{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 2423, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0004127115146512588, "grad_norm": 25.235434647385926, "learning_rate": 4.1152263374485605e-08, "loss": 1.4522, "step": 1 }, { "epoch": 0.0020635575732562937, "grad_norm": 23.516883014791038, "learning_rate": 2.05761316872428e-07, "loss": 1.4159, "step": 5 }, { "epoch": 0.004127115146512587, "grad_norm": 16.310748464273388, "learning_rate": 4.11522633744856e-07, "loss": 1.4053, "step": 10 }, { "epoch": 0.006190672719768881, "grad_norm": 8.538169665885547, "learning_rate": 6.17283950617284e-07, "loss": 1.2698, "step": 15 }, { "epoch": 0.008254230293025175, "grad_norm": 10.15366069671476, "learning_rate": 8.23045267489712e-07, "loss": 1.1677, "step": 20 }, { "epoch": 0.010317787866281469, "grad_norm": 4.654435880312678, "learning_rate": 1.02880658436214e-06, "loss": 1.0417, "step": 25 }, { "epoch": 0.012381345439537762, "grad_norm": 3.4749334652345074, "learning_rate": 1.234567901234568e-06, "loss": 1.0036, "step": 30 }, { "epoch": 0.014444903012794058, "grad_norm": 3.4554780570574053, "learning_rate": 1.440329218106996e-06, "loss": 0.9619, "step": 35 }, { "epoch": 0.01650846058605035, "grad_norm": 3.015216950887853, "learning_rate": 1.646090534979424e-06, "loss": 0.9613, "step": 40 }, { "epoch": 0.018572018159306643, "grad_norm": 2.995932999192709, "learning_rate": 1.8518518518518519e-06, "loss": 0.9286, "step": 45 }, { "epoch": 0.020635575732562937, "grad_norm": 3.177220875947938, "learning_rate": 2.05761316872428e-06, "loss": 0.9406, "step": 50 }, { "epoch": 0.02269913330581923, "grad_norm": 2.973888661127361, "learning_rate": 2.263374485596708e-06, "loss": 0.9212, "step": 55 }, { "epoch": 0.024762690879075525, "grad_norm": 3.1222853603397405, "learning_rate": 2.469135802469136e-06, "loss": 0.8993, "step": 60 }, { "epoch": 0.026826248452331822, "grad_norm": 3.1191152663812804, "learning_rate": 2.674897119341564e-06, "loss": 0.9091, "step": 65 }, { "epoch": 0.028889806025588115, "grad_norm": 3.1470535554852748, "learning_rate": 2.880658436213992e-06, "loss": 0.8987, "step": 70 }, { "epoch": 0.03095336359884441, "grad_norm": 3.190380473643661, "learning_rate": 3.08641975308642e-06, "loss": 0.8951, "step": 75 }, { "epoch": 0.0330169211721007, "grad_norm": 3.0843445112175294, "learning_rate": 3.292181069958848e-06, "loss": 0.8701, "step": 80 }, { "epoch": 0.035080478745357, "grad_norm": 3.076061495060162, "learning_rate": 3.4979423868312762e-06, "loss": 0.8793, "step": 85 }, { "epoch": 0.03714403631861329, "grad_norm": 3.193975210227239, "learning_rate": 3.7037037037037037e-06, "loss": 0.862, "step": 90 }, { "epoch": 0.039207593891869584, "grad_norm": 3.3788505643133493, "learning_rate": 3.909465020576132e-06, "loss": 0.8649, "step": 95 }, { "epoch": 0.041271151465125874, "grad_norm": 3.0784797010252074, "learning_rate": 4.11522633744856e-06, "loss": 0.8747, "step": 100 }, { "epoch": 0.04333470903838217, "grad_norm": 3.104817547757262, "learning_rate": 4.3209876543209875e-06, "loss": 0.8636, "step": 105 }, { "epoch": 0.04539826661163846, "grad_norm": 3.3527956695037364, "learning_rate": 4.526748971193416e-06, "loss": 0.8511, "step": 110 }, { "epoch": 0.04746182418489476, "grad_norm": 3.2593344187687294, "learning_rate": 4.732510288065844e-06, "loss": 0.8553, "step": 115 }, { "epoch": 0.04952538175815105, "grad_norm": 3.0710027642600277, "learning_rate": 4.938271604938272e-06, "loss": 0.8684, "step": 120 }, { "epoch": 0.051588939331407346, "grad_norm": 2.975162533645493, "learning_rate": 5.1440329218107e-06, "loss": 0.8472, "step": 125 }, { "epoch": 0.053652496904663644, "grad_norm": 3.2010808374803887, "learning_rate": 5.349794238683128e-06, "loss": 0.8514, "step": 130 }, { "epoch": 0.055716054477919934, "grad_norm": 3.3050026545334954, "learning_rate": 5.555555555555557e-06, "loss": 0.8585, "step": 135 }, { "epoch": 0.05777961205117623, "grad_norm": 3.225426426848108, "learning_rate": 5.761316872427984e-06, "loss": 0.84, "step": 140 }, { "epoch": 0.05984316962443252, "grad_norm": 3.00873438458862, "learning_rate": 5.967078189300412e-06, "loss": 0.8528, "step": 145 }, { "epoch": 0.06190672719768882, "grad_norm": 3.185986437820424, "learning_rate": 6.17283950617284e-06, "loss": 0.8359, "step": 150 }, { "epoch": 0.06397028477094512, "grad_norm": 3.147767825675856, "learning_rate": 6.3786008230452675e-06, "loss": 0.8407, "step": 155 }, { "epoch": 0.0660338423442014, "grad_norm": 3.1215665332931386, "learning_rate": 6.584362139917696e-06, "loss": 0.8312, "step": 160 }, { "epoch": 0.0680973999174577, "grad_norm": 3.103014664590955, "learning_rate": 6.790123456790124e-06, "loss": 0.8429, "step": 165 }, { "epoch": 0.070160957490714, "grad_norm": 2.8902164902179135, "learning_rate": 6.9958847736625525e-06, "loss": 0.8435, "step": 170 }, { "epoch": 0.07222451506397029, "grad_norm": 2.9932838048876507, "learning_rate": 7.201646090534981e-06, "loss": 0.8336, "step": 175 }, { "epoch": 0.07428807263722657, "grad_norm": 2.9769966947135145, "learning_rate": 7.4074074074074075e-06, "loss": 0.8278, "step": 180 }, { "epoch": 0.07635163021048287, "grad_norm": 3.0042631272069404, "learning_rate": 7.613168724279836e-06, "loss": 0.8479, "step": 185 }, { "epoch": 0.07841518778373917, "grad_norm": 3.0470699491439777, "learning_rate": 7.818930041152263e-06, "loss": 0.8106, "step": 190 }, { "epoch": 0.08047874535699547, "grad_norm": 3.1238776120132212, "learning_rate": 8.024691358024692e-06, "loss": 0.812, "step": 195 }, { "epoch": 0.08254230293025175, "grad_norm": 3.057700682791058, "learning_rate": 8.23045267489712e-06, "loss": 0.825, "step": 200 }, { "epoch": 0.08460586050350805, "grad_norm": 2.9197548906371065, "learning_rate": 8.43621399176955e-06, "loss": 0.829, "step": 205 }, { "epoch": 0.08666941807676434, "grad_norm": 3.058206818326276, "learning_rate": 8.641975308641975e-06, "loss": 0.8301, "step": 210 }, { "epoch": 0.08873297565002064, "grad_norm": 3.2407750676325144, "learning_rate": 8.847736625514404e-06, "loss": 0.8262, "step": 215 }, { "epoch": 0.09079653322327692, "grad_norm": 3.06339049568001, "learning_rate": 9.053497942386832e-06, "loss": 0.8083, "step": 220 }, { "epoch": 0.09286009079653322, "grad_norm": 3.0476164185256716, "learning_rate": 9.25925925925926e-06, "loss": 0.8104, "step": 225 }, { "epoch": 0.09492364836978952, "grad_norm": 3.187404740873087, "learning_rate": 9.465020576131688e-06, "loss": 0.8128, "step": 230 }, { "epoch": 0.09698720594304581, "grad_norm": 2.9797983180430037, "learning_rate": 9.670781893004116e-06, "loss": 0.8228, "step": 235 }, { "epoch": 0.0990507635163021, "grad_norm": 3.0368245696102885, "learning_rate": 9.876543209876543e-06, "loss": 0.8148, "step": 240 }, { "epoch": 0.1011143210895584, "grad_norm": 3.029778459790171, "learning_rate": 9.999979232392962e-06, "loss": 0.8107, "step": 245 }, { "epoch": 0.10317787866281469, "grad_norm": 3.0041036936784713, "learning_rate": 9.999745598795033e-06, "loss": 0.809, "step": 250 }, { "epoch": 0.10524143623607099, "grad_norm": 2.9518943273714933, "learning_rate": 9.999252384260794e-06, "loss": 0.8184, "step": 255 }, { "epoch": 0.10730499380932729, "grad_norm": 3.177840308260484, "learning_rate": 9.998499614397364e-06, "loss": 0.7992, "step": 260 }, { "epoch": 0.10936855138258357, "grad_norm": 3.141068179351825, "learning_rate": 9.997487328287675e-06, "loss": 0.8074, "step": 265 }, { "epoch": 0.11143210895583987, "grad_norm": 3.0175805760778127, "learning_rate": 9.996215578488434e-06, "loss": 0.8079, "step": 270 }, { "epoch": 0.11349566652909616, "grad_norm": 2.994452130786046, "learning_rate": 9.994684431027407e-06, "loss": 0.8053, "step": 275 }, { "epoch": 0.11555922410235246, "grad_norm": 2.8844458617867903, "learning_rate": 9.99289396539997e-06, "loss": 0.8047, "step": 280 }, { "epoch": 0.11762278167560875, "grad_norm": 2.9422429920323303, "learning_rate": 9.990844274565004e-06, "loss": 0.8092, "step": 285 }, { "epoch": 0.11968633924886504, "grad_norm": 2.9422113664370766, "learning_rate": 9.98853546494006e-06, "loss": 0.8106, "step": 290 }, { "epoch": 0.12174989682212134, "grad_norm": 3.0976632552121046, "learning_rate": 9.985967656395823e-06, "loss": 0.8053, "step": 295 }, { "epoch": 0.12381345439537764, "grad_norm": 2.781275499920025, "learning_rate": 9.983140982249913e-06, "loss": 0.794, "step": 300 }, { "epoch": 0.12587701196863393, "grad_norm": 2.9334519545991142, "learning_rate": 9.980055589259937e-06, "loss": 0.784, "step": 305 }, { "epoch": 0.12794056954189023, "grad_norm": 3.090693612262552, "learning_rate": 9.976711637615886e-06, "loss": 0.792, "step": 310 }, { "epoch": 0.1300041271151465, "grad_norm": 3.3690668234777568, "learning_rate": 9.973109300931813e-06, "loss": 0.7948, "step": 315 }, { "epoch": 0.1320676846884028, "grad_norm": 2.9454556413778987, "learning_rate": 9.969248766236823e-06, "loss": 0.7815, "step": 320 }, { "epoch": 0.1341312422616591, "grad_norm": 2.9937506262439353, "learning_rate": 9.965130233965353e-06, "loss": 0.7823, "step": 325 }, { "epoch": 0.1361947998349154, "grad_norm": 2.881968261468614, "learning_rate": 9.960753917946777e-06, "loss": 0.7847, "step": 330 }, { "epoch": 0.1382583574081717, "grad_norm": 3.1357151874563125, "learning_rate": 9.956120045394297e-06, "loss": 0.7728, "step": 335 }, { "epoch": 0.140321914981428, "grad_norm": 2.862718781525608, "learning_rate": 9.951228856893152e-06, "loss": 0.7751, "step": 340 }, { "epoch": 0.14238547255468428, "grad_norm": 3.057415849549758, "learning_rate": 9.946080606388115e-06, "loss": 0.7668, "step": 345 }, { "epoch": 0.14444903012794058, "grad_norm": 2.710224632238816, "learning_rate": 9.940675561170328e-06, "loss": 0.7606, "step": 350 }, { "epoch": 0.14651258770119685, "grad_norm": 2.9233034589381033, "learning_rate": 9.935014001863405e-06, "loss": 0.7679, "step": 355 }, { "epoch": 0.14857614527445315, "grad_norm": 2.811358249750531, "learning_rate": 9.92909622240888e-06, "loss": 0.751, "step": 360 }, { "epoch": 0.15063970284770944, "grad_norm": 2.995283445034626, "learning_rate": 9.92292253005093e-06, "loss": 0.7578, "step": 365 }, { "epoch": 0.15270326042096574, "grad_norm": 2.8376311683829964, "learning_rate": 9.916493245320428e-06, "loss": 0.7654, "step": 370 }, { "epoch": 0.15476681799422204, "grad_norm": 3.025029201724415, "learning_rate": 9.909808702018315e-06, "loss": 0.7622, "step": 375 }, { "epoch": 0.15683037556747834, "grad_norm": 2.72153150268686, "learning_rate": 9.902869247198246e-06, "loss": 0.7505, "step": 380 }, { "epoch": 0.15889393314073463, "grad_norm": 2.9477499411080164, "learning_rate": 9.895675241148588e-06, "loss": 0.7484, "step": 385 }, { "epoch": 0.16095749071399093, "grad_norm": 2.773036825581616, "learning_rate": 9.888227057373716e-06, "loss": 0.7505, "step": 390 }, { "epoch": 0.16302104828724723, "grad_norm": 3.069671722869942, "learning_rate": 9.880525082574604e-06, "loss": 0.7356, "step": 395 }, { "epoch": 0.1650846058605035, "grad_norm": 2.841072256877606, "learning_rate": 9.872569716628764e-06, "loss": 0.731, "step": 400 }, { "epoch": 0.1671481634337598, "grad_norm": 2.8324828515854525, "learning_rate": 9.86436137256948e-06, "loss": 0.7296, "step": 405 }, { "epoch": 0.1692117210070161, "grad_norm": 2.639310017931045, "learning_rate": 9.855900476564365e-06, "loss": 0.7502, "step": 410 }, { "epoch": 0.1712752785802724, "grad_norm": 2.809931040070872, "learning_rate": 9.847187467893228e-06, "loss": 0.7385, "step": 415 }, { "epoch": 0.17333883615352869, "grad_norm": 2.919849626683873, "learning_rate": 9.83822279892528e-06, "loss": 0.7408, "step": 420 }, { "epoch": 0.17540239372678498, "grad_norm": 2.785601538123713, "learning_rate": 9.829006935095629e-06, "loss": 0.7288, "step": 425 }, { "epoch": 0.17746595130004128, "grad_norm": 2.825998365463023, "learning_rate": 9.819540354881136e-06, "loss": 0.7138, "step": 430 }, { "epoch": 0.17952950887329758, "grad_norm": 3.057762442385732, "learning_rate": 9.809823549775559e-06, "loss": 0.7208, "step": 435 }, { "epoch": 0.18159306644655385, "grad_norm": 3.3074234071210795, "learning_rate": 9.79985702426404e-06, "loss": 0.715, "step": 440 }, { "epoch": 0.18365662401981014, "grad_norm": 2.647134717185485, "learning_rate": 9.78964129579691e-06, "loss": 0.7201, "step": 445 }, { "epoch": 0.18572018159306644, "grad_norm": 2.8563895875202423, "learning_rate": 9.779176894762833e-06, "loss": 0.7169, "step": 450 }, { "epoch": 0.18778373916632274, "grad_norm": 2.873990090156598, "learning_rate": 9.768464364461248e-06, "loss": 0.7081, "step": 455 }, { "epoch": 0.18984729673957904, "grad_norm": 3.417747544665542, "learning_rate": 9.75750426107419e-06, "loss": 0.7349, "step": 460 }, { "epoch": 0.19191085431283533, "grad_norm": 2.868974325639969, "learning_rate": 9.746297153637386e-06, "loss": 0.7117, "step": 465 }, { "epoch": 0.19397441188609163, "grad_norm": 2.607611903193476, "learning_rate": 9.73484362401073e-06, "loss": 0.7071, "step": 470 }, { "epoch": 0.19603796945934793, "grad_norm": 2.815425132319591, "learning_rate": 9.723144266848073e-06, "loss": 0.7085, "step": 475 }, { "epoch": 0.1981015270326042, "grad_norm": 2.7618770706471922, "learning_rate": 9.71119968956633e-06, "loss": 0.7154, "step": 480 }, { "epoch": 0.2001650846058605, "grad_norm": 2.8415483921014233, "learning_rate": 9.69901051231397e-06, "loss": 0.7057, "step": 485 }, { "epoch": 0.2022286421791168, "grad_norm": 2.751187895162721, "learning_rate": 9.686577367938802e-06, "loss": 0.7001, "step": 490 }, { "epoch": 0.2042921997523731, "grad_norm": 2.832703546952298, "learning_rate": 9.673900901955118e-06, "loss": 0.7125, "step": 495 }, { "epoch": 0.20635575732562939, "grad_norm": 2.7310630012600288, "learning_rate": 9.66098177251019e-06, "loss": 0.6911, "step": 500 }, { "epoch": 0.20841931489888568, "grad_norm": 3.1926411306126457, "learning_rate": 9.647820650350087e-06, "loss": 0.6906, "step": 505 }, { "epoch": 0.21048287247214198, "grad_norm": 2.936831571628704, "learning_rate": 9.634418218784856e-06, "loss": 0.697, "step": 510 }, { "epoch": 0.21254643004539828, "grad_norm": 2.6709397648736566, "learning_rate": 9.620775173653055e-06, "loss": 0.7245, "step": 515 }, { "epoch": 0.21460998761865457, "grad_norm": 2.840589276150786, "learning_rate": 9.606892223285604e-06, "loss": 0.6796, "step": 520 }, { "epoch": 0.21667354519191084, "grad_norm": 2.7719630321900315, "learning_rate": 9.592770088469032e-06, "loss": 0.6762, "step": 525 }, { "epoch": 0.21873710276516714, "grad_norm": 2.790299282079467, "learning_rate": 9.578409502408037e-06, "loss": 0.6689, "step": 530 }, { "epoch": 0.22080066033842344, "grad_norm": 2.748391116303158, "learning_rate": 9.563811210687433e-06, "loss": 0.6901, "step": 535 }, { "epoch": 0.22286421791167974, "grad_norm": 2.9318642076173997, "learning_rate": 9.548975971233427e-06, "loss": 0.687, "step": 540 }, { "epoch": 0.22492777548493603, "grad_norm": 2.7386846294888905, "learning_rate": 9.53390455427428e-06, "loss": 0.6763, "step": 545 }, { "epoch": 0.22699133305819233, "grad_norm": 2.718226178739275, "learning_rate": 9.518597742300309e-06, "loss": 0.686, "step": 550 }, { "epoch": 0.22905489063144863, "grad_norm": 2.76961873798565, "learning_rate": 9.503056330023267e-06, "loss": 0.6765, "step": 555 }, { "epoch": 0.23111844820470492, "grad_norm": 2.745243843743178, "learning_rate": 9.48728112433508e-06, "loss": 0.6329, "step": 560 }, { "epoch": 0.2331820057779612, "grad_norm": 2.7640600937945656, "learning_rate": 9.471272944265948e-06, "loss": 0.6631, "step": 565 }, { "epoch": 0.2352455633512175, "grad_norm": 2.6291456770239767, "learning_rate": 9.45503262094184e-06, "loss": 0.6509, "step": 570 }, { "epoch": 0.2373091209244738, "grad_norm": 2.6599302374735876, "learning_rate": 9.438560997541319e-06, "loss": 0.6734, "step": 575 }, { "epoch": 0.23937267849773008, "grad_norm": 2.730778505794662, "learning_rate": 9.421858929251786e-06, "loss": 0.6636, "step": 580 }, { "epoch": 0.24143623607098638, "grad_norm": 2.7451915579486608, "learning_rate": 9.404927283225064e-06, "loss": 0.6856, "step": 585 }, { "epoch": 0.24349979364424268, "grad_norm": 3.039314626330203, "learning_rate": 9.387766938532386e-06, "loss": 0.6589, "step": 590 }, { "epoch": 0.24556335121749898, "grad_norm": 2.549623176233669, "learning_rate": 9.370378786118755e-06, "loss": 0.6497, "step": 595 }, { "epoch": 0.24762690879075527, "grad_norm": 2.8288299094715605, "learning_rate": 9.352763728756677e-06, "loss": 0.651, "step": 600 }, { "epoch": 0.24969046636401154, "grad_norm": 2.7431025493492744, "learning_rate": 9.334922680999304e-06, "loss": 0.6626, "step": 605 }, { "epoch": 0.25175402393726787, "grad_norm": 3.2475236208260543, "learning_rate": 9.316856569132942e-06, "loss": 0.6513, "step": 610 }, { "epoch": 0.25381758151052414, "grad_norm": 2.7007134995502935, "learning_rate": 9.29856633112896e-06, "loss": 0.6572, "step": 615 }, { "epoch": 0.25588113908378046, "grad_norm": 2.815555455133585, "learning_rate": 9.280052916595098e-06, "loss": 0.6446, "step": 620 }, { "epoch": 0.25794469665703673, "grad_norm": 2.6595687929164016, "learning_rate": 9.261317286726157e-06, "loss": 0.6704, "step": 625 }, { "epoch": 0.260008254230293, "grad_norm": 2.5437379039499888, "learning_rate": 9.242360414254098e-06, "loss": 0.6446, "step": 630 }, { "epoch": 0.2620718118035493, "grad_norm": 2.6187302536077754, "learning_rate": 9.223183283397538e-06, "loss": 0.6455, "step": 635 }, { "epoch": 0.2641353693768056, "grad_norm": 2.7419025070488865, "learning_rate": 9.203786889810655e-06, "loss": 0.6423, "step": 640 }, { "epoch": 0.2661989269500619, "grad_norm": 2.6652519466347355, "learning_rate": 9.18417224053149e-06, "loss": 0.6277, "step": 645 }, { "epoch": 0.2682624845233182, "grad_norm": 2.6998314438271884, "learning_rate": 9.16434035392966e-06, "loss": 0.6448, "step": 650 }, { "epoch": 0.2703260420965745, "grad_norm": 2.8927572992202912, "learning_rate": 9.144292259653493e-06, "loss": 0.6428, "step": 655 }, { "epoch": 0.2723895996698308, "grad_norm": 2.8217940274279445, "learning_rate": 9.124028998576568e-06, "loss": 0.6271, "step": 660 }, { "epoch": 0.2744531572430871, "grad_norm": 2.698357037715431, "learning_rate": 9.103551622743667e-06, "loss": 0.6473, "step": 665 }, { "epoch": 0.2765167148163434, "grad_norm": 2.5311539033283004, "learning_rate": 9.082861195316164e-06, "loss": 0.6374, "step": 670 }, { "epoch": 0.27858027238959965, "grad_norm": 2.684451644511072, "learning_rate": 9.061958790516821e-06, "loss": 0.6114, "step": 675 }, { "epoch": 0.280643829962856, "grad_norm": 2.70882173878851, "learning_rate": 9.040845493574016e-06, "loss": 0.6246, "step": 680 }, { "epoch": 0.28270738753611224, "grad_norm": 2.697313520964982, "learning_rate": 9.019522400665397e-06, "loss": 0.6377, "step": 685 }, { "epoch": 0.28477094510936857, "grad_norm": 2.6722384414059945, "learning_rate": 8.99799061886098e-06, "loss": 0.6128, "step": 690 }, { "epoch": 0.28683450268262484, "grad_norm": 2.5884058570994126, "learning_rate": 8.976251266065663e-06, "loss": 0.6288, "step": 695 }, { "epoch": 0.28889806025588116, "grad_norm": 2.6279686832374782, "learning_rate": 8.95430547096118e-06, "loss": 0.6227, "step": 700 }, { "epoch": 0.29096161782913743, "grad_norm": 2.5391493323340404, "learning_rate": 8.932154372947512e-06, "loss": 0.6075, "step": 705 }, { "epoch": 0.2930251754023937, "grad_norm": 2.57675256446438, "learning_rate": 8.90979912208373e-06, "loss": 0.6241, "step": 710 }, { "epoch": 0.29508873297565, "grad_norm": 2.6453069428655427, "learning_rate": 8.887240879028276e-06, "loss": 0.6166, "step": 715 }, { "epoch": 0.2971522905489063, "grad_norm": 2.716239502166498, "learning_rate": 8.864480814978715e-06, "loss": 0.635, "step": 720 }, { "epoch": 0.2992158481221626, "grad_norm": 2.671204351007953, "learning_rate": 8.841520111610914e-06, "loss": 0.6334, "step": 725 }, { "epoch": 0.3012794056954189, "grad_norm": 2.7070781042398435, "learning_rate": 8.818359961017705e-06, "loss": 0.5996, "step": 730 }, { "epoch": 0.3033429632686752, "grad_norm": 2.880064298808319, "learning_rate": 8.795001565646983e-06, "loss": 0.6225, "step": 735 }, { "epoch": 0.3054065208419315, "grad_norm": 2.9242515009409167, "learning_rate": 8.771446138239282e-06, "loss": 0.5961, "step": 740 }, { "epoch": 0.3074700784151878, "grad_norm": 2.6615599908346295, "learning_rate": 8.747694901764807e-06, "loss": 0.6024, "step": 745 }, { "epoch": 0.3095336359884441, "grad_norm": 2.6968883124705805, "learning_rate": 8.723749089359941e-06, "loss": 0.6255, "step": 750 }, { "epoch": 0.31159719356170035, "grad_norm": 2.6101422499861204, "learning_rate": 8.699609944263219e-06, "loss": 0.6108, "step": 755 }, { "epoch": 0.3136607511349567, "grad_norm": 2.7883861950882913, "learning_rate": 8.675278719750788e-06, "loss": 0.5861, "step": 760 }, { "epoch": 0.31572430870821294, "grad_norm": 2.6287544173708275, "learning_rate": 8.65075667907133e-06, "loss": 0.6246, "step": 765 }, { "epoch": 0.31778786628146927, "grad_norm": 2.5802067106250264, "learning_rate": 8.626045095380477e-06, "loss": 0.6084, "step": 770 }, { "epoch": 0.31985142385472554, "grad_norm": 2.644312738631867, "learning_rate": 8.601145251674718e-06, "loss": 0.596, "step": 775 }, { "epoch": 0.32191498142798186, "grad_norm": 2.6478619849265126, "learning_rate": 8.576058440724777e-06, "loss": 0.5863, "step": 780 }, { "epoch": 0.32397853900123813, "grad_norm": 2.8982795494605367, "learning_rate": 8.5507859650085e-06, "loss": 0.594, "step": 785 }, { "epoch": 0.32604209657449446, "grad_norm": 2.613119255826806, "learning_rate": 8.525329136643227e-06, "loss": 0.5997, "step": 790 }, { "epoch": 0.3281056541477507, "grad_norm": 2.641896137078953, "learning_rate": 8.499689277317675e-06, "loss": 0.5973, "step": 795 }, { "epoch": 0.330169211721007, "grad_norm": 2.7663511494728383, "learning_rate": 8.473867718223317e-06, "loss": 0.61, "step": 800 }, { "epoch": 0.3322327692942633, "grad_norm": 3.072469841974409, "learning_rate": 8.447865799985258e-06, "loss": 0.5842, "step": 805 }, { "epoch": 0.3342963268675196, "grad_norm": 2.6983197850454155, "learning_rate": 8.421684872592643e-06, "loss": 0.5762, "step": 810 }, { "epoch": 0.3363598844407759, "grad_norm": 2.597729127641379, "learning_rate": 8.395326295328562e-06, "loss": 0.5768, "step": 815 }, { "epoch": 0.3384234420140322, "grad_norm": 2.6102066891309454, "learning_rate": 8.368791436699482e-06, "loss": 0.5738, "step": 820 }, { "epoch": 0.3404869995872885, "grad_norm": 2.7353445805279337, "learning_rate": 8.342081674364182e-06, "loss": 0.5778, "step": 825 }, { "epoch": 0.3425505571605448, "grad_norm": 2.715476077229618, "learning_rate": 8.315198395062246e-06, "loss": 0.5866, "step": 830 }, { "epoch": 0.34461411473380105, "grad_norm": 2.6142000113147996, "learning_rate": 8.28814299454205e-06, "loss": 0.582, "step": 835 }, { "epoch": 0.34667767230705737, "grad_norm": 2.629102491763381, "learning_rate": 8.260916877488308e-06, "loss": 0.5627, "step": 840 }, { "epoch": 0.34874122988031364, "grad_norm": 2.81871300835726, "learning_rate": 8.233521457449131e-06, "loss": 0.5765, "step": 845 }, { "epoch": 0.35080478745356997, "grad_norm": 2.5798337967139786, "learning_rate": 8.205958156762647e-06, "loss": 0.5786, "step": 850 }, { "epoch": 0.35286834502682624, "grad_norm": 2.6428520472332053, "learning_rate": 8.178228406483145e-06, "loss": 0.5733, "step": 855 }, { "epoch": 0.35493190260008256, "grad_norm": 2.5884542760518183, "learning_rate": 8.150333646306787e-06, "loss": 0.5737, "step": 860 }, { "epoch": 0.35699546017333883, "grad_norm": 2.5867571487581267, "learning_rate": 8.122275324496855e-06, "loss": 0.5622, "step": 865 }, { "epoch": 0.35905901774659515, "grad_norm": 2.631316038454596, "learning_rate": 8.094054897808556e-06, "loss": 0.5784, "step": 870 }, { "epoch": 0.3611225753198514, "grad_norm": 2.645392311184159, "learning_rate": 8.065673831413396e-06, "loss": 0.5606, "step": 875 }, { "epoch": 0.3631861328931077, "grad_norm": 2.660143190960995, "learning_rate": 8.037133598823107e-06, "loss": 0.5609, "step": 880 }, { "epoch": 0.365249690466364, "grad_norm": 2.654741259576228, "learning_rate": 8.008435681813139e-06, "loss": 0.5666, "step": 885 }, { "epoch": 0.3673132480396203, "grad_norm": 2.644345571482939, "learning_rate": 7.979581570345737e-06, "loss": 0.5612, "step": 890 }, { "epoch": 0.3693768056128766, "grad_norm": 2.655988106559658, "learning_rate": 7.950572762492577e-06, "loss": 0.5694, "step": 895 }, { "epoch": 0.3714403631861329, "grad_norm": 2.5992311526005745, "learning_rate": 7.92141076435699e-06, "loss": 0.572, "step": 900 }, { "epoch": 0.3735039207593892, "grad_norm": 5.134294676560021, "learning_rate": 7.892097089995767e-06, "loss": 0.5639, "step": 905 }, { "epoch": 0.3755674783326455, "grad_norm": 2.632953530183168, "learning_rate": 7.862633261340556e-06, "loss": 0.5574, "step": 910 }, { "epoch": 0.3776310359059018, "grad_norm": 2.5562996763390315, "learning_rate": 7.83302080811883e-06, "loss": 0.5602, "step": 915 }, { "epoch": 0.37969459347915807, "grad_norm": 2.8859657279668585, "learning_rate": 7.803261267774484e-06, "loss": 0.5637, "step": 920 }, { "epoch": 0.38175815105241434, "grad_norm": 2.9014408054514074, "learning_rate": 7.773356185388003e-06, "loss": 0.5533, "step": 925 }, { "epoch": 0.38382170862567067, "grad_norm": 2.643266197862959, "learning_rate": 7.74330711359624e-06, "loss": 0.5545, "step": 930 }, { "epoch": 0.38588526619892694, "grad_norm": 2.59877885908958, "learning_rate": 7.713115612511815e-06, "loss": 0.5447, "step": 935 }, { "epoch": 0.38794882377218326, "grad_norm": 2.75299257019946, "learning_rate": 7.682783249642104e-06, "loss": 0.5633, "step": 940 }, { "epoch": 0.39001238134543953, "grad_norm": 2.8724654236851417, "learning_rate": 7.652311599807868e-06, "loss": 0.5386, "step": 945 }, { "epoch": 0.39207593891869585, "grad_norm": 2.7801527178903678, "learning_rate": 7.62170224506148e-06, "loss": 0.543, "step": 950 }, { "epoch": 0.3941394964919521, "grad_norm": 2.5304746677885146, "learning_rate": 7.590956774604791e-06, "loss": 0.5419, "step": 955 }, { "epoch": 0.3962030540652084, "grad_norm": 2.5651138008685668, "learning_rate": 7.5600767847066215e-06, "loss": 0.5537, "step": 960 }, { "epoch": 0.3982666116384647, "grad_norm": 2.564284493533834, "learning_rate": 7.529063878619886e-06, "loss": 0.5398, "step": 965 }, { "epoch": 0.400330169211721, "grad_norm": 2.494478384859758, "learning_rate": 7.497919666498346e-06, "loss": 0.5357, "step": 970 }, { "epoch": 0.4023937267849773, "grad_norm": 2.8076248650822477, "learning_rate": 7.466645765313023e-06, "loss": 0.5146, "step": 975 }, { "epoch": 0.4044572843582336, "grad_norm": 2.6136639010718445, "learning_rate": 7.435243798768242e-06, "loss": 0.5353, "step": 980 }, { "epoch": 0.4065208419314899, "grad_norm": 2.6497465192937795, "learning_rate": 7.403715397217335e-06, "loss": 0.5474, "step": 985 }, { "epoch": 0.4085843995047462, "grad_norm": 2.689734067118011, "learning_rate": 7.3720621975779815e-06, "loss": 0.5216, "step": 990 }, { "epoch": 0.4106479570780025, "grad_norm": 2.729820805980585, "learning_rate": 7.3402858432472416e-06, "loss": 0.5379, "step": 995 }, { "epoch": 0.41271151465125877, "grad_norm": 2.4714254580125163, "learning_rate": 7.308387984016217e-06, "loss": 0.532, "step": 1000 }, { "epoch": 0.41477507222451504, "grad_norm": 2.5844803753294143, "learning_rate": 7.276370275984408e-06, "loss": 0.5247, "step": 1005 }, { "epoch": 0.41683862979777137, "grad_norm": 3.019301602672612, "learning_rate": 7.2442343814737135e-06, "loss": 0.5298, "step": 1010 }, { "epoch": 0.41890218737102763, "grad_norm": 2.570769692042143, "learning_rate": 7.211981968942147e-06, "loss": 0.5113, "step": 1015 }, { "epoch": 0.42096574494428396, "grad_norm": 2.4646300115464594, "learning_rate": 7.179614712897195e-06, "loss": 0.5187, "step": 1020 }, { "epoch": 0.42302930251754023, "grad_norm": 2.5855438508864634, "learning_rate": 7.147134293808885e-06, "loss": 0.529, "step": 1025 }, { "epoch": 0.42509286009079655, "grad_norm": 2.522462544239274, "learning_rate": 7.114542398022539e-06, "loss": 0.5209, "step": 1030 }, { "epoch": 0.4271564176640528, "grad_norm": 2.614294003282357, "learning_rate": 7.08184071767122e-06, "loss": 0.5267, "step": 1035 }, { "epoch": 0.42921997523730915, "grad_norm": 2.830907197335319, "learning_rate": 7.049030950587874e-06, "loss": 0.519, "step": 1040 }, { "epoch": 0.4312835328105654, "grad_norm": 2.6174975890970216, "learning_rate": 7.016114800217182e-06, "loss": 0.527, "step": 1045 }, { "epoch": 0.4333470903838217, "grad_norm": 2.802553384062955, "learning_rate": 6.983093975527128e-06, "loss": 0.5318, "step": 1050 }, { "epoch": 0.435410647957078, "grad_norm": 2.705147699006786, "learning_rate": 6.949970190920255e-06, "loss": 0.5249, "step": 1055 }, { "epoch": 0.4374742055303343, "grad_norm": 2.6377750477757185, "learning_rate": 6.916745166144671e-06, "loss": 0.5234, "step": 1060 }, { "epoch": 0.4395377631035906, "grad_norm": 2.5696551738966273, "learning_rate": 6.883420626204751e-06, "loss": 0.5141, "step": 1065 }, { "epoch": 0.4416013206768469, "grad_norm": 2.4805345968877917, "learning_rate": 6.849998301271585e-06, "loss": 0.5274, "step": 1070 }, { "epoch": 0.4436648782501032, "grad_norm": 2.56113425497375, "learning_rate": 6.81647992659314e-06, "loss": 0.5107, "step": 1075 }, { "epoch": 0.44572843582335947, "grad_norm": 2.5171137587224615, "learning_rate": 6.782867242404181e-06, "loss": 0.5134, "step": 1080 }, { "epoch": 0.44779199339661574, "grad_norm": 2.5736722638156238, "learning_rate": 6.749161993835901e-06, "loss": 0.5136, "step": 1085 }, { "epoch": 0.44985555096987206, "grad_norm": 2.626575358402108, "learning_rate": 6.715365930825337e-06, "loss": 0.5151, "step": 1090 }, { "epoch": 0.45191910854312833, "grad_norm": 2.4213943263851228, "learning_rate": 6.681480808024503e-06, "loss": 0.5004, "step": 1095 }, { "epoch": 0.45398266611638466, "grad_norm": 2.4880322309907514, "learning_rate": 6.6475083847092895e-06, "loss": 0.4985, "step": 1100 }, { "epoch": 0.45604622368964093, "grad_norm": 2.540846199810243, "learning_rate": 6.613450424688131e-06, "loss": 0.4994, "step": 1105 }, { "epoch": 0.45810978126289725, "grad_norm": 2.5006175664094155, "learning_rate": 6.579308696210428e-06, "loss": 0.5074, "step": 1110 }, { "epoch": 0.4601733388361535, "grad_norm": 2.7461638796906827, "learning_rate": 6.545084971874738e-06, "loss": 0.4927, "step": 1115 }, { "epoch": 0.46223689640940985, "grad_norm": 2.470553920107453, "learning_rate": 6.51078102853675e-06, "loss": 0.5127, "step": 1120 }, { "epoch": 0.4643004539826661, "grad_norm": 2.5482664076648236, "learning_rate": 6.47639864721703e-06, "loss": 0.5017, "step": 1125 }, { "epoch": 0.4663640115559224, "grad_norm": 2.372890442140938, "learning_rate": 6.44193961300855e-06, "loss": 0.4962, "step": 1130 }, { "epoch": 0.4684275691291787, "grad_norm": 2.646245482981057, "learning_rate": 6.407405714984011e-06, "loss": 0.4999, "step": 1135 }, { "epoch": 0.470491126702435, "grad_norm": 2.664991642169432, "learning_rate": 6.3727987461029565e-06, "loss": 0.4936, "step": 1140 }, { "epoch": 0.4725546842756913, "grad_norm": 2.4837407787514367, "learning_rate": 6.338120503118684e-06, "loss": 0.4962, "step": 1145 }, { "epoch": 0.4746182418489476, "grad_norm": 2.4158811276299685, "learning_rate": 6.303372786484953e-06, "loss": 0.503, "step": 1150 }, { "epoch": 0.4766817994222039, "grad_norm": 2.4486606315641155, "learning_rate": 6.2685574002625235e-06, "loss": 0.488, "step": 1155 }, { "epoch": 0.47874535699546017, "grad_norm": 2.534342542089352, "learning_rate": 6.233676152025474e-06, "loss": 0.4838, "step": 1160 }, { "epoch": 0.4808089145687165, "grad_norm": 2.435648348373461, "learning_rate": 6.198730852767364e-06, "loss": 0.4839, "step": 1165 }, { "epoch": 0.48287247214197276, "grad_norm": 2.4768025227747343, "learning_rate": 6.1637233168072066e-06, "loss": 0.4886, "step": 1170 }, { "epoch": 0.48493602971522903, "grad_norm": 2.6219734229239475, "learning_rate": 6.1286553616952705e-06, "loss": 0.4954, "step": 1175 }, { "epoch": 0.48699958728848536, "grad_norm": 2.778291336802215, "learning_rate": 6.09352880811872e-06, "loss": 0.4919, "step": 1180 }, { "epoch": 0.4890631448617416, "grad_norm": 2.4645634336265414, "learning_rate": 6.058345479807077e-06, "loss": 0.4828, "step": 1185 }, { "epoch": 0.49112670243499795, "grad_norm": 2.724531923287532, "learning_rate": 6.023107203437547e-06, "loss": 0.4776, "step": 1190 }, { "epoch": 0.4931902600082542, "grad_norm": 2.391696574957001, "learning_rate": 5.987815808540169e-06, "loss": 0.4897, "step": 1195 }, { "epoch": 0.49525381758151055, "grad_norm": 2.4407340478477666, "learning_rate": 5.95247312740284e-06, "loss": 0.4779, "step": 1200 }, { "epoch": 0.4973173751547668, "grad_norm": 2.5156624925628734, "learning_rate": 5.917080994976172e-06, "loss": 0.489, "step": 1205 }, { "epoch": 0.4993809327280231, "grad_norm": 2.483104200971057, "learning_rate": 5.881641248778235e-06, "loss": 0.4594, "step": 1210 }, { "epoch": 0.5014444903012794, "grad_norm": 2.3607392567695147, "learning_rate": 5.8461557287991455e-06, "loss": 0.4725, "step": 1215 }, { "epoch": 0.5035080478745357, "grad_norm": 2.62125549075324, "learning_rate": 5.810626277405548e-06, "loss": 0.4622, "step": 1220 }, { "epoch": 0.505571605447792, "grad_norm": 2.38093974135357, "learning_rate": 5.775054739244948e-06, "loss": 0.4742, "step": 1225 }, { "epoch": 0.5076351630210483, "grad_norm": 2.4403884189451652, "learning_rate": 5.739442961149949e-06, "loss": 0.4649, "step": 1230 }, { "epoch": 0.5096987205943045, "grad_norm": 2.548613734052058, "learning_rate": 5.703792792042363e-06, "loss": 0.4831, "step": 1235 }, { "epoch": 0.5117622781675609, "grad_norm": 2.588087383188382, "learning_rate": 5.668106082837226e-06, "loss": 0.4474, "step": 1240 }, { "epoch": 0.5138258357408172, "grad_norm": 2.4261305746179356, "learning_rate": 5.632384686346682e-06, "loss": 0.4701, "step": 1245 }, { "epoch": 0.5158893933140735, "grad_norm": 2.5688197420389405, "learning_rate": 5.5966304571838084e-06, "loss": 0.4566, "step": 1250 }, { "epoch": 0.5179529508873297, "grad_norm": 2.4849310649305334, "learning_rate": 5.560845251666307e-06, "loss": 0.4723, "step": 1255 }, { "epoch": 0.520016508460586, "grad_norm": 2.4560981599718374, "learning_rate": 5.525030927720142e-06, "loss": 0.4595, "step": 1260 }, { "epoch": 0.5220800660338424, "grad_norm": 2.453710751803809, "learning_rate": 5.489189344783072e-06, "loss": 0.4714, "step": 1265 }, { "epoch": 0.5241436236070987, "grad_norm": 2.41401982732661, "learning_rate": 5.4533223637081075e-06, "loss": 0.4545, "step": 1270 }, { "epoch": 0.5262071811803549, "grad_norm": 2.56915988739668, "learning_rate": 5.417431846666903e-06, "loss": 0.4715, "step": 1275 }, { "epoch": 0.5282707387536112, "grad_norm": 2.394420903807903, "learning_rate": 5.381519657053072e-06, "loss": 0.4638, "step": 1280 }, { "epoch": 0.5303342963268676, "grad_norm": 2.56898333828972, "learning_rate": 5.3455876593854435e-06, "loss": 0.4666, "step": 1285 }, { "epoch": 0.5323978539001238, "grad_norm": 2.568125994287113, "learning_rate": 5.309637719211256e-06, "loss": 0.4464, "step": 1290 }, { "epoch": 0.5344614114733801, "grad_norm": 2.5715373228495064, "learning_rate": 5.273671703009301e-06, "loss": 0.4727, "step": 1295 }, { "epoch": 0.5365249690466364, "grad_norm": 2.496647449571793, "learning_rate": 5.2376914780930225e-06, "loss": 0.466, "step": 1300 }, { "epoch": 0.5385885266198926, "grad_norm": 2.3890459661538057, "learning_rate": 5.201698912513561e-06, "loss": 0.4528, "step": 1305 }, { "epoch": 0.540652084193149, "grad_norm": 2.3547456473134725, "learning_rate": 5.165695874962769e-06, "loss": 0.4617, "step": 1310 }, { "epoch": 0.5427156417664053, "grad_norm": 2.6010061169482603, "learning_rate": 5.129684234676195e-06, "loss": 0.4533, "step": 1315 }, { "epoch": 0.5447791993396616, "grad_norm": 2.4443777898976586, "learning_rate": 5.0936658613360304e-06, "loss": 0.4577, "step": 1320 }, { "epoch": 0.5468427569129178, "grad_norm": 2.584543480259313, "learning_rate": 5.057642624974036e-06, "loss": 0.469, "step": 1325 }, { "epoch": 0.5489063144861742, "grad_norm": 2.4716531666690833, "learning_rate": 5.021616395874459e-06, "loss": 0.4585, "step": 1330 }, { "epoch": 0.5509698720594305, "grad_norm": 2.5271116754698952, "learning_rate": 4.9855890444769226e-06, "loss": 0.4372, "step": 1335 }, { "epoch": 0.5530334296326868, "grad_norm": 2.3576001845079717, "learning_rate": 4.94956244127932e-06, "loss": 0.4562, "step": 1340 }, { "epoch": 0.555096987205943, "grad_norm": 2.2754652981031076, "learning_rate": 4.9135384567407e-06, "loss": 0.4436, "step": 1345 }, { "epoch": 0.5571605447791993, "grad_norm": 2.363270346030166, "learning_rate": 4.877518961184149e-06, "loss": 0.4507, "step": 1350 }, { "epoch": 0.5592241023524557, "grad_norm": 2.533993564175955, "learning_rate": 4.841505824699697e-06, "loss": 0.4488, "step": 1355 }, { "epoch": 0.561287659925712, "grad_norm": 2.3819079595896397, "learning_rate": 4.805500917047217e-06, "loss": 0.4515, "step": 1360 }, { "epoch": 0.5633512174989682, "grad_norm": 2.491729497563898, "learning_rate": 4.769506107559344e-06, "loss": 0.4586, "step": 1365 }, { "epoch": 0.5654147750722245, "grad_norm": 2.561770462555589, "learning_rate": 4.7335232650444376e-06, "loss": 0.4499, "step": 1370 }, { "epoch": 0.5674783326454808, "grad_norm": 2.351954002604241, "learning_rate": 4.697554257689541e-06, "loss": 0.4499, "step": 1375 }, { "epoch": 0.5695418902187371, "grad_norm": 2.654369874134926, "learning_rate": 4.661600952963391e-06, "loss": 0.4567, "step": 1380 }, { "epoch": 0.5716054477919934, "grad_norm": 2.371229317990664, "learning_rate": 4.6256652175194675e-06, "loss": 0.4423, "step": 1385 }, { "epoch": 0.5736690053652497, "grad_norm": 2.298496605142076, "learning_rate": 4.589748917099067e-06, "loss": 0.4562, "step": 1390 }, { "epoch": 0.5757325629385059, "grad_norm": 2.5061324004792107, "learning_rate": 4.553853916434448e-06, "loss": 0.4319, "step": 1395 }, { "epoch": 0.5777961205117623, "grad_norm": 2.324768263839684, "learning_rate": 4.517982079152009e-06, "loss": 0.4438, "step": 1400 }, { "epoch": 0.5798596780850186, "grad_norm": 2.431831664255018, "learning_rate": 4.482135267675529e-06, "loss": 0.4286, "step": 1405 }, { "epoch": 0.5819232356582749, "grad_norm": 2.5652232034141513, "learning_rate": 4.446315343129484e-06, "loss": 0.4432, "step": 1410 }, { "epoch": 0.5839867932315311, "grad_norm": 2.450015657552314, "learning_rate": 4.410524165242407e-06, "loss": 0.4351, "step": 1415 }, { "epoch": 0.5860503508047874, "grad_norm": 2.3652736540722072, "learning_rate": 4.3747635922503364e-06, "loss": 0.4418, "step": 1420 }, { "epoch": 0.5881139083780438, "grad_norm": 2.4574463185369253, "learning_rate": 4.3390354808003464e-06, "loss": 0.4434, "step": 1425 }, { "epoch": 0.5901774659513, "grad_norm": 2.72804171955095, "learning_rate": 4.30334168585414e-06, "loss": 0.4418, "step": 1430 }, { "epoch": 0.5922410235245563, "grad_norm": 2.3725721673165476, "learning_rate": 4.26768406059175e-06, "loss": 0.4181, "step": 1435 }, { "epoch": 0.5943045810978126, "grad_norm": 2.5417177804377586, "learning_rate": 4.2320644563153244e-06, "loss": 0.422, "step": 1440 }, { "epoch": 0.596368138671069, "grad_norm": 2.380785546542783, "learning_rate": 4.196484722352999e-06, "loss": 0.4546, "step": 1445 }, { "epoch": 0.5984316962443252, "grad_norm": 2.3513507961703306, "learning_rate": 4.160946705962895e-06, "loss": 0.4308, "step": 1450 }, { "epoch": 0.6004952538175815, "grad_norm": 2.3721791109455497, "learning_rate": 4.12545225223721e-06, "loss": 0.4286, "step": 1455 }, { "epoch": 0.6025588113908378, "grad_norm": 2.4903389897766433, "learning_rate": 4.090003204006406e-06, "loss": 0.4233, "step": 1460 }, { "epoch": 0.604622368964094, "grad_norm": 2.464965524463984, "learning_rate": 4.054601401743561e-06, "loss": 0.4296, "step": 1465 }, { "epoch": 0.6066859265373504, "grad_norm": 2.5248850649302272, "learning_rate": 4.019248683468781e-06, "loss": 0.4166, "step": 1470 }, { "epoch": 0.6087494841106067, "grad_norm": 2.408463829006206, "learning_rate": 3.983946884653804e-06, "loss": 0.4179, "step": 1475 }, { "epoch": 0.610813041683863, "grad_norm": 2.886076857710221, "learning_rate": 3.948697838126681e-06, "loss": 0.4349, "step": 1480 }, { "epoch": 0.6128765992571192, "grad_norm": 2.4019193355765767, "learning_rate": 3.9135033739766275e-06, "loss": 0.4067, "step": 1485 }, { "epoch": 0.6149401568303756, "grad_norm": 2.4578108424736036, "learning_rate": 3.8783653194590055e-06, "loss": 0.4274, "step": 1490 }, { "epoch": 0.6170037144036319, "grad_norm": 2.2228361204521128, "learning_rate": 3.843285498900457e-06, "loss": 0.4108, "step": 1495 }, { "epoch": 0.6190672719768882, "grad_norm": 2.458133195943694, "learning_rate": 3.808265733604181e-06, "loss": 0.4223, "step": 1500 }, { "epoch": 0.6211308295501444, "grad_norm": 2.5008365079486015, "learning_rate": 3.7733078417553835e-06, "loss": 0.4223, "step": 1505 }, { "epoch": 0.6231943871234007, "grad_norm": 2.492347209214054, "learning_rate": 3.7384136383268673e-06, "loss": 0.4331, "step": 1510 }, { "epoch": 0.6252579446966571, "grad_norm": 2.5240341637209487, "learning_rate": 3.70358493498481e-06, "loss": 0.4301, "step": 1515 }, { "epoch": 0.6273215022699133, "grad_norm": 2.381396139732087, "learning_rate": 3.668823539994706e-06, "loss": 0.4087, "step": 1520 }, { "epoch": 0.6293850598431696, "grad_norm": 2.4559560522199266, "learning_rate": 3.634131258127467e-06, "loss": 0.4161, "step": 1525 }, { "epoch": 0.6314486174164259, "grad_norm": 2.4479714606517224, "learning_rate": 3.5995098905657457e-06, "loss": 0.4173, "step": 1530 }, { "epoch": 0.6335121749896823, "grad_norm": 2.375493358114495, "learning_rate": 3.564961234810399e-06, "loss": 0.4149, "step": 1535 }, { "epoch": 0.6355757325629385, "grad_norm": 2.3325498269090654, "learning_rate": 3.530487084587173e-06, "loss": 0.4195, "step": 1540 }, { "epoch": 0.6376392901361948, "grad_norm": 2.535340656053122, "learning_rate": 3.4960892297535765e-06, "loss": 0.4112, "step": 1545 }, { "epoch": 0.6397028477094511, "grad_norm": 2.3941982687900842, "learning_rate": 3.4617694562059465e-06, "loss": 0.4072, "step": 1550 }, { "epoch": 0.6417664052827073, "grad_norm": 2.365602311155293, "learning_rate": 3.427529545786736e-06, "loss": 0.4188, "step": 1555 }, { "epoch": 0.6438299628559637, "grad_norm": 2.3690581384741445, "learning_rate": 3.393371276191997e-06, "loss": 0.4197, "step": 1560 }, { "epoch": 0.64589352042922, "grad_norm": 2.457307965822714, "learning_rate": 3.3592964208790808e-06, "loss": 0.4081, "step": 1565 }, { "epoch": 0.6479570780024763, "grad_norm": 2.357082586970919, "learning_rate": 3.3253067489745716e-06, "loss": 0.4112, "step": 1570 }, { "epoch": 0.6500206355757325, "grad_norm": 2.5012296457407155, "learning_rate": 3.291404025182432e-06, "loss": 0.404, "step": 1575 }, { "epoch": 0.6520841931489889, "grad_norm": 2.4691233983492955, "learning_rate": 3.2575900096923753e-06, "loss": 0.4072, "step": 1580 }, { "epoch": 0.6541477507222452, "grad_norm": 2.2900105868553573, "learning_rate": 3.2238664580884877e-06, "loss": 0.4019, "step": 1585 }, { "epoch": 0.6562113082955014, "grad_norm": 2.641519071963186, "learning_rate": 3.1902351212580734e-06, "loss": 0.4107, "step": 1590 }, { "epoch": 0.6582748658687577, "grad_norm": 2.4094768409949885, "learning_rate": 3.1566977453007564e-06, "loss": 0.3998, "step": 1595 }, { "epoch": 0.660338423442014, "grad_norm": 2.32317932530284, "learning_rate": 3.1232560714378214e-06, "loss": 0.3957, "step": 1600 }, { "epoch": 0.6624019810152704, "grad_norm": 2.3435260760685406, "learning_rate": 3.0899118359218104e-06, "loss": 0.4037, "step": 1605 }, { "epoch": 0.6644655385885266, "grad_norm": 2.408671664196668, "learning_rate": 3.056666769946382e-06, "loss": 0.4008, "step": 1610 }, { "epoch": 0.6665290961617829, "grad_norm": 2.373661045473137, "learning_rate": 3.0235225995564323e-06, "loss": 0.3957, "step": 1615 }, { "epoch": 0.6685926537350392, "grad_norm": 2.396049608120342, "learning_rate": 2.9904810455584664e-06, "loss": 0.3935, "step": 1620 }, { "epoch": 0.6706562113082954, "grad_norm": 2.4498169325496577, "learning_rate": 2.9575438234312807e-06, "loss": 0.3974, "step": 1625 }, { "epoch": 0.6727197688815518, "grad_norm": 2.361494138080272, "learning_rate": 2.9247126432368685e-06, "loss": 0.4047, "step": 1630 }, { "epoch": 0.6747833264548081, "grad_norm": 2.460105798727151, "learning_rate": 2.8919892095316616e-06, "loss": 0.3765, "step": 1635 }, { "epoch": 0.6768468840280644, "grad_norm": 2.372751881717518, "learning_rate": 2.859375221278014e-06, "loss": 0.3962, "step": 1640 }, { "epoch": 0.6789104416013206, "grad_norm": 2.3506543852418744, "learning_rate": 2.826872371756e-06, "loss": 0.4026, "step": 1645 }, { "epoch": 0.680973999174577, "grad_norm": 2.590859611059556, "learning_rate": 2.7944823484755053e-06, "loss": 0.4048, "step": 1650 }, { "epoch": 0.6830375567478333, "grad_norm": 2.459558916625972, "learning_rate": 2.762206833088608e-06, "loss": 0.411, "step": 1655 }, { "epoch": 0.6851011143210896, "grad_norm": 2.376635712009111, "learning_rate": 2.7300475013022666e-06, "loss": 0.3939, "step": 1660 }, { "epoch": 0.6871646718943458, "grad_norm": 2.3253681384920064, "learning_rate": 2.6980060227913273e-06, "loss": 0.3857, "step": 1665 }, { "epoch": 0.6892282294676021, "grad_norm": 2.447348990131711, "learning_rate": 2.666084061111828e-06, "loss": 0.3884, "step": 1670 }, { "epoch": 0.6912917870408585, "grad_norm": 2.2731087359726283, "learning_rate": 2.6342832736146403e-06, "loss": 0.3922, "step": 1675 }, { "epoch": 0.6933553446141147, "grad_norm": 2.4964094280306997, "learning_rate": 2.6026053113594056e-06, "loss": 0.3812, "step": 1680 }, { "epoch": 0.695418902187371, "grad_norm": 2.334488758447207, "learning_rate": 2.571051819028826e-06, "loss": 0.3741, "step": 1685 }, { "epoch": 0.6974824597606273, "grad_norm": 2.5996429738885234, "learning_rate": 2.539624434843272e-06, "loss": 0.4043, "step": 1690 }, { "epoch": 0.6995460173338837, "grad_norm": 2.4333949480585098, "learning_rate": 2.508324790475731e-06, "loss": 0.401, "step": 1695 }, { "epoch": 0.7016095749071399, "grad_norm": 2.4886687072102576, "learning_rate": 2.4771545109670746e-06, "loss": 0.3839, "step": 1700 }, { "epoch": 0.7036731324803962, "grad_norm": 2.3725443568572406, "learning_rate": 2.446115214641719e-06, "loss": 0.3971, "step": 1705 }, { "epoch": 0.7057366900536525, "grad_norm": 2.396722214047279, "learning_rate": 2.415208513023574e-06, "loss": 0.3783, "step": 1710 }, { "epoch": 0.7078002476269087, "grad_norm": 2.382163514854232, "learning_rate": 2.3844360107523973e-06, "loss": 0.3846, "step": 1715 }, { "epoch": 0.7098638052001651, "grad_norm": 2.2994057435859494, "learning_rate": 2.353799305500467e-06, "loss": 0.3807, "step": 1720 }, { "epoch": 0.7119273627734214, "grad_norm": 2.4555093057589623, "learning_rate": 2.3232999878896407e-06, "loss": 0.3889, "step": 1725 }, { "epoch": 0.7139909203466777, "grad_norm": 2.3210433792093186, "learning_rate": 2.2929396414087737e-06, "loss": 0.3832, "step": 1730 }, { "epoch": 0.7160544779199339, "grad_norm": 2.4086267793109197, "learning_rate": 2.2627198423314988e-06, "loss": 0.3886, "step": 1735 }, { "epoch": 0.7181180354931903, "grad_norm": 2.3254337447952813, "learning_rate": 2.2326421596343923e-06, "loss": 0.3666, "step": 1740 }, { "epoch": 0.7201815930664466, "grad_norm": 2.345502767097687, "learning_rate": 2.2027081549155188e-06, "loss": 0.3779, "step": 1745 }, { "epoch": 0.7222451506397028, "grad_norm": 2.5598742194643846, "learning_rate": 2.172919382313347e-06, "loss": 0.3671, "step": 1750 }, { "epoch": 0.7243087082129591, "grad_norm": 2.3018476224088, "learning_rate": 2.1432773884260627e-06, "loss": 0.3738, "step": 1755 }, { "epoch": 0.7263722657862154, "grad_norm": 2.1733721333936487, "learning_rate": 2.1137837122312787e-06, "loss": 0.3822, "step": 1760 }, { "epoch": 0.7284358233594718, "grad_norm": 2.406238665035196, "learning_rate": 2.0844398850061186e-06, "loss": 0.3898, "step": 1765 }, { "epoch": 0.730499380932728, "grad_norm": 2.350333111473755, "learning_rate": 2.0552474302477327e-06, "loss": 0.3762, "step": 1770 }, { "epoch": 0.7325629385059843, "grad_norm": 2.492103708014071, "learning_rate": 2.0262078635941818e-06, "loss": 0.3844, "step": 1775 }, { "epoch": 0.7346264960792406, "grad_norm": 2.3623860872439346, "learning_rate": 1.9973226927457567e-06, "loss": 0.3802, "step": 1780 }, { "epoch": 0.736690053652497, "grad_norm": 2.336773220978403, "learning_rate": 1.968593417386705e-06, "loss": 0.3754, "step": 1785 }, { "epoch": 0.7387536112257532, "grad_norm": 2.4097716944008054, "learning_rate": 1.940021529107356e-06, "loss": 0.375, "step": 1790 }, { "epoch": 0.7408171687990095, "grad_norm": 2.5592525016406213, "learning_rate": 1.911608511326688e-06, "loss": 0.38, "step": 1795 }, { "epoch": 0.7428807263722658, "grad_norm": 2.280187972882149, "learning_rate": 1.8833558392153118e-06, "loss": 0.3665, "step": 1800 }, { "epoch": 0.744944283945522, "grad_norm": 2.3420925718126218, "learning_rate": 1.8552649796188765e-06, "loss": 0.372, "step": 1805 }, { "epoch": 0.7470078415187784, "grad_norm": 2.301653995033941, "learning_rate": 1.8273373909819132e-06, "loss": 0.3647, "step": 1810 }, { "epoch": 0.7490713990920347, "grad_norm": 2.3840051611185684, "learning_rate": 1.7995745232721207e-06, "loss": 0.3809, "step": 1815 }, { "epoch": 0.751134956665291, "grad_norm": 2.2642625662574036, "learning_rate": 1.771977817905075e-06, "loss": 0.3735, "step": 1820 }, { "epoch": 0.7531985142385472, "grad_norm": 2.268239232419045, "learning_rate": 1.744548707669404e-06, "loss": 0.3712, "step": 1825 }, { "epoch": 0.7552620718118036, "grad_norm": 2.4254083309780317, "learning_rate": 1.717288616652386e-06, "loss": 0.3734, "step": 1830 }, { "epoch": 0.7573256293850599, "grad_norm": 2.4221738596443334, "learning_rate": 1.6901989601660224e-06, "loss": 0.3661, "step": 1835 }, { "epoch": 0.7593891869583161, "grad_norm": 2.375829541005397, "learning_rate": 1.6632811446735553e-06, "loss": 0.376, "step": 1840 }, { "epoch": 0.7614527445315724, "grad_norm": 2.2919709177403487, "learning_rate": 1.6365365677164413e-06, "loss": 0.3675, "step": 1845 }, { "epoch": 0.7635163021048287, "grad_norm": 2.3726188787120517, "learning_rate": 1.6099666178417927e-06, "loss": 0.3705, "step": 1850 }, { "epoch": 0.7655798596780851, "grad_norm": 2.500763584763627, "learning_rate": 1.5835726745302953e-06, "loss": 0.366, "step": 1855 }, { "epoch": 0.7676434172513413, "grad_norm": 2.3479469227773713, "learning_rate": 1.5573561081245724e-06, "loss": 0.3576, "step": 1860 }, { "epoch": 0.7697069748245976, "grad_norm": 2.3705937787564872, "learning_rate": 1.531318279758055e-06, "loss": 0.369, "step": 1865 }, { "epoch": 0.7717705323978539, "grad_norm": 2.313207458585096, "learning_rate": 1.5054605412842915e-06, "loss": 0.3584, "step": 1870 }, { "epoch": 0.7738340899711101, "grad_norm": 2.4072611292571713, "learning_rate": 1.479784235206786e-06, "loss": 0.3604, "step": 1875 }, { "epoch": 0.7758976475443665, "grad_norm": 2.6300005236757342, "learning_rate": 1.4542906946092817e-06, "loss": 0.3738, "step": 1880 }, { "epoch": 0.7779612051176228, "grad_norm": 2.340659762526081, "learning_rate": 1.428981243086549e-06, "loss": 0.3775, "step": 1885 }, { "epoch": 0.7800247626908791, "grad_norm": 2.4070947815123187, "learning_rate": 1.4038571946756724e-06, "loss": 0.376, "step": 1890 }, { "epoch": 0.7820883202641353, "grad_norm": 2.3888375339701446, "learning_rate": 1.3789198537878202e-06, "loss": 0.37, "step": 1895 }, { "epoch": 0.7841518778373917, "grad_norm": 2.519263424398352, "learning_rate": 1.3541705151405304e-06, "loss": 0.3704, "step": 1900 }, { "epoch": 0.786215435410648, "grad_norm": 2.333167098182409, "learning_rate": 1.3296104636904806e-06, "loss": 0.3744, "step": 1905 }, { "epoch": 0.7882789929839042, "grad_norm": 2.3202050184652903, "learning_rate": 1.3052409745667783e-06, "loss": 0.3655, "step": 1910 }, { "epoch": 0.7903425505571605, "grad_norm": 2.4584503227102643, "learning_rate": 1.281063313004761e-06, "loss": 0.373, "step": 1915 }, { "epoch": 0.7924061081304168, "grad_norm": 2.353593087374877, "learning_rate": 1.2570787342803064e-06, "loss": 0.3743, "step": 1920 }, { "epoch": 0.7944696657036732, "grad_norm": 2.5940030762409543, "learning_rate": 1.2332884836446473e-06, "loss": 0.3604, "step": 1925 }, { "epoch": 0.7965332232769294, "grad_norm": 2.4517904999917546, "learning_rate": 1.2096937962597399e-06, "loss": 0.3548, "step": 1930 }, { "epoch": 0.7985967808501857, "grad_norm": 2.474589073943442, "learning_rate": 1.1862958971341199e-06, "loss": 0.3648, "step": 1935 }, { "epoch": 0.800660338423442, "grad_norm": 2.4815347762577153, "learning_rate": 1.16309600105931e-06, "loss": 0.3602, "step": 1940 }, { "epoch": 0.8027238959966984, "grad_norm": 2.301031931736506, "learning_rate": 1.1400953125467452e-06, "loss": 0.3484, "step": 1945 }, { "epoch": 0.8047874535699546, "grad_norm": 2.4259097691636557, "learning_rate": 1.117295025765235e-06, "loss": 0.3576, "step": 1950 }, { "epoch": 0.8068510111432109, "grad_norm": 2.2363991886781354, "learning_rate": 1.09469632447897e-06, "loss": 0.3576, "step": 1955 }, { "epoch": 0.8089145687164672, "grad_norm": 2.3333527927276303, "learning_rate": 1.0723003819860555e-06, "loss": 0.3552, "step": 1960 }, { "epoch": 0.8109781262897234, "grad_norm": 2.3366155476197625, "learning_rate": 1.0501083610575958e-06, "loss": 0.3672, "step": 1965 }, { "epoch": 0.8130416838629798, "grad_norm": 2.35373840567771, "learning_rate": 1.0281214138773315e-06, "loss": 0.3602, "step": 1970 }, { "epoch": 0.8151052414362361, "grad_norm": 2.4504836040452807, "learning_rate": 1.0063406819818106e-06, "loss": 0.3634, "step": 1975 }, { "epoch": 0.8171687990094924, "grad_norm": 2.3054981249745143, "learning_rate": 9.847672962011233e-07, "loss": 0.3494, "step": 1980 }, { "epoch": 0.8192323565827486, "grad_norm": 2.370081714773592, "learning_rate": 9.634023766001981e-07, "loss": 0.3664, "step": 1985 }, { "epoch": 0.821295914156005, "grad_norm": 2.351209150973171, "learning_rate": 9.422470324206385e-07, "loss": 0.355, "step": 1990 }, { "epoch": 0.8233594717292613, "grad_norm": 2.5038331410556207, "learning_rate": 9.213023620231404e-07, "loss": 0.3522, "step": 1995 }, { "epoch": 0.8254230293025175, "grad_norm": 2.475980769316644, "learning_rate": 9.005694528304621e-07, "loss": 0.3766, "step": 2000 }, { "epoch": 0.8274865868757738, "grad_norm": 2.3262421050251487, "learning_rate": 8.800493812709677e-07, "loss": 0.3506, "step": 2005 }, { "epoch": 0.8295501444490301, "grad_norm": 2.478801238519718, "learning_rate": 8.597432127227434e-07, "loss": 0.3671, "step": 2010 }, { "epoch": 0.8316137020222865, "grad_norm": 2.4409216250973715, "learning_rate": 8.396520014582798e-07, "loss": 0.3635, "step": 2015 }, { "epoch": 0.8336772595955427, "grad_norm": 2.4615179041756154, "learning_rate": 8.197767905897341e-07, "loss": 0.3483, "step": 2020 }, { "epoch": 0.835740817168799, "grad_norm": 2.4434801105794275, "learning_rate": 8.001186120147825e-07, "loss": 0.3511, "step": 2025 }, { "epoch": 0.8378043747420553, "grad_norm": 2.3137831042406547, "learning_rate": 7.806784863630324e-07, "loss": 0.3544, "step": 2030 }, { "epoch": 0.8398679323153116, "grad_norm": 2.3214543067749345, "learning_rate": 7.614574229430432e-07, "loss": 0.3564, "step": 2035 }, { "epoch": 0.8419314898885679, "grad_norm": 2.449709912024583, "learning_rate": 7.424564196899175e-07, "loss": 0.3528, "step": 2040 }, { "epoch": 0.8439950474618242, "grad_norm": 2.567817456247611, "learning_rate": 7.236764631134907e-07, "loss": 0.3619, "step": 2045 }, { "epoch": 0.8460586050350805, "grad_norm": 2.3392413654682938, "learning_rate": 7.051185282471173e-07, "loss": 0.3584, "step": 2050 }, { "epoch": 0.8481221626083367, "grad_norm": 2.39558795485472, "learning_rate": 6.867835785970417e-07, "loss": 0.3532, "step": 2055 }, { "epoch": 0.8501857201815931, "grad_norm": 2.3679947128138283, "learning_rate": 6.68672566092376e-07, "loss": 0.3524, "step": 2060 }, { "epoch": 0.8522492777548494, "grad_norm": 2.4990613971706996, "learning_rate": 6.507864310356826e-07, "loss": 0.3577, "step": 2065 }, { "epoch": 0.8543128353281056, "grad_norm": 2.4082980308634108, "learning_rate": 6.331261020541462e-07, "loss": 0.3639, "step": 2070 }, { "epoch": 0.8563763929013619, "grad_norm": 2.3803702613226707, "learning_rate": 6.156924960513638e-07, "loss": 0.3535, "step": 2075 }, { "epoch": 0.8584399504746183, "grad_norm": 2.4917029731472087, "learning_rate": 5.984865181597454e-07, "loss": 0.3554, "step": 2080 }, { "epoch": 0.8605035080478746, "grad_norm": 2.3628202883375815, "learning_rate": 5.815090616935115e-07, "loss": 0.3502, "step": 2085 }, { "epoch": 0.8625670656211308, "grad_norm": 2.418649789048316, "learning_rate": 5.647610081023214e-07, "loss": 0.3476, "step": 2090 }, { "epoch": 0.8646306231943871, "grad_norm": 2.3253415135004296, "learning_rate": 5.482432269255011e-07, "loss": 0.3612, "step": 2095 }, { "epoch": 0.8666941807676434, "grad_norm": 2.363158240683325, "learning_rate": 5.31956575746907e-07, "loss": 0.3523, "step": 2100 }, { "epoch": 0.8687577383408998, "grad_norm": 2.5515755490970027, "learning_rate": 5.159019001503962e-07, "loss": 0.3455, "step": 2105 }, { "epoch": 0.870821295914156, "grad_norm": 2.3759537438441507, "learning_rate": 5.000800336759232e-07, "loss": 0.3581, "step": 2110 }, { "epoch": 0.8728848534874123, "grad_norm": 2.3600457913542243, "learning_rate": 4.844917977762653e-07, "loss": 0.3434, "step": 2115 }, { "epoch": 0.8749484110606686, "grad_norm": 2.321377644223267, "learning_rate": 4.691380017743769e-07, "loss": 0.3506, "step": 2120 }, { "epoch": 0.8770119686339248, "grad_norm": 2.4474994788793687, "learning_rate": 4.5401944282136454e-07, "loss": 0.3446, "step": 2125 }, { "epoch": 0.8790755262071812, "grad_norm": 2.3833455011506306, "learning_rate": 4.3913690585510427e-07, "loss": 0.3487, "step": 2130 }, { "epoch": 0.8811390837804375, "grad_norm": 2.4277357505299313, "learning_rate": 4.244911635594856e-07, "loss": 0.3512, "step": 2135 }, { "epoch": 0.8832026413536938, "grad_norm": 2.4169504867595046, "learning_rate": 4.100829763242975e-07, "loss": 0.3453, "step": 2140 }, { "epoch": 0.88526619892695, "grad_norm": 2.4063841282552922, "learning_rate": 3.959130922057497e-07, "loss": 0.3413, "step": 2145 }, { "epoch": 0.8873297565002064, "grad_norm": 2.55749823991654, "learning_rate": 3.819822468876283e-07, "loss": 0.3483, "step": 2150 }, { "epoch": 0.8893933140734627, "grad_norm": 2.4953456490666204, "learning_rate": 3.6829116364310914e-07, "loss": 0.3426, "step": 2155 }, { "epoch": 0.8914568716467189, "grad_norm": 2.4865116434035817, "learning_rate": 3.548405532972016e-07, "loss": 0.3596, "step": 2160 }, { "epoch": 0.8935204292199752, "grad_norm": 2.4845730208040107, "learning_rate": 3.416311141898421e-07, "loss": 0.3445, "step": 2165 }, { "epoch": 0.8955839867932315, "grad_norm": 2.4894246175031, "learning_rate": 3.286635321396392e-07, "loss": 0.3557, "step": 2170 }, { "epoch": 0.8976475443664879, "grad_norm": 2.575724473223171, "learning_rate": 3.159384804082666e-07, "loss": 0.3459, "step": 2175 }, { "epoch": 0.8997111019397441, "grad_norm": 2.3955179437613157, "learning_rate": 3.034566196655092e-07, "loss": 0.3356, "step": 2180 }, { "epoch": 0.9017746595130004, "grad_norm": 2.3823562728530163, "learning_rate": 2.912185979549587e-07, "loss": 0.342, "step": 2185 }, { "epoch": 0.9038382170862567, "grad_norm": 2.2681018992676676, "learning_rate": 2.792250506603694e-07, "loss": 0.3363, "step": 2190 }, { "epoch": 0.905901774659513, "grad_norm": 2.424509333838691, "learning_rate": 2.67476600472672e-07, "loss": 0.3413, "step": 2195 }, { "epoch": 0.9079653322327693, "grad_norm": 2.4447196507867757, "learning_rate": 2.5597385735764256e-07, "loss": 0.3485, "step": 2200 }, { "epoch": 0.9100288898060256, "grad_norm": 2.5045080164847544, "learning_rate": 2.447174185242324e-07, "loss": 0.3447, "step": 2205 }, { "epoch": 0.9120924473792819, "grad_norm": 2.4413194212287643, "learning_rate": 2.3370786839356286e-07, "loss": 0.3442, "step": 2210 }, { "epoch": 0.9141560049525381, "grad_norm": 2.3540975860230704, "learning_rate": 2.2294577856858236e-07, "loss": 0.3519, "step": 2215 }, { "epoch": 0.9162195625257945, "grad_norm": 2.3709600934638133, "learning_rate": 2.124317078043936e-07, "loss": 0.3412, "step": 2220 }, { "epoch": 0.9182831200990508, "grad_norm": 2.3596360500822504, "learning_rate": 2.0216620197923642e-07, "loss": 0.3378, "step": 2225 }, { "epoch": 0.920346677672307, "grad_norm": 2.4864046728091935, "learning_rate": 1.9214979406615097e-07, "loss": 0.3392, "step": 2230 }, { "epoch": 0.9224102352455633, "grad_norm": 2.43802794639703, "learning_rate": 1.823830041053065e-07, "loss": 0.3418, "step": 2235 }, { "epoch": 0.9244737928188197, "grad_norm": 2.6023299391768764, "learning_rate": 1.7286633917700134e-07, "loss": 0.3386, "step": 2240 }, { "epoch": 0.926537350392076, "grad_norm": 2.3417082576165638, "learning_rate": 1.6360029337533056e-07, "loss": 0.3448, "step": 2245 }, { "epoch": 0.9286009079653322, "grad_norm": 2.5146181859872274, "learning_rate": 1.5458534778254319e-07, "loss": 0.3414, "step": 2250 }, { "epoch": 0.9306644655385885, "grad_norm": 2.4941180593728007, "learning_rate": 1.4582197044405556e-07, "loss": 0.3485, "step": 2255 }, { "epoch": 0.9327280231118448, "grad_norm": 2.5130823741003385, "learning_rate": 1.3731061634415787e-07, "loss": 0.3595, "step": 2260 }, { "epoch": 0.9347915806851012, "grad_norm": 2.2572849254119456, "learning_rate": 1.2905172738238603e-07, "loss": 0.3372, "step": 2265 }, { "epoch": 0.9368551382583574, "grad_norm": 2.6107535720743336, "learning_rate": 1.2104573235058314e-07, "loss": 0.3488, "step": 2270 }, { "epoch": 0.9389186958316137, "grad_norm": 2.338779134457757, "learning_rate": 1.1329304691063692e-07, "loss": 0.3407, "step": 2275 }, { "epoch": 0.94098225340487, "grad_norm": 2.358541293298548, "learning_rate": 1.0579407357289461e-07, "loss": 0.3318, "step": 2280 }, { "epoch": 0.9430458109781263, "grad_norm": 2.4317952744108444, "learning_rate": 9.854920167526983e-08, "loss": 0.3379, "step": 2285 }, { "epoch": 0.9451093685513826, "grad_norm": 2.493392786013269, "learning_rate": 9.155880736302857e-08, "loss": 0.348, "step": 2290 }, { "epoch": 0.9471729261246389, "grad_norm": 2.4984110771019195, "learning_rate": 8.482325356925614e-08, "loss": 0.343, "step": 2295 }, { "epoch": 0.9492364836978952, "grad_norm": 2.5354969848226148, "learning_rate": 7.834288999601703e-08, "loss": 0.3424, "step": 2300 }, { "epoch": 0.9513000412711514, "grad_norm": 2.423785240142543, "learning_rate": 7.211805309620013e-08, "loss": 0.3473, "step": 2305 }, { "epoch": 0.9533635988444078, "grad_norm": 2.4677178264547726, "learning_rate": 6.614906605604598e-08, "loss": 0.3381, "step": 2310 }, { "epoch": 0.9554271564176641, "grad_norm": 2.408816641908432, "learning_rate": 6.043623877837301e-08, "loss": 0.3433, "step": 2315 }, { "epoch": 0.9574907139909203, "grad_norm": 2.4440297911345272, "learning_rate": 5.4979867866482015e-08, "loss": 0.3313, "step": 2320 }, { "epoch": 0.9595542715641766, "grad_norm": 2.4048555132674734, "learning_rate": 4.978023660876075e-08, "loss": 0.3479, "step": 2325 }, { "epoch": 0.961617829137433, "grad_norm": 2.312208373027164, "learning_rate": 4.4837614963976205e-08, "loss": 0.3284, "step": 2330 }, { "epoch": 0.9636813867106893, "grad_norm": 2.4836720558405316, "learning_rate": 4.015225954725421e-08, "loss": 0.3348, "step": 2335 }, { "epoch": 0.9657449442839455, "grad_norm": 2.3121106746942424, "learning_rate": 3.572441361676171e-08, "loss": 0.34, "step": 2340 }, { "epoch": 0.9678085018572018, "grad_norm": 2.418973197250497, "learning_rate": 3.155430706107465e-08, "loss": 0.3393, "step": 2345 }, { "epoch": 0.9698720594304581, "grad_norm": 2.361515650946405, "learning_rate": 2.7642156387240882e-08, "loss": 0.3479, "step": 2350 }, { "epoch": 0.9719356170037144, "grad_norm": 2.4742764209435566, "learning_rate": 2.3988164709542462e-08, "loss": 0.3478, "step": 2355 }, { "epoch": 0.9739991745769707, "grad_norm": 2.3287638903216914, "learning_rate": 2.0592521738947434e-08, "loss": 0.3487, "step": 2360 }, { "epoch": 0.976062732150227, "grad_norm": 2.3843285639801186, "learning_rate": 1.7455403773262713e-08, "loss": 0.3341, "step": 2365 }, { "epoch": 0.9781262897234833, "grad_norm": 2.4395312038190866, "learning_rate": 1.4576973687979168e-08, "loss": 0.3381, "step": 2370 }, { "epoch": 0.9801898472967395, "grad_norm": 2.3330484221096124, "learning_rate": 1.1957380927816176e-08, "loss": 0.3338, "step": 2375 }, { "epoch": 0.9822534048699959, "grad_norm": 2.5553034933321963, "learning_rate": 9.596761498961715e-09, "loss": 0.3317, "step": 2380 }, { "epoch": 0.9843169624432522, "grad_norm": 2.3671150560277128, "learning_rate": 7.495237962011902e-09, "loss": 0.3528, "step": 2385 }, { "epoch": 0.9863805200165084, "grad_norm": 2.4557372551442085, "learning_rate": 5.65291942560775e-09, "loss": 0.3422, "step": 2390 }, { "epoch": 0.9884440775897647, "grad_norm": 2.4643344844592456, "learning_rate": 4.0699015407702495e-09, "loss": 0.3423, "step": 2395 }, { "epoch": 0.9905076351630211, "grad_norm": 2.480821502235499, "learning_rate": 2.7462664959343465e-09, "loss": 0.3483, "step": 2400 }, { "epoch": 0.9925711927362774, "grad_norm": 2.625866813637489, "learning_rate": 1.682083012681246e-09, "loss": 0.3468, "step": 2405 }, { "epoch": 0.9946347503095336, "grad_norm": 2.2860364192318947, "learning_rate": 8.774063421712608e-10, "loss": 0.3482, "step": 2410 }, { "epoch": 0.9966983078827899, "grad_norm": 2.378283693085081, "learning_rate": 3.322782622738885e-10, "loss": 0.3395, "step": 2415 }, { "epoch": 0.9987618654560462, "grad_norm": 2.6351565892849855, "learning_rate": 4.672707540231969e-11, "loss": 0.3528, "step": 2420 }, { "epoch": 1.0, "eval_runtime": 3.4841, "eval_samples_per_second": 2.87, "eval_steps_per_second": 0.861, "step": 2423 }, { "epoch": 1.0, "step": 2423, "total_flos": 253663452856320.0, "train_loss": 0.5332261629454912, "train_runtime": 21421.0705, "train_samples_per_second": 1.81, "train_steps_per_second": 0.113 } ], "logging_steps": 5, "max_steps": 2423, "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": 253663452856320.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }