 88350 }, { "epoch": 0.9426242625329393, "grad_norm": 0.8795185402527872, "learning_rate": 5.403945464292495e-06, "loss": 0.514, "num_tokens": 527901819.0, "step": 88355 }, { "epoch": 0.9426776055391377, "grad_norm": 0.6951494683284776, "learning_rate": 5.403197095649265e-06, "loss": 0.4615, "num_tokens": 527948734.0, "step": 88360 }, { "epoch": 0.9427309485453362, "grad_norm": 1.1849184219516333, "learning_rate": 5.402449414613157e-06, "loss": 0.3582, "num_tokens": 527981702.0, "step": 88365 }, { "epoch": 0.9427842915515346, "grad_norm": 1.7675393295026445, "learning_rate": 5.401702421207431e-06, "loss": 0.5668, "num_tokens": 528012707.0, "step": 88370 }, { "epoch": 0.9428376345577332, "grad_norm": 0.9697000773028474, "learning_rate": 5.400956115455339e-06, "loss": 0.3588, "num_tokens": 528043038.0, "step": 88375 }, { "epoch": 0.9428909775639316, "grad_norm": 1.1143972512248903, "learning_rate": 5.4002104973800966e-06, "loss": 0.445, "num_tokens": 528059463.0, "step": 88380 }, { "epoch": 0.94294432057013, "grad_norm": 0.8624958940542246, "learning_rate": 5.39946556700491e-06, "loss": 0.5449, "num_tokens": 528101893.0, "step": 88385 }, { "epoch": 0.9429976635763285, "grad_norm": 0.6579246414648, "learning_rate": 5.398721324352958e-06, "loss": 0.4609, "num_tokens": 528133786.0, "step": 88390 }, { "epoch": 0.9430510065825269, "grad_norm": 0.860024075729082, "learning_rate": 5.397977769447402e-06, "loss": 0.4696, "num_tokens": 528162421.0, "step": 88395 }, { "epoch": 0.9431043495887255, "grad_norm": 0.718806042425823, "learning_rate": 5.397234902311378e-06, "loss": 0.3725, "num_tokens": 528196808.0, "step": 88400 }, { "epoch": 0.9431576925949239, "grad_norm": 0.8336324380374192, "learning_rate": 5.396492722968003e-06, "loss": 0.4644, "num_tokens": 528233338.0, "step": 88405 }, { "epoch": 0.9432110356011223, "grad_norm": 0.7373351724288589, "learning_rate": 5.395751231440375e-06, "loss": 0.4704, "num_tokens": 528279813.0, "step": 88410 }, { "epoch": 0.9432643786073208, "grad_norm": 0.9143697109661624, "learning_rate": 5.395010427751565e-06, "loss": 0.38, "num_tokens": 528298013.0, "step": 88415 }, { "epoch": 0.9433177216135192, "grad_norm": 0.6859532049584838, "learning_rate": 5.394270311924623e-06, "loss": 0.4587, "num_tokens": 528328932.0, "step": 88420 }, { "epoch": 0.9433710646197178, "grad_norm": 0.7737995969022393, "learning_rate": 5.393530883982587e-06, "loss": 0.3461, "num_tokens": 528356829.0, "step": 88425 }, { "epoch": 0.9434244076259162, "grad_norm": 0.8926743432412317, "learning_rate": 5.392792143948457e-06, "loss": 0.4303, "num_tokens": 528379343.0, "step": 88430 }, { "epoch": 0.9434777506321146, "grad_norm": 0.7703350573473088, "learning_rate": 5.392054091845226e-06, "loss": 0.4908, "num_tokens": 528414516.0, "step": 88435 }, { "epoch": 0.9435310936383131, "grad_norm": 1.2680163347360476, "learning_rate": 5.391316727695864e-06, "loss": 0.4528, "num_tokens": 528450261.0, "step": 88440 }, { "epoch": 0.9435844366445115, "grad_norm": 1.0408168518632943, "learning_rate": 5.390580051523312e-06, "loss": 0.4509, "num_tokens": 528472674.0, "step": 88445 }, { "epoch": 0.9436377796507099, "grad_norm": 1.0635131920976966, "learning_rate": 5.3898440633504945e-06, "loss": 0.611, "num_tokens": 528512219.0, "step": 88450 }, { "epoch": 0.9436911226569085, "grad_norm": 0.9905763250649862, "learning_rate": 5.389108763200314e-06, "loss": 0.3663, "num_tokens": 528535487.0, "step": 88455 }, { "epoch": 0.9437444656631069, "grad_norm": 1.4664356187422423, "learning_rate": 5.388374151095653e-06, "loss": 0.5114, "num_tokens": 528577234.0, "step": 88460 }, { "epoch": 0.9437978086693054, "grad_norm": 0.7095787070320979, "learning_rate": 5.387640227059365e-06, "loss": 0.4711, "num_tokens": 528615167.0, "step": 88465 }, { "epoch": 0.9438511516755038, "grad_norm": 2.4509964597139784, "learning_rate": 5.386906991114299e-06, "loss": 0.631, "num_tokens": 528647642.0, "step": 88470 }, { "epoch": 0.9439044946817022, "grad_norm": 1.32945465699348, "learning_rate": 5.386174443283262e-06, "loss": 0.5428, "num_tokens": 528680052.0, "step": 88475 }, { "epoch": 0.9439578376879008, "grad_norm": 0.8405817760846862, "learning_rate": 5.385442583589055e-06, "loss": 0.4381, "num_tokens": 528711638.0, "step": 88480 }, { "epoch": 0.9440111806940992, "grad_norm": 1.1407386183882042, "learning_rate": 5.38471141205445e-06, "loss": 0.4898, "num_tokens": 528739606.0, "step": 88485 }, { "epoch": 0.9440645237002977, "grad_norm": 1.0148070600358656, "learning_rate": 5.3839809287021995e-06, "loss": 0.5018, "num_tokens": 528773162.0, "step": 88490 }, { "epoch": 0.9441178667064961, "grad_norm": 0.8140864078956852, "learning_rate": 5.3832511335550356e-06, "loss": 0.5031, "num_tokens": 528802245.0, "step": 88495 }, { "epoch": 0.9441712097126945, "grad_norm": 1.308929998187872, "learning_rate": 5.382522026635666e-06, "loss": 0.4867, "num_tokens": 528824627.0, "step": 88500 }, { "epoch": 0.944224552718893, "grad_norm": 0.6262995231014491, "learning_rate": 5.3817936079667815e-06, "loss": 0.4492, "num_tokens": 528863951.0, "step": 88505 }, { "epoch": 0.9442778957250915, "grad_norm": 1.2277274526103523, "learning_rate": 5.3810658775710466e-06, "loss": 0.5042, "num_tokens": 528886227.0, "step": 88510 }, { "epoch": 0.94433123873129, "grad_norm": 0.8681422136484769, "learning_rate": 5.380338835471107e-06, "loss": 0.549, "num_tokens": 528912524.0, "step": 88515 }, { "epoch": 0.9443845817374884, "grad_norm": 1.4551512977879912, "learning_rate": 5.3796124816895915e-06, "loss": 0.5134, "num_tokens": 528941853.0, "step": 88520 }, { "epoch": 0.9444379247436868, "grad_norm": 0.8745390794412666, "learning_rate": 5.378886816249096e-06, "loss": 0.4116, "num_tokens": 528967992.0, "step": 88525 }, { "epoch": 0.9444912677498853, "grad_norm": 0.9539937262465272, "learning_rate": 5.3781618391722075e-06, "loss": 0.4291, "num_tokens": 528995128.0, "step": 88530 }, { "epoch": 0.9445446107560838, "grad_norm": 0.9588678895326453, "learning_rate": 5.3774375504814785e-06, "loss": 0.408, "num_tokens": 529021611.0, "step": 88535 }, { "epoch": 0.9445979537622822, "grad_norm": 0.8184751352975588, "learning_rate": 5.376713950199456e-06, "loss": 0.4307, "num_tokens": 529058479.0, "step": 88540 }, { "epoch": 0.9446512967684807, "grad_norm": 1.889644254046987, "learning_rate": 5.375991038348652e-06, "loss": 0.5083, "num_tokens": 529095330.0, "step": 88545 }, { "epoch": 0.9447046397746791, "grad_norm": 0.6531289162149101, "learning_rate": 5.37526881495156e-06, "loss": 0.5115, "num_tokens": 529126308.0, "step": 88550 }, { "epoch": 0.9447579827808776, "grad_norm": 1.4485757571539624, "learning_rate": 5.374547280030662e-06, "loss": 0.5145, "num_tokens": 529157182.0, "step": 88555 }, { "epoch": 0.944811325787076, "grad_norm": 2.0201517088496335, "learning_rate": 5.373826433608403e-06, "loss": 0.3776, "num_tokens": 529179204.0, "step": 88560 }, { "epoch": 0.9448646687932745, "grad_norm": 0.6759015795712083, "learning_rate": 5.373106275707215e-06, "loss": 0.5013, "num_tokens": 529213721.0, "step": 88565 }, { "epoch": 0.944918011799473, "grad_norm": 0.6207814055885793, "learning_rate": 5.372386806349512e-06, "loss": 0.39, "num_tokens": 529239604.0, "step": 88570 }, { "epoch": 0.9449713548056714, "grad_norm": 1.1787814201637665, "learning_rate": 5.3716680255576815e-06, "loss": 0.5091, "num_tokens": 529271401.0, "step": 88575 }, { "epoch": 0.9450246978118699, "grad_norm": 0.5273795241067889, "learning_rate": 5.370949933354086e-06, "loss": 0.5439, "num_tokens": 529311616.0, "step": 88580 }, { "epoch": 0.9450780408180683, "grad_norm": 1.01201882229043, "learning_rate": 5.370232529761076e-06, "loss": 0.5425, "num_tokens": 529336491.0, "step": 88585 }, { "epoch": 0.9451313838242668, "grad_norm": 0.8725911316601622, "learning_rate": 5.369515814800975e-06, "loss": 0.424, "num_tokens": 529363639.0, "step": 88590 }, { "epoch": 0.9451847268304653, "grad_norm": 1.472335905995063, "learning_rate": 5.368799788496082e-06, "loss": 0.4191, "num_tokens": 529391147.0, "step": 88595 }, { "epoch": 0.9452380698366637, "grad_norm": 1.0068156427657478, "learning_rate": 5.368084450868682e-06, "loss": 0.4856, "num_tokens": 529420438.0, "step": 88600 }, { "epoch": 0.9452914128428622, "grad_norm": 1.0150665420027543, "learning_rate": 5.367369801941034e-06, "loss": 0.434, "num_tokens": 529440902.0, "step": 88605 }, { "epoch": 0.9453447558490606, "grad_norm": 0.7883200255028807, "learning_rate": 5.3666558417353745e-06, "loss": 0.3921, "num_tokens": 529473379.0, "step": 88610 }, { "epoch": 0.945398098855259, "grad_norm": 1.0496773923093092, "learning_rate": 5.365942570273923e-06, "loss": 0.499, "num_tokens": 529494464.0, "step": 88615 }, { "epoch": 0.9454514418614576, "grad_norm": 0.8053567408046902, "learning_rate": 5.365229987578872e-06, "loss": 0.4506, "num_tokens": 529522224.0, "step": 88620 }, { "epoch": 0.945504784867656, "grad_norm": 1.1695710382421058, "learning_rate": 5.3645180936724005e-06, "loss": 0.482, "num_tokens": 529544271.0, "step": 88625 }, { "epoch": 0.9455581278738544, "grad_norm": 1.0004679205926987, "learning_rate": 5.363806888576657e-06, "loss": 0.372, "num_tokens": 529564950.0, "step": 88630 }, { "epoch": 0.9456114708800529, "grad_norm": 0.6615897612276919, "learning_rate": 5.363096372313775e-06, "loss": 0.3328, "num_tokens": 529587890.0, "step": 88635 }, { "epoch": 0.9456648138862513, "grad_norm": 0.7271859410774162, "learning_rate": 5.362386544905865e-06, "loss": 0.5045, "num_tokens": 529624010.0, "step": 88640 }, { "epoch": 0.9457181568924499, "grad_norm": 0.8955101059590385, "learning_rate": 5.361677406375011e-06, "loss": 0.5748, "num_tokens": 529642658.0, "step": 88645 }, { "epoch": 0.9457714998986483, "grad_norm": 1.2166018442420614, "learning_rate": 5.360968956743282e-06, "loss": 0.3603, "num_tokens": 529664973.0, "step": 88650 }, { "epoch": 0.9458248429048467, "grad_norm": 0.890141068409375, "learning_rate": 5.3602611960327255e-06, "loss": 0.4022, "num_tokens": 529706058.0, "step": 88655 }, { "epoch": 0.9458781859110452, "grad_norm": 1.0490631743350771, "learning_rate": 5.359554124265365e-06, "loss": 0.4985, "num_tokens": 529742007.0, "step": 88660 }, { "epoch": 0.9459315289172436, "grad_norm": 0.842100964783895, "learning_rate": 5.358847741463204e-06, "loss": 0.5172, "num_tokens": 529780701.0, "step": 88665 }, { "epoch": 0.9459848719234422, "grad_norm": 1.2561694388811162, "learning_rate": 5.358142047648219e-06, "loss": 0.424, "num_tokens": 529812956.0, "step": 88670 }, { "epoch": 0.9460382149296406, "grad_norm": 0.8794633444187393, "learning_rate": 5.357437042842373e-06, "loss": 0.3775, "num_tokens": 529834657.0, "step": 88675 }, { "epoch": 0.946091557935839, "grad_norm": 1.4108365117385102, "learning_rate": 5.356732727067605e-06, "loss": 0.5807, "num_tokens": 529869752.0, "step": 88680 }, { "epoch": 0.9461449009420375, "grad_norm": 0.7849677908484531, "learning_rate": 5.35602910034583e-06, "loss": 0.5077, "num_tokens": 529900649.0, "step": 88685 }, { "epoch": 0.9461982439482359, "grad_norm": 0.8300504391404371, "learning_rate": 5.3553261626989445e-06, "loss": 0.5229, "num_tokens": 529941266.0, "step": 88690 }, { "epoch": 0.9462515869544345, "grad_norm": 0.9987781310863787, "learning_rate": 5.354623914148822e-06, "loss": 0.4109, "num_tokens": 529962231.0, "step": 88695 }, { "epoch": 0.9463049299606329, "grad_norm": 0.9545976685817581, "learning_rate": 5.353922354717318e-06, "loss": 0.3891, "num_tokens": 529989981.0, "step": 88700 }, { "epoch": 0.9463582729668313, "grad_norm": 1.5918017732533158, "learning_rate": 5.3532214844262594e-06, "loss": 0.4777, "num_tokens": 530023135.0, "step": 88705 }, { "epoch": 0.9464116159730298, "grad_norm": 1.5457792371935224, "learning_rate": 5.3525213032974575e-06, "loss": 0.6011, "num_tokens": 530036062.0, "step": 88710 }, { "epoch": 0.9464649589792282, "grad_norm": 0.9538611718778431, "learning_rate": 5.351821811352701e-06, "loss": 0.5138, "num_tokens": 530078139.0, "step": 88715 }, { "epoch": 0.9465183019854266, "grad_norm": 1.429663353282107, "learning_rate": 5.351123008613754e-06, "loss": 0.3233, "num_tokens": 530098534.0, "step": 88720 }, { "epoch": 0.9465716449916252, "grad_norm": 0.5595373187825486, "learning_rate": 5.350424895102365e-06, "loss": 0.5231, "num_tokens": 530134602.0, "step": 88725 }, { "epoch": 0.9466249879978236, "grad_norm": 0.9289678828965685, "learning_rate": 5.349727470840259e-06, "loss": 0.4409, "num_tokens": 530166938.0, "step": 88730 }, { "epoch": 0.9466783310040221, "grad_norm": 1.7339273311242256, "learning_rate": 5.349030735849132e-06, "loss": 0.5601, "num_tokens": 530186884.0, "step": 88735 }, { "epoch": 0.9467316740102205, "grad_norm": 0.7653376465696689, "learning_rate": 5.3483346901506714e-06, "loss": 0.3422, "num_tokens": 530197746.0, "step": 88740 }, { "epoch": 0.9467850170164189, "grad_norm": 0.6922589313921602, "learning_rate": 5.347639333766536e-06, "loss": 0.3868, "num_tokens": 530221813.0, "step": 88745 }, { "epoch": 0.9468383600226175, "grad_norm": 0.7907633866310226, "learning_rate": 5.346944666718359e-06, "loss": 0.4124, "num_tokens": 530259500.0, "step": 88750 }, { "epoch": 0.9468917030288159, "grad_norm": 0.6453004326077556, "learning_rate": 5.346250689027761e-06, "loss": 0.3637, "num_tokens": 530282140.0, "step": 88755 }, { "epoch": 0.9469450460350144, "grad_norm": 0.9978356428972733, "learning_rate": 5.345557400716338e-06, "loss": 0.3991, "num_tokens": 530306888.0, "step": 88760 }, { "epoch": 0.9469983890412128, "grad_norm": 0.8456026155488073, "learning_rate": 5.344864801805663e-06, "loss": 0.3909, "num_tokens": 530333244.0, "step": 88765 }, { "epoch": 0.9470517320474112, "grad_norm": 0.9103386764594907, "learning_rate": 5.344172892317284e-06, "loss": 0.473, "num_tokens": 530366924.0, "step": 88770 }, { "epoch": 0.9471050750536097, "grad_norm": 1.4380123064764896, "learning_rate": 5.343481672272737e-06, "loss": 0.5617, "num_tokens": 530419214.0, "step": 88775 }, { "epoch": 0.9471584180598082, "grad_norm": 0.8618004016090067, "learning_rate": 5.342791141693533e-06, "loss": 0.4045, "num_tokens": 530438196.0, "step": 88780 }, { "epoch": 0.9472117610660067, "grad_norm": 0.577592012969003, "learning_rate": 5.34210130060115e-06, "loss": 0.4362, "num_tokens": 530484960.0, "step": 88785 }, { "epoch": 0.9472651040722051, "grad_norm": 0.846897896849795, "learning_rate": 5.341412149017066e-06, "loss": 0.4305, "num_tokens": 530507731.0, "step": 88790 }, { "epoch": 0.9473184470784035, "grad_norm": 0.9022197936503835, "learning_rate": 5.340723686962718e-06, "loss": 0.5035, "num_tokens": 530530015.0, "step": 88795 }, { "epoch": 0.947371790084602, "grad_norm": 1.1746791023901564, "learning_rate": 5.340035914459531e-06, "loss": 0.4687, "num_tokens": 530544972.0, "step": 88800 }, { "epoch": 0.9474251330908005, "grad_norm": 0.84717148350311, "learning_rate": 5.339348831528913e-06, "loss": 0.505, "num_tokens": 530581727.0, "step": 88805 }, { "epoch": 0.9474784760969989, "grad_norm": 0.911205793599129, "learning_rate": 5.338662438192237e-06, "loss": 0.4957, "num_tokens": 530617052.0, "step": 88810 }, { "epoch": 0.9475318191031974, "grad_norm": 1.0346757579121761, "learning_rate": 5.3379767344708665e-06, "loss": 0.4525, "num_tokens": 530659522.0, "step": 88815 }, { "epoch": 0.9475851621093958, "grad_norm": 1.3860698148372896, "learning_rate": 5.337291720386137e-06, "loss": 0.4513, "num_tokens": 530682152.0, "step": 88820 }, { "epoch": 0.9476385051155943, "grad_norm": 0.9560100895888918, "learning_rate": 5.336607395959367e-06, "loss": 0.6403, "num_tokens": 530711083.0, "step": 88825 }, { "epoch": 0.9476918481217927, "grad_norm": 2.3150773397269018, "learning_rate": 5.335923761211849e-06, "loss": 0.5491, "num_tokens": 530745864.0, "step": 88830 }, { "epoch": 0.9477451911279912, "grad_norm": 0.7607074252151291, "learning_rate": 5.335240816164856e-06, "loss": 0.4577, "num_tokens": 530767387.0, "step": 88835 }, { "epoch": 0.9477985341341897, "grad_norm": 0.9899803796653172, "learning_rate": 5.334558560839644e-06, "loss": 0.5067, "num_tokens": 530799366.0, "step": 88840 }, { "epoch": 0.9478518771403881, "grad_norm": 4.112731363316548, "learning_rate": 5.333876995257439e-06, "loss": 0.5944, "num_tokens": 530832170.0, "step": 88845 }, { "epoch": 0.9479052201465866, "grad_norm": 0.844398547645437, "learning_rate": 5.333196119439452e-06, "loss": 0.3665, "num_tokens": 530853467.0, "step": 88850 }, { "epoch": 0.947958563152785, "grad_norm": 0.755697369473311, "learning_rate": 5.332515933406867e-06, "loss": 0.4785, "num_tokens": 530888053.0, "step": 88855 }, { "epoch": 0.9480119061589835, "grad_norm": 1.5249374967536222, "learning_rate": 5.331836437180856e-06, "loss": 0.4035, "num_tokens": 530912438.0, "step": 88860 }, { "epoch": 0.948065249165182, "grad_norm": 0.7232204667845521, "learning_rate": 5.33115763078256e-06, "loss": 0.4621, "num_tokens": 530941717.0, "step": 88865 }, { "epoch": 0.9481185921713804, "grad_norm": 0.8361768725398143, "learning_rate": 5.3304795142331e-06, "loss": 0.4368, "num_tokens": 530968309.0, "step": 88870 }, { "epoch": 0.9481719351775789, "grad_norm": 1.7449436232700568, "learning_rate": 5.32980208755358e-06, "loss": 0.4387, "num_tokens": 530988552.0, "step": 88875 }, { "epoch": 0.9482252781837773, "grad_norm": 1.541138927153161, "learning_rate": 5.329125350765083e-06, "loss": 0.3778, "num_tokens": 531009231.0, "step": 88880 }, { "epoch": 0.9482786211899757, "grad_norm": 1.335036920082724, "learning_rate": 5.328449303888666e-06, "loss": 0.4182, "num_tokens": 531025599.0, "step": 88885 }, { "epoch": 0.9483319641961743, "grad_norm": 1.2281639295765914, "learning_rate": 5.327773946945361e-06, "loss": 0.4755, "num_tokens": 531062432.0, "step": 88890 }, { "epoch": 0.9483853072023727, "grad_norm": 0.6522868360216812, "learning_rate": 5.327099279956191e-06, "loss": 0.3553, "num_tokens": 531079324.0, "step": 88895 }, { "epoch": 0.9484386502085711, "grad_norm": 1.0778742353490403, "learning_rate": 5.326425302942145e-06, "loss": 0.5227, "num_tokens": 531116715.0, "step": 88900 }, { "epoch": 0.9484919932147696, "grad_norm": 0.7488467963336501, "learning_rate": 5.325752015924197e-06, "loss": 0.4746, "num_tokens": 531155695.0, "step": 88905 }, { "epoch": 0.948545336220968, "grad_norm": 0.6724232964722449, "learning_rate": 5.325079418923302e-06, "loss": 0.367, "num_tokens": 531180388.0, "step": 88910 }, { "epoch": 0.9485986792271666, "grad_norm": 1.1516434527743022, "learning_rate": 5.324407511960384e-06, "loss": 0.436, "num_tokens": 531197952.0, "step": 88915 }, { "epoch": 0.948652022233365, "grad_norm": 0.8294144875033588, "learning_rate": 5.323736295056356e-06, "loss": 0.4652, "num_tokens": 531223042.0, "step": 88920 }, { "epoch": 0.9487053652395634, "grad_norm": 1.4571629639174482, "learning_rate": 5.323065768232101e-06, "loss": 0.5915, "num_tokens": 531245023.0, "step": 88925 }, { "epoch": 0.9487587082457619, "grad_norm": 1.0052700409236532, "learning_rate": 5.322395931508488e-06, "loss": 0.4878, "num_tokens": 531274478.0, "step": 88930 }, { "epoch": 0.9488120512519603, "grad_norm": 0.7824377076722593, "learning_rate": 5.32172678490636e-06, "loss": 0.5843, "num_tokens": 531315511.0, "step": 88935 }, { "epoch": 0.9488653942581589, "grad_norm": 0.7374144402063588, "learning_rate": 5.321058328446537e-06, "loss": 0.363, "num_tokens": 531344049.0, "step": 88940 }, { "epoch": 0.9489187372643573, "grad_norm": 1.215578654213971, "learning_rate": 5.320390562149825e-06, "loss": 0.5932, "num_tokens": 531371309.0, "step": 88945 }, { "epoch": 0.9489720802705557, "grad_norm": 0.5555083302567814, "learning_rate": 5.319723486036997e-06, "loss": 0.4474, "num_tokens": 531418565.0, "step": 88950 }, { "epoch": 0.9490254232767542, "grad_norm": 0.7384914252524241, "learning_rate": 5.319057100128817e-06, "loss": 0.4659, "num_tokens": 531437684.0, "step": 88955 }, { "epoch": 0.9490787662829526, "grad_norm": 0.7060761570278505, "learning_rate": 5.318391404446019e-06, "loss": 0.421, "num_tokens": 531466359.0, "step": 88960 }, { "epoch": 0.9491321092891511, "grad_norm": 1.3591994259128841, "learning_rate": 5.3177263990093196e-06, "loss": 0.449, "num_tokens": 531483474.0, "step": 88965 }, { "epoch": 0.9491854522953496, "grad_norm": 0.9155113429904204, "learning_rate": 5.317062083839408e-06, "loss": 0.3909, "num_tokens": 531521105.0, "step": 88970 }, { "epoch": 0.949238795301548, "grad_norm": 0.9369636783445787, "learning_rate": 5.31639845895696e-06, "loss": 0.429, "num_tokens": 531540458.0, "step": 88975 }, { "epoch": 0.9492921383077465, "grad_norm": 1.1643751914029095, "learning_rate": 5.3157355243826254e-06, "loss": 0.4148, "num_tokens": 531553112.0, "step": 88980 }, { "epoch": 0.9493454813139449, "grad_norm": 0.8622441700725061, "learning_rate": 5.315073280137034e-06, "loss": 0.4481, "num_tokens": 531589218.0, "step": 88985 }, { "epoch": 0.9493988243201433, "grad_norm": 1.5513038277734728, "learning_rate": 5.314411726240793e-06, "loss": 0.4069, "num_tokens": 531612948.0, "step": 88990 }, { "epoch": 0.9494521673263419, "grad_norm": 1.4148024881601864, "learning_rate": 5.31375086271449e-06, "loss": 0.6493, "num_tokens": 531653565.0, "step": 88995 }, { "epoch": 0.9495055103325403, "grad_norm": 1.193729639520286, "learning_rate": 5.3130906895786866e-06, "loss": 0.4513, "num_tokens": 531679158.0, "step": 89000 }, { "epoch": 0.9495588533387388, "grad_norm": 1.0183795382418197, "learning_rate": 5.312431206853927e-06, "loss": 0.4062, "num_tokens": 531703054.0, "step": 89005 }, { "epoch": 0.9496121963449372, "grad_norm": 0.7319195085349507, "learning_rate": 5.311772414560735e-06, "loss": 0.5248, "num_tokens": 531741975.0, "step": 89010 }, { "epoch": 0.9496655393511356, "grad_norm": 0.8653482602144189, "learning_rate": 5.31111431271961e-06, "loss": 0.5532, "num_tokens": 531795584.0, "step": 89015 }, { "epoch": 0.9497188823573341, "grad_norm": 1.2828264859092322, "learning_rate": 5.310456901351029e-06, "loss": 0.5301, "num_tokens": 531812902.0, "step": 89020 }, { "epoch": 0.9497722253635326, "grad_norm": 1.200698967326649, "learning_rate": 5.309800180475451e-06, "loss": 0.3745, "num_tokens": 531842284.0, "step": 89025 }, { "epoch": 0.9498255683697311, "grad_norm": 1.487979686173171, "learning_rate": 5.309144150113313e-06, "loss": 0.4613, "num_tokens": 531882732.0, "step": 89030 }, { "epoch": 0.9498789113759295, "grad_norm": 0.9892678434964303, "learning_rate": 5.3084888102850265e-06, "loss": 0.4136, "num_tokens": 531912342.0, "step": 89035 }, { "epoch": 0.9499322543821279, "grad_norm": 1.2254022752563987, "learning_rate": 5.3078341610109834e-06, "loss": 0.5176, "num_tokens": 531933919.0, "step": 89040 }, { "epoch": 0.9499855973883264, "grad_norm": 1.2424179174097962, "learning_rate": 5.307180202311561e-06, "loss": 0.382, "num_tokens": 531947678.0, "step": 89045 }, { "epoch": 0.9500389403945249, "grad_norm": 0.8300880314550239, "learning_rate": 5.3065269342071025e-06, "loss": 0.4602, "num_tokens": 531987357.0, "step": 89050 }, { "epoch": 0.9500922834007234, "grad_norm": 0.7909231869106236, "learning_rate": 5.305874356717938e-06, "loss": 0.4787, "num_tokens": 532022658.0, "step": 89055 }, { "epoch": 0.9501456264069218, "grad_norm": 0.7197003720228605, "learning_rate": 5.305222469864381e-06, "loss": 0.4823, "num_tokens": 532051236.0, "step": 89060 }, { "epoch": 0.9501989694131202, "grad_norm": 0.9035363276319308, "learning_rate": 5.304571273666706e-06, "loss": 0.5257, "num_tokens": 532089122.0, "step": 89065 }, { "epoch": 0.9502523124193187, "grad_norm": 0.555931408410577, "learning_rate": 5.303920768145184e-06, "loss": 0.409, "num_tokens": 532126877.0, "step": 89070 }, { "epoch": 0.9503056554255171, "grad_norm": 0.8429045999658891, "learning_rate": 5.303270953320058e-06, "loss": 0.4219, "num_tokens": 532157306.0, "step": 89075 }, { "epoch": 0.9503589984317156, "grad_norm": 1.4551759236047315, "learning_rate": 5.302621829211543e-06, "loss": 0.4709, "num_tokens": 532174725.0, "step": 89080 }, { "epoch": 0.9504123414379141, "grad_norm": 0.9188945795868868, "learning_rate": 5.301973395839843e-06, "loss": 0.5065, "num_tokens": 532193950.0, "step": 89085 }, { "epoch": 0.9504656844441125, "grad_norm": 1.214684616597596, "learning_rate": 5.301325653225135e-06, "loss": 0.4409, "num_tokens": 532221558.0, "step": 89090 }, { "epoch": 0.950519027450311, "grad_norm": 0.7497062550772583, "learning_rate": 5.300678601387575e-06, "loss": 0.4729, "num_tokens": 532253118.0, "step": 89095 }, { "epoch": 0.9505723704565094, "grad_norm": 0.6622372458702492, "learning_rate": 5.3000322403473e-06, "loss": 0.4925, "num_tokens": 532297643.0, "step": 89100 }, { "epoch": 0.9506257134627079, "grad_norm": 0.9823626376644937, "learning_rate": 5.299386570124422e-06, "loss": 0.4917, "num_tokens": 532336496.0, "step": 89105 }, { "epoch": 0.9506790564689064, "grad_norm": 0.8320004744952388, "learning_rate": 5.2987415907390295e-06, "loss": 0.5686, "num_tokens": 532383930.0, "step": 89110 }, { "epoch": 0.9507323994751048, "grad_norm": 1.1575744155840402, "learning_rate": 5.298097302211196e-06, "loss": 0.4809, "num_tokens": 532408919.0, "step": 89115 }, { "epoch": 0.9507857424813033, "grad_norm": 0.7134179394031251, "learning_rate": 5.297453704560973e-06, "loss": 0.4256, "num_tokens": 532445330.0, "step": 89120 }, { "epoch": 0.9508390854875017, "grad_norm": 1.02092602422227, "learning_rate": 5.296810797808384e-06, "loss": 0.4481, "num_tokens": 532461259.0, "step": 89125 }, { "epoch": 0.9508924284937001, "grad_norm": 0.8399771711798959, "learning_rate": 5.2961685819734345e-06, "loss": 0.5267, "num_tokens": 532498900.0, "step": 89130 }, { "epoch": 0.9509457714998987, "grad_norm": 1.243058087237352, "learning_rate": 5.295527057076115e-06, "loss": 0.5644, "num_tokens": 532512383.0, "step": 89135 }, { "epoch": 0.9509991145060971, "grad_norm": 0.7981089283062784, "learning_rate": 5.294886223136382e-06, "loss": 0.6349, "num_tokens": 532551746.0, "step": 89140 }, { "epoch": 0.9510524575122956, "grad_norm": 0.7950506536165423, "learning_rate": 5.294246080174178e-06, "loss": 0.5108, "num_tokens": 532571589.0, "step": 89145 }, { "epoch": 0.951105800518494, "grad_norm": 0.9965273725673852, "learning_rate": 5.293606628209427e-06, "loss": 0.4338, "num_tokens": 532593527.0, "step": 89150 }, { "epoch": 0.9511591435246924, "grad_norm": 0.9114251758813183, "learning_rate": 5.292967867262022e-06, "loss": 0.4106, "num_tokens": 532616277.0, "step": 89155 }, { "epoch": 0.951212486530891, "grad_norm": 0.7501653077260134, "learning_rate": 5.292329797351843e-06, "loss": 0.561, "num_tokens": 532648245.0, "step": 89160 }, { "epoch": 0.9512658295370894, "grad_norm": 2.042316704097309, "learning_rate": 5.291692418498743e-06, "loss": 0.4213, "num_tokens": 532666523.0, "step": 89165 }, { "epoch": 0.9513191725432878, "grad_norm": 1.134670602921988, "learning_rate": 5.291055730722561e-06, "loss": 0.4683, "num_tokens": 532703550.0, "step": 89170 }, { "epoch": 0.9513725155494863, "grad_norm": 1.0368151528954797, "learning_rate": 5.290419734043107e-06, "loss": 0.471, "num_tokens": 532730685.0, "step": 89175 }, { "epoch": 0.9514258585556847, "grad_norm": 1.0847040929947387, "learning_rate": 5.28978442848017e-06, "loss": 0.4972, "num_tokens": 532752818.0, "step": 89180 }, { "epoch": 0.9514792015618833, "grad_norm": 1.1558837847866312, "learning_rate": 5.289149814053518e-06, "loss": 0.5535, "num_tokens": 532770931.0, "step": 89185 }, { "epoch": 0.9515325445680817, "grad_norm": 0.8944758667221057, "learning_rate": 5.288515890782902e-06, "loss": 0.479, "num_tokens": 532815062.0, "step": 89190 }, { "epoch": 0.9515858875742801, "grad_norm": 0.7185800012891469, "learning_rate": 5.287882658688049e-06, "loss": 0.4447, "num_tokens": 532845059.0, "step": 89195 }, { "epoch": 0.9516392305804786, "grad_norm": 1.2777641071234223, "learning_rate": 5.28725011778866e-06, "loss": 0.4675, "num_tokens": 532867290.0, "step": 89200 }, { "epoch": 0.951692573586677, "grad_norm": 0.6669007983185578, "learning_rate": 5.286618268104423e-06, "loss": 0.4316, "num_tokens": 532890619.0, "step": 89205 }, { "epoch": 0.9517459165928756, "grad_norm": 0.5309818678739753, "learning_rate": 5.285987109654999e-06, "loss": 0.3952, "num_tokens": 532932278.0, "step": 89210 }, { "epoch": 0.951799259599074, "grad_norm": 0.8418286854227611, "learning_rate": 5.285356642460029e-06, "loss": 0.4214, "num_tokens": 532971862.0, "step": 89215 }, { "epoch": 0.9518526026052724, "grad_norm": 0.7308546834076965, "learning_rate": 5.284726866539126e-06, "loss": 0.5144, "num_tokens": 533009433.0, "step": 89220 }, { "epoch": 0.9519059456114709, "grad_norm": 1.7785214028188379, "learning_rate": 5.284097781911896e-06, "loss": 0.4686, "num_tokens": 533035242.0, "step": 89225 }, { "epoch": 0.9519592886176693, "grad_norm": 0.7215362478500197, "learning_rate": 5.2834693885979034e-06, "loss": 0.4604, "num_tokens": 533077320.0, "step": 89230 }, { "epoch": 0.9520126316238678, "grad_norm": 1.1153356488359036, "learning_rate": 5.282841686616713e-06, "loss": 0.58, "num_tokens": 533107890.0, "step": 89235 }, { "epoch": 0.9520659746300663, "grad_norm": 0.843387332276322, "learning_rate": 5.2822146759878556e-06, "loss": 0.3899, "num_tokens": 533128082.0, "step": 89240 }, { "epoch": 0.9521193176362647, "grad_norm": 0.965369494142913, "learning_rate": 5.2815883567308404e-06, "loss": 0.4985, "num_tokens": 533151412.0, "step": 89245 }, { "epoch": 0.9521726606424632, "grad_norm": 0.8274553371634372, "learning_rate": 5.280962728865157e-06, "loss": 0.4583, "num_tokens": 533181980.0, "step": 89250 }, { "epoch": 0.9522260036486616, "grad_norm": 0.9788050089988027, "learning_rate": 5.280337792410275e-06, "loss": 0.3343, "num_tokens": 533210432.0, "step": 89255 }, { "epoch": 0.95227934665486, "grad_norm": 0.9836305399520628, "learning_rate": 5.279713547385638e-06, "loss": 0.5421, "num_tokens": 533234197.0, "step": 89260 }, { "epoch": 0.9523326896610586, "grad_norm": 0.8454114669165134, "learning_rate": 5.279089993810674e-06, "loss": 0.5244, "num_tokens": 533264102.0, "step": 89265 }, { "epoch": 0.952386032667257, "grad_norm": 0.9979437250967931, "learning_rate": 5.278467131704788e-06, "loss": 0.4295, "num_tokens": 533289200.0, "step": 89270 }, { "epoch": 0.9524393756734555, "grad_norm": 0.9996645752506627, "learning_rate": 5.27784496108736e-06, "loss": 0.3386, "num_tokens": 533312672.0, "step": 89275 }, { "epoch": 0.9524927186796539, "grad_norm": 0.6001539245756878, "learning_rate": 5.27722348197775e-06, "loss": 0.5332, "num_tokens": 533360398.0, "step": 89280 }, { "epoch": 0.9525460616858523, "grad_norm": 0.7504474860082537, "learning_rate": 5.276602694395301e-06, "loss": 0.5184, "num_tokens": 533392150.0, "step": 89285 }, { "epoch": 0.9525994046920508, "grad_norm": 1.1784079329467516, "learning_rate": 5.275982598359327e-06, "loss": 0.4706, "num_tokens": 533435821.0, "step": 89290 }, { "epoch": 0.9526527476982493, "grad_norm": 0.7443941718496568, "learning_rate": 5.275363193889125e-06, "loss": 0.3745, "num_tokens": 533478281.0, "step": 89295 }, { "epoch": 0.9527060907044478, "grad_norm": 1.0265343676197396, "learning_rate": 5.27474448100397e-06, "loss": 0.5138, "num_tokens": 533502257.0, "step": 89300 }, { "epoch": 0.9527594337106462, "grad_norm": 1.0767251298264329, "learning_rate": 5.2741264597231124e-06, "loss": 0.5174, "num_tokens": 533544238.0, "step": 89305 }, { "epoch": 0.9528127767168446, "grad_norm": 0.9527902403366699, "learning_rate": 5.273509130065788e-06, "loss": 0.4916, "num_tokens": 533564618.0, "step": 89310 }, { "epoch": 0.9528661197230431, "grad_norm": 1.0082007170900158, "learning_rate": 5.272892492051205e-06, "loss": 0.4884, "num_tokens": 533590043.0, "step": 89315 }, { "epoch": 0.9529194627292416, "grad_norm": 1.326171594987812, "learning_rate": 5.27227654569855e-06, "loss": 0.4014, "num_tokens": 533614764.0, "step": 89320 }, { "epoch": 0.9529728057354401, "grad_norm": 0.7948728960063414, "learning_rate": 5.271661291026995e-06, "loss": 0.4648, "num_tokens": 533660764.0, "step": 89325 }, { "epoch": 0.9530261487416385, "grad_norm": 2.9169504989928168, "learning_rate": 5.27104672805568e-06, "loss": 0.5267, "num_tokens": 533689648.0, "step": 89330 }, { "epoch": 0.9530794917478369, "grad_norm": 1.8819634364444908, "learning_rate": 5.270432856803731e-06, "loss": 0.4866, "num_tokens": 533711300.0, "step": 89335 }, { "epoch": 0.9531328347540354, "grad_norm": 1.0902425655709203, "learning_rate": 5.269819677290252e-06, "loss": 0.3535, "num_tokens": 533730834.0, "step": 89340 }, { "epoch": 0.9531861777602338, "grad_norm": 0.9429346477311985, "learning_rate": 5.269207189534324e-06, "loss": 0.4148, "num_tokens": 533756507.0, "step": 89345 }, { "epoch": 0.9532395207664323, "grad_norm": 1.0428942012343043, "learning_rate": 5.268595393555001e-06, "loss": 0.3804, "num_tokens": 533771754.0, "step": 89350 }, { "epoch": 0.9532928637726308, "grad_norm": 2.7475737502850768, "learning_rate": 5.267984289371325e-06, "loss": 0.4574, "num_tokens": 533801647.0, "step": 89355 }, { "epoch": 0.9533462067788292, "grad_norm": 0.9266933190006794, "learning_rate": 5.267373877002316e-06, "loss": 0.4528, "num_tokens": 533824967.0, "step": 89360 }, { "epoch": 0.9533995497850277, "grad_norm": 0.8306759348897309, "learning_rate": 5.2667641564669635e-06, "loss": 0.4544, "num_tokens": 533855236.0, "step": 89365 }, { "epoch": 0.9534528927912261, "grad_norm": 0.7103462385271673, "learning_rate": 5.266155127784241e-06, "loss": 0.3912, "num_tokens": 533903916.0, "step": 89370 }, { "epoch": 0.9535062357974246, "grad_norm": 1.020854110358297, "learning_rate": 5.265546790973102e-06, "loss": 0.5059, "num_tokens": 533937697.0, "step": 89375 }, { "epoch": 0.9535595788036231, "grad_norm": 1.1127120327851596, "learning_rate": 5.264939146052474e-06, "loss": 0.4638, "num_tokens": 533955752.0, "step": 89380 }, { "epoch": 0.9536129218098215, "grad_norm": 1.9897437668819034, "learning_rate": 5.264332193041269e-06, "loss": 0.5468, "num_tokens": 533984914.0, "step": 89385 }, { "epoch": 0.95366626481602, "grad_norm": 1.111616199902358, "learning_rate": 5.263725931958373e-06, "loss": 0.4816, "num_tokens": 534020574.0, "step": 89390 }, { "epoch": 0.9537196078222184, "grad_norm": 1.4347591957524497, "learning_rate": 5.263120362822654e-06, "loss": 0.2969, "num_tokens": 534040941.0, "step": 89395 }, { "epoch": 0.9537729508284168, "grad_norm": 1.1410304644935805, "learning_rate": 5.262515485652949e-06, "loss": 0.5506, "num_tokens": 534064694.0, "step": 89400 }, { "epoch": 0.9538262938346154, "grad_norm": 0.667482020863334, "learning_rate": 5.261911300468087e-06, "loss": 0.4856, "num_tokens": 534099501.0, "step": 89405 }, { "epoch": 0.9538796368408138, "grad_norm": 1.025515016334468, "learning_rate": 5.2613078072868655e-06, "loss": 0.5196, "num_tokens": 534120909.0, "step": 89410 }, { "epoch": 0.9539329798470123, "grad_norm": 0.9783960475383094, "learning_rate": 5.260705006128066e-06, "loss": 0.3846, "num_tokens": 534146332.0, "step": 89415 }, { "epoch": 0.9539863228532107, "grad_norm": 1.72625463042305, "learning_rate": 5.260102897010447e-06, "loss": 0.4481, "num_tokens": 534168723.0, "step": 89420 }, { "epoch": 0.9540396658594091, "grad_norm": 0.8656779993819299, "learning_rate": 5.2595014799527445e-06, "loss": 0.4766, "num_tokens": 534205551.0, "step": 89425 }, { "epoch": 0.9540930088656077, "grad_norm": 2.348912612578688, "learning_rate": 5.258900754973672e-06, "loss": 0.5322, "num_tokens": 534246264.0, "step": 89430 }, { "epoch": 0.9541463518718061, "grad_norm": 0.7856021090850491, "learning_rate": 5.258300722091923e-06, "loss": 0.4854, "num_tokens": 534284973.0, "step": 89435 }, { "epoch": 0.9541996948780045, "grad_norm": 0.8356016961913662, "learning_rate": 5.257701381326171e-06, "loss": 0.4476, "num_tokens": 534313767.0, "step": 89440 }, { "epoch": 0.954253037884203, "grad_norm": 1.341699343211695, "learning_rate": 5.257102732695061e-06, "loss": 0.5386, "num_tokens": 534329812.0, "step": 89445 }, { "epoch": 0.9543063808904014, "grad_norm": 1.0356591985779116, "learning_rate": 5.256504776217232e-06, "loss": 0.5186, "num_tokens": 534369848.0, "step": 89450 }, { "epoch": 0.9543597238966, "grad_norm": 0.7158126016559481, "learning_rate": 5.2559075119112785e-06, "loss": 0.3606, "num_tokens": 534396484.0, "step": 89455 }, { "epoch": 0.9544130669027984, "grad_norm": 1.1637755418932443, "learning_rate": 5.255310939795796e-06, "loss": 0.5813, "num_tokens": 534426641.0, "step": 89460 }, { "epoch": 0.9544664099089968, "grad_norm": 0.9938958552727278, "learning_rate": 5.254715059889346e-06, "loss": 0.459, "num_tokens": 534452409.0, "step": 89465 }, { "epoch": 0.9545197529151953, "grad_norm": 1.2238501735083638, "learning_rate": 5.2541198722104685e-06, "loss": 0.4158, "num_tokens": 534482518.0, "step": 89470 }, { "epoch": 0.9545730959213937, "grad_norm": 0.9839142029759823, "learning_rate": 5.253525376777687e-06, "loss": 0.4264, "num_tokens": 534516815.0, "step": 89475 }, { "epoch": 0.9546264389275922, "grad_norm": 0.7984434818245326, "learning_rate": 5.2529315736095006e-06, "loss": 0.5033, "num_tokens": 534547913.0, "step": 89480 }, { "epoch": 0.9546797819337907, "grad_norm": 0.8046612386506645, "learning_rate": 5.252338462724385e-06, "loss": 0.3583, "num_tokens": 534573977.0, "step": 89485 }, { "epoch": 0.9547331249399891, "grad_norm": 0.6098812215739323, "learning_rate": 5.251746044140799e-06, "loss": 0.4753, "num_tokens": 534621986.0, "step": 89490 }, { "epoch": 0.9547864679461876, "grad_norm": 1.0958092000670423, "learning_rate": 5.251154317877178e-06, "loss": 0.4362, "num_tokens": 534647466.0, "step": 89495 }, { "epoch": 0.954839810952386, "grad_norm": 0.8038582476042502, "learning_rate": 5.250563283951931e-06, "loss": 0.43, "num_tokens": 534675895.0, "step": 89500 }, { "epoch": 0.9548931539585845, "grad_norm": 1.2891488377906617, "learning_rate": 5.249972942383458e-06, "loss": 0.4616, "num_tokens": 534709804.0, "step": 89505 }, { "epoch": 0.954946496964783, "grad_norm": 0.9828894793908277, "learning_rate": 5.249383293190123e-06, "loss": 0.4792, "num_tokens": 534730339.0, "step": 89510 }, { "epoch": 0.9549998399709814, "grad_norm": 1.7701176194128656, "learning_rate": 5.248794336390273e-06, "loss": 0.4477, "num_tokens": 534761590.0, "step": 89515 }, { "epoch": 0.9550531829771799, "grad_norm": 0.7960184018078971, "learning_rate": 5.248206072002239e-06, "loss": 0.4987, "num_tokens": 534792678.0, "step": 89520 }, { "epoch": 0.9551065259833783, "grad_norm": 0.7643341662005895, "learning_rate": 5.247618500044328e-06, "loss": 0.4988, "num_tokens": 534822400.0, "step": 89525 }, { "epoch": 0.9551598689895767, "grad_norm": 0.9736765697709998, "learning_rate": 5.247031620534818e-06, "loss": 0.4127, "num_tokens": 534842191.0, "step": 89530 }, { "epoch": 0.9552132119957752, "grad_norm": 1.2336132496437566, "learning_rate": 5.2464454334919765e-06, "loss": 0.3825, "num_tokens": 534871257.0, "step": 89535 }, { "epoch": 0.9552665550019737, "grad_norm": 2.471492220846011, "learning_rate": 5.245859938934043e-06, "loss": 0.3612, "num_tokens": 534893207.0, "step": 89540 }, { "epoch": 0.9553198980081722, "grad_norm": 1.3702292571481418, "learning_rate": 5.24527513687924e-06, "loss": 0.4611, "num_tokens": 534918055.0, "step": 89545 }, { "epoch": 0.9553732410143706, "grad_norm": 1.1801828858372403, "learning_rate": 5.244691027345758e-06, "loss": 0.5012, "num_tokens": 534949869.0, "step": 89550 }, { "epoch": 0.955426584020569, "grad_norm": 1.084774724210415, "learning_rate": 5.244107610351779e-06, "loss": 0.6527, "num_tokens": 534981304.0, "step": 89555 }, { "epoch": 0.9554799270267675, "grad_norm": 1.2194009256012361, "learning_rate": 5.243524885915456e-06, "loss": 0.3842, "num_tokens": 535002575.0, "step": 89560 }, { "epoch": 0.955533270032966, "grad_norm": 1.5342166211242776, "learning_rate": 5.2429428540549225e-06, "loss": 0.4282, "num_tokens": 535025037.0, "step": 89565 }, { "epoch": 0.9555866130391645, "grad_norm": 0.7485141145525814, "learning_rate": 5.2423615147882894e-06, "loss": 0.4557, "num_tokens": 535045677.0, "step": 89570 }, { "epoch": 0.9556399560453629, "grad_norm": 1.1570720723126269, "learning_rate": 5.241780868133647e-06, "loss": 0.4067, "num_tokens": 535067248.0, "step": 89575 }, { "epoch": 0.9556932990515613, "grad_norm": 0.7980497968402819, "learning_rate": 5.241200914109068e-06, "loss": 0.4816, "num_tokens": 535112444.0, "step": 89580 }, { "epoch": 0.9557466420577598, "grad_norm": 1.470569902854885, "learning_rate": 5.2406216527325925e-06, "loss": 0.4543, "num_tokens": 535140434.0, "step": 89585 }, { "epoch": 0.9557999850639582, "grad_norm": 1.2648196441605668, "learning_rate": 5.240043084022249e-06, "loss": 0.4273, "num_tokens": 535166684.0, "step": 89590 }, { "epoch": 0.9558533280701568, "grad_norm": 1.0170488258791357, "learning_rate": 5.239465207996043e-06, "loss": 0.5083, "num_tokens": 535214864.0, "step": 89595 }, { "epoch": 0.9559066710763552, "grad_norm": 1.1569757361464867, "learning_rate": 5.238888024671953e-06, "loss": 0.419, "num_tokens": 535253217.0, "step": 89600 }, { "epoch": 0.9559600140825536, "grad_norm": 0.5988394016392024, "learning_rate": 5.238311534067944e-06, "loss": 0.4086, "num_tokens": 535276837.0, "step": 89605 }, { "epoch": 0.9560133570887521, "grad_norm": 0.6870978366830593, "learning_rate": 5.237735736201954e-06, "loss": 0.3927, "num_tokens": 535312693.0, "step": 89610 }, { "epoch": 0.9560667000949505, "grad_norm": 0.727818185737379, "learning_rate": 5.237160631091898e-06, "loss": 0.5862, "num_tokens": 535348750.0, "step": 89615 }, { "epoch": 0.956120043101149, "grad_norm": 0.5086614396797633, "learning_rate": 5.236586218755676e-06, "loss": 0.372, "num_tokens": 535396943.0, "step": 89620 }, { "epoch": 0.9561733861073475, "grad_norm": 1.101535796048582, "learning_rate": 5.2360124992111594e-06, "loss": 0.4804, "num_tokens": 535431133.0, "step": 89625 }, { "epoch": 0.9562267291135459, "grad_norm": 0.7287372513201468, "learning_rate": 5.235439472476202e-06, "loss": 0.487, "num_tokens": 535481998.0, "step": 89630 }, { "epoch": 0.9562800721197444, "grad_norm": 1.2537761206213047, "learning_rate": 5.234867138568635e-06, "loss": 0.4002, "num_tokens": 535510339.0, "step": 89635 }, { "epoch": 0.9563334151259428, "grad_norm": 0.641743403416829, "learning_rate": 5.234295497506269e-06, "loss": 0.4376, "num_tokens": 535543137.0, "step": 89640 }, { "epoch": 0.9563867581321412, "grad_norm": 1.155484609197164, "learning_rate": 5.23372454930689e-06, "loss": 0.4481, "num_tokens": 535562001.0, "step": 89645 }, { "epoch": 0.9564401011383398, "grad_norm": 1.3532436077217018, "learning_rate": 5.233154293988272e-06, "loss": 0.4671, "num_tokens": 535588147.0, "step": 89650 }, { "epoch": 0.9564934441445382, "grad_norm": 0.7058960058818038, "learning_rate": 5.232584731568152e-06, "loss": 0.4354, "num_tokens": 535623604.0, "step": 89655 }, { "epoch": 0.9565467871507367, "grad_norm": 0.9642192200456826, "learning_rate": 5.232015862064256e-06, "loss": 0.3627, "num_tokens": 535644535.0, "step": 89660 }, { "epoch": 0.9566001301569351, "grad_norm": 1.0128559397603458, "learning_rate": 5.231447685494288e-06, "loss": 0.4461, "num_tokens": 535670626.0, "step": 89665 }, { "epoch": 0.9566534731631335, "grad_norm": 0.631894619040866, "learning_rate": 5.230880201875927e-06, "loss": 0.4197, "num_tokens": 535698979.0, "step": 89670 }, { "epoch": 0.9567068161693321, "grad_norm": 0.8038858217364433, "learning_rate": 5.23031341122683e-06, "loss": 0.5506, "num_tokens": 535721931.0, "step": 89675 }, { "epoch": 0.9567601591755305, "grad_norm": 0.7844059531732891, "learning_rate": 5.229747313564637e-06, "loss": 0.4289, "num_tokens": 535753016.0, "step": 89680 }, { "epoch": 0.956813502181729, "grad_norm": 0.7036498012910669, "learning_rate": 5.229181908906965e-06, "loss": 0.5163, "num_tokens": 535782830.0, "step": 89685 }, { "epoch": 0.9568668451879274, "grad_norm": 1.2258019715148252, "learning_rate": 5.228617197271406e-06, "loss": 0.5085, "num_tokens": 535812601.0, "step": 89690 }, { "epoch": 0.9569201881941258, "grad_norm": 0.895688240293381, "learning_rate": 5.2280531786755335e-06, "loss": 0.4113, "num_tokens": 535839369.0, "step": 89695 }, { "epoch": 0.9569735312003244, "grad_norm": 0.7397724072299109, "learning_rate": 5.227489853136897e-06, "loss": 0.3406, "num_tokens": 535864974.0, "step": 89700 }, { "epoch": 0.9570268742065228, "grad_norm": 0.6929096864737622, "learning_rate": 5.226927220673027e-06, "loss": 0.4264, "num_tokens": 535900863.0, "step": 89705 }, { "epoch": 0.9570802172127212, "grad_norm": 0.9315676181185528, "learning_rate": 5.226365281301431e-06, "loss": 0.4496, "num_tokens": 535921197.0, "step": 89710 }, { "epoch": 0.9571335602189197, "grad_norm": 0.8162178329926455, "learning_rate": 5.225804035039598e-06, "loss": 0.4149, "num_tokens": 535943560.0, "step": 89715 }, { "epoch": 0.9571869032251181, "grad_norm": 0.608574513268746, "learning_rate": 5.225243481904991e-06, "loss": 0.4208, "num_tokens": 535971342.0, "step": 89720 }, { "epoch": 0.9572402462313166, "grad_norm": 1.3169069430991138, "learning_rate": 5.224683621915053e-06, "loss": 0.4869, "num_tokens": 535995970.0, "step": 89725 }, { "epoch": 0.9572935892375151, "grad_norm": 0.6956278604120733, "learning_rate": 5.224124455087205e-06, "loss": 0.3825, "num_tokens": 536026420.0, "step": 89730 }, { "epoch": 0.9573469322437135, "grad_norm": 0.6445597416198735, "learning_rate": 5.223565981438846e-06, "loss": 0.4038, "num_tokens": 536060444.0, "step": 89735 }, { "epoch": 0.957400275249912, "grad_norm": 0.7256767453100019, "learning_rate": 5.223008200987362e-06, "loss": 0.5199, "num_tokens": 536078628.0, "step": 89740 }, { "epoch": 0.9574536182561104, "grad_norm": 1.1931008122854487, "learning_rate": 5.222451113750099e-06, "loss": 0.4911, "num_tokens": 536107767.0, "step": 89745 }, { "epoch": 0.9575069612623089, "grad_norm": 0.8126559788974607, "learning_rate": 5.2218947197444004e-06, "loss": 0.5642, "num_tokens": 536139871.0, "step": 89750 }, { "epoch": 0.9575603042685074, "grad_norm": 1.907463015964113, "learning_rate": 5.221339018987578e-06, "loss": 0.4432, "num_tokens": 536178250.0, "step": 89755 }, { "epoch": 0.9576136472747058, "grad_norm": 1.6749126050854286, "learning_rate": 5.220784011496924e-06, "loss": 0.5451, "num_tokens": 536208655.0, "step": 89760 }, { "epoch": 0.9576669902809043, "grad_norm": 1.3611689978516617, "learning_rate": 5.2202296972897065e-06, "loss": 0.4241, "num_tokens": 536238815.0, "step": 89765 }, { "epoch": 0.9577203332871027, "grad_norm": 0.7271297228965135, "learning_rate": 5.2196760763831784e-06, "loss": 0.498, "num_tokens": 536265203.0, "step": 89770 }, { "epoch": 0.9577736762933012, "grad_norm": 0.8272414170834523, "learning_rate": 5.2191231487945654e-06, "loss": 0.4592, "num_tokens": 536293724.0, "step": 89775 }, { "epoch": 0.9578270192994996, "grad_norm": 0.9106734296918256, "learning_rate": 5.218570914541075e-06, "loss": 0.4565, "num_tokens": 536335705.0, "step": 89780 }, { "epoch": 0.9578803623056981, "grad_norm": 0.9964476074095945, "learning_rate": 5.21801937363989e-06, "loss": 0.4693, "num_tokens": 536361620.0, "step": 89785 }, { "epoch": 0.9579337053118966, "grad_norm": 0.9967465903008245, "learning_rate": 5.217468526108171e-06, "loss": 0.3405, "num_tokens": 536405114.0, "step": 89790 }, { "epoch": 0.957987048318095, "grad_norm": 0.6689937907924304, "learning_rate": 5.216918371963066e-06, "loss": 0.4456, "num_tokens": 536435138.0, "step": 89795 }, { "epoch": 0.9580403913242934, "grad_norm": 1.0723467603491, "learning_rate": 5.216368911221687e-06, "loss": 0.462, "num_tokens": 536463055.0, "step": 89800 }, { "epoch": 0.9580937343304919, "grad_norm": 1.06441056156326, "learning_rate": 5.215820143901137e-06, "loss": 0.4697, "num_tokens": 536490796.0, "step": 89805 }, { "epoch": 0.9581470773366904, "grad_norm": 1.2428601354615643, "learning_rate": 5.2152720700184894e-06, "loss": 0.4046, "num_tokens": 536518880.0, "step": 89810 }, { "epoch": 0.9582004203428889, "grad_norm": 0.753988154992149, "learning_rate": 5.214724689590805e-06, "loss": 0.45, "num_tokens": 536555639.0, "step": 89815 }, { "epoch": 0.9582537633490873, "grad_norm": 0.9208007615228733, "learning_rate": 5.2141780026351074e-06, "loss": 0.4347, "num_tokens": 536581229.0, "step": 89820 }, { "epoch": 0.9583071063552857, "grad_norm": 1.2056420720130814, "learning_rate": 5.213632009168417e-06, "loss": 0.4929, "num_tokens": 536616457.0, "step": 89825 }, { "epoch": 0.9583604493614842, "grad_norm": 1.089930111796313, "learning_rate": 5.213086709207723e-06, "loss": 0.5541, "num_tokens": 536651331.0, "step": 89830 }, { "epoch": 0.9584137923676826, "grad_norm": 0.8688723448489554, "learning_rate": 5.2125421027699895e-06, "loss": 0.4494, "num_tokens": 536689436.0, "step": 89835 }, { "epoch": 0.9584671353738812, "grad_norm": 0.8280549512785403, "learning_rate": 5.211998189872165e-06, "loss": 0.459, "num_tokens": 536721286.0, "step": 89840 }, { "epoch": 0.9585204783800796, "grad_norm": 1.5673087071671736, "learning_rate": 5.2114549705311785e-06, "loss": 0.4558, "num_tokens": 536759658.0, "step": 89845 }, { "epoch": 0.958573821386278, "grad_norm": 0.7708247234029613, "learning_rate": 5.21091244476393e-06, "loss": 0.4911, "num_tokens": 536798254.0, "step": 89850 }, { "epoch": 0.9586271643924765, "grad_norm": 0.6112941638873121, "learning_rate": 5.2103706125873045e-06, "loss": 0.3698, "num_tokens": 536825018.0, "step": 89855 }, { "epoch": 0.9586805073986749, "grad_norm": 1.4629575777640769, "learning_rate": 5.209829474018159e-06, "loss": 0.4247, "num_tokens": 536851379.0, "step": 89860 }, { "epoch": 0.9587338504048735, "grad_norm": 0.9281162805844291, "learning_rate": 5.209289029073336e-06, "loss": 0.5078, "num_tokens": 536884349.0, "step": 89865 }, { "epoch": 0.9587871934110719, "grad_norm": 0.7358610572114165, "learning_rate": 5.208749277769654e-06, "loss": 0.4968, "num_tokens": 536941274.0, "step": 89870 }, { "epoch": 0.9588405364172703, "grad_norm": 0.9156018202522616, "learning_rate": 5.2082102201239054e-06, "loss": 0.4289, "num_tokens": 536974503.0, "step": 89875 }, { "epoch": 0.9588938794234688, "grad_norm": 0.9403512986594974, "learning_rate": 5.2076718561528646e-06, "loss": 0.4038, "num_tokens": 536995054.0, "step": 89880 }, { "epoch": 0.9589472224296672, "grad_norm": 0.5946193580457003, "learning_rate": 5.207134185873286e-06, "loss": 0.4485, "num_tokens": 537030086.0, "step": 89885 }, { "epoch": 0.9590005654358656, "grad_norm": 0.9519358498137238, "learning_rate": 5.206597209301903e-06, "loss": 0.4241, "num_tokens": 537051666.0, "step": 89890 }, { "epoch": 0.9590539084420642, "grad_norm": 0.9565963458160118, "learning_rate": 5.206060926455419e-06, "loss": 0.3828, "num_tokens": 537079458.0, "step": 89895 }, { "epoch": 0.9591072514482626, "grad_norm": 0.9205985776599035, "learning_rate": 5.205525337350528e-06, "loss": 0.5207, "num_tokens": 537112707.0, "step": 89900 }, { "epoch": 0.9591605944544611, "grad_norm": 0.7202159043696135, "learning_rate": 5.204990442003897e-06, "loss": 0.436, "num_tokens": 537145727.0, "step": 89905 }, { "epoch": 0.9592139374606595, "grad_norm": 0.7064390345993259, "learning_rate": 5.204456240432167e-06, "loss": 0.362, "num_tokens": 537184084.0, "step": 89910 }, { "epoch": 0.9592672804668579, "grad_norm": 1.0137593478896592, "learning_rate": 5.2039227326519606e-06, "loss": 0.3769, "num_tokens": 537216457.0, "step": 89915 }, { "epoch": 0.9593206234730565, "grad_norm": 1.1138516631621869, "learning_rate": 5.203389918679883e-06, "loss": 0.5606, "num_tokens": 537247787.0, "step": 89920 }, { "epoch": 0.9593739664792549, "grad_norm": 1.035410534480446, "learning_rate": 5.20285779853251e-06, "loss": 0.4307, "num_tokens": 537282013.0, "step": 89925 }, { "epoch": 0.9594273094854534, "grad_norm": 1.2742024437344999, "learning_rate": 5.202326372226404e-06, "loss": 0.4436, "num_tokens": 537301005.0, "step": 89930 }, { "epoch": 0.9594806524916518, "grad_norm": 1.1457659983710204, "learning_rate": 5.201795639778102e-06, "loss": 0.4904, "num_tokens": 537321965.0, "step": 89935 }, { "epoch": 0.9595339954978502, "grad_norm": 1.429591567361492, "learning_rate": 5.201265601204116e-06, "loss": 0.5174, "num_tokens": 537353121.0, "step": 89940 }, { "epoch": 0.9595873385040488, "grad_norm": 0.6831173143513007, "learning_rate": 5.200736256520944e-06, "loss": 0.3561, "num_tokens": 537380915.0, "step": 89945 }, { "epoch": 0.9596406815102472, "grad_norm": 1.265332932324007, "learning_rate": 5.200207605745054e-06, "loss": 0.4175, "num_tokens": 537408685.0, "step": 89950 }, { "epoch": 0.9596940245164457, "grad_norm": 0.5780653227781147, "learning_rate": 5.199679648892898e-06, "loss": 0.457, "num_tokens": 537451176.0, "step": 89955 }, { "epoch": 0.9597473675226441, "grad_norm": 1.103873119209197, "learning_rate": 5.1991523859809045e-06, "loss": 0.4328, "num_tokens": 537478940.0, "step": 89960 }, { "epoch": 0.9598007105288425, "grad_norm": 1.7667929292388538, "learning_rate": 5.198625817025483e-06, "loss": 0.3694, "num_tokens": 537510804.0, "step": 89965 }, { "epoch": 0.959854053535041, "grad_norm": 1.4515739954934297, "learning_rate": 5.198099942043018e-06, "loss": 0.4828, "num_tokens": 537550914.0, "step": 89970 }, { "epoch": 0.9599073965412395, "grad_norm": 1.1552803925564372, "learning_rate": 5.197574761049871e-06, "loss": 0.5174, "num_tokens": 537577230.0, "step": 89975 }, { "epoch": 0.9599607395474379, "grad_norm": 1.051265629781936, "learning_rate": 5.19705027406239e-06, "loss": 0.4576, "num_tokens": 537600166.0, "step": 89980 }, { "epoch": 0.9600140825536364, "grad_norm": 0.5574374081215048, "learning_rate": 5.196526481096892e-06, "loss": 0.3917, "num_tokens": 537639712.0, "step": 89985 }, { "epoch": 0.9600674255598348, "grad_norm": 0.8411188599751142, "learning_rate": 5.196003382169675e-06, "loss": 0.4541, "num_tokens": 537671064.0, "step": 89990 }, { "epoch": 0.9601207685660333, "grad_norm": 0.5907176140687233, "learning_rate": 5.195480977297023e-06, "loss": 0.5335, "num_tokens": 537718641.0, "step": 89995 }, { "epoch": 0.9601741115722318, "grad_norm": 1.6431872886369496, "learning_rate": 5.194959266495185e-06, "loss": 0.5177, "num_tokens": 537749179.0, "step": 90000 }, { "epoch": 0.9602274545784302, "grad_norm": 1.5414859708998878, "learning_rate": 5.194438249780398e-06, "loss": 0.5296, "num_tokens": 537775481.0, "step": 90005 }, { "epoch": 0.9602807975846287, "grad_norm": 1.3002695837577782, "learning_rate": 5.193917927168879e-06, "loss": 0.5847, "num_tokens": 537806467.0, "step": 90010 }, { "epoch": 0.9603341405908271, "grad_norm": 0.6676357902687419, "learning_rate": 5.193398298676816e-06, "loss": 0.5153, "num_tokens": 537836364.0, "step": 90015 }, { "epoch": 0.9603874835970256, "grad_norm": 2.128703687834329, "learning_rate": 5.192879364320375e-06, "loss": 0.5905, "num_tokens": 537870200.0, "step": 90020 }, { "epoch": 0.960440826603224, "grad_norm": 0.9224641142317768, "learning_rate": 5.192361124115713e-06, "loss": 0.4301, "num_tokens": 537902637.0, "step": 90025 }, { "epoch": 0.9604941696094225, "grad_norm": 0.7803098797734643, "learning_rate": 5.191843578078948e-06, "loss": 0.4832, "num_tokens": 537942381.0, "step": 90030 }, { "epoch": 0.960547512615621, "grad_norm": 0.9392609070043245, "learning_rate": 5.1913267262261895e-06, "loss": 0.4847, "num_tokens": 537960699.0, "step": 90035 }, { "epoch": 0.9606008556218194, "grad_norm": 1.1921797179946183, "learning_rate": 5.190810568573521e-06, "loss": 0.384, "num_tokens": 537992046.0, "step": 90040 }, { "epoch": 0.9606541986280179, "grad_norm": 0.9561612822457611, "learning_rate": 5.190295105137001e-06, "loss": 0.344, "num_tokens": 538018234.0, "step": 90045 }, { "epoch": 0.9607075416342163, "grad_norm": 1.2069628472439615, "learning_rate": 5.189780335932673e-06, "loss": 0.4821, "num_tokens": 538057531.0, "step": 90050 }, { "epoch": 0.9607608846404148, "grad_norm": 1.4309437023636582, "learning_rate": 5.189266260976557e-06, "loss": 0.3842, "num_tokens": 538068905.0, "step": 90055 }, { "epoch": 0.9608142276466133, "grad_norm": 0.6407870165458105, "learning_rate": 5.188752880284644e-06, "loss": 0.4764, "num_tokens": 538108832.0, "step": 90060 }, { "epoch": 0.9608675706528117, "grad_norm": 1.1586362380507005, "learning_rate": 5.188240193872912e-06, "loss": 0.6069, "num_tokens": 538139217.0, "step": 90065 }, { "epoch": 0.9609209136590101, "grad_norm": 0.7219059684648959, "learning_rate": 5.187728201757318e-06, "loss": 0.4617, "num_tokens": 538175687.0, "step": 90070 }, { "epoch": 0.9609742566652086, "grad_norm": 0.8633471247949477, "learning_rate": 5.187216903953792e-06, "loss": 0.5554, "num_tokens": 538208852.0, "step": 90075 }, { "epoch": 0.961027599671407, "grad_norm": 0.8514867579094952, "learning_rate": 5.186706300478241e-06, "loss": 0.4198, "num_tokens": 538243070.0, "step": 90080 }, { "epoch": 0.9610809426776056, "grad_norm": 1.0634367765116972, "learning_rate": 5.18619639134656e-06, "loss": 0.3739, "num_tokens": 538265420.0, "step": 90085 }, { "epoch": 0.961134285683804, "grad_norm": 1.0883628561794387, "learning_rate": 5.185687176574614e-06, "loss": 0.392, "num_tokens": 538279651.0, "step": 90090 }, { "epoch": 0.9611876286900024, "grad_norm": 1.4140581852219314, "learning_rate": 5.1851786561782475e-06, "loss": 0.4387, "num_tokens": 538303651.0, "step": 90095 }, { "epoch": 0.9612409716962009, "grad_norm": 1.2129345958620117, "learning_rate": 5.184670830173285e-06, "loss": 0.4375, "num_tokens": 538343220.0, "step": 90100 }, { "epoch": 0.9612943147023993, "grad_norm": 0.7705164037182267, "learning_rate": 5.184163698575527e-06, "loss": 0.51, "num_tokens": 538386030.0, "step": 90105 }, { "epoch": 0.9613476577085979, "grad_norm": 0.6911813850905256, "learning_rate": 5.183657261400758e-06, "loss": 0.3639, "num_tokens": 538415450.0, "step": 90110 }, { "epoch": 0.9614010007147963, "grad_norm": 0.6748268223468794, "learning_rate": 5.183151518664737e-06, "loss": 0.4743, "num_tokens": 538436783.0, "step": 90115 }, { "epoch": 0.9614543437209947, "grad_norm": 0.7419388916148216, "learning_rate": 5.182646470383199e-06, "loss": 0.5097, "num_tokens": 538479010.0, "step": 90120 }, { "epoch": 0.9615076867271932, "grad_norm": 0.6369461030551028, "learning_rate": 5.182142116571864e-06, "loss": 0.4342, "num_tokens": 538501134.0, "step": 90125 }, { "epoch": 0.9615610297333916, "grad_norm": 1.0487400930278525, "learning_rate": 5.181638457246424e-06, "loss": 0.5041, "num_tokens": 538534583.0, "step": 90130 }, { "epoch": 0.9616143727395902, "grad_norm": 0.7685373096235212, "learning_rate": 5.1811354924225515e-06, "loss": 0.4342, "num_tokens": 538567666.0, "step": 90135 }, { "epoch": 0.9616677157457886, "grad_norm": 0.8404013351458528, "learning_rate": 5.180633222115895e-06, "loss": 0.3577, "num_tokens": 538598051.0, "step": 90140 }, { "epoch": 0.961721058751987, "grad_norm": 0.5859575932691578, "learning_rate": 5.180131646342093e-06, "loss": 0.4053, "num_tokens": 538620641.0, "step": 90145 }, { "epoch": 0.9617744017581855, "grad_norm": 1.1176251836928914, "learning_rate": 5.179630765116742e-06, "loss": 0.3666, "num_tokens": 538635645.0, "step": 90150 }, { "epoch": 0.9618277447643839, "grad_norm": 0.8367570274967412, "learning_rate": 5.179130578455438e-06, "loss": 0.3985, "num_tokens": 538659137.0, "step": 90155 }, { "epoch": 0.9618810877705823, "grad_norm": 0.9154480785227069, "learning_rate": 5.178631086373742e-06, "loss": 0.4324, "num_tokens": 538682596.0, "step": 90160 }, { "epoch": 0.9619344307767809, "grad_norm": 0.7739390269344477, "learning_rate": 5.1781322888871965e-06, "loss": 0.4271, "num_tokens": 538718432.0, "step": 90165 }, { "epoch": 0.9619877737829793, "grad_norm": 1.2890995080043863, "learning_rate": 5.177634186011322e-06, "loss": 0.4328, "num_tokens": 538746160.0, "step": 90170 }, { "epoch": 0.9620411167891778, "grad_norm": 0.9016425965213436, "learning_rate": 5.177136777761623e-06, "loss": 0.5222, "num_tokens": 538772887.0, "step": 90175 }, { "epoch": 0.9620944597953762, "grad_norm": 0.6736553382172104, "learning_rate": 5.176640064153573e-06, "loss": 0.4317, "num_tokens": 538808294.0, "step": 90180 }, { "epoch": 0.9621478028015746, "grad_norm": 1.384337013652856, "learning_rate": 5.17614404520263e-06, "loss": 0.4561, "num_tokens": 538830239.0, "step": 90185 }, { "epoch": 0.9622011458077732, "grad_norm": 0.7575124909340122, "learning_rate": 5.175648720924235e-06, "loss": 0.3927, "num_tokens": 538854571.0, "step": 90190 }, { "epoch": 0.9622544888139716, "grad_norm": 1.7731238859268919, "learning_rate": 5.175154091333791e-06, "loss": 0.4688, "num_tokens": 538876354.0, "step": 90195 }, { "epoch": 0.9623078318201701, "grad_norm": 1.0126526355137797, "learning_rate": 5.174660156446697e-06, "loss": 0.5399, "num_tokens": 538903600.0, "step": 90200 }, { "epoch": 0.9623611748263685, "grad_norm": 0.6745056396631015, "learning_rate": 5.17416691627832e-06, "loss": 0.4215, "num_tokens": 538936230.0, "step": 90205 }, { "epoch": 0.9624145178325669, "grad_norm": 1.1092379074553966, "learning_rate": 5.173674370844012e-06, "loss": 0.4457, "num_tokens": 538977052.0, "step": 90210 }, { "epoch": 0.9624678608387655, "grad_norm": 0.5793376992387134, "learning_rate": 5.1731825201590965e-06, "loss": 0.4339, "num_tokens": 539010170.0, "step": 90215 }, { "epoch": 0.9625212038449639, "grad_norm": 0.7851473260686355, "learning_rate": 5.172691364238882e-06, "loss": 0.3667, "num_tokens": 539026883.0, "step": 90220 }, { "epoch": 0.9625745468511624, "grad_norm": 0.8042719477112678, "learning_rate": 5.172200903098648e-06, "loss": 0.4577, "num_tokens": 539061082.0, "step": 90225 }, { "epoch": 0.9626278898573608, "grad_norm": 1.8264375253777627, "learning_rate": 5.17171113675366e-06, "loss": 0.5255, "num_tokens": 539080135.0, "step": 90230 }, { "epoch": 0.9626812328635592, "grad_norm": 1.7898156070816225, "learning_rate": 5.17122206521916e-06, "loss": 0.4632, "num_tokens": 539106789.0, "step": 90235 }, { "epoch": 0.9627345758697577, "grad_norm": 0.9926488956443389, "learning_rate": 5.170733688510364e-06, "loss": 0.4345, "num_tokens": 539137436.0, "step": 90240 }, { "epoch": 0.9627879188759562, "grad_norm": 0.9844962164261775, "learning_rate": 5.170246006642467e-06, "loss": 0.4306, "num_tokens": 539162387.0, "step": 90245 }, { "epoch": 0.9628412618821546, "grad_norm": 1.2878036290845067, "learning_rate": 5.169759019630651e-06, "loss": 0.3991, "num_tokens": 539193835.0, "step": 90250 }, { "epoch": 0.9628946048883531, "grad_norm": 0.8857996519082855, "learning_rate": 5.169272727490066e-06, "loss": 0.5239, "num_tokens": 539219167.0, "step": 90255 }, { "epoch": 0.9629479478945515, "grad_norm": 1.0295316749794294, "learning_rate": 5.168787130235843e-06, "loss": 0.5217, "num_tokens": 539254927.0, "step": 90260 }, { "epoch": 0.96300129090075, "grad_norm": 0.7332115053471889, "learning_rate": 5.168302227883097e-06, "loss": 0.4733, "num_tokens": 539283759.0, "step": 90265 }, { "epoch": 0.9630546339069485, "grad_norm": 0.607920735293781, "learning_rate": 5.167818020446915e-06, "loss": 0.4802, "num_tokens": 539307624.0, "step": 90270 }, { "epoch": 0.9631079769131469, "grad_norm": 1.2355330844812538, "learning_rate": 5.167334507942366e-06, "loss": 0.3557, "num_tokens": 539329865.0, "step": 90275 }, { "epoch": 0.9631613199193454, "grad_norm": 1.7629158244107856, "learning_rate": 5.1668516903844915e-06, "loss": 0.4687, "num_tokens": 539370134.0, "step": 90280 }, { "epoch": 0.9632146629255438, "grad_norm": 0.6389986146417911, "learning_rate": 5.1663695677883205e-06, "loss": 0.5624, "num_tokens": 539403950.0, "step": 90285 }, { "epoch": 0.9632680059317423, "grad_norm": 0.8650218421811467, "learning_rate": 5.165888140168853e-06, "loss": 0.5791, "num_tokens": 539440795.0, "step": 90290 }, { "epoch": 0.9633213489379407, "grad_norm": 1.054346771550222, "learning_rate": 5.165407407541073e-06, "loss": 0.4013, "num_tokens": 539469929.0, "step": 90295 }, { "epoch": 0.9633746919441392, "grad_norm": 1.2559815636748952, "learning_rate": 5.164927369919935e-06, "loss": 0.4482, "num_tokens": 539496999.0, "step": 90300 }, { "epoch": 0.9634280349503377, "grad_norm": 1.2138980846519731, "learning_rate": 5.164448027320382e-06, "loss": 0.4742, "num_tokens": 539531877.0, "step": 90305 }, { "epoch": 0.9634813779565361, "grad_norm": 0.7745262463476181, "learning_rate": 5.163969379757327e-06, "loss": 0.4489, "num_tokens": 539560789.0, "step": 90310 }, { "epoch": 0.9635347209627346, "grad_norm": 1.245242988149827, "learning_rate": 5.163491427245663e-06, "loss": 0.4028, "num_tokens": 539602217.0, "step": 90315 }, { "epoch": 0.963588063968933, "grad_norm": 2.3045143547723677, "learning_rate": 5.1630141698002695e-06, "loss": 0.437, "num_tokens": 539629434.0, "step": 90320 }, { "epoch": 0.9636414069751315, "grad_norm": 1.7457538257172653, "learning_rate": 5.1625376074359914e-06, "loss": 0.4242, "num_tokens": 539656174.0, "step": 90325 }, { "epoch": 0.96369474998133, "grad_norm": 1.0870522421561684, "learning_rate": 5.1620617401676615e-06, "loss": 0.4093, "num_tokens": 539676143.0, "step": 90330 }, { "epoch": 0.9637480929875284, "grad_norm": 0.9910775564557239, "learning_rate": 5.161586568010085e-06, "loss": 0.423, "num_tokens": 539695766.0, "step": 90335 }, { "epoch": 0.9638014359937268, "grad_norm": 0.8411503261579376, "learning_rate": 5.16111209097805e-06, "loss": 0.477, "num_tokens": 539734062.0, "step": 90340 }, { "epoch": 0.9638547789999253, "grad_norm": 0.95575250726402, "learning_rate": 5.160638309086324e-06, "loss": 0.4828, "num_tokens": 539770957.0, "step": 90345 }, { "epoch": 0.9639081220061237, "grad_norm": 0.7965373695888623, "learning_rate": 5.160165222349646e-06, "loss": 0.4797, "num_tokens": 539814611.0, "step": 90350 }, { "epoch": 0.9639614650123223, "grad_norm": 0.6525114160135088, "learning_rate": 5.15969283078274e-06, "loss": 0.3931, "num_tokens": 539843081.0, "step": 90355 }, { "epoch": 0.9640148080185207, "grad_norm": 1.008970459075733, "learning_rate": 5.159221134400301e-06, "loss": 0.4999, "num_tokens": 539891463.0, "step": 90360 }, { "epoch": 0.9640681510247191, "grad_norm": 0.641902174835456, "learning_rate": 5.158750133217013e-06, "loss": 0.5309, "num_tokens": 539935294.0, "step": 90365 }, { "epoch": 0.9641214940309176, "grad_norm": 0.9351513584351885, "learning_rate": 5.158279827247535e-06, "loss": 0.378, "num_tokens": 539959579.0, "step": 90370 }, { "epoch": 0.964174837037116, "grad_norm": 0.6204167946361226, "learning_rate": 5.157810216506491e-06, "loss": 0.4149, "num_tokens": 539987507.0, "step": 90375 }, { "epoch": 0.9642281800433146, "grad_norm": 0.8940296078004303, "learning_rate": 5.1573413010085054e-06, "loss": 0.432, "num_tokens": 540002602.0, "step": 90380 }, { "epoch": 0.964281523049513, "grad_norm": 0.9195973189170504, "learning_rate": 5.156873080768165e-06, "loss": 0.4579, "num_tokens": 540030935.0, "step": 90385 }, { "epoch": 0.9643348660557114, "grad_norm": 2.1520297534643156, "learning_rate": 5.156405555800038e-06, "loss": 0.4594, "num_tokens": 540055255.0, "step": 90390 }, { "epoch": 0.9643882090619099, "grad_norm": 0.8867223010029988, "learning_rate": 5.1559387261186745e-06, "loss": 0.371, "num_tokens": 540075215.0, "step": 90395 }, { "epoch": 0.9644415520681083, "grad_norm": 1.4400801533807508, "learning_rate": 5.1554725917386045e-06, "loss": 0.5526, "num_tokens": 540099303.0, "step": 90400 }, { "epoch": 0.9644948950743069, "grad_norm": 0.8823683128097896, "learning_rate": 5.155007152674329e-06, "loss": 0.5097, "num_tokens": 540125409.0, "step": 90405 }, { "epoch": 0.9645482380805053, "grad_norm": 0.9150459096255734, "learning_rate": 5.154542408940333e-06, "loss": 0.4048, "num_tokens": 540148633.0, "step": 90410 }, { "epoch": 0.9646015810867037, "grad_norm": 0.7590546125890875, "learning_rate": 5.15407836055108e-06, "loss": 0.4891, "num_tokens": 540190746.0, "step": 90415 }, { "epoch": 0.9646549240929022, "grad_norm": 0.9730189075899406, "learning_rate": 5.153615007521008e-06, "loss": 0.4525, "num_tokens": 540220211.0, "step": 90420 }, { "epoch": 0.9647082670991006, "grad_norm": 0.6546263777707664, "learning_rate": 5.153152349864535e-06, "loss": 0.4708, "num_tokens": 540241394.0, "step": 90425 }, { "epoch": 0.964761610105299, "grad_norm": 1.0600774450377721, "learning_rate": 5.152690387596059e-06, "loss": 0.4223, "num_tokens": 540267733.0, "step": 90430 }, { "epoch": 0.9648149531114976, "grad_norm": 1.4487000556379903, "learning_rate": 5.152229120729956e-06, "loss": 0.3527, "num_tokens": 540287285.0, "step": 90435 }, { "epoch": 0.964868296117696, "grad_norm": 1.1397141477350308, "learning_rate": 5.151768549280579e-06, "loss": 0.5628, "num_tokens": 540305482.0, "step": 90440 }, { "epoch": 0.9649216391238945, "grad_norm": 1.9764584062262134, "learning_rate": 5.1513086732622615e-06, "loss": 0.4684, "num_tokens": 540319748.0, "step": 90445 }, { "epoch": 0.9649749821300929, "grad_norm": 1.0523980292965556, "learning_rate": 5.150849492689311e-06, "loss": 0.4791, "num_tokens": 540338364.0, "step": 90450 }, { "epoch": 0.9650283251362913, "grad_norm": 1.2382816007870325, "learning_rate": 5.150391007576019e-06, "loss": 0.3619, "num_tokens": 540367381.0, "step": 90455 }, { "epoch": 0.9650816681424899, "grad_norm": 3.8742962820977427, "learning_rate": 5.14993321793665e-06, "loss": 0.5399, "num_tokens": 540387979.0, "step": 90460 }, { "epoch": 0.9651350111486883, "grad_norm": 0.9815383380323869, "learning_rate": 5.1494761237854506e-06, "loss": 0.3256, "num_tokens": 540410905.0, "step": 90465 }, { "epoch": 0.9651883541548868, "grad_norm": 1.149460202838426, "learning_rate": 5.149019725136646e-06, "loss": 0.4835, "num_tokens": 540435597.0, "step": 90470 }, { "epoch": 0.9652416971610852, "grad_norm": 0.8358340145713872, "learning_rate": 5.148564022004437e-06, "loss": 0.4881, "num_tokens": 540470250.0, "step": 90475 }, { "epoch": 0.9652950401672836, "grad_norm": 0.7831604980732197, "learning_rate": 5.148109014403005e-06, "loss": 0.5207, "num_tokens": 540499463.0, "step": 90480 }, { "epoch": 0.9653483831734821, "grad_norm": 2.1919615701354176, "learning_rate": 5.1476547023465086e-06, "loss": 0.4836, "num_tokens": 540518722.0, "step": 90485 }, { "epoch": 0.9654017261796806, "grad_norm": 1.0745606552408185, "learning_rate": 5.147201085849084e-06, "loss": 0.4953, "num_tokens": 540542781.0, "step": 90490 }, { "epoch": 0.9654550691858791, "grad_norm": 0.7687168706425295, "learning_rate": 5.146748164924849e-06, "loss": 0.4342, "num_tokens": 540586452.0, "step": 90495 }, { "epoch": 0.9655084121920775, "grad_norm": 0.5882390106656963, "learning_rate": 5.146295939587893e-06, "loss": 0.5707, "num_tokens": 540612172.0, "step": 90500 }, { "epoch": 0.9655617551982759, "grad_norm": 1.012515249858728, "learning_rate": 5.145844409852295e-06, "loss": 0.4544, "num_tokens": 540642016.0, "step": 90505 }, { "epoch": 0.9656150982044744, "grad_norm": 1.0405125920605576, "learning_rate": 5.145393575732102e-06, "loss": 0.528, "num_tokens": 540671150.0, "step": 90510 }, { "epoch": 0.9656684412106729, "grad_norm": 1.2678249187372397, "learning_rate": 5.14494343724134e-06, "loss": 0.4485, "num_tokens": 540700107.0, "step": 90515 }, { "epoch": 0.9657217842168713, "grad_norm": 1.3897882073298355, "learning_rate": 5.144493994394023e-06, "loss": 0.4768, "num_tokens": 540737642.0, "step": 90520 }, { "epoch": 0.9657751272230698, "grad_norm": 0.7083258490747867, "learning_rate": 5.144045247204131e-06, "loss": 0.4343, "num_tokens": 540756636.0, "step": 90525 }, { "epoch": 0.9658284702292682, "grad_norm": 0.9128799258847624, "learning_rate": 5.143597195685634e-06, "loss": 0.5934, "num_tokens": 540790079.0, "step": 90530 }, { "epoch": 0.9658818132354667, "grad_norm": 0.9024752537516602, "learning_rate": 5.143149839852467e-06, "loss": 0.4459, "num_tokens": 540823152.0, "step": 90535 }, { "epoch": 0.9659351562416651, "grad_norm": 1.5123592380081854, "learning_rate": 5.142703179718557e-06, "loss": 0.4469, "num_tokens": 540850379.0, "step": 90540 }, { "epoch": 0.9659884992478636, "grad_norm": 1.2648319663174878, "learning_rate": 5.1422572152978e-06, "loss": 0.5302, "num_tokens": 540878318.0, "step": 90545 }, { "epoch": 0.9660418422540621, "grad_norm": 0.7745414617402242, "learning_rate": 5.141811946604074e-06, "loss": 0.4255, "num_tokens": 540906085.0, "step": 90550 }, { "epoch": 0.9660951852602605, "grad_norm": 0.9855862116755163, "learning_rate": 5.141367373651235e-06, "loss": 0.4169, "num_tokens": 540931389.0, "step": 90555 }, { "epoch": 0.966148528266459, "grad_norm": 1.7503110961471402, "learning_rate": 5.140923496453118e-06, "loss": 0.4493, "num_tokens": 540954808.0, "step": 90560 }, { "epoch": 0.9662018712726574, "grad_norm": 0.7688852060304228, "learning_rate": 5.140480315023536e-06, "loss": 0.5208, "num_tokens": 540994024.0, "step": 90565 }, { "epoch": 0.9662552142788559, "grad_norm": 1.0280936904200675, "learning_rate": 5.140037829376278e-06, "loss": 0.3999, "num_tokens": 541030213.0, "step": 90570 }, { "epoch": 0.9663085572850544, "grad_norm": 0.6869133900867926, "learning_rate": 5.1395960395251134e-06, "loss": 0.4468, "num_tokens": 541058378.0, "step": 90575 }, { "epoch": 0.9663619002912528, "grad_norm": 1.1514602943136476, "learning_rate": 5.13915494548379e-06, "loss": 0.5637, "num_tokens": 541084194.0, "step": 90580 }, { "epoch": 0.9664152432974513, "grad_norm": 1.2327532274739639, "learning_rate": 5.138714547266037e-06, "loss": 0.4084, "num_tokens": 541104989.0, "step": 90585 }, { "epoch": 0.9664685863036497, "grad_norm": 1.2673905635220704, "learning_rate": 5.138274844885553e-06, "loss": 0.3624, "num_tokens": 541131547.0, "step": 90590 }, { "epoch": 0.9665219293098481, "grad_norm": 0.7466194204407897, "learning_rate": 5.137835838356024e-06, "loss": 0.5239, "num_tokens": 541158119.0, "step": 90595 }, { "epoch": 0.9665752723160467, "grad_norm": 0.9938367444324122, "learning_rate": 5.137397527691111e-06, "loss": 0.6003, "num_tokens": 541187661.0, "step": 90600 }, { "epoch": 0.9666286153222451, "grad_norm": 0.8491831753107852, "learning_rate": 5.136959912904453e-06, "loss": 0.4477, "num_tokens": 541220645.0, "step": 90605 }, { "epoch": 0.9666819583284435, "grad_norm": 0.8474166354249676, "learning_rate": 5.136522994009666e-06, "loss": 0.582, "num_tokens": 541254224.0, "step": 90610 }, { "epoch": 0.966735301334642, "grad_norm": 0.6692675225292977, "learning_rate": 5.136086771020351e-06, "loss": 0.5435, "num_tokens": 541286423.0, "step": 90615 }, { "epoch": 0.9667886443408404, "grad_norm": 0.8030921379356202, "learning_rate": 5.1356512439500754e-06, "loss": 0.4247, "num_tokens": 541319152.0, "step": 90620 }, { "epoch": 0.966841987347039, "grad_norm": 1.1550027905815474, "learning_rate": 5.135216412812396e-06, "loss": 0.4939, "num_tokens": 541334248.0, "step": 90625 }, { "epoch": 0.9668953303532374, "grad_norm": 0.8876169230478262, "learning_rate": 5.134782277620845e-06, "loss": 0.4426, "num_tokens": 541367631.0, "step": 90630 }, { "epoch": 0.9669486733594358, "grad_norm": 1.0011985709833569, "learning_rate": 5.134348838388929e-06, "loss": 0.5154, "num_tokens": 541391830.0, "step": 90635 }, { "epoch": 0.9670020163656343, "grad_norm": 0.8806470472420993, "learning_rate": 5.133916095130137e-06, "loss": 0.5311, "num_tokens": 541430687.0, "step": 90640 }, { "epoch": 0.9670553593718327, "grad_norm": 1.7998130994624009, "learning_rate": 5.133484047857936e-06, "loss": 0.3769, "num_tokens": 541457555.0, "step": 90645 }, { "epoch": 0.9671087023780313, "grad_norm": 0.9630541997819838, "learning_rate": 5.133052696585768e-06, "loss": 0.4331, "num_tokens": 541485974.0, "step": 90650 }, { "epoch": 0.9671620453842297, "grad_norm": 0.8948477098518398, "learning_rate": 5.132622041327056e-06, "loss": 0.3521, "num_tokens": 541512724.0, "step": 90655 }, { "epoch": 0.9672153883904281, "grad_norm": 0.7639029420177171, "learning_rate": 5.132192082095203e-06, "loss": 0.399, "num_tokens": 541534439.0, "step": 90660 }, { "epoch": 0.9672687313966266, "grad_norm": 0.8438971215787884, "learning_rate": 5.131762818903588e-06, "loss": 0.4014, "num_tokens": 541566881.0, "step": 90665 }, { "epoch": 0.967322074402825, "grad_norm": 0.8874706903963755, "learning_rate": 5.1313342517655706e-06, "loss": 0.4084, "num_tokens": 541586036.0, "step": 90670 }, { "epoch": 0.9673754174090236, "grad_norm": 0.876203239381044, "learning_rate": 5.130906380694482e-06, "loss": 0.3813, "num_tokens": 541610977.0, "step": 90675 }, { "epoch": 0.967428760415222, "grad_norm": 1.4700899488278807, "learning_rate": 5.130479205703639e-06, "loss": 0.6326, "num_tokens": 541651208.0, "step": 90680 }, { "epoch": 0.9674821034214204, "grad_norm": 1.3797258687604352, "learning_rate": 5.1300527268063365e-06, "loss": 0.4512, "num_tokens": 541677850.0, "step": 90685 }, { "epoch": 0.9675354464276189, "grad_norm": 1.0792208047801233, "learning_rate": 5.129626944015841e-06, "loss": 0.4651, "num_tokens": 541704028.0, "step": 90690 }, { "epoch": 0.9675887894338173, "grad_norm": 0.713099107826506, "learning_rate": 5.1292018573454076e-06, "loss": 0.4038, "num_tokens": 541735532.0, "step": 90695 }, { "epoch": 0.9676421324400157, "grad_norm": 0.7167200045310735, "learning_rate": 5.12877746680826e-06, "loss": 0.3224, "num_tokens": 541763495.0, "step": 90700 }, { "epoch": 0.9676954754462143, "grad_norm": 0.9166238057583521, "learning_rate": 5.128353772417608e-06, "loss": 0.4428, "num_tokens": 541793438.0, "step": 90705 }, { "epoch": 0.9677488184524127, "grad_norm": 0.8320289587480286, "learning_rate": 5.127930774186633e-06, "loss": 0.3292, "num_tokens": 541827707.0, "step": 90710 }, { "epoch": 0.9678021614586112, "grad_norm": 1.1806198117176947, "learning_rate": 5.127508472128498e-06, "loss": 0.5561, "num_tokens": 541859148.0, "step": 90715 }, { "epoch": 0.9678555044648096, "grad_norm": 0.8900643541690807, "learning_rate": 5.127086866256346e-06, "loss": 0.5446, "num_tokens": 541890275.0, "step": 90720 }, { "epoch": 0.967908847471008, "grad_norm": 0.9065073620518247, "learning_rate": 5.126665956583296e-06, "loss": 0.4675, "num_tokens": 541908576.0, "step": 90725 }, { "epoch": 0.9679621904772066, "grad_norm": 0.819635496653045, "learning_rate": 5.1262457431224434e-06, "loss": 0.3959, "num_tokens": 541935127.0, "step": 90730 }, { "epoch": 0.968015533483405, "grad_norm": 1.0669716189370477, "learning_rate": 5.125826225886865e-06, "loss": 0.4431, "num_tokens": 541952323.0, "step": 90735 }, { "epoch": 0.9680688764896035, "grad_norm": 0.7288405069512848, "learning_rate": 5.1254074048896195e-06, "loss": 0.37, "num_tokens": 541995301.0, "step": 90740 }, { "epoch": 0.9681222194958019, "grad_norm": 0.9778009084142399, "learning_rate": 5.124989280143737e-06, "loss": 0.434, "num_tokens": 542009814.0, "step": 90745 }, { "epoch": 0.9681755625020003, "grad_norm": 0.6968313320128968, "learning_rate": 5.124571851662227e-06, "loss": 0.5328, "num_tokens": 542050280.0, "step": 90750 }, { "epoch": 0.9682289055081988, "grad_norm": 0.5505011471049723, "learning_rate": 5.124155119458079e-06, "loss": 0.3776, "num_tokens": 542076778.0, "step": 90755 }, { "epoch": 0.9682822485143973, "grad_norm": 0.7219689135601233, "learning_rate": 5.123739083544265e-06, "loss": 0.5019, "num_tokens": 542105081.0, "step": 90760 }, { "epoch": 0.9683355915205958, "grad_norm": 1.1971967200449587, "learning_rate": 5.123323743933728e-06, "loss": 0.5432, "num_tokens": 542129776.0, "step": 90765 }, { "epoch": 0.9683889345267942, "grad_norm": 1.0056771176580446, "learning_rate": 5.122909100639393e-06, "loss": 0.4419, "num_tokens": 542161262.0, "step": 90770 }, { "epoch": 0.9684422775329926, "grad_norm": 0.8057397473224214, "learning_rate": 5.122495153674163e-06, "loss": 0.4188, "num_tokens": 542198567.0, "step": 90775 }, { "epoch": 0.9684956205391911, "grad_norm": 1.3575453280020369, "learning_rate": 5.12208190305092e-06, "loss": 0.4025, "num_tokens": 542232410.0, "step": 90780 }, { "epoch": 0.9685489635453896, "grad_norm": 0.8935555119321262, "learning_rate": 5.121669348782522e-06, "loss": 0.4199, "num_tokens": 542258648.0, "step": 90785 }, { "epoch": 0.968602306551588, "grad_norm": 1.2177378813249533, "learning_rate": 5.1212574908818055e-06, "loss": 0.5, "num_tokens": 542286242.0, "step": 90790 }, { "epoch": 0.9686556495577865, "grad_norm": 0.9435642347939587, "learning_rate": 5.120846329361592e-06, "loss": 0.4148, "num_tokens": 542308023.0, "step": 90795 }, { "epoch": 0.9687089925639849, "grad_norm": 1.5044392447910035, "learning_rate": 5.120435864234669e-06, "loss": 0.4614, "num_tokens": 542332623.0, "step": 90800 }, { "epoch": 0.9687623355701834, "grad_norm": 0.8895108540755858, "learning_rate": 5.120026095513815e-06, "loss": 0.3737, "num_tokens": 542351014.0, "step": 90805 }, { "epoch": 0.9688156785763818, "grad_norm": 2.0524916546154452, "learning_rate": 5.11961702321178e-06, "loss": 0.4504, "num_tokens": 542368016.0, "step": 90810 }, { "epoch": 0.9688690215825803, "grad_norm": 0.8902888097683224, "learning_rate": 5.11920864734129e-06, "loss": 0.4842, "num_tokens": 542400612.0, "step": 90815 }, { "epoch": 0.9689223645887788, "grad_norm": 2.730841949384433, "learning_rate": 5.118800967915058e-06, "loss": 0.5097, "num_tokens": 542442362.0, "step": 90820 }, { "epoch": 0.9689757075949772, "grad_norm": 0.8691751810346801, "learning_rate": 5.1183939849457675e-06, "loss": 0.3569, "num_tokens": 542465229.0, "step": 90825 }, { "epoch": 0.9690290506011757, "grad_norm": 2.0164376525947647, "learning_rate": 5.1179876984460814e-06, "loss": 0.4521, "num_tokens": 542481051.0, "step": 90830 }, { "epoch": 0.9690823936073741, "grad_norm": 0.7891689239988441, "learning_rate": 5.117582108428644e-06, "loss": 0.4751, "num_tokens": 542515726.0, "step": 90835 }, { "epoch": 0.9691357366135726, "grad_norm": 0.6202867027283501, "learning_rate": 5.117177214906077e-06, "loss": 0.4174, "num_tokens": 542546645.0, "step": 90840 }, { "epoch": 0.9691890796197711, "grad_norm": 1.1189804998264812, "learning_rate": 5.116773017890982e-06, "loss": 0.4798, "num_tokens": 542597375.0, "step": 90845 }, { "epoch": 0.9692424226259695, "grad_norm": 1.0521098189861091, "learning_rate": 5.11636951739593e-06, "loss": 0.3664, "num_tokens": 542636542.0, "step": 90850 }, { "epoch": 0.969295765632168, "grad_norm": 0.927953244673462, "learning_rate": 5.115966713433483e-06, "loss": 0.4467, "num_tokens": 542671211.0, "step": 90855 }, { "epoch": 0.9693491086383664, "grad_norm": 1.124160417141864, "learning_rate": 5.1155646060161744e-06, "loss": 0.5527, "num_tokens": 542697653.0, "step": 90860 }, { "epoch": 0.9694024516445648, "grad_norm": 1.2464607952858346, "learning_rate": 5.115163195156518e-06, "loss": 0.5791, "num_tokens": 542730922.0, "step": 90865 }, { "epoch": 0.9694557946507634, "grad_norm": 1.0438993577771931, "learning_rate": 5.114762480867e-06, "loss": 0.457, "num_tokens": 542761621.0, "step": 90870 }, { "epoch": 0.9695091376569618, "grad_norm": 1.1991624972473653, "learning_rate": 5.114362463160094e-06, "loss": 0.3402, "num_tokens": 542778872.0, "step": 90875 }, { "epoch": 0.9695624806631602, "grad_norm": 0.8190304601733539, "learning_rate": 5.113963142048248e-06, "loss": 0.5864, "num_tokens": 542824098.0, "step": 90880 }, { "epoch": 0.9696158236693587, "grad_norm": 1.331840457671486, "learning_rate": 5.1135645175438845e-06, "loss": 0.4391, "num_tokens": 542848927.0, "step": 90885 }, { "epoch": 0.9696691666755571, "grad_norm": 0.7648444051871853, "learning_rate": 5.113166589659411e-06, "loss": 0.5375, "num_tokens": 542892688.0, "step": 90890 }, { "epoch": 0.9697225096817557, "grad_norm": 1.6618776514829043, "learning_rate": 5.112769358407212e-06, "loss": 0.4054, "num_tokens": 542907800.0, "step": 90895 }, { "epoch": 0.9697758526879541, "grad_norm": 1.0486710340130019, "learning_rate": 5.1123728237996454e-06, "loss": 0.3478, "num_tokens": 542936366.0, "step": 90900 }, { "epoch": 0.9698291956941525, "grad_norm": 0.9085253376336574, "learning_rate": 5.111976985849047e-06, "loss": 0.4746, "num_tokens": 542960360.0, "step": 90905 }, { "epoch": 0.969882538700351, "grad_norm": 0.7371391605176757, "learning_rate": 5.111581844567739e-06, "loss": 0.4191, "num_tokens": 542987412.0, "step": 90910 }, { "epoch": 0.9699358817065494, "grad_norm": 0.9695213606903487, "learning_rate": 5.1111873999680214e-06, "loss": 0.5032, "num_tokens": 543031134.0, "step": 90915 }, { "epoch": 0.969989224712748, "grad_norm": 0.7976759452953525, "learning_rate": 5.110793652062159e-06, "loss": 0.4635, "num_tokens": 543072957.0, "step": 90920 }, { "epoch": 0.9700425677189464, "grad_norm": 0.8539766587267703, "learning_rate": 5.110400600862414e-06, "loss": 0.4075, "num_tokens": 543109382.0, "step": 90925 }, { "epoch": 0.9700959107251448, "grad_norm": 0.8757581862683324, "learning_rate": 5.11000824638101e-06, "loss": 0.4049, "num_tokens": 543136124.0, "step": 90930 }, { "epoch": 0.9701492537313433, "grad_norm": 0.9773775286585819, "learning_rate": 5.109616588630159e-06, "loss": 0.4084, "num_tokens": 543166336.0, "step": 90935 }, { "epoch": 0.9702025967375417, "grad_norm": 0.8700118538497641, "learning_rate": 5.109225627622048e-06, "loss": 0.3907, "num_tokens": 543193431.0, "step": 90940 }, { "epoch": 0.9702559397437402, "grad_norm": 1.0170705454541806, "learning_rate": 5.108835363368847e-06, "loss": 0.531, "num_tokens": 543224265.0, "step": 90945 }, { "epoch": 0.9703092827499387, "grad_norm": 0.9895942265548815, "learning_rate": 5.1084457958826925e-06, "loss": 0.4708, "num_tokens": 543268031.0, "step": 90950 }, { "epoch": 0.9703626257561371, "grad_norm": 0.8562093593682726, "learning_rate": 5.108056925175712e-06, "loss": 0.4115, "num_tokens": 543292667.0, "step": 90955 }, { "epoch": 0.9704159687623356, "grad_norm": 1.2066634750462755, "learning_rate": 5.107668751260009e-06, "loss": 0.503, "num_tokens": 543324871.0, "step": 90960 }, { "epoch": 0.970469311768534, "grad_norm": 0.6817328224865048, "learning_rate": 5.1072812741476555e-06, "loss": 0.4268, "num_tokens": 543352038.0, "step": 90965 }, { "epoch": 0.9705226547747324, "grad_norm": 1.3269322833962658, "learning_rate": 5.106894493850715e-06, "loss": 0.6197, "num_tokens": 543388801.0, "step": 90970 }, { "epoch": 0.970575997780931, "grad_norm": 0.8432583078809014, "learning_rate": 5.10650841038122e-06, "loss": 0.4502, "num_tokens": 543403990.0, "step": 90975 }, { "epoch": 0.9706293407871294, "grad_norm": 1.2256918825594654, "learning_rate": 5.106123023751186e-06, "loss": 0.3936, "num_tokens": 543439977.0, "step": 90980 }, { "epoch": 0.9706826837933279, "grad_norm": 0.7044042241706028, "learning_rate": 5.105738333972605e-06, "loss": 0.3967, "num_tokens": 543466708.0, "step": 90985 }, { "epoch": 0.9707360267995263, "grad_norm": 0.9692727212807865, "learning_rate": 5.105354341057447e-06, "loss": 0.4951, "num_tokens": 543503707.0, "step": 90990 }, { "epoch": 0.9707893698057247, "grad_norm": 0.5328532278752091, "learning_rate": 5.104971045017665e-06, "loss": 0.5817, "num_tokens": 543547032.0, "step": 90995 }, { "epoch": 0.9708427128119232, "grad_norm": 0.9611981321172208, "learning_rate": 5.10458844586518e-06, "loss": 0.6376, "num_tokens": 543581342.0, "step": 91000 }, { "epoch": 0.9708960558181217, "grad_norm": 0.9660408117521975, "learning_rate": 5.104206543611903e-06, "loss": 0.4541, "num_tokens": 543606782.0, "step": 91005 }, { "epoch": 0.9709493988243202, "grad_norm": 0.5790253743976788, "learning_rate": 5.103825338269716e-06, "loss": 0.4343, "num_tokens": 543639162.0, "step": 91010 }, { "epoch": 0.9710027418305186, "grad_norm": 0.7790788424716986, "learning_rate": 5.10344482985048e-06, "loss": 0.3716, "num_tokens": 543660784.0, "step": 91015 }, { "epoch": 0.971056084836717, "grad_norm": 0.7057354059916102, "learning_rate": 5.103065018366039e-06, "loss": 0.5946, "num_tokens": 543700124.0, "step": 91020 }, { "epoch": 0.9711094278429155, "grad_norm": 1.3639437999459576, "learning_rate": 5.102685903828209e-06, "loss": 0.5683, "num_tokens": 543730806.0, "step": 91025 }, { "epoch": 0.971162770849114, "grad_norm": 1.1139874631756497, "learning_rate": 5.102307486248787e-06, "loss": 0.4654, "num_tokens": 543757583.0, "step": 91030 }, { "epoch": 0.9712161138553125, "grad_norm": 1.0806384283527866, "learning_rate": 5.101929765639552e-06, "loss": 0.4428, "num_tokens": 543776853.0, "step": 91035 }, { "epoch": 0.9712694568615109, "grad_norm": 1.2208641750562488, "learning_rate": 5.101552742012256e-06, "loss": 0.4718, "num_tokens": 543799379.0, "step": 91040 }, { "epoch": 0.9713227998677093, "grad_norm": 1.0144782564415689, "learning_rate": 5.1011764153786306e-06, "loss": 0.5586, "num_tokens": 543824442.0, "step": 91045 }, { "epoch": 0.9713761428739078, "grad_norm": 0.883395411588059, "learning_rate": 5.100800785750387e-06, "loss": 0.449, "num_tokens": 543862077.0, "step": 91050 }, { "epoch": 0.9714294858801062, "grad_norm": 1.0466340621292871, "learning_rate": 5.100425853139211e-06, "loss": 0.5681, "num_tokens": 543903269.0, "step": 91055 }, { "epoch": 0.9714828288863047, "grad_norm": 0.8200022576193576, "learning_rate": 5.100051617556772e-06, "loss": 0.4377, "num_tokens": 543938479.0, "step": 91060 }, { "epoch": 0.9715361718925032, "grad_norm": 0.8583576635025277, "learning_rate": 5.09967807901472e-06, "loss": 0.5227, "num_tokens": 543978517.0, "step": 91065 }, { "epoch": 0.9715895148987016, "grad_norm": 1.0040696955864332, "learning_rate": 5.099305237524673e-06, "loss": 0.6136, "num_tokens": 544020287.0, "step": 91070 }, { "epoch": 0.9716428579049001, "grad_norm": 0.7205867348271089, "learning_rate": 5.098933093098234e-06, "loss": 0.4779, "num_tokens": 544055898.0, "step": 91075 }, { "epoch": 0.9716962009110985, "grad_norm": 1.1867708302472189, "learning_rate": 5.098561645746983e-06, "loss": 0.5651, "num_tokens": 544088765.0, "step": 91080 }, { "epoch": 0.971749543917297, "grad_norm": 0.9375776738102586, "learning_rate": 5.098190895482482e-06, "loss": 0.5062, "num_tokens": 544108342.0, "step": 91085 }, { "epoch": 0.9718028869234955, "grad_norm": 0.8850767412141809, "learning_rate": 5.097820842316264e-06, "loss": 0.43, "num_tokens": 544126903.0, "step": 91090 }, { "epoch": 0.9718562299296939, "grad_norm": 1.1883114506207106, "learning_rate": 5.097451486259847e-06, "loss": 0.4446, "num_tokens": 544143979.0, "step": 91095 }, { "epoch": 0.9719095729358924, "grad_norm": 0.9974777105484319, "learning_rate": 5.097082827324723e-06, "loss": 0.416, "num_tokens": 544166492.0, "step": 91100 }, { "epoch": 0.9719629159420908, "grad_norm": 0.6791186889712982, "learning_rate": 5.096714865522365e-06, "loss": 0.5255, "num_tokens": 544218271.0, "step": 91105 }, { "epoch": 0.9720162589482892, "grad_norm": 1.0936794166977932, "learning_rate": 5.096347600864222e-06, "loss": 0.4045, "num_tokens": 544249459.0, "step": 91110 }, { "epoch": 0.9720696019544878, "grad_norm": 0.7263566806135231, "learning_rate": 5.095981033361725e-06, "loss": 0.5314, "num_tokens": 544278511.0, "step": 91115 }, { "epoch": 0.9721229449606862, "grad_norm": 0.9644666998234737, "learning_rate": 5.095615163026277e-06, "loss": 0.3497, "num_tokens": 544299226.0, "step": 91120 }, { "epoch": 0.9721762879668847, "grad_norm": 0.9124113585797861, "learning_rate": 5.095249989869267e-06, "loss": 0.5645, "num_tokens": 544345513.0, "step": 91125 }, { "epoch": 0.9722296309730831, "grad_norm": 0.8861312179332848, "learning_rate": 5.094885513902054e-06, "loss": 0.4009, "num_tokens": 544359929.0, "step": 91130 }, { "epoch": 0.9722829739792815, "grad_norm": 1.4832703881227762, "learning_rate": 5.094521735135983e-06, "loss": 0.4091, "num_tokens": 544386333.0, "step": 91135 }, { "epoch": 0.9723363169854801, "grad_norm": 2.513920634020317, "learning_rate": 5.094158653582376e-06, "loss": 0.5883, "num_tokens": 544416949.0, "step": 91140 }, { "epoch": 0.9723896599916785, "grad_norm": 0.7207974364519348, "learning_rate": 5.093796269252527e-06, "loss": 0.435, "num_tokens": 544457732.0, "step": 91145 }, { "epoch": 0.9724430029978769, "grad_norm": 1.302392452715789, "learning_rate": 5.0934345821577155e-06, "loss": 0.4869, "num_tokens": 544474275.0, "step": 91150 }, { "epoch": 0.9724963460040754, "grad_norm": 0.9310201802403089, "learning_rate": 5.0930735923091945e-06, "loss": 0.4757, "num_tokens": 544513291.0, "step": 91155 }, { "epoch": 0.9725496890102738, "grad_norm": 0.5800264825322596, "learning_rate": 5.092713299718198e-06, "loss": 0.3396, "num_tokens": 544542599.0, "step": 91160 }, { "epoch": 0.9726030320164724, "grad_norm": 0.6895959386370554, "learning_rate": 5.092353704395936e-06, "loss": 0.6607, "num_tokens": 544585936.0, "step": 91165 }, { "epoch": 0.9726563750226708, "grad_norm": 0.8963658591122967, "learning_rate": 5.091994806353603e-06, "loss": 0.4195, "num_tokens": 544606734.0, "step": 91170 }, { "epoch": 0.9727097180288692, "grad_norm": 1.1992479362235646, "learning_rate": 5.091636605602363e-06, "loss": 0.461, "num_tokens": 544631041.0, "step": 91175 }, { "epoch": 0.9727630610350677, "grad_norm": 1.9066662147525246, "learning_rate": 5.0912791021533634e-06, "loss": 0.4333, "num_tokens": 544664175.0, "step": 91180 }, { "epoch": 0.9728164040412661, "grad_norm": 1.148723475450098, "learning_rate": 5.090922296017731e-06, "loss": 0.481, "num_tokens": 544703187.0, "step": 91185 }, { "epoch": 0.9728697470474647, "grad_norm": 0.6307973565865614, "learning_rate": 5.090566187206567e-06, "loss": 0.551, "num_tokens": 544729086.0, "step": 91190 }, { "epoch": 0.9729230900536631, "grad_norm": 1.6756710737765688, "learning_rate": 5.090210775730952e-06, "loss": 0.4664, "num_tokens": 544744299.0, "step": 91195 }, { "epoch": 0.9729764330598615, "grad_norm": 0.9411437601901832, "learning_rate": 5.089856061601947e-06, "loss": 0.3703, "num_tokens": 544761712.0, "step": 91200 }, { "epoch": 0.97302977606606, "grad_norm": 0.8531985261492097, "learning_rate": 5.089502044830589e-06, "loss": 0.416, "num_tokens": 544800712.0, "step": 91205 }, { "epoch": 0.9730831190722584, "grad_norm": 0.9072666666679491, "learning_rate": 5.0891487254278945e-06, "loss": 0.4276, "num_tokens": 544837794.0, "step": 91210 }, { "epoch": 0.9731364620784569, "grad_norm": 0.5867777027773387, "learning_rate": 5.088796103404859e-06, "loss": 0.3588, "num_tokens": 544876710.0, "step": 91215 }, { "epoch": 0.9731898050846554, "grad_norm": 1.5283445492530385, "learning_rate": 5.088444178772455e-06, "loss": 0.5226, "num_tokens": 544897330.0, "step": 91220 }, { "epoch": 0.9732431480908538, "grad_norm": 1.394455803125973, "learning_rate": 5.0880929515416335e-06, "loss": 0.5538, "num_tokens": 544915085.0, "step": 91225 }, { "epoch": 0.9732964910970523, "grad_norm": 1.0453940102719954, "learning_rate": 5.087742421723325e-06, "loss": 0.4116, "num_tokens": 544945744.0, "step": 91230 }, { "epoch": 0.9733498341032507, "grad_norm": 0.7769835921240329, "learning_rate": 5.087392589328434e-06, "loss": 0.5123, "num_tokens": 544973873.0, "step": 91235 }, { "epoch": 0.9734031771094491, "grad_norm": 0.9798919445349967, "learning_rate": 5.08704345436785e-06, "loss": 0.4273, "num_tokens": 544991292.0, "step": 91240 }, { "epoch": 0.9734565201156476, "grad_norm": 0.6922292629514349, "learning_rate": 5.0866950168524375e-06, "loss": 0.5164, "num_tokens": 545042434.0, "step": 91245 }, { "epoch": 0.9735098631218461, "grad_norm": 0.8578852015613796, "learning_rate": 5.086347276793037e-06, "loss": 0.5861, "num_tokens": 545061495.0, "step": 91250 }, { "epoch": 0.9735632061280446, "grad_norm": 0.9414111450750261, "learning_rate": 5.086000234200469e-06, "loss": 0.347, "num_tokens": 545089528.0, "step": 91255 }, { "epoch": 0.973616549134243, "grad_norm": 1.3011367626048713, "learning_rate": 5.085653889085535e-06, "loss": 0.4572, "num_tokens": 545113676.0, "step": 91260 }, { "epoch": 0.9736698921404414, "grad_norm": 0.5881166409005076, "learning_rate": 5.085308241459012e-06, "loss": 0.4412, "num_tokens": 545140756.0, "step": 91265 }, { "epoch": 0.9737232351466399, "grad_norm": 1.2047003556221874, "learning_rate": 5.084963291331653e-06, "loss": 0.4933, "num_tokens": 545166673.0, "step": 91270 }, { "epoch": 0.9737765781528384, "grad_norm": 1.2327233428893947, "learning_rate": 5.084619038714198e-06, "loss": 0.5811, "num_tokens": 545201393.0, "step": 91275 }, { "epoch": 0.9738299211590369, "grad_norm": 0.8287603143957616, "learning_rate": 5.084275483617354e-06, "loss": 0.4457, "num_tokens": 545226097.0, "step": 91280 }, { "epoch": 0.9738832641652353, "grad_norm": 0.8884426637228943, "learning_rate": 5.083932626051813e-06, "loss": 0.5683, "num_tokens": 545255441.0, "step": 91285 }, { "epoch": 0.9739366071714337, "grad_norm": 1.045447538288114, "learning_rate": 5.083590466028247e-06, "loss": 0.4329, "num_tokens": 545281065.0, "step": 91290 }, { "epoch": 0.9739899501776322, "grad_norm": 0.7638955908012325, "learning_rate": 5.083249003557301e-06, "loss": 0.4865, "num_tokens": 545314356.0, "step": 91295 }, { "epoch": 0.9740432931838306, "grad_norm": 1.5249892895832018, "learning_rate": 5.0829082386495986e-06, "loss": 0.4651, "num_tokens": 545338897.0, "step": 91300 }, { "epoch": 0.9740966361900292, "grad_norm": 1.7654210296872435, "learning_rate": 5.0825681713157494e-06, "loss": 0.487, "num_tokens": 545369896.0, "step": 91305 }, { "epoch": 0.9741499791962276, "grad_norm": 0.675018921499733, "learning_rate": 5.082228801566326e-06, "loss": 0.4273, "num_tokens": 545414514.0, "step": 91310 }, { "epoch": 0.974203322202426, "grad_norm": 1.4065777458249538, "learning_rate": 5.081890129411901e-06, "loss": 0.4666, "num_tokens": 545445708.0, "step": 91315 }, { "epoch": 0.9742566652086245, "grad_norm": 1.003238812103642, "learning_rate": 5.081552154863003e-06, "loss": 0.6152, "num_tokens": 545466937.0, "step": 91320 }, { "epoch": 0.9743100082148229, "grad_norm": 0.6791878488704521, "learning_rate": 5.081214877930153e-06, "loss": 0.4672, "num_tokens": 545513838.0, "step": 91325 }, { "epoch": 0.9743633512210214, "grad_norm": 1.7743958524455232, "learning_rate": 5.08087829862385e-06, "loss": 0.3796, "num_tokens": 545528482.0, "step": 91330 }, { "epoch": 0.9744166942272199, "grad_norm": 1.2565516379754627, "learning_rate": 5.080542416954562e-06, "loss": 0.3743, "num_tokens": 545548214.0, "step": 91335 }, { "epoch": 0.9744700372334183, "grad_norm": 1.1584697828574761, "learning_rate": 5.080207232932744e-06, "loss": 0.4372, "num_tokens": 545563055.0, "step": 91340 }, { "epoch": 0.9745233802396168, "grad_norm": 1.01739849294443, "learning_rate": 5.079872746568823e-06, "loss": 0.4285, "num_tokens": 545591124.0, "step": 91345 }, { "epoch": 0.9745767232458152, "grad_norm": 1.2005398005116854, "learning_rate": 5.079538957873211e-06, "loss": 0.5332, "num_tokens": 545619481.0, "step": 91350 }, { "epoch": 0.9746300662520136, "grad_norm": 1.0116014518096725, "learning_rate": 5.0792058668562956e-06, "loss": 0.3514, "num_tokens": 545636218.0, "step": 91355 }, { "epoch": 0.9746834092582122, "grad_norm": 0.6523921068365934, "learning_rate": 5.078873473528439e-06, "loss": 0.4705, "num_tokens": 545668081.0, "step": 91360 }, { "epoch": 0.9747367522644106, "grad_norm": 1.3304194948950616, "learning_rate": 5.078541777899984e-06, "loss": 0.4349, "num_tokens": 545687326.0, "step": 91365 }, { "epoch": 0.9747900952706091, "grad_norm": 1.3663369125305858, "learning_rate": 5.078210779981256e-06, "loss": 0.3943, "num_tokens": 545717467.0, "step": 91370 }, { "epoch": 0.9748434382768075, "grad_norm": 0.7260123648640393, "learning_rate": 5.077880479782551e-06, "loss": 0.4272, "num_tokens": 545739417.0, "step": 91375 }, { "epoch": 0.9748967812830059, "grad_norm": 0.7135507090936606, "learning_rate": 5.07755087731415e-06, "loss": 0.367, "num_tokens": 545764789.0, "step": 91380 }, { "epoch": 0.9749501242892045, "grad_norm": 1.4175811035835992, "learning_rate": 5.077221972586309e-06, "loss": 0.4331, "num_tokens": 545787708.0, "step": 91385 }, { "epoch": 0.9750034672954029, "grad_norm": 1.2467410742754608, "learning_rate": 5.076893765609264e-06, "loss": 0.4784, "num_tokens": 545806973.0, "step": 91390 }, { "epoch": 0.9750568103016014, "grad_norm": 1.1838570498482417, "learning_rate": 5.076566256393224e-06, "loss": 0.4651, "num_tokens": 545821814.0, "step": 91395 }, { "epoch": 0.9751101533077998, "grad_norm": 0.8559196686069468, "learning_rate": 5.076239444948383e-06, "loss": 0.583, "num_tokens": 545850378.0, "step": 91400 }, { "epoch": 0.9751634963139982, "grad_norm": 1.1544938433448677, "learning_rate": 5.0759133312849115e-06, "loss": 0.3907, "num_tokens": 545872081.0, "step": 91405 }, { "epoch": 0.9752168393201968, "grad_norm": 1.12267308007625, "learning_rate": 5.075587915412958e-06, "loss": 0.5644, "num_tokens": 545892433.0, "step": 91410 }, { "epoch": 0.9752701823263952, "grad_norm": 0.9519990478056967, "learning_rate": 5.075263197342645e-06, "loss": 0.4716, "num_tokens": 545934221.0, "step": 91415 }, { "epoch": 0.9753235253325936, "grad_norm": 1.2219927463106854, "learning_rate": 5.074939177084081e-06, "loss": 0.4597, "num_tokens": 545965764.0, "step": 91420 }, { "epoch": 0.9753768683387921, "grad_norm": 0.6690902099728971, "learning_rate": 5.074615854647347e-06, "loss": 0.3833, "num_tokens": 545993262.0, "step": 91425 }, { "epoch": 0.9754302113449905, "grad_norm": 0.6669450685280457, "learning_rate": 5.074293230042505e-06, "loss": 0.4159, "num_tokens": 546035424.0, "step": 91430 }, { "epoch": 0.975483554351189, "grad_norm": 1.148380755756586, "learning_rate": 5.073971303279595e-06, "loss": 0.3964, "num_tokens": 546062709.0, "step": 91435 }, { "epoch": 0.9755368973573875, "grad_norm": 1.1720331281105345, "learning_rate": 5.073650074368632e-06, "loss": 0.3953, "num_tokens": 546087948.0, "step": 91440 }, { "epoch": 0.9755902403635859, "grad_norm": 0.6812368390056, "learning_rate": 5.073329543319615e-06, "loss": 0.5024, "num_tokens": 546119624.0, "step": 91445 }, { "epoch": 0.9756435833697844, "grad_norm": 1.0695002784744092, "learning_rate": 5.073009710142516e-06, "loss": 0.423, "num_tokens": 546142348.0, "step": 91450 }, { "epoch": 0.9756969263759828, "grad_norm": 1.1844481234846602, "learning_rate": 5.072690574847288e-06, "loss": 0.5117, "num_tokens": 546161236.0, "step": 91455 }, { "epoch": 0.9757502693821813, "grad_norm": 1.183595863930969, "learning_rate": 5.072372137443863e-06, "loss": 0.5327, "num_tokens": 546191871.0, "step": 91460 }, { "epoch": 0.9758036123883798, "grad_norm": 0.6020500878861524, "learning_rate": 5.0720543979421486e-06, "loss": 0.5853, "num_tokens": 546229613.0, "step": 91465 }, { "epoch": 0.9758569553945782, "grad_norm": 0.7089809929370335, "learning_rate": 5.071737356352035e-06, "loss": 0.4359, "num_tokens": 546265759.0, "step": 91470 }, { "epoch": 0.9759102984007767, "grad_norm": 1.0278305308322728, "learning_rate": 5.071421012683384e-06, "loss": 0.469, "num_tokens": 546311428.0, "step": 91475 }, { "epoch": 0.9759636414069751, "grad_norm": 2.306726212888242, "learning_rate": 5.071105366946042e-06, "loss": 0.5939, "num_tokens": 546346448.0, "step": 91480 }, { "epoch": 0.9760169844131736, "grad_norm": 1.453002901033703, "learning_rate": 5.0707904191498315e-06, "loss": 0.5904, "num_tokens": 546377131.0, "step": 91485 }, { "epoch": 0.976070327419372, "grad_norm": 0.9230941200976545, "learning_rate": 5.070476169304551e-06, "loss": 0.441, "num_tokens": 546406567.0, "step": 91490 }, { "epoch": 0.9761236704255705, "grad_norm": 0.8707432095976448, "learning_rate": 5.070162617419981e-06, "loss": 0.5243, "num_tokens": 546432881.0, "step": 91495 }, { "epoch": 0.976177013431769, "grad_norm": 1.2893719015240266, "learning_rate": 5.06984976350588e-06, "loss": 0.4389, "num_tokens": 546472415.0, "step": 91500 }, { "epoch": 0.9762303564379674, "grad_norm": 0.9390977425135948, "learning_rate": 5.069537607571978e-06, "loss": 0.4384, "num_tokens": 546503296.0, "step": 91505 }, { "epoch": 0.9762836994441658, "grad_norm": 0.9905867840800564, "learning_rate": 5.069226149627995e-06, "loss": 0.4482, "num_tokens": 546524408.0, "step": 91510 }, { "epoch": 0.9763370424503643, "grad_norm": 0.832640910415753, "learning_rate": 5.068915389683617e-06, "loss": 0.4279, "num_tokens": 546557212.0, "step": 91515 }, { "epoch": 0.9763903854565628, "grad_norm": 1.0529765089137797, "learning_rate": 5.06860532774852e-06, "loss": 0.3964, "num_tokens": 546578047.0, "step": 91520 }, { "epoch": 0.9764437284627613, "grad_norm": 1.5646212223603726, "learning_rate": 5.068295963832351e-06, "loss": 0.4697, "num_tokens": 546606707.0, "step": 91525 }, { "epoch": 0.9764970714689597, "grad_norm": 1.0140714349123063, "learning_rate": 5.067987297944731e-06, "loss": 0.4838, "num_tokens": 546633096.0, "step": 91530 }, { "epoch": 0.9765504144751581, "grad_norm": 1.2902118417313282, "learning_rate": 5.067679330095274e-06, "loss": 0.4715, "num_tokens": 546656990.0, "step": 91535 }, { "epoch": 0.9766037574813566, "grad_norm": 1.671465328555948, "learning_rate": 5.067372060293556e-06, "loss": 0.5051, "num_tokens": 546691258.0, "step": 91540 }, { "epoch": 0.976657100487555, "grad_norm": 0.7752886771318183, "learning_rate": 5.067065488549144e-06, "loss": 0.4737, "num_tokens": 546718675.0, "step": 91545 }, { "epoch": 0.9767104434937536, "grad_norm": 0.8569917138049677, "learning_rate": 5.066759614871575e-06, "loss": 0.5123, "num_tokens": 546756421.0, "step": 91550 }, { "epoch": 0.976763786499952, "grad_norm": 1.2385805430386105, "learning_rate": 5.0664544392703646e-06, "loss": 0.406, "num_tokens": 546781259.0, "step": 91555 }, { "epoch": 0.9768171295061504, "grad_norm": 1.6488492731213218, "learning_rate": 5.066149961755015e-06, "loss": 0.5705, "num_tokens": 546805287.0, "step": 91560 }, { "epoch": 0.9768704725123489, "grad_norm": 0.7480073863390428, "learning_rate": 5.065846182334998e-06, "loss": 0.3437, "num_tokens": 546838863.0, "step": 91565 }, { "epoch": 0.9769238155185473, "grad_norm": 0.9386899272876535, "learning_rate": 5.065543101019766e-06, "loss": 0.3717, "num_tokens": 546856767.0, "step": 91570 }, { "epoch": 0.9769771585247459, "grad_norm": 0.9623896039074649, "learning_rate": 5.065240717818752e-06, "loss": 0.4725, "num_tokens": 546878585.0, "step": 91575 }, { "epoch": 0.9770305015309443, "grad_norm": 0.8788141175191333, "learning_rate": 5.064939032741363e-06, "loss": 0.4562, "num_tokens": 546904335.0, "step": 91580 }, { "epoch": 0.9770838445371427, "grad_norm": 0.7873569146319888, "learning_rate": 5.064638045796989e-06, "loss": 0.3327, "num_tokens": 546940579.0, "step": 91585 }, { "epoch": 0.9771371875433412, "grad_norm": 1.1540463790013362, "learning_rate": 5.064337756994998e-06, "loss": 0.4247, "num_tokens": 546971118.0, "step": 91590 }, { "epoch": 0.9771905305495396, "grad_norm": 1.2128137838150614, "learning_rate": 5.064038166344727e-06, "loss": 0.5226, "num_tokens": 546991396.0, "step": 91595 }, { "epoch": 0.977243873555738, "grad_norm": 0.8805753341003323, "learning_rate": 5.063739273855506e-06, "loss": 0.338, "num_tokens": 547009365.0, "step": 91600 }, { "epoch": 0.9772972165619366, "grad_norm": 0.8610816989115906, "learning_rate": 5.063441079536634e-06, "loss": 0.4721, "num_tokens": 547047498.0, "step": 91605 }, { "epoch": 0.977350559568135, "grad_norm": 0.657605210428914, "learning_rate": 5.06314358339739e-06, "loss": 0.3781, "num_tokens": 547078943.0, "step": 91610 }, { "epoch": 0.9774039025743335, "grad_norm": 1.458294646841068, "learning_rate": 5.062846785447028e-06, "loss": 0.5086, "num_tokens": 547112601.0, "step": 91615 }, { "epoch": 0.9774572455805319, "grad_norm": 0.5848150904325857, "learning_rate": 5.062550685694792e-06, "loss": 0.3902, "num_tokens": 547145591.0, "step": 91620 }, { "epoch": 0.9775105885867303, "grad_norm": 0.8909253148576192, "learning_rate": 5.062255284149886e-06, "loss": 0.4237, "num_tokens": 547165167.0, "step": 91625 }, { "epoch": 0.9775639315929289, "grad_norm": 1.3943835668529532, "learning_rate": 5.061960580821508e-06, "loss": 0.4214, "num_tokens": 547189111.0, "step": 91630 }, { "epoch": 0.9776172745991273, "grad_norm": 0.814317430849116, "learning_rate": 5.06166657571883e-06, "loss": 0.3931, "num_tokens": 547219069.0, "step": 91635 }, { "epoch": 0.9776706176053258, "grad_norm": 1.0740850148090133, "learning_rate": 5.061373268850996e-06, "loss": 0.4606, "num_tokens": 547254492.0, "step": 91640 }, { "epoch": 0.9777239606115242, "grad_norm": 1.217417468523914, "learning_rate": 5.061080660227138e-06, "loss": 0.6494, "num_tokens": 547286141.0, "step": 91645 }, { "epoch": 0.9777773036177226, "grad_norm": 0.9443474373832051, "learning_rate": 5.060788749856355e-06, "loss": 0.3947, "num_tokens": 547307108.0, "step": 91650 }, { "epoch": 0.9778306466239212, "grad_norm": 1.5171743044418298, "learning_rate": 5.060497537747738e-06, "loss": 0.4755, "num_tokens": 547337829.0, "step": 91655 }, { "epoch": 0.9778839896301196, "grad_norm": 0.9065088931174029, "learning_rate": 5.060207023910346e-06, "loss": 0.4341, "num_tokens": 547376564.0, "step": 91660 }, { "epoch": 0.9779373326363181, "grad_norm": 0.5769774469438611, "learning_rate": 5.059917208353218e-06, "loss": 0.465, "num_tokens": 547422004.0, "step": 91665 }, { "epoch": 0.9779906756425165, "grad_norm": 0.9016465219588118, "learning_rate": 5.059628091085372e-06, "loss": 0.4235, "num_tokens": 547452297.0, "step": 91670 }, { "epoch": 0.9780440186487149, "grad_norm": 1.787465098244954, "learning_rate": 5.059339672115806e-06, "loss": 0.5018, "num_tokens": 547499625.0, "step": 91675 }, { "epoch": 0.9780973616549135, "grad_norm": 1.1629747328553253, "learning_rate": 5.059051951453497e-06, "loss": 0.6362, "num_tokens": 547530783.0, "step": 91680 }, { "epoch": 0.9781507046611119, "grad_norm": 0.7936134937421131, "learning_rate": 5.0587649291073935e-06, "loss": 0.4556, "num_tokens": 547580524.0, "step": 91685 }, { "epoch": 0.9782040476673103, "grad_norm": 1.1620996116236642, "learning_rate": 5.0584786050864305e-06, "loss": 0.5615, "num_tokens": 547602055.0, "step": 91690 }, { "epoch": 0.9782573906735088, "grad_norm": 0.9648052385082201, "learning_rate": 5.0581929793995185e-06, "loss": 0.4377, "num_tokens": 547636172.0, "step": 91695 }, { "epoch": 0.9783107336797072, "grad_norm": 1.40489710405357, "learning_rate": 5.0579080520555445e-06, "loss": 0.5359, "num_tokens": 547665819.0, "step": 91700 }, { "epoch": 0.9783640766859057, "grad_norm": 0.8279308315263778, "learning_rate": 5.057623823063373e-06, "loss": 0.3929, "num_tokens": 547686791.0, "step": 91705 }, { "epoch": 0.9784174196921042, "grad_norm": 1.1899781687204787, "learning_rate": 5.057340292431852e-06, "loss": 0.4474, "num_tokens": 547707959.0, "step": 91710 }, { "epoch": 0.9784707626983026, "grad_norm": 0.6427649916058399, "learning_rate": 5.057057460169801e-06, "loss": 0.5479, "num_tokens": 547747786.0, "step": 91715 }, { "epoch": 0.9785241057045011, "grad_norm": 0.5596341920489772, "learning_rate": 5.056775326286024e-06, "loss": 0.4966, "num_tokens": 547792617.0, "step": 91720 }, { "epoch": 0.9785774487106995, "grad_norm": 0.5588257028776126, "learning_rate": 5.056493890789296e-06, "loss": 0.4623, "num_tokens": 547836076.0, "step": 91725 }, { "epoch": 0.978630791716898, "grad_norm": 0.7877978111504366, "learning_rate": 5.05621315368838e-06, "loss": 0.4131, "num_tokens": 547858567.0, "step": 91730 }, { "epoch": 0.9786841347230965, "grad_norm": 0.6788277913872978, "learning_rate": 5.055933114992011e-06, "loss": 0.4652, "num_tokens": 547905223.0, "step": 91735 }, { "epoch": 0.9787374777292949, "grad_norm": 0.8940287405677837, "learning_rate": 5.055653774708901e-06, "loss": 0.3946, "num_tokens": 547934388.0, "step": 91740 }, { "epoch": 0.9787908207354934, "grad_norm": 0.7596053240354098, "learning_rate": 5.0553751328477435e-06, "loss": 0.4041, "num_tokens": 547963101.0, "step": 91745 }, { "epoch": 0.9788441637416918, "grad_norm": 1.7971187619633402, "learning_rate": 5.055097189417208e-06, "loss": 0.4636, "num_tokens": 547993660.0, "step": 91750 }, { "epoch": 0.9788975067478903, "grad_norm": 1.0355318895177354, "learning_rate": 5.0548199444259456e-06, "loss": 0.6538, "num_tokens": 548026988.0, "step": 91755 }, { "epoch": 0.9789508497540887, "grad_norm": 1.061412061986767, "learning_rate": 5.054543397882586e-06, "loss": 0.4016, "num_tokens": 548048140.0, "step": 91760 }, { "epoch": 0.9790041927602872, "grad_norm": 0.917392374266288, "learning_rate": 5.054267549795728e-06, "loss": 0.5037, "num_tokens": 548084395.0, "step": 91765 }, { "epoch": 0.9790575357664857, "grad_norm": 1.2420087496451717, "learning_rate": 5.053992400173958e-06, "loss": 0.481, "num_tokens": 548115011.0, "step": 91770 }, { "epoch": 0.9791108787726841, "grad_norm": 1.0645335979683646, "learning_rate": 5.053717949025843e-06, "loss": 0.3541, "num_tokens": 548141840.0, "step": 91775 }, { "epoch": 0.9791642217788825, "grad_norm": 1.4404228352141226, "learning_rate": 5.053444196359915e-06, "loss": 0.4489, "num_tokens": 548169909.0, "step": 91780 }, { "epoch": 0.979217564785081, "grad_norm": 2.475304398547454, "learning_rate": 5.0531711421847e-06, "loss": 0.5512, "num_tokens": 548185347.0, "step": 91785 }, { "epoch": 0.9792709077912795, "grad_norm": 0.7084678556367053, "learning_rate": 5.052898786508692e-06, "loss": 0.6866, "num_tokens": 548212480.0, "step": 91790 }, { "epoch": 0.979324250797478, "grad_norm": 1.216447715820305, "learning_rate": 5.052627129340365e-06, "loss": 0.3686, "num_tokens": 548244000.0, "step": 91795 }, { "epoch": 0.9793775938036764, "grad_norm": 0.9376571150053267, "learning_rate": 5.052356170688175e-06, "loss": 0.4199, "num_tokens": 548269679.0, "step": 91800 }, { "epoch": 0.9794309368098748, "grad_norm": 0.9184139406633514, "learning_rate": 5.05208591056055e-06, "loss": 0.5143, "num_tokens": 548286490.0, "step": 91805 }, { "epoch": 0.9794842798160733, "grad_norm": 1.3233392647201394, "learning_rate": 5.051816348965904e-06, "loss": 0.4989, "num_tokens": 548317857.0, "step": 91810 }, { "epoch": 0.9795376228222717, "grad_norm": 3.0212915004501495, "learning_rate": 5.051547485912623e-06, "loss": 0.4854, "num_tokens": 548343795.0, "step": 91815 }, { "epoch": 0.9795909658284703, "grad_norm": 1.0471242528319642, "learning_rate": 5.051279321409072e-06, "loss": 0.4787, "num_tokens": 548375694.0, "step": 91820 }, { "epoch": 0.9796443088346687, "grad_norm": 0.5823298236561717, "learning_rate": 5.051011855463599e-06, "loss": 0.5064, "num_tokens": 548409776.0, "step": 91825 }, { "epoch": 0.9796976518408671, "grad_norm": 1.2577523943622286, "learning_rate": 5.050745088084524e-06, "loss": 0.4259, "num_tokens": 548436891.0, "step": 91830 }, { "epoch": 0.9797509948470656, "grad_norm": 1.2857568160470905, "learning_rate": 5.050479019280153e-06, "loss": 0.484, "num_tokens": 548469908.0, "step": 91835 }, { "epoch": 0.979804337853264, "grad_norm": 2.057346327849641, "learning_rate": 5.050213649058761e-06, "loss": 0.5342, "num_tokens": 548490659.0, "step": 91840 }, { "epoch": 0.9798576808594626, "grad_norm": 0.6098606607235155, "learning_rate": 5.049948977428605e-06, "loss": 0.4057, "num_tokens": 548512817.0, "step": 91845 }, { "epoch": 0.979911023865661, "grad_norm": 0.6771050811354029, "learning_rate": 5.049685004397926e-06, "loss": 0.5086, "num_tokens": 548536037.0, "step": 91850 }, { "epoch": 0.9799643668718594, "grad_norm": 2.054852548835289, "learning_rate": 5.049421729974934e-06, "loss": 0.4735, "num_tokens": 548558209.0, "step": 91855 }, { "epoch": 0.9800177098780579, "grad_norm": 1.0568318952452143, "learning_rate": 5.0491591541678215e-06, "loss": 0.4662, "num_tokens": 548593205.0, "step": 91860 }, { "epoch": 0.9800710528842563, "grad_norm": 1.0659651092542677, "learning_rate": 5.048897276984763e-06, "loss": 0.499, "num_tokens": 548639172.0, "step": 91865 }, { "epoch": 0.9801243958904547, "grad_norm": 0.7090174553205746, "learning_rate": 5.048636098433903e-06, "loss": 0.3725, "num_tokens": 548658356.0, "step": 91870 }, { "epoch": 0.9801777388966533, "grad_norm": 0.7431860053446349, "learning_rate": 5.048375618523375e-06, "loss": 0.4214, "num_tokens": 548689350.0, "step": 91875 }, { "epoch": 0.9802310819028517, "grad_norm": 0.7866273512578728, "learning_rate": 5.048115837261278e-06, "loss": 0.5504, "num_tokens": 548722592.0, "step": 91880 }, { "epoch": 0.9802844249090502, "grad_norm": 2.019816480051994, "learning_rate": 5.047856754655699e-06, "loss": 0.3975, "num_tokens": 548742542.0, "step": 91885 }, { "epoch": 0.9803377679152486, "grad_norm": 0.8471756134302337, "learning_rate": 5.047598370714701e-06, "loss": 0.6029, "num_tokens": 548782775.0, "step": 91890 }, { "epoch": 0.980391110921447, "grad_norm": 1.4052711016026396, "learning_rate": 5.047340685446322e-06, "loss": 0.5506, "num_tokens": 548822221.0, "step": 91895 }, { "epoch": 0.9804444539276456, "grad_norm": 0.8919927294582936, "learning_rate": 5.04708369885858e-06, "loss": 0.3715, "num_tokens": 548843155.0, "step": 91900 }, { "epoch": 0.980497796933844, "grad_norm": 0.864307865382123, "learning_rate": 5.046827410959477e-06, "loss": 0.5437, "num_tokens": 548872231.0, "step": 91905 }, { "epoch": 0.9805511399400425, "grad_norm": 0.8338878784332672, "learning_rate": 5.046571821756982e-06, "loss": 0.4983, "num_tokens": 548919190.0, "step": 91910 }, { "epoch": 0.9806044829462409, "grad_norm": 0.7795810179696951, "learning_rate": 5.046316931259054e-06, "loss": 0.4078, "num_tokens": 548948997.0, "step": 91915 }, { "epoch": 0.9806578259524393, "grad_norm": 0.8221549894012229, "learning_rate": 5.046062739473621e-06, "loss": 0.4994, "num_tokens": 548976069.0, "step": 91920 }, { "epoch": 0.9807111689586379, "grad_norm": 0.7603080700662933, "learning_rate": 5.045809246408595e-06, "loss": 0.5442, "num_tokens": 548995121.0, "step": 91925 }, { "epoch": 0.9807645119648363, "grad_norm": 1.6533862339324137, "learning_rate": 5.0455564520718585e-06, "loss": 0.5658, "num_tokens": 549032144.0, "step": 91930 }, { "epoch": 0.9808178549710348, "grad_norm": 0.7968997810032266, "learning_rate": 5.0453043564712865e-06, "loss": 0.4208, "num_tokens": 549050877.0, "step": 91935 }, { "epoch": 0.9808711979772332, "grad_norm": 0.8743596127068586, "learning_rate": 5.045052959614719e-06, "loss": 0.4687, "num_tokens": 549079054.0, "step": 91940 }, { "epoch": 0.9809245409834316, "grad_norm": 1.1938835530081364, "learning_rate": 5.044802261509979e-06, "loss": 0.477, "num_tokens": 549098462.0, "step": 91945 }, { "epoch": 0.9809778839896302, "grad_norm": 0.8026111716073878, "learning_rate": 5.044552262164868e-06, "loss": 0.3567, "num_tokens": 549119930.0, "step": 91950 }, { "epoch": 0.9810312269958286, "grad_norm": 1.775285380691128, "learning_rate": 5.044302961587166e-06, "loss": 0.4578, "num_tokens": 549147787.0, "step": 91955 }, { "epoch": 0.981084570002027, "grad_norm": 1.110896711679851, "learning_rate": 5.044054359784633e-06, "loss": 0.3829, "num_tokens": 549183187.0, "step": 91960 }, { "epoch": 0.9811379130082255, "grad_norm": 1.426408053360973, "learning_rate": 5.043806456764997e-06, "loss": 0.4134, "num_tokens": 549204044.0, "step": 91965 }, { "epoch": 0.9811912560144239, "grad_norm": 0.6292905369608935, "learning_rate": 5.043559252535983e-06, "loss": 0.3433, "num_tokens": 549239395.0, "step": 91970 }, { "epoch": 0.9812445990206224, "grad_norm": 1.398377340709668, "learning_rate": 5.0433127471052754e-06, "loss": 0.502, "num_tokens": 549272144.0, "step": 91975 }, { "epoch": 0.9812979420268209, "grad_norm": 0.9520282863743916, "learning_rate": 5.043066940480549e-06, "loss": 0.4371, "num_tokens": 549294621.0, "step": 91980 }, { "epoch": 0.9813512850330193, "grad_norm": 0.6012623416351063, "learning_rate": 5.0428218326694515e-06, "loss": 0.4311, "num_tokens": 549330592.0, "step": 91985 }, { "epoch": 0.9814046280392178, "grad_norm": 0.9103794156033239, "learning_rate": 5.0425774236796115e-06, "loss": 0.4651, "num_tokens": 549359399.0, "step": 91990 }, { "epoch": 0.9814579710454162, "grad_norm": 1.0446114935559485, "learning_rate": 5.04233371351863e-06, "loss": 0.668, "num_tokens": 549396845.0, "step": 91995 }, { "epoch": 0.9815113140516147, "grad_norm": 2.0685001855572445, "learning_rate": 5.042090702194097e-06, "loss": 0.554, "num_tokens": 549421354.0, "step": 92000 }, { "epoch": 0.9815646570578132, "grad_norm": 0.7403134258678966, "learning_rate": 5.041848389713568e-06, "loss": 0.4531, "num_tokens": 549445518.0, "step": 92005 }, { "epoch": 0.9816180000640116, "grad_norm": 1.4561992710151292, "learning_rate": 5.041606776084589e-06, "loss": 0.4593, "num_tokens": 549469424.0, "step": 92010 }, { "epoch": 0.9816713430702101, "grad_norm": 0.7540208887476509, "learning_rate": 5.0413658613146756e-06, "loss": 0.503, "num_tokens": 549494195.0, "step": 92015 }, { "epoch": 0.9817246860764085, "grad_norm": 1.5786411445843471, "learning_rate": 5.041125645411327e-06, "loss": 0.4411, "num_tokens": 549518379.0, "step": 92020 }, { "epoch": 0.981778029082607, "grad_norm": 0.8979507487316963, "learning_rate": 5.040886128382014e-06, "loss": 0.3749, "num_tokens": 549545868.0, "step": 92025 }, { "epoch": 0.9818313720888054, "grad_norm": 0.8248553802131376, "learning_rate": 5.040647310234194e-06, "loss": 0.348, "num_tokens": 549569628.0, "step": 92030 }, { "epoch": 0.9818847150950039, "grad_norm": 0.8083008549371905, "learning_rate": 5.040409190975296e-06, "loss": 0.3947, "num_tokens": 549601795.0, "step": 92035 }, { "epoch": 0.9819380581012024, "grad_norm": 0.8676546360068428, "learning_rate": 5.040171770612731e-06, "loss": 0.4693, "num_tokens": 549631724.0, "step": 92040 }, { "epoch": 0.9819914011074008, "grad_norm": 0.8870573095036446, "learning_rate": 5.039935049153889e-06, "loss": 0.4728, "num_tokens": 549662590.0, "step": 92045 }, { "epoch": 0.9820447441135992, "grad_norm": 0.7727240658526214, "learning_rate": 5.039699026606131e-06, "loss": 0.3919, "num_tokens": 549696717.0, "step": 92050 }, { "epoch": 0.9820980871197977, "grad_norm": 2.142173688985617, "learning_rate": 5.039463702976805e-06, "loss": 0.729, "num_tokens": 549721777.0, "step": 92055 }, { "epoch": 0.9821514301259961, "grad_norm": 1.019277851569642, "learning_rate": 5.039229078273235e-06, "loss": 0.5342, "num_tokens": 549772102.0, "step": 92060 }, { "epoch": 0.9822047731321947, "grad_norm": 0.841347563945993, "learning_rate": 5.038995152502718e-06, "loss": 0.4455, "num_tokens": 549802490.0, "step": 92065 }, { "epoch": 0.9822581161383931, "grad_norm": 1.0998035612232608, "learning_rate": 5.038761925672536e-06, "loss": 0.4438, "num_tokens": 549843031.0, "step": 92070 }, { "epoch": 0.9823114591445915, "grad_norm": 0.7351797890288554, "learning_rate": 5.038529397789948e-06, "loss": 0.432, "num_tokens": 549875974.0, "step": 92075 }, { "epoch": 0.98236480215079, "grad_norm": 0.595005931792876, "learning_rate": 5.038297568862186e-06, "loss": 0.3313, "num_tokens": 549907691.0, "step": 92080 }, { "epoch": 0.9824181451569884, "grad_norm": 0.6956418753283696, "learning_rate": 5.038066438896466e-06, "loss": 0.3208, "num_tokens": 549930645.0, "step": 92085 }, { "epoch": 0.982471488163187, "grad_norm": 1.1695997212146325, "learning_rate": 5.03783600789998e-06, "loss": 0.3914, "num_tokens": 549958233.0, "step": 92090 }, { "epoch": 0.9825248311693854, "grad_norm": 0.6433337837871895, "learning_rate": 5.0376062758799e-06, "loss": 0.3917, "num_tokens": 549991082.0, "step": 92095 }, { "epoch": 0.9825781741755838, "grad_norm": 0.8167477806783251, "learning_rate": 5.037377242843374e-06, "loss": 0.4192, "num_tokens": 550014894.0, "step": 92100 }, { "epoch": 0.9826315171817823, "grad_norm": 0.9461308397927753, "learning_rate": 5.037148908797528e-06, "loss": 0.401, "num_tokens": 550036546.0, "step": 92105 }, { "epoch": 0.9826848601879807, "grad_norm": 0.8380491170542057, "learning_rate": 5.0369212737494696e-06, "loss": 0.4374, "num_tokens": 550069989.0, "step": 92110 }, { "epoch": 0.9827382031941793, "grad_norm": 2.119439358928286, "learning_rate": 5.036694337706277e-06, "loss": 0.6767, "num_tokens": 550095799.0, "step": 92115 }, { "epoch": 0.9827915462003777, "grad_norm": 0.7919077183182308, "learning_rate": 5.036468100675018e-06, "loss": 0.4585, "num_tokens": 550133176.0, "step": 92120 }, { "epoch": 0.9828448892065761, "grad_norm": 0.955979530610079, "learning_rate": 5.03624256266273e-06, "loss": 0.4992, "num_tokens": 550175840.0, "step": 92125 }, { "epoch": 0.9828982322127746, "grad_norm": 0.8763653984804536, "learning_rate": 5.0360177236764335e-06, "loss": 0.4162, "num_tokens": 550213153.0, "step": 92130 }, { "epoch": 0.982951575218973, "grad_norm": 1.1049755307818339, "learning_rate": 5.03579358372312e-06, "loss": 0.4247, "num_tokens": 550240193.0, "step": 92135 }, { "epoch": 0.9830049182251714, "grad_norm": 0.5950891858323111, "learning_rate": 5.035570142809769e-06, "loss": 0.4689, "num_tokens": 550298600.0, "step": 92140 }, { "epoch": 0.98305826123137, "grad_norm": 0.7889746349981113, "learning_rate": 5.03534740094333e-06, "loss": 0.4275, "num_tokens": 550320483.0, "step": 92145 }, { "epoch": 0.9831116042375684, "grad_norm": 1.049436575369426, "learning_rate": 5.035125358130739e-06, "loss": 0.4642, "num_tokens": 550343665.0, "step": 92150 }, { "epoch": 0.9831649472437669, "grad_norm": 1.5539608080962655, "learning_rate": 5.034904014378901e-06, "loss": 0.3501, "num_tokens": 550352959.0, "step": 92155 }, { "epoch": 0.9832182902499653, "grad_norm": 0.6160709377680751, "learning_rate": 5.0346833696947055e-06, "loss": 0.4862, "num_tokens": 550377811.0, "step": 92160 }, { "epoch": 0.9832716332561637, "grad_norm": 1.044229587493433, "learning_rate": 5.034463424085018e-06, "loss": 0.3806, "num_tokens": 550396654.0, "step": 92165 }, { "epoch": 0.9833249762623623, "grad_norm": 0.8657368160513875, "learning_rate": 5.034244177556685e-06, "loss": 0.5878, "num_tokens": 550411497.0, "step": 92170 }, { "epoch": 0.9833783192685607, "grad_norm": 0.8768861504421124, "learning_rate": 5.034025630116525e-06, "loss": 0.3921, "num_tokens": 550431138.0, "step": 92175 }, { "epoch": 0.9834316622747592, "grad_norm": 1.2655942073804696, "learning_rate": 5.033807781771342e-06, "loss": 0.4926, "num_tokens": 550455300.0, "step": 92180 }, { "epoch": 0.9834850052809576, "grad_norm": 0.7226162526676322, "learning_rate": 5.033590632527915e-06, "loss": 0.347, "num_tokens": 550475192.0, "step": 92185 }, { "epoch": 0.983538348287156, "grad_norm": 1.7714512296188445, "learning_rate": 5.033374182393e-06, "loss": 0.588, "num_tokens": 550528558.0, "step": 92190 }, { "epoch": 0.9835916912933546, "grad_norm": 1.994637187748094, "learning_rate": 5.03315843137333e-06, "loss": 0.5007, "num_tokens": 550546387.0, "step": 92195 }, { "epoch": 0.983645034299553, "grad_norm": 0.5326195620249364, "learning_rate": 5.032943379475623e-06, "loss": 0.4202, "num_tokens": 550587136.0, "step": 92200 }, { "epoch": 0.9836983773057515, "grad_norm": 0.9386369204635251, "learning_rate": 5.0327290267065705e-06, "loss": 0.5221, "num_tokens": 550607271.0, "step": 92205 }, { "epoch": 0.9837517203119499, "grad_norm": 1.0325952982762816, "learning_rate": 5.032515373072841e-06, "loss": 0.4778, "num_tokens": 550638603.0, "step": 92210 }, { "epoch": 0.9838050633181483, "grad_norm": 0.8904553703864121, "learning_rate": 5.0323024185810826e-06, "loss": 0.4128, "num_tokens": 550669413.0, "step": 92215 }, { "epoch": 0.9838584063243468, "grad_norm": 1.3790663060026869, "learning_rate": 5.0320901632379236e-06, "loss": 0.699, "num_tokens": 550706285.0, "step": 92220 }, { "epoch": 0.9839117493305453, "grad_norm": 1.4808756633968185, "learning_rate": 5.031878607049971e-06, "loss": 0.471, "num_tokens": 550732393.0, "step": 92225 }, { "epoch": 0.9839650923367437, "grad_norm": 0.6261003513205377, "learning_rate": 5.031667750023801e-06, "loss": 0.3883, "num_tokens": 550766835.0, "step": 92230 }, { "epoch": 0.9840184353429422, "grad_norm": 0.8193861866175104, "learning_rate": 5.03145759216598e-06, "loss": 0.4609, "num_tokens": 550802637.0, "step": 92235 }, { "epoch": 0.9840717783491406, "grad_norm": 1.0534055497440957, "learning_rate": 5.031248133483049e-06, "loss": 0.5171, "num_tokens": 550821356.0, "step": 92240 }, { "epoch": 0.9841251213553391, "grad_norm": 1.008134282846704, "learning_rate": 5.031039373981524e-06, "loss": 0.5528, "num_tokens": 550844852.0, "step": 92245 }, { "epoch": 0.9841784643615376, "grad_norm": 0.9260531480249495, "learning_rate": 5.030831313667898e-06, "loss": 0.4489, "num_tokens": 550862285.0, "step": 92250 }, { "epoch": 0.984231807367736, "grad_norm": 1.3455172031639326, "learning_rate": 5.030623952548653e-06, "loss": 0.4242, "num_tokens": 550893110.0, "step": 92255 }, { "epoch": 0.9842851503739345, "grad_norm": 2.6594801211168866, "learning_rate": 5.030417290630235e-06, "loss": 0.5067, "num_tokens": 550918403.0, "step": 92260 }, { "epoch": 0.9843384933801329, "grad_norm": 1.0010758682237166, "learning_rate": 5.030211327919076e-06, "loss": 0.4315, "num_tokens": 550944365.0, "step": 92265 }, { "epoch": 0.9843918363863314, "grad_norm": 1.943045068634711, "learning_rate": 5.030006064421587e-06, "loss": 0.3749, "num_tokens": 550961982.0, "step": 92270 }, { "epoch": 0.9844451793925298, "grad_norm": 0.6357655826111436, "learning_rate": 5.0298015001441545e-06, "loss": 0.4131, "num_tokens": 550995192.0, "step": 92275 }, { "epoch": 0.9844985223987283, "grad_norm": 0.7458855627244375, "learning_rate": 5.029597635093145e-06, "loss": 0.3921, "num_tokens": 551034438.0, "step": 92280 }, { "epoch": 0.9845518654049268, "grad_norm": 1.3511419488898417, "learning_rate": 5.029394469274901e-06, "loss": 0.4694, "num_tokens": 551053429.0, "step": 92285 }, { "epoch": 0.9846052084111252, "grad_norm": 0.6439022552914955, "learning_rate": 5.029192002695746e-06, "loss": 0.4828, "num_tokens": 551102037.0, "step": 92290 }, { "epoch": 0.9846585514173237, "grad_norm": 1.287037022624185, "learning_rate": 5.028990235361977e-06, "loss": 0.4632, "num_tokens": 551132519.0, "step": 92295 }, { "epoch": 0.9847118944235221, "grad_norm": 1.191853140655206, "learning_rate": 5.0287891672798785e-06, "loss": 0.4833, "num_tokens": 551169616.0, "step": 92300 }, { "epoch": 0.9847652374297206, "grad_norm": 2.3246857530124094, "learning_rate": 5.028588798455701e-06, "loss": 0.4438, "num_tokens": 551201446.0, "step": 92305 }, { "epoch": 0.9848185804359191, "grad_norm": 1.2027838841377205, "learning_rate": 5.028389128895683e-06, "loss": 0.489, "num_tokens": 551216361.0, "step": 92310 }, { "epoch": 0.9848719234421175, "grad_norm": 1.0130280219619456, "learning_rate": 5.028190158606038e-06, "loss": 0.4892, "num_tokens": 551254617.0, "step": 92315 }, { "epoch": 0.9849252664483159, "grad_norm": 1.7984170481877688, "learning_rate": 5.0279918875929585e-06, "loss": 0.4878, "num_tokens": 551285985.0, "step": 92320 }, { "epoch": 0.9849786094545144, "grad_norm": 0.9661350196337464, "learning_rate": 5.027794315862609e-06, "loss": 0.4725, "num_tokens": 551318938.0, "step": 92325 }, { "epoch": 0.9850319524607128, "grad_norm": 0.8438060338816614, "learning_rate": 5.027597443421146e-06, "loss": 0.4436, "num_tokens": 551349637.0, "step": 92330 }, { "epoch": 0.9850852954669114, "grad_norm": 0.7916208014421044, "learning_rate": 5.027401270274685e-06, "loss": 0.3619, "num_tokens": 551366880.0, "step": 92335 }, { "epoch": 0.9851386384731098, "grad_norm": 1.4476699772549464, "learning_rate": 5.027205796429341e-06, "loss": 0.4606, "num_tokens": 551411972.0, "step": 92340 }, { "epoch": 0.9851919814793082, "grad_norm": 1.1085431463581112, "learning_rate": 5.02701102189119e-06, "loss": 0.4324, "num_tokens": 551433528.0, "step": 92345 }, { "epoch": 0.9852453244855067, "grad_norm": 0.8847750769808619, "learning_rate": 5.026816946666297e-06, "loss": 0.4481, "num_tokens": 551470790.0, "step": 92350 }, { "epoch": 0.9852986674917051, "grad_norm": 1.0728499202667463, "learning_rate": 5.026623570760698e-06, "loss": 0.4935, "num_tokens": 551498832.0, "step": 92355 }, { "epoch": 0.9853520104979037, "grad_norm": 0.8407016693762235, "learning_rate": 5.026430894180412e-06, "loss": 0.4146, "num_tokens": 551526471.0, "step": 92360 }, { "epoch": 0.9854053535041021, "grad_norm": 0.9436822735850942, "learning_rate": 5.026238916931435e-06, "loss": 0.6371, "num_tokens": 551556274.0, "step": 92365 }, { "epoch": 0.9854586965103005, "grad_norm": 0.7255256800749044, "learning_rate": 5.0260476390197405e-06, "loss": 0.4394, "num_tokens": 551586977.0, "step": 92370 }, { "epoch": 0.985512039516499, "grad_norm": 2.3497837699333495, "learning_rate": 5.025857060451278e-06, "loss": 0.465, "num_tokens": 551627307.0, "step": 92375 }, { "epoch": 0.9855653825226974, "grad_norm": 0.9858483202566032, "learning_rate": 5.025667181231983e-06, "loss": 0.3894, "num_tokens": 551668312.0, "step": 92380 }, { "epoch": 0.985618725528896, "grad_norm": 0.8022798079927527, "learning_rate": 5.025478001367762e-06, "loss": 0.3749, "num_tokens": 551699195.0, "step": 92385 }, { "epoch": 0.9856720685350944, "grad_norm": 0.9457447181931148, "learning_rate": 5.025289520864502e-06, "loss": 0.4629, "num_tokens": 551738107.0, "step": 92390 }, { "epoch": 0.9857254115412928, "grad_norm": 1.1394239310890009, "learning_rate": 5.025101739728066e-06, "loss": 0.4825, "num_tokens": 551767039.0, "step": 92395 }, { "epoch": 0.9857787545474913, "grad_norm": 0.6321285708748795, "learning_rate": 5.024914657964301e-06, "loss": 0.5562, "num_tokens": 551824071.0, "step": 92400 }, { "epoch": 0.9858320975536897, "grad_norm": 0.7812721302048556, "learning_rate": 5.0247282755790255e-06, "loss": 0.4007, "num_tokens": 551864075.0, "step": 92405 }, { "epoch": 0.9858854405598881, "grad_norm": 0.5037760074453613, "learning_rate": 5.024542592578041e-06, "loss": 0.5128, "num_tokens": 551906995.0, "step": 92410 }, { "epoch": 0.9859387835660867, "grad_norm": 1.2959290759511333, "learning_rate": 5.0243576089671245e-06, "loss": 0.6119, "num_tokens": 551941104.0, "step": 92415 }, { "epoch": 0.9859921265722851, "grad_norm": 1.1410174536069437, "learning_rate": 5.0241733247520334e-06, "loss": 0.4152, "num_tokens": 551961607.0, "step": 92420 }, { "epoch": 0.9860454695784836, "grad_norm": 1.7332439829191422, "learning_rate": 5.0239897399385e-06, "loss": 0.5347, "num_tokens": 551989565.0, "step": 92425 }, { "epoch": 0.986098812584682, "grad_norm": 0.7614309703109908, "learning_rate": 5.023806854532241e-06, "loss": 0.4941, "num_tokens": 552022225.0, "step": 92430 }, { "epoch": 0.9861521555908804, "grad_norm": 1.1065207520062108, "learning_rate": 5.023624668538944e-06, "loss": 0.4207, "num_tokens": 552044140.0, "step": 92435 }, { "epoch": 0.986205498597079, "grad_norm": 1.3214966349508832, "learning_rate": 5.023443181964281e-06, "loss": 0.517, "num_tokens": 552079543.0, "step": 92440 }, { "epoch": 0.9862588416032774, "grad_norm": 0.796138300843862, "learning_rate": 5.023262394813898e-06, "loss": 0.4736, "num_tokens": 552103886.0, "step": 92445 }, { "epoch": 0.9863121846094759, "grad_norm": 1.5955135348978915, "learning_rate": 5.02308230709342e-06, "loss": 0.4809, "num_tokens": 552130979.0, "step": 92450 }, { "epoch": 0.9863655276156743, "grad_norm": 1.4909989491159281, "learning_rate": 5.02290291880845e-06, "loss": 0.4666, "num_tokens": 552163699.0, "step": 92455 }, { "epoch": 0.9864188706218727, "grad_norm": 1.533537252152393, "learning_rate": 5.022724229964574e-06, "loss": 0.6466, "num_tokens": 552182518.0, "step": 92460 }, { "epoch": 0.9864722136280712, "grad_norm": 0.9441175206071343, "learning_rate": 5.022546240567351e-06, "loss": 0.4004, "num_tokens": 552205022.0, "step": 92465 }, { "epoch": 0.9865255566342697, "grad_norm": 1.167509623428811, "learning_rate": 5.022368950622318e-06, "loss": 0.4762, "num_tokens": 552239040.0, "step": 92470 }, { "epoch": 0.9865788996404682, "grad_norm": 0.8933793392613193, "learning_rate": 5.0221923601349935e-06, "loss": 0.3934, "num_tokens": 552270104.0, "step": 92475 }, { "epoch": 0.9866322426466666, "grad_norm": 0.6352157770096463, "learning_rate": 5.02201646911087e-06, "loss": 0.4808, "num_tokens": 552306122.0, "step": 92480 }, { "epoch": 0.986685585652865, "grad_norm": 0.8593173754278157, "learning_rate": 5.0218412775554245e-06, "loss": 0.4323, "num_tokens": 552338010.0, "step": 92485 }, { "epoch": 0.9867389286590635, "grad_norm": 0.8529063551077927, "learning_rate": 5.021666785474106e-06, "loss": 0.3783, "num_tokens": 552376397.0, "step": 92490 }, { "epoch": 0.986792271665262, "grad_norm": 0.7713574366495359, "learning_rate": 5.021492992872346e-06, "loss": 0.4353, "num_tokens": 552404642.0, "step": 92495 }, { "epoch": 0.9868456146714604, "grad_norm": 0.9852514584465953, "learning_rate": 5.021319899755552e-06, "loss": 0.4182, "num_tokens": 552430009.0, "step": 92500 }, { "epoch": 0.9868989576776589, "grad_norm": 1.5279378614811674, "learning_rate": 5.021147506129109e-06, "loss": 0.4708, "num_tokens": 552459793.0, "step": 92505 }, { "epoch": 0.9869523006838573, "grad_norm": 0.8352841122221637, "learning_rate": 5.020975811998384e-06, "loss": 0.4262, "num_tokens": 552479377.0, "step": 92510 }, { "epoch": 0.9870056436900558, "grad_norm": 0.5746821508157754, "learning_rate": 5.020804817368718e-06, "loss": 0.3607, "num_tokens": 552512483.0, "step": 92515 }, { "epoch": 0.9870589866962542, "grad_norm": 1.078152439413842, "learning_rate": 5.020634522245432e-06, "loss": 0.3921, "num_tokens": 552537935.0, "step": 92520 }, { "epoch": 0.9871123297024527, "grad_norm": 1.243902869440593, "learning_rate": 5.020464926633826e-06, "loss": 0.516, "num_tokens": 552561625.0, "step": 92525 }, { "epoch": 0.9871656727086512, "grad_norm": 0.811846799845624, "learning_rate": 5.020296030539179e-06, "loss": 0.4595, "num_tokens": 552591302.0, "step": 92530 }, { "epoch": 0.9872190157148496, "grad_norm": 1.3434335449921488, "learning_rate": 5.020127833966743e-06, "loss": 0.3396, "num_tokens": 552606401.0, "step": 92535 }, { "epoch": 0.9872723587210481, "grad_norm": 1.5281603728370343, "learning_rate": 5.019960336921755e-06, "loss": 0.3744, "num_tokens": 552625307.0, "step": 92540 }, { "epoch": 0.9873257017272465, "grad_norm": 0.6846332270240428, "learning_rate": 5.019793539409425e-06, "loss": 0.4586, "num_tokens": 552683205.0, "step": 92545 }, { "epoch": 0.987379044733445, "grad_norm": 0.7108372354133818, "learning_rate": 5.019627441434946e-06, "loss": 0.425, "num_tokens": 552708580.0, "step": 92550 }, { "epoch": 0.9874323877396435, "grad_norm": 0.4872015183522706, "learning_rate": 5.019462043003483e-06, "loss": 0.3908, "num_tokens": 552737773.0, "step": 92555 }, { "epoch": 0.9874857307458419, "grad_norm": 0.6770445161280457, "learning_rate": 5.0192973441201856e-06, "loss": 0.4504, "num_tokens": 552776931.0, "step": 92560 }, { "epoch": 0.9875390737520404, "grad_norm": 0.8963124715440142, "learning_rate": 5.019133344790177e-06, "loss": 0.4033, "num_tokens": 552812413.0, "step": 92565 }, { "epoch": 0.9875924167582388, "grad_norm": 0.9747766433966175, "learning_rate": 5.018970045018565e-06, "loss": 0.4313, "num_tokens": 552845889.0, "step": 92570 }, { "epoch": 0.9876457597644372, "grad_norm": 0.995542856303499, "learning_rate": 5.018807444810425e-06, "loss": 0.4493, "num_tokens": 552873847.0, "step": 92575 }, { "epoch": 0.9876991027706358, "grad_norm": 1.8819579687442256, "learning_rate": 5.01864554417082e-06, "loss": 0.5484, "num_tokens": 552889717.0, "step": 92580 }, { "epoch": 0.9877524457768342, "grad_norm": 0.9556995244983217, "learning_rate": 5.018484343104789e-06, "loss": 0.5342, "num_tokens": 552915857.0, "step": 92585 }, { "epoch": 0.9878057887830326, "grad_norm": 0.769216361567085, "learning_rate": 5.018323841617346e-06, "loss": 0.3973, "num_tokens": 552960236.0, "step": 92590 }, { "epoch": 0.9878591317892311, "grad_norm": 2.0877359504170845, "learning_rate": 5.018164039713484e-06, "loss": 0.5786, "num_tokens": 552990344.0, "step": 92595 }, { "epoch": 0.9879124747954295, "grad_norm": 0.99646711566646, "learning_rate": 5.018004937398181e-06, "loss": 0.3912, "num_tokens": 553017905.0, "step": 92600 }, { "epoch": 0.9879658178016281, "grad_norm": 1.450788933919557, "learning_rate": 5.017846534676385e-06, "loss": 0.3363, "num_tokens": 553033496.0, "step": 92605 }, { "epoch": 0.9880191608078265, "grad_norm": 1.1310633566793344, "learning_rate": 5.0176888315530245e-06, "loss": 0.4198, "num_tokens": 553057249.0, "step": 92610 }, { "epoch": 0.9880725038140249, "grad_norm": 0.8619789833292373, "learning_rate": 5.017531828033007e-06, "loss": 0.5013, "num_tokens": 553101751.0, "step": 92615 }, { "epoch": 0.9881258468202234, "grad_norm": 0.9571659644451784, "learning_rate": 5.017375524121221e-06, "loss": 0.4918, "num_tokens": 553128591.0, "step": 92620 }, { "epoch": 0.9881791898264218, "grad_norm": 1.515644403959888, "learning_rate": 5.017219919822525e-06, "loss": 0.4916, "num_tokens": 553169338.0, "step": 92625 }, { "epoch": 0.9882325328326204, "grad_norm": 3.701394973269952, "learning_rate": 5.017065015141765e-06, "loss": 0.5, "num_tokens": 553199905.0, "step": 92630 }, { "epoch": 0.9882858758388188, "grad_norm": 0.8433048833600174, "learning_rate": 5.0169108100837625e-06, "loss": 0.4911, "num_tokens": 553237391.0, "step": 92635 }, { "epoch": 0.9883392188450172, "grad_norm": 0.7997019276363678, "learning_rate": 5.01675730465331e-06, "loss": 0.5149, "num_tokens": 553287217.0, "step": 92640 }, { "epoch": 0.9883925618512157, "grad_norm": 0.7958427003378565, "learning_rate": 5.016604498855193e-06, "loss": 0.4384, "num_tokens": 553301416.0, "step": 92645 }, { "epoch": 0.9884459048574141, "grad_norm": 0.8974679653624087, "learning_rate": 5.016452392694158e-06, "loss": 0.5108, "num_tokens": 553318799.0, "step": 92650 }, { "epoch": 0.9884992478636127, "grad_norm": 1.3810357461347131, "learning_rate": 5.016300986174944e-06, "loss": 0.5054, "num_tokens": 553347941.0, "step": 92655 }, { "epoch": 0.9885525908698111, "grad_norm": 0.8481266294455029, "learning_rate": 5.01615027930226e-06, "loss": 0.4181, "num_tokens": 553381763.0, "step": 92660 }, { "epoch": 0.9886059338760095, "grad_norm": 1.095104627102094, "learning_rate": 5.016000272080796e-06, "loss": 0.4055, "num_tokens": 553406154.0, "step": 92665 }, { "epoch": 0.988659276882208, "grad_norm": 0.737010187527124, "learning_rate": 5.01585096451522e-06, "loss": 0.3491, "num_tokens": 553433331.0, "step": 92670 }, { "epoch": 0.9887126198884064, "grad_norm": 0.7840587644349108, "learning_rate": 5.015702356610178e-06, "loss": 0.3858, "num_tokens": 553458427.0, "step": 92675 }, { "epoch": 0.9887659628946048, "grad_norm": 0.6460350099762816, "learning_rate": 5.015554448370295e-06, "loss": 0.3887, "num_tokens": 553480097.0, "step": 92680 }, { "epoch": 0.9888193059008034, "grad_norm": 0.8350132263715057, "learning_rate": 5.015407239800173e-06, "loss": 0.4935, "num_tokens": 553504886.0, "step": 92685 }, { "epoch": 0.9888726489070018, "grad_norm": 0.8001822411349151, "learning_rate": 5.015260730904394e-06, "loss": 0.5568, "num_tokens": 553537856.0, "step": 92690 }, { "epoch": 0.9889259919132003, "grad_norm": 0.8033839475514756, "learning_rate": 5.015114921687515e-06, "loss": 0.3983, "num_tokens": 553575247.0, "step": 92695 }, { "epoch": 0.9889793349193987, "grad_norm": 0.7606710547774591, "learning_rate": 5.014969812154076e-06, "loss": 0.5268, "num_tokens": 553631165.0, "step": 92700 }, { "epoch": 0.9890326779255971, "grad_norm": 1.4137499334552242, "learning_rate": 5.01482540230859e-06, "loss": 0.3768, "num_tokens": 553657689.0, "step": 92705 }, { "epoch": 0.9890860209317957, "grad_norm": 2.109024490191963, "learning_rate": 5.014681692155549e-06, "loss": 0.4561, "num_tokens": 553680906.0, "step": 92710 }, { "epoch": 0.9891393639379941, "grad_norm": 1.092881128578439, "learning_rate": 5.0145386816994316e-06, "loss": 0.4172, "num_tokens": 553702297.0, "step": 92715 }, { "epoch": 0.9891927069441926, "grad_norm": 1.0251301255237317, "learning_rate": 5.0143963709446806e-06, "loss": 0.3967, "num_tokens": 553736993.0, "step": 92720 }, { "epoch": 0.989246049950391, "grad_norm": 0.8286132884029639, "learning_rate": 5.014254759895729e-06, "loss": 0.5242, "num_tokens": 553775821.0, "step": 92725 }, { "epoch": 0.9892993929565894, "grad_norm": 0.7162038400234809, "learning_rate": 5.014113848556984e-06, "loss": 0.545, "num_tokens": 553812902.0, "step": 92730 }, { "epoch": 0.9893527359627879, "grad_norm": 0.8981284456849298, "learning_rate": 5.013973636932826e-06, "loss": 0.4812, "num_tokens": 553850490.0, "step": 92735 }, { "epoch": 0.9894060789689864, "grad_norm": 0.48096891376663975, "learning_rate": 5.013834125027622e-06, "loss": 0.4495, "num_tokens": 553888061.0, "step": 92740 }, { "epoch": 0.9894594219751849, "grad_norm": 1.6692249662292167, "learning_rate": 5.013695312845713e-06, "loss": 0.4645, "num_tokens": 553922555.0, "step": 92745 }, { "epoch": 0.9895127649813833, "grad_norm": 1.0452461926102965, "learning_rate": 5.013557200391418e-06, "loss": 0.4344, "num_tokens": 553956763.0, "step": 92750 }, { "epoch": 0.9895661079875817, "grad_norm": 0.8091059486089133, "learning_rate": 5.0134197876690315e-06, "loss": 0.48, "num_tokens": 553973495.0, "step": 92755 }, { "epoch": 0.9896194509937802, "grad_norm": 0.6403908946323431, "learning_rate": 5.013283074682835e-06, "loss": 0.3795, "num_tokens": 554012076.0, "step": 92760 }, { "epoch": 0.9896727939999787, "grad_norm": 0.4796871598623681, "learning_rate": 5.013147061437079e-06, "loss": 0.4984, "num_tokens": 554056598.0, "step": 92765 }, { "epoch": 0.9897261370061771, "grad_norm": 0.6400079837797836, "learning_rate": 5.013011747935997e-06, "loss": 0.3663, "num_tokens": 554081649.0, "step": 92770 }, { "epoch": 0.9897794800123756, "grad_norm": 1.098550459098457, "learning_rate": 5.012877134183802e-06, "loss": 0.3741, "num_tokens": 554105491.0, "step": 92775 }, { "epoch": 0.989832823018574, "grad_norm": 0.6149847651534435, "learning_rate": 5.012743220184678e-06, "loss": 0.4835, "num_tokens": 554127461.0, "step": 92780 }, { "epoch": 0.9898861660247725, "grad_norm": 2.701725633293595, "learning_rate": 5.012610005942795e-06, "loss": 0.3698, "num_tokens": 554141860.0, "step": 92785 }, { "epoch": 0.9899395090309709, "grad_norm": 0.8709891285536829, "learning_rate": 5.012477491462302e-06, "loss": 0.4501, "num_tokens": 554178071.0, "step": 92790 }, { "epoch": 0.9899928520371694, "grad_norm": 1.0357392235049192, "learning_rate": 5.012345676747313e-06, "loss": 0.4004, "num_tokens": 554195564.0, "step": 92795 }, { "epoch": 0.9900461950433679, "grad_norm": 0.9088976844521266, "learning_rate": 5.012214561801939e-06, "loss": 0.4018, "num_tokens": 554224024.0, "step": 92800 }, { "epoch": 0.9900995380495663, "grad_norm": 0.690863212394855, "learning_rate": 5.012084146630256e-06, "loss": 0.4655, "num_tokens": 554266136.0, "step": 92805 }, { "epoch": 0.9901528810557648, "grad_norm": 0.8703836578933565, "learning_rate": 5.011954431236325e-06, "loss": 0.4642, "num_tokens": 554292083.0, "step": 92810 }, { "epoch": 0.9902062240619632, "grad_norm": 1.1785272305689063, "learning_rate": 5.011825415624176e-06, "loss": 0.3202, "num_tokens": 554310466.0, "step": 92815 }, { "epoch": 0.9902595670681617, "grad_norm": 1.0664009910474768, "learning_rate": 5.011697099797831e-06, "loss": 0.6051, "num_tokens": 554343552.0, "step": 92820 }, { "epoch": 0.9903129100743602, "grad_norm": 1.034474106237413, "learning_rate": 5.0115694837612784e-06, "loss": 0.3716, "num_tokens": 554371455.0, "step": 92825 }, { "epoch": 0.9903662530805586, "grad_norm": 0.9521302540760268, "learning_rate": 5.0114425675184925e-06, "loss": 0.6234, "num_tokens": 554403526.0, "step": 92830 }, { "epoch": 0.9904195960867571, "grad_norm": 0.7447081713207339, "learning_rate": 5.0113163510734194e-06, "loss": 0.4446, "num_tokens": 554431257.0, "step": 92835 }, { "epoch": 0.9904729390929555, "grad_norm": 1.1972591957546959, "learning_rate": 5.01119083442999e-06, "loss": 0.378, "num_tokens": 554452845.0, "step": 92840 }, { "epoch": 0.9905262820991539, "grad_norm": 1.6870364125853217, "learning_rate": 5.011066017592108e-06, "loss": 0.4374, "num_tokens": 554484045.0, "step": 92845 }, { "epoch": 0.9905796251053525, "grad_norm": 0.671453317588732, "learning_rate": 5.010941900563658e-06, "loss": 0.464, "num_tokens": 554513646.0, "step": 92850 }, { "epoch": 0.9906329681115509, "grad_norm": 0.7484255865395254, "learning_rate": 5.0108184833485005e-06, "loss": 0.4009, "num_tokens": 554547068.0, "step": 92855 }, { "epoch": 0.9906863111177493, "grad_norm": 0.9866298614766604, "learning_rate": 5.010695765950479e-06, "loss": 0.474, "num_tokens": 554582438.0, "step": 92860 }, { "epoch": 0.9907396541239478, "grad_norm": 1.180635654685468, "learning_rate": 5.010573748373412e-06, "loss": 0.4847, "num_tokens": 554595250.0, "step": 92865 }, { "epoch": 0.9907929971301462, "grad_norm": 0.7526797206025546, "learning_rate": 5.010452430621093e-06, "loss": 0.3293, "num_tokens": 554615967.0, "step": 92870 }, { "epoch": 0.9908463401363448, "grad_norm": 1.1204230418184595, "learning_rate": 5.010331812697302e-06, "loss": 0.4752, "num_tokens": 554641185.0, "step": 92875 }, { "epoch": 0.9908996831425432, "grad_norm": 1.0796234314600863, "learning_rate": 5.01021189460579e-06, "loss": 0.3311, "num_tokens": 554664197.0, "step": 92880 }, { "epoch": 0.9909530261487416, "grad_norm": 0.7651063275006993, "learning_rate": 5.010092676350288e-06, "loss": 0.3861, "num_tokens": 554686887.0, "step": 92885 }, { "epoch": 0.9910063691549401, "grad_norm": 0.8101185323778339, "learning_rate": 5.009974157934504e-06, "loss": 0.343, "num_tokens": 554705112.0, "step": 92890 }, { "epoch": 0.9910597121611385, "grad_norm": 0.8821548220069483, "learning_rate": 5.0098563393621305e-06, "loss": 0.5268, "num_tokens": 554759570.0, "step": 92895 }, { "epoch": 0.991113055167337, "grad_norm": 0.5871644408323095, "learning_rate": 5.00973922063683e-06, "loss": 0.4825, "num_tokens": 554790947.0, "step": 92900 }, { "epoch": 0.9911663981735355, "grad_norm": 1.1939519529715281, "learning_rate": 5.009622801762252e-06, "loss": 0.4625, "num_tokens": 554819387.0, "step": 92905 }, { "epoch": 0.9912197411797339, "grad_norm": 0.8101070123609769, "learning_rate": 5.009507082742014e-06, "loss": 0.4138, "num_tokens": 554847202.0, "step": 92910 }, { "epoch": 0.9912730841859324, "grad_norm": 1.2076831431899566, "learning_rate": 5.009392063579716e-06, "loss": 0.4369, "num_tokens": 554866790.0, "step": 92915 }, { "epoch": 0.9913264271921308, "grad_norm": 0.8721037310518651, "learning_rate": 5.009277744278943e-06, "loss": 0.4789, "num_tokens": 554907165.0, "step": 92920 }, { "epoch": 0.9913797701983293, "grad_norm": 0.6865156297029682, "learning_rate": 5.009164124843248e-06, "loss": 0.4467, "num_tokens": 554926882.0, "step": 92925 }, { "epoch": 0.9914331132045278, "grad_norm": 0.6881373810853756, "learning_rate": 5.009051205276169e-06, "loss": 0.4648, "num_tokens": 554963987.0, "step": 92930 }, { "epoch": 0.9914864562107262, "grad_norm": 0.8664626706887723, "learning_rate": 5.008938985581217e-06, "loss": 0.4883, "num_tokens": 554999778.0, "step": 92935 }, { "epoch": 0.9915397992169247, "grad_norm": 0.5939582349323065, "learning_rate": 5.008827465761888e-06, "loss": 0.3372, "num_tokens": 555029027.0, "step": 92940 }, { "epoch": 0.9915931422231231, "grad_norm": 0.956887365484924, "learning_rate": 5.008716645821648e-06, "loss": 0.4164, "num_tokens": 555048104.0, "step": 92945 }, { "epoch": 0.9916464852293215, "grad_norm": 0.9950080716025597, "learning_rate": 5.0086065257639505e-06, "loss": 0.555, "num_tokens": 555083923.0, "step": 92950 }, { "epoch": 0.99169982823552, "grad_norm": 1.034965987547875, "learning_rate": 5.008497105592218e-06, "loss": 0.3502, "num_tokens": 555096215.0, "step": 92955 }, { "epoch": 0.9917531712417185, "grad_norm": 0.7978492215765358, "learning_rate": 5.008388385309856e-06, "loss": 0.51, "num_tokens": 555125933.0, "step": 92960 }, { "epoch": 0.991806514247917, "grad_norm": 0.8852521261081889, "learning_rate": 5.008280364920248e-06, "loss": 0.4041, "num_tokens": 555159671.0, "step": 92965 }, { "epoch": 0.9918598572541154, "grad_norm": 0.7622356047116652, "learning_rate": 5.008173044426756e-06, "loss": 0.4793, "num_tokens": 555185613.0, "step": 92970 }, { "epoch": 0.9919132002603138, "grad_norm": 0.7327355803687005, "learning_rate": 5.00806642383272e-06, "loss": 0.3535, "num_tokens": 555214704.0, "step": 92975 }, { "epoch": 0.9919665432665123, "grad_norm": 1.236914526462091, "learning_rate": 5.007960503141457e-06, "loss": 0.4553, "num_tokens": 555262711.0, "step": 92980 }, { "epoch": 0.9920198862727108, "grad_norm": 1.1316354745120052, "learning_rate": 5.007855282356264e-06, "loss": 0.5697, "num_tokens": 555298567.0, "step": 92985 }, { "epoch": 0.9920732292789093, "grad_norm": 0.7261676698302714, "learning_rate": 5.007750761480413e-06, "loss": 0.4331, "num_tokens": 555334726.0, "step": 92990 }, { "epoch": 0.9921265722851077, "grad_norm": 1.5839588502502495, "learning_rate": 5.007646940517158e-06, "loss": 0.4737, "num_tokens": 555355168.0, "step": 92995 }, { "epoch": 0.9921799152913061, "grad_norm": 0.7471579139577144, "learning_rate": 5.00754381946973e-06, "loss": 0.3973, "num_tokens": 555383556.0, "step": 93000 }, { "epoch": 0.9922332582975046, "grad_norm": 0.6076324471170317, "learning_rate": 5.007441398341337e-06, "loss": 0.4464, "num_tokens": 555410606.0, "step": 93005 }, { "epoch": 0.992286601303703, "grad_norm": 2.9417026561504875, "learning_rate": 5.007339677135169e-06, "loss": 0.6335, "num_tokens": 555443982.0, "step": 93010 }, { "epoch": 0.9923399443099016, "grad_norm": 0.8515967734178653, "learning_rate": 5.007238655854385e-06, "loss": 0.4346, "num_tokens": 555467860.0, "step": 93015 }, { "epoch": 0.9923932873161, "grad_norm": 1.0186341611245713, "learning_rate": 5.007138334502134e-06, "loss": 0.3765, "num_tokens": 555483747.0, "step": 93020 }, { "epoch": 0.9924466303222984, "grad_norm": 0.9261551891270012, "learning_rate": 5.0070387130815394e-06, "loss": 0.4882, "num_tokens": 555510374.0, "step": 93025 }, { "epoch": 0.9924999733284969, "grad_norm": 1.0153638784955512, "learning_rate": 5.006939791595694e-06, "loss": 0.4704, "num_tokens": 555536993.0, "step": 93030 }, { "epoch": 0.9925533163346953, "grad_norm": 1.4063838696932776, "learning_rate": 5.006841570047682e-06, "loss": 0.5889, "num_tokens": 555573231.0, "step": 93035 }, { "epoch": 0.9926066593408938, "grad_norm": 1.3234719062826736, "learning_rate": 5.006744048440559e-06, "loss": 0.4104, "num_tokens": 555596651.0, "step": 93040 }, { "epoch": 0.9926600023470923, "grad_norm": 0.9096417421065112, "learning_rate": 5.006647226777357e-06, "loss": 0.4374, "num_tokens": 555616109.0, "step": 93045 }, { "epoch": 0.9927133453532907, "grad_norm": 1.5238717013714478, "learning_rate": 5.0065511050610936e-06, "loss": 0.4358, "num_tokens": 555644992.0, "step": 93050 }, { "epoch": 0.9927666883594892, "grad_norm": 0.7345827490064111, "learning_rate": 5.006455683294753e-06, "loss": 0.4817, "num_tokens": 555681376.0, "step": 93055 }, { "epoch": 0.9928200313656876, "grad_norm": 1.2713043025375692, "learning_rate": 5.00636096148131e-06, "loss": 0.4195, "num_tokens": 555699413.0, "step": 93060 }, { "epoch": 0.992873374371886, "grad_norm": 1.2864909300184595, "learning_rate": 5.006266939623713e-06, "loss": 0.5583, "num_tokens": 555734499.0, "step": 93065 }, { "epoch": 0.9929267173780846, "grad_norm": 0.8444526444185093, "learning_rate": 5.006173617724881e-06, "loss": 0.4917, "num_tokens": 555774203.0, "step": 93070 }, { "epoch": 0.992980060384283, "grad_norm": 1.1832239951862464, "learning_rate": 5.006080995787726e-06, "loss": 0.5785, "num_tokens": 555804678.0, "step": 93075 }, { "epoch": 0.9930334033904815, "grad_norm": 1.3685547231416537, "learning_rate": 5.005989073815126e-06, "loss": 0.4542, "num_tokens": 555823815.0, "step": 93080 }, { "epoch": 0.9930867463966799, "grad_norm": 0.7072441602597734, "learning_rate": 5.005897851809941e-06, "loss": 0.447, "num_tokens": 555853179.0, "step": 93085 }, { "epoch": 0.9931400894028783, "grad_norm": 0.7265240445640075, "learning_rate": 5.005807329775011e-06, "loss": 0.4225, "num_tokens": 555878747.0, "step": 93090 }, { "epoch": 0.9931934324090769, "grad_norm": 1.1476545873279276, "learning_rate": 5.005717507713152e-06, "loss": 0.4501, "num_tokens": 555900660.0, "step": 93095 }, { "epoch": 0.9932467754152753, "grad_norm": 0.5697590721300916, "learning_rate": 5.005628385627161e-06, "loss": 0.4541, "num_tokens": 555926632.0, "step": 93100 }, { "epoch": 0.9933001184214738, "grad_norm": 1.2398925475819849, "learning_rate": 5.005539963519808e-06, "loss": 0.5424, "num_tokens": 555960373.0, "step": 93105 }, { "epoch": 0.9933534614276722, "grad_norm": 1.1652893920698477, "learning_rate": 5.005452241393846e-06, "loss": 0.4349, "num_tokens": 555989094.0, "step": 93110 }, { "epoch": 0.9934068044338706, "grad_norm": 0.552029350593639, "learning_rate": 5.005365219252007e-06, "loss": 0.3635, "num_tokens": 556018366.0, "step": 93115 }, { "epoch": 0.9934601474400692, "grad_norm": 0.7467319946446854, "learning_rate": 5.005278897096997e-06, "loss": 0.4627, "num_tokens": 556055771.0, "step": 93120 }, { "epoch": 0.9935134904462676, "grad_norm": 1.6215003951500007, "learning_rate": 5.005193274931502e-06, "loss": 0.5352, "num_tokens": 556084393.0, "step": 93125 }, { "epoch": 0.993566833452466, "grad_norm": 0.910917817359636, "learning_rate": 5.005108352758186e-06, "loss": 0.5219, "num_tokens": 556117294.0, "step": 93130 }, { "epoch": 0.9936201764586645, "grad_norm": 1.2631564950819336, "learning_rate": 5.005024130579693e-06, "loss": 0.4165, "num_tokens": 556145449.0, "step": 93135 }, { "epoch": 0.9936735194648629, "grad_norm": 0.5570357852637425, "learning_rate": 5.004940608398642e-06, "loss": 0.4867, "num_tokens": 556182400.0, "step": 93140 }, { "epoch": 0.9937268624710615, "grad_norm": 1.5904721234868544, "learning_rate": 5.004857786217633e-06, "loss": 0.6093, "num_tokens": 556216724.0, "step": 93145 }, { "epoch": 0.9937802054772599, "grad_norm": 0.7163407451589706, "learning_rate": 5.004775664039245e-06, "loss": 0.3856, "num_tokens": 556244333.0, "step": 93150 }, { "epoch": 0.9938335484834583, "grad_norm": 0.8972311083933892, "learning_rate": 5.004694241866031e-06, "loss": 0.4706, "num_tokens": 556269873.0, "step": 93155 }, { "epoch": 0.9938868914896568, "grad_norm": 0.8531632359858498, "learning_rate": 5.004613519700525e-06, "loss": 0.5052, "num_tokens": 556294330.0, "step": 93160 }, { "epoch": 0.9939402344958552, "grad_norm": 0.7635487659293895, "learning_rate": 5.00453349754524e-06, "loss": 0.4336, "num_tokens": 556332835.0, "step": 93165 }, { "epoch": 0.9939935775020537, "grad_norm": 0.9290048859113821, "learning_rate": 5.004454175402666e-06, "loss": 0.42, "num_tokens": 556358175.0, "step": 93170 }, { "epoch": 0.9940469205082522, "grad_norm": 0.5448547022815581, "learning_rate": 5.00437555327527e-06, "loss": 0.5041, "num_tokens": 556404074.0, "step": 93175 }, { "epoch": 0.9941002635144506, "grad_norm": 1.0780818743300733, "learning_rate": 5.0042976311655e-06, "loss": 0.4972, "num_tokens": 556427906.0, "step": 93180 }, { "epoch": 0.9941536065206491, "grad_norm": 1.9416556104624558, "learning_rate": 5.00422040907578e-06, "loss": 0.5255, "num_tokens": 556454486.0, "step": 93185 }, { "epoch": 0.9942069495268475, "grad_norm": 1.1409128522468173, "learning_rate": 5.004143887008512e-06, "loss": 0.3635, "num_tokens": 556478045.0, "step": 93190 }, { "epoch": 0.994260292533046, "grad_norm": 1.2275415252886972, "learning_rate": 5.00406806496608e-06, "loss": 0.3716, "num_tokens": 556507631.0, "step": 93195 }, { "epoch": 0.9943136355392445, "grad_norm": 1.2149875379008015, "learning_rate": 5.003992942950842e-06, "loss": 0.3959, "num_tokens": 556531567.0, "step": 93200 }, { "epoch": 0.9943669785454429, "grad_norm": 0.8213461817254784, "learning_rate": 5.0039185209651355e-06, "loss": 0.5631, "num_tokens": 556559510.0, "step": 93205 }, { "epoch": 0.9944203215516414, "grad_norm": 0.8540053201561608, "learning_rate": 5.003844799011274e-06, "loss": 0.5309, "num_tokens": 556593876.0, "step": 93210 }, { "epoch": 0.9944736645578398, "grad_norm": 0.7738634017832282, "learning_rate": 5.003771777091555e-06, "loss": 0.5602, "num_tokens": 556637784.0, "step": 93215 }, { "epoch": 0.9945270075640382, "grad_norm": 1.2970051855600486, "learning_rate": 5.003699455208251e-06, "loss": 0.434, "num_tokens": 556658992.0, "step": 93220 }, { "epoch": 0.9945803505702367, "grad_norm": 0.8153755806897194, "learning_rate": 5.00362783336361e-06, "loss": 0.4905, "num_tokens": 556693008.0, "step": 93225 }, { "epoch": 0.9946336935764352, "grad_norm": 0.7885280743564629, "learning_rate": 5.003556911559863e-06, "loss": 0.4504, "num_tokens": 556724432.0, "step": 93230 }, { "epoch": 0.9946870365826337, "grad_norm": 1.1231325213089647, "learning_rate": 5.003486689799217e-06, "loss": 0.3122, "num_tokens": 556737825.0, "step": 93235 }, { "epoch": 0.9947403795888321, "grad_norm": 0.9887137042326576, "learning_rate": 5.003417168083855e-06, "loss": 0.4837, "num_tokens": 556751112.0, "step": 93240 }, { "epoch": 0.9947937225950305, "grad_norm": 1.678118071050048, "learning_rate": 5.0033483464159405e-06, "loss": 0.5132, "num_tokens": 556777450.0, "step": 93245 }, { "epoch": 0.994847065601229, "grad_norm": 0.7022131347492272, "learning_rate": 5.0032802247976165e-06, "loss": 0.3729, "num_tokens": 556831931.0, "step": 93250 }, { "epoch": 0.9949004086074275, "grad_norm": 0.8502419297099068, "learning_rate": 5.003212803231002e-06, "loss": 0.4202, "num_tokens": 556851274.0, "step": 93255 }, { "epoch": 0.994953751613626, "grad_norm": 1.1622774930000521, "learning_rate": 5.003146081718195e-06, "loss": 0.3831, "num_tokens": 556876032.0, "step": 93260 }, { "epoch": 0.9950070946198244, "grad_norm": 0.8520811730317551, "learning_rate": 5.003080060261273e-06, "loss": 0.4538, "num_tokens": 556905814.0, "step": 93265 }, { "epoch": 0.9950604376260228, "grad_norm": 1.3678158782771663, "learning_rate": 5.0030147388622915e-06, "loss": 0.3818, "num_tokens": 556929146.0, "step": 93270 }, { "epoch": 0.9951137806322213, "grad_norm": 0.9719862620788645, "learning_rate": 5.002950117523276e-06, "loss": 0.3616, "num_tokens": 556948519.0, "step": 93275 }, { "epoch": 0.9951671236384197, "grad_norm": 0.8883698262424939, "learning_rate": 5.002886196246246e-06, "loss": 0.5148, "num_tokens": 556984461.0, "step": 93280 }, { "epoch": 0.9952204666446183, "grad_norm": 0.9995430208846716, "learning_rate": 5.002822975033187e-06, "loss": 0.4537, "num_tokens": 557015590.0, "step": 93285 }, { "epoch": 0.9952738096508167, "grad_norm": 0.8237097920622662, "learning_rate": 5.002760453886065e-06, "loss": 0.3743, "num_tokens": 557049058.0, "step": 93290 }, { "epoch": 0.9953271526570151, "grad_norm": 0.9160191992257964, "learning_rate": 5.002698632806829e-06, "loss": 0.3874, "num_tokens": 557098048.0, "step": 93295 }, { "epoch": 0.9953804956632136, "grad_norm": 1.357623883224898, "learning_rate": 5.002637511797401e-06, "loss": 0.4968, "num_tokens": 557122143.0, "step": 93300 }, { "epoch": 0.995433838669412, "grad_norm": 1.1884223991638017, "learning_rate": 5.00257709085968e-06, "loss": 0.4158, "num_tokens": 557154709.0, "step": 93305 }, { "epoch": 0.9954871816756105, "grad_norm": 0.7251025320967898, "learning_rate": 5.0025173699955515e-06, "loss": 0.3939, "num_tokens": 557187420.0, "step": 93310 }, { "epoch": 0.995540524681809, "grad_norm": 5.073148800897098, "learning_rate": 5.0024583492068695e-06, "loss": 0.5672, "num_tokens": 557209724.0, "step": 93315 }, { "epoch": 0.9955938676880074, "grad_norm": 0.5991811405393828, "learning_rate": 5.002400028495475e-06, "loss": 0.4097, "num_tokens": 557261255.0, "step": 93320 }, { "epoch": 0.9956472106942059, "grad_norm": 1.9712108521038125, "learning_rate": 5.00234240786318e-06, "loss": 0.5427, "num_tokens": 557291221.0, "step": 93325 }, { "epoch": 0.9957005537004043, "grad_norm": 0.6451236360348866, "learning_rate": 5.002285487311775e-06, "loss": 0.4684, "num_tokens": 557324078.0, "step": 93330 }, { "epoch": 0.9957538967066027, "grad_norm": 0.7041697446270452, "learning_rate": 5.0022292668430335e-06, "loss": 0.4157, "num_tokens": 557363982.0, "step": 93335 }, { "epoch": 0.9958072397128013, "grad_norm": 0.6586394625845062, "learning_rate": 5.002173746458709e-06, "loss": 0.5086, "num_tokens": 557395359.0, "step": 93340 }, { "epoch": 0.9958605827189997, "grad_norm": 1.0089766328385035, "learning_rate": 5.002118926160523e-06, "loss": 0.5767, "num_tokens": 557418915.0, "step": 93345 }, { "epoch": 0.9959139257251982, "grad_norm": 1.041942328232711, "learning_rate": 5.0020648059501855e-06, "loss": 0.4998, "num_tokens": 557451286.0, "step": 93350 }, { "epoch": 0.9959672687313966, "grad_norm": 1.0959834830879385, "learning_rate": 5.002011385829378e-06, "loss": 0.3758, "num_tokens": 557471100.0, "step": 93355 }, { "epoch": 0.996020611737595, "grad_norm": 1.564503533250478, "learning_rate": 5.001958665799766e-06, "loss": 0.4481, "num_tokens": 557506305.0, "step": 93360 }, { "epoch": 0.9960739547437936, "grad_norm": 0.6401354880584049, "learning_rate": 5.001906645862985e-06, "loss": 0.4494, "num_tokens": 557540190.0, "step": 93365 }, { "epoch": 0.996127297749992, "grad_norm": 0.6341323486535719, "learning_rate": 5.001855326020659e-06, "loss": 0.5369, "num_tokens": 557582107.0, "step": 93370 }, { "epoch": 0.9961806407561905, "grad_norm": 0.9249683890136438, "learning_rate": 5.001804706274382e-06, "loss": 0.5327, "num_tokens": 557622688.0, "step": 93375 }, { "epoch": 0.9962339837623889, "grad_norm": 2.251558816924975, "learning_rate": 5.00175478662573e-06, "loss": 0.4944, "num_tokens": 557657900.0, "step": 93380 }, { "epoch": 0.9962873267685873, "grad_norm": 0.4892226388557988, "learning_rate": 5.001705567076256e-06, "loss": 0.336, "num_tokens": 557690441.0, "step": 93385 }, { "epoch": 0.9963406697747859, "grad_norm": 0.9585978940058588, "learning_rate": 5.001657047627493e-06, "loss": 0.3906, "num_tokens": 557710470.0, "step": 93390 }, { "epoch": 0.9963940127809843, "grad_norm": 0.8046612575839125, "learning_rate": 5.00160922828095e-06, "loss": 0.4975, "num_tokens": 557747298.0, "step": 93395 }, { "epoch": 0.9964473557871827, "grad_norm": 0.7772086404476459, "learning_rate": 5.001562109038113e-06, "loss": 0.3904, "num_tokens": 557786382.0, "step": 93400 }, { "epoch": 0.9965006987933812, "grad_norm": 0.8169091688691027, "learning_rate": 5.001515689900452e-06, "loss": 0.4739, "num_tokens": 557815030.0, "step": 93405 }, { "epoch": 0.9965540417995796, "grad_norm": 1.2062654711990204, "learning_rate": 5.001469970869408e-06, "loss": 0.4595, "num_tokens": 557830892.0, "step": 93410 }, { "epoch": 0.9966073848057782, "grad_norm": 0.7960734492737052, "learning_rate": 5.0014249519464065e-06, "loss": 0.4634, "num_tokens": 557853378.0, "step": 93415 }, { "epoch": 0.9966607278119766, "grad_norm": 0.814989535148004, "learning_rate": 5.001380633132845e-06, "loss": 0.4399, "num_tokens": 557875657.0, "step": 93420 }, { "epoch": 0.996714070818175, "grad_norm": 0.927505594007191, "learning_rate": 5.001337014430108e-06, "loss": 0.4615, "num_tokens": 557897699.0, "step": 93425 }, { "epoch": 0.9967674138243735, "grad_norm": 0.6428014071973356, "learning_rate": 5.001294095839546e-06, "loss": 0.4357, "num_tokens": 557930552.0, "step": 93430 }, { "epoch": 0.9968207568305719, "grad_norm": 0.5373207694822005, "learning_rate": 5.001251877362499e-06, "loss": 0.4787, "num_tokens": 557960373.0, "step": 93435 }, { "epoch": 0.9968740998367704, "grad_norm": 1.3091220886893973, "learning_rate": 5.001210359000281e-06, "loss": 0.4979, "num_tokens": 558001366.0, "step": 93440 }, { "epoch": 0.9969274428429689, "grad_norm": 0.9172808200696881, "learning_rate": 5.0011695407541834e-06, "loss": 0.5338, "num_tokens": 558038822.0, "step": 93445 }, { "epoch": 0.9969807858491673, "grad_norm": 1.152436091775475, "learning_rate": 5.001129422625473e-06, "loss": 0.4251, "num_tokens": 558064466.0, "step": 93450 }, { "epoch": 0.9970341288553658, "grad_norm": 1.3985735245075095, "learning_rate": 5.0010900046154025e-06, "loss": 0.4854, "num_tokens": 558087897.0, "step": 93455 }, { "epoch": 0.9970874718615642, "grad_norm": 0.7441524240340532, "learning_rate": 5.001051286725199e-06, "loss": 0.4359, "num_tokens": 558126592.0, "step": 93460 }, { "epoch": 0.9971408148677627, "grad_norm": 1.0209912208941931, "learning_rate": 5.001013268956061e-06, "loss": 0.4695, "num_tokens": 558151382.0, "step": 93465 }, { "epoch": 0.9971941578739612, "grad_norm": 1.7783602248671468, "learning_rate": 5.000975951309178e-06, "loss": 0.3741, "num_tokens": 558170706.0, "step": 93470 }, { "epoch": 0.9972475008801596, "grad_norm": 1.1351356075035544, "learning_rate": 5.0009393337857096e-06, "loss": 0.5442, "num_tokens": 558193791.0, "step": 93475 }, { "epoch": 0.9973008438863581, "grad_norm": 0.6719275539573571, "learning_rate": 5.0009034163867954e-06, "loss": 0.415, "num_tokens": 558220826.0, "step": 93480 }, { "epoch": 0.9973541868925565, "grad_norm": 0.8953317173802358, "learning_rate": 5.000868199113553e-06, "loss": 0.4765, "num_tokens": 558252031.0, "step": 93485 }, { "epoch": 0.9974075298987549, "grad_norm": 0.6892268733023252, "learning_rate": 5.000833681967074e-06, "loss": 0.4507, "num_tokens": 558286800.0, "step": 93490 }, { "epoch": 0.9974608729049534, "grad_norm": 1.238149011510969, "learning_rate": 5.000799864948438e-06, "loss": 0.4071, "num_tokens": 558316792.0, "step": 93495 }, { "epoch": 0.9975142159111519, "grad_norm": 0.7087875429301581, "learning_rate": 5.000766748058696e-06, "loss": 0.4552, "num_tokens": 558344350.0, "step": 93500 }, { "epoch": 0.9975675589173504, "grad_norm": 0.7469100353464376, "learning_rate": 5.0007343312988785e-06, "loss": 0.4319, "num_tokens": 558365150.0, "step": 93505 }, { "epoch": 0.9976209019235488, "grad_norm": 0.8278999459141764, "learning_rate": 5.000702614669993e-06, "loss": 0.5023, "num_tokens": 558395503.0, "step": 93510 }, { "epoch": 0.9976742449297472, "grad_norm": 1.784990729922394, "learning_rate": 5.000671598173028e-06, "loss": 0.4468, "num_tokens": 558415640.0, "step": 93515 }, { "epoch": 0.9977275879359457, "grad_norm": 1.0722076692548597, "learning_rate": 5.000641281808946e-06, "loss": 0.593, "num_tokens": 558445102.0, "step": 93520 }, { "epoch": 0.9977809309421442, "grad_norm": 1.0724415024226617, "learning_rate": 5.000611665578695e-06, "loss": 0.3616, "num_tokens": 558460231.0, "step": 93525 }, { "epoch": 0.9978342739483427, "grad_norm": 0.6948822828820392, "learning_rate": 5.000582749483192e-06, "loss": 0.4936, "num_tokens": 558501528.0, "step": 93530 }, { "epoch": 0.9978876169545411, "grad_norm": 1.45576528090938, "learning_rate": 5.000554533523339e-06, "loss": 0.428, "num_tokens": 558548310.0, "step": 93535 }, { "epoch": 0.9979409599607395, "grad_norm": 1.1506473186207997, "learning_rate": 5.000527017700013e-06, "loss": 0.4852, "num_tokens": 558574971.0, "step": 93540 }, { "epoch": 0.997994302966938, "grad_norm": 0.5772537999269359, "learning_rate": 5.000500202014075e-06, "loss": 0.4887, "num_tokens": 558614838.0, "step": 93545 }, { "epoch": 0.9980476459731364, "grad_norm": 0.6155174063895411, "learning_rate": 5.00047408646635e-06, "loss": 0.3939, "num_tokens": 558649871.0, "step": 93550 }, { "epoch": 0.998100988979335, "grad_norm": 0.7096633729988501, "learning_rate": 5.00044867105766e-06, "loss": 0.4229, "num_tokens": 558692691.0, "step": 93555 }, { "epoch": 0.9981543319855334, "grad_norm": 0.7249869676929943, "learning_rate": 5.000423955788789e-06, "loss": 0.4824, "num_tokens": 558713664.0, "step": 93560 }, { "epoch": 0.9982076749917318, "grad_norm": 1.2726122877208097, "learning_rate": 5.00039994066051e-06, "loss": 0.3529, "num_tokens": 558731188.0, "step": 93565 }, { "epoch": 0.9982610179979303, "grad_norm": 1.0101638628217768, "learning_rate": 5.000376625673571e-06, "loss": 0.4348, "num_tokens": 558748169.0, "step": 93570 }, { "epoch": 0.9983143610041287, "grad_norm": 0.8261898925094644, "learning_rate": 5.000354010828694e-06, "loss": 0.4369, "num_tokens": 558775633.0, "step": 93575 }, { "epoch": 0.9983677040103272, "grad_norm": 1.2578139158071848, "learning_rate": 5.000332096126586e-06, "loss": 0.372, "num_tokens": 558788857.0, "step": 93580 }, { "epoch": 0.9984210470165257, "grad_norm": 1.4113936904285724, "learning_rate": 5.0003108815679265e-06, "loss": 0.4392, "num_tokens": 558820977.0, "step": 93585 }, { "epoch": 0.9984743900227241, "grad_norm": 0.7100732805260264, "learning_rate": 5.000290367153377e-06, "loss": 0.4032, "num_tokens": 558852053.0, "step": 93590 }, { "epoch": 0.9985277330289226, "grad_norm": 0.7168399816834067, "learning_rate": 5.000270552883575e-06, "loss": 0.388, "num_tokens": 558877119.0, "step": 93595 }, { "epoch": 0.998581076035121, "grad_norm": 0.9604557004962435, "learning_rate": 5.000251438759139e-06, "loss": 0.423, "num_tokens": 558905839.0, "step": 93600 }, { "epoch": 0.9986344190413194, "grad_norm": 0.8296592115344735, "learning_rate": 5.000233024780662e-06, "loss": 0.4816, "num_tokens": 558926542.0, "step": 93605 }, { "epoch": 0.998687762047518, "grad_norm": 0.731179304211703, "learning_rate": 5.000215310948716e-06, "loss": 0.4836, "num_tokens": 558962004.0, "step": 93610 }, { "epoch": 0.9987411050537164, "grad_norm": 0.6271964960720676, "learning_rate": 5.000198297263855e-06, "loss": 0.4498, "num_tokens": 559000500.0, "step": 93615 }, { "epoch": 0.9987944480599149, "grad_norm": 1.1773281386086631, "learning_rate": 5.0001819837266064e-06, "loss": 0.3949, "num_tokens": 559028597.0, "step": 93620 }, { "epoch": 0.9988477910661133, "grad_norm": 0.7261936012653833, "learning_rate": 5.00016637033748e-06, "loss": 0.4901, "num_tokens": 559070786.0, "step": 93625 }, { "epoch": 0.9989011340723117, "grad_norm": 0.8692379039560333, "learning_rate": 5.000151457096957e-06, "loss": 0.4184, "num_tokens": 559107327.0, "step": 93630 }, { "epoch": 0.9989544770785103, "grad_norm": 0.9925176262900086, "learning_rate": 5.000137244005508e-06, "loss": 0.4384, "num_tokens": 559130806.0, "step": 93635 }, { "epoch": 0.9990078200847087, "grad_norm": 0.885758966448086, "learning_rate": 5.00012373106357e-06, "loss": 0.4343, "num_tokens": 559165137.0, "step": 93640 }, { "epoch": 0.9990611630909072, "grad_norm": 0.815975521753301, "learning_rate": 5.000110918271565e-06, "loss": 0.4361, "num_tokens": 559217690.0, "step": 93645 }, { "epoch": 0.9991145060971056, "grad_norm": 0.7007615540743972, "learning_rate": 5.000098805629894e-06, "loss": 0.5116, "num_tokens": 559251981.0, "step": 93650 }, { "epoch": 0.999167849103304, "grad_norm": 0.8324991605639724, "learning_rate": 5.000087393138931e-06, "loss": 0.3746, "num_tokens": 559285348.0, "step": 93655 }, { "epoch": 0.9992211921095026, "grad_norm": 0.7580093937478046, "learning_rate": 5.000076680799033e-06, "loss": 0.3857, "num_tokens": 559312681.0, "step": 93660 }, { "epoch": 0.999274535115701, "grad_norm": 0.8120892850255681, "learning_rate": 5.0000666686105324e-06, "loss": 0.4543, "num_tokens": 559343724.0, "step": 93665 }, { "epoch": 0.9993278781218994, "grad_norm": 1.1468052599513696, "learning_rate": 5.000057356573738e-06, "loss": 0.5705, "num_tokens": 559368621.0, "step": 93670 }, { "epoch": 0.9993812211280979, "grad_norm": 0.8208411243272513, "learning_rate": 5.0000487446889455e-06, "loss": 0.4725, "num_tokens": 559401314.0, "step": 93675 }, { "epoch": 0.9994345641342963, "grad_norm": 1.0858669135548964, "learning_rate": 5.000040832956419e-06, "loss": 0.4345, "num_tokens": 559413406.0, "step": 93680 }, { "epoch": 0.9994879071404948, "grad_norm": 0.6029090139556201, "learning_rate": 5.000033621376406e-06, "loss": 0.5102, "num_tokens": 559438099.0, "step": 93685 }, { "epoch": 0.9995412501466933, "grad_norm": 0.5784381330274894, "learning_rate": 5.000027109949131e-06, "loss": 0.3931, "num_tokens": 559473987.0, "step": 93690 }, { "epoch": 0.9995945931528917, "grad_norm": 0.9250234462506346, "learning_rate": 5.000021298674794e-06, "loss": 0.5055, "num_tokens": 559502884.0, "step": 93695 }, { "epoch": 0.9996479361590902, "grad_norm": 0.7142068421915859, "learning_rate": 5.000016187553581e-06, "loss": 0.5974, "num_tokens": 559545915.0, "step": 93700 }, { "epoch": 0.9997012791652886, "grad_norm": 0.9833386069187112, "learning_rate": 5.0000117765856444e-06, "loss": 0.5054, "num_tokens": 559582711.0, "step": 93705 }, { "epoch": 0.9997546221714871, "grad_norm": 1.0033752747110496, "learning_rate": 5.0000080657711264e-06, "loss": 0.3699, "num_tokens": 559610263.0, "step": 93710 }, { "epoch": 0.9998079651776856, "grad_norm": 1.9025807356168105, "learning_rate": 5.000005055110144e-06, "loss": 0.4403, "num_tokens": 559632852.0, "step": 93715 }, { "epoch": 0.999861308183884, "grad_norm": 0.6722365233953962, "learning_rate": 5.000002744602783e-06, "loss": 0.4296, "num_tokens": 559669116.0, "step": 93720 }, { "epoch": 0.9999146511900825, "grad_norm": 1.13636573170522, "learning_rate": 5.000001134249123e-06, "loss": 0.4767, "num_tokens": 559706543.0, "step": 93725 }, { "epoch": 0.9999679941962809, "grad_norm": 1.2812347914493245, "learning_rate": 5.000000224049212e-06, "loss": 0.474, "num_tokens": 559741507.0, "step": 93730 }, { "epoch": 1.0, "step": 93733, "total_flos": 486636766648320.0, "train_loss": 0.0, "train_runtime": 5.536, "train_samples_per_second": 16931.445, "train_steps_per_second": 16931.445 } ], "logging_steps": 5, "max_steps": 93733, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 486636766648320.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }