{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 5334, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0037495313085864268, "grad_norm": 66.16914766859206, "learning_rate": 5.590062111801243e-07, "loss": 2.6619, "step": 10 }, { "epoch": 0.0074990626171728535, "grad_norm": 21.727609558931295, "learning_rate": 1.1801242236024846e-06, "loss": 2.145, "step": 20 }, { "epoch": 0.01124859392575928, "grad_norm": 9.554825526385697, "learning_rate": 1.8012422360248449e-06, "loss": 1.4826, "step": 30 }, { "epoch": 0.014998125234345707, "grad_norm": 4.604349308145926, "learning_rate": 2.422360248447205e-06, "loss": 1.0784, "step": 40 }, { "epoch": 0.018747656542932135, "grad_norm": 5.073729494160188, "learning_rate": 3.043478260869566e-06, "loss": 0.8519, "step": 50 }, { "epoch": 0.02249718785151856, "grad_norm": 4.333895775424238, "learning_rate": 3.664596273291926e-06, "loss": 0.757, "step": 60 }, { "epoch": 0.026246719160104987, "grad_norm": 4.103032815426519, "learning_rate": 4.2857142857142855e-06, "loss": 0.6282, "step": 70 }, { "epoch": 0.029996250468691414, "grad_norm": 3.673983730567822, "learning_rate": 4.906832298136646e-06, "loss": 0.6461, "step": 80 }, { "epoch": 0.03374578177727784, "grad_norm": 3.9260332492270336, "learning_rate": 5.527950310559007e-06, "loss": 0.6181, "step": 90 }, { "epoch": 0.03749531308586427, "grad_norm": 3.3512980697296966, "learning_rate": 6.1490683229813675e-06, "loss": 0.6179, "step": 100 }, { "epoch": 0.0412448443944507, "grad_norm": 3.574275270271436, "learning_rate": 6.7701863354037265e-06, "loss": 0.5559, "step": 110 }, { "epoch": 0.04499437570303712, "grad_norm": 3.1744754801691037, "learning_rate": 7.391304347826087e-06, "loss": 0.6518, "step": 120 }, { "epoch": 0.048743907011623545, "grad_norm": 3.167521116265953, "learning_rate": 8.012422360248447e-06, "loss": 0.526, "step": 130 }, { "epoch": 0.05249343832020997, "grad_norm": 3.207108522564362, "learning_rate": 8.633540372670808e-06, "loss": 0.5249, "step": 140 }, { "epoch": 0.0562429696287964, "grad_norm": 2.9106167418624076, "learning_rate": 9.254658385093168e-06, "loss": 0.5941, "step": 150 }, { "epoch": 0.05999250093738283, "grad_norm": 2.75463200771962, "learning_rate": 9.875776397515529e-06, "loss": 0.5849, "step": 160 }, { "epoch": 0.06374203224596925, "grad_norm": 3.0472766152039323, "learning_rate": 9.99994098887191e-06, "loss": 0.5962, "step": 170 }, { "epoch": 0.06749156355455568, "grad_norm": 2.8277315090766706, "learning_rate": 9.999701258551321e-06, "loss": 0.6037, "step": 180 }, { "epoch": 0.0712410948631421, "grad_norm": 2.6138236721932238, "learning_rate": 9.999277129677647e-06, "loss": 0.5809, "step": 190 }, { "epoch": 0.07499062617172854, "grad_norm": 2.161543111714362, "learning_rate": 9.99866861789357e-06, "loss": 0.555, "step": 200 }, { "epoch": 0.07874015748031496, "grad_norm": 2.9348094377457716, "learning_rate": 9.997875745642166e-06, "loss": 0.5206, "step": 210 }, { "epoch": 0.0824896887889014, "grad_norm": 2.4860664145260016, "learning_rate": 9.996898542166084e-06, "loss": 0.5258, "step": 220 }, { "epoch": 0.08623922009748781, "grad_norm": 2.5462849081755414, "learning_rate": 9.995737043506461e-06, "loss": 0.54, "step": 230 }, { "epoch": 0.08998875140607424, "grad_norm": 2.3649431837108974, "learning_rate": 9.994391292501587e-06, "loss": 0.6015, "step": 240 }, { "epoch": 0.09373828271466067, "grad_norm": 2.3338311655608477, "learning_rate": 9.992861338785337e-06, "loss": 0.5724, "step": 250 }, { "epoch": 0.09748781402324709, "grad_norm": 2.5608896062075193, "learning_rate": 9.991147238785335e-06, "loss": 0.5736, "step": 260 }, { "epoch": 0.10123734533183353, "grad_norm": 2.737950376161913, "learning_rate": 9.989249055720865e-06, "loss": 0.5194, "step": 270 }, { "epoch": 0.10498687664041995, "grad_norm": 2.0275768399386047, "learning_rate": 9.987166859600557e-06, "loss": 0.5778, "step": 280 }, { "epoch": 0.10873640794900638, "grad_norm": 2.3341572162013495, "learning_rate": 9.984900727219786e-06, "loss": 0.5183, "step": 290 }, { "epoch": 0.1124859392575928, "grad_norm": 2.5240048933911137, "learning_rate": 9.982450742157856e-06, "loss": 0.5298, "step": 300 }, { "epoch": 0.11623547056617922, "grad_norm": 2.6422452878366536, "learning_rate": 9.979816994774903e-06, "loss": 0.4903, "step": 310 }, { "epoch": 0.11998500187476566, "grad_norm": 2.5215699470534068, "learning_rate": 9.976999582208572e-06, "loss": 0.531, "step": 320 }, { "epoch": 0.12373453318335208, "grad_norm": 2.271696778427734, "learning_rate": 9.973998608370433e-06, "loss": 0.5333, "step": 330 }, { "epoch": 0.1274840644919385, "grad_norm": 1.9843663777302045, "learning_rate": 9.970814183942145e-06, "loss": 0.5104, "step": 340 }, { "epoch": 0.13123359580052493, "grad_norm": 2.064125406129319, "learning_rate": 9.96744642637138e-06, "loss": 0.5379, "step": 350 }, { "epoch": 0.13498312710911137, "grad_norm": 2.428007571609196, "learning_rate": 9.963895459867478e-06, "loss": 0.5426, "step": 360 }, { "epoch": 0.13873265841769777, "grad_norm": 2.50774397438367, "learning_rate": 9.960161415396885e-06, "loss": 0.5341, "step": 370 }, { "epoch": 0.1424821897262842, "grad_norm": 2.491829399488034, "learning_rate": 9.956244430678308e-06, "loss": 0.5199, "step": 380 }, { "epoch": 0.14623172103487064, "grad_norm": 1.9992349699036513, "learning_rate": 9.952144650177641e-06, "loss": 0.5494, "step": 390 }, { "epoch": 0.14998125234345708, "grad_norm": 2.1348177437169396, "learning_rate": 9.947862225102637e-06, "loss": 0.5208, "step": 400 }, { "epoch": 0.15373078365204348, "grad_norm": 2.108784384127794, "learning_rate": 9.943397313397334e-06, "loss": 0.4929, "step": 410 }, { "epoch": 0.15748031496062992, "grad_norm": 2.343796887487267, "learning_rate": 9.938750079736218e-06, "loss": 0.4938, "step": 420 }, { "epoch": 0.16122984626921635, "grad_norm": 2.285205073169561, "learning_rate": 9.933920695518161e-06, "loss": 0.4816, "step": 430 }, { "epoch": 0.1649793775778028, "grad_norm": 2.297551263677707, "learning_rate": 9.928909338860105e-06, "loss": 0.5126, "step": 440 }, { "epoch": 0.1687289088863892, "grad_norm": 1.9624443951689527, "learning_rate": 9.92371619459047e-06, "loss": 0.4962, "step": 450 }, { "epoch": 0.17247844019497563, "grad_norm": 2.0721262932294606, "learning_rate": 9.91834145424236e-06, "loss": 0.5026, "step": 460 }, { "epoch": 0.17622797150356206, "grad_norm": 2.279624584722672, "learning_rate": 9.912785316046487e-06, "loss": 0.5331, "step": 470 }, { "epoch": 0.17997750281214847, "grad_norm": 1.9679642152690628, "learning_rate": 9.907047984923864e-06, "loss": 0.5092, "step": 480 }, { "epoch": 0.1837270341207349, "grad_norm": 2.24663463578073, "learning_rate": 9.901129672478244e-06, "loss": 0.522, "step": 490 }, { "epoch": 0.18747656542932134, "grad_norm": 1.962790320690953, "learning_rate": 9.895030596988323e-06, "loss": 0.5207, "step": 500 }, { "epoch": 0.19122609673790777, "grad_norm": 1.914864720129168, "learning_rate": 9.888750983399676e-06, "loss": 0.5167, "step": 510 }, { "epoch": 0.19497562804649418, "grad_norm": 2.215767582962427, "learning_rate": 9.882291063316474e-06, "loss": 0.5023, "step": 520 }, { "epoch": 0.19872515935508062, "grad_norm": 1.4400778015818723, "learning_rate": 9.875651074992936e-06, "loss": 0.5175, "step": 530 }, { "epoch": 0.20247469066366705, "grad_norm": 2.5907260912353767, "learning_rate": 9.868831263324543e-06, "loss": 0.5277, "step": 540 }, { "epoch": 0.20622422197225346, "grad_norm": 2.740676008164538, "learning_rate": 9.861831879839003e-06, "loss": 0.5191, "step": 550 }, { "epoch": 0.2099737532808399, "grad_norm": 1.9983948740863677, "learning_rate": 9.854653182686977e-06, "loss": 0.5192, "step": 560 }, { "epoch": 0.21372328458942633, "grad_norm": 2.0302627825100057, "learning_rate": 9.84729543663256e-06, "loss": 0.5067, "step": 570 }, { "epoch": 0.21747281589801276, "grad_norm": 2.1687738160918077, "learning_rate": 9.83975891304351e-06, "loss": 0.5107, "step": 580 }, { "epoch": 0.22122234720659917, "grad_norm": 2.0201164592237335, "learning_rate": 9.83204388988124e-06, "loss": 0.5292, "step": 590 }, { "epoch": 0.2249718785151856, "grad_norm": 2.0814878944375175, "learning_rate": 9.824150651690578e-06, "loss": 0.5305, "step": 600 }, { "epoch": 0.22872140982377204, "grad_norm": 1.6956859575797187, "learning_rate": 9.816079489589257e-06, "loss": 0.5028, "step": 610 }, { "epoch": 0.23247094113235844, "grad_norm": 2.053275098671879, "learning_rate": 9.807830701257183e-06, "loss": 0.4839, "step": 620 }, { "epoch": 0.23622047244094488, "grad_norm": 2.070367703821508, "learning_rate": 9.79940459092546e-06, "loss": 0.5076, "step": 630 }, { "epoch": 0.2399700037495313, "grad_norm": 2.083709580419921, "learning_rate": 9.790801469365172e-06, "loss": 0.4612, "step": 640 }, { "epoch": 0.24371953505811775, "grad_norm": 2.0178175937889495, "learning_rate": 9.782021653875904e-06, "loss": 0.5182, "step": 650 }, { "epoch": 0.24746906636670415, "grad_norm": 2.720530043024262, "learning_rate": 9.773065468274063e-06, "loss": 0.5322, "step": 660 }, { "epoch": 0.2512185976752906, "grad_norm": 1.780275422901838, "learning_rate": 9.763933242880914e-06, "loss": 0.4971, "step": 670 }, { "epoch": 0.254968128983877, "grad_norm": 2.002484525332709, "learning_rate": 9.754625314510416e-06, "loss": 0.4285, "step": 680 }, { "epoch": 0.25871766029246346, "grad_norm": 2.134571234040845, "learning_rate": 9.74514202645678e-06, "loss": 0.4836, "step": 690 }, { "epoch": 0.26246719160104987, "grad_norm": 2.254304763620984, "learning_rate": 9.735483728481825e-06, "loss": 0.5122, "step": 700 }, { "epoch": 0.26621672290963627, "grad_norm": 1.933473493125299, "learning_rate": 9.725650776802068e-06, "loss": 0.4889, "step": 710 }, { "epoch": 0.26996625421822273, "grad_norm": 2.0639188524199357, "learning_rate": 9.715643534075591e-06, "loss": 0.5351, "step": 720 }, { "epoch": 0.27371578552680914, "grad_norm": 1.9768000109609183, "learning_rate": 9.705462369388661e-06, "loss": 0.5174, "step": 730 }, { "epoch": 0.27746531683539555, "grad_norm": 1.8730666484030738, "learning_rate": 9.695107658242123e-06, "loss": 0.4923, "step": 740 }, { "epoch": 0.281214848143982, "grad_norm": 1.6254668149349485, "learning_rate": 9.684579782537542e-06, "loss": 0.5059, "step": 750 }, { "epoch": 0.2849643794525684, "grad_norm": 1.6025034918901628, "learning_rate": 9.673879130563129e-06, "loss": 0.5111, "step": 760 }, { "epoch": 0.2887139107611549, "grad_norm": 1.9608851077719296, "learning_rate": 9.663006096979413e-06, "loss": 0.5146, "step": 770 }, { "epoch": 0.2924634420697413, "grad_norm": 1.8379991262598727, "learning_rate": 9.651961082804684e-06, "loss": 0.4709, "step": 780 }, { "epoch": 0.2962129733783277, "grad_norm": 2.028997226179882, "learning_rate": 9.640744495400212e-06, "loss": 0.4705, "step": 790 }, { "epoch": 0.29996250468691416, "grad_norm": 1.870806846336672, "learning_rate": 9.629356748455208e-06, "loss": 0.4708, "step": 800 }, { "epoch": 0.30371203599550056, "grad_norm": 1.710201836164435, "learning_rate": 9.617798261971579e-06, "loss": 0.4904, "step": 810 }, { "epoch": 0.30746156730408697, "grad_norm": 1.9636312344070224, "learning_rate": 9.606069462248432e-06, "loss": 0.4555, "step": 820 }, { "epoch": 0.31121109861267343, "grad_norm": 1.920460963223514, "learning_rate": 9.594170781866354e-06, "loss": 0.5008, "step": 830 }, { "epoch": 0.31496062992125984, "grad_norm": 1.8273222575699104, "learning_rate": 9.582102659671455e-06, "loss": 0.496, "step": 840 }, { "epoch": 0.31871016122984624, "grad_norm": 1.9003363964619957, "learning_rate": 9.56986554075918e-06, "loss": 0.4918, "step": 850 }, { "epoch": 0.3224596925384327, "grad_norm": 1.853346545500746, "learning_rate": 9.557459876457902e-06, "loss": 0.4745, "step": 860 }, { "epoch": 0.3262092238470191, "grad_norm": 2.1781694637156526, "learning_rate": 9.544886124312267e-06, "loss": 0.4906, "step": 870 }, { "epoch": 0.3299587551556056, "grad_norm": 1.799860788333503, "learning_rate": 9.532144748066324e-06, "loss": 0.508, "step": 880 }, { "epoch": 0.333708286464192, "grad_norm": 1.9043964382223286, "learning_rate": 9.519236217646419e-06, "loss": 0.5005, "step": 890 }, { "epoch": 0.3374578177727784, "grad_norm": 1.9541931172095994, "learning_rate": 9.506161009143864e-06, "loss": 0.5064, "step": 900 }, { "epoch": 0.34120734908136485, "grad_norm": 1.8874741249112625, "learning_rate": 9.492919604797376e-06, "loss": 0.4433, "step": 910 }, { "epoch": 0.34495688038995126, "grad_norm": 1.471202981999028, "learning_rate": 9.479512492975299e-06, "loss": 0.4844, "step": 920 }, { "epoch": 0.34870641169853767, "grad_norm": 1.9931388327142978, "learning_rate": 9.465940168157576e-06, "loss": 0.4953, "step": 930 }, { "epoch": 0.35245594300712413, "grad_norm": 1.9661668591139976, "learning_rate": 9.452203130917532e-06, "loss": 0.4945, "step": 940 }, { "epoch": 0.35620547431571054, "grad_norm": 1.7291952540650422, "learning_rate": 9.438301887903392e-06, "loss": 0.4599, "step": 950 }, { "epoch": 0.35995500562429694, "grad_norm": 2.141330973742592, "learning_rate": 9.424236951819612e-06, "loss": 0.496, "step": 960 }, { "epoch": 0.3637045369328834, "grad_norm": 1.4370827669242452, "learning_rate": 9.410008841407959e-06, "loss": 0.5038, "step": 970 }, { "epoch": 0.3674540682414698, "grad_norm": 1.9895251227694721, "learning_rate": 9.395618081428379e-06, "loss": 0.4502, "step": 980 }, { "epoch": 0.3712035995500562, "grad_norm": 1.8927849904671654, "learning_rate": 9.381065202639648e-06, "loss": 0.5, "step": 990 }, { "epoch": 0.3749531308586427, "grad_norm": 1.8849164339996531, "learning_rate": 9.366350741779794e-06, "loss": 0.472, "step": 1000 }, { "epoch": 0.3787026621672291, "grad_norm": 1.7979456946407923, "learning_rate": 9.3514752415463e-06, "loss": 0.4817, "step": 1010 }, { "epoch": 0.38245219347581555, "grad_norm": 1.948570511717519, "learning_rate": 9.33643925057609e-06, "loss": 0.4907, "step": 1020 }, { "epoch": 0.38620172478440196, "grad_norm": 1.85505401056172, "learning_rate": 9.321243323425298e-06, "loss": 0.4784, "step": 1030 }, { "epoch": 0.38995125609298836, "grad_norm": 1.8552532110448916, "learning_rate": 9.3058880205488e-06, "loss": 0.4769, "step": 1040 }, { "epoch": 0.3937007874015748, "grad_norm": 1.6869927611362934, "learning_rate": 9.290373908279561e-06, "loss": 0.5015, "step": 1050 }, { "epoch": 0.39745031871016123, "grad_norm": 2.174421179118309, "learning_rate": 9.274701558807743e-06, "loss": 0.4418, "step": 1060 }, { "epoch": 0.40119985001874764, "grad_norm": 1.8060503910905386, "learning_rate": 9.258871550159591e-06, "loss": 0.4606, "step": 1070 }, { "epoch": 0.4049493813273341, "grad_norm": 1.843597627751789, "learning_rate": 9.24288446617613e-06, "loss": 0.4701, "step": 1080 }, { "epoch": 0.4086989126359205, "grad_norm": 2.0095368590138536, "learning_rate": 9.226740896491618e-06, "loss": 0.5003, "step": 1090 }, { "epoch": 0.4124484439445069, "grad_norm": 2.043446521362851, "learning_rate": 9.21044143651181e-06, "loss": 0.4383, "step": 1100 }, { "epoch": 0.4161979752530934, "grad_norm": 1.5590697931206552, "learning_rate": 9.193986687391989e-06, "loss": 0.5023, "step": 1110 }, { "epoch": 0.4199475065616798, "grad_norm": 1.6074593653560434, "learning_rate": 9.177377256014802e-06, "loss": 0.4888, "step": 1120 }, { "epoch": 0.4236970378702662, "grad_norm": 1.6971722577173616, "learning_rate": 9.160613754967873e-06, "loss": 0.4351, "step": 1130 }, { "epoch": 0.42744656917885265, "grad_norm": 1.7245870522969824, "learning_rate": 9.143696802521211e-06, "loss": 0.4931, "step": 1140 }, { "epoch": 0.43119610048743906, "grad_norm": 1.4571925877855862, "learning_rate": 9.126627022604405e-06, "loss": 0.427, "step": 1150 }, { "epoch": 0.4349456317960255, "grad_norm": 1.6417724514312875, "learning_rate": 9.109405044783613e-06, "loss": 0.4787, "step": 1160 }, { "epoch": 0.43869516310461193, "grad_norm": 1.8631509839889044, "learning_rate": 9.092031504238343e-06, "loss": 0.4671, "step": 1170 }, { "epoch": 0.44244469441319834, "grad_norm": 1.778363136676875, "learning_rate": 9.074507041738031e-06, "loss": 0.4696, "step": 1180 }, { "epoch": 0.4461942257217848, "grad_norm": 1.7654725385652734, "learning_rate": 9.0568323036184e-06, "loss": 0.486, "step": 1190 }, { "epoch": 0.4499437570303712, "grad_norm": 1.6373722381444982, "learning_rate": 9.039007941757621e-06, "loss": 0.4842, "step": 1200 }, { "epoch": 0.4536932883389576, "grad_norm": 1.9503340832150107, "learning_rate": 9.021034613552286e-06, "loss": 0.5171, "step": 1210 }, { "epoch": 0.4574428196475441, "grad_norm": 1.5767860020062734, "learning_rate": 9.00291298189314e-06, "loss": 0.4958, "step": 1220 }, { "epoch": 0.4611923509561305, "grad_norm": 1.6221839338709414, "learning_rate": 8.98464371514065e-06, "loss": 0.508, "step": 1230 }, { "epoch": 0.4649418822647169, "grad_norm": 1.667719772700975, "learning_rate": 8.966227487100346e-06, "loss": 0.4398, "step": 1240 }, { "epoch": 0.46869141357330335, "grad_norm": 1.6014570651616795, "learning_rate": 8.94766497699797e-06, "loss": 0.4679, "step": 1250 }, { "epoch": 0.47244094488188976, "grad_norm": 1.5434395071588847, "learning_rate": 8.92895686945443e-06, "loss": 0.4652, "step": 1260 }, { "epoch": 0.47619047619047616, "grad_norm": 1.505361664052988, "learning_rate": 8.910103854460541e-06, "loss": 0.4363, "step": 1270 }, { "epoch": 0.4799400074990626, "grad_norm": 1.624095610036329, "learning_rate": 8.891106627351588e-06, "loss": 0.4537, "step": 1280 }, { "epoch": 0.48368953880764903, "grad_norm": 1.6521324975390672, "learning_rate": 8.87196588878167e-06, "loss": 0.4447, "step": 1290 }, { "epoch": 0.4874390701162355, "grad_norm": 1.7966859537260924, "learning_rate": 8.852682344697869e-06, "loss": 0.4944, "step": 1300 }, { "epoch": 0.4911886014248219, "grad_norm": 1.703709359771672, "learning_rate": 8.8332567063142e-06, "loss": 0.5004, "step": 1310 }, { "epoch": 0.4949381327334083, "grad_norm": 1.6860855868182902, "learning_rate": 8.813689690085396e-06, "loss": 0.4428, "step": 1320 }, { "epoch": 0.49868766404199477, "grad_norm": 1.9406920504306782, "learning_rate": 8.79398201768047e-06, "loss": 0.4675, "step": 1330 }, { "epoch": 0.5024371953505812, "grad_norm": 1.804015672603719, "learning_rate": 8.774134415956104e-06, "loss": 0.4701, "step": 1340 }, { "epoch": 0.5061867266591676, "grad_norm": 1.9742313920708663, "learning_rate": 8.754147616929845e-06, "loss": 0.4857, "step": 1350 }, { "epoch": 0.509936257967754, "grad_norm": 1.6599457354110132, "learning_rate": 8.734022357753101e-06, "loss": 0.4255, "step": 1360 }, { "epoch": 0.5136857892763405, "grad_norm": 1.5729788401406142, "learning_rate": 8.713759380683954e-06, "loss": 0.4712, "step": 1370 }, { "epoch": 0.5174353205849269, "grad_norm": 1.765196894075061, "learning_rate": 8.693359433059789e-06, "loss": 0.4553, "step": 1380 }, { "epoch": 0.5211848518935133, "grad_norm": 1.4151578788545043, "learning_rate": 8.67282326726972e-06, "loss": 0.4917, "step": 1390 }, { "epoch": 0.5249343832020997, "grad_norm": 1.593301825099594, "learning_rate": 8.652151640726857e-06, "loss": 0.4336, "step": 1400 }, { "epoch": 0.5286839145106862, "grad_norm": 2.048679168051114, "learning_rate": 8.631345315840357e-06, "loss": 0.4579, "step": 1410 }, { "epoch": 0.5324334458192725, "grad_norm": 1.3660585537761392, "learning_rate": 8.61040505998731e-06, "loss": 0.4455, "step": 1420 }, { "epoch": 0.536182977127859, "grad_norm": 1.7822250040015608, "learning_rate": 8.589331645484436e-06, "loss": 0.459, "step": 1430 }, { "epoch": 0.5399325084364455, "grad_norm": 1.8801128601315606, "learning_rate": 8.568125849559601e-06, "loss": 0.4478, "step": 1440 }, { "epoch": 0.5436820397450318, "grad_norm": 1.7290226738818377, "learning_rate": 8.546788454323153e-06, "loss": 0.447, "step": 1450 }, { "epoch": 0.5474315710536183, "grad_norm": 1.7601581990613564, "learning_rate": 8.525320246739076e-06, "loss": 0.4677, "step": 1460 }, { "epoch": 0.5511811023622047, "grad_norm": 1.5697120189469005, "learning_rate": 8.503722018595954e-06, "loss": 0.4759, "step": 1470 }, { "epoch": 0.5549306336707911, "grad_norm": 1.7812910806177753, "learning_rate": 8.481994566477793e-06, "loss": 0.4682, "step": 1480 }, { "epoch": 0.5586801649793776, "grad_norm": 1.476362699275203, "learning_rate": 8.460138691734614e-06, "loss": 0.4515, "step": 1490 }, { "epoch": 0.562429696287964, "grad_norm": 1.5729378965623713, "learning_rate": 8.438155200452917e-06, "loss": 0.474, "step": 1500 }, { "epoch": 0.5661792275965505, "grad_norm": 1.4946799806731523, "learning_rate": 8.416044903425944e-06, "loss": 0.4886, "step": 1510 }, { "epoch": 0.5699287589051368, "grad_norm": 1.9724532926568625, "learning_rate": 8.393808616123771e-06, "loss": 0.459, "step": 1520 }, { "epoch": 0.5736782902137233, "grad_norm": 1.5663145785480466, "learning_rate": 8.37144715866324e-06, "loss": 0.469, "step": 1530 }, { "epoch": 0.5774278215223098, "grad_norm": 1.7161111662313737, "learning_rate": 8.348961355777708e-06, "loss": 0.4657, "step": 1540 }, { "epoch": 0.5811773528308961, "grad_norm": 1.6336031587956026, "learning_rate": 8.32635203678663e-06, "loss": 0.4501, "step": 1550 }, { "epoch": 0.5849268841394826, "grad_norm": 1.807442369617976, "learning_rate": 8.303620035564968e-06, "loss": 0.4125, "step": 1560 }, { "epoch": 0.588676415448069, "grad_norm": 1.6692317545041289, "learning_rate": 8.280766190512444e-06, "loss": 0.4806, "step": 1570 }, { "epoch": 0.5924259467566554, "grad_norm": 1.268195730897819, "learning_rate": 8.257791344522609e-06, "loss": 0.4474, "step": 1580 }, { "epoch": 0.5961754780652418, "grad_norm": 1.5504998202606357, "learning_rate": 8.234696344951767e-06, "loss": 0.4528, "step": 1590 }, { "epoch": 0.5999250093738283, "grad_norm": 1.9782522216197214, "learning_rate": 8.211482043587707e-06, "loss": 0.4615, "step": 1600 }, { "epoch": 0.6036745406824147, "grad_norm": 1.7939673558938711, "learning_rate": 8.188149296618303e-06, "loss": 0.4549, "step": 1610 }, { "epoch": 0.6074240719910011, "grad_norm": 1.6186017090813558, "learning_rate": 8.164698964599929e-06, "loss": 0.4262, "step": 1620 }, { "epoch": 0.6111736032995876, "grad_norm": 1.9316869339129283, "learning_rate": 8.141131912425717e-06, "loss": 0.4582, "step": 1630 }, { "epoch": 0.6149231346081739, "grad_norm": 1.3928457483552223, "learning_rate": 8.117449009293668e-06, "loss": 0.4844, "step": 1640 }, { "epoch": 0.6186726659167604, "grad_norm": 1.7366324637295354, "learning_rate": 8.093651128674582e-06, "loss": 0.4581, "step": 1650 }, { "epoch": 0.6224221972253469, "grad_norm": 1.396705792623325, "learning_rate": 8.069739148279851e-06, "loss": 0.4512, "step": 1660 }, { "epoch": 0.6261717285339332, "grad_norm": 1.7298930758531432, "learning_rate": 8.045713950029088e-06, "loss": 0.4679, "step": 1670 }, { "epoch": 0.6299212598425197, "grad_norm": 1.701378823645829, "learning_rate": 8.021576420017591e-06, "loss": 0.4913, "step": 1680 }, { "epoch": 0.6336707911511061, "grad_norm": 1.514548692944433, "learning_rate": 7.997327448483675e-06, "loss": 0.4248, "step": 1690 }, { "epoch": 0.6374203224596925, "grad_norm": 1.339643131835874, "learning_rate": 7.97296792977583e-06, "loss": 0.4491, "step": 1700 }, { "epoch": 0.641169853768279, "grad_norm": 1.4822102441266218, "learning_rate": 7.948498762319732e-06, "loss": 0.4806, "step": 1710 }, { "epoch": 0.6449193850768654, "grad_norm": 1.4095728218309376, "learning_rate": 7.923920848585118e-06, "loss": 0.4718, "step": 1720 }, { "epoch": 0.6486689163854518, "grad_norm": 1.811805331891866, "learning_rate": 7.899235095052497e-06, "loss": 0.4305, "step": 1730 }, { "epoch": 0.6524184476940382, "grad_norm": 1.5656052356450447, "learning_rate": 7.874442412179712e-06, "loss": 0.4586, "step": 1740 }, { "epoch": 0.6561679790026247, "grad_norm": 1.6934618995112547, "learning_rate": 7.849543714368368e-06, "loss": 0.4635, "step": 1750 }, { "epoch": 0.6599175103112112, "grad_norm": 1.4757472771214821, "learning_rate": 7.824539919930101e-06, "loss": 0.4817, "step": 1760 }, { "epoch": 0.6636670416197975, "grad_norm": 1.9359499790354673, "learning_rate": 7.799431951052713e-06, "loss": 0.4894, "step": 1770 }, { "epoch": 0.667416572928384, "grad_norm": 1.7385844098687482, "learning_rate": 7.774220733766162e-06, "loss": 0.4714, "step": 1780 }, { "epoch": 0.6711661042369704, "grad_norm": 1.5388760764605944, "learning_rate": 7.748907197908402e-06, "loss": 0.4475, "step": 1790 }, { "epoch": 0.6749156355455568, "grad_norm": 1.561055502348693, "learning_rate": 7.723492277091089e-06, "loss": 0.455, "step": 1800 }, { "epoch": 0.6786651668541432, "grad_norm": 1.8301497132171218, "learning_rate": 7.697976908665152e-06, "loss": 0.4675, "step": 1810 }, { "epoch": 0.6824146981627297, "grad_norm": 1.4336421680889462, "learning_rate": 7.672362033686227e-06, "loss": 0.4241, "step": 1820 }, { "epoch": 0.6861642294713161, "grad_norm": 1.5846450312846152, "learning_rate": 7.64664859687993e-06, "loss": 0.4334, "step": 1830 }, { "epoch": 0.6899137607799025, "grad_norm": 1.8251148884513415, "learning_rate": 7.6208375466070384e-06, "loss": 0.4834, "step": 1840 }, { "epoch": 0.693663292088489, "grad_norm": 1.504012651265535, "learning_rate": 7.594929834828493e-06, "loss": 0.4283, "step": 1850 }, { "epoch": 0.6974128233970753, "grad_norm": 1.5172419980460834, "learning_rate": 7.5689264170702945e-06, "loss": 0.4071, "step": 1860 }, { "epoch": 0.7011623547056618, "grad_norm": 1.6647031645270838, "learning_rate": 7.542828252388271e-06, "loss": 0.4592, "step": 1870 }, { "epoch": 0.7049118860142483, "grad_norm": 1.5793809995824761, "learning_rate": 7.516636303332694e-06, "loss": 0.4522, "step": 1880 }, { "epoch": 0.7086614173228346, "grad_norm": 1.4359131084932295, "learning_rate": 7.49035153591278e-06, "loss": 0.4468, "step": 1890 }, { "epoch": 0.7124109486314211, "grad_norm": 1.6408242271637359, "learning_rate": 7.463974919561069e-06, "loss": 0.4367, "step": 1900 }, { "epoch": 0.7161604799400075, "grad_norm": 1.5267289059789886, "learning_rate": 7.437507427097663e-06, "loss": 0.4598, "step": 1910 }, { "epoch": 0.7199100112485939, "grad_norm": 1.5797997878302645, "learning_rate": 7.410950034694349e-06, "loss": 0.4354, "step": 1920 }, { "epoch": 0.7236595425571803, "grad_norm": 1.5709365251506726, "learning_rate": 7.384303721838598e-06, "loss": 0.4834, "step": 1930 }, { "epoch": 0.7274090738657668, "grad_norm": 1.4464133618845003, "learning_rate": 7.3575694712974335e-06, "loss": 0.4298, "step": 1940 }, { "epoch": 0.7311586051743532, "grad_norm": 1.5032073201547242, "learning_rate": 7.330748269081193e-06, "loss": 0.4135, "step": 1950 }, { "epoch": 0.7349081364829396, "grad_norm": 1.632206944194483, "learning_rate": 7.303841104407156e-06, "loss": 0.4508, "step": 1960 }, { "epoch": 0.7386576677915261, "grad_norm": 1.719534333785193, "learning_rate": 7.276848969663063e-06, "loss": 0.4486, "step": 1970 }, { "epoch": 0.7424071991001124, "grad_norm": 1.5450731205094679, "learning_rate": 7.249772860370513e-06, "loss": 0.4547, "step": 1980 }, { "epoch": 0.7461567304086989, "grad_norm": 1.501085771982292, "learning_rate": 7.2226137751482475e-06, "loss": 0.451, "step": 1990 }, { "epoch": 0.7499062617172854, "grad_norm": 1.5713532774666692, "learning_rate": 7.195372715675317e-06, "loss": 0.4259, "step": 2000 }, { "epoch": 0.7536557930258717, "grad_norm": 1.8284212899625003, "learning_rate": 7.168050686654144e-06, "loss": 0.4248, "step": 2010 }, { "epoch": 0.7574053243344582, "grad_norm": 1.8016541806792579, "learning_rate": 7.140648695773458e-06, "loss": 0.4379, "step": 2020 }, { "epoch": 0.7611548556430446, "grad_norm": 1.3859906339610455, "learning_rate": 7.1131677536711366e-06, "loss": 0.447, "step": 2030 }, { "epoch": 0.7649043869516311, "grad_norm": 1.5203736990464538, "learning_rate": 7.085608873896931e-06, "loss": 0.4126, "step": 2040 }, { "epoch": 0.7686539182602175, "grad_norm": 1.563396288766627, "learning_rate": 7.0579730728750805e-06, "loss": 0.4617, "step": 2050 }, { "epoch": 0.7724034495688039, "grad_norm": 1.476384564746799, "learning_rate": 7.03026136986683e-06, "loss": 0.4072, "step": 2060 }, { "epoch": 0.7761529808773904, "grad_norm": 1.5663035783002321, "learning_rate": 7.002474786932833e-06, "loss": 0.4391, "step": 2070 }, { "epoch": 0.7799025121859767, "grad_norm": 1.5720239676742827, "learning_rate": 6.974614348895459e-06, "loss": 0.4224, "step": 2080 }, { "epoch": 0.7836520434945632, "grad_norm": 1.6614871216284757, "learning_rate": 6.946681083300993e-06, "loss": 0.4303, "step": 2090 }, { "epoch": 0.7874015748031497, "grad_norm": 1.581661595655136, "learning_rate": 6.918676020381745e-06, "loss": 0.4209, "step": 2100 }, { "epoch": 0.791151106111736, "grad_norm": 1.285947328201979, "learning_rate": 6.890600193018039e-06, "loss": 0.4551, "step": 2110 }, { "epoch": 0.7949006374203225, "grad_norm": 1.753075545826239, "learning_rate": 6.8624546367001355e-06, "loss": 0.4372, "step": 2120 }, { "epoch": 0.7986501687289089, "grad_norm": 1.5656569575080206, "learning_rate": 6.83424038949003e-06, "loss": 0.4795, "step": 2130 }, { "epoch": 0.8023997000374953, "grad_norm": 1.5293494682100162, "learning_rate": 6.8059584919831656e-06, "loss": 0.4141, "step": 2140 }, { "epoch": 0.8061492313460817, "grad_norm": 1.41662599322919, "learning_rate": 6.777609987270064e-06, "loss": 0.4739, "step": 2150 }, { "epoch": 0.8098987626546682, "grad_norm": 1.5396310534080353, "learning_rate": 6.7491959208978415e-06, "loss": 0.4225, "step": 2160 }, { "epoch": 0.8136482939632546, "grad_norm": 1.74132222100325, "learning_rate": 6.7207173408316615e-06, "loss": 0.4545, "step": 2170 }, { "epoch": 0.817397825271841, "grad_norm": 1.6679000781333428, "learning_rate": 6.69217529741607e-06, "loss": 0.4234, "step": 2180 }, { "epoch": 0.8211473565804275, "grad_norm": 1.4589180160124926, "learning_rate": 6.6635708433362656e-06, "loss": 0.4751, "step": 2190 }, { "epoch": 0.8248968878890138, "grad_norm": 1.6639826148552832, "learning_rate": 6.634905033579269e-06, "loss": 0.3916, "step": 2200 }, { "epoch": 0.8286464191976003, "grad_norm": 1.400966717030695, "learning_rate": 6.606178925395021e-06, "loss": 0.421, "step": 2210 }, { "epoch": 0.8323959505061868, "grad_norm": 1.6090405587233547, "learning_rate": 6.577393578257375e-06, "loss": 0.4316, "step": 2220 }, { "epoch": 0.8361454818147731, "grad_norm": 1.5917064625404207, "learning_rate": 6.548550053825039e-06, "loss": 0.4224, "step": 2230 }, { "epoch": 0.8398950131233596, "grad_norm": 1.7686504391694868, "learning_rate": 6.519649415902409e-06, "loss": 0.4461, "step": 2240 }, { "epoch": 0.843644544431946, "grad_norm": 1.3400153098243521, "learning_rate": 6.490692730400332e-06, "loss": 0.4394, "step": 2250 }, { "epoch": 0.8473940757405324, "grad_norm": 1.6077638319766128, "learning_rate": 6.461681065296801e-06, "loss": 0.4386, "step": 2260 }, { "epoch": 0.8511436070491188, "grad_norm": 1.732845712449404, "learning_rate": 6.4326154905975615e-06, "loss": 0.4796, "step": 2270 }, { "epoch": 0.8548931383577053, "grad_norm": 1.5667120022244951, "learning_rate": 6.403497078296644e-06, "loss": 0.4214, "step": 2280 }, { "epoch": 0.8586426696662918, "grad_norm": 1.569109385411531, "learning_rate": 6.374326902336838e-06, "loss": 0.4421, "step": 2290 }, { "epoch": 0.8623922009748781, "grad_norm": 1.5268650476493761, "learning_rate": 6.345106038570069e-06, "loss": 0.4465, "step": 2300 }, { "epoch": 0.8661417322834646, "grad_norm": 1.4934422135151564, "learning_rate": 6.3158355647177296e-06, "loss": 0.4412, "step": 2310 }, { "epoch": 0.869891263592051, "grad_norm": 1.4724334638583783, "learning_rate": 6.286516560330926e-06, "loss": 0.4697, "step": 2320 }, { "epoch": 0.8736407949006374, "grad_norm": 1.5428859737010552, "learning_rate": 6.257150106750664e-06, "loss": 0.4529, "step": 2330 }, { "epoch": 0.8773903262092239, "grad_norm": 1.479848479334163, "learning_rate": 6.227737287067968e-06, "loss": 0.4516, "step": 2340 }, { "epoch": 0.8811398575178103, "grad_norm": 1.679894229111639, "learning_rate": 6.198279186083931e-06, "loss": 0.4335, "step": 2350 }, { "epoch": 0.8848893888263967, "grad_norm": 1.425009501571365, "learning_rate": 6.1687768902697045e-06, "loss": 0.4351, "step": 2360 }, { "epoch": 0.8886389201349831, "grad_norm": 1.6684513238640328, "learning_rate": 6.139231487726435e-06, "loss": 0.4246, "step": 2370 }, { "epoch": 0.8923884514435696, "grad_norm": 1.4603204608064504, "learning_rate": 6.1096440681451265e-06, "loss": 0.4103, "step": 2380 }, { "epoch": 0.896137982752156, "grad_norm": 1.292108885445141, "learning_rate": 6.080015722766448e-06, "loss": 0.4193, "step": 2390 }, { "epoch": 0.8998875140607424, "grad_norm": 1.4544811665421629, "learning_rate": 6.050347544340497e-06, "loss": 0.4713, "step": 2400 }, { "epoch": 0.9036370453693289, "grad_norm": 1.6610527367350025, "learning_rate": 6.0206406270864834e-06, "loss": 0.442, "step": 2410 }, { "epoch": 0.9073865766779152, "grad_norm": 1.6837608119256071, "learning_rate": 5.990896066652382e-06, "loss": 0.462, "step": 2420 }, { "epoch": 0.9111361079865017, "grad_norm": 1.4238072477717296, "learning_rate": 5.96111496007452e-06, "loss": 0.4495, "step": 2430 }, { "epoch": 0.9148856392950881, "grad_norm": 1.7653556704382825, "learning_rate": 5.931298405737119e-06, "loss": 0.4253, "step": 2440 }, { "epoch": 0.9186351706036745, "grad_norm": 1.458377217470481, "learning_rate": 5.901447503331775e-06, "loss": 0.4588, "step": 2450 }, { "epoch": 0.922384701912261, "grad_norm": 1.4847373264946722, "learning_rate": 5.871563353816916e-06, "loss": 0.4564, "step": 2460 }, { "epoch": 0.9261342332208474, "grad_norm": 1.418662707390335, "learning_rate": 5.841647059377177e-06, "loss": 0.3921, "step": 2470 }, { "epoch": 0.9298837645294338, "grad_norm": 1.576686818275687, "learning_rate": 5.8116997233827654e-06, "loss": 0.4512, "step": 2480 }, { "epoch": 0.9336332958380202, "grad_norm": 1.4861873000711647, "learning_rate": 5.781722450348762e-06, "loss": 0.4079, "step": 2490 }, { "epoch": 0.9373828271466067, "grad_norm": 1.7041910481198668, "learning_rate": 5.751716345894377e-06, "loss": 0.4139, "step": 2500 }, { "epoch": 0.941132358455193, "grad_norm": 1.4367828784546732, "learning_rate": 5.721682516702183e-06, "loss": 0.4515, "step": 2510 }, { "epoch": 0.9448818897637795, "grad_norm": 1.6009673462846763, "learning_rate": 5.691622070477294e-06, "loss": 0.457, "step": 2520 }, { "epoch": 0.948631421072366, "grad_norm": 1.464560827229555, "learning_rate": 5.661536115906509e-06, "loss": 0.4555, "step": 2530 }, { "epoch": 0.9523809523809523, "grad_norm": 1.4393133398803335, "learning_rate": 5.631425762617424e-06, "loss": 0.4191, "step": 2540 }, { "epoch": 0.9561304836895388, "grad_norm": 1.4630361890611578, "learning_rate": 5.601292121137507e-06, "loss": 0.4471, "step": 2550 }, { "epoch": 0.9598800149981253, "grad_norm": 1.416728692732121, "learning_rate": 5.57113630285314e-06, "loss": 0.4428, "step": 2560 }, { "epoch": 0.9636295463067117, "grad_norm": 1.598991156812034, "learning_rate": 5.5409594199686265e-06, "loss": 0.4533, "step": 2570 }, { "epoch": 0.9673790776152981, "grad_norm": 1.466750310447934, "learning_rate": 5.5107625854651735e-06, "loss": 0.4507, "step": 2580 }, { "epoch": 0.9711286089238845, "grad_norm": 1.948618480814742, "learning_rate": 5.480546913059842e-06, "loss": 0.4338, "step": 2590 }, { "epoch": 0.974878140232471, "grad_norm": 1.7304787312921837, "learning_rate": 5.450313517164472e-06, "loss": 0.4497, "step": 2600 }, { "epoch": 0.9786276715410573, "grad_norm": 1.4475340138633586, "learning_rate": 5.4200635128445755e-06, "loss": 0.4278, "step": 2610 }, { "epoch": 0.9823772028496438, "grad_norm": 1.5286628612711708, "learning_rate": 5.389798015778218e-06, "loss": 0.4404, "step": 2620 }, { "epoch": 0.9861267341582303, "grad_norm": 1.3833644347502816, "learning_rate": 5.35951814221487e-06, "loss": 0.4292, "step": 2630 }, { "epoch": 0.9898762654668166, "grad_norm": 1.5461759126873602, "learning_rate": 5.329225008934228e-06, "loss": 0.4304, "step": 2640 }, { "epoch": 0.9936257967754031, "grad_norm": 1.364017970426797, "learning_rate": 5.298919733205039e-06, "loss": 0.4454, "step": 2650 }, { "epoch": 0.9973753280839895, "grad_norm": 1.6206500426796433, "learning_rate": 5.2686034327438825e-06, "loss": 0.4574, "step": 2660 }, { "epoch": 1.001124859392576, "grad_norm": 1.4509177404341558, "learning_rate": 5.238277225673952e-06, "loss": 0.4395, "step": 2670 }, { "epoch": 1.0048743907011624, "grad_norm": 1.4600370021411608, "learning_rate": 5.2079422304838166e-06, "loss": 0.3524, "step": 2680 }, { "epoch": 1.0086239220097488, "grad_norm": 1.447975270941574, "learning_rate": 5.1775995659861685e-06, "loss": 0.3686, "step": 2690 }, { "epoch": 1.0123734533183353, "grad_norm": 1.3646608201366774, "learning_rate": 5.147250351276557e-06, "loss": 0.3523, "step": 2700 }, { "epoch": 1.0161229846269217, "grad_norm": 1.3779201976186628, "learning_rate": 5.116895705692117e-06, "loss": 0.383, "step": 2710 }, { "epoch": 1.019872515935508, "grad_norm": 1.5184013110135273, "learning_rate": 5.086536748770282e-06, "loss": 0.3637, "step": 2720 }, { "epoch": 1.0236220472440944, "grad_norm": 1.7069783404591081, "learning_rate": 5.0561746002075e-06, "loss": 0.3695, "step": 2730 }, { "epoch": 1.027371578552681, "grad_norm": 1.5529783667917585, "learning_rate": 5.025810379817931e-06, "loss": 0.3752, "step": 2740 }, { "epoch": 1.0311211098612674, "grad_norm": 1.3752792638239564, "learning_rate": 4.995445207492148e-06, "loss": 0.3524, "step": 2750 }, { "epoch": 1.0348706411698538, "grad_norm": 1.3284788467324906, "learning_rate": 4.965080203155829e-06, "loss": 0.3704, "step": 2760 }, { "epoch": 1.0386201724784403, "grad_norm": 1.7254188527509466, "learning_rate": 4.9347164867284655e-06, "loss": 0.3777, "step": 2770 }, { "epoch": 1.0423697037870265, "grad_norm": 1.6551082962510602, "learning_rate": 4.904355178082038e-06, "loss": 0.3084, "step": 2780 }, { "epoch": 1.046119235095613, "grad_norm": 1.6293581536731405, "learning_rate": 4.8739973969997315e-06, "loss": 0.37, "step": 2790 }, { "epoch": 1.0498687664041995, "grad_norm": 1.2423949388143443, "learning_rate": 4.843644263134624e-06, "loss": 0.3512, "step": 2800 }, { "epoch": 1.053618297712786, "grad_norm": 1.4534303829690964, "learning_rate": 4.813296895968396e-06, "loss": 0.3955, "step": 2810 }, { "epoch": 1.0573678290213724, "grad_norm": 1.8305450789655346, "learning_rate": 4.7829564147700405e-06, "loss": 0.363, "step": 2820 }, { "epoch": 1.0611173603299588, "grad_norm": 1.4985187089223733, "learning_rate": 4.752623938554585e-06, "loss": 0.368, "step": 2830 }, { "epoch": 1.064866891638545, "grad_norm": 1.9037220672066917, "learning_rate": 4.722300586041814e-06, "loss": 0.3468, "step": 2840 }, { "epoch": 1.0686164229471316, "grad_norm": 1.4045271420864065, "learning_rate": 4.691987475615016e-06, "loss": 0.3618, "step": 2850 }, { "epoch": 1.072365954255718, "grad_norm": 1.5331342076404493, "learning_rate": 4.66168572527973e-06, "loss": 0.3736, "step": 2860 }, { "epoch": 1.0761154855643045, "grad_norm": 1.5104420025559635, "learning_rate": 4.631396452622512e-06, "loss": 0.3605, "step": 2870 }, { "epoch": 1.079865016872891, "grad_norm": 1.4802274202762906, "learning_rate": 4.601120774769723e-06, "loss": 0.3292, "step": 2880 }, { "epoch": 1.0836145481814774, "grad_norm": 1.6120010180908886, "learning_rate": 4.570859808346312e-06, "loss": 0.3758, "step": 2890 }, { "epoch": 1.0873640794900636, "grad_norm": 1.4368272496025816, "learning_rate": 4.540614669434651e-06, "loss": 0.3694, "step": 2900 }, { "epoch": 1.09111361079865, "grad_norm": 1.4289994143605698, "learning_rate": 4.51038647353336e-06, "loss": 0.3729, "step": 2910 }, { "epoch": 1.0948631421072366, "grad_norm": 1.600619836215753, "learning_rate": 4.480176335516167e-06, "loss": 0.3632, "step": 2920 }, { "epoch": 1.098612673415823, "grad_norm": 1.5449735349304339, "learning_rate": 4.4499853695907914e-06, "loss": 0.3426, "step": 2930 }, { "epoch": 1.1023622047244095, "grad_norm": 1.5402355674131845, "learning_rate": 4.419814689257852e-06, "loss": 0.3251, "step": 2940 }, { "epoch": 1.106111736032996, "grad_norm": 1.7371515597283957, "learning_rate": 4.38966540726979e-06, "loss": 0.3466, "step": 2950 }, { "epoch": 1.1098612673415822, "grad_norm": 1.3731370421000497, "learning_rate": 4.3595386355898416e-06, "loss": 0.3676, "step": 2960 }, { "epoch": 1.1136107986501687, "grad_norm": 2.045661574385117, "learning_rate": 4.329435485351014e-06, "loss": 0.3387, "step": 2970 }, { "epoch": 1.1173603299587551, "grad_norm": 1.7642719703481893, "learning_rate": 4.299357066815115e-06, "loss": 0.3412, "step": 2980 }, { "epoch": 1.1211098612673416, "grad_norm": 1.629878985163515, "learning_rate": 4.269304489331797e-06, "loss": 0.3626, "step": 2990 }, { "epoch": 1.124859392575928, "grad_norm": 1.4514620764935986, "learning_rate": 4.239278861297645e-06, "loss": 0.355, "step": 3000 }, { "epoch": 1.1286089238845145, "grad_norm": 1.6246439053383326, "learning_rate": 4.209281290115298e-06, "loss": 0.3305, "step": 3010 }, { "epoch": 1.132358455193101, "grad_norm": 1.559581043359515, "learning_rate": 4.1793128821526056e-06, "loss": 0.3436, "step": 3020 }, { "epoch": 1.1361079865016872, "grad_norm": 1.3545539819405519, "learning_rate": 4.1493747427018164e-06, "loss": 0.3454, "step": 3030 }, { "epoch": 1.1398575178102737, "grad_norm": 1.4999692429399012, "learning_rate": 4.119467975938827e-06, "loss": 0.3625, "step": 3040 }, { "epoch": 1.1436070491188601, "grad_norm": 1.5582260846660347, "learning_rate": 4.089593684882442e-06, "loss": 0.3595, "step": 3050 }, { "epoch": 1.1473565804274466, "grad_norm": 1.4540830073447943, "learning_rate": 4.059752971353702e-06, "loss": 0.3436, "step": 3060 }, { "epoch": 1.151106111736033, "grad_norm": 1.3630855061085607, "learning_rate": 4.029946935935246e-06, "loss": 0.319, "step": 3070 }, { "epoch": 1.1548556430446195, "grad_norm": 1.2709222239232254, "learning_rate": 4.000176677930716e-06, "loss": 0.3622, "step": 3080 }, { "epoch": 1.1586051743532058, "grad_norm": 1.530493419371819, "learning_rate": 3.970443295324214e-06, "loss": 0.3468, "step": 3090 }, { "epoch": 1.1623547056617922, "grad_norm": 1.7207469805743774, "learning_rate": 3.9407478847398095e-06, "loss": 0.3648, "step": 3100 }, { "epoch": 1.1661042369703787, "grad_norm": 1.3791663354763244, "learning_rate": 3.911091541401087e-06, "loss": 0.3705, "step": 3110 }, { "epoch": 1.1698537682789651, "grad_norm": 1.4925519621708816, "learning_rate": 3.881475359090761e-06, "loss": 0.3815, "step": 3120 }, { "epoch": 1.1736032995875516, "grad_norm": 1.6331215095378881, "learning_rate": 3.851900430110326e-06, "loss": 0.3628, "step": 3130 }, { "epoch": 1.177352830896138, "grad_norm": 1.2428072174152918, "learning_rate": 3.822367845239777e-06, "loss": 0.3504, "step": 3140 }, { "epoch": 1.1811023622047245, "grad_norm": 1.2804950030575, "learning_rate": 3.792878693697376e-06, "loss": 0.3259, "step": 3150 }, { "epoch": 1.1848518935133108, "grad_norm": 1.9443068177583767, "learning_rate": 3.763434063099483e-06, "loss": 0.3591, "step": 3160 }, { "epoch": 1.1886014248218972, "grad_norm": 1.6681828485465113, "learning_rate": 3.7340350394204374e-06, "loss": 0.3408, "step": 3170 }, { "epoch": 1.1923509561304837, "grad_norm": 1.3835566510328632, "learning_rate": 3.7046827069525093e-06, "loss": 0.3517, "step": 3180 }, { "epoch": 1.1961004874390702, "grad_norm": 1.7105018849133968, "learning_rate": 3.6753781482659102e-06, "loss": 0.3384, "step": 3190 }, { "epoch": 1.1998500187476566, "grad_norm": 1.6394418057914444, "learning_rate": 3.646122444168858e-06, "loss": 0.3596, "step": 3200 }, { "epoch": 1.2035995500562429, "grad_norm": 1.3508919610851433, "learning_rate": 3.616916673667724e-06, "loss": 0.3657, "step": 3210 }, { "epoch": 1.2073490813648293, "grad_norm": 1.8613282471420294, "learning_rate": 3.5877619139272313e-06, "loss": 0.3574, "step": 3220 }, { "epoch": 1.2110986126734158, "grad_norm": 1.5889016643021363, "learning_rate": 3.558659240230728e-06, "loss": 0.3352, "step": 3230 }, { "epoch": 1.2148481439820022, "grad_norm": 1.804642874945209, "learning_rate": 3.5296097259405294e-06, "loss": 0.3561, "step": 3240 }, { "epoch": 1.2185976752905887, "grad_norm": 1.6838282811395573, "learning_rate": 3.5006144424583334e-06, "loss": 0.3738, "step": 3250 }, { "epoch": 1.2223472065991752, "grad_norm": 1.351894565655114, "learning_rate": 3.4716744591856945e-06, "loss": 0.3497, "step": 3260 }, { "epoch": 1.2260967379077616, "grad_norm": 1.614477056987546, "learning_rate": 3.442790843484598e-06, "loss": 0.3796, "step": 3270 }, { "epoch": 1.2298462692163479, "grad_norm": 1.4372889987652464, "learning_rate": 3.413964660638079e-06, "loss": 0.3577, "step": 3280 }, { "epoch": 1.2335958005249343, "grad_norm": 1.5297663651555256, "learning_rate": 3.3851969738109423e-06, "loss": 0.3695, "step": 3290 }, { "epoch": 1.2373453318335208, "grad_norm": 1.5119914959987049, "learning_rate": 3.3564888440105474e-06, "loss": 0.3224, "step": 3300 }, { "epoch": 1.2410948631421073, "grad_norm": 1.6479969063384772, "learning_rate": 3.3278413300476743e-06, "loss": 0.3746, "step": 3310 }, { "epoch": 1.2448443944506937, "grad_norm": 1.6318702190896464, "learning_rate": 3.2992554884974766e-06, "loss": 0.3541, "step": 3320 }, { "epoch": 1.24859392575928, "grad_norm": 1.3442025076621051, "learning_rate": 3.270732373660513e-06, "loss": 0.3436, "step": 3330 }, { "epoch": 1.2523434570678664, "grad_norm": 1.8454214496196244, "learning_rate": 3.2422730375238566e-06, "loss": 0.3541, "step": 3340 }, { "epoch": 1.256092988376453, "grad_norm": 1.3677639488210138, "learning_rate": 3.213878529722304e-06, "loss": 0.3795, "step": 3350 }, { "epoch": 1.2598425196850394, "grad_norm": 1.5530265905857163, "learning_rate": 3.1855498974996557e-06, "loss": 0.3304, "step": 3360 }, { "epoch": 1.2635920509936258, "grad_norm": 1.5275420632742793, "learning_rate": 3.1572881856700967e-06, "loss": 0.3702, "step": 3370 }, { "epoch": 1.2673415823022123, "grad_norm": 1.4193327163467433, "learning_rate": 3.1290944365796606e-06, "loss": 0.3681, "step": 3380 }, { "epoch": 1.2710911136107987, "grad_norm": 1.5233262834487242, "learning_rate": 3.100969690067782e-06, "loss": 0.3494, "step": 3390 }, { "epoch": 1.2748406449193852, "grad_norm": 1.5818787485233796, "learning_rate": 3.0729149834289503e-06, "loss": 0.3519, "step": 3400 }, { "epoch": 1.2785901762279714, "grad_norm": 1.509245223830659, "learning_rate": 3.044931351374451e-06, "loss": 0.3583, "step": 3410 }, { "epoch": 1.282339707536558, "grad_norm": 1.4382211580420754, "learning_rate": 3.0170198259942006e-06, "loss": 0.3606, "step": 3420 }, { "epoch": 1.2860892388451444, "grad_norm": 1.7433417851229887, "learning_rate": 2.9891814367186855e-06, "loss": 0.3606, "step": 3430 }, { "epoch": 1.2898387701537308, "grad_norm": 1.9997941282624365, "learning_rate": 2.9614172102809923e-06, "loss": 0.3454, "step": 3440 }, { "epoch": 1.2935883014623173, "grad_norm": 1.5421328119182844, "learning_rate": 2.933728170678938e-06, "loss": 0.3346, "step": 3450 }, { "epoch": 1.2973378327709035, "grad_norm": 1.523428044583653, "learning_rate": 2.9061153391373086e-06, "loss": 0.3321, "step": 3460 }, { "epoch": 1.30108736407949, "grad_norm": 1.62939013511284, "learning_rate": 2.878579734070187e-06, "loss": 0.3138, "step": 3470 }, { "epoch": 1.3048368953880765, "grad_norm": 1.5230194793312595, "learning_rate": 2.8511223710434016e-06, "loss": 0.3459, "step": 3480 }, { "epoch": 1.308586426696663, "grad_norm": 1.4108776056216374, "learning_rate": 2.823744262737059e-06, "loss": 0.3616, "step": 3490 }, { "epoch": 1.3123359580052494, "grad_norm": 1.491688451645582, "learning_rate": 2.796446418908202e-06, "loss": 0.3401, "step": 3500 }, { "epoch": 1.3160854893138358, "grad_norm": 1.423389485727877, "learning_rate": 2.769229846353563e-06, "loss": 0.3558, "step": 3510 }, { "epoch": 1.3198350206224223, "grad_norm": 1.7410109557749134, "learning_rate": 2.7420955488724447e-06, "loss": 0.3387, "step": 3520 }, { "epoch": 1.3235845519310085, "grad_norm": 1.310812307150263, "learning_rate": 2.7150445272296714e-06, "loss": 0.3636, "step": 3530 }, { "epoch": 1.327334083239595, "grad_norm": 1.7582343889806566, "learning_rate": 2.6880777791187097e-06, "loss": 0.345, "step": 3540 }, { "epoch": 1.3310836145481815, "grad_norm": 1.6584673745064358, "learning_rate": 2.6611962991248487e-06, "loss": 0.3387, "step": 3550 }, { "epoch": 1.334833145856768, "grad_norm": 1.9434097962048138, "learning_rate": 2.6344010786885264e-06, "loss": 0.3719, "step": 3560 }, { "epoch": 1.3385826771653544, "grad_norm": 1.4952229222908306, "learning_rate": 2.6076931060687704e-06, "loss": 0.3562, "step": 3570 }, { "epoch": 1.3423322084739406, "grad_norm": 1.635877562304977, "learning_rate": 2.581073366306733e-06, "loss": 0.3542, "step": 3580 }, { "epoch": 1.346081739782527, "grad_norm": 1.4652098577237482, "learning_rate": 2.5545428411893717e-06, "loss": 0.3099, "step": 3590 }, { "epoch": 1.3498312710911136, "grad_norm": 1.4698865184832401, "learning_rate": 2.528102509213244e-06, "loss": 0.3573, "step": 3600 }, { "epoch": 1.3535808023997, "grad_norm": 1.793575097950632, "learning_rate": 2.5017533455484034e-06, "loss": 0.3397, "step": 3610 }, { "epoch": 1.3573303337082865, "grad_norm": 1.5680213075061908, "learning_rate": 2.4754963220024452e-06, "loss": 0.3403, "step": 3620 }, { "epoch": 1.361079865016873, "grad_norm": 1.3060785948128115, "learning_rate": 2.4493324069846585e-06, "loss": 0.3564, "step": 3630 }, { "epoch": 1.3648293963254594, "grad_norm": 1.8035421253784634, "learning_rate": 2.423262565470317e-06, "loss": 0.3766, "step": 3640 }, { "epoch": 1.3685789276340459, "grad_norm": 1.918906691968443, "learning_rate": 2.3972877589650777e-06, "loss": 0.353, "step": 3650 }, { "epoch": 1.3723284589426321, "grad_norm": 1.5163031286118671, "learning_rate": 2.3714089454695256e-06, "loss": 0.3513, "step": 3660 }, { "epoch": 1.3760779902512186, "grad_norm": 1.6026049538693206, "learning_rate": 2.345627079443844e-06, "loss": 0.3648, "step": 3670 }, { "epoch": 1.379827521559805, "grad_norm": 1.596617717069379, "learning_rate": 2.3199431117726035e-06, "loss": 0.365, "step": 3680 }, { "epoch": 1.3835770528683915, "grad_norm": 1.5993573229954199, "learning_rate": 2.2943579897296947e-06, "loss": 0.3492, "step": 3690 }, { "epoch": 1.3873265841769777, "grad_norm": 1.3967315640962592, "learning_rate": 2.2688726569433994e-06, "loss": 0.3069, "step": 3700 }, { "epoch": 1.3910761154855642, "grad_norm": 1.3448302981616773, "learning_rate": 2.2434880533615738e-06, "loss": 0.3247, "step": 3710 }, { "epoch": 1.3948256467941507, "grad_norm": 1.9178008199538998, "learning_rate": 2.2182051152169885e-06, "loss": 0.3312, "step": 3720 }, { "epoch": 1.3985751781027371, "grad_norm": 1.267530325769369, "learning_rate": 2.1930247749928047e-06, "loss": 0.3486, "step": 3730 }, { "epoch": 1.4023247094113236, "grad_norm": 1.7874206206982515, "learning_rate": 2.1679479613881675e-06, "loss": 0.3521, "step": 3740 }, { "epoch": 1.40607424071991, "grad_norm": 1.4367358186199526, "learning_rate": 2.1429755992839663e-06, "loss": 0.3555, "step": 3750 }, { "epoch": 1.4098237720284965, "grad_norm": 1.5221931463416962, "learning_rate": 2.1181086097087204e-06, "loss": 0.3481, "step": 3760 }, { "epoch": 1.413573303337083, "grad_norm": 1.6561648823951545, "learning_rate": 2.093347909804607e-06, "loss": 0.361, "step": 3770 }, { "epoch": 1.4173228346456692, "grad_norm": 1.4838892164710282, "learning_rate": 2.068694412793634e-06, "loss": 0.3428, "step": 3780 }, { "epoch": 1.4210723659542557, "grad_norm": 1.5968851127215336, "learning_rate": 2.0441490279439675e-06, "loss": 0.3344, "step": 3790 }, { "epoch": 1.4248218972628421, "grad_norm": 1.7687806424405534, "learning_rate": 2.0197126605363854e-06, "loss": 0.3518, "step": 3800 }, { "epoch": 1.4285714285714286, "grad_norm": 1.6703057515265487, "learning_rate": 1.995386211830895e-06, "loss": 0.3276, "step": 3810 }, { "epoch": 1.432320959880015, "grad_norm": 1.7484761838277776, "learning_rate": 1.971170579033489e-06, "loss": 0.3361, "step": 3820 }, { "epoch": 1.4360704911886013, "grad_norm": 1.3488988878835058, "learning_rate": 1.947066655263064e-06, "loss": 0.3634, "step": 3830 }, { "epoch": 1.4398200224971878, "grad_norm": 1.5467802523956982, "learning_rate": 1.923075329518467e-06, "loss": 0.3314, "step": 3840 }, { "epoch": 1.4435695538057742, "grad_norm": 1.6288296211280038, "learning_rate": 1.8991974866457162e-06, "loss": 0.3508, "step": 3850 }, { "epoch": 1.4473190851143607, "grad_norm": 1.505990488917917, "learning_rate": 1.8754340073053677e-06, "loss": 0.3308, "step": 3860 }, { "epoch": 1.4510686164229472, "grad_norm": 1.8341836419010746, "learning_rate": 1.851785767940027e-06, "loss": 0.3409, "step": 3870 }, { "epoch": 1.4548181477315336, "grad_norm": 1.6912554488210527, "learning_rate": 1.8282536407420287e-06, "loss": 0.3465, "step": 3880 }, { "epoch": 1.45856767904012, "grad_norm": 1.840592484384188, "learning_rate": 1.8048384936212744e-06, "loss": 0.3225, "step": 3890 }, { "epoch": 1.4623172103487065, "grad_norm": 1.7604049267997468, "learning_rate": 1.7815411901732093e-06, "loss": 0.3559, "step": 3900 }, { "epoch": 1.4660667416572928, "grad_norm": 1.5746735913936412, "learning_rate": 1.7583625896469814e-06, "loss": 0.3528, "step": 3910 }, { "epoch": 1.4698162729658792, "grad_norm": 1.6369916331260816, "learning_rate": 1.7353035469137498e-06, "loss": 0.3493, "step": 3920 }, { "epoch": 1.4735658042744657, "grad_norm": 1.4741093193120587, "learning_rate": 1.7123649124351516e-06, "loss": 0.3337, "step": 3930 }, { "epoch": 1.4773153355830522, "grad_norm": 1.703066627567801, "learning_rate": 1.6895475322319315e-06, "loss": 0.3391, "step": 3940 }, { "epoch": 1.4810648668916384, "grad_norm": 1.637755304727519, "learning_rate": 1.6668522478527548e-06, "loss": 0.3237, "step": 3950 }, { "epoch": 1.4848143982002249, "grad_norm": 1.5269566908036458, "learning_rate": 1.6442798963431523e-06, "loss": 0.2986, "step": 3960 }, { "epoch": 1.4885639295088113, "grad_norm": 1.6781854582303293, "learning_rate": 1.6218313102146544e-06, "loss": 0.3303, "step": 3970 }, { "epoch": 1.4923134608173978, "grad_norm": 1.821466701971633, "learning_rate": 1.599507317414094e-06, "loss": 0.3369, "step": 3980 }, { "epoch": 1.4960629921259843, "grad_norm": 1.2913502212146863, "learning_rate": 1.5773087412930566e-06, "loss": 0.336, "step": 3990 }, { "epoch": 1.4998125234345707, "grad_norm": 1.7860072947446817, "learning_rate": 1.5552364005775222e-06, "loss": 0.3316, "step": 4000 }, { "epoch": 1.5035620547431572, "grad_norm": 1.6773206915152195, "learning_rate": 1.5332911093376718e-06, "loss": 0.3522, "step": 4010 }, { "epoch": 1.5073115860517436, "grad_norm": 1.5358531503439834, "learning_rate": 1.5114736769578525e-06, "loss": 0.3304, "step": 4020 }, { "epoch": 1.51106111736033, "grad_norm": 1.4489287522840915, "learning_rate": 1.489784908106734e-06, "loss": 0.3393, "step": 4030 }, { "epoch": 1.5148106486689163, "grad_norm": 1.3479943861270867, "learning_rate": 1.4682256027076313e-06, "loss": 0.3322, "step": 4040 }, { "epoch": 1.5185601799775028, "grad_norm": 1.7269227584088385, "learning_rate": 1.446796555908997e-06, "loss": 0.3122, "step": 4050 }, { "epoch": 1.5223097112860893, "grad_norm": 1.8403178217996174, "learning_rate": 1.425498558055095e-06, "loss": 0.307, "step": 4060 }, { "epoch": 1.5260592425946755, "grad_norm": 1.438610433972195, "learning_rate": 1.4043323946568593e-06, "loss": 0.3159, "step": 4070 }, { "epoch": 1.529808773903262, "grad_norm": 1.2736382379202882, "learning_rate": 1.3832988463629115e-06, "loss": 0.324, "step": 4080 }, { "epoch": 1.5335583052118484, "grad_norm": 1.6346184941099664, "learning_rate": 1.3623986889307755e-06, "loss": 0.3462, "step": 4090 }, { "epoch": 1.537307836520435, "grad_norm": 1.8534023922988863, "learning_rate": 1.3416326931982677e-06, "loss": 0.3253, "step": 4100 }, { "epoch": 1.5410573678290214, "grad_norm": 1.1624126889223485, "learning_rate": 1.3210016250550605e-06, "loss": 0.321, "step": 4110 }, { "epoch": 1.5448068991376078, "grad_norm": 1.695674838282803, "learning_rate": 1.3005062454144407e-06, "loss": 0.316, "step": 4120 }, { "epoch": 1.5485564304461943, "grad_norm": 1.579979524547565, "learning_rate": 1.28014731018524e-06, "loss": 0.3464, "step": 4130 }, { "epoch": 1.5523059617547807, "grad_norm": 1.7648858646585621, "learning_rate": 1.2599255702439667e-06, "loss": 0.3455, "step": 4140 }, { "epoch": 1.5560554930633672, "grad_norm": 1.8186319486307774, "learning_rate": 1.2398417714070955e-06, "loss": 0.3436, "step": 4150 }, { "epoch": 1.5598050243719535, "grad_norm": 1.5892756908867762, "learning_rate": 1.2198966544035728e-06, "loss": 0.3192, "step": 4160 }, { "epoch": 1.56355455568054, "grad_norm": 1.3416851449864013, "learning_rate": 1.2000909548474964e-06, "loss": 0.3063, "step": 4170 }, { "epoch": 1.5673040869891264, "grad_norm": 1.6068288131459285, "learning_rate": 1.1804254032109774e-06, "loss": 0.3164, "step": 4180 }, { "epoch": 1.5710536182977128, "grad_norm": 1.6405737001520029, "learning_rate": 1.1609007247972031e-06, "loss": 0.3438, "step": 4190 }, { "epoch": 1.574803149606299, "grad_norm": 1.6670808254579221, "learning_rate": 1.1415176397136919e-06, "loss": 0.3033, "step": 4200 }, { "epoch": 1.5785526809148855, "grad_norm": 1.7762598543243198, "learning_rate": 1.1222768628457236e-06, "loss": 0.3132, "step": 4210 }, { "epoch": 1.582302212223472, "grad_norm": 1.5521757184387595, "learning_rate": 1.1031791038299805e-06, "loss": 0.2986, "step": 4220 }, { "epoch": 1.5860517435320585, "grad_norm": 1.7195653520711562, "learning_rate": 1.0842250670283745e-06, "loss": 0.3424, "step": 4230 }, { "epoch": 1.589801274840645, "grad_norm": 1.711426929532078, "learning_rate": 1.0654154515020648e-06, "loss": 0.357, "step": 4240 }, { "epoch": 1.5935508061492314, "grad_norm": 1.5008204279258828, "learning_rate": 1.0467509509856772e-06, "loss": 0.3364, "step": 4250 }, { "epoch": 1.5973003374578179, "grad_norm": 1.662172814163422, "learning_rate": 1.0282322538617217e-06, "loss": 0.3303, "step": 4260 }, { "epoch": 1.6010498687664043, "grad_norm": 1.4480786096814473, "learning_rate": 1.0098600431351963e-06, "loss": 0.3321, "step": 4270 }, { "epoch": 1.6047994000749908, "grad_norm": 1.6965447079983016, "learning_rate": 9.916349964084e-07, "loss": 0.322, "step": 4280 }, { "epoch": 1.608548931383577, "grad_norm": 1.4650791774635374, "learning_rate": 9.735577858559458e-07, "loss": 0.3224, "step": 4290 }, { "epoch": 1.6122984626921635, "grad_norm": 1.5856693015320342, "learning_rate": 9.556290781999627e-07, "loss": 0.3304, "step": 4300 }, { "epoch": 1.61604799400075, "grad_norm": 1.7858329746245327, "learning_rate": 9.378495346855088e-07, "loss": 0.3302, "step": 4310 }, { "epoch": 1.6197975253093362, "grad_norm": 1.678782769089936, "learning_rate": 9.202198110561817e-07, "loss": 0.3546, "step": 4320 }, { "epoch": 1.6235470566179226, "grad_norm": 1.3495582321203792, "learning_rate": 9.027405575299402e-07, "loss": 0.2868, "step": 4330 }, { "epoch": 1.627296587926509, "grad_norm": 1.6161226140896592, "learning_rate": 8.854124187751101e-07, "loss": 0.3431, "step": 4340 }, { "epoch": 1.6310461192350956, "grad_norm": 1.6189885117319822, "learning_rate": 8.682360338866213e-07, "loss": 0.331, "step": 4350 }, { "epoch": 1.634795650543682, "grad_norm": 1.7743940251650934, "learning_rate": 8.512120363624276e-07, "loss": 0.3176, "step": 4360 }, { "epoch": 1.6385451818522685, "grad_norm": 1.631233182846724, "learning_rate": 8.343410540801456e-07, "loss": 0.3225, "step": 4370 }, { "epoch": 1.642294713160855, "grad_norm": 1.7305485511210092, "learning_rate": 8.176237092738986e-07, "loss": 0.3273, "step": 4380 }, { "epoch": 1.6460442444694414, "grad_norm": 1.7423707337184162, "learning_rate": 8.010606185113628e-07, "loss": 0.3223, "step": 4390 }, { "epoch": 1.6497937757780279, "grad_norm": 1.7521485149354392, "learning_rate": 7.846523926710314e-07, "loss": 0.3432, "step": 4400 }, { "epoch": 1.6535433070866141, "grad_norm": 1.478190837960175, "learning_rate": 7.683996369196839e-07, "loss": 0.309, "step": 4410 }, { "epoch": 1.6572928383952006, "grad_norm": 1.6732581538468771, "learning_rate": 7.523029506900636e-07, "loss": 0.3449, "step": 4420 }, { "epoch": 1.661042369703787, "grad_norm": 1.6593549523755358, "learning_rate": 7.36362927658772e-07, "loss": 0.332, "step": 4430 }, { "epoch": 1.6647919010123733, "grad_norm": 1.5520741968805116, "learning_rate": 7.205801557243702e-07, "loss": 0.3481, "step": 4440 }, { "epoch": 1.6685414323209597, "grad_norm": 1.4765600184430352, "learning_rate": 7.04955216985701e-07, "loss": 0.3202, "step": 4450 }, { "epoch": 1.6722909636295462, "grad_norm": 1.781655129079553, "learning_rate": 6.894886877204155e-07, "loss": 0.3104, "step": 4460 }, { "epoch": 1.6760404949381327, "grad_norm": 1.949451182744521, "learning_rate": 6.74181138363717e-07, "loss": 0.3484, "step": 4470 }, { "epoch": 1.6797900262467191, "grad_norm": 1.8715453509538882, "learning_rate": 6.590331334873318e-07, "loss": 0.3169, "step": 4480 }, { "epoch": 1.6835395575553056, "grad_norm": 1.5174991101570423, "learning_rate": 6.440452317786744e-07, "loss": 0.3256, "step": 4490 }, { "epoch": 1.687289088863892, "grad_norm": 1.9701424428551593, "learning_rate": 6.292179860202507e-07, "loss": 0.2942, "step": 4500 }, { "epoch": 1.6910386201724785, "grad_norm": 1.7351929428622102, "learning_rate": 6.145519430692681e-07, "loss": 0.3133, "step": 4510 }, { "epoch": 1.694788151481065, "grad_norm": 1.4493386906180452, "learning_rate": 6.000476438374653e-07, "loss": 0.3329, "step": 4520 }, { "epoch": 1.6985376827896514, "grad_norm": 1.506254801365949, "learning_rate": 5.857056232711611e-07, "loss": 0.3305, "step": 4530 }, { "epoch": 1.7022872140982377, "grad_norm": 1.841446151238675, "learning_rate": 5.715264103315299e-07, "loss": 0.3164, "step": 4540 }, { "epoch": 1.7060367454068242, "grad_norm": 1.1520694398410507, "learning_rate": 5.57510527975087e-07, "loss": 0.3127, "step": 4550 }, { "epoch": 1.7097862767154106, "grad_norm": 1.6058041812798236, "learning_rate": 5.436584931344024e-07, "loss": 0.345, "step": 4560 }, { "epoch": 1.7135358080239969, "grad_norm": 1.6897542929200635, "learning_rate": 5.299708166990397e-07, "loss": 0.3008, "step": 4570 }, { "epoch": 1.7172853393325833, "grad_norm": 1.741788100213935, "learning_rate": 5.164480034967056e-07, "loss": 0.3179, "step": 4580 }, { "epoch": 1.7210348706411698, "grad_norm": 1.4158674733181444, "learning_rate": 5.030905522746366e-07, "loss": 0.3351, "step": 4590 }, { "epoch": 1.7247844019497562, "grad_norm": 1.7261515020882374, "learning_rate": 4.89898955681205e-07, "loss": 0.331, "step": 4600 }, { "epoch": 1.7285339332583427, "grad_norm": 1.7604754165078564, "learning_rate": 4.768737002477447e-07, "loss": 0.3334, "step": 4610 }, { "epoch": 1.7322834645669292, "grad_norm": 1.977362808066586, "learning_rate": 4.6401526637060876e-07, "loss": 0.3551, "step": 4620 }, { "epoch": 1.7360329958755156, "grad_norm": 1.734146871262949, "learning_rate": 4.5132412829345275e-07, "loss": 0.3509, "step": 4630 }, { "epoch": 1.739782527184102, "grad_norm": 1.6265547659136985, "learning_rate": 4.3880075408974486e-07, "loss": 0.3581, "step": 4640 }, { "epoch": 1.7435320584926886, "grad_norm": 1.4873642055577037, "learning_rate": 4.2644560564549687e-07, "loss": 0.3348, "step": 4650 }, { "epoch": 1.7472815898012748, "grad_norm": 1.6466902230897535, "learning_rate": 4.1425913864223346e-07, "loss": 0.3589, "step": 4660 }, { "epoch": 1.7510311211098613, "grad_norm": 1.622218109412269, "learning_rate": 4.0224180254018807e-07, "loss": 0.3478, "step": 4670 }, { "epoch": 1.7547806524184477, "grad_norm": 2.101702024311268, "learning_rate": 3.9039404056171846e-07, "loss": 0.3571, "step": 4680 }, { "epoch": 1.758530183727034, "grad_norm": 1.6692588350741207, "learning_rate": 3.7871628967496633e-07, "loss": 0.305, "step": 4690 }, { "epoch": 1.7622797150356204, "grad_norm": 1.7690633175873733, "learning_rate": 3.672089805777396e-07, "loss": 0.3402, "step": 4700 }, { "epoch": 1.7660292463442069, "grad_norm": 1.7260409999717325, "learning_rate": 3.558725376816247e-07, "loss": 0.3392, "step": 4710 }, { "epoch": 1.7697787776527933, "grad_norm": 1.5368178184553536, "learning_rate": 3.447073790963351e-07, "loss": 0.3306, "step": 4720 }, { "epoch": 1.7735283089613798, "grad_norm": 1.7279863649017744, "learning_rate": 3.337139166142961e-07, "loss": 0.3577, "step": 4730 }, { "epoch": 1.7772778402699663, "grad_norm": 1.5951368264599288, "learning_rate": 3.228925556954443e-07, "loss": 0.3197, "step": 4740 }, { "epoch": 1.7810273715785527, "grad_norm": 1.683957269882327, "learning_rate": 3.1224369545228675e-07, "loss": 0.3323, "step": 4750 }, { "epoch": 1.7847769028871392, "grad_norm": 1.525225950631349, "learning_rate": 3.017677286351739e-07, "loss": 0.3445, "step": 4760 }, { "epoch": 1.7885264341957257, "grad_norm": 1.4498272908309162, "learning_rate": 2.914650416178155e-07, "loss": 0.3178, "step": 4770 }, { "epoch": 1.7922759655043121, "grad_norm": 1.5337860505438168, "learning_rate": 2.8133601438303015e-07, "loss": 0.2986, "step": 4780 }, { "epoch": 1.7960254968128984, "grad_norm": 1.5146072225242588, "learning_rate": 2.7138102050873305e-07, "loss": 0.3079, "step": 4790 }, { "epoch": 1.7997750281214848, "grad_norm": 1.6032344984759979, "learning_rate": 2.6160042715415335e-07, "loss": 0.3233, "step": 4800 }, { "epoch": 1.8035245594300713, "grad_norm": 1.3518923570485677, "learning_rate": 2.519945950462965e-07, "loss": 0.3443, "step": 4810 }, { "epoch": 1.8072740907386575, "grad_norm": 1.6243326351035674, "learning_rate": 2.425638784666395e-07, "loss": 0.3377, "step": 4820 }, { "epoch": 1.811023622047244, "grad_norm": 1.6220735555992578, "learning_rate": 2.3330862523806174e-07, "loss": 0.3502, "step": 4830 }, { "epoch": 1.8147731533558304, "grad_norm": 1.5824242486219604, "learning_rate": 2.2422917671201917e-07, "loss": 0.2909, "step": 4840 }, { "epoch": 1.818522684664417, "grad_norm": 1.5587909505486748, "learning_rate": 2.1532586775595443e-07, "loss": 0.327, "step": 4850 }, { "epoch": 1.8222722159730034, "grad_norm": 1.5564348831807615, "learning_rate": 2.0659902674094456e-07, "loss": 0.3329, "step": 4860 }, { "epoch": 1.8260217472815898, "grad_norm": 1.520143961544948, "learning_rate": 1.9804897552959112e-07, "loss": 0.3148, "step": 4870 }, { "epoch": 1.8297712785901763, "grad_norm": 1.4864600634323033, "learning_rate": 1.8967602946415088e-07, "loss": 0.3079, "step": 4880 }, { "epoch": 1.8335208098987628, "grad_norm": 2.010638171832356, "learning_rate": 1.8148049735490115e-07, "loss": 0.3382, "step": 4890 }, { "epoch": 1.8372703412073492, "grad_norm": 1.5880312488642092, "learning_rate": 1.734626814687551e-07, "loss": 0.3393, "step": 4900 }, { "epoch": 1.8410198725159355, "grad_norm": 1.713755576709262, "learning_rate": 1.6562287751811124e-07, "loss": 0.3297, "step": 4910 }, { "epoch": 1.844769403824522, "grad_norm": 1.773055177354968, "learning_rate": 1.5796137464994643e-07, "loss": 0.3318, "step": 4920 }, { "epoch": 1.8485189351331084, "grad_norm": 1.630439406283337, "learning_rate": 1.5047845543515184e-07, "loss": 0.3234, "step": 4930 }, { "epoch": 1.8522684664416946, "grad_norm": 1.592923423512905, "learning_rate": 1.4317439585811165e-07, "loss": 0.3464, "step": 4940 }, { "epoch": 1.856017997750281, "grad_norm": 2.2673787792706497, "learning_rate": 1.3604946530652695e-07, "loss": 0.3498, "step": 4950 }, { "epoch": 1.8597675290588676, "grad_norm": 1.5030493168671641, "learning_rate": 1.291039265614741e-07, "loss": 0.3569, "step": 4960 }, { "epoch": 1.863517060367454, "grad_norm": 1.513102418957751, "learning_rate": 1.2233803578771686e-07, "loss": 0.3194, "step": 4970 }, { "epoch": 1.8672665916760405, "grad_norm": 1.6929638834211231, "learning_rate": 1.1575204252425975e-07, "loss": 0.3228, "step": 4980 }, { "epoch": 1.871016122984627, "grad_norm": 1.8435380984698735, "learning_rate": 1.0934618967514188e-07, "loss": 0.3571, "step": 4990 }, { "epoch": 1.8747656542932134, "grad_norm": 1.7849767075923193, "learning_rate": 1.0312071350047693e-07, "loss": 0.3038, "step": 5000 }, { "epoch": 1.8785151856017999, "grad_norm": 1.5542605612599745, "learning_rate": 9.707584360774458e-08, "loss": 0.3437, "step": 5010 }, { "epoch": 1.8822647169103863, "grad_norm": 1.3826537469939908, "learning_rate": 9.121180294331844e-08, "loss": 0.3044, "step": 5020 }, { "epoch": 1.8860142482189728, "grad_norm": 1.6972888138472486, "learning_rate": 8.552880778424144e-08, "loss": 0.3561, "step": 5030 }, { "epoch": 1.889763779527559, "grad_norm": 1.8063921975208026, "learning_rate": 8.002706773025615e-08, "loss": 0.3465, "step": 5040 }, { "epoch": 1.8935133108361455, "grad_norm": 1.6103754092895761, "learning_rate": 7.470678569606537e-08, "loss": 0.3468, "step": 5050 }, { "epoch": 1.897262842144732, "grad_norm": 1.3443955816887398, "learning_rate": 6.956815790385596e-08, "loss": 0.277, "step": 5060 }, { "epoch": 1.9010123734533182, "grad_norm": 1.7402172733992678, "learning_rate": 6.461137387605787e-08, "loss": 0.3247, "step": 5070 }, { "epoch": 1.9047619047619047, "grad_norm": 1.601756671478112, "learning_rate": 5.98366164283537e-08, "loss": 0.3453, "step": 5080 }, { "epoch": 1.9085114360704911, "grad_norm": 1.6998445628464385, "learning_rate": 5.5244061662937944e-08, "loss": 0.3383, "step": 5090 }, { "epoch": 1.9122609673790776, "grad_norm": 1.8604325500409327, "learning_rate": 5.0833878962022743e-08, "loss": 0.3203, "step": 5100 }, { "epoch": 1.916010498687664, "grad_norm": 1.712899852847211, "learning_rate": 4.66062309815879e-08, "loss": 0.3184, "step": 5110 }, { "epoch": 1.9197600299962505, "grad_norm": 1.558964923052988, "learning_rate": 4.256127364538343e-08, "loss": 0.3247, "step": 5120 }, { "epoch": 1.923509561304837, "grad_norm": 1.5938262662798197, "learning_rate": 3.869915613917863e-08, "loss": 0.3327, "step": 5130 }, { "epoch": 1.9272590926134234, "grad_norm": 1.7604701222470183, "learning_rate": 3.5020020905261465e-08, "loss": 0.3243, "step": 5140 }, { "epoch": 1.93100862392201, "grad_norm": 1.6948672950425423, "learning_rate": 3.152400363718056e-08, "loss": 0.327, "step": 5150 }, { "epoch": 1.9347581552305961, "grad_norm": 1.5246438177325667, "learning_rate": 2.8211233274745842e-08, "loss": 0.3304, "step": 5160 }, { "epoch": 1.9385076865391826, "grad_norm": 1.6236324056330804, "learning_rate": 2.5081831999270167e-08, "loss": 0.3512, "step": 5170 }, { "epoch": 1.942257217847769, "grad_norm": 1.6776897373076485, "learning_rate": 2.2135915229061776e-08, "loss": 0.3286, "step": 5180 }, { "epoch": 1.9460067491563553, "grad_norm": 1.7792412049607735, "learning_rate": 1.9373591615171605e-08, "loss": 0.3111, "step": 5190 }, { "epoch": 1.9497562804649418, "grad_norm": 1.4131068603769794, "learning_rate": 1.679496303738204e-08, "loss": 0.3209, "step": 5200 }, { "epoch": 1.9535058117735282, "grad_norm": 1.600093625948686, "learning_rate": 1.4400124600450482e-08, "loss": 0.3095, "step": 5210 }, { "epoch": 1.9572553430821147, "grad_norm": 2.078606324481016, "learning_rate": 1.2189164630603268e-08, "loss": 0.3264, "step": 5220 }, { "epoch": 1.9610048743907011, "grad_norm": 1.4610778030098712, "learning_rate": 1.0162164672276598e-08, "loss": 0.3256, "step": 5230 }, { "epoch": 1.9647544056992876, "grad_norm": 1.830688393235122, "learning_rate": 8.319199485108397e-09, "loss": 0.3388, "step": 5240 }, { "epoch": 1.968503937007874, "grad_norm": 1.4910118526980476, "learning_rate": 6.660337041183851e-09, "loss": 0.3069, "step": 5250 }, { "epoch": 1.9722534683164605, "grad_norm": 1.929456675739591, "learning_rate": 5.1856385225246275e-09, "loss": 0.3483, "step": 5260 }, { "epoch": 1.976002999625047, "grad_norm": 1.6027522115048347, "learning_rate": 3.895158318835135e-09, "loss": 0.3363, "step": 5270 }, { "epoch": 1.9797525309336335, "grad_norm": 1.5571160776029904, "learning_rate": 2.7889440254952328e-09, "loss": 0.318, "step": 5280 }, { "epoch": 1.9835020622422197, "grad_norm": 1.9746053079305605, "learning_rate": 1.8670364418060803e-09, "loss": 0.3173, "step": 5290 }, { "epoch": 1.9872515935508062, "grad_norm": 1.7744476329786605, "learning_rate": 1.1294695694841207e-09, "loss": 0.3242, "step": 5300 }, { "epoch": 1.9910011248593926, "grad_norm": 1.597146803195604, "learning_rate": 5.762706114076367e-10, "loss": 0.3281, "step": 5310 }, { "epoch": 1.9947506561679789, "grad_norm": 1.2904621286243896, "learning_rate": 2.0745997061255575e-10, "loss": 0.3285, "step": 5320 }, { "epoch": 1.9985001874765653, "grad_norm": 1.713283248366531, "learning_rate": 2.3051249541383715e-11, "loss": 0.3271, "step": 5330 }, { "epoch": 2.0, "step": 5334, "total_flos": 119225402720256.0, "train_loss": 0.41984647874488873, "train_runtime": 6257.3371, "train_samples_per_second": 13.637, "train_steps_per_second": 0.852 } ], "logging_steps": 10, "max_steps": 5334, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 119225402720256.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }