| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.2610340479192939, |
| "eval_steps": 500, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0012610340479192938, |
| "grad_norm": 3.78216552734375, |
| "learning_rate": 0.0, |
| "loss": 1.8184, |
| "mean_token_accuracy": 0.5478422045707703, |
| "num_tokens": 1932.0, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0025220680958385876, |
| "grad_norm": 4.4499335289001465, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 2.123, |
| "mean_token_accuracy": 0.5311873555183411, |
| "num_tokens": 3698.0, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.0037831021437578815, |
| "grad_norm": 3.8226370811462402, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 2.0533, |
| "mean_token_accuracy": 0.5195541083812714, |
| "num_tokens": 5712.0, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.005044136191677175, |
| "grad_norm": 4.1222825050354, |
| "learning_rate": 6e-06, |
| "loss": 2.1825, |
| "mean_token_accuracy": 0.5058494061231613, |
| "num_tokens": 7550.0, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.006305170239596469, |
| "grad_norm": 3.844985246658325, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 1.9298, |
| "mean_token_accuracy": 0.5106111168861389, |
| "num_tokens": 9424.0, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.007566204287515763, |
| "grad_norm": 3.5116820335388184, |
| "learning_rate": 1e-05, |
| "loss": 1.8564, |
| "mean_token_accuracy": 0.5460174679756165, |
| "num_tokens": 11327.0, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.008827238335435058, |
| "grad_norm": 3.154329299926758, |
| "learning_rate": 9.98994974874372e-06, |
| "loss": 1.9824, |
| "mean_token_accuracy": 0.5224607586860657, |
| "num_tokens": 13271.0, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.01008827238335435, |
| "grad_norm": 2.797213554382324, |
| "learning_rate": 9.979899497487437e-06, |
| "loss": 1.9916, |
| "mean_token_accuracy": 0.5350979268550873, |
| "num_tokens": 15088.0, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.011349306431273645, |
| "grad_norm": 2.268925189971924, |
| "learning_rate": 9.969849246231156e-06, |
| "loss": 1.8282, |
| "mean_token_accuracy": 0.5434771478176117, |
| "num_tokens": 17144.0, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.012610340479192938, |
| "grad_norm": 2.4971511363983154, |
| "learning_rate": 9.959798994974875e-06, |
| "loss": 2.0409, |
| "mean_token_accuracy": 0.5182838141918182, |
| "num_tokens": 19008.0, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.013871374527112233, |
| "grad_norm": 2.171393871307373, |
| "learning_rate": 9.949748743718594e-06, |
| "loss": 1.9347, |
| "mean_token_accuracy": 0.532874196767807, |
| "num_tokens": 20974.0, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.015132408575031526, |
| "grad_norm": 2.3439807891845703, |
| "learning_rate": 9.939698492462311e-06, |
| "loss": 1.9792, |
| "mean_token_accuracy": 0.5403009951114655, |
| "num_tokens": 22779.0, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.01639344262295082, |
| "grad_norm": 2.170363187789917, |
| "learning_rate": 9.929648241206032e-06, |
| "loss": 1.9991, |
| "mean_token_accuracy": 0.5162927210330963, |
| "num_tokens": 24656.0, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.017654476670870115, |
| "grad_norm": 2.308042287826538, |
| "learning_rate": 9.91959798994975e-06, |
| "loss": 1.9188, |
| "mean_token_accuracy": 0.5402237772941589, |
| "num_tokens": 26662.0, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.018915510718789406, |
| "grad_norm": 1.8713246583938599, |
| "learning_rate": 9.909547738693468e-06, |
| "loss": 1.8725, |
| "mean_token_accuracy": 0.5225067734718323, |
| "num_tokens": 28600.0, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.0201765447667087, |
| "grad_norm": 1.9223459959030151, |
| "learning_rate": 9.899497487437186e-06, |
| "loss": 1.773, |
| "mean_token_accuracy": 0.5440478324890137, |
| "num_tokens": 30600.0, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.021437578814627996, |
| "grad_norm": 2.454831838607788, |
| "learning_rate": 9.889447236180906e-06, |
| "loss": 1.5866, |
| "mean_token_accuracy": 0.5830827057361603, |
| "num_tokens": 32754.0, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.02269861286254729, |
| "grad_norm": 2.471298933029175, |
| "learning_rate": 9.879396984924624e-06, |
| "loss": 1.6787, |
| "mean_token_accuracy": 0.5635462701320648, |
| "num_tokens": 34713.0, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.02395964691046658, |
| "grad_norm": 2.109905958175659, |
| "learning_rate": 9.869346733668343e-06, |
| "loss": 1.7912, |
| "mean_token_accuracy": 0.5421053469181061, |
| "num_tokens": 36576.0, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.025220680958385876, |
| "grad_norm": 1.8330053091049194, |
| "learning_rate": 9.859296482412062e-06, |
| "loss": 1.7343, |
| "mean_token_accuracy": 0.5540662705898285, |
| "num_tokens": 38619.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.02648171500630517, |
| "grad_norm": 1.9908827543258667, |
| "learning_rate": 9.84924623115578e-06, |
| "loss": 1.8354, |
| "mean_token_accuracy": 0.5480290353298187, |
| "num_tokens": 40508.0, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.027742749054224466, |
| "grad_norm": 2.128009080886841, |
| "learning_rate": 9.839195979899498e-06, |
| "loss": 1.6946, |
| "mean_token_accuracy": 0.5512959659099579, |
| "num_tokens": 42308.0, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.029003783102143757, |
| "grad_norm": 2.040771484375, |
| "learning_rate": 9.829145728643217e-06, |
| "loss": 1.6718, |
| "mean_token_accuracy": 0.5608045160770416, |
| "num_tokens": 44330.0, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.03026481715006305, |
| "grad_norm": 2.1296682357788086, |
| "learning_rate": 9.819095477386936e-06, |
| "loss": 1.7464, |
| "mean_token_accuracy": 0.5513394474983215, |
| "num_tokens": 46186.0, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.031525851197982346, |
| "grad_norm": 1.8986268043518066, |
| "learning_rate": 9.809045226130655e-06, |
| "loss": 1.7569, |
| "mean_token_accuracy": 0.5630869269371033, |
| "num_tokens": 48236.0, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.03278688524590164, |
| "grad_norm": 2.336251974105835, |
| "learning_rate": 9.798994974874372e-06, |
| "loss": 1.7443, |
| "mean_token_accuracy": 0.5652304887771606, |
| "num_tokens": 50014.0, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.034047919293820936, |
| "grad_norm": 2.187518835067749, |
| "learning_rate": 9.788944723618091e-06, |
| "loss": 1.6389, |
| "mean_token_accuracy": 0.5563819110393524, |
| "num_tokens": 51968.0, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.03530895334174023, |
| "grad_norm": 2.472879409790039, |
| "learning_rate": 9.77889447236181e-06, |
| "loss": 1.6906, |
| "mean_token_accuracy": 0.5612628161907196, |
| "num_tokens": 53868.0, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.03656998738965952, |
| "grad_norm": 2.7643585205078125, |
| "learning_rate": 9.768844221105529e-06, |
| "loss": 1.926, |
| "mean_token_accuracy": 0.5238874852657318, |
| "num_tokens": 55687.0, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.03783102143757881, |
| "grad_norm": 2.3360137939453125, |
| "learning_rate": 9.758793969849248e-06, |
| "loss": 1.7736, |
| "mean_token_accuracy": 0.5509012341499329, |
| "num_tokens": 57789.0, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.03909205548549811, |
| "grad_norm": 2.017324209213257, |
| "learning_rate": 9.748743718592965e-06, |
| "loss": 1.6972, |
| "mean_token_accuracy": 0.5527718961238861, |
| "num_tokens": 59675.0, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.0403530895334174, |
| "grad_norm": 2.628589153289795, |
| "learning_rate": 9.738693467336684e-06, |
| "loss": 1.7336, |
| "mean_token_accuracy": 0.5779553949832916, |
| "num_tokens": 61686.0, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.0416141235813367, |
| "grad_norm": 2.2835693359375, |
| "learning_rate": 9.728643216080402e-06, |
| "loss": 1.6555, |
| "mean_token_accuracy": 0.5376385748386383, |
| "num_tokens": 63553.0, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.04287515762925599, |
| "grad_norm": 2.2488043308258057, |
| "learning_rate": 9.718592964824122e-06, |
| "loss": 1.5774, |
| "mean_token_accuracy": 0.5675285756587982, |
| "num_tokens": 65558.0, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.044136191677175286, |
| "grad_norm": 2.18747615814209, |
| "learning_rate": 9.70854271356784e-06, |
| "loss": 1.5627, |
| "mean_token_accuracy": 0.5848238170146942, |
| "num_tokens": 67564.0, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.04539722572509458, |
| "grad_norm": 2.113203525543213, |
| "learning_rate": 9.698492462311559e-06, |
| "loss": 1.508, |
| "mean_token_accuracy": 0.5855603218078613, |
| "num_tokens": 69539.0, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.04665825977301387, |
| "grad_norm": 2.139422655105591, |
| "learning_rate": 9.688442211055276e-06, |
| "loss": 1.73, |
| "mean_token_accuracy": 0.5467312037944794, |
| "num_tokens": 71512.0, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.04791929382093316, |
| "grad_norm": 2.383866310119629, |
| "learning_rate": 9.678391959798997e-06, |
| "loss": 1.6626, |
| "mean_token_accuracy": 0.5782844126224518, |
| "num_tokens": 73383.0, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.04918032786885246, |
| "grad_norm": 2.376224994659424, |
| "learning_rate": 9.668341708542714e-06, |
| "loss": 1.5964, |
| "mean_token_accuracy": 0.5940257608890533, |
| "num_tokens": 75361.0, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.05044136191677175, |
| "grad_norm": 2.2688498497009277, |
| "learning_rate": 9.658291457286433e-06, |
| "loss": 1.7523, |
| "mean_token_accuracy": 0.5537542700767517, |
| "num_tokens": 77248.0, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.05170239596469105, |
| "grad_norm": 2.20978045463562, |
| "learning_rate": 9.648241206030152e-06, |
| "loss": 1.627, |
| "mean_token_accuracy": 0.5710009932518005, |
| "num_tokens": 79221.0, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.05296343001261034, |
| "grad_norm": 2.337334394454956, |
| "learning_rate": 9.63819095477387e-06, |
| "loss": 1.6273, |
| "mean_token_accuracy": 0.5725916922092438, |
| "num_tokens": 81153.0, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.05422446406052964, |
| "grad_norm": 2.7503042221069336, |
| "learning_rate": 9.628140703517588e-06, |
| "loss": 1.7434, |
| "mean_token_accuracy": 0.559061199426651, |
| "num_tokens": 83040.0, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.05548549810844893, |
| "grad_norm": 2.37021541595459, |
| "learning_rate": 9.618090452261307e-06, |
| "loss": 1.792, |
| "mean_token_accuracy": 0.5494310259819031, |
| "num_tokens": 85031.0, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.05674653215636822, |
| "grad_norm": 2.2034897804260254, |
| "learning_rate": 9.608040201005026e-06, |
| "loss": 1.695, |
| "mean_token_accuracy": 0.564236044883728, |
| "num_tokens": 87028.0, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.058007566204287514, |
| "grad_norm": 2.2136058807373047, |
| "learning_rate": 9.597989949748745e-06, |
| "loss": 1.6232, |
| "mean_token_accuracy": 0.5797427892684937, |
| "num_tokens": 89126.0, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.05926860025220681, |
| "grad_norm": 2.24617338180542, |
| "learning_rate": 9.587939698492464e-06, |
| "loss": 1.5857, |
| "mean_token_accuracy": 0.586712121963501, |
| "num_tokens": 91168.0, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.0605296343001261, |
| "grad_norm": 2.30289626121521, |
| "learning_rate": 9.577889447236181e-06, |
| "loss": 1.7726, |
| "mean_token_accuracy": 0.561294674873352, |
| "num_tokens": 93032.0, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.0617906683480454, |
| "grad_norm": 2.2215540409088135, |
| "learning_rate": 9.5678391959799e-06, |
| "loss": 1.6229, |
| "mean_token_accuracy": 0.5766045451164246, |
| "num_tokens": 95044.0, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.06305170239596469, |
| "grad_norm": 2.1347873210906982, |
| "learning_rate": 9.55778894472362e-06, |
| "loss": 1.6054, |
| "mean_token_accuracy": 0.6011253893375397, |
| "num_tokens": 97163.0, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.06431273644388398, |
| "grad_norm": 2.5861363410949707, |
| "learning_rate": 9.547738693467338e-06, |
| "loss": 1.7562, |
| "mean_token_accuracy": 0.5489908456802368, |
| "num_tokens": 98944.0, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.06557377049180328, |
| "grad_norm": 2.5892691612243652, |
| "learning_rate": 9.537688442211056e-06, |
| "loss": 1.8814, |
| "mean_token_accuracy": 0.5629627406597137, |
| "num_tokens": 100938.0, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.06683480453972257, |
| "grad_norm": 2.378854751586914, |
| "learning_rate": 9.527638190954775e-06, |
| "loss": 1.689, |
| "mean_token_accuracy": 0.5640824437141418, |
| "num_tokens": 102836.0, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.06809583858764187, |
| "grad_norm": 2.3754119873046875, |
| "learning_rate": 9.517587939698492e-06, |
| "loss": 1.7916, |
| "mean_token_accuracy": 0.541223794221878, |
| "num_tokens": 104784.0, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.06935687263556116, |
| "grad_norm": 2.4103832244873047, |
| "learning_rate": 9.507537688442213e-06, |
| "loss": 1.6894, |
| "mean_token_accuracy": 0.5598744451999664, |
| "num_tokens": 106741.0, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.07061790668348046, |
| "grad_norm": 2.4184606075286865, |
| "learning_rate": 9.49748743718593e-06, |
| "loss": 1.696, |
| "mean_token_accuracy": 0.5523494184017181, |
| "num_tokens": 108562.0, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.07187894073139975, |
| "grad_norm": 2.68520188331604, |
| "learning_rate": 9.487437185929649e-06, |
| "loss": 1.7054, |
| "mean_token_accuracy": 0.5673016011714935, |
| "num_tokens": 110453.0, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.07313997477931904, |
| "grad_norm": 2.291822910308838, |
| "learning_rate": 9.477386934673368e-06, |
| "loss": 1.5153, |
| "mean_token_accuracy": 0.6045016646385193, |
| "num_tokens": 112433.0, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.07440100882723834, |
| "grad_norm": 2.432077169418335, |
| "learning_rate": 9.467336683417087e-06, |
| "loss": 1.5092, |
| "mean_token_accuracy": 0.583935409784317, |
| "num_tokens": 114403.0, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.07566204287515763, |
| "grad_norm": 2.637488603591919, |
| "learning_rate": 9.457286432160804e-06, |
| "loss": 1.7462, |
| "mean_token_accuracy": 0.555133581161499, |
| "num_tokens": 116273.0, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.07692307692307693, |
| "grad_norm": 2.5129623413085938, |
| "learning_rate": 9.447236180904523e-06, |
| "loss": 1.4024, |
| "mean_token_accuracy": 0.605218768119812, |
| "num_tokens": 118225.0, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.07818411097099622, |
| "grad_norm": 2.738636016845703, |
| "learning_rate": 9.437185929648242e-06, |
| "loss": 1.7453, |
| "mean_token_accuracy": 0.5735966861248016, |
| "num_tokens": 119996.0, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.07944514501891552, |
| "grad_norm": 2.4731392860412598, |
| "learning_rate": 9.427135678391961e-06, |
| "loss": 1.616, |
| "mean_token_accuracy": 0.5887857377529144, |
| "num_tokens": 121942.0, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.0807061790668348, |
| "grad_norm": 2.652911424636841, |
| "learning_rate": 9.41708542713568e-06, |
| "loss": 1.5038, |
| "mean_token_accuracy": 0.5989990532398224, |
| "num_tokens": 123805.0, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.08196721311475409, |
| "grad_norm": 2.7178895473480225, |
| "learning_rate": 9.407035175879397e-06, |
| "loss": 1.5098, |
| "mean_token_accuracy": 0.5910103917121887, |
| "num_tokens": 125565.0, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.0832282471626734, |
| "grad_norm": 2.8396823406219482, |
| "learning_rate": 9.396984924623116e-06, |
| "loss": 1.6004, |
| "mean_token_accuracy": 0.55643430352211, |
| "num_tokens": 127386.0, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.08448928121059268, |
| "grad_norm": 2.6496288776397705, |
| "learning_rate": 9.386934673366835e-06, |
| "loss": 1.504, |
| "mean_token_accuracy": 0.5963855981826782, |
| "num_tokens": 129221.0, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.08575031525851198, |
| "grad_norm": 2.787884473800659, |
| "learning_rate": 9.376884422110554e-06, |
| "loss": 1.5342, |
| "mean_token_accuracy": 0.5652304589748383, |
| "num_tokens": 131174.0, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.08701134930643127, |
| "grad_norm": 2.9477081298828125, |
| "learning_rate": 9.366834170854272e-06, |
| "loss": 1.6672, |
| "mean_token_accuracy": 0.5643592774868011, |
| "num_tokens": 133057.0, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.08827238335435057, |
| "grad_norm": 2.6482694149017334, |
| "learning_rate": 9.35678391959799e-06, |
| "loss": 1.6656, |
| "mean_token_accuracy": 0.5611771643161774, |
| "num_tokens": 134987.0, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.08953341740226986, |
| "grad_norm": 2.859524965286255, |
| "learning_rate": 9.34673366834171e-06, |
| "loss": 1.7194, |
| "mean_token_accuracy": 0.5627062320709229, |
| "num_tokens": 137011.0, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.09079445145018916, |
| "grad_norm": 2.6479501724243164, |
| "learning_rate": 9.336683417085429e-06, |
| "loss": 1.6618, |
| "mean_token_accuracy": 0.5560078024864197, |
| "num_tokens": 139091.0, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.09205548549810845, |
| "grad_norm": 3.0027458667755127, |
| "learning_rate": 9.326633165829146e-06, |
| "loss": 1.4664, |
| "mean_token_accuracy": 0.5918697118759155, |
| "num_tokens": 140792.0, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.09331651954602774, |
| "grad_norm": 2.6897335052490234, |
| "learning_rate": 9.316582914572865e-06, |
| "loss": 1.7032, |
| "mean_token_accuracy": 0.5572026073932648, |
| "num_tokens": 142860.0, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.09457755359394704, |
| "grad_norm": 2.633775234222412, |
| "learning_rate": 9.306532663316584e-06, |
| "loss": 1.5962, |
| "mean_token_accuracy": 0.5584298372268677, |
| "num_tokens": 144791.0, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.09583858764186633, |
| "grad_norm": 2.569234609603882, |
| "learning_rate": 9.296482412060303e-06, |
| "loss": 1.5447, |
| "mean_token_accuracy": 0.5784437358379364, |
| "num_tokens": 146664.0, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.09709962168978563, |
| "grad_norm": 2.6059482097625732, |
| "learning_rate": 9.28643216080402e-06, |
| "loss": 1.5189, |
| "mean_token_accuracy": 0.5865690112113953, |
| "num_tokens": 148523.0, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.09836065573770492, |
| "grad_norm": 2.596928358078003, |
| "learning_rate": 9.276381909547739e-06, |
| "loss": 1.5184, |
| "mean_token_accuracy": 0.607656866312027, |
| "num_tokens": 150391.0, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.09962168978562422, |
| "grad_norm": 2.553182363510132, |
| "learning_rate": 9.266331658291458e-06, |
| "loss": 1.6261, |
| "mean_token_accuracy": 0.5972858965396881, |
| "num_tokens": 152283.0, |
| "step": 79 |
| }, |
| { |
| "epoch": 0.1008827238335435, |
| "grad_norm": 2.491711139678955, |
| "learning_rate": 9.256281407035177e-06, |
| "loss": 1.5702, |
| "mean_token_accuracy": 0.5803692638874054, |
| "num_tokens": 154205.0, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.1021437578814628, |
| "grad_norm": 2.6098482608795166, |
| "learning_rate": 9.246231155778896e-06, |
| "loss": 1.5923, |
| "mean_token_accuracy": 0.5922619104385376, |
| "num_tokens": 156072.0, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.1034047919293821, |
| "grad_norm": 2.5393171310424805, |
| "learning_rate": 9.236180904522613e-06, |
| "loss": 1.5839, |
| "mean_token_accuracy": 0.5735230147838593, |
| "num_tokens": 158117.0, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.10466582597730138, |
| "grad_norm": 2.4480690956115723, |
| "learning_rate": 9.226130653266332e-06, |
| "loss": 1.5234, |
| "mean_token_accuracy": 0.5989161133766174, |
| "num_tokens": 160108.0, |
| "step": 83 |
| }, |
| { |
| "epoch": 0.10592686002522068, |
| "grad_norm": 2.672848701477051, |
| "learning_rate": 9.216080402010051e-06, |
| "loss": 1.5663, |
| "mean_token_accuracy": 0.5825683176517487, |
| "num_tokens": 161980.0, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.10718789407313997, |
| "grad_norm": 2.712820053100586, |
| "learning_rate": 9.20603015075377e-06, |
| "loss": 1.6086, |
| "mean_token_accuracy": 0.5695419013500214, |
| "num_tokens": 163855.0, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.10844892812105927, |
| "grad_norm": 2.6897265911102295, |
| "learning_rate": 9.195979899497488e-06, |
| "loss": 1.4995, |
| "mean_token_accuracy": 0.5717358291149139, |
| "num_tokens": 165804.0, |
| "step": 86 |
| }, |
| { |
| "epoch": 0.10970996216897856, |
| "grad_norm": 2.598402500152588, |
| "learning_rate": 9.185929648241207e-06, |
| "loss": 1.5517, |
| "mean_token_accuracy": 0.6070716977119446, |
| "num_tokens": 167766.0, |
| "step": 87 |
| }, |
| { |
| "epoch": 0.11097099621689786, |
| "grad_norm": 2.501206159591675, |
| "learning_rate": 9.175879396984926e-06, |
| "loss": 1.5865, |
| "mean_token_accuracy": 0.5794200301170349, |
| "num_tokens": 169824.0, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.11223203026481715, |
| "grad_norm": 2.627718210220337, |
| "learning_rate": 9.165829145728645e-06, |
| "loss": 1.6783, |
| "mean_token_accuracy": 0.5721315741539001, |
| "num_tokens": 171889.0, |
| "step": 89 |
| }, |
| { |
| "epoch": 0.11349306431273644, |
| "grad_norm": 2.721613883972168, |
| "learning_rate": 9.155778894472362e-06, |
| "loss": 1.688, |
| "mean_token_accuracy": 0.5747184753417969, |
| "num_tokens": 173856.0, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.11475409836065574, |
| "grad_norm": 2.6621620655059814, |
| "learning_rate": 9.14572864321608e-06, |
| "loss": 1.6448, |
| "mean_token_accuracy": 0.5579420924186707, |
| "num_tokens": 175948.0, |
| "step": 91 |
| }, |
| { |
| "epoch": 0.11601513240857503, |
| "grad_norm": 2.5622129440307617, |
| "learning_rate": 9.1356783919598e-06, |
| "loss": 1.6262, |
| "mean_token_accuracy": 0.5832908749580383, |
| "num_tokens": 177895.0, |
| "step": 92 |
| }, |
| { |
| "epoch": 0.11727616645649433, |
| "grad_norm": 2.75614333152771, |
| "learning_rate": 9.125628140703519e-06, |
| "loss": 1.6881, |
| "mean_token_accuracy": 0.57300865650177, |
| "num_tokens": 179936.0, |
| "step": 93 |
| }, |
| { |
| "epoch": 0.11853720050441362, |
| "grad_norm": 2.635789632797241, |
| "learning_rate": 9.115577889447236e-06, |
| "loss": 1.5284, |
| "mean_token_accuracy": 0.5902575850486755, |
| "num_tokens": 181893.0, |
| "step": 94 |
| }, |
| { |
| "epoch": 0.11979823455233292, |
| "grad_norm": 2.6811742782592773, |
| "learning_rate": 9.105527638190955e-06, |
| "loss": 1.5528, |
| "mean_token_accuracy": 0.5842621624469757, |
| "num_tokens": 183786.0, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.1210592686002522, |
| "grad_norm": 2.7067983150482178, |
| "learning_rate": 9.095477386934674e-06, |
| "loss": 1.4788, |
| "mean_token_accuracy": 0.6176944077014923, |
| "num_tokens": 185598.0, |
| "step": 96 |
| }, |
| { |
| "epoch": 0.1223203026481715, |
| "grad_norm": 2.74711537361145, |
| "learning_rate": 9.085427135678393e-06, |
| "loss": 1.6061, |
| "mean_token_accuracy": 0.57203009724617, |
| "num_tokens": 187533.0, |
| "step": 97 |
| }, |
| { |
| "epoch": 0.1235813366960908, |
| "grad_norm": 2.709876775741577, |
| "learning_rate": 9.075376884422112e-06, |
| "loss": 1.6724, |
| "mean_token_accuracy": 0.5607536435127258, |
| "num_tokens": 189657.0, |
| "step": 98 |
| }, |
| { |
| "epoch": 0.12484237074401008, |
| "grad_norm": 2.878828763961792, |
| "learning_rate": 9.06532663316583e-06, |
| "loss": 1.6774, |
| "mean_token_accuracy": 0.572198748588562, |
| "num_tokens": 191490.0, |
| "step": 99 |
| }, |
| { |
| "epoch": 0.12610340479192939, |
| "grad_norm": 2.648038387298584, |
| "learning_rate": 9.055276381909548e-06, |
| "loss": 1.5169, |
| "mean_token_accuracy": 0.591842383146286, |
| "num_tokens": 193315.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.1273644388398487, |
| "grad_norm": 2.595611810684204, |
| "learning_rate": 9.045226130653267e-06, |
| "loss": 1.5233, |
| "mean_token_accuracy": 0.5999257862567902, |
| "num_tokens": 195216.0, |
| "step": 101 |
| }, |
| { |
| "epoch": 0.12862547288776796, |
| "grad_norm": 2.832615613937378, |
| "learning_rate": 9.035175879396986e-06, |
| "loss": 1.6097, |
| "mean_token_accuracy": 0.5809868276119232, |
| "num_tokens": 197195.0, |
| "step": 102 |
| }, |
| { |
| "epoch": 0.12988650693568726, |
| "grad_norm": 2.7986865043640137, |
| "learning_rate": 9.025125628140704e-06, |
| "loss": 1.4399, |
| "mean_token_accuracy": 0.6075018346309662, |
| "num_tokens": 199089.0, |
| "step": 103 |
| }, |
| { |
| "epoch": 0.13114754098360656, |
| "grad_norm": 3.110140085220337, |
| "learning_rate": 9.015075376884423e-06, |
| "loss": 1.5235, |
| "mean_token_accuracy": 0.5926302969455719, |
| "num_tokens": 200996.0, |
| "step": 104 |
| }, |
| { |
| "epoch": 0.13240857503152584, |
| "grad_norm": 3.1775548458099365, |
| "learning_rate": 9.005025125628142e-06, |
| "loss": 1.7052, |
| "mean_token_accuracy": 0.5665183067321777, |
| "num_tokens": 203036.0, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.13366960907944514, |
| "grad_norm": 2.8712027072906494, |
| "learning_rate": 8.99497487437186e-06, |
| "loss": 1.6732, |
| "mean_token_accuracy": 0.5525965392589569, |
| "num_tokens": 204989.0, |
| "step": 106 |
| }, |
| { |
| "epoch": 0.13493064312736444, |
| "grad_norm": 3.003157138824463, |
| "learning_rate": 8.984924623115578e-06, |
| "loss": 1.4789, |
| "mean_token_accuracy": 0.6096234619617462, |
| "num_tokens": 206890.0, |
| "step": 107 |
| }, |
| { |
| "epoch": 0.13619167717528374, |
| "grad_norm": 3.042806625366211, |
| "learning_rate": 8.974874371859297e-06, |
| "loss": 1.7016, |
| "mean_token_accuracy": 0.5704866051673889, |
| "num_tokens": 208746.0, |
| "step": 108 |
| }, |
| { |
| "epoch": 0.13745271122320302, |
| "grad_norm": 2.9089457988739014, |
| "learning_rate": 8.964824120603016e-06, |
| "loss": 1.617, |
| "mean_token_accuracy": 0.5876918733119965, |
| "num_tokens": 210524.0, |
| "step": 109 |
| }, |
| { |
| "epoch": 0.13871374527112232, |
| "grad_norm": 2.7279868125915527, |
| "learning_rate": 8.954773869346735e-06, |
| "loss": 1.4657, |
| "mean_token_accuracy": 0.6049702763557434, |
| "num_tokens": 212559.0, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.13997477931904162, |
| "grad_norm": 2.714931011199951, |
| "learning_rate": 8.944723618090452e-06, |
| "loss": 1.517, |
| "mean_token_accuracy": 0.5795559883117676, |
| "num_tokens": 214556.0, |
| "step": 111 |
| }, |
| { |
| "epoch": 0.14123581336696092, |
| "grad_norm": 3.201127052307129, |
| "learning_rate": 8.934673366834171e-06, |
| "loss": 1.7466, |
| "mean_token_accuracy": 0.5589637458324432, |
| "num_tokens": 216431.0, |
| "step": 112 |
| }, |
| { |
| "epoch": 0.1424968474148802, |
| "grad_norm": 2.897251844406128, |
| "learning_rate": 8.92462311557789e-06, |
| "loss": 1.6198, |
| "mean_token_accuracy": 0.5685024857521057, |
| "num_tokens": 218385.0, |
| "step": 113 |
| }, |
| { |
| "epoch": 0.1437578814627995, |
| "grad_norm": 2.9811577796936035, |
| "learning_rate": 8.914572864321609e-06, |
| "loss": 1.6918, |
| "mean_token_accuracy": 0.5592131316661835, |
| "num_tokens": 220264.0, |
| "step": 114 |
| }, |
| { |
| "epoch": 0.1450189155107188, |
| "grad_norm": 2.761154890060425, |
| "learning_rate": 8.904522613065328e-06, |
| "loss": 1.4413, |
| "mean_token_accuracy": 0.607598602771759, |
| "num_tokens": 222234.0, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.14627994955863807, |
| "grad_norm": 2.7430713176727295, |
| "learning_rate": 8.894472361809045e-06, |
| "loss": 1.6057, |
| "mean_token_accuracy": 0.5697590708732605, |
| "num_tokens": 224235.0, |
| "step": 116 |
| }, |
| { |
| "epoch": 0.14754098360655737, |
| "grad_norm": 2.918210506439209, |
| "learning_rate": 8.884422110552764e-06, |
| "loss": 1.5457, |
| "mean_token_accuracy": 0.591588020324707, |
| "num_tokens": 226096.0, |
| "step": 117 |
| }, |
| { |
| "epoch": 0.14880201765447668, |
| "grad_norm": 2.6790671348571777, |
| "learning_rate": 8.874371859296483e-06, |
| "loss": 1.443, |
| "mean_token_accuracy": 0.6012678742408752, |
| "num_tokens": 228019.0, |
| "step": 118 |
| }, |
| { |
| "epoch": 0.15006305170239598, |
| "grad_norm": 2.750054121017456, |
| "learning_rate": 8.864321608040202e-06, |
| "loss": 1.637, |
| "mean_token_accuracy": 0.5751925110816956, |
| "num_tokens": 229941.0, |
| "step": 119 |
| }, |
| { |
| "epoch": 0.15132408575031525, |
| "grad_norm": 2.8466269969940186, |
| "learning_rate": 8.85427135678392e-06, |
| "loss": 1.6366, |
| "mean_token_accuracy": 0.5905842185020447, |
| "num_tokens": 231876.0, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.15258511979823455, |
| "grad_norm": 2.7871110439300537, |
| "learning_rate": 8.84422110552764e-06, |
| "loss": 1.6715, |
| "mean_token_accuracy": 0.5633519887924194, |
| "num_tokens": 233843.0, |
| "step": 121 |
| }, |
| { |
| "epoch": 0.15384615384615385, |
| "grad_norm": 2.968783140182495, |
| "learning_rate": 8.834170854271358e-06, |
| "loss": 1.6749, |
| "mean_token_accuracy": 0.5574239790439606, |
| "num_tokens": 235793.0, |
| "step": 122 |
| }, |
| { |
| "epoch": 0.15510718789407313, |
| "grad_norm": 2.7860939502716064, |
| "learning_rate": 8.824120603015077e-06, |
| "loss": 1.5969, |
| "mean_token_accuracy": 0.5728148519992828, |
| "num_tokens": 237694.0, |
| "step": 123 |
| }, |
| { |
| "epoch": 0.15636822194199243, |
| "grad_norm": 3.2282159328460693, |
| "learning_rate": 8.814070351758794e-06, |
| "loss": 1.7204, |
| "mean_token_accuracy": 0.5495528876781464, |
| "num_tokens": 239552.0, |
| "step": 124 |
| }, |
| { |
| "epoch": 0.15762925598991173, |
| "grad_norm": 3.045755386352539, |
| "learning_rate": 8.804020100502513e-06, |
| "loss": 1.661, |
| "mean_token_accuracy": 0.5639893710613251, |
| "num_tokens": 241426.0, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.15889029003783103, |
| "grad_norm": 3.0578441619873047, |
| "learning_rate": 8.793969849246232e-06, |
| "loss": 1.5309, |
| "mean_token_accuracy": 0.595091313123703, |
| "num_tokens": 243267.0, |
| "step": 126 |
| }, |
| { |
| "epoch": 0.1601513240857503, |
| "grad_norm": 2.958604574203491, |
| "learning_rate": 8.78391959798995e-06, |
| "loss": 1.6655, |
| "mean_token_accuracy": 0.5795525014400482, |
| "num_tokens": 245083.0, |
| "step": 127 |
| }, |
| { |
| "epoch": 0.1614123581336696, |
| "grad_norm": 3.106072187423706, |
| "learning_rate": 8.773869346733668e-06, |
| "loss": 1.6707, |
| "mean_token_accuracy": 0.5593680441379547, |
| "num_tokens": 246989.0, |
| "step": 128 |
| }, |
| { |
| "epoch": 0.1626733921815889, |
| "grad_norm": 2.5481674671173096, |
| "learning_rate": 8.763819095477387e-06, |
| "loss": 1.3744, |
| "mean_token_accuracy": 0.6058414876461029, |
| "num_tokens": 249166.0, |
| "step": 129 |
| }, |
| { |
| "epoch": 0.16393442622950818, |
| "grad_norm": 2.921290397644043, |
| "learning_rate": 8.753768844221106e-06, |
| "loss": 1.4897, |
| "mean_token_accuracy": 0.5849105715751648, |
| "num_tokens": 251116.0, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.16519546027742749, |
| "grad_norm": 2.922968864440918, |
| "learning_rate": 8.743718592964825e-06, |
| "loss": 1.5134, |
| "mean_token_accuracy": 0.5913949608802795, |
| "num_tokens": 253149.0, |
| "step": 131 |
| }, |
| { |
| "epoch": 0.1664564943253468, |
| "grad_norm": 2.970926284790039, |
| "learning_rate": 8.733668341708544e-06, |
| "loss": 1.6613, |
| "mean_token_accuracy": 0.5610753297805786, |
| "num_tokens": 255159.0, |
| "step": 132 |
| }, |
| { |
| "epoch": 0.1677175283732661, |
| "grad_norm": 3.0989766120910645, |
| "learning_rate": 8.723618090452261e-06, |
| "loss": 1.6105, |
| "mean_token_accuracy": 0.5713566243648529, |
| "num_tokens": 257043.0, |
| "step": 133 |
| }, |
| { |
| "epoch": 0.16897856242118536, |
| "grad_norm": 3.1648123264312744, |
| "learning_rate": 8.71356783919598e-06, |
| "loss": 1.6512, |
| "mean_token_accuracy": 0.5838274359703064, |
| "num_tokens": 258957.0, |
| "step": 134 |
| }, |
| { |
| "epoch": 0.17023959646910466, |
| "grad_norm": 2.8205583095550537, |
| "learning_rate": 8.7035175879397e-06, |
| "loss": 1.5361, |
| "mean_token_accuracy": 0.5936324000358582, |
| "num_tokens": 260985.0, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.17150063051702397, |
| "grad_norm": 2.8423306941986084, |
| "learning_rate": 8.693467336683418e-06, |
| "loss": 1.486, |
| "mean_token_accuracy": 0.6080349981784821, |
| "num_tokens": 262979.0, |
| "step": 136 |
| }, |
| { |
| "epoch": 0.17276166456494324, |
| "grad_norm": 2.691563606262207, |
| "learning_rate": 8.683417085427136e-06, |
| "loss": 1.3849, |
| "mean_token_accuracy": 0.6165161728858948, |
| "num_tokens": 265104.0, |
| "step": 137 |
| }, |
| { |
| "epoch": 0.17402269861286254, |
| "grad_norm": 3.1580026149749756, |
| "learning_rate": 8.673366834170856e-06, |
| "loss": 1.6945, |
| "mean_token_accuracy": 0.5731165111064911, |
| "num_tokens": 266978.0, |
| "step": 138 |
| }, |
| { |
| "epoch": 0.17528373266078184, |
| "grad_norm": 2.9275593757629395, |
| "learning_rate": 8.663316582914574e-06, |
| "loss": 1.5525, |
| "mean_token_accuracy": 0.5952293872833252, |
| "num_tokens": 268974.0, |
| "step": 139 |
| }, |
| { |
| "epoch": 0.17654476670870115, |
| "grad_norm": 3.0754551887512207, |
| "learning_rate": 8.653266331658293e-06, |
| "loss": 1.5217, |
| "mean_token_accuracy": 0.5957006216049194, |
| "num_tokens": 270907.0, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.17780580075662042, |
| "grad_norm": 2.886082410812378, |
| "learning_rate": 8.64321608040201e-06, |
| "loss": 1.5821, |
| "mean_token_accuracy": 0.5947231650352478, |
| "num_tokens": 272954.0, |
| "step": 141 |
| }, |
| { |
| "epoch": 0.17906683480453972, |
| "grad_norm": 3.351433515548706, |
| "learning_rate": 8.63316582914573e-06, |
| "loss": 1.6648, |
| "mean_token_accuracy": 0.5699703097343445, |
| "num_tokens": 274775.0, |
| "step": 142 |
| }, |
| { |
| "epoch": 0.18032786885245902, |
| "grad_norm": 3.4224631786346436, |
| "learning_rate": 8.623115577889448e-06, |
| "loss": 1.7437, |
| "mean_token_accuracy": 0.5447712540626526, |
| "num_tokens": 276768.0, |
| "step": 143 |
| }, |
| { |
| "epoch": 0.18158890290037832, |
| "grad_norm": 3.0779998302459717, |
| "learning_rate": 8.613065326633167e-06, |
| "loss": 1.5684, |
| "mean_token_accuracy": 0.5806187391281128, |
| "num_tokens": 278833.0, |
| "step": 144 |
| }, |
| { |
| "epoch": 0.1828499369482976, |
| "grad_norm": 2.9735560417175293, |
| "learning_rate": 8.603015075376884e-06, |
| "loss": 1.5676, |
| "mean_token_accuracy": 0.5861871242523193, |
| "num_tokens": 280943.0, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.1841109709962169, |
| "grad_norm": 3.011720895767212, |
| "learning_rate": 8.592964824120603e-06, |
| "loss": 1.5876, |
| "mean_token_accuracy": 0.5901258885860443, |
| "num_tokens": 282915.0, |
| "step": 146 |
| }, |
| { |
| "epoch": 0.1853720050441362, |
| "grad_norm": 2.793816566467285, |
| "learning_rate": 8.582914572864322e-06, |
| "loss": 1.6132, |
| "mean_token_accuracy": 0.5637544989585876, |
| "num_tokens": 284878.0, |
| "step": 147 |
| }, |
| { |
| "epoch": 0.18663303909205547, |
| "grad_norm": 3.4991912841796875, |
| "learning_rate": 8.572864321608041e-06, |
| "loss": 1.7657, |
| "mean_token_accuracy": 0.5335510969161987, |
| "num_tokens": 286705.0, |
| "step": 148 |
| }, |
| { |
| "epoch": 0.18789407313997478, |
| "grad_norm": 3.0108628273010254, |
| "learning_rate": 8.56281407035176e-06, |
| "loss": 1.6132, |
| "mean_token_accuracy": 0.5785773396492004, |
| "num_tokens": 288754.0, |
| "step": 149 |
| }, |
| { |
| "epoch": 0.18915510718789408, |
| "grad_norm": 2.9029171466827393, |
| "learning_rate": 8.552763819095477e-06, |
| "loss": 1.579, |
| "mean_token_accuracy": 0.569399356842041, |
| "num_tokens": 290870.0, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.19041614123581338, |
| "grad_norm": 2.9917798042297363, |
| "learning_rate": 8.542713567839196e-06, |
| "loss": 1.4786, |
| "mean_token_accuracy": 0.5690844357013702, |
| "num_tokens": 292793.0, |
| "step": 151 |
| }, |
| { |
| "epoch": 0.19167717528373265, |
| "grad_norm": 2.975250244140625, |
| "learning_rate": 8.532663316582915e-06, |
| "loss": 1.5581, |
| "mean_token_accuracy": 0.5852090418338776, |
| "num_tokens": 294720.0, |
| "step": 152 |
| }, |
| { |
| "epoch": 0.19293820933165196, |
| "grad_norm": 2.9272823333740234, |
| "learning_rate": 8.522613065326634e-06, |
| "loss": 1.5473, |
| "mean_token_accuracy": 0.6112104654312134, |
| "num_tokens": 296635.0, |
| "step": 153 |
| }, |
| { |
| "epoch": 0.19419924337957126, |
| "grad_norm": 2.9161503314971924, |
| "learning_rate": 8.512562814070352e-06, |
| "loss": 1.6033, |
| "mean_token_accuracy": 0.5668641626834869, |
| "num_tokens": 298594.0, |
| "step": 154 |
| }, |
| { |
| "epoch": 0.19546027742749053, |
| "grad_norm": 3.18533992767334, |
| "learning_rate": 8.50251256281407e-06, |
| "loss": 1.7068, |
| "mean_token_accuracy": 0.5527530014514923, |
| "num_tokens": 300486.0, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.19672131147540983, |
| "grad_norm": 2.7139334678649902, |
| "learning_rate": 8.49246231155779e-06, |
| "loss": 1.4933, |
| "mean_token_accuracy": 0.6057660579681396, |
| "num_tokens": 302644.0, |
| "step": 156 |
| }, |
| { |
| "epoch": 0.19798234552332913, |
| "grad_norm": 3.2782130241394043, |
| "learning_rate": 8.482412060301509e-06, |
| "loss": 1.7089, |
| "mean_token_accuracy": 0.5606865286827087, |
| "num_tokens": 304633.0, |
| "step": 157 |
| }, |
| { |
| "epoch": 0.19924337957124844, |
| "grad_norm": 2.9586639404296875, |
| "learning_rate": 8.472361809045226e-06, |
| "loss": 1.5175, |
| "mean_token_accuracy": 0.5918884575366974, |
| "num_tokens": 306464.0, |
| "step": 158 |
| }, |
| { |
| "epoch": 0.2005044136191677, |
| "grad_norm": 2.9477293491363525, |
| "learning_rate": 8.462311557788947e-06, |
| "loss": 1.577, |
| "mean_token_accuracy": 0.5871914923191071, |
| "num_tokens": 308411.0, |
| "step": 159 |
| }, |
| { |
| "epoch": 0.201765447667087, |
| "grad_norm": 3.1232988834381104, |
| "learning_rate": 8.452261306532664e-06, |
| "loss": 1.6529, |
| "mean_token_accuracy": 0.5661388039588928, |
| "num_tokens": 310318.0, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.2030264817150063, |
| "grad_norm": 3.2044501304626465, |
| "learning_rate": 8.442211055276383e-06, |
| "loss": 1.5058, |
| "mean_token_accuracy": 0.5906364917755127, |
| "num_tokens": 312258.0, |
| "step": 161 |
| }, |
| { |
| "epoch": 0.2042875157629256, |
| "grad_norm": 3.000061511993408, |
| "learning_rate": 8.4321608040201e-06, |
| "loss": 1.598, |
| "mean_token_accuracy": 0.5909577012062073, |
| "num_tokens": 314240.0, |
| "step": 162 |
| }, |
| { |
| "epoch": 0.2055485498108449, |
| "grad_norm": 3.1347744464874268, |
| "learning_rate": 8.42211055276382e-06, |
| "loss": 1.6521, |
| "mean_token_accuracy": 0.5816281735897064, |
| "num_tokens": 316143.0, |
| "step": 163 |
| }, |
| { |
| "epoch": 0.2068095838587642, |
| "grad_norm": 3.3936872482299805, |
| "learning_rate": 8.412060301507538e-06, |
| "loss": 1.6464, |
| "mean_token_accuracy": 0.5704096853733063, |
| "num_tokens": 317991.0, |
| "step": 164 |
| }, |
| { |
| "epoch": 0.2080706179066835, |
| "grad_norm": 3.3278539180755615, |
| "learning_rate": 8.402010050251257e-06, |
| "loss": 1.6449, |
| "mean_token_accuracy": 0.5696335732936859, |
| "num_tokens": 319862.0, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.20933165195460277, |
| "grad_norm": 3.020671844482422, |
| "learning_rate": 8.391959798994976e-06, |
| "loss": 1.4622, |
| "mean_token_accuracy": 0.6038527488708496, |
| "num_tokens": 321818.0, |
| "step": 166 |
| }, |
| { |
| "epoch": 0.21059268600252207, |
| "grad_norm": 3.302604913711548, |
| "learning_rate": 8.381909547738695e-06, |
| "loss": 1.6799, |
| "mean_token_accuracy": 0.5652211308479309, |
| "num_tokens": 323697.0, |
| "step": 167 |
| }, |
| { |
| "epoch": 0.21185372005044137, |
| "grad_norm": 3.095177412033081, |
| "learning_rate": 8.371859296482412e-06, |
| "loss": 1.546, |
| "mean_token_accuracy": 0.6060132384300232, |
| "num_tokens": 325514.0, |
| "step": 168 |
| }, |
| { |
| "epoch": 0.21311475409836064, |
| "grad_norm": 3.172431230545044, |
| "learning_rate": 8.361809045226131e-06, |
| "loss": 1.5454, |
| "mean_token_accuracy": 0.5665743947029114, |
| "num_tokens": 327475.0, |
| "step": 169 |
| }, |
| { |
| "epoch": 0.21437578814627994, |
| "grad_norm": 3.219557523727417, |
| "learning_rate": 8.35175879396985e-06, |
| "loss": 1.5308, |
| "mean_token_accuracy": 0.5844057202339172, |
| "num_tokens": 329369.0, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.21563682219419925, |
| "grad_norm": 3.15195369720459, |
| "learning_rate": 8.341708542713568e-06, |
| "loss": 1.4547, |
| "mean_token_accuracy": 0.5937274396419525, |
| "num_tokens": 331331.0, |
| "step": 171 |
| }, |
| { |
| "epoch": 0.21689785624211855, |
| "grad_norm": 3.384577512741089, |
| "learning_rate": 8.331658291457287e-06, |
| "loss": 1.5924, |
| "mean_token_accuracy": 0.5657446384429932, |
| "num_tokens": 333397.0, |
| "step": 172 |
| }, |
| { |
| "epoch": 0.21815889029003782, |
| "grad_norm": 3.2312798500061035, |
| "learning_rate": 8.321608040201006e-06, |
| "loss": 1.6828, |
| "mean_token_accuracy": 0.5660585463047028, |
| "num_tokens": 335414.0, |
| "step": 173 |
| }, |
| { |
| "epoch": 0.21941992433795712, |
| "grad_norm": 3.4180638790130615, |
| "learning_rate": 8.311557788944725e-06, |
| "loss": 1.6958, |
| "mean_token_accuracy": 0.5627331435680389, |
| "num_tokens": 337345.0, |
| "step": 174 |
| }, |
| { |
| "epoch": 0.22068095838587642, |
| "grad_norm": 2.9662837982177734, |
| "learning_rate": 8.301507537688442e-06, |
| "loss": 1.527, |
| "mean_token_accuracy": 0.6001080572605133, |
| "num_tokens": 339337.0, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.22194199243379573, |
| "grad_norm": 3.2255606651306152, |
| "learning_rate": 8.291457286432163e-06, |
| "loss": 1.5278, |
| "mean_token_accuracy": 0.5946673154830933, |
| "num_tokens": 341181.0, |
| "step": 176 |
| }, |
| { |
| "epoch": 0.223203026481715, |
| "grad_norm": 3.2812938690185547, |
| "learning_rate": 8.28140703517588e-06, |
| "loss": 1.5797, |
| "mean_token_accuracy": 0.5628663897514343, |
| "num_tokens": 343082.0, |
| "step": 177 |
| }, |
| { |
| "epoch": 0.2244640605296343, |
| "grad_norm": 3.1544275283813477, |
| "learning_rate": 8.271356783919599e-06, |
| "loss": 1.6043, |
| "mean_token_accuracy": 0.5775841474533081, |
| "num_tokens": 345084.0, |
| "step": 178 |
| }, |
| { |
| "epoch": 0.2257250945775536, |
| "grad_norm": 3.251833915710449, |
| "learning_rate": 8.261306532663316e-06, |
| "loss": 1.5187, |
| "mean_token_accuracy": 0.5886312425136566, |
| "num_tokens": 347066.0, |
| "step": 179 |
| }, |
| { |
| "epoch": 0.22698612862547288, |
| "grad_norm": 2.958277463912964, |
| "learning_rate": 8.251256281407037e-06, |
| "loss": 1.3687, |
| "mean_token_accuracy": 0.6186133921146393, |
| "num_tokens": 349078.0, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.22824716267339218, |
| "grad_norm": 3.3169801235198975, |
| "learning_rate": 8.241206030150754e-06, |
| "loss": 1.6039, |
| "mean_token_accuracy": 0.5811094343662262, |
| "num_tokens": 351027.0, |
| "step": 181 |
| }, |
| { |
| "epoch": 0.22950819672131148, |
| "grad_norm": 3.2675843238830566, |
| "learning_rate": 8.231155778894473e-06, |
| "loss": 1.6857, |
| "mean_token_accuracy": 0.5660231411457062, |
| "num_tokens": 353029.0, |
| "step": 182 |
| }, |
| { |
| "epoch": 0.23076923076923078, |
| "grad_norm": 3.0925302505493164, |
| "learning_rate": 8.221105527638192e-06, |
| "loss": 1.4972, |
| "mean_token_accuracy": 0.5996102690696716, |
| "num_tokens": 355021.0, |
| "step": 183 |
| }, |
| { |
| "epoch": 0.23203026481715006, |
| "grad_norm": 3.138523817062378, |
| "learning_rate": 8.211055276381911e-06, |
| "loss": 1.5691, |
| "mean_token_accuracy": 0.5705575346946716, |
| "num_tokens": 357111.0, |
| "step": 184 |
| }, |
| { |
| "epoch": 0.23329129886506936, |
| "grad_norm": 3.525383949279785, |
| "learning_rate": 8.201005025125628e-06, |
| "loss": 1.7461, |
| "mean_token_accuracy": 0.5512031316757202, |
| "num_tokens": 359069.0, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.23455233291298866, |
| "grad_norm": 3.2351460456848145, |
| "learning_rate": 8.190954773869347e-06, |
| "loss": 1.4813, |
| "mean_token_accuracy": 0.6038375794887543, |
| "num_tokens": 360938.0, |
| "step": 186 |
| }, |
| { |
| "epoch": 0.23581336696090793, |
| "grad_norm": 3.557286262512207, |
| "learning_rate": 8.180904522613066e-06, |
| "loss": 1.5621, |
| "mean_token_accuracy": 0.5763691961765289, |
| "num_tokens": 362776.0, |
| "step": 187 |
| }, |
| { |
| "epoch": 0.23707440100882723, |
| "grad_norm": 3.5422346591949463, |
| "learning_rate": 8.170854271356785e-06, |
| "loss": 1.6161, |
| "mean_token_accuracy": 0.569455623626709, |
| "num_tokens": 364738.0, |
| "step": 188 |
| }, |
| { |
| "epoch": 0.23833543505674654, |
| "grad_norm": 3.873141288757324, |
| "learning_rate": 8.160804020100503e-06, |
| "loss": 1.7209, |
| "mean_token_accuracy": 0.5447860360145569, |
| "num_tokens": 366531.0, |
| "step": 189 |
| }, |
| { |
| "epoch": 0.23959646910466584, |
| "grad_norm": 3.153902530670166, |
| "learning_rate": 8.150753768844222e-06, |
| "loss": 1.5113, |
| "mean_token_accuracy": 0.5915417969226837, |
| "num_tokens": 368428.0, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.2408575031525851, |
| "grad_norm": 3.097055435180664, |
| "learning_rate": 8.14070351758794e-06, |
| "loss": 1.5195, |
| "mean_token_accuracy": 0.6002468466758728, |
| "num_tokens": 370322.0, |
| "step": 191 |
| }, |
| { |
| "epoch": 0.2421185372005044, |
| "grad_norm": 3.285097599029541, |
| "learning_rate": 8.130653266331658e-06, |
| "loss": 1.6581, |
| "mean_token_accuracy": 0.5739455223083496, |
| "num_tokens": 372252.0, |
| "step": 192 |
| }, |
| { |
| "epoch": 0.24337957124842372, |
| "grad_norm": 3.3507330417633057, |
| "learning_rate": 8.120603015075379e-06, |
| "loss": 1.5387, |
| "mean_token_accuracy": 0.5838408470153809, |
| "num_tokens": 374192.0, |
| "step": 193 |
| }, |
| { |
| "epoch": 0.244640605296343, |
| "grad_norm": 3.3167335987091064, |
| "learning_rate": 8.110552763819096e-06, |
| "loss": 1.6052, |
| "mean_token_accuracy": 0.5623520910739899, |
| "num_tokens": 376066.0, |
| "step": 194 |
| }, |
| { |
| "epoch": 0.2459016393442623, |
| "grad_norm": 3.131056547164917, |
| "learning_rate": 8.100502512562815e-06, |
| "loss": 1.5329, |
| "mean_token_accuracy": 0.594320148229599, |
| "num_tokens": 377964.0, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.2471626733921816, |
| "grad_norm": 3.329434394836426, |
| "learning_rate": 8.090452261306532e-06, |
| "loss": 1.5315, |
| "mean_token_accuracy": 0.5931278765201569, |
| "num_tokens": 379795.0, |
| "step": 196 |
| }, |
| { |
| "epoch": 0.2484237074401009, |
| "grad_norm": 3.336644172668457, |
| "learning_rate": 8.080402010050253e-06, |
| "loss": 1.3831, |
| "mean_token_accuracy": 0.6193466484546661, |
| "num_tokens": 381825.0, |
| "step": 197 |
| }, |
| { |
| "epoch": 0.24968474148802017, |
| "grad_norm": 3.461484670639038, |
| "learning_rate": 8.07035175879397e-06, |
| "loss": 1.5953, |
| "mean_token_accuracy": 0.5787071585655212, |
| "num_tokens": 383761.0, |
| "step": 198 |
| }, |
| { |
| "epoch": 0.2509457755359395, |
| "grad_norm": 3.5501725673675537, |
| "learning_rate": 8.060301507537689e-06, |
| "loss": 1.672, |
| "mean_token_accuracy": 0.5670656561851501, |
| "num_tokens": 385481.0, |
| "step": 199 |
| }, |
| { |
| "epoch": 0.25220680958385877, |
| "grad_norm": 3.112483263015747, |
| "learning_rate": 8.050251256281408e-06, |
| "loss": 1.5285, |
| "mean_token_accuracy": 0.6005093157291412, |
| "num_tokens": 387572.0, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.25346784363177804, |
| "grad_norm": 3.0677380561828613, |
| "learning_rate": 8.040201005025127e-06, |
| "loss": 1.4804, |
| "mean_token_accuracy": 0.5969712436199188, |
| "num_tokens": 389616.0, |
| "step": 201 |
| }, |
| { |
| "epoch": 0.2547288776796974, |
| "grad_norm": 3.4487736225128174, |
| "learning_rate": 8.030150753768844e-06, |
| "loss": 1.5816, |
| "mean_token_accuracy": 0.5854290127754211, |
| "num_tokens": 391573.0, |
| "step": 202 |
| }, |
| { |
| "epoch": 0.25598991172761665, |
| "grad_norm": 3.226769208908081, |
| "learning_rate": 8.020100502512563e-06, |
| "loss": 1.517, |
| "mean_token_accuracy": 0.5958291292190552, |
| "num_tokens": 393528.0, |
| "step": 203 |
| }, |
| { |
| "epoch": 0.2572509457755359, |
| "grad_norm": 3.3854405879974365, |
| "learning_rate": 8.010050251256282e-06, |
| "loss": 1.4866, |
| "mean_token_accuracy": 0.6049782931804657, |
| "num_tokens": 395381.0, |
| "step": 204 |
| }, |
| { |
| "epoch": 0.25851197982345525, |
| "grad_norm": 3.206881284713745, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 1.6414, |
| "mean_token_accuracy": 0.5518943816423416, |
| "num_tokens": 397374.0, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.2597730138713745, |
| "grad_norm": 3.5540504455566406, |
| "learning_rate": 7.989949748743719e-06, |
| "loss": 1.5438, |
| "mean_token_accuracy": 0.6025577485561371, |
| "num_tokens": 399160.0, |
| "step": 206 |
| }, |
| { |
| "epoch": 0.2610340479192938, |
| "grad_norm": 3.0213472843170166, |
| "learning_rate": 7.979899497487438e-06, |
| "loss": 1.4256, |
| "mean_token_accuracy": 0.6132605969905853, |
| "num_tokens": 401346.0, |
| "step": 207 |
| }, |
| { |
| "epoch": 0.26229508196721313, |
| "grad_norm": 3.229039192199707, |
| "learning_rate": 7.969849246231157e-06, |
| "loss": 1.4214, |
| "mean_token_accuracy": 0.6175378262996674, |
| "num_tokens": 403274.0, |
| "step": 208 |
| }, |
| { |
| "epoch": 0.2635561160151324, |
| "grad_norm": 3.717940330505371, |
| "learning_rate": 7.959798994974876e-06, |
| "loss": 1.651, |
| "mean_token_accuracy": 0.5754619240760803, |
| "num_tokens": 405216.0, |
| "step": 209 |
| }, |
| { |
| "epoch": 0.2648171500630517, |
| "grad_norm": 3.3337504863739014, |
| "learning_rate": 7.949748743718595e-06, |
| "loss": 1.5087, |
| "mean_token_accuracy": 0.5871202051639557, |
| "num_tokens": 407019.0, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.266078184110971, |
| "grad_norm": 3.459760904312134, |
| "learning_rate": 7.939698492462312e-06, |
| "loss": 1.4881, |
| "mean_token_accuracy": 0.594930499792099, |
| "num_tokens": 408900.0, |
| "step": 211 |
| }, |
| { |
| "epoch": 0.2673392181588903, |
| "grad_norm": 3.259221076965332, |
| "learning_rate": 7.929648241206031e-06, |
| "loss": 1.5088, |
| "mean_token_accuracy": 0.596918374300003, |
| "num_tokens": 410700.0, |
| "step": 212 |
| }, |
| { |
| "epoch": 0.2686002522068096, |
| "grad_norm": 3.226205825805664, |
| "learning_rate": 7.91959798994975e-06, |
| "loss": 1.5928, |
| "mean_token_accuracy": 0.5743635892868042, |
| "num_tokens": 412621.0, |
| "step": 213 |
| }, |
| { |
| "epoch": 0.2698612862547289, |
| "grad_norm": 3.419466495513916, |
| "learning_rate": 7.909547738693469e-06, |
| "loss": 1.5618, |
| "mean_token_accuracy": 0.611274391412735, |
| "num_tokens": 414556.0, |
| "step": 214 |
| }, |
| { |
| "epoch": 0.27112232030264816, |
| "grad_norm": 3.5824954509735107, |
| "learning_rate": 7.899497487437186e-06, |
| "loss": 1.6001, |
| "mean_token_accuracy": 0.5866841375827789, |
| "num_tokens": 416473.0, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.2723833543505675, |
| "grad_norm": 3.112147092819214, |
| "learning_rate": 7.889447236180905e-06, |
| "loss": 1.5417, |
| "mean_token_accuracy": 0.5974981188774109, |
| "num_tokens": 418501.0, |
| "step": 216 |
| }, |
| { |
| "epoch": 0.27364438839848676, |
| "grad_norm": 3.240135669708252, |
| "learning_rate": 7.879396984924622e-06, |
| "loss": 1.5652, |
| "mean_token_accuracy": 0.5818172693252563, |
| "num_tokens": 420660.0, |
| "step": 217 |
| }, |
| { |
| "epoch": 0.27490542244640603, |
| "grad_norm": 3.4452712535858154, |
| "learning_rate": 7.869346733668343e-06, |
| "loss": 1.4589, |
| "mean_token_accuracy": 0.6087662279605865, |
| "num_tokens": 422643.0, |
| "step": 218 |
| }, |
| { |
| "epoch": 0.27616645649432536, |
| "grad_norm": 3.3906800746917725, |
| "learning_rate": 7.85929648241206e-06, |
| "loss": 1.5622, |
| "mean_token_accuracy": 0.5805779695510864, |
| "num_tokens": 424539.0, |
| "step": 219 |
| }, |
| { |
| "epoch": 0.27742749054224464, |
| "grad_norm": 3.3936314582824707, |
| "learning_rate": 7.84924623115578e-06, |
| "loss": 1.619, |
| "mean_token_accuracy": 0.579449862241745, |
| "num_tokens": 426508.0, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.2786885245901639, |
| "grad_norm": 3.3436079025268555, |
| "learning_rate": 7.839195979899498e-06, |
| "loss": 1.4223, |
| "mean_token_accuracy": 0.6132674217224121, |
| "num_tokens": 428335.0, |
| "step": 221 |
| }, |
| { |
| "epoch": 0.27994955863808324, |
| "grad_norm": 3.456958293914795, |
| "learning_rate": 7.829145728643217e-06, |
| "loss": 1.7676, |
| "mean_token_accuracy": 0.561681717634201, |
| "num_tokens": 430337.0, |
| "step": 222 |
| }, |
| { |
| "epoch": 0.2812105926860025, |
| "grad_norm": 3.24194598197937, |
| "learning_rate": 7.819095477386935e-06, |
| "loss": 1.4769, |
| "mean_token_accuracy": 0.6050495803356171, |
| "num_tokens": 432258.0, |
| "step": 223 |
| }, |
| { |
| "epoch": 0.28247162673392184, |
| "grad_norm": 3.5072057247161865, |
| "learning_rate": 7.809045226130654e-06, |
| "loss": 1.5944, |
| "mean_token_accuracy": 0.5768154859542847, |
| "num_tokens": 434223.0, |
| "step": 224 |
| }, |
| { |
| "epoch": 0.2837326607818411, |
| "grad_norm": 3.5962231159210205, |
| "learning_rate": 7.798994974874373e-06, |
| "loss": 1.6088, |
| "mean_token_accuracy": 0.5840071141719818, |
| "num_tokens": 436104.0, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.2849936948297604, |
| "grad_norm": 3.3810791969299316, |
| "learning_rate": 7.788944723618092e-06, |
| "loss": 1.666, |
| "mean_token_accuracy": 0.589882493019104, |
| "num_tokens": 438077.0, |
| "step": 226 |
| }, |
| { |
| "epoch": 0.2862547288776797, |
| "grad_norm": 3.416822671890259, |
| "learning_rate": 7.77889447236181e-06, |
| "loss": 1.5487, |
| "mean_token_accuracy": 0.5801858901977539, |
| "num_tokens": 439945.0, |
| "step": 227 |
| }, |
| { |
| "epoch": 0.287515762925599, |
| "grad_norm": 3.2244937419891357, |
| "learning_rate": 7.768844221105528e-06, |
| "loss": 1.6216, |
| "mean_token_accuracy": 0.5723104178905487, |
| "num_tokens": 441954.0, |
| "step": 228 |
| }, |
| { |
| "epoch": 0.28877679697351827, |
| "grad_norm": 3.1371960639953613, |
| "learning_rate": 7.758793969849247e-06, |
| "loss": 1.4734, |
| "mean_token_accuracy": 0.6173639297485352, |
| "num_tokens": 443779.0, |
| "step": 229 |
| }, |
| { |
| "epoch": 0.2900378310214376, |
| "grad_norm": 3.1513185501098633, |
| "learning_rate": 7.748743718592966e-06, |
| "loss": 1.4223, |
| "mean_token_accuracy": 0.6023972630500793, |
| "num_tokens": 445796.0, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.29129886506935687, |
| "grad_norm": 3.282952308654785, |
| "learning_rate": 7.738693467336685e-06, |
| "loss": 1.4113, |
| "mean_token_accuracy": 0.6114111840724945, |
| "num_tokens": 447836.0, |
| "step": 231 |
| }, |
| { |
| "epoch": 0.29255989911727615, |
| "grad_norm": 3.6755146980285645, |
| "learning_rate": 7.728643216080402e-06, |
| "loss": 1.718, |
| "mean_token_accuracy": 0.5667296946048737, |
| "num_tokens": 449695.0, |
| "step": 232 |
| }, |
| { |
| "epoch": 0.2938209331651955, |
| "grad_norm": 3.4634885787963867, |
| "learning_rate": 7.718592964824121e-06, |
| "loss": 1.3988, |
| "mean_token_accuracy": 0.5955272018909454, |
| "num_tokens": 451449.0, |
| "step": 233 |
| }, |
| { |
| "epoch": 0.29508196721311475, |
| "grad_norm": 3.4528040885925293, |
| "learning_rate": 7.70854271356784e-06, |
| "loss": 1.5645, |
| "mean_token_accuracy": 0.5831862390041351, |
| "num_tokens": 453390.0, |
| "step": 234 |
| }, |
| { |
| "epoch": 0.296343001261034, |
| "grad_norm": 3.343466281890869, |
| "learning_rate": 7.698492462311559e-06, |
| "loss": 1.5536, |
| "mean_token_accuracy": 0.5883003771305084, |
| "num_tokens": 455368.0, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.29760403530895335, |
| "grad_norm": 3.345386505126953, |
| "learning_rate": 7.688442211055276e-06, |
| "loss": 1.4676, |
| "mean_token_accuracy": 0.6198924779891968, |
| "num_tokens": 457179.0, |
| "step": 236 |
| }, |
| { |
| "epoch": 0.2988650693568726, |
| "grad_norm": 3.400317430496216, |
| "learning_rate": 7.678391959798995e-06, |
| "loss": 1.5702, |
| "mean_token_accuracy": 0.5746136009693146, |
| "num_tokens": 459171.0, |
| "step": 237 |
| }, |
| { |
| "epoch": 0.30012610340479196, |
| "grad_norm": 3.1317386627197266, |
| "learning_rate": 7.668341708542714e-06, |
| "loss": 1.4624, |
| "mean_token_accuracy": 0.599567323923111, |
| "num_tokens": 461065.0, |
| "step": 238 |
| }, |
| { |
| "epoch": 0.30138713745271123, |
| "grad_norm": 3.305025815963745, |
| "learning_rate": 7.658291457286433e-06, |
| "loss": 1.5403, |
| "mean_token_accuracy": 0.5903847515583038, |
| "num_tokens": 463055.0, |
| "step": 239 |
| }, |
| { |
| "epoch": 0.3026481715006305, |
| "grad_norm": 3.4997472763061523, |
| "learning_rate": 7.64824120603015e-06, |
| "loss": 1.5039, |
| "mean_token_accuracy": 0.5802099704742432, |
| "num_tokens": 464970.0, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.30390920554854983, |
| "grad_norm": 3.480299711227417, |
| "learning_rate": 7.63819095477387e-06, |
| "loss": 1.5373, |
| "mean_token_accuracy": 0.5994563102722168, |
| "num_tokens": 466656.0, |
| "step": 241 |
| }, |
| { |
| "epoch": 0.3051702395964691, |
| "grad_norm": 3.341118335723877, |
| "learning_rate": 7.628140703517588e-06, |
| "loss": 1.5392, |
| "mean_token_accuracy": 0.6160714328289032, |
| "num_tokens": 468715.0, |
| "step": 242 |
| }, |
| { |
| "epoch": 0.3064312736443884, |
| "grad_norm": 3.537838935852051, |
| "learning_rate": 7.618090452261308e-06, |
| "loss": 1.622, |
| "mean_token_accuracy": 0.5691687762737274, |
| "num_tokens": 470568.0, |
| "step": 243 |
| }, |
| { |
| "epoch": 0.3076923076923077, |
| "grad_norm": 3.255831718444824, |
| "learning_rate": 7.608040201005026e-06, |
| "loss": 1.4539, |
| "mean_token_accuracy": 0.5966324210166931, |
| "num_tokens": 472552.0, |
| "step": 244 |
| }, |
| { |
| "epoch": 0.308953341740227, |
| "grad_norm": 3.5343971252441406, |
| "learning_rate": 7.597989949748744e-06, |
| "loss": 1.547, |
| "mean_token_accuracy": 0.560786098241806, |
| "num_tokens": 474516.0, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.31021437578814626, |
| "grad_norm": 3.706355333328247, |
| "learning_rate": 7.587939698492463e-06, |
| "loss": 1.6709, |
| "mean_token_accuracy": 0.5740863680839539, |
| "num_tokens": 476281.0, |
| "step": 246 |
| }, |
| { |
| "epoch": 0.3114754098360656, |
| "grad_norm": 3.2384960651397705, |
| "learning_rate": 7.577889447236182e-06, |
| "loss": 1.3929, |
| "mean_token_accuracy": 0.6230832040309906, |
| "num_tokens": 478264.0, |
| "step": 247 |
| }, |
| { |
| "epoch": 0.31273644388398486, |
| "grad_norm": 3.2530055046081543, |
| "learning_rate": 7.5678391959799e-06, |
| "loss": 1.5825, |
| "mean_token_accuracy": 0.568926066160202, |
| "num_tokens": 480187.0, |
| "step": 248 |
| }, |
| { |
| "epoch": 0.31399747793190413, |
| "grad_norm": 3.1975150108337402, |
| "learning_rate": 7.557788944723619e-06, |
| "loss": 1.5019, |
| "mean_token_accuracy": 0.6005967259407043, |
| "num_tokens": 482183.0, |
| "step": 249 |
| }, |
| { |
| "epoch": 0.31525851197982346, |
| "grad_norm": 3.5112428665161133, |
| "learning_rate": 7.547738693467337e-06, |
| "loss": 1.5426, |
| "mean_token_accuracy": 0.582888126373291, |
| "num_tokens": 484091.0, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.31651954602774274, |
| "grad_norm": 3.1252670288085938, |
| "learning_rate": 7.537688442211056e-06, |
| "loss": 1.5386, |
| "mean_token_accuracy": 0.5831706821918488, |
| "num_tokens": 486205.0, |
| "step": 251 |
| }, |
| { |
| "epoch": 0.31778058007566207, |
| "grad_norm": 3.2698404788970947, |
| "learning_rate": 7.527638190954774e-06, |
| "loss": 1.5461, |
| "mean_token_accuracy": 0.5842161774635315, |
| "num_tokens": 488201.0, |
| "step": 252 |
| }, |
| { |
| "epoch": 0.31904161412358134, |
| "grad_norm": 3.515662670135498, |
| "learning_rate": 7.517587939698493e-06, |
| "loss": 1.4948, |
| "mean_token_accuracy": 0.6040887832641602, |
| "num_tokens": 490232.0, |
| "step": 253 |
| }, |
| { |
| "epoch": 0.3203026481715006, |
| "grad_norm": 3.363635301589966, |
| "learning_rate": 7.507537688442211e-06, |
| "loss": 1.5889, |
| "mean_token_accuracy": 0.5748326480388641, |
| "num_tokens": 492202.0, |
| "step": 254 |
| }, |
| { |
| "epoch": 0.32156368221941994, |
| "grad_norm": 3.3681282997131348, |
| "learning_rate": 7.49748743718593e-06, |
| "loss": 1.4903, |
| "mean_token_accuracy": 0.5962914228439331, |
| "num_tokens": 494155.0, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.3228247162673392, |
| "grad_norm": 3.3991456031799316, |
| "learning_rate": 7.487437185929649e-06, |
| "loss": 1.4905, |
| "mean_token_accuracy": 0.5902964472770691, |
| "num_tokens": 496044.0, |
| "step": 256 |
| }, |
| { |
| "epoch": 0.3240857503152585, |
| "grad_norm": 3.4034206867218018, |
| "learning_rate": 7.4773869346733675e-06, |
| "loss": 1.5376, |
| "mean_token_accuracy": 0.5930163264274597, |
| "num_tokens": 497847.0, |
| "step": 257 |
| }, |
| { |
| "epoch": 0.3253467843631778, |
| "grad_norm": 3.560014486312866, |
| "learning_rate": 7.467336683417086e-06, |
| "loss": 1.5081, |
| "mean_token_accuracy": 0.5968503654003143, |
| "num_tokens": 499693.0, |
| "step": 258 |
| }, |
| { |
| "epoch": 0.3266078184110971, |
| "grad_norm": 3.226555585861206, |
| "learning_rate": 7.4572864321608055e-06, |
| "loss": 1.3905, |
| "mean_token_accuracy": 0.6348022222518921, |
| "num_tokens": 501657.0, |
| "step": 259 |
| }, |
| { |
| "epoch": 0.32786885245901637, |
| "grad_norm": 3.1267666816711426, |
| "learning_rate": 7.447236180904524e-06, |
| "loss": 1.4394, |
| "mean_token_accuracy": 0.6076530516147614, |
| "num_tokens": 503642.0, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.3291298865069357, |
| "grad_norm": 3.6100828647613525, |
| "learning_rate": 7.437185929648242e-06, |
| "loss": 1.5895, |
| "mean_token_accuracy": 0.5834925472736359, |
| "num_tokens": 505453.0, |
| "step": 261 |
| }, |
| { |
| "epoch": 0.33039092055485497, |
| "grad_norm": 3.512857675552368, |
| "learning_rate": 7.42713567839196e-06, |
| "loss": 1.4701, |
| "mean_token_accuracy": 0.576601505279541, |
| "num_tokens": 507481.0, |
| "step": 262 |
| }, |
| { |
| "epoch": 0.3316519546027743, |
| "grad_norm": 3.622948408126831, |
| "learning_rate": 7.417085427135679e-06, |
| "loss": 1.6335, |
| "mean_token_accuracy": 0.5916898250579834, |
| "num_tokens": 509453.0, |
| "step": 263 |
| }, |
| { |
| "epoch": 0.3329129886506936, |
| "grad_norm": 3.31835675239563, |
| "learning_rate": 7.407035175879398e-06, |
| "loss": 1.5441, |
| "mean_token_accuracy": 0.5772275924682617, |
| "num_tokens": 511416.0, |
| "step": 264 |
| }, |
| { |
| "epoch": 0.33417402269861285, |
| "grad_norm": 3.157770872116089, |
| "learning_rate": 7.396984924623116e-06, |
| "loss": 1.5197, |
| "mean_token_accuracy": 0.5890756845474243, |
| "num_tokens": 513595.0, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.3354350567465322, |
| "grad_norm": 3.92372727394104, |
| "learning_rate": 7.386934673366835e-06, |
| "loss": 1.629, |
| "mean_token_accuracy": 0.5840604603290558, |
| "num_tokens": 515409.0, |
| "step": 266 |
| }, |
| { |
| "epoch": 0.33669609079445145, |
| "grad_norm": 3.6059534549713135, |
| "learning_rate": 7.376884422110553e-06, |
| "loss": 1.5641, |
| "mean_token_accuracy": 0.5883042216300964, |
| "num_tokens": 517277.0, |
| "step": 267 |
| }, |
| { |
| "epoch": 0.3379571248423707, |
| "grad_norm": 3.586806535720825, |
| "learning_rate": 7.366834170854272e-06, |
| "loss": 1.5702, |
| "mean_token_accuracy": 0.5803182721138, |
| "num_tokens": 519188.0, |
| "step": 268 |
| }, |
| { |
| "epoch": 0.33921815889029006, |
| "grad_norm": 3.5984644889831543, |
| "learning_rate": 7.35678391959799e-06, |
| "loss": 1.473, |
| "mean_token_accuracy": 0.5921387076377869, |
| "num_tokens": 520932.0, |
| "step": 269 |
| }, |
| { |
| "epoch": 0.34047919293820933, |
| "grad_norm": 3.5097007751464844, |
| "learning_rate": 7.346733668341709e-06, |
| "loss": 1.6462, |
| "mean_token_accuracy": 0.5728191137313843, |
| "num_tokens": 522824.0, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.3417402269861286, |
| "grad_norm": 3.278890609741211, |
| "learning_rate": 7.336683417085427e-06, |
| "loss": 1.4339, |
| "mean_token_accuracy": 0.621574342250824, |
| "num_tokens": 524880.0, |
| "step": 271 |
| }, |
| { |
| "epoch": 0.34300126103404793, |
| "grad_norm": 3.6301679611206055, |
| "learning_rate": 7.326633165829146e-06, |
| "loss": 1.6102, |
| "mean_token_accuracy": 0.582743227481842, |
| "num_tokens": 526729.0, |
| "step": 272 |
| }, |
| { |
| "epoch": 0.3442622950819672, |
| "grad_norm": 3.449260950088501, |
| "learning_rate": 7.316582914572865e-06, |
| "loss": 1.481, |
| "mean_token_accuracy": 0.6034297347068787, |
| "num_tokens": 528717.0, |
| "step": 273 |
| }, |
| { |
| "epoch": 0.3455233291298865, |
| "grad_norm": 3.588651180267334, |
| "learning_rate": 7.3065326633165835e-06, |
| "loss": 1.5565, |
| "mean_token_accuracy": 0.5857305526733398, |
| "num_tokens": 530527.0, |
| "step": 274 |
| }, |
| { |
| "epoch": 0.3467843631778058, |
| "grad_norm": 3.3884775638580322, |
| "learning_rate": 7.296482412060302e-06, |
| "loss": 1.5433, |
| "mean_token_accuracy": 0.5868272185325623, |
| "num_tokens": 532530.0, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.3480453972257251, |
| "grad_norm": 3.4553635120391846, |
| "learning_rate": 7.2864321608040215e-06, |
| "loss": 1.651, |
| "mean_token_accuracy": 0.5584719777107239, |
| "num_tokens": 534420.0, |
| "step": 276 |
| }, |
| { |
| "epoch": 0.3493064312736444, |
| "grad_norm": 3.581951379776001, |
| "learning_rate": 7.27638190954774e-06, |
| "loss": 1.6782, |
| "mean_token_accuracy": 0.5574658215045929, |
| "num_tokens": 536363.0, |
| "step": 277 |
| }, |
| { |
| "epoch": 0.3505674653215637, |
| "grad_norm": 3.633190870285034, |
| "learning_rate": 7.266331658291458e-06, |
| "loss": 1.4971, |
| "mean_token_accuracy": 0.5972879827022552, |
| "num_tokens": 538130.0, |
| "step": 278 |
| }, |
| { |
| "epoch": 0.35182849936948296, |
| "grad_norm": 3.3500475883483887, |
| "learning_rate": 7.256281407035176e-06, |
| "loss": 1.423, |
| "mean_token_accuracy": 0.6157679557800293, |
| "num_tokens": 540189.0, |
| "step": 279 |
| }, |
| { |
| "epoch": 0.3530895334174023, |
| "grad_norm": 3.57883620262146, |
| "learning_rate": 7.246231155778896e-06, |
| "loss": 1.4429, |
| "mean_token_accuracy": 0.6090534329414368, |
| "num_tokens": 541974.0, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.35435056746532156, |
| "grad_norm": 3.4005300998687744, |
| "learning_rate": 7.236180904522614e-06, |
| "loss": 1.4919, |
| "mean_token_accuracy": 0.6023952960968018, |
| "num_tokens": 543907.0, |
| "step": 281 |
| }, |
| { |
| "epoch": 0.35561160151324084, |
| "grad_norm": 3.6614432334899902, |
| "learning_rate": 7.226130653266332e-06, |
| "loss": 1.5978, |
| "mean_token_accuracy": 0.5835244953632355, |
| "num_tokens": 545716.0, |
| "step": 282 |
| }, |
| { |
| "epoch": 0.35687263556116017, |
| "grad_norm": 3.832292318344116, |
| "learning_rate": 7.21608040201005e-06, |
| "loss": 1.6014, |
| "mean_token_accuracy": 0.587654173374176, |
| "num_tokens": 547461.0, |
| "step": 283 |
| }, |
| { |
| "epoch": 0.35813366960907944, |
| "grad_norm": 3.8352723121643066, |
| "learning_rate": 7.206030150753769e-06, |
| "loss": 1.5845, |
| "mean_token_accuracy": 0.5823471248149872, |
| "num_tokens": 549327.0, |
| "step": 284 |
| }, |
| { |
| "epoch": 0.3593947036569987, |
| "grad_norm": 3.360823392868042, |
| "learning_rate": 7.195979899497488e-06, |
| "loss": 1.3829, |
| "mean_token_accuracy": 0.5972756445407867, |
| "num_tokens": 551255.0, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.36065573770491804, |
| "grad_norm": 3.6959569454193115, |
| "learning_rate": 7.185929648241206e-06, |
| "loss": 1.5397, |
| "mean_token_accuracy": 0.5979055464267731, |
| "num_tokens": 553196.0, |
| "step": 286 |
| }, |
| { |
| "epoch": 0.3619167717528373, |
| "grad_norm": 3.6229543685913086, |
| "learning_rate": 7.175879396984925e-06, |
| "loss": 1.6193, |
| "mean_token_accuracy": 0.5753526091575623, |
| "num_tokens": 555122.0, |
| "step": 287 |
| }, |
| { |
| "epoch": 0.36317780580075665, |
| "grad_norm": 3.5911548137664795, |
| "learning_rate": 7.165829145728643e-06, |
| "loss": 1.5747, |
| "mean_token_accuracy": 0.5769863426685333, |
| "num_tokens": 557154.0, |
| "step": 288 |
| }, |
| { |
| "epoch": 0.3644388398486759, |
| "grad_norm": 3.4651150703430176, |
| "learning_rate": 7.155778894472362e-06, |
| "loss": 1.3895, |
| "mean_token_accuracy": 0.6170580685138702, |
| "num_tokens": 558955.0, |
| "step": 289 |
| }, |
| { |
| "epoch": 0.3656998738965952, |
| "grad_norm": 3.70967435836792, |
| "learning_rate": 7.145728643216081e-06, |
| "loss": 1.5437, |
| "mean_token_accuracy": 0.5942074656486511, |
| "num_tokens": 560959.0, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.3669609079445145, |
| "grad_norm": 4.166418075561523, |
| "learning_rate": 7.1356783919597995e-06, |
| "loss": 1.7647, |
| "mean_token_accuracy": 0.5498536229133606, |
| "num_tokens": 562835.0, |
| "step": 291 |
| }, |
| { |
| "epoch": 0.3682219419924338, |
| "grad_norm": 3.428269147872925, |
| "learning_rate": 7.125628140703518e-06, |
| "loss": 1.4921, |
| "mean_token_accuracy": 0.6013461649417877, |
| "num_tokens": 564812.0, |
| "step": 292 |
| }, |
| { |
| "epoch": 0.3694829760403531, |
| "grad_norm": 3.4391069412231445, |
| "learning_rate": 7.1155778894472375e-06, |
| "loss": 1.466, |
| "mean_token_accuracy": 0.6071295142173767, |
| "num_tokens": 566726.0, |
| "step": 293 |
| }, |
| { |
| "epoch": 0.3707440100882724, |
| "grad_norm": 3.696010112762451, |
| "learning_rate": 7.105527638190956e-06, |
| "loss": 1.5173, |
| "mean_token_accuracy": 0.5932539701461792, |
| "num_tokens": 568541.0, |
| "step": 294 |
| }, |
| { |
| "epoch": 0.3720050441361917, |
| "grad_norm": 3.4588735103607178, |
| "learning_rate": 7.095477386934674e-06, |
| "loss": 1.5271, |
| "mean_token_accuracy": 0.5952229201793671, |
| "num_tokens": 570444.0, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.37326607818411095, |
| "grad_norm": 3.6353812217712402, |
| "learning_rate": 7.085427135678392e-06, |
| "loss": 1.4789, |
| "mean_token_accuracy": 0.6043215095996857, |
| "num_tokens": 572305.0, |
| "step": 296 |
| }, |
| { |
| "epoch": 0.3745271122320303, |
| "grad_norm": 3.3734288215637207, |
| "learning_rate": 7.075376884422112e-06, |
| "loss": 1.5768, |
| "mean_token_accuracy": 0.597922682762146, |
| "num_tokens": 574300.0, |
| "step": 297 |
| }, |
| { |
| "epoch": 0.37578814627994955, |
| "grad_norm": 3.565824031829834, |
| "learning_rate": 7.06532663316583e-06, |
| "loss": 1.5451, |
| "mean_token_accuracy": 0.5807141661643982, |
| "num_tokens": 576263.0, |
| "step": 298 |
| }, |
| { |
| "epoch": 0.3770491803278688, |
| "grad_norm": 3.5629653930664062, |
| "learning_rate": 7.055276381909548e-06, |
| "loss": 1.5098, |
| "mean_token_accuracy": 0.5914612412452698, |
| "num_tokens": 578186.0, |
| "step": 299 |
| }, |
| { |
| "epoch": 0.37831021437578816, |
| "grad_norm": 3.560530424118042, |
| "learning_rate": 7.045226130653266e-06, |
| "loss": 1.5232, |
| "mean_token_accuracy": 0.584885448217392, |
| "num_tokens": 580202.0, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.37957124842370743, |
| "grad_norm": 3.871509075164795, |
| "learning_rate": 7.035175879396986e-06, |
| "loss": 1.535, |
| "mean_token_accuracy": 0.6103837490081787, |
| "num_tokens": 582044.0, |
| "step": 301 |
| }, |
| { |
| "epoch": 0.38083228247162676, |
| "grad_norm": 3.4511566162109375, |
| "learning_rate": 7.025125628140704e-06, |
| "loss": 1.5337, |
| "mean_token_accuracy": 0.5950207114219666, |
| "num_tokens": 584068.0, |
| "step": 302 |
| }, |
| { |
| "epoch": 0.38209331651954603, |
| "grad_norm": 3.5363433361053467, |
| "learning_rate": 7.015075376884422e-06, |
| "loss": 1.4386, |
| "mean_token_accuracy": 0.614103227853775, |
| "num_tokens": 586008.0, |
| "step": 303 |
| }, |
| { |
| "epoch": 0.3833543505674653, |
| "grad_norm": 3.7647736072540283, |
| "learning_rate": 7.005025125628141e-06, |
| "loss": 1.4409, |
| "mean_token_accuracy": 0.612841010093689, |
| "num_tokens": 587891.0, |
| "step": 304 |
| }, |
| { |
| "epoch": 0.38461538461538464, |
| "grad_norm": 3.5250868797302246, |
| "learning_rate": 6.99497487437186e-06, |
| "loss": 1.4043, |
| "mean_token_accuracy": 0.6251619756221771, |
| "num_tokens": 589753.0, |
| "step": 305 |
| }, |
| { |
| "epoch": 0.3858764186633039, |
| "grad_norm": 3.9123361110687256, |
| "learning_rate": 6.984924623115578e-06, |
| "loss": 1.6266, |
| "mean_token_accuracy": 0.5853596925735474, |
| "num_tokens": 591699.0, |
| "step": 306 |
| }, |
| { |
| "epoch": 0.3871374527112232, |
| "grad_norm": 3.690964698791504, |
| "learning_rate": 6.974874371859297e-06, |
| "loss": 1.4404, |
| "mean_token_accuracy": 0.6029550135135651, |
| "num_tokens": 593533.0, |
| "step": 307 |
| }, |
| { |
| "epoch": 0.3883984867591425, |
| "grad_norm": 3.27056884765625, |
| "learning_rate": 6.9648241206030155e-06, |
| "loss": 1.4887, |
| "mean_token_accuracy": 0.6173494160175323, |
| "num_tokens": 595691.0, |
| "step": 308 |
| }, |
| { |
| "epoch": 0.3896595208070618, |
| "grad_norm": 3.4807684421539307, |
| "learning_rate": 6.954773869346734e-06, |
| "loss": 1.5053, |
| "mean_token_accuracy": 0.6042143106460571, |
| "num_tokens": 597662.0, |
| "step": 309 |
| }, |
| { |
| "epoch": 0.39092055485498106, |
| "grad_norm": 3.356614112854004, |
| "learning_rate": 6.9447236180904535e-06, |
| "loss": 1.4235, |
| "mean_token_accuracy": 0.6391147971153259, |
| "num_tokens": 599704.0, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.3921815889029004, |
| "grad_norm": 3.2894527912139893, |
| "learning_rate": 6.934673366834172e-06, |
| "loss": 1.4029, |
| "mean_token_accuracy": 0.5988073348999023, |
| "num_tokens": 601747.0, |
| "step": 311 |
| }, |
| { |
| "epoch": 0.39344262295081966, |
| "grad_norm": 3.321415901184082, |
| "learning_rate": 6.92462311557789e-06, |
| "loss": 1.4514, |
| "mean_token_accuracy": 0.6025426089763641, |
| "num_tokens": 603752.0, |
| "step": 312 |
| }, |
| { |
| "epoch": 0.39470365699873894, |
| "grad_norm": 3.693838596343994, |
| "learning_rate": 6.914572864321608e-06, |
| "loss": 1.641, |
| "mean_token_accuracy": 0.593621551990509, |
| "num_tokens": 605636.0, |
| "step": 313 |
| }, |
| { |
| "epoch": 0.39596469104665827, |
| "grad_norm": 3.431027889251709, |
| "learning_rate": 6.904522613065328e-06, |
| "loss": 1.4971, |
| "mean_token_accuracy": 0.6019426584243774, |
| "num_tokens": 607668.0, |
| "step": 314 |
| }, |
| { |
| "epoch": 0.39722572509457754, |
| "grad_norm": 3.324200391769409, |
| "learning_rate": 6.894472361809046e-06, |
| "loss": 1.2605, |
| "mean_token_accuracy": 0.6371206939220428, |
| "num_tokens": 609776.0, |
| "step": 315 |
| }, |
| { |
| "epoch": 0.39848675914249687, |
| "grad_norm": 3.5025103092193604, |
| "learning_rate": 6.884422110552764e-06, |
| "loss": 1.4792, |
| "mean_token_accuracy": 0.6097474098205566, |
| "num_tokens": 611733.0, |
| "step": 316 |
| }, |
| { |
| "epoch": 0.39974779319041615, |
| "grad_norm": 3.4346227645874023, |
| "learning_rate": 6.874371859296482e-06, |
| "loss": 1.4824, |
| "mean_token_accuracy": 0.6024090647697449, |
| "num_tokens": 613792.0, |
| "step": 317 |
| }, |
| { |
| "epoch": 0.4010088272383354, |
| "grad_norm": 3.794248342514038, |
| "learning_rate": 6.864321608040202e-06, |
| "loss": 1.6139, |
| "mean_token_accuracy": 0.5796649754047394, |
| "num_tokens": 615719.0, |
| "step": 318 |
| }, |
| { |
| "epoch": 0.40226986128625475, |
| "grad_norm": 3.5062665939331055, |
| "learning_rate": 6.85427135678392e-06, |
| "loss": 1.3076, |
| "mean_token_accuracy": 0.6257610321044922, |
| "num_tokens": 617457.0, |
| "step": 319 |
| }, |
| { |
| "epoch": 0.403530895334174, |
| "grad_norm": 3.643422842025757, |
| "learning_rate": 6.844221105527638e-06, |
| "loss": 1.5519, |
| "mean_token_accuracy": 0.5946029126644135, |
| "num_tokens": 619400.0, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.4047919293820933, |
| "grad_norm": 3.482797861099243, |
| "learning_rate": 6.834170854271357e-06, |
| "loss": 1.3773, |
| "mean_token_accuracy": 0.6242743134498596, |
| "num_tokens": 621199.0, |
| "step": 321 |
| }, |
| { |
| "epoch": 0.4060529634300126, |
| "grad_norm": 3.4563512802124023, |
| "learning_rate": 6.824120603015076e-06, |
| "loss": 1.4123, |
| "mean_token_accuracy": 0.6065900325775146, |
| "num_tokens": 623253.0, |
| "step": 322 |
| }, |
| { |
| "epoch": 0.4073139974779319, |
| "grad_norm": 3.565988063812256, |
| "learning_rate": 6.814070351758794e-06, |
| "loss": 1.5338, |
| "mean_token_accuracy": 0.5892141759395599, |
| "num_tokens": 625299.0, |
| "step": 323 |
| }, |
| { |
| "epoch": 0.4085750315258512, |
| "grad_norm": 3.317450523376465, |
| "learning_rate": 6.804020100502513e-06, |
| "loss": 1.3202, |
| "mean_token_accuracy": 0.6311619281768799, |
| "num_tokens": 627384.0, |
| "step": 324 |
| }, |
| { |
| "epoch": 0.4098360655737705, |
| "grad_norm": 3.554368019104004, |
| "learning_rate": 6.7939698492462315e-06, |
| "loss": 1.3807, |
| "mean_token_accuracy": 0.6325357258319855, |
| "num_tokens": 629392.0, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.4110970996216898, |
| "grad_norm": 3.8393025398254395, |
| "learning_rate": 6.7839195979899505e-06, |
| "loss": 1.5416, |
| "mean_token_accuracy": 0.5836489200592041, |
| "num_tokens": 631258.0, |
| "step": 326 |
| }, |
| { |
| "epoch": 0.4123581336696091, |
| "grad_norm": 4.803038120269775, |
| "learning_rate": 6.7738693467336695e-06, |
| "loss": 1.6351, |
| "mean_token_accuracy": 0.5894414782524109, |
| "num_tokens": 632944.0, |
| "step": 327 |
| }, |
| { |
| "epoch": 0.4136191677175284, |
| "grad_norm": 3.708953857421875, |
| "learning_rate": 6.763819095477388e-06, |
| "loss": 1.5059, |
| "mean_token_accuracy": 0.5842276513576508, |
| "num_tokens": 634849.0, |
| "step": 328 |
| }, |
| { |
| "epoch": 0.41488020176544765, |
| "grad_norm": 3.8436810970306396, |
| "learning_rate": 6.753768844221106e-06, |
| "loss": 1.591, |
| "mean_token_accuracy": 0.5714927613735199, |
| "num_tokens": 636802.0, |
| "step": 329 |
| }, |
| { |
| "epoch": 0.416141235813367, |
| "grad_norm": 3.6697144508361816, |
| "learning_rate": 6.743718592964824e-06, |
| "loss": 1.4802, |
| "mean_token_accuracy": 0.6012425124645233, |
| "num_tokens": 638751.0, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.41740226986128626, |
| "grad_norm": 3.839346170425415, |
| "learning_rate": 6.733668341708544e-06, |
| "loss": 1.5578, |
| "mean_token_accuracy": 0.5954178273677826, |
| "num_tokens": 640576.0, |
| "step": 331 |
| }, |
| { |
| "epoch": 0.41866330390920553, |
| "grad_norm": 3.3863039016723633, |
| "learning_rate": 6.723618090452262e-06, |
| "loss": 1.4534, |
| "mean_token_accuracy": 0.5870424509048462, |
| "num_tokens": 642696.0, |
| "step": 332 |
| }, |
| { |
| "epoch": 0.41992433795712486, |
| "grad_norm": 3.6930651664733887, |
| "learning_rate": 6.71356783919598e-06, |
| "loss": 1.4956, |
| "mean_token_accuracy": 0.6030255258083344, |
| "num_tokens": 644533.0, |
| "step": 333 |
| }, |
| { |
| "epoch": 0.42118537200504413, |
| "grad_norm": 3.647780656814575, |
| "learning_rate": 6.703517587939698e-06, |
| "loss": 1.304, |
| "mean_token_accuracy": 0.6348400712013245, |
| "num_tokens": 646576.0, |
| "step": 334 |
| }, |
| { |
| "epoch": 0.4224464060529634, |
| "grad_norm": 3.7852511405944824, |
| "learning_rate": 6.693467336683418e-06, |
| "loss": 1.5824, |
| "mean_token_accuracy": 0.5777440667152405, |
| "num_tokens": 648373.0, |
| "step": 335 |
| }, |
| { |
| "epoch": 0.42370744010088274, |
| "grad_norm": 3.745816707611084, |
| "learning_rate": 6.683417085427136e-06, |
| "loss": 1.4897, |
| "mean_token_accuracy": 0.5879658460617065, |
| "num_tokens": 650233.0, |
| "step": 336 |
| }, |
| { |
| "epoch": 0.424968474148802, |
| "grad_norm": 3.7030370235443115, |
| "learning_rate": 6.673366834170854e-06, |
| "loss": 1.6036, |
| "mean_token_accuracy": 0.5585098266601562, |
| "num_tokens": 652112.0, |
| "step": 337 |
| }, |
| { |
| "epoch": 0.4262295081967213, |
| "grad_norm": 3.903932809829712, |
| "learning_rate": 6.663316582914573e-06, |
| "loss": 1.5308, |
| "mean_token_accuracy": 0.5922743678092957, |
| "num_tokens": 653944.0, |
| "step": 338 |
| }, |
| { |
| "epoch": 0.4274905422446406, |
| "grad_norm": 3.4703927040100098, |
| "learning_rate": 6.653266331658292e-06, |
| "loss": 1.3799, |
| "mean_token_accuracy": 0.6140010058879852, |
| "num_tokens": 655965.0, |
| "step": 339 |
| }, |
| { |
| "epoch": 0.4287515762925599, |
| "grad_norm": 3.6348063945770264, |
| "learning_rate": 6.64321608040201e-06, |
| "loss": 1.4927, |
| "mean_token_accuracy": 0.6057197153568268, |
| "num_tokens": 657825.0, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.4300126103404792, |
| "grad_norm": 3.5278713703155518, |
| "learning_rate": 6.633165829145729e-06, |
| "loss": 1.5693, |
| "mean_token_accuracy": 0.5865167081356049, |
| "num_tokens": 659916.0, |
| "step": 341 |
| }, |
| { |
| "epoch": 0.4312736443883985, |
| "grad_norm": 3.410468339920044, |
| "learning_rate": 6.6231155778894475e-06, |
| "loss": 1.6004, |
| "mean_token_accuracy": 0.5903503000736237, |
| "num_tokens": 661951.0, |
| "step": 342 |
| }, |
| { |
| "epoch": 0.43253467843631777, |
| "grad_norm": 3.543788194656372, |
| "learning_rate": 6.6130653266331665e-06, |
| "loss": 1.5349, |
| "mean_token_accuracy": 0.5815105140209198, |
| "num_tokens": 664084.0, |
| "step": 343 |
| }, |
| { |
| "epoch": 0.4337957124842371, |
| "grad_norm": 3.322620391845703, |
| "learning_rate": 6.6030150753768855e-06, |
| "loss": 1.3467, |
| "mean_token_accuracy": 0.6259259283542633, |
| "num_tokens": 666083.0, |
| "step": 344 |
| }, |
| { |
| "epoch": 0.43505674653215637, |
| "grad_norm": 3.5650386810302734, |
| "learning_rate": 6.592964824120604e-06, |
| "loss": 1.4744, |
| "mean_token_accuracy": 0.5977911651134491, |
| "num_tokens": 668111.0, |
| "step": 345 |
| }, |
| { |
| "epoch": 0.43631778058007564, |
| "grad_norm": 3.8183364868164062, |
| "learning_rate": 6.582914572864322e-06, |
| "loss": 1.4991, |
| "mean_token_accuracy": 0.6056190133094788, |
| "num_tokens": 670019.0, |
| "step": 346 |
| }, |
| { |
| "epoch": 0.43757881462799497, |
| "grad_norm": 3.7838871479034424, |
| "learning_rate": 6.572864321608042e-06, |
| "loss": 1.5455, |
| "mean_token_accuracy": 0.6015400588512421, |
| "num_tokens": 671942.0, |
| "step": 347 |
| }, |
| { |
| "epoch": 0.43883984867591425, |
| "grad_norm": 3.7491555213928223, |
| "learning_rate": 6.56281407035176e-06, |
| "loss": 1.4943, |
| "mean_token_accuracy": 0.5917006731033325, |
| "num_tokens": 673892.0, |
| "step": 348 |
| }, |
| { |
| "epoch": 0.4401008827238335, |
| "grad_norm": 3.5047571659088135, |
| "learning_rate": 6.552763819095478e-06, |
| "loss": 1.4276, |
| "mean_token_accuracy": 0.6164177656173706, |
| "num_tokens": 675989.0, |
| "step": 349 |
| }, |
| { |
| "epoch": 0.44136191677175285, |
| "grad_norm": 3.5856776237487793, |
| "learning_rate": 6.542713567839196e-06, |
| "loss": 1.5142, |
| "mean_token_accuracy": 0.6096100211143494, |
| "num_tokens": 677846.0, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.4426229508196721, |
| "grad_norm": 3.9831364154815674, |
| "learning_rate": 6.532663316582916e-06, |
| "loss": 1.4138, |
| "mean_token_accuracy": 0.6201036274433136, |
| "num_tokens": 679857.0, |
| "step": 351 |
| }, |
| { |
| "epoch": 0.44388398486759145, |
| "grad_norm": 3.3696045875549316, |
| "learning_rate": 6.522613065326634e-06, |
| "loss": 1.4871, |
| "mean_token_accuracy": 0.5868003368377686, |
| "num_tokens": 681938.0, |
| "step": 352 |
| }, |
| { |
| "epoch": 0.4451450189155107, |
| "grad_norm": 3.821829319000244, |
| "learning_rate": 6.512562814070352e-06, |
| "loss": 1.6191, |
| "mean_token_accuracy": 0.5949346721172333, |
| "num_tokens": 683945.0, |
| "step": 353 |
| }, |
| { |
| "epoch": 0.44640605296343, |
| "grad_norm": 4.1476149559021, |
| "learning_rate": 6.50251256281407e-06, |
| "loss": 1.6671, |
| "mean_token_accuracy": 0.58425173163414, |
| "num_tokens": 685857.0, |
| "step": 354 |
| }, |
| { |
| "epoch": 0.44766708701134933, |
| "grad_norm": 3.5411603450775146, |
| "learning_rate": 6.492462311557789e-06, |
| "loss": 1.4401, |
| "mean_token_accuracy": 0.6158699989318848, |
| "num_tokens": 687900.0, |
| "step": 355 |
| }, |
| { |
| "epoch": 0.4489281210592686, |
| "grad_norm": 3.8513166904449463, |
| "learning_rate": 6.482412060301508e-06, |
| "loss": 1.4646, |
| "mean_token_accuracy": 0.6156655848026276, |
| "num_tokens": 689828.0, |
| "step": 356 |
| }, |
| { |
| "epoch": 0.4501891551071879, |
| "grad_norm": 3.3844692707061768, |
| "learning_rate": 6.472361809045226e-06, |
| "loss": 1.4562, |
| "mean_token_accuracy": 0.5778538584709167, |
| "num_tokens": 691883.0, |
| "step": 357 |
| }, |
| { |
| "epoch": 0.4514501891551072, |
| "grad_norm": 3.508922815322876, |
| "learning_rate": 6.462311557788945e-06, |
| "loss": 1.4385, |
| "mean_token_accuracy": 0.5973396003246307, |
| "num_tokens": 694006.0, |
| "step": 358 |
| }, |
| { |
| "epoch": 0.4527112232030265, |
| "grad_norm": 3.9150846004486084, |
| "learning_rate": 6.4522613065326635e-06, |
| "loss": 1.508, |
| "mean_token_accuracy": 0.6005319356918335, |
| "num_tokens": 695920.0, |
| "step": 359 |
| }, |
| { |
| "epoch": 0.45397225725094575, |
| "grad_norm": 4.307052135467529, |
| "learning_rate": 6.4422110552763825e-06, |
| "loss": 1.4884, |
| "mean_token_accuracy": 0.6120457649230957, |
| "num_tokens": 697867.0, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.4552332912988651, |
| "grad_norm": 3.687908172607422, |
| "learning_rate": 6.4321608040201015e-06, |
| "loss": 1.4761, |
| "mean_token_accuracy": 0.5905785262584686, |
| "num_tokens": 699743.0, |
| "step": 361 |
| }, |
| { |
| "epoch": 0.45649432534678436, |
| "grad_norm": 3.474442720413208, |
| "learning_rate": 6.42211055276382e-06, |
| "loss": 1.4165, |
| "mean_token_accuracy": 0.6130950152873993, |
| "num_tokens": 701729.0, |
| "step": 362 |
| }, |
| { |
| "epoch": 0.45775535939470363, |
| "grad_norm": 4.1334452629089355, |
| "learning_rate": 6.412060301507538e-06, |
| "loss": 1.5196, |
| "mean_token_accuracy": 0.5886242687702179, |
| "num_tokens": 703552.0, |
| "step": 363 |
| }, |
| { |
| "epoch": 0.45901639344262296, |
| "grad_norm": 3.5810012817382812, |
| "learning_rate": 6.402010050251258e-06, |
| "loss": 1.5103, |
| "mean_token_accuracy": 0.5963969528675079, |
| "num_tokens": 705585.0, |
| "step": 364 |
| }, |
| { |
| "epoch": 0.46027742749054223, |
| "grad_norm": 4.0280256271362305, |
| "learning_rate": 6.391959798994976e-06, |
| "loss": 1.6474, |
| "mean_token_accuracy": 0.5783868432044983, |
| "num_tokens": 707375.0, |
| "step": 365 |
| }, |
| { |
| "epoch": 0.46153846153846156, |
| "grad_norm": 3.934354305267334, |
| "learning_rate": 6.381909547738694e-06, |
| "loss": 1.6371, |
| "mean_token_accuracy": 0.5782681107521057, |
| "num_tokens": 709198.0, |
| "step": 366 |
| }, |
| { |
| "epoch": 0.46279949558638084, |
| "grad_norm": 3.8574609756469727, |
| "learning_rate": 6.371859296482412e-06, |
| "loss": 1.4247, |
| "mean_token_accuracy": 0.605307936668396, |
| "num_tokens": 711260.0, |
| "step": 367 |
| }, |
| { |
| "epoch": 0.4640605296343001, |
| "grad_norm": 4.1762518882751465, |
| "learning_rate": 6.361809045226132e-06, |
| "loss": 1.5521, |
| "mean_token_accuracy": 0.5752246379852295, |
| "num_tokens": 712956.0, |
| "step": 368 |
| }, |
| { |
| "epoch": 0.46532156368221944, |
| "grad_norm": 3.9887688159942627, |
| "learning_rate": 6.35175879396985e-06, |
| "loss": 1.4642, |
| "mean_token_accuracy": 0.612546294927597, |
| "num_tokens": 714675.0, |
| "step": 369 |
| }, |
| { |
| "epoch": 0.4665825977301387, |
| "grad_norm": 3.601942777633667, |
| "learning_rate": 6.341708542713568e-06, |
| "loss": 1.387, |
| "mean_token_accuracy": 0.6236040592193604, |
| "num_tokens": 716725.0, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.467843631778058, |
| "grad_norm": 3.91477108001709, |
| "learning_rate": 6.331658291457286e-06, |
| "loss": 1.4851, |
| "mean_token_accuracy": 0.6054001152515411, |
| "num_tokens": 718449.0, |
| "step": 371 |
| }, |
| { |
| "epoch": 0.4691046658259773, |
| "grad_norm": 3.6185572147369385, |
| "learning_rate": 6.321608040201006e-06, |
| "loss": 1.3861, |
| "mean_token_accuracy": 0.6127656102180481, |
| "num_tokens": 720577.0, |
| "step": 372 |
| }, |
| { |
| "epoch": 0.4703656998738966, |
| "grad_norm": 3.6203348636627197, |
| "learning_rate": 6.311557788944724e-06, |
| "loss": 1.4493, |
| "mean_token_accuracy": 0.6147701144218445, |
| "num_tokens": 722444.0, |
| "step": 373 |
| }, |
| { |
| "epoch": 0.47162673392181587, |
| "grad_norm": 3.9971113204956055, |
| "learning_rate": 6.301507537688442e-06, |
| "loss": 1.5187, |
| "mean_token_accuracy": 0.5887904763221741, |
| "num_tokens": 724283.0, |
| "step": 374 |
| }, |
| { |
| "epoch": 0.4728877679697352, |
| "grad_norm": 3.7521986961364746, |
| "learning_rate": 6.291457286432161e-06, |
| "loss": 1.4663, |
| "mean_token_accuracy": 0.6025364696979523, |
| "num_tokens": 726415.0, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.47414880201765447, |
| "grad_norm": 3.8074052333831787, |
| "learning_rate": 6.28140703517588e-06, |
| "loss": 1.5155, |
| "mean_token_accuracy": 0.5930048227310181, |
| "num_tokens": 728281.0, |
| "step": 376 |
| }, |
| { |
| "epoch": 0.47540983606557374, |
| "grad_norm": 4.051740646362305, |
| "learning_rate": 6.2713567839195985e-06, |
| "loss": 1.6541, |
| "mean_token_accuracy": 0.5947281718254089, |
| "num_tokens": 730266.0, |
| "step": 377 |
| }, |
| { |
| "epoch": 0.4766708701134931, |
| "grad_norm": 3.7151358127593994, |
| "learning_rate": 6.2613065326633175e-06, |
| "loss": 1.3374, |
| "mean_token_accuracy": 0.612007737159729, |
| "num_tokens": 732202.0, |
| "step": 378 |
| }, |
| { |
| "epoch": 0.47793190416141235, |
| "grad_norm": 4.122408390045166, |
| "learning_rate": 6.251256281407036e-06, |
| "loss": 1.4805, |
| "mean_token_accuracy": 0.5938221216201782, |
| "num_tokens": 734091.0, |
| "step": 379 |
| }, |
| { |
| "epoch": 0.4791929382093317, |
| "grad_norm": 3.908778667449951, |
| "learning_rate": 6.241206030150754e-06, |
| "loss": 1.5331, |
| "mean_token_accuracy": 0.5997506678104401, |
| "num_tokens": 736074.0, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.48045397225725095, |
| "grad_norm": 4.155081748962402, |
| "learning_rate": 6.231155778894474e-06, |
| "loss": 1.5731, |
| "mean_token_accuracy": 0.5773967504501343, |
| "num_tokens": 737974.0, |
| "step": 381 |
| }, |
| { |
| "epoch": 0.4817150063051702, |
| "grad_norm": 3.9985005855560303, |
| "learning_rate": 6.221105527638192e-06, |
| "loss": 1.4398, |
| "mean_token_accuracy": 0.6126863658428192, |
| "num_tokens": 739838.0, |
| "step": 382 |
| }, |
| { |
| "epoch": 0.48297604035308955, |
| "grad_norm": 3.937734842300415, |
| "learning_rate": 6.21105527638191e-06, |
| "loss": 1.525, |
| "mean_token_accuracy": 0.6130150854587555, |
| "num_tokens": 741692.0, |
| "step": 383 |
| }, |
| { |
| "epoch": 0.4842370744010088, |
| "grad_norm": 3.8296337127685547, |
| "learning_rate": 6.201005025125628e-06, |
| "loss": 1.4805, |
| "mean_token_accuracy": 0.6192940175533295, |
| "num_tokens": 743636.0, |
| "step": 384 |
| }, |
| { |
| "epoch": 0.4854981084489281, |
| "grad_norm": 3.6199262142181396, |
| "learning_rate": 6.190954773869348e-06, |
| "loss": 1.3644, |
| "mean_token_accuracy": 0.6284566223621368, |
| "num_tokens": 745627.0, |
| "step": 385 |
| }, |
| { |
| "epoch": 0.48675914249684743, |
| "grad_norm": 3.931962490081787, |
| "learning_rate": 6.180904522613066e-06, |
| "loss": 1.6314, |
| "mean_token_accuracy": 0.575654000043869, |
| "num_tokens": 747592.0, |
| "step": 386 |
| }, |
| { |
| "epoch": 0.4880201765447667, |
| "grad_norm": 3.6779048442840576, |
| "learning_rate": 6.170854271356784e-06, |
| "loss": 1.4776, |
| "mean_token_accuracy": 0.594518393278122, |
| "num_tokens": 749615.0, |
| "step": 387 |
| }, |
| { |
| "epoch": 0.489281210592686, |
| "grad_norm": 3.832871198654175, |
| "learning_rate": 6.160804020100502e-06, |
| "loss": 1.4508, |
| "mean_token_accuracy": 0.6090913116931915, |
| "num_tokens": 751515.0, |
| "step": 388 |
| }, |
| { |
| "epoch": 0.4905422446406053, |
| "grad_norm": 3.9489598274230957, |
| "learning_rate": 6.150753768844222e-06, |
| "loss": 1.5567, |
| "mean_token_accuracy": 0.5768946707248688, |
| "num_tokens": 753381.0, |
| "step": 389 |
| }, |
| { |
| "epoch": 0.4918032786885246, |
| "grad_norm": 3.927081823348999, |
| "learning_rate": 6.14070351758794e-06, |
| "loss": 1.5296, |
| "mean_token_accuracy": 0.5951372683048248, |
| "num_tokens": 755255.0, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.4930643127364439, |
| "grad_norm": 3.9887728691101074, |
| "learning_rate": 6.130653266331658e-06, |
| "loss": 1.5766, |
| "mean_token_accuracy": 0.587302178144455, |
| "num_tokens": 757058.0, |
| "step": 391 |
| }, |
| { |
| "epoch": 0.4943253467843632, |
| "grad_norm": 3.8660635948181152, |
| "learning_rate": 6.120603015075377e-06, |
| "loss": 1.3367, |
| "mean_token_accuracy": 0.6324070990085602, |
| "num_tokens": 758996.0, |
| "step": 392 |
| }, |
| { |
| "epoch": 0.49558638083228246, |
| "grad_norm": 4.087164878845215, |
| "learning_rate": 6.110552763819096e-06, |
| "loss": 1.5956, |
| "mean_token_accuracy": 0.5824276208877563, |
| "num_tokens": 760934.0, |
| "step": 393 |
| }, |
| { |
| "epoch": 0.4968474148802018, |
| "grad_norm": 3.9089858531951904, |
| "learning_rate": 6.1005025125628145e-06, |
| "loss": 1.406, |
| "mean_token_accuracy": 0.6238544881343842, |
| "num_tokens": 762847.0, |
| "step": 394 |
| }, |
| { |
| "epoch": 0.49810844892812106, |
| "grad_norm": 3.826852560043335, |
| "learning_rate": 6.0904522613065335e-06, |
| "loss": 1.3496, |
| "mean_token_accuracy": 0.621149480342865, |
| "num_tokens": 764885.0, |
| "step": 395 |
| }, |
| { |
| "epoch": 0.49936948297604034, |
| "grad_norm": 3.906343936920166, |
| "learning_rate": 6.080402010050252e-06, |
| "loss": 1.5116, |
| "mean_token_accuracy": 0.5996163189411163, |
| "num_tokens": 766879.0, |
| "step": 396 |
| }, |
| { |
| "epoch": 0.5006305170239597, |
| "grad_norm": 3.915363073348999, |
| "learning_rate": 6.070351758793971e-06, |
| "loss": 1.4962, |
| "mean_token_accuracy": 0.5924739837646484, |
| "num_tokens": 768855.0, |
| "step": 397 |
| }, |
| { |
| "epoch": 0.501891551071879, |
| "grad_norm": 3.8229563236236572, |
| "learning_rate": 6.06030150753769e-06, |
| "loss": 1.5012, |
| "mean_token_accuracy": 0.5963457524776459, |
| "num_tokens": 770683.0, |
| "step": 398 |
| }, |
| { |
| "epoch": 0.5031525851197982, |
| "grad_norm": 3.8112332820892334, |
| "learning_rate": 6.050251256281408e-06, |
| "loss": 1.4278, |
| "mean_token_accuracy": 0.6047469675540924, |
| "num_tokens": 772607.0, |
| "step": 399 |
| }, |
| { |
| "epoch": 0.5044136191677175, |
| "grad_norm": 3.7356104850769043, |
| "learning_rate": 6.040201005025126e-06, |
| "loss": 1.4171, |
| "mean_token_accuracy": 0.6060886383056641, |
| "num_tokens": 774528.0, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.5056746532156369, |
| "grad_norm": 3.9361140727996826, |
| "learning_rate": 6.030150753768844e-06, |
| "loss": 1.5603, |
| "mean_token_accuracy": 0.5814925730228424, |
| "num_tokens": 776337.0, |
| "step": 401 |
| }, |
| { |
| "epoch": 0.5069356872635561, |
| "grad_norm": 3.743752956390381, |
| "learning_rate": 6.020100502512564e-06, |
| "loss": 1.4307, |
| "mean_token_accuracy": 0.6159599125385284, |
| "num_tokens": 778242.0, |
| "step": 402 |
| }, |
| { |
| "epoch": 0.5081967213114754, |
| "grad_norm": 3.4296321868896484, |
| "learning_rate": 6.010050251256282e-06, |
| "loss": 1.2756, |
| "mean_token_accuracy": 0.6444790065288544, |
| "num_tokens": 780168.0, |
| "step": 403 |
| }, |
| { |
| "epoch": 0.5094577553593947, |
| "grad_norm": 4.4306864738464355, |
| "learning_rate": 6e-06, |
| "loss": 1.6425, |
| "mean_token_accuracy": 0.5818255543708801, |
| "num_tokens": 781990.0, |
| "step": 404 |
| }, |
| { |
| "epoch": 0.510718789407314, |
| "grad_norm": 4.045053482055664, |
| "learning_rate": 5.989949748743718e-06, |
| "loss": 1.5048, |
| "mean_token_accuracy": 0.5999021828174591, |
| "num_tokens": 783882.0, |
| "step": 405 |
| }, |
| { |
| "epoch": 0.5119798234552333, |
| "grad_norm": 3.576313018798828, |
| "learning_rate": 5.979899497487438e-06, |
| "loss": 1.4715, |
| "mean_token_accuracy": 0.5854345858097076, |
| "num_tokens": 785888.0, |
| "step": 406 |
| }, |
| { |
| "epoch": 0.5132408575031526, |
| "grad_norm": 3.9152069091796875, |
| "learning_rate": 5.969849246231156e-06, |
| "loss": 1.421, |
| "mean_token_accuracy": 0.6086308360099792, |
| "num_tokens": 787821.0, |
| "step": 407 |
| }, |
| { |
| "epoch": 0.5145018915510718, |
| "grad_norm": 4.192541599273682, |
| "learning_rate": 5.959798994974874e-06, |
| "loss": 1.5941, |
| "mean_token_accuracy": 0.591251790523529, |
| "num_tokens": 789593.0, |
| "step": 408 |
| }, |
| { |
| "epoch": 0.5157629255989912, |
| "grad_norm": 3.80621337890625, |
| "learning_rate": 5.949748743718593e-06, |
| "loss": 1.5137, |
| "mean_token_accuracy": 0.5962553918361664, |
| "num_tokens": 791559.0, |
| "step": 409 |
| }, |
| { |
| "epoch": 0.5170239596469105, |
| "grad_norm": 3.8430941104888916, |
| "learning_rate": 5.939698492462312e-06, |
| "loss": 1.456, |
| "mean_token_accuracy": 0.6207826733589172, |
| "num_tokens": 793446.0, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.5182849936948297, |
| "grad_norm": 3.751850128173828, |
| "learning_rate": 5.9296482412060305e-06, |
| "loss": 1.4189, |
| "mean_token_accuracy": 0.6290108561515808, |
| "num_tokens": 795278.0, |
| "step": 411 |
| }, |
| { |
| "epoch": 0.519546027742749, |
| "grad_norm": 4.246517658233643, |
| "learning_rate": 5.9195979899497495e-06, |
| "loss": 1.6446, |
| "mean_token_accuracy": 0.5721382200717926, |
| "num_tokens": 797144.0, |
| "step": 412 |
| }, |
| { |
| "epoch": 0.5208070617906684, |
| "grad_norm": 3.7303225994110107, |
| "learning_rate": 5.909547738693468e-06, |
| "loss": 1.397, |
| "mean_token_accuracy": 0.6230327188968658, |
| "num_tokens": 799007.0, |
| "step": 413 |
| }, |
| { |
| "epoch": 0.5220680958385876, |
| "grad_norm": 3.9755711555480957, |
| "learning_rate": 5.899497487437187e-06, |
| "loss": 1.5544, |
| "mean_token_accuracy": 0.5930447280406952, |
| "num_tokens": 800807.0, |
| "step": 414 |
| }, |
| { |
| "epoch": 0.5233291298865069, |
| "grad_norm": 4.000508785247803, |
| "learning_rate": 5.889447236180905e-06, |
| "loss": 1.6292, |
| "mean_token_accuracy": 0.5693787634372711, |
| "num_tokens": 802783.0, |
| "step": 415 |
| }, |
| { |
| "epoch": 0.5245901639344263, |
| "grad_norm": 4.1713337898254395, |
| "learning_rate": 5.879396984924624e-06, |
| "loss": 1.5307, |
| "mean_token_accuracy": 0.6000028848648071, |
| "num_tokens": 804596.0, |
| "step": 416 |
| }, |
| { |
| "epoch": 0.5258511979823455, |
| "grad_norm": 3.8140196800231934, |
| "learning_rate": 5.869346733668342e-06, |
| "loss": 1.4934, |
| "mean_token_accuracy": 0.6128242611885071, |
| "num_tokens": 806564.0, |
| "step": 417 |
| }, |
| { |
| "epoch": 0.5271122320302648, |
| "grad_norm": 3.724236488342285, |
| "learning_rate": 5.859296482412061e-06, |
| "loss": 1.4355, |
| "mean_token_accuracy": 0.6146958768367767, |
| "num_tokens": 808550.0, |
| "step": 418 |
| }, |
| { |
| "epoch": 0.5283732660781841, |
| "grad_norm": 4.29474401473999, |
| "learning_rate": 5.84924623115578e-06, |
| "loss": 1.5489, |
| "mean_token_accuracy": 0.5955554842948914, |
| "num_tokens": 810335.0, |
| "step": 419 |
| }, |
| { |
| "epoch": 0.5296343001261034, |
| "grad_norm": 3.720149040222168, |
| "learning_rate": 5.839195979899498e-06, |
| "loss": 1.3334, |
| "mean_token_accuracy": 0.6176763474941254, |
| "num_tokens": 812250.0, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.5308953341740227, |
| "grad_norm": 4.0187201499938965, |
| "learning_rate": 5.829145728643216e-06, |
| "loss": 1.5864, |
| "mean_token_accuracy": 0.5855948626995087, |
| "num_tokens": 814160.0, |
| "step": 421 |
| }, |
| { |
| "epoch": 0.532156368221942, |
| "grad_norm": 3.415576219558716, |
| "learning_rate": 5.819095477386936e-06, |
| "loss": 1.3088, |
| "mean_token_accuracy": 0.6266660094261169, |
| "num_tokens": 816237.0, |
| "step": 422 |
| }, |
| { |
| "epoch": 0.5334174022698613, |
| "grad_norm": 3.7157742977142334, |
| "learning_rate": 5.809045226130654e-06, |
| "loss": 1.5874, |
| "mean_token_accuracy": 0.5831565260887146, |
| "num_tokens": 818263.0, |
| "step": 423 |
| }, |
| { |
| "epoch": 0.5346784363177806, |
| "grad_norm": 3.988062620162964, |
| "learning_rate": 5.798994974874372e-06, |
| "loss": 1.4411, |
| "mean_token_accuracy": 0.6083543598651886, |
| "num_tokens": 820136.0, |
| "step": 424 |
| }, |
| { |
| "epoch": 0.5359394703656999, |
| "grad_norm": 3.623262405395508, |
| "learning_rate": 5.78894472361809e-06, |
| "loss": 1.3701, |
| "mean_token_accuracy": 0.6176230311393738, |
| "num_tokens": 822213.0, |
| "step": 425 |
| }, |
| { |
| "epoch": 0.5372005044136192, |
| "grad_norm": 3.895170211791992, |
| "learning_rate": 5.778894472361809e-06, |
| "loss": 1.353, |
| "mean_token_accuracy": 0.6239413321018219, |
| "num_tokens": 824114.0, |
| "step": 426 |
| }, |
| { |
| "epoch": 0.5384615384615384, |
| "grad_norm": 3.889404296875, |
| "learning_rate": 5.768844221105528e-06, |
| "loss": 1.4688, |
| "mean_token_accuracy": 0.6074230074882507, |
| "num_tokens": 826150.0, |
| "step": 427 |
| }, |
| { |
| "epoch": 0.5397225725094578, |
| "grad_norm": 4.306681156158447, |
| "learning_rate": 5.7587939698492465e-06, |
| "loss": 1.5199, |
| "mean_token_accuracy": 0.5849421322345734, |
| "num_tokens": 827971.0, |
| "step": 428 |
| }, |
| { |
| "epoch": 0.5409836065573771, |
| "grad_norm": 4.184123516082764, |
| "learning_rate": 5.7487437185929655e-06, |
| "loss": 1.4457, |
| "mean_token_accuracy": 0.6024906635284424, |
| "num_tokens": 829886.0, |
| "step": 429 |
| }, |
| { |
| "epoch": 0.5422446406052963, |
| "grad_norm": 4.066215515136719, |
| "learning_rate": 5.738693467336684e-06, |
| "loss": 1.5743, |
| "mean_token_accuracy": 0.5810816884040833, |
| "num_tokens": 831780.0, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.5435056746532156, |
| "grad_norm": 3.6609530448913574, |
| "learning_rate": 5.728643216080403e-06, |
| "loss": 1.3719, |
| "mean_token_accuracy": 0.615295022726059, |
| "num_tokens": 833782.0, |
| "step": 431 |
| }, |
| { |
| "epoch": 0.544766708701135, |
| "grad_norm": 3.7818527221679688, |
| "learning_rate": 5.718592964824121e-06, |
| "loss": 1.4128, |
| "mean_token_accuracy": 0.6150719523429871, |
| "num_tokens": 835728.0, |
| "step": 432 |
| }, |
| { |
| "epoch": 0.5460277427490542, |
| "grad_norm": 3.8660855293273926, |
| "learning_rate": 5.70854271356784e-06, |
| "loss": 1.4527, |
| "mean_token_accuracy": 0.6020141839981079, |
| "num_tokens": 837648.0, |
| "step": 433 |
| }, |
| { |
| "epoch": 0.5472887767969735, |
| "grad_norm": 3.8554327487945557, |
| "learning_rate": 5.698492462311558e-06, |
| "loss": 1.3445, |
| "mean_token_accuracy": 0.6199198365211487, |
| "num_tokens": 839518.0, |
| "step": 434 |
| }, |
| { |
| "epoch": 0.5485498108448928, |
| "grad_norm": 4.233033657073975, |
| "learning_rate": 5.688442211055277e-06, |
| "loss": 1.6077, |
| "mean_token_accuracy": 0.5790873765945435, |
| "num_tokens": 841311.0, |
| "step": 435 |
| }, |
| { |
| "epoch": 0.5498108448928121, |
| "grad_norm": 3.7273433208465576, |
| "learning_rate": 5.678391959798996e-06, |
| "loss": 1.3938, |
| "mean_token_accuracy": 0.6058596968650818, |
| "num_tokens": 843396.0, |
| "step": 436 |
| }, |
| { |
| "epoch": 0.5510718789407314, |
| "grad_norm": 4.387331008911133, |
| "learning_rate": 5.668341708542714e-06, |
| "loss": 1.5958, |
| "mean_token_accuracy": 0.5863657295703888, |
| "num_tokens": 845309.0, |
| "step": 437 |
| }, |
| { |
| "epoch": 0.5523329129886507, |
| "grad_norm": 3.9680373668670654, |
| "learning_rate": 5.658291457286432e-06, |
| "loss": 1.4952, |
| "mean_token_accuracy": 0.6114929616451263, |
| "num_tokens": 847210.0, |
| "step": 438 |
| }, |
| { |
| "epoch": 0.5535939470365699, |
| "grad_norm": 3.9168810844421387, |
| "learning_rate": 5.648241206030152e-06, |
| "loss": 1.4169, |
| "mean_token_accuracy": 0.6114987432956696, |
| "num_tokens": 849213.0, |
| "step": 439 |
| }, |
| { |
| "epoch": 0.5548549810844893, |
| "grad_norm": 4.25286340713501, |
| "learning_rate": 5.63819095477387e-06, |
| "loss": 1.6493, |
| "mean_token_accuracy": 0.570509523153305, |
| "num_tokens": 851092.0, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.5561160151324086, |
| "grad_norm": 3.875514507293701, |
| "learning_rate": 5.628140703517588e-06, |
| "loss": 1.4016, |
| "mean_token_accuracy": 0.6159034967422485, |
| "num_tokens": 852991.0, |
| "step": 441 |
| }, |
| { |
| "epoch": 0.5573770491803278, |
| "grad_norm": 3.8609631061553955, |
| "learning_rate": 5.618090452261306e-06, |
| "loss": 1.3906, |
| "mean_token_accuracy": 0.6153773963451385, |
| "num_tokens": 855038.0, |
| "step": 442 |
| }, |
| { |
| "epoch": 0.5586380832282472, |
| "grad_norm": 3.846491575241089, |
| "learning_rate": 5.608040201005026e-06, |
| "loss": 1.4185, |
| "mean_token_accuracy": 0.6202840507030487, |
| "num_tokens": 857076.0, |
| "step": 443 |
| }, |
| { |
| "epoch": 0.5598991172761665, |
| "grad_norm": 4.081157207489014, |
| "learning_rate": 5.597989949748744e-06, |
| "loss": 1.5429, |
| "mean_token_accuracy": 0.5890442430973053, |
| "num_tokens": 859076.0, |
| "step": 444 |
| }, |
| { |
| "epoch": 0.5611601513240857, |
| "grad_norm": 3.8386566638946533, |
| "learning_rate": 5.5879396984924625e-06, |
| "loss": 1.4287, |
| "mean_token_accuracy": 0.6156394481658936, |
| "num_tokens": 861047.0, |
| "step": 445 |
| }, |
| { |
| "epoch": 0.562421185372005, |
| "grad_norm": 3.7738113403320312, |
| "learning_rate": 5.577889447236181e-06, |
| "loss": 1.4732, |
| "mean_token_accuracy": 0.5908475816249847, |
| "num_tokens": 863083.0, |
| "step": 446 |
| }, |
| { |
| "epoch": 0.5636822194199244, |
| "grad_norm": 3.8559048175811768, |
| "learning_rate": 5.5678391959799e-06, |
| "loss": 1.3873, |
| "mean_token_accuracy": 0.6156317889690399, |
| "num_tokens": 865068.0, |
| "step": 447 |
| }, |
| { |
| "epoch": 0.5649432534678437, |
| "grad_norm": 3.549217939376831, |
| "learning_rate": 5.557788944723619e-06, |
| "loss": 1.3209, |
| "mean_token_accuracy": 0.6351846158504486, |
| "num_tokens": 867085.0, |
| "step": 448 |
| }, |
| { |
| "epoch": 0.5662042875157629, |
| "grad_norm": 4.134774208068848, |
| "learning_rate": 5.547738693467337e-06, |
| "loss": 1.6058, |
| "mean_token_accuracy": 0.5775579214096069, |
| "num_tokens": 869059.0, |
| "step": 449 |
| }, |
| { |
| "epoch": 0.5674653215636822, |
| "grad_norm": 3.7273738384246826, |
| "learning_rate": 5.537688442211056e-06, |
| "loss": 1.4557, |
| "mean_token_accuracy": 0.6038585305213928, |
| "num_tokens": 871051.0, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.5687263556116016, |
| "grad_norm": 4.377529621124268, |
| "learning_rate": 5.527638190954774e-06, |
| "loss": 1.4937, |
| "mean_token_accuracy": 0.5913034677505493, |
| "num_tokens": 872900.0, |
| "step": 451 |
| }, |
| { |
| "epoch": 0.5699873896595208, |
| "grad_norm": 4.095523834228516, |
| "learning_rate": 5.517587939698493e-06, |
| "loss": 1.5148, |
| "mean_token_accuracy": 0.6133293807506561, |
| "num_tokens": 874801.0, |
| "step": 452 |
| }, |
| { |
| "epoch": 0.5712484237074401, |
| "grad_norm": 3.8340799808502197, |
| "learning_rate": 5.507537688442212e-06, |
| "loss": 1.4924, |
| "mean_token_accuracy": 0.5960003435611725, |
| "num_tokens": 876646.0, |
| "step": 453 |
| }, |
| { |
| "epoch": 0.5725094577553594, |
| "grad_norm": 3.5290746688842773, |
| "learning_rate": 5.49748743718593e-06, |
| "loss": 1.326, |
| "mean_token_accuracy": 0.6205747723579407, |
| "num_tokens": 878739.0, |
| "step": 454 |
| }, |
| { |
| "epoch": 0.5737704918032787, |
| "grad_norm": 4.257903099060059, |
| "learning_rate": 5.487437185929648e-06, |
| "loss": 1.5482, |
| "mean_token_accuracy": 0.5878141522407532, |
| "num_tokens": 880465.0, |
| "step": 455 |
| }, |
| { |
| "epoch": 0.575031525851198, |
| "grad_norm": 3.8454947471618652, |
| "learning_rate": 5.477386934673368e-06, |
| "loss": 1.4434, |
| "mean_token_accuracy": 0.6128550171852112, |
| "num_tokens": 882500.0, |
| "step": 456 |
| }, |
| { |
| "epoch": 0.5762925598991173, |
| "grad_norm": 3.810124158859253, |
| "learning_rate": 5.467336683417086e-06, |
| "loss": 1.4584, |
| "mean_token_accuracy": 0.6083512902259827, |
| "num_tokens": 884588.0, |
| "step": 457 |
| }, |
| { |
| "epoch": 0.5775535939470365, |
| "grad_norm": 3.951253652572632, |
| "learning_rate": 5.457286432160804e-06, |
| "loss": 1.3561, |
| "mean_token_accuracy": 0.6184321939945221, |
| "num_tokens": 886527.0, |
| "step": 458 |
| }, |
| { |
| "epoch": 0.5788146279949559, |
| "grad_norm": 4.112410545349121, |
| "learning_rate": 5.447236180904522e-06, |
| "loss": 1.4046, |
| "mean_token_accuracy": 0.6035341024398804, |
| "num_tokens": 888317.0, |
| "step": 459 |
| }, |
| { |
| "epoch": 0.5800756620428752, |
| "grad_norm": 3.8871636390686035, |
| "learning_rate": 5.437185929648242e-06, |
| "loss": 1.4532, |
| "mean_token_accuracy": 0.614162027835846, |
| "num_tokens": 890191.0, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.5813366960907944, |
| "grad_norm": 3.9813950061798096, |
| "learning_rate": 5.42713567839196e-06, |
| "loss": 1.4054, |
| "mean_token_accuracy": 0.613822340965271, |
| "num_tokens": 892069.0, |
| "step": 461 |
| }, |
| { |
| "epoch": 0.5825977301387137, |
| "grad_norm": 3.930206298828125, |
| "learning_rate": 5.4170854271356785e-06, |
| "loss": 1.5206, |
| "mean_token_accuracy": 0.5886333584785461, |
| "num_tokens": 894011.0, |
| "step": 462 |
| }, |
| { |
| "epoch": 0.5838587641866331, |
| "grad_norm": 3.8400161266326904, |
| "learning_rate": 5.407035175879397e-06, |
| "loss": 1.278, |
| "mean_token_accuracy": 0.6264286637306213, |
| "num_tokens": 895826.0, |
| "step": 463 |
| }, |
| { |
| "epoch": 0.5851197982345523, |
| "grad_norm": 4.199733734130859, |
| "learning_rate": 5.3969849246231165e-06, |
| "loss": 1.429, |
| "mean_token_accuracy": 0.612981379032135, |
| "num_tokens": 897788.0, |
| "step": 464 |
| }, |
| { |
| "epoch": 0.5863808322824716, |
| "grad_norm": 4.702413082122803, |
| "learning_rate": 5.386934673366835e-06, |
| "loss": 1.6482, |
| "mean_token_accuracy": 0.5548197329044342, |
| "num_tokens": 899611.0, |
| "step": 465 |
| }, |
| { |
| "epoch": 0.587641866330391, |
| "grad_norm": 4.299721717834473, |
| "learning_rate": 5.376884422110553e-06, |
| "loss": 1.5122, |
| "mean_token_accuracy": 0.591781735420227, |
| "num_tokens": 901499.0, |
| "step": 466 |
| }, |
| { |
| "epoch": 0.5889029003783102, |
| "grad_norm": 4.097691535949707, |
| "learning_rate": 5.366834170854272e-06, |
| "loss": 1.4837, |
| "mean_token_accuracy": 0.5834101438522339, |
| "num_tokens": 903365.0, |
| "step": 467 |
| }, |
| { |
| "epoch": 0.5901639344262295, |
| "grad_norm": 3.9655864238739014, |
| "learning_rate": 5.356783919597991e-06, |
| "loss": 1.3773, |
| "mean_token_accuracy": 0.6133775413036346, |
| "num_tokens": 905349.0, |
| "step": 468 |
| }, |
| { |
| "epoch": 0.5914249684741488, |
| "grad_norm": 3.8645100593566895, |
| "learning_rate": 5.346733668341709e-06, |
| "loss": 1.3445, |
| "mean_token_accuracy": 0.6294296383857727, |
| "num_tokens": 907283.0, |
| "step": 469 |
| }, |
| { |
| "epoch": 0.592686002522068, |
| "grad_norm": 3.720658540725708, |
| "learning_rate": 5.336683417085428e-06, |
| "loss": 1.3897, |
| "mean_token_accuracy": 0.610343724489212, |
| "num_tokens": 909322.0, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.5939470365699874, |
| "grad_norm": 4.123734951019287, |
| "learning_rate": 5.326633165829146e-06, |
| "loss": 1.4428, |
| "mean_token_accuracy": 0.6127735376358032, |
| "num_tokens": 911283.0, |
| "step": 471 |
| }, |
| { |
| "epoch": 0.5952080706179067, |
| "grad_norm": 4.503159999847412, |
| "learning_rate": 5.316582914572864e-06, |
| "loss": 1.5428, |
| "mean_token_accuracy": 0.5835637450218201, |
| "num_tokens": 913205.0, |
| "step": 472 |
| }, |
| { |
| "epoch": 0.5964691046658259, |
| "grad_norm": 4.117824554443359, |
| "learning_rate": 5.306532663316584e-06, |
| "loss": 1.2964, |
| "mean_token_accuracy": 0.6239383518695831, |
| "num_tokens": 914962.0, |
| "step": 473 |
| }, |
| { |
| "epoch": 0.5977301387137453, |
| "grad_norm": 4.203347682952881, |
| "learning_rate": 5.296482412060302e-06, |
| "loss": 1.4524, |
| "mean_token_accuracy": 0.6028485894203186, |
| "num_tokens": 916915.0, |
| "step": 474 |
| }, |
| { |
| "epoch": 0.5989911727616646, |
| "grad_norm": 4.006253719329834, |
| "learning_rate": 5.28643216080402e-06, |
| "loss": 1.4569, |
| "mean_token_accuracy": 0.6102553606033325, |
| "num_tokens": 918862.0, |
| "step": 475 |
| }, |
| { |
| "epoch": 0.6002522068095839, |
| "grad_norm": 4.148035049438477, |
| "learning_rate": 5.2763819095477384e-06, |
| "loss": 1.5128, |
| "mean_token_accuracy": 0.5903106033802032, |
| "num_tokens": 920708.0, |
| "step": 476 |
| }, |
| { |
| "epoch": 0.6015132408575031, |
| "grad_norm": 4.400207042694092, |
| "learning_rate": 5.266331658291458e-06, |
| "loss": 1.5556, |
| "mean_token_accuracy": 0.5801825821399689, |
| "num_tokens": 922440.0, |
| "step": 477 |
| }, |
| { |
| "epoch": 0.6027742749054225, |
| "grad_norm": 3.911195993423462, |
| "learning_rate": 5.256281407035176e-06, |
| "loss": 1.3527, |
| "mean_token_accuracy": 0.6198071241378784, |
| "num_tokens": 924327.0, |
| "step": 478 |
| }, |
| { |
| "epoch": 0.6040353089533418, |
| "grad_norm": 4.530071258544922, |
| "learning_rate": 5.2462311557788945e-06, |
| "loss": 1.5821, |
| "mean_token_accuracy": 0.580609917640686, |
| "num_tokens": 926140.0, |
| "step": 479 |
| }, |
| { |
| "epoch": 0.605296343001261, |
| "grad_norm": 3.8630685806274414, |
| "learning_rate": 5.236180904522613e-06, |
| "loss": 1.3839, |
| "mean_token_accuracy": 0.6292921006679535, |
| "num_tokens": 928105.0, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.6065573770491803, |
| "grad_norm": 3.9717369079589844, |
| "learning_rate": 5.2261306532663325e-06, |
| "loss": 1.423, |
| "mean_token_accuracy": 0.6069486737251282, |
| "num_tokens": 930094.0, |
| "step": 481 |
| }, |
| { |
| "epoch": 0.6078184110970997, |
| "grad_norm": 3.7706334590911865, |
| "learning_rate": 5.216080402010051e-06, |
| "loss": 1.4392, |
| "mean_token_accuracy": 0.6127463579177856, |
| "num_tokens": 932075.0, |
| "step": 482 |
| }, |
| { |
| "epoch": 0.6090794451450189, |
| "grad_norm": 4.312561511993408, |
| "learning_rate": 5.206030150753769e-06, |
| "loss": 1.5057, |
| "mean_token_accuracy": 0.5967552363872528, |
| "num_tokens": 933860.0, |
| "step": 483 |
| }, |
| { |
| "epoch": 0.6103404791929382, |
| "grad_norm": 4.139890193939209, |
| "learning_rate": 5.195979899497488e-06, |
| "loss": 1.425, |
| "mean_token_accuracy": 0.602910578250885, |
| "num_tokens": 935729.0, |
| "step": 484 |
| }, |
| { |
| "epoch": 0.6116015132408575, |
| "grad_norm": 4.032483100891113, |
| "learning_rate": 5.185929648241207e-06, |
| "loss": 1.4033, |
| "mean_token_accuracy": 0.5998988151550293, |
| "num_tokens": 937684.0, |
| "step": 485 |
| }, |
| { |
| "epoch": 0.6128625472887768, |
| "grad_norm": 4.146860122680664, |
| "learning_rate": 5.175879396984925e-06, |
| "loss": 1.4753, |
| "mean_token_accuracy": 0.6013561189174652, |
| "num_tokens": 939604.0, |
| "step": 486 |
| }, |
| { |
| "epoch": 0.6141235813366961, |
| "grad_norm": 4.384416580200195, |
| "learning_rate": 5.165829145728644e-06, |
| "loss": 1.3525, |
| "mean_token_accuracy": 0.6071769595146179, |
| "num_tokens": 941669.0, |
| "step": 487 |
| }, |
| { |
| "epoch": 0.6153846153846154, |
| "grad_norm": 4.441947937011719, |
| "learning_rate": 5.155778894472362e-06, |
| "loss": 1.4166, |
| "mean_token_accuracy": 0.6223839223384857, |
| "num_tokens": 943543.0, |
| "step": 488 |
| }, |
| { |
| "epoch": 0.6166456494325346, |
| "grad_norm": 4.2887115478515625, |
| "learning_rate": 5.145728643216081e-06, |
| "loss": 1.3786, |
| "mean_token_accuracy": 0.6249210238456726, |
| "num_tokens": 945387.0, |
| "step": 489 |
| }, |
| { |
| "epoch": 0.617906683480454, |
| "grad_norm": 4.079659461975098, |
| "learning_rate": 5.1356783919598e-06, |
| "loss": 1.342, |
| "mean_token_accuracy": 0.6278223991394043, |
| "num_tokens": 947294.0, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.6191677175283733, |
| "grad_norm": 4.367201328277588, |
| "learning_rate": 5.125628140703518e-06, |
| "loss": 1.6105, |
| "mean_token_accuracy": 0.5611352920532227, |
| "num_tokens": 949245.0, |
| "step": 491 |
| }, |
| { |
| "epoch": 0.6204287515762925, |
| "grad_norm": 4.136919021606445, |
| "learning_rate": 5.115577889447236e-06, |
| "loss": 1.5049, |
| "mean_token_accuracy": 0.6014758944511414, |
| "num_tokens": 951077.0, |
| "step": 492 |
| }, |
| { |
| "epoch": 0.6216897856242118, |
| "grad_norm": 4.354308605194092, |
| "learning_rate": 5.1055276381909544e-06, |
| "loss": 1.3732, |
| "mean_token_accuracy": 0.6369976699352264, |
| "num_tokens": 952980.0, |
| "step": 493 |
| }, |
| { |
| "epoch": 0.6229508196721312, |
| "grad_norm": 4.78447961807251, |
| "learning_rate": 5.095477386934674e-06, |
| "loss": 1.5297, |
| "mean_token_accuracy": 0.5905880928039551, |
| "num_tokens": 954830.0, |
| "step": 494 |
| }, |
| { |
| "epoch": 0.6242118537200504, |
| "grad_norm": 4.451809883117676, |
| "learning_rate": 5.085427135678392e-06, |
| "loss": 1.51, |
| "mean_token_accuracy": 0.5860687792301178, |
| "num_tokens": 956642.0, |
| "step": 495 |
| }, |
| { |
| "epoch": 0.6254728877679697, |
| "grad_norm": 4.794120788574219, |
| "learning_rate": 5.0753768844221105e-06, |
| "loss": 1.5092, |
| "mean_token_accuracy": 0.6137255132198334, |
| "num_tokens": 958342.0, |
| "step": 496 |
| }, |
| { |
| "epoch": 0.626733921815889, |
| "grad_norm": 4.356624603271484, |
| "learning_rate": 5.065326633165829e-06, |
| "loss": 1.4437, |
| "mean_token_accuracy": 0.5994245707988739, |
| "num_tokens": 960176.0, |
| "step": 497 |
| }, |
| { |
| "epoch": 0.6279949558638083, |
| "grad_norm": 4.708098888397217, |
| "learning_rate": 5.0552763819095485e-06, |
| "loss": 1.5365, |
| "mean_token_accuracy": 0.6074124574661255, |
| "num_tokens": 962049.0, |
| "step": 498 |
| }, |
| { |
| "epoch": 0.6292559899117276, |
| "grad_norm": 4.1611785888671875, |
| "learning_rate": 5.045226130653267e-06, |
| "loss": 1.5711, |
| "mean_token_accuracy": 0.5907929241657257, |
| "num_tokens": 964044.0, |
| "step": 499 |
| }, |
| { |
| "epoch": 0.6305170239596469, |
| "grad_norm": 4.215281963348389, |
| "learning_rate": 5.035175879396985e-06, |
| "loss": 1.359, |
| "mean_token_accuracy": 0.6179487109184265, |
| "num_tokens": 966015.0, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.6317780580075663, |
| "grad_norm": 4.392022132873535, |
| "learning_rate": 5.025125628140704e-06, |
| "loss": 1.5106, |
| "mean_token_accuracy": 0.6017323136329651, |
| "num_tokens": 967891.0, |
| "step": 501 |
| }, |
| { |
| "epoch": 0.6330390920554855, |
| "grad_norm": 3.9430975914001465, |
| "learning_rate": 5.015075376884423e-06, |
| "loss": 1.3659, |
| "mean_token_accuracy": 0.622453361749649, |
| "num_tokens": 969888.0, |
| "step": 502 |
| }, |
| { |
| "epoch": 0.6343001261034048, |
| "grad_norm": 3.892613172531128, |
| "learning_rate": 5.005025125628141e-06, |
| "loss": 1.4432, |
| "mean_token_accuracy": 0.6056107580661774, |
| "num_tokens": 972007.0, |
| "step": 503 |
| }, |
| { |
| "epoch": 0.6355611601513241, |
| "grad_norm": 4.147119522094727, |
| "learning_rate": 4.99497487437186e-06, |
| "loss": 1.3801, |
| "mean_token_accuracy": 0.6145619451999664, |
| "num_tokens": 974059.0, |
| "step": 504 |
| }, |
| { |
| "epoch": 0.6368221941992434, |
| "grad_norm": 3.900256872177124, |
| "learning_rate": 4.984924623115578e-06, |
| "loss": 1.5498, |
| "mean_token_accuracy": 0.6014587879180908, |
| "num_tokens": 976086.0, |
| "step": 505 |
| }, |
| { |
| "epoch": 0.6380832282471627, |
| "grad_norm": 4.286009788513184, |
| "learning_rate": 4.974874371859297e-06, |
| "loss": 1.4711, |
| "mean_token_accuracy": 0.5997771620750427, |
| "num_tokens": 978000.0, |
| "step": 506 |
| }, |
| { |
| "epoch": 0.639344262295082, |
| "grad_norm": 4.044436931610107, |
| "learning_rate": 4.964824120603016e-06, |
| "loss": 1.3599, |
| "mean_token_accuracy": 0.6190573871135712, |
| "num_tokens": 980122.0, |
| "step": 507 |
| }, |
| { |
| "epoch": 0.6406052963430012, |
| "grad_norm": 3.8622653484344482, |
| "learning_rate": 4.954773869346734e-06, |
| "loss": 1.299, |
| "mean_token_accuracy": 0.6397116184234619, |
| "num_tokens": 982107.0, |
| "step": 508 |
| }, |
| { |
| "epoch": 0.6418663303909206, |
| "grad_norm": 4.036622524261475, |
| "learning_rate": 4.944723618090453e-06, |
| "loss": 1.3907, |
| "mean_token_accuracy": 0.5995530188083649, |
| "num_tokens": 984115.0, |
| "step": 509 |
| }, |
| { |
| "epoch": 0.6431273644388399, |
| "grad_norm": 4.12971830368042, |
| "learning_rate": 4.934673366834171e-06, |
| "loss": 1.49, |
| "mean_token_accuracy": 0.6049287021160126, |
| "num_tokens": 986018.0, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.6443883984867591, |
| "grad_norm": 4.413822650909424, |
| "learning_rate": 4.92462311557789e-06, |
| "loss": 1.5757, |
| "mean_token_accuracy": 0.5891340374946594, |
| "num_tokens": 988040.0, |
| "step": 511 |
| }, |
| { |
| "epoch": 0.6456494325346784, |
| "grad_norm": 4.282911777496338, |
| "learning_rate": 4.914572864321608e-06, |
| "loss": 1.5484, |
| "mean_token_accuracy": 0.5913865864276886, |
| "num_tokens": 990049.0, |
| "step": 512 |
| }, |
| { |
| "epoch": 0.6469104665825978, |
| "grad_norm": 4.138622283935547, |
| "learning_rate": 4.904522613065327e-06, |
| "loss": 1.3762, |
| "mean_token_accuracy": 0.6090503036975861, |
| "num_tokens": 991939.0, |
| "step": 513 |
| }, |
| { |
| "epoch": 0.648171500630517, |
| "grad_norm": 4.5050435066223145, |
| "learning_rate": 4.8944723618090455e-06, |
| "loss": 1.4768, |
| "mean_token_accuracy": 0.5987947881221771, |
| "num_tokens": 993670.0, |
| "step": 514 |
| }, |
| { |
| "epoch": 0.6494325346784363, |
| "grad_norm": 4.05117130279541, |
| "learning_rate": 4.8844221105527645e-06, |
| "loss": 1.4625, |
| "mean_token_accuracy": 0.6028375625610352, |
| "num_tokens": 995631.0, |
| "step": 515 |
| }, |
| { |
| "epoch": 0.6506935687263556, |
| "grad_norm": 4.307063102722168, |
| "learning_rate": 4.874371859296483e-06, |
| "loss": 1.3849, |
| "mean_token_accuracy": 0.6143765449523926, |
| "num_tokens": 997576.0, |
| "step": 516 |
| }, |
| { |
| "epoch": 0.6519546027742749, |
| "grad_norm": 4.198483467102051, |
| "learning_rate": 4.864321608040201e-06, |
| "loss": 1.459, |
| "mean_token_accuracy": 0.591049462556839, |
| "num_tokens": 999431.0, |
| "step": 517 |
| }, |
| { |
| "epoch": 0.6532156368221942, |
| "grad_norm": 4.2448835372924805, |
| "learning_rate": 4.85427135678392e-06, |
| "loss": 1.5409, |
| "mean_token_accuracy": 0.5864794254302979, |
| "num_tokens": 1001402.0, |
| "step": 518 |
| }, |
| { |
| "epoch": 0.6544766708701135, |
| "grad_norm": 3.9349770545959473, |
| "learning_rate": 4.844221105527638e-06, |
| "loss": 1.3259, |
| "mean_token_accuracy": 0.6447261869907379, |
| "num_tokens": 1003371.0, |
| "step": 519 |
| }, |
| { |
| "epoch": 0.6557377049180327, |
| "grad_norm": 4.384145259857178, |
| "learning_rate": 4.834170854271357e-06, |
| "loss": 1.4976, |
| "mean_token_accuracy": 0.60174959897995, |
| "num_tokens": 1005205.0, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.6569987389659521, |
| "grad_norm": 4.253158092498779, |
| "learning_rate": 4.824120603015076e-06, |
| "loss": 1.3808, |
| "mean_token_accuracy": 0.6132340133190155, |
| "num_tokens": 1007120.0, |
| "step": 521 |
| }, |
| { |
| "epoch": 0.6582597730138714, |
| "grad_norm": 4.16796875, |
| "learning_rate": 4.814070351758794e-06, |
| "loss": 1.5749, |
| "mean_token_accuracy": 0.6019249558448792, |
| "num_tokens": 1009045.0, |
| "step": 522 |
| }, |
| { |
| "epoch": 0.6595208070617906, |
| "grad_norm": 4.176485538482666, |
| "learning_rate": 4.804020100502513e-06, |
| "loss": 1.489, |
| "mean_token_accuracy": 0.6130034625530243, |
| "num_tokens": 1010978.0, |
| "step": 523 |
| }, |
| { |
| "epoch": 0.6607818411097099, |
| "grad_norm": 4.173998832702637, |
| "learning_rate": 4.793969849246232e-06, |
| "loss": 1.4154, |
| "mean_token_accuracy": 0.6257044970989227, |
| "num_tokens": 1012941.0, |
| "step": 524 |
| }, |
| { |
| "epoch": 0.6620428751576293, |
| "grad_norm": 4.313329219818115, |
| "learning_rate": 4.78391959798995e-06, |
| "loss": 1.4384, |
| "mean_token_accuracy": 0.5984161496162415, |
| "num_tokens": 1014844.0, |
| "step": 525 |
| }, |
| { |
| "epoch": 0.6633039092055486, |
| "grad_norm": 4.119398593902588, |
| "learning_rate": 4.773869346733669e-06, |
| "loss": 1.4806, |
| "mean_token_accuracy": 0.6089716553688049, |
| "num_tokens": 1016768.0, |
| "step": 526 |
| }, |
| { |
| "epoch": 0.6645649432534678, |
| "grad_norm": 3.8196797370910645, |
| "learning_rate": 4.763819095477387e-06, |
| "loss": 1.4531, |
| "mean_token_accuracy": 0.6100893914699554, |
| "num_tokens": 1018940.0, |
| "step": 527 |
| }, |
| { |
| "epoch": 0.6658259773013872, |
| "grad_norm": 3.7822678089141846, |
| "learning_rate": 4.753768844221106e-06, |
| "loss": 1.3299, |
| "mean_token_accuracy": 0.6366003751754761, |
| "num_tokens": 1021088.0, |
| "step": 528 |
| }, |
| { |
| "epoch": 0.6670870113493065, |
| "grad_norm": 4.061533451080322, |
| "learning_rate": 4.743718592964824e-06, |
| "loss": 1.4227, |
| "mean_token_accuracy": 0.6176785826683044, |
| "num_tokens": 1023129.0, |
| "step": 529 |
| }, |
| { |
| "epoch": 0.6683480453972257, |
| "grad_norm": 4.252097129821777, |
| "learning_rate": 4.733668341708543e-06, |
| "loss": 1.3714, |
| "mean_token_accuracy": 0.6185733079910278, |
| "num_tokens": 1025194.0, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.669609079445145, |
| "grad_norm": 3.9393389225006104, |
| "learning_rate": 4.7236180904522615e-06, |
| "loss": 1.4285, |
| "mean_token_accuracy": 0.6074325740337372, |
| "num_tokens": 1027265.0, |
| "step": 531 |
| }, |
| { |
| "epoch": 0.6708701134930644, |
| "grad_norm": 4.501029968261719, |
| "learning_rate": 4.7135678391959805e-06, |
| "loss": 1.5284, |
| "mean_token_accuracy": 0.5852837264537811, |
| "num_tokens": 1029237.0, |
| "step": 532 |
| }, |
| { |
| "epoch": 0.6721311475409836, |
| "grad_norm": 4.294065475463867, |
| "learning_rate": 4.703517587939699e-06, |
| "loss": 1.3974, |
| "mean_token_accuracy": 0.602262407541275, |
| "num_tokens": 1031116.0, |
| "step": 533 |
| }, |
| { |
| "epoch": 0.6733921815889029, |
| "grad_norm": 4.042904376983643, |
| "learning_rate": 4.693467336683418e-06, |
| "loss": 1.3956, |
| "mean_token_accuracy": 0.6112872660160065, |
| "num_tokens": 1033181.0, |
| "step": 534 |
| }, |
| { |
| "epoch": 0.6746532156368222, |
| "grad_norm": 4.032866954803467, |
| "learning_rate": 4.683417085427136e-06, |
| "loss": 1.4685, |
| "mean_token_accuracy": 0.6069096922874451, |
| "num_tokens": 1035145.0, |
| "step": 535 |
| }, |
| { |
| "epoch": 0.6759142496847415, |
| "grad_norm": 4.177650451660156, |
| "learning_rate": 4.673366834170855e-06, |
| "loss": 1.3029, |
| "mean_token_accuracy": 0.6414700150489807, |
| "num_tokens": 1037178.0, |
| "step": 536 |
| }, |
| { |
| "epoch": 0.6771752837326608, |
| "grad_norm": 4.131723880767822, |
| "learning_rate": 4.663316582914573e-06, |
| "loss": 1.4881, |
| "mean_token_accuracy": 0.5847931206226349, |
| "num_tokens": 1039259.0, |
| "step": 537 |
| }, |
| { |
| "epoch": 0.6784363177805801, |
| "grad_norm": 4.277894496917725, |
| "learning_rate": 4.653266331658292e-06, |
| "loss": 1.4666, |
| "mean_token_accuracy": 0.5960581600666046, |
| "num_tokens": 1041108.0, |
| "step": 538 |
| }, |
| { |
| "epoch": 0.6796973518284993, |
| "grad_norm": 4.391327857971191, |
| "learning_rate": 4.64321608040201e-06, |
| "loss": 1.4966, |
| "mean_token_accuracy": 0.5966735780239105, |
| "num_tokens": 1043111.0, |
| "step": 539 |
| }, |
| { |
| "epoch": 0.6809583858764187, |
| "grad_norm": 4.3835673332214355, |
| "learning_rate": 4.633165829145729e-06, |
| "loss": 1.4816, |
| "mean_token_accuracy": 0.5919269919395447, |
| "num_tokens": 1045039.0, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.682219419924338, |
| "grad_norm": 4.380410671234131, |
| "learning_rate": 4.623115577889448e-06, |
| "loss": 1.4864, |
| "mean_token_accuracy": 0.5843121707439423, |
| "num_tokens": 1047056.0, |
| "step": 541 |
| }, |
| { |
| "epoch": 0.6834804539722572, |
| "grad_norm": 4.51450252532959, |
| "learning_rate": 4.613065326633166e-06, |
| "loss": 1.5087, |
| "mean_token_accuracy": 0.5990866422653198, |
| "num_tokens": 1049015.0, |
| "step": 542 |
| }, |
| { |
| "epoch": 0.6847414880201765, |
| "grad_norm": 4.474623203277588, |
| "learning_rate": 4.603015075376885e-06, |
| "loss": 1.5369, |
| "mean_token_accuracy": 0.5826748311519623, |
| "num_tokens": 1051016.0, |
| "step": 543 |
| }, |
| { |
| "epoch": 0.6860025220680959, |
| "grad_norm": 4.619833946228027, |
| "learning_rate": 4.592964824120603e-06, |
| "loss": 1.5901, |
| "mean_token_accuracy": 0.5855450630187988, |
| "num_tokens": 1052884.0, |
| "step": 544 |
| }, |
| { |
| "epoch": 0.6872635561160151, |
| "grad_norm": 4.460485935211182, |
| "learning_rate": 4.582914572864322e-06, |
| "loss": 1.476, |
| "mean_token_accuracy": 0.5999694764614105, |
| "num_tokens": 1054726.0, |
| "step": 545 |
| }, |
| { |
| "epoch": 0.6885245901639344, |
| "grad_norm": 4.181125640869141, |
| "learning_rate": 4.57286432160804e-06, |
| "loss": 1.365, |
| "mean_token_accuracy": 0.6187720596790314, |
| "num_tokens": 1056663.0, |
| "step": 546 |
| }, |
| { |
| "epoch": 0.6897856242118537, |
| "grad_norm": 4.0265583992004395, |
| "learning_rate": 4.562814070351759e-06, |
| "loss": 1.4209, |
| "mean_token_accuracy": 0.6083628833293915, |
| "num_tokens": 1058657.0, |
| "step": 547 |
| }, |
| { |
| "epoch": 0.691046658259773, |
| "grad_norm": 4.170673847198486, |
| "learning_rate": 4.5527638190954775e-06, |
| "loss": 1.3842, |
| "mean_token_accuracy": 0.6233990788459778, |
| "num_tokens": 1060720.0, |
| "step": 548 |
| }, |
| { |
| "epoch": 0.6923076923076923, |
| "grad_norm": 4.298334121704102, |
| "learning_rate": 4.5427135678391965e-06, |
| "loss": 1.5274, |
| "mean_token_accuracy": 0.5755627751350403, |
| "num_tokens": 1062706.0, |
| "step": 549 |
| }, |
| { |
| "epoch": 0.6935687263556116, |
| "grad_norm": 4.409641742706299, |
| "learning_rate": 4.532663316582915e-06, |
| "loss": 1.4234, |
| "mean_token_accuracy": 0.6005873680114746, |
| "num_tokens": 1064567.0, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.694829760403531, |
| "grad_norm": 4.0575175285339355, |
| "learning_rate": 4.522613065326634e-06, |
| "loss": 1.47, |
| "mean_token_accuracy": 0.6192085146903992, |
| "num_tokens": 1066620.0, |
| "step": 551 |
| }, |
| { |
| "epoch": 0.6960907944514502, |
| "grad_norm": 4.188862323760986, |
| "learning_rate": 4.512562814070352e-06, |
| "loss": 1.4006, |
| "mean_token_accuracy": 0.609145849943161, |
| "num_tokens": 1068663.0, |
| "step": 552 |
| }, |
| { |
| "epoch": 0.6973518284993695, |
| "grad_norm": 4.311684608459473, |
| "learning_rate": 4.502512562814071e-06, |
| "loss": 1.4287, |
| "mean_token_accuracy": 0.5967524945735931, |
| "num_tokens": 1070500.0, |
| "step": 553 |
| }, |
| { |
| "epoch": 0.6986128625472888, |
| "grad_norm": 4.478208065032959, |
| "learning_rate": 4.492462311557789e-06, |
| "loss": 1.5679, |
| "mean_token_accuracy": 0.5677984654903412, |
| "num_tokens": 1072399.0, |
| "step": 554 |
| }, |
| { |
| "epoch": 0.699873896595208, |
| "grad_norm": 4.476880073547363, |
| "learning_rate": 4.482412060301508e-06, |
| "loss": 1.5745, |
| "mean_token_accuracy": 0.5820361375808716, |
| "num_tokens": 1074229.0, |
| "step": 555 |
| }, |
| { |
| "epoch": 0.7011349306431274, |
| "grad_norm": 4.118135929107666, |
| "learning_rate": 4.472361809045226e-06, |
| "loss": 1.3818, |
| "mean_token_accuracy": 0.6199574172496796, |
| "num_tokens": 1076179.0, |
| "step": 556 |
| }, |
| { |
| "epoch": 0.7023959646910467, |
| "grad_norm": 4.258944988250732, |
| "learning_rate": 4.462311557788945e-06, |
| "loss": 1.4556, |
| "mean_token_accuracy": 0.6048978269100189, |
| "num_tokens": 1078196.0, |
| "step": 557 |
| }, |
| { |
| "epoch": 0.7036569987389659, |
| "grad_norm": 4.3716206550598145, |
| "learning_rate": 4.452261306532664e-06, |
| "loss": 1.4638, |
| "mean_token_accuracy": 0.6035429835319519, |
| "num_tokens": 1080054.0, |
| "step": 558 |
| }, |
| { |
| "epoch": 0.7049180327868853, |
| "grad_norm": 4.203842639923096, |
| "learning_rate": 4.442211055276382e-06, |
| "loss": 1.519, |
| "mean_token_accuracy": 0.5738790929317474, |
| "num_tokens": 1082139.0, |
| "step": 559 |
| }, |
| { |
| "epoch": 0.7061790668348046, |
| "grad_norm": 3.9735658168792725, |
| "learning_rate": 4.432160804020101e-06, |
| "loss": 1.2718, |
| "mean_token_accuracy": 0.6296245157718658, |
| "num_tokens": 1084184.0, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.7074401008827238, |
| "grad_norm": 4.601116180419922, |
| "learning_rate": 4.42211055276382e-06, |
| "loss": 1.4758, |
| "mean_token_accuracy": 0.5895026922225952, |
| "num_tokens": 1086114.0, |
| "step": 561 |
| }, |
| { |
| "epoch": 0.7087011349306431, |
| "grad_norm": 4.092045307159424, |
| "learning_rate": 4.412060301507538e-06, |
| "loss": 1.4217, |
| "mean_token_accuracy": 0.6099154055118561, |
| "num_tokens": 1088186.0, |
| "step": 562 |
| }, |
| { |
| "epoch": 0.7099621689785625, |
| "grad_norm": 4.286192417144775, |
| "learning_rate": 4.4020100502512564e-06, |
| "loss": 1.5134, |
| "mean_token_accuracy": 0.5960166454315186, |
| "num_tokens": 1090066.0, |
| "step": 563 |
| }, |
| { |
| "epoch": 0.7112232030264817, |
| "grad_norm": 4.366318225860596, |
| "learning_rate": 4.391959798994975e-06, |
| "loss": 1.3797, |
| "mean_token_accuracy": 0.6279633641242981, |
| "num_tokens": 1091943.0, |
| "step": 564 |
| }, |
| { |
| "epoch": 0.712484237074401, |
| "grad_norm": 4.332135200500488, |
| "learning_rate": 4.3819095477386936e-06, |
| "loss": 1.4498, |
| "mean_token_accuracy": 0.6036017537117004, |
| "num_tokens": 1093927.0, |
| "step": 565 |
| }, |
| { |
| "epoch": 0.7137452711223203, |
| "grad_norm": 4.145910739898682, |
| "learning_rate": 4.3718592964824125e-06, |
| "loss": 1.467, |
| "mean_token_accuracy": 0.5955266952514648, |
| "num_tokens": 1095943.0, |
| "step": 566 |
| }, |
| { |
| "epoch": 0.7150063051702396, |
| "grad_norm": 4.207005500793457, |
| "learning_rate": 4.361809045226131e-06, |
| "loss": 1.4077, |
| "mean_token_accuracy": 0.6239123344421387, |
| "num_tokens": 1097960.0, |
| "step": 567 |
| }, |
| { |
| "epoch": 0.7162673392181589, |
| "grad_norm": 4.264434337615967, |
| "learning_rate": 4.35175879396985e-06, |
| "loss": 1.5408, |
| "mean_token_accuracy": 0.5840959250926971, |
| "num_tokens": 1100027.0, |
| "step": 568 |
| }, |
| { |
| "epoch": 0.7175283732660782, |
| "grad_norm": 4.43059778213501, |
| "learning_rate": 4.341708542713568e-06, |
| "loss": 1.417, |
| "mean_token_accuracy": 0.6145318448543549, |
| "num_tokens": 1101888.0, |
| "step": 569 |
| }, |
| { |
| "epoch": 0.7187894073139974, |
| "grad_norm": 4.425664901733398, |
| "learning_rate": 4.331658291457287e-06, |
| "loss": 1.4231, |
| "mean_token_accuracy": 0.6067825257778168, |
| "num_tokens": 1103765.0, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.7200504413619168, |
| "grad_norm": 4.427340507507324, |
| "learning_rate": 4.321608040201005e-06, |
| "loss": 1.4333, |
| "mean_token_accuracy": 0.6241535246372223, |
| "num_tokens": 1105637.0, |
| "step": 571 |
| }, |
| { |
| "epoch": 0.7213114754098361, |
| "grad_norm": 4.249168872833252, |
| "learning_rate": 4.311557788944724e-06, |
| "loss": 1.334, |
| "mean_token_accuracy": 0.6373594701290131, |
| "num_tokens": 1107675.0, |
| "step": 572 |
| }, |
| { |
| "epoch": 0.7225725094577553, |
| "grad_norm": 4.880923271179199, |
| "learning_rate": 4.301507537688442e-06, |
| "loss": 1.6842, |
| "mean_token_accuracy": 0.5585279166698456, |
| "num_tokens": 1109568.0, |
| "step": 573 |
| }, |
| { |
| "epoch": 0.7238335435056746, |
| "grad_norm": 4.138409614562988, |
| "learning_rate": 4.291457286432161e-06, |
| "loss": 1.4518, |
| "mean_token_accuracy": 0.6146091818809509, |
| "num_tokens": 1111491.0, |
| "step": 574 |
| }, |
| { |
| "epoch": 0.725094577553594, |
| "grad_norm": 4.344665050506592, |
| "learning_rate": 4.28140703517588e-06, |
| "loss": 1.4003, |
| "mean_token_accuracy": 0.6278960406780243, |
| "num_tokens": 1113417.0, |
| "step": 575 |
| }, |
| { |
| "epoch": 0.7263556116015133, |
| "grad_norm": 4.1242146492004395, |
| "learning_rate": 4.271356783919598e-06, |
| "loss": 1.3366, |
| "mean_token_accuracy": 0.6168392598628998, |
| "num_tokens": 1115469.0, |
| "step": 576 |
| }, |
| { |
| "epoch": 0.7276166456494325, |
| "grad_norm": 4.681807041168213, |
| "learning_rate": 4.261306532663317e-06, |
| "loss": 1.4971, |
| "mean_token_accuracy": 0.5873031616210938, |
| "num_tokens": 1117326.0, |
| "step": 577 |
| }, |
| { |
| "epoch": 0.7288776796973518, |
| "grad_norm": 4.148594379425049, |
| "learning_rate": 4.251256281407035e-06, |
| "loss": 1.4957, |
| "mean_token_accuracy": 0.6133466064929962, |
| "num_tokens": 1119353.0, |
| "step": 578 |
| }, |
| { |
| "epoch": 0.7301387137452712, |
| "grad_norm": 4.205901622772217, |
| "learning_rate": 4.241206030150754e-06, |
| "loss": 1.3541, |
| "mean_token_accuracy": 0.6136380732059479, |
| "num_tokens": 1121372.0, |
| "step": 579 |
| }, |
| { |
| "epoch": 0.7313997477931904, |
| "grad_norm": 4.561435699462891, |
| "learning_rate": 4.231155778894473e-06, |
| "loss": 1.5047, |
| "mean_token_accuracy": 0.5941650867462158, |
| "num_tokens": 1123316.0, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.7326607818411097, |
| "grad_norm": 4.207332611083984, |
| "learning_rate": 4.221105527638191e-06, |
| "loss": 1.4151, |
| "mean_token_accuracy": 0.6092670261859894, |
| "num_tokens": 1125322.0, |
| "step": 581 |
| }, |
| { |
| "epoch": 0.733921815889029, |
| "grad_norm": 4.15023946762085, |
| "learning_rate": 4.21105527638191e-06, |
| "loss": 1.3431, |
| "mean_token_accuracy": 0.6442605555057526, |
| "num_tokens": 1127284.0, |
| "step": 582 |
| }, |
| { |
| "epoch": 0.7351828499369483, |
| "grad_norm": 4.073770046234131, |
| "learning_rate": 4.2010050251256285e-06, |
| "loss": 1.4278, |
| "mean_token_accuracy": 0.6028145551681519, |
| "num_tokens": 1129336.0, |
| "step": 583 |
| }, |
| { |
| "epoch": 0.7364438839848676, |
| "grad_norm": 4.155696392059326, |
| "learning_rate": 4.1909547738693475e-06, |
| "loss": 1.5242, |
| "mean_token_accuracy": 0.6014257669448853, |
| "num_tokens": 1131229.0, |
| "step": 584 |
| }, |
| { |
| "epoch": 0.7377049180327869, |
| "grad_norm": 4.599628925323486, |
| "learning_rate": 4.180904522613066e-06, |
| "loss": 1.4689, |
| "mean_token_accuracy": 0.6075104475021362, |
| "num_tokens": 1133138.0, |
| "step": 585 |
| }, |
| { |
| "epoch": 0.7389659520807061, |
| "grad_norm": 4.1771345138549805, |
| "learning_rate": 4.170854271356784e-06, |
| "loss": 1.4611, |
| "mean_token_accuracy": 0.6091577410697937, |
| "num_tokens": 1135144.0, |
| "step": 586 |
| }, |
| { |
| "epoch": 0.7402269861286255, |
| "grad_norm": 4.629430294036865, |
| "learning_rate": 4.160804020100503e-06, |
| "loss": 1.4212, |
| "mean_token_accuracy": 0.6028386056423187, |
| "num_tokens": 1136946.0, |
| "step": 587 |
| }, |
| { |
| "epoch": 0.7414880201765448, |
| "grad_norm": 4.687736988067627, |
| "learning_rate": 4.150753768844221e-06, |
| "loss": 1.6235, |
| "mean_token_accuracy": 0.5800973176956177, |
| "num_tokens": 1138786.0, |
| "step": 588 |
| }, |
| { |
| "epoch": 0.742749054224464, |
| "grad_norm": 4.503421783447266, |
| "learning_rate": 4.14070351758794e-06, |
| "loss": 1.3945, |
| "mean_token_accuracy": 0.602990061044693, |
| "num_tokens": 1140532.0, |
| "step": 589 |
| }, |
| { |
| "epoch": 0.7440100882723834, |
| "grad_norm": 4.563640117645264, |
| "learning_rate": 4.130653266331658e-06, |
| "loss": 1.4467, |
| "mean_token_accuracy": 0.595698207616806, |
| "num_tokens": 1142407.0, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.7452711223203027, |
| "grad_norm": 4.475567817687988, |
| "learning_rate": 4.120603015075377e-06, |
| "loss": 1.4367, |
| "mean_token_accuracy": 0.6017897129058838, |
| "num_tokens": 1144273.0, |
| "step": 591 |
| }, |
| { |
| "epoch": 0.7465321563682219, |
| "grad_norm": 4.657721519470215, |
| "learning_rate": 4.110552763819096e-06, |
| "loss": 1.5447, |
| "mean_token_accuracy": 0.5949556827545166, |
| "num_tokens": 1146103.0, |
| "step": 592 |
| }, |
| { |
| "epoch": 0.7477931904161412, |
| "grad_norm": 4.46821403503418, |
| "learning_rate": 4.100502512562814e-06, |
| "loss": 1.5193, |
| "mean_token_accuracy": 0.5897854566574097, |
| "num_tokens": 1148055.0, |
| "step": 593 |
| }, |
| { |
| "epoch": 0.7490542244640606, |
| "grad_norm": 4.4468536376953125, |
| "learning_rate": 4.090452261306533e-06, |
| "loss": 1.5036, |
| "mean_token_accuracy": 0.594214141368866, |
| "num_tokens": 1149916.0, |
| "step": 594 |
| }, |
| { |
| "epoch": 0.7503152585119798, |
| "grad_norm": 4.743985652923584, |
| "learning_rate": 4.080402010050251e-06, |
| "loss": 1.3838, |
| "mean_token_accuracy": 0.6155570149421692, |
| "num_tokens": 1151952.0, |
| "step": 595 |
| }, |
| { |
| "epoch": 0.7515762925598991, |
| "grad_norm": 4.6654462814331055, |
| "learning_rate": 4.07035175879397e-06, |
| "loss": 1.4874, |
| "mean_token_accuracy": 0.5827921628952026, |
| "num_tokens": 1153786.0, |
| "step": 596 |
| }, |
| { |
| "epoch": 0.7528373266078184, |
| "grad_norm": 4.544785022735596, |
| "learning_rate": 4.060301507537689e-06, |
| "loss": 1.4062, |
| "mean_token_accuracy": 0.6182176172733307, |
| "num_tokens": 1155728.0, |
| "step": 597 |
| }, |
| { |
| "epoch": 0.7540983606557377, |
| "grad_norm": 4.02006196975708, |
| "learning_rate": 4.0502512562814074e-06, |
| "loss": 1.3816, |
| "mean_token_accuracy": 0.6215299069881439, |
| "num_tokens": 1157784.0, |
| "step": 598 |
| }, |
| { |
| "epoch": 0.755359394703657, |
| "grad_norm": 4.205069065093994, |
| "learning_rate": 4.040201005025126e-06, |
| "loss": 1.3984, |
| "mean_token_accuracy": 0.6212480962276459, |
| "num_tokens": 1159746.0, |
| "step": 599 |
| }, |
| { |
| "epoch": 0.7566204287515763, |
| "grad_norm": 4.572359561920166, |
| "learning_rate": 4.0301507537688446e-06, |
| "loss": 1.5142, |
| "mean_token_accuracy": 0.5926640629768372, |
| "num_tokens": 1161692.0, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.7578814627994955, |
| "grad_norm": 4.29414701461792, |
| "learning_rate": 4.0201005025125635e-06, |
| "loss": 1.4277, |
| "mean_token_accuracy": 0.6287708878517151, |
| "num_tokens": 1163559.0, |
| "step": 601 |
| }, |
| { |
| "epoch": 0.7591424968474149, |
| "grad_norm": 4.80892276763916, |
| "learning_rate": 4.010050251256282e-06, |
| "loss": 1.5654, |
| "mean_token_accuracy": 0.575875848531723, |
| "num_tokens": 1165372.0, |
| "step": 602 |
| }, |
| { |
| "epoch": 0.7604035308953342, |
| "grad_norm": 4.304175853729248, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 1.4001, |
| "mean_token_accuracy": 0.6016526520252228, |
| "num_tokens": 1167257.0, |
| "step": 603 |
| }, |
| { |
| "epoch": 0.7616645649432535, |
| "grad_norm": 4.059518337249756, |
| "learning_rate": 3.989949748743719e-06, |
| "loss": 1.2838, |
| "mean_token_accuracy": 0.647224634885788, |
| "num_tokens": 1169254.0, |
| "step": 604 |
| }, |
| { |
| "epoch": 0.7629255989911727, |
| "grad_norm": 4.799088001251221, |
| "learning_rate": 3.979899497487438e-06, |
| "loss": 1.4551, |
| "mean_token_accuracy": 0.6063340604305267, |
| "num_tokens": 1171048.0, |
| "step": 605 |
| }, |
| { |
| "epoch": 0.7641866330390921, |
| "grad_norm": 4.762022972106934, |
| "learning_rate": 3.969849246231156e-06, |
| "loss": 1.6099, |
| "mean_token_accuracy": 0.5841151475906372, |
| "num_tokens": 1172943.0, |
| "step": 606 |
| }, |
| { |
| "epoch": 0.7654476670870114, |
| "grad_norm": 4.426660537719727, |
| "learning_rate": 3.959798994974875e-06, |
| "loss": 1.3641, |
| "mean_token_accuracy": 0.6199142932891846, |
| "num_tokens": 1174952.0, |
| "step": 607 |
| }, |
| { |
| "epoch": 0.7667087011349306, |
| "grad_norm": 4.9128923416137695, |
| "learning_rate": 3.949748743718593e-06, |
| "loss": 1.5432, |
| "mean_token_accuracy": 0.6037909686565399, |
| "num_tokens": 1176792.0, |
| "step": 608 |
| }, |
| { |
| "epoch": 0.7679697351828499, |
| "grad_norm": 4.370631694793701, |
| "learning_rate": 3.939698492462311e-06, |
| "loss": 1.4049, |
| "mean_token_accuracy": 0.6263740062713623, |
| "num_tokens": 1178856.0, |
| "step": 609 |
| }, |
| { |
| "epoch": 0.7692307692307693, |
| "grad_norm": 4.397915363311768, |
| "learning_rate": 3.92964824120603e-06, |
| "loss": 1.3521, |
| "mean_token_accuracy": 0.6210023164749146, |
| "num_tokens": 1180599.0, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.7704918032786885, |
| "grad_norm": 4.44165563583374, |
| "learning_rate": 3.919597989949749e-06, |
| "loss": 1.488, |
| "mean_token_accuracy": 0.5845552682876587, |
| "num_tokens": 1182446.0, |
| "step": 611 |
| }, |
| { |
| "epoch": 0.7717528373266078, |
| "grad_norm": 4.571348190307617, |
| "learning_rate": 3.909547738693467e-06, |
| "loss": 1.3733, |
| "mean_token_accuracy": 0.5972480475902557, |
| "num_tokens": 1184361.0, |
| "step": 612 |
| }, |
| { |
| "epoch": 0.7730138713745272, |
| "grad_norm": 4.486395359039307, |
| "learning_rate": 3.899497487437186e-06, |
| "loss": 1.4094, |
| "mean_token_accuracy": 0.6077009737491608, |
| "num_tokens": 1186296.0, |
| "step": 613 |
| }, |
| { |
| "epoch": 0.7742749054224464, |
| "grad_norm": 4.390718936920166, |
| "learning_rate": 3.889447236180905e-06, |
| "loss": 1.4609, |
| "mean_token_accuracy": 0.6105667650699615, |
| "num_tokens": 1188264.0, |
| "step": 614 |
| }, |
| { |
| "epoch": 0.7755359394703657, |
| "grad_norm": 4.085479259490967, |
| "learning_rate": 3.8793969849246234e-06, |
| "loss": 1.3808, |
| "mean_token_accuracy": 0.6208994686603546, |
| "num_tokens": 1190225.0, |
| "step": 615 |
| }, |
| { |
| "epoch": 0.776796973518285, |
| "grad_norm": 4.256773471832275, |
| "learning_rate": 3.869346733668342e-06, |
| "loss": 1.4493, |
| "mean_token_accuracy": 0.6007210910320282, |
| "num_tokens": 1192274.0, |
| "step": 616 |
| }, |
| { |
| "epoch": 0.7780580075662042, |
| "grad_norm": 4.536936283111572, |
| "learning_rate": 3.8592964824120606e-06, |
| "loss": 1.5483, |
| "mean_token_accuracy": 0.5986529290676117, |
| "num_tokens": 1194327.0, |
| "step": 617 |
| }, |
| { |
| "epoch": 0.7793190416141236, |
| "grad_norm": 4.602484226226807, |
| "learning_rate": 3.8492462311557795e-06, |
| "loss": 1.4892, |
| "mean_token_accuracy": 0.5982283651828766, |
| "num_tokens": 1196227.0, |
| "step": 618 |
| }, |
| { |
| "epoch": 0.7805800756620429, |
| "grad_norm": 4.350205898284912, |
| "learning_rate": 3.839195979899498e-06, |
| "loss": 1.3968, |
| "mean_token_accuracy": 0.630781501531601, |
| "num_tokens": 1198122.0, |
| "step": 619 |
| }, |
| { |
| "epoch": 0.7818411097099621, |
| "grad_norm": 4.328808784484863, |
| "learning_rate": 3.829145728643217e-06, |
| "loss": 1.5386, |
| "mean_token_accuracy": 0.5927076935768127, |
| "num_tokens": 1200218.0, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.7831021437578815, |
| "grad_norm": 4.0366597175598145, |
| "learning_rate": 3.819095477386935e-06, |
| "loss": 1.3376, |
| "mean_token_accuracy": 0.6228463053703308, |
| "num_tokens": 1202311.0, |
| "step": 621 |
| }, |
| { |
| "epoch": 0.7843631778058008, |
| "grad_norm": 4.308081150054932, |
| "learning_rate": 3.809045226130654e-06, |
| "loss": 1.3082, |
| "mean_token_accuracy": 0.6177918612957001, |
| "num_tokens": 1204308.0, |
| "step": 622 |
| }, |
| { |
| "epoch": 0.78562421185372, |
| "grad_norm": 4.21478271484375, |
| "learning_rate": 3.798994974874372e-06, |
| "loss": 1.3921, |
| "mean_token_accuracy": 0.6253844499588013, |
| "num_tokens": 1206385.0, |
| "step": 623 |
| }, |
| { |
| "epoch": 0.7868852459016393, |
| "grad_norm": 4.382959365844727, |
| "learning_rate": 3.788944723618091e-06, |
| "loss": 1.5071, |
| "mean_token_accuracy": 0.5961708128452301, |
| "num_tokens": 1208393.0, |
| "step": 624 |
| }, |
| { |
| "epoch": 0.7881462799495587, |
| "grad_norm": 4.760127067565918, |
| "learning_rate": 3.7788944723618095e-06, |
| "loss": 1.3599, |
| "mean_token_accuracy": 0.6244753301143646, |
| "num_tokens": 1210303.0, |
| "step": 625 |
| }, |
| { |
| "epoch": 0.7894073139974779, |
| "grad_norm": 4.651197910308838, |
| "learning_rate": 3.768844221105528e-06, |
| "loss": 1.3909, |
| "mean_token_accuracy": 0.6095870137214661, |
| "num_tokens": 1212284.0, |
| "step": 626 |
| }, |
| { |
| "epoch": 0.7906683480453972, |
| "grad_norm": 4.659881591796875, |
| "learning_rate": 3.7587939698492466e-06, |
| "loss": 1.4808, |
| "mean_token_accuracy": 0.5926066935062408, |
| "num_tokens": 1214147.0, |
| "step": 627 |
| }, |
| { |
| "epoch": 0.7919293820933165, |
| "grad_norm": 4.688325881958008, |
| "learning_rate": 3.748743718592965e-06, |
| "loss": 1.4284, |
| "mean_token_accuracy": 0.6090951859951019, |
| "num_tokens": 1216040.0, |
| "step": 628 |
| }, |
| { |
| "epoch": 0.7931904161412359, |
| "grad_norm": 4.855409622192383, |
| "learning_rate": 3.7386934673366837e-06, |
| "loss": 1.5242, |
| "mean_token_accuracy": 0.582084596157074, |
| "num_tokens": 1217799.0, |
| "step": 629 |
| }, |
| { |
| "epoch": 0.7944514501891551, |
| "grad_norm": 4.540473937988281, |
| "learning_rate": 3.7286432160804027e-06, |
| "loss": 1.3878, |
| "mean_token_accuracy": 0.5953293144702911, |
| "num_tokens": 1219712.0, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.7957124842370744, |
| "grad_norm": 4.534702301025391, |
| "learning_rate": 3.718592964824121e-06, |
| "loss": 1.3955, |
| "mean_token_accuracy": 0.6180699467658997, |
| "num_tokens": 1221652.0, |
| "step": 631 |
| }, |
| { |
| "epoch": 0.7969735182849937, |
| "grad_norm": 4.40645694732666, |
| "learning_rate": 3.7085427135678394e-06, |
| "loss": 1.4383, |
| "mean_token_accuracy": 0.6130342781543732, |
| "num_tokens": 1223575.0, |
| "step": 632 |
| }, |
| { |
| "epoch": 0.798234552332913, |
| "grad_norm": 4.6681623458862305, |
| "learning_rate": 3.698492462311558e-06, |
| "loss": 1.427, |
| "mean_token_accuracy": 0.5881649851799011, |
| "num_tokens": 1225561.0, |
| "step": 633 |
| }, |
| { |
| "epoch": 0.7994955863808323, |
| "grad_norm": 4.4728474617004395, |
| "learning_rate": 3.6884422110552766e-06, |
| "loss": 1.4221, |
| "mean_token_accuracy": 0.6145466864109039, |
| "num_tokens": 1227379.0, |
| "step": 634 |
| }, |
| { |
| "epoch": 0.8007566204287516, |
| "grad_norm": 4.362063884735107, |
| "learning_rate": 3.678391959798995e-06, |
| "loss": 1.4629, |
| "mean_token_accuracy": 0.5976041853427887, |
| "num_tokens": 1229400.0, |
| "step": 635 |
| }, |
| { |
| "epoch": 0.8020176544766708, |
| "grad_norm": 4.435058116912842, |
| "learning_rate": 3.6683417085427137e-06, |
| "loss": 1.5734, |
| "mean_token_accuracy": 0.5893145501613617, |
| "num_tokens": 1231403.0, |
| "step": 636 |
| }, |
| { |
| "epoch": 0.8032786885245902, |
| "grad_norm": 4.274704456329346, |
| "learning_rate": 3.6582914572864327e-06, |
| "loss": 1.4007, |
| "mean_token_accuracy": 0.6151903867721558, |
| "num_tokens": 1233353.0, |
| "step": 637 |
| }, |
| { |
| "epoch": 0.8045397225725095, |
| "grad_norm": 4.3847975730896, |
| "learning_rate": 3.648241206030151e-06, |
| "loss": 1.3496, |
| "mean_token_accuracy": 0.6147129237651825, |
| "num_tokens": 1235288.0, |
| "step": 638 |
| }, |
| { |
| "epoch": 0.8058007566204287, |
| "grad_norm": 4.745240688323975, |
| "learning_rate": 3.63819095477387e-06, |
| "loss": 1.5088, |
| "mean_token_accuracy": 0.5913102626800537, |
| "num_tokens": 1237251.0, |
| "step": 639 |
| }, |
| { |
| "epoch": 0.807061790668348, |
| "grad_norm": 4.760833740234375, |
| "learning_rate": 3.628140703517588e-06, |
| "loss": 1.4202, |
| "mean_token_accuracy": 0.6121359467506409, |
| "num_tokens": 1239082.0, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.8083228247162674, |
| "grad_norm": 4.281674861907959, |
| "learning_rate": 3.618090452261307e-06, |
| "loss": 1.3884, |
| "mean_token_accuracy": 0.6337145864963531, |
| "num_tokens": 1241059.0, |
| "step": 641 |
| }, |
| { |
| "epoch": 0.8095838587641866, |
| "grad_norm": 4.366747856140137, |
| "learning_rate": 3.608040201005025e-06, |
| "loss": 1.3475, |
| "mean_token_accuracy": 0.6259979605674744, |
| "num_tokens": 1242914.0, |
| "step": 642 |
| }, |
| { |
| "epoch": 0.8108448928121059, |
| "grad_norm": 4.431673526763916, |
| "learning_rate": 3.597989949748744e-06, |
| "loss": 1.5013, |
| "mean_token_accuracy": 0.5821367800235748, |
| "num_tokens": 1244902.0, |
| "step": 643 |
| }, |
| { |
| "epoch": 0.8121059268600253, |
| "grad_norm": 4.428189754486084, |
| "learning_rate": 3.5879396984924626e-06, |
| "loss": 1.4184, |
| "mean_token_accuracy": 0.6101392805576324, |
| "num_tokens": 1246868.0, |
| "step": 644 |
| }, |
| { |
| "epoch": 0.8133669609079445, |
| "grad_norm": 4.415472507476807, |
| "learning_rate": 3.577889447236181e-06, |
| "loss": 1.4531, |
| "mean_token_accuracy": 0.6098997592926025, |
| "num_tokens": 1248753.0, |
| "step": 645 |
| }, |
| { |
| "epoch": 0.8146279949558638, |
| "grad_norm": 4.518283843994141, |
| "learning_rate": 3.5678391959798997e-06, |
| "loss": 1.4393, |
| "mean_token_accuracy": 0.6256670653820038, |
| "num_tokens": 1250582.0, |
| "step": 646 |
| }, |
| { |
| "epoch": 0.8158890290037831, |
| "grad_norm": 4.306365489959717, |
| "learning_rate": 3.5577889447236187e-06, |
| "loss": 1.5138, |
| "mean_token_accuracy": 0.5980395376682281, |
| "num_tokens": 1252644.0, |
| "step": 647 |
| }, |
| { |
| "epoch": 0.8171500630517023, |
| "grad_norm": 5.037056922912598, |
| "learning_rate": 3.547738693467337e-06, |
| "loss": 1.5757, |
| "mean_token_accuracy": 0.5927419364452362, |
| "num_tokens": 1254494.0, |
| "step": 648 |
| }, |
| { |
| "epoch": 0.8184110970996217, |
| "grad_norm": 4.363806247711182, |
| "learning_rate": 3.537688442211056e-06, |
| "loss": 1.452, |
| "mean_token_accuracy": 0.6023588478565216, |
| "num_tokens": 1256495.0, |
| "step": 649 |
| }, |
| { |
| "epoch": 0.819672131147541, |
| "grad_norm": 4.607044696807861, |
| "learning_rate": 3.527638190954774e-06, |
| "loss": 1.4529, |
| "mean_token_accuracy": 0.6298587918281555, |
| "num_tokens": 1258309.0, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.8209331651954602, |
| "grad_norm": 4.5787482261657715, |
| "learning_rate": 3.517587939698493e-06, |
| "loss": 1.4734, |
| "mean_token_accuracy": 0.6061556339263916, |
| "num_tokens": 1260298.0, |
| "step": 651 |
| }, |
| { |
| "epoch": 0.8221941992433796, |
| "grad_norm": 4.130124568939209, |
| "learning_rate": 3.507537688442211e-06, |
| "loss": 1.3836, |
| "mean_token_accuracy": 0.6267567276954651, |
| "num_tokens": 1262427.0, |
| "step": 652 |
| }, |
| { |
| "epoch": 0.8234552332912989, |
| "grad_norm": 4.490095615386963, |
| "learning_rate": 3.49748743718593e-06, |
| "loss": 1.3904, |
| "mean_token_accuracy": 0.6128627061843872, |
| "num_tokens": 1264349.0, |
| "step": 653 |
| }, |
| { |
| "epoch": 0.8247162673392182, |
| "grad_norm": 4.538565635681152, |
| "learning_rate": 3.4874371859296487e-06, |
| "loss": 1.4888, |
| "mean_token_accuracy": 0.6063677072525024, |
| "num_tokens": 1266212.0, |
| "step": 654 |
| }, |
| { |
| "epoch": 0.8259773013871374, |
| "grad_norm": 4.711320877075195, |
| "learning_rate": 3.477386934673367e-06, |
| "loss": 1.5548, |
| "mean_token_accuracy": 0.59187251329422, |
| "num_tokens": 1267999.0, |
| "step": 655 |
| }, |
| { |
| "epoch": 0.8272383354350568, |
| "grad_norm": 4.422387599945068, |
| "learning_rate": 3.467336683417086e-06, |
| "loss": 1.3466, |
| "mean_token_accuracy": 0.6210170686244965, |
| "num_tokens": 1269937.0, |
| "step": 656 |
| }, |
| { |
| "epoch": 0.8284993694829761, |
| "grad_norm": 4.336258888244629, |
| "learning_rate": 3.457286432160804e-06, |
| "loss": 1.3277, |
| "mean_token_accuracy": 0.629963606595993, |
| "num_tokens": 1271810.0, |
| "step": 657 |
| }, |
| { |
| "epoch": 0.8297604035308953, |
| "grad_norm": 4.430080413818359, |
| "learning_rate": 3.447236180904523e-06, |
| "loss": 1.4157, |
| "mean_token_accuracy": 0.6269070208072662, |
| "num_tokens": 1273694.0, |
| "step": 658 |
| }, |
| { |
| "epoch": 0.8310214375788146, |
| "grad_norm": 4.436978816986084, |
| "learning_rate": 3.437185929648241e-06, |
| "loss": 1.4499, |
| "mean_token_accuracy": 0.6197161674499512, |
| "num_tokens": 1275670.0, |
| "step": 659 |
| }, |
| { |
| "epoch": 0.832282471626734, |
| "grad_norm": 4.394755840301514, |
| "learning_rate": 3.42713567839196e-06, |
| "loss": 1.5152, |
| "mean_token_accuracy": 0.6004717350006104, |
| "num_tokens": 1277686.0, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.8335435056746532, |
| "grad_norm": 4.80107307434082, |
| "learning_rate": 3.4170854271356786e-06, |
| "loss": 1.6007, |
| "mean_token_accuracy": 0.574835330247879, |
| "num_tokens": 1279613.0, |
| "step": 661 |
| }, |
| { |
| "epoch": 0.8348045397225725, |
| "grad_norm": 4.431844234466553, |
| "learning_rate": 3.407035175879397e-06, |
| "loss": 1.4222, |
| "mean_token_accuracy": 0.6128553450107574, |
| "num_tokens": 1281595.0, |
| "step": 662 |
| }, |
| { |
| "epoch": 0.8360655737704918, |
| "grad_norm": 4.554701328277588, |
| "learning_rate": 3.3969849246231158e-06, |
| "loss": 1.301, |
| "mean_token_accuracy": 0.6317387223243713, |
| "num_tokens": 1283596.0, |
| "step": 663 |
| }, |
| { |
| "epoch": 0.8373266078184111, |
| "grad_norm": 4.815081596374512, |
| "learning_rate": 3.3869346733668347e-06, |
| "loss": 1.5612, |
| "mean_token_accuracy": 0.5957655310630798, |
| "num_tokens": 1285528.0, |
| "step": 664 |
| }, |
| { |
| "epoch": 0.8385876418663304, |
| "grad_norm": 4.433903694152832, |
| "learning_rate": 3.376884422110553e-06, |
| "loss": 1.3869, |
| "mean_token_accuracy": 0.6024475693702698, |
| "num_tokens": 1287456.0, |
| "step": 665 |
| }, |
| { |
| "epoch": 0.8398486759142497, |
| "grad_norm": 4.512532711029053, |
| "learning_rate": 3.366834170854272e-06, |
| "loss": 1.3795, |
| "mean_token_accuracy": 0.630597710609436, |
| "num_tokens": 1289330.0, |
| "step": 666 |
| }, |
| { |
| "epoch": 0.8411097099621689, |
| "grad_norm": 4.5717854499816895, |
| "learning_rate": 3.35678391959799e-06, |
| "loss": 1.455, |
| "mean_token_accuracy": 0.6052423119544983, |
| "num_tokens": 1291142.0, |
| "step": 667 |
| }, |
| { |
| "epoch": 0.8423707440100883, |
| "grad_norm": 4.499806880950928, |
| "learning_rate": 3.346733668341709e-06, |
| "loss": 1.3583, |
| "mean_token_accuracy": 0.6096299588680267, |
| "num_tokens": 1293029.0, |
| "step": 668 |
| }, |
| { |
| "epoch": 0.8436317780580076, |
| "grad_norm": 4.7041473388671875, |
| "learning_rate": 3.336683417085427e-06, |
| "loss": 1.393, |
| "mean_token_accuracy": 0.6280495524406433, |
| "num_tokens": 1294847.0, |
| "step": 669 |
| }, |
| { |
| "epoch": 0.8448928121059268, |
| "grad_norm": 4.718618869781494, |
| "learning_rate": 3.326633165829146e-06, |
| "loss": 1.5803, |
| "mean_token_accuracy": 0.589573085308075, |
| "num_tokens": 1296756.0, |
| "step": 670 |
| }, |
| { |
| "epoch": 0.8461538461538461, |
| "grad_norm": 4.51429557800293, |
| "learning_rate": 3.3165829145728647e-06, |
| "loss": 1.5713, |
| "mean_token_accuracy": 0.5885864496231079, |
| "num_tokens": 1298728.0, |
| "step": 671 |
| }, |
| { |
| "epoch": 0.8474148802017655, |
| "grad_norm": 5.319494724273682, |
| "learning_rate": 3.3065326633165833e-06, |
| "loss": 1.6109, |
| "mean_token_accuracy": 0.5749770998954773, |
| "num_tokens": 1300535.0, |
| "step": 672 |
| }, |
| { |
| "epoch": 0.8486759142496847, |
| "grad_norm": 4.48340368270874, |
| "learning_rate": 3.296482412060302e-06, |
| "loss": 1.5013, |
| "mean_token_accuracy": 0.5988208651542664, |
| "num_tokens": 1302597.0, |
| "step": 673 |
| }, |
| { |
| "epoch": 0.849936948297604, |
| "grad_norm": 4.54470157623291, |
| "learning_rate": 3.286432160804021e-06, |
| "loss": 1.4674, |
| "mean_token_accuracy": 0.6040069758892059, |
| "num_tokens": 1304445.0, |
| "step": 674 |
| }, |
| { |
| "epoch": 0.8511979823455234, |
| "grad_norm": 4.200180530548096, |
| "learning_rate": 3.276381909547739e-06, |
| "loss": 1.4606, |
| "mean_token_accuracy": 0.59771728515625, |
| "num_tokens": 1306592.0, |
| "step": 675 |
| }, |
| { |
| "epoch": 0.8524590163934426, |
| "grad_norm": 4.604515552520752, |
| "learning_rate": 3.266331658291458e-06, |
| "loss": 1.3684, |
| "mean_token_accuracy": 0.6281431317329407, |
| "num_tokens": 1308472.0, |
| "step": 676 |
| }, |
| { |
| "epoch": 0.8537200504413619, |
| "grad_norm": 4.382105350494385, |
| "learning_rate": 3.256281407035176e-06, |
| "loss": 1.3825, |
| "mean_token_accuracy": 0.6295027732849121, |
| "num_tokens": 1310610.0, |
| "step": 677 |
| }, |
| { |
| "epoch": 0.8549810844892812, |
| "grad_norm": 4.814754486083984, |
| "learning_rate": 3.2462311557788946e-06, |
| "loss": 1.5009, |
| "mean_token_accuracy": 0.6055155396461487, |
| "num_tokens": 1312453.0, |
| "step": 678 |
| }, |
| { |
| "epoch": 0.8562421185372006, |
| "grad_norm": 4.793276786804199, |
| "learning_rate": 3.236180904522613e-06, |
| "loss": 1.3342, |
| "mean_token_accuracy": 0.6250176429748535, |
| "num_tokens": 1314212.0, |
| "step": 679 |
| }, |
| { |
| "epoch": 0.8575031525851198, |
| "grad_norm": 4.565577507019043, |
| "learning_rate": 3.2261306532663318e-06, |
| "loss": 1.5052, |
| "mean_token_accuracy": 0.5999468564987183, |
| "num_tokens": 1316074.0, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.8587641866330391, |
| "grad_norm": 4.617696285247803, |
| "learning_rate": 3.2160804020100507e-06, |
| "loss": 1.474, |
| "mean_token_accuracy": 0.6138873398303986, |
| "num_tokens": 1317957.0, |
| "step": 681 |
| }, |
| { |
| "epoch": 0.8600252206809584, |
| "grad_norm": 4.252396106719971, |
| "learning_rate": 3.206030150753769e-06, |
| "loss": 1.3459, |
| "mean_token_accuracy": 0.6233983039855957, |
| "num_tokens": 1319929.0, |
| "step": 682 |
| }, |
| { |
| "epoch": 0.8612862547288777, |
| "grad_norm": 4.807640552520752, |
| "learning_rate": 3.195979899497488e-06, |
| "loss": 1.5199, |
| "mean_token_accuracy": 0.5885966122150421, |
| "num_tokens": 1321796.0, |
| "step": 683 |
| }, |
| { |
| "epoch": 0.862547288776797, |
| "grad_norm": 4.889383792877197, |
| "learning_rate": 3.185929648241206e-06, |
| "loss": 1.5128, |
| "mean_token_accuracy": 0.5876397490501404, |
| "num_tokens": 1323666.0, |
| "step": 684 |
| }, |
| { |
| "epoch": 0.8638083228247163, |
| "grad_norm": 4.820505142211914, |
| "learning_rate": 3.175879396984925e-06, |
| "loss": 1.5802, |
| "mean_token_accuracy": 0.58903369307518, |
| "num_tokens": 1325573.0, |
| "step": 685 |
| }, |
| { |
| "epoch": 0.8650693568726355, |
| "grad_norm": 4.336293697357178, |
| "learning_rate": 3.165829145728643e-06, |
| "loss": 1.3696, |
| "mean_token_accuracy": 0.6184759736061096, |
| "num_tokens": 1327590.0, |
| "step": 686 |
| }, |
| { |
| "epoch": 0.8663303909205549, |
| "grad_norm": 4.746899604797363, |
| "learning_rate": 3.155778894472362e-06, |
| "loss": 1.5816, |
| "mean_token_accuracy": 0.5919223725795746, |
| "num_tokens": 1329387.0, |
| "step": 687 |
| }, |
| { |
| "epoch": 0.8675914249684742, |
| "grad_norm": 4.493013381958008, |
| "learning_rate": 3.1457286432160807e-06, |
| "loss": 1.2895, |
| "mean_token_accuracy": 0.6384941339492798, |
| "num_tokens": 1331261.0, |
| "step": 688 |
| }, |
| { |
| "epoch": 0.8688524590163934, |
| "grad_norm": 4.692387580871582, |
| "learning_rate": 3.1356783919597993e-06, |
| "loss": 1.3633, |
| "mean_token_accuracy": 0.6215213239192963, |
| "num_tokens": 1333061.0, |
| "step": 689 |
| }, |
| { |
| "epoch": 0.8701134930643127, |
| "grad_norm": 4.2351460456848145, |
| "learning_rate": 3.125628140703518e-06, |
| "loss": 1.3547, |
| "mean_token_accuracy": 0.6269940733909607, |
| "num_tokens": 1334999.0, |
| "step": 690 |
| }, |
| { |
| "epoch": 0.8713745271122321, |
| "grad_norm": 4.679457187652588, |
| "learning_rate": 3.115577889447237e-06, |
| "loss": 1.4769, |
| "mean_token_accuracy": 0.597771018743515, |
| "num_tokens": 1336957.0, |
| "step": 691 |
| }, |
| { |
| "epoch": 0.8726355611601513, |
| "grad_norm": 4.976491928100586, |
| "learning_rate": 3.105527638190955e-06, |
| "loss": 1.4483, |
| "mean_token_accuracy": 0.5990459024906158, |
| "num_tokens": 1338814.0, |
| "step": 692 |
| }, |
| { |
| "epoch": 0.8738965952080706, |
| "grad_norm": 4.698354721069336, |
| "learning_rate": 3.095477386934674e-06, |
| "loss": 1.5794, |
| "mean_token_accuracy": 0.5691917240619659, |
| "num_tokens": 1340791.0, |
| "step": 693 |
| }, |
| { |
| "epoch": 0.8751576292559899, |
| "grad_norm": 4.409573554992676, |
| "learning_rate": 3.085427135678392e-06, |
| "loss": 1.335, |
| "mean_token_accuracy": 0.6246625781059265, |
| "num_tokens": 1342748.0, |
| "step": 694 |
| }, |
| { |
| "epoch": 0.8764186633039092, |
| "grad_norm": 4.804214954376221, |
| "learning_rate": 3.075376884422111e-06, |
| "loss": 1.4505, |
| "mean_token_accuracy": 0.6022706627845764, |
| "num_tokens": 1344647.0, |
| "step": 695 |
| }, |
| { |
| "epoch": 0.8776796973518285, |
| "grad_norm": 4.49189567565918, |
| "learning_rate": 3.065326633165829e-06, |
| "loss": 1.36, |
| "mean_token_accuracy": 0.6258461177349091, |
| "num_tokens": 1346581.0, |
| "step": 696 |
| }, |
| { |
| "epoch": 0.8789407313997478, |
| "grad_norm": 4.685361862182617, |
| "learning_rate": 3.055276381909548e-06, |
| "loss": 1.4595, |
| "mean_token_accuracy": 0.6182919144630432, |
| "num_tokens": 1348444.0, |
| "step": 697 |
| }, |
| { |
| "epoch": 0.880201765447667, |
| "grad_norm": 4.615530967712402, |
| "learning_rate": 3.0452261306532668e-06, |
| "loss": 1.2957, |
| "mean_token_accuracy": 0.6101522147655487, |
| "num_tokens": 1350314.0, |
| "step": 698 |
| }, |
| { |
| "epoch": 0.8814627994955864, |
| "grad_norm": 5.159006595611572, |
| "learning_rate": 3.0351758793969853e-06, |
| "loss": 1.5901, |
| "mean_token_accuracy": 0.5731832981109619, |
| "num_tokens": 1352111.0, |
| "step": 699 |
| }, |
| { |
| "epoch": 0.8827238335435057, |
| "grad_norm": 4.202300071716309, |
| "learning_rate": 3.025125628140704e-06, |
| "loss": 1.4044, |
| "mean_token_accuracy": 0.6054458022117615, |
| "num_tokens": 1354114.0, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.8839848675914249, |
| "grad_norm": 5.155057907104492, |
| "learning_rate": 3.015075376884422e-06, |
| "loss": 1.5627, |
| "mean_token_accuracy": 0.5730942487716675, |
| "num_tokens": 1356043.0, |
| "step": 701 |
| }, |
| { |
| "epoch": 0.8852459016393442, |
| "grad_norm": 4.509034156799316, |
| "learning_rate": 3.005025125628141e-06, |
| "loss": 1.4089, |
| "mean_token_accuracy": 0.6151978075504303, |
| "num_tokens": 1358118.0, |
| "step": 702 |
| }, |
| { |
| "epoch": 0.8865069356872636, |
| "grad_norm": 4.847167491912842, |
| "learning_rate": 2.994974874371859e-06, |
| "loss": 1.4613, |
| "mean_token_accuracy": 0.6082049012184143, |
| "num_tokens": 1360003.0, |
| "step": 703 |
| }, |
| { |
| "epoch": 0.8877679697351829, |
| "grad_norm": 4.529287338256836, |
| "learning_rate": 2.984924623115578e-06, |
| "loss": 1.4005, |
| "mean_token_accuracy": 0.6232767403125763, |
| "num_tokens": 1361950.0, |
| "step": 704 |
| }, |
| { |
| "epoch": 0.8890290037831021, |
| "grad_norm": 4.487297058105469, |
| "learning_rate": 2.9748743718592967e-06, |
| "loss": 1.3502, |
| "mean_token_accuracy": 0.6181976497173309, |
| "num_tokens": 1364018.0, |
| "step": 705 |
| }, |
| { |
| "epoch": 0.8902900378310215, |
| "grad_norm": 5.078628063201904, |
| "learning_rate": 2.9648241206030153e-06, |
| "loss": 1.5075, |
| "mean_token_accuracy": 0.5930404663085938, |
| "num_tokens": 1365836.0, |
| "step": 706 |
| }, |
| { |
| "epoch": 0.8915510718789408, |
| "grad_norm": 4.510313987731934, |
| "learning_rate": 2.954773869346734e-06, |
| "loss": 1.3429, |
| "mean_token_accuracy": 0.6260442435741425, |
| "num_tokens": 1367764.0, |
| "step": 707 |
| }, |
| { |
| "epoch": 0.89281210592686, |
| "grad_norm": 4.804049015045166, |
| "learning_rate": 2.9447236180904524e-06, |
| "loss": 1.5816, |
| "mean_token_accuracy": 0.5857201814651489, |
| "num_tokens": 1369711.0, |
| "step": 708 |
| }, |
| { |
| "epoch": 0.8940731399747793, |
| "grad_norm": 5.134244918823242, |
| "learning_rate": 2.934673366834171e-06, |
| "loss": 1.4602, |
| "mean_token_accuracy": 0.5985281467437744, |
| "num_tokens": 1371602.0, |
| "step": 709 |
| }, |
| { |
| "epoch": 0.8953341740226987, |
| "grad_norm": 4.867412567138672, |
| "learning_rate": 2.92462311557789e-06, |
| "loss": 1.4093, |
| "mean_token_accuracy": 0.6199544668197632, |
| "num_tokens": 1373503.0, |
| "step": 710 |
| }, |
| { |
| "epoch": 0.8965952080706179, |
| "grad_norm": 4.599572658538818, |
| "learning_rate": 2.914572864321608e-06, |
| "loss": 1.4213, |
| "mean_token_accuracy": 0.6173719167709351, |
| "num_tokens": 1375473.0, |
| "step": 711 |
| }, |
| { |
| "epoch": 0.8978562421185372, |
| "grad_norm": 4.485718250274658, |
| "learning_rate": 2.904522613065327e-06, |
| "loss": 1.3855, |
| "mean_token_accuracy": 0.6124942898750305, |
| "num_tokens": 1377487.0, |
| "step": 712 |
| }, |
| { |
| "epoch": 0.8991172761664565, |
| "grad_norm": 4.551990032196045, |
| "learning_rate": 2.894472361809045e-06, |
| "loss": 1.2479, |
| "mean_token_accuracy": 0.6429057419300079, |
| "num_tokens": 1379357.0, |
| "step": 713 |
| }, |
| { |
| "epoch": 0.9003783102143758, |
| "grad_norm": 4.8430352210998535, |
| "learning_rate": 2.884422110552764e-06, |
| "loss": 1.3304, |
| "mean_token_accuracy": 0.647765189409256, |
| "num_tokens": 1381137.0, |
| "step": 714 |
| }, |
| { |
| "epoch": 0.9016393442622951, |
| "grad_norm": 4.718348503112793, |
| "learning_rate": 2.8743718592964828e-06, |
| "loss": 1.4785, |
| "mean_token_accuracy": 0.5891905426979065, |
| "num_tokens": 1383021.0, |
| "step": 715 |
| }, |
| { |
| "epoch": 0.9029003783102144, |
| "grad_norm": 4.648007392883301, |
| "learning_rate": 2.8643216080402013e-06, |
| "loss": 1.3729, |
| "mean_token_accuracy": 0.6156680881977081, |
| "num_tokens": 1384944.0, |
| "step": 716 |
| }, |
| { |
| "epoch": 0.9041614123581336, |
| "grad_norm": 4.859986305236816, |
| "learning_rate": 2.85427135678392e-06, |
| "loss": 1.4065, |
| "mean_token_accuracy": 0.6208228170871735, |
| "num_tokens": 1386856.0, |
| "step": 717 |
| }, |
| { |
| "epoch": 0.905422446406053, |
| "grad_norm": 4.757213115692139, |
| "learning_rate": 2.8442211055276384e-06, |
| "loss": 1.4957, |
| "mean_token_accuracy": 0.6022606790065765, |
| "num_tokens": 1388890.0, |
| "step": 718 |
| }, |
| { |
| "epoch": 0.9066834804539723, |
| "grad_norm": 4.622291564941406, |
| "learning_rate": 2.834170854271357e-06, |
| "loss": 1.4246, |
| "mean_token_accuracy": 0.6103483438491821, |
| "num_tokens": 1390911.0, |
| "step": 719 |
| }, |
| { |
| "epoch": 0.9079445145018915, |
| "grad_norm": 4.5715484619140625, |
| "learning_rate": 2.824120603015076e-06, |
| "loss": 1.2987, |
| "mean_token_accuracy": 0.6245031952857971, |
| "num_tokens": 1392827.0, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.9092055485498108, |
| "grad_norm": 4.618542194366455, |
| "learning_rate": 2.814070351758794e-06, |
| "loss": 1.3845, |
| "mean_token_accuracy": 0.610100269317627, |
| "num_tokens": 1394748.0, |
| "step": 721 |
| }, |
| { |
| "epoch": 0.9104665825977302, |
| "grad_norm": 4.695566654205322, |
| "learning_rate": 2.804020100502513e-06, |
| "loss": 1.3981, |
| "mean_token_accuracy": 0.6025079786777496, |
| "num_tokens": 1396738.0, |
| "step": 722 |
| }, |
| { |
| "epoch": 0.9117276166456494, |
| "grad_norm": 4.790529251098633, |
| "learning_rate": 2.7939698492462313e-06, |
| "loss": 1.4573, |
| "mean_token_accuracy": 0.5892115533351898, |
| "num_tokens": 1398750.0, |
| "step": 723 |
| }, |
| { |
| "epoch": 0.9129886506935687, |
| "grad_norm": 4.78794002532959, |
| "learning_rate": 2.78391959798995e-06, |
| "loss": 1.462, |
| "mean_token_accuracy": 0.6218155920505524, |
| "num_tokens": 1400699.0, |
| "step": 724 |
| }, |
| { |
| "epoch": 0.914249684741488, |
| "grad_norm": 4.759215354919434, |
| "learning_rate": 2.7738693467336684e-06, |
| "loss": 1.4259, |
| "mean_token_accuracy": 0.6136111617088318, |
| "num_tokens": 1402645.0, |
| "step": 725 |
| }, |
| { |
| "epoch": 0.9155107187894073, |
| "grad_norm": 4.643594741821289, |
| "learning_rate": 2.763819095477387e-06, |
| "loss": 1.427, |
| "mean_token_accuracy": 0.6215586960315704, |
| "num_tokens": 1404573.0, |
| "step": 726 |
| }, |
| { |
| "epoch": 0.9167717528373266, |
| "grad_norm": 4.983770370483398, |
| "learning_rate": 2.753768844221106e-06, |
| "loss": 1.4837, |
| "mean_token_accuracy": 0.6027411818504333, |
| "num_tokens": 1406370.0, |
| "step": 727 |
| }, |
| { |
| "epoch": 0.9180327868852459, |
| "grad_norm": 4.207434177398682, |
| "learning_rate": 2.743718592964824e-06, |
| "loss": 1.3002, |
| "mean_token_accuracy": 0.6143061518669128, |
| "num_tokens": 1408350.0, |
| "step": 728 |
| }, |
| { |
| "epoch": 0.9192938209331651, |
| "grad_norm": 4.515687465667725, |
| "learning_rate": 2.733668341708543e-06, |
| "loss": 1.35, |
| "mean_token_accuracy": 0.6112845540046692, |
| "num_tokens": 1410230.0, |
| "step": 729 |
| }, |
| { |
| "epoch": 0.9205548549810845, |
| "grad_norm": 4.651388645172119, |
| "learning_rate": 2.723618090452261e-06, |
| "loss": 1.2633, |
| "mean_token_accuracy": 0.662914365530014, |
| "num_tokens": 1412105.0, |
| "step": 730 |
| }, |
| { |
| "epoch": 0.9218158890290038, |
| "grad_norm": 4.572433948516846, |
| "learning_rate": 2.71356783919598e-06, |
| "loss": 1.4194, |
| "mean_token_accuracy": 0.6180647909641266, |
| "num_tokens": 1414080.0, |
| "step": 731 |
| }, |
| { |
| "epoch": 0.9230769230769231, |
| "grad_norm": 4.718845367431641, |
| "learning_rate": 2.7035175879396983e-06, |
| "loss": 1.4143, |
| "mean_token_accuracy": 0.6059090197086334, |
| "num_tokens": 1416061.0, |
| "step": 732 |
| }, |
| { |
| "epoch": 0.9243379571248423, |
| "grad_norm": 4.787539005279541, |
| "learning_rate": 2.6934673366834173e-06, |
| "loss": 1.4048, |
| "mean_token_accuracy": 0.6251717209815979, |
| "num_tokens": 1417916.0, |
| "step": 733 |
| }, |
| { |
| "epoch": 0.9255989911727617, |
| "grad_norm": 4.552307605743408, |
| "learning_rate": 2.683417085427136e-06, |
| "loss": 1.4179, |
| "mean_token_accuracy": 0.6130162477493286, |
| "num_tokens": 1419914.0, |
| "step": 734 |
| }, |
| { |
| "epoch": 0.926860025220681, |
| "grad_norm": 4.877958297729492, |
| "learning_rate": 2.6733668341708545e-06, |
| "loss": 1.4155, |
| "mean_token_accuracy": 0.6053019165992737, |
| "num_tokens": 1421723.0, |
| "step": 735 |
| }, |
| { |
| "epoch": 0.9281210592686002, |
| "grad_norm": 4.281277179718018, |
| "learning_rate": 2.663316582914573e-06, |
| "loss": 1.3621, |
| "mean_token_accuracy": 0.6375770568847656, |
| "num_tokens": 1423771.0, |
| "step": 736 |
| }, |
| { |
| "epoch": 0.9293820933165196, |
| "grad_norm": 4.664444446563721, |
| "learning_rate": 2.653266331658292e-06, |
| "loss": 1.4706, |
| "mean_token_accuracy": 0.6099792718887329, |
| "num_tokens": 1425701.0, |
| "step": 737 |
| }, |
| { |
| "epoch": 0.9306431273644389, |
| "grad_norm": 4.789531707763672, |
| "learning_rate": 2.64321608040201e-06, |
| "loss": 1.4989, |
| "mean_token_accuracy": 0.6028049290180206, |
| "num_tokens": 1427611.0, |
| "step": 738 |
| }, |
| { |
| "epoch": 0.9319041614123581, |
| "grad_norm": 4.176892280578613, |
| "learning_rate": 2.633165829145729e-06, |
| "loss": 1.2358, |
| "mean_token_accuracy": 0.6365175545215607, |
| "num_tokens": 1429695.0, |
| "step": 739 |
| }, |
| { |
| "epoch": 0.9331651954602774, |
| "grad_norm": 4.739315986633301, |
| "learning_rate": 2.6231155778894473e-06, |
| "loss": 1.3257, |
| "mean_token_accuracy": 0.6217921674251556, |
| "num_tokens": 1431842.0, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.9344262295081968, |
| "grad_norm": 4.4287800788879395, |
| "learning_rate": 2.6130653266331663e-06, |
| "loss": 1.2712, |
| "mean_token_accuracy": 0.6399266123771667, |
| "num_tokens": 1433802.0, |
| "step": 741 |
| }, |
| { |
| "epoch": 0.935687263556116, |
| "grad_norm": 4.2787251472473145, |
| "learning_rate": 2.6030150753768844e-06, |
| "loss": 1.3577, |
| "mean_token_accuracy": 0.6182697415351868, |
| "num_tokens": 1435927.0, |
| "step": 742 |
| }, |
| { |
| "epoch": 0.9369482976040353, |
| "grad_norm": 4.666017532348633, |
| "learning_rate": 2.5929648241206034e-06, |
| "loss": 1.4217, |
| "mean_token_accuracy": 0.6318005323410034, |
| "num_tokens": 1437917.0, |
| "step": 743 |
| }, |
| { |
| "epoch": 0.9382093316519546, |
| "grad_norm": 4.566494941711426, |
| "learning_rate": 2.582914572864322e-06, |
| "loss": 1.3476, |
| "mean_token_accuracy": 0.6440158486366272, |
| "num_tokens": 1439816.0, |
| "step": 744 |
| }, |
| { |
| "epoch": 0.9394703656998739, |
| "grad_norm": 4.964987277984619, |
| "learning_rate": 2.5728643216080405e-06, |
| "loss": 1.5741, |
| "mean_token_accuracy": 0.5829296708106995, |
| "num_tokens": 1441693.0, |
| "step": 745 |
| }, |
| { |
| "epoch": 0.9407313997477932, |
| "grad_norm": 4.58892822265625, |
| "learning_rate": 2.562814070351759e-06, |
| "loss": 1.4067, |
| "mean_token_accuracy": 0.6247598826885223, |
| "num_tokens": 1443618.0, |
| "step": 746 |
| }, |
| { |
| "epoch": 0.9419924337957125, |
| "grad_norm": 4.80293083190918, |
| "learning_rate": 2.5527638190954772e-06, |
| "loss": 1.4583, |
| "mean_token_accuracy": 0.5979767441749573, |
| "num_tokens": 1445541.0, |
| "step": 747 |
| }, |
| { |
| "epoch": 0.9432534678436317, |
| "grad_norm": 4.42380952835083, |
| "learning_rate": 2.542713567839196e-06, |
| "loss": 1.3464, |
| "mean_token_accuracy": 0.6280787885189056, |
| "num_tokens": 1447530.0, |
| "step": 748 |
| }, |
| { |
| "epoch": 0.9445145018915511, |
| "grad_norm": 4.366753578186035, |
| "learning_rate": 2.5326633165829143e-06, |
| "loss": 1.2985, |
| "mean_token_accuracy": 0.6283706724643707, |
| "num_tokens": 1449581.0, |
| "step": 749 |
| }, |
| { |
| "epoch": 0.9457755359394704, |
| "grad_norm": 5.115789413452148, |
| "learning_rate": 2.5226130653266333e-06, |
| "loss": 1.468, |
| "mean_token_accuracy": 0.5940811038017273, |
| "num_tokens": 1451352.0, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.9470365699873896, |
| "grad_norm": 5.07560920715332, |
| "learning_rate": 2.512562814070352e-06, |
| "loss": 1.4144, |
| "mean_token_accuracy": 0.6068819165229797, |
| "num_tokens": 1453291.0, |
| "step": 751 |
| }, |
| { |
| "epoch": 0.9482976040353089, |
| "grad_norm": 5.055481910705566, |
| "learning_rate": 2.5025125628140705e-06, |
| "loss": 1.5266, |
| "mean_token_accuracy": 0.5825677812099457, |
| "num_tokens": 1455216.0, |
| "step": 752 |
| }, |
| { |
| "epoch": 0.9495586380832283, |
| "grad_norm": 4.670107364654541, |
| "learning_rate": 2.492462311557789e-06, |
| "loss": 1.3108, |
| "mean_token_accuracy": 0.639474481344223, |
| "num_tokens": 1457181.0, |
| "step": 753 |
| }, |
| { |
| "epoch": 0.9508196721311475, |
| "grad_norm": 5.033635139465332, |
| "learning_rate": 2.482412060301508e-06, |
| "loss": 1.4711, |
| "mean_token_accuracy": 0.6088995933532715, |
| "num_tokens": 1459026.0, |
| "step": 754 |
| }, |
| { |
| "epoch": 0.9520807061790668, |
| "grad_norm": 4.375858783721924, |
| "learning_rate": 2.4723618090452266e-06, |
| "loss": 1.3317, |
| "mean_token_accuracy": 0.632611870765686, |
| "num_tokens": 1461001.0, |
| "step": 755 |
| }, |
| { |
| "epoch": 0.9533417402269861, |
| "grad_norm": 4.497524261474609, |
| "learning_rate": 2.462311557788945e-06, |
| "loss": 1.3779, |
| "mean_token_accuracy": 0.6088739335536957, |
| "num_tokens": 1463014.0, |
| "step": 756 |
| }, |
| { |
| "epoch": 0.9546027742749055, |
| "grad_norm": 5.146448135375977, |
| "learning_rate": 2.4522613065326637e-06, |
| "loss": 1.5071, |
| "mean_token_accuracy": 0.5854723751544952, |
| "num_tokens": 1464864.0, |
| "step": 757 |
| }, |
| { |
| "epoch": 0.9558638083228247, |
| "grad_norm": 4.540935516357422, |
| "learning_rate": 2.4422110552763823e-06, |
| "loss": 1.3522, |
| "mean_token_accuracy": 0.6171889901161194, |
| "num_tokens": 1466795.0, |
| "step": 758 |
| }, |
| { |
| "epoch": 0.957124842370744, |
| "grad_norm": 4.848739147186279, |
| "learning_rate": 2.4321608040201004e-06, |
| "loss": 1.4463, |
| "mean_token_accuracy": 0.5893578827381134, |
| "num_tokens": 1468671.0, |
| "step": 759 |
| }, |
| { |
| "epoch": 0.9583858764186634, |
| "grad_norm": 4.940702438354492, |
| "learning_rate": 2.422110552763819e-06, |
| "loss": 1.427, |
| "mean_token_accuracy": 0.578980565071106, |
| "num_tokens": 1470508.0, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.9596469104665826, |
| "grad_norm": 4.815670490264893, |
| "learning_rate": 2.412060301507538e-06, |
| "loss": 1.3316, |
| "mean_token_accuracy": 0.6391838192939758, |
| "num_tokens": 1472378.0, |
| "step": 761 |
| }, |
| { |
| "epoch": 0.9609079445145019, |
| "grad_norm": 4.629350185394287, |
| "learning_rate": 2.4020100502512565e-06, |
| "loss": 1.4238, |
| "mean_token_accuracy": 0.6231440901756287, |
| "num_tokens": 1474409.0, |
| "step": 762 |
| }, |
| { |
| "epoch": 0.9621689785624212, |
| "grad_norm": 5.507829666137695, |
| "learning_rate": 2.391959798994975e-06, |
| "loss": 1.625, |
| "mean_token_accuracy": 0.5813977718353271, |
| "num_tokens": 1476222.0, |
| "step": 763 |
| }, |
| { |
| "epoch": 0.9634300126103404, |
| "grad_norm": 4.723374843597412, |
| "learning_rate": 2.3819095477386936e-06, |
| "loss": 1.3546, |
| "mean_token_accuracy": 0.6329129934310913, |
| "num_tokens": 1478087.0, |
| "step": 764 |
| }, |
| { |
| "epoch": 0.9646910466582598, |
| "grad_norm": 4.788589954376221, |
| "learning_rate": 2.371859296482412e-06, |
| "loss": 1.4588, |
| "mean_token_accuracy": 0.6007176041603088, |
| "num_tokens": 1479994.0, |
| "step": 765 |
| }, |
| { |
| "epoch": 0.9659520807061791, |
| "grad_norm": 4.644597053527832, |
| "learning_rate": 2.3618090452261308e-06, |
| "loss": 1.3886, |
| "mean_token_accuracy": 0.6195676028728485, |
| "num_tokens": 1481926.0, |
| "step": 766 |
| }, |
| { |
| "epoch": 0.9672131147540983, |
| "grad_norm": 4.900524616241455, |
| "learning_rate": 2.3517587939698493e-06, |
| "loss": 1.5086, |
| "mean_token_accuracy": 0.5896070003509521, |
| "num_tokens": 1483763.0, |
| "step": 767 |
| }, |
| { |
| "epoch": 0.9684741488020177, |
| "grad_norm": 4.506715774536133, |
| "learning_rate": 2.341708542713568e-06, |
| "loss": 1.3994, |
| "mean_token_accuracy": 0.6048212349414825, |
| "num_tokens": 1485638.0, |
| "step": 768 |
| }, |
| { |
| "epoch": 0.969735182849937, |
| "grad_norm": 4.923521518707275, |
| "learning_rate": 2.3316582914572865e-06, |
| "loss": 1.4353, |
| "mean_token_accuracy": 0.6291594505310059, |
| "num_tokens": 1487423.0, |
| "step": 769 |
| }, |
| { |
| "epoch": 0.9709962168978562, |
| "grad_norm": 4.444231986999512, |
| "learning_rate": 2.321608040201005e-06, |
| "loss": 1.3988, |
| "mean_token_accuracy": 0.6323827803134918, |
| "num_tokens": 1489443.0, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.9722572509457755, |
| "grad_norm": 4.672366142272949, |
| "learning_rate": 2.311557788944724e-06, |
| "loss": 1.5099, |
| "mean_token_accuracy": 0.5915838181972504, |
| "num_tokens": 1491513.0, |
| "step": 771 |
| }, |
| { |
| "epoch": 0.9735182849936949, |
| "grad_norm": 4.950202465057373, |
| "learning_rate": 2.3015075376884426e-06, |
| "loss": 1.3394, |
| "mean_token_accuracy": 0.6242406666278839, |
| "num_tokens": 1493366.0, |
| "step": 772 |
| }, |
| { |
| "epoch": 0.9747793190416141, |
| "grad_norm": 4.696926116943359, |
| "learning_rate": 2.291457286432161e-06, |
| "loss": 1.388, |
| "mean_token_accuracy": 0.6303937137126923, |
| "num_tokens": 1495258.0, |
| "step": 773 |
| }, |
| { |
| "epoch": 0.9760403530895334, |
| "grad_norm": 4.909535884857178, |
| "learning_rate": 2.2814070351758797e-06, |
| "loss": 1.465, |
| "mean_token_accuracy": 0.5960476994514465, |
| "num_tokens": 1497097.0, |
| "step": 774 |
| }, |
| { |
| "epoch": 0.9773013871374527, |
| "grad_norm": 4.92638635635376, |
| "learning_rate": 2.2713567839195983e-06, |
| "loss": 1.598, |
| "mean_token_accuracy": 0.5790300369262695, |
| "num_tokens": 1499002.0, |
| "step": 775 |
| }, |
| { |
| "epoch": 0.978562421185372, |
| "grad_norm": 5.75028133392334, |
| "learning_rate": 2.261306532663317e-06, |
| "loss": 1.6262, |
| "mean_token_accuracy": 0.5684725046157837, |
| "num_tokens": 1500739.0, |
| "step": 776 |
| }, |
| { |
| "epoch": 0.9798234552332913, |
| "grad_norm": 4.659389972686768, |
| "learning_rate": 2.2512562814070354e-06, |
| "loss": 1.4997, |
| "mean_token_accuracy": 0.6040664911270142, |
| "num_tokens": 1502766.0, |
| "step": 777 |
| }, |
| { |
| "epoch": 0.9810844892812106, |
| "grad_norm": 4.826159954071045, |
| "learning_rate": 2.241206030150754e-06, |
| "loss": 1.3497, |
| "mean_token_accuracy": 0.6199261844158173, |
| "num_tokens": 1504543.0, |
| "step": 778 |
| }, |
| { |
| "epoch": 0.9823455233291298, |
| "grad_norm": 4.797970771789551, |
| "learning_rate": 2.2311557788944725e-06, |
| "loss": 1.4605, |
| "mean_token_accuracy": 0.6027579307556152, |
| "num_tokens": 1506581.0, |
| "step": 779 |
| }, |
| { |
| "epoch": 0.9836065573770492, |
| "grad_norm": 5.0854291915893555, |
| "learning_rate": 2.221105527638191e-06, |
| "loss": 1.4007, |
| "mean_token_accuracy": 0.6198207437992096, |
| "num_tokens": 1508414.0, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.9848675914249685, |
| "grad_norm": 4.761533260345459, |
| "learning_rate": 2.21105527638191e-06, |
| "loss": 1.3869, |
| "mean_token_accuracy": 0.6144894063472748, |
| "num_tokens": 1510323.0, |
| "step": 781 |
| }, |
| { |
| "epoch": 0.9861286254728878, |
| "grad_norm": 4.917034149169922, |
| "learning_rate": 2.2010050251256282e-06, |
| "loss": 1.5707, |
| "mean_token_accuracy": 0.5760520994663239, |
| "num_tokens": 1512444.0, |
| "step": 782 |
| }, |
| { |
| "epoch": 0.987389659520807, |
| "grad_norm": 4.831483364105225, |
| "learning_rate": 2.1909547738693468e-06, |
| "loss": 1.376, |
| "mean_token_accuracy": 0.603929340839386, |
| "num_tokens": 1514339.0, |
| "step": 783 |
| }, |
| { |
| "epoch": 0.9886506935687264, |
| "grad_norm": 4.954286098480225, |
| "learning_rate": 2.1809045226130653e-06, |
| "loss": 1.5463, |
| "mean_token_accuracy": 0.5951487720012665, |
| "num_tokens": 1516264.0, |
| "step": 784 |
| }, |
| { |
| "epoch": 0.9899117276166457, |
| "grad_norm": 5.119381904602051, |
| "learning_rate": 2.170854271356784e-06, |
| "loss": 1.4713, |
| "mean_token_accuracy": 0.5979754626750946, |
| "num_tokens": 1518121.0, |
| "step": 785 |
| }, |
| { |
| "epoch": 0.9911727616645649, |
| "grad_norm": 4.790980339050293, |
| "learning_rate": 2.1608040201005025e-06, |
| "loss": 1.3491, |
| "mean_token_accuracy": 0.6425934433937073, |
| "num_tokens": 1519948.0, |
| "step": 786 |
| }, |
| { |
| "epoch": 0.9924337957124842, |
| "grad_norm": 4.7805495262146, |
| "learning_rate": 2.150753768844221e-06, |
| "loss": 1.2154, |
| "mean_token_accuracy": 0.6537107527256012, |
| "num_tokens": 1521854.0, |
| "step": 787 |
| }, |
| { |
| "epoch": 0.9936948297604036, |
| "grad_norm": 4.60954475402832, |
| "learning_rate": 2.14070351758794e-06, |
| "loss": 1.2991, |
| "mean_token_accuracy": 0.6362617313861847, |
| "num_tokens": 1523793.0, |
| "step": 788 |
| }, |
| { |
| "epoch": 0.9949558638083228, |
| "grad_norm": 4.655366897583008, |
| "learning_rate": 2.1306532663316586e-06, |
| "loss": 1.3924, |
| "mean_token_accuracy": 0.6305295526981354, |
| "num_tokens": 1525902.0, |
| "step": 789 |
| }, |
| { |
| "epoch": 0.9962168978562421, |
| "grad_norm": 5.052053451538086, |
| "learning_rate": 2.120603015075377e-06, |
| "loss": 1.392, |
| "mean_token_accuracy": 0.6316825747489929, |
| "num_tokens": 1527769.0, |
| "step": 790 |
| }, |
| { |
| "epoch": 0.9974779319041615, |
| "grad_norm": 4.823788166046143, |
| "learning_rate": 2.1105527638190957e-06, |
| "loss": 1.5008, |
| "mean_token_accuracy": 0.5882376730442047, |
| "num_tokens": 1530004.0, |
| "step": 791 |
| }, |
| { |
| "epoch": 0.9987389659520807, |
| "grad_norm": 5.215896129608154, |
| "learning_rate": 2.1005025125628143e-06, |
| "loss": 1.4967, |
| "mean_token_accuracy": 0.6016424000263214, |
| "num_tokens": 1531801.0, |
| "step": 792 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 5.053985595703125, |
| "learning_rate": 2.090452261306533e-06, |
| "loss": 1.4931, |
| "mean_token_accuracy": 0.6124192774295807, |
| "num_tokens": 1533640.0, |
| "step": 793 |
| }, |
| { |
| "epoch": 1.0012610340479193, |
| "grad_norm": 4.859620094299316, |
| "learning_rate": 2.0804020100502514e-06, |
| "loss": 1.4346, |
| "mean_token_accuracy": 0.6008819937705994, |
| "num_tokens": 1535732.0, |
| "step": 794 |
| }, |
| { |
| "epoch": 1.0025220680958387, |
| "grad_norm": 4.924972057342529, |
| "learning_rate": 2.07035175879397e-06, |
| "loss": 1.3304, |
| "mean_token_accuracy": 0.6425945162773132, |
| "num_tokens": 1537619.0, |
| "step": 795 |
| }, |
| { |
| "epoch": 1.003783102143758, |
| "grad_norm": 4.552638053894043, |
| "learning_rate": 2.0603015075376885e-06, |
| "loss": 1.4359, |
| "mean_token_accuracy": 0.6067358255386353, |
| "num_tokens": 1539634.0, |
| "step": 796 |
| }, |
| { |
| "epoch": 1.005044136191677, |
| "grad_norm": 5.06874418258667, |
| "learning_rate": 2.050251256281407e-06, |
| "loss": 1.5327, |
| "mean_token_accuracy": 0.6117250621318817, |
| "num_tokens": 1541468.0, |
| "step": 797 |
| }, |
| { |
| "epoch": 1.0063051702395964, |
| "grad_norm": 5.16888427734375, |
| "learning_rate": 2.0402010050251257e-06, |
| "loss": 1.4799, |
| "mean_token_accuracy": 0.615227073431015, |
| "num_tokens": 1543264.0, |
| "step": 798 |
| }, |
| { |
| "epoch": 1.0075662042875158, |
| "grad_norm": 4.693305969238281, |
| "learning_rate": 2.0301507537688446e-06, |
| "loss": 1.2996, |
| "mean_token_accuracy": 0.6404381990432739, |
| "num_tokens": 1545137.0, |
| "step": 799 |
| }, |
| { |
| "epoch": 1.008827238335435, |
| "grad_norm": 4.820840835571289, |
| "learning_rate": 2.020100502512563e-06, |
| "loss": 1.4245, |
| "mean_token_accuracy": 0.6199676990509033, |
| "num_tokens": 1547213.0, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.0100882723833544, |
| "grad_norm": 5.359424591064453, |
| "learning_rate": 2.0100502512562818e-06, |
| "loss": 1.5496, |
| "mean_token_accuracy": 0.5789197981357574, |
| "num_tokens": 1548973.0, |
| "step": 801 |
| }, |
| { |
| "epoch": 1.0113493064312737, |
| "grad_norm": 5.1563262939453125, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 1.4537, |
| "mean_token_accuracy": 0.5936600565910339, |
| "num_tokens": 1550755.0, |
| "step": 802 |
| }, |
| { |
| "epoch": 1.0126103404791928, |
| "grad_norm": 4.531444072723389, |
| "learning_rate": 1.989949748743719e-06, |
| "loss": 1.2974, |
| "mean_token_accuracy": 0.6466964781284332, |
| "num_tokens": 1552830.0, |
| "step": 803 |
| }, |
| { |
| "epoch": 1.0138713745271122, |
| "grad_norm": 4.835750579833984, |
| "learning_rate": 1.9798994974874375e-06, |
| "loss": 1.477, |
| "mean_token_accuracy": 0.5901938676834106, |
| "num_tokens": 1554850.0, |
| "step": 804 |
| }, |
| { |
| "epoch": 1.0151324085750315, |
| "grad_norm": 4.399245262145996, |
| "learning_rate": 1.9698492462311556e-06, |
| "loss": 1.4017, |
| "mean_token_accuracy": 0.626316249370575, |
| "num_tokens": 1556904.0, |
| "step": 805 |
| }, |
| { |
| "epoch": 1.0163934426229508, |
| "grad_norm": 5.141709327697754, |
| "learning_rate": 1.9597989949748746e-06, |
| "loss": 1.3327, |
| "mean_token_accuracy": 0.6160070896148682, |
| "num_tokens": 1558816.0, |
| "step": 806 |
| }, |
| { |
| "epoch": 1.0176544766708702, |
| "grad_norm": 4.775214672088623, |
| "learning_rate": 1.949748743718593e-06, |
| "loss": 1.3999, |
| "mean_token_accuracy": 0.6168196499347687, |
| "num_tokens": 1560702.0, |
| "step": 807 |
| }, |
| { |
| "epoch": 1.0189155107187895, |
| "grad_norm": 5.105827331542969, |
| "learning_rate": 1.9396984924623117e-06, |
| "loss": 1.4751, |
| "mean_token_accuracy": 0.6149435937404633, |
| "num_tokens": 1562529.0, |
| "step": 808 |
| }, |
| { |
| "epoch": 1.0201765447667086, |
| "grad_norm": 4.85412073135376, |
| "learning_rate": 1.9296482412060303e-06, |
| "loss": 1.3805, |
| "mean_token_accuracy": 0.6386726498603821, |
| "num_tokens": 1564418.0, |
| "step": 809 |
| }, |
| { |
| "epoch": 1.021437578814628, |
| "grad_norm": 4.5922064781188965, |
| "learning_rate": 1.919597989949749e-06, |
| "loss": 1.404, |
| "mean_token_accuracy": 0.6304318010807037, |
| "num_tokens": 1566411.0, |
| "step": 810 |
| }, |
| { |
| "epoch": 1.0226986128625473, |
| "grad_norm": 4.626622676849365, |
| "learning_rate": 1.9095477386934674e-06, |
| "loss": 1.2757, |
| "mean_token_accuracy": 0.6312589943408966, |
| "num_tokens": 1568268.0, |
| "step": 811 |
| }, |
| { |
| "epoch": 1.0239596469104666, |
| "grad_norm": 4.924299716949463, |
| "learning_rate": 1.899497487437186e-06, |
| "loss": 1.4809, |
| "mean_token_accuracy": 0.5968372523784637, |
| "num_tokens": 1570241.0, |
| "step": 812 |
| }, |
| { |
| "epoch": 1.025220680958386, |
| "grad_norm": 4.954929828643799, |
| "learning_rate": 1.8894472361809047e-06, |
| "loss": 1.4648, |
| "mean_token_accuracy": 0.5949355065822601, |
| "num_tokens": 1572138.0, |
| "step": 813 |
| }, |
| { |
| "epoch": 1.0264817150063053, |
| "grad_norm": 4.762870788574219, |
| "learning_rate": 1.8793969849246233e-06, |
| "loss": 1.3555, |
| "mean_token_accuracy": 0.6090791821479797, |
| "num_tokens": 1574119.0, |
| "step": 814 |
| }, |
| { |
| "epoch": 1.0277427490542244, |
| "grad_norm": 4.991880893707275, |
| "learning_rate": 1.8693467336683419e-06, |
| "loss": 1.5048, |
| "mean_token_accuracy": 0.5935323536396027, |
| "num_tokens": 1576022.0, |
| "step": 815 |
| }, |
| { |
| "epoch": 1.0290037831021437, |
| "grad_norm": 4.592222213745117, |
| "learning_rate": 1.8592964824120604e-06, |
| "loss": 1.3832, |
| "mean_token_accuracy": 0.6328803896903992, |
| "num_tokens": 1578031.0, |
| "step": 816 |
| }, |
| { |
| "epoch": 1.030264817150063, |
| "grad_norm": 4.974219799041748, |
| "learning_rate": 1.849246231155779e-06, |
| "loss": 1.4417, |
| "mean_token_accuracy": 0.6144815683364868, |
| "num_tokens": 1579953.0, |
| "step": 817 |
| }, |
| { |
| "epoch": 1.0315258511979823, |
| "grad_norm": 4.911769390106201, |
| "learning_rate": 1.8391959798994976e-06, |
| "loss": 1.3348, |
| "mean_token_accuracy": 0.6101964116096497, |
| "num_tokens": 1581942.0, |
| "step": 818 |
| }, |
| { |
| "epoch": 1.0327868852459017, |
| "grad_norm": 4.82524299621582, |
| "learning_rate": 1.8291457286432163e-06, |
| "loss": 1.4193, |
| "mean_token_accuracy": 0.6024172008037567, |
| "num_tokens": 1583802.0, |
| "step": 819 |
| }, |
| { |
| "epoch": 1.034047919293821, |
| "grad_norm": 5.037111282348633, |
| "learning_rate": 1.819095477386935e-06, |
| "loss": 1.4243, |
| "mean_token_accuracy": 0.5954607129096985, |
| "num_tokens": 1585699.0, |
| "step": 820 |
| }, |
| { |
| "epoch": 1.0353089533417403, |
| "grad_norm": 5.0072174072265625, |
| "learning_rate": 1.8090452261306535e-06, |
| "loss": 1.5389, |
| "mean_token_accuracy": 0.5851928889751434, |
| "num_tokens": 1587730.0, |
| "step": 821 |
| }, |
| { |
| "epoch": 1.0365699873896594, |
| "grad_norm": 5.133855819702148, |
| "learning_rate": 1.798994974874372e-06, |
| "loss": 1.4712, |
| "mean_token_accuracy": 0.604417622089386, |
| "num_tokens": 1589520.0, |
| "step": 822 |
| }, |
| { |
| "epoch": 1.0378310214375788, |
| "grad_norm": 4.941107749938965, |
| "learning_rate": 1.7889447236180906e-06, |
| "loss": 1.2498, |
| "mean_token_accuracy": 0.6343302428722382, |
| "num_tokens": 1591363.0, |
| "step": 823 |
| }, |
| { |
| "epoch": 1.039092055485498, |
| "grad_norm": 4.669431209564209, |
| "learning_rate": 1.7788944723618094e-06, |
| "loss": 1.4315, |
| "mean_token_accuracy": 0.6125501692295074, |
| "num_tokens": 1593345.0, |
| "step": 824 |
| }, |
| { |
| "epoch": 1.0403530895334174, |
| "grad_norm": 4.921899795532227, |
| "learning_rate": 1.768844221105528e-06, |
| "loss": 1.4912, |
| "mean_token_accuracy": 0.6139432787895203, |
| "num_tokens": 1595264.0, |
| "step": 825 |
| }, |
| { |
| "epoch": 1.0416141235813368, |
| "grad_norm": 4.989323616027832, |
| "learning_rate": 1.7587939698492465e-06, |
| "loss": 1.4128, |
| "mean_token_accuracy": 0.6252074241638184, |
| "num_tokens": 1597177.0, |
| "step": 826 |
| }, |
| { |
| "epoch": 1.042875157629256, |
| "grad_norm": 4.729038238525391, |
| "learning_rate": 1.748743718592965e-06, |
| "loss": 1.3916, |
| "mean_token_accuracy": 0.6020833551883698, |
| "num_tokens": 1599154.0, |
| "step": 827 |
| }, |
| { |
| "epoch": 1.0441361916771752, |
| "grad_norm": 5.2605299949646, |
| "learning_rate": 1.7386934673366834e-06, |
| "loss": 1.451, |
| "mean_token_accuracy": 0.6022846102714539, |
| "num_tokens": 1600975.0, |
| "step": 828 |
| }, |
| { |
| "epoch": 1.0453972257250945, |
| "grad_norm": 4.817141056060791, |
| "learning_rate": 1.728643216080402e-06, |
| "loss": 1.3798, |
| "mean_token_accuracy": 0.6150883734226227, |
| "num_tokens": 1602854.0, |
| "step": 829 |
| }, |
| { |
| "epoch": 1.0466582597730139, |
| "grad_norm": 4.8491106033325195, |
| "learning_rate": 1.7185929648241205e-06, |
| "loss": 1.364, |
| "mean_token_accuracy": 0.6204774081707001, |
| "num_tokens": 1604765.0, |
| "step": 830 |
| }, |
| { |
| "epoch": 1.0479192938209332, |
| "grad_norm": 4.595874309539795, |
| "learning_rate": 1.7085427135678393e-06, |
| "loss": 1.4007, |
| "mean_token_accuracy": 0.6227355897426605, |
| "num_tokens": 1606739.0, |
| "step": 831 |
| }, |
| { |
| "epoch": 1.0491803278688525, |
| "grad_norm": 5.359395980834961, |
| "learning_rate": 1.6984924623115579e-06, |
| "loss": 1.5305, |
| "mean_token_accuracy": 0.5770443975925446, |
| "num_tokens": 1608545.0, |
| "step": 832 |
| }, |
| { |
| "epoch": 1.0504413619167718, |
| "grad_norm": 4.606545925140381, |
| "learning_rate": 1.6884422110552764e-06, |
| "loss": 1.3824, |
| "mean_token_accuracy": 0.6272301375865936, |
| "num_tokens": 1610675.0, |
| "step": 833 |
| }, |
| { |
| "epoch": 1.051702395964691, |
| "grad_norm": 4.8444719314575195, |
| "learning_rate": 1.678391959798995e-06, |
| "loss": 1.4138, |
| "mean_token_accuracy": 0.6037014126777649, |
| "num_tokens": 1612584.0, |
| "step": 834 |
| }, |
| { |
| "epoch": 1.0529634300126103, |
| "grad_norm": 5.316982746124268, |
| "learning_rate": 1.6683417085427136e-06, |
| "loss": 1.4045, |
| "mean_token_accuracy": 0.5941404402256012, |
| "num_tokens": 1614490.0, |
| "step": 835 |
| }, |
| { |
| "epoch": 1.0542244640605296, |
| "grad_norm": 4.479865550994873, |
| "learning_rate": 1.6582914572864323e-06, |
| "loss": 1.1823, |
| "mean_token_accuracy": 0.657404899597168, |
| "num_tokens": 1616480.0, |
| "step": 836 |
| }, |
| { |
| "epoch": 1.055485498108449, |
| "grad_norm": 5.054855823516846, |
| "learning_rate": 1.648241206030151e-06, |
| "loss": 1.4334, |
| "mean_token_accuracy": 0.6027690470218658, |
| "num_tokens": 1618429.0, |
| "step": 837 |
| }, |
| { |
| "epoch": 1.0567465321563683, |
| "grad_norm": 4.986600875854492, |
| "learning_rate": 1.6381909547738695e-06, |
| "loss": 1.4179, |
| "mean_token_accuracy": 0.6209523677825928, |
| "num_tokens": 1620432.0, |
| "step": 838 |
| }, |
| { |
| "epoch": 1.0580075662042876, |
| "grad_norm": 5.486791610717773, |
| "learning_rate": 1.628140703517588e-06, |
| "loss": 1.511, |
| "mean_token_accuracy": 0.6114962697029114, |
| "num_tokens": 1622308.0, |
| "step": 839 |
| }, |
| { |
| "epoch": 1.0592686002522067, |
| "grad_norm": 4.979884147644043, |
| "learning_rate": 1.6180904522613066e-06, |
| "loss": 1.4186, |
| "mean_token_accuracy": 0.6098051369190216, |
| "num_tokens": 1624344.0, |
| "step": 840 |
| }, |
| { |
| "epoch": 1.060529634300126, |
| "grad_norm": 5.088829517364502, |
| "learning_rate": 1.6080402010050254e-06, |
| "loss": 1.4596, |
| "mean_token_accuracy": 0.5979678332805634, |
| "num_tokens": 1626206.0, |
| "step": 841 |
| }, |
| { |
| "epoch": 1.0617906683480454, |
| "grad_norm": 4.898533344268799, |
| "learning_rate": 1.597989949748744e-06, |
| "loss": 1.3975, |
| "mean_token_accuracy": 0.6214229166507721, |
| "num_tokens": 1628109.0, |
| "step": 842 |
| }, |
| { |
| "epoch": 1.0630517023959647, |
| "grad_norm": 4.962382793426514, |
| "learning_rate": 1.5879396984924625e-06, |
| "loss": 1.3319, |
| "mean_token_accuracy": 0.6575819253921509, |
| "num_tokens": 1629969.0, |
| "step": 843 |
| }, |
| { |
| "epoch": 1.064312736443884, |
| "grad_norm": 5.184306621551514, |
| "learning_rate": 1.577889447236181e-06, |
| "loss": 1.4438, |
| "mean_token_accuracy": 0.5859068334102631, |
| "num_tokens": 1631913.0, |
| "step": 844 |
| }, |
| { |
| "epoch": 1.0655737704918034, |
| "grad_norm": 5.116397857666016, |
| "learning_rate": 1.5678391959798996e-06, |
| "loss": 1.3804, |
| "mean_token_accuracy": 0.6171029508113861, |
| "num_tokens": 1633748.0, |
| "step": 845 |
| }, |
| { |
| "epoch": 1.0668348045397225, |
| "grad_norm": 5.0195722579956055, |
| "learning_rate": 1.5577889447236184e-06, |
| "loss": 1.2668, |
| "mean_token_accuracy": 0.6535399854183197, |
| "num_tokens": 1635488.0, |
| "step": 846 |
| }, |
| { |
| "epoch": 1.0680958385876418, |
| "grad_norm": 4.750542640686035, |
| "learning_rate": 1.547738693467337e-06, |
| "loss": 1.2745, |
| "mean_token_accuracy": 0.6426283717155457, |
| "num_tokens": 1637407.0, |
| "step": 847 |
| }, |
| { |
| "epoch": 1.0693568726355611, |
| "grad_norm": 5.365578651428223, |
| "learning_rate": 1.5376884422110555e-06, |
| "loss": 1.5784, |
| "mean_token_accuracy": 0.5733594000339508, |
| "num_tokens": 1639147.0, |
| "step": 848 |
| }, |
| { |
| "epoch": 1.0706179066834804, |
| "grad_norm": 5.130395412445068, |
| "learning_rate": 1.527638190954774e-06, |
| "loss": 1.4151, |
| "mean_token_accuracy": 0.621956080198288, |
| "num_tokens": 1640943.0, |
| "step": 849 |
| }, |
| { |
| "epoch": 1.0718789407313998, |
| "grad_norm": 5.161646842956543, |
| "learning_rate": 1.5175879396984927e-06, |
| "loss": 1.3837, |
| "mean_token_accuracy": 0.6152097582817078, |
| "num_tokens": 1642812.0, |
| "step": 850 |
| }, |
| { |
| "epoch": 1.073139974779319, |
| "grad_norm": 4.936598777770996, |
| "learning_rate": 1.507537688442211e-06, |
| "loss": 1.3275, |
| "mean_token_accuracy": 0.6371041238307953, |
| "num_tokens": 1644634.0, |
| "step": 851 |
| }, |
| { |
| "epoch": 1.0744010088272384, |
| "grad_norm": 5.145509243011475, |
| "learning_rate": 1.4974874371859296e-06, |
| "loss": 1.5006, |
| "mean_token_accuracy": 0.5886007249355316, |
| "num_tokens": 1646412.0, |
| "step": 852 |
| }, |
| { |
| "epoch": 1.0756620428751575, |
| "grad_norm": 4.668916702270508, |
| "learning_rate": 1.4874371859296483e-06, |
| "loss": 1.3728, |
| "mean_token_accuracy": 0.6374690234661102, |
| "num_tokens": 1648357.0, |
| "step": 853 |
| }, |
| { |
| "epoch": 1.0769230769230769, |
| "grad_norm": 5.067697525024414, |
| "learning_rate": 1.477386934673367e-06, |
| "loss": 1.3785, |
| "mean_token_accuracy": 0.616924911737442, |
| "num_tokens": 1650296.0, |
| "step": 854 |
| }, |
| { |
| "epoch": 1.0781841109709962, |
| "grad_norm": 4.902146816253662, |
| "learning_rate": 1.4673366834170855e-06, |
| "loss": 1.5745, |
| "mean_token_accuracy": 0.5848622024059296, |
| "num_tokens": 1652305.0, |
| "step": 855 |
| }, |
| { |
| "epoch": 1.0794451450189155, |
| "grad_norm": 4.2945942878723145, |
| "learning_rate": 1.457286432160804e-06, |
| "loss": 1.2442, |
| "mean_token_accuracy": 0.6502452194690704, |
| "num_tokens": 1654462.0, |
| "step": 856 |
| }, |
| { |
| "epoch": 1.0807061790668349, |
| "grad_norm": 5.339733123779297, |
| "learning_rate": 1.4472361809045226e-06, |
| "loss": 1.509, |
| "mean_token_accuracy": 0.5843194723129272, |
| "num_tokens": 1656294.0, |
| "step": 857 |
| }, |
| { |
| "epoch": 1.0819672131147542, |
| "grad_norm": 4.766898155212402, |
| "learning_rate": 1.4371859296482414e-06, |
| "loss": 1.309, |
| "mean_token_accuracy": 0.6335008442401886, |
| "num_tokens": 1658248.0, |
| "step": 858 |
| }, |
| { |
| "epoch": 1.0832282471626733, |
| "grad_norm": 4.7863359451293945, |
| "learning_rate": 1.42713567839196e-06, |
| "loss": 1.3785, |
| "mean_token_accuracy": 0.6025950014591217, |
| "num_tokens": 1660239.0, |
| "step": 859 |
| }, |
| { |
| "epoch": 1.0844892812105926, |
| "grad_norm": 4.966418743133545, |
| "learning_rate": 1.4170854271356785e-06, |
| "loss": 1.5104, |
| "mean_token_accuracy": 0.5946759879589081, |
| "num_tokens": 1662327.0, |
| "step": 860 |
| }, |
| { |
| "epoch": 1.085750315258512, |
| "grad_norm": 4.864983081817627, |
| "learning_rate": 1.407035175879397e-06, |
| "loss": 1.5377, |
| "mean_token_accuracy": 0.6015218496322632, |
| "num_tokens": 1664343.0, |
| "step": 861 |
| }, |
| { |
| "epoch": 1.0870113493064313, |
| "grad_norm": 4.3726654052734375, |
| "learning_rate": 1.3969849246231156e-06, |
| "loss": 1.2715, |
| "mean_token_accuracy": 0.660163015127182, |
| "num_tokens": 1666409.0, |
| "step": 862 |
| }, |
| { |
| "epoch": 1.0882723833543506, |
| "grad_norm": 5.346407890319824, |
| "learning_rate": 1.3869346733668342e-06, |
| "loss": 1.5033, |
| "mean_token_accuracy": 0.5938428044319153, |
| "num_tokens": 1668169.0, |
| "step": 863 |
| }, |
| { |
| "epoch": 1.08953341740227, |
| "grad_norm": 5.046968936920166, |
| "learning_rate": 1.376884422110553e-06, |
| "loss": 1.4499, |
| "mean_token_accuracy": 0.6061795651912689, |
| "num_tokens": 1670117.0, |
| "step": 864 |
| }, |
| { |
| "epoch": 1.090794451450189, |
| "grad_norm": 5.136297702789307, |
| "learning_rate": 1.3668341708542715e-06, |
| "loss": 1.3553, |
| "mean_token_accuracy": 0.6270474493503571, |
| "num_tokens": 1672035.0, |
| "step": 865 |
| }, |
| { |
| "epoch": 1.0920554854981084, |
| "grad_norm": 4.889704704284668, |
| "learning_rate": 1.35678391959799e-06, |
| "loss": 1.4321, |
| "mean_token_accuracy": 0.6256860196590424, |
| "num_tokens": 1673881.0, |
| "step": 866 |
| }, |
| { |
| "epoch": 1.0933165195460277, |
| "grad_norm": 4.772144794464111, |
| "learning_rate": 1.3467336683417087e-06, |
| "loss": 1.2987, |
| "mean_token_accuracy": 0.6305316090583801, |
| "num_tokens": 1675786.0, |
| "step": 867 |
| }, |
| { |
| "epoch": 1.094577553593947, |
| "grad_norm": 4.752320289611816, |
| "learning_rate": 1.3366834170854272e-06, |
| "loss": 1.3301, |
| "mean_token_accuracy": 0.6470165550708771, |
| "num_tokens": 1677834.0, |
| "step": 868 |
| }, |
| { |
| "epoch": 1.0958385876418664, |
| "grad_norm": 5.081295013427734, |
| "learning_rate": 1.326633165829146e-06, |
| "loss": 1.3346, |
| "mean_token_accuracy": 0.6263269782066345, |
| "num_tokens": 1679707.0, |
| "step": 869 |
| }, |
| { |
| "epoch": 1.0970996216897857, |
| "grad_norm": 4.907476902008057, |
| "learning_rate": 1.3165829145728646e-06, |
| "loss": 1.3672, |
| "mean_token_accuracy": 0.6208414137363434, |
| "num_tokens": 1681629.0, |
| "step": 870 |
| }, |
| { |
| "epoch": 1.098360655737705, |
| "grad_norm": 4.639259338378906, |
| "learning_rate": 1.3065326633165831e-06, |
| "loss": 1.295, |
| "mean_token_accuracy": 0.6292709112167358, |
| "num_tokens": 1683723.0, |
| "step": 871 |
| }, |
| { |
| "epoch": 1.0996216897856241, |
| "grad_norm": 5.0603461265563965, |
| "learning_rate": 1.2964824120603017e-06, |
| "loss": 1.3148, |
| "mean_token_accuracy": 0.6325615048408508, |
| "num_tokens": 1685518.0, |
| "step": 872 |
| }, |
| { |
| "epoch": 1.1008827238335435, |
| "grad_norm": 4.925965785980225, |
| "learning_rate": 1.2864321608040203e-06, |
| "loss": 1.4408, |
| "mean_token_accuracy": 0.6115374267101288, |
| "num_tokens": 1687519.0, |
| "step": 873 |
| }, |
| { |
| "epoch": 1.1021437578814628, |
| "grad_norm": 4.810086250305176, |
| "learning_rate": 1.2763819095477386e-06, |
| "loss": 1.2673, |
| "mean_token_accuracy": 0.642699807882309, |
| "num_tokens": 1689596.0, |
| "step": 874 |
| }, |
| { |
| "epoch": 1.1034047919293821, |
| "grad_norm": 5.053249359130859, |
| "learning_rate": 1.2663316582914572e-06, |
| "loss": 1.3439, |
| "mean_token_accuracy": 0.6248357594013214, |
| "num_tokens": 1691524.0, |
| "step": 875 |
| }, |
| { |
| "epoch": 1.1046658259773015, |
| "grad_norm": 4.817336559295654, |
| "learning_rate": 1.256281407035176e-06, |
| "loss": 1.4219, |
| "mean_token_accuracy": 0.62397900223732, |
| "num_tokens": 1693448.0, |
| "step": 876 |
| }, |
| { |
| "epoch": 1.1059268600252208, |
| "grad_norm": 5.001347541809082, |
| "learning_rate": 1.2462311557788945e-06, |
| "loss": 1.5118, |
| "mean_token_accuracy": 0.5976948142051697, |
| "num_tokens": 1695362.0, |
| "step": 877 |
| }, |
| { |
| "epoch": 1.1071878940731399, |
| "grad_norm": 5.020344257354736, |
| "learning_rate": 1.2361809045226133e-06, |
| "loss": 1.4163, |
| "mean_token_accuracy": 0.608789473772049, |
| "num_tokens": 1697349.0, |
| "step": 878 |
| }, |
| { |
| "epoch": 1.1084489281210592, |
| "grad_norm": 4.469849586486816, |
| "learning_rate": 1.2261306532663318e-06, |
| "loss": 1.2971, |
| "mean_token_accuracy": 0.6297315359115601, |
| "num_tokens": 1699484.0, |
| "step": 879 |
| }, |
| { |
| "epoch": 1.1097099621689785, |
| "grad_norm": 5.064508438110352, |
| "learning_rate": 1.2160804020100502e-06, |
| "loss": 1.3802, |
| "mean_token_accuracy": 0.6266240477561951, |
| "num_tokens": 1701370.0, |
| "step": 880 |
| }, |
| { |
| "epoch": 1.1109709962168979, |
| "grad_norm": 5.334554672241211, |
| "learning_rate": 1.206030150753769e-06, |
| "loss": 1.5268, |
| "mean_token_accuracy": 0.590501219034195, |
| "num_tokens": 1703236.0, |
| "step": 881 |
| }, |
| { |
| "epoch": 1.1122320302648172, |
| "grad_norm": 4.9287590980529785, |
| "learning_rate": 1.1959798994974875e-06, |
| "loss": 1.3817, |
| "mean_token_accuracy": 0.6426202356815338, |
| "num_tokens": 1705181.0, |
| "step": 882 |
| }, |
| { |
| "epoch": 1.1134930643127365, |
| "grad_norm": 4.90025520324707, |
| "learning_rate": 1.185929648241206e-06, |
| "loss": 1.3757, |
| "mean_token_accuracy": 0.6233894228935242, |
| "num_tokens": 1707138.0, |
| "step": 883 |
| }, |
| { |
| "epoch": 1.1147540983606556, |
| "grad_norm": 4.745693683624268, |
| "learning_rate": 1.1758793969849247e-06, |
| "loss": 1.3317, |
| "mean_token_accuracy": 0.6354628205299377, |
| "num_tokens": 1709038.0, |
| "step": 884 |
| }, |
| { |
| "epoch": 1.116015132408575, |
| "grad_norm": 4.981682300567627, |
| "learning_rate": 1.1658291457286432e-06, |
| "loss": 1.3259, |
| "mean_token_accuracy": 0.6297134160995483, |
| "num_tokens": 1710879.0, |
| "step": 885 |
| }, |
| { |
| "epoch": 1.1172761664564943, |
| "grad_norm": 5.087985038757324, |
| "learning_rate": 1.155778894472362e-06, |
| "loss": 1.4851, |
| "mean_token_accuracy": 0.5866974294185638, |
| "num_tokens": 1712758.0, |
| "step": 886 |
| }, |
| { |
| "epoch": 1.1185372005044136, |
| "grad_norm": 4.942793846130371, |
| "learning_rate": 1.1457286432160806e-06, |
| "loss": 1.4352, |
| "mean_token_accuracy": 0.5849944055080414, |
| "num_tokens": 1714695.0, |
| "step": 887 |
| }, |
| { |
| "epoch": 1.119798234552333, |
| "grad_norm": 4.774109840393066, |
| "learning_rate": 1.1356783919597991e-06, |
| "loss": 1.4464, |
| "mean_token_accuracy": 0.6079711019992828, |
| "num_tokens": 1716756.0, |
| "step": 888 |
| }, |
| { |
| "epoch": 1.1210592686002523, |
| "grad_norm": 4.673050880432129, |
| "learning_rate": 1.1256281407035177e-06, |
| "loss": 1.2345, |
| "mean_token_accuracy": 0.6406926512718201, |
| "num_tokens": 1718637.0, |
| "step": 889 |
| }, |
| { |
| "epoch": 1.1223203026481714, |
| "grad_norm": 4.597579479217529, |
| "learning_rate": 1.1155778894472363e-06, |
| "loss": 1.2355, |
| "mean_token_accuracy": 0.6603090167045593, |
| "num_tokens": 1720597.0, |
| "step": 890 |
| }, |
| { |
| "epoch": 1.1235813366960907, |
| "grad_norm": 5.344587802886963, |
| "learning_rate": 1.105527638190955e-06, |
| "loss": 1.459, |
| "mean_token_accuracy": 0.6139001846313477, |
| "num_tokens": 1722426.0, |
| "step": 891 |
| }, |
| { |
| "epoch": 1.12484237074401, |
| "grad_norm": 5.077244758605957, |
| "learning_rate": 1.0954773869346734e-06, |
| "loss": 1.4039, |
| "mean_token_accuracy": 0.6174876689910889, |
| "num_tokens": 1724298.0, |
| "step": 892 |
| }, |
| { |
| "epoch": 1.1261034047919294, |
| "grad_norm": 4.649603366851807, |
| "learning_rate": 1.085427135678392e-06, |
| "loss": 1.3202, |
| "mean_token_accuracy": 0.6394246816635132, |
| "num_tokens": 1726155.0, |
| "step": 893 |
| }, |
| { |
| "epoch": 1.1273644388398487, |
| "grad_norm": 4.656422138214111, |
| "learning_rate": 1.0753768844221105e-06, |
| "loss": 1.3173, |
| "mean_token_accuracy": 0.6460046172142029, |
| "num_tokens": 1728121.0, |
| "step": 894 |
| }, |
| { |
| "epoch": 1.128625472887768, |
| "grad_norm": 5.245925426483154, |
| "learning_rate": 1.0653266331658293e-06, |
| "loss": 1.5032, |
| "mean_token_accuracy": 0.6162103414535522, |
| "num_tokens": 1729979.0, |
| "step": 895 |
| }, |
| { |
| "epoch": 1.1298865069356872, |
| "grad_norm": 5.046647548675537, |
| "learning_rate": 1.0552763819095479e-06, |
| "loss": 1.5197, |
| "mean_token_accuracy": 0.5832743048667908, |
| "num_tokens": 1731906.0, |
| "step": 896 |
| }, |
| { |
| "epoch": 1.1311475409836065, |
| "grad_norm": 5.067801475524902, |
| "learning_rate": 1.0452261306532664e-06, |
| "loss": 1.4258, |
| "mean_token_accuracy": 0.6073438227176666, |
| "num_tokens": 1733737.0, |
| "step": 897 |
| }, |
| { |
| "epoch": 1.1324085750315258, |
| "grad_norm": 4.663293361663818, |
| "learning_rate": 1.035175879396985e-06, |
| "loss": 1.3173, |
| "mean_token_accuracy": 0.64065220952034, |
| "num_tokens": 1735752.0, |
| "step": 898 |
| }, |
| { |
| "epoch": 1.1336696090794451, |
| "grad_norm": 5.36110782623291, |
| "learning_rate": 1.0251256281407035e-06, |
| "loss": 1.4858, |
| "mean_token_accuracy": 0.5942147076129913, |
| "num_tokens": 1737597.0, |
| "step": 899 |
| }, |
| { |
| "epoch": 1.1349306431273645, |
| "grad_norm": 5.239461421966553, |
| "learning_rate": 1.0150753768844223e-06, |
| "loss": 1.3483, |
| "mean_token_accuracy": 0.6205393671989441, |
| "num_tokens": 1739348.0, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.1361916771752838, |
| "grad_norm": 5.277314186096191, |
| "learning_rate": 1.0050251256281409e-06, |
| "loss": 1.3441, |
| "mean_token_accuracy": 0.6316133439540863, |
| "num_tokens": 1741230.0, |
| "step": 901 |
| }, |
| { |
| "epoch": 1.1374527112232031, |
| "grad_norm": 5.051476955413818, |
| "learning_rate": 9.949748743718594e-07, |
| "loss": 1.4172, |
| "mean_token_accuracy": 0.6009290218353271, |
| "num_tokens": 1743140.0, |
| "step": 902 |
| }, |
| { |
| "epoch": 1.1387137452711222, |
| "grad_norm": 4.778693199157715, |
| "learning_rate": 9.849246231155778e-07, |
| "loss": 1.3541, |
| "mean_token_accuracy": 0.6240184009075165, |
| "num_tokens": 1745096.0, |
| "step": 903 |
| }, |
| { |
| "epoch": 1.1399747793190416, |
| "grad_norm": 5.342038631439209, |
| "learning_rate": 9.748743718592966e-07, |
| "loss": 1.3844, |
| "mean_token_accuracy": 0.6123272478580475, |
| "num_tokens": 1746956.0, |
| "step": 904 |
| }, |
| { |
| "epoch": 1.141235813366961, |
| "grad_norm": 5.211719989776611, |
| "learning_rate": 9.648241206030151e-07, |
| "loss": 1.4345, |
| "mean_token_accuracy": 0.6103442311286926, |
| "num_tokens": 1748802.0, |
| "step": 905 |
| }, |
| { |
| "epoch": 1.1424968474148802, |
| "grad_norm": 4.845167636871338, |
| "learning_rate": 9.547738693467337e-07, |
| "loss": 1.3347, |
| "mean_token_accuracy": 0.6275226771831512, |
| "num_tokens": 1750816.0, |
| "step": 906 |
| }, |
| { |
| "epoch": 1.1437578814627996, |
| "grad_norm": 4.847137451171875, |
| "learning_rate": 9.447236180904524e-07, |
| "loss": 1.3872, |
| "mean_token_accuracy": 0.61635622382164, |
| "num_tokens": 1752796.0, |
| "step": 907 |
| }, |
| { |
| "epoch": 1.1450189155107189, |
| "grad_norm": 5.0400166511535645, |
| "learning_rate": 9.346733668341709e-07, |
| "loss": 1.449, |
| "mean_token_accuracy": 0.601254791021347, |
| "num_tokens": 1754805.0, |
| "step": 908 |
| }, |
| { |
| "epoch": 1.146279949558638, |
| "grad_norm": 4.840874195098877, |
| "learning_rate": 9.246231155778895e-07, |
| "loss": 1.3805, |
| "mean_token_accuracy": 0.6148854196071625, |
| "num_tokens": 1756877.0, |
| "step": 909 |
| }, |
| { |
| "epoch": 1.1475409836065573, |
| "grad_norm": 5.118767738342285, |
| "learning_rate": 9.145728643216082e-07, |
| "loss": 1.4999, |
| "mean_token_accuracy": 0.5984103679656982, |
| "num_tokens": 1758852.0, |
| "step": 910 |
| }, |
| { |
| "epoch": 1.1488020176544766, |
| "grad_norm": 4.932574272155762, |
| "learning_rate": 9.045226130653267e-07, |
| "loss": 1.4006, |
| "mean_token_accuracy": 0.6041274070739746, |
| "num_tokens": 1760856.0, |
| "step": 911 |
| }, |
| { |
| "epoch": 1.150063051702396, |
| "grad_norm": 4.902439117431641, |
| "learning_rate": 8.944723618090453e-07, |
| "loss": 1.2811, |
| "mean_token_accuracy": 0.6541339159011841, |
| "num_tokens": 1762797.0, |
| "step": 912 |
| }, |
| { |
| "epoch": 1.1513240857503153, |
| "grad_norm": 5.102466106414795, |
| "learning_rate": 8.84422110552764e-07, |
| "loss": 1.4599, |
| "mean_token_accuracy": 0.5948452055454254, |
| "num_tokens": 1764710.0, |
| "step": 913 |
| }, |
| { |
| "epoch": 1.1525851197982346, |
| "grad_norm": 5.040976047515869, |
| "learning_rate": 8.743718592964825e-07, |
| "loss": 1.4398, |
| "mean_token_accuracy": 0.6058560907840729, |
| "num_tokens": 1766649.0, |
| "step": 914 |
| }, |
| { |
| "epoch": 1.1538461538461537, |
| "grad_norm": 4.775660514831543, |
| "learning_rate": 8.64321608040201e-07, |
| "loss": 1.2688, |
| "mean_token_accuracy": 0.6359184980392456, |
| "num_tokens": 1768822.0, |
| "step": 915 |
| }, |
| { |
| "epoch": 1.155107187894073, |
| "grad_norm": 5.1789703369140625, |
| "learning_rate": 8.542713567839197e-07, |
| "loss": 1.4468, |
| "mean_token_accuracy": 0.5935891568660736, |
| "num_tokens": 1770754.0, |
| "step": 916 |
| }, |
| { |
| "epoch": 1.1563682219419924, |
| "grad_norm": 4.609385967254639, |
| "learning_rate": 8.442211055276382e-07, |
| "loss": 1.2928, |
| "mean_token_accuracy": 0.6313645839691162, |
| "num_tokens": 1772740.0, |
| "step": 917 |
| }, |
| { |
| "epoch": 1.1576292559899117, |
| "grad_norm": 5.162957668304443, |
| "learning_rate": 8.341708542713568e-07, |
| "loss": 1.3787, |
| "mean_token_accuracy": 0.6098227500915527, |
| "num_tokens": 1774706.0, |
| "step": 918 |
| }, |
| { |
| "epoch": 1.158890290037831, |
| "grad_norm": 4.727216720581055, |
| "learning_rate": 8.241206030150755e-07, |
| "loss": 1.3411, |
| "mean_token_accuracy": 0.6247797906398773, |
| "num_tokens": 1776761.0, |
| "step": 919 |
| }, |
| { |
| "epoch": 1.1601513240857504, |
| "grad_norm": 5.466963768005371, |
| "learning_rate": 8.14070351758794e-07, |
| "loss": 1.5878, |
| "mean_token_accuracy": 0.5861708521842957, |
| "num_tokens": 1778643.0, |
| "step": 920 |
| }, |
| { |
| "epoch": 1.1614123581336697, |
| "grad_norm": 5.906630516052246, |
| "learning_rate": 8.040201005025127e-07, |
| "loss": 1.628, |
| "mean_token_accuracy": 0.5795406103134155, |
| "num_tokens": 1780398.0, |
| "step": 921 |
| }, |
| { |
| "epoch": 1.1626733921815888, |
| "grad_norm": 4.632744789123535, |
| "learning_rate": 7.939698492462313e-07, |
| "loss": 1.3589, |
| "mean_token_accuracy": 0.6283348500728607, |
| "num_tokens": 1782437.0, |
| "step": 922 |
| }, |
| { |
| "epoch": 1.1639344262295082, |
| "grad_norm": 5.072994232177734, |
| "learning_rate": 7.839195979899498e-07, |
| "loss": 1.3792, |
| "mean_token_accuracy": 0.6125733852386475, |
| "num_tokens": 1784407.0, |
| "step": 923 |
| }, |
| { |
| "epoch": 1.1651954602774275, |
| "grad_norm": 5.171667575836182, |
| "learning_rate": 7.738693467336685e-07, |
| "loss": 1.4334, |
| "mean_token_accuracy": 0.617727667093277, |
| "num_tokens": 1786360.0, |
| "step": 924 |
| }, |
| { |
| "epoch": 1.1664564943253468, |
| "grad_norm": 5.152869701385498, |
| "learning_rate": 7.63819095477387e-07, |
| "loss": 1.4553, |
| "mean_token_accuracy": 0.5993034839630127, |
| "num_tokens": 1788397.0, |
| "step": 925 |
| }, |
| { |
| "epoch": 1.1677175283732661, |
| "grad_norm": 4.626251697540283, |
| "learning_rate": 7.537688442211055e-07, |
| "loss": 1.2551, |
| "mean_token_accuracy": 0.6582286357879639, |
| "num_tokens": 1790522.0, |
| "step": 926 |
| }, |
| { |
| "epoch": 1.1689785624211853, |
| "grad_norm": 4.900967121124268, |
| "learning_rate": 7.437185929648242e-07, |
| "loss": 1.286, |
| "mean_token_accuracy": 0.6288881003856659, |
| "num_tokens": 1792448.0, |
| "step": 927 |
| }, |
| { |
| "epoch": 1.1702395964691046, |
| "grad_norm": 4.809275150299072, |
| "learning_rate": 7.336683417085427e-07, |
| "loss": 1.3884, |
| "mean_token_accuracy": 0.6122523248195648, |
| "num_tokens": 1794566.0, |
| "step": 928 |
| }, |
| { |
| "epoch": 1.171500630517024, |
| "grad_norm": 5.039896488189697, |
| "learning_rate": 7.236180904522613e-07, |
| "loss": 1.3066, |
| "mean_token_accuracy": 0.6312415897846222, |
| "num_tokens": 1796559.0, |
| "step": 929 |
| }, |
| { |
| "epoch": 1.1727616645649432, |
| "grad_norm": 5.1657538414001465, |
| "learning_rate": 7.1356783919598e-07, |
| "loss": 1.5675, |
| "mean_token_accuracy": 0.5969944596290588, |
| "num_tokens": 1798499.0, |
| "step": 930 |
| }, |
| { |
| "epoch": 1.1740226986128626, |
| "grad_norm": 4.674160003662109, |
| "learning_rate": 7.035175879396985e-07, |
| "loss": 1.2363, |
| "mean_token_accuracy": 0.6646978855133057, |
| "num_tokens": 1800436.0, |
| "step": 931 |
| }, |
| { |
| "epoch": 1.175283732660782, |
| "grad_norm": 4.792122840881348, |
| "learning_rate": 6.934673366834171e-07, |
| "loss": 1.3855, |
| "mean_token_accuracy": 0.6197312772274017, |
| "num_tokens": 1802460.0, |
| "step": 932 |
| }, |
| { |
| "epoch": 1.1765447667087012, |
| "grad_norm": 5.117883682250977, |
| "learning_rate": 6.834170854271358e-07, |
| "loss": 1.3949, |
| "mean_token_accuracy": 0.5948143601417542, |
| "num_tokens": 1804295.0, |
| "step": 933 |
| }, |
| { |
| "epoch": 1.1778058007566203, |
| "grad_norm": 5.0117387771606445, |
| "learning_rate": 6.733668341708543e-07, |
| "loss": 1.5329, |
| "mean_token_accuracy": 0.5969884097576141, |
| "num_tokens": 1806314.0, |
| "step": 934 |
| }, |
| { |
| "epoch": 1.1790668348045397, |
| "grad_norm": 4.953305721282959, |
| "learning_rate": 6.63316582914573e-07, |
| "loss": 1.3986, |
| "mean_token_accuracy": 0.6202296614646912, |
| "num_tokens": 1808343.0, |
| "step": 935 |
| }, |
| { |
| "epoch": 1.180327868852459, |
| "grad_norm": 5.259175777435303, |
| "learning_rate": 6.532663316582916e-07, |
| "loss": 1.4476, |
| "mean_token_accuracy": 0.6117253601551056, |
| "num_tokens": 1810135.0, |
| "step": 936 |
| }, |
| { |
| "epoch": 1.1815889029003783, |
| "grad_norm": 4.881397724151611, |
| "learning_rate": 6.432160804020101e-07, |
| "loss": 1.186, |
| "mean_token_accuracy": 0.6482206284999847, |
| "num_tokens": 1812003.0, |
| "step": 937 |
| }, |
| { |
| "epoch": 1.1828499369482977, |
| "grad_norm": 5.129254341125488, |
| "learning_rate": 6.331658291457286e-07, |
| "loss": 1.4479, |
| "mean_token_accuracy": 0.6047539412975311, |
| "num_tokens": 1813913.0, |
| "step": 938 |
| }, |
| { |
| "epoch": 1.184110970996217, |
| "grad_norm": 5.123323917388916, |
| "learning_rate": 6.231155778894473e-07, |
| "loss": 1.4659, |
| "mean_token_accuracy": 0.6227533519268036, |
| "num_tokens": 1815758.0, |
| "step": 939 |
| }, |
| { |
| "epoch": 1.1853720050441363, |
| "grad_norm": 5.076217174530029, |
| "learning_rate": 6.130653266331659e-07, |
| "loss": 1.2311, |
| "mean_token_accuracy": 0.6610271036624908, |
| "num_tokens": 1817639.0, |
| "step": 940 |
| }, |
| { |
| "epoch": 1.1866330390920554, |
| "grad_norm": 5.267666816711426, |
| "learning_rate": 6.030150753768845e-07, |
| "loss": 1.4227, |
| "mean_token_accuracy": 0.6167608201503754, |
| "num_tokens": 1819582.0, |
| "step": 941 |
| }, |
| { |
| "epoch": 1.1878940731399747, |
| "grad_norm": 5.258944034576416, |
| "learning_rate": 5.92964824120603e-07, |
| "loss": 1.4665, |
| "mean_token_accuracy": 0.5967157781124115, |
| "num_tokens": 1821342.0, |
| "step": 942 |
| }, |
| { |
| "epoch": 1.189155107187894, |
| "grad_norm": 5.271570682525635, |
| "learning_rate": 5.829145728643216e-07, |
| "loss": 1.3629, |
| "mean_token_accuracy": 0.6277696192264557, |
| "num_tokens": 1823287.0, |
| "step": 943 |
| }, |
| { |
| "epoch": 1.1904161412358134, |
| "grad_norm": 5.216139793395996, |
| "learning_rate": 5.728643216080403e-07, |
| "loss": 1.4321, |
| "mean_token_accuracy": 0.6034521460533142, |
| "num_tokens": 1825173.0, |
| "step": 944 |
| }, |
| { |
| "epoch": 1.1916771752837327, |
| "grad_norm": 4.663553714752197, |
| "learning_rate": 5.628140703517588e-07, |
| "loss": 1.3356, |
| "mean_token_accuracy": 0.6389399468898773, |
| "num_tokens": 1827152.0, |
| "step": 945 |
| }, |
| { |
| "epoch": 1.1929382093316518, |
| "grad_norm": 5.13004732131958, |
| "learning_rate": 5.527638190954775e-07, |
| "loss": 1.4534, |
| "mean_token_accuracy": 0.6107485592365265, |
| "num_tokens": 1829095.0, |
| "step": 946 |
| }, |
| { |
| "epoch": 1.1941992433795712, |
| "grad_norm": 5.074164390563965, |
| "learning_rate": 5.42713567839196e-07, |
| "loss": 1.4438, |
| "mean_token_accuracy": 0.6243781745433807, |
| "num_tokens": 1830919.0, |
| "step": 947 |
| }, |
| { |
| "epoch": 1.1954602774274905, |
| "grad_norm": 5.084892272949219, |
| "learning_rate": 5.326633165829146e-07, |
| "loss": 1.3777, |
| "mean_token_accuracy": 0.6200196444988251, |
| "num_tokens": 1832886.0, |
| "step": 948 |
| }, |
| { |
| "epoch": 1.1967213114754098, |
| "grad_norm": 5.34892463684082, |
| "learning_rate": 5.226130653266332e-07, |
| "loss": 1.5094, |
| "mean_token_accuracy": 0.586660623550415, |
| "num_tokens": 1834806.0, |
| "step": 949 |
| }, |
| { |
| "epoch": 1.1979823455233292, |
| "grad_norm": 5.087215423583984, |
| "learning_rate": 5.125628140703518e-07, |
| "loss": 1.3344, |
| "mean_token_accuracy": 0.6292024254798889, |
| "num_tokens": 1836645.0, |
| "step": 950 |
| }, |
| { |
| "epoch": 1.1992433795712485, |
| "grad_norm": 5.228329181671143, |
| "learning_rate": 5.025125628140704e-07, |
| "loss": 1.466, |
| "mean_token_accuracy": 0.5961521863937378, |
| "num_tokens": 1838667.0, |
| "step": 951 |
| }, |
| { |
| "epoch": 1.2005044136191678, |
| "grad_norm": 5.482524871826172, |
| "learning_rate": 4.924623115577889e-07, |
| "loss": 1.4509, |
| "mean_token_accuracy": 0.59737628698349, |
| "num_tokens": 1840592.0, |
| "step": 952 |
| }, |
| { |
| "epoch": 1.201765447667087, |
| "grad_norm": 5.0047407150268555, |
| "learning_rate": 4.824120603015076e-07, |
| "loss": 1.5227, |
| "mean_token_accuracy": 0.589676022529602, |
| "num_tokens": 1842572.0, |
| "step": 953 |
| }, |
| { |
| "epoch": 1.2030264817150063, |
| "grad_norm": 5.240270614624023, |
| "learning_rate": 4.723618090452262e-07, |
| "loss": 1.4232, |
| "mean_token_accuracy": 0.602595180273056, |
| "num_tokens": 1844510.0, |
| "step": 954 |
| }, |
| { |
| "epoch": 1.2042875157629256, |
| "grad_norm": 5.139934539794922, |
| "learning_rate": 4.6231155778894475e-07, |
| "loss": 1.3838, |
| "mean_token_accuracy": 0.6217158138751984, |
| "num_tokens": 1846434.0, |
| "step": 955 |
| }, |
| { |
| "epoch": 1.205548549810845, |
| "grad_norm": 5.630468845367432, |
| "learning_rate": 4.5226130653266337e-07, |
| "loss": 1.4834, |
| "mean_token_accuracy": 0.5865810513496399, |
| "num_tokens": 1848310.0, |
| "step": 956 |
| }, |
| { |
| "epoch": 1.2068095838587642, |
| "grad_norm": 4.692196369171143, |
| "learning_rate": 4.42211055276382e-07, |
| "loss": 1.3122, |
| "mean_token_accuracy": 0.6437986791133881, |
| "num_tokens": 1850320.0, |
| "step": 957 |
| }, |
| { |
| "epoch": 1.2080706179066836, |
| "grad_norm": 4.836750507354736, |
| "learning_rate": 4.321608040201005e-07, |
| "loss": 1.4254, |
| "mean_token_accuracy": 0.6103801727294922, |
| "num_tokens": 1852240.0, |
| "step": 958 |
| }, |
| { |
| "epoch": 1.2093316519546027, |
| "grad_norm": 5.327441215515137, |
| "learning_rate": 4.221105527638191e-07, |
| "loss": 1.5109, |
| "mean_token_accuracy": 0.5911853909492493, |
| "num_tokens": 1854188.0, |
| "step": 959 |
| }, |
| { |
| "epoch": 1.210592686002522, |
| "grad_norm": 4.50408935546875, |
| "learning_rate": 4.1206030150753773e-07, |
| "loss": 1.3162, |
| "mean_token_accuracy": 0.6251911222934723, |
| "num_tokens": 1856242.0, |
| "step": 960 |
| }, |
| { |
| "epoch": 1.2118537200504413, |
| "grad_norm": 4.922251224517822, |
| "learning_rate": 4.0201005025125634e-07, |
| "loss": 1.4668, |
| "mean_token_accuracy": 0.6030009984970093, |
| "num_tokens": 1858306.0, |
| "step": 961 |
| }, |
| { |
| "epoch": 1.2131147540983607, |
| "grad_norm": 5.415045738220215, |
| "learning_rate": 3.919597989949749e-07, |
| "loss": 1.4913, |
| "mean_token_accuracy": 0.5978050827980042, |
| "num_tokens": 1860313.0, |
| "step": 962 |
| }, |
| { |
| "epoch": 1.21437578814628, |
| "grad_norm": 5.077240943908691, |
| "learning_rate": 3.819095477386935e-07, |
| "loss": 1.3712, |
| "mean_token_accuracy": 0.6228812038898468, |
| "num_tokens": 1862220.0, |
| "step": 963 |
| }, |
| { |
| "epoch": 1.2156368221941993, |
| "grad_norm": 5.192144870758057, |
| "learning_rate": 3.718592964824121e-07, |
| "loss": 1.3479, |
| "mean_token_accuracy": 0.625325471162796, |
| "num_tokens": 1864092.0, |
| "step": 964 |
| }, |
| { |
| "epoch": 1.2168978562421184, |
| "grad_norm": 4.991547584533691, |
| "learning_rate": 3.6180904522613065e-07, |
| "loss": 1.333, |
| "mean_token_accuracy": 0.6345547437667847, |
| "num_tokens": 1866153.0, |
| "step": 965 |
| }, |
| { |
| "epoch": 1.2181588902900378, |
| "grad_norm": 5.291337490081787, |
| "learning_rate": 3.5175879396984927e-07, |
| "loss": 1.3972, |
| "mean_token_accuracy": 0.6194877922534943, |
| "num_tokens": 1868053.0, |
| "step": 966 |
| }, |
| { |
| "epoch": 1.219419924337957, |
| "grad_norm": 5.237453937530518, |
| "learning_rate": 3.417085427135679e-07, |
| "loss": 1.311, |
| "mean_token_accuracy": 0.6315875053405762, |
| "num_tokens": 1869990.0, |
| "step": 967 |
| }, |
| { |
| "epoch": 1.2206809583858764, |
| "grad_norm": 5.804203987121582, |
| "learning_rate": 3.316582914572865e-07, |
| "loss": 1.4085, |
| "mean_token_accuracy": 0.6040690243244171, |
| "num_tokens": 1871716.0, |
| "step": 968 |
| }, |
| { |
| "epoch": 1.2219419924337958, |
| "grad_norm": 5.937376022338867, |
| "learning_rate": 3.2160804020100506e-07, |
| "loss": 1.5021, |
| "mean_token_accuracy": 0.6007244288921356, |
| "num_tokens": 1873622.0, |
| "step": 969 |
| }, |
| { |
| "epoch": 1.223203026481715, |
| "grad_norm": 5.428589344024658, |
| "learning_rate": 3.1155778894472363e-07, |
| "loss": 1.4529, |
| "mean_token_accuracy": 0.6070205569267273, |
| "num_tokens": 1875500.0, |
| "step": 970 |
| }, |
| { |
| "epoch": 1.2244640605296344, |
| "grad_norm": 5.018257141113281, |
| "learning_rate": 3.0150753768844224e-07, |
| "loss": 1.2837, |
| "mean_token_accuracy": 0.642302542924881, |
| "num_tokens": 1877351.0, |
| "step": 971 |
| }, |
| { |
| "epoch": 1.2257250945775535, |
| "grad_norm": 4.901374816894531, |
| "learning_rate": 2.914572864321608e-07, |
| "loss": 1.3173, |
| "mean_token_accuracy": 0.6497815549373627, |
| "num_tokens": 1879291.0, |
| "step": 972 |
| }, |
| { |
| "epoch": 1.2269861286254728, |
| "grad_norm": 4.900482654571533, |
| "learning_rate": 2.814070351758794e-07, |
| "loss": 1.3306, |
| "mean_token_accuracy": 0.6035780906677246, |
| "num_tokens": 1881288.0, |
| "step": 973 |
| }, |
| { |
| "epoch": 1.2282471626733922, |
| "grad_norm": 4.8116774559021, |
| "learning_rate": 2.71356783919598e-07, |
| "loss": 1.2566, |
| "mean_token_accuracy": 0.6475660502910614, |
| "num_tokens": 1883149.0, |
| "step": 974 |
| }, |
| { |
| "epoch": 1.2295081967213115, |
| "grad_norm": 4.605260848999023, |
| "learning_rate": 2.613065326633166e-07, |
| "loss": 1.414, |
| "mean_token_accuracy": 0.621475875377655, |
| "num_tokens": 1885183.0, |
| "step": 975 |
| }, |
| { |
| "epoch": 1.2307692307692308, |
| "grad_norm": 4.634363651275635, |
| "learning_rate": 2.512562814070352e-07, |
| "loss": 1.3724, |
| "mean_token_accuracy": 0.6205690801143646, |
| "num_tokens": 1887171.0, |
| "step": 976 |
| }, |
| { |
| "epoch": 1.23203026481715, |
| "grad_norm": 5.679710865020752, |
| "learning_rate": 2.412060301507538e-07, |
| "loss": 1.5362, |
| "mean_token_accuracy": 0.5842530131340027, |
| "num_tokens": 1889014.0, |
| "step": 977 |
| }, |
| { |
| "epoch": 1.2332912988650693, |
| "grad_norm": 5.509294509887695, |
| "learning_rate": 2.3115577889447237e-07, |
| "loss": 1.4568, |
| "mean_token_accuracy": 0.6119529604911804, |
| "num_tokens": 1890746.0, |
| "step": 978 |
| }, |
| { |
| "epoch": 1.2345523329129886, |
| "grad_norm": 4.818939208984375, |
| "learning_rate": 2.21105527638191e-07, |
| "loss": 1.212, |
| "mean_token_accuracy": 0.6457622051239014, |
| "num_tokens": 1892570.0, |
| "step": 979 |
| }, |
| { |
| "epoch": 1.235813366960908, |
| "grad_norm": 5.132483959197998, |
| "learning_rate": 2.1105527638190956e-07, |
| "loss": 1.4684, |
| "mean_token_accuracy": 0.6010770797729492, |
| "num_tokens": 1894591.0, |
| "step": 980 |
| }, |
| { |
| "epoch": 1.2370744010088273, |
| "grad_norm": 5.0741167068481445, |
| "learning_rate": 2.0100502512562817e-07, |
| "loss": 1.4341, |
| "mean_token_accuracy": 0.6012249886989594, |
| "num_tokens": 1896483.0, |
| "step": 981 |
| }, |
| { |
| "epoch": 1.2383354350567466, |
| "grad_norm": 5.2892746925354, |
| "learning_rate": 1.9095477386934676e-07, |
| "loss": 1.4243, |
| "mean_token_accuracy": 0.5856616497039795, |
| "num_tokens": 1898341.0, |
| "step": 982 |
| }, |
| { |
| "epoch": 1.239596469104666, |
| "grad_norm": 5.422547817230225, |
| "learning_rate": 1.8090452261306533e-07, |
| "loss": 1.4239, |
| "mean_token_accuracy": 0.6171863377094269, |
| "num_tokens": 1900203.0, |
| "step": 983 |
| }, |
| { |
| "epoch": 1.240857503152585, |
| "grad_norm": 5.478043079376221, |
| "learning_rate": 1.7085427135678394e-07, |
| "loss": 1.5671, |
| "mean_token_accuracy": 0.5849802196025848, |
| "num_tokens": 1902029.0, |
| "step": 984 |
| }, |
| { |
| "epoch": 1.2421185372005044, |
| "grad_norm": 5.046949863433838, |
| "learning_rate": 1.6080402010050253e-07, |
| "loss": 1.4521, |
| "mean_token_accuracy": 0.6011047959327698, |
| "num_tokens": 1903898.0, |
| "step": 985 |
| }, |
| { |
| "epoch": 1.2433795712484237, |
| "grad_norm": 4.796839237213135, |
| "learning_rate": 1.5075376884422112e-07, |
| "loss": 1.3994, |
| "mean_token_accuracy": 0.6067076921463013, |
| "num_tokens": 1905807.0, |
| "step": 986 |
| }, |
| { |
| "epoch": 1.244640605296343, |
| "grad_norm": 5.78264045715332, |
| "learning_rate": 1.407035175879397e-07, |
| "loss": 1.71, |
| "mean_token_accuracy": 0.5604110062122345, |
| "num_tokens": 1907818.0, |
| "step": 987 |
| }, |
| { |
| "epoch": 1.2459016393442623, |
| "grad_norm": 4.714611530303955, |
| "learning_rate": 1.306532663316583e-07, |
| "loss": 1.315, |
| "mean_token_accuracy": 0.6363774240016937, |
| "num_tokens": 1909809.0, |
| "step": 988 |
| }, |
| { |
| "epoch": 1.2471626733921817, |
| "grad_norm": 5.528034210205078, |
| "learning_rate": 1.206030150753769e-07, |
| "loss": 1.5308, |
| "mean_token_accuracy": 0.5902082026004791, |
| "num_tokens": 1911626.0, |
| "step": 989 |
| }, |
| { |
| "epoch": 1.248423707440101, |
| "grad_norm": 5.443125247955322, |
| "learning_rate": 1.105527638190955e-07, |
| "loss": 1.4753, |
| "mean_token_accuracy": 0.6086395978927612, |
| "num_tokens": 1913529.0, |
| "step": 990 |
| }, |
| { |
| "epoch": 1.2496847414880201, |
| "grad_norm": 5.464473247528076, |
| "learning_rate": 1.0050251256281409e-07, |
| "loss": 1.4429, |
| "mean_token_accuracy": 0.6182594001293182, |
| "num_tokens": 1915369.0, |
| "step": 991 |
| }, |
| { |
| "epoch": 1.2509457755359394, |
| "grad_norm": 5.163119316101074, |
| "learning_rate": 9.045226130653266e-08, |
| "loss": 1.3722, |
| "mean_token_accuracy": 0.6328320205211639, |
| "num_tokens": 1917246.0, |
| "step": 992 |
| }, |
| { |
| "epoch": 1.2522068095838588, |
| "grad_norm": 5.1116743087768555, |
| "learning_rate": 8.040201005025127e-08, |
| "loss": 1.4695, |
| "mean_token_accuracy": 0.6038559377193451, |
| "num_tokens": 1919135.0, |
| "step": 993 |
| }, |
| { |
| "epoch": 1.253467843631778, |
| "grad_norm": 5.0618462562561035, |
| "learning_rate": 7.035175879396986e-08, |
| "loss": 1.3716, |
| "mean_token_accuracy": 0.5951160490512848, |
| "num_tokens": 1920964.0, |
| "step": 994 |
| }, |
| { |
| "epoch": 1.2547288776796974, |
| "grad_norm": 4.8035759925842285, |
| "learning_rate": 6.030150753768845e-08, |
| "loss": 1.3621, |
| "mean_token_accuracy": 0.6313849091529846, |
| "num_tokens": 1922859.0, |
| "step": 995 |
| }, |
| { |
| "epoch": 1.2559899117276165, |
| "grad_norm": 4.914729118347168, |
| "learning_rate": 5.025125628140704e-08, |
| "loss": 1.239, |
| "mean_token_accuracy": 0.6349127888679504, |
| "num_tokens": 1924713.0, |
| "step": 996 |
| }, |
| { |
| "epoch": 1.2572509457755359, |
| "grad_norm": 4.952082633972168, |
| "learning_rate": 4.020100502512563e-08, |
| "loss": 1.3765, |
| "mean_token_accuracy": 0.6257254481315613, |
| "num_tokens": 1926640.0, |
| "step": 997 |
| }, |
| { |
| "epoch": 1.2585119798234552, |
| "grad_norm": 5.086965084075928, |
| "learning_rate": 3.015075376884422e-08, |
| "loss": 1.4267, |
| "mean_token_accuracy": 0.6163321137428284, |
| "num_tokens": 1928611.0, |
| "step": 998 |
| }, |
| { |
| "epoch": 1.2597730138713745, |
| "grad_norm": 5.323322296142578, |
| "learning_rate": 2.0100502512562817e-08, |
| "loss": 1.4194, |
| "mean_token_accuracy": 0.6186275482177734, |
| "num_tokens": 1930441.0, |
| "step": 999 |
| }, |
| { |
| "epoch": 1.2610340479192939, |
| "grad_norm": 4.54163932800293, |
| "learning_rate": 1.0050251256281408e-08, |
| "loss": 1.2804, |
| "mean_token_accuracy": 0.6409396231174469, |
| "num_tokens": 1932506.0, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 250, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7.758847907620454e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
