diff --git "a/trainer_state.json" "b/trainer_state.json" new file mode 100644--- /dev/null +++ "b/trainer_state.json" @@ -0,0 +1,42033 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.7995735607675906, + "eval_steps": 500, + "global_step": 6000, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.00013326226012793177, + "grad_norm": 2.855597570850582, + "learning_rate": 2.2172949002217297e-08, + "loss": 0.5459, + "step": 1 + }, + { + "epoch": 0.00026652452025586353, + "grad_norm": 0.37797297695652915, + "learning_rate": 4.4345898004434594e-08, + "loss": 0.4386, + "step": 2 + }, + { + "epoch": 0.0003997867803837953, + "grad_norm": 0.3680524766545551, + "learning_rate": 6.651884700665188e-08, + "loss": 0.4269, + "step": 3 + }, + { + "epoch": 0.0005330490405117271, + "grad_norm": 0.3741007749819736, + "learning_rate": 8.869179600886919e-08, + "loss": 0.4266, + "step": 4 + }, + { + "epoch": 0.0006663113006396588, + "grad_norm": 0.39501823362995725, + "learning_rate": 1.1086474501108649e-07, + "loss": 0.468, + "step": 5 + }, + { + "epoch": 0.0007995735607675906, + "grad_norm": 6.979610864131782, + "learning_rate": 1.3303769401330377e-07, + "loss": 0.514, + "step": 6 + }, + { + "epoch": 0.0009328358208955224, + "grad_norm": 0.38289507107029636, + "learning_rate": 1.5521064301552109e-07, + "loss": 0.4668, + "step": 7 + }, + { + "epoch": 0.0010660980810234541, + "grad_norm": 0.6840942965391579, + "learning_rate": 1.7738359201773838e-07, + "loss": 0.4653, + "step": 8 + }, + { + "epoch": 0.001199360341151386, + "grad_norm": 0.6349309758326671, + "learning_rate": 1.9955654101995567e-07, + "loss": 0.4243, + "step": 9 + }, + { + "epoch": 0.0013326226012793177, + "grad_norm": 0.4343338038257737, + "learning_rate": 2.2172949002217298e-07, + "loss": 0.4643, + "step": 10 + }, + { + "epoch": 0.0014658848614072495, + "grad_norm": 0.5372645612178816, + "learning_rate": 2.439024390243903e-07, + "loss": 0.4124, + "step": 11 + }, + { + "epoch": 0.0015991471215351812, + "grad_norm": 0.3501276368818081, + "learning_rate": 2.6607538802660754e-07, + "loss": 0.406, + "step": 12 + }, + { + "epoch": 0.001732409381663113, + "grad_norm": 0.6597164903168519, + "learning_rate": 2.8824833702882486e-07, + "loss": 0.4878, + "step": 13 + }, + { + "epoch": 0.0018656716417910447, + "grad_norm": 0.3585829433902042, + "learning_rate": 3.1042128603104217e-07, + "loss": 0.4215, + "step": 14 + }, + { + "epoch": 0.0019989339019189766, + "grad_norm": 0.41795393940823383, + "learning_rate": 3.3259423503325944e-07, + "loss": 0.4576, + "step": 15 + }, + { + "epoch": 0.0021321961620469083, + "grad_norm": 0.3405233355049504, + "learning_rate": 3.5476718403547675e-07, + "loss": 0.6198, + "step": 16 + }, + { + "epoch": 0.00226545842217484, + "grad_norm": 4.555883350341243, + "learning_rate": 3.7694013303769407e-07, + "loss": 0.492, + "step": 17 + }, + { + "epoch": 0.002398720682302772, + "grad_norm": 0.3529941406415074, + "learning_rate": 3.9911308203991133e-07, + "loss": 0.447, + "step": 18 + }, + { + "epoch": 0.0025319829424307037, + "grad_norm": 0.39645677917117744, + "learning_rate": 4.2128603104212865e-07, + "loss": 0.42, + "step": 19 + }, + { + "epoch": 0.0026652452025586353, + "grad_norm": 0.33958085143856703, + "learning_rate": 4.4345898004434597e-07, + "loss": 0.4331, + "step": 20 + }, + { + "epoch": 0.002798507462686567, + "grad_norm": 0.3663703678973881, + "learning_rate": 4.6563192904656323e-07, + "loss": 0.4583, + "step": 21 + }, + { + "epoch": 0.002931769722814499, + "grad_norm": 0.3488302016626225, + "learning_rate": 4.878048780487805e-07, + "loss": 0.4933, + "step": 22 + }, + { + "epoch": 0.0030650319829424308, + "grad_norm": 0.34542585043852075, + "learning_rate": 5.099778270509978e-07, + "loss": 0.4637, + "step": 23 + }, + { + "epoch": 0.0031982942430703624, + "grad_norm": 0.33700568905160344, + "learning_rate": 5.321507760532151e-07, + "loss": 0.4096, + "step": 24 + }, + { + "epoch": 0.003331556503198294, + "grad_norm": 0.3156327323741949, + "learning_rate": 5.543237250554324e-07, + "loss": 0.5112, + "step": 25 + }, + { + "epoch": 0.003464818763326226, + "grad_norm": 0.3546892825051266, + "learning_rate": 5.764966740576497e-07, + "loss": 0.5243, + "step": 26 + }, + { + "epoch": 0.003598081023454158, + "grad_norm": 0.3475931694899412, + "learning_rate": 5.98669623059867e-07, + "loss": 0.4156, + "step": 27 + }, + { + "epoch": 0.0037313432835820895, + "grad_norm": 0.35388355210960704, + "learning_rate": 6.208425720620843e-07, + "loss": 0.4472, + "step": 28 + }, + { + "epoch": 0.003864605543710021, + "grad_norm": 0.3514407145518632, + "learning_rate": 6.430155210643016e-07, + "loss": 0.4163, + "step": 29 + }, + { + "epoch": 0.003997867803837953, + "grad_norm": 0.41226152340964795, + "learning_rate": 6.651884700665189e-07, + "loss": 0.3754, + "step": 30 + }, + { + "epoch": 0.004131130063965885, + "grad_norm": 0.4260464207190392, + "learning_rate": 6.873614190687362e-07, + "loss": 0.3744, + "step": 31 + }, + { + "epoch": 0.0042643923240938165, + "grad_norm": 0.3375334586464966, + "learning_rate": 7.095343680709535e-07, + "loss": 0.5545, + "step": 32 + }, + { + "epoch": 0.004397654584221748, + "grad_norm": 0.3475881836048743, + "learning_rate": 7.317073170731707e-07, + "loss": 0.4245, + "step": 33 + }, + { + "epoch": 0.00453091684434968, + "grad_norm": 0.33920540596473164, + "learning_rate": 7.538802660753881e-07, + "loss": 0.4396, + "step": 34 + }, + { + "epoch": 0.0046641791044776115, + "grad_norm": 3.2102403668783603, + "learning_rate": 7.760532150776054e-07, + "loss": 0.4393, + "step": 35 + }, + { + "epoch": 0.004797441364605544, + "grad_norm": 1.7833361072896947, + "learning_rate": 7.982261640798227e-07, + "loss": 0.5051, + "step": 36 + }, + { + "epoch": 0.004930703624733476, + "grad_norm": 0.6750970307683521, + "learning_rate": 8.203991130820401e-07, + "loss": 0.414, + "step": 37 + }, + { + "epoch": 0.005063965884861407, + "grad_norm": 0.31672573262201603, + "learning_rate": 8.425720620842573e-07, + "loss": 0.3763, + "step": 38 + }, + { + "epoch": 0.005197228144989339, + "grad_norm": 0.32914524728815336, + "learning_rate": 8.647450110864745e-07, + "loss": 0.4689, + "step": 39 + }, + { + "epoch": 0.005330490405117271, + "grad_norm": 0.44288066911611756, + "learning_rate": 8.869179600886919e-07, + "loss": 0.4105, + "step": 40 + }, + { + "epoch": 0.005463752665245202, + "grad_norm": 0.3385687150548603, + "learning_rate": 9.090909090909091e-07, + "loss": 0.4256, + "step": 41 + }, + { + "epoch": 0.005597014925373134, + "grad_norm": 0.36772359777467617, + "learning_rate": 9.312638580931265e-07, + "loss": 0.4234, + "step": 42 + }, + { + "epoch": 0.0057302771855010665, + "grad_norm": 0.3120800605353845, + "learning_rate": 9.534368070953437e-07, + "loss": 0.457, + "step": 43 + }, + { + "epoch": 0.005863539445628998, + "grad_norm": 0.3020975468217848, + "learning_rate": 9.75609756097561e-07, + "loss": 0.3713, + "step": 44 + }, + { + "epoch": 0.00599680170575693, + "grad_norm": 2.2362264534541727, + "learning_rate": 9.977827050997784e-07, + "loss": 0.5239, + "step": 45 + }, + { + "epoch": 0.0061300639658848615, + "grad_norm": 0.30472896664684773, + "learning_rate": 1.0199556541019955e-06, + "loss": 0.424, + "step": 46 + }, + { + "epoch": 0.006263326226012793, + "grad_norm": 0.3070711621234119, + "learning_rate": 1.042128603104213e-06, + "loss": 0.4058, + "step": 47 + }, + { + "epoch": 0.006396588486140725, + "grad_norm": 0.3000638353913815, + "learning_rate": 1.0643015521064302e-06, + "loss": 0.4549, + "step": 48 + }, + { + "epoch": 0.0065298507462686565, + "grad_norm": 0.3136009279772101, + "learning_rate": 1.0864745011086475e-06, + "loss": 0.4789, + "step": 49 + }, + { + "epoch": 0.006663113006396588, + "grad_norm": 0.3134580698413611, + "learning_rate": 1.1086474501108648e-06, + "loss": 0.4196, + "step": 50 + }, + { + "epoch": 0.006796375266524521, + "grad_norm": 0.31513902226373314, + "learning_rate": 1.130820399113082e-06, + "loss": 0.4225, + "step": 51 + }, + { + "epoch": 0.006929637526652452, + "grad_norm": 0.3164074909562225, + "learning_rate": 1.1529933481152994e-06, + "loss": 0.4957, + "step": 52 + }, + { + "epoch": 0.007062899786780384, + "grad_norm": 0.31526024055438806, + "learning_rate": 1.1751662971175167e-06, + "loss": 0.4576, + "step": 53 + }, + { + "epoch": 0.007196162046908316, + "grad_norm": 0.30439760550699707, + "learning_rate": 1.197339246119734e-06, + "loss": 0.4533, + "step": 54 + }, + { + "epoch": 0.007329424307036247, + "grad_norm": 0.29587189250761153, + "learning_rate": 1.2195121951219514e-06, + "loss": 0.4716, + "step": 55 + }, + { + "epoch": 0.007462686567164179, + "grad_norm": 0.30054932703870896, + "learning_rate": 1.2416851441241687e-06, + "loss": 0.4545, + "step": 56 + }, + { + "epoch": 0.007595948827292111, + "grad_norm": 3.588679757593861, + "learning_rate": 1.2638580931263858e-06, + "loss": 0.457, + "step": 57 + }, + { + "epoch": 0.007729211087420042, + "grad_norm": 0.2966361422832631, + "learning_rate": 1.2860310421286031e-06, + "loss": 0.4343, + "step": 58 + }, + { + "epoch": 0.007862473347547975, + "grad_norm": 0.31808891977983333, + "learning_rate": 1.3082039911308206e-06, + "loss": 0.488, + "step": 59 + }, + { + "epoch": 0.007995735607675906, + "grad_norm": 0.30084686412740047, + "learning_rate": 1.3303769401330377e-06, + "loss": 0.4095, + "step": 60 + }, + { + "epoch": 0.008128997867803838, + "grad_norm": 0.304595548240149, + "learning_rate": 1.352549889135255e-06, + "loss": 0.4489, + "step": 61 + }, + { + "epoch": 0.00826226012793177, + "grad_norm": 0.29079032787785264, + "learning_rate": 1.3747228381374724e-06, + "loss": 0.4199, + "step": 62 + }, + { + "epoch": 0.008395522388059701, + "grad_norm": 0.3296758981294055, + "learning_rate": 1.3968957871396897e-06, + "loss": 0.4877, + "step": 63 + }, + { + "epoch": 0.008528784648187633, + "grad_norm": 0.6514052304295479, + "learning_rate": 1.419068736141907e-06, + "loss": 0.4625, + "step": 64 + }, + { + "epoch": 0.008662046908315565, + "grad_norm": 0.3033285972683471, + "learning_rate": 1.4412416851441243e-06, + "loss": 0.3695, + "step": 65 + }, + { + "epoch": 0.008795309168443496, + "grad_norm": 0.28913814188030723, + "learning_rate": 1.4634146341463414e-06, + "loss": 0.4674, + "step": 66 + }, + { + "epoch": 0.008928571428571428, + "grad_norm": 0.29617705996021254, + "learning_rate": 1.485587583148559e-06, + "loss": 0.4199, + "step": 67 + }, + { + "epoch": 0.00906183368869936, + "grad_norm": 0.3018068185359129, + "learning_rate": 1.5077605321507763e-06, + "loss": 0.4575, + "step": 68 + }, + { + "epoch": 0.009195095948827291, + "grad_norm": 0.29396575947241815, + "learning_rate": 1.5299334811529934e-06, + "loss": 0.3888, + "step": 69 + }, + { + "epoch": 0.009328358208955223, + "grad_norm": 0.2970767669631579, + "learning_rate": 1.5521064301552107e-06, + "loss": 0.5401, + "step": 70 + }, + { + "epoch": 0.009461620469083156, + "grad_norm": 0.2912099301461429, + "learning_rate": 1.5742793791574282e-06, + "loss": 0.4075, + "step": 71 + }, + { + "epoch": 0.009594882729211088, + "grad_norm": 6.109934635119822, + "learning_rate": 1.5964523281596453e-06, + "loss": 0.5122, + "step": 72 + }, + { + "epoch": 0.00972814498933902, + "grad_norm": 0.3145350565420381, + "learning_rate": 1.6186252771618627e-06, + "loss": 0.4512, + "step": 73 + }, + { + "epoch": 0.009861407249466951, + "grad_norm": 0.2962733201611189, + "learning_rate": 1.6407982261640802e-06, + "loss": 0.437, + "step": 74 + }, + { + "epoch": 0.009994669509594883, + "grad_norm": 0.2930069388917254, + "learning_rate": 1.6629711751662973e-06, + "loss": 0.4093, + "step": 75 + }, + { + "epoch": 0.010127931769722815, + "grad_norm": 0.28432384050835424, + "learning_rate": 1.6851441241685146e-06, + "loss": 0.459, + "step": 76 + }, + { + "epoch": 0.010261194029850746, + "grad_norm": 0.30813559768085913, + "learning_rate": 1.707317073170732e-06, + "loss": 0.4187, + "step": 77 + }, + { + "epoch": 0.010394456289978678, + "grad_norm": 0.30374014849850584, + "learning_rate": 1.729490022172949e-06, + "loss": 0.4455, + "step": 78 + }, + { + "epoch": 0.01052771855010661, + "grad_norm": 0.3757265995029127, + "learning_rate": 1.7516629711751666e-06, + "loss": 0.4439, + "step": 79 + }, + { + "epoch": 0.010660980810234541, + "grad_norm": 0.32013085551968457, + "learning_rate": 1.7738359201773839e-06, + "loss": 0.4803, + "step": 80 + }, + { + "epoch": 0.010794243070362473, + "grad_norm": 0.2829207681954075, + "learning_rate": 1.796008869179601e-06, + "loss": 0.4145, + "step": 81 + }, + { + "epoch": 0.010927505330490405, + "grad_norm": 0.2891313400775337, + "learning_rate": 1.8181818181818183e-06, + "loss": 0.5037, + "step": 82 + }, + { + "epoch": 0.011060767590618336, + "grad_norm": 0.2931857467767175, + "learning_rate": 1.8403547671840354e-06, + "loss": 0.434, + "step": 83 + }, + { + "epoch": 0.011194029850746268, + "grad_norm": 0.3006307891356459, + "learning_rate": 1.862527716186253e-06, + "loss": 0.4948, + "step": 84 + }, + { + "epoch": 0.0113272921108742, + "grad_norm": 0.2924562790651781, + "learning_rate": 1.8847006651884702e-06, + "loss": 0.4514, + "step": 85 + }, + { + "epoch": 0.011460554371002133, + "grad_norm": 0.29192802977382043, + "learning_rate": 1.9068736141906873e-06, + "loss": 0.467, + "step": 86 + }, + { + "epoch": 0.011593816631130065, + "grad_norm": 0.29714759707906413, + "learning_rate": 1.9290465631929047e-06, + "loss": 0.4468, + "step": 87 + }, + { + "epoch": 0.011727078891257996, + "grad_norm": 0.275955259661459, + "learning_rate": 1.951219512195122e-06, + "loss": 0.3917, + "step": 88 + }, + { + "epoch": 0.011860341151385928, + "grad_norm": 0.2849562844933025, + "learning_rate": 1.9733924611973393e-06, + "loss": 0.5346, + "step": 89 + }, + { + "epoch": 0.01199360341151386, + "grad_norm": 0.29984802306526215, + "learning_rate": 1.995565410199557e-06, + "loss": 0.5516, + "step": 90 + }, + { + "epoch": 0.012126865671641791, + "grad_norm": 0.2879823720911563, + "learning_rate": 2.017738359201774e-06, + "loss": 0.4285, + "step": 91 + }, + { + "epoch": 0.012260127931769723, + "grad_norm": 0.2905821049731216, + "learning_rate": 2.039911308203991e-06, + "loss": 0.4174, + "step": 92 + }, + { + "epoch": 0.012393390191897655, + "grad_norm": 0.2977068254652101, + "learning_rate": 2.0620842572062086e-06, + "loss": 0.491, + "step": 93 + }, + { + "epoch": 0.012526652452025586, + "grad_norm": 0.2944403531034739, + "learning_rate": 2.084257206208426e-06, + "loss": 0.3967, + "step": 94 + }, + { + "epoch": 0.012659914712153518, + "grad_norm": 0.28940037562183796, + "learning_rate": 2.106430155210643e-06, + "loss": 0.4316, + "step": 95 + }, + { + "epoch": 0.01279317697228145, + "grad_norm": 0.28679321147917525, + "learning_rate": 2.1286031042128603e-06, + "loss": 0.3957, + "step": 96 + }, + { + "epoch": 0.012926439232409381, + "grad_norm": 0.2854119284140816, + "learning_rate": 2.150776053215078e-06, + "loss": 0.4051, + "step": 97 + }, + { + "epoch": 0.013059701492537313, + "grad_norm": 0.2914605091293353, + "learning_rate": 2.172949002217295e-06, + "loss": 0.4569, + "step": 98 + }, + { + "epoch": 0.013192963752665245, + "grad_norm": 0.2958624601288701, + "learning_rate": 2.1951219512195125e-06, + "loss": 0.4184, + "step": 99 + }, + { + "epoch": 0.013326226012793176, + "grad_norm": 0.2873887802164695, + "learning_rate": 2.2172949002217296e-06, + "loss": 0.4474, + "step": 100 + }, + { + "epoch": 0.013459488272921108, + "grad_norm": 0.3012738131389704, + "learning_rate": 2.2394678492239467e-06, + "loss": 0.4498, + "step": 101 + }, + { + "epoch": 0.013592750533049041, + "grad_norm": 0.2964278135823601, + "learning_rate": 2.261640798226164e-06, + "loss": 0.4368, + "step": 102 + }, + { + "epoch": 0.013726012793176973, + "grad_norm": 0.2829054317133452, + "learning_rate": 2.2838137472283817e-06, + "loss": 0.4081, + "step": 103 + }, + { + "epoch": 0.013859275053304905, + "grad_norm": 0.3036619477841686, + "learning_rate": 2.305986696230599e-06, + "loss": 0.4541, + "step": 104 + }, + { + "epoch": 0.013992537313432836, + "grad_norm": 0.30518822871238166, + "learning_rate": 2.3281596452328164e-06, + "loss": 0.4741, + "step": 105 + }, + { + "epoch": 0.014125799573560768, + "grad_norm": 0.3175412487013645, + "learning_rate": 2.3503325942350335e-06, + "loss": 0.5043, + "step": 106 + }, + { + "epoch": 0.0142590618336887, + "grad_norm": 0.29132455554033376, + "learning_rate": 2.3725055432372506e-06, + "loss": 0.3913, + "step": 107 + }, + { + "epoch": 0.014392324093816631, + "grad_norm": 0.2983570178322864, + "learning_rate": 2.394678492239468e-06, + "loss": 0.5141, + "step": 108 + }, + { + "epoch": 0.014525586353944563, + "grad_norm": 0.29689263143317596, + "learning_rate": 2.4168514412416856e-06, + "loss": 0.4798, + "step": 109 + }, + { + "epoch": 0.014658848614072495, + "grad_norm": 0.28574033848366787, + "learning_rate": 2.4390243902439027e-06, + "loss": 0.3798, + "step": 110 + }, + { + "epoch": 0.014792110874200426, + "grad_norm": 0.29067748275394034, + "learning_rate": 2.46119733924612e-06, + "loss": 0.5126, + "step": 111 + }, + { + "epoch": 0.014925373134328358, + "grad_norm": 0.3293750562118452, + "learning_rate": 2.4833702882483374e-06, + "loss": 0.4888, + "step": 112 + }, + { + "epoch": 0.01505863539445629, + "grad_norm": 0.2922508471751356, + "learning_rate": 2.5055432372505545e-06, + "loss": 0.4096, + "step": 113 + }, + { + "epoch": 0.015191897654584221, + "grad_norm": 0.2736850129094647, + "learning_rate": 2.5277161862527716e-06, + "loss": 0.4148, + "step": 114 + }, + { + "epoch": 0.015325159914712153, + "grad_norm": 0.295959784669357, + "learning_rate": 2.549889135254989e-06, + "loss": 0.4622, + "step": 115 + }, + { + "epoch": 0.015458422174840085, + "grad_norm": 0.30165996091406877, + "learning_rate": 2.5720620842572062e-06, + "loss": 0.4562, + "step": 116 + }, + { + "epoch": 0.015591684434968016, + "grad_norm": 0.32508254516802465, + "learning_rate": 2.5942350332594233e-06, + "loss": 0.4835, + "step": 117 + }, + { + "epoch": 0.01572494669509595, + "grad_norm": 0.2715977095100739, + "learning_rate": 2.6164079822616413e-06, + "loss": 0.3377, + "step": 118 + }, + { + "epoch": 0.01585820895522388, + "grad_norm": 0.3292969935947778, + "learning_rate": 2.6385809312638584e-06, + "loss": 0.4714, + "step": 119 + }, + { + "epoch": 0.015991471215351813, + "grad_norm": 0.28101837891300574, + "learning_rate": 2.6607538802660755e-06, + "loss": 0.3989, + "step": 120 + }, + { + "epoch": 0.016124733475479745, + "grad_norm": 0.28416012537655155, + "learning_rate": 2.682926829268293e-06, + "loss": 0.4275, + "step": 121 + }, + { + "epoch": 0.016257995735607676, + "grad_norm": 0.2775454924391981, + "learning_rate": 2.70509977827051e-06, + "loss": 0.3827, + "step": 122 + }, + { + "epoch": 0.016391257995735608, + "grad_norm": 0.28255784660039385, + "learning_rate": 2.7272727272727272e-06, + "loss": 0.3737, + "step": 123 + }, + { + "epoch": 0.01652452025586354, + "grad_norm": 0.3054395835043756, + "learning_rate": 2.7494456762749448e-06, + "loss": 0.5147, + "step": 124 + }, + { + "epoch": 0.01665778251599147, + "grad_norm": 0.28996569958746093, + "learning_rate": 2.7716186252771623e-06, + "loss": 0.4014, + "step": 125 + }, + { + "epoch": 0.016791044776119403, + "grad_norm": 0.3366255435471582, + "learning_rate": 2.7937915742793794e-06, + "loss": 0.4298, + "step": 126 + }, + { + "epoch": 0.016924307036247335, + "grad_norm": 0.3029889736194596, + "learning_rate": 2.815964523281597e-06, + "loss": 0.3983, + "step": 127 + }, + { + "epoch": 0.017057569296375266, + "grad_norm": 0.3049092853111851, + "learning_rate": 2.838137472283814e-06, + "loss": 0.4386, + "step": 128 + }, + { + "epoch": 0.017190831556503198, + "grad_norm": 0.30355819745377993, + "learning_rate": 2.860310421286031e-06, + "loss": 0.4312, + "step": 129 + }, + { + "epoch": 0.01732409381663113, + "grad_norm": 0.31896809146320393, + "learning_rate": 2.8824833702882487e-06, + "loss": 0.4361, + "step": 130 + }, + { + "epoch": 0.01745735607675906, + "grad_norm": 0.30629298048312886, + "learning_rate": 2.9046563192904658e-06, + "loss": 0.4539, + "step": 131 + }, + { + "epoch": 0.017590618336886993, + "grad_norm": 0.3009147242054265, + "learning_rate": 2.926829268292683e-06, + "loss": 0.3822, + "step": 132 + }, + { + "epoch": 0.017723880597014924, + "grad_norm": 0.2947991634788754, + "learning_rate": 2.949002217294901e-06, + "loss": 0.4038, + "step": 133 + }, + { + "epoch": 0.017857142857142856, + "grad_norm": 0.29816538835641254, + "learning_rate": 2.971175166297118e-06, + "loss": 0.441, + "step": 134 + }, + { + "epoch": 0.017990405117270788, + "grad_norm": 0.2871059346306559, + "learning_rate": 2.993348115299335e-06, + "loss": 0.4033, + "step": 135 + }, + { + "epoch": 0.01812366737739872, + "grad_norm": 0.3019840858382017, + "learning_rate": 3.0155210643015526e-06, + "loss": 0.466, + "step": 136 + }, + { + "epoch": 0.01825692963752665, + "grad_norm": 0.31220215357270414, + "learning_rate": 3.0376940133037697e-06, + "loss": 0.4132, + "step": 137 + }, + { + "epoch": 0.018390191897654583, + "grad_norm": 0.30677926572931247, + "learning_rate": 3.0598669623059868e-06, + "loss": 0.4997, + "step": 138 + }, + { + "epoch": 0.018523454157782514, + "grad_norm": 0.2984216470034485, + "learning_rate": 3.0820399113082043e-06, + "loss": 0.419, + "step": 139 + }, + { + "epoch": 0.018656716417910446, + "grad_norm": 0.28968258325888346, + "learning_rate": 3.1042128603104214e-06, + "loss": 0.4242, + "step": 140 + }, + { + "epoch": 0.01878997867803838, + "grad_norm": 0.31300796114860235, + "learning_rate": 3.1263858093126385e-06, + "loss": 0.4657, + "step": 141 + }, + { + "epoch": 0.018923240938166313, + "grad_norm": 0.3084988915098087, + "learning_rate": 3.1485587583148565e-06, + "loss": 0.4013, + "step": 142 + }, + { + "epoch": 0.019056503198294245, + "grad_norm": 0.2935435194701963, + "learning_rate": 3.1707317073170736e-06, + "loss": 0.5013, + "step": 143 + }, + { + "epoch": 0.019189765458422176, + "grad_norm": 0.2958778689656613, + "learning_rate": 3.1929046563192907e-06, + "loss": 0.3952, + "step": 144 + }, + { + "epoch": 0.019323027718550108, + "grad_norm": 0.29614199937085756, + "learning_rate": 3.215077605321508e-06, + "loss": 0.4358, + "step": 145 + }, + { + "epoch": 0.01945628997867804, + "grad_norm": 0.49793189600279164, + "learning_rate": 3.2372505543237253e-06, + "loss": 0.4047, + "step": 146 + }, + { + "epoch": 0.01958955223880597, + "grad_norm": 0.28766898580111155, + "learning_rate": 3.2594235033259424e-06, + "loss": 0.4837, + "step": 147 + }, + { + "epoch": 0.019722814498933903, + "grad_norm": 0.31021257227324756, + "learning_rate": 3.2815964523281604e-06, + "loss": 0.5347, + "step": 148 + }, + { + "epoch": 0.019856076759061835, + "grad_norm": 0.30910540969485784, + "learning_rate": 3.3037694013303775e-06, + "loss": 0.3693, + "step": 149 + }, + { + "epoch": 0.019989339019189766, + "grad_norm": 0.3025873576506316, + "learning_rate": 3.3259423503325946e-06, + "loss": 0.4216, + "step": 150 + }, + { + "epoch": 0.020122601279317698, + "grad_norm": 0.3038905299477172, + "learning_rate": 3.348115299334812e-06, + "loss": 0.4015, + "step": 151 + }, + { + "epoch": 0.02025586353944563, + "grad_norm": 0.3691007094768603, + "learning_rate": 3.370288248337029e-06, + "loss": 0.4537, + "step": 152 + }, + { + "epoch": 0.02038912579957356, + "grad_norm": 0.29585615109470376, + "learning_rate": 3.3924611973392463e-06, + "loss": 0.4212, + "step": 153 + }, + { + "epoch": 0.020522388059701493, + "grad_norm": 0.3038898409638945, + "learning_rate": 3.414634146341464e-06, + "loss": 0.404, + "step": 154 + }, + { + "epoch": 0.020655650319829424, + "grad_norm": 0.299711582383995, + "learning_rate": 3.436807095343681e-06, + "loss": 0.4823, + "step": 155 + }, + { + "epoch": 0.020788912579957356, + "grad_norm": 0.3007995400417457, + "learning_rate": 3.458980044345898e-06, + "loss": 0.4367, + "step": 156 + }, + { + "epoch": 0.020922174840085288, + "grad_norm": 0.3100631285759546, + "learning_rate": 3.481152993348116e-06, + "loss": 0.4339, + "step": 157 + }, + { + "epoch": 0.02105543710021322, + "grad_norm": 0.3052892664382976, + "learning_rate": 3.503325942350333e-06, + "loss": 0.4394, + "step": 158 + }, + { + "epoch": 0.02118869936034115, + "grad_norm": 0.3058153813935044, + "learning_rate": 3.52549889135255e-06, + "loss": 0.4008, + "step": 159 + }, + { + "epoch": 0.021321961620469083, + "grad_norm": 0.31193381576258006, + "learning_rate": 3.5476718403547677e-06, + "loss": 0.4776, + "step": 160 + }, + { + "epoch": 0.021455223880597014, + "grad_norm": 0.3028074956667018, + "learning_rate": 3.569844789356985e-06, + "loss": 0.4231, + "step": 161 + }, + { + "epoch": 0.021588486140724946, + "grad_norm": 0.30342283554018246, + "learning_rate": 3.592017738359202e-06, + "loss": 0.4007, + "step": 162 + }, + { + "epoch": 0.021721748400852878, + "grad_norm": 0.29004531374142956, + "learning_rate": 3.614190687361419e-06, + "loss": 0.406, + "step": 163 + }, + { + "epoch": 0.02185501066098081, + "grad_norm": 0.3038941461103449, + "learning_rate": 3.6363636363636366e-06, + "loss": 0.3897, + "step": 164 + }, + { + "epoch": 0.02198827292110874, + "grad_norm": 0.30043200600696907, + "learning_rate": 3.6585365853658537e-06, + "loss": 0.496, + "step": 165 + }, + { + "epoch": 0.022121535181236673, + "grad_norm": 0.32551322613394873, + "learning_rate": 3.680709534368071e-06, + "loss": 0.4327, + "step": 166 + }, + { + "epoch": 0.022254797441364604, + "grad_norm": 0.2948544330508995, + "learning_rate": 3.7028824833702887e-06, + "loss": 0.4731, + "step": 167 + }, + { + "epoch": 0.022388059701492536, + "grad_norm": 0.283934897299666, + "learning_rate": 3.725055432372506e-06, + "loss": 0.3458, + "step": 168 + }, + { + "epoch": 0.022521321961620468, + "grad_norm": 0.29753708270778373, + "learning_rate": 3.747228381374723e-06, + "loss": 0.3952, + "step": 169 + }, + { + "epoch": 0.0226545842217484, + "grad_norm": 0.31154595046843553, + "learning_rate": 3.7694013303769405e-06, + "loss": 0.4017, + "step": 170 + }, + { + "epoch": 0.02278784648187633, + "grad_norm": 0.303714911842248, + "learning_rate": 3.7915742793791576e-06, + "loss": 0.3941, + "step": 171 + }, + { + "epoch": 0.022921108742004266, + "grad_norm": 0.2999057697811732, + "learning_rate": 3.8137472283813747e-06, + "loss": 0.4837, + "step": 172 + }, + { + "epoch": 0.023054371002132198, + "grad_norm": 0.2975766557285875, + "learning_rate": 3.835920177383592e-06, + "loss": 0.4429, + "step": 173 + }, + { + "epoch": 0.02318763326226013, + "grad_norm": 0.2960715382647352, + "learning_rate": 3.858093126385809e-06, + "loss": 0.3892, + "step": 174 + }, + { + "epoch": 0.02332089552238806, + "grad_norm": 0.3041483672410719, + "learning_rate": 3.8802660753880264e-06, + "loss": 0.3779, + "step": 175 + }, + { + "epoch": 0.023454157782515993, + "grad_norm": 0.2883403311017782, + "learning_rate": 3.902439024390244e-06, + "loss": 0.4017, + "step": 176 + }, + { + "epoch": 0.023587420042643924, + "grad_norm": 0.29387408306230406, + "learning_rate": 3.9246119733924615e-06, + "loss": 0.5278, + "step": 177 + }, + { + "epoch": 0.023720682302771856, + "grad_norm": 0.30542389708808393, + "learning_rate": 3.946784922394679e-06, + "loss": 0.434, + "step": 178 + }, + { + "epoch": 0.023853944562899788, + "grad_norm": 0.30633234841192936, + "learning_rate": 3.9689578713968965e-06, + "loss": 0.3942, + "step": 179 + }, + { + "epoch": 0.02398720682302772, + "grad_norm": 0.3063050910736435, + "learning_rate": 3.991130820399114e-06, + "loss": 0.4298, + "step": 180 + }, + { + "epoch": 0.02412046908315565, + "grad_norm": 0.3081779344228308, + "learning_rate": 4.013303769401331e-06, + "loss": 0.4758, + "step": 181 + }, + { + "epoch": 0.024253731343283583, + "grad_norm": 0.3185766760548407, + "learning_rate": 4.035476718403548e-06, + "loss": 0.3846, + "step": 182 + }, + { + "epoch": 0.024386993603411514, + "grad_norm": 0.3084566234537635, + "learning_rate": 4.057649667405765e-06, + "loss": 0.4782, + "step": 183 + }, + { + "epoch": 0.024520255863539446, + "grad_norm": 0.30639027253299067, + "learning_rate": 4.079822616407982e-06, + "loss": 0.5023, + "step": 184 + }, + { + "epoch": 0.024653518123667378, + "grad_norm": 0.3163665557859706, + "learning_rate": 4.1019955654102e-06, + "loss": 0.4566, + "step": 185 + }, + { + "epoch": 0.02478678038379531, + "grad_norm": 0.31560113690257435, + "learning_rate": 4.124168514412417e-06, + "loss": 0.4314, + "step": 186 + }, + { + "epoch": 0.02492004264392324, + "grad_norm": 0.307337750282998, + "learning_rate": 4.146341463414634e-06, + "loss": 0.4165, + "step": 187 + }, + { + "epoch": 0.025053304904051173, + "grad_norm": 0.3139999157170842, + "learning_rate": 4.168514412416852e-06, + "loss": 0.4994, + "step": 188 + }, + { + "epoch": 0.025186567164179104, + "grad_norm": 0.31721508178511515, + "learning_rate": 4.190687361419069e-06, + "loss": 0.4059, + "step": 189 + }, + { + "epoch": 0.025319829424307036, + "grad_norm": 0.31939123409436937, + "learning_rate": 4.212860310421286e-06, + "loss": 0.4401, + "step": 190 + }, + { + "epoch": 0.025453091684434968, + "grad_norm": 0.31296701436761637, + "learning_rate": 4.2350332594235035e-06, + "loss": 0.3985, + "step": 191 + }, + { + "epoch": 0.0255863539445629, + "grad_norm": 0.30668263367612353, + "learning_rate": 4.257206208425721e-06, + "loss": 0.3857, + "step": 192 + }, + { + "epoch": 0.02571961620469083, + "grad_norm": 0.3367401541081361, + "learning_rate": 4.279379157427938e-06, + "loss": 0.4269, + "step": 193 + }, + { + "epoch": 0.025852878464818763, + "grad_norm": 0.298213223915774, + "learning_rate": 4.301552106430156e-06, + "loss": 0.3932, + "step": 194 + }, + { + "epoch": 0.025986140724946694, + "grad_norm": 0.48477779635736895, + "learning_rate": 4.323725055432373e-06, + "loss": 0.4318, + "step": 195 + }, + { + "epoch": 0.026119402985074626, + "grad_norm": 0.3133366497594018, + "learning_rate": 4.34589800443459e-06, + "loss": 0.4377, + "step": 196 + }, + { + "epoch": 0.026252665245202558, + "grad_norm": 0.39168452554656286, + "learning_rate": 4.368070953436808e-06, + "loss": 0.4697, + "step": 197 + }, + { + "epoch": 0.02638592750533049, + "grad_norm": 0.3294579313808277, + "learning_rate": 4.390243902439025e-06, + "loss": 0.4196, + "step": 198 + }, + { + "epoch": 0.02651918976545842, + "grad_norm": 0.31781248528911843, + "learning_rate": 4.412416851441242e-06, + "loss": 0.4322, + "step": 199 + }, + { + "epoch": 0.026652452025586353, + "grad_norm": 0.3039469618730872, + "learning_rate": 4.434589800443459e-06, + "loss": 0.389, + "step": 200 + }, + { + "epoch": 0.026785714285714284, + "grad_norm": 0.3526860609818267, + "learning_rate": 4.456762749445676e-06, + "loss": 0.3952, + "step": 201 + }, + { + "epoch": 0.026918976545842216, + "grad_norm": 0.3149943895367458, + "learning_rate": 4.478935698447893e-06, + "loss": 0.4593, + "step": 202 + }, + { + "epoch": 0.027052238805970148, + "grad_norm": 0.33508148211847166, + "learning_rate": 4.501108647450111e-06, + "loss": 0.4682, + "step": 203 + }, + { + "epoch": 0.027185501066098083, + "grad_norm": 0.29416598523741266, + "learning_rate": 4.523281596452328e-06, + "loss": 0.4381, + "step": 204 + }, + { + "epoch": 0.027318763326226014, + "grad_norm": 0.32115172083156707, + "learning_rate": 4.5454545454545455e-06, + "loss": 0.4431, + "step": 205 + }, + { + "epoch": 0.027452025586353946, + "grad_norm": 0.3032214046756702, + "learning_rate": 4.5676274944567635e-06, + "loss": 0.4015, + "step": 206 + }, + { + "epoch": 0.027585287846481878, + "grad_norm": 0.31774076756147074, + "learning_rate": 4.5898004434589806e-06, + "loss": 0.4186, + "step": 207 + }, + { + "epoch": 0.02771855010660981, + "grad_norm": 0.31373406642748053, + "learning_rate": 4.611973392461198e-06, + "loss": 0.4304, + "step": 208 + }, + { + "epoch": 0.02785181236673774, + "grad_norm": 0.3132935295929912, + "learning_rate": 4.634146341463416e-06, + "loss": 0.5424, + "step": 209 + }, + { + "epoch": 0.027985074626865673, + "grad_norm": 0.3195492611951643, + "learning_rate": 4.656319290465633e-06, + "loss": 0.4228, + "step": 210 + }, + { + "epoch": 0.028118336886993604, + "grad_norm": 0.3097766305611097, + "learning_rate": 4.67849223946785e-06, + "loss": 0.4249, + "step": 211 + }, + { + "epoch": 0.028251599147121536, + "grad_norm": 0.3020385680144838, + "learning_rate": 4.700665188470067e-06, + "loss": 0.3841, + "step": 212 + }, + { + "epoch": 0.028384861407249468, + "grad_norm": 0.3251233531055384, + "learning_rate": 4.722838137472284e-06, + "loss": 0.4247, + "step": 213 + }, + { + "epoch": 0.0285181236673774, + "grad_norm": 0.2989515260673567, + "learning_rate": 4.745011086474501e-06, + "loss": 0.3707, + "step": 214 + }, + { + "epoch": 0.02865138592750533, + "grad_norm": 0.3022390851058971, + "learning_rate": 4.767184035476719e-06, + "loss": 0.4441, + "step": 215 + }, + { + "epoch": 0.028784648187633263, + "grad_norm": 0.3125492436244745, + "learning_rate": 4.789356984478936e-06, + "loss": 0.4482, + "step": 216 + }, + { + "epoch": 0.028917910447761194, + "grad_norm": 0.3104484457111638, + "learning_rate": 4.811529933481153e-06, + "loss": 0.4193, + "step": 217 + }, + { + "epoch": 0.029051172707889126, + "grad_norm": 0.3037341891631677, + "learning_rate": 4.833702882483371e-06, + "loss": 0.3477, + "step": 218 + }, + { + "epoch": 0.029184434968017058, + "grad_norm": 0.29430887346945805, + "learning_rate": 4.855875831485588e-06, + "loss": 0.4813, + "step": 219 + }, + { + "epoch": 0.02931769722814499, + "grad_norm": 0.31526477010538284, + "learning_rate": 4.8780487804878055e-06, + "loss": 0.4425, + "step": 220 + }, + { + "epoch": 0.02945095948827292, + "grad_norm": 0.3212045089893793, + "learning_rate": 4.900221729490023e-06, + "loss": 0.3511, + "step": 221 + }, + { + "epoch": 0.029584221748400853, + "grad_norm": 0.29740779092471503, + "learning_rate": 4.92239467849224e-06, + "loss": 0.5164, + "step": 222 + }, + { + "epoch": 0.029717484008528784, + "grad_norm": 0.3017066796087591, + "learning_rate": 4.944567627494457e-06, + "loss": 0.4003, + "step": 223 + }, + { + "epoch": 0.029850746268656716, + "grad_norm": 0.3188338307830401, + "learning_rate": 4.966740576496675e-06, + "loss": 0.5292, + "step": 224 + }, + { + "epoch": 0.029984008528784648, + "grad_norm": 0.29830366659582297, + "learning_rate": 4.988913525498892e-06, + "loss": 0.3463, + "step": 225 + }, + { + "epoch": 0.03011727078891258, + "grad_norm": 0.3157231071285337, + "learning_rate": 5.011086474501109e-06, + "loss": 0.4991, + "step": 226 + }, + { + "epoch": 0.03025053304904051, + "grad_norm": 0.34051381909355893, + "learning_rate": 5.033259423503326e-06, + "loss": 0.4527, + "step": 227 + }, + { + "epoch": 0.030383795309168442, + "grad_norm": 0.31495168774044185, + "learning_rate": 5.055432372505543e-06, + "loss": 0.3956, + "step": 228 + }, + { + "epoch": 0.030517057569296374, + "grad_norm": 0.3835039517125173, + "learning_rate": 5.077605321507761e-06, + "loss": 0.4193, + "step": 229 + }, + { + "epoch": 0.030650319829424306, + "grad_norm": 0.3401837583699542, + "learning_rate": 5.099778270509978e-06, + "loss": 0.4914, + "step": 230 + }, + { + "epoch": 0.030783582089552237, + "grad_norm": 0.32922557625897686, + "learning_rate": 5.121951219512195e-06, + "loss": 0.4566, + "step": 231 + }, + { + "epoch": 0.03091684434968017, + "grad_norm": 0.44476585998227247, + "learning_rate": 5.1441241685144124e-06, + "loss": 0.5249, + "step": 232 + }, + { + "epoch": 0.0310501066098081, + "grad_norm": 0.30511308997266817, + "learning_rate": 5.1662971175166295e-06, + "loss": 0.4777, + "step": 233 + }, + { + "epoch": 0.031183368869936032, + "grad_norm": 0.309074623349281, + "learning_rate": 5.188470066518847e-06, + "loss": 0.5552, + "step": 234 + }, + { + "epoch": 0.031316631130063964, + "grad_norm": 0.31845398406735415, + "learning_rate": 5.2106430155210654e-06, + "loss": 0.4636, + "step": 235 + }, + { + "epoch": 0.0314498933901919, + "grad_norm": 0.2987641793755796, + "learning_rate": 5.2328159645232826e-06, + "loss": 0.3779, + "step": 236 + }, + { + "epoch": 0.03158315565031983, + "grad_norm": 0.3133375295959761, + "learning_rate": 5.2549889135255e-06, + "loss": 0.4394, + "step": 237 + }, + { + "epoch": 0.03171641791044776, + "grad_norm": 0.29323289035339284, + "learning_rate": 5.277161862527717e-06, + "loss": 0.3671, + "step": 238 + }, + { + "epoch": 0.03184968017057569, + "grad_norm": 0.3072089484223632, + "learning_rate": 5.299334811529934e-06, + "loss": 0.449, + "step": 239 + }, + { + "epoch": 0.031982942430703626, + "grad_norm": 0.2980208900099303, + "learning_rate": 5.321507760532151e-06, + "loss": 0.4774, + "step": 240 + }, + { + "epoch": 0.032116204690831554, + "grad_norm": 0.3201862974437162, + "learning_rate": 5.343680709534369e-06, + "loss": 0.3627, + "step": 241 + }, + { + "epoch": 0.03224946695095949, + "grad_norm": 0.2939655702332219, + "learning_rate": 5.365853658536586e-06, + "loss": 0.3802, + "step": 242 + }, + { + "epoch": 0.03238272921108742, + "grad_norm": 0.3326896649367625, + "learning_rate": 5.388026607538803e-06, + "loss": 0.4404, + "step": 243 + }, + { + "epoch": 0.03251599147121535, + "grad_norm": 0.31114781719262824, + "learning_rate": 5.41019955654102e-06, + "loss": 0.4507, + "step": 244 + }, + { + "epoch": 0.03264925373134328, + "grad_norm": 0.3093670240284899, + "learning_rate": 5.432372505543237e-06, + "loss": 0.3729, + "step": 245 + }, + { + "epoch": 0.032782515991471216, + "grad_norm": 0.306697624596574, + "learning_rate": 5.4545454545454545e-06, + "loss": 0.4171, + "step": 246 + }, + { + "epoch": 0.032915778251599144, + "grad_norm": 0.31531856817868703, + "learning_rate": 5.476718403547672e-06, + "loss": 0.4361, + "step": 247 + }, + { + "epoch": 0.03304904051172708, + "grad_norm": 0.3098526893349826, + "learning_rate": 5.4988913525498895e-06, + "loss": 0.3954, + "step": 248 + }, + { + "epoch": 0.03318230277185501, + "grad_norm": 0.3428347718344662, + "learning_rate": 5.5210643015521075e-06, + "loss": 0.5087, + "step": 249 + }, + { + "epoch": 0.03331556503198294, + "grad_norm": 0.33343766623699084, + "learning_rate": 5.5432372505543246e-06, + "loss": 0.4967, + "step": 250 + }, + { + "epoch": 0.03344882729211088, + "grad_norm": 0.3076549205653277, + "learning_rate": 5.565410199556542e-06, + "loss": 0.4708, + "step": 251 + }, + { + "epoch": 0.033582089552238806, + "grad_norm": 0.33973802399726266, + "learning_rate": 5.587583148558759e-06, + "loss": 0.4783, + "step": 252 + }, + { + "epoch": 0.03371535181236674, + "grad_norm": 0.32572806358588463, + "learning_rate": 5.609756097560977e-06, + "loss": 0.5312, + "step": 253 + }, + { + "epoch": 0.03384861407249467, + "grad_norm": 0.3412013883010886, + "learning_rate": 5.631929046563194e-06, + "loss": 0.4931, + "step": 254 + }, + { + "epoch": 0.033981876332622604, + "grad_norm": 0.3384347807282603, + "learning_rate": 5.654101995565411e-06, + "loss": 0.5364, + "step": 255 + }, + { + "epoch": 0.03411513859275053, + "grad_norm": 0.3247165794855813, + "learning_rate": 5.676274944567628e-06, + "loss": 0.4811, + "step": 256 + }, + { + "epoch": 0.03424840085287847, + "grad_norm": 0.3305767672754324, + "learning_rate": 5.698447893569845e-06, + "loss": 0.4321, + "step": 257 + }, + { + "epoch": 0.034381663113006396, + "grad_norm": 0.35460239397227394, + "learning_rate": 5.720620842572062e-06, + "loss": 0.5077, + "step": 258 + }, + { + "epoch": 0.03451492537313433, + "grad_norm": 0.30188378508246755, + "learning_rate": 5.742793791574279e-06, + "loss": 0.4238, + "step": 259 + }, + { + "epoch": 0.03464818763326226, + "grad_norm": 0.31142922687149416, + "learning_rate": 5.764966740576497e-06, + "loss": 0.3987, + "step": 260 + }, + { + "epoch": 0.034781449893390194, + "grad_norm": 0.32483331711925406, + "learning_rate": 5.787139689578714e-06, + "loss": 0.3996, + "step": 261 + }, + { + "epoch": 0.03491471215351812, + "grad_norm": 0.31701091165257655, + "learning_rate": 5.8093126385809315e-06, + "loss": 0.4426, + "step": 262 + }, + { + "epoch": 0.03504797441364606, + "grad_norm": 0.32693126662885835, + "learning_rate": 5.831485587583149e-06, + "loss": 0.4252, + "step": 263 + }, + { + "epoch": 0.035181236673773986, + "grad_norm": 0.3195145810771108, + "learning_rate": 5.853658536585366e-06, + "loss": 0.4377, + "step": 264 + }, + { + "epoch": 0.03531449893390192, + "grad_norm": 0.30796621779508404, + "learning_rate": 5.875831485587583e-06, + "loss": 0.4401, + "step": 265 + }, + { + "epoch": 0.03544776119402985, + "grad_norm": 0.31053450741463046, + "learning_rate": 5.898004434589802e-06, + "loss": 0.4022, + "step": 266 + }, + { + "epoch": 0.035581023454157784, + "grad_norm": 0.301796779191555, + "learning_rate": 5.920177383592019e-06, + "loss": 0.4714, + "step": 267 + }, + { + "epoch": 0.03571428571428571, + "grad_norm": 0.30361800699187913, + "learning_rate": 5.942350332594236e-06, + "loss": 0.3728, + "step": 268 + }, + { + "epoch": 0.03584754797441365, + "grad_norm": 0.3389898721866029, + "learning_rate": 5.964523281596453e-06, + "loss": 0.4362, + "step": 269 + }, + { + "epoch": 0.035980810234541576, + "grad_norm": 0.31137036829201387, + "learning_rate": 5.98669623059867e-06, + "loss": 0.364, + "step": 270 + }, + { + "epoch": 0.03611407249466951, + "grad_norm": 0.3575239307581398, + "learning_rate": 6.008869179600887e-06, + "loss": 0.5511, + "step": 271 + }, + { + "epoch": 0.03624733475479744, + "grad_norm": 0.3061039097266564, + "learning_rate": 6.031042128603105e-06, + "loss": 0.4631, + "step": 272 + }, + { + "epoch": 0.036380597014925374, + "grad_norm": 0.7117796618919405, + "learning_rate": 6.053215077605322e-06, + "loss": 0.3781, + "step": 273 + }, + { + "epoch": 0.0365138592750533, + "grad_norm": 0.32594211886323193, + "learning_rate": 6.075388026607539e-06, + "loss": 0.4143, + "step": 274 + }, + { + "epoch": 0.03664712153518124, + "grad_norm": 0.3072790877502273, + "learning_rate": 6.0975609756097564e-06, + "loss": 0.3719, + "step": 275 + }, + { + "epoch": 0.036780383795309166, + "grad_norm": 0.2944039136369746, + "learning_rate": 6.1197339246119735e-06, + "loss": 0.4095, + "step": 276 + }, + { + "epoch": 0.0369136460554371, + "grad_norm": 0.3175553523737841, + "learning_rate": 6.141906873614191e-06, + "loss": 0.5242, + "step": 277 + }, + { + "epoch": 0.03704690831556503, + "grad_norm": 0.33556174680774, + "learning_rate": 6.164079822616409e-06, + "loss": 0.4386, + "step": 278 + }, + { + "epoch": 0.037180170575692964, + "grad_norm": 0.3133747808368858, + "learning_rate": 6.186252771618626e-06, + "loss": 0.4839, + "step": 279 + }, + { + "epoch": 0.03731343283582089, + "grad_norm": 0.3220717616241582, + "learning_rate": 6.208425720620843e-06, + "loss": 0.468, + "step": 280 + }, + { + "epoch": 0.03744669509594883, + "grad_norm": 0.3322495054557286, + "learning_rate": 6.23059866962306e-06, + "loss": 0.4822, + "step": 281 + }, + { + "epoch": 0.03757995735607676, + "grad_norm": 0.33457521046805283, + "learning_rate": 6.252771618625277e-06, + "loss": 0.4504, + "step": 282 + }, + { + "epoch": 0.03771321961620469, + "grad_norm": 0.3087228932997992, + "learning_rate": 6.274944567627494e-06, + "loss": 0.4185, + "step": 283 + }, + { + "epoch": 0.037846481876332626, + "grad_norm": 0.31817676342315476, + "learning_rate": 6.297117516629713e-06, + "loss": 0.4465, + "step": 284 + }, + { + "epoch": 0.037979744136460554, + "grad_norm": 0.33619439746273494, + "learning_rate": 6.31929046563193e-06, + "loss": 0.4668, + "step": 285 + }, + { + "epoch": 0.03811300639658849, + "grad_norm": 0.3053105988942183, + "learning_rate": 6.341463414634147e-06, + "loss": 0.375, + "step": 286 + }, + { + "epoch": 0.03824626865671642, + "grad_norm": 0.34713604225375233, + "learning_rate": 6.363636363636364e-06, + "loss": 0.4248, + "step": 287 + }, + { + "epoch": 0.03837953091684435, + "grad_norm": 0.3378715202538644, + "learning_rate": 6.385809312638581e-06, + "loss": 0.4398, + "step": 288 + }, + { + "epoch": 0.03851279317697228, + "grad_norm": 0.3379167811481556, + "learning_rate": 6.4079822616407984e-06, + "loss": 0.4176, + "step": 289 + }, + { + "epoch": 0.038646055437100216, + "grad_norm": 0.3341440753229213, + "learning_rate": 6.430155210643016e-06, + "loss": 0.4499, + "step": 290 + }, + { + "epoch": 0.038779317697228144, + "grad_norm": 0.33134801427041355, + "learning_rate": 6.4523281596452335e-06, + "loss": 0.3774, + "step": 291 + }, + { + "epoch": 0.03891257995735608, + "grad_norm": 0.32940988748563643, + "learning_rate": 6.474501108647451e-06, + "loss": 0.4339, + "step": 292 + }, + { + "epoch": 0.03904584221748401, + "grad_norm": 0.32797390480579763, + "learning_rate": 6.496674057649668e-06, + "loss": 0.4117, + "step": 293 + }, + { + "epoch": 0.03917910447761194, + "grad_norm": 0.3296194612218913, + "learning_rate": 6.518847006651885e-06, + "loss": 0.5277, + "step": 294 + }, + { + "epoch": 0.03931236673773987, + "grad_norm": 0.3375682292176925, + "learning_rate": 6.541019955654102e-06, + "loss": 0.496, + "step": 295 + }, + { + "epoch": 0.039445628997867806, + "grad_norm": 0.3496589878642477, + "learning_rate": 6.563192904656321e-06, + "loss": 0.5891, + "step": 296 + }, + { + "epoch": 0.039578891257995734, + "grad_norm": 0.3125492194724814, + "learning_rate": 6.585365853658538e-06, + "loss": 0.4493, + "step": 297 + }, + { + "epoch": 0.03971215351812367, + "grad_norm": 0.30991277865372, + "learning_rate": 6.607538802660755e-06, + "loss": 0.3819, + "step": 298 + }, + { + "epoch": 0.0398454157782516, + "grad_norm": 0.35071633449264533, + "learning_rate": 6.629711751662972e-06, + "loss": 0.4499, + "step": 299 + }, + { + "epoch": 0.03997867803837953, + "grad_norm": 0.3135103846583698, + "learning_rate": 6.651884700665189e-06, + "loss": 0.3843, + "step": 300 + }, + { + "epoch": 0.04011194029850746, + "grad_norm": 0.292612523601128, + "learning_rate": 6.674057649667406e-06, + "loss": 0.3809, + "step": 301 + }, + { + "epoch": 0.040245202558635396, + "grad_norm": 0.3155227907945306, + "learning_rate": 6.696230598669624e-06, + "loss": 0.4149, + "step": 302 + }, + { + "epoch": 0.040378464818763324, + "grad_norm": 0.34036471270335167, + "learning_rate": 6.718403547671841e-06, + "loss": 0.511, + "step": 303 + }, + { + "epoch": 0.04051172707889126, + "grad_norm": 0.3757492916064218, + "learning_rate": 6.740576496674058e-06, + "loss": 0.468, + "step": 304 + }, + { + "epoch": 0.04064498933901919, + "grad_norm": 0.3529731875383806, + "learning_rate": 6.7627494456762755e-06, + "loss": 0.4575, + "step": 305 + }, + { + "epoch": 0.04077825159914712, + "grad_norm": 0.31469216703456965, + "learning_rate": 6.784922394678493e-06, + "loss": 0.4332, + "step": 306 + }, + { + "epoch": 0.04091151385927505, + "grad_norm": 0.3177822791626496, + "learning_rate": 6.80709534368071e-06, + "loss": 0.4479, + "step": 307 + }, + { + "epoch": 0.041044776119402986, + "grad_norm": 0.3495732767005663, + "learning_rate": 6.829268292682928e-06, + "loss": 0.4153, + "step": 308 + }, + { + "epoch": 0.041178038379530914, + "grad_norm": 0.322926166655043, + "learning_rate": 6.851441241685145e-06, + "loss": 0.4253, + "step": 309 + }, + { + "epoch": 0.04131130063965885, + "grad_norm": 0.3573429098984255, + "learning_rate": 6.873614190687362e-06, + "loss": 0.5162, + "step": 310 + }, + { + "epoch": 0.04144456289978678, + "grad_norm": 0.33713692560080477, + "learning_rate": 6.895787139689579e-06, + "loss": 0.4087, + "step": 311 + }, + { + "epoch": 0.04157782515991471, + "grad_norm": 0.3682267225125015, + "learning_rate": 6.917960088691796e-06, + "loss": 0.4547, + "step": 312 + }, + { + "epoch": 0.04171108742004265, + "grad_norm": 0.3347201490280819, + "learning_rate": 6.940133037694013e-06, + "loss": 0.4104, + "step": 313 + }, + { + "epoch": 0.041844349680170576, + "grad_norm": 0.3441108350827023, + "learning_rate": 6.962305986696232e-06, + "loss": 0.4162, + "step": 314 + }, + { + "epoch": 0.04197761194029851, + "grad_norm": 0.34253194737855264, + "learning_rate": 6.984478935698449e-06, + "loss": 0.4072, + "step": 315 + }, + { + "epoch": 0.04211087420042644, + "grad_norm": 0.35283926416583844, + "learning_rate": 7.006651884700666e-06, + "loss": 0.4332, + "step": 316 + }, + { + "epoch": 0.042244136460554374, + "grad_norm": 0.34031735175153904, + "learning_rate": 7.028824833702883e-06, + "loss": 0.4339, + "step": 317 + }, + { + "epoch": 0.0423773987206823, + "grad_norm": 0.3350233531140661, + "learning_rate": 7.0509977827051e-06, + "loss": 0.4203, + "step": 318 + }, + { + "epoch": 0.04251066098081024, + "grad_norm": 0.3379073253502789, + "learning_rate": 7.0731707317073175e-06, + "loss": 0.4472, + "step": 319 + }, + { + "epoch": 0.042643923240938165, + "grad_norm": 0.34467141505767207, + "learning_rate": 7.0953436807095355e-06, + "loss": 0.4392, + "step": 320 + }, + { + "epoch": 0.0427771855010661, + "grad_norm": 0.3346911544945433, + "learning_rate": 7.117516629711753e-06, + "loss": 0.4171, + "step": 321 + }, + { + "epoch": 0.04291044776119403, + "grad_norm": 0.3487900478760954, + "learning_rate": 7.13968957871397e-06, + "loss": 0.4294, + "step": 322 + }, + { + "epoch": 0.043043710021321964, + "grad_norm": 0.3441194479445481, + "learning_rate": 7.161862527716187e-06, + "loss": 0.4199, + "step": 323 + }, + { + "epoch": 0.04317697228144989, + "grad_norm": 0.35416773641189164, + "learning_rate": 7.184035476718404e-06, + "loss": 0.5506, + "step": 324 + }, + { + "epoch": 0.04331023454157783, + "grad_norm": 0.3439199856541361, + "learning_rate": 7.206208425720621e-06, + "loss": 0.4373, + "step": 325 + }, + { + "epoch": 0.043443496801705755, + "grad_norm": 0.3117594955828615, + "learning_rate": 7.228381374722838e-06, + "loss": 0.4238, + "step": 326 + }, + { + "epoch": 0.04357675906183369, + "grad_norm": 0.3299447127892656, + "learning_rate": 7.250554323725056e-06, + "loss": 0.5219, + "step": 327 + }, + { + "epoch": 0.04371002132196162, + "grad_norm": 0.34380384479777343, + "learning_rate": 7.272727272727273e-06, + "loss": 0.4413, + "step": 328 + }, + { + "epoch": 0.043843283582089554, + "grad_norm": 0.3246769668210682, + "learning_rate": 7.29490022172949e-06, + "loss": 0.4995, + "step": 329 + }, + { + "epoch": 0.04397654584221748, + "grad_norm": 0.3188032762251944, + "learning_rate": 7.317073170731707e-06, + "loss": 0.4946, + "step": 330 + }, + { + "epoch": 0.04410980810234542, + "grad_norm": 0.32741997762696323, + "learning_rate": 7.3392461197339245e-06, + "loss": 0.4139, + "step": 331 + }, + { + "epoch": 0.044243070362473345, + "grad_norm": 0.32957065441051187, + "learning_rate": 7.361419068736142e-06, + "loss": 0.4046, + "step": 332 + }, + { + "epoch": 0.04437633262260128, + "grad_norm": 0.3277210316738401, + "learning_rate": 7.38359201773836e-06, + "loss": 0.3846, + "step": 333 + }, + { + "epoch": 0.04450959488272921, + "grad_norm": 0.351900644297163, + "learning_rate": 7.4057649667405775e-06, + "loss": 0.4728, + "step": 334 + }, + { + "epoch": 0.044642857142857144, + "grad_norm": 0.33666315126269175, + "learning_rate": 7.427937915742795e-06, + "loss": 0.5955, + "step": 335 + }, + { + "epoch": 0.04477611940298507, + "grad_norm": 0.33143113176127237, + "learning_rate": 7.450110864745012e-06, + "loss": 0.4764, + "step": 336 + }, + { + "epoch": 0.04490938166311301, + "grad_norm": 0.3247502117162239, + "learning_rate": 7.472283813747229e-06, + "loss": 0.42, + "step": 337 + }, + { + "epoch": 0.045042643923240935, + "grad_norm": 0.34382353392341347, + "learning_rate": 7.494456762749446e-06, + "loss": 0.4492, + "step": 338 + }, + { + "epoch": 0.04517590618336887, + "grad_norm": 0.38992325143678846, + "learning_rate": 7.516629711751664e-06, + "loss": 0.3847, + "step": 339 + }, + { + "epoch": 0.0453091684434968, + "grad_norm": 0.3760208373348356, + "learning_rate": 7.538802660753881e-06, + "loss": 0.4467, + "step": 340 + }, + { + "epoch": 0.045442430703624734, + "grad_norm": 0.33249854929917677, + "learning_rate": 7.560975609756098e-06, + "loss": 0.4402, + "step": 341 + }, + { + "epoch": 0.04557569296375266, + "grad_norm": 0.3806857709167802, + "learning_rate": 7.583148558758315e-06, + "loss": 0.413, + "step": 342 + }, + { + "epoch": 0.0457089552238806, + "grad_norm": 0.34166486931900336, + "learning_rate": 7.605321507760532e-06, + "loss": 0.4379, + "step": 343 + }, + { + "epoch": 0.04584221748400853, + "grad_norm": 0.33808965837455285, + "learning_rate": 7.627494456762749e-06, + "loss": 0.4307, + "step": 344 + }, + { + "epoch": 0.04597547974413646, + "grad_norm": 0.3403115512834847, + "learning_rate": 7.649667405764967e-06, + "loss": 0.4297, + "step": 345 + }, + { + "epoch": 0.046108742004264396, + "grad_norm": 0.3550628707066635, + "learning_rate": 7.671840354767184e-06, + "loss": 0.4493, + "step": 346 + }, + { + "epoch": 0.046242004264392324, + "grad_norm": 0.343294636728275, + "learning_rate": 7.694013303769402e-06, + "loss": 0.5878, + "step": 347 + }, + { + "epoch": 0.04637526652452026, + "grad_norm": 0.3191420231602692, + "learning_rate": 7.716186252771619e-06, + "loss": 0.3866, + "step": 348 + }, + { + "epoch": 0.04650852878464819, + "grad_norm": 1.6249788880516012, + "learning_rate": 7.738359201773836e-06, + "loss": 0.3732, + "step": 349 + }, + { + "epoch": 0.04664179104477612, + "grad_norm": 0.3563949899388172, + "learning_rate": 7.760532150776053e-06, + "loss": 0.3699, + "step": 350 + }, + { + "epoch": 0.04677505330490405, + "grad_norm": 0.35403148372300786, + "learning_rate": 7.782705099778272e-06, + "loss": 0.4395, + "step": 351 + }, + { + "epoch": 0.046908315565031986, + "grad_norm": 0.35823463586646226, + "learning_rate": 7.804878048780489e-06, + "loss": 0.4261, + "step": 352 + }, + { + "epoch": 0.047041577825159914, + "grad_norm": 0.3334874292666243, + "learning_rate": 7.827050997782706e-06, + "loss": 0.4296, + "step": 353 + }, + { + "epoch": 0.04717484008528785, + "grad_norm": 0.3801659622217095, + "learning_rate": 7.849223946784923e-06, + "loss": 0.4273, + "step": 354 + }, + { + "epoch": 0.04730810234541578, + "grad_norm": 0.342477203175331, + "learning_rate": 7.87139689578714e-06, + "loss": 0.4271, + "step": 355 + }, + { + "epoch": 0.04744136460554371, + "grad_norm": 0.3357174125555028, + "learning_rate": 7.893569844789357e-06, + "loss": 0.4323, + "step": 356 + }, + { + "epoch": 0.04757462686567164, + "grad_norm": 0.36949995172053535, + "learning_rate": 7.915742793791576e-06, + "loss": 0.4875, + "step": 357 + }, + { + "epoch": 0.047707889125799575, + "grad_norm": 0.34511677951954006, + "learning_rate": 7.937915742793793e-06, + "loss": 0.4388, + "step": 358 + }, + { + "epoch": 0.047841151385927504, + "grad_norm": 0.3383416100956853, + "learning_rate": 7.96008869179601e-06, + "loss": 0.3713, + "step": 359 + }, + { + "epoch": 0.04797441364605544, + "grad_norm": 0.33699463962860504, + "learning_rate": 7.982261640798227e-06, + "loss": 0.4059, + "step": 360 + }, + { + "epoch": 0.04810767590618337, + "grad_norm": 0.334947241227542, + "learning_rate": 8.004434589800444e-06, + "loss": 0.4533, + "step": 361 + }, + { + "epoch": 0.0482409381663113, + "grad_norm": 0.3614764781919695, + "learning_rate": 8.026607538802662e-06, + "loss": 0.4314, + "step": 362 + }, + { + "epoch": 0.04837420042643923, + "grad_norm": 0.32487364692404874, + "learning_rate": 8.048780487804879e-06, + "loss": 0.4829, + "step": 363 + }, + { + "epoch": 0.048507462686567165, + "grad_norm": 0.32596477953870256, + "learning_rate": 8.070953436807096e-06, + "loss": 0.4748, + "step": 364 + }, + { + "epoch": 0.048640724946695094, + "grad_norm": 0.3527060004684179, + "learning_rate": 8.093126385809313e-06, + "loss": 0.4028, + "step": 365 + }, + { + "epoch": 0.04877398720682303, + "grad_norm": 0.30872392077952737, + "learning_rate": 8.11529933481153e-06, + "loss": 0.4939, + "step": 366 + }, + { + "epoch": 0.04890724946695096, + "grad_norm": 0.32866091528623687, + "learning_rate": 8.137472283813747e-06, + "loss": 0.3921, + "step": 367 + }, + { + "epoch": 0.04904051172707889, + "grad_norm": 0.31441076398167805, + "learning_rate": 8.159645232815964e-06, + "loss": 0.3896, + "step": 368 + }, + { + "epoch": 0.04917377398720682, + "grad_norm": 0.3152230673377294, + "learning_rate": 8.181818181818183e-06, + "loss": 0.4442, + "step": 369 + }, + { + "epoch": 0.049307036247334755, + "grad_norm": 0.31228572356697, + "learning_rate": 8.2039911308204e-06, + "loss": 0.4004, + "step": 370 + }, + { + "epoch": 0.049440298507462684, + "grad_norm": 0.3255189833099599, + "learning_rate": 8.226164079822617e-06, + "loss": 0.3464, + "step": 371 + }, + { + "epoch": 0.04957356076759062, + "grad_norm": 0.30725897104419103, + "learning_rate": 8.248337028824834e-06, + "loss": 0.4036, + "step": 372 + }, + { + "epoch": 0.04970682302771855, + "grad_norm": 0.3543644361668986, + "learning_rate": 8.270509977827051e-06, + "loss": 0.5151, + "step": 373 + }, + { + "epoch": 0.04984008528784648, + "grad_norm": 0.3080885257526926, + "learning_rate": 8.292682926829268e-06, + "loss": 0.3466, + "step": 374 + }, + { + "epoch": 0.04997334754797441, + "grad_norm": 0.3174140368663189, + "learning_rate": 8.314855875831487e-06, + "loss": 0.3854, + "step": 375 + }, + { + "epoch": 0.050106609808102345, + "grad_norm": 0.3512625963955434, + "learning_rate": 8.337028824833704e-06, + "loss": 0.4264, + "step": 376 + }, + { + "epoch": 0.05023987206823028, + "grad_norm": 0.33053771182141134, + "learning_rate": 8.359201773835921e-06, + "loss": 0.4264, + "step": 377 + }, + { + "epoch": 0.05037313432835821, + "grad_norm": 0.3233026660380627, + "learning_rate": 8.381374722838139e-06, + "loss": 0.4133, + "step": 378 + }, + { + "epoch": 0.050506396588486144, + "grad_norm": 0.3600130395871304, + "learning_rate": 8.403547671840356e-06, + "loss": 0.4588, + "step": 379 + }, + { + "epoch": 0.05063965884861407, + "grad_norm": 0.3264405118104151, + "learning_rate": 8.425720620842573e-06, + "loss": 0.4274, + "step": 380 + }, + { + "epoch": 0.05077292110874201, + "grad_norm": 0.3743989489471016, + "learning_rate": 8.44789356984479e-06, + "loss": 0.522, + "step": 381 + }, + { + "epoch": 0.050906183368869935, + "grad_norm": 0.3516567960741937, + "learning_rate": 8.470066518847007e-06, + "loss": 0.4494, + "step": 382 + }, + { + "epoch": 0.05103944562899787, + "grad_norm": 0.35971286253617624, + "learning_rate": 8.492239467849224e-06, + "loss": 0.4352, + "step": 383 + }, + { + "epoch": 0.0511727078891258, + "grad_norm": 0.36039169724516895, + "learning_rate": 8.514412416851441e-06, + "loss": 0.4664, + "step": 384 + }, + { + "epoch": 0.051305970149253734, + "grad_norm": 0.342137255984797, + "learning_rate": 8.536585365853658e-06, + "loss": 0.428, + "step": 385 + }, + { + "epoch": 0.05143923240938166, + "grad_norm": 0.31702574103166004, + "learning_rate": 8.558758314855875e-06, + "loss": 0.3984, + "step": 386 + }, + { + "epoch": 0.0515724946695096, + "grad_norm": 0.37064179321266205, + "learning_rate": 8.580931263858093e-06, + "loss": 0.4126, + "step": 387 + }, + { + "epoch": 0.051705756929637525, + "grad_norm": 0.3391233732903581, + "learning_rate": 8.603104212860311e-06, + "loss": 0.4208, + "step": 388 + }, + { + "epoch": 0.05183901918976546, + "grad_norm": 0.36009773079704105, + "learning_rate": 8.625277161862528e-06, + "loss": 0.5157, + "step": 389 + }, + { + "epoch": 0.05197228144989339, + "grad_norm": 0.32549179617371293, + "learning_rate": 8.647450110864746e-06, + "loss": 0.4604, + "step": 390 + }, + { + "epoch": 0.052105543710021324, + "grad_norm": 0.3299472791470057, + "learning_rate": 8.669623059866963e-06, + "loss": 0.3859, + "step": 391 + }, + { + "epoch": 0.05223880597014925, + "grad_norm": 0.3735721686285961, + "learning_rate": 8.69179600886918e-06, + "loss": 0.4248, + "step": 392 + }, + { + "epoch": 0.05237206823027719, + "grad_norm": 0.34517731427219867, + "learning_rate": 8.713968957871397e-06, + "loss": 0.4399, + "step": 393 + }, + { + "epoch": 0.052505330490405115, + "grad_norm": 0.349550309040036, + "learning_rate": 8.736141906873616e-06, + "loss": 0.4137, + "step": 394 + }, + { + "epoch": 0.05263859275053305, + "grad_norm": 0.34478781521396445, + "learning_rate": 8.758314855875833e-06, + "loss": 0.4273, + "step": 395 + }, + { + "epoch": 0.05277185501066098, + "grad_norm": 0.3468877924442863, + "learning_rate": 8.78048780487805e-06, + "loss": 0.4369, + "step": 396 + }, + { + "epoch": 0.052905117270788914, + "grad_norm": 0.3218635586024508, + "learning_rate": 8.802660753880267e-06, + "loss": 0.3544, + "step": 397 + }, + { + "epoch": 0.05303837953091684, + "grad_norm": 0.38196461927180064, + "learning_rate": 8.824833702882484e-06, + "loss": 0.4821, + "step": 398 + }, + { + "epoch": 0.05317164179104478, + "grad_norm": 0.31924749802966607, + "learning_rate": 8.847006651884701e-06, + "loss": 0.4085, + "step": 399 + }, + { + "epoch": 0.053304904051172705, + "grad_norm": 0.36139976085604125, + "learning_rate": 8.869179600886918e-06, + "loss": 0.4452, + "step": 400 + }, + { + "epoch": 0.05343816631130064, + "grad_norm": 0.33499664188005496, + "learning_rate": 8.891352549889135e-06, + "loss": 0.3985, + "step": 401 + }, + { + "epoch": 0.05357142857142857, + "grad_norm": 0.379707015953988, + "learning_rate": 8.913525498891353e-06, + "loss": 0.4741, + "step": 402 + }, + { + "epoch": 0.053704690831556504, + "grad_norm": 0.3307831516390236, + "learning_rate": 8.93569844789357e-06, + "loss": 0.4161, + "step": 403 + }, + { + "epoch": 0.05383795309168443, + "grad_norm": 0.32249940003762806, + "learning_rate": 8.957871396895787e-06, + "loss": 0.4294, + "step": 404 + }, + { + "epoch": 0.05397121535181237, + "grad_norm": 0.36203583469911105, + "learning_rate": 8.980044345898006e-06, + "loss": 0.3991, + "step": 405 + }, + { + "epoch": 0.054104477611940295, + "grad_norm": 0.34386495204924244, + "learning_rate": 9.002217294900223e-06, + "loss": 0.4832, + "step": 406 + }, + { + "epoch": 0.05423773987206823, + "grad_norm": 0.339220072813432, + "learning_rate": 9.02439024390244e-06, + "loss": 0.4317, + "step": 407 + }, + { + "epoch": 0.054371002132196165, + "grad_norm": 0.3583797536831599, + "learning_rate": 9.046563192904657e-06, + "loss": 0.4114, + "step": 408 + }, + { + "epoch": 0.054504264392324094, + "grad_norm": 0.40299502351701677, + "learning_rate": 9.068736141906874e-06, + "loss": 0.45, + "step": 409 + }, + { + "epoch": 0.05463752665245203, + "grad_norm": 0.3323557402536994, + "learning_rate": 9.090909090909091e-06, + "loss": 0.4122, + "step": 410 + }, + { + "epoch": 0.05477078891257996, + "grad_norm": 0.35974244219330154, + "learning_rate": 9.113082039911308e-06, + "loss": 0.441, + "step": 411 + }, + { + "epoch": 0.05490405117270789, + "grad_norm": 0.33129996176447357, + "learning_rate": 9.135254988913527e-06, + "loss": 0.3885, + "step": 412 + }, + { + "epoch": 0.05503731343283582, + "grad_norm": 0.3249296077826736, + "learning_rate": 9.157427937915744e-06, + "loss": 0.4027, + "step": 413 + }, + { + "epoch": 0.055170575692963755, + "grad_norm": 0.33380083832157426, + "learning_rate": 9.179600886917961e-06, + "loss": 0.3731, + "step": 414 + }, + { + "epoch": 0.055303837953091683, + "grad_norm": 0.3350580397494292, + "learning_rate": 9.201773835920178e-06, + "loss": 0.3811, + "step": 415 + }, + { + "epoch": 0.05543710021321962, + "grad_norm": 0.35490404677864645, + "learning_rate": 9.223946784922395e-06, + "loss": 0.4325, + "step": 416 + }, + { + "epoch": 0.05557036247334755, + "grad_norm": 0.36351973128467385, + "learning_rate": 9.246119733924612e-06, + "loss": 0.4991, + "step": 417 + }, + { + "epoch": 0.05570362473347548, + "grad_norm": 0.33003437397397967, + "learning_rate": 9.268292682926831e-06, + "loss": 0.4292, + "step": 418 + }, + { + "epoch": 0.05583688699360341, + "grad_norm": 0.32517897410219604, + "learning_rate": 9.290465631929048e-06, + "loss": 0.4444, + "step": 419 + }, + { + "epoch": 0.055970149253731345, + "grad_norm": 0.3573694274710754, + "learning_rate": 9.312638580931265e-06, + "loss": 0.4121, + "step": 420 + }, + { + "epoch": 0.05610341151385927, + "grad_norm": 0.319537915079207, + "learning_rate": 9.334811529933483e-06, + "loss": 0.4344, + "step": 421 + }, + { + "epoch": 0.05623667377398721, + "grad_norm": 0.34071485588234635, + "learning_rate": 9.3569844789357e-06, + "loss": 0.4919, + "step": 422 + }, + { + "epoch": 0.05636993603411514, + "grad_norm": 0.33214753931919494, + "learning_rate": 9.379157427937917e-06, + "loss": 0.3792, + "step": 423 + }, + { + "epoch": 0.05650319829424307, + "grad_norm": 0.32393946669192586, + "learning_rate": 9.401330376940134e-06, + "loss": 0.4027, + "step": 424 + }, + { + "epoch": 0.056636460554371, + "grad_norm": 0.338876356305499, + "learning_rate": 9.423503325942351e-06, + "loss": 0.4227, + "step": 425 + }, + { + "epoch": 0.056769722814498935, + "grad_norm": 0.3362484129015652, + "learning_rate": 9.445676274944568e-06, + "loss": 0.4594, + "step": 426 + }, + { + "epoch": 0.05690298507462686, + "grad_norm": 0.36645990578202553, + "learning_rate": 9.467849223946785e-06, + "loss": 0.3899, + "step": 427 + }, + { + "epoch": 0.0570362473347548, + "grad_norm": 0.33175136836239577, + "learning_rate": 9.490022172949002e-06, + "loss": 0.4327, + "step": 428 + }, + { + "epoch": 0.05716950959488273, + "grad_norm": 0.3476821233244116, + "learning_rate": 9.51219512195122e-06, + "loss": 0.4773, + "step": 429 + }, + { + "epoch": 0.05730277185501066, + "grad_norm": 0.34352739833815843, + "learning_rate": 9.534368070953438e-06, + "loss": 0.4195, + "step": 430 + }, + { + "epoch": 0.05743603411513859, + "grad_norm": 0.3192499849941525, + "learning_rate": 9.556541019955655e-06, + "loss": 0.3943, + "step": 431 + }, + { + "epoch": 0.057569296375266525, + "grad_norm": 0.31487635366294825, + "learning_rate": 9.578713968957872e-06, + "loss": 0.3883, + "step": 432 + }, + { + "epoch": 0.05770255863539445, + "grad_norm": 0.3183426171921883, + "learning_rate": 9.60088691796009e-06, + "loss": 0.4215, + "step": 433 + }, + { + "epoch": 0.05783582089552239, + "grad_norm": 0.33701560575592054, + "learning_rate": 9.623059866962307e-06, + "loss": 0.4369, + "step": 434 + }, + { + "epoch": 0.05796908315565032, + "grad_norm": 0.31145480571280576, + "learning_rate": 9.645232815964524e-06, + "loss": 0.3682, + "step": 435 + }, + { + "epoch": 0.05810234541577825, + "grad_norm": 0.3350229879577721, + "learning_rate": 9.667405764966743e-06, + "loss": 0.4638, + "step": 436 + }, + { + "epoch": 0.05823560767590618, + "grad_norm": 0.3442161072426591, + "learning_rate": 9.68957871396896e-06, + "loss": 0.4028, + "step": 437 + }, + { + "epoch": 0.058368869936034115, + "grad_norm": 0.33533305378224976, + "learning_rate": 9.711751662971177e-06, + "loss": 0.4093, + "step": 438 + }, + { + "epoch": 0.05850213219616205, + "grad_norm": 0.3211700905534748, + "learning_rate": 9.733924611973394e-06, + "loss": 0.366, + "step": 439 + }, + { + "epoch": 0.05863539445628998, + "grad_norm": 0.3518297719374847, + "learning_rate": 9.756097560975611e-06, + "loss": 0.4315, + "step": 440 + }, + { + "epoch": 0.058768656716417914, + "grad_norm": 0.35737085981709266, + "learning_rate": 9.778270509977828e-06, + "loss": 0.4829, + "step": 441 + }, + { + "epoch": 0.05890191897654584, + "grad_norm": 0.32093861123716605, + "learning_rate": 9.800443458980045e-06, + "loss": 0.4827, + "step": 442 + }, + { + "epoch": 0.05903518123667378, + "grad_norm": 0.36741890153926404, + "learning_rate": 9.822616407982262e-06, + "loss": 0.4604, + "step": 443 + }, + { + "epoch": 0.059168443496801705, + "grad_norm": 0.32802491879519347, + "learning_rate": 9.84478935698448e-06, + "loss": 0.4648, + "step": 444 + }, + { + "epoch": 0.05930170575692964, + "grad_norm": 0.340645748199214, + "learning_rate": 9.866962305986696e-06, + "loss": 0.459, + "step": 445 + }, + { + "epoch": 0.05943496801705757, + "grad_norm": 0.3198334703424997, + "learning_rate": 9.889135254988914e-06, + "loss": 0.5145, + "step": 446 + }, + { + "epoch": 0.059568230277185504, + "grad_norm": 0.3448573900092419, + "learning_rate": 9.91130820399113e-06, + "loss": 0.4293, + "step": 447 + }, + { + "epoch": 0.05970149253731343, + "grad_norm": 0.3271094795764444, + "learning_rate": 9.93348115299335e-06, + "loss": 0.4216, + "step": 448 + }, + { + "epoch": 0.05983475479744137, + "grad_norm": 0.3555685002851802, + "learning_rate": 9.955654101995567e-06, + "loss": 0.509, + "step": 449 + }, + { + "epoch": 0.059968017057569295, + "grad_norm": 0.345529325481297, + "learning_rate": 9.977827050997784e-06, + "loss": 0.53, + "step": 450 + }, + { + "epoch": 0.06010127931769723, + "grad_norm": 0.3305552775113965, + "learning_rate": 1e-05, + "loss": 0.4431, + "step": 451 + }, + { + "epoch": 0.06023454157782516, + "grad_norm": 0.32303644022656985, + "learning_rate": 9.999999949302172e-06, + "loss": 0.4372, + "step": 452 + }, + { + "epoch": 0.06036780383795309, + "grad_norm": 0.31569443135556846, + "learning_rate": 9.999999797208685e-06, + "loss": 0.376, + "step": 453 + }, + { + "epoch": 0.06050106609808102, + "grad_norm": 0.33021596364727035, + "learning_rate": 9.999999543719544e-06, + "loss": 0.4548, + "step": 454 + }, + { + "epoch": 0.06063432835820896, + "grad_norm": 0.3557882916109362, + "learning_rate": 9.999999188834755e-06, + "loss": 0.4911, + "step": 455 + }, + { + "epoch": 0.060767590618336885, + "grad_norm": 0.3328416739887454, + "learning_rate": 9.999998732554322e-06, + "loss": 0.448, + "step": 456 + }, + { + "epoch": 0.06090085287846482, + "grad_norm": 0.3622764638615193, + "learning_rate": 9.999998174878257e-06, + "loss": 0.4677, + "step": 457 + }, + { + "epoch": 0.06103411513859275, + "grad_norm": 0.36151264227885416, + "learning_rate": 9.99999751580657e-06, + "loss": 0.5666, + "step": 458 + }, + { + "epoch": 0.06116737739872068, + "grad_norm": 0.3494401115457736, + "learning_rate": 9.999996755339276e-06, + "loss": 0.4632, + "step": 459 + }, + { + "epoch": 0.06130063965884861, + "grad_norm": 0.3469825364689266, + "learning_rate": 9.99999589347639e-06, + "loss": 0.4278, + "step": 460 + }, + { + "epoch": 0.06143390191897655, + "grad_norm": 0.33237831064412915, + "learning_rate": 9.999994930217926e-06, + "loss": 0.3792, + "step": 461 + }, + { + "epoch": 0.061567164179104475, + "grad_norm": 0.3366812539544897, + "learning_rate": 9.999993865563909e-06, + "loss": 0.3998, + "step": 462 + }, + { + "epoch": 0.06170042643923241, + "grad_norm": 0.341588125134107, + "learning_rate": 9.999992699514359e-06, + "loss": 0.5367, + "step": 463 + }, + { + "epoch": 0.06183368869936034, + "grad_norm": 0.34365725879511555, + "learning_rate": 9.999991432069295e-06, + "loss": 0.4586, + "step": 464 + }, + { + "epoch": 0.06196695095948827, + "grad_norm": 0.37160090472118207, + "learning_rate": 9.999990063228748e-06, + "loss": 0.4563, + "step": 465 + }, + { + "epoch": 0.0621002132196162, + "grad_norm": 0.34439375787062576, + "learning_rate": 9.999988592992745e-06, + "loss": 0.4563, + "step": 466 + }, + { + "epoch": 0.06223347547974414, + "grad_norm": 0.3458780015288555, + "learning_rate": 9.999987021361316e-06, + "loss": 0.4184, + "step": 467 + }, + { + "epoch": 0.062366737739872065, + "grad_norm": 0.41344445064365504, + "learning_rate": 9.99998534833449e-06, + "loss": 0.4267, + "step": 468 + }, + { + "epoch": 0.0625, + "grad_norm": 0.3731285740908006, + "learning_rate": 9.9999835739123e-06, + "loss": 0.4484, + "step": 469 + }, + { + "epoch": 0.06263326226012793, + "grad_norm": 0.3347889238831603, + "learning_rate": 9.999981698094788e-06, + "loss": 0.4037, + "step": 470 + }, + { + "epoch": 0.06276652452025587, + "grad_norm": 0.36476657917007077, + "learning_rate": 9.999979720881988e-06, + "loss": 0.4379, + "step": 471 + }, + { + "epoch": 0.0628997867803838, + "grad_norm": 0.3554456225634817, + "learning_rate": 9.999977642273941e-06, + "loss": 0.4876, + "step": 472 + }, + { + "epoch": 0.06303304904051173, + "grad_norm": 0.349745859795326, + "learning_rate": 9.999975462270688e-06, + "loss": 0.4714, + "step": 473 + }, + { + "epoch": 0.06316631130063965, + "grad_norm": 0.33155458791510084, + "learning_rate": 9.999973180872275e-06, + "loss": 0.4246, + "step": 474 + }, + { + "epoch": 0.0632995735607676, + "grad_norm": 0.3448147631481317, + "learning_rate": 9.999970798078748e-06, + "loss": 0.5143, + "step": 475 + }, + { + "epoch": 0.06343283582089553, + "grad_norm": 0.3262718513745306, + "learning_rate": 9.999968313890154e-06, + "loss": 0.4848, + "step": 476 + }, + { + "epoch": 0.06356609808102345, + "grad_norm": 0.326493567012079, + "learning_rate": 9.999965728306545e-06, + "loss": 0.4611, + "step": 477 + }, + { + "epoch": 0.06369936034115138, + "grad_norm": 0.33144731129157684, + "learning_rate": 9.999963041327972e-06, + "loss": 0.4425, + "step": 478 + }, + { + "epoch": 0.06383262260127932, + "grad_norm": 0.3216514787674715, + "learning_rate": 9.999960252954489e-06, + "loss": 0.4157, + "step": 479 + }, + { + "epoch": 0.06396588486140725, + "grad_norm": 0.35726292583991204, + "learning_rate": 9.999957363186155e-06, + "loss": 0.4167, + "step": 480 + }, + { + "epoch": 0.06409914712153518, + "grad_norm": 0.32324052997213487, + "learning_rate": 9.999954372023027e-06, + "loss": 0.454, + "step": 481 + }, + { + "epoch": 0.06423240938166311, + "grad_norm": 0.35449151684386604, + "learning_rate": 9.999951279465165e-06, + "loss": 0.4153, + "step": 482 + }, + { + "epoch": 0.06436567164179105, + "grad_norm": 0.3610385143684281, + "learning_rate": 9.999948085512633e-06, + "loss": 0.4254, + "step": 483 + }, + { + "epoch": 0.06449893390191898, + "grad_norm": 0.350887925120969, + "learning_rate": 9.999944790165494e-06, + "loss": 0.4768, + "step": 484 + }, + { + "epoch": 0.0646321961620469, + "grad_norm": 0.34379497417396726, + "learning_rate": 9.999941393423818e-06, + "loss": 0.4447, + "step": 485 + }, + { + "epoch": 0.06476545842217483, + "grad_norm": 0.3483719731461869, + "learning_rate": 9.999937895287672e-06, + "loss": 0.4566, + "step": 486 + }, + { + "epoch": 0.06489872068230278, + "grad_norm": 0.3325546937460451, + "learning_rate": 9.999934295757127e-06, + "loss": 0.4637, + "step": 487 + }, + { + "epoch": 0.0650319829424307, + "grad_norm": 0.35960503118517756, + "learning_rate": 9.999930594832256e-06, + "loss": 0.4221, + "step": 488 + }, + { + "epoch": 0.06516524520255863, + "grad_norm": 0.3548735847024571, + "learning_rate": 9.999926792513135e-06, + "loss": 0.538, + "step": 489 + }, + { + "epoch": 0.06529850746268656, + "grad_norm": 0.31855926710600796, + "learning_rate": 9.999922888799838e-06, + "loss": 0.3807, + "step": 490 + }, + { + "epoch": 0.0654317697228145, + "grad_norm": 0.34627459968954305, + "learning_rate": 9.999918883692447e-06, + "loss": 0.4223, + "step": 491 + }, + { + "epoch": 0.06556503198294243, + "grad_norm": 0.3580205713077455, + "learning_rate": 9.999914777191043e-06, + "loss": 0.4973, + "step": 492 + }, + { + "epoch": 0.06569829424307036, + "grad_norm": 0.36070538590334594, + "learning_rate": 9.999910569295707e-06, + "loss": 0.447, + "step": 493 + }, + { + "epoch": 0.06583155650319829, + "grad_norm": 0.3616015976797031, + "learning_rate": 9.999906260006528e-06, + "loss": 0.4176, + "step": 494 + }, + { + "epoch": 0.06596481876332623, + "grad_norm": 0.32997588513836984, + "learning_rate": 9.999901849323592e-06, + "loss": 0.4149, + "step": 495 + }, + { + "epoch": 0.06609808102345416, + "grad_norm": 0.3719949463820994, + "learning_rate": 9.999897337246987e-06, + "loss": 0.4469, + "step": 496 + }, + { + "epoch": 0.06623134328358209, + "grad_norm": 0.3209181322521384, + "learning_rate": 9.999892723776804e-06, + "loss": 0.4106, + "step": 497 + }, + { + "epoch": 0.06636460554371001, + "grad_norm": 0.38111183292117573, + "learning_rate": 9.99988800891314e-06, + "loss": 0.4362, + "step": 498 + }, + { + "epoch": 0.06649786780383796, + "grad_norm": 0.3620021962288695, + "learning_rate": 9.99988319265609e-06, + "loss": 0.4221, + "step": 499 + }, + { + "epoch": 0.06663113006396588, + "grad_norm": 0.3586256601496763, + "learning_rate": 9.999878275005749e-06, + "loss": 0.4675, + "step": 500 + }, + { + "epoch": 0.06676439232409381, + "grad_norm": 0.3436988317851837, + "learning_rate": 9.999873255962218e-06, + "loss": 0.4736, + "step": 501 + }, + { + "epoch": 0.06689765458422176, + "grad_norm": 0.34095945462236454, + "learning_rate": 9.999868135525598e-06, + "loss": 0.4205, + "step": 502 + }, + { + "epoch": 0.06703091684434968, + "grad_norm": 0.37599780701733276, + "learning_rate": 9.999862913695995e-06, + "loss": 0.4469, + "step": 503 + }, + { + "epoch": 0.06716417910447761, + "grad_norm": 0.4909117648284253, + "learning_rate": 9.999857590473511e-06, + "loss": 0.3909, + "step": 504 + }, + { + "epoch": 0.06729744136460554, + "grad_norm": 0.37925798291364593, + "learning_rate": 9.99985216585826e-06, + "loss": 0.4279, + "step": 505 + }, + { + "epoch": 0.06743070362473348, + "grad_norm": 0.3465841065956696, + "learning_rate": 9.999846639850346e-06, + "loss": 0.4202, + "step": 506 + }, + { + "epoch": 0.06756396588486141, + "grad_norm": 0.36204708575393696, + "learning_rate": 9.999841012449884e-06, + "loss": 0.4102, + "step": 507 + }, + { + "epoch": 0.06769722814498934, + "grad_norm": 0.3581657340296208, + "learning_rate": 9.999835283656988e-06, + "loss": 0.4275, + "step": 508 + }, + { + "epoch": 0.06783049040511727, + "grad_norm": 0.35815178136062703, + "learning_rate": 9.999829453471775e-06, + "loss": 0.3875, + "step": 509 + }, + { + "epoch": 0.06796375266524521, + "grad_norm": 0.3660886179629453, + "learning_rate": 9.999823521894361e-06, + "loss": 0.4136, + "step": 510 + }, + { + "epoch": 0.06809701492537314, + "grad_norm": 0.3194603064623231, + "learning_rate": 9.999817488924866e-06, + "loss": 0.4188, + "step": 511 + }, + { + "epoch": 0.06823027718550106, + "grad_norm": 0.35263461336353735, + "learning_rate": 9.999811354563417e-06, + "loss": 0.4131, + "step": 512 + }, + { + "epoch": 0.06836353944562899, + "grad_norm": 0.3306648212284924, + "learning_rate": 9.999805118810132e-06, + "loss": 0.3701, + "step": 513 + }, + { + "epoch": 0.06849680170575694, + "grad_norm": 0.36681588917250707, + "learning_rate": 9.999798781665143e-06, + "loss": 0.4764, + "step": 514 + }, + { + "epoch": 0.06863006396588486, + "grad_norm": 0.3337744502562148, + "learning_rate": 9.999792343128573e-06, + "loss": 0.5075, + "step": 515 + }, + { + "epoch": 0.06876332622601279, + "grad_norm": 0.3627519512515587, + "learning_rate": 9.999785803200559e-06, + "loss": 0.41, + "step": 516 + }, + { + "epoch": 0.06889658848614072, + "grad_norm": 0.3267149790933984, + "learning_rate": 9.999779161881228e-06, + "loss": 0.4541, + "step": 517 + }, + { + "epoch": 0.06902985074626866, + "grad_norm": 0.3376389683973104, + "learning_rate": 9.999772419170719e-06, + "loss": 0.4413, + "step": 518 + }, + { + "epoch": 0.06916311300639659, + "grad_norm": 0.33936003031813183, + "learning_rate": 9.999765575069165e-06, + "loss": 0.4422, + "step": 519 + }, + { + "epoch": 0.06929637526652452, + "grad_norm": 0.33687856191717885, + "learning_rate": 9.999758629576708e-06, + "loss": 0.4379, + "step": 520 + }, + { + "epoch": 0.06942963752665245, + "grad_norm": 0.3352352631353441, + "learning_rate": 9.999751582693486e-06, + "loss": 0.3977, + "step": 521 + }, + { + "epoch": 0.06956289978678039, + "grad_norm": 0.32529414438016896, + "learning_rate": 9.999744434419643e-06, + "loss": 0.4289, + "step": 522 + }, + { + "epoch": 0.06969616204690832, + "grad_norm": 0.3533968434200535, + "learning_rate": 9.999737184755326e-06, + "loss": 0.4553, + "step": 523 + }, + { + "epoch": 0.06982942430703624, + "grad_norm": 0.357167481089775, + "learning_rate": 9.999729833700679e-06, + "loss": 0.4254, + "step": 524 + }, + { + "epoch": 0.06996268656716417, + "grad_norm": 0.33020705815194484, + "learning_rate": 9.999722381255852e-06, + "loss": 0.4351, + "step": 525 + }, + { + "epoch": 0.07009594882729211, + "grad_norm": 0.3166073242888957, + "learning_rate": 9.999714827420997e-06, + "loss": 0.4696, + "step": 526 + }, + { + "epoch": 0.07022921108742004, + "grad_norm": 0.34254485477136104, + "learning_rate": 9.999707172196266e-06, + "loss": 0.3943, + "step": 527 + }, + { + "epoch": 0.07036247334754797, + "grad_norm": 0.3361099195657274, + "learning_rate": 9.999699415581815e-06, + "loss": 0.5045, + "step": 528 + }, + { + "epoch": 0.0704957356076759, + "grad_norm": 0.3618181021776154, + "learning_rate": 9.999691557577803e-06, + "loss": 0.4004, + "step": 529 + }, + { + "epoch": 0.07062899786780384, + "grad_norm": 0.3507632992301449, + "learning_rate": 9.999683598184387e-06, + "loss": 0.454, + "step": 530 + }, + { + "epoch": 0.07076226012793177, + "grad_norm": 0.3636388712930367, + "learning_rate": 9.999675537401727e-06, + "loss": 0.4525, + "step": 531 + }, + { + "epoch": 0.0708955223880597, + "grad_norm": 0.34175094865562994, + "learning_rate": 9.999667375229988e-06, + "loss": 0.4085, + "step": 532 + }, + { + "epoch": 0.07102878464818764, + "grad_norm": 0.34819170108115544, + "learning_rate": 9.999659111669339e-06, + "loss": 0.4284, + "step": 533 + }, + { + "epoch": 0.07116204690831557, + "grad_norm": 0.35276738490325704, + "learning_rate": 9.999650746719942e-06, + "loss": 0.4501, + "step": 534 + }, + { + "epoch": 0.0712953091684435, + "grad_norm": 0.33851406298502806, + "learning_rate": 9.999642280381971e-06, + "loss": 0.4953, + "step": 535 + }, + { + "epoch": 0.07142857142857142, + "grad_norm": 0.3291742714890973, + "learning_rate": 9.999633712655594e-06, + "loss": 0.4307, + "step": 536 + }, + { + "epoch": 0.07156183368869937, + "grad_norm": 0.35167423296124983, + "learning_rate": 9.999625043540987e-06, + "loss": 0.4445, + "step": 537 + }, + { + "epoch": 0.0716950959488273, + "grad_norm": 0.32241677785721073, + "learning_rate": 9.999616273038327e-06, + "loss": 0.3438, + "step": 538 + }, + { + "epoch": 0.07182835820895522, + "grad_norm": 0.35223387677020573, + "learning_rate": 9.999607401147788e-06, + "loss": 0.4489, + "step": 539 + }, + { + "epoch": 0.07196162046908315, + "grad_norm": 0.32653794600910446, + "learning_rate": 9.999598427869552e-06, + "loss": 0.4089, + "step": 540 + }, + { + "epoch": 0.0720948827292111, + "grad_norm": 0.338062854293121, + "learning_rate": 9.999589353203803e-06, + "loss": 0.3858, + "step": 541 + }, + { + "epoch": 0.07222814498933902, + "grad_norm": 0.3517950400146442, + "learning_rate": 9.999580177150722e-06, + "loss": 0.5577, + "step": 542 + }, + { + "epoch": 0.07236140724946695, + "grad_norm": 0.34288645582146127, + "learning_rate": 9.999570899710495e-06, + "loss": 0.4307, + "step": 543 + }, + { + "epoch": 0.07249466950959488, + "grad_norm": 0.3540098420014865, + "learning_rate": 9.999561520883314e-06, + "loss": 0.4511, + "step": 544 + }, + { + "epoch": 0.07262793176972282, + "grad_norm": 0.3675698990629213, + "learning_rate": 9.999552040669364e-06, + "loss": 0.597, + "step": 545 + }, + { + "epoch": 0.07276119402985075, + "grad_norm": 0.3715709357215255, + "learning_rate": 9.999542459068843e-06, + "loss": 0.4275, + "step": 546 + }, + { + "epoch": 0.07289445628997868, + "grad_norm": 0.31859563883714986, + "learning_rate": 9.99953277608194e-06, + "loss": 0.4134, + "step": 547 + }, + { + "epoch": 0.0730277185501066, + "grad_norm": 0.35265562930811484, + "learning_rate": 9.999522991708853e-06, + "loss": 0.4954, + "step": 548 + }, + { + "epoch": 0.07316098081023455, + "grad_norm": 0.3418725451002923, + "learning_rate": 9.999513105949782e-06, + "loss": 0.5077, + "step": 549 + }, + { + "epoch": 0.07329424307036247, + "grad_norm": 0.3686072480373189, + "learning_rate": 9.999503118804925e-06, + "loss": 0.3832, + "step": 550 + }, + { + "epoch": 0.0734275053304904, + "grad_norm": 0.3541920942221385, + "learning_rate": 9.999493030274488e-06, + "loss": 0.4481, + "step": 551 + }, + { + "epoch": 0.07356076759061833, + "grad_norm": 0.34614820954024067, + "learning_rate": 9.999482840358672e-06, + "loss": 0.4469, + "step": 552 + }, + { + "epoch": 0.07369402985074627, + "grad_norm": 0.34814222354285923, + "learning_rate": 9.999472549057685e-06, + "loss": 0.5011, + "step": 553 + }, + { + "epoch": 0.0738272921108742, + "grad_norm": 0.3677601716248793, + "learning_rate": 9.999462156371736e-06, + "loss": 0.4043, + "step": 554 + }, + { + "epoch": 0.07396055437100213, + "grad_norm": 0.3656391278078277, + "learning_rate": 9.999451662301035e-06, + "loss": 0.4382, + "step": 555 + }, + { + "epoch": 0.07409381663113006, + "grad_norm": 0.35982473734427367, + "learning_rate": 9.999441066845797e-06, + "loss": 0.4126, + "step": 556 + }, + { + "epoch": 0.074227078891258, + "grad_norm": 0.39472831321177815, + "learning_rate": 9.999430370006234e-06, + "loss": 0.4343, + "step": 557 + }, + { + "epoch": 0.07436034115138593, + "grad_norm": 0.34207962794351454, + "learning_rate": 9.999419571782566e-06, + "loss": 0.385, + "step": 558 + }, + { + "epoch": 0.07449360341151386, + "grad_norm": 0.3296575135170513, + "learning_rate": 9.999408672175008e-06, + "loss": 0.4205, + "step": 559 + }, + { + "epoch": 0.07462686567164178, + "grad_norm": 0.355777579260544, + "learning_rate": 9.999397671183784e-06, + "loss": 0.464, + "step": 560 + }, + { + "epoch": 0.07476012793176973, + "grad_norm": 0.3454438516621896, + "learning_rate": 9.999386568809115e-06, + "loss": 0.5324, + "step": 561 + }, + { + "epoch": 0.07489339019189765, + "grad_norm": 0.38320339696673106, + "learning_rate": 9.99937536505123e-06, + "loss": 0.4349, + "step": 562 + }, + { + "epoch": 0.07502665245202558, + "grad_norm": 0.364959027771837, + "learning_rate": 9.999364059910352e-06, + "loss": 0.5552, + "step": 563 + }, + { + "epoch": 0.07515991471215352, + "grad_norm": 0.40865370982673904, + "learning_rate": 9.99935265338671e-06, + "loss": 0.4711, + "step": 564 + }, + { + "epoch": 0.07529317697228145, + "grad_norm": 0.301447412874837, + "learning_rate": 9.999341145480541e-06, + "loss": 0.4413, + "step": 565 + }, + { + "epoch": 0.07542643923240938, + "grad_norm": 0.34262705944725674, + "learning_rate": 9.999329536192073e-06, + "loss": 0.5608, + "step": 566 + }, + { + "epoch": 0.07555970149253731, + "grad_norm": 0.37566323598879414, + "learning_rate": 9.999317825521542e-06, + "loss": 0.5274, + "step": 567 + }, + { + "epoch": 0.07569296375266525, + "grad_norm": 0.3600173588696942, + "learning_rate": 9.999306013469188e-06, + "loss": 0.4139, + "step": 568 + }, + { + "epoch": 0.07582622601279318, + "grad_norm": 0.3319562076343435, + "learning_rate": 9.999294100035248e-06, + "loss": 0.5028, + "step": 569 + }, + { + "epoch": 0.07595948827292111, + "grad_norm": 0.38064492203843064, + "learning_rate": 9.999282085219966e-06, + "loss": 0.4515, + "step": 570 + }, + { + "epoch": 0.07609275053304904, + "grad_norm": 0.3432936449510282, + "learning_rate": 9.999269969023582e-06, + "loss": 0.466, + "step": 571 + }, + { + "epoch": 0.07622601279317698, + "grad_norm": 0.3270587024805463, + "learning_rate": 9.999257751446345e-06, + "loss": 0.4135, + "step": 572 + }, + { + "epoch": 0.0763592750533049, + "grad_norm": 0.3506770540100518, + "learning_rate": 9.999245432488503e-06, + "loss": 0.4612, + "step": 573 + }, + { + "epoch": 0.07649253731343283, + "grad_norm": 0.36948881152456076, + "learning_rate": 9.999233012150302e-06, + "loss": 0.5584, + "step": 574 + }, + { + "epoch": 0.07662579957356076, + "grad_norm": 0.3329326109269454, + "learning_rate": 9.999220490431997e-06, + "loss": 0.4476, + "step": 575 + }, + { + "epoch": 0.0767590618336887, + "grad_norm": 0.3549555141228401, + "learning_rate": 9.999207867333843e-06, + "loss": 0.3932, + "step": 576 + }, + { + "epoch": 0.07689232409381663, + "grad_norm": 0.3290162757942283, + "learning_rate": 9.999195142856095e-06, + "loss": 0.4065, + "step": 577 + }, + { + "epoch": 0.07702558635394456, + "grad_norm": 0.3656391685205163, + "learning_rate": 9.999182316999007e-06, + "loss": 0.4292, + "step": 578 + }, + { + "epoch": 0.07715884861407249, + "grad_norm": 0.39523070347573047, + "learning_rate": 9.999169389762845e-06, + "loss": 0.39, + "step": 579 + }, + { + "epoch": 0.07729211087420043, + "grad_norm": 0.3206698401955026, + "learning_rate": 9.999156361147868e-06, + "loss": 0.4099, + "step": 580 + }, + { + "epoch": 0.07742537313432836, + "grad_norm": 0.32422988120419866, + "learning_rate": 9.99914323115434e-06, + "loss": 0.4448, + "step": 581 + }, + { + "epoch": 0.07755863539445629, + "grad_norm": 0.3391916241514358, + "learning_rate": 9.99912999978253e-06, + "loss": 0.5024, + "step": 582 + }, + { + "epoch": 0.07769189765458422, + "grad_norm": 0.32812009448477936, + "learning_rate": 9.999116667032702e-06, + "loss": 0.3792, + "step": 583 + }, + { + "epoch": 0.07782515991471216, + "grad_norm": 0.33507864327378367, + "learning_rate": 9.999103232905131e-06, + "loss": 0.4821, + "step": 584 + }, + { + "epoch": 0.07795842217484009, + "grad_norm": 0.34329484978134284, + "learning_rate": 9.999089697400087e-06, + "loss": 0.5434, + "step": 585 + }, + { + "epoch": 0.07809168443496801, + "grad_norm": 0.3511053563752711, + "learning_rate": 9.999076060517843e-06, + "loss": 0.4082, + "step": 586 + }, + { + "epoch": 0.07822494669509594, + "grad_norm": 0.3290107004338434, + "learning_rate": 9.999062322258679e-06, + "loss": 0.364, + "step": 587 + }, + { + "epoch": 0.07835820895522388, + "grad_norm": 0.4410082073898651, + "learning_rate": 9.999048482622871e-06, + "loss": 0.4197, + "step": 588 + }, + { + "epoch": 0.07849147121535181, + "grad_norm": 0.3250845626814754, + "learning_rate": 9.9990345416107e-06, + "loss": 0.4465, + "step": 589 + }, + { + "epoch": 0.07862473347547974, + "grad_norm": 0.3189283620799368, + "learning_rate": 9.999020499222449e-06, + "loss": 0.4433, + "step": 590 + }, + { + "epoch": 0.07875799573560767, + "grad_norm": 0.3246902479155915, + "learning_rate": 9.999006355458405e-06, + "loss": 0.4565, + "step": 591 + }, + { + "epoch": 0.07889125799573561, + "grad_norm": 0.3143598437710093, + "learning_rate": 9.998992110318852e-06, + "loss": 0.4079, + "step": 592 + }, + { + "epoch": 0.07902452025586354, + "grad_norm": 0.32123273398427554, + "learning_rate": 9.998977763804078e-06, + "loss": 0.4769, + "step": 593 + }, + { + "epoch": 0.07915778251599147, + "grad_norm": 0.31627372061068393, + "learning_rate": 9.99896331591438e-06, + "loss": 0.3979, + "step": 594 + }, + { + "epoch": 0.07929104477611941, + "grad_norm": 0.3454371227484242, + "learning_rate": 9.99894876665004e-06, + "loss": 0.422, + "step": 595 + }, + { + "epoch": 0.07942430703624734, + "grad_norm": 0.33650693851974145, + "learning_rate": 9.998934116011365e-06, + "loss": 0.374, + "step": 596 + }, + { + "epoch": 0.07955756929637527, + "grad_norm": 0.32400866471449674, + "learning_rate": 9.998919363998645e-06, + "loss": 0.4031, + "step": 597 + }, + { + "epoch": 0.0796908315565032, + "grad_norm": 0.34457368075749634, + "learning_rate": 9.99890451061218e-06, + "loss": 0.4484, + "step": 598 + }, + { + "epoch": 0.07982409381663114, + "grad_norm": 0.3323962621493954, + "learning_rate": 9.998889555852273e-06, + "loss": 0.5088, + "step": 599 + }, + { + "epoch": 0.07995735607675906, + "grad_norm": 0.34719353501477707, + "learning_rate": 9.998874499719226e-06, + "loss": 0.4161, + "step": 600 + }, + { + "epoch": 0.08009061833688699, + "grad_norm": 0.40516983639362064, + "learning_rate": 9.998859342213347e-06, + "loss": 0.399, + "step": 601 + }, + { + "epoch": 0.08022388059701492, + "grad_norm": 0.33368032417356974, + "learning_rate": 9.99884408333494e-06, + "loss": 0.4161, + "step": 602 + }, + { + "epoch": 0.08035714285714286, + "grad_norm": 0.3181072048112107, + "learning_rate": 9.998828723084314e-06, + "loss": 0.3811, + "step": 603 + }, + { + "epoch": 0.08049040511727079, + "grad_norm": 0.37301669063687254, + "learning_rate": 9.998813261461783e-06, + "loss": 0.5021, + "step": 604 + }, + { + "epoch": 0.08062366737739872, + "grad_norm": 0.3358626464431904, + "learning_rate": 9.99879769846766e-06, + "loss": 0.3784, + "step": 605 + }, + { + "epoch": 0.08075692963752665, + "grad_norm": 0.42641913732542785, + "learning_rate": 9.998782034102259e-06, + "loss": 0.4865, + "step": 606 + }, + { + "epoch": 0.08089019189765459, + "grad_norm": 0.3409894517155153, + "learning_rate": 9.998766268365901e-06, + "loss": 0.4337, + "step": 607 + }, + { + "epoch": 0.08102345415778252, + "grad_norm": 0.3236007989982186, + "learning_rate": 9.9987504012589e-06, + "loss": 0.4349, + "step": 608 + }, + { + "epoch": 0.08115671641791045, + "grad_norm": 0.3545366096353331, + "learning_rate": 9.998734432781585e-06, + "loss": 0.4558, + "step": 609 + }, + { + "epoch": 0.08128997867803837, + "grad_norm": 0.31954587686250646, + "learning_rate": 9.998718362934274e-06, + "loss": 0.3848, + "step": 610 + }, + { + "epoch": 0.08142324093816632, + "grad_norm": 0.3210660399635334, + "learning_rate": 9.998702191717295e-06, + "loss": 0.4246, + "step": 611 + }, + { + "epoch": 0.08155650319829424, + "grad_norm": 0.3196165291786048, + "learning_rate": 9.998685919130977e-06, + "loss": 0.4372, + "step": 612 + }, + { + "epoch": 0.08168976545842217, + "grad_norm": 0.33560787892491634, + "learning_rate": 9.99866954517565e-06, + "loss": 0.4749, + "step": 613 + }, + { + "epoch": 0.0818230277185501, + "grad_norm": 0.3364902646456088, + "learning_rate": 9.998653069851642e-06, + "loss": 0.4488, + "step": 614 + }, + { + "epoch": 0.08195628997867804, + "grad_norm": 0.33779803448823964, + "learning_rate": 9.998636493159293e-06, + "loss": 0.4983, + "step": 615 + }, + { + "epoch": 0.08208955223880597, + "grad_norm": 0.31017871522389673, + "learning_rate": 9.998619815098936e-06, + "loss": 0.4307, + "step": 616 + }, + { + "epoch": 0.0822228144989339, + "grad_norm": 0.3153015072512774, + "learning_rate": 9.998603035670908e-06, + "loss": 0.4491, + "step": 617 + }, + { + "epoch": 0.08235607675906183, + "grad_norm": 0.30835461565605843, + "learning_rate": 9.99858615487555e-06, + "loss": 0.4235, + "step": 618 + }, + { + "epoch": 0.08248933901918977, + "grad_norm": 0.30608633420016657, + "learning_rate": 9.99856917271321e-06, + "loss": 0.3594, + "step": 619 + }, + { + "epoch": 0.0826226012793177, + "grad_norm": 0.33380523528721434, + "learning_rate": 9.998552089184222e-06, + "loss": 0.5718, + "step": 620 + }, + { + "epoch": 0.08275586353944563, + "grad_norm": 0.3072034101029289, + "learning_rate": 9.998534904288941e-06, + "loss": 0.3923, + "step": 621 + }, + { + "epoch": 0.08288912579957355, + "grad_norm": 0.31206315045158783, + "learning_rate": 9.998517618027711e-06, + "loss": 0.4083, + "step": 622 + }, + { + "epoch": 0.0830223880597015, + "grad_norm": 0.3516070796566667, + "learning_rate": 9.998500230400886e-06, + "loss": 0.4711, + "step": 623 + }, + { + "epoch": 0.08315565031982942, + "grad_norm": 0.34383583208228585, + "learning_rate": 9.998482741408813e-06, + "loss": 0.3812, + "step": 624 + }, + { + "epoch": 0.08328891257995735, + "grad_norm": 0.3394573202462147, + "learning_rate": 9.998465151051853e-06, + "loss": 0.444, + "step": 625 + }, + { + "epoch": 0.0834221748400853, + "grad_norm": 0.325031186861959, + "learning_rate": 9.998447459330359e-06, + "loss": 0.4726, + "step": 626 + }, + { + "epoch": 0.08355543710021322, + "grad_norm": 0.34815134206283643, + "learning_rate": 9.998429666244691e-06, + "loss": 0.561, + "step": 627 + }, + { + "epoch": 0.08368869936034115, + "grad_norm": 0.342781847519828, + "learning_rate": 9.99841177179521e-06, + "loss": 0.4554, + "step": 628 + }, + { + "epoch": 0.08382196162046908, + "grad_norm": 0.3374330256798373, + "learning_rate": 9.998393775982279e-06, + "loss": 0.4279, + "step": 629 + }, + { + "epoch": 0.08395522388059702, + "grad_norm": 0.35552549014765067, + "learning_rate": 9.99837567880626e-06, + "loss": 0.4305, + "step": 630 + }, + { + "epoch": 0.08408848614072495, + "grad_norm": 0.3352886139859798, + "learning_rate": 9.998357480267525e-06, + "loss": 0.4309, + "step": 631 + }, + { + "epoch": 0.08422174840085288, + "grad_norm": 0.38012267388176313, + "learning_rate": 9.998339180366439e-06, + "loss": 0.4371, + "step": 632 + }, + { + "epoch": 0.0843550106609808, + "grad_norm": 0.33948788647614714, + "learning_rate": 9.998320779103375e-06, + "loss": 0.4228, + "step": 633 + }, + { + "epoch": 0.08448827292110875, + "grad_norm": 0.33348461791813205, + "learning_rate": 9.998302276478706e-06, + "loss": 0.4066, + "step": 634 + }, + { + "epoch": 0.08462153518123668, + "grad_norm": 0.3424713827907488, + "learning_rate": 9.998283672492805e-06, + "loss": 0.4606, + "step": 635 + }, + { + "epoch": 0.0847547974413646, + "grad_norm": 0.3303929708422847, + "learning_rate": 9.998264967146055e-06, + "loss": 0.5379, + "step": 636 + }, + { + "epoch": 0.08488805970149253, + "grad_norm": 0.3383229797846613, + "learning_rate": 9.998246160438827e-06, + "loss": 0.4548, + "step": 637 + }, + { + "epoch": 0.08502132196162047, + "grad_norm": 0.3219801327921914, + "learning_rate": 9.99822725237151e-06, + "loss": 0.416, + "step": 638 + }, + { + "epoch": 0.0851545842217484, + "grad_norm": 0.3404775388798864, + "learning_rate": 9.998208242944484e-06, + "loss": 0.4405, + "step": 639 + }, + { + "epoch": 0.08528784648187633, + "grad_norm": 0.3359925742675219, + "learning_rate": 9.998189132158134e-06, + "loss": 0.4154, + "step": 640 + }, + { + "epoch": 0.08542110874200426, + "grad_norm": 0.3413995667611447, + "learning_rate": 9.998169920012847e-06, + "loss": 0.4418, + "step": 641 + }, + { + "epoch": 0.0855543710021322, + "grad_norm": 0.3658244935313804, + "learning_rate": 9.998150606509018e-06, + "loss": 0.442, + "step": 642 + }, + { + "epoch": 0.08568763326226013, + "grad_norm": 0.3270273294832049, + "learning_rate": 9.998131191647032e-06, + "loss": 0.4433, + "step": 643 + }, + { + "epoch": 0.08582089552238806, + "grad_norm": 0.3309256392449202, + "learning_rate": 9.998111675427286e-06, + "loss": 0.4244, + "step": 644 + }, + { + "epoch": 0.08595415778251599, + "grad_norm": 0.32649133010478576, + "learning_rate": 9.998092057850175e-06, + "loss": 0.3656, + "step": 645 + }, + { + "epoch": 0.08608742004264393, + "grad_norm": 0.3300056702134557, + "learning_rate": 9.998072338916097e-06, + "loss": 0.3626, + "step": 646 + }, + { + "epoch": 0.08622068230277186, + "grad_norm": 0.36296040756948234, + "learning_rate": 9.998052518625452e-06, + "loss": 0.4485, + "step": 647 + }, + { + "epoch": 0.08635394456289978, + "grad_norm": 0.35115796268408794, + "learning_rate": 9.99803259697864e-06, + "loss": 0.4224, + "step": 648 + }, + { + "epoch": 0.08648720682302771, + "grad_norm": 0.34617283945739097, + "learning_rate": 9.998012573976069e-06, + "loss": 0.4772, + "step": 649 + }, + { + "epoch": 0.08662046908315565, + "grad_norm": 0.33293092021290366, + "learning_rate": 9.997992449618142e-06, + "loss": 0.4795, + "step": 650 + }, + { + "epoch": 0.08675373134328358, + "grad_norm": 0.32915025211296733, + "learning_rate": 9.997972223905269e-06, + "loss": 0.4438, + "step": 651 + }, + { + "epoch": 0.08688699360341151, + "grad_norm": 0.3429693195293358, + "learning_rate": 9.997951896837857e-06, + "loss": 0.4352, + "step": 652 + }, + { + "epoch": 0.08702025586353944, + "grad_norm": 0.3293915590583844, + "learning_rate": 9.997931468416322e-06, + "loss": 0.4101, + "step": 653 + }, + { + "epoch": 0.08715351812366738, + "grad_norm": 0.31627108735970255, + "learning_rate": 9.997910938641075e-06, + "loss": 0.4073, + "step": 654 + }, + { + "epoch": 0.08728678038379531, + "grad_norm": 0.3431880162162784, + "learning_rate": 9.997890307512537e-06, + "loss": 0.435, + "step": 655 + }, + { + "epoch": 0.08742004264392324, + "grad_norm": 0.3339724551522791, + "learning_rate": 9.99786957503112e-06, + "loss": 0.3658, + "step": 656 + }, + { + "epoch": 0.08755330490405118, + "grad_norm": 0.35025918925670513, + "learning_rate": 9.997848741197248e-06, + "loss": 0.4416, + "step": 657 + }, + { + "epoch": 0.08768656716417911, + "grad_norm": 0.34831870092849976, + "learning_rate": 9.997827806011347e-06, + "loss": 0.4016, + "step": 658 + }, + { + "epoch": 0.08781982942430704, + "grad_norm": 0.35548521107228565, + "learning_rate": 9.997806769473834e-06, + "loss": 0.5262, + "step": 659 + }, + { + "epoch": 0.08795309168443496, + "grad_norm": 0.371380985170282, + "learning_rate": 9.99778563158514e-06, + "loss": 0.3903, + "step": 660 + }, + { + "epoch": 0.0880863539445629, + "grad_norm": 0.3230155169841856, + "learning_rate": 9.997764392345694e-06, + "loss": 0.4299, + "step": 661 + }, + { + "epoch": 0.08821961620469083, + "grad_norm": 0.30885372030690356, + "learning_rate": 9.997743051755926e-06, + "loss": 0.4151, + "step": 662 + }, + { + "epoch": 0.08835287846481876, + "grad_norm": 0.3290961896526037, + "learning_rate": 9.997721609816266e-06, + "loss": 0.4369, + "step": 663 + }, + { + "epoch": 0.08848614072494669, + "grad_norm": 0.3464280168815044, + "learning_rate": 9.997700066527154e-06, + "loss": 0.4546, + "step": 664 + }, + { + "epoch": 0.08861940298507463, + "grad_norm": 0.34468477270289344, + "learning_rate": 9.997678421889022e-06, + "loss": 0.4519, + "step": 665 + }, + { + "epoch": 0.08875266524520256, + "grad_norm": 0.34266502293049156, + "learning_rate": 9.997656675902314e-06, + "loss": 0.4379, + "step": 666 + }, + { + "epoch": 0.08888592750533049, + "grad_norm": 0.35668883793339934, + "learning_rate": 9.997634828567467e-06, + "loss": 0.4815, + "step": 667 + }, + { + "epoch": 0.08901918976545842, + "grad_norm": 0.3248191679557085, + "learning_rate": 9.997612879884925e-06, + "loss": 0.4234, + "step": 668 + }, + { + "epoch": 0.08915245202558636, + "grad_norm": 1.1298002488789847, + "learning_rate": 9.997590829855133e-06, + "loss": 0.5013, + "step": 669 + }, + { + "epoch": 0.08928571428571429, + "grad_norm": 0.3631766984380802, + "learning_rate": 9.997568678478539e-06, + "loss": 0.4324, + "step": 670 + }, + { + "epoch": 0.08941897654584222, + "grad_norm": 0.3745773612966985, + "learning_rate": 9.997546425755591e-06, + "loss": 0.5018, + "step": 671 + }, + { + "epoch": 0.08955223880597014, + "grad_norm": 0.3482834170892808, + "learning_rate": 9.997524071686742e-06, + "loss": 0.4329, + "step": 672 + }, + { + "epoch": 0.08968550106609809, + "grad_norm": 0.3232782266449016, + "learning_rate": 9.997501616272443e-06, + "loss": 0.4475, + "step": 673 + }, + { + "epoch": 0.08981876332622601, + "grad_norm": 0.3538715019962539, + "learning_rate": 9.997479059513151e-06, + "loss": 0.4255, + "step": 674 + }, + { + "epoch": 0.08995202558635394, + "grad_norm": 0.3141786189227492, + "learning_rate": 9.997456401409322e-06, + "loss": 0.3981, + "step": 675 + }, + { + "epoch": 0.09008528784648187, + "grad_norm": 0.3412528094044966, + "learning_rate": 9.997433641961418e-06, + "loss": 0.5298, + "step": 676 + }, + { + "epoch": 0.09021855010660981, + "grad_norm": 0.33001801932030717, + "learning_rate": 9.997410781169899e-06, + "loss": 0.4981, + "step": 677 + }, + { + "epoch": 0.09035181236673774, + "grad_norm": 0.32295537186068174, + "learning_rate": 9.997387819035228e-06, + "loss": 0.4044, + "step": 678 + }, + { + "epoch": 0.09048507462686567, + "grad_norm": 0.325797720673079, + "learning_rate": 9.997364755557872e-06, + "loss": 0.4269, + "step": 679 + }, + { + "epoch": 0.0906183368869936, + "grad_norm": 0.31677467505788404, + "learning_rate": 9.997341590738298e-06, + "loss": 0.5587, + "step": 680 + }, + { + "epoch": 0.09075159914712154, + "grad_norm": 0.3569575884489381, + "learning_rate": 9.997318324576975e-06, + "loss": 0.5272, + "step": 681 + }, + { + "epoch": 0.09088486140724947, + "grad_norm": 0.3235633190828491, + "learning_rate": 9.997294957074376e-06, + "loss": 0.4257, + "step": 682 + }, + { + "epoch": 0.0910181236673774, + "grad_norm": 0.33525703306369503, + "learning_rate": 9.997271488230976e-06, + "loss": 0.4079, + "step": 683 + }, + { + "epoch": 0.09115138592750532, + "grad_norm": 0.3224533194974222, + "learning_rate": 9.997247918047248e-06, + "loss": 0.5017, + "step": 684 + }, + { + "epoch": 0.09128464818763327, + "grad_norm": 0.3455516861490265, + "learning_rate": 9.99722424652367e-06, + "loss": 0.4158, + "step": 685 + }, + { + "epoch": 0.0914179104477612, + "grad_norm": 0.33206122295753376, + "learning_rate": 9.997200473660726e-06, + "loss": 0.4417, + "step": 686 + }, + { + "epoch": 0.09155117270788912, + "grad_norm": 0.3496648661362614, + "learning_rate": 9.997176599458894e-06, + "loss": 0.6631, + "step": 687 + }, + { + "epoch": 0.09168443496801706, + "grad_norm": 0.36025004476481853, + "learning_rate": 9.99715262391866e-06, + "loss": 0.4299, + "step": 688 + }, + { + "epoch": 0.09181769722814499, + "grad_norm": 0.3277322854870017, + "learning_rate": 9.99712854704051e-06, + "loss": 0.3808, + "step": 689 + }, + { + "epoch": 0.09195095948827292, + "grad_norm": 0.34015772507097897, + "learning_rate": 9.997104368824932e-06, + "loss": 0.4798, + "step": 690 + }, + { + "epoch": 0.09208422174840085, + "grad_norm": 0.3416650393592192, + "learning_rate": 9.997080089272416e-06, + "loss": 0.4424, + "step": 691 + }, + { + "epoch": 0.09221748400852879, + "grad_norm": 0.36423754231541033, + "learning_rate": 9.997055708383457e-06, + "loss": 0.4303, + "step": 692 + }, + { + "epoch": 0.09235074626865672, + "grad_norm": 0.29680891794438174, + "learning_rate": 9.997031226158545e-06, + "loss": 0.3828, + "step": 693 + }, + { + "epoch": 0.09248400852878465, + "grad_norm": 0.3330921427152892, + "learning_rate": 9.99700664259818e-06, + "loss": 0.3606, + "step": 694 + }, + { + "epoch": 0.09261727078891258, + "grad_norm": 0.3406154199316804, + "learning_rate": 9.996981957702858e-06, + "loss": 0.4303, + "step": 695 + }, + { + "epoch": 0.09275053304904052, + "grad_norm": 0.3463168154051608, + "learning_rate": 9.99695717147308e-06, + "loss": 0.4637, + "step": 696 + }, + { + "epoch": 0.09288379530916845, + "grad_norm": 0.35608836875260047, + "learning_rate": 9.996932283909352e-06, + "loss": 0.4514, + "step": 697 + }, + { + "epoch": 0.09301705756929637, + "grad_norm": 0.3380124644818287, + "learning_rate": 9.996907295012175e-06, + "loss": 0.4392, + "step": 698 + }, + { + "epoch": 0.0931503198294243, + "grad_norm": 0.31729089664841487, + "learning_rate": 9.996882204782056e-06, + "loss": 0.4097, + "step": 699 + }, + { + "epoch": 0.09328358208955224, + "grad_norm": 0.33172397906287077, + "learning_rate": 9.996857013219508e-06, + "loss": 0.4323, + "step": 700 + }, + { + "epoch": 0.09341684434968017, + "grad_norm": 0.3363160156879377, + "learning_rate": 9.996831720325035e-06, + "loss": 0.4751, + "step": 701 + }, + { + "epoch": 0.0935501066098081, + "grad_norm": 0.32793642814596347, + "learning_rate": 9.996806326099155e-06, + "loss": 0.4059, + "step": 702 + }, + { + "epoch": 0.09368336886993603, + "grad_norm": 0.32080292683018424, + "learning_rate": 9.996780830542382e-06, + "loss": 0.4243, + "step": 703 + }, + { + "epoch": 0.09381663113006397, + "grad_norm": 0.313694048650784, + "learning_rate": 9.99675523365523e-06, + "loss": 0.4634, + "step": 704 + }, + { + "epoch": 0.0939498933901919, + "grad_norm": 0.333988032827146, + "learning_rate": 9.996729535438225e-06, + "loss": 0.4293, + "step": 705 + }, + { + "epoch": 0.09408315565031983, + "grad_norm": 0.32562621169749284, + "learning_rate": 9.99670373589188e-06, + "loss": 0.4716, + "step": 706 + }, + { + "epoch": 0.09421641791044776, + "grad_norm": 0.33826910918164116, + "learning_rate": 9.996677835016724e-06, + "loss": 0.4358, + "step": 707 + }, + { + "epoch": 0.0943496801705757, + "grad_norm": 0.32782206777761946, + "learning_rate": 9.99665183281328e-06, + "loss": 0.5136, + "step": 708 + }, + { + "epoch": 0.09448294243070363, + "grad_norm": 0.32005989729038636, + "learning_rate": 9.996625729282074e-06, + "loss": 0.4015, + "step": 709 + }, + { + "epoch": 0.09461620469083155, + "grad_norm": 0.3315236958749645, + "learning_rate": 9.996599524423638e-06, + "loss": 0.4307, + "step": 710 + }, + { + "epoch": 0.09474946695095948, + "grad_norm": 0.3211770724519511, + "learning_rate": 9.996573218238503e-06, + "loss": 0.5181, + "step": 711 + }, + { + "epoch": 0.09488272921108742, + "grad_norm": 0.3291711912107501, + "learning_rate": 9.9965468107272e-06, + "loss": 0.3663, + "step": 712 + }, + { + "epoch": 0.09501599147121535, + "grad_norm": 0.31616611168166203, + "learning_rate": 9.996520301890267e-06, + "loss": 0.4092, + "step": 713 + }, + { + "epoch": 0.09514925373134328, + "grad_norm": 0.3243646449353433, + "learning_rate": 9.99649369172824e-06, + "loss": 0.3891, + "step": 714 + }, + { + "epoch": 0.09528251599147121, + "grad_norm": 0.34833925294264495, + "learning_rate": 9.996466980241662e-06, + "loss": 0.5617, + "step": 715 + }, + { + "epoch": 0.09541577825159915, + "grad_norm": 0.46148150790466586, + "learning_rate": 9.996440167431069e-06, + "loss": 0.4272, + "step": 716 + }, + { + "epoch": 0.09554904051172708, + "grad_norm": 0.33624557670807304, + "learning_rate": 9.99641325329701e-06, + "loss": 0.4294, + "step": 717 + }, + { + "epoch": 0.09568230277185501, + "grad_norm": 0.3268140961236408, + "learning_rate": 9.996386237840028e-06, + "loss": 0.4589, + "step": 718 + }, + { + "epoch": 0.09581556503198294, + "grad_norm": 0.32862303174559315, + "learning_rate": 9.996359121060672e-06, + "loss": 0.4104, + "step": 719 + }, + { + "epoch": 0.09594882729211088, + "grad_norm": 0.31348317112308377, + "learning_rate": 9.996331902959491e-06, + "loss": 0.4473, + "step": 720 + }, + { + "epoch": 0.0960820895522388, + "grad_norm": 0.29974699781684633, + "learning_rate": 9.996304583537037e-06, + "loss": 0.4108, + "step": 721 + }, + { + "epoch": 0.09621535181236673, + "grad_norm": 0.3313974764087887, + "learning_rate": 9.996277162793864e-06, + "loss": 0.4752, + "step": 722 + }, + { + "epoch": 0.09634861407249468, + "grad_norm": 0.32396833632085686, + "learning_rate": 9.99624964073053e-06, + "loss": 0.4155, + "step": 723 + }, + { + "epoch": 0.0964818763326226, + "grad_norm": 0.34602368765494224, + "learning_rate": 9.99622201734759e-06, + "loss": 0.3824, + "step": 724 + }, + { + "epoch": 0.09661513859275053, + "grad_norm": 0.3317202272029745, + "learning_rate": 9.996194292645607e-06, + "loss": 0.4946, + "step": 725 + }, + { + "epoch": 0.09674840085287846, + "grad_norm": 0.3317802404795911, + "learning_rate": 9.996166466625141e-06, + "loss": 0.3573, + "step": 726 + }, + { + "epoch": 0.0968816631130064, + "grad_norm": 0.32046084472587344, + "learning_rate": 9.99613853928676e-06, + "loss": 0.403, + "step": 727 + }, + { + "epoch": 0.09701492537313433, + "grad_norm": 0.3325485363554059, + "learning_rate": 9.996110510631024e-06, + "loss": 0.3778, + "step": 728 + }, + { + "epoch": 0.09714818763326226, + "grad_norm": 0.31793267290941785, + "learning_rate": 9.996082380658507e-06, + "loss": 0.4255, + "step": 729 + }, + { + "epoch": 0.09728144989339019, + "grad_norm": 0.32864692932462125, + "learning_rate": 9.996054149369778e-06, + "loss": 0.5309, + "step": 730 + }, + { + "epoch": 0.09741471215351813, + "grad_norm": 0.31457809707196577, + "learning_rate": 9.996025816765406e-06, + "loss": 0.4405, + "step": 731 + }, + { + "epoch": 0.09754797441364606, + "grad_norm": 0.32292620529079197, + "learning_rate": 9.995997382845972e-06, + "loss": 0.4625, + "step": 732 + }, + { + "epoch": 0.09768123667377399, + "grad_norm": 0.3445812477333474, + "learning_rate": 9.995968847612048e-06, + "loss": 0.4473, + "step": 733 + }, + { + "epoch": 0.09781449893390191, + "grad_norm": 0.3139655486470282, + "learning_rate": 9.995940211064212e-06, + "loss": 0.3815, + "step": 734 + }, + { + "epoch": 0.09794776119402986, + "grad_norm": 0.3525344497422001, + "learning_rate": 9.995911473203049e-06, + "loss": 0.4323, + "step": 735 + }, + { + "epoch": 0.09808102345415778, + "grad_norm": 0.32098564430043813, + "learning_rate": 9.99588263402914e-06, + "loss": 0.4373, + "step": 736 + }, + { + "epoch": 0.09821428571428571, + "grad_norm": 0.3614632810370204, + "learning_rate": 9.995853693543067e-06, + "loss": 0.3897, + "step": 737 + }, + { + "epoch": 0.09834754797441364, + "grad_norm": 0.32682906533287137, + "learning_rate": 9.99582465174542e-06, + "loss": 0.4381, + "step": 738 + }, + { + "epoch": 0.09848081023454158, + "grad_norm": 0.34395542550116465, + "learning_rate": 9.995795508636786e-06, + "loss": 0.4408, + "step": 739 + }, + { + "epoch": 0.09861407249466951, + "grad_norm": 0.40038040034608635, + "learning_rate": 9.995766264217757e-06, + "loss": 0.447, + "step": 740 + }, + { + "epoch": 0.09874733475479744, + "grad_norm": 0.32184018316749746, + "learning_rate": 9.995736918488928e-06, + "loss": 0.4067, + "step": 741 + }, + { + "epoch": 0.09888059701492537, + "grad_norm": 0.34820264863257433, + "learning_rate": 9.99570747145089e-06, + "loss": 0.4625, + "step": 742 + }, + { + "epoch": 0.09901385927505331, + "grad_norm": 0.3740717623867634, + "learning_rate": 9.995677923104243e-06, + "loss": 0.4576, + "step": 743 + }, + { + "epoch": 0.09914712153518124, + "grad_norm": 0.3167225959022921, + "learning_rate": 9.995648273449587e-06, + "loss": 0.3955, + "step": 744 + }, + { + "epoch": 0.09928038379530917, + "grad_norm": 0.3496204379844668, + "learning_rate": 9.99561852248752e-06, + "loss": 0.4391, + "step": 745 + }, + { + "epoch": 0.0994136460554371, + "grad_norm": 0.3264569010442704, + "learning_rate": 9.995588670218648e-06, + "loss": 0.3989, + "step": 746 + }, + { + "epoch": 0.09954690831556504, + "grad_norm": 0.349434841407941, + "learning_rate": 9.995558716643575e-06, + "loss": 0.4148, + "step": 747 + }, + { + "epoch": 0.09968017057569296, + "grad_norm": 0.33454785689457084, + "learning_rate": 9.99552866176291e-06, + "loss": 0.4181, + "step": 748 + }, + { + "epoch": 0.09981343283582089, + "grad_norm": 0.35221429944216553, + "learning_rate": 9.99549850557726e-06, + "loss": 0.439, + "step": 749 + }, + { + "epoch": 0.09994669509594882, + "grad_norm": 0.33595653946186915, + "learning_rate": 9.99546824808724e-06, + "loss": 0.5464, + "step": 750 + }, + { + "epoch": 0.10007995735607676, + "grad_norm": 0.3415775228920245, + "learning_rate": 9.99543788929346e-06, + "loss": 0.3723, + "step": 751 + }, + { + "epoch": 0.10021321961620469, + "grad_norm": 0.32701362834244085, + "learning_rate": 9.995407429196536e-06, + "loss": 0.4083, + "step": 752 + }, + { + "epoch": 0.10034648187633262, + "grad_norm": 0.3540296495698765, + "learning_rate": 9.99537686779709e-06, + "loss": 0.4573, + "step": 753 + }, + { + "epoch": 0.10047974413646056, + "grad_norm": 0.3233972546321003, + "learning_rate": 9.995346205095735e-06, + "loss": 0.4005, + "step": 754 + }, + { + "epoch": 0.10061300639658849, + "grad_norm": 0.35135920354303324, + "learning_rate": 9.995315441093098e-06, + "loss": 0.4054, + "step": 755 + }, + { + "epoch": 0.10074626865671642, + "grad_norm": 0.33998302146106246, + "learning_rate": 9.995284575789803e-06, + "loss": 0.4595, + "step": 756 + }, + { + "epoch": 0.10087953091684435, + "grad_norm": 0.39005935766129096, + "learning_rate": 9.995253609186472e-06, + "loss": 0.4114, + "step": 757 + }, + { + "epoch": 0.10101279317697229, + "grad_norm": 0.5552825502636174, + "learning_rate": 9.995222541283737e-06, + "loss": 0.3642, + "step": 758 + }, + { + "epoch": 0.10114605543710022, + "grad_norm": 0.36880594723804927, + "learning_rate": 9.995191372082225e-06, + "loss": 0.4107, + "step": 759 + }, + { + "epoch": 0.10127931769722814, + "grad_norm": 0.3118291172007578, + "learning_rate": 9.99516010158257e-06, + "loss": 0.5132, + "step": 760 + }, + { + "epoch": 0.10141257995735607, + "grad_norm": 0.3733475594190064, + "learning_rate": 9.995128729785407e-06, + "loss": 0.4884, + "step": 761 + }, + { + "epoch": 0.10154584221748401, + "grad_norm": 0.3344957208850376, + "learning_rate": 9.995097256691368e-06, + "loss": 0.5035, + "step": 762 + }, + { + "epoch": 0.10167910447761194, + "grad_norm": 0.34775567565699267, + "learning_rate": 9.995065682301095e-06, + "loss": 0.4188, + "step": 763 + }, + { + "epoch": 0.10181236673773987, + "grad_norm": 0.3287642762338547, + "learning_rate": 9.995034006615227e-06, + "loss": 0.3962, + "step": 764 + }, + { + "epoch": 0.1019456289978678, + "grad_norm": 0.44718205787004006, + "learning_rate": 9.995002229634407e-06, + "loss": 0.3512, + "step": 765 + }, + { + "epoch": 0.10207889125799574, + "grad_norm": 0.32974745819162427, + "learning_rate": 9.994970351359278e-06, + "loss": 0.5081, + "step": 766 + }, + { + "epoch": 0.10221215351812367, + "grad_norm": 0.3490926236564695, + "learning_rate": 9.99493837179049e-06, + "loss": 0.4402, + "step": 767 + }, + { + "epoch": 0.1023454157782516, + "grad_norm": 0.34264316247574317, + "learning_rate": 9.994906290928688e-06, + "loss": 0.4286, + "step": 768 + }, + { + "epoch": 0.10247867803837953, + "grad_norm": 0.35571201023142374, + "learning_rate": 9.994874108774521e-06, + "loss": 0.4566, + "step": 769 + }, + { + "epoch": 0.10261194029850747, + "grad_norm": 0.32682339472147776, + "learning_rate": 9.994841825328648e-06, + "loss": 0.4463, + "step": 770 + }, + { + "epoch": 0.1027452025586354, + "grad_norm": 0.34536171317375336, + "learning_rate": 9.994809440591717e-06, + "loss": 0.4422, + "step": 771 + }, + { + "epoch": 0.10287846481876332, + "grad_norm": 0.3338509498191086, + "learning_rate": 9.994776954564389e-06, + "loss": 0.4125, + "step": 772 + }, + { + "epoch": 0.10301172707889125, + "grad_norm": 0.3340707581816469, + "learning_rate": 9.99474436724732e-06, + "loss": 0.3836, + "step": 773 + }, + { + "epoch": 0.1031449893390192, + "grad_norm": 0.3254263531197277, + "learning_rate": 9.994711678641174e-06, + "loss": 0.4379, + "step": 774 + }, + { + "epoch": 0.10327825159914712, + "grad_norm": 0.3397404653986468, + "learning_rate": 9.994678888746612e-06, + "loss": 0.4653, + "step": 775 + }, + { + "epoch": 0.10341151385927505, + "grad_norm": 0.32413980243785734, + "learning_rate": 9.994645997564299e-06, + "loss": 0.4174, + "step": 776 + }, + { + "epoch": 0.10354477611940298, + "grad_norm": 0.31569806019678787, + "learning_rate": 9.994613005094901e-06, + "loss": 0.5093, + "step": 777 + }, + { + "epoch": 0.10367803837953092, + "grad_norm": 0.3376738051170829, + "learning_rate": 9.994579911339089e-06, + "loss": 0.4358, + "step": 778 + }, + { + "epoch": 0.10381130063965885, + "grad_norm": 0.3253203299072543, + "learning_rate": 9.994546716297533e-06, + "loss": 0.4573, + "step": 779 + }, + { + "epoch": 0.10394456289978678, + "grad_norm": 0.3335000991264376, + "learning_rate": 9.994513419970907e-06, + "loss": 0.5334, + "step": 780 + }, + { + "epoch": 0.1040778251599147, + "grad_norm": 0.3284444368807706, + "learning_rate": 9.994480022359885e-06, + "loss": 0.4199, + "step": 781 + }, + { + "epoch": 0.10421108742004265, + "grad_norm": 0.3244242979150648, + "learning_rate": 9.994446523465145e-06, + "loss": 0.4281, + "step": 782 + }, + { + "epoch": 0.10434434968017058, + "grad_norm": 0.3229366280717793, + "learning_rate": 9.994412923287366e-06, + "loss": 0.4271, + "step": 783 + }, + { + "epoch": 0.1044776119402985, + "grad_norm": 0.33481936865662604, + "learning_rate": 9.994379221827229e-06, + "loss": 0.5442, + "step": 784 + }, + { + "epoch": 0.10461087420042645, + "grad_norm": 0.35650195825850967, + "learning_rate": 9.994345419085419e-06, + "loss": 0.4296, + "step": 785 + }, + { + "epoch": 0.10474413646055437, + "grad_norm": 0.32525349639244283, + "learning_rate": 9.994311515062621e-06, + "loss": 0.4105, + "step": 786 + }, + { + "epoch": 0.1048773987206823, + "grad_norm": 0.3173317058577457, + "learning_rate": 9.99427750975952e-06, + "loss": 0.4442, + "step": 787 + }, + { + "epoch": 0.10501066098081023, + "grad_norm": 0.3591920477569359, + "learning_rate": 9.994243403176811e-06, + "loss": 0.5473, + "step": 788 + }, + { + "epoch": 0.10514392324093817, + "grad_norm": 0.33567921986214205, + "learning_rate": 9.99420919531518e-06, + "loss": 0.4491, + "step": 789 + }, + { + "epoch": 0.1052771855010661, + "grad_norm": 0.33010202187485, + "learning_rate": 9.994174886175323e-06, + "loss": 0.4349, + "step": 790 + }, + { + "epoch": 0.10541044776119403, + "grad_norm": 0.344843786382631, + "learning_rate": 9.994140475757938e-06, + "loss": 0.4007, + "step": 791 + }, + { + "epoch": 0.10554371002132196, + "grad_norm": 0.3253744868436078, + "learning_rate": 9.994105964063719e-06, + "loss": 0.504, + "step": 792 + }, + { + "epoch": 0.1056769722814499, + "grad_norm": 0.33044944037901236, + "learning_rate": 9.994071351093368e-06, + "loss": 0.5222, + "step": 793 + }, + { + "epoch": 0.10581023454157783, + "grad_norm": 0.34607503791651295, + "learning_rate": 9.994036636847584e-06, + "loss": 0.4368, + "step": 794 + }, + { + "epoch": 0.10594349680170576, + "grad_norm": 0.3472039287398151, + "learning_rate": 9.994001821327077e-06, + "loss": 0.3788, + "step": 795 + }, + { + "epoch": 0.10607675906183368, + "grad_norm": 0.3148709087298113, + "learning_rate": 9.993966904532549e-06, + "loss": 0.4001, + "step": 796 + }, + { + "epoch": 0.10621002132196163, + "grad_norm": 0.3446062142239341, + "learning_rate": 9.993931886464705e-06, + "loss": 0.4905, + "step": 797 + }, + { + "epoch": 0.10634328358208955, + "grad_norm": 0.3534331455591841, + "learning_rate": 9.993896767124262e-06, + "loss": 0.484, + "step": 798 + }, + { + "epoch": 0.10647654584221748, + "grad_norm": 0.3193328109729677, + "learning_rate": 9.993861546511927e-06, + "loss": 0.4346, + "step": 799 + }, + { + "epoch": 0.10660980810234541, + "grad_norm": 0.34488341074553663, + "learning_rate": 9.993826224628418e-06, + "loss": 0.4504, + "step": 800 + }, + { + "epoch": 0.10674307036247335, + "grad_norm": 0.35173902045968986, + "learning_rate": 9.993790801474448e-06, + "loss": 0.434, + "step": 801 + }, + { + "epoch": 0.10687633262260128, + "grad_norm": 0.32011581817338763, + "learning_rate": 9.993755277050736e-06, + "loss": 0.4225, + "step": 802 + }, + { + "epoch": 0.10700959488272921, + "grad_norm": 0.364368195817761, + "learning_rate": 9.993719651358005e-06, + "loss": 0.4453, + "step": 803 + }, + { + "epoch": 0.10714285714285714, + "grad_norm": 0.3361896866678198, + "learning_rate": 9.993683924396975e-06, + "loss": 0.4593, + "step": 804 + }, + { + "epoch": 0.10727611940298508, + "grad_norm": 0.36187105106961015, + "learning_rate": 9.993648096168372e-06, + "loss": 0.5177, + "step": 805 + }, + { + "epoch": 0.10740938166311301, + "grad_norm": 0.3620223589644586, + "learning_rate": 9.99361216667292e-06, + "loss": 0.4881, + "step": 806 + }, + { + "epoch": 0.10754264392324094, + "grad_norm": 0.339115456125278, + "learning_rate": 9.993576135911349e-06, + "loss": 0.4891, + "step": 807 + }, + { + "epoch": 0.10767590618336886, + "grad_norm": 0.3365380409652069, + "learning_rate": 9.99354000388439e-06, + "loss": 0.3849, + "step": 808 + }, + { + "epoch": 0.1078091684434968, + "grad_norm": 0.3579788241775642, + "learning_rate": 9.993503770592777e-06, + "loss": 0.4572, + "step": 809 + }, + { + "epoch": 0.10794243070362473, + "grad_norm": 0.34429013296208844, + "learning_rate": 9.993467436037243e-06, + "loss": 0.4619, + "step": 810 + }, + { + "epoch": 0.10807569296375266, + "grad_norm": 0.36439712244881156, + "learning_rate": 9.993431000218526e-06, + "loss": 0.4541, + "step": 811 + }, + { + "epoch": 0.10820895522388059, + "grad_norm": 0.30907359300723325, + "learning_rate": 9.993394463137363e-06, + "loss": 0.4596, + "step": 812 + }, + { + "epoch": 0.10834221748400853, + "grad_norm": 0.3542982168115412, + "learning_rate": 9.993357824794496e-06, + "loss": 0.4261, + "step": 813 + }, + { + "epoch": 0.10847547974413646, + "grad_norm": 0.3733338600485063, + "learning_rate": 9.993321085190668e-06, + "loss": 0.442, + "step": 814 + }, + { + "epoch": 0.10860874200426439, + "grad_norm": 0.3198479274205369, + "learning_rate": 9.993284244326626e-06, + "loss": 0.413, + "step": 815 + }, + { + "epoch": 0.10874200426439233, + "grad_norm": 0.3768007744883432, + "learning_rate": 9.993247302203114e-06, + "loss": 0.4189, + "step": 816 + }, + { + "epoch": 0.10887526652452026, + "grad_norm": 0.31241882167586044, + "learning_rate": 9.993210258820882e-06, + "loss": 0.4111, + "step": 817 + }, + { + "epoch": 0.10900852878464819, + "grad_norm": 0.3552492616402414, + "learning_rate": 9.99317311418068e-06, + "loss": 0.4245, + "step": 818 + }, + { + "epoch": 0.10914179104477612, + "grad_norm": 0.33722576380120484, + "learning_rate": 9.993135868283266e-06, + "loss": 0.4607, + "step": 819 + }, + { + "epoch": 0.10927505330490406, + "grad_norm": 0.33387252316183436, + "learning_rate": 9.993098521129391e-06, + "loss": 0.3563, + "step": 820 + }, + { + "epoch": 0.10940831556503199, + "grad_norm": 0.3441515341685132, + "learning_rate": 9.993061072719814e-06, + "loss": 0.4614, + "step": 821 + }, + { + "epoch": 0.10954157782515991, + "grad_norm": 0.34543298786158516, + "learning_rate": 9.993023523055295e-06, + "loss": 0.3696, + "step": 822 + }, + { + "epoch": 0.10967484008528784, + "grad_norm": 0.3436928948663073, + "learning_rate": 9.992985872136591e-06, + "loss": 0.4102, + "step": 823 + }, + { + "epoch": 0.10980810234541578, + "grad_norm": 0.3284692176996944, + "learning_rate": 9.992948119964472e-06, + "loss": 0.5489, + "step": 824 + }, + { + "epoch": 0.10994136460554371, + "grad_norm": 0.35464814523808585, + "learning_rate": 9.9929102665397e-06, + "loss": 0.458, + "step": 825 + }, + { + "epoch": 0.11007462686567164, + "grad_norm": 0.33642035275875404, + "learning_rate": 9.992872311863042e-06, + "loss": 0.5313, + "step": 826 + }, + { + "epoch": 0.11020788912579957, + "grad_norm": 0.34565793879803325, + "learning_rate": 9.99283425593527e-06, + "loss": 0.4378, + "step": 827 + }, + { + "epoch": 0.11034115138592751, + "grad_norm": 0.35407392022265005, + "learning_rate": 9.992796098757155e-06, + "loss": 0.4328, + "step": 828 + }, + { + "epoch": 0.11047441364605544, + "grad_norm": 0.32572598802526537, + "learning_rate": 9.99275784032947e-06, + "loss": 0.4613, + "step": 829 + }, + { + "epoch": 0.11060767590618337, + "grad_norm": 0.32267353430248985, + "learning_rate": 9.99271948065299e-06, + "loss": 0.3783, + "step": 830 + }, + { + "epoch": 0.1107409381663113, + "grad_norm": 0.3205152299329985, + "learning_rate": 9.992681019728497e-06, + "loss": 0.4158, + "step": 831 + }, + { + "epoch": 0.11087420042643924, + "grad_norm": 0.32552927074793075, + "learning_rate": 9.992642457556764e-06, + "loss": 0.4871, + "step": 832 + }, + { + "epoch": 0.11100746268656717, + "grad_norm": 0.3240614992622419, + "learning_rate": 9.99260379413858e-06, + "loss": 0.4561, + "step": 833 + }, + { + "epoch": 0.1111407249466951, + "grad_norm": 0.3207548853198641, + "learning_rate": 9.992565029474726e-06, + "loss": 0.3757, + "step": 834 + }, + { + "epoch": 0.11127398720682302, + "grad_norm": 0.32351293760957717, + "learning_rate": 9.992526163565988e-06, + "loss": 0.4288, + "step": 835 + }, + { + "epoch": 0.11140724946695096, + "grad_norm": 0.3245130029826855, + "learning_rate": 9.992487196413155e-06, + "loss": 0.4252, + "step": 836 + }, + { + "epoch": 0.11154051172707889, + "grad_norm": 0.34070062299660225, + "learning_rate": 9.992448128017016e-06, + "loss": 0.485, + "step": 837 + }, + { + "epoch": 0.11167377398720682, + "grad_norm": 0.32840726923739233, + "learning_rate": 9.992408958378365e-06, + "loss": 0.4419, + "step": 838 + }, + { + "epoch": 0.11180703624733475, + "grad_norm": 0.3373736796474714, + "learning_rate": 9.992369687497994e-06, + "loss": 0.391, + "step": 839 + }, + { + "epoch": 0.11194029850746269, + "grad_norm": 0.3253116501716599, + "learning_rate": 9.992330315376702e-06, + "loss": 0.4296, + "step": 840 + }, + { + "epoch": 0.11207356076759062, + "grad_norm": 0.3561066291527859, + "learning_rate": 9.992290842015283e-06, + "loss": 0.4478, + "step": 841 + }, + { + "epoch": 0.11220682302771855, + "grad_norm": 0.34007877125410385, + "learning_rate": 9.992251267414546e-06, + "loss": 0.5243, + "step": 842 + }, + { + "epoch": 0.11234008528784648, + "grad_norm": 0.32369118524587337, + "learning_rate": 9.992211591575284e-06, + "loss": 0.4572, + "step": 843 + }, + { + "epoch": 0.11247334754797442, + "grad_norm": 0.3438054165074421, + "learning_rate": 9.992171814498306e-06, + "loss": 0.4396, + "step": 844 + }, + { + "epoch": 0.11260660980810235, + "grad_norm": 0.32298662677893214, + "learning_rate": 9.992131936184419e-06, + "loss": 0.442, + "step": 845 + }, + { + "epoch": 0.11273987206823027, + "grad_norm": 0.33858366002785983, + "learning_rate": 9.992091956634432e-06, + "loss": 0.4403, + "step": 846 + }, + { + "epoch": 0.11287313432835822, + "grad_norm": 0.3383042570525774, + "learning_rate": 9.992051875849154e-06, + "loss": 0.4099, + "step": 847 + }, + { + "epoch": 0.11300639658848614, + "grad_norm": 0.331739268773511, + "learning_rate": 9.992011693829399e-06, + "loss": 0.3957, + "step": 848 + }, + { + "epoch": 0.11313965884861407, + "grad_norm": 0.3279907290451416, + "learning_rate": 9.99197141057598e-06, + "loss": 0.468, + "step": 849 + }, + { + "epoch": 0.113272921108742, + "grad_norm": 0.3595692734257586, + "learning_rate": 9.991931026089717e-06, + "loss": 0.5456, + "step": 850 + }, + { + "epoch": 0.11340618336886994, + "grad_norm": 0.3305574446417737, + "learning_rate": 9.991890540371427e-06, + "loss": 0.4037, + "step": 851 + }, + { + "epoch": 0.11353944562899787, + "grad_norm": 0.3393934544104253, + "learning_rate": 9.991849953421931e-06, + "loss": 0.4503, + "step": 852 + }, + { + "epoch": 0.1136727078891258, + "grad_norm": 0.3529306053867814, + "learning_rate": 9.991809265242055e-06, + "loss": 0.4649, + "step": 853 + }, + { + "epoch": 0.11380597014925373, + "grad_norm": 0.32298682619400354, + "learning_rate": 9.991768475832617e-06, + "loss": 0.3974, + "step": 854 + }, + { + "epoch": 0.11393923240938167, + "grad_norm": 0.3357964494263878, + "learning_rate": 9.991727585194452e-06, + "loss": 0.4128, + "step": 855 + }, + { + "epoch": 0.1140724946695096, + "grad_norm": 0.33609688686383543, + "learning_rate": 9.991686593328385e-06, + "loss": 0.3964, + "step": 856 + }, + { + "epoch": 0.11420575692963753, + "grad_norm": 0.3381558803211046, + "learning_rate": 9.991645500235247e-06, + "loss": 0.5292, + "step": 857 + }, + { + "epoch": 0.11433901918976545, + "grad_norm": 0.32976237535578884, + "learning_rate": 9.991604305915875e-06, + "loss": 0.4143, + "step": 858 + }, + { + "epoch": 0.1144722814498934, + "grad_norm": 0.34825599775276983, + "learning_rate": 9.9915630103711e-06, + "loss": 0.4028, + "step": 859 + }, + { + "epoch": 0.11460554371002132, + "grad_norm": 0.32487264398079024, + "learning_rate": 9.991521613601763e-06, + "loss": 0.4105, + "step": 860 + }, + { + "epoch": 0.11473880597014925, + "grad_norm": 0.3735784995468277, + "learning_rate": 9.9914801156087e-06, + "loss": 0.4109, + "step": 861 + }, + { + "epoch": 0.11487206823027718, + "grad_norm": 0.35194127312261003, + "learning_rate": 9.991438516392755e-06, + "loss": 0.4352, + "step": 862 + }, + { + "epoch": 0.11500533049040512, + "grad_norm": 0.32410743966828365, + "learning_rate": 9.991396815954773e-06, + "loss": 0.3985, + "step": 863 + }, + { + "epoch": 0.11513859275053305, + "grad_norm": 0.3501889129814369, + "learning_rate": 9.991355014295594e-06, + "loss": 0.4358, + "step": 864 + }, + { + "epoch": 0.11527185501066098, + "grad_norm": 0.32942980871441535, + "learning_rate": 9.991313111416072e-06, + "loss": 0.5273, + "step": 865 + }, + { + "epoch": 0.1154051172707889, + "grad_norm": 0.3320228334556584, + "learning_rate": 9.991271107317053e-06, + "loss": 0.4751, + "step": 866 + }, + { + "epoch": 0.11553837953091685, + "grad_norm": 0.34544306632397237, + "learning_rate": 9.991229001999392e-06, + "loss": 0.4303, + "step": 867 + }, + { + "epoch": 0.11567164179104478, + "grad_norm": 0.30319132916943103, + "learning_rate": 9.991186795463938e-06, + "loss": 0.3569, + "step": 868 + }, + { + "epoch": 0.1158049040511727, + "grad_norm": 0.31660949287714957, + "learning_rate": 9.991144487711551e-06, + "loss": 0.4195, + "step": 869 + }, + { + "epoch": 0.11593816631130063, + "grad_norm": 0.324342349705349, + "learning_rate": 9.991102078743089e-06, + "loss": 0.3978, + "step": 870 + }, + { + "epoch": 0.11607142857142858, + "grad_norm": 0.31242717898139793, + "learning_rate": 9.99105956855941e-06, + "loss": 0.4436, + "step": 871 + }, + { + "epoch": 0.1162046908315565, + "grad_norm": 0.33133509976626435, + "learning_rate": 9.991016957161374e-06, + "loss": 0.4251, + "step": 872 + }, + { + "epoch": 0.11633795309168443, + "grad_norm": 0.33060675279319973, + "learning_rate": 9.990974244549852e-06, + "loss": 0.3852, + "step": 873 + }, + { + "epoch": 0.11647121535181236, + "grad_norm": 0.30407696970178044, + "learning_rate": 9.990931430725702e-06, + "loss": 0.4344, + "step": 874 + }, + { + "epoch": 0.1166044776119403, + "grad_norm": 0.33632340140822325, + "learning_rate": 9.990888515689798e-06, + "loss": 0.4363, + "step": 875 + }, + { + "epoch": 0.11673773987206823, + "grad_norm": 0.3360114411293813, + "learning_rate": 9.990845499443009e-06, + "loss": 0.3975, + "step": 876 + }, + { + "epoch": 0.11687100213219616, + "grad_norm": 0.3161485488486996, + "learning_rate": 9.990802381986207e-06, + "loss": 0.3401, + "step": 877 + }, + { + "epoch": 0.1170042643923241, + "grad_norm": 0.32831544250917777, + "learning_rate": 9.990759163320267e-06, + "loss": 0.4306, + "step": 878 + }, + { + "epoch": 0.11713752665245203, + "grad_norm": 0.33119947615120243, + "learning_rate": 9.990715843446064e-06, + "loss": 0.4468, + "step": 879 + }, + { + "epoch": 0.11727078891257996, + "grad_norm": 0.3541541646785907, + "learning_rate": 9.990672422364476e-06, + "loss": 0.4591, + "step": 880 + }, + { + "epoch": 0.11740405117270789, + "grad_norm": 0.3268109585556604, + "learning_rate": 9.990628900076387e-06, + "loss": 0.4301, + "step": 881 + }, + { + "epoch": 0.11753731343283583, + "grad_norm": 0.331418128168709, + "learning_rate": 9.990585276582676e-06, + "loss": 0.4048, + "step": 882 + }, + { + "epoch": 0.11767057569296376, + "grad_norm": 0.33586006060986634, + "learning_rate": 9.990541551884228e-06, + "loss": 0.4177, + "step": 883 + }, + { + "epoch": 0.11780383795309168, + "grad_norm": 0.355910446383196, + "learning_rate": 9.990497725981931e-06, + "loss": 0.5397, + "step": 884 + }, + { + "epoch": 0.11793710021321961, + "grad_norm": 0.3434243986979816, + "learning_rate": 9.990453798876675e-06, + "loss": 0.4836, + "step": 885 + }, + { + "epoch": 0.11807036247334755, + "grad_norm": 0.3206215599286929, + "learning_rate": 9.990409770569348e-06, + "loss": 0.3523, + "step": 886 + }, + { + "epoch": 0.11820362473347548, + "grad_norm": 0.3718256700529695, + "learning_rate": 9.990365641060844e-06, + "loss": 0.4918, + "step": 887 + }, + { + "epoch": 0.11833688699360341, + "grad_norm": 0.32719093339803534, + "learning_rate": 9.99032141035206e-06, + "loss": 0.3975, + "step": 888 + }, + { + "epoch": 0.11847014925373134, + "grad_norm": 0.3350596896535814, + "learning_rate": 9.99027707844389e-06, + "loss": 0.3702, + "step": 889 + }, + { + "epoch": 0.11860341151385928, + "grad_norm": 0.3335394927606605, + "learning_rate": 9.990232645337232e-06, + "loss": 0.4209, + "step": 890 + }, + { + "epoch": 0.11873667377398721, + "grad_norm": 0.3633337759186495, + "learning_rate": 9.99018811103299e-06, + "loss": 0.5116, + "step": 891 + }, + { + "epoch": 0.11886993603411514, + "grad_norm": 0.32952605695688014, + "learning_rate": 9.990143475532066e-06, + "loss": 0.5628, + "step": 892 + }, + { + "epoch": 0.11900319829424306, + "grad_norm": 0.34687535187228086, + "learning_rate": 9.990098738835366e-06, + "loss": 0.4032, + "step": 893 + }, + { + "epoch": 0.11913646055437101, + "grad_norm": 0.3305919702362504, + "learning_rate": 9.990053900943797e-06, + "loss": 0.4082, + "step": 894 + }, + { + "epoch": 0.11926972281449894, + "grad_norm": 0.349985382236258, + "learning_rate": 9.990008961858268e-06, + "loss": 0.5699, + "step": 895 + }, + { + "epoch": 0.11940298507462686, + "grad_norm": 0.33821122639380136, + "learning_rate": 9.989963921579688e-06, + "loss": 0.4532, + "step": 896 + }, + { + "epoch": 0.11953624733475479, + "grad_norm": 0.351419880774976, + "learning_rate": 9.989918780108974e-06, + "loss": 0.466, + "step": 897 + }, + { + "epoch": 0.11966950959488273, + "grad_norm": 0.33818421913526725, + "learning_rate": 9.98987353744704e-06, + "loss": 0.4508, + "step": 898 + }, + { + "epoch": 0.11980277185501066, + "grad_norm": 0.3323527888291918, + "learning_rate": 9.989828193594803e-06, + "loss": 0.3652, + "step": 899 + }, + { + "epoch": 0.11993603411513859, + "grad_norm": 0.33170339484667966, + "learning_rate": 9.989782748553185e-06, + "loss": 0.4415, + "step": 900 + }, + { + "epoch": 0.12006929637526652, + "grad_norm": 0.3522483126655363, + "learning_rate": 9.989737202323103e-06, + "loss": 0.4361, + "step": 901 + }, + { + "epoch": 0.12020255863539446, + "grad_norm": 0.331174892865463, + "learning_rate": 9.989691554905484e-06, + "loss": 0.3714, + "step": 902 + }, + { + "epoch": 0.12033582089552239, + "grad_norm": 0.33809889233246937, + "learning_rate": 9.989645806301254e-06, + "loss": 0.4011, + "step": 903 + }, + { + "epoch": 0.12046908315565032, + "grad_norm": 0.3275097223492691, + "learning_rate": 9.989599956511338e-06, + "loss": 0.4481, + "step": 904 + }, + { + "epoch": 0.12060234541577824, + "grad_norm": 0.35458878425836066, + "learning_rate": 9.989554005536667e-06, + "loss": 0.4036, + "step": 905 + }, + { + "epoch": 0.12073560767590619, + "grad_norm": 0.34178269682839296, + "learning_rate": 9.989507953378175e-06, + "loss": 0.5254, + "step": 906 + }, + { + "epoch": 0.12086886993603412, + "grad_norm": 0.32866731870708665, + "learning_rate": 9.989461800036793e-06, + "loss": 0.4096, + "step": 907 + }, + { + "epoch": 0.12100213219616204, + "grad_norm": 0.33699243463916906, + "learning_rate": 9.989415545513459e-06, + "loss": 0.4013, + "step": 908 + }, + { + "epoch": 0.12113539445628999, + "grad_norm": 0.33595609417480765, + "learning_rate": 9.989369189809109e-06, + "loss": 0.49, + "step": 909 + }, + { + "epoch": 0.12126865671641791, + "grad_norm": 0.353141227718161, + "learning_rate": 9.989322732924685e-06, + "loss": 0.483, + "step": 910 + }, + { + "epoch": 0.12140191897654584, + "grad_norm": 0.32231482114655885, + "learning_rate": 9.989276174861128e-06, + "loss": 0.444, + "step": 911 + }, + { + "epoch": 0.12153518123667377, + "grad_norm": 0.3622026957767886, + "learning_rate": 9.989229515619382e-06, + "loss": 0.4105, + "step": 912 + }, + { + "epoch": 0.12166844349680171, + "grad_norm": 0.3334515121305082, + "learning_rate": 9.989182755200395e-06, + "loss": 0.5102, + "step": 913 + }, + { + "epoch": 0.12180170575692964, + "grad_norm": 0.33707373246842004, + "learning_rate": 9.989135893605114e-06, + "loss": 0.448, + "step": 914 + }, + { + "epoch": 0.12193496801705757, + "grad_norm": 0.33324353110986865, + "learning_rate": 9.989088930834487e-06, + "loss": 0.4126, + "step": 915 + }, + { + "epoch": 0.1220682302771855, + "grad_norm": 0.3158287065841538, + "learning_rate": 9.989041866889469e-06, + "loss": 0.3949, + "step": 916 + }, + { + "epoch": 0.12220149253731344, + "grad_norm": 0.3352591313408401, + "learning_rate": 9.988994701771016e-06, + "loss": 0.4132, + "step": 917 + }, + { + "epoch": 0.12233475479744137, + "grad_norm": 0.31964342874376467, + "learning_rate": 9.988947435480081e-06, + "loss": 0.4907, + "step": 918 + }, + { + "epoch": 0.1224680170575693, + "grad_norm": 0.3317736703941072, + "learning_rate": 9.988900068017623e-06, + "loss": 0.4834, + "step": 919 + }, + { + "epoch": 0.12260127931769722, + "grad_norm": 0.3307835689373304, + "learning_rate": 9.988852599384605e-06, + "loss": 0.4653, + "step": 920 + }, + { + "epoch": 0.12273454157782517, + "grad_norm": 0.322440262373477, + "learning_rate": 9.988805029581989e-06, + "loss": 0.5586, + "step": 921 + }, + { + "epoch": 0.1228678038379531, + "grad_norm": 0.3329041546215809, + "learning_rate": 9.988757358610737e-06, + "loss": 0.4475, + "step": 922 + }, + { + "epoch": 0.12300106609808102, + "grad_norm": 0.33408695087059426, + "learning_rate": 9.988709586471819e-06, + "loss": 0.4447, + "step": 923 + }, + { + "epoch": 0.12313432835820895, + "grad_norm": 0.32408340872169294, + "learning_rate": 9.988661713166202e-06, + "loss": 0.4705, + "step": 924 + }, + { + "epoch": 0.12326759061833689, + "grad_norm": 0.33571866242832027, + "learning_rate": 9.988613738694857e-06, + "loss": 0.4562, + "step": 925 + }, + { + "epoch": 0.12340085287846482, + "grad_norm": 0.34080366143148944, + "learning_rate": 9.988565663058755e-06, + "loss": 0.4637, + "step": 926 + }, + { + "epoch": 0.12353411513859275, + "grad_norm": 0.3298843213678911, + "learning_rate": 9.988517486258875e-06, + "loss": 0.4119, + "step": 927 + }, + { + "epoch": 0.12366737739872068, + "grad_norm": 0.3322952915428179, + "learning_rate": 9.988469208296192e-06, + "loss": 0.3637, + "step": 928 + }, + { + "epoch": 0.12380063965884862, + "grad_norm": 0.30439485395907184, + "learning_rate": 9.988420829171686e-06, + "loss": 0.3748, + "step": 929 + }, + { + "epoch": 0.12393390191897655, + "grad_norm": 0.3250561998974076, + "learning_rate": 9.988372348886336e-06, + "loss": 0.5016, + "step": 930 + }, + { + "epoch": 0.12406716417910447, + "grad_norm": 0.291350773876482, + "learning_rate": 9.988323767441126e-06, + "loss": 0.4393, + "step": 931 + }, + { + "epoch": 0.1242004264392324, + "grad_norm": 0.3138144759768395, + "learning_rate": 9.988275084837042e-06, + "loss": 0.3714, + "step": 932 + }, + { + "epoch": 0.12433368869936035, + "grad_norm": 0.3234061062183473, + "learning_rate": 9.98822630107507e-06, + "loss": 0.4796, + "step": 933 + }, + { + "epoch": 0.12446695095948827, + "grad_norm": 0.35058870088466904, + "learning_rate": 9.9881774161562e-06, + "loss": 0.4431, + "step": 934 + }, + { + "epoch": 0.1246002132196162, + "grad_norm": 0.3125999071552325, + "learning_rate": 9.988128430081425e-06, + "loss": 0.4191, + "step": 935 + }, + { + "epoch": 0.12473347547974413, + "grad_norm": 0.3063672255676606, + "learning_rate": 9.988079342851735e-06, + "loss": 0.4368, + "step": 936 + }, + { + "epoch": 0.12486673773987207, + "grad_norm": 0.34010538066026047, + "learning_rate": 9.988030154468127e-06, + "loss": 0.4432, + "step": 937 + }, + { + "epoch": 0.125, + "grad_norm": 0.3165561952529604, + "learning_rate": 9.987980864931599e-06, + "loss": 0.3825, + "step": 938 + }, + { + "epoch": 0.12513326226012794, + "grad_norm": 0.3486441453005681, + "learning_rate": 9.98793147424315e-06, + "loss": 0.4999, + "step": 939 + }, + { + "epoch": 0.12526652452025586, + "grad_norm": 0.3377783293450586, + "learning_rate": 9.987881982403782e-06, + "loss": 0.4406, + "step": 940 + }, + { + "epoch": 0.1253997867803838, + "grad_norm": 0.30425494588543855, + "learning_rate": 9.987832389414497e-06, + "loss": 0.3449, + "step": 941 + }, + { + "epoch": 0.12553304904051174, + "grad_norm": 0.34566507824389064, + "learning_rate": 9.987782695276305e-06, + "loss": 0.3904, + "step": 942 + }, + { + "epoch": 0.12566631130063965, + "grad_norm": 0.3332211794428145, + "learning_rate": 9.98773289999021e-06, + "loss": 0.4937, + "step": 943 + }, + { + "epoch": 0.1257995735607676, + "grad_norm": 0.34966097601224067, + "learning_rate": 9.987683003557223e-06, + "loss": 0.468, + "step": 944 + }, + { + "epoch": 0.1259328358208955, + "grad_norm": 0.3432805710172726, + "learning_rate": 9.987633005978354e-06, + "loss": 0.4176, + "step": 945 + }, + { + "epoch": 0.12606609808102345, + "grad_norm": 0.35221877895181986, + "learning_rate": 9.98758290725462e-06, + "loss": 0.5372, + "step": 946 + }, + { + "epoch": 0.1261993603411514, + "grad_norm": 0.346323147118792, + "learning_rate": 9.987532707387033e-06, + "loss": 0.4839, + "step": 947 + }, + { + "epoch": 0.1263326226012793, + "grad_norm": 0.34797757068463003, + "learning_rate": 9.987482406376616e-06, + "loss": 0.4533, + "step": 948 + }, + { + "epoch": 0.12646588486140725, + "grad_norm": 0.3259601550221118, + "learning_rate": 9.987432004224385e-06, + "loss": 0.4528, + "step": 949 + }, + { + "epoch": 0.1265991471215352, + "grad_norm": 0.3457763092016774, + "learning_rate": 9.987381500931365e-06, + "loss": 0.4248, + "step": 950 + }, + { + "epoch": 0.1267324093816631, + "grad_norm": 0.3282405348506851, + "learning_rate": 9.987330896498577e-06, + "loss": 0.4174, + "step": 951 + }, + { + "epoch": 0.12686567164179105, + "grad_norm": 0.32894848660596065, + "learning_rate": 9.987280190927051e-06, + "loss": 0.387, + "step": 952 + }, + { + "epoch": 0.12699893390191896, + "grad_norm": 0.3409044671069502, + "learning_rate": 9.987229384217812e-06, + "loss": 0.4446, + "step": 953 + }, + { + "epoch": 0.1271321961620469, + "grad_norm": 0.35887591739883523, + "learning_rate": 9.987178476371893e-06, + "loss": 0.3834, + "step": 954 + }, + { + "epoch": 0.12726545842217485, + "grad_norm": 0.33462619243382785, + "learning_rate": 9.987127467390322e-06, + "loss": 0.3467, + "step": 955 + }, + { + "epoch": 0.12739872068230276, + "grad_norm": 0.3197464046011773, + "learning_rate": 9.987076357274139e-06, + "loss": 0.3964, + "step": 956 + }, + { + "epoch": 0.1275319829424307, + "grad_norm": 0.3436696991998625, + "learning_rate": 9.987025146024377e-06, + "loss": 0.5224, + "step": 957 + }, + { + "epoch": 0.12766524520255865, + "grad_norm": 0.35022602872532765, + "learning_rate": 9.986973833642075e-06, + "loss": 0.3993, + "step": 958 + }, + { + "epoch": 0.12779850746268656, + "grad_norm": 0.330958935795321, + "learning_rate": 9.986922420128275e-06, + "loss": 0.3816, + "step": 959 + }, + { + "epoch": 0.1279317697228145, + "grad_norm": 0.35673850726098355, + "learning_rate": 9.986870905484017e-06, + "loss": 0.4526, + "step": 960 + }, + { + "epoch": 0.12806503198294242, + "grad_norm": 0.35834870466418034, + "learning_rate": 9.986819289710348e-06, + "loss": 0.4825, + "step": 961 + }, + { + "epoch": 0.12819829424307036, + "grad_norm": 0.35525359053435707, + "learning_rate": 9.986767572808313e-06, + "loss": 0.4278, + "step": 962 + }, + { + "epoch": 0.1283315565031983, + "grad_norm": 0.39371931620346606, + "learning_rate": 9.986715754778963e-06, + "loss": 0.483, + "step": 963 + }, + { + "epoch": 0.12846481876332622, + "grad_norm": 0.32464461536953276, + "learning_rate": 9.986663835623347e-06, + "loss": 0.4244, + "step": 964 + }, + { + "epoch": 0.12859808102345416, + "grad_norm": 0.34618031201069777, + "learning_rate": 9.98661181534252e-06, + "loss": 0.4923, + "step": 965 + }, + { + "epoch": 0.1287313432835821, + "grad_norm": 0.3380523556517145, + "learning_rate": 9.986559693937532e-06, + "loss": 0.3818, + "step": 966 + }, + { + "epoch": 0.12886460554371001, + "grad_norm": 0.3491653771014489, + "learning_rate": 9.986507471409445e-06, + "loss": 0.498, + "step": 967 + }, + { + "epoch": 0.12899786780383796, + "grad_norm": 0.32907954186350213, + "learning_rate": 9.986455147759318e-06, + "loss": 0.4371, + "step": 968 + }, + { + "epoch": 0.12913113006396587, + "grad_norm": 0.3333736993389416, + "learning_rate": 9.986402722988208e-06, + "loss": 0.5237, + "step": 969 + }, + { + "epoch": 0.1292643923240938, + "grad_norm": 0.3359121712041218, + "learning_rate": 9.98635019709718e-06, + "loss": 0.4549, + "step": 970 + }, + { + "epoch": 0.12939765458422176, + "grad_norm": 0.33349408180082624, + "learning_rate": 9.986297570087302e-06, + "loss": 0.4814, + "step": 971 + }, + { + "epoch": 0.12953091684434967, + "grad_norm": 0.3482537600093298, + "learning_rate": 9.986244841959638e-06, + "loss": 0.4489, + "step": 972 + }, + { + "epoch": 0.1296641791044776, + "grad_norm": 0.34632168600714935, + "learning_rate": 9.98619201271526e-06, + "loss": 0.4484, + "step": 973 + }, + { + "epoch": 0.12979744136460555, + "grad_norm": 0.343306528666906, + "learning_rate": 9.986139082355236e-06, + "loss": 0.427, + "step": 974 + }, + { + "epoch": 0.12993070362473347, + "grad_norm": 0.326367436933536, + "learning_rate": 9.98608605088064e-06, + "loss": 0.4119, + "step": 975 + }, + { + "epoch": 0.1300639658848614, + "grad_norm": 0.35987018061533177, + "learning_rate": 9.986032918292548e-06, + "loss": 0.4452, + "step": 976 + }, + { + "epoch": 0.13019722814498935, + "grad_norm": 0.32335783354205433, + "learning_rate": 9.98597968459204e-06, + "loss": 0.3868, + "step": 977 + }, + { + "epoch": 0.13033049040511727, + "grad_norm": 0.3446529458172881, + "learning_rate": 9.985926349780192e-06, + "loss": 0.3945, + "step": 978 + }, + { + "epoch": 0.1304637526652452, + "grad_norm": 0.3333835854239694, + "learning_rate": 9.985872913858087e-06, + "loss": 0.4268, + "step": 979 + }, + { + "epoch": 0.13059701492537312, + "grad_norm": 0.35423800399378147, + "learning_rate": 9.985819376826808e-06, + "loss": 0.4732, + "step": 980 + }, + { + "epoch": 0.13073027718550106, + "grad_norm": 0.338075870816495, + "learning_rate": 9.985765738687443e-06, + "loss": 0.4118, + "step": 981 + }, + { + "epoch": 0.130863539445629, + "grad_norm": 0.33223308044451166, + "learning_rate": 9.985711999441078e-06, + "loss": 0.4152, + "step": 982 + }, + { + "epoch": 0.13099680170575692, + "grad_norm": 0.3246297042683456, + "learning_rate": 9.985658159088803e-06, + "loss": 0.4267, + "step": 983 + }, + { + "epoch": 0.13113006396588486, + "grad_norm": 0.5130840820288155, + "learning_rate": 9.985604217631708e-06, + "loss": 0.3985, + "step": 984 + }, + { + "epoch": 0.1312633262260128, + "grad_norm": 0.3398925581940045, + "learning_rate": 9.985550175070888e-06, + "loss": 0.395, + "step": 985 + }, + { + "epoch": 0.13139658848614072, + "grad_norm": 0.32202086842814437, + "learning_rate": 9.985496031407442e-06, + "loss": 0.3619, + "step": 986 + }, + { + "epoch": 0.13152985074626866, + "grad_norm": 0.36673027851566586, + "learning_rate": 9.985441786642464e-06, + "loss": 0.5097, + "step": 987 + }, + { + "epoch": 0.13166311300639658, + "grad_norm": 0.3311080550416306, + "learning_rate": 9.985387440777056e-06, + "loss": 0.5072, + "step": 988 + }, + { + "epoch": 0.13179637526652452, + "grad_norm": 0.3575774875797953, + "learning_rate": 9.985332993812319e-06, + "loss": 0.3862, + "step": 989 + }, + { + "epoch": 0.13192963752665246, + "grad_norm": 0.3429213081033057, + "learning_rate": 9.985278445749358e-06, + "loss": 0.422, + "step": 990 + }, + { + "epoch": 0.13206289978678037, + "grad_norm": 0.3286210272007724, + "learning_rate": 9.98522379658928e-06, + "loss": 0.4596, + "step": 991 + }, + { + "epoch": 0.13219616204690832, + "grad_norm": 0.34645278486510017, + "learning_rate": 9.98516904633319e-06, + "loss": 0.4033, + "step": 992 + }, + { + "epoch": 0.13232942430703626, + "grad_norm": 0.3380630406801063, + "learning_rate": 9.985114194982202e-06, + "loss": 0.5041, + "step": 993 + }, + { + "epoch": 0.13246268656716417, + "grad_norm": 0.33325860150249625, + "learning_rate": 9.985059242537425e-06, + "loss": 0.4423, + "step": 994 + }, + { + "epoch": 0.13259594882729211, + "grad_norm": 0.3274649806727609, + "learning_rate": 9.985004188999975e-06, + "loss": 0.424, + "step": 995 + }, + { + "epoch": 0.13272921108742003, + "grad_norm": 0.32156621070785424, + "learning_rate": 9.984949034370971e-06, + "loss": 0.4475, + "step": 996 + }, + { + "epoch": 0.13286247334754797, + "grad_norm": 0.33208369822838335, + "learning_rate": 9.98489377865153e-06, + "loss": 0.4371, + "step": 997 + }, + { + "epoch": 0.1329957356076759, + "grad_norm": 0.3452238164007947, + "learning_rate": 9.984838421842769e-06, + "loss": 0.4445, + "step": 998 + }, + { + "epoch": 0.13312899786780383, + "grad_norm": 0.3358294564771051, + "learning_rate": 9.984782963945814e-06, + "loss": 0.3998, + "step": 999 + }, + { + "epoch": 0.13326226012793177, + "grad_norm": 0.33059383486352883, + "learning_rate": 9.984727404961788e-06, + "loss": 0.4844, + "step": 1000 + }, + { + "epoch": 0.1333955223880597, + "grad_norm": 0.3340385342794549, + "learning_rate": 9.98467174489182e-06, + "loss": 0.4732, + "step": 1001 + }, + { + "epoch": 0.13352878464818763, + "grad_norm": 0.3443358827841558, + "learning_rate": 9.984615983737037e-06, + "loss": 0.4357, + "step": 1002 + }, + { + "epoch": 0.13366204690831557, + "grad_norm": 0.33877585092119966, + "learning_rate": 9.984560121498568e-06, + "loss": 0.4716, + "step": 1003 + }, + { + "epoch": 0.1337953091684435, + "grad_norm": 0.32846433236072836, + "learning_rate": 9.98450415817755e-06, + "loss": 0.4175, + "step": 1004 + }, + { + "epoch": 0.13392857142857142, + "grad_norm": 0.3005535283320229, + "learning_rate": 9.984448093775116e-06, + "loss": 0.396, + "step": 1005 + }, + { + "epoch": 0.13406183368869937, + "grad_norm": 0.3296259141932075, + "learning_rate": 9.9843919282924e-06, + "loss": 0.3766, + "step": 1006 + }, + { + "epoch": 0.13419509594882728, + "grad_norm": 0.32267089174341984, + "learning_rate": 9.984335661730547e-06, + "loss": 0.4328, + "step": 1007 + }, + { + "epoch": 0.13432835820895522, + "grad_norm": 0.32257974649079996, + "learning_rate": 9.984279294090693e-06, + "loss": 0.4521, + "step": 1008 + }, + { + "epoch": 0.13446162046908317, + "grad_norm": 0.29476339684912384, + "learning_rate": 9.984222825373983e-06, + "loss": 0.4709, + "step": 1009 + }, + { + "epoch": 0.13459488272921108, + "grad_norm": 0.2945122641832862, + "learning_rate": 9.984166255581564e-06, + "loss": 0.4444, + "step": 1010 + }, + { + "epoch": 0.13472814498933902, + "grad_norm": 0.32490332214995815, + "learning_rate": 9.984109584714578e-06, + "loss": 0.4616, + "step": 1011 + }, + { + "epoch": 0.13486140724946696, + "grad_norm": 0.30361747347019824, + "learning_rate": 9.984052812774178e-06, + "loss": 0.547, + "step": 1012 + }, + { + "epoch": 0.13499466950959488, + "grad_norm": 0.31703332819833163, + "learning_rate": 9.983995939761518e-06, + "loss": 0.432, + "step": 1013 + }, + { + "epoch": 0.13512793176972282, + "grad_norm": 0.3024651260349858, + "learning_rate": 9.983938965677743e-06, + "loss": 0.3799, + "step": 1014 + }, + { + "epoch": 0.13526119402985073, + "grad_norm": 0.29863129106268416, + "learning_rate": 9.983881890524016e-06, + "loss": 0.3648, + "step": 1015 + }, + { + "epoch": 0.13539445628997868, + "grad_norm": 0.3217839346739674, + "learning_rate": 9.983824714301493e-06, + "loss": 0.4203, + "step": 1016 + }, + { + "epoch": 0.13552771855010662, + "grad_norm": 0.3169858795038294, + "learning_rate": 9.983767437011332e-06, + "loss": 0.4182, + "step": 1017 + }, + { + "epoch": 0.13566098081023453, + "grad_norm": 0.3342492047419237, + "learning_rate": 9.983710058654692e-06, + "loss": 0.4218, + "step": 1018 + }, + { + "epoch": 0.13579424307036247, + "grad_norm": 0.32446546448564073, + "learning_rate": 9.983652579232742e-06, + "loss": 0.3528, + "step": 1019 + }, + { + "epoch": 0.13592750533049042, + "grad_norm": 0.33739314563412515, + "learning_rate": 9.983594998746644e-06, + "loss": 0.4758, + "step": 1020 + }, + { + "epoch": 0.13606076759061833, + "grad_norm": 0.31953571517818247, + "learning_rate": 9.983537317197567e-06, + "loss": 0.377, + "step": 1021 + }, + { + "epoch": 0.13619402985074627, + "grad_norm": 0.3339786268374736, + "learning_rate": 9.983479534586682e-06, + "loss": 0.4478, + "step": 1022 + }, + { + "epoch": 0.1363272921108742, + "grad_norm": 0.3160943504117234, + "learning_rate": 9.983421650915158e-06, + "loss": 0.4534, + "step": 1023 + }, + { + "epoch": 0.13646055437100213, + "grad_norm": 0.3278786679650099, + "learning_rate": 9.98336366618417e-06, + "loss": 0.375, + "step": 1024 + }, + { + "epoch": 0.13659381663113007, + "grad_norm": 0.33785379776178703, + "learning_rate": 9.983305580394894e-06, + "loss": 0.404, + "step": 1025 + }, + { + "epoch": 0.13672707889125799, + "grad_norm": 0.3202212923026862, + "learning_rate": 9.983247393548507e-06, + "loss": 0.4352, + "step": 1026 + }, + { + "epoch": 0.13686034115138593, + "grad_norm": 0.3217250042781443, + "learning_rate": 9.98318910564619e-06, + "loss": 0.4126, + "step": 1027 + }, + { + "epoch": 0.13699360341151387, + "grad_norm": 0.29796207589921636, + "learning_rate": 9.983130716689127e-06, + "loss": 0.3626, + "step": 1028 + }, + { + "epoch": 0.13712686567164178, + "grad_norm": 0.32807875464795516, + "learning_rate": 9.983072226678498e-06, + "loss": 0.4308, + "step": 1029 + }, + { + "epoch": 0.13726012793176973, + "grad_norm": 0.3147762847800468, + "learning_rate": 9.983013635615492e-06, + "loss": 0.4188, + "step": 1030 + }, + { + "epoch": 0.13739339019189764, + "grad_norm": 0.3175628268938806, + "learning_rate": 9.982954943501296e-06, + "loss": 0.4025, + "step": 1031 + }, + { + "epoch": 0.13752665245202558, + "grad_norm": 0.33229564483892693, + "learning_rate": 9.982896150337101e-06, + "loss": 0.4481, + "step": 1032 + }, + { + "epoch": 0.13765991471215352, + "grad_norm": 0.41873006140714136, + "learning_rate": 9.982837256124098e-06, + "loss": 0.3924, + "step": 1033 + }, + { + "epoch": 0.13779317697228144, + "grad_norm": 0.34222092770422846, + "learning_rate": 9.982778260863481e-06, + "loss": 0.4895, + "step": 1034 + }, + { + "epoch": 0.13792643923240938, + "grad_norm": 0.30492116643492145, + "learning_rate": 9.982719164556449e-06, + "loss": 0.4357, + "step": 1035 + }, + { + "epoch": 0.13805970149253732, + "grad_norm": 0.34363523123139067, + "learning_rate": 9.9826599672042e-06, + "loss": 0.3707, + "step": 1036 + }, + { + "epoch": 0.13819296375266524, + "grad_norm": 0.3108185870564616, + "learning_rate": 9.982600668807932e-06, + "loss": 0.4797, + "step": 1037 + }, + { + "epoch": 0.13832622601279318, + "grad_norm": 0.3368523553299434, + "learning_rate": 9.98254126936885e-06, + "loss": 0.4111, + "step": 1038 + }, + { + "epoch": 0.13845948827292112, + "grad_norm": 0.3135711273808432, + "learning_rate": 9.982481768888155e-06, + "loss": 0.3838, + "step": 1039 + }, + { + "epoch": 0.13859275053304904, + "grad_norm": 0.47952212588444976, + "learning_rate": 9.98242216736706e-06, + "loss": 0.3736, + "step": 1040 + }, + { + "epoch": 0.13872601279317698, + "grad_norm": 0.3265955374300904, + "learning_rate": 9.982362464806766e-06, + "loss": 0.4318, + "step": 1041 + }, + { + "epoch": 0.1388592750533049, + "grad_norm": 0.34181972959942086, + "learning_rate": 9.982302661208487e-06, + "loss": 0.3975, + "step": 1042 + }, + { + "epoch": 0.13899253731343283, + "grad_norm": 0.33762069977864, + "learning_rate": 9.98224275657344e-06, + "loss": 0.5188, + "step": 1043 + }, + { + "epoch": 0.13912579957356078, + "grad_norm": 0.34188803113975746, + "learning_rate": 9.982182750902834e-06, + "loss": 0.4524, + "step": 1044 + }, + { + "epoch": 0.1392590618336887, + "grad_norm": 0.29983367239622166, + "learning_rate": 9.982122644197886e-06, + "loss": 0.3584, + "step": 1045 + }, + { + "epoch": 0.13939232409381663, + "grad_norm": 0.35287778067158354, + "learning_rate": 9.982062436459821e-06, + "loss": 0.4657, + "step": 1046 + }, + { + "epoch": 0.13952558635394458, + "grad_norm": 0.3207709848186954, + "learning_rate": 9.982002127689853e-06, + "loss": 0.4324, + "step": 1047 + }, + { + "epoch": 0.1396588486140725, + "grad_norm": 0.31488209958332847, + "learning_rate": 9.981941717889207e-06, + "loss": 0.449, + "step": 1048 + }, + { + "epoch": 0.13979211087420043, + "grad_norm": 0.32336464050264346, + "learning_rate": 9.981881207059111e-06, + "loss": 0.3707, + "step": 1049 + }, + { + "epoch": 0.13992537313432835, + "grad_norm": 0.34364360611088557, + "learning_rate": 9.98182059520079e-06, + "loss": 0.4666, + "step": 1050 + }, + { + "epoch": 0.1400586353944563, + "grad_norm": 0.3530336603842863, + "learning_rate": 9.981759882315472e-06, + "loss": 0.4397, + "step": 1051 + }, + { + "epoch": 0.14019189765458423, + "grad_norm": 0.3448179584549568, + "learning_rate": 9.981699068404389e-06, + "loss": 0.4835, + "step": 1052 + }, + { + "epoch": 0.14032515991471214, + "grad_norm": 0.3168510230803005, + "learning_rate": 9.981638153468775e-06, + "loss": 0.4017, + "step": 1053 + }, + { + "epoch": 0.1404584221748401, + "grad_norm": 0.34267231349101673, + "learning_rate": 9.981577137509866e-06, + "loss": 0.4031, + "step": 1054 + }, + { + "epoch": 0.14059168443496803, + "grad_norm": 0.3283157852843872, + "learning_rate": 9.981516020528897e-06, + "loss": 0.4182, + "step": 1055 + }, + { + "epoch": 0.14072494669509594, + "grad_norm": 0.3243548226540603, + "learning_rate": 9.981454802527109e-06, + "loss": 0.4323, + "step": 1056 + }, + { + "epoch": 0.14085820895522388, + "grad_norm": 0.3252518126603156, + "learning_rate": 9.981393483505744e-06, + "loss": 0.4923, + "step": 1057 + }, + { + "epoch": 0.1409914712153518, + "grad_norm": 0.31711000386631105, + "learning_rate": 9.981332063466042e-06, + "loss": 0.4473, + "step": 1058 + }, + { + "epoch": 0.14112473347547974, + "grad_norm": 0.30238764732784484, + "learning_rate": 9.981270542409254e-06, + "loss": 0.3903, + "step": 1059 + }, + { + "epoch": 0.14125799573560768, + "grad_norm": 0.320062808812742, + "learning_rate": 9.981208920336622e-06, + "loss": 0.4856, + "step": 1060 + }, + { + "epoch": 0.1413912579957356, + "grad_norm": 0.33732131282944805, + "learning_rate": 9.9811471972494e-06, + "loss": 0.4232, + "step": 1061 + }, + { + "epoch": 0.14152452025586354, + "grad_norm": 0.31639805495218315, + "learning_rate": 9.981085373148837e-06, + "loss": 0.3855, + "step": 1062 + }, + { + "epoch": 0.14165778251599148, + "grad_norm": 0.33618559352590605, + "learning_rate": 9.98102344803619e-06, + "loss": 0.4978, + "step": 1063 + }, + { + "epoch": 0.1417910447761194, + "grad_norm": 0.34442003858891057, + "learning_rate": 9.98096142191271e-06, + "loss": 0.4738, + "step": 1064 + }, + { + "epoch": 0.14192430703624734, + "grad_norm": 0.32456012887392244, + "learning_rate": 9.98089929477966e-06, + "loss": 0.4403, + "step": 1065 + }, + { + "epoch": 0.14205756929637528, + "grad_norm": 0.3523835345407354, + "learning_rate": 9.980837066638295e-06, + "loss": 0.4236, + "step": 1066 + }, + { + "epoch": 0.1421908315565032, + "grad_norm": 0.32408229884283785, + "learning_rate": 9.98077473748988e-06, + "loss": 0.4339, + "step": 1067 + }, + { + "epoch": 0.14232409381663114, + "grad_norm": 0.32732611656278043, + "learning_rate": 9.980712307335678e-06, + "loss": 0.3911, + "step": 1068 + }, + { + "epoch": 0.14245735607675905, + "grad_norm": 0.3364819852820994, + "learning_rate": 9.980649776176955e-06, + "loss": 0.4484, + "step": 1069 + }, + { + "epoch": 0.142590618336887, + "grad_norm": 0.3276354593441979, + "learning_rate": 9.980587144014981e-06, + "loss": 0.4442, + "step": 1070 + }, + { + "epoch": 0.14272388059701493, + "grad_norm": 0.3494254371550637, + "learning_rate": 9.980524410851023e-06, + "loss": 0.3992, + "step": 1071 + }, + { + "epoch": 0.14285714285714285, + "grad_norm": 0.35638664145875426, + "learning_rate": 9.980461576686353e-06, + "loss": 0.4493, + "step": 1072 + }, + { + "epoch": 0.1429904051172708, + "grad_norm": 0.300912782481897, + "learning_rate": 9.980398641522249e-06, + "loss": 0.3997, + "step": 1073 + }, + { + "epoch": 0.14312366737739873, + "grad_norm": 0.36473954531126995, + "learning_rate": 9.980335605359986e-06, + "loss": 0.4975, + "step": 1074 + }, + { + "epoch": 0.14325692963752665, + "grad_norm": 0.3263955427921499, + "learning_rate": 9.98027246820084e-06, + "loss": 0.4665, + "step": 1075 + }, + { + "epoch": 0.1433901918976546, + "grad_norm": 0.33060926884673114, + "learning_rate": 9.980209230046093e-06, + "loss": 0.383, + "step": 1076 + }, + { + "epoch": 0.1435234541577825, + "grad_norm": 0.33213926541707534, + "learning_rate": 9.980145890897025e-06, + "loss": 0.403, + "step": 1077 + }, + { + "epoch": 0.14365671641791045, + "grad_norm": 0.3555543998525032, + "learning_rate": 9.980082450754926e-06, + "loss": 0.4336, + "step": 1078 + }, + { + "epoch": 0.1437899786780384, + "grad_norm": 0.3471425379866343, + "learning_rate": 9.98001890962108e-06, + "loss": 0.4697, + "step": 1079 + }, + { + "epoch": 0.1439232409381663, + "grad_norm": 0.349818627626319, + "learning_rate": 9.97995526749677e-06, + "loss": 0.3998, + "step": 1080 + }, + { + "epoch": 0.14405650319829424, + "grad_norm": 0.34794811755824673, + "learning_rate": 9.979891524383294e-06, + "loss": 0.4037, + "step": 1081 + }, + { + "epoch": 0.1441897654584222, + "grad_norm": 0.3380323698214574, + "learning_rate": 9.979827680281943e-06, + "loss": 0.4139, + "step": 1082 + }, + { + "epoch": 0.1443230277185501, + "grad_norm": 0.3440312654318739, + "learning_rate": 9.97976373519401e-06, + "loss": 0.4038, + "step": 1083 + }, + { + "epoch": 0.14445628997867804, + "grad_norm": 0.31531075262102115, + "learning_rate": 9.979699689120792e-06, + "loss": 0.4316, + "step": 1084 + }, + { + "epoch": 0.14458955223880596, + "grad_norm": 0.34162691391532857, + "learning_rate": 9.979635542063589e-06, + "loss": 0.4296, + "step": 1085 + }, + { + "epoch": 0.1447228144989339, + "grad_norm": 0.3395139986630476, + "learning_rate": 9.979571294023699e-06, + "loss": 0.3467, + "step": 1086 + }, + { + "epoch": 0.14485607675906184, + "grad_norm": 0.3461718776124448, + "learning_rate": 9.979506945002428e-06, + "loss": 0.4498, + "step": 1087 + }, + { + "epoch": 0.14498933901918976, + "grad_norm": 0.3360910732424609, + "learning_rate": 9.979442495001082e-06, + "loss": 0.3933, + "step": 1088 + }, + { + "epoch": 0.1451226012793177, + "grad_norm": 0.3481838015854296, + "learning_rate": 9.979377944020963e-06, + "loss": 0.4302, + "step": 1089 + }, + { + "epoch": 0.14525586353944564, + "grad_norm": 0.3607731639627209, + "learning_rate": 9.979313292063384e-06, + "loss": 0.4185, + "step": 1090 + }, + { + "epoch": 0.14538912579957355, + "grad_norm": 0.36709284624509003, + "learning_rate": 9.979248539129656e-06, + "loss": 0.469, + "step": 1091 + }, + { + "epoch": 0.1455223880597015, + "grad_norm": 0.40176777411912085, + "learning_rate": 9.97918368522109e-06, + "loss": 0.441, + "step": 1092 + }, + { + "epoch": 0.1456556503198294, + "grad_norm": 0.3486306485264874, + "learning_rate": 9.979118730339002e-06, + "loss": 0.524, + "step": 1093 + }, + { + "epoch": 0.14578891257995735, + "grad_norm": 0.3210219430067414, + "learning_rate": 9.979053674484711e-06, + "loss": 0.4181, + "step": 1094 + }, + { + "epoch": 0.1459221748400853, + "grad_norm": 0.33720210706660286, + "learning_rate": 9.978988517659533e-06, + "loss": 0.4529, + "step": 1095 + }, + { + "epoch": 0.1460554371002132, + "grad_norm": 0.34614997625503763, + "learning_rate": 9.978923259864795e-06, + "loss": 0.3956, + "step": 1096 + }, + { + "epoch": 0.14618869936034115, + "grad_norm": 0.33148026029264516, + "learning_rate": 9.978857901101812e-06, + "loss": 0.4151, + "step": 1097 + }, + { + "epoch": 0.1463219616204691, + "grad_norm": 0.33575431852286836, + "learning_rate": 9.978792441371916e-06, + "loss": 0.4273, + "step": 1098 + }, + { + "epoch": 0.146455223880597, + "grad_norm": 0.35552304700190074, + "learning_rate": 9.978726880676433e-06, + "loss": 0.4445, + "step": 1099 + }, + { + "epoch": 0.14658848614072495, + "grad_norm": 0.31246246738620437, + "learning_rate": 9.978661219016692e-06, + "loss": 0.375, + "step": 1100 + }, + { + "epoch": 0.1467217484008529, + "grad_norm": 0.3633856941888199, + "learning_rate": 9.978595456394023e-06, + "loss": 0.4126, + "step": 1101 + }, + { + "epoch": 0.1468550106609808, + "grad_norm": 0.3532735161797364, + "learning_rate": 9.978529592809763e-06, + "loss": 0.5223, + "step": 1102 + }, + { + "epoch": 0.14698827292110875, + "grad_norm": 0.3507208173365598, + "learning_rate": 9.978463628265245e-06, + "loss": 0.4667, + "step": 1103 + }, + { + "epoch": 0.14712153518123666, + "grad_norm": 0.36199858734997753, + "learning_rate": 9.978397562761806e-06, + "loss": 0.4202, + "step": 1104 + }, + { + "epoch": 0.1472547974413646, + "grad_norm": 0.3164660046998882, + "learning_rate": 9.978331396300789e-06, + "loss": 0.3929, + "step": 1105 + }, + { + "epoch": 0.14738805970149255, + "grad_norm": 0.3440287075049196, + "learning_rate": 9.978265128883534e-06, + "loss": 0.3687, + "step": 1106 + }, + { + "epoch": 0.14752132196162046, + "grad_norm": 0.32243120435223116, + "learning_rate": 9.978198760511384e-06, + "loss": 0.4299, + "step": 1107 + }, + { + "epoch": 0.1476545842217484, + "grad_norm": 0.3393982933868876, + "learning_rate": 9.978132291185686e-06, + "loss": 0.3947, + "step": 1108 + }, + { + "epoch": 0.14778784648187634, + "grad_norm": 0.34264851351817616, + "learning_rate": 9.978065720907788e-06, + "loss": 0.4598, + "step": 1109 + }, + { + "epoch": 0.14792110874200426, + "grad_norm": 0.30972907929330534, + "learning_rate": 9.977999049679039e-06, + "loss": 0.3329, + "step": 1110 + }, + { + "epoch": 0.1480543710021322, + "grad_norm": 0.33259238001019614, + "learning_rate": 9.977932277500793e-06, + "loss": 0.4619, + "step": 1111 + }, + { + "epoch": 0.14818763326226012, + "grad_norm": 0.32089139855363774, + "learning_rate": 9.977865404374402e-06, + "loss": 0.4175, + "step": 1112 + }, + { + "epoch": 0.14832089552238806, + "grad_norm": 0.3380944358127501, + "learning_rate": 9.977798430301224e-06, + "loss": 0.4081, + "step": 1113 + }, + { + "epoch": 0.148454157782516, + "grad_norm": 0.31487588345379486, + "learning_rate": 9.977731355282614e-06, + "loss": 0.4172, + "step": 1114 + }, + { + "epoch": 0.14858742004264391, + "grad_norm": 0.32985117444550094, + "learning_rate": 9.977664179319935e-06, + "loss": 0.4066, + "step": 1115 + }, + { + "epoch": 0.14872068230277186, + "grad_norm": 0.3399830794905965, + "learning_rate": 9.97759690241455e-06, + "loss": 0.4629, + "step": 1116 + }, + { + "epoch": 0.1488539445628998, + "grad_norm": 0.32383994784871056, + "learning_rate": 9.977529524567821e-06, + "loss": 0.4019, + "step": 1117 + }, + { + "epoch": 0.1489872068230277, + "grad_norm": 0.34908495076736007, + "learning_rate": 9.977462045781116e-06, + "loss": 0.4082, + "step": 1118 + }, + { + "epoch": 0.14912046908315565, + "grad_norm": 0.3159249781897787, + "learning_rate": 9.9773944660558e-06, + "loss": 0.4268, + "step": 1119 + }, + { + "epoch": 0.14925373134328357, + "grad_norm": 0.32110659815711035, + "learning_rate": 9.97732678539325e-06, + "loss": 0.3701, + "step": 1120 + }, + { + "epoch": 0.1493869936034115, + "grad_norm": 0.34748599879670833, + "learning_rate": 9.977259003794833e-06, + "loss": 0.4507, + "step": 1121 + }, + { + "epoch": 0.14952025586353945, + "grad_norm": 0.3768513119734622, + "learning_rate": 9.977191121261925e-06, + "loss": 0.4153, + "step": 1122 + }, + { + "epoch": 0.14965351812366737, + "grad_norm": 0.33097425773371825, + "learning_rate": 9.977123137795904e-06, + "loss": 0.4281, + "step": 1123 + }, + { + "epoch": 0.1497867803837953, + "grad_norm": 0.37074785121176435, + "learning_rate": 9.977055053398146e-06, + "loss": 0.5104, + "step": 1124 + }, + { + "epoch": 0.14992004264392325, + "grad_norm": 0.3473266008069972, + "learning_rate": 9.976986868070033e-06, + "loss": 0.4653, + "step": 1125 + }, + { + "epoch": 0.15005330490405117, + "grad_norm": 0.33142631768973685, + "learning_rate": 9.976918581812949e-06, + "loss": 0.3422, + "step": 1126 + }, + { + "epoch": 0.1501865671641791, + "grad_norm": 0.32161831178090544, + "learning_rate": 9.976850194628277e-06, + "loss": 0.4195, + "step": 1127 + }, + { + "epoch": 0.15031982942430705, + "grad_norm": 0.3246845605361341, + "learning_rate": 9.976781706517404e-06, + "loss": 0.43, + "step": 1128 + }, + { + "epoch": 0.15045309168443496, + "grad_norm": 0.3309812283605566, + "learning_rate": 9.97671311748172e-06, + "loss": 0.405, + "step": 1129 + }, + { + "epoch": 0.1505863539445629, + "grad_norm": 0.3357430369742648, + "learning_rate": 9.976644427522617e-06, + "loss": 0.4294, + "step": 1130 + }, + { + "epoch": 0.15071961620469082, + "grad_norm": 0.34736013850954134, + "learning_rate": 9.976575636641483e-06, + "loss": 0.4445, + "step": 1131 + }, + { + "epoch": 0.15085287846481876, + "grad_norm": 0.3647484138906116, + "learning_rate": 9.97650674483972e-06, + "loss": 0.4852, + "step": 1132 + }, + { + "epoch": 0.1509861407249467, + "grad_norm": 0.3402339326079305, + "learning_rate": 9.976437752118719e-06, + "loss": 0.4846, + "step": 1133 + }, + { + "epoch": 0.15111940298507462, + "grad_norm": 0.35213449373921396, + "learning_rate": 9.976368658479882e-06, + "loss": 0.4541, + "step": 1134 + }, + { + "epoch": 0.15125266524520256, + "grad_norm": 0.334794917724364, + "learning_rate": 9.97629946392461e-06, + "loss": 0.4241, + "step": 1135 + }, + { + "epoch": 0.1513859275053305, + "grad_norm": 0.34663175377731387, + "learning_rate": 9.976230168454304e-06, + "loss": 0.4266, + "step": 1136 + }, + { + "epoch": 0.15151918976545842, + "grad_norm": 0.32544757531644924, + "learning_rate": 9.976160772070374e-06, + "loss": 0.3629, + "step": 1137 + }, + { + "epoch": 0.15165245202558636, + "grad_norm": 0.34532916550960846, + "learning_rate": 9.976091274774222e-06, + "loss": 0.386, + "step": 1138 + }, + { + "epoch": 0.15178571428571427, + "grad_norm": 0.3211896177698924, + "learning_rate": 9.97602167656726e-06, + "loss": 0.4618, + "step": 1139 + }, + { + "epoch": 0.15191897654584222, + "grad_norm": 0.3745988271493931, + "learning_rate": 9.9759519774509e-06, + "loss": 0.4754, + "step": 1140 + }, + { + "epoch": 0.15205223880597016, + "grad_norm": 0.36566471008107704, + "learning_rate": 9.975882177426554e-06, + "loss": 0.4184, + "step": 1141 + }, + { + "epoch": 0.15218550106609807, + "grad_norm": 0.3532583623719, + "learning_rate": 9.97581227649564e-06, + "loss": 0.4385, + "step": 1142 + }, + { + "epoch": 0.15231876332622601, + "grad_norm": 0.3580059141302877, + "learning_rate": 9.975742274659573e-06, + "loss": 0.4538, + "step": 1143 + }, + { + "epoch": 0.15245202558635396, + "grad_norm": 0.3378262345946331, + "learning_rate": 9.975672171919772e-06, + "loss": 0.4716, + "step": 1144 + }, + { + "epoch": 0.15258528784648187, + "grad_norm": 0.334904537161075, + "learning_rate": 9.97560196827766e-06, + "loss": 0.3936, + "step": 1145 + }, + { + "epoch": 0.1527185501066098, + "grad_norm": 0.32665942545313986, + "learning_rate": 9.97553166373466e-06, + "loss": 0.4007, + "step": 1146 + }, + { + "epoch": 0.15285181236673773, + "grad_norm": 0.3502029182891027, + "learning_rate": 9.975461258292199e-06, + "loss": 0.3935, + "step": 1147 + }, + { + "epoch": 0.15298507462686567, + "grad_norm": 0.3586370845164562, + "learning_rate": 9.975390751951704e-06, + "loss": 0.3985, + "step": 1148 + }, + { + "epoch": 0.1531183368869936, + "grad_norm": 0.34218508236323536, + "learning_rate": 9.975320144714604e-06, + "loss": 0.4272, + "step": 1149 + }, + { + "epoch": 0.15325159914712153, + "grad_norm": 0.33727331076817396, + "learning_rate": 9.975249436582331e-06, + "loss": 0.3745, + "step": 1150 + }, + { + "epoch": 0.15338486140724947, + "grad_norm": 0.3411602766129516, + "learning_rate": 9.975178627556321e-06, + "loss": 0.4574, + "step": 1151 + }, + { + "epoch": 0.1535181236673774, + "grad_norm": 0.3318842647267342, + "learning_rate": 9.975107717638008e-06, + "loss": 0.4018, + "step": 1152 + }, + { + "epoch": 0.15365138592750532, + "grad_norm": 0.3076120001627611, + "learning_rate": 9.97503670682883e-06, + "loss": 0.4478, + "step": 1153 + }, + { + "epoch": 0.15378464818763327, + "grad_norm": 0.34440212523971797, + "learning_rate": 9.974965595130229e-06, + "loss": 0.3916, + "step": 1154 + }, + { + "epoch": 0.15391791044776118, + "grad_norm": 0.34147487267487425, + "learning_rate": 9.974894382543644e-06, + "loss": 0.4397, + "step": 1155 + }, + { + "epoch": 0.15405117270788912, + "grad_norm": 0.33972609704995715, + "learning_rate": 9.97482306907052e-06, + "loss": 0.5278, + "step": 1156 + }, + { + "epoch": 0.15418443496801706, + "grad_norm": 0.3360557349366825, + "learning_rate": 9.974751654712306e-06, + "loss": 0.4357, + "step": 1157 + }, + { + "epoch": 0.15431769722814498, + "grad_norm": 0.3364707743174597, + "learning_rate": 9.974680139470448e-06, + "loss": 0.4888, + "step": 1158 + }, + { + "epoch": 0.15445095948827292, + "grad_norm": 0.3374149258716878, + "learning_rate": 9.974608523346394e-06, + "loss": 0.3943, + "step": 1159 + }, + { + "epoch": 0.15458422174840086, + "grad_norm": 0.3382293741276622, + "learning_rate": 9.974536806341602e-06, + "loss": 0.392, + "step": 1160 + }, + { + "epoch": 0.15471748400852878, + "grad_norm": 0.3573832423878092, + "learning_rate": 9.97446498845752e-06, + "loss": 0.4578, + "step": 1161 + }, + { + "epoch": 0.15485074626865672, + "grad_norm": 0.32407429722496656, + "learning_rate": 9.974393069695609e-06, + "loss": 0.4093, + "step": 1162 + }, + { + "epoch": 0.15498400852878466, + "grad_norm": 0.3284755398617121, + "learning_rate": 9.974321050057326e-06, + "loss": 0.3889, + "step": 1163 + }, + { + "epoch": 0.15511727078891258, + "grad_norm": 0.3155485420208432, + "learning_rate": 9.97424892954413e-06, + "loss": 0.4316, + "step": 1164 + }, + { + "epoch": 0.15525053304904052, + "grad_norm": 0.3661710266173392, + "learning_rate": 9.974176708157485e-06, + "loss": 0.5158, + "step": 1165 + }, + { + "epoch": 0.15538379530916843, + "grad_norm": 0.33202542257947193, + "learning_rate": 9.974104385898857e-06, + "loss": 0.4692, + "step": 1166 + }, + { + "epoch": 0.15551705756929637, + "grad_norm": 0.31683419774931226, + "learning_rate": 9.974031962769711e-06, + "loss": 0.4324, + "step": 1167 + }, + { + "epoch": 0.15565031982942432, + "grad_norm": 0.32439342283682787, + "learning_rate": 9.973959438771514e-06, + "loss": 0.391, + "step": 1168 + }, + { + "epoch": 0.15578358208955223, + "grad_norm": 0.3338153570330927, + "learning_rate": 9.97388681390574e-06, + "loss": 0.4277, + "step": 1169 + }, + { + "epoch": 0.15591684434968017, + "grad_norm": 0.3314744220482114, + "learning_rate": 9.97381408817386e-06, + "loss": 0.4356, + "step": 1170 + }, + { + "epoch": 0.15605010660980811, + "grad_norm": 0.35861400574384855, + "learning_rate": 9.97374126157735e-06, + "loss": 0.4614, + "step": 1171 + }, + { + "epoch": 0.15618336886993603, + "grad_norm": 0.309744901729087, + "learning_rate": 9.973668334117684e-06, + "loss": 0.3827, + "step": 1172 + }, + { + "epoch": 0.15631663113006397, + "grad_norm": 0.3296498053651292, + "learning_rate": 9.973595305796345e-06, + "loss": 0.4511, + "step": 1173 + }, + { + "epoch": 0.15644989339019189, + "grad_norm": 0.33063555667309685, + "learning_rate": 9.97352217661481e-06, + "loss": 0.4454, + "step": 1174 + }, + { + "epoch": 0.15658315565031983, + "grad_norm": 0.3254010539806137, + "learning_rate": 9.973448946574565e-06, + "loss": 0.4669, + "step": 1175 + }, + { + "epoch": 0.15671641791044777, + "grad_norm": 0.3133341756204822, + "learning_rate": 9.973375615677094e-06, + "loss": 0.4071, + "step": 1176 + }, + { + "epoch": 0.15684968017057568, + "grad_norm": 0.3151653296474969, + "learning_rate": 9.973302183923882e-06, + "loss": 0.4195, + "step": 1177 + }, + { + "epoch": 0.15698294243070363, + "grad_norm": 0.32378571893837826, + "learning_rate": 9.973228651316423e-06, + "loss": 0.4675, + "step": 1178 + }, + { + "epoch": 0.15711620469083157, + "grad_norm": 0.30603300861733784, + "learning_rate": 9.973155017856205e-06, + "loss": 0.3695, + "step": 1179 + }, + { + "epoch": 0.15724946695095948, + "grad_norm": 0.31743339869051274, + "learning_rate": 9.973081283544719e-06, + "loss": 0.4311, + "step": 1180 + }, + { + "epoch": 0.15738272921108742, + "grad_norm": 0.32131722982438293, + "learning_rate": 9.973007448383465e-06, + "loss": 0.4132, + "step": 1181 + }, + { + "epoch": 0.15751599147121534, + "grad_norm": 0.3277989772840338, + "learning_rate": 9.972933512373937e-06, + "loss": 0.409, + "step": 1182 + }, + { + "epoch": 0.15764925373134328, + "grad_norm": 0.3246228377474986, + "learning_rate": 9.972859475517636e-06, + "loss": 0.4623, + "step": 1183 + }, + { + "epoch": 0.15778251599147122, + "grad_norm": 0.3267008023975133, + "learning_rate": 9.972785337816063e-06, + "loss": 0.3998, + "step": 1184 + }, + { + "epoch": 0.15791577825159914, + "grad_norm": 0.3112307275584038, + "learning_rate": 9.97271109927072e-06, + "loss": 0.4082, + "step": 1185 + }, + { + "epoch": 0.15804904051172708, + "grad_norm": 0.32909463056873656, + "learning_rate": 9.972636759883115e-06, + "loss": 0.4357, + "step": 1186 + }, + { + "epoch": 0.15818230277185502, + "grad_norm": 0.3000746546530869, + "learning_rate": 9.972562319654753e-06, + "loss": 0.3896, + "step": 1187 + }, + { + "epoch": 0.15831556503198294, + "grad_norm": 0.3298025045503388, + "learning_rate": 9.972487778587145e-06, + "loss": 0.4637, + "step": 1188 + }, + { + "epoch": 0.15844882729211088, + "grad_norm": 0.3156662725109061, + "learning_rate": 9.972413136681804e-06, + "loss": 0.4032, + "step": 1189 + }, + { + "epoch": 0.15858208955223882, + "grad_norm": 0.3196266911763566, + "learning_rate": 9.972338393940241e-06, + "loss": 0.4263, + "step": 1190 + }, + { + "epoch": 0.15871535181236673, + "grad_norm": 0.30790650976656214, + "learning_rate": 9.972263550363974e-06, + "loss": 0.4043, + "step": 1191 + }, + { + "epoch": 0.15884861407249468, + "grad_norm": 0.3537224745991133, + "learning_rate": 9.972188605954519e-06, + "loss": 0.4826, + "step": 1192 + }, + { + "epoch": 0.1589818763326226, + "grad_norm": 0.33287305045530563, + "learning_rate": 9.972113560713396e-06, + "loss": 0.4615, + "step": 1193 + }, + { + "epoch": 0.15911513859275053, + "grad_norm": 0.3418186412542211, + "learning_rate": 9.972038414642129e-06, + "loss": 0.474, + "step": 1194 + }, + { + "epoch": 0.15924840085287847, + "grad_norm": 0.3168049365608417, + "learning_rate": 9.971963167742238e-06, + "loss": 0.4275, + "step": 1195 + }, + { + "epoch": 0.1593816631130064, + "grad_norm": 0.31387387327293254, + "learning_rate": 9.971887820015254e-06, + "loss": 0.5058, + "step": 1196 + }, + { + "epoch": 0.15951492537313433, + "grad_norm": 0.34510600762417615, + "learning_rate": 9.9718123714627e-06, + "loss": 0.4843, + "step": 1197 + }, + { + "epoch": 0.15964818763326227, + "grad_norm": 0.32522175691820604, + "learning_rate": 9.971736822086109e-06, + "loss": 0.46, + "step": 1198 + }, + { + "epoch": 0.1597814498933902, + "grad_norm": 0.34678502639595205, + "learning_rate": 9.971661171887012e-06, + "loss": 0.4697, + "step": 1199 + }, + { + "epoch": 0.15991471215351813, + "grad_norm": 0.345738840517907, + "learning_rate": 9.971585420866943e-06, + "loss": 0.4766, + "step": 1200 + }, + { + "epoch": 0.16004797441364604, + "grad_norm": 0.31481237043094434, + "learning_rate": 9.97150956902744e-06, + "loss": 0.4183, + "step": 1201 + }, + { + "epoch": 0.16018123667377399, + "grad_norm": 0.32217840019677324, + "learning_rate": 9.971433616370037e-06, + "loss": 0.4564, + "step": 1202 + }, + { + "epoch": 0.16031449893390193, + "grad_norm": 0.32946699181164424, + "learning_rate": 9.97135756289628e-06, + "loss": 0.4404, + "step": 1203 + }, + { + "epoch": 0.16044776119402984, + "grad_norm": 0.3224401401697111, + "learning_rate": 9.971281408607706e-06, + "loss": 0.4683, + "step": 1204 + }, + { + "epoch": 0.16058102345415778, + "grad_norm": 0.3112315158541572, + "learning_rate": 9.971205153505862e-06, + "loss": 0.4281, + "step": 1205 + }, + { + "epoch": 0.16071428571428573, + "grad_norm": 0.3415298622719317, + "learning_rate": 9.971128797592295e-06, + "loss": 0.4096, + "step": 1206 + }, + { + "epoch": 0.16084754797441364, + "grad_norm": 0.3182063764483251, + "learning_rate": 9.971052340868554e-06, + "loss": 0.4389, + "step": 1207 + }, + { + "epoch": 0.16098081023454158, + "grad_norm": 0.3241995186030198, + "learning_rate": 9.970975783336185e-06, + "loss": 0.4301, + "step": 1208 + }, + { + "epoch": 0.1611140724946695, + "grad_norm": 0.30109381050055084, + "learning_rate": 9.970899124996744e-06, + "loss": 0.4262, + "step": 1209 + }, + { + "epoch": 0.16124733475479744, + "grad_norm": 0.3286316261423427, + "learning_rate": 9.970822365851787e-06, + "loss": 0.4733, + "step": 1210 + }, + { + "epoch": 0.16138059701492538, + "grad_norm": 0.31266302893752396, + "learning_rate": 9.970745505902868e-06, + "loss": 0.4299, + "step": 1211 + }, + { + "epoch": 0.1615138592750533, + "grad_norm": 0.32277990904939863, + "learning_rate": 9.970668545151545e-06, + "loss": 0.3814, + "step": 1212 + }, + { + "epoch": 0.16164712153518124, + "grad_norm": 0.319818176468178, + "learning_rate": 9.970591483599381e-06, + "loss": 0.4746, + "step": 1213 + }, + { + "epoch": 0.16178038379530918, + "grad_norm": 0.33987617088833183, + "learning_rate": 9.970514321247937e-06, + "loss": 0.4454, + "step": 1214 + }, + { + "epoch": 0.1619136460554371, + "grad_norm": 0.3029550080065097, + "learning_rate": 9.970437058098779e-06, + "loss": 0.3804, + "step": 1215 + }, + { + "epoch": 0.16204690831556504, + "grad_norm": 0.35103823914409843, + "learning_rate": 9.970359694153473e-06, + "loss": 0.4055, + "step": 1216 + }, + { + "epoch": 0.16218017057569295, + "grad_norm": 0.3252627681068782, + "learning_rate": 9.970282229413589e-06, + "loss": 0.4213, + "step": 1217 + }, + { + "epoch": 0.1623134328358209, + "grad_norm": 0.3291608600328401, + "learning_rate": 9.970204663880698e-06, + "loss": 0.4056, + "step": 1218 + }, + { + "epoch": 0.16244669509594883, + "grad_norm": 0.28686183175524443, + "learning_rate": 9.97012699755637e-06, + "loss": 0.3688, + "step": 1219 + }, + { + "epoch": 0.16257995735607675, + "grad_norm": 0.3007927921124504, + "learning_rate": 9.970049230442183e-06, + "loss": 0.3617, + "step": 1220 + }, + { + "epoch": 0.1627132196162047, + "grad_norm": 0.3423803993523537, + "learning_rate": 9.969971362539714e-06, + "loss": 0.4352, + "step": 1221 + }, + { + "epoch": 0.16284648187633263, + "grad_norm": 0.30213170629927205, + "learning_rate": 9.969893393850539e-06, + "loss": 0.3628, + "step": 1222 + }, + { + "epoch": 0.16297974413646055, + "grad_norm": 0.3160789652404436, + "learning_rate": 9.969815324376243e-06, + "loss": 0.4177, + "step": 1223 + }, + { + "epoch": 0.1631130063965885, + "grad_norm": 0.33007119378179695, + "learning_rate": 9.969737154118407e-06, + "loss": 0.4357, + "step": 1224 + }, + { + "epoch": 0.16324626865671643, + "grad_norm": 0.32316855961754315, + "learning_rate": 9.969658883078618e-06, + "loss": 0.3927, + "step": 1225 + }, + { + "epoch": 0.16337953091684435, + "grad_norm": 0.3201070039997634, + "learning_rate": 9.96958051125846e-06, + "loss": 0.3682, + "step": 1226 + }, + { + "epoch": 0.1635127931769723, + "grad_norm": 0.32737046808824066, + "learning_rate": 9.969502038659526e-06, + "loss": 0.3925, + "step": 1227 + }, + { + "epoch": 0.1636460554371002, + "grad_norm": 0.3211830235113921, + "learning_rate": 9.969423465283405e-06, + "loss": 0.3818, + "step": 1228 + }, + { + "epoch": 0.16377931769722814, + "grad_norm": 0.33111949819328224, + "learning_rate": 9.969344791131692e-06, + "loss": 0.4217, + "step": 1229 + }, + { + "epoch": 0.16391257995735609, + "grad_norm": 0.31076110335849527, + "learning_rate": 9.969266016205981e-06, + "loss": 0.5269, + "step": 1230 + }, + { + "epoch": 0.164045842217484, + "grad_norm": 0.3496675261433929, + "learning_rate": 9.96918714050787e-06, + "loss": 0.4325, + "step": 1231 + }, + { + "epoch": 0.16417910447761194, + "grad_norm": 0.29606672186127403, + "learning_rate": 9.969108164038958e-06, + "loss": 0.356, + "step": 1232 + }, + { + "epoch": 0.16431236673773988, + "grad_norm": 0.3252031348863038, + "learning_rate": 9.96902908680085e-06, + "loss": 0.3915, + "step": 1233 + }, + { + "epoch": 0.1644456289978678, + "grad_norm": 0.3034779747271308, + "learning_rate": 9.968949908795145e-06, + "loss": 0.4013, + "step": 1234 + }, + { + "epoch": 0.16457889125799574, + "grad_norm": 0.3076811947191026, + "learning_rate": 9.96887063002345e-06, + "loss": 0.3985, + "step": 1235 + }, + { + "epoch": 0.16471215351812366, + "grad_norm": 0.31415165506151727, + "learning_rate": 9.968791250487372e-06, + "loss": 0.365, + "step": 1236 + }, + { + "epoch": 0.1648454157782516, + "grad_norm": 0.3168442539845445, + "learning_rate": 9.968711770188524e-06, + "loss": 0.4445, + "step": 1237 + }, + { + "epoch": 0.16497867803837954, + "grad_norm": 0.3174099769810381, + "learning_rate": 9.968632189128516e-06, + "loss": 0.4871, + "step": 1238 + }, + { + "epoch": 0.16511194029850745, + "grad_norm": 0.3275626135266604, + "learning_rate": 9.968552507308959e-06, + "loss": 0.4232, + "step": 1239 + }, + { + "epoch": 0.1652452025586354, + "grad_norm": 0.3213093478887646, + "learning_rate": 9.968472724731472e-06, + "loss": 0.5478, + "step": 1240 + }, + { + "epoch": 0.16537846481876334, + "grad_norm": 0.3413316514583113, + "learning_rate": 9.968392841397673e-06, + "loss": 0.4155, + "step": 1241 + }, + { + "epoch": 0.16551172707889125, + "grad_norm": 0.3177200196325331, + "learning_rate": 9.968312857309183e-06, + "loss": 0.4244, + "step": 1242 + }, + { + "epoch": 0.1656449893390192, + "grad_norm": 0.3297483099623255, + "learning_rate": 9.96823277246762e-06, + "loss": 0.4219, + "step": 1243 + }, + { + "epoch": 0.1657782515991471, + "grad_norm": 0.358475446296621, + "learning_rate": 9.968152586874612e-06, + "loss": 0.4436, + "step": 1244 + }, + { + "epoch": 0.16591151385927505, + "grad_norm": 0.32559475362594215, + "learning_rate": 9.968072300531783e-06, + "loss": 0.5448, + "step": 1245 + }, + { + "epoch": 0.166044776119403, + "grad_norm": 0.34569373746043314, + "learning_rate": 9.967991913440761e-06, + "loss": 0.4233, + "step": 1246 + }, + { + "epoch": 0.1661780383795309, + "grad_norm": 0.31364644198973424, + "learning_rate": 9.967911425603177e-06, + "loss": 0.4214, + "step": 1247 + }, + { + "epoch": 0.16631130063965885, + "grad_norm": 0.33205629694055805, + "learning_rate": 9.967830837020662e-06, + "loss": 0.4941, + "step": 1248 + }, + { + "epoch": 0.1664445628997868, + "grad_norm": 0.31999383027658934, + "learning_rate": 9.967750147694853e-06, + "loss": 0.4275, + "step": 1249 + }, + { + "epoch": 0.1665778251599147, + "grad_norm": 0.3146910886132376, + "learning_rate": 9.967669357627385e-06, + "loss": 0.4222, + "step": 1250 + }, + { + "epoch": 0.16671108742004265, + "grad_norm": 0.331477767371042, + "learning_rate": 9.967588466819893e-06, + "loss": 0.3786, + "step": 1251 + }, + { + "epoch": 0.1668443496801706, + "grad_norm": 0.3113242524219961, + "learning_rate": 9.967507475274024e-06, + "loss": 0.3512, + "step": 1252 + }, + { + "epoch": 0.1669776119402985, + "grad_norm": 0.31779463352731574, + "learning_rate": 9.967426382991414e-06, + "loss": 0.4131, + "step": 1253 + }, + { + "epoch": 0.16711087420042645, + "grad_norm": 0.32881060609453133, + "learning_rate": 9.96734518997371e-06, + "loss": 0.4477, + "step": 1254 + }, + { + "epoch": 0.16724413646055436, + "grad_norm": 0.32805866794185473, + "learning_rate": 9.96726389622256e-06, + "loss": 0.431, + "step": 1255 + }, + { + "epoch": 0.1673773987206823, + "grad_norm": 1.6278116925620123, + "learning_rate": 9.967182501739611e-06, + "loss": 0.414, + "step": 1256 + }, + { + "epoch": 0.16751066098081024, + "grad_norm": 0.3601564849697182, + "learning_rate": 9.967101006526515e-06, + "loss": 0.4455, + "step": 1257 + }, + { + "epoch": 0.16764392324093816, + "grad_norm": 0.5728272510846124, + "learning_rate": 9.967019410584923e-06, + "loss": 0.44, + "step": 1258 + }, + { + "epoch": 0.1677771855010661, + "grad_norm": 0.3471160339485748, + "learning_rate": 9.966937713916489e-06, + "loss": 0.4178, + "step": 1259 + }, + { + "epoch": 0.16791044776119404, + "grad_norm": 0.3193434138624409, + "learning_rate": 9.966855916522873e-06, + "loss": 0.3717, + "step": 1260 + }, + { + "epoch": 0.16804371002132196, + "grad_norm": 0.41517111928684575, + "learning_rate": 9.966774018405731e-06, + "loss": 0.3825, + "step": 1261 + }, + { + "epoch": 0.1681769722814499, + "grad_norm": 0.3811745327391326, + "learning_rate": 9.966692019566724e-06, + "loss": 0.4524, + "step": 1262 + }, + { + "epoch": 0.1683102345415778, + "grad_norm": 0.35455586519026006, + "learning_rate": 9.966609920007516e-06, + "loss": 0.4105, + "step": 1263 + }, + { + "epoch": 0.16844349680170576, + "grad_norm": 0.3491617378328539, + "learning_rate": 9.966527719729771e-06, + "loss": 0.3991, + "step": 1264 + }, + { + "epoch": 0.1685767590618337, + "grad_norm": 0.36550127065204646, + "learning_rate": 9.966445418735155e-06, + "loss": 0.4752, + "step": 1265 + }, + { + "epoch": 0.1687100213219616, + "grad_norm": 0.3200011479535133, + "learning_rate": 9.96636301702534e-06, + "loss": 0.4014, + "step": 1266 + }, + { + "epoch": 0.16884328358208955, + "grad_norm": 0.3271068332002133, + "learning_rate": 9.966280514601997e-06, + "loss": 0.4437, + "step": 1267 + }, + { + "epoch": 0.1689765458422175, + "grad_norm": 0.33127175974782425, + "learning_rate": 9.966197911466796e-06, + "loss": 0.4936, + "step": 1268 + }, + { + "epoch": 0.1691098081023454, + "grad_norm": 0.3266232766998047, + "learning_rate": 9.966115207621413e-06, + "loss": 0.4003, + "step": 1269 + }, + { + "epoch": 0.16924307036247335, + "grad_norm": 0.32594026815750854, + "learning_rate": 9.966032403067526e-06, + "loss": 0.4172, + "step": 1270 + }, + { + "epoch": 0.16937633262260127, + "grad_norm": 0.35106753519481104, + "learning_rate": 9.965949497806814e-06, + "loss": 0.4401, + "step": 1271 + }, + { + "epoch": 0.1695095948827292, + "grad_norm": 0.3254522791972898, + "learning_rate": 9.965866491840959e-06, + "loss": 0.4598, + "step": 1272 + }, + { + "epoch": 0.16964285714285715, + "grad_norm": 0.3251827649827743, + "learning_rate": 9.965783385171642e-06, + "loss": 0.4842, + "step": 1273 + }, + { + "epoch": 0.16977611940298507, + "grad_norm": 0.3179943017615617, + "learning_rate": 9.96570017780055e-06, + "loss": 0.4291, + "step": 1274 + }, + { + "epoch": 0.169909381663113, + "grad_norm": 0.33622912584948556, + "learning_rate": 9.965616869729372e-06, + "loss": 0.4911, + "step": 1275 + }, + { + "epoch": 0.17004264392324095, + "grad_norm": 0.32969053626034384, + "learning_rate": 9.965533460959794e-06, + "loss": 0.4901, + "step": 1276 + }, + { + "epoch": 0.17017590618336886, + "grad_norm": 0.3253909545764446, + "learning_rate": 9.96544995149351e-06, + "loss": 0.5483, + "step": 1277 + }, + { + "epoch": 0.1703091684434968, + "grad_norm": 0.32258000502076384, + "learning_rate": 9.96536634133221e-06, + "loss": 0.3973, + "step": 1278 + }, + { + "epoch": 0.17044243070362472, + "grad_norm": 0.3066307970864146, + "learning_rate": 9.965282630477595e-06, + "loss": 0.4445, + "step": 1279 + }, + { + "epoch": 0.17057569296375266, + "grad_norm": 0.3267951312294542, + "learning_rate": 9.965198818931359e-06, + "loss": 0.4505, + "step": 1280 + }, + { + "epoch": 0.1707089552238806, + "grad_norm": 0.34746175808509017, + "learning_rate": 9.9651149066952e-06, + "loss": 0.4277, + "step": 1281 + }, + { + "epoch": 0.17084221748400852, + "grad_norm": 0.3188163526191367, + "learning_rate": 9.965030893770825e-06, + "loss": 0.3908, + "step": 1282 + }, + { + "epoch": 0.17097547974413646, + "grad_norm": 0.30444302963786396, + "learning_rate": 9.964946780159934e-06, + "loss": 0.3801, + "step": 1283 + }, + { + "epoch": 0.1711087420042644, + "grad_norm": 0.3287543132167289, + "learning_rate": 9.964862565864233e-06, + "loss": 0.385, + "step": 1284 + }, + { + "epoch": 0.17124200426439232, + "grad_norm": 0.30974304844187545, + "learning_rate": 9.96477825088543e-06, + "loss": 0.4413, + "step": 1285 + }, + { + "epoch": 0.17137526652452026, + "grad_norm": 0.3343309291495915, + "learning_rate": 9.964693835225236e-06, + "loss": 0.4694, + "step": 1286 + }, + { + "epoch": 0.1715085287846482, + "grad_norm": 0.32813753122979195, + "learning_rate": 9.96460931888536e-06, + "loss": 0.4311, + "step": 1287 + }, + { + "epoch": 0.17164179104477612, + "grad_norm": 0.3114885386946285, + "learning_rate": 9.964524701867519e-06, + "loss": 0.4313, + "step": 1288 + }, + { + "epoch": 0.17177505330490406, + "grad_norm": 0.3252701726996235, + "learning_rate": 9.964439984173428e-06, + "loss": 0.4958, + "step": 1289 + }, + { + "epoch": 0.17190831556503197, + "grad_norm": 0.3187245467226345, + "learning_rate": 9.964355165804805e-06, + "loss": 0.3964, + "step": 1290 + }, + { + "epoch": 0.1720415778251599, + "grad_norm": 0.31209694949740485, + "learning_rate": 9.96427024676337e-06, + "loss": 0.3744, + "step": 1291 + }, + { + "epoch": 0.17217484008528786, + "grad_norm": 0.32264953910931293, + "learning_rate": 9.964185227050845e-06, + "loss": 0.4184, + "step": 1292 + }, + { + "epoch": 0.17230810234541577, + "grad_norm": 0.3335532574390132, + "learning_rate": 9.964100106668953e-06, + "loss": 0.4708, + "step": 1293 + }, + { + "epoch": 0.1724413646055437, + "grad_norm": 0.31268369207121216, + "learning_rate": 9.964014885619421e-06, + "loss": 0.3486, + "step": 1294 + }, + { + "epoch": 0.17257462686567165, + "grad_norm": 0.3283773526677269, + "learning_rate": 9.963929563903977e-06, + "loss": 0.4279, + "step": 1295 + }, + { + "epoch": 0.17270788912579957, + "grad_norm": 0.32653945993182315, + "learning_rate": 9.963844141524355e-06, + "loss": 0.396, + "step": 1296 + }, + { + "epoch": 0.1728411513859275, + "grad_norm": 0.3363710161892561, + "learning_rate": 9.963758618482282e-06, + "loss": 0.3943, + "step": 1297 + }, + { + "epoch": 0.17297441364605542, + "grad_norm": 0.3223325370466159, + "learning_rate": 9.963672994779494e-06, + "loss": 0.4141, + "step": 1298 + }, + { + "epoch": 0.17310767590618337, + "grad_norm": 0.3687431402879558, + "learning_rate": 9.963587270417727e-06, + "loss": 0.4208, + "step": 1299 + }, + { + "epoch": 0.1732409381663113, + "grad_norm": 0.31322825097434964, + "learning_rate": 9.963501445398723e-06, + "loss": 0.4105, + "step": 1300 + }, + { + "epoch": 0.17337420042643922, + "grad_norm": 0.39232606064711023, + "learning_rate": 9.963415519724215e-06, + "loss": 0.4727, + "step": 1301 + }, + { + "epoch": 0.17350746268656717, + "grad_norm": 0.3148193873973449, + "learning_rate": 9.963329493395954e-06, + "loss": 0.479, + "step": 1302 + }, + { + "epoch": 0.1736407249466951, + "grad_norm": 0.37517584854675473, + "learning_rate": 9.96324336641568e-06, + "loss": 0.3866, + "step": 1303 + }, + { + "epoch": 0.17377398720682302, + "grad_norm": 0.32751343273610717, + "learning_rate": 9.963157138785138e-06, + "loss": 0.4125, + "step": 1304 + }, + { + "epoch": 0.17390724946695096, + "grad_norm": 0.34827491173756003, + "learning_rate": 9.963070810506082e-06, + "loss": 0.4586, + "step": 1305 + }, + { + "epoch": 0.17404051172707888, + "grad_norm": 0.30885934962138467, + "learning_rate": 9.962984381580256e-06, + "loss": 0.419, + "step": 1306 + }, + { + "epoch": 0.17417377398720682, + "grad_norm": 0.36086810432653244, + "learning_rate": 9.96289785200942e-06, + "loss": 0.457, + "step": 1307 + }, + { + "epoch": 0.17430703624733476, + "grad_norm": 0.3072475195703819, + "learning_rate": 9.96281122179532e-06, + "loss": 0.4039, + "step": 1308 + }, + { + "epoch": 0.17444029850746268, + "grad_norm": 0.3279729887555252, + "learning_rate": 9.962724490939721e-06, + "loss": 0.4157, + "step": 1309 + }, + { + "epoch": 0.17457356076759062, + "grad_norm": 0.31326850229842185, + "learning_rate": 9.962637659444379e-06, + "loss": 0.4536, + "step": 1310 + }, + { + "epoch": 0.17470682302771856, + "grad_norm": 0.32240048077817623, + "learning_rate": 9.962550727311054e-06, + "loss": 0.4343, + "step": 1311 + }, + { + "epoch": 0.17484008528784648, + "grad_norm": 0.3254947285889671, + "learning_rate": 9.962463694541506e-06, + "loss": 0.5014, + "step": 1312 + }, + { + "epoch": 0.17497334754797442, + "grad_norm": 0.31703001694345617, + "learning_rate": 9.962376561137507e-06, + "loss": 0.4273, + "step": 1313 + }, + { + "epoch": 0.17510660980810236, + "grad_norm": 0.390297901350946, + "learning_rate": 9.96228932710082e-06, + "loss": 0.4067, + "step": 1314 + }, + { + "epoch": 0.17523987206823027, + "grad_norm": 0.3062035803705733, + "learning_rate": 9.962201992433212e-06, + "loss": 0.4582, + "step": 1315 + }, + { + "epoch": 0.17537313432835822, + "grad_norm": 0.33053602298887264, + "learning_rate": 9.962114557136459e-06, + "loss": 0.4801, + "step": 1316 + }, + { + "epoch": 0.17550639658848613, + "grad_norm": 0.3133677182599101, + "learning_rate": 9.96202702121233e-06, + "loss": 0.4206, + "step": 1317 + }, + { + "epoch": 0.17563965884861407, + "grad_norm": 0.343521065447302, + "learning_rate": 9.961939384662602e-06, + "loss": 0.4278, + "step": 1318 + }, + { + "epoch": 0.17577292110874201, + "grad_norm": 0.31351917923562583, + "learning_rate": 9.961851647489052e-06, + "loss": 0.4462, + "step": 1319 + }, + { + "epoch": 0.17590618336886993, + "grad_norm": 0.3191667846329664, + "learning_rate": 9.961763809693457e-06, + "loss": 0.4802, + "step": 1320 + }, + { + "epoch": 0.17603944562899787, + "grad_norm": 0.3405679001860054, + "learning_rate": 9.961675871277603e-06, + "loss": 0.5149, + "step": 1321 + }, + { + "epoch": 0.1761727078891258, + "grad_norm": 0.35981760295610726, + "learning_rate": 9.961587832243268e-06, + "loss": 0.4105, + "step": 1322 + }, + { + "epoch": 0.17630597014925373, + "grad_norm": 0.33633393211682333, + "learning_rate": 9.961499692592242e-06, + "loss": 0.5392, + "step": 1323 + }, + { + "epoch": 0.17643923240938167, + "grad_norm": 0.33774747338276356, + "learning_rate": 9.96141145232631e-06, + "loss": 0.3918, + "step": 1324 + }, + { + "epoch": 0.17657249466950958, + "grad_norm": 0.3265727402071609, + "learning_rate": 9.961323111447263e-06, + "loss": 0.3539, + "step": 1325 + }, + { + "epoch": 0.17670575692963753, + "grad_norm": 0.34881598327197283, + "learning_rate": 9.96123466995689e-06, + "loss": 0.4157, + "step": 1326 + }, + { + "epoch": 0.17683901918976547, + "grad_norm": 0.3323870556975694, + "learning_rate": 9.961146127856985e-06, + "loss": 0.4503, + "step": 1327 + }, + { + "epoch": 0.17697228144989338, + "grad_norm": 0.31869560381042955, + "learning_rate": 9.961057485149346e-06, + "loss": 0.4142, + "step": 1328 + }, + { + "epoch": 0.17710554371002132, + "grad_norm": 0.32506797756662936, + "learning_rate": 9.960968741835767e-06, + "loss": 0.3916, + "step": 1329 + }, + { + "epoch": 0.17723880597014927, + "grad_norm": 0.3184610816752561, + "learning_rate": 9.96087989791805e-06, + "loss": 0.4195, + "step": 1330 + }, + { + "epoch": 0.17737206823027718, + "grad_norm": 0.3517253651611303, + "learning_rate": 9.960790953397999e-06, + "loss": 0.5026, + "step": 1331 + }, + { + "epoch": 0.17750533049040512, + "grad_norm": 0.31905416458927505, + "learning_rate": 9.960701908277413e-06, + "loss": 0.4455, + "step": 1332 + }, + { + "epoch": 0.17763859275053304, + "grad_norm": 0.3373037398977715, + "learning_rate": 9.9606127625581e-06, + "loss": 0.4017, + "step": 1333 + }, + { + "epoch": 0.17777185501066098, + "grad_norm": 0.3207733353432573, + "learning_rate": 9.960523516241867e-06, + "loss": 0.4542, + "step": 1334 + }, + { + "epoch": 0.17790511727078892, + "grad_norm": 0.3382449121771698, + "learning_rate": 9.960434169330524e-06, + "loss": 0.3934, + "step": 1335 + }, + { + "epoch": 0.17803837953091683, + "grad_norm": 0.34582842961539473, + "learning_rate": 9.960344721825883e-06, + "loss": 0.4821, + "step": 1336 + }, + { + "epoch": 0.17817164179104478, + "grad_norm": 0.3286627277086681, + "learning_rate": 9.96025517372976e-06, + "loss": 0.4189, + "step": 1337 + }, + { + "epoch": 0.17830490405117272, + "grad_norm": 0.33528498130209733, + "learning_rate": 9.960165525043968e-06, + "loss": 0.3477, + "step": 1338 + }, + { + "epoch": 0.17843816631130063, + "grad_norm": 0.32964688640560613, + "learning_rate": 9.960075775770325e-06, + "loss": 0.3658, + "step": 1339 + }, + { + "epoch": 0.17857142857142858, + "grad_norm": 0.34539327088735455, + "learning_rate": 9.959985925910654e-06, + "loss": 0.4028, + "step": 1340 + }, + { + "epoch": 0.1787046908315565, + "grad_norm": 0.34178586906826947, + "learning_rate": 9.959895975466775e-06, + "loss": 0.4608, + "step": 1341 + }, + { + "epoch": 0.17883795309168443, + "grad_norm": 0.3106695842439354, + "learning_rate": 9.959805924440513e-06, + "loss": 0.4318, + "step": 1342 + }, + { + "epoch": 0.17897121535181237, + "grad_norm": 0.37341706584056567, + "learning_rate": 9.959715772833693e-06, + "loss": 0.3904, + "step": 1343 + }, + { + "epoch": 0.1791044776119403, + "grad_norm": 0.3249002562888881, + "learning_rate": 9.959625520648143e-06, + "loss": 0.4535, + "step": 1344 + }, + { + "epoch": 0.17923773987206823, + "grad_norm": 0.3224964321417484, + "learning_rate": 9.959535167885695e-06, + "loss": 0.3953, + "step": 1345 + }, + { + "epoch": 0.17937100213219617, + "grad_norm": 0.33624665486513017, + "learning_rate": 9.959444714548179e-06, + "loss": 0.4058, + "step": 1346 + }, + { + "epoch": 0.1795042643923241, + "grad_norm": 0.3311284247843114, + "learning_rate": 9.959354160637431e-06, + "loss": 0.5286, + "step": 1347 + }, + { + "epoch": 0.17963752665245203, + "grad_norm": 0.3060578207309216, + "learning_rate": 9.959263506155285e-06, + "loss": 0.5359, + "step": 1348 + }, + { + "epoch": 0.17977078891257997, + "grad_norm": 0.33428776452342324, + "learning_rate": 9.959172751103586e-06, + "loss": 0.3895, + "step": 1349 + }, + { + "epoch": 0.17990405117270789, + "grad_norm": 0.3279089993598118, + "learning_rate": 9.959081895484166e-06, + "loss": 0.495, + "step": 1350 + }, + { + "epoch": 0.18003731343283583, + "grad_norm": 0.31394952174368723, + "learning_rate": 9.958990939298872e-06, + "loss": 0.3963, + "step": 1351 + }, + { + "epoch": 0.18017057569296374, + "grad_norm": 0.3097322753091377, + "learning_rate": 9.958899882549548e-06, + "loss": 0.3975, + "step": 1352 + }, + { + "epoch": 0.18030383795309168, + "grad_norm": 0.32416091544413567, + "learning_rate": 9.95880872523804e-06, + "loss": 0.4159, + "step": 1353 + }, + { + "epoch": 0.18043710021321963, + "grad_norm": 0.3100939735958152, + "learning_rate": 9.958717467366197e-06, + "loss": 0.4141, + "step": 1354 + }, + { + "epoch": 0.18057036247334754, + "grad_norm": 0.3279870688840919, + "learning_rate": 9.95862610893587e-06, + "loss": 0.4262, + "step": 1355 + }, + { + "epoch": 0.18070362473347548, + "grad_norm": 0.31654546163692415, + "learning_rate": 9.95853464994891e-06, + "loss": 0.4777, + "step": 1356 + }, + { + "epoch": 0.18083688699360342, + "grad_norm": 0.32793219561530884, + "learning_rate": 9.958443090407173e-06, + "loss": 0.4813, + "step": 1357 + }, + { + "epoch": 0.18097014925373134, + "grad_norm": 0.3140620141501062, + "learning_rate": 9.958351430312516e-06, + "loss": 0.4249, + "step": 1358 + }, + { + "epoch": 0.18110341151385928, + "grad_norm": 0.32192379478552374, + "learning_rate": 9.958259669666798e-06, + "loss": 0.4121, + "step": 1359 + }, + { + "epoch": 0.1812366737739872, + "grad_norm": 0.32141673313708613, + "learning_rate": 9.95816780847188e-06, + "loss": 0.4416, + "step": 1360 + }, + { + "epoch": 0.18136993603411514, + "grad_norm": 0.3216091860290025, + "learning_rate": 9.958075846729622e-06, + "loss": 0.423, + "step": 1361 + }, + { + "epoch": 0.18150319829424308, + "grad_norm": 0.31663182387809785, + "learning_rate": 9.957983784441892e-06, + "loss": 0.4498, + "step": 1362 + }, + { + "epoch": 0.181636460554371, + "grad_norm": 0.35068009602278605, + "learning_rate": 9.957891621610555e-06, + "loss": 0.3984, + "step": 1363 + }, + { + "epoch": 0.18176972281449894, + "grad_norm": 0.32274729764168325, + "learning_rate": 9.957799358237481e-06, + "loss": 0.407, + "step": 1364 + }, + { + "epoch": 0.18190298507462688, + "grad_norm": 0.30458193772630704, + "learning_rate": 9.957706994324543e-06, + "loss": 0.4166, + "step": 1365 + }, + { + "epoch": 0.1820362473347548, + "grad_norm": 0.31447933095152464, + "learning_rate": 9.95761452987361e-06, + "loss": 0.3804, + "step": 1366 + }, + { + "epoch": 0.18216950959488273, + "grad_norm": 0.31089244972751195, + "learning_rate": 9.957521964886558e-06, + "loss": 0.467, + "step": 1367 + }, + { + "epoch": 0.18230277185501065, + "grad_norm": 0.3201704714737683, + "learning_rate": 9.957429299365269e-06, + "loss": 0.3901, + "step": 1368 + }, + { + "epoch": 0.1824360341151386, + "grad_norm": 0.3372427782625622, + "learning_rate": 9.957336533311614e-06, + "loss": 0.4942, + "step": 1369 + }, + { + "epoch": 0.18256929637526653, + "grad_norm": 0.30581556847406327, + "learning_rate": 9.957243666727483e-06, + "loss": 0.415, + "step": 1370 + }, + { + "epoch": 0.18270255863539445, + "grad_norm": 0.3623168179458951, + "learning_rate": 9.957150699614752e-06, + "loss": 0.5675, + "step": 1371 + }, + { + "epoch": 0.1828358208955224, + "grad_norm": 0.3202920280356965, + "learning_rate": 9.95705763197531e-06, + "loss": 0.402, + "step": 1372 + }, + { + "epoch": 0.18296908315565033, + "grad_norm": 0.33718146751397743, + "learning_rate": 9.956964463811043e-06, + "loss": 0.4269, + "step": 1373 + }, + { + "epoch": 0.18310234541577824, + "grad_norm": 0.313901269769581, + "learning_rate": 9.956871195123841e-06, + "loss": 0.433, + "step": 1374 + }, + { + "epoch": 0.1832356076759062, + "grad_norm": 0.35358818648062595, + "learning_rate": 9.956777825915597e-06, + "loss": 0.4286, + "step": 1375 + }, + { + "epoch": 0.18336886993603413, + "grad_norm": 0.34374963783527096, + "learning_rate": 9.956684356188202e-06, + "loss": 0.4181, + "step": 1376 + }, + { + "epoch": 0.18350213219616204, + "grad_norm": 7.954371192321488, + "learning_rate": 9.95659078594355e-06, + "loss": 0.4059, + "step": 1377 + }, + { + "epoch": 0.18363539445628999, + "grad_norm": 0.3648732606591613, + "learning_rate": 9.956497115183544e-06, + "loss": 0.3866, + "step": 1378 + }, + { + "epoch": 0.1837686567164179, + "grad_norm": 0.3337556713604201, + "learning_rate": 9.956403343910078e-06, + "loss": 0.4239, + "step": 1379 + }, + { + "epoch": 0.18390191897654584, + "grad_norm": 0.3902228398518375, + "learning_rate": 9.956309472125056e-06, + "loss": 0.4169, + "step": 1380 + }, + { + "epoch": 0.18403518123667378, + "grad_norm": 0.3535474945743539, + "learning_rate": 9.956215499830382e-06, + "loss": 0.5287, + "step": 1381 + }, + { + "epoch": 0.1841684434968017, + "grad_norm": 0.3779711037972004, + "learning_rate": 9.95612142702796e-06, + "loss": 0.4383, + "step": 1382 + }, + { + "epoch": 0.18430170575692964, + "grad_norm": 0.34043675606669044, + "learning_rate": 9.956027253719702e-06, + "loss": 0.4417, + "step": 1383 + }, + { + "epoch": 0.18443496801705758, + "grad_norm": 0.36028245783380586, + "learning_rate": 9.955932979907512e-06, + "loss": 0.4538, + "step": 1384 + }, + { + "epoch": 0.1845682302771855, + "grad_norm": 0.3230955873630049, + "learning_rate": 9.955838605593305e-06, + "loss": 0.4153, + "step": 1385 + }, + { + "epoch": 0.18470149253731344, + "grad_norm": 0.346893953926626, + "learning_rate": 9.955744130778994e-06, + "loss": 0.4734, + "step": 1386 + }, + { + "epoch": 0.18483475479744135, + "grad_norm": 0.3433288958145577, + "learning_rate": 9.955649555466498e-06, + "loss": 0.4165, + "step": 1387 + }, + { + "epoch": 0.1849680170575693, + "grad_norm": 0.34591654593023957, + "learning_rate": 9.95555487965773e-06, + "loss": 0.4247, + "step": 1388 + }, + { + "epoch": 0.18510127931769724, + "grad_norm": 0.3262379932888451, + "learning_rate": 9.95546010335461e-06, + "loss": 0.4568, + "step": 1389 + }, + { + "epoch": 0.18523454157782515, + "grad_norm": 0.32921916161298925, + "learning_rate": 9.955365226559066e-06, + "loss": 0.4035, + "step": 1390 + }, + { + "epoch": 0.1853678038379531, + "grad_norm": 0.3205068414999446, + "learning_rate": 9.955270249273015e-06, + "loss": 0.3573, + "step": 1391 + }, + { + "epoch": 0.18550106609808104, + "grad_norm": 0.3579191181951323, + "learning_rate": 9.955175171498387e-06, + "loss": 0.4981, + "step": 1392 + }, + { + "epoch": 0.18563432835820895, + "grad_norm": 0.3248779976411897, + "learning_rate": 9.955079993237109e-06, + "loss": 0.4621, + "step": 1393 + }, + { + "epoch": 0.1857675906183369, + "grad_norm": 0.3455772309657606, + "learning_rate": 9.954984714491112e-06, + "loss": 0.4848, + "step": 1394 + }, + { + "epoch": 0.1859008528784648, + "grad_norm": 0.3420533948990277, + "learning_rate": 9.954889335262325e-06, + "loss": 0.474, + "step": 1395 + }, + { + "epoch": 0.18603411513859275, + "grad_norm": 0.32946936860341436, + "learning_rate": 9.954793855552688e-06, + "loss": 0.4283, + "step": 1396 + }, + { + "epoch": 0.1861673773987207, + "grad_norm": 0.3736474600690331, + "learning_rate": 9.954698275364132e-06, + "loss": 0.4556, + "step": 1397 + }, + { + "epoch": 0.1863006396588486, + "grad_norm": 0.33384017949242245, + "learning_rate": 9.954602594698598e-06, + "loss": 0.5564, + "step": 1398 + }, + { + "epoch": 0.18643390191897655, + "grad_norm": 0.3380116010662967, + "learning_rate": 9.954506813558025e-06, + "loss": 0.5264, + "step": 1399 + }, + { + "epoch": 0.1865671641791045, + "grad_norm": 0.3682888146418086, + "learning_rate": 9.954410931944356e-06, + "loss": 0.4911, + "step": 1400 + }, + { + "epoch": 0.1867004264392324, + "grad_norm": 0.3251027610578727, + "learning_rate": 9.954314949859536e-06, + "loss": 0.4439, + "step": 1401 + }, + { + "epoch": 0.18683368869936035, + "grad_norm": 0.3467539335063132, + "learning_rate": 9.95421886730551e-06, + "loss": 0.4233, + "step": 1402 + }, + { + "epoch": 0.18696695095948826, + "grad_norm": 0.3271881151950413, + "learning_rate": 9.954122684284227e-06, + "loss": 0.3511, + "step": 1403 + }, + { + "epoch": 0.1871002132196162, + "grad_norm": 0.3247543211918978, + "learning_rate": 9.954026400797638e-06, + "loss": 0.3946, + "step": 1404 + }, + { + "epoch": 0.18723347547974414, + "grad_norm": 0.33515444668503275, + "learning_rate": 9.953930016847695e-06, + "loss": 0.4002, + "step": 1405 + }, + { + "epoch": 0.18736673773987206, + "grad_norm": 0.31541898405885965, + "learning_rate": 9.953833532436354e-06, + "loss": 0.4078, + "step": 1406 + }, + { + "epoch": 0.1875, + "grad_norm": 0.30932009160073665, + "learning_rate": 9.95373694756557e-06, + "loss": 0.3636, + "step": 1407 + }, + { + "epoch": 0.18763326226012794, + "grad_norm": 0.32902910731870283, + "learning_rate": 9.953640262237301e-06, + "loss": 0.3949, + "step": 1408 + }, + { + "epoch": 0.18776652452025586, + "grad_norm": 0.33212615739769474, + "learning_rate": 9.953543476453508e-06, + "loss": 0.381, + "step": 1409 + }, + { + "epoch": 0.1878997867803838, + "grad_norm": 0.3319387540069383, + "learning_rate": 9.953446590216157e-06, + "loss": 0.503, + "step": 1410 + }, + { + "epoch": 0.18803304904051174, + "grad_norm": 0.34141959793922166, + "learning_rate": 9.95334960352721e-06, + "loss": 0.4158, + "step": 1411 + }, + { + "epoch": 0.18816631130063965, + "grad_norm": 0.5004467509306146, + "learning_rate": 9.953252516388632e-06, + "loss": 0.4197, + "step": 1412 + }, + { + "epoch": 0.1882995735607676, + "grad_norm": 0.3250229628767642, + "learning_rate": 9.953155328802395e-06, + "loss": 0.4235, + "step": 1413 + }, + { + "epoch": 0.1884328358208955, + "grad_norm": 0.3416903132530254, + "learning_rate": 9.953058040770469e-06, + "loss": 0.4475, + "step": 1414 + }, + { + "epoch": 0.18856609808102345, + "grad_norm": 0.3474152871589584, + "learning_rate": 9.952960652294828e-06, + "loss": 0.4565, + "step": 1415 + }, + { + "epoch": 0.1886993603411514, + "grad_norm": 0.32641286519425455, + "learning_rate": 9.952863163377444e-06, + "loss": 0.5181, + "step": 1416 + }, + { + "epoch": 0.1888326226012793, + "grad_norm": 0.3379313825292435, + "learning_rate": 9.952765574020296e-06, + "loss": 0.4816, + "step": 1417 + }, + { + "epoch": 0.18896588486140725, + "grad_norm": 0.3299834605298751, + "learning_rate": 9.952667884225363e-06, + "loss": 0.4225, + "step": 1418 + }, + { + "epoch": 0.1890991471215352, + "grad_norm": 0.3320185762311333, + "learning_rate": 9.952570093994628e-06, + "loss": 0.4526, + "step": 1419 + }, + { + "epoch": 0.1892324093816631, + "grad_norm": 0.4552877901440306, + "learning_rate": 9.952472203330068e-06, + "loss": 0.4587, + "step": 1420 + }, + { + "epoch": 0.18936567164179105, + "grad_norm": 0.35515528919268946, + "learning_rate": 9.952374212233673e-06, + "loss": 0.4934, + "step": 1421 + }, + { + "epoch": 0.18949893390191896, + "grad_norm": 0.33377355974459877, + "learning_rate": 9.95227612070743e-06, + "loss": 0.425, + "step": 1422 + }, + { + "epoch": 0.1896321961620469, + "grad_norm": 0.3618772019985546, + "learning_rate": 9.952177928753327e-06, + "loss": 0.4287, + "step": 1423 + }, + { + "epoch": 0.18976545842217485, + "grad_norm": 0.3475014178945359, + "learning_rate": 9.952079636373356e-06, + "loss": 0.4133, + "step": 1424 + }, + { + "epoch": 0.18989872068230276, + "grad_norm": 0.29877873951020734, + "learning_rate": 9.95198124356951e-06, + "loss": 0.3362, + "step": 1425 + }, + { + "epoch": 0.1900319829424307, + "grad_norm": 0.3344992905433896, + "learning_rate": 9.951882750343783e-06, + "loss": 0.4131, + "step": 1426 + }, + { + "epoch": 0.19016524520255865, + "grad_norm": 0.3561472518610966, + "learning_rate": 9.951784156698176e-06, + "loss": 0.468, + "step": 1427 + }, + { + "epoch": 0.19029850746268656, + "grad_norm": 0.30490528712536663, + "learning_rate": 9.951685462634683e-06, + "loss": 0.413, + "step": 1428 + }, + { + "epoch": 0.1904317697228145, + "grad_norm": 0.3348628068374817, + "learning_rate": 9.951586668155311e-06, + "loss": 0.4411, + "step": 1429 + }, + { + "epoch": 0.19056503198294242, + "grad_norm": 0.31620360860351304, + "learning_rate": 9.95148777326206e-06, + "loss": 0.3871, + "step": 1430 + }, + { + "epoch": 0.19069829424307036, + "grad_norm": 0.32098557051589255, + "learning_rate": 9.951388777956936e-06, + "loss": 0.4403, + "step": 1431 + }, + { + "epoch": 0.1908315565031983, + "grad_norm": 0.3219593819514916, + "learning_rate": 9.951289682241948e-06, + "loss": 0.4238, + "step": 1432 + }, + { + "epoch": 0.19096481876332622, + "grad_norm": 0.36032567411962846, + "learning_rate": 9.951190486119103e-06, + "loss": 0.4066, + "step": 1433 + }, + { + "epoch": 0.19109808102345416, + "grad_norm": 0.3267774216674683, + "learning_rate": 9.951091189590416e-06, + "loss": 0.4807, + "step": 1434 + }, + { + "epoch": 0.1912313432835821, + "grad_norm": 0.3227906471866864, + "learning_rate": 9.950991792657896e-06, + "loss": 0.3882, + "step": 1435 + }, + { + "epoch": 0.19136460554371001, + "grad_norm": 0.3229450982566907, + "learning_rate": 9.950892295323564e-06, + "loss": 0.5015, + "step": 1436 + }, + { + "epoch": 0.19149786780383796, + "grad_norm": 0.33993779866453305, + "learning_rate": 9.950792697589435e-06, + "loss": 0.4713, + "step": 1437 + }, + { + "epoch": 0.19163113006396587, + "grad_norm": 0.3467006669545379, + "learning_rate": 9.950692999457528e-06, + "loss": 0.4484, + "step": 1438 + }, + { + "epoch": 0.1917643923240938, + "grad_norm": 0.32522847775741104, + "learning_rate": 9.950593200929866e-06, + "loss": 0.4871, + "step": 1439 + }, + { + "epoch": 0.19189765458422176, + "grad_norm": 0.3294476874723546, + "learning_rate": 9.950493302008472e-06, + "loss": 0.3699, + "step": 1440 + }, + { + "epoch": 0.19203091684434967, + "grad_norm": 0.3103967118679011, + "learning_rate": 9.950393302695374e-06, + "loss": 0.3831, + "step": 1441 + }, + { + "epoch": 0.1921641791044776, + "grad_norm": 0.3288961287392624, + "learning_rate": 9.950293202992597e-06, + "loss": 0.4121, + "step": 1442 + }, + { + "epoch": 0.19229744136460555, + "grad_norm": 0.31279070585769253, + "learning_rate": 9.950193002902171e-06, + "loss": 0.4361, + "step": 1443 + }, + { + "epoch": 0.19243070362473347, + "grad_norm": 0.32089170040276027, + "learning_rate": 9.950092702426132e-06, + "loss": 0.3926, + "step": 1444 + }, + { + "epoch": 0.1925639658848614, + "grad_norm": 0.31131390908717393, + "learning_rate": 9.94999230156651e-06, + "loss": 0.4578, + "step": 1445 + }, + { + "epoch": 0.19269722814498935, + "grad_norm": 0.32342211958964906, + "learning_rate": 9.949891800325341e-06, + "loss": 0.4163, + "step": 1446 + }, + { + "epoch": 0.19283049040511727, + "grad_norm": 0.3398798188080709, + "learning_rate": 9.949791198704668e-06, + "loss": 0.4389, + "step": 1447 + }, + { + "epoch": 0.1929637526652452, + "grad_norm": 0.3342726510033035, + "learning_rate": 9.949690496706524e-06, + "loss": 0.487, + "step": 1448 + }, + { + "epoch": 0.19309701492537312, + "grad_norm": 0.3107494518169437, + "learning_rate": 9.949589694332955e-06, + "loss": 0.407, + "step": 1449 + }, + { + "epoch": 0.19323027718550106, + "grad_norm": 0.33804069120646435, + "learning_rate": 9.949488791586007e-06, + "loss": 0.4456, + "step": 1450 + }, + { + "epoch": 0.193363539445629, + "grad_norm": 0.33906764379597915, + "learning_rate": 9.949387788467722e-06, + "loss": 0.4128, + "step": 1451 + }, + { + "epoch": 0.19349680170575692, + "grad_norm": 0.3232311208834164, + "learning_rate": 9.94928668498015e-06, + "loss": 0.3714, + "step": 1452 + }, + { + "epoch": 0.19363006396588486, + "grad_norm": 0.31742157859120096, + "learning_rate": 9.949185481125343e-06, + "loss": 0.4466, + "step": 1453 + }, + { + "epoch": 0.1937633262260128, + "grad_norm": 0.33050069485253286, + "learning_rate": 9.94908417690535e-06, + "loss": 0.4275, + "step": 1454 + }, + { + "epoch": 0.19389658848614072, + "grad_norm": 0.32194104718821137, + "learning_rate": 9.948982772322229e-06, + "loss": 0.4028, + "step": 1455 + }, + { + "epoch": 0.19402985074626866, + "grad_norm": 0.3229807782051873, + "learning_rate": 9.948881267378034e-06, + "loss": 0.4781, + "step": 1456 + }, + { + "epoch": 0.19416311300639658, + "grad_norm": 0.32225294215804623, + "learning_rate": 9.948779662074824e-06, + "loss": 0.4458, + "step": 1457 + }, + { + "epoch": 0.19429637526652452, + "grad_norm": 0.3237332755480436, + "learning_rate": 9.948677956414661e-06, + "loss": 0.4671, + "step": 1458 + }, + { + "epoch": 0.19442963752665246, + "grad_norm": 0.3200365374635605, + "learning_rate": 9.948576150399603e-06, + "loss": 0.3963, + "step": 1459 + }, + { + "epoch": 0.19456289978678037, + "grad_norm": 0.3232018773946268, + "learning_rate": 9.94847424403172e-06, + "loss": 0.381, + "step": 1460 + }, + { + "epoch": 0.19469616204690832, + "grad_norm": 0.30663297274344786, + "learning_rate": 9.948372237313075e-06, + "loss": 0.3453, + "step": 1461 + }, + { + "epoch": 0.19482942430703626, + "grad_norm": 0.33309809429994824, + "learning_rate": 9.948270130245738e-06, + "loss": 0.3765, + "step": 1462 + }, + { + "epoch": 0.19496268656716417, + "grad_norm": 0.3315056064120118, + "learning_rate": 9.948167922831781e-06, + "loss": 0.491, + "step": 1463 + }, + { + "epoch": 0.19509594882729211, + "grad_norm": 0.33705361138814577, + "learning_rate": 9.948065615073274e-06, + "loss": 0.4182, + "step": 1464 + }, + { + "epoch": 0.19522921108742003, + "grad_norm": 0.3861914501132992, + "learning_rate": 9.947963206972291e-06, + "loss": 0.441, + "step": 1465 + }, + { + "epoch": 0.19536247334754797, + "grad_norm": 0.31230361077085356, + "learning_rate": 9.947860698530913e-06, + "loss": 0.4473, + "step": 1466 + }, + { + "epoch": 0.1954957356076759, + "grad_norm": 0.34417251842037805, + "learning_rate": 9.947758089751216e-06, + "loss": 0.4657, + "step": 1467 + }, + { + "epoch": 0.19562899786780383, + "grad_norm": 0.30872082684215446, + "learning_rate": 9.94765538063528e-06, + "loss": 0.382, + "step": 1468 + }, + { + "epoch": 0.19576226012793177, + "grad_norm": 0.3306861189480107, + "learning_rate": 9.947552571185189e-06, + "loss": 0.4425, + "step": 1469 + }, + { + "epoch": 0.1958955223880597, + "grad_norm": 0.3322422417847072, + "learning_rate": 9.947449661403029e-06, + "loss": 0.3892, + "step": 1470 + }, + { + "epoch": 0.19602878464818763, + "grad_norm": 0.31533042614181545, + "learning_rate": 9.947346651290885e-06, + "loss": 0.5195, + "step": 1471 + }, + { + "epoch": 0.19616204690831557, + "grad_norm": 0.37762463007111174, + "learning_rate": 9.947243540850846e-06, + "loss": 0.4853, + "step": 1472 + }, + { + "epoch": 0.1962953091684435, + "grad_norm": 0.31208589418143806, + "learning_rate": 9.947140330085005e-06, + "loss": 0.4498, + "step": 1473 + }, + { + "epoch": 0.19642857142857142, + "grad_norm": 0.3367094367368884, + "learning_rate": 9.947037018995455e-06, + "loss": 0.3944, + "step": 1474 + }, + { + "epoch": 0.19656183368869937, + "grad_norm": 0.3216021597749439, + "learning_rate": 9.946933607584288e-06, + "loss": 0.4539, + "step": 1475 + }, + { + "epoch": 0.19669509594882728, + "grad_norm": 0.34655148242447964, + "learning_rate": 9.946830095853604e-06, + "loss": 0.4578, + "step": 1476 + }, + { + "epoch": 0.19682835820895522, + "grad_norm": 0.3263876988780329, + "learning_rate": 9.9467264838055e-06, + "loss": 0.4161, + "step": 1477 + }, + { + "epoch": 0.19696162046908317, + "grad_norm": 0.34862215401839347, + "learning_rate": 9.946622771442078e-06, + "loss": 0.4196, + "step": 1478 + }, + { + "epoch": 0.19709488272921108, + "grad_norm": 0.32971101905316136, + "learning_rate": 9.946518958765442e-06, + "loss": 0.388, + "step": 1479 + }, + { + "epoch": 0.19722814498933902, + "grad_norm": 0.3418599596481595, + "learning_rate": 9.946415045777697e-06, + "loss": 0.4738, + "step": 1480 + }, + { + "epoch": 0.19736140724946696, + "grad_norm": 0.34538687478536634, + "learning_rate": 9.946311032480949e-06, + "loss": 0.4116, + "step": 1481 + }, + { + "epoch": 0.19749466950959488, + "grad_norm": 0.324006138956055, + "learning_rate": 9.946206918877309e-06, + "loss": 0.4275, + "step": 1482 + }, + { + "epoch": 0.19762793176972282, + "grad_norm": 0.34143200777158755, + "learning_rate": 9.946102704968888e-06, + "loss": 0.3973, + "step": 1483 + }, + { + "epoch": 0.19776119402985073, + "grad_norm": 0.3206227346998692, + "learning_rate": 9.945998390757797e-06, + "loss": 0.3864, + "step": 1484 + }, + { + "epoch": 0.19789445628997868, + "grad_norm": 0.3370085154364301, + "learning_rate": 9.945893976246155e-06, + "loss": 0.3744, + "step": 1485 + }, + { + "epoch": 0.19802771855010662, + "grad_norm": 0.35095957409158535, + "learning_rate": 9.945789461436077e-06, + "loss": 0.4307, + "step": 1486 + }, + { + "epoch": 0.19816098081023453, + "grad_norm": 0.32752606088963104, + "learning_rate": 9.945684846329684e-06, + "loss": 0.3852, + "step": 1487 + }, + { + "epoch": 0.19829424307036247, + "grad_norm": 0.33141678019661097, + "learning_rate": 9.945580130929095e-06, + "loss": 0.5061, + "step": 1488 + }, + { + "epoch": 0.19842750533049042, + "grad_norm": 0.32699481238877026, + "learning_rate": 9.945475315236437e-06, + "loss": 0.4839, + "step": 1489 + }, + { + "epoch": 0.19856076759061833, + "grad_norm": 0.3565397511410979, + "learning_rate": 9.945370399253832e-06, + "loss": 0.4859, + "step": 1490 + }, + { + "epoch": 0.19869402985074627, + "grad_norm": 0.36014424908461956, + "learning_rate": 9.945265382983411e-06, + "loss": 0.486, + "step": 1491 + }, + { + "epoch": 0.1988272921108742, + "grad_norm": 0.3534622283311304, + "learning_rate": 9.945160266427303e-06, + "loss": 0.3927, + "step": 1492 + }, + { + "epoch": 0.19896055437100213, + "grad_norm": 0.335083014499547, + "learning_rate": 9.945055049587637e-06, + "loss": 0.4453, + "step": 1493 + }, + { + "epoch": 0.19909381663113007, + "grad_norm": 0.33229952739442165, + "learning_rate": 9.944949732466548e-06, + "loss": 0.4527, + "step": 1494 + }, + { + "epoch": 0.19922707889125799, + "grad_norm": 0.3376490619132051, + "learning_rate": 9.944844315066175e-06, + "loss": 0.4407, + "step": 1495 + }, + { + "epoch": 0.19936034115138593, + "grad_norm": 0.3293287321534983, + "learning_rate": 9.944738797388652e-06, + "loss": 0.4047, + "step": 1496 + }, + { + "epoch": 0.19949360341151387, + "grad_norm": 0.33795145103127283, + "learning_rate": 9.944633179436118e-06, + "loss": 0.4377, + "step": 1497 + }, + { + "epoch": 0.19962686567164178, + "grad_norm": 0.36461379007786476, + "learning_rate": 9.944527461210717e-06, + "loss": 0.4084, + "step": 1498 + }, + { + "epoch": 0.19976012793176973, + "grad_norm": 0.29717652001565864, + "learning_rate": 9.944421642714594e-06, + "loss": 0.3427, + "step": 1499 + }, + { + "epoch": 0.19989339019189764, + "grad_norm": 0.3304361607839004, + "learning_rate": 9.944315723949892e-06, + "loss": 0.372, + "step": 1500 + }, + { + "epoch": 0.20002665245202558, + "grad_norm": 0.3227025570626246, + "learning_rate": 9.94420970491876e-06, + "loss": 0.3974, + "step": 1501 + }, + { + "epoch": 0.20015991471215352, + "grad_norm": 0.3201883882645394, + "learning_rate": 9.94410358562335e-06, + "loss": 0.3679, + "step": 1502 + }, + { + "epoch": 0.20029317697228144, + "grad_norm": 0.3254382145195989, + "learning_rate": 9.943997366065812e-06, + "loss": 0.406, + "step": 1503 + }, + { + "epoch": 0.20042643923240938, + "grad_norm": 0.34468742419962256, + "learning_rate": 9.943891046248299e-06, + "loss": 0.4863, + "step": 1504 + }, + { + "epoch": 0.20055970149253732, + "grad_norm": 0.33391563060717144, + "learning_rate": 9.943784626172968e-06, + "loss": 0.3783, + "step": 1505 + }, + { + "epoch": 0.20069296375266524, + "grad_norm": 0.31040337838003546, + "learning_rate": 9.94367810584198e-06, + "loss": 0.3986, + "step": 1506 + }, + { + "epoch": 0.20082622601279318, + "grad_norm": 0.3319155419916233, + "learning_rate": 9.943571485257491e-06, + "loss": 0.4272, + "step": 1507 + }, + { + "epoch": 0.20095948827292112, + "grad_norm": 0.32225251728491006, + "learning_rate": 9.943464764421665e-06, + "loss": 0.5099, + "step": 1508 + }, + { + "epoch": 0.20109275053304904, + "grad_norm": 0.3327767499528836, + "learning_rate": 9.943357943336666e-06, + "loss": 0.4751, + "step": 1509 + }, + { + "epoch": 0.20122601279317698, + "grad_norm": 0.3337552746798133, + "learning_rate": 9.94325102200466e-06, + "loss": 0.4878, + "step": 1510 + }, + { + "epoch": 0.2013592750533049, + "grad_norm": 0.3315432906936707, + "learning_rate": 9.943144000427818e-06, + "loss": 0.4066, + "step": 1511 + }, + { + "epoch": 0.20149253731343283, + "grad_norm": 0.3477519804502539, + "learning_rate": 9.943036878608306e-06, + "loss": 0.4391, + "step": 1512 + }, + { + "epoch": 0.20162579957356078, + "grad_norm": 0.3205014945069357, + "learning_rate": 9.942929656548297e-06, + "loss": 0.4378, + "step": 1513 + }, + { + "epoch": 0.2017590618336887, + "grad_norm": 0.30147586399777776, + "learning_rate": 9.94282233424997e-06, + "loss": 0.4417, + "step": 1514 + }, + { + "epoch": 0.20189232409381663, + "grad_norm": 0.3134171190911947, + "learning_rate": 9.942714911715494e-06, + "loss": 0.3776, + "step": 1515 + }, + { + "epoch": 0.20202558635394458, + "grad_norm": 0.31585997762663465, + "learning_rate": 9.942607388947053e-06, + "loss": 0.38, + "step": 1516 + }, + { + "epoch": 0.2021588486140725, + "grad_norm": 0.3338346466262373, + "learning_rate": 9.942499765946826e-06, + "loss": 0.4333, + "step": 1517 + }, + { + "epoch": 0.20229211087420043, + "grad_norm": 0.3170083775746666, + "learning_rate": 9.942392042716994e-06, + "loss": 0.4144, + "step": 1518 + }, + { + "epoch": 0.20242537313432835, + "grad_norm": 0.3053483840293477, + "learning_rate": 9.942284219259746e-06, + "loss": 0.3764, + "step": 1519 + }, + { + "epoch": 0.2025586353944563, + "grad_norm": 0.3196680541188147, + "learning_rate": 9.942176295577263e-06, + "loss": 0.4509, + "step": 1520 + }, + { + "epoch": 0.20269189765458423, + "grad_norm": 0.3092703072281893, + "learning_rate": 9.942068271671737e-06, + "loss": 0.5628, + "step": 1521 + }, + { + "epoch": 0.20282515991471214, + "grad_norm": 0.3188008871907141, + "learning_rate": 9.941960147545358e-06, + "loss": 0.4212, + "step": 1522 + }, + { + "epoch": 0.2029584221748401, + "grad_norm": 0.33184917121901797, + "learning_rate": 9.941851923200318e-06, + "loss": 0.433, + "step": 1523 + }, + { + "epoch": 0.20309168443496803, + "grad_norm": 0.3280415186130422, + "learning_rate": 9.941743598638812e-06, + "loss": 0.4395, + "step": 1524 + }, + { + "epoch": 0.20322494669509594, + "grad_norm": 0.3855063464764108, + "learning_rate": 9.941635173863039e-06, + "loss": 0.4233, + "step": 1525 + }, + { + "epoch": 0.20335820895522388, + "grad_norm": 0.32939136287402354, + "learning_rate": 9.941526648875192e-06, + "loss": 0.4396, + "step": 1526 + }, + { + "epoch": 0.2034914712153518, + "grad_norm": 0.3025247419925725, + "learning_rate": 9.941418023677476e-06, + "loss": 0.3788, + "step": 1527 + }, + { + "epoch": 0.20362473347547974, + "grad_norm": 0.29867588577688386, + "learning_rate": 9.941309298272095e-06, + "loss": 0.4652, + "step": 1528 + }, + { + "epoch": 0.20375799573560768, + "grad_norm": 0.3202836174449927, + "learning_rate": 9.94120047266125e-06, + "loss": 0.412, + "step": 1529 + }, + { + "epoch": 0.2038912579957356, + "grad_norm": 0.31729173372673497, + "learning_rate": 9.941091546847152e-06, + "loss": 0.4281, + "step": 1530 + }, + { + "epoch": 0.20402452025586354, + "grad_norm": 0.32345536176696715, + "learning_rate": 9.940982520832007e-06, + "loss": 0.4808, + "step": 1531 + }, + { + "epoch": 0.20415778251599148, + "grad_norm": 0.3231185466323681, + "learning_rate": 9.940873394618026e-06, + "loss": 0.4287, + "step": 1532 + }, + { + "epoch": 0.2042910447761194, + "grad_norm": 0.30944165137390056, + "learning_rate": 9.940764168207424e-06, + "loss": 0.3779, + "step": 1533 + }, + { + "epoch": 0.20442430703624734, + "grad_norm": 0.3501649582175791, + "learning_rate": 9.940654841602413e-06, + "loss": 0.4976, + "step": 1534 + }, + { + "epoch": 0.20455756929637528, + "grad_norm": 0.31245320426422235, + "learning_rate": 9.940545414805215e-06, + "loss": 0.5842, + "step": 1535 + }, + { + "epoch": 0.2046908315565032, + "grad_norm": 0.30244664172944596, + "learning_rate": 9.940435887818042e-06, + "loss": 0.3417, + "step": 1536 + }, + { + "epoch": 0.20482409381663114, + "grad_norm": 0.30947593235471377, + "learning_rate": 9.940326260643122e-06, + "loss": 0.5187, + "step": 1537 + }, + { + "epoch": 0.20495735607675905, + "grad_norm": 0.3294446092156426, + "learning_rate": 9.940216533282674e-06, + "loss": 0.405, + "step": 1538 + }, + { + "epoch": 0.205090618336887, + "grad_norm": 0.3121565976441194, + "learning_rate": 9.940106705738925e-06, + "loss": 0.3498, + "step": 1539 + }, + { + "epoch": 0.20522388059701493, + "grad_norm": 0.31474941254929706, + "learning_rate": 9.939996778014101e-06, + "loss": 0.6143, + "step": 1540 + }, + { + "epoch": 0.20535714285714285, + "grad_norm": 0.3060526160728276, + "learning_rate": 9.939886750110431e-06, + "loss": 0.4455, + "step": 1541 + }, + { + "epoch": 0.2054904051172708, + "grad_norm": 0.32292336949837763, + "learning_rate": 9.939776622030148e-06, + "loss": 0.3966, + "step": 1542 + }, + { + "epoch": 0.20562366737739873, + "grad_norm": 0.31667917577452465, + "learning_rate": 9.939666393775484e-06, + "loss": 0.3843, + "step": 1543 + }, + { + "epoch": 0.20575692963752665, + "grad_norm": 0.3147443400106398, + "learning_rate": 9.939556065348675e-06, + "loss": 0.4256, + "step": 1544 + }, + { + "epoch": 0.2058901918976546, + "grad_norm": 0.3139403378233399, + "learning_rate": 9.93944563675196e-06, + "loss": 0.4522, + "step": 1545 + }, + { + "epoch": 0.2060234541577825, + "grad_norm": 0.3547123524389865, + "learning_rate": 9.939335107987574e-06, + "loss": 0.4286, + "step": 1546 + }, + { + "epoch": 0.20615671641791045, + "grad_norm": 0.31329958061296337, + "learning_rate": 9.939224479057761e-06, + "loss": 0.4447, + "step": 1547 + }, + { + "epoch": 0.2062899786780384, + "grad_norm": 0.35140494497253655, + "learning_rate": 9.939113749964766e-06, + "loss": 0.4789, + "step": 1548 + }, + { + "epoch": 0.2064232409381663, + "grad_norm": 0.30054614382769795, + "learning_rate": 9.93900292071083e-06, + "loss": 0.3894, + "step": 1549 + }, + { + "epoch": 0.20655650319829424, + "grad_norm": 0.31075339228818943, + "learning_rate": 9.938891991298206e-06, + "loss": 0.3796, + "step": 1550 + }, + { + "epoch": 0.2066897654584222, + "grad_norm": 0.33454800879383767, + "learning_rate": 9.938780961729139e-06, + "loss": 0.4274, + "step": 1551 + }, + { + "epoch": 0.2068230277185501, + "grad_norm": 0.32016383300750395, + "learning_rate": 9.938669832005885e-06, + "loss": 0.5074, + "step": 1552 + }, + { + "epoch": 0.20695628997867804, + "grad_norm": 0.29822972443355333, + "learning_rate": 9.938558602130694e-06, + "loss": 0.4423, + "step": 1553 + }, + { + "epoch": 0.20708955223880596, + "grad_norm": 0.34180779367899755, + "learning_rate": 9.938447272105822e-06, + "loss": 0.5114, + "step": 1554 + }, + { + "epoch": 0.2072228144989339, + "grad_norm": 0.31712342612173117, + "learning_rate": 9.938335841933528e-06, + "loss": 0.4672, + "step": 1555 + }, + { + "epoch": 0.20735607675906184, + "grad_norm": 0.3439036753850702, + "learning_rate": 9.93822431161607e-06, + "loss": 0.4263, + "step": 1556 + }, + { + "epoch": 0.20748933901918976, + "grad_norm": 0.3209610332381423, + "learning_rate": 9.938112681155712e-06, + "loss": 0.407, + "step": 1557 + }, + { + "epoch": 0.2076226012793177, + "grad_norm": 0.3515245411339095, + "learning_rate": 9.938000950554717e-06, + "loss": 0.5648, + "step": 1558 + }, + { + "epoch": 0.20775586353944564, + "grad_norm": 0.31875805835210586, + "learning_rate": 9.93788911981535e-06, + "loss": 0.4182, + "step": 1559 + }, + { + "epoch": 0.20788912579957355, + "grad_norm": 0.31871883325823847, + "learning_rate": 9.93777718893988e-06, + "loss": 0.4112, + "step": 1560 + }, + { + "epoch": 0.2080223880597015, + "grad_norm": 0.32177897680623857, + "learning_rate": 9.937665157930574e-06, + "loss": 0.4046, + "step": 1561 + }, + { + "epoch": 0.2081556503198294, + "grad_norm": 0.3188084602170347, + "learning_rate": 9.937553026789708e-06, + "loss": 0.4201, + "step": 1562 + }, + { + "epoch": 0.20828891257995735, + "grad_norm": 0.30311311107502464, + "learning_rate": 9.937440795519555e-06, + "loss": 0.4131, + "step": 1563 + }, + { + "epoch": 0.2084221748400853, + "grad_norm": 0.33051322503326364, + "learning_rate": 9.937328464122387e-06, + "loss": 0.4545, + "step": 1564 + }, + { + "epoch": 0.2085554371002132, + "grad_norm": 0.33680170168816365, + "learning_rate": 9.937216032600486e-06, + "loss": 0.4666, + "step": 1565 + }, + { + "epoch": 0.20868869936034115, + "grad_norm": 0.31528418265940594, + "learning_rate": 9.93710350095613e-06, + "loss": 0.374, + "step": 1566 + }, + { + "epoch": 0.2088219616204691, + "grad_norm": 0.3210417757908177, + "learning_rate": 9.936990869191604e-06, + "loss": 0.3906, + "step": 1567 + }, + { + "epoch": 0.208955223880597, + "grad_norm": 0.318640295012712, + "learning_rate": 9.93687813730919e-06, + "loss": 0.4333, + "step": 1568 + }, + { + "epoch": 0.20908848614072495, + "grad_norm": 0.32995176545113275, + "learning_rate": 9.936765305311173e-06, + "loss": 0.5244, + "step": 1569 + }, + { + "epoch": 0.2092217484008529, + "grad_norm": 0.31813945627870227, + "learning_rate": 9.936652373199841e-06, + "loss": 0.4787, + "step": 1570 + }, + { + "epoch": 0.2093550106609808, + "grad_norm": 0.33932861115196306, + "learning_rate": 9.93653934097749e-06, + "loss": 0.4157, + "step": 1571 + }, + { + "epoch": 0.20948827292110875, + "grad_norm": 0.33582873029241483, + "learning_rate": 9.936426208646404e-06, + "loss": 0.4608, + "step": 1572 + }, + { + "epoch": 0.20962153518123666, + "grad_norm": 0.3205436702022905, + "learning_rate": 9.936312976208881e-06, + "loss": 0.4953, + "step": 1573 + }, + { + "epoch": 0.2097547974413646, + "grad_norm": 0.32245685273965474, + "learning_rate": 9.936199643667217e-06, + "loss": 0.4346, + "step": 1574 + }, + { + "epoch": 0.20988805970149255, + "grad_norm": 0.30237448134307954, + "learning_rate": 9.936086211023712e-06, + "loss": 0.3832, + "step": 1575 + }, + { + "epoch": 0.21002132196162046, + "grad_norm": 0.3319910055972291, + "learning_rate": 9.935972678280663e-06, + "loss": 0.4429, + "step": 1576 + }, + { + "epoch": 0.2101545842217484, + "grad_norm": 0.3238814227150805, + "learning_rate": 9.935859045440375e-06, + "loss": 0.4703, + "step": 1577 + }, + { + "epoch": 0.21028784648187634, + "grad_norm": 0.332023134811427, + "learning_rate": 9.935745312505152e-06, + "loss": 0.4075, + "step": 1578 + }, + { + "epoch": 0.21042110874200426, + "grad_norm": 0.3272979917700737, + "learning_rate": 9.935631479477298e-06, + "loss": 0.4508, + "step": 1579 + }, + { + "epoch": 0.2105543710021322, + "grad_norm": 0.3265961219826092, + "learning_rate": 9.935517546359124e-06, + "loss": 0.4186, + "step": 1580 + }, + { + "epoch": 0.21068763326226012, + "grad_norm": 0.3025379999847494, + "learning_rate": 9.93540351315294e-06, + "loss": 0.4313, + "step": 1581 + }, + { + "epoch": 0.21082089552238806, + "grad_norm": 0.31246081181187907, + "learning_rate": 9.935289379861059e-06, + "loss": 0.4483, + "step": 1582 + }, + { + "epoch": 0.210954157782516, + "grad_norm": 0.3270677525753939, + "learning_rate": 9.935175146485794e-06, + "loss": 0.4742, + "step": 1583 + }, + { + "epoch": 0.21108742004264391, + "grad_norm": 0.320786633071551, + "learning_rate": 9.935060813029462e-06, + "loss": 0.4001, + "step": 1584 + }, + { + "epoch": 0.21122068230277186, + "grad_norm": 0.32638736112499844, + "learning_rate": 9.934946379494382e-06, + "loss": 0.4467, + "step": 1585 + }, + { + "epoch": 0.2113539445628998, + "grad_norm": 0.31284034733470484, + "learning_rate": 9.934831845882875e-06, + "loss": 0.3797, + "step": 1586 + }, + { + "epoch": 0.2114872068230277, + "grad_norm": 0.2953710266574236, + "learning_rate": 9.934717212197262e-06, + "loss": 0.4555, + "step": 1587 + }, + { + "epoch": 0.21162046908315565, + "grad_norm": 0.3608015361692789, + "learning_rate": 9.93460247843987e-06, + "loss": 0.4585, + "step": 1588 + }, + { + "epoch": 0.21175373134328357, + "grad_norm": 0.2856084093032672, + "learning_rate": 9.934487644613024e-06, + "loss": 0.413, + "step": 1589 + }, + { + "epoch": 0.2118869936034115, + "grad_norm": 0.31253107860303536, + "learning_rate": 9.934372710719053e-06, + "loss": 0.3904, + "step": 1590 + }, + { + "epoch": 0.21202025586353945, + "grad_norm": 0.2966810413517957, + "learning_rate": 9.93425767676029e-06, + "loss": 0.3963, + "step": 1591 + }, + { + "epoch": 0.21215351812366737, + "grad_norm": 0.3210393664116903, + "learning_rate": 9.934142542739063e-06, + "loss": 0.439, + "step": 1592 + }, + { + "epoch": 0.2122867803837953, + "grad_norm": 0.33984044313655876, + "learning_rate": 9.934027308657712e-06, + "loss": 0.5133, + "step": 1593 + }, + { + "epoch": 0.21242004264392325, + "grad_norm": 0.30697479998864297, + "learning_rate": 9.93391197451857e-06, + "loss": 0.3619, + "step": 1594 + }, + { + "epoch": 0.21255330490405117, + "grad_norm": 0.307012730598184, + "learning_rate": 9.933796540323976e-06, + "loss": 0.4291, + "step": 1595 + }, + { + "epoch": 0.2126865671641791, + "grad_norm": 0.3143247143719272, + "learning_rate": 9.933681006076276e-06, + "loss": 0.3865, + "step": 1596 + }, + { + "epoch": 0.21281982942430705, + "grad_norm": 0.30655533169021415, + "learning_rate": 9.933565371777807e-06, + "loss": 0.4089, + "step": 1597 + }, + { + "epoch": 0.21295309168443496, + "grad_norm": 0.33312050536881466, + "learning_rate": 9.933449637430917e-06, + "loss": 0.499, + "step": 1598 + }, + { + "epoch": 0.2130863539445629, + "grad_norm": 0.3113018237835377, + "learning_rate": 9.93333380303795e-06, + "loss": 0.388, + "step": 1599 + }, + { + "epoch": 0.21321961620469082, + "grad_norm": 0.30933864843818865, + "learning_rate": 9.933217868601259e-06, + "loss": 0.4715, + "step": 1600 + }, + { + "epoch": 0.21335287846481876, + "grad_norm": 0.3172346944603029, + "learning_rate": 9.933101834123192e-06, + "loss": 0.4009, + "step": 1601 + }, + { + "epoch": 0.2134861407249467, + "grad_norm": 0.329192610825392, + "learning_rate": 9.932985699606104e-06, + "loss": 0.5116, + "step": 1602 + }, + { + "epoch": 0.21361940298507462, + "grad_norm": 0.32102714330800186, + "learning_rate": 9.93286946505235e-06, + "loss": 0.3818, + "step": 1603 + }, + { + "epoch": 0.21375266524520256, + "grad_norm": 0.3455306458169411, + "learning_rate": 9.932753130464286e-06, + "loss": 0.4332, + "step": 1604 + }, + { + "epoch": 0.2138859275053305, + "grad_norm": 0.3245204393212757, + "learning_rate": 9.932636695844272e-06, + "loss": 0.4616, + "step": 1605 + }, + { + "epoch": 0.21401918976545842, + "grad_norm": 0.349775797621194, + "learning_rate": 9.932520161194668e-06, + "loss": 0.3976, + "step": 1606 + }, + { + "epoch": 0.21415245202558636, + "grad_norm": 0.3297970044509201, + "learning_rate": 9.932403526517838e-06, + "loss": 0.4475, + "step": 1607 + }, + { + "epoch": 0.21428571428571427, + "grad_norm": 5.0772695440282805, + "learning_rate": 9.932286791816148e-06, + "loss": 0.4414, + "step": 1608 + }, + { + "epoch": 0.21441897654584222, + "grad_norm": 0.4375106379098926, + "learning_rate": 9.932169957091965e-06, + "loss": 0.4185, + "step": 1609 + }, + { + "epoch": 0.21455223880597016, + "grad_norm": 0.3221714159713808, + "learning_rate": 9.932053022347657e-06, + "loss": 0.4119, + "step": 1610 + }, + { + "epoch": 0.21468550106609807, + "grad_norm": 0.4522424583623967, + "learning_rate": 9.931935987585596e-06, + "loss": 0.4605, + "step": 1611 + }, + { + "epoch": 0.21481876332622601, + "grad_norm": 0.36164474101634486, + "learning_rate": 9.931818852808156e-06, + "loss": 0.389, + "step": 1612 + }, + { + "epoch": 0.21495202558635396, + "grad_norm": 0.3651327033101048, + "learning_rate": 9.931701618017715e-06, + "loss": 0.3942, + "step": 1613 + }, + { + "epoch": 0.21508528784648187, + "grad_norm": 0.3581474297408109, + "learning_rate": 9.931584283216645e-06, + "loss": 0.4456, + "step": 1614 + }, + { + "epoch": 0.2152185501066098, + "grad_norm": 0.34887282604476677, + "learning_rate": 9.931466848407328e-06, + "loss": 0.3895, + "step": 1615 + }, + { + "epoch": 0.21535181236673773, + "grad_norm": 0.3402970120030782, + "learning_rate": 9.931349313592144e-06, + "loss": 0.3745, + "step": 1616 + }, + { + "epoch": 0.21548507462686567, + "grad_norm": 0.3839315983832731, + "learning_rate": 9.931231678773478e-06, + "loss": 0.4946, + "step": 1617 + }, + { + "epoch": 0.2156183368869936, + "grad_norm": 0.3530957471471906, + "learning_rate": 9.931113943953718e-06, + "loss": 0.4201, + "step": 1618 + }, + { + "epoch": 0.21575159914712153, + "grad_norm": 0.3852995130176989, + "learning_rate": 9.930996109135246e-06, + "loss": 0.4106, + "step": 1619 + }, + { + "epoch": 0.21588486140724947, + "grad_norm": 0.41200800375550917, + "learning_rate": 9.930878174320458e-06, + "loss": 0.5057, + "step": 1620 + }, + { + "epoch": 0.2160181236673774, + "grad_norm": 0.3288959837528769, + "learning_rate": 9.93076013951174e-06, + "loss": 0.4517, + "step": 1621 + }, + { + "epoch": 0.21615138592750532, + "grad_norm": 0.3734307387635185, + "learning_rate": 9.930642004711488e-06, + "loss": 0.3852, + "step": 1622 + }, + { + "epoch": 0.21628464818763327, + "grad_norm": 0.31987250008347534, + "learning_rate": 9.930523769922095e-06, + "loss": 0.4373, + "step": 1623 + }, + { + "epoch": 0.21641791044776118, + "grad_norm": 0.35523687770296597, + "learning_rate": 9.930405435145964e-06, + "loss": 0.4313, + "step": 1624 + }, + { + "epoch": 0.21655117270788912, + "grad_norm": 0.31257286194862577, + "learning_rate": 9.930287000385493e-06, + "loss": 0.3848, + "step": 1625 + }, + { + "epoch": 0.21668443496801706, + "grad_norm": 0.3427028309112161, + "learning_rate": 9.93016846564308e-06, + "loss": 0.5831, + "step": 1626 + }, + { + "epoch": 0.21681769722814498, + "grad_norm": 0.3318930243361615, + "learning_rate": 9.930049830921134e-06, + "loss": 0.4477, + "step": 1627 + }, + { + "epoch": 0.21695095948827292, + "grad_norm": 0.31797593841091765, + "learning_rate": 9.929931096222056e-06, + "loss": 0.453, + "step": 1628 + }, + { + "epoch": 0.21708422174840086, + "grad_norm": 0.37870518632420125, + "learning_rate": 9.929812261548257e-06, + "loss": 0.4709, + "step": 1629 + }, + { + "epoch": 0.21721748400852878, + "grad_norm": 1.1264126929623401, + "learning_rate": 9.929693326902146e-06, + "loss": 0.431, + "step": 1630 + }, + { + "epoch": 0.21735074626865672, + "grad_norm": 0.34177219877768583, + "learning_rate": 9.929574292286135e-06, + "loss": 0.4509, + "step": 1631 + }, + { + "epoch": 0.21748400852878466, + "grad_norm": 0.3062836757358989, + "learning_rate": 9.929455157702638e-06, + "loss": 0.3756, + "step": 1632 + }, + { + "epoch": 0.21761727078891258, + "grad_norm": 0.33773761961518095, + "learning_rate": 9.929335923154071e-06, + "loss": 0.4255, + "step": 1633 + }, + { + "epoch": 0.21775053304904052, + "grad_norm": 0.3237486479291798, + "learning_rate": 9.92921658864285e-06, + "loss": 0.4073, + "step": 1634 + }, + { + "epoch": 0.21788379530916843, + "grad_norm": 0.33486128119744757, + "learning_rate": 9.929097154171397e-06, + "loss": 0.4581, + "step": 1635 + }, + { + "epoch": 0.21801705756929637, + "grad_norm": 0.3326563246275133, + "learning_rate": 9.928977619742135e-06, + "loss": 0.4165, + "step": 1636 + }, + { + "epoch": 0.21815031982942432, + "grad_norm": 0.33086839979532123, + "learning_rate": 9.928857985357486e-06, + "loss": 0.4398, + "step": 1637 + }, + { + "epoch": 0.21828358208955223, + "grad_norm": 0.3221320428282007, + "learning_rate": 9.928738251019878e-06, + "loss": 0.4816, + "step": 1638 + }, + { + "epoch": 0.21841684434968017, + "grad_norm": 0.34844952258568196, + "learning_rate": 9.928618416731737e-06, + "loss": 0.5148, + "step": 1639 + }, + { + "epoch": 0.21855010660980811, + "grad_norm": 0.7501657589317839, + "learning_rate": 9.928498482495494e-06, + "loss": 0.3981, + "step": 1640 + }, + { + "epoch": 0.21868336886993603, + "grad_norm": 0.3182157475943403, + "learning_rate": 9.92837844831358e-06, + "loss": 0.4347, + "step": 1641 + }, + { + "epoch": 0.21881663113006397, + "grad_norm": 0.3229649161582368, + "learning_rate": 9.928258314188433e-06, + "loss": 0.4648, + "step": 1642 + }, + { + "epoch": 0.21894989339019189, + "grad_norm": 0.3126481378008185, + "learning_rate": 9.928138080122484e-06, + "loss": 0.4604, + "step": 1643 + }, + { + "epoch": 0.21908315565031983, + "grad_norm": 0.3173047734875841, + "learning_rate": 9.928017746118177e-06, + "loss": 0.4951, + "step": 1644 + }, + { + "epoch": 0.21921641791044777, + "grad_norm": 0.3200050460032527, + "learning_rate": 9.927897312177947e-06, + "loss": 0.4218, + "step": 1645 + }, + { + "epoch": 0.21934968017057568, + "grad_norm": 0.32008434127513036, + "learning_rate": 9.92777677830424e-06, + "loss": 0.3823, + "step": 1646 + }, + { + "epoch": 0.21948294243070363, + "grad_norm": 0.3207411498001186, + "learning_rate": 9.927656144499497e-06, + "loss": 0.4075, + "step": 1647 + }, + { + "epoch": 0.21961620469083157, + "grad_norm": 0.32882196359526483, + "learning_rate": 9.927535410766166e-06, + "loss": 0.4686, + "step": 1648 + }, + { + "epoch": 0.21974946695095948, + "grad_norm": 0.3233793376843228, + "learning_rate": 9.927414577106697e-06, + "loss": 0.4201, + "step": 1649 + }, + { + "epoch": 0.21988272921108742, + "grad_norm": 0.32488050542716135, + "learning_rate": 9.927293643523539e-06, + "loss": 0.4865, + "step": 1650 + }, + { + "epoch": 0.22001599147121534, + "grad_norm": 0.32593787533584617, + "learning_rate": 9.927172610019143e-06, + "loss": 0.5355, + "step": 1651 + }, + { + "epoch": 0.22014925373134328, + "grad_norm": 0.3127404331110776, + "learning_rate": 9.927051476595966e-06, + "loss": 0.4981, + "step": 1652 + }, + { + "epoch": 0.22028251599147122, + "grad_norm": 0.32670003466934405, + "learning_rate": 9.926930243256463e-06, + "loss": 0.4642, + "step": 1653 + }, + { + "epoch": 0.22041577825159914, + "grad_norm": 0.33128990814195064, + "learning_rate": 9.926808910003092e-06, + "loss": 0.4192, + "step": 1654 + }, + { + "epoch": 0.22054904051172708, + "grad_norm": 0.32446652813749316, + "learning_rate": 9.926687476838315e-06, + "loss": 0.4474, + "step": 1655 + }, + { + "epoch": 0.22068230277185502, + "grad_norm": 0.33147583677212855, + "learning_rate": 9.926565943764593e-06, + "loss": 0.5382, + "step": 1656 + }, + { + "epoch": 0.22081556503198294, + "grad_norm": 0.3045014495630583, + "learning_rate": 9.926444310784394e-06, + "loss": 0.3713, + "step": 1657 + }, + { + "epoch": 0.22094882729211088, + "grad_norm": 0.32419486539867703, + "learning_rate": 9.926322577900179e-06, + "loss": 0.5025, + "step": 1658 + }, + { + "epoch": 0.22108208955223882, + "grad_norm": 0.3059143049011025, + "learning_rate": 9.926200745114421e-06, + "loss": 0.4497, + "step": 1659 + }, + { + "epoch": 0.22121535181236673, + "grad_norm": 0.38210525311013577, + "learning_rate": 9.92607881242959e-06, + "loss": 0.4034, + "step": 1660 + }, + { + "epoch": 0.22134861407249468, + "grad_norm": 0.31597482015188255, + "learning_rate": 9.925956779848156e-06, + "loss": 0.3569, + "step": 1661 + }, + { + "epoch": 0.2214818763326226, + "grad_norm": 0.3439221921649674, + "learning_rate": 9.925834647372598e-06, + "loss": 0.4486, + "step": 1662 + }, + { + "epoch": 0.22161513859275053, + "grad_norm": 0.31969001250903833, + "learning_rate": 9.92571241500539e-06, + "loss": 0.3878, + "step": 1663 + }, + { + "epoch": 0.22174840085287847, + "grad_norm": 0.3129919403614523, + "learning_rate": 9.92559008274901e-06, + "loss": 0.4973, + "step": 1664 + }, + { + "epoch": 0.2218816631130064, + "grad_norm": 0.31786104011871624, + "learning_rate": 9.925467650605942e-06, + "loss": 0.375, + "step": 1665 + }, + { + "epoch": 0.22201492537313433, + "grad_norm": 0.3143028066765632, + "learning_rate": 9.925345118578666e-06, + "loss": 0.4545, + "step": 1666 + }, + { + "epoch": 0.22214818763326227, + "grad_norm": 0.3099182882565111, + "learning_rate": 9.925222486669668e-06, + "loss": 0.4666, + "step": 1667 + }, + { + "epoch": 0.2222814498933902, + "grad_norm": 0.30525694646945584, + "learning_rate": 9.925099754881432e-06, + "loss": 0.3685, + "step": 1668 + }, + { + "epoch": 0.22241471215351813, + "grad_norm": 0.3162436420313744, + "learning_rate": 9.924976923216454e-06, + "loss": 0.414, + "step": 1669 + }, + { + "epoch": 0.22254797441364604, + "grad_norm": 0.302903896979126, + "learning_rate": 9.924853991677218e-06, + "loss": 0.4631, + "step": 1670 + }, + { + "epoch": 0.22268123667377399, + "grad_norm": 1.1732895536977987, + "learning_rate": 9.92473096026622e-06, + "loss": 0.4908, + "step": 1671 + }, + { + "epoch": 0.22281449893390193, + "grad_norm": 0.3298572880872473, + "learning_rate": 9.924607828985954e-06, + "loss": 0.3931, + "step": 1672 + }, + { + "epoch": 0.22294776119402984, + "grad_norm": 0.31178362049704744, + "learning_rate": 9.924484597838918e-06, + "loss": 0.4331, + "step": 1673 + }, + { + "epoch": 0.22308102345415778, + "grad_norm": 0.3238395522679948, + "learning_rate": 9.924361266827609e-06, + "loss": 0.3587, + "step": 1674 + }, + { + "epoch": 0.22321428571428573, + "grad_norm": 0.3234909891584917, + "learning_rate": 9.92423783595453e-06, + "loss": 0.4605, + "step": 1675 + }, + { + "epoch": 0.22334754797441364, + "grad_norm": 0.33154055385413367, + "learning_rate": 9.924114305222184e-06, + "loss": 0.4161, + "step": 1676 + }, + { + "epoch": 0.22348081023454158, + "grad_norm": 0.3249753814956817, + "learning_rate": 9.923990674633075e-06, + "loss": 0.4176, + "step": 1677 + }, + { + "epoch": 0.2236140724946695, + "grad_norm": 0.31410433856287745, + "learning_rate": 9.92386694418971e-06, + "loss": 0.4017, + "step": 1678 + }, + { + "epoch": 0.22374733475479744, + "grad_norm": 0.3057554369195124, + "learning_rate": 9.9237431138946e-06, + "loss": 0.4255, + "step": 1679 + }, + { + "epoch": 0.22388059701492538, + "grad_norm": 0.33119353713317073, + "learning_rate": 9.923619183750255e-06, + "loss": 0.5761, + "step": 1680 + }, + { + "epoch": 0.2240138592750533, + "grad_norm": 0.324994826059965, + "learning_rate": 9.923495153759188e-06, + "loss": 0.4675, + "step": 1681 + }, + { + "epoch": 0.22414712153518124, + "grad_norm": 0.3382319687779073, + "learning_rate": 9.923371023923913e-06, + "loss": 0.5274, + "step": 1682 + }, + { + "epoch": 0.22428038379530918, + "grad_norm": 0.3130557873006724, + "learning_rate": 9.92324679424695e-06, + "loss": 0.3918, + "step": 1683 + }, + { + "epoch": 0.2244136460554371, + "grad_norm": 0.3471968966040274, + "learning_rate": 9.923122464730817e-06, + "loss": 0.4586, + "step": 1684 + }, + { + "epoch": 0.22454690831556504, + "grad_norm": 0.3332424340851516, + "learning_rate": 9.922998035378034e-06, + "loss": 0.4357, + "step": 1685 + }, + { + "epoch": 0.22468017057569295, + "grad_norm": 0.3265209463701874, + "learning_rate": 9.922873506191127e-06, + "loss": 0.4157, + "step": 1686 + }, + { + "epoch": 0.2248134328358209, + "grad_norm": 0.31479307189479044, + "learning_rate": 9.92274887717262e-06, + "loss": 0.3514, + "step": 1687 + }, + { + "epoch": 0.22494669509594883, + "grad_norm": 0.34145804405894575, + "learning_rate": 9.92262414832504e-06, + "loss": 0.4249, + "step": 1688 + }, + { + "epoch": 0.22507995735607675, + "grad_norm": 0.31842691024205905, + "learning_rate": 9.922499319650916e-06, + "loss": 0.4609, + "step": 1689 + }, + { + "epoch": 0.2252132196162047, + "grad_norm": 0.32434298256291816, + "learning_rate": 9.92237439115278e-06, + "loss": 0.4907, + "step": 1690 + }, + { + "epoch": 0.22534648187633263, + "grad_norm": 0.323783241586855, + "learning_rate": 9.922249362833167e-06, + "loss": 0.4443, + "step": 1691 + }, + { + "epoch": 0.22547974413646055, + "grad_norm": 0.3306976314360106, + "learning_rate": 9.92212423469461e-06, + "loss": 0.4243, + "step": 1692 + }, + { + "epoch": 0.2256130063965885, + "grad_norm": 0.3564026355258888, + "learning_rate": 9.921999006739646e-06, + "loss": 0.4406, + "step": 1693 + }, + { + "epoch": 0.22574626865671643, + "grad_norm": 0.33375194710286665, + "learning_rate": 9.92187367897082e-06, + "loss": 0.4402, + "step": 1694 + }, + { + "epoch": 0.22587953091684435, + "grad_norm": 0.32383725054471235, + "learning_rate": 9.921748251390666e-06, + "loss": 0.4081, + "step": 1695 + }, + { + "epoch": 0.2260127931769723, + "grad_norm": 0.3729833101395897, + "learning_rate": 9.921622724001732e-06, + "loss": 0.4644, + "step": 1696 + }, + { + "epoch": 0.2261460554371002, + "grad_norm": 0.3092617048912589, + "learning_rate": 9.921497096806562e-06, + "loss": 0.4449, + "step": 1697 + }, + { + "epoch": 0.22627931769722814, + "grad_norm": 0.3497177002379297, + "learning_rate": 9.921371369807705e-06, + "loss": 0.4644, + "step": 1698 + }, + { + "epoch": 0.22641257995735609, + "grad_norm": 0.341272202741915, + "learning_rate": 9.921245543007709e-06, + "loss": 0.4282, + "step": 1699 + }, + { + "epoch": 0.226545842217484, + "grad_norm": 0.3341325732785523, + "learning_rate": 9.921119616409128e-06, + "loss": 0.4628, + "step": 1700 + }, + { + "epoch": 0.22667910447761194, + "grad_norm": 0.3381509175325218, + "learning_rate": 9.920993590014514e-06, + "loss": 0.467, + "step": 1701 + }, + { + "epoch": 0.22681236673773988, + "grad_norm": 0.31952907246958223, + "learning_rate": 9.920867463826423e-06, + "loss": 0.3895, + "step": 1702 + }, + { + "epoch": 0.2269456289978678, + "grad_norm": 0.32329795329637245, + "learning_rate": 9.920741237847413e-06, + "loss": 0.3983, + "step": 1703 + }, + { + "epoch": 0.22707889125799574, + "grad_norm": 0.35778539656892844, + "learning_rate": 9.920614912080042e-06, + "loss": 0.4704, + "step": 1704 + }, + { + "epoch": 0.22721215351812366, + "grad_norm": 0.3266368780093762, + "learning_rate": 9.920488486526873e-06, + "loss": 0.4361, + "step": 1705 + }, + { + "epoch": 0.2273454157782516, + "grad_norm": 0.3254791352983438, + "learning_rate": 9.920361961190472e-06, + "loss": 0.4829, + "step": 1706 + }, + { + "epoch": 0.22747867803837954, + "grad_norm": 0.34048544440113243, + "learning_rate": 9.920235336073401e-06, + "loss": 0.4592, + "step": 1707 + }, + { + "epoch": 0.22761194029850745, + "grad_norm": 0.33344593546550383, + "learning_rate": 9.920108611178231e-06, + "loss": 0.3712, + "step": 1708 + }, + { + "epoch": 0.2277452025586354, + "grad_norm": 0.32592145765630787, + "learning_rate": 9.919981786507532e-06, + "loss": 0.3807, + "step": 1709 + }, + { + "epoch": 0.22787846481876334, + "grad_norm": 0.3154639620913526, + "learning_rate": 9.919854862063871e-06, + "loss": 0.4428, + "step": 1710 + }, + { + "epoch": 0.22801172707889125, + "grad_norm": 0.3302460779307013, + "learning_rate": 9.919727837849826e-06, + "loss": 0.4494, + "step": 1711 + }, + { + "epoch": 0.2281449893390192, + "grad_norm": 0.35199966443208974, + "learning_rate": 9.919600713867974e-06, + "loss": 0.5016, + "step": 1712 + }, + { + "epoch": 0.2282782515991471, + "grad_norm": 0.3332539079231311, + "learning_rate": 9.91947349012089e-06, + "loss": 0.4983, + "step": 1713 + }, + { + "epoch": 0.22841151385927505, + "grad_norm": 0.3479177896689341, + "learning_rate": 9.919346166611156e-06, + "loss": 0.4166, + "step": 1714 + }, + { + "epoch": 0.228544776119403, + "grad_norm": 0.3289307819310567, + "learning_rate": 9.919218743341353e-06, + "loss": 0.3861, + "step": 1715 + }, + { + "epoch": 0.2286780383795309, + "grad_norm": 0.3190840562739228, + "learning_rate": 9.919091220314066e-06, + "loss": 0.3803, + "step": 1716 + }, + { + "epoch": 0.22881130063965885, + "grad_norm": 0.33991297874152365, + "learning_rate": 9.91896359753188e-06, + "loss": 0.4624, + "step": 1717 + }, + { + "epoch": 0.2289445628997868, + "grad_norm": 0.30222846571214373, + "learning_rate": 9.918835874997384e-06, + "loss": 0.3905, + "step": 1718 + }, + { + "epoch": 0.2290778251599147, + "grad_norm": 0.3097349348191891, + "learning_rate": 9.918708052713165e-06, + "loss": 0.3791, + "step": 1719 + }, + { + "epoch": 0.22921108742004265, + "grad_norm": 0.32728683643463674, + "learning_rate": 9.918580130681819e-06, + "loss": 0.415, + "step": 1720 + }, + { + "epoch": 0.2293443496801706, + "grad_norm": 0.31386176408908917, + "learning_rate": 9.91845210890594e-06, + "loss": 0.4432, + "step": 1721 + }, + { + "epoch": 0.2294776119402985, + "grad_norm": 0.3678320775055359, + "learning_rate": 9.918323987388122e-06, + "loss": 0.4552, + "step": 1722 + }, + { + "epoch": 0.22961087420042645, + "grad_norm": 0.3352777058312181, + "learning_rate": 9.918195766130964e-06, + "loss": 0.5013, + "step": 1723 + }, + { + "epoch": 0.22974413646055436, + "grad_norm": 0.30843973035337946, + "learning_rate": 9.918067445137068e-06, + "loss": 0.4107, + "step": 1724 + }, + { + "epoch": 0.2298773987206823, + "grad_norm": 0.31113329948595186, + "learning_rate": 9.917939024409034e-06, + "loss": 0.4467, + "step": 1725 + }, + { + "epoch": 0.23001066098081024, + "grad_norm": 0.3103022302644601, + "learning_rate": 9.917810503949466e-06, + "loss": 0.4597, + "step": 1726 + }, + { + "epoch": 0.23014392324093816, + "grad_norm": 0.30874546334841857, + "learning_rate": 9.91768188376097e-06, + "loss": 0.354, + "step": 1727 + }, + { + "epoch": 0.2302771855010661, + "grad_norm": 0.3114082993327775, + "learning_rate": 9.917553163846158e-06, + "loss": 0.4872, + "step": 1728 + }, + { + "epoch": 0.23041044776119404, + "grad_norm": 0.32762535239765017, + "learning_rate": 9.917424344207635e-06, + "loss": 0.4625, + "step": 1729 + }, + { + "epoch": 0.23054371002132196, + "grad_norm": 0.3116474947099396, + "learning_rate": 9.917295424848018e-06, + "loss": 0.3761, + "step": 1730 + }, + { + "epoch": 0.2306769722814499, + "grad_norm": 0.31785418302376073, + "learning_rate": 9.91716640576992e-06, + "loss": 0.4704, + "step": 1731 + }, + { + "epoch": 0.2308102345415778, + "grad_norm": 0.3086406856967, + "learning_rate": 9.917037286975956e-06, + "loss": 0.4127, + "step": 1732 + }, + { + "epoch": 0.23094349680170576, + "grad_norm": 0.31016982361609646, + "learning_rate": 9.916908068468746e-06, + "loss": 0.4209, + "step": 1733 + }, + { + "epoch": 0.2310767590618337, + "grad_norm": 0.3066868734376978, + "learning_rate": 9.916778750250911e-06, + "loss": 0.3758, + "step": 1734 + }, + { + "epoch": 0.2312100213219616, + "grad_norm": 0.31482224021280375, + "learning_rate": 9.91664933232507e-06, + "loss": 0.4831, + "step": 1735 + }, + { + "epoch": 0.23134328358208955, + "grad_norm": 0.3286869930070689, + "learning_rate": 9.916519814693852e-06, + "loss": 0.4454, + "step": 1736 + }, + { + "epoch": 0.2314765458422175, + "grad_norm": 0.3240059783078954, + "learning_rate": 9.91639019735988e-06, + "loss": 0.427, + "step": 1737 + }, + { + "epoch": 0.2316098081023454, + "grad_norm": 0.35299809138768173, + "learning_rate": 9.916260480325782e-06, + "loss": 0.4853, + "step": 1738 + }, + { + "epoch": 0.23174307036247335, + "grad_norm": 0.3378475216299161, + "learning_rate": 9.916130663594192e-06, + "loss": 0.4428, + "step": 1739 + }, + { + "epoch": 0.23187633262260127, + "grad_norm": 0.30247851415788835, + "learning_rate": 9.91600074716774e-06, + "loss": 0.3836, + "step": 1740 + }, + { + "epoch": 0.2320095948827292, + "grad_norm": 0.49629537423260883, + "learning_rate": 9.915870731049064e-06, + "loss": 0.5383, + "step": 1741 + }, + { + "epoch": 0.23214285714285715, + "grad_norm": 0.3306085904048949, + "learning_rate": 9.915740615240796e-06, + "loss": 0.5176, + "step": 1742 + }, + { + "epoch": 0.23227611940298507, + "grad_norm": 0.31811859271933035, + "learning_rate": 9.915610399745576e-06, + "loss": 0.4355, + "step": 1743 + }, + { + "epoch": 0.232409381663113, + "grad_norm": 0.33458749171185664, + "learning_rate": 9.915480084566047e-06, + "loss": 0.4252, + "step": 1744 + }, + { + "epoch": 0.23254264392324095, + "grad_norm": 0.31891412714415546, + "learning_rate": 9.91534966970485e-06, + "loss": 0.4191, + "step": 1745 + }, + { + "epoch": 0.23267590618336886, + "grad_norm": 0.3118178115038547, + "learning_rate": 9.91521915516463e-06, + "loss": 0.4785, + "step": 1746 + }, + { + "epoch": 0.2328091684434968, + "grad_norm": 0.31758512683185763, + "learning_rate": 9.915088540948032e-06, + "loss": 0.4382, + "step": 1747 + }, + { + "epoch": 0.23294243070362472, + "grad_norm": 0.30137764031490283, + "learning_rate": 9.914957827057708e-06, + "loss": 0.3561, + "step": 1748 + }, + { + "epoch": 0.23307569296375266, + "grad_norm": 0.3220836301735662, + "learning_rate": 9.914827013496304e-06, + "loss": 0.4789, + "step": 1749 + }, + { + "epoch": 0.2332089552238806, + "grad_norm": 0.32355816078053506, + "learning_rate": 9.914696100266479e-06, + "loss": 0.3737, + "step": 1750 + }, + { + "epoch": 0.23334221748400852, + "grad_norm": 0.32742074239931124, + "learning_rate": 9.914565087370882e-06, + "loss": 0.4662, + "step": 1751 + }, + { + "epoch": 0.23347547974413646, + "grad_norm": 0.31700113008600045, + "learning_rate": 9.914433974812175e-06, + "loss": 0.4002, + "step": 1752 + }, + { + "epoch": 0.2336087420042644, + "grad_norm": 0.3303833366360522, + "learning_rate": 9.914302762593013e-06, + "loss": 0.4642, + "step": 1753 + }, + { + "epoch": 0.23374200426439232, + "grad_norm": 0.3191988744220921, + "learning_rate": 9.914171450716057e-06, + "loss": 0.4912, + "step": 1754 + }, + { + "epoch": 0.23387526652452026, + "grad_norm": 0.3194132054141338, + "learning_rate": 9.914040039183973e-06, + "loss": 0.3741, + "step": 1755 + }, + { + "epoch": 0.2340085287846482, + "grad_norm": 0.3248303334072788, + "learning_rate": 9.913908527999423e-06, + "loss": 0.4199, + "step": 1756 + }, + { + "epoch": 0.23414179104477612, + "grad_norm": 0.29765468200791423, + "learning_rate": 9.913776917165074e-06, + "loss": 0.4604, + "step": 1757 + }, + { + "epoch": 0.23427505330490406, + "grad_norm": 0.3341280275469785, + "learning_rate": 9.913645206683597e-06, + "loss": 0.5929, + "step": 1758 + }, + { + "epoch": 0.23440831556503197, + "grad_norm": 0.31576905300014685, + "learning_rate": 9.913513396557663e-06, + "loss": 0.3423, + "step": 1759 + }, + { + "epoch": 0.2345415778251599, + "grad_norm": 0.32598961685163097, + "learning_rate": 9.913381486789942e-06, + "loss": 0.4376, + "step": 1760 + }, + { + "epoch": 0.23467484008528786, + "grad_norm": 0.32628724435942263, + "learning_rate": 9.913249477383111e-06, + "loss": 0.4258, + "step": 1761 + }, + { + "epoch": 0.23480810234541577, + "grad_norm": 0.3073513825659177, + "learning_rate": 9.913117368339846e-06, + "loss": 0.4356, + "step": 1762 + }, + { + "epoch": 0.2349413646055437, + "grad_norm": 0.3472763022001595, + "learning_rate": 9.91298515966283e-06, + "loss": 0.4261, + "step": 1763 + }, + { + "epoch": 0.23507462686567165, + "grad_norm": 0.3129386282060543, + "learning_rate": 9.912852851354738e-06, + "loss": 0.3904, + "step": 1764 + }, + { + "epoch": 0.23520788912579957, + "grad_norm": 0.3349168718028577, + "learning_rate": 9.912720443418255e-06, + "loss": 0.6681, + "step": 1765 + }, + { + "epoch": 0.2353411513859275, + "grad_norm": 0.34047282680866026, + "learning_rate": 9.912587935856071e-06, + "loss": 0.4442, + "step": 1766 + }, + { + "epoch": 0.23547441364605542, + "grad_norm": 0.33459733833754457, + "learning_rate": 9.912455328670866e-06, + "loss": 0.4509, + "step": 1767 + }, + { + "epoch": 0.23560767590618337, + "grad_norm": 0.32131747956858697, + "learning_rate": 9.912322621865335e-06, + "loss": 0.3795, + "step": 1768 + }, + { + "epoch": 0.2357409381663113, + "grad_norm": 0.31479126263407275, + "learning_rate": 9.912189815442165e-06, + "loss": 0.4072, + "step": 1769 + }, + { + "epoch": 0.23587420042643922, + "grad_norm": 0.3334167716266694, + "learning_rate": 9.912056909404051e-06, + "loss": 0.4162, + "step": 1770 + }, + { + "epoch": 0.23600746268656717, + "grad_norm": 0.32298135194743793, + "learning_rate": 9.911923903753689e-06, + "loss": 0.3942, + "step": 1771 + }, + { + "epoch": 0.2361407249466951, + "grad_norm": 0.31215178675940874, + "learning_rate": 9.911790798493775e-06, + "loss": 0.3919, + "step": 1772 + }, + { + "epoch": 0.23627398720682302, + "grad_norm": 0.3200746215722332, + "learning_rate": 9.91165759362701e-06, + "loss": 0.4429, + "step": 1773 + }, + { + "epoch": 0.23640724946695096, + "grad_norm": 0.32092316857511904, + "learning_rate": 9.911524289156091e-06, + "loss": 0.3621, + "step": 1774 + }, + { + "epoch": 0.23654051172707888, + "grad_norm": 0.3146023881800183, + "learning_rate": 9.911390885083725e-06, + "loss": 0.4097, + "step": 1775 + }, + { + "epoch": 0.23667377398720682, + "grad_norm": 0.3213707876696355, + "learning_rate": 9.911257381412617e-06, + "loss": 0.4278, + "step": 1776 + }, + { + "epoch": 0.23680703624733476, + "grad_norm": 0.3018959994894293, + "learning_rate": 9.911123778145474e-06, + "loss": 0.4465, + "step": 1777 + }, + { + "epoch": 0.23694029850746268, + "grad_norm": 0.33562302122658594, + "learning_rate": 9.910990075285005e-06, + "loss": 0.4189, + "step": 1778 + }, + { + "epoch": 0.23707356076759062, + "grad_norm": 0.3220497624265449, + "learning_rate": 9.910856272833922e-06, + "loss": 0.4705, + "step": 1779 + }, + { + "epoch": 0.23720682302771856, + "grad_norm": 0.30918538131734047, + "learning_rate": 9.910722370794936e-06, + "loss": 0.476, + "step": 1780 + }, + { + "epoch": 0.23734008528784648, + "grad_norm": 0.3121701542782622, + "learning_rate": 9.910588369170765e-06, + "loss": 0.4347, + "step": 1781 + }, + { + "epoch": 0.23747334754797442, + "grad_norm": 0.3088093368537265, + "learning_rate": 9.910454267964128e-06, + "loss": 0.4076, + "step": 1782 + }, + { + "epoch": 0.23760660980810236, + "grad_norm": 0.2936825194877224, + "learning_rate": 9.910320067177741e-06, + "loss": 0.3611, + "step": 1783 + }, + { + "epoch": 0.23773987206823027, + "grad_norm": 0.31150500686932875, + "learning_rate": 9.910185766814327e-06, + "loss": 0.4146, + "step": 1784 + }, + { + "epoch": 0.23787313432835822, + "grad_norm": 0.31172504028998527, + "learning_rate": 9.910051366876608e-06, + "loss": 0.3969, + "step": 1785 + }, + { + "epoch": 0.23800639658848613, + "grad_norm": 0.32622368407876867, + "learning_rate": 9.909916867367312e-06, + "loss": 0.3868, + "step": 1786 + }, + { + "epoch": 0.23813965884861407, + "grad_norm": 0.307248101936004, + "learning_rate": 9.909782268289165e-06, + "loss": 0.4311, + "step": 1787 + }, + { + "epoch": 0.23827292110874201, + "grad_norm": 0.3185773087428083, + "learning_rate": 9.909647569644896e-06, + "loss": 0.4714, + "step": 1788 + }, + { + "epoch": 0.23840618336886993, + "grad_norm": 0.31724579859498697, + "learning_rate": 9.909512771437239e-06, + "loss": 0.3726, + "step": 1789 + }, + { + "epoch": 0.23853944562899787, + "grad_norm": 0.30322444679618255, + "learning_rate": 9.909377873668924e-06, + "loss": 0.3675, + "step": 1790 + }, + { + "epoch": 0.2386727078891258, + "grad_norm": 0.3398983743831398, + "learning_rate": 9.909242876342691e-06, + "loss": 0.4561, + "step": 1791 + }, + { + "epoch": 0.23880597014925373, + "grad_norm": 0.312323037561446, + "learning_rate": 9.909107779461274e-06, + "loss": 0.4587, + "step": 1792 + }, + { + "epoch": 0.23893923240938167, + "grad_norm": 0.3187115069558171, + "learning_rate": 9.908972583027414e-06, + "loss": 0.4298, + "step": 1793 + }, + { + "epoch": 0.23907249466950958, + "grad_norm": 0.3132639044815435, + "learning_rate": 9.90883728704385e-06, + "loss": 0.3756, + "step": 1794 + }, + { + "epoch": 0.23920575692963753, + "grad_norm": 0.32161573101781293, + "learning_rate": 9.908701891513332e-06, + "loss": 0.3946, + "step": 1795 + }, + { + "epoch": 0.23933901918976547, + "grad_norm": 0.33337750124989124, + "learning_rate": 9.9085663964386e-06, + "loss": 0.4302, + "step": 1796 + }, + { + "epoch": 0.23947228144989338, + "grad_norm": 0.3329069171178411, + "learning_rate": 9.908430801822405e-06, + "loss": 0.4342, + "step": 1797 + }, + { + "epoch": 0.23960554371002132, + "grad_norm": 0.35012491023994946, + "learning_rate": 9.908295107667494e-06, + "loss": 0.4593, + "step": 1798 + }, + { + "epoch": 0.23973880597014927, + "grad_norm": 0.3096600138162191, + "learning_rate": 9.90815931397662e-06, + "loss": 0.4864, + "step": 1799 + }, + { + "epoch": 0.23987206823027718, + "grad_norm": 0.3711716040331645, + "learning_rate": 9.908023420752538e-06, + "loss": 0.4019, + "step": 1800 + }, + { + "epoch": 0.24000533049040512, + "grad_norm": 0.335997514652669, + "learning_rate": 9.907887427998001e-06, + "loss": 0.4558, + "step": 1801 + }, + { + "epoch": 0.24013859275053304, + "grad_norm": 0.37302196078935096, + "learning_rate": 9.907751335715772e-06, + "loss": 0.512, + "step": 1802 + }, + { + "epoch": 0.24027185501066098, + "grad_norm": 0.3470370134660976, + "learning_rate": 9.907615143908605e-06, + "loss": 0.5525, + "step": 1803 + }, + { + "epoch": 0.24040511727078892, + "grad_norm": 0.3406979473029221, + "learning_rate": 9.907478852579264e-06, + "loss": 0.3668, + "step": 1804 + }, + { + "epoch": 0.24053837953091683, + "grad_norm": 0.3275505089209379, + "learning_rate": 9.907342461730513e-06, + "loss": 0.4494, + "step": 1805 + }, + { + "epoch": 0.24067164179104478, + "grad_norm": 0.31843955472576824, + "learning_rate": 9.90720597136512e-06, + "loss": 0.4091, + "step": 1806 + }, + { + "epoch": 0.24080490405117272, + "grad_norm": 0.3782266061102013, + "learning_rate": 9.907069381485849e-06, + "loss": 0.4063, + "step": 1807 + }, + { + "epoch": 0.24093816631130063, + "grad_norm": 0.3338994328024839, + "learning_rate": 9.906932692095472e-06, + "loss": 0.4493, + "step": 1808 + }, + { + "epoch": 0.24107142857142858, + "grad_norm": 0.3367197131237818, + "learning_rate": 9.90679590319676e-06, + "loss": 0.481, + "step": 1809 + }, + { + "epoch": 0.2412046908315565, + "grad_norm": 0.3251301358422103, + "learning_rate": 9.906659014792491e-06, + "loss": 0.4167, + "step": 1810 + }, + { + "epoch": 0.24133795309168443, + "grad_norm": 0.31472037313561263, + "learning_rate": 9.906522026885435e-06, + "loss": 0.4361, + "step": 1811 + }, + { + "epoch": 0.24147121535181237, + "grad_norm": 0.3151676832154604, + "learning_rate": 9.906384939478372e-06, + "loss": 0.3744, + "step": 1812 + }, + { + "epoch": 0.2416044776119403, + "grad_norm": 0.3220950808351631, + "learning_rate": 9.906247752574085e-06, + "loss": 0.3712, + "step": 1813 + }, + { + "epoch": 0.24173773987206823, + "grad_norm": 0.35433252945002464, + "learning_rate": 9.906110466175352e-06, + "loss": 0.5946, + "step": 1814 + }, + { + "epoch": 0.24187100213219617, + "grad_norm": 0.3232512690451372, + "learning_rate": 9.905973080284958e-06, + "loss": 0.3914, + "step": 1815 + }, + { + "epoch": 0.2420042643923241, + "grad_norm": 0.31912851357210537, + "learning_rate": 9.905835594905693e-06, + "loss": 0.3925, + "step": 1816 + }, + { + "epoch": 0.24213752665245203, + "grad_norm": 0.31115575758247427, + "learning_rate": 9.90569801004034e-06, + "loss": 0.4418, + "step": 1817 + }, + { + "epoch": 0.24227078891257997, + "grad_norm": 0.3346852356623035, + "learning_rate": 9.905560325691691e-06, + "loss": 0.4142, + "step": 1818 + }, + { + "epoch": 0.24240405117270789, + "grad_norm": 0.31570822213551414, + "learning_rate": 9.905422541862538e-06, + "loss": 0.4242, + "step": 1819 + }, + { + "epoch": 0.24253731343283583, + "grad_norm": 0.3089219616744057, + "learning_rate": 9.905284658555676e-06, + "loss": 0.5243, + "step": 1820 + }, + { + "epoch": 0.24267057569296374, + "grad_norm": 0.32009323129229195, + "learning_rate": 9.9051466757739e-06, + "loss": 0.3979, + "step": 1821 + }, + { + "epoch": 0.24280383795309168, + "grad_norm": 0.30948064733163894, + "learning_rate": 9.905008593520009e-06, + "loss": 0.4434, + "step": 1822 + }, + { + "epoch": 0.24293710021321963, + "grad_norm": 0.3238674163542033, + "learning_rate": 9.904870411796802e-06, + "loss": 0.4249, + "step": 1823 + }, + { + "epoch": 0.24307036247334754, + "grad_norm": 0.32881060789117705, + "learning_rate": 9.904732130607083e-06, + "loss": 0.4921, + "step": 1824 + }, + { + "epoch": 0.24320362473347548, + "grad_norm": 0.3284541559430794, + "learning_rate": 9.904593749953655e-06, + "loss": 0.4372, + "step": 1825 + }, + { + "epoch": 0.24333688699360342, + "grad_norm": 0.31623514735127056, + "learning_rate": 9.904455269839323e-06, + "loss": 0.5038, + "step": 1826 + }, + { + "epoch": 0.24347014925373134, + "grad_norm": 0.3296213236977238, + "learning_rate": 9.9043166902669e-06, + "loss": 0.4629, + "step": 1827 + }, + { + "epoch": 0.24360341151385928, + "grad_norm": 0.33156207050676395, + "learning_rate": 9.90417801123919e-06, + "loss": 0.4418, + "step": 1828 + }, + { + "epoch": 0.2437366737739872, + "grad_norm": 0.309506069691363, + "learning_rate": 9.904039232759008e-06, + "loss": 0.4529, + "step": 1829 + }, + { + "epoch": 0.24386993603411514, + "grad_norm": 0.3219419165404468, + "learning_rate": 9.903900354829171e-06, + "loss": 0.4363, + "step": 1830 + }, + { + "epoch": 0.24400319829424308, + "grad_norm": 0.2935345195591931, + "learning_rate": 9.903761377452493e-06, + "loss": 0.3822, + "step": 1831 + }, + { + "epoch": 0.244136460554371, + "grad_norm": 0.31783988662072105, + "learning_rate": 9.90362230063179e-06, + "loss": 0.4384, + "step": 1832 + }, + { + "epoch": 0.24426972281449894, + "grad_norm": 0.3277773382362167, + "learning_rate": 9.903483124369886e-06, + "loss": 0.3688, + "step": 1833 + }, + { + "epoch": 0.24440298507462688, + "grad_norm": 0.29660947158653533, + "learning_rate": 9.903343848669603e-06, + "loss": 0.4427, + "step": 1834 + }, + { + "epoch": 0.2445362473347548, + "grad_norm": 0.33214012841838536, + "learning_rate": 9.903204473533762e-06, + "loss": 0.4076, + "step": 1835 + }, + { + "epoch": 0.24466950959488273, + "grad_norm": 0.31262382331903193, + "learning_rate": 9.903064998965193e-06, + "loss": 0.4217, + "step": 1836 + }, + { + "epoch": 0.24480277185501065, + "grad_norm": 0.3121914398523251, + "learning_rate": 9.902925424966723e-06, + "loss": 0.4488, + "step": 1837 + }, + { + "epoch": 0.2449360341151386, + "grad_norm": 0.312499471115007, + "learning_rate": 9.902785751541182e-06, + "loss": 0.4442, + "step": 1838 + }, + { + "epoch": 0.24506929637526653, + "grad_norm": 0.3079892038211947, + "learning_rate": 9.902645978691404e-06, + "loss": 0.421, + "step": 1839 + }, + { + "epoch": 0.24520255863539445, + "grad_norm": 0.32426527633196917, + "learning_rate": 9.902506106420222e-06, + "loss": 0.4085, + "step": 1840 + }, + { + "epoch": 0.2453358208955224, + "grad_norm": 0.2946915327224865, + "learning_rate": 9.902366134730474e-06, + "loss": 0.4106, + "step": 1841 + }, + { + "epoch": 0.24546908315565033, + "grad_norm": 0.31504980005034466, + "learning_rate": 9.902226063624998e-06, + "loss": 0.3896, + "step": 1842 + }, + { + "epoch": 0.24560234541577824, + "grad_norm": 0.30817891542591935, + "learning_rate": 9.902085893106632e-06, + "loss": 0.4391, + "step": 1843 + }, + { + "epoch": 0.2457356076759062, + "grad_norm": 0.3156720191240934, + "learning_rate": 9.901945623178222e-06, + "loss": 0.4398, + "step": 1844 + }, + { + "epoch": 0.24586886993603413, + "grad_norm": 0.42005489735758894, + "learning_rate": 9.90180525384261e-06, + "loss": 0.4774, + "step": 1845 + }, + { + "epoch": 0.24600213219616204, + "grad_norm": 0.32223514740698556, + "learning_rate": 9.901664785102647e-06, + "loss": 0.4361, + "step": 1846 + }, + { + "epoch": 0.24613539445628999, + "grad_norm": 0.3266611340464229, + "learning_rate": 9.901524216961176e-06, + "loss": 0.4532, + "step": 1847 + }, + { + "epoch": 0.2462686567164179, + "grad_norm": 0.3562214566147522, + "learning_rate": 9.90138354942105e-06, + "loss": 0.5033, + "step": 1848 + }, + { + "epoch": 0.24640191897654584, + "grad_norm": 0.32524836653771116, + "learning_rate": 9.901242782485121e-06, + "loss": 0.3757, + "step": 1849 + }, + { + "epoch": 0.24653518123667378, + "grad_norm": 0.3407953196969093, + "learning_rate": 9.901101916156245e-06, + "loss": 0.5701, + "step": 1850 + }, + { + "epoch": 0.2466684434968017, + "grad_norm": 0.33613310020214054, + "learning_rate": 9.900960950437277e-06, + "loss": 0.4808, + "step": 1851 + }, + { + "epoch": 0.24680170575692964, + "grad_norm": 0.33040020163382416, + "learning_rate": 9.900819885331078e-06, + "loss": 0.3936, + "step": 1852 + }, + { + "epoch": 0.24693496801705758, + "grad_norm": 0.3345302495944285, + "learning_rate": 9.900678720840506e-06, + "loss": 0.446, + "step": 1853 + }, + { + "epoch": 0.2470682302771855, + "grad_norm": 0.3453440612590072, + "learning_rate": 9.900537456968426e-06, + "loss": 0.4304, + "step": 1854 + }, + { + "epoch": 0.24720149253731344, + "grad_norm": 0.3276250105430231, + "learning_rate": 9.9003960937177e-06, + "loss": 0.4806, + "step": 1855 + }, + { + "epoch": 0.24733475479744135, + "grad_norm": 0.33248339339986943, + "learning_rate": 9.900254631091198e-06, + "loss": 0.4478, + "step": 1856 + }, + { + "epoch": 0.2474680170575693, + "grad_norm": 0.33726766284909887, + "learning_rate": 9.900113069091786e-06, + "loss": 0.4876, + "step": 1857 + }, + { + "epoch": 0.24760127931769724, + "grad_norm": 0.3252970311795819, + "learning_rate": 9.899971407722336e-06, + "loss": 0.4409, + "step": 1858 + }, + { + "epoch": 0.24773454157782515, + "grad_norm": 0.318021731834367, + "learning_rate": 9.89982964698572e-06, + "loss": 0.3888, + "step": 1859 + }, + { + "epoch": 0.2478678038379531, + "grad_norm": 0.3391826903970666, + "learning_rate": 9.899687786884813e-06, + "loss": 0.3782, + "step": 1860 + }, + { + "epoch": 0.24800106609808104, + "grad_norm": 0.3276963183945238, + "learning_rate": 9.899545827422493e-06, + "loss": 0.3937, + "step": 1861 + }, + { + "epoch": 0.24813432835820895, + "grad_norm": 0.31962932182895687, + "learning_rate": 9.899403768601639e-06, + "loss": 0.461, + "step": 1862 + }, + { + "epoch": 0.2482675906183369, + "grad_norm": 0.3244072102277052, + "learning_rate": 9.899261610425129e-06, + "loss": 0.4856, + "step": 1863 + }, + { + "epoch": 0.2484008528784648, + "grad_norm": 0.331345787812111, + "learning_rate": 9.899119352895849e-06, + "loss": 0.4608, + "step": 1864 + }, + { + "epoch": 0.24853411513859275, + "grad_norm": 0.30297102797418085, + "learning_rate": 9.898976996016682e-06, + "loss": 0.4148, + "step": 1865 + }, + { + "epoch": 0.2486673773987207, + "grad_norm": 0.331953486387446, + "learning_rate": 9.898834539790515e-06, + "loss": 0.4385, + "step": 1866 + }, + { + "epoch": 0.2488006396588486, + "grad_norm": 0.30899522606597585, + "learning_rate": 9.898691984220237e-06, + "loss": 0.4034, + "step": 1867 + }, + { + "epoch": 0.24893390191897655, + "grad_norm": 0.314223086990717, + "learning_rate": 9.89854932930874e-06, + "loss": 0.4195, + "step": 1868 + }, + { + "epoch": 0.2490671641791045, + "grad_norm": 0.32087239697417436, + "learning_rate": 9.898406575058916e-06, + "loss": 0.4793, + "step": 1869 + }, + { + "epoch": 0.2492004264392324, + "grad_norm": 0.30360236419367675, + "learning_rate": 9.898263721473659e-06, + "loss": 0.3737, + "step": 1870 + }, + { + "epoch": 0.24933368869936035, + "grad_norm": 0.3321709852685544, + "learning_rate": 9.898120768555867e-06, + "loss": 0.3832, + "step": 1871 + }, + { + "epoch": 0.24946695095948826, + "grad_norm": 0.4119863757842873, + "learning_rate": 9.89797771630844e-06, + "loss": 0.425, + "step": 1872 + }, + { + "epoch": 0.2496002132196162, + "grad_norm": 0.28798717179283767, + "learning_rate": 9.897834564734278e-06, + "loss": 0.5225, + "step": 1873 + }, + { + "epoch": 0.24973347547974414, + "grad_norm": 0.36227670340670903, + "learning_rate": 9.897691313836284e-06, + "loss": 0.4135, + "step": 1874 + }, + { + "epoch": 0.24986673773987206, + "grad_norm": 0.3079721813540198, + "learning_rate": 9.897547963617361e-06, + "loss": 0.381, + "step": 1875 + }, + { + "epoch": 0.25, + "grad_norm": 0.3070874709667089, + "learning_rate": 9.89740451408042e-06, + "loss": 0.3668, + "step": 1876 + }, + { + "epoch": 0.25013326226012794, + "grad_norm": 0.3412291712015097, + "learning_rate": 9.897260965228365e-06, + "loss": 0.3793, + "step": 1877 + }, + { + "epoch": 0.2502665245202559, + "grad_norm": 0.30561363888745513, + "learning_rate": 9.897117317064112e-06, + "loss": 0.4082, + "step": 1878 + }, + { + "epoch": 0.25039978678038377, + "grad_norm": 0.3329852861272759, + "learning_rate": 9.896973569590573e-06, + "loss": 0.3974, + "step": 1879 + }, + { + "epoch": 0.2505330490405117, + "grad_norm": 0.32086025191404993, + "learning_rate": 9.896829722810662e-06, + "loss": 0.4791, + "step": 1880 + }, + { + "epoch": 0.25066631130063965, + "grad_norm": 0.306789344908274, + "learning_rate": 9.896685776727295e-06, + "loss": 0.4177, + "step": 1881 + }, + { + "epoch": 0.2507995735607676, + "grad_norm": 0.37312917597130335, + "learning_rate": 9.896541731343393e-06, + "loss": 0.5227, + "step": 1882 + }, + { + "epoch": 0.25093283582089554, + "grad_norm": 0.3042287426910982, + "learning_rate": 9.896397586661876e-06, + "loss": 0.3608, + "step": 1883 + }, + { + "epoch": 0.2510660980810235, + "grad_norm": 0.3394421965212339, + "learning_rate": 9.896253342685668e-06, + "loss": 0.5011, + "step": 1884 + }, + { + "epoch": 0.25119936034115137, + "grad_norm": 0.3114979711738614, + "learning_rate": 9.896108999417693e-06, + "loss": 0.4065, + "step": 1885 + }, + { + "epoch": 0.2513326226012793, + "grad_norm": 0.2971967615435862, + "learning_rate": 9.895964556860879e-06, + "loss": 0.3799, + "step": 1886 + }, + { + "epoch": 0.25146588486140725, + "grad_norm": 0.31965142429687093, + "learning_rate": 9.895820015018156e-06, + "loss": 0.4435, + "step": 1887 + }, + { + "epoch": 0.2515991471215352, + "grad_norm": 0.3088830139436938, + "learning_rate": 9.895675373892453e-06, + "loss": 0.409, + "step": 1888 + }, + { + "epoch": 0.25173240938166314, + "grad_norm": 0.3110661212031485, + "learning_rate": 9.895530633486706e-06, + "loss": 0.358, + "step": 1889 + }, + { + "epoch": 0.251865671641791, + "grad_norm": 0.3163528886712798, + "learning_rate": 9.895385793803846e-06, + "loss": 0.4179, + "step": 1890 + }, + { + "epoch": 0.25199893390191896, + "grad_norm": 0.344068241081903, + "learning_rate": 9.895240854846815e-06, + "loss": 0.4378, + "step": 1891 + }, + { + "epoch": 0.2521321961620469, + "grad_norm": 0.28387600193829926, + "learning_rate": 9.89509581661855e-06, + "loss": 0.3416, + "step": 1892 + }, + { + "epoch": 0.25226545842217485, + "grad_norm": 0.2993047089174317, + "learning_rate": 9.89495067912199e-06, + "loss": 0.3591, + "step": 1893 + }, + { + "epoch": 0.2523987206823028, + "grad_norm": 0.29982476818552156, + "learning_rate": 9.894805442360083e-06, + "loss": 0.4472, + "step": 1894 + }, + { + "epoch": 0.2525319829424307, + "grad_norm": 0.3841129758917693, + "learning_rate": 9.894660106335772e-06, + "loss": 0.4471, + "step": 1895 + }, + { + "epoch": 0.2526652452025586, + "grad_norm": 0.3664112096590431, + "learning_rate": 9.894514671052003e-06, + "loss": 0.4838, + "step": 1896 + }, + { + "epoch": 0.25279850746268656, + "grad_norm": 0.2980763501185593, + "learning_rate": 9.894369136511726e-06, + "loss": 0.4082, + "step": 1897 + }, + { + "epoch": 0.2529317697228145, + "grad_norm": 0.321601794819494, + "learning_rate": 9.894223502717895e-06, + "loss": 0.4336, + "step": 1898 + }, + { + "epoch": 0.25306503198294245, + "grad_norm": 0.3109846855357186, + "learning_rate": 9.894077769673458e-06, + "loss": 0.465, + "step": 1899 + }, + { + "epoch": 0.2531982942430704, + "grad_norm": 0.3230235864026315, + "learning_rate": 9.893931937381376e-06, + "loss": 0.4997, + "step": 1900 + }, + { + "epoch": 0.2533315565031983, + "grad_norm": 0.2913816552393883, + "learning_rate": 9.893786005844602e-06, + "loss": 0.4347, + "step": 1901 + }, + { + "epoch": 0.2534648187633262, + "grad_norm": 0.32967741604758094, + "learning_rate": 9.893639975066099e-06, + "loss": 0.4587, + "step": 1902 + }, + { + "epoch": 0.25359808102345416, + "grad_norm": 0.31671803644574503, + "learning_rate": 9.893493845048825e-06, + "loss": 0.4294, + "step": 1903 + }, + { + "epoch": 0.2537313432835821, + "grad_norm": 0.33175138005403654, + "learning_rate": 9.893347615795745e-06, + "loss": 0.4245, + "step": 1904 + }, + { + "epoch": 0.25386460554371004, + "grad_norm": 0.3104932765714208, + "learning_rate": 9.893201287309823e-06, + "loss": 0.4056, + "step": 1905 + }, + { + "epoch": 0.25399786780383793, + "grad_norm": 0.3148692998795664, + "learning_rate": 9.893054859594032e-06, + "loss": 0.4072, + "step": 1906 + }, + { + "epoch": 0.25413113006396587, + "grad_norm": 0.34915009951901715, + "learning_rate": 9.892908332651333e-06, + "loss": 0.5243, + "step": 1907 + }, + { + "epoch": 0.2542643923240938, + "grad_norm": 0.3034893815661616, + "learning_rate": 9.892761706484704e-06, + "loss": 0.4018, + "step": 1908 + }, + { + "epoch": 0.25439765458422176, + "grad_norm": 0.3435985974763347, + "learning_rate": 9.892614981097115e-06, + "loss": 0.3873, + "step": 1909 + }, + { + "epoch": 0.2545309168443497, + "grad_norm": 0.29929568214505403, + "learning_rate": 9.89246815649154e-06, + "loss": 0.3755, + "step": 1910 + }, + { + "epoch": 0.25466417910447764, + "grad_norm": 0.31862263170666205, + "learning_rate": 9.892321232670965e-06, + "loss": 0.3589, + "step": 1911 + }, + { + "epoch": 0.2547974413646055, + "grad_norm": 0.30669747279904863, + "learning_rate": 9.89217420963836e-06, + "loss": 0.406, + "step": 1912 + }, + { + "epoch": 0.25493070362473347, + "grad_norm": 0.3283865157811861, + "learning_rate": 9.892027087396709e-06, + "loss": 0.4306, + "step": 1913 + }, + { + "epoch": 0.2550639658848614, + "grad_norm": 0.3226918223628616, + "learning_rate": 9.891879865948997e-06, + "loss": 0.4031, + "step": 1914 + }, + { + "epoch": 0.25519722814498935, + "grad_norm": 0.32903644497477635, + "learning_rate": 9.89173254529821e-06, + "loss": 0.4838, + "step": 1915 + }, + { + "epoch": 0.2553304904051173, + "grad_norm": 0.3435301511958212, + "learning_rate": 9.891585125447334e-06, + "loss": 0.3986, + "step": 1916 + }, + { + "epoch": 0.2554637526652452, + "grad_norm": 0.3191438500123989, + "learning_rate": 9.891437606399358e-06, + "loss": 0.5261, + "step": 1917 + }, + { + "epoch": 0.2555970149253731, + "grad_norm": 0.32243217003855695, + "learning_rate": 9.891289988157277e-06, + "loss": 0.431, + "step": 1918 + }, + { + "epoch": 0.25573027718550106, + "grad_norm": 0.33626336519429384, + "learning_rate": 9.89114227072408e-06, + "loss": 0.4103, + "step": 1919 + }, + { + "epoch": 0.255863539445629, + "grad_norm": 0.33416105899146464, + "learning_rate": 9.890994454102767e-06, + "loss": 0.4592, + "step": 1920 + }, + { + "epoch": 0.25599680170575695, + "grad_norm": 0.33183430255567553, + "learning_rate": 9.890846538296332e-06, + "loss": 0.4108, + "step": 1921 + }, + { + "epoch": 0.25613006396588484, + "grad_norm": 0.34807565845018207, + "learning_rate": 9.890698523307776e-06, + "loss": 0.4773, + "step": 1922 + }, + { + "epoch": 0.2562633262260128, + "grad_norm": 0.3292605507147389, + "learning_rate": 9.8905504091401e-06, + "loss": 0.3813, + "step": 1923 + }, + { + "epoch": 0.2563965884861407, + "grad_norm": 0.32986940517653734, + "learning_rate": 9.89040219579631e-06, + "loss": 0.4331, + "step": 1924 + }, + { + "epoch": 0.25652985074626866, + "grad_norm": 0.38800822409161745, + "learning_rate": 9.890253883279409e-06, + "loss": 0.4752, + "step": 1925 + }, + { + "epoch": 0.2566631130063966, + "grad_norm": 0.2976610230929859, + "learning_rate": 9.890105471592406e-06, + "loss": 0.4098, + "step": 1926 + }, + { + "epoch": 0.25679637526652455, + "grad_norm": 0.34351536195651206, + "learning_rate": 9.88995696073831e-06, + "loss": 0.4545, + "step": 1927 + }, + { + "epoch": 0.25692963752665243, + "grad_norm": 0.3280355941512694, + "learning_rate": 9.889808350720131e-06, + "loss": 0.4119, + "step": 1928 + }, + { + "epoch": 0.2570628997867804, + "grad_norm": 0.3186018980121476, + "learning_rate": 9.889659641540886e-06, + "loss": 0.412, + "step": 1929 + }, + { + "epoch": 0.2571961620469083, + "grad_norm": 0.31790622766210175, + "learning_rate": 9.889510833203591e-06, + "loss": 0.3713, + "step": 1930 + }, + { + "epoch": 0.25732942430703626, + "grad_norm": 0.31163826579069404, + "learning_rate": 9.889361925711258e-06, + "loss": 0.4342, + "step": 1931 + }, + { + "epoch": 0.2574626865671642, + "grad_norm": 0.31224390204601615, + "learning_rate": 9.889212919066914e-06, + "loss": 0.412, + "step": 1932 + }, + { + "epoch": 0.2575959488272921, + "grad_norm": 0.3428466200481009, + "learning_rate": 9.889063813273575e-06, + "loss": 0.4961, + "step": 1933 + }, + { + "epoch": 0.25772921108742003, + "grad_norm": 0.3438066257647268, + "learning_rate": 9.88891460833427e-06, + "loss": 0.5809, + "step": 1934 + }, + { + "epoch": 0.25786247334754797, + "grad_norm": 0.3003889073672875, + "learning_rate": 9.888765304252019e-06, + "loss": 0.3977, + "step": 1935 + }, + { + "epoch": 0.2579957356076759, + "grad_norm": 0.3299493005046966, + "learning_rate": 9.888615901029854e-06, + "loss": 0.3598, + "step": 1936 + }, + { + "epoch": 0.25812899786780386, + "grad_norm": 0.3327737399000591, + "learning_rate": 9.888466398670802e-06, + "loss": 0.3989, + "step": 1937 + }, + { + "epoch": 0.25826226012793174, + "grad_norm": 0.3260417667152547, + "learning_rate": 9.888316797177898e-06, + "loss": 0.4392, + "step": 1938 + }, + { + "epoch": 0.2583955223880597, + "grad_norm": 0.3148245606948364, + "learning_rate": 9.888167096554173e-06, + "loss": 0.4691, + "step": 1939 + }, + { + "epoch": 0.2585287846481876, + "grad_norm": 0.3311931399070672, + "learning_rate": 9.888017296802665e-06, + "loss": 0.4877, + "step": 1940 + }, + { + "epoch": 0.25866204690831557, + "grad_norm": 0.3031178067071377, + "learning_rate": 9.88786739792641e-06, + "loss": 0.3923, + "step": 1941 + }, + { + "epoch": 0.2587953091684435, + "grad_norm": 0.3320461712235284, + "learning_rate": 9.887717399928448e-06, + "loss": 0.4209, + "step": 1942 + }, + { + "epoch": 0.25892857142857145, + "grad_norm": 0.32019704856458864, + "learning_rate": 9.88756730281182e-06, + "loss": 0.4228, + "step": 1943 + }, + { + "epoch": 0.25906183368869934, + "grad_norm": 0.3064948744197308, + "learning_rate": 9.887417106579572e-06, + "loss": 0.4491, + "step": 1944 + }, + { + "epoch": 0.2591950959488273, + "grad_norm": 0.3101033118545042, + "learning_rate": 9.88726681123475e-06, + "loss": 0.3738, + "step": 1945 + }, + { + "epoch": 0.2593283582089552, + "grad_norm": 0.3464001016645125, + "learning_rate": 9.8871164167804e-06, + "loss": 0.4081, + "step": 1946 + }, + { + "epoch": 0.25946162046908317, + "grad_norm": 0.3068227908184816, + "learning_rate": 9.886965923219571e-06, + "loss": 0.3555, + "step": 1947 + }, + { + "epoch": 0.2595948827292111, + "grad_norm": 0.3199556194766627, + "learning_rate": 9.886815330555318e-06, + "loss": 0.4376, + "step": 1948 + }, + { + "epoch": 0.259728144989339, + "grad_norm": 0.3386845244220093, + "learning_rate": 9.886664638790693e-06, + "loss": 0.447, + "step": 1949 + }, + { + "epoch": 0.25986140724946694, + "grad_norm": 0.5283158110468621, + "learning_rate": 9.886513847928754e-06, + "loss": 0.3594, + "step": 1950 + }, + { + "epoch": 0.2599946695095949, + "grad_norm": 0.30805399880979445, + "learning_rate": 9.886362957972556e-06, + "loss": 0.4257, + "step": 1951 + }, + { + "epoch": 0.2601279317697228, + "grad_norm": 0.30487867781264666, + "learning_rate": 9.88621196892516e-06, + "loss": 0.5691, + "step": 1952 + }, + { + "epoch": 0.26026119402985076, + "grad_norm": 0.335990494199708, + "learning_rate": 9.886060880789627e-06, + "loss": 0.4358, + "step": 1953 + }, + { + "epoch": 0.2603944562899787, + "grad_norm": 0.3429522304019688, + "learning_rate": 9.885909693569023e-06, + "loss": 0.4366, + "step": 1954 + }, + { + "epoch": 0.2605277185501066, + "grad_norm": 0.3174117692152562, + "learning_rate": 9.885758407266412e-06, + "loss": 0.5266, + "step": 1955 + }, + { + "epoch": 0.26066098081023453, + "grad_norm": 0.3278631763704597, + "learning_rate": 9.885607021884865e-06, + "loss": 0.5188, + "step": 1956 + }, + { + "epoch": 0.2607942430703625, + "grad_norm": 0.31806802201483875, + "learning_rate": 9.885455537427447e-06, + "loss": 0.5324, + "step": 1957 + }, + { + "epoch": 0.2609275053304904, + "grad_norm": 0.3445858022141069, + "learning_rate": 9.885303953897234e-06, + "loss": 0.4369, + "step": 1958 + }, + { + "epoch": 0.26106076759061836, + "grad_norm": 0.335348231454603, + "learning_rate": 9.885152271297301e-06, + "loss": 0.3806, + "step": 1959 + }, + { + "epoch": 0.26119402985074625, + "grad_norm": 0.31792467809853747, + "learning_rate": 9.885000489630718e-06, + "loss": 0.45, + "step": 1960 + }, + { + "epoch": 0.2613272921108742, + "grad_norm": 0.29512303014736946, + "learning_rate": 9.88484860890057e-06, + "loss": 0.4917, + "step": 1961 + }, + { + "epoch": 0.26146055437100213, + "grad_norm": 0.30811451910277093, + "learning_rate": 9.884696629109931e-06, + "loss": 0.3899, + "step": 1962 + }, + { + "epoch": 0.26159381663113007, + "grad_norm": 0.31548664044802727, + "learning_rate": 9.884544550261888e-06, + "loss": 0.5335, + "step": 1963 + }, + { + "epoch": 0.261727078891258, + "grad_norm": 0.29716069540693946, + "learning_rate": 9.884392372359522e-06, + "loss": 0.3623, + "step": 1964 + }, + { + "epoch": 0.2618603411513859, + "grad_norm": 0.3222327567967967, + "learning_rate": 9.884240095405919e-06, + "loss": 0.3936, + "step": 1965 + }, + { + "epoch": 0.26199360341151384, + "grad_norm": 0.3009689235990755, + "learning_rate": 9.88408771940417e-06, + "loss": 0.4201, + "step": 1966 + }, + { + "epoch": 0.2621268656716418, + "grad_norm": 0.3271002090109513, + "learning_rate": 9.883935244357361e-06, + "loss": 0.4059, + "step": 1967 + }, + { + "epoch": 0.2622601279317697, + "grad_norm": 0.3163397975169151, + "learning_rate": 9.883782670268587e-06, + "loss": 0.3653, + "step": 1968 + }, + { + "epoch": 0.26239339019189767, + "grad_norm": 0.30636201752817444, + "learning_rate": 9.88362999714094e-06, + "loss": 0.4055, + "step": 1969 + }, + { + "epoch": 0.2625266524520256, + "grad_norm": 0.3246822367903032, + "learning_rate": 9.883477224977519e-06, + "loss": 0.3938, + "step": 1970 + }, + { + "epoch": 0.2626599147121535, + "grad_norm": 0.31148765222967606, + "learning_rate": 9.88332435378142e-06, + "loss": 0.3901, + "step": 1971 + }, + { + "epoch": 0.26279317697228144, + "grad_norm": 0.3190388803368343, + "learning_rate": 9.883171383555742e-06, + "loss": 0.4414, + "step": 1972 + }, + { + "epoch": 0.2629264392324094, + "grad_norm": 0.30775512478869543, + "learning_rate": 9.88301831430359e-06, + "loss": 0.5281, + "step": 1973 + }, + { + "epoch": 0.2630597014925373, + "grad_norm": 0.32464917386324116, + "learning_rate": 9.882865146028064e-06, + "loss": 0.4313, + "step": 1974 + }, + { + "epoch": 0.26319296375266527, + "grad_norm": 0.3085792690242703, + "learning_rate": 9.882711878732276e-06, + "loss": 0.3797, + "step": 1975 + }, + { + "epoch": 0.26332622601279315, + "grad_norm": 0.31731891784325084, + "learning_rate": 9.88255851241933e-06, + "loss": 0.507, + "step": 1976 + }, + { + "epoch": 0.2634594882729211, + "grad_norm": 0.30391857543849654, + "learning_rate": 9.882405047092336e-06, + "loss": 0.3918, + "step": 1977 + }, + { + "epoch": 0.26359275053304904, + "grad_norm": 0.29601985141350085, + "learning_rate": 9.882251482754405e-06, + "loss": 0.4065, + "step": 1978 + }, + { + "epoch": 0.263726012793177, + "grad_norm": 0.33536728957206813, + "learning_rate": 9.882097819408657e-06, + "loss": 0.4003, + "step": 1979 + }, + { + "epoch": 0.2638592750533049, + "grad_norm": 0.3138649712533975, + "learning_rate": 9.881944057058204e-06, + "loss": 0.459, + "step": 1980 + }, + { + "epoch": 0.26399253731343286, + "grad_norm": 0.32675976511910043, + "learning_rate": 9.881790195706163e-06, + "loss": 0.4501, + "step": 1981 + }, + { + "epoch": 0.26412579957356075, + "grad_norm": 0.3157165917470405, + "learning_rate": 9.881636235355655e-06, + "loss": 0.4522, + "step": 1982 + }, + { + "epoch": 0.2642590618336887, + "grad_norm": 0.35235016777089434, + "learning_rate": 9.881482176009805e-06, + "loss": 0.3946, + "step": 1983 + }, + { + "epoch": 0.26439232409381663, + "grad_norm": 0.3156430187310959, + "learning_rate": 9.881328017671734e-06, + "loss": 0.3716, + "step": 1984 + }, + { + "epoch": 0.2645255863539446, + "grad_norm": 0.3093828847865431, + "learning_rate": 9.88117376034457e-06, + "loss": 0.3641, + "step": 1985 + }, + { + "epoch": 0.2646588486140725, + "grad_norm": 0.3313109830210125, + "learning_rate": 9.88101940403144e-06, + "loss": 0.3757, + "step": 1986 + }, + { + "epoch": 0.2647921108742004, + "grad_norm": 0.33006309058563243, + "learning_rate": 9.880864948735475e-06, + "loss": 0.4988, + "step": 1987 + }, + { + "epoch": 0.26492537313432835, + "grad_norm": 0.3072740130232253, + "learning_rate": 9.880710394459809e-06, + "loss": 0.4366, + "step": 1988 + }, + { + "epoch": 0.2650586353944563, + "grad_norm": 0.33037481196779395, + "learning_rate": 9.880555741207572e-06, + "loss": 0.4149, + "step": 1989 + }, + { + "epoch": 0.26519189765458423, + "grad_norm": 0.3192031318257968, + "learning_rate": 9.880400988981903e-06, + "loss": 0.4382, + "step": 1990 + }, + { + "epoch": 0.26532515991471217, + "grad_norm": 0.31219426653893, + "learning_rate": 9.880246137785938e-06, + "loss": 0.502, + "step": 1991 + }, + { + "epoch": 0.26545842217484006, + "grad_norm": 0.32449284196627154, + "learning_rate": 9.88009118762282e-06, + "loss": 0.4393, + "step": 1992 + }, + { + "epoch": 0.265591684434968, + "grad_norm": 0.3014626427984867, + "learning_rate": 9.879936138495691e-06, + "loss": 0.4321, + "step": 1993 + }, + { + "epoch": 0.26572494669509594, + "grad_norm": 0.3251160430509743, + "learning_rate": 9.879780990407694e-06, + "loss": 0.384, + "step": 1994 + }, + { + "epoch": 0.2658582089552239, + "grad_norm": 0.3268420943562063, + "learning_rate": 9.879625743361975e-06, + "loss": 0.5515, + "step": 1995 + }, + { + "epoch": 0.2659914712153518, + "grad_norm": 0.33233321456333803, + "learning_rate": 9.879470397361684e-06, + "loss": 0.4223, + "step": 1996 + }, + { + "epoch": 0.26612473347547977, + "grad_norm": 0.3128069468480595, + "learning_rate": 9.879314952409969e-06, + "loss": 0.4674, + "step": 1997 + }, + { + "epoch": 0.26625799573560766, + "grad_norm": 0.3328577402995199, + "learning_rate": 9.879159408509984e-06, + "loss": 0.377, + "step": 1998 + }, + { + "epoch": 0.2663912579957356, + "grad_norm": 0.30465393206063957, + "learning_rate": 9.879003765664883e-06, + "loss": 0.3448, + "step": 1999 + }, + { + "epoch": 0.26652452025586354, + "grad_norm": 0.338303212489692, + "learning_rate": 9.878848023877822e-06, + "loss": 0.4292, + "step": 2000 + }, + { + "epoch": 0.2666577825159915, + "grad_norm": 0.32923401197796154, + "learning_rate": 9.87869218315196e-06, + "loss": 0.491, + "step": 2001 + }, + { + "epoch": 0.2667910447761194, + "grad_norm": 0.3319091323083076, + "learning_rate": 9.878536243490456e-06, + "loss": 0.4354, + "step": 2002 + }, + { + "epoch": 0.2669243070362473, + "grad_norm": 0.3302394498936779, + "learning_rate": 9.878380204896474e-06, + "loss": 0.4281, + "step": 2003 + }, + { + "epoch": 0.26705756929637525, + "grad_norm": 0.31661391493229113, + "learning_rate": 9.878224067373177e-06, + "loss": 0.4154, + "step": 2004 + }, + { + "epoch": 0.2671908315565032, + "grad_norm": 0.33393071253550094, + "learning_rate": 9.878067830923732e-06, + "loss": 0.384, + "step": 2005 + }, + { + "epoch": 0.26732409381663114, + "grad_norm": 0.3359179080224411, + "learning_rate": 9.877911495551307e-06, + "loss": 0.4468, + "step": 2006 + }, + { + "epoch": 0.2674573560767591, + "grad_norm": 0.3303442907337257, + "learning_rate": 9.877755061259072e-06, + "loss": 0.401, + "step": 2007 + }, + { + "epoch": 0.267590618336887, + "grad_norm": 0.31109951776479533, + "learning_rate": 9.877598528050198e-06, + "loss": 0.4052, + "step": 2008 + }, + { + "epoch": 0.2677238805970149, + "grad_norm": 0.31155840368293264, + "learning_rate": 9.877441895927863e-06, + "loss": 0.4568, + "step": 2009 + }, + { + "epoch": 0.26785714285714285, + "grad_norm": 0.31801467325340027, + "learning_rate": 9.877285164895243e-06, + "loss": 0.356, + "step": 2010 + }, + { + "epoch": 0.2679904051172708, + "grad_norm": 0.31832405128566116, + "learning_rate": 9.877128334955512e-06, + "loss": 0.4316, + "step": 2011 + }, + { + "epoch": 0.26812366737739873, + "grad_norm": 0.3239105424438836, + "learning_rate": 9.876971406111855e-06, + "loss": 0.4692, + "step": 2012 + }, + { + "epoch": 0.2682569296375267, + "grad_norm": 0.33567411293706967, + "learning_rate": 9.876814378367453e-06, + "loss": 0.5171, + "step": 2013 + }, + { + "epoch": 0.26839019189765456, + "grad_norm": 0.3011137680664098, + "learning_rate": 9.876657251725489e-06, + "loss": 0.404, + "step": 2014 + }, + { + "epoch": 0.2685234541577825, + "grad_norm": 0.3124638077857407, + "learning_rate": 9.87650002618915e-06, + "loss": 0.3742, + "step": 2015 + }, + { + "epoch": 0.26865671641791045, + "grad_norm": 0.32988597763404487, + "learning_rate": 9.876342701761627e-06, + "loss": 0.4204, + "step": 2016 + }, + { + "epoch": 0.2687899786780384, + "grad_norm": 0.31610593963146205, + "learning_rate": 9.876185278446106e-06, + "loss": 0.5054, + "step": 2017 + }, + { + "epoch": 0.26892324093816633, + "grad_norm": 0.3122596554431381, + "learning_rate": 9.876027756245783e-06, + "loss": 0.3797, + "step": 2018 + }, + { + "epoch": 0.2690565031982942, + "grad_norm": 1.8002240952946955, + "learning_rate": 9.87587013516385e-06, + "loss": 0.648, + "step": 2019 + }, + { + "epoch": 0.26918976545842216, + "grad_norm": 0.3192635244235372, + "learning_rate": 9.875712415203505e-06, + "loss": 0.3815, + "step": 2020 + }, + { + "epoch": 0.2693230277185501, + "grad_norm": 0.3322100653745105, + "learning_rate": 9.875554596367944e-06, + "loss": 0.4779, + "step": 2021 + }, + { + "epoch": 0.26945628997867804, + "grad_norm": 0.3103024252258647, + "learning_rate": 9.875396678660371e-06, + "loss": 0.4085, + "step": 2022 + }, + { + "epoch": 0.269589552238806, + "grad_norm": 0.34216942352319046, + "learning_rate": 9.875238662083988e-06, + "loss": 0.4762, + "step": 2023 + }, + { + "epoch": 0.2697228144989339, + "grad_norm": 0.3186906768264556, + "learning_rate": 9.875080546641996e-06, + "loss": 0.4345, + "step": 2024 + }, + { + "epoch": 0.2698560767590618, + "grad_norm": 0.31157079434207147, + "learning_rate": 9.874922332337605e-06, + "loss": 0.3621, + "step": 2025 + }, + { + "epoch": 0.26998933901918976, + "grad_norm": 0.33537726553486763, + "learning_rate": 9.874764019174021e-06, + "loss": 0.4625, + "step": 2026 + }, + { + "epoch": 0.2701226012793177, + "grad_norm": 0.308415242307394, + "learning_rate": 9.874605607154456e-06, + "loss": 0.3926, + "step": 2027 + }, + { + "epoch": 0.27025586353944564, + "grad_norm": 0.31250997251882634, + "learning_rate": 9.874447096282123e-06, + "loss": 0.3977, + "step": 2028 + }, + { + "epoch": 0.2703891257995736, + "grad_norm": 0.3317305118682141, + "learning_rate": 9.874288486560233e-06, + "loss": 0.4979, + "step": 2029 + }, + { + "epoch": 0.27052238805970147, + "grad_norm": 0.3066742906853052, + "learning_rate": 9.874129777992007e-06, + "loss": 0.4008, + "step": 2030 + }, + { + "epoch": 0.2706556503198294, + "grad_norm": 0.30526158601192677, + "learning_rate": 9.873970970580662e-06, + "loss": 0.4047, + "step": 2031 + }, + { + "epoch": 0.27078891257995735, + "grad_norm": 0.32942692349104075, + "learning_rate": 9.873812064329416e-06, + "loss": 0.5544, + "step": 2032 + }, + { + "epoch": 0.2709221748400853, + "grad_norm": 0.28768215204485587, + "learning_rate": 9.873653059241493e-06, + "loss": 0.3636, + "step": 2033 + }, + { + "epoch": 0.27105543710021324, + "grad_norm": 0.3208942161634035, + "learning_rate": 9.87349395532012e-06, + "loss": 0.5108, + "step": 2034 + }, + { + "epoch": 0.2711886993603412, + "grad_norm": 0.31491879708440906, + "learning_rate": 9.873334752568518e-06, + "loss": 0.4163, + "step": 2035 + }, + { + "epoch": 0.27132196162046907, + "grad_norm": 0.32352666008564773, + "learning_rate": 9.873175450989922e-06, + "loss": 0.3861, + "step": 2036 + }, + { + "epoch": 0.271455223880597, + "grad_norm": 0.3148296469166128, + "learning_rate": 9.873016050587558e-06, + "loss": 0.4007, + "step": 2037 + }, + { + "epoch": 0.27158848614072495, + "grad_norm": 0.3069305829394814, + "learning_rate": 9.87285655136466e-06, + "loss": 0.4212, + "step": 2038 + }, + { + "epoch": 0.2717217484008529, + "grad_norm": 0.32771725945174335, + "learning_rate": 9.87269695332446e-06, + "loss": 0.3858, + "step": 2039 + }, + { + "epoch": 0.27185501066098083, + "grad_norm": 0.306199377505306, + "learning_rate": 9.872537256470201e-06, + "loss": 0.4083, + "step": 2040 + }, + { + "epoch": 0.2719882729211087, + "grad_norm": 0.32939221623719167, + "learning_rate": 9.872377460805115e-06, + "loss": 0.4061, + "step": 2041 + }, + { + "epoch": 0.27212153518123666, + "grad_norm": 0.32330477622529685, + "learning_rate": 9.872217566332446e-06, + "loss": 0.4239, + "step": 2042 + }, + { + "epoch": 0.2722547974413646, + "grad_norm": 0.3276237522376271, + "learning_rate": 9.872057573055433e-06, + "loss": 0.4143, + "step": 2043 + }, + { + "epoch": 0.27238805970149255, + "grad_norm": 0.32508153904698955, + "learning_rate": 9.871897480977325e-06, + "loss": 0.431, + "step": 2044 + }, + { + "epoch": 0.2725213219616205, + "grad_norm": 0.3479872075256589, + "learning_rate": 9.871737290101366e-06, + "loss": 0.4206, + "step": 2045 + }, + { + "epoch": 0.2726545842217484, + "grad_norm": 0.31321274305774255, + "learning_rate": 9.871577000430805e-06, + "loss": 0.4183, + "step": 2046 + }, + { + "epoch": 0.2727878464818763, + "grad_norm": 0.31831751527529073, + "learning_rate": 9.87141661196889e-06, + "loss": 0.435, + "step": 2047 + }, + { + "epoch": 0.27292110874200426, + "grad_norm": 0.3281421268827858, + "learning_rate": 9.87125612471888e-06, + "loss": 0.4298, + "step": 2048 + }, + { + "epoch": 0.2730543710021322, + "grad_norm": 0.31877948156333064, + "learning_rate": 9.871095538684024e-06, + "loss": 0.4019, + "step": 2049 + }, + { + "epoch": 0.27318763326226014, + "grad_norm": 0.3115615300432184, + "learning_rate": 9.87093485386758e-06, + "loss": 0.4005, + "step": 2050 + }, + { + "epoch": 0.2733208955223881, + "grad_norm": 0.30956719415288486, + "learning_rate": 9.870774070272807e-06, + "loss": 0.4504, + "step": 2051 + }, + { + "epoch": 0.27345415778251597, + "grad_norm": 0.3327196058727588, + "learning_rate": 9.870613187902964e-06, + "loss": 0.4288, + "step": 2052 + }, + { + "epoch": 0.2735874200426439, + "grad_norm": 0.30460430627930024, + "learning_rate": 9.870452206761317e-06, + "loss": 0.4051, + "step": 2053 + }, + { + "epoch": 0.27372068230277186, + "grad_norm": 0.37900027580662726, + "learning_rate": 9.870291126851125e-06, + "loss": 0.4921, + "step": 2054 + }, + { + "epoch": 0.2738539445628998, + "grad_norm": 0.3055883150935667, + "learning_rate": 9.870129948175662e-06, + "loss": 0.3781, + "step": 2055 + }, + { + "epoch": 0.27398720682302774, + "grad_norm": 0.30401244717111287, + "learning_rate": 9.86996867073819e-06, + "loss": 0.395, + "step": 2056 + }, + { + "epoch": 0.2741204690831556, + "grad_norm": 0.32204990842998027, + "learning_rate": 9.869807294541983e-06, + "loss": 0.522, + "step": 2057 + }, + { + "epoch": 0.27425373134328357, + "grad_norm": 0.34416550274403845, + "learning_rate": 9.86964581959031e-06, + "loss": 0.383, + "step": 2058 + }, + { + "epoch": 0.2743869936034115, + "grad_norm": 0.31594029362126846, + "learning_rate": 9.869484245886452e-06, + "loss": 0.4241, + "step": 2059 + }, + { + "epoch": 0.27452025586353945, + "grad_norm": 0.32528331856365567, + "learning_rate": 9.86932257343368e-06, + "loss": 0.5797, + "step": 2060 + }, + { + "epoch": 0.2746535181236674, + "grad_norm": 0.33369143172989923, + "learning_rate": 9.869160802235273e-06, + "loss": 0.5267, + "step": 2061 + }, + { + "epoch": 0.2747867803837953, + "grad_norm": 0.31020220537054016, + "learning_rate": 9.868998932294514e-06, + "loss": 0.4068, + "step": 2062 + }, + { + "epoch": 0.2749200426439232, + "grad_norm": 0.32485625557581005, + "learning_rate": 9.868836963614684e-06, + "loss": 0.4143, + "step": 2063 + }, + { + "epoch": 0.27505330490405117, + "grad_norm": 0.30889948813016527, + "learning_rate": 9.86867489619907e-06, + "loss": 0.38, + "step": 2064 + }, + { + "epoch": 0.2751865671641791, + "grad_norm": 0.33716590240528166, + "learning_rate": 9.868512730050955e-06, + "loss": 0.4195, + "step": 2065 + }, + { + "epoch": 0.27531982942430705, + "grad_norm": 0.2916062124729205, + "learning_rate": 9.868350465173629e-06, + "loss": 0.3868, + "step": 2066 + }, + { + "epoch": 0.275453091684435, + "grad_norm": 0.3275609723116764, + "learning_rate": 9.868188101570382e-06, + "loss": 0.456, + "step": 2067 + }, + { + "epoch": 0.2755863539445629, + "grad_norm": 0.3036274838058977, + "learning_rate": 9.86802563924451e-06, + "loss": 0.4198, + "step": 2068 + }, + { + "epoch": 0.2757196162046908, + "grad_norm": 0.31056415021437955, + "learning_rate": 9.867863078199303e-06, + "loss": 0.4071, + "step": 2069 + }, + { + "epoch": 0.27585287846481876, + "grad_norm": 0.30332268047212035, + "learning_rate": 9.86770041843806e-06, + "loss": 0.506, + "step": 2070 + }, + { + "epoch": 0.2759861407249467, + "grad_norm": 0.30035525344001235, + "learning_rate": 9.867537659964079e-06, + "loss": 0.444, + "step": 2071 + }, + { + "epoch": 0.27611940298507465, + "grad_norm": 0.38127413651591796, + "learning_rate": 9.867374802780662e-06, + "loss": 0.3662, + "step": 2072 + }, + { + "epoch": 0.27625266524520253, + "grad_norm": 0.3027305725400744, + "learning_rate": 9.86721184689111e-06, + "loss": 0.4641, + "step": 2073 + }, + { + "epoch": 0.2763859275053305, + "grad_norm": 0.29652505871885004, + "learning_rate": 9.867048792298727e-06, + "loss": 0.4205, + "step": 2074 + }, + { + "epoch": 0.2765191897654584, + "grad_norm": 0.300376591954629, + "learning_rate": 9.866885639006822e-06, + "loss": 0.372, + "step": 2075 + }, + { + "epoch": 0.27665245202558636, + "grad_norm": 0.30085211726512273, + "learning_rate": 9.866722387018702e-06, + "loss": 0.4356, + "step": 2076 + }, + { + "epoch": 0.2767857142857143, + "grad_norm": 0.307655445499575, + "learning_rate": 9.866559036337675e-06, + "loss": 0.4374, + "step": 2077 + }, + { + "epoch": 0.27691897654584224, + "grad_norm": 0.3107062585316575, + "learning_rate": 9.866395586967058e-06, + "loss": 0.4597, + "step": 2078 + }, + { + "epoch": 0.27705223880597013, + "grad_norm": 0.3289663398164011, + "learning_rate": 9.866232038910166e-06, + "loss": 0.3965, + "step": 2079 + }, + { + "epoch": 0.2771855010660981, + "grad_norm": 0.30383518726281505, + "learning_rate": 9.866068392170315e-06, + "loss": 0.4483, + "step": 2080 + }, + { + "epoch": 0.277318763326226, + "grad_norm": 0.34794937728753383, + "learning_rate": 9.865904646750818e-06, + "loss": 0.4692, + "step": 2081 + }, + { + "epoch": 0.27745202558635396, + "grad_norm": 0.30420035258110284, + "learning_rate": 9.865740802655001e-06, + "loss": 0.3639, + "step": 2082 + }, + { + "epoch": 0.2775852878464819, + "grad_norm": 0.32875369747922384, + "learning_rate": 9.865576859886186e-06, + "loss": 0.4314, + "step": 2083 + }, + { + "epoch": 0.2777185501066098, + "grad_norm": 0.3316702348584604, + "learning_rate": 9.865412818447698e-06, + "loss": 0.4006, + "step": 2084 + }, + { + "epoch": 0.2778518123667377, + "grad_norm": 0.3208123627995058, + "learning_rate": 9.865248678342863e-06, + "loss": 0.4155, + "step": 2085 + }, + { + "epoch": 0.27798507462686567, + "grad_norm": 0.3120979247552617, + "learning_rate": 9.865084439575008e-06, + "loss": 0.3863, + "step": 2086 + }, + { + "epoch": 0.2781183368869936, + "grad_norm": 0.32498594255506, + "learning_rate": 9.864920102147465e-06, + "loss": 0.3984, + "step": 2087 + }, + { + "epoch": 0.27825159914712155, + "grad_norm": 0.3013538187093497, + "learning_rate": 9.864755666063566e-06, + "loss": 0.4368, + "step": 2088 + }, + { + "epoch": 0.27838486140724944, + "grad_norm": 0.3197081539257964, + "learning_rate": 9.864591131326649e-06, + "loss": 0.4176, + "step": 2089 + }, + { + "epoch": 0.2785181236673774, + "grad_norm": 0.3010871714852422, + "learning_rate": 9.864426497940045e-06, + "loss": 0.3899, + "step": 2090 + }, + { + "epoch": 0.2786513859275053, + "grad_norm": 0.338775055394574, + "learning_rate": 9.864261765907098e-06, + "loss": 0.4488, + "step": 2091 + }, + { + "epoch": 0.27878464818763327, + "grad_norm": 0.3402951931706321, + "learning_rate": 9.864096935231144e-06, + "loss": 0.4106, + "step": 2092 + }, + { + "epoch": 0.2789179104477612, + "grad_norm": 0.31095846381975817, + "learning_rate": 9.863932005915529e-06, + "loss": 0.5144, + "step": 2093 + }, + { + "epoch": 0.27905117270788915, + "grad_norm": 0.31569590307422696, + "learning_rate": 9.863766977963594e-06, + "loss": 0.4427, + "step": 2094 + }, + { + "epoch": 0.27918443496801704, + "grad_norm": 0.3219840396946621, + "learning_rate": 9.86360185137869e-06, + "loss": 0.4421, + "step": 2095 + }, + { + "epoch": 0.279317697228145, + "grad_norm": 0.32548201215527645, + "learning_rate": 9.863436626164164e-06, + "loss": 0.3845, + "step": 2096 + }, + { + "epoch": 0.2794509594882729, + "grad_norm": 0.3203241897397642, + "learning_rate": 9.863271302323365e-06, + "loss": 0.4128, + "step": 2097 + }, + { + "epoch": 0.27958422174840086, + "grad_norm": 0.3185648646777215, + "learning_rate": 9.863105879859647e-06, + "loss": 0.4071, + "step": 2098 + }, + { + "epoch": 0.2797174840085288, + "grad_norm": 0.3179647017840083, + "learning_rate": 9.862940358776364e-06, + "loss": 0.398, + "step": 2099 + }, + { + "epoch": 0.2798507462686567, + "grad_norm": 0.33519533431587517, + "learning_rate": 9.862774739076874e-06, + "loss": 0.3989, + "step": 2100 + }, + { + "epoch": 0.27998400852878463, + "grad_norm": 0.306696912500267, + "learning_rate": 9.862609020764536e-06, + "loss": 0.3996, + "step": 2101 + }, + { + "epoch": 0.2801172707889126, + "grad_norm": 0.33300101773513857, + "learning_rate": 9.862443203842707e-06, + "loss": 0.4011, + "step": 2102 + }, + { + "epoch": 0.2802505330490405, + "grad_norm": 0.32850374552377093, + "learning_rate": 9.862277288314753e-06, + "loss": 0.4284, + "step": 2103 + }, + { + "epoch": 0.28038379530916846, + "grad_norm": 0.3127810042600511, + "learning_rate": 9.862111274184037e-06, + "loss": 0.4068, + "step": 2104 + }, + { + "epoch": 0.2805170575692964, + "grad_norm": 0.32479723231435, + "learning_rate": 9.861945161453927e-06, + "loss": 0.398, + "step": 2105 + }, + { + "epoch": 0.2806503198294243, + "grad_norm": 0.33689662736140397, + "learning_rate": 9.86177895012779e-06, + "loss": 0.4345, + "step": 2106 + }, + { + "epoch": 0.28078358208955223, + "grad_norm": 0.3254897440430583, + "learning_rate": 9.861612640208998e-06, + "loss": 0.411, + "step": 2107 + }, + { + "epoch": 0.2809168443496802, + "grad_norm": 0.3244238897632692, + "learning_rate": 9.861446231700922e-06, + "loss": 0.4238, + "step": 2108 + }, + { + "epoch": 0.2810501066098081, + "grad_norm": 0.32676127681137673, + "learning_rate": 9.86127972460694e-06, + "loss": 0.4614, + "step": 2109 + }, + { + "epoch": 0.28118336886993606, + "grad_norm": 0.29894806572903687, + "learning_rate": 9.861113118930424e-06, + "loss": 0.349, + "step": 2110 + }, + { + "epoch": 0.28131663113006394, + "grad_norm": 0.33326868187936665, + "learning_rate": 9.860946414674756e-06, + "loss": 0.3961, + "step": 2111 + }, + { + "epoch": 0.2814498933901919, + "grad_norm": 0.32120384277916386, + "learning_rate": 9.860779611843316e-06, + "loss": 0.4861, + "step": 2112 + }, + { + "epoch": 0.2815831556503198, + "grad_norm": 0.34492185787888147, + "learning_rate": 9.860612710439484e-06, + "loss": 0.461, + "step": 2113 + }, + { + "epoch": 0.28171641791044777, + "grad_norm": 0.32741333307539766, + "learning_rate": 9.860445710466648e-06, + "loss": 0.415, + "step": 2114 + }, + { + "epoch": 0.2818496801705757, + "grad_norm": 0.339571896036956, + "learning_rate": 9.860278611928195e-06, + "loss": 0.5355, + "step": 2115 + }, + { + "epoch": 0.2819829424307036, + "grad_norm": 0.30528087997944664, + "learning_rate": 9.86011141482751e-06, + "loss": 0.4107, + "step": 2116 + }, + { + "epoch": 0.28211620469083154, + "grad_norm": 0.30422647585948553, + "learning_rate": 9.859944119167985e-06, + "loss": 0.3504, + "step": 2117 + }, + { + "epoch": 0.2822494669509595, + "grad_norm": 0.3479924757966823, + "learning_rate": 9.859776724953017e-06, + "loss": 0.416, + "step": 2118 + }, + { + "epoch": 0.2823827292110874, + "grad_norm": 0.34047464780481224, + "learning_rate": 9.859609232185992e-06, + "loss": 0.3866, + "step": 2119 + }, + { + "epoch": 0.28251599147121537, + "grad_norm": 0.3082496520612851, + "learning_rate": 9.859441640870315e-06, + "loss": 0.3969, + "step": 2120 + }, + { + "epoch": 0.2826492537313433, + "grad_norm": 0.3407785950064261, + "learning_rate": 9.859273951009379e-06, + "loss": 0.4692, + "step": 2121 + }, + { + "epoch": 0.2827825159914712, + "grad_norm": 0.3308489982462521, + "learning_rate": 9.859106162606587e-06, + "loss": 0.3969, + "step": 2122 + }, + { + "epoch": 0.28291577825159914, + "grad_norm": 0.3153026237587464, + "learning_rate": 9.858938275665342e-06, + "loss": 0.3965, + "step": 2123 + }, + { + "epoch": 0.2830490405117271, + "grad_norm": 0.3496477834677497, + "learning_rate": 9.858770290189048e-06, + "loss": 0.4299, + "step": 2124 + }, + { + "epoch": 0.283182302771855, + "grad_norm": 0.5289314894008387, + "learning_rate": 9.858602206181112e-06, + "loss": 0.4272, + "step": 2125 + }, + { + "epoch": 0.28331556503198296, + "grad_norm": 0.31795186363932626, + "learning_rate": 9.85843402364494e-06, + "loss": 0.4427, + "step": 2126 + }, + { + "epoch": 0.28344882729211085, + "grad_norm": 0.34176472842341626, + "learning_rate": 9.858265742583945e-06, + "loss": 0.4057, + "step": 2127 + }, + { + "epoch": 0.2835820895522388, + "grad_norm": 0.300262499364149, + "learning_rate": 9.85809736300154e-06, + "loss": 0.3726, + "step": 2128 + }, + { + "epoch": 0.28371535181236673, + "grad_norm": 0.34472740795448503, + "learning_rate": 9.857928884901138e-06, + "loss": 0.4891, + "step": 2129 + }, + { + "epoch": 0.2838486140724947, + "grad_norm": 0.30335838546053134, + "learning_rate": 9.857760308286157e-06, + "loss": 0.3486, + "step": 2130 + }, + { + "epoch": 0.2839818763326226, + "grad_norm": 0.3172073420068924, + "learning_rate": 9.857591633160017e-06, + "loss": 0.3541, + "step": 2131 + }, + { + "epoch": 0.28411513859275056, + "grad_norm": 0.3223530221763956, + "learning_rate": 9.857422859526133e-06, + "loss": 0.4127, + "step": 2132 + }, + { + "epoch": 0.28424840085287845, + "grad_norm": 0.3122504234436281, + "learning_rate": 9.857253987387934e-06, + "loss": 0.4579, + "step": 2133 + }, + { + "epoch": 0.2843816631130064, + "grad_norm": 0.32192835810033765, + "learning_rate": 9.85708501674884e-06, + "loss": 0.4336, + "step": 2134 + }, + { + "epoch": 0.28451492537313433, + "grad_norm": 0.30454449530692723, + "learning_rate": 9.85691594761228e-06, + "loss": 0.493, + "step": 2135 + }, + { + "epoch": 0.2846481876332623, + "grad_norm": 0.4483760184842883, + "learning_rate": 9.856746779981683e-06, + "loss": 0.4782, + "step": 2136 + }, + { + "epoch": 0.2847814498933902, + "grad_norm": 0.30945592729216503, + "learning_rate": 9.856577513860476e-06, + "loss": 0.4598, + "step": 2137 + }, + { + "epoch": 0.2849147121535181, + "grad_norm": 0.3268866628459038, + "learning_rate": 9.856408149252096e-06, + "loss": 0.4493, + "step": 2138 + }, + { + "epoch": 0.28504797441364604, + "grad_norm": 0.3136098111644288, + "learning_rate": 9.856238686159975e-06, + "loss": 0.5037, + "step": 2139 + }, + { + "epoch": 0.285181236673774, + "grad_norm": 0.30656778796346673, + "learning_rate": 9.856069124587551e-06, + "loss": 0.3894, + "step": 2140 + }, + { + "epoch": 0.2853144989339019, + "grad_norm": 0.321180063793256, + "learning_rate": 9.85589946453826e-06, + "loss": 0.4547, + "step": 2141 + }, + { + "epoch": 0.28544776119402987, + "grad_norm": 0.308870265555047, + "learning_rate": 9.855729706015545e-06, + "loss": 0.4898, + "step": 2142 + }, + { + "epoch": 0.28558102345415776, + "grad_norm": 0.2996987175218097, + "learning_rate": 9.855559849022848e-06, + "loss": 0.3955, + "step": 2143 + }, + { + "epoch": 0.2857142857142857, + "grad_norm": 0.3096334691229105, + "learning_rate": 9.855389893563613e-06, + "loss": 0.3814, + "step": 2144 + }, + { + "epoch": 0.28584754797441364, + "grad_norm": 0.3163846179405768, + "learning_rate": 9.855219839641288e-06, + "loss": 0.4461, + "step": 2145 + }, + { + "epoch": 0.2859808102345416, + "grad_norm": 0.34976219924494084, + "learning_rate": 9.85504968725932e-06, + "loss": 0.5219, + "step": 2146 + }, + { + "epoch": 0.2861140724946695, + "grad_norm": 0.33108984991441487, + "learning_rate": 9.854879436421162e-06, + "loss": 0.4344, + "step": 2147 + }, + { + "epoch": 0.28624733475479747, + "grad_norm": 0.33794534954680044, + "learning_rate": 9.854709087130261e-06, + "loss": 0.4704, + "step": 2148 + }, + { + "epoch": 0.28638059701492535, + "grad_norm": 0.3070172603696786, + "learning_rate": 9.854538639390077e-06, + "loss": 0.4121, + "step": 2149 + }, + { + "epoch": 0.2865138592750533, + "grad_norm": 0.33743717984094124, + "learning_rate": 9.854368093204064e-06, + "loss": 0.4877, + "step": 2150 + }, + { + "epoch": 0.28664712153518124, + "grad_norm": 0.30622449790006184, + "learning_rate": 9.854197448575682e-06, + "loss": 0.4074, + "step": 2151 + }, + { + "epoch": 0.2867803837953092, + "grad_norm": 0.32037535848252036, + "learning_rate": 9.85402670550839e-06, + "loss": 0.4916, + "step": 2152 + }, + { + "epoch": 0.2869136460554371, + "grad_norm": 0.32508066556099136, + "learning_rate": 9.853855864005652e-06, + "loss": 0.4222, + "step": 2153 + }, + { + "epoch": 0.287046908315565, + "grad_norm": 0.34575359813773066, + "learning_rate": 9.85368492407093e-06, + "loss": 0.3837, + "step": 2154 + }, + { + "epoch": 0.28718017057569295, + "grad_norm": 0.32159834323206943, + "learning_rate": 9.853513885707694e-06, + "loss": 0.4796, + "step": 2155 + }, + { + "epoch": 0.2873134328358209, + "grad_norm": 0.31139740092530577, + "learning_rate": 9.85334274891941e-06, + "loss": 0.4385, + "step": 2156 + }, + { + "epoch": 0.28744669509594883, + "grad_norm": 0.287430630352531, + "learning_rate": 9.85317151370955e-06, + "loss": 0.4288, + "step": 2157 + }, + { + "epoch": 0.2875799573560768, + "grad_norm": 0.31116860779574246, + "learning_rate": 9.853000180081585e-06, + "loss": 0.4317, + "step": 2158 + }, + { + "epoch": 0.2877132196162047, + "grad_norm": 0.30560424796155283, + "learning_rate": 9.852828748038992e-06, + "loss": 0.389, + "step": 2159 + }, + { + "epoch": 0.2878464818763326, + "grad_norm": 0.32211151157049633, + "learning_rate": 9.852657217585243e-06, + "loss": 0.4042, + "step": 2160 + }, + { + "epoch": 0.28797974413646055, + "grad_norm": 0.31564910643115596, + "learning_rate": 9.852485588723821e-06, + "loss": 0.3953, + "step": 2161 + }, + { + "epoch": 0.2881130063965885, + "grad_norm": 0.3436579542878922, + "learning_rate": 9.852313861458204e-06, + "loss": 0.4763, + "step": 2162 + }, + { + "epoch": 0.28824626865671643, + "grad_norm": 0.3084778813637624, + "learning_rate": 9.852142035791877e-06, + "loss": 0.4197, + "step": 2163 + }, + { + "epoch": 0.2883795309168444, + "grad_norm": 0.3364481926846137, + "learning_rate": 9.851970111728319e-06, + "loss": 0.4844, + "step": 2164 + }, + { + "epoch": 0.28851279317697226, + "grad_norm": 0.3245654292946216, + "learning_rate": 9.851798089271022e-06, + "loss": 0.3855, + "step": 2165 + }, + { + "epoch": 0.2886460554371002, + "grad_norm": 0.3387078181729132, + "learning_rate": 9.851625968423474e-06, + "loss": 0.396, + "step": 2166 + }, + { + "epoch": 0.28877931769722814, + "grad_norm": 0.31702895888331617, + "learning_rate": 9.851453749189163e-06, + "loss": 0.3717, + "step": 2167 + }, + { + "epoch": 0.2889125799573561, + "grad_norm": 0.31095631925763967, + "learning_rate": 9.851281431571584e-06, + "loss": 0.3948, + "step": 2168 + }, + { + "epoch": 0.28904584221748403, + "grad_norm": 0.3592775700111767, + "learning_rate": 9.851109015574228e-06, + "loss": 0.4081, + "step": 2169 + }, + { + "epoch": 0.2891791044776119, + "grad_norm": 0.3158416806109544, + "learning_rate": 9.850936501200594e-06, + "loss": 0.439, + "step": 2170 + }, + { + "epoch": 0.28931236673773986, + "grad_norm": 0.3453143479725374, + "learning_rate": 9.85076388845418e-06, + "loss": 0.454, + "step": 2171 + }, + { + "epoch": 0.2894456289978678, + "grad_norm": 0.3341209096726741, + "learning_rate": 9.850591177338486e-06, + "loss": 0.4054, + "step": 2172 + }, + { + "epoch": 0.28957889125799574, + "grad_norm": 0.35294199975102275, + "learning_rate": 9.850418367857016e-06, + "loss": 0.4754, + "step": 2173 + }, + { + "epoch": 0.2897121535181237, + "grad_norm": 0.2986352711393629, + "learning_rate": 9.850245460013272e-06, + "loss": 0.4179, + "step": 2174 + }, + { + "epoch": 0.2898454157782516, + "grad_norm": 0.3289516290205582, + "learning_rate": 9.850072453810762e-06, + "loss": 0.4237, + "step": 2175 + }, + { + "epoch": 0.2899786780383795, + "grad_norm": 0.3189083640186148, + "learning_rate": 9.849899349252993e-06, + "loss": 0.4893, + "step": 2176 + }, + { + "epoch": 0.29011194029850745, + "grad_norm": 0.310951134190718, + "learning_rate": 9.849726146343479e-06, + "loss": 0.4252, + "step": 2177 + }, + { + "epoch": 0.2902452025586354, + "grad_norm": 0.3284477535822542, + "learning_rate": 9.849552845085729e-06, + "loss": 0.4457, + "step": 2178 + }, + { + "epoch": 0.29037846481876334, + "grad_norm": 0.31901004438464187, + "learning_rate": 9.849379445483255e-06, + "loss": 0.4053, + "step": 2179 + }, + { + "epoch": 0.2905117270788913, + "grad_norm": 0.30149220364323076, + "learning_rate": 9.849205947539579e-06, + "loss": 0.4059, + "step": 2180 + }, + { + "epoch": 0.29064498933901917, + "grad_norm": 0.313837306405872, + "learning_rate": 9.849032351258218e-06, + "loss": 0.4057, + "step": 2181 + }, + { + "epoch": 0.2907782515991471, + "grad_norm": 0.32702668845641414, + "learning_rate": 9.84885865664269e-06, + "loss": 0.431, + "step": 2182 + }, + { + "epoch": 0.29091151385927505, + "grad_norm": 0.3034659549414131, + "learning_rate": 9.84868486369652e-06, + "loss": 0.39, + "step": 2183 + }, + { + "epoch": 0.291044776119403, + "grad_norm": 0.3177496193666999, + "learning_rate": 9.84851097242323e-06, + "loss": 0.4109, + "step": 2184 + }, + { + "epoch": 0.29117803837953093, + "grad_norm": 0.32762387003709526, + "learning_rate": 9.848336982826347e-06, + "loss": 0.5143, + "step": 2185 + }, + { + "epoch": 0.2913113006396588, + "grad_norm": 0.3246491426158628, + "learning_rate": 9.848162894909402e-06, + "loss": 0.4341, + "step": 2186 + }, + { + "epoch": 0.29144456289978676, + "grad_norm": 0.326617233933742, + "learning_rate": 9.847988708675923e-06, + "loss": 0.4214, + "step": 2187 + }, + { + "epoch": 0.2915778251599147, + "grad_norm": 0.34856164712454196, + "learning_rate": 9.84781442412944e-06, + "loss": 0.4861, + "step": 2188 + }, + { + "epoch": 0.29171108742004265, + "grad_norm": 0.3243692806905173, + "learning_rate": 9.847640041273491e-06, + "loss": 0.4158, + "step": 2189 + }, + { + "epoch": 0.2918443496801706, + "grad_norm": 0.3041686122674625, + "learning_rate": 9.847465560111613e-06, + "loss": 0.4002, + "step": 2190 + }, + { + "epoch": 0.29197761194029853, + "grad_norm": 0.30333323261962764, + "learning_rate": 9.847290980647342e-06, + "loss": 0.3661, + "step": 2191 + }, + { + "epoch": 0.2921108742004264, + "grad_norm": 0.31269893074402705, + "learning_rate": 9.847116302884216e-06, + "loss": 0.3898, + "step": 2192 + }, + { + "epoch": 0.29224413646055436, + "grad_norm": 0.32550473889952053, + "learning_rate": 9.846941526825783e-06, + "loss": 0.5986, + "step": 2193 + }, + { + "epoch": 0.2923773987206823, + "grad_norm": 0.40755640653996883, + "learning_rate": 9.846766652475584e-06, + "loss": 0.4431, + "step": 2194 + }, + { + "epoch": 0.29251066098081024, + "grad_norm": 0.3277382304891552, + "learning_rate": 9.846591679837165e-06, + "loss": 0.3764, + "step": 2195 + }, + { + "epoch": 0.2926439232409382, + "grad_norm": 0.3198885694929203, + "learning_rate": 9.846416608914076e-06, + "loss": 0.4011, + "step": 2196 + }, + { + "epoch": 0.2927771855010661, + "grad_norm": 0.3360588176584989, + "learning_rate": 9.846241439709868e-06, + "loss": 0.4366, + "step": 2197 + }, + { + "epoch": 0.292910447761194, + "grad_norm": 0.31009998371868575, + "learning_rate": 9.846066172228088e-06, + "loss": 0.4367, + "step": 2198 + }, + { + "epoch": 0.29304371002132196, + "grad_norm": 0.2956811735106749, + "learning_rate": 9.845890806472296e-06, + "loss": 0.3533, + "step": 2199 + }, + { + "epoch": 0.2931769722814499, + "grad_norm": 0.31635008499537715, + "learning_rate": 9.845715342446045e-06, + "loss": 0.4254, + "step": 2200 + }, + { + "epoch": 0.29331023454157784, + "grad_norm": 0.3046969246111805, + "learning_rate": 9.845539780152895e-06, + "loss": 0.3995, + "step": 2201 + }, + { + "epoch": 0.2934434968017058, + "grad_norm": 0.31197565102036967, + "learning_rate": 9.845364119596408e-06, + "loss": 0.4123, + "step": 2202 + }, + { + "epoch": 0.29357675906183367, + "grad_norm": 0.31618950919488065, + "learning_rate": 9.84518836078014e-06, + "loss": 0.4171, + "step": 2203 + }, + { + "epoch": 0.2937100213219616, + "grad_norm": 0.31316713528062323, + "learning_rate": 9.845012503707662e-06, + "loss": 0.3706, + "step": 2204 + }, + { + "epoch": 0.29384328358208955, + "grad_norm": 0.2964008056718728, + "learning_rate": 9.844836548382536e-06, + "loss": 0.4077, + "step": 2205 + }, + { + "epoch": 0.2939765458422175, + "grad_norm": 0.3214068584198194, + "learning_rate": 9.844660494808333e-06, + "loss": 0.4833, + "step": 2206 + }, + { + "epoch": 0.29410980810234544, + "grad_norm": 0.31934412887744273, + "learning_rate": 9.844484342988621e-06, + "loss": 0.5527, + "step": 2207 + }, + { + "epoch": 0.2942430703624733, + "grad_norm": 0.31071509009182874, + "learning_rate": 9.844308092926973e-06, + "loss": 0.4247, + "step": 2208 + }, + { + "epoch": 0.29437633262260127, + "grad_norm": 0.31879734849541613, + "learning_rate": 9.844131744626963e-06, + "loss": 0.4218, + "step": 2209 + }, + { + "epoch": 0.2945095948827292, + "grad_norm": 0.3094963555794477, + "learning_rate": 9.843955298092168e-06, + "loss": 0.3886, + "step": 2210 + }, + { + "epoch": 0.29464285714285715, + "grad_norm": 0.3428689633671758, + "learning_rate": 9.843778753326165e-06, + "loss": 0.375, + "step": 2211 + }, + { + "epoch": 0.2947761194029851, + "grad_norm": 0.30797348265273916, + "learning_rate": 9.843602110332535e-06, + "loss": 0.5171, + "step": 2212 + }, + { + "epoch": 0.294909381663113, + "grad_norm": 0.3173091822640365, + "learning_rate": 9.84342536911486e-06, + "loss": 0.4179, + "step": 2213 + }, + { + "epoch": 0.2950426439232409, + "grad_norm": 0.30270444792062495, + "learning_rate": 9.843248529676726e-06, + "loss": 0.4407, + "step": 2214 + }, + { + "epoch": 0.29517590618336886, + "grad_norm": 0.3120816200361712, + "learning_rate": 9.843071592021716e-06, + "loss": 0.4981, + "step": 2215 + }, + { + "epoch": 0.2953091684434968, + "grad_norm": 0.3193135730680372, + "learning_rate": 9.842894556153418e-06, + "loss": 0.4564, + "step": 2216 + }, + { + "epoch": 0.29544243070362475, + "grad_norm": 0.32632529528353793, + "learning_rate": 9.842717422075425e-06, + "loss": 0.513, + "step": 2217 + }, + { + "epoch": 0.2955756929637527, + "grad_norm": 0.29870422252454903, + "learning_rate": 9.842540189791327e-06, + "loss": 0.4464, + "step": 2218 + }, + { + "epoch": 0.2957089552238806, + "grad_norm": 0.30291062355162146, + "learning_rate": 9.84236285930472e-06, + "loss": 0.3542, + "step": 2219 + }, + { + "epoch": 0.2958422174840085, + "grad_norm": 0.31601083020387544, + "learning_rate": 9.842185430619197e-06, + "loss": 0.428, + "step": 2220 + }, + { + "epoch": 0.29597547974413646, + "grad_norm": 0.31158966047380116, + "learning_rate": 9.842007903738358e-06, + "loss": 0.4082, + "step": 2221 + }, + { + "epoch": 0.2961087420042644, + "grad_norm": 0.31250583823041206, + "learning_rate": 9.841830278665805e-06, + "loss": 0.41, + "step": 2222 + }, + { + "epoch": 0.29624200426439234, + "grad_norm": 0.3067505701252493, + "learning_rate": 9.841652555405136e-06, + "loss": 0.5409, + "step": 2223 + }, + { + "epoch": 0.29637526652452023, + "grad_norm": 0.3173748599175371, + "learning_rate": 9.841474733959959e-06, + "loss": 0.4349, + "step": 2224 + }, + { + "epoch": 0.2965085287846482, + "grad_norm": 0.3232653862626922, + "learning_rate": 9.841296814333878e-06, + "loss": 0.4297, + "step": 2225 + }, + { + "epoch": 0.2966417910447761, + "grad_norm": 0.30551781650678184, + "learning_rate": 9.841118796530502e-06, + "loss": 0.367, + "step": 2226 + }, + { + "epoch": 0.29677505330490406, + "grad_norm": 0.34916575264506455, + "learning_rate": 9.84094068055344e-06, + "loss": 0.4155, + "step": 2227 + }, + { + "epoch": 0.296908315565032, + "grad_norm": 0.3098610590485389, + "learning_rate": 9.840762466406302e-06, + "loss": 0.3982, + "step": 2228 + }, + { + "epoch": 0.29704157782515994, + "grad_norm": 0.34826452176890177, + "learning_rate": 9.840584154092708e-06, + "loss": 0.5543, + "step": 2229 + }, + { + "epoch": 0.29717484008528783, + "grad_norm": 0.3160330394616263, + "learning_rate": 9.840405743616267e-06, + "loss": 0.4867, + "step": 2230 + }, + { + "epoch": 0.29730810234541577, + "grad_norm": 0.3432716706900488, + "learning_rate": 9.840227234980604e-06, + "loss": 0.5184, + "step": 2231 + }, + { + "epoch": 0.2974413646055437, + "grad_norm": 0.33929807181680527, + "learning_rate": 9.840048628189334e-06, + "loss": 0.5125, + "step": 2232 + }, + { + "epoch": 0.29757462686567165, + "grad_norm": 0.3795585448978735, + "learning_rate": 9.83986992324608e-06, + "loss": 0.4894, + "step": 2233 + }, + { + "epoch": 0.2977078891257996, + "grad_norm": 0.34121712700340284, + "learning_rate": 9.839691120154468e-06, + "loss": 0.398, + "step": 2234 + }, + { + "epoch": 0.2978411513859275, + "grad_norm": 0.3540446941076815, + "learning_rate": 9.83951221891812e-06, + "loss": 0.4561, + "step": 2235 + }, + { + "epoch": 0.2979744136460554, + "grad_norm": 0.323868687302959, + "learning_rate": 9.839333219540668e-06, + "loss": 0.4684, + "step": 2236 + }, + { + "epoch": 0.29810767590618337, + "grad_norm": 0.332786343060739, + "learning_rate": 9.83915412202574e-06, + "loss": 0.5251, + "step": 2237 + }, + { + "epoch": 0.2982409381663113, + "grad_norm": 0.3131312027044204, + "learning_rate": 9.83897492637697e-06, + "loss": 0.4098, + "step": 2238 + }, + { + "epoch": 0.29837420042643925, + "grad_norm": 0.32613594584494987, + "learning_rate": 9.838795632597989e-06, + "loss": 0.3566, + "step": 2239 + }, + { + "epoch": 0.29850746268656714, + "grad_norm": 0.3099903227302112, + "learning_rate": 9.838616240692433e-06, + "loss": 0.3711, + "step": 2240 + }, + { + "epoch": 0.2986407249466951, + "grad_norm": 0.3190056044856831, + "learning_rate": 9.838436750663943e-06, + "loss": 0.4612, + "step": 2241 + }, + { + "epoch": 0.298773987206823, + "grad_norm": 0.3319719584615517, + "learning_rate": 9.838257162516155e-06, + "loss": 0.409, + "step": 2242 + }, + { + "epoch": 0.29890724946695096, + "grad_norm": 0.3358758998577449, + "learning_rate": 9.838077476252715e-06, + "loss": 0.4602, + "step": 2243 + }, + { + "epoch": 0.2990405117270789, + "grad_norm": 0.31620432609897237, + "learning_rate": 9.837897691877263e-06, + "loss": 0.4444, + "step": 2244 + }, + { + "epoch": 0.29917377398720685, + "grad_norm": 0.33665086002300676, + "learning_rate": 9.837717809393446e-06, + "loss": 0.4322, + "step": 2245 + }, + { + "epoch": 0.29930703624733473, + "grad_norm": 0.307410828714878, + "learning_rate": 9.837537828804915e-06, + "loss": 0.4033, + "step": 2246 + }, + { + "epoch": 0.2994402985074627, + "grad_norm": 0.3223127194404204, + "learning_rate": 9.837357750115315e-06, + "loss": 0.5163, + "step": 2247 + }, + { + "epoch": 0.2995735607675906, + "grad_norm": 0.31527002953187666, + "learning_rate": 9.837177573328301e-06, + "loss": 0.4105, + "step": 2248 + }, + { + "epoch": 0.29970682302771856, + "grad_norm": 0.320367972989515, + "learning_rate": 9.836997298447527e-06, + "loss": 0.4114, + "step": 2249 + }, + { + "epoch": 0.2998400852878465, + "grad_norm": 0.3014615544064735, + "learning_rate": 9.836816925476647e-06, + "loss": 0.4751, + "step": 2250 + }, + { + "epoch": 0.2999733475479744, + "grad_norm": 0.32828633441761157, + "learning_rate": 9.836636454419319e-06, + "loss": 0.492, + "step": 2251 + }, + { + "epoch": 0.30010660980810233, + "grad_norm": 0.3104380055396783, + "learning_rate": 9.836455885279205e-06, + "loss": 0.4128, + "step": 2252 + }, + { + "epoch": 0.3002398720682303, + "grad_norm": 0.31179896361361936, + "learning_rate": 9.836275218059965e-06, + "loss": 0.3936, + "step": 2253 + }, + { + "epoch": 0.3003731343283582, + "grad_norm": 0.3205947811468307, + "learning_rate": 9.83609445276526e-06, + "loss": 0.4417, + "step": 2254 + }, + { + "epoch": 0.30050639658848616, + "grad_norm": 0.30673235215092237, + "learning_rate": 9.835913589398763e-06, + "loss": 0.4572, + "step": 2255 + }, + { + "epoch": 0.3006396588486141, + "grad_norm": 0.3057308290957919, + "learning_rate": 9.835732627964134e-06, + "loss": 0.4158, + "step": 2256 + }, + { + "epoch": 0.300772921108742, + "grad_norm": 0.2988737837794102, + "learning_rate": 9.835551568465048e-06, + "loss": 0.3348, + "step": 2257 + }, + { + "epoch": 0.30090618336886993, + "grad_norm": 0.33341748838003055, + "learning_rate": 9.835370410905175e-06, + "loss": 0.389, + "step": 2258 + }, + { + "epoch": 0.30103944562899787, + "grad_norm": 0.30824601676770175, + "learning_rate": 9.835189155288189e-06, + "loss": 0.4293, + "step": 2259 + }, + { + "epoch": 0.3011727078891258, + "grad_norm": 0.3149713705005129, + "learning_rate": 9.835007801617764e-06, + "loss": 0.5248, + "step": 2260 + }, + { + "epoch": 0.30130597014925375, + "grad_norm": 0.30139215451558266, + "learning_rate": 9.83482634989758e-06, + "loss": 0.4332, + "step": 2261 + }, + { + "epoch": 0.30143923240938164, + "grad_norm": 0.3035763957127547, + "learning_rate": 9.834644800131316e-06, + "loss": 0.4509, + "step": 2262 + }, + { + "epoch": 0.3015724946695096, + "grad_norm": 0.3162679066478091, + "learning_rate": 9.834463152322652e-06, + "loss": 0.4096, + "step": 2263 + }, + { + "epoch": 0.3017057569296375, + "grad_norm": 0.31131825376314437, + "learning_rate": 9.834281406475275e-06, + "loss": 0.4553, + "step": 2264 + }, + { + "epoch": 0.30183901918976547, + "grad_norm": 0.3509403549388207, + "learning_rate": 9.834099562592867e-06, + "loss": 0.3727, + "step": 2265 + }, + { + "epoch": 0.3019722814498934, + "grad_norm": 0.3495865074883685, + "learning_rate": 9.833917620679119e-06, + "loss": 0.4778, + "step": 2266 + }, + { + "epoch": 0.3021055437100213, + "grad_norm": 0.32974572080059367, + "learning_rate": 9.833735580737718e-06, + "loss": 0.3885, + "step": 2267 + }, + { + "epoch": 0.30223880597014924, + "grad_norm": 0.8162073165464496, + "learning_rate": 9.833553442772356e-06, + "loss": 0.4395, + "step": 2268 + }, + { + "epoch": 0.3023720682302772, + "grad_norm": 0.35336923791387537, + "learning_rate": 9.83337120678673e-06, + "loss": 0.4135, + "step": 2269 + }, + { + "epoch": 0.3025053304904051, + "grad_norm": 0.362448144893333, + "learning_rate": 9.83318887278453e-06, + "loss": 0.4744, + "step": 2270 + }, + { + "epoch": 0.30263859275053306, + "grad_norm": 0.3382193755581291, + "learning_rate": 9.833006440769458e-06, + "loss": 0.4194, + "step": 2271 + }, + { + "epoch": 0.302771855010661, + "grad_norm": 0.3324080386968548, + "learning_rate": 9.83282391074521e-06, + "loss": 0.4372, + "step": 2272 + }, + { + "epoch": 0.3029051172707889, + "grad_norm": 0.29337896740139274, + "learning_rate": 9.832641282715491e-06, + "loss": 0.3995, + "step": 2273 + }, + { + "epoch": 0.30303837953091683, + "grad_norm": 0.3290528462025232, + "learning_rate": 9.832458556684003e-06, + "loss": 0.3813, + "step": 2274 + }, + { + "epoch": 0.3031716417910448, + "grad_norm": 0.31451370338501616, + "learning_rate": 9.832275732654452e-06, + "loss": 0.3882, + "step": 2275 + }, + { + "epoch": 0.3033049040511727, + "grad_norm": 0.30044445905826456, + "learning_rate": 9.832092810630544e-06, + "loss": 0.4359, + "step": 2276 + }, + { + "epoch": 0.30343816631130066, + "grad_norm": 0.2997153007754767, + "learning_rate": 9.83190979061599e-06, + "loss": 0.3693, + "step": 2277 + }, + { + "epoch": 0.30357142857142855, + "grad_norm": 0.3261390910768391, + "learning_rate": 9.831726672614502e-06, + "loss": 0.3965, + "step": 2278 + }, + { + "epoch": 0.3037046908315565, + "grad_norm": 0.31639822456891764, + "learning_rate": 9.83154345662979e-06, + "loss": 0.3972, + "step": 2279 + }, + { + "epoch": 0.30383795309168443, + "grad_norm": 0.3168709642360065, + "learning_rate": 9.831360142665574e-06, + "loss": 0.4698, + "step": 2280 + }, + { + "epoch": 0.3039712153518124, + "grad_norm": 0.28189530000028257, + "learning_rate": 9.831176730725568e-06, + "loss": 0.3446, + "step": 2281 + }, + { + "epoch": 0.3041044776119403, + "grad_norm": 0.3257148529707776, + "learning_rate": 9.830993220813495e-06, + "loss": 0.4076, + "step": 2282 + }, + { + "epoch": 0.30423773987206826, + "grad_norm": 0.32391764953692886, + "learning_rate": 9.830809612933073e-06, + "loss": 0.4199, + "step": 2283 + }, + { + "epoch": 0.30437100213219614, + "grad_norm": 0.29828164680497327, + "learning_rate": 9.830625907088027e-06, + "loss": 0.3801, + "step": 2284 + }, + { + "epoch": 0.3045042643923241, + "grad_norm": 0.36052263035088217, + "learning_rate": 9.830442103282083e-06, + "loss": 0.464, + "step": 2285 + }, + { + "epoch": 0.30463752665245203, + "grad_norm": 0.32380123380083997, + "learning_rate": 9.830258201518965e-06, + "loss": 0.3822, + "step": 2286 + }, + { + "epoch": 0.30477078891257997, + "grad_norm": 0.3179179836198549, + "learning_rate": 9.830074201802406e-06, + "loss": 0.4606, + "step": 2287 + }, + { + "epoch": 0.3049040511727079, + "grad_norm": 0.3312018515065086, + "learning_rate": 9.829890104136138e-06, + "loss": 0.4303, + "step": 2288 + }, + { + "epoch": 0.3050373134328358, + "grad_norm": 0.31776622534231613, + "learning_rate": 9.82970590852389e-06, + "loss": 0.4241, + "step": 2289 + }, + { + "epoch": 0.30517057569296374, + "grad_norm": 0.33456727015504717, + "learning_rate": 9.829521614969402e-06, + "loss": 0.4447, + "step": 2290 + }, + { + "epoch": 0.3053038379530917, + "grad_norm": 0.3667887370765062, + "learning_rate": 9.829337223476408e-06, + "loss": 0.3989, + "step": 2291 + }, + { + "epoch": 0.3054371002132196, + "grad_norm": 0.3207085635684494, + "learning_rate": 9.829152734048648e-06, + "loss": 0.4319, + "step": 2292 + }, + { + "epoch": 0.30557036247334757, + "grad_norm": 0.33760128063106853, + "learning_rate": 9.828968146689865e-06, + "loss": 0.3513, + "step": 2293 + }, + { + "epoch": 0.30570362473347545, + "grad_norm": 0.3277039943034563, + "learning_rate": 9.8287834614038e-06, + "loss": 0.4907, + "step": 2294 + }, + { + "epoch": 0.3058368869936034, + "grad_norm": 0.3102354059483135, + "learning_rate": 9.8285986781942e-06, + "loss": 0.3523, + "step": 2295 + }, + { + "epoch": 0.30597014925373134, + "grad_norm": 0.3476003898691066, + "learning_rate": 9.828413797064811e-06, + "loss": 0.4583, + "step": 2296 + }, + { + "epoch": 0.3061034115138593, + "grad_norm": 0.3435160161267455, + "learning_rate": 9.828228818019384e-06, + "loss": 0.4582, + "step": 2297 + }, + { + "epoch": 0.3062366737739872, + "grad_norm": 0.5359517103250955, + "learning_rate": 9.828043741061667e-06, + "loss": 0.4953, + "step": 2298 + }, + { + "epoch": 0.30636993603411516, + "grad_norm": 0.3169792098366088, + "learning_rate": 9.827858566195416e-06, + "loss": 0.3972, + "step": 2299 + }, + { + "epoch": 0.30650319829424305, + "grad_norm": 0.33088303302856575, + "learning_rate": 9.827673293424387e-06, + "loss": 0.3676, + "step": 2300 + }, + { + "epoch": 0.306636460554371, + "grad_norm": 0.3172573688345792, + "learning_rate": 9.827487922752334e-06, + "loss": 0.3992, + "step": 2301 + }, + { + "epoch": 0.30676972281449894, + "grad_norm": 0.34581743071081866, + "learning_rate": 9.827302454183017e-06, + "loss": 0.4744, + "step": 2302 + }, + { + "epoch": 0.3069029850746269, + "grad_norm": 0.34434431926037035, + "learning_rate": 9.827116887720199e-06, + "loss": 0.4586, + "step": 2303 + }, + { + "epoch": 0.3070362473347548, + "grad_norm": 0.3355714255493535, + "learning_rate": 9.826931223367642e-06, + "loss": 0.3702, + "step": 2304 + }, + { + "epoch": 0.3071695095948827, + "grad_norm": 0.3124042144676429, + "learning_rate": 9.82674546112911e-06, + "loss": 0.422, + "step": 2305 + }, + { + "epoch": 0.30730277185501065, + "grad_norm": 0.3337121105398621, + "learning_rate": 9.826559601008372e-06, + "loss": 0.4333, + "step": 2306 + }, + { + "epoch": 0.3074360341151386, + "grad_norm": 0.32121068218232307, + "learning_rate": 9.826373643009198e-06, + "loss": 0.462, + "step": 2307 + }, + { + "epoch": 0.30756929637526653, + "grad_norm": 0.3176417071927209, + "learning_rate": 9.826187587135353e-06, + "loss": 0.4045, + "step": 2308 + }, + { + "epoch": 0.3077025586353945, + "grad_norm": 0.32935711104436416, + "learning_rate": 9.826001433390618e-06, + "loss": 0.5161, + "step": 2309 + }, + { + "epoch": 0.30783582089552236, + "grad_norm": 0.31764072732603815, + "learning_rate": 9.825815181778764e-06, + "loss": 0.4956, + "step": 2310 + }, + { + "epoch": 0.3079690831556503, + "grad_norm": 0.33637361810919414, + "learning_rate": 9.825628832303567e-06, + "loss": 0.4089, + "step": 2311 + }, + { + "epoch": 0.30810234541577824, + "grad_norm": 0.301978887602077, + "learning_rate": 9.825442384968808e-06, + "loss": 0.3651, + "step": 2312 + }, + { + "epoch": 0.3082356076759062, + "grad_norm": 0.3073184005127327, + "learning_rate": 9.825255839778267e-06, + "loss": 0.3319, + "step": 2313 + }, + { + "epoch": 0.30836886993603413, + "grad_norm": 0.31544675664784533, + "learning_rate": 9.825069196735728e-06, + "loss": 0.4018, + "step": 2314 + }, + { + "epoch": 0.30850213219616207, + "grad_norm": 0.3495043525653101, + "learning_rate": 9.824882455844976e-06, + "loss": 0.4565, + "step": 2315 + }, + { + "epoch": 0.30863539445628996, + "grad_norm": 0.34817987706401415, + "learning_rate": 9.824695617109796e-06, + "loss": 0.442, + "step": 2316 + }, + { + "epoch": 0.3087686567164179, + "grad_norm": 0.31572429988143264, + "learning_rate": 9.824508680533979e-06, + "loss": 0.4242, + "step": 2317 + }, + { + "epoch": 0.30890191897654584, + "grad_norm": 0.33266843217217257, + "learning_rate": 9.824321646121316e-06, + "loss": 0.4562, + "step": 2318 + }, + { + "epoch": 0.3090351812366738, + "grad_norm": 0.3034055533768297, + "learning_rate": 9.824134513875598e-06, + "loss": 0.3756, + "step": 2319 + }, + { + "epoch": 0.3091684434968017, + "grad_norm": 0.3153255202889744, + "learning_rate": 9.823947283800621e-06, + "loss": 0.3745, + "step": 2320 + }, + { + "epoch": 0.3093017057569296, + "grad_norm": 0.31318695323463486, + "learning_rate": 9.823759955900181e-06, + "loss": 0.4193, + "step": 2321 + }, + { + "epoch": 0.30943496801705755, + "grad_norm": 0.29959869023709057, + "learning_rate": 9.823572530178078e-06, + "loss": 0.4158, + "step": 2322 + }, + { + "epoch": 0.3095682302771855, + "grad_norm": 0.33610214214525364, + "learning_rate": 9.823385006638113e-06, + "loss": 0.4491, + "step": 2323 + }, + { + "epoch": 0.30970149253731344, + "grad_norm": 0.30954149223693334, + "learning_rate": 9.82319738528409e-06, + "loss": 0.4002, + "step": 2324 + }, + { + "epoch": 0.3098347547974414, + "grad_norm": 0.3464661031791616, + "learning_rate": 9.823009666119809e-06, + "loss": 0.4744, + "step": 2325 + }, + { + "epoch": 0.3099680170575693, + "grad_norm": 0.32250965488769173, + "learning_rate": 9.82282184914908e-06, + "loss": 0.3757, + "step": 2326 + }, + { + "epoch": 0.3101012793176972, + "grad_norm": 0.31892762472686526, + "learning_rate": 9.822633934375714e-06, + "loss": 0.4448, + "step": 2327 + }, + { + "epoch": 0.31023454157782515, + "grad_norm": 0.32954682481239406, + "learning_rate": 9.822445921803518e-06, + "loss": 0.4327, + "step": 2328 + }, + { + "epoch": 0.3103678038379531, + "grad_norm": 0.3237064949122703, + "learning_rate": 9.822257811436306e-06, + "loss": 0.4671, + "step": 2329 + }, + { + "epoch": 0.31050106609808104, + "grad_norm": 0.46846265652304725, + "learning_rate": 9.822069603277892e-06, + "loss": 0.4642, + "step": 2330 + }, + { + "epoch": 0.310634328358209, + "grad_norm": 0.32023607544057703, + "learning_rate": 9.821881297332095e-06, + "loss": 0.3865, + "step": 2331 + }, + { + "epoch": 0.31076759061833686, + "grad_norm": 0.3416559896246439, + "learning_rate": 9.821692893602732e-06, + "loss": 0.4636, + "step": 2332 + }, + { + "epoch": 0.3109008528784648, + "grad_norm": 0.3424648890979984, + "learning_rate": 9.821504392093623e-06, + "loss": 0.4837, + "step": 2333 + }, + { + "epoch": 0.31103411513859275, + "grad_norm": 0.3207638073930122, + "learning_rate": 9.821315792808593e-06, + "loss": 0.4116, + "step": 2334 + }, + { + "epoch": 0.3111673773987207, + "grad_norm": 0.33040693692505657, + "learning_rate": 9.821127095751464e-06, + "loss": 0.4071, + "step": 2335 + }, + { + "epoch": 0.31130063965884863, + "grad_norm": 0.2975340228180146, + "learning_rate": 9.820938300926064e-06, + "loss": 0.4642, + "step": 2336 + }, + { + "epoch": 0.3114339019189765, + "grad_norm": 0.30618634762737, + "learning_rate": 9.820749408336222e-06, + "loss": 0.3783, + "step": 2337 + }, + { + "epoch": 0.31156716417910446, + "grad_norm": 0.30944147095659535, + "learning_rate": 9.820560417985768e-06, + "loss": 0.4215, + "step": 2338 + }, + { + "epoch": 0.3117004264392324, + "grad_norm": 0.31450982418138906, + "learning_rate": 9.820371329878532e-06, + "loss": 0.385, + "step": 2339 + }, + { + "epoch": 0.31183368869936035, + "grad_norm": 0.3252885849433757, + "learning_rate": 9.820182144018353e-06, + "loss": 0.3934, + "step": 2340 + }, + { + "epoch": 0.3119669509594883, + "grad_norm": 0.31211617946958653, + "learning_rate": 9.819992860409065e-06, + "loss": 0.3859, + "step": 2341 + }, + { + "epoch": 0.31210021321961623, + "grad_norm": 0.3379167399624769, + "learning_rate": 9.819803479054507e-06, + "loss": 0.3736, + "step": 2342 + }, + { + "epoch": 0.3122334754797441, + "grad_norm": 0.3045721642750325, + "learning_rate": 9.81961399995852e-06, + "loss": 0.4857, + "step": 2343 + }, + { + "epoch": 0.31236673773987206, + "grad_norm": 0.3422241299013482, + "learning_rate": 9.819424423124946e-06, + "loss": 0.4211, + "step": 2344 + }, + { + "epoch": 0.3125, + "grad_norm": 0.32751874681688803, + "learning_rate": 9.819234748557629e-06, + "loss": 0.377, + "step": 2345 + }, + { + "epoch": 0.31263326226012794, + "grad_norm": 0.3716981972420045, + "learning_rate": 9.819044976260416e-06, + "loss": 0.3993, + "step": 2346 + }, + { + "epoch": 0.3127665245202559, + "grad_norm": 0.31529148861685347, + "learning_rate": 9.818855106237156e-06, + "loss": 0.4217, + "step": 2347 + }, + { + "epoch": 0.31289978678038377, + "grad_norm": 0.33344709366225883, + "learning_rate": 9.818665138491698e-06, + "loss": 0.566, + "step": 2348 + }, + { + "epoch": 0.3130330490405117, + "grad_norm": 0.34543147040679834, + "learning_rate": 9.818475073027895e-06, + "loss": 0.4924, + "step": 2349 + }, + { + "epoch": 0.31316631130063965, + "grad_norm": 0.30882851096467406, + "learning_rate": 9.818284909849602e-06, + "loss": 0.469, + "step": 2350 + }, + { + "epoch": 0.3132995735607676, + "grad_norm": 0.32122919792732924, + "learning_rate": 9.818094648960676e-06, + "loss": 0.5089, + "step": 2351 + }, + { + "epoch": 0.31343283582089554, + "grad_norm": 0.31766905197057776, + "learning_rate": 9.817904290364972e-06, + "loss": 0.4775, + "step": 2352 + }, + { + "epoch": 0.3135660980810235, + "grad_norm": 0.31208957522927355, + "learning_rate": 9.817713834066353e-06, + "loss": 0.4502, + "step": 2353 + }, + { + "epoch": 0.31369936034115137, + "grad_norm": 0.3131744553357654, + "learning_rate": 9.817523280068681e-06, + "loss": 0.4346, + "step": 2354 + }, + { + "epoch": 0.3138326226012793, + "grad_norm": 0.3016300475933813, + "learning_rate": 9.81733262837582e-06, + "loss": 0.4176, + "step": 2355 + }, + { + "epoch": 0.31396588486140725, + "grad_norm": 0.31205652834333153, + "learning_rate": 9.817141878991636e-06, + "loss": 0.4036, + "step": 2356 + }, + { + "epoch": 0.3140991471215352, + "grad_norm": 0.30101836764765644, + "learning_rate": 9.816951031919998e-06, + "loss": 0.4189, + "step": 2357 + }, + { + "epoch": 0.31423240938166314, + "grad_norm": 0.3351436648457656, + "learning_rate": 9.816760087164775e-06, + "loss": 0.4895, + "step": 2358 + }, + { + "epoch": 0.314365671641791, + "grad_norm": 0.30626828043497356, + "learning_rate": 9.816569044729842e-06, + "loss": 0.3763, + "step": 2359 + }, + { + "epoch": 0.31449893390191896, + "grad_norm": 0.3287098202309471, + "learning_rate": 9.816377904619068e-06, + "loss": 0.414, + "step": 2360 + }, + { + "epoch": 0.3146321961620469, + "grad_norm": 0.3081679687676874, + "learning_rate": 9.816186666836333e-06, + "loss": 0.4174, + "step": 2361 + }, + { + "epoch": 0.31476545842217485, + "grad_norm": 0.3121999651823896, + "learning_rate": 9.815995331385515e-06, + "loss": 0.3976, + "step": 2362 + }, + { + "epoch": 0.3148987206823028, + "grad_norm": 0.30511247876424796, + "learning_rate": 9.815803898270494e-06, + "loss": 0.44, + "step": 2363 + }, + { + "epoch": 0.3150319829424307, + "grad_norm": 0.30403145067017756, + "learning_rate": 9.81561236749515e-06, + "loss": 0.4506, + "step": 2364 + }, + { + "epoch": 0.3151652452025586, + "grad_norm": 0.3064303572777609, + "learning_rate": 9.81542073906337e-06, + "loss": 0.4174, + "step": 2365 + }, + { + "epoch": 0.31529850746268656, + "grad_norm": 0.3302824508283113, + "learning_rate": 9.81522901297904e-06, + "loss": 0.4489, + "step": 2366 + }, + { + "epoch": 0.3154317697228145, + "grad_norm": 0.3175288891341259, + "learning_rate": 9.815037189246044e-06, + "loss": 0.4567, + "step": 2367 + }, + { + "epoch": 0.31556503198294245, + "grad_norm": 0.3195710172098606, + "learning_rate": 9.814845267868275e-06, + "loss": 0.4772, + "step": 2368 + }, + { + "epoch": 0.3156982942430704, + "grad_norm": 0.29624029849553224, + "learning_rate": 9.814653248849626e-06, + "loss": 0.3788, + "step": 2369 + }, + { + "epoch": 0.3158315565031983, + "grad_norm": 0.2944892122249283, + "learning_rate": 9.81446113219399e-06, + "loss": 0.4152, + "step": 2370 + }, + { + "epoch": 0.3159648187633262, + "grad_norm": 0.29904410971243445, + "learning_rate": 9.814268917905262e-06, + "loss": 0.3525, + "step": 2371 + }, + { + "epoch": 0.31609808102345416, + "grad_norm": 0.31111338489527146, + "learning_rate": 9.814076605987341e-06, + "loss": 0.3535, + "step": 2372 + }, + { + "epoch": 0.3162313432835821, + "grad_norm": 0.29723922848817314, + "learning_rate": 9.813884196444126e-06, + "loss": 0.3765, + "step": 2373 + }, + { + "epoch": 0.31636460554371004, + "grad_norm": 0.3076753113121175, + "learning_rate": 9.81369168927952e-06, + "loss": 0.4888, + "step": 2374 + }, + { + "epoch": 0.31649786780383793, + "grad_norm": 0.2957264933939656, + "learning_rate": 9.813499084497426e-06, + "loss": 0.4404, + "step": 2375 + }, + { + "epoch": 0.31663113006396587, + "grad_norm": 0.31596538767200727, + "learning_rate": 9.813306382101751e-06, + "loss": 0.3912, + "step": 2376 + }, + { + "epoch": 0.3167643923240938, + "grad_norm": 0.3007957641636321, + "learning_rate": 9.813113582096401e-06, + "loss": 0.4051, + "step": 2377 + }, + { + "epoch": 0.31689765458422176, + "grad_norm": 0.290579477708628, + "learning_rate": 9.812920684485287e-06, + "loss": 0.5596, + "step": 2378 + }, + { + "epoch": 0.3170309168443497, + "grad_norm": 0.36205870038311905, + "learning_rate": 9.81272768927232e-06, + "loss": 0.4839, + "step": 2379 + }, + { + "epoch": 0.31716417910447764, + "grad_norm": 0.3211582308561086, + "learning_rate": 9.812534596461415e-06, + "loss": 0.3877, + "step": 2380 + }, + { + "epoch": 0.3172974413646055, + "grad_norm": 0.30248528280524434, + "learning_rate": 9.812341406056487e-06, + "loss": 0.4216, + "step": 2381 + }, + { + "epoch": 0.31743070362473347, + "grad_norm": 0.34093898887913526, + "learning_rate": 9.812148118061455e-06, + "loss": 0.3979, + "step": 2382 + }, + { + "epoch": 0.3175639658848614, + "grad_norm": 0.2997673192449573, + "learning_rate": 9.811954732480236e-06, + "loss": 0.3874, + "step": 2383 + }, + { + "epoch": 0.31769722814498935, + "grad_norm": 0.33005295399126583, + "learning_rate": 9.811761249316755e-06, + "loss": 0.4276, + "step": 2384 + }, + { + "epoch": 0.3178304904051173, + "grad_norm": 0.31416107160960316, + "learning_rate": 9.811567668574932e-06, + "loss": 0.4229, + "step": 2385 + }, + { + "epoch": 0.3179637526652452, + "grad_norm": 0.3087409252322883, + "learning_rate": 9.811373990258697e-06, + "loss": 0.3682, + "step": 2386 + }, + { + "epoch": 0.3180970149253731, + "grad_norm": 0.2920064868531304, + "learning_rate": 9.811180214371974e-06, + "loss": 0.3855, + "step": 2387 + }, + { + "epoch": 0.31823027718550106, + "grad_norm": 0.3265525361766208, + "learning_rate": 9.810986340918694e-06, + "loss": 0.4238, + "step": 2388 + }, + { + "epoch": 0.318363539445629, + "grad_norm": 0.35322929681479676, + "learning_rate": 9.810792369902789e-06, + "loss": 0.3667, + "step": 2389 + }, + { + "epoch": 0.31849680170575695, + "grad_norm": 0.31245745209635245, + "learning_rate": 9.81059830132819e-06, + "loss": 0.4853, + "step": 2390 + }, + { + "epoch": 0.31863006396588484, + "grad_norm": 0.30440407456125307, + "learning_rate": 9.810404135198836e-06, + "loss": 0.4079, + "step": 2391 + }, + { + "epoch": 0.3187633262260128, + "grad_norm": 0.3558341730759711, + "learning_rate": 9.810209871518663e-06, + "loss": 0.4318, + "step": 2392 + }, + { + "epoch": 0.3188965884861407, + "grad_norm": 0.306667199209296, + "learning_rate": 9.810015510291611e-06, + "loss": 0.5002, + "step": 2393 + }, + { + "epoch": 0.31902985074626866, + "grad_norm": 0.3184373185318995, + "learning_rate": 9.809821051521619e-06, + "loss": 0.406, + "step": 2394 + }, + { + "epoch": 0.3191631130063966, + "grad_norm": 0.3089403017060369, + "learning_rate": 9.809626495212635e-06, + "loss": 0.3623, + "step": 2395 + }, + { + "epoch": 0.31929637526652455, + "grad_norm": 0.31040866814979673, + "learning_rate": 9.809431841368602e-06, + "loss": 0.4991, + "step": 2396 + }, + { + "epoch": 0.31942963752665243, + "grad_norm": 0.3204214906646975, + "learning_rate": 9.809237089993467e-06, + "loss": 0.4325, + "step": 2397 + }, + { + "epoch": 0.3195628997867804, + "grad_norm": 0.33312031245039975, + "learning_rate": 9.809042241091178e-06, + "loss": 0.4025, + "step": 2398 + }, + { + "epoch": 0.3196961620469083, + "grad_norm": 0.33182476095935637, + "learning_rate": 9.808847294665688e-06, + "loss": 0.5132, + "step": 2399 + }, + { + "epoch": 0.31982942430703626, + "grad_norm": 0.3487600835645017, + "learning_rate": 9.808652250720953e-06, + "loss": 0.4895, + "step": 2400 + }, + { + "epoch": 0.3199626865671642, + "grad_norm": 0.2983989587068536, + "learning_rate": 9.808457109260925e-06, + "loss": 0.4886, + "step": 2401 + }, + { + "epoch": 0.3200959488272921, + "grad_norm": 0.32787833945190636, + "learning_rate": 9.808261870289562e-06, + "loss": 0.4011, + "step": 2402 + }, + { + "epoch": 0.32022921108742003, + "grad_norm": 0.3342519726459543, + "learning_rate": 9.808066533810821e-06, + "loss": 0.4112, + "step": 2403 + }, + { + "epoch": 0.32036247334754797, + "grad_norm": 0.3258776219982102, + "learning_rate": 9.80787109982867e-06, + "loss": 0.3691, + "step": 2404 + }, + { + "epoch": 0.3204957356076759, + "grad_norm": 0.3234877070989964, + "learning_rate": 9.807675568347064e-06, + "loss": 0.4878, + "step": 2405 + }, + { + "epoch": 0.32062899786780386, + "grad_norm": 0.3768154880599215, + "learning_rate": 9.807479939369972e-06, + "loss": 0.4549, + "step": 2406 + }, + { + "epoch": 0.32076226012793174, + "grad_norm": 0.3366227796712654, + "learning_rate": 9.807284212901363e-06, + "loss": 0.3526, + "step": 2407 + }, + { + "epoch": 0.3208955223880597, + "grad_norm": 0.3073158997891711, + "learning_rate": 9.807088388945205e-06, + "loss": 0.442, + "step": 2408 + }, + { + "epoch": 0.3210287846481876, + "grad_norm": 0.3220973137190878, + "learning_rate": 9.806892467505467e-06, + "loss": 0.4003, + "step": 2409 + }, + { + "epoch": 0.32116204690831557, + "grad_norm": 0.33142328068550475, + "learning_rate": 9.806696448586124e-06, + "loss": 0.4175, + "step": 2410 + }, + { + "epoch": 0.3212953091684435, + "grad_norm": 0.31545227262347375, + "learning_rate": 9.806500332191152e-06, + "loss": 0.4732, + "step": 2411 + }, + { + "epoch": 0.32142857142857145, + "grad_norm": 0.3251829690938, + "learning_rate": 9.806304118324525e-06, + "loss": 0.424, + "step": 2412 + }, + { + "epoch": 0.32156183368869934, + "grad_norm": 0.32855505507721033, + "learning_rate": 9.806107806990225e-06, + "loss": 0.4206, + "step": 2413 + }, + { + "epoch": 0.3216950959488273, + "grad_norm": 0.30620328890561066, + "learning_rate": 9.805911398192232e-06, + "loss": 0.5367, + "step": 2414 + }, + { + "epoch": 0.3218283582089552, + "grad_norm": 0.33649394284143913, + "learning_rate": 9.805714891934528e-06, + "loss": 0.4026, + "step": 2415 + }, + { + "epoch": 0.32196162046908317, + "grad_norm": 0.34108985650822893, + "learning_rate": 9.805518288221099e-06, + "loss": 0.433, + "step": 2416 + }, + { + "epoch": 0.3220948827292111, + "grad_norm": 0.30195491335353736, + "learning_rate": 9.805321587055932e-06, + "loss": 0.4247, + "step": 2417 + }, + { + "epoch": 0.322228144989339, + "grad_norm": 0.31721015409698605, + "learning_rate": 9.805124788443015e-06, + "loss": 0.4362, + "step": 2418 + }, + { + "epoch": 0.32236140724946694, + "grad_norm": 0.31716252678684853, + "learning_rate": 9.804927892386341e-06, + "loss": 0.4498, + "step": 2419 + }, + { + "epoch": 0.3224946695095949, + "grad_norm": 0.3332683329676778, + "learning_rate": 9.8047308988899e-06, + "loss": 0.4613, + "step": 2420 + }, + { + "epoch": 0.3226279317697228, + "grad_norm": 0.3120732061744606, + "learning_rate": 9.80453380795769e-06, + "loss": 0.3957, + "step": 2421 + }, + { + "epoch": 0.32276119402985076, + "grad_norm": 0.33926133627257793, + "learning_rate": 9.804336619593707e-06, + "loss": 0.4332, + "step": 2422 + }, + { + "epoch": 0.3228944562899787, + "grad_norm": 0.31446220604022723, + "learning_rate": 9.804139333801947e-06, + "loss": 0.5055, + "step": 2423 + }, + { + "epoch": 0.3230277185501066, + "grad_norm": 0.3233425501503077, + "learning_rate": 9.803941950586413e-06, + "loss": 0.3972, + "step": 2424 + }, + { + "epoch": 0.32316098081023453, + "grad_norm": 0.3134319045235533, + "learning_rate": 9.803744469951107e-06, + "loss": 0.429, + "step": 2425 + }, + { + "epoch": 0.3232942430703625, + "grad_norm": 0.32918916773924645, + "learning_rate": 9.803546891900036e-06, + "loss": 0.4418, + "step": 2426 + }, + { + "epoch": 0.3234275053304904, + "grad_norm": 0.31677316635349906, + "learning_rate": 9.803349216437203e-06, + "loss": 0.347, + "step": 2427 + }, + { + "epoch": 0.32356076759061836, + "grad_norm": 0.32797328455502434, + "learning_rate": 9.803151443566622e-06, + "loss": 0.4604, + "step": 2428 + }, + { + "epoch": 0.32369402985074625, + "grad_norm": 0.3075074780676649, + "learning_rate": 9.802953573292298e-06, + "loss": 0.4216, + "step": 2429 + }, + { + "epoch": 0.3238272921108742, + "grad_norm": 0.37812952678285583, + "learning_rate": 9.802755605618246e-06, + "loss": 0.4165, + "step": 2430 + }, + { + "epoch": 0.32396055437100213, + "grad_norm": 0.3498052601913122, + "learning_rate": 9.80255754054848e-06, + "loss": 0.373, + "step": 2431 + }, + { + "epoch": 0.32409381663113007, + "grad_norm": 0.3006748781770053, + "learning_rate": 9.80235937808702e-06, + "loss": 0.363, + "step": 2432 + }, + { + "epoch": 0.324227078891258, + "grad_norm": 0.3259327758426406, + "learning_rate": 9.802161118237879e-06, + "loss": 0.3909, + "step": 2433 + }, + { + "epoch": 0.3243603411513859, + "grad_norm": 0.3190911398037234, + "learning_rate": 9.80196276100508e-06, + "loss": 0.4072, + "step": 2434 + }, + { + "epoch": 0.32449360341151384, + "grad_norm": 0.3045591902451715, + "learning_rate": 9.801764306392649e-06, + "loss": 0.4248, + "step": 2435 + }, + { + "epoch": 0.3246268656716418, + "grad_norm": 0.29128248913787985, + "learning_rate": 9.801565754404604e-06, + "loss": 0.427, + "step": 2436 + }, + { + "epoch": 0.3247601279317697, + "grad_norm": 0.3327586470969385, + "learning_rate": 9.801367105044976e-06, + "loss": 0.5347, + "step": 2437 + }, + { + "epoch": 0.32489339019189767, + "grad_norm": 0.30335609917645134, + "learning_rate": 9.801168358317792e-06, + "loss": 0.3918, + "step": 2438 + }, + { + "epoch": 0.3250266524520256, + "grad_norm": 0.5384703942343437, + "learning_rate": 9.800969514227084e-06, + "loss": 0.4676, + "step": 2439 + }, + { + "epoch": 0.3251599147121535, + "grad_norm": 0.3382975358607571, + "learning_rate": 9.800770572776881e-06, + "loss": 0.4094, + "step": 2440 + }, + { + "epoch": 0.32529317697228144, + "grad_norm": 0.35241965927840885, + "learning_rate": 9.800571533971221e-06, + "loss": 0.3898, + "step": 2441 + }, + { + "epoch": 0.3254264392324094, + "grad_norm": 0.2991203987807524, + "learning_rate": 9.800372397814137e-06, + "loss": 0.352, + "step": 2442 + }, + { + "epoch": 0.3255597014925373, + "grad_norm": 0.3081517584198808, + "learning_rate": 9.800173164309671e-06, + "loss": 0.4493, + "step": 2443 + }, + { + "epoch": 0.32569296375266527, + "grad_norm": 0.30626174693821856, + "learning_rate": 9.79997383346186e-06, + "loss": 0.3974, + "step": 2444 + }, + { + "epoch": 0.32582622601279315, + "grad_norm": 0.32533696401468876, + "learning_rate": 9.799774405274748e-06, + "loss": 0.4875, + "step": 2445 + }, + { + "epoch": 0.3259594882729211, + "grad_norm": 1.3121495684916076, + "learning_rate": 9.799574879752379e-06, + "loss": 0.4468, + "step": 2446 + }, + { + "epoch": 0.32609275053304904, + "grad_norm": 0.30050147571474795, + "learning_rate": 9.799375256898797e-06, + "loss": 0.386, + "step": 2447 + }, + { + "epoch": 0.326226012793177, + "grad_norm": 0.46584468935998313, + "learning_rate": 9.799175536718056e-06, + "loss": 0.395, + "step": 2448 + }, + { + "epoch": 0.3263592750533049, + "grad_norm": 0.31829193180961846, + "learning_rate": 9.798975719214199e-06, + "loss": 0.4538, + "step": 2449 + }, + { + "epoch": 0.32649253731343286, + "grad_norm": 0.30563754206994703, + "learning_rate": 9.798775804391281e-06, + "loss": 0.4529, + "step": 2450 + }, + { + "epoch": 0.32662579957356075, + "grad_norm": 0.33389852718130003, + "learning_rate": 9.79857579225336e-06, + "loss": 0.4814, + "step": 2451 + }, + { + "epoch": 0.3267590618336887, + "grad_norm": 0.30912167703935883, + "learning_rate": 9.798375682804486e-06, + "loss": 0.3974, + "step": 2452 + }, + { + "epoch": 0.32689232409381663, + "grad_norm": 0.2935036016034649, + "learning_rate": 9.798175476048719e-06, + "loss": 0.355, + "step": 2453 + }, + { + "epoch": 0.3270255863539446, + "grad_norm": 0.32297195326293643, + "learning_rate": 9.797975171990121e-06, + "loss": 0.3728, + "step": 2454 + }, + { + "epoch": 0.3271588486140725, + "grad_norm": 0.3309016962961695, + "learning_rate": 9.797774770632752e-06, + "loss": 0.5713, + "step": 2455 + }, + { + "epoch": 0.3272921108742004, + "grad_norm": 0.316584692816929, + "learning_rate": 9.797574271980678e-06, + "loss": 0.5404, + "step": 2456 + }, + { + "epoch": 0.32742537313432835, + "grad_norm": 0.3156801666677365, + "learning_rate": 9.797373676037963e-06, + "loss": 0.4153, + "step": 2457 + }, + { + "epoch": 0.3275586353944563, + "grad_norm": 0.3101764188976767, + "learning_rate": 9.797172982808675e-06, + "loss": 0.4077, + "step": 2458 + }, + { + "epoch": 0.32769189765458423, + "grad_norm": 0.331783474484944, + "learning_rate": 9.796972192296885e-06, + "loss": 0.4071, + "step": 2459 + }, + { + "epoch": 0.32782515991471217, + "grad_norm": 0.3236498573403448, + "learning_rate": 9.796771304506662e-06, + "loss": 0.3885, + "step": 2460 + }, + { + "epoch": 0.32795842217484006, + "grad_norm": 0.30969078517893533, + "learning_rate": 9.796570319442084e-06, + "loss": 0.4314, + "step": 2461 + }, + { + "epoch": 0.328091684434968, + "grad_norm": 0.3053267611221277, + "learning_rate": 9.796369237107226e-06, + "loss": 0.4514, + "step": 2462 + }, + { + "epoch": 0.32822494669509594, + "grad_norm": 0.3324340433743242, + "learning_rate": 9.796168057506163e-06, + "loss": 0.3841, + "step": 2463 + }, + { + "epoch": 0.3283582089552239, + "grad_norm": 0.30876789957723216, + "learning_rate": 9.795966780642975e-06, + "loss": 0.3471, + "step": 2464 + }, + { + "epoch": 0.3284914712153518, + "grad_norm": 0.3122335323802718, + "learning_rate": 9.795765406521748e-06, + "loss": 0.3765, + "step": 2465 + }, + { + "epoch": 0.32862473347547977, + "grad_norm": 0.3083813991864737, + "learning_rate": 9.795563935146561e-06, + "loss": 0.3822, + "step": 2466 + }, + { + "epoch": 0.32875799573560766, + "grad_norm": 0.3121290673283017, + "learning_rate": 9.795362366521502e-06, + "loss": 0.3683, + "step": 2467 + }, + { + "epoch": 0.3288912579957356, + "grad_norm": 0.3542315770717939, + "learning_rate": 9.79516070065066e-06, + "loss": 0.4764, + "step": 2468 + }, + { + "epoch": 0.32902452025586354, + "grad_norm": 0.31830508790516565, + "learning_rate": 9.79495893753812e-06, + "loss": 0.4262, + "step": 2469 + }, + { + "epoch": 0.3291577825159915, + "grad_norm": 0.34209150125957216, + "learning_rate": 9.794757077187977e-06, + "loss": 0.4326, + "step": 2470 + }, + { + "epoch": 0.3292910447761194, + "grad_norm": 0.32144847203289934, + "learning_rate": 9.794555119604323e-06, + "loss": 0.4533, + "step": 2471 + }, + { + "epoch": 0.3294243070362473, + "grad_norm": 0.3277093362756287, + "learning_rate": 9.794353064791255e-06, + "loss": 0.4662, + "step": 2472 + }, + { + "epoch": 0.32955756929637525, + "grad_norm": 0.3244940585306073, + "learning_rate": 9.794150912752872e-06, + "loss": 0.372, + "step": 2473 + }, + { + "epoch": 0.3296908315565032, + "grad_norm": 0.3314366637116717, + "learning_rate": 9.793948663493268e-06, + "loss": 0.4367, + "step": 2474 + }, + { + "epoch": 0.32982409381663114, + "grad_norm": 0.3282781395265489, + "learning_rate": 9.79374631701655e-06, + "loss": 0.4379, + "step": 2475 + }, + { + "epoch": 0.3299573560767591, + "grad_norm": 0.3075018301027835, + "learning_rate": 9.793543873326818e-06, + "loss": 0.387, + "step": 2476 + }, + { + "epoch": 0.330090618336887, + "grad_norm": 0.3192730531696718, + "learning_rate": 9.793341332428177e-06, + "loss": 0.3907, + "step": 2477 + }, + { + "epoch": 0.3302238805970149, + "grad_norm": 0.30953146533133297, + "learning_rate": 9.793138694324738e-06, + "loss": 0.388, + "step": 2478 + }, + { + "epoch": 0.33035714285714285, + "grad_norm": 0.30695071320432693, + "learning_rate": 9.792935959020608e-06, + "loss": 0.381, + "step": 2479 + }, + { + "epoch": 0.3304904051172708, + "grad_norm": 0.312932123004393, + "learning_rate": 9.7927331265199e-06, + "loss": 0.4441, + "step": 2480 + }, + { + "epoch": 0.33062366737739873, + "grad_norm": 0.31787068628097104, + "learning_rate": 9.792530196826723e-06, + "loss": 0.3962, + "step": 2481 + }, + { + "epoch": 0.3307569296375267, + "grad_norm": 0.3354568769083684, + "learning_rate": 9.792327169945197e-06, + "loss": 0.4775, + "step": 2482 + }, + { + "epoch": 0.33089019189765456, + "grad_norm": 0.312738241526604, + "learning_rate": 9.792124045879436e-06, + "loss": 0.3887, + "step": 2483 + }, + { + "epoch": 0.3310234541577825, + "grad_norm": 0.32658037545618224, + "learning_rate": 9.79192082463356e-06, + "loss": 0.3704, + "step": 2484 + }, + { + "epoch": 0.33115671641791045, + "grad_norm": 0.32424755717666126, + "learning_rate": 9.791717506211693e-06, + "loss": 0.4879, + "step": 2485 + }, + { + "epoch": 0.3312899786780384, + "grad_norm": 0.32017428831555556, + "learning_rate": 9.791514090617954e-06, + "loss": 0.4178, + "step": 2486 + }, + { + "epoch": 0.33142324093816633, + "grad_norm": 0.33007068082699653, + "learning_rate": 9.79131057785647e-06, + "loss": 0.3948, + "step": 2487 + }, + { + "epoch": 0.3315565031982942, + "grad_norm": 0.35091418690845766, + "learning_rate": 9.791106967931367e-06, + "loss": 0.4719, + "step": 2488 + }, + { + "epoch": 0.33168976545842216, + "grad_norm": 0.3105483308129227, + "learning_rate": 9.790903260846776e-06, + "loss": 0.3857, + "step": 2489 + }, + { + "epoch": 0.3318230277185501, + "grad_norm": 0.3192864965057659, + "learning_rate": 9.790699456606827e-06, + "loss": 0.4449, + "step": 2490 + }, + { + "epoch": 0.33195628997867804, + "grad_norm": 0.3268005398227439, + "learning_rate": 9.790495555215652e-06, + "loss": 0.341, + "step": 2491 + }, + { + "epoch": 0.332089552238806, + "grad_norm": 0.32773485419668175, + "learning_rate": 9.790291556677387e-06, + "loss": 0.4635, + "step": 2492 + }, + { + "epoch": 0.3322228144989339, + "grad_norm": 0.3237882025528692, + "learning_rate": 9.79008746099617e-06, + "loss": 0.4106, + "step": 2493 + }, + { + "epoch": 0.3323560767590618, + "grad_norm": 0.30689277931719344, + "learning_rate": 9.789883268176136e-06, + "loss": 0.3868, + "step": 2494 + }, + { + "epoch": 0.33248933901918976, + "grad_norm": 0.3222389449626225, + "learning_rate": 9.78967897822143e-06, + "loss": 0.4218, + "step": 2495 + }, + { + "epoch": 0.3326226012793177, + "grad_norm": 0.3193890318556742, + "learning_rate": 9.789474591136195e-06, + "loss": 0.5048, + "step": 2496 + }, + { + "epoch": 0.33275586353944564, + "grad_norm": 0.3153652067682853, + "learning_rate": 9.789270106924571e-06, + "loss": 0.4079, + "step": 2497 + }, + { + "epoch": 0.3328891257995736, + "grad_norm": 0.34105416265225397, + "learning_rate": 9.789065525590708e-06, + "loss": 0.4717, + "step": 2498 + }, + { + "epoch": 0.33302238805970147, + "grad_norm": 0.3085494352940443, + "learning_rate": 9.788860847138756e-06, + "loss": 0.3933, + "step": 2499 + }, + { + "epoch": 0.3331556503198294, + "grad_norm": 0.29423595695108723, + "learning_rate": 9.788656071572864e-06, + "loss": 0.42, + "step": 2500 + }, + { + "epoch": 0.33328891257995735, + "grad_norm": 0.3065871086768866, + "learning_rate": 9.788451198897186e-06, + "loss": 0.4403, + "step": 2501 + }, + { + "epoch": 0.3334221748400853, + "grad_norm": 0.3143637710352816, + "learning_rate": 9.788246229115875e-06, + "loss": 0.4778, + "step": 2502 + }, + { + "epoch": 0.33355543710021324, + "grad_norm": 0.30744450381598437, + "learning_rate": 9.788041162233087e-06, + "loss": 0.393, + "step": 2503 + }, + { + "epoch": 0.3336886993603412, + "grad_norm": 0.30694265148321387, + "learning_rate": 9.78783599825298e-06, + "loss": 0.4356, + "step": 2504 + }, + { + "epoch": 0.33382196162046907, + "grad_norm": 0.30762934211505094, + "learning_rate": 9.787630737179721e-06, + "loss": 0.447, + "step": 2505 + }, + { + "epoch": 0.333955223880597, + "grad_norm": 0.3063321760273899, + "learning_rate": 9.787425379017464e-06, + "loss": 0.4937, + "step": 2506 + }, + { + "epoch": 0.33408848614072495, + "grad_norm": 0.3011021904821261, + "learning_rate": 9.787219923770379e-06, + "loss": 0.4518, + "step": 2507 + }, + { + "epoch": 0.3342217484008529, + "grad_norm": 0.3110526328210695, + "learning_rate": 9.78701437144263e-06, + "loss": 0.3866, + "step": 2508 + }, + { + "epoch": 0.33435501066098083, + "grad_norm": 0.31001155070318953, + "learning_rate": 9.786808722038389e-06, + "loss": 0.4482, + "step": 2509 + }, + { + "epoch": 0.3344882729211087, + "grad_norm": 0.30691340037866316, + "learning_rate": 9.786602975561819e-06, + "loss": 0.4119, + "step": 2510 + }, + { + "epoch": 0.33462153518123666, + "grad_norm": 0.3063306950371557, + "learning_rate": 9.786397132017098e-06, + "loss": 0.3895, + "step": 2511 + }, + { + "epoch": 0.3347547974413646, + "grad_norm": 0.3157179678017353, + "learning_rate": 9.786191191408402e-06, + "loss": 0.4101, + "step": 2512 + }, + { + "epoch": 0.33488805970149255, + "grad_norm": 0.29944123704729997, + "learning_rate": 9.785985153739903e-06, + "loss": 0.3945, + "step": 2513 + }, + { + "epoch": 0.3350213219616205, + "grad_norm": 0.3263519076007375, + "learning_rate": 9.78577901901578e-06, + "loss": 0.3804, + "step": 2514 + }, + { + "epoch": 0.3351545842217484, + "grad_norm": 0.30478962061471887, + "learning_rate": 9.785572787240216e-06, + "loss": 0.4076, + "step": 2515 + }, + { + "epoch": 0.3352878464818763, + "grad_norm": 0.3146918401754077, + "learning_rate": 9.785366458417389e-06, + "loss": 0.4645, + "step": 2516 + }, + { + "epoch": 0.33542110874200426, + "grad_norm": 0.3177324102511219, + "learning_rate": 9.785160032551486e-06, + "loss": 0.4856, + "step": 2517 + }, + { + "epoch": 0.3355543710021322, + "grad_norm": 0.30678246446872703, + "learning_rate": 9.784953509646694e-06, + "loss": 0.4546, + "step": 2518 + }, + { + "epoch": 0.33568763326226014, + "grad_norm": 0.31317891493981687, + "learning_rate": 9.784746889707198e-06, + "loss": 0.4506, + "step": 2519 + }, + { + "epoch": 0.3358208955223881, + "grad_norm": 0.32084907361995385, + "learning_rate": 9.784540172737191e-06, + "loss": 0.4278, + "step": 2520 + }, + { + "epoch": 0.33595415778251597, + "grad_norm": 0.321407247712807, + "learning_rate": 9.784333358740863e-06, + "loss": 0.4671, + "step": 2521 + }, + { + "epoch": 0.3360874200426439, + "grad_norm": 0.32852296467791087, + "learning_rate": 9.784126447722408e-06, + "loss": 0.5125, + "step": 2522 + }, + { + "epoch": 0.33622068230277186, + "grad_norm": 0.48853961194193857, + "learning_rate": 9.783919439686024e-06, + "loss": 0.3967, + "step": 2523 + }, + { + "epoch": 0.3363539445628998, + "grad_norm": 0.3110404800246154, + "learning_rate": 9.78371233463591e-06, + "loss": 0.4003, + "step": 2524 + }, + { + "epoch": 0.33648720682302774, + "grad_norm": 0.30659151037612015, + "learning_rate": 9.78350513257626e-06, + "loss": 0.3818, + "step": 2525 + }, + { + "epoch": 0.3366204690831556, + "grad_norm": 0.3244923663850256, + "learning_rate": 9.78329783351128e-06, + "loss": 0.4808, + "step": 2526 + }, + { + "epoch": 0.33675373134328357, + "grad_norm": 0.31651495465037766, + "learning_rate": 9.783090437445174e-06, + "loss": 0.4681, + "step": 2527 + }, + { + "epoch": 0.3368869936034115, + "grad_norm": 0.3057462137239042, + "learning_rate": 9.782882944382146e-06, + "loss": 0.3723, + "step": 2528 + }, + { + "epoch": 0.33702025586353945, + "grad_norm": 0.33887371599878774, + "learning_rate": 9.782675354326406e-06, + "loss": 0.393, + "step": 2529 + }, + { + "epoch": 0.3371535181236674, + "grad_norm": 0.29428736783695386, + "learning_rate": 9.782467667282162e-06, + "loss": 0.4055, + "step": 2530 + }, + { + "epoch": 0.3372867803837953, + "grad_norm": 0.32280763815900054, + "learning_rate": 9.782259883253629e-06, + "loss": 0.4566, + "step": 2531 + }, + { + "epoch": 0.3374200426439232, + "grad_norm": 0.3270464817839003, + "learning_rate": 9.782052002245015e-06, + "loss": 0.4251, + "step": 2532 + }, + { + "epoch": 0.33755330490405117, + "grad_norm": 0.32407939821096476, + "learning_rate": 9.78184402426054e-06, + "loss": 0.4067, + "step": 2533 + }, + { + "epoch": 0.3376865671641791, + "grad_norm": 0.33987540748864337, + "learning_rate": 9.78163594930442e-06, + "loss": 0.3952, + "step": 2534 + }, + { + "epoch": 0.33781982942430705, + "grad_norm": 0.296066097186563, + "learning_rate": 9.781427777380875e-06, + "loss": 0.4634, + "step": 2535 + }, + { + "epoch": 0.337953091684435, + "grad_norm": 0.33842866603936406, + "learning_rate": 9.781219508494126e-06, + "loss": 0.454, + "step": 2536 + }, + { + "epoch": 0.3380863539445629, + "grad_norm": 0.315924940389636, + "learning_rate": 9.781011142648397e-06, + "loss": 0.4409, + "step": 2537 + }, + { + "epoch": 0.3382196162046908, + "grad_norm": 0.31907760735678625, + "learning_rate": 9.780802679847915e-06, + "loss": 0.4529, + "step": 2538 + }, + { + "epoch": 0.33835287846481876, + "grad_norm": 0.3505051100454161, + "learning_rate": 9.780594120096905e-06, + "loss": 0.4142, + "step": 2539 + }, + { + "epoch": 0.3384861407249467, + "grad_norm": 0.3126643189507147, + "learning_rate": 9.780385463399597e-06, + "loss": 0.3921, + "step": 2540 + }, + { + "epoch": 0.33861940298507465, + "grad_norm": 0.34265052875027585, + "learning_rate": 9.780176709760222e-06, + "loss": 0.4697, + "step": 2541 + }, + { + "epoch": 0.33875266524520253, + "grad_norm": 0.32461209750556086, + "learning_rate": 9.779967859183014e-06, + "loss": 0.4494, + "step": 2542 + }, + { + "epoch": 0.3388859275053305, + "grad_norm": 0.3387044198946874, + "learning_rate": 9.779758911672211e-06, + "loss": 0.4592, + "step": 2543 + }, + { + "epoch": 0.3390191897654584, + "grad_norm": 0.31326521790741624, + "learning_rate": 9.779549867232046e-06, + "loss": 0.4456, + "step": 2544 + }, + { + "epoch": 0.33915245202558636, + "grad_norm": 0.34429561321952123, + "learning_rate": 9.779340725866759e-06, + "loss": 0.4306, + "step": 2545 + }, + { + "epoch": 0.3392857142857143, + "grad_norm": 0.3540357763337586, + "learning_rate": 9.779131487580593e-06, + "loss": 0.4211, + "step": 2546 + }, + { + "epoch": 0.33941897654584224, + "grad_norm": 0.31594365257983414, + "learning_rate": 9.77892215237779e-06, + "loss": 0.4708, + "step": 2547 + }, + { + "epoch": 0.33955223880597013, + "grad_norm": 0.3813567321873813, + "learning_rate": 9.778712720262594e-06, + "loss": 0.4242, + "step": 2548 + }, + { + "epoch": 0.3396855010660981, + "grad_norm": 0.29341551404739546, + "learning_rate": 9.778503191239255e-06, + "loss": 0.4316, + "step": 2549 + }, + { + "epoch": 0.339818763326226, + "grad_norm": 0.3340371786102754, + "learning_rate": 9.77829356531202e-06, + "loss": 0.4648, + "step": 2550 + }, + { + "epoch": 0.33995202558635396, + "grad_norm": 0.3100901623763265, + "learning_rate": 9.778083842485142e-06, + "loss": 0.4828, + "step": 2551 + }, + { + "epoch": 0.3400852878464819, + "grad_norm": 0.3387147781976711, + "learning_rate": 9.77787402276287e-06, + "loss": 0.463, + "step": 2552 + }, + { + "epoch": 0.3402185501066098, + "grad_norm": 0.2996237516226404, + "learning_rate": 9.777664106149462e-06, + "loss": 0.416, + "step": 2553 + }, + { + "epoch": 0.3403518123667377, + "grad_norm": 0.31776146206475, + "learning_rate": 9.777454092649177e-06, + "loss": 0.3607, + "step": 2554 + }, + { + "epoch": 0.34048507462686567, + "grad_norm": 0.29928633328150817, + "learning_rate": 9.77724398226627e-06, + "loss": 0.3619, + "step": 2555 + }, + { + "epoch": 0.3406183368869936, + "grad_norm": 0.3412496825121221, + "learning_rate": 9.777033775005e-06, + "loss": 0.509, + "step": 2556 + }, + { + "epoch": 0.34075159914712155, + "grad_norm": 0.3099971157114031, + "learning_rate": 9.776823470869636e-06, + "loss": 0.4114, + "step": 2557 + }, + { + "epoch": 0.34088486140724944, + "grad_norm": 0.3051911972801441, + "learning_rate": 9.77661306986444e-06, + "loss": 0.3763, + "step": 2558 + }, + { + "epoch": 0.3410181236673774, + "grad_norm": 0.30203562935789463, + "learning_rate": 9.776402571993679e-06, + "loss": 0.3949, + "step": 2559 + }, + { + "epoch": 0.3411513859275053, + "grad_norm": 0.41478855116038543, + "learning_rate": 9.77619197726162e-06, + "loss": 0.3977, + "step": 2560 + }, + { + "epoch": 0.34128464818763327, + "grad_norm": 0.34142014377971536, + "learning_rate": 9.775981285672536e-06, + "loss": 0.4513, + "step": 2561 + }, + { + "epoch": 0.3414179104477612, + "grad_norm": 0.32505315975959775, + "learning_rate": 9.775770497230697e-06, + "loss": 0.4255, + "step": 2562 + }, + { + "epoch": 0.34155117270788915, + "grad_norm": 0.3384585489818243, + "learning_rate": 9.775559611940379e-06, + "loss": 0.4233, + "step": 2563 + }, + { + "epoch": 0.34168443496801704, + "grad_norm": 0.3398449956292653, + "learning_rate": 9.775348629805862e-06, + "loss": 0.438, + "step": 2564 + }, + { + "epoch": 0.341817697228145, + "grad_norm": 0.35409205264930965, + "learning_rate": 9.775137550831418e-06, + "loss": 0.4327, + "step": 2565 + }, + { + "epoch": 0.3419509594882729, + "grad_norm": 0.33205021882954383, + "learning_rate": 9.774926375021332e-06, + "loss": 0.4099, + "step": 2566 + }, + { + "epoch": 0.34208422174840086, + "grad_norm": 0.33991619110924814, + "learning_rate": 9.774715102379884e-06, + "loss": 0.5886, + "step": 2567 + }, + { + "epoch": 0.3422174840085288, + "grad_norm": 0.31313829889909833, + "learning_rate": 9.77450373291136e-06, + "loss": 0.3872, + "step": 2568 + }, + { + "epoch": 0.3423507462686567, + "grad_norm": 0.3249988292778109, + "learning_rate": 9.774292266620048e-06, + "loss": 0.4258, + "step": 2569 + }, + { + "epoch": 0.34248400852878463, + "grad_norm": 0.3007113904219029, + "learning_rate": 9.774080703510233e-06, + "loss": 0.4299, + "step": 2570 + }, + { + "epoch": 0.3426172707889126, + "grad_norm": 0.36355196250366933, + "learning_rate": 9.773869043586208e-06, + "loss": 0.4448, + "step": 2571 + }, + { + "epoch": 0.3427505330490405, + "grad_norm": 0.3308381500989383, + "learning_rate": 9.773657286852261e-06, + "loss": 0.5023, + "step": 2572 + }, + { + "epoch": 0.34288379530916846, + "grad_norm": 0.36250577171066817, + "learning_rate": 9.773445433312691e-06, + "loss": 0.3677, + "step": 2573 + }, + { + "epoch": 0.3430170575692964, + "grad_norm": 0.3242795472950788, + "learning_rate": 9.773233482971793e-06, + "loss": 0.3564, + "step": 2574 + }, + { + "epoch": 0.3431503198294243, + "grad_norm": 0.31659676729270214, + "learning_rate": 9.773021435833864e-06, + "loss": 0.4048, + "step": 2575 + }, + { + "epoch": 0.34328358208955223, + "grad_norm": 0.33980328733118914, + "learning_rate": 9.772809291903205e-06, + "loss": 0.4349, + "step": 2576 + }, + { + "epoch": 0.3434168443496802, + "grad_norm": 0.3113882149351746, + "learning_rate": 9.772597051184118e-06, + "loss": 0.3883, + "step": 2577 + }, + { + "epoch": 0.3435501066098081, + "grad_norm": 0.32167961143922197, + "learning_rate": 9.772384713680907e-06, + "loss": 0.4318, + "step": 2578 + }, + { + "epoch": 0.34368336886993606, + "grad_norm": 0.34590519344717663, + "learning_rate": 9.772172279397878e-06, + "loss": 0.4301, + "step": 2579 + }, + { + "epoch": 0.34381663113006394, + "grad_norm": 0.3171593329515051, + "learning_rate": 9.77195974833934e-06, + "loss": 0.4235, + "step": 2580 + }, + { + "epoch": 0.3439498933901919, + "grad_norm": 0.3578896201792474, + "learning_rate": 9.7717471205096e-06, + "loss": 0.4721, + "step": 2581 + }, + { + "epoch": 0.3440831556503198, + "grad_norm": 0.32331602846242813, + "learning_rate": 9.771534395912972e-06, + "loss": 0.3418, + "step": 2582 + }, + { + "epoch": 0.34421641791044777, + "grad_norm": 0.34014549467818667, + "learning_rate": 9.77132157455377e-06, + "loss": 0.432, + "step": 2583 + }, + { + "epoch": 0.3443496801705757, + "grad_norm": 0.3156239164625302, + "learning_rate": 9.77110865643631e-06, + "loss": 0.426, + "step": 2584 + }, + { + "epoch": 0.3444829424307036, + "grad_norm": 0.32576554606077857, + "learning_rate": 9.770895641564909e-06, + "loss": 0.4705, + "step": 2585 + }, + { + "epoch": 0.34461620469083154, + "grad_norm": 0.31220810852549263, + "learning_rate": 9.770682529943885e-06, + "loss": 0.4408, + "step": 2586 + }, + { + "epoch": 0.3447494669509595, + "grad_norm": 0.3457493624401948, + "learning_rate": 9.770469321577564e-06, + "loss": 0.4139, + "step": 2587 + }, + { + "epoch": 0.3448827292110874, + "grad_norm": 0.38636487256682805, + "learning_rate": 9.770256016470268e-06, + "loss": 0.4123, + "step": 2588 + }, + { + "epoch": 0.34501599147121537, + "grad_norm": 0.3265369884440307, + "learning_rate": 9.77004261462632e-06, + "loss": 0.3824, + "step": 2589 + }, + { + "epoch": 0.3451492537313433, + "grad_norm": 0.3029146896351412, + "learning_rate": 9.76982911605005e-06, + "loss": 0.371, + "step": 2590 + }, + { + "epoch": 0.3452825159914712, + "grad_norm": 0.29611540518225415, + "learning_rate": 9.769615520745788e-06, + "loss": 0.5043, + "step": 2591 + }, + { + "epoch": 0.34541577825159914, + "grad_norm": 0.3074889232004526, + "learning_rate": 9.769401828717863e-06, + "loss": 0.4511, + "step": 2592 + }, + { + "epoch": 0.3455490405117271, + "grad_norm": 0.30036406704666885, + "learning_rate": 9.769188039970614e-06, + "loss": 0.3832, + "step": 2593 + }, + { + "epoch": 0.345682302771855, + "grad_norm": 0.31424700307412706, + "learning_rate": 9.76897415450837e-06, + "loss": 0.5055, + "step": 2594 + }, + { + "epoch": 0.34581556503198296, + "grad_norm": 0.31137315337982285, + "learning_rate": 9.768760172335471e-06, + "loss": 0.4096, + "step": 2595 + }, + { + "epoch": 0.34594882729211085, + "grad_norm": 0.3107118887259604, + "learning_rate": 9.768546093456258e-06, + "loss": 0.4484, + "step": 2596 + }, + { + "epoch": 0.3460820895522388, + "grad_norm": 0.2985260795817976, + "learning_rate": 9.768331917875069e-06, + "loss": 0.4257, + "step": 2597 + }, + { + "epoch": 0.34621535181236673, + "grad_norm": 0.3144575333392463, + "learning_rate": 9.768117645596251e-06, + "loss": 0.4176, + "step": 2598 + }, + { + "epoch": 0.3463486140724947, + "grad_norm": 0.3190269797513344, + "learning_rate": 9.767903276624147e-06, + "loss": 0.4396, + "step": 2599 + }, + { + "epoch": 0.3464818763326226, + "grad_norm": 0.30031489461330274, + "learning_rate": 9.767688810963103e-06, + "loss": 0.3925, + "step": 2600 + }, + { + "epoch": 0.34661513859275056, + "grad_norm": 0.32001954316328163, + "learning_rate": 9.76747424861747e-06, + "loss": 0.4275, + "step": 2601 + }, + { + "epoch": 0.34674840085287845, + "grad_norm": 0.2932654698676856, + "learning_rate": 9.7672595895916e-06, + "loss": 0.3241, + "step": 2602 + }, + { + "epoch": 0.3468816631130064, + "grad_norm": 0.3137492642014689, + "learning_rate": 9.767044833889846e-06, + "loss": 0.4204, + "step": 2603 + }, + { + "epoch": 0.34701492537313433, + "grad_norm": 0.3128845424190114, + "learning_rate": 9.766829981516558e-06, + "loss": 0.3801, + "step": 2604 + }, + { + "epoch": 0.3471481876332623, + "grad_norm": 0.29525929509751525, + "learning_rate": 9.7666150324761e-06, + "loss": 0.4109, + "step": 2605 + }, + { + "epoch": 0.3472814498933902, + "grad_norm": 1.2314989235298452, + "learning_rate": 9.76639998677283e-06, + "loss": 0.4576, + "step": 2606 + }, + { + "epoch": 0.3474147121535181, + "grad_norm": 0.3332602071614081, + "learning_rate": 9.766184844411103e-06, + "loss": 0.4293, + "step": 2607 + }, + { + "epoch": 0.34754797441364604, + "grad_norm": 0.3459732804230611, + "learning_rate": 9.765969605395289e-06, + "loss": 0.4729, + "step": 2608 + }, + { + "epoch": 0.347681236673774, + "grad_norm": 0.3211137180845028, + "learning_rate": 9.765754269729747e-06, + "loss": 0.4232, + "step": 2609 + }, + { + "epoch": 0.3478144989339019, + "grad_norm": 0.3186931571336032, + "learning_rate": 9.76553883741885e-06, + "loss": 0.4074, + "step": 2610 + }, + { + "epoch": 0.34794776119402987, + "grad_norm": 0.3158214605583753, + "learning_rate": 9.76532330846696e-06, + "loss": 0.4268, + "step": 2611 + }, + { + "epoch": 0.34808102345415776, + "grad_norm": 0.3157076163970905, + "learning_rate": 9.765107682878455e-06, + "loss": 0.454, + "step": 2612 + }, + { + "epoch": 0.3482142857142857, + "grad_norm": 0.32019960578367845, + "learning_rate": 9.7648919606577e-06, + "loss": 0.4691, + "step": 2613 + }, + { + "epoch": 0.34834754797441364, + "grad_norm": 0.5623752720704726, + "learning_rate": 9.764676141809074e-06, + "loss": 0.4235, + "step": 2614 + }, + { + "epoch": 0.3484808102345416, + "grad_norm": 0.31594504076531127, + "learning_rate": 9.764460226336953e-06, + "loss": 0.4258, + "step": 2615 + }, + { + "epoch": 0.3486140724946695, + "grad_norm": 0.3183663852479738, + "learning_rate": 9.764244214245718e-06, + "loss": 0.3971, + "step": 2616 + }, + { + "epoch": 0.34874733475479747, + "grad_norm": 0.29646299306448615, + "learning_rate": 9.764028105539746e-06, + "loss": 0.4351, + "step": 2617 + }, + { + "epoch": 0.34888059701492535, + "grad_norm": 0.313708796461314, + "learning_rate": 9.76381190022342e-06, + "loss": 0.442, + "step": 2618 + }, + { + "epoch": 0.3490138592750533, + "grad_norm": 0.3169690280459806, + "learning_rate": 9.763595598301125e-06, + "loss": 0.4407, + "step": 2619 + }, + { + "epoch": 0.34914712153518124, + "grad_norm": 0.30413625943537465, + "learning_rate": 9.763379199777248e-06, + "loss": 0.5165, + "step": 2620 + }, + { + "epoch": 0.3492803837953092, + "grad_norm": 0.30799647708363137, + "learning_rate": 9.763162704656178e-06, + "loss": 0.4916, + "step": 2621 + }, + { + "epoch": 0.3494136460554371, + "grad_norm": 0.31017757763921283, + "learning_rate": 9.762946112942303e-06, + "loss": 0.3822, + "step": 2622 + }, + { + "epoch": 0.349546908315565, + "grad_norm": 0.3060419409583609, + "learning_rate": 9.762729424640017e-06, + "loss": 0.401, + "step": 2623 + }, + { + "epoch": 0.34968017057569295, + "grad_norm": 0.3250302932001565, + "learning_rate": 9.762512639753714e-06, + "loss": 0.4737, + "step": 2624 + }, + { + "epoch": 0.3498134328358209, + "grad_norm": 0.31743018907427517, + "learning_rate": 9.76229575828779e-06, + "loss": 0.3621, + "step": 2625 + }, + { + "epoch": 0.34994669509594883, + "grad_norm": 0.28701193295116323, + "learning_rate": 9.762078780246641e-06, + "loss": 0.3859, + "step": 2626 + }, + { + "epoch": 0.3500799573560768, + "grad_norm": 0.32408343251856897, + "learning_rate": 9.761861705634672e-06, + "loss": 0.4236, + "step": 2627 + }, + { + "epoch": 0.3502132196162047, + "grad_norm": 0.2979402238082018, + "learning_rate": 9.761644534456282e-06, + "loss": 0.4011, + "step": 2628 + }, + { + "epoch": 0.3503464818763326, + "grad_norm": 0.29063414143251576, + "learning_rate": 9.761427266715876e-06, + "loss": 0.4249, + "step": 2629 + }, + { + "epoch": 0.35047974413646055, + "grad_norm": 0.2903234580017947, + "learning_rate": 9.761209902417857e-06, + "loss": 0.3929, + "step": 2630 + }, + { + "epoch": 0.3506130063965885, + "grad_norm": 0.3047037892195321, + "learning_rate": 9.760992441566637e-06, + "loss": 0.4142, + "step": 2631 + }, + { + "epoch": 0.35074626865671643, + "grad_norm": 0.3007700445275665, + "learning_rate": 9.760774884166625e-06, + "loss": 0.3979, + "step": 2632 + }, + { + "epoch": 0.3508795309168444, + "grad_norm": 0.3317634552033598, + "learning_rate": 9.76055723022223e-06, + "loss": 0.4031, + "step": 2633 + }, + { + "epoch": 0.35101279317697226, + "grad_norm": 0.314816771654745, + "learning_rate": 9.760339479737871e-06, + "loss": 0.4138, + "step": 2634 + }, + { + "epoch": 0.3511460554371002, + "grad_norm": 0.318459104256857, + "learning_rate": 9.760121632717957e-06, + "loss": 0.5415, + "step": 2635 + }, + { + "epoch": 0.35127931769722814, + "grad_norm": 0.30881851105031805, + "learning_rate": 9.759903689166913e-06, + "loss": 0.528, + "step": 2636 + }, + { + "epoch": 0.3514125799573561, + "grad_norm": 0.34472489210463375, + "learning_rate": 9.759685649089155e-06, + "loss": 0.4691, + "step": 2637 + }, + { + "epoch": 0.35154584221748403, + "grad_norm": 0.30494082821741747, + "learning_rate": 9.759467512489102e-06, + "loss": 0.4374, + "step": 2638 + }, + { + "epoch": 0.3516791044776119, + "grad_norm": 0.3188664881929915, + "learning_rate": 9.759249279371184e-06, + "loss": 0.368, + "step": 2639 + }, + { + "epoch": 0.35181236673773986, + "grad_norm": 0.3418583760761625, + "learning_rate": 9.75903094973982e-06, + "loss": 0.4979, + "step": 2640 + }, + { + "epoch": 0.3519456289978678, + "grad_norm": 0.2925273643742775, + "learning_rate": 9.758812523599444e-06, + "loss": 0.3699, + "step": 2641 + }, + { + "epoch": 0.35207889125799574, + "grad_norm": 0.34079657936968377, + "learning_rate": 9.75859400095448e-06, + "loss": 0.4377, + "step": 2642 + }, + { + "epoch": 0.3522121535181237, + "grad_norm": 0.33413216433313, + "learning_rate": 9.758375381809362e-06, + "loss": 0.5029, + "step": 2643 + }, + { + "epoch": 0.3523454157782516, + "grad_norm": 0.3127265931882286, + "learning_rate": 9.758156666168523e-06, + "loss": 0.43, + "step": 2644 + }, + { + "epoch": 0.3524786780383795, + "grad_norm": 0.35126539908685017, + "learning_rate": 9.757937854036398e-06, + "loss": 0.401, + "step": 2645 + }, + { + "epoch": 0.35261194029850745, + "grad_norm": 0.30698372243842625, + "learning_rate": 9.757718945417427e-06, + "loss": 0.4368, + "step": 2646 + }, + { + "epoch": 0.3527452025586354, + "grad_norm": 0.3358455511818674, + "learning_rate": 9.757499940316044e-06, + "loss": 0.4385, + "step": 2647 + }, + { + "epoch": 0.35287846481876334, + "grad_norm": 0.32423854584751993, + "learning_rate": 9.757280838736694e-06, + "loss": 0.4001, + "step": 2648 + }, + { + "epoch": 0.3530117270788913, + "grad_norm": 0.30701029952599623, + "learning_rate": 9.75706164068382e-06, + "loss": 0.3737, + "step": 2649 + }, + { + "epoch": 0.35314498933901917, + "grad_norm": 0.3925977948197439, + "learning_rate": 9.756842346161868e-06, + "loss": 0.4398, + "step": 2650 + }, + { + "epoch": 0.3532782515991471, + "grad_norm": 0.3317890826680968, + "learning_rate": 9.756622955175281e-06, + "loss": 0.4386, + "step": 2651 + }, + { + "epoch": 0.35341151385927505, + "grad_norm": 0.306327110059433, + "learning_rate": 9.756403467728512e-06, + "loss": 0.375, + "step": 2652 + }, + { + "epoch": 0.353544776119403, + "grad_norm": 0.3150040123939355, + "learning_rate": 9.75618388382601e-06, + "loss": 0.4792, + "step": 2653 + }, + { + "epoch": 0.35367803837953093, + "grad_norm": 0.32657415247470534, + "learning_rate": 9.75596420347223e-06, + "loss": 0.4081, + "step": 2654 + }, + { + "epoch": 0.3538113006396588, + "grad_norm": 0.3018544151324203, + "learning_rate": 9.755744426671625e-06, + "loss": 0.4163, + "step": 2655 + }, + { + "epoch": 0.35394456289978676, + "grad_norm": 0.3252847746619779, + "learning_rate": 9.755524553428652e-06, + "loss": 0.4935, + "step": 2656 + }, + { + "epoch": 0.3540778251599147, + "grad_norm": 0.3272933044098617, + "learning_rate": 9.75530458374777e-06, + "loss": 0.3968, + "step": 2657 + }, + { + "epoch": 0.35421108742004265, + "grad_norm": 0.30406466764324264, + "learning_rate": 9.75508451763344e-06, + "loss": 0.4825, + "step": 2658 + }, + { + "epoch": 0.3543443496801706, + "grad_norm": 0.32063642335694686, + "learning_rate": 9.754864355090125e-06, + "loss": 0.4294, + "step": 2659 + }, + { + "epoch": 0.35447761194029853, + "grad_norm": 0.31506154446653273, + "learning_rate": 9.754644096122292e-06, + "loss": 0.3926, + "step": 2660 + }, + { + "epoch": 0.3546108742004264, + "grad_norm": 0.3041338124550325, + "learning_rate": 9.754423740734404e-06, + "loss": 0.4071, + "step": 2661 + }, + { + "epoch": 0.35474413646055436, + "grad_norm": 0.3813551425471605, + "learning_rate": 9.75420328893093e-06, + "loss": 0.4933, + "step": 2662 + }, + { + "epoch": 0.3548773987206823, + "grad_norm": 0.3249197517410947, + "learning_rate": 9.75398274071634e-06, + "loss": 0.4209, + "step": 2663 + }, + { + "epoch": 0.35501066098081024, + "grad_norm": 0.3281531993814412, + "learning_rate": 9.753762096095111e-06, + "loss": 0.4424, + "step": 2664 + }, + { + "epoch": 0.3551439232409382, + "grad_norm": 0.328805535544515, + "learning_rate": 9.753541355071713e-06, + "loss": 0.4507, + "step": 2665 + }, + { + "epoch": 0.3552771855010661, + "grad_norm": 0.3180319347104235, + "learning_rate": 9.753320517650625e-06, + "loss": 0.4146, + "step": 2666 + }, + { + "epoch": 0.355410447761194, + "grad_norm": 0.3365653208763228, + "learning_rate": 9.753099583836323e-06, + "loss": 0.3773, + "step": 2667 + }, + { + "epoch": 0.35554371002132196, + "grad_norm": 0.31624170265199825, + "learning_rate": 9.75287855363329e-06, + "loss": 0.4925, + "step": 2668 + }, + { + "epoch": 0.3556769722814499, + "grad_norm": 0.3122498009535137, + "learning_rate": 9.752657427046004e-06, + "loss": 0.4902, + "step": 2669 + }, + { + "epoch": 0.35581023454157784, + "grad_norm": 0.31796143050196246, + "learning_rate": 9.752436204078955e-06, + "loss": 0.3217, + "step": 2670 + }, + { + "epoch": 0.3559434968017058, + "grad_norm": 0.30567501469596886, + "learning_rate": 9.752214884736625e-06, + "loss": 0.3546, + "step": 2671 + }, + { + "epoch": 0.35607675906183367, + "grad_norm": 0.31248240087135615, + "learning_rate": 9.751993469023503e-06, + "loss": 0.3917, + "step": 2672 + }, + { + "epoch": 0.3562100213219616, + "grad_norm": 0.3590829576519434, + "learning_rate": 9.751771956944082e-06, + "loss": 0.4743, + "step": 2673 + }, + { + "epoch": 0.35634328358208955, + "grad_norm": 0.3229187838515567, + "learning_rate": 9.75155034850285e-06, + "loss": 0.4017, + "step": 2674 + }, + { + "epoch": 0.3564765458422175, + "grad_norm": 0.3596157194407674, + "learning_rate": 9.751328643704304e-06, + "loss": 0.3607, + "step": 2675 + }, + { + "epoch": 0.35660980810234544, + "grad_norm": 0.3285057743234901, + "learning_rate": 9.751106842552938e-06, + "loss": 0.4382, + "step": 2676 + }, + { + "epoch": 0.3567430703624733, + "grad_norm": 0.32882763417408395, + "learning_rate": 9.75088494505325e-06, + "loss": 0.3523, + "step": 2677 + }, + { + "epoch": 0.35687633262260127, + "grad_norm": 0.30904799470077726, + "learning_rate": 9.750662951209742e-06, + "loss": 0.4073, + "step": 2678 + }, + { + "epoch": 0.3570095948827292, + "grad_norm": 0.31877681693674864, + "learning_rate": 9.750440861026913e-06, + "loss": 0.3789, + "step": 2679 + }, + { + "epoch": 0.35714285714285715, + "grad_norm": 0.3075040230597819, + "learning_rate": 9.75021867450927e-06, + "loss": 0.3954, + "step": 2680 + }, + { + "epoch": 0.3572761194029851, + "grad_norm": 0.33744846289487507, + "learning_rate": 9.749996391661313e-06, + "loss": 0.5116, + "step": 2681 + }, + { + "epoch": 0.357409381663113, + "grad_norm": 0.7201723264874464, + "learning_rate": 9.749774012487558e-06, + "loss": 0.3994, + "step": 2682 + }, + { + "epoch": 0.3575426439232409, + "grad_norm": 0.29479990945158685, + "learning_rate": 9.749551536992507e-06, + "loss": 0.4367, + "step": 2683 + }, + { + "epoch": 0.35767590618336886, + "grad_norm": 0.31215885416572886, + "learning_rate": 9.749328965180677e-06, + "loss": 0.4155, + "step": 2684 + }, + { + "epoch": 0.3578091684434968, + "grad_norm": 0.3294929521432725, + "learning_rate": 9.749106297056582e-06, + "loss": 0.4079, + "step": 2685 + }, + { + "epoch": 0.35794243070362475, + "grad_norm": 0.32208044281828946, + "learning_rate": 9.748883532624732e-06, + "loss": 0.4434, + "step": 2686 + }, + { + "epoch": 0.3580756929637527, + "grad_norm": 0.33577552664756677, + "learning_rate": 9.748660671889645e-06, + "loss": 0.4531, + "step": 2687 + }, + { + "epoch": 0.3582089552238806, + "grad_norm": 0.3114649896940741, + "learning_rate": 9.748437714855847e-06, + "loss": 0.4087, + "step": 2688 + }, + { + "epoch": 0.3583422174840085, + "grad_norm": 0.3166279585171906, + "learning_rate": 9.748214661527852e-06, + "loss": 0.3867, + "step": 2689 + }, + { + "epoch": 0.35847547974413646, + "grad_norm": 0.3399666147199968, + "learning_rate": 9.74799151191019e-06, + "loss": 0.4107, + "step": 2690 + }, + { + "epoch": 0.3586087420042644, + "grad_norm": 0.2944720723735325, + "learning_rate": 9.747768266007381e-06, + "loss": 0.4606, + "step": 2691 + }, + { + "epoch": 0.35874200426439234, + "grad_norm": 0.31640513826154165, + "learning_rate": 9.747544923823955e-06, + "loss": 0.3335, + "step": 2692 + }, + { + "epoch": 0.35887526652452023, + "grad_norm": 0.30833098017846505, + "learning_rate": 9.747321485364439e-06, + "loss": 0.4374, + "step": 2693 + }, + { + "epoch": 0.3590085287846482, + "grad_norm": 0.32298880610556957, + "learning_rate": 9.747097950633366e-06, + "loss": 0.4206, + "step": 2694 + }, + { + "epoch": 0.3591417910447761, + "grad_norm": 0.32001272229842753, + "learning_rate": 9.746874319635269e-06, + "loss": 0.3573, + "step": 2695 + }, + { + "epoch": 0.35927505330490406, + "grad_norm": 0.2984516139015659, + "learning_rate": 9.746650592374683e-06, + "loss": 0.3549, + "step": 2696 + }, + { + "epoch": 0.359408315565032, + "grad_norm": 0.34342886216455765, + "learning_rate": 9.746426768856143e-06, + "loss": 0.5233, + "step": 2697 + }, + { + "epoch": 0.35954157782515994, + "grad_norm": 0.3027341995052157, + "learning_rate": 9.74620284908419e-06, + "loss": 0.4222, + "step": 2698 + }, + { + "epoch": 0.35967484008528783, + "grad_norm": 0.33826516523756417, + "learning_rate": 9.745978833063366e-06, + "loss": 0.4232, + "step": 2699 + }, + { + "epoch": 0.35980810234541577, + "grad_norm": 0.3225536818965048, + "learning_rate": 9.74575472079821e-06, + "loss": 0.4963, + "step": 2700 + }, + { + "epoch": 0.3599413646055437, + "grad_norm": 0.33203414670898823, + "learning_rate": 9.74553051229327e-06, + "loss": 0.4358, + "step": 2701 + }, + { + "epoch": 0.36007462686567165, + "grad_norm": 0.3486019596145053, + "learning_rate": 9.745306207553092e-06, + "loss": 0.4103, + "step": 2702 + }, + { + "epoch": 0.3602078891257996, + "grad_norm": 0.3371736618744188, + "learning_rate": 9.745081806582225e-06, + "loss": 0.4434, + "step": 2703 + }, + { + "epoch": 0.3603411513859275, + "grad_norm": 0.3262827853159637, + "learning_rate": 9.744857309385218e-06, + "loss": 0.4131, + "step": 2704 + }, + { + "epoch": 0.3604744136460554, + "grad_norm": 0.3195865897620583, + "learning_rate": 9.744632715966627e-06, + "loss": 0.5114, + "step": 2705 + }, + { + "epoch": 0.36060767590618337, + "grad_norm": 0.30390298152030204, + "learning_rate": 9.744408026331001e-06, + "loss": 0.4097, + "step": 2706 + }, + { + "epoch": 0.3607409381663113, + "grad_norm": 0.36917590339724154, + "learning_rate": 9.744183240482904e-06, + "loss": 0.4961, + "step": 2707 + }, + { + "epoch": 0.36087420042643925, + "grad_norm": 0.3267833237883863, + "learning_rate": 9.743958358426886e-06, + "loss": 0.4185, + "step": 2708 + }, + { + "epoch": 0.36100746268656714, + "grad_norm": 0.3900642534986805, + "learning_rate": 9.743733380167514e-06, + "loss": 0.4314, + "step": 2709 + }, + { + "epoch": 0.3611407249466951, + "grad_norm": 0.35607099282082494, + "learning_rate": 9.743508305709349e-06, + "loss": 0.3956, + "step": 2710 + }, + { + "epoch": 0.361273987206823, + "grad_norm": 0.31018667963949054, + "learning_rate": 9.743283135056951e-06, + "loss": 0.4391, + "step": 2711 + }, + { + "epoch": 0.36140724946695096, + "grad_norm": 0.32740642441336554, + "learning_rate": 9.743057868214894e-06, + "loss": 0.3556, + "step": 2712 + }, + { + "epoch": 0.3615405117270789, + "grad_norm": 0.35314529662502525, + "learning_rate": 9.742832505187738e-06, + "loss": 0.4002, + "step": 2713 + }, + { + "epoch": 0.36167377398720685, + "grad_norm": 0.31484675861895534, + "learning_rate": 9.74260704598006e-06, + "loss": 0.39, + "step": 2714 + }, + { + "epoch": 0.36180703624733473, + "grad_norm": 0.3342798101146889, + "learning_rate": 9.742381490596426e-06, + "loss": 0.3635, + "step": 2715 + }, + { + "epoch": 0.3619402985074627, + "grad_norm": 0.31144743185912727, + "learning_rate": 9.742155839041417e-06, + "loss": 0.4404, + "step": 2716 + }, + { + "epoch": 0.3620735607675906, + "grad_norm": 0.30313529720128, + "learning_rate": 9.741930091319602e-06, + "loss": 0.3776, + "step": 2717 + }, + { + "epoch": 0.36220682302771856, + "grad_norm": 0.3033066410043691, + "learning_rate": 9.741704247435566e-06, + "loss": 0.3875, + "step": 2718 + }, + { + "epoch": 0.3623400852878465, + "grad_norm": 0.3163294241433167, + "learning_rate": 9.74147830739388e-06, + "loss": 0.5044, + "step": 2719 + }, + { + "epoch": 0.3624733475479744, + "grad_norm": 0.30703026403639666, + "learning_rate": 9.741252271199134e-06, + "loss": 0.484, + "step": 2720 + }, + { + "epoch": 0.36260660980810233, + "grad_norm": 0.3194929079815755, + "learning_rate": 9.74102613885591e-06, + "loss": 0.414, + "step": 2721 + }, + { + "epoch": 0.3627398720682303, + "grad_norm": 0.29947721699604246, + "learning_rate": 9.740799910368791e-06, + "loss": 0.3716, + "step": 2722 + }, + { + "epoch": 0.3628731343283582, + "grad_norm": 0.3537691666052663, + "learning_rate": 9.740573585742367e-06, + "loss": 0.4704, + "step": 2723 + }, + { + "epoch": 0.36300639658848616, + "grad_norm": 0.32925290395239276, + "learning_rate": 9.740347164981226e-06, + "loss": 0.3856, + "step": 2724 + }, + { + "epoch": 0.3631396588486141, + "grad_norm": 0.2951056606209873, + "learning_rate": 9.740120648089961e-06, + "loss": 0.4353, + "step": 2725 + }, + { + "epoch": 0.363272921108742, + "grad_norm": 0.3331072786506157, + "learning_rate": 9.739894035073166e-06, + "loss": 0.451, + "step": 2726 + }, + { + "epoch": 0.36340618336886993, + "grad_norm": 0.31319191051654943, + "learning_rate": 9.739667325935436e-06, + "loss": 0.4297, + "step": 2727 + }, + { + "epoch": 0.36353944562899787, + "grad_norm": 0.3164845711182704, + "learning_rate": 9.739440520681368e-06, + "loss": 0.4261, + "step": 2728 + }, + { + "epoch": 0.3636727078891258, + "grad_norm": 0.31796507716865097, + "learning_rate": 9.73921361931556e-06, + "loss": 0.4465, + "step": 2729 + }, + { + "epoch": 0.36380597014925375, + "grad_norm": 0.33465365478480164, + "learning_rate": 9.738986621842614e-06, + "loss": 0.5297, + "step": 2730 + }, + { + "epoch": 0.36393923240938164, + "grad_norm": 0.2952224802089486, + "learning_rate": 9.738759528267136e-06, + "loss": 0.4377, + "step": 2731 + }, + { + "epoch": 0.3640724946695096, + "grad_norm": 0.30333312883013785, + "learning_rate": 9.73853233859373e-06, + "loss": 0.4081, + "step": 2732 + }, + { + "epoch": 0.3642057569296375, + "grad_norm": 0.30029740387513093, + "learning_rate": 9.738305052827002e-06, + "loss": 0.3938, + "step": 2733 + }, + { + "epoch": 0.36433901918976547, + "grad_norm": 0.3241735118576937, + "learning_rate": 9.738077670971562e-06, + "loss": 0.4166, + "step": 2734 + }, + { + "epoch": 0.3644722814498934, + "grad_norm": 0.3000068590369955, + "learning_rate": 9.73785019303202e-06, + "loss": 0.3889, + "step": 2735 + }, + { + "epoch": 0.3646055437100213, + "grad_norm": 0.3137994689962046, + "learning_rate": 9.737622619012992e-06, + "loss": 0.4025, + "step": 2736 + }, + { + "epoch": 0.36473880597014924, + "grad_norm": 0.3094044673512051, + "learning_rate": 9.73739494891909e-06, + "loss": 0.4507, + "step": 2737 + }, + { + "epoch": 0.3648720682302772, + "grad_norm": 0.33388926593879803, + "learning_rate": 9.737167182754931e-06, + "loss": 0.5498, + "step": 2738 + }, + { + "epoch": 0.3650053304904051, + "grad_norm": 0.3122789365030483, + "learning_rate": 9.736939320525138e-06, + "loss": 0.4441, + "step": 2739 + }, + { + "epoch": 0.36513859275053306, + "grad_norm": 0.34661765479200124, + "learning_rate": 9.736711362234326e-06, + "loss": 0.4978, + "step": 2740 + }, + { + "epoch": 0.365271855010661, + "grad_norm": 0.30266946232810776, + "learning_rate": 9.736483307887121e-06, + "loss": 0.4067, + "step": 2741 + }, + { + "epoch": 0.3654051172707889, + "grad_norm": 0.3196643955881865, + "learning_rate": 9.736255157488149e-06, + "loss": 0.4487, + "step": 2742 + }, + { + "epoch": 0.36553837953091683, + "grad_norm": 0.2960728477357806, + "learning_rate": 9.736026911042032e-06, + "loss": 0.3973, + "step": 2743 + }, + { + "epoch": 0.3656716417910448, + "grad_norm": 0.3128909183889129, + "learning_rate": 9.735798568553402e-06, + "loss": 0.4515, + "step": 2744 + }, + { + "epoch": 0.3658049040511727, + "grad_norm": 1.5448479416792622, + "learning_rate": 9.735570130026891e-06, + "loss": 0.5412, + "step": 2745 + }, + { + "epoch": 0.36593816631130066, + "grad_norm": 0.3250763645391532, + "learning_rate": 9.735341595467129e-06, + "loss": 0.5577, + "step": 2746 + }, + { + "epoch": 0.36607142857142855, + "grad_norm": 0.3127380275234924, + "learning_rate": 9.73511296487875e-06, + "loss": 0.3537, + "step": 2747 + }, + { + "epoch": 0.3662046908315565, + "grad_norm": 0.30217476501671564, + "learning_rate": 9.734884238266394e-06, + "loss": 0.4068, + "step": 2748 + }, + { + "epoch": 0.36633795309168443, + "grad_norm": 0.3005813533005387, + "learning_rate": 9.734655415634695e-06, + "loss": 0.3523, + "step": 2749 + }, + { + "epoch": 0.3664712153518124, + "grad_norm": 0.3046603726758541, + "learning_rate": 9.734426496988297e-06, + "loss": 0.396, + "step": 2750 + }, + { + "epoch": 0.3666044776119403, + "grad_norm": 0.3343929471340042, + "learning_rate": 9.73419748233184e-06, + "loss": 0.4423, + "step": 2751 + }, + { + "epoch": 0.36673773987206826, + "grad_norm": 0.3088992089218549, + "learning_rate": 9.733968371669968e-06, + "loss": 0.3768, + "step": 2752 + }, + { + "epoch": 0.36687100213219614, + "grad_norm": 0.3136673788548846, + "learning_rate": 9.733739165007327e-06, + "loss": 0.3568, + "step": 2753 + }, + { + "epoch": 0.3670042643923241, + "grad_norm": 0.34293140767182445, + "learning_rate": 9.733509862348569e-06, + "loss": 0.4429, + "step": 2754 + }, + { + "epoch": 0.36713752665245203, + "grad_norm": 0.30249457624525855, + "learning_rate": 9.733280463698338e-06, + "loss": 0.4252, + "step": 2755 + }, + { + "epoch": 0.36727078891257997, + "grad_norm": 0.3230233295446023, + "learning_rate": 9.733050969061293e-06, + "loss": 0.5023, + "step": 2756 + }, + { + "epoch": 0.3674040511727079, + "grad_norm": 0.3029036449942373, + "learning_rate": 9.732821378442081e-06, + "loss": 0.3518, + "step": 2757 + }, + { + "epoch": 0.3675373134328358, + "grad_norm": 0.31867067437220664, + "learning_rate": 9.732591691845362e-06, + "loss": 0.4141, + "step": 2758 + }, + { + "epoch": 0.36767057569296374, + "grad_norm": 0.3165093155621649, + "learning_rate": 9.732361909275793e-06, + "loss": 0.4291, + "step": 2759 + }, + { + "epoch": 0.3678038379530917, + "grad_norm": 0.33491585355527914, + "learning_rate": 9.732132030738033e-06, + "loss": 0.4859, + "step": 2760 + }, + { + "epoch": 0.3679371002132196, + "grad_norm": 0.28935603858317893, + "learning_rate": 9.731902056236746e-06, + "loss": 0.3625, + "step": 2761 + }, + { + "epoch": 0.36807036247334757, + "grad_norm": 0.31993730081309885, + "learning_rate": 9.731671985776591e-06, + "loss": 0.3828, + "step": 2762 + }, + { + "epoch": 0.36820362473347545, + "grad_norm": 0.3420563937072052, + "learning_rate": 9.73144181936224e-06, + "loss": 0.3804, + "step": 2763 + }, + { + "epoch": 0.3683368869936034, + "grad_norm": 0.32211971859651306, + "learning_rate": 9.731211556998357e-06, + "loss": 0.424, + "step": 2764 + }, + { + "epoch": 0.36847014925373134, + "grad_norm": 0.30707267587071224, + "learning_rate": 9.730981198689611e-06, + "loss": 0.4159, + "step": 2765 + }, + { + "epoch": 0.3686034115138593, + "grad_norm": 0.3047372684740395, + "learning_rate": 9.730750744440674e-06, + "loss": 0.4074, + "step": 2766 + }, + { + "epoch": 0.3687366737739872, + "grad_norm": 0.30112128039423747, + "learning_rate": 9.73052019425622e-06, + "loss": 0.3849, + "step": 2767 + }, + { + "epoch": 0.36886993603411516, + "grad_norm": 0.2961837677575259, + "learning_rate": 9.730289548140923e-06, + "loss": 0.4165, + "step": 2768 + }, + { + "epoch": 0.36900319829424305, + "grad_norm": 0.29860922545338886, + "learning_rate": 9.730058806099462e-06, + "loss": 0.5055, + "step": 2769 + }, + { + "epoch": 0.369136460554371, + "grad_norm": 0.33739111322718823, + "learning_rate": 9.729827968136516e-06, + "loss": 0.3822, + "step": 2770 + }, + { + "epoch": 0.36926972281449894, + "grad_norm": 0.3160327237627878, + "learning_rate": 9.729597034256765e-06, + "loss": 0.4324, + "step": 2771 + }, + { + "epoch": 0.3694029850746269, + "grad_norm": 0.3267038678634973, + "learning_rate": 9.729366004464893e-06, + "loss": 0.4015, + "step": 2772 + }, + { + "epoch": 0.3695362473347548, + "grad_norm": 0.34881583482251627, + "learning_rate": 9.729134878765586e-06, + "loss": 0.4223, + "step": 2773 + }, + { + "epoch": 0.3696695095948827, + "grad_norm": 0.5189176901290482, + "learning_rate": 9.728903657163528e-06, + "loss": 0.4063, + "step": 2774 + }, + { + "epoch": 0.36980277185501065, + "grad_norm": 0.33713008875338646, + "learning_rate": 9.728672339663413e-06, + "loss": 0.4584, + "step": 2775 + }, + { + "epoch": 0.3699360341151386, + "grad_norm": 0.2991420273907225, + "learning_rate": 9.728440926269926e-06, + "loss": 0.3624, + "step": 2776 + }, + { + "epoch": 0.37006929637526653, + "grad_norm": 0.30468172289187895, + "learning_rate": 9.728209416987765e-06, + "loss": 0.4225, + "step": 2777 + }, + { + "epoch": 0.3702025586353945, + "grad_norm": 0.32575371223492466, + "learning_rate": 9.727977811821621e-06, + "loss": 0.4602, + "step": 2778 + }, + { + "epoch": 0.37033582089552236, + "grad_norm": 0.2909168306365873, + "learning_rate": 9.727746110776195e-06, + "loss": 0.3999, + "step": 2779 + }, + { + "epoch": 0.3704690831556503, + "grad_norm": 0.313201468566253, + "learning_rate": 9.72751431385618e-06, + "loss": 0.4468, + "step": 2780 + }, + { + "epoch": 0.37060234541577824, + "grad_norm": 0.30061862491092883, + "learning_rate": 9.72728242106628e-06, + "loss": 0.3751, + "step": 2781 + }, + { + "epoch": 0.3707356076759062, + "grad_norm": 0.3154668499373699, + "learning_rate": 9.727050432411197e-06, + "loss": 0.4958, + "step": 2782 + }, + { + "epoch": 0.37086886993603413, + "grad_norm": 0.3012165950604042, + "learning_rate": 9.72681834789564e-06, + "loss": 0.4561, + "step": 2783 + }, + { + "epoch": 0.37100213219616207, + "grad_norm": 0.3104994548539969, + "learning_rate": 9.726586167524307e-06, + "loss": 0.3993, + "step": 2784 + }, + { + "epoch": 0.37113539445628996, + "grad_norm": 0.5698937458911089, + "learning_rate": 9.726353891301912e-06, + "loss": 0.4112, + "step": 2785 + }, + { + "epoch": 0.3712686567164179, + "grad_norm": 0.3068242962448202, + "learning_rate": 9.726121519233163e-06, + "loss": 0.4555, + "step": 2786 + }, + { + "epoch": 0.37140191897654584, + "grad_norm": 0.31875105610796245, + "learning_rate": 9.725889051322774e-06, + "loss": 0.3641, + "step": 2787 + }, + { + "epoch": 0.3715351812366738, + "grad_norm": 0.3889794237782248, + "learning_rate": 9.725656487575458e-06, + "loss": 0.442, + "step": 2788 + }, + { + "epoch": 0.3716684434968017, + "grad_norm": 0.31551088722156884, + "learning_rate": 9.725423827995934e-06, + "loss": 0.5221, + "step": 2789 + }, + { + "epoch": 0.3718017057569296, + "grad_norm": 0.3176598242117185, + "learning_rate": 9.725191072588916e-06, + "loss": 0.5106, + "step": 2790 + }, + { + "epoch": 0.37193496801705755, + "grad_norm": 0.3403111306983955, + "learning_rate": 9.724958221359126e-06, + "loss": 0.3661, + "step": 2791 + }, + { + "epoch": 0.3720682302771855, + "grad_norm": 0.3190102500620088, + "learning_rate": 9.724725274311288e-06, + "loss": 0.4086, + "step": 2792 + }, + { + "epoch": 0.37220149253731344, + "grad_norm": 0.3176168294431309, + "learning_rate": 9.724492231450123e-06, + "loss": 0.4081, + "step": 2793 + }, + { + "epoch": 0.3723347547974414, + "grad_norm": 0.33751393569685534, + "learning_rate": 9.724259092780356e-06, + "loss": 0.3646, + "step": 2794 + }, + { + "epoch": 0.3724680170575693, + "grad_norm": 0.3313258092922876, + "learning_rate": 9.724025858306717e-06, + "loss": 0.3958, + "step": 2795 + }, + { + "epoch": 0.3726012793176972, + "grad_norm": 0.3140064832688601, + "learning_rate": 9.723792528033937e-06, + "loss": 0.3911, + "step": 2796 + }, + { + "epoch": 0.37273454157782515, + "grad_norm": 0.3048107197568341, + "learning_rate": 9.723559101966747e-06, + "loss": 0.4122, + "step": 2797 + }, + { + "epoch": 0.3728678038379531, + "grad_norm": 0.31255729427175155, + "learning_rate": 9.72332558010988e-06, + "loss": 0.3972, + "step": 2798 + }, + { + "epoch": 0.37300106609808104, + "grad_norm": 0.29990054173367425, + "learning_rate": 9.723091962468068e-06, + "loss": 0.4182, + "step": 2799 + }, + { + "epoch": 0.373134328358209, + "grad_norm": 0.3107533763955966, + "learning_rate": 9.722858249046055e-06, + "loss": 0.4, + "step": 2800 + }, + { + "epoch": 0.37326759061833686, + "grad_norm": 0.3310783478662223, + "learning_rate": 9.722624439848578e-06, + "loss": 0.4864, + "step": 2801 + }, + { + "epoch": 0.3734008528784648, + "grad_norm": 0.3020215540978471, + "learning_rate": 9.722390534880377e-06, + "loss": 0.4375, + "step": 2802 + }, + { + "epoch": 0.37353411513859275, + "grad_norm": 0.3029292855237099, + "learning_rate": 9.722156534146196e-06, + "loss": 0.4816, + "step": 2803 + }, + { + "epoch": 0.3736673773987207, + "grad_norm": 0.3294507179830779, + "learning_rate": 9.721922437650781e-06, + "loss": 0.4452, + "step": 2804 + }, + { + "epoch": 0.37380063965884863, + "grad_norm": 0.3225907807719786, + "learning_rate": 9.72168824539888e-06, + "loss": 0.424, + "step": 2805 + }, + { + "epoch": 0.3739339019189765, + "grad_norm": 0.3134726854325132, + "learning_rate": 9.721453957395241e-06, + "loss": 0.4364, + "step": 2806 + }, + { + "epoch": 0.37406716417910446, + "grad_norm": 0.33530304496577623, + "learning_rate": 9.721219573644617e-06, + "loss": 0.4025, + "step": 2807 + }, + { + "epoch": 0.3742004264392324, + "grad_norm": 0.2949059453829507, + "learning_rate": 9.720985094151755e-06, + "loss": 0.3185, + "step": 2808 + }, + { + "epoch": 0.37433368869936035, + "grad_norm": 0.31124081592359043, + "learning_rate": 9.720750518921418e-06, + "loss": 0.3887, + "step": 2809 + }, + { + "epoch": 0.3744669509594883, + "grad_norm": 1.0528422559420147, + "learning_rate": 9.72051584795836e-06, + "loss": 0.3987, + "step": 2810 + }, + { + "epoch": 0.37460021321961623, + "grad_norm": 0.3401621068837676, + "learning_rate": 9.720281081267338e-06, + "loss": 0.3903, + "step": 2811 + }, + { + "epoch": 0.3747334754797441, + "grad_norm": 0.30435997252565095, + "learning_rate": 9.720046218853114e-06, + "loss": 0.3579, + "step": 2812 + }, + { + "epoch": 0.37486673773987206, + "grad_norm": 0.3340537011163489, + "learning_rate": 9.719811260720453e-06, + "loss": 0.4813, + "step": 2813 + }, + { + "epoch": 0.375, + "grad_norm": 0.30734211791533544, + "learning_rate": 9.719576206874118e-06, + "loss": 0.3825, + "step": 2814 + }, + { + "epoch": 0.37513326226012794, + "grad_norm": 0.3186770372108286, + "learning_rate": 9.719341057318874e-06, + "loss": 0.4884, + "step": 2815 + }, + { + "epoch": 0.3752665245202559, + "grad_norm": 0.3216088387329535, + "learning_rate": 9.71910581205949e-06, + "loss": 0.3974, + "step": 2816 + }, + { + "epoch": 0.37539978678038377, + "grad_norm": 0.31688394814901943, + "learning_rate": 9.71887047110074e-06, + "loss": 0.4036, + "step": 2817 + }, + { + "epoch": 0.3755330490405117, + "grad_norm": 0.29825316217559994, + "learning_rate": 9.718635034447395e-06, + "loss": 0.4191, + "step": 2818 + }, + { + "epoch": 0.37566631130063965, + "grad_norm": 0.30987822708329993, + "learning_rate": 9.718399502104227e-06, + "loss": 0.4421, + "step": 2819 + }, + { + "epoch": 0.3757995735607676, + "grad_norm": 0.3017196558404205, + "learning_rate": 9.718163874076014e-06, + "loss": 0.4795, + "step": 2820 + }, + { + "epoch": 0.37593283582089554, + "grad_norm": 0.29179227027459276, + "learning_rate": 9.717928150367536e-06, + "loss": 0.5769, + "step": 2821 + }, + { + "epoch": 0.3760660980810235, + "grad_norm": 0.3066757446563039, + "learning_rate": 9.71769233098357e-06, + "loss": 0.4107, + "step": 2822 + }, + { + "epoch": 0.37619936034115137, + "grad_norm": 0.2924784935075412, + "learning_rate": 9.717456415928901e-06, + "loss": 0.3507, + "step": 2823 + }, + { + "epoch": 0.3763326226012793, + "grad_norm": 0.29229909821656075, + "learning_rate": 9.717220405208313e-06, + "loss": 0.354, + "step": 2824 + }, + { + "epoch": 0.37646588486140725, + "grad_norm": 0.32039852233168736, + "learning_rate": 9.716984298826591e-06, + "loss": 0.4645, + "step": 2825 + }, + { + "epoch": 0.3765991471215352, + "grad_norm": 0.30719443104533317, + "learning_rate": 9.716748096788521e-06, + "loss": 0.4099, + "step": 2826 + }, + { + "epoch": 0.37673240938166314, + "grad_norm": 0.313219257197613, + "learning_rate": 9.716511799098898e-06, + "loss": 0.3921, + "step": 2827 + }, + { + "epoch": 0.376865671641791, + "grad_norm": 0.3209397967283722, + "learning_rate": 9.71627540576251e-06, + "loss": 0.4101, + "step": 2828 + }, + { + "epoch": 0.37699893390191896, + "grad_norm": 0.32712663196048264, + "learning_rate": 9.716038916784151e-06, + "loss": 0.4779, + "step": 2829 + }, + { + "epoch": 0.3771321961620469, + "grad_norm": 0.3097255424067587, + "learning_rate": 9.715802332168619e-06, + "loss": 0.4699, + "step": 2830 + }, + { + "epoch": 0.37726545842217485, + "grad_norm": 0.30166348029531176, + "learning_rate": 9.715565651920709e-06, + "loss": 0.4161, + "step": 2831 + }, + { + "epoch": 0.3773987206823028, + "grad_norm": 0.3097691319131561, + "learning_rate": 9.715328876045223e-06, + "loss": 0.3988, + "step": 2832 + }, + { + "epoch": 0.3775319829424307, + "grad_norm": 0.3020899650674714, + "learning_rate": 9.715092004546962e-06, + "loss": 0.4553, + "step": 2833 + }, + { + "epoch": 0.3776652452025586, + "grad_norm": 0.2945321334630927, + "learning_rate": 9.714855037430731e-06, + "loss": 0.4254, + "step": 2834 + }, + { + "epoch": 0.37779850746268656, + "grad_norm": 0.2977799078507176, + "learning_rate": 9.714617974701331e-06, + "loss": 0.3831, + "step": 2835 + }, + { + "epoch": 0.3779317697228145, + "grad_norm": 0.32381695142090966, + "learning_rate": 9.714380816363573e-06, + "loss": 0.416, + "step": 2836 + }, + { + "epoch": 0.37806503198294245, + "grad_norm": 0.3265354866291403, + "learning_rate": 9.714143562422267e-06, + "loss": 0.46, + "step": 2837 + }, + { + "epoch": 0.3781982942430704, + "grad_norm": 0.30257792291043856, + "learning_rate": 9.71390621288222e-06, + "loss": 0.4276, + "step": 2838 + }, + { + "epoch": 0.3783315565031983, + "grad_norm": 0.2965976579715588, + "learning_rate": 9.713668767748252e-06, + "loss": 0.3796, + "step": 2839 + }, + { + "epoch": 0.3784648187633262, + "grad_norm": 0.3031702321213475, + "learning_rate": 9.713431227025171e-06, + "loss": 0.3774, + "step": 2840 + }, + { + "epoch": 0.37859808102345416, + "grad_norm": 0.33298931200092946, + "learning_rate": 9.7131935907178e-06, + "loss": 0.5252, + "step": 2841 + }, + { + "epoch": 0.3787313432835821, + "grad_norm": 0.3108682989218449, + "learning_rate": 9.712955858830954e-06, + "loss": 0.4482, + "step": 2842 + }, + { + "epoch": 0.37886460554371004, + "grad_norm": 0.30649341199023555, + "learning_rate": 9.712718031369456e-06, + "loss": 0.4396, + "step": 2843 + }, + { + "epoch": 0.37899786780383793, + "grad_norm": 0.29544472286514145, + "learning_rate": 9.712480108338127e-06, + "loss": 0.3652, + "step": 2844 + }, + { + "epoch": 0.37913113006396587, + "grad_norm": 0.3023195528951882, + "learning_rate": 9.712242089741794e-06, + "loss": 0.405, + "step": 2845 + }, + { + "epoch": 0.3792643923240938, + "grad_norm": 0.33765465960932667, + "learning_rate": 9.712003975585285e-06, + "loss": 0.4782, + "step": 2846 + }, + { + "epoch": 0.37939765458422176, + "grad_norm": 0.29384968357037666, + "learning_rate": 9.711765765873425e-06, + "loss": 0.3611, + "step": 2847 + }, + { + "epoch": 0.3795309168443497, + "grad_norm": 0.30250238678103447, + "learning_rate": 9.711527460611047e-06, + "loss": 0.3942, + "step": 2848 + }, + { + "epoch": 0.37966417910447764, + "grad_norm": 0.3114780719972246, + "learning_rate": 9.711289059802984e-06, + "loss": 0.444, + "step": 2849 + }, + { + "epoch": 0.3797974413646055, + "grad_norm": 0.3327815649297159, + "learning_rate": 9.71105056345407e-06, + "loss": 0.4451, + "step": 2850 + }, + { + "epoch": 0.37993070362473347, + "grad_norm": 0.3409555107744585, + "learning_rate": 9.710811971569139e-06, + "loss": 0.3809, + "step": 2851 + }, + { + "epoch": 0.3800639658848614, + "grad_norm": 0.30165112073693784, + "learning_rate": 9.710573284153032e-06, + "loss": 0.4002, + "step": 2852 + }, + { + "epoch": 0.38019722814498935, + "grad_norm": 0.3234055339125502, + "learning_rate": 9.710334501210592e-06, + "loss": 0.4693, + "step": 2853 + }, + { + "epoch": 0.3803304904051173, + "grad_norm": 0.3219466525480935, + "learning_rate": 9.710095622746656e-06, + "loss": 0.5143, + "step": 2854 + }, + { + "epoch": 0.3804637526652452, + "grad_norm": 0.31249725013866486, + "learning_rate": 9.709856648766071e-06, + "loss": 0.4078, + "step": 2855 + }, + { + "epoch": 0.3805970149253731, + "grad_norm": 0.31597034716960787, + "learning_rate": 9.709617579273682e-06, + "loss": 0.4406, + "step": 2856 + }, + { + "epoch": 0.38073027718550106, + "grad_norm": 0.30532836397676594, + "learning_rate": 9.70937841427434e-06, + "loss": 0.4137, + "step": 2857 + }, + { + "epoch": 0.380863539445629, + "grad_norm": 0.31114829158177826, + "learning_rate": 9.70913915377289e-06, + "loss": 0.4377, + "step": 2858 + }, + { + "epoch": 0.38099680170575695, + "grad_norm": 0.3275491825482921, + "learning_rate": 9.70889979777419e-06, + "loss": 0.4048, + "step": 2859 + }, + { + "epoch": 0.38113006396588484, + "grad_norm": 0.30173788214189584, + "learning_rate": 9.70866034628309e-06, + "loss": 0.3987, + "step": 2860 + }, + { + "epoch": 0.3812633262260128, + "grad_norm": 0.3181658527123042, + "learning_rate": 9.708420799304445e-06, + "loss": 0.4179, + "step": 2861 + }, + { + "epoch": 0.3813965884861407, + "grad_norm": 0.3162965390077847, + "learning_rate": 9.708181156843117e-06, + "loss": 0.4567, + "step": 2862 + }, + { + "epoch": 0.38152985074626866, + "grad_norm": 0.3139306013512926, + "learning_rate": 9.707941418903962e-06, + "loss": 0.3859, + "step": 2863 + }, + { + "epoch": 0.3816631130063966, + "grad_norm": 0.29062120498543426, + "learning_rate": 9.707701585491843e-06, + "loss": 0.4138, + "step": 2864 + }, + { + "epoch": 0.38179637526652455, + "grad_norm": 0.31530193423014324, + "learning_rate": 9.707461656611623e-06, + "loss": 0.4586, + "step": 2865 + }, + { + "epoch": 0.38192963752665243, + "grad_norm": 0.3364086249978369, + "learning_rate": 9.707221632268169e-06, + "loss": 0.4971, + "step": 2866 + }, + { + "epoch": 0.3820628997867804, + "grad_norm": 0.3011414071897853, + "learning_rate": 9.706981512466348e-06, + "loss": 0.4544, + "step": 2867 + }, + { + "epoch": 0.3821961620469083, + "grad_norm": 0.29629493165888576, + "learning_rate": 9.706741297211029e-06, + "loss": 0.3927, + "step": 2868 + }, + { + "epoch": 0.38232942430703626, + "grad_norm": 0.3167538068595624, + "learning_rate": 9.706500986507084e-06, + "loss": 0.409, + "step": 2869 + }, + { + "epoch": 0.3824626865671642, + "grad_norm": 0.30013533228752476, + "learning_rate": 9.706260580359384e-06, + "loss": 0.4165, + "step": 2870 + }, + { + "epoch": 0.3825959488272921, + "grad_norm": 0.3038948532833988, + "learning_rate": 9.706020078772807e-06, + "loss": 0.4414, + "step": 2871 + }, + { + "epoch": 0.38272921108742003, + "grad_norm": 0.3038181073455614, + "learning_rate": 9.705779481752229e-06, + "loss": 0.4006, + "step": 2872 + }, + { + "epoch": 0.38286247334754797, + "grad_norm": 0.3245044677247814, + "learning_rate": 9.705538789302528e-06, + "loss": 0.4615, + "step": 2873 + }, + { + "epoch": 0.3829957356076759, + "grad_norm": 0.2981179698851099, + "learning_rate": 9.705298001428587e-06, + "loss": 0.3765, + "step": 2874 + }, + { + "epoch": 0.38312899786780386, + "grad_norm": 0.31630426153901203, + "learning_rate": 9.705057118135289e-06, + "loss": 0.4051, + "step": 2875 + }, + { + "epoch": 0.38326226012793174, + "grad_norm": 0.29885570826399666, + "learning_rate": 9.704816139427518e-06, + "loss": 0.3608, + "step": 2876 + }, + { + "epoch": 0.3833955223880597, + "grad_norm": 0.31246735729287894, + "learning_rate": 9.70457506531016e-06, + "loss": 0.4366, + "step": 2877 + }, + { + "epoch": 0.3835287846481876, + "grad_norm": 0.30642994706527066, + "learning_rate": 9.704333895788104e-06, + "loss": 0.3967, + "step": 2878 + }, + { + "epoch": 0.38366204690831557, + "grad_norm": 0.34106519690427944, + "learning_rate": 9.704092630866243e-06, + "loss": 0.5104, + "step": 2879 + }, + { + "epoch": 0.3837953091684435, + "grad_norm": 0.2922560993283016, + "learning_rate": 9.703851270549469e-06, + "loss": 0.4085, + "step": 2880 + }, + { + "epoch": 0.38392857142857145, + "grad_norm": 0.3226566197146509, + "learning_rate": 9.703609814842674e-06, + "loss": 0.4628, + "step": 2881 + }, + { + "epoch": 0.38406183368869934, + "grad_norm": 0.3021306485712456, + "learning_rate": 9.703368263750756e-06, + "loss": 0.3962, + "step": 2882 + }, + { + "epoch": 0.3841950959488273, + "grad_norm": 0.3046077434941965, + "learning_rate": 9.703126617278616e-06, + "loss": 0.4364, + "step": 2883 + }, + { + "epoch": 0.3843283582089552, + "grad_norm": 0.311571075159566, + "learning_rate": 9.70288487543115e-06, + "loss": 0.381, + "step": 2884 + }, + { + "epoch": 0.38446162046908317, + "grad_norm": 0.30526965202098594, + "learning_rate": 9.702643038213261e-06, + "loss": 0.387, + "step": 2885 + }, + { + "epoch": 0.3845948827292111, + "grad_norm": 0.30398389307527773, + "learning_rate": 9.702401105629857e-06, + "loss": 0.3601, + "step": 2886 + }, + { + "epoch": 0.384728144989339, + "grad_norm": 0.34593608715356616, + "learning_rate": 9.702159077685841e-06, + "loss": 0.557, + "step": 2887 + }, + { + "epoch": 0.38486140724946694, + "grad_norm": 0.3285619831205183, + "learning_rate": 9.701916954386121e-06, + "loss": 0.4523, + "step": 2888 + }, + { + "epoch": 0.3849946695095949, + "grad_norm": 0.3229457197800097, + "learning_rate": 9.70167473573561e-06, + "loss": 0.4224, + "step": 2889 + }, + { + "epoch": 0.3851279317697228, + "grad_norm": 0.3008494224087536, + "learning_rate": 9.701432421739215e-06, + "loss": 0.3269, + "step": 2890 + }, + { + "epoch": 0.38526119402985076, + "grad_norm": 0.3282834203429953, + "learning_rate": 9.701190012401855e-06, + "loss": 0.3848, + "step": 2891 + }, + { + "epoch": 0.3853944562899787, + "grad_norm": 0.31004821726482523, + "learning_rate": 9.700947507728443e-06, + "loss": 0.4426, + "step": 2892 + }, + { + "epoch": 0.3855277185501066, + "grad_norm": 0.29695830009402546, + "learning_rate": 9.700704907723897e-06, + "loss": 0.3929, + "step": 2893 + }, + { + "epoch": 0.38566098081023453, + "grad_norm": 0.30778351478753085, + "learning_rate": 9.700462212393138e-06, + "loss": 0.4736, + "step": 2894 + }, + { + "epoch": 0.3857942430703625, + "grad_norm": 0.3265586814243273, + "learning_rate": 9.700219421741087e-06, + "loss": 0.3765, + "step": 2895 + }, + { + "epoch": 0.3859275053304904, + "grad_norm": 0.3006090560078317, + "learning_rate": 9.699976535772666e-06, + "loss": 0.3796, + "step": 2896 + }, + { + "epoch": 0.38606076759061836, + "grad_norm": 0.3214198291515578, + "learning_rate": 9.699733554492802e-06, + "loss": 0.432, + "step": 2897 + }, + { + "epoch": 0.38619402985074625, + "grad_norm": 0.30104549360011623, + "learning_rate": 9.699490477906423e-06, + "loss": 0.5022, + "step": 2898 + }, + { + "epoch": 0.3863272921108742, + "grad_norm": 0.3079661737263009, + "learning_rate": 9.699247306018457e-06, + "loss": 0.4359, + "step": 2899 + }, + { + "epoch": 0.38646055437100213, + "grad_norm": 0.3107794942646912, + "learning_rate": 9.699004038833837e-06, + "loss": 0.4712, + "step": 2900 + }, + { + "epoch": 0.38659381663113007, + "grad_norm": 0.32262921026984426, + "learning_rate": 9.698760676357496e-06, + "loss": 0.4353, + "step": 2901 + }, + { + "epoch": 0.386727078891258, + "grad_norm": 0.31144502461243573, + "learning_rate": 9.698517218594367e-06, + "loss": 0.4929, + "step": 2902 + }, + { + "epoch": 0.3868603411513859, + "grad_norm": 0.3039546406681857, + "learning_rate": 9.698273665549389e-06, + "loss": 0.4398, + "step": 2903 + }, + { + "epoch": 0.38699360341151384, + "grad_norm": 0.30060766328624816, + "learning_rate": 9.6980300172275e-06, + "loss": 0.4651, + "step": 2904 + }, + { + "epoch": 0.3871268656716418, + "grad_norm": 0.30792957014101136, + "learning_rate": 9.697786273633642e-06, + "loss": 0.4102, + "step": 2905 + }, + { + "epoch": 0.3872601279317697, + "grad_norm": 0.3022326433947693, + "learning_rate": 9.697542434772759e-06, + "loss": 0.3959, + "step": 2906 + }, + { + "epoch": 0.38739339019189767, + "grad_norm": 0.30154553292296554, + "learning_rate": 9.697298500649792e-06, + "loss": 0.3651, + "step": 2907 + }, + { + "epoch": 0.3875266524520256, + "grad_norm": 0.29790868879616017, + "learning_rate": 9.697054471269692e-06, + "loss": 0.3792, + "step": 2908 + }, + { + "epoch": 0.3876599147121535, + "grad_norm": 0.2908282181906082, + "learning_rate": 9.696810346637406e-06, + "loss": 0.3885, + "step": 2909 + }, + { + "epoch": 0.38779317697228144, + "grad_norm": 0.3035504049972817, + "learning_rate": 9.696566126757883e-06, + "loss": 0.4147, + "step": 2910 + }, + { + "epoch": 0.3879264392324094, + "grad_norm": 0.3200920219529828, + "learning_rate": 9.696321811636079e-06, + "loss": 0.4585, + "step": 2911 + }, + { + "epoch": 0.3880597014925373, + "grad_norm": 0.30806879582840624, + "learning_rate": 9.696077401276945e-06, + "loss": 0.3964, + "step": 2912 + }, + { + "epoch": 0.38819296375266527, + "grad_norm": 0.2985712532521964, + "learning_rate": 9.69583289568544e-06, + "loss": 0.4212, + "step": 2913 + }, + { + "epoch": 0.38832622601279315, + "grad_norm": 0.4235168033541682, + "learning_rate": 9.695588294866519e-06, + "loss": 0.4486, + "step": 2914 + }, + { + "epoch": 0.3884594882729211, + "grad_norm": 0.31782194770648137, + "learning_rate": 9.695343598825146e-06, + "loss": 0.4286, + "step": 2915 + }, + { + "epoch": 0.38859275053304904, + "grad_norm": 0.3145287149784932, + "learning_rate": 9.695098807566281e-06, + "loss": 0.4615, + "step": 2916 + }, + { + "epoch": 0.388726012793177, + "grad_norm": 0.31675041611086907, + "learning_rate": 9.694853921094892e-06, + "loss": 0.4195, + "step": 2917 + }, + { + "epoch": 0.3888592750533049, + "grad_norm": 0.30514402089760706, + "learning_rate": 9.69460893941594e-06, + "loss": 0.5006, + "step": 2918 + }, + { + "epoch": 0.38899253731343286, + "grad_norm": 0.30185751102781394, + "learning_rate": 9.694363862534394e-06, + "loss": 0.4153, + "step": 2919 + }, + { + "epoch": 0.38912579957356075, + "grad_norm": 0.3013150289187811, + "learning_rate": 9.694118690455228e-06, + "loss": 0.434, + "step": 2920 + }, + { + "epoch": 0.3892590618336887, + "grad_norm": 0.30858320996376404, + "learning_rate": 9.693873423183408e-06, + "loss": 0.4042, + "step": 2921 + }, + { + "epoch": 0.38939232409381663, + "grad_norm": 0.3002896977955645, + "learning_rate": 9.693628060723912e-06, + "loss": 0.3681, + "step": 2922 + }, + { + "epoch": 0.3895255863539446, + "grad_norm": 0.31019214814739043, + "learning_rate": 9.693382603081714e-06, + "loss": 0.5011, + "step": 2923 + }, + { + "epoch": 0.3896588486140725, + "grad_norm": 0.3223703897252858, + "learning_rate": 9.693137050261793e-06, + "loss": 0.4098, + "step": 2924 + }, + { + "epoch": 0.3897921108742004, + "grad_norm": 0.31458071776476654, + "learning_rate": 9.692891402269127e-06, + "loss": 0.417, + "step": 2925 + }, + { + "epoch": 0.38992537313432835, + "grad_norm": 0.30467772841522833, + "learning_rate": 9.692645659108699e-06, + "loss": 0.3706, + "step": 2926 + }, + { + "epoch": 0.3900586353944563, + "grad_norm": 0.29907832098853404, + "learning_rate": 9.692399820785491e-06, + "loss": 0.3748, + "step": 2927 + }, + { + "epoch": 0.39019189765458423, + "grad_norm": 0.30765060644276465, + "learning_rate": 9.69215388730449e-06, + "loss": 0.4601, + "step": 2928 + }, + { + "epoch": 0.39032515991471217, + "grad_norm": 0.2971873380940106, + "learning_rate": 9.691907858670682e-06, + "loss": 0.4952, + "step": 2929 + }, + { + "epoch": 0.39045842217484006, + "grad_norm": 0.30878152852679025, + "learning_rate": 9.691661734889055e-06, + "loss": 0.3953, + "step": 2930 + }, + { + "epoch": 0.390591684434968, + "grad_norm": 0.3018191050818357, + "learning_rate": 9.691415515964603e-06, + "loss": 0.4492, + "step": 2931 + }, + { + "epoch": 0.39072494669509594, + "grad_norm": 0.288440074901337, + "learning_rate": 9.691169201902319e-06, + "loss": 0.3628, + "step": 2932 + }, + { + "epoch": 0.3908582089552239, + "grad_norm": 0.2975254751349855, + "learning_rate": 9.690922792707196e-06, + "loss": 0.4749, + "step": 2933 + }, + { + "epoch": 0.3909914712153518, + "grad_norm": 0.30169823329135587, + "learning_rate": 9.690676288384232e-06, + "loss": 0.4121, + "step": 2934 + }, + { + "epoch": 0.39112473347547977, + "grad_norm": 0.3106923591721529, + "learning_rate": 9.690429688938426e-06, + "loss": 0.4121, + "step": 2935 + }, + { + "epoch": 0.39125799573560766, + "grad_norm": 0.28380520936781867, + "learning_rate": 9.690182994374779e-06, + "loss": 0.4034, + "step": 2936 + }, + { + "epoch": 0.3913912579957356, + "grad_norm": 0.29261018414577533, + "learning_rate": 9.689936204698294e-06, + "loss": 0.385, + "step": 2937 + }, + { + "epoch": 0.39152452025586354, + "grad_norm": 0.2971282889850028, + "learning_rate": 9.689689319913973e-06, + "loss": 0.4394, + "step": 2938 + }, + { + "epoch": 0.3916577825159915, + "grad_norm": 0.2898259068736625, + "learning_rate": 9.689442340026827e-06, + "loss": 0.4342, + "step": 2939 + }, + { + "epoch": 0.3917910447761194, + "grad_norm": 0.32004452106092435, + "learning_rate": 9.68919526504186e-06, + "loss": 0.489, + "step": 2940 + }, + { + "epoch": 0.3919243070362473, + "grad_norm": 0.3058662619811016, + "learning_rate": 9.688948094964085e-06, + "loss": 0.36, + "step": 2941 + }, + { + "epoch": 0.39205756929637525, + "grad_norm": 0.2933112899888082, + "learning_rate": 9.688700829798516e-06, + "loss": 0.4024, + "step": 2942 + }, + { + "epoch": 0.3921908315565032, + "grad_norm": 0.3289306497194446, + "learning_rate": 9.688453469550165e-06, + "loss": 0.5132, + "step": 2943 + }, + { + "epoch": 0.39232409381663114, + "grad_norm": 0.31601208809951004, + "learning_rate": 9.68820601422405e-06, + "loss": 0.4363, + "step": 2944 + }, + { + "epoch": 0.3924573560767591, + "grad_norm": 0.296994891254855, + "learning_rate": 9.687958463825184e-06, + "loss": 0.387, + "step": 2945 + }, + { + "epoch": 0.392590618336887, + "grad_norm": 0.3046210834789365, + "learning_rate": 9.687710818358593e-06, + "loss": 0.3982, + "step": 2946 + }, + { + "epoch": 0.3927238805970149, + "grad_norm": 0.3097007601435223, + "learning_rate": 9.687463077829298e-06, + "loss": 0.4387, + "step": 2947 + }, + { + "epoch": 0.39285714285714285, + "grad_norm": 0.3102630669072169, + "learning_rate": 9.687215242242321e-06, + "loss": 0.3987, + "step": 2948 + }, + { + "epoch": 0.3929904051172708, + "grad_norm": 0.31018507224346903, + "learning_rate": 9.686967311602688e-06, + "loss": 0.3871, + "step": 2949 + }, + { + "epoch": 0.39312366737739873, + "grad_norm": 0.3034262343285345, + "learning_rate": 9.686719285915428e-06, + "loss": 0.4189, + "step": 2950 + }, + { + "epoch": 0.3932569296375267, + "grad_norm": 0.32519785629235143, + "learning_rate": 9.686471165185572e-06, + "loss": 0.4513, + "step": 2951 + }, + { + "epoch": 0.39339019189765456, + "grad_norm": 0.3197380269386783, + "learning_rate": 9.686222949418149e-06, + "loss": 0.4, + "step": 2952 + }, + { + "epoch": 0.3935234541577825, + "grad_norm": 0.30709899783320205, + "learning_rate": 9.685974638618192e-06, + "loss": 0.4862, + "step": 2953 + }, + { + "epoch": 0.39365671641791045, + "grad_norm": 0.32867609230218303, + "learning_rate": 9.685726232790741e-06, + "loss": 0.4007, + "step": 2954 + }, + { + "epoch": 0.3937899786780384, + "grad_norm": 0.3113518252034492, + "learning_rate": 9.685477731940829e-06, + "loss": 0.4112, + "step": 2955 + }, + { + "epoch": 0.39392324093816633, + "grad_norm": 0.3387064221468105, + "learning_rate": 9.685229136073498e-06, + "loss": 0.4106, + "step": 2956 + }, + { + "epoch": 0.3940565031982942, + "grad_norm": 0.31048096808524245, + "learning_rate": 9.684980445193788e-06, + "loss": 0.3803, + "step": 2957 + }, + { + "epoch": 0.39418976545842216, + "grad_norm": 0.33552078244570327, + "learning_rate": 9.684731659306743e-06, + "loss": 0.5002, + "step": 2958 + }, + { + "epoch": 0.3943230277185501, + "grad_norm": 0.3211857065259698, + "learning_rate": 9.684482778417408e-06, + "loss": 0.4109, + "step": 2959 + }, + { + "epoch": 0.39445628997867804, + "grad_norm": 0.32254402305448115, + "learning_rate": 9.684233802530829e-06, + "loss": 0.4175, + "step": 2960 + }, + { + "epoch": 0.394589552238806, + "grad_norm": 0.3601384234084837, + "learning_rate": 9.683984731652056e-06, + "loss": 0.4056, + "step": 2961 + }, + { + "epoch": 0.3947228144989339, + "grad_norm": 0.30204777623092616, + "learning_rate": 9.68373556578614e-06, + "loss": 0.3824, + "step": 2962 + }, + { + "epoch": 0.3948560767590618, + "grad_norm": 0.3439834518993902, + "learning_rate": 9.683486304938132e-06, + "loss": 0.4953, + "step": 2963 + }, + { + "epoch": 0.39498933901918976, + "grad_norm": 0.31935256736998907, + "learning_rate": 9.68323694911309e-06, + "loss": 0.4545, + "step": 2964 + }, + { + "epoch": 0.3951226012793177, + "grad_norm": 0.33234164701450075, + "learning_rate": 9.682987498316069e-06, + "loss": 0.4093, + "step": 2965 + }, + { + "epoch": 0.39525586353944564, + "grad_norm": 0.3102829721579964, + "learning_rate": 9.68273795255213e-06, + "loss": 0.4044, + "step": 2966 + }, + { + "epoch": 0.3953891257995736, + "grad_norm": 0.3206418598146106, + "learning_rate": 9.68248831182633e-06, + "loss": 0.5886, + "step": 2967 + }, + { + "epoch": 0.39552238805970147, + "grad_norm": 0.33133549697124176, + "learning_rate": 9.682238576143733e-06, + "loss": 0.464, + "step": 2968 + }, + { + "epoch": 0.3956556503198294, + "grad_norm": 0.30769345256488445, + "learning_rate": 9.681988745509401e-06, + "loss": 0.5295, + "step": 2969 + }, + { + "epoch": 0.39578891257995735, + "grad_norm": 0.32306347242314415, + "learning_rate": 9.681738819928404e-06, + "loss": 0.4417, + "step": 2970 + }, + { + "epoch": 0.3959221748400853, + "grad_norm": 0.3234838830493696, + "learning_rate": 9.681488799405809e-06, + "loss": 0.3885, + "step": 2971 + }, + { + "epoch": 0.39605543710021324, + "grad_norm": 0.32005342891215843, + "learning_rate": 9.681238683946688e-06, + "loss": 0.4587, + "step": 2972 + }, + { + "epoch": 0.3961886993603412, + "grad_norm": 0.3080089106073009, + "learning_rate": 9.680988473556109e-06, + "loss": 0.4863, + "step": 2973 + }, + { + "epoch": 0.39632196162046907, + "grad_norm": 0.35611273864068127, + "learning_rate": 9.68073816823915e-06, + "loss": 0.4041, + "step": 2974 + }, + { + "epoch": 0.396455223880597, + "grad_norm": 0.2911552394108176, + "learning_rate": 9.680487768000883e-06, + "loss": 0.4166, + "step": 2975 + }, + { + "epoch": 0.39658848614072495, + "grad_norm": 0.30660784053317247, + "learning_rate": 9.68023727284639e-06, + "loss": 0.4642, + "step": 2976 + }, + { + "epoch": 0.3967217484008529, + "grad_norm": 0.30737136090341727, + "learning_rate": 9.679986682780749e-06, + "loss": 0.3434, + "step": 2977 + }, + { + "epoch": 0.39685501066098083, + "grad_norm": 0.31758171904650717, + "learning_rate": 9.67973599780904e-06, + "loss": 0.4862, + "step": 2978 + }, + { + "epoch": 0.3969882729211087, + "grad_norm": 0.3064798848920504, + "learning_rate": 9.679485217936351e-06, + "loss": 0.309, + "step": 2979 + }, + { + "epoch": 0.39712153518123666, + "grad_norm": 0.3194637027633714, + "learning_rate": 9.679234343167764e-06, + "loss": 0.4242, + "step": 2980 + }, + { + "epoch": 0.3972547974413646, + "grad_norm": 0.32608669719855954, + "learning_rate": 9.678983373508367e-06, + "loss": 0.472, + "step": 2981 + }, + { + "epoch": 0.39738805970149255, + "grad_norm": 0.3103164870833503, + "learning_rate": 9.67873230896325e-06, + "loss": 0.4473, + "step": 2982 + }, + { + "epoch": 0.3975213219616205, + "grad_norm": 0.30315134041775743, + "learning_rate": 9.678481149537506e-06, + "loss": 0.5162, + "step": 2983 + }, + { + "epoch": 0.3976545842217484, + "grad_norm": 0.3329546646059559, + "learning_rate": 9.678229895236224e-06, + "loss": 0.4989, + "step": 2984 + }, + { + "epoch": 0.3977878464818763, + "grad_norm": 0.31301997032153517, + "learning_rate": 9.677978546064503e-06, + "loss": 0.4344, + "step": 2985 + }, + { + "epoch": 0.39792110874200426, + "grad_norm": 0.3024545759905348, + "learning_rate": 9.67772710202744e-06, + "loss": 0.4455, + "step": 2986 + }, + { + "epoch": 0.3980543710021322, + "grad_norm": 0.3036879659290102, + "learning_rate": 9.677475563130133e-06, + "loss": 0.4658, + "step": 2987 + }, + { + "epoch": 0.39818763326226014, + "grad_norm": 0.28956345028790553, + "learning_rate": 9.677223929377683e-06, + "loss": 0.4064, + "step": 2988 + }, + { + "epoch": 0.3983208955223881, + "grad_norm": 0.2957526090094977, + "learning_rate": 9.676972200775192e-06, + "loss": 0.3808, + "step": 2989 + }, + { + "epoch": 0.39845415778251597, + "grad_norm": 0.3142916757061957, + "learning_rate": 9.676720377327767e-06, + "loss": 0.5568, + "step": 2990 + }, + { + "epoch": 0.3985874200426439, + "grad_norm": 0.28788485195766705, + "learning_rate": 9.676468459040514e-06, + "loss": 0.5613, + "step": 2991 + }, + { + "epoch": 0.39872068230277186, + "grad_norm": 0.31259957291368173, + "learning_rate": 9.67621644591854e-06, + "loss": 0.3878, + "step": 2992 + }, + { + "epoch": 0.3988539445628998, + "grad_norm": 0.2940206405176207, + "learning_rate": 9.675964337966956e-06, + "loss": 0.4598, + "step": 2993 + }, + { + "epoch": 0.39898720682302774, + "grad_norm": 0.3078806399858472, + "learning_rate": 9.675712135190877e-06, + "loss": 0.4021, + "step": 2994 + }, + { + "epoch": 0.3991204690831556, + "grad_norm": 0.2892838905564314, + "learning_rate": 9.675459837595415e-06, + "loss": 0.3595, + "step": 2995 + }, + { + "epoch": 0.39925373134328357, + "grad_norm": 0.30183237532739776, + "learning_rate": 9.675207445185688e-06, + "loss": 0.4725, + "step": 2996 + }, + { + "epoch": 0.3993869936034115, + "grad_norm": 0.28262156057576976, + "learning_rate": 9.674954957966813e-06, + "loss": 0.3815, + "step": 2997 + }, + { + "epoch": 0.39952025586353945, + "grad_norm": 0.28896965316654005, + "learning_rate": 9.674702375943911e-06, + "loss": 0.4076, + "step": 2998 + }, + { + "epoch": 0.3996535181236674, + "grad_norm": 0.30147160127596523, + "learning_rate": 9.674449699122107e-06, + "loss": 0.4385, + "step": 2999 + }, + { + "epoch": 0.3997867803837953, + "grad_norm": 0.29984432221407165, + "learning_rate": 9.674196927506517e-06, + "loss": 0.3996, + "step": 3000 + }, + { + "epoch": 0.3999200426439232, + "grad_norm": 0.3030120805328541, + "learning_rate": 9.673944061102274e-06, + "loss": 0.3929, + "step": 3001 + }, + { + "epoch": 0.40005330490405117, + "grad_norm": 0.30841144021353256, + "learning_rate": 9.673691099914504e-06, + "loss": 0.4715, + "step": 3002 + }, + { + "epoch": 0.4001865671641791, + "grad_norm": 0.29015033917656624, + "learning_rate": 9.673438043948339e-06, + "loss": 0.3743, + "step": 3003 + }, + { + "epoch": 0.40031982942430705, + "grad_norm": 0.3110308952171781, + "learning_rate": 9.673184893208905e-06, + "loss": 0.4118, + "step": 3004 + }, + { + "epoch": 0.400453091684435, + "grad_norm": 0.3086394840006935, + "learning_rate": 9.67293164770134e-06, + "loss": 0.3903, + "step": 3005 + }, + { + "epoch": 0.4005863539445629, + "grad_norm": 0.31931131978697375, + "learning_rate": 9.672678307430779e-06, + "loss": 0.5568, + "step": 3006 + }, + { + "epoch": 0.4007196162046908, + "grad_norm": 0.3310367333280477, + "learning_rate": 9.67242487240236e-06, + "loss": 0.4482, + "step": 3007 + }, + { + "epoch": 0.40085287846481876, + "grad_norm": 0.2892944623079035, + "learning_rate": 9.67217134262122e-06, + "loss": 0.3512, + "step": 3008 + }, + { + "epoch": 0.4009861407249467, + "grad_norm": 0.3022322163634319, + "learning_rate": 9.671917718092503e-06, + "loss": 0.3933, + "step": 3009 + }, + { + "epoch": 0.40111940298507465, + "grad_norm": 0.3080039688946217, + "learning_rate": 9.671663998821353e-06, + "loss": 0.4903, + "step": 3010 + }, + { + "epoch": 0.40125266524520253, + "grad_norm": 0.30882381756209826, + "learning_rate": 9.67141018481291e-06, + "loss": 0.407, + "step": 3011 + }, + { + "epoch": 0.4013859275053305, + "grad_norm": 0.30079656668608634, + "learning_rate": 9.671156276072328e-06, + "loss": 0.3847, + "step": 3012 + }, + { + "epoch": 0.4015191897654584, + "grad_norm": 0.31229980680733305, + "learning_rate": 9.67090227260475e-06, + "loss": 0.3732, + "step": 3013 + }, + { + "epoch": 0.40165245202558636, + "grad_norm": 0.29417044553801525, + "learning_rate": 9.670648174415332e-06, + "loss": 0.3552, + "step": 3014 + }, + { + "epoch": 0.4017857142857143, + "grad_norm": 0.3059240831820466, + "learning_rate": 9.670393981509223e-06, + "loss": 0.3743, + "step": 3015 + }, + { + "epoch": 0.40191897654584224, + "grad_norm": 0.3140157301978523, + "learning_rate": 9.670139693891582e-06, + "loss": 0.5263, + "step": 3016 + }, + { + "epoch": 0.40205223880597013, + "grad_norm": 0.3011646573275661, + "learning_rate": 9.66988531156756e-06, + "loss": 0.3267, + "step": 3017 + }, + { + "epoch": 0.4021855010660981, + "grad_norm": 0.303826357166676, + "learning_rate": 9.66963083454232e-06, + "loss": 0.4585, + "step": 3018 + }, + { + "epoch": 0.402318763326226, + "grad_norm": 0.3056436760188882, + "learning_rate": 9.669376262821022e-06, + "loss": 0.4296, + "step": 3019 + }, + { + "epoch": 0.40245202558635396, + "grad_norm": 0.30761901145517034, + "learning_rate": 9.669121596408828e-06, + "loss": 0.4307, + "step": 3020 + }, + { + "epoch": 0.4025852878464819, + "grad_norm": 0.31796004769666014, + "learning_rate": 9.668866835310901e-06, + "loss": 0.4225, + "step": 3021 + }, + { + "epoch": 0.4027185501066098, + "grad_norm": 0.31342819687626944, + "learning_rate": 9.66861197953241e-06, + "loss": 0.3982, + "step": 3022 + }, + { + "epoch": 0.4028518123667377, + "grad_norm": 0.28211683656575637, + "learning_rate": 9.66835702907852e-06, + "loss": 0.3708, + "step": 3023 + }, + { + "epoch": 0.40298507462686567, + "grad_norm": 0.306172239101436, + "learning_rate": 9.668101983954406e-06, + "loss": 0.371, + "step": 3024 + }, + { + "epoch": 0.4031183368869936, + "grad_norm": 0.2906899234036253, + "learning_rate": 9.667846844165236e-06, + "loss": 0.4495, + "step": 3025 + }, + { + "epoch": 0.40325159914712155, + "grad_norm": 0.3189755092556747, + "learning_rate": 9.667591609716183e-06, + "loss": 0.378, + "step": 3026 + }, + { + "epoch": 0.40338486140724944, + "grad_norm": 0.3194340396319071, + "learning_rate": 9.667336280612427e-06, + "loss": 0.4861, + "step": 3027 + }, + { + "epoch": 0.4035181236673774, + "grad_norm": 0.31046833858226985, + "learning_rate": 9.667080856859144e-06, + "loss": 0.3633, + "step": 3028 + }, + { + "epoch": 0.4036513859275053, + "grad_norm": 0.30013744611284626, + "learning_rate": 9.666825338461513e-06, + "loss": 0.3305, + "step": 3029 + }, + { + "epoch": 0.40378464818763327, + "grad_norm": 0.3164163111316692, + "learning_rate": 9.666569725424717e-06, + "loss": 0.4091, + "step": 3030 + }, + { + "epoch": 0.4039179104477612, + "grad_norm": 0.3038147993479359, + "learning_rate": 9.66631401775394e-06, + "loss": 0.4445, + "step": 3031 + }, + { + "epoch": 0.40405117270788915, + "grad_norm": 0.3403278424730379, + "learning_rate": 9.666058215454364e-06, + "loss": 0.4096, + "step": 3032 + }, + { + "epoch": 0.40418443496801704, + "grad_norm": 0.31203463288044025, + "learning_rate": 9.66580231853118e-06, + "loss": 0.4601, + "step": 3033 + }, + { + "epoch": 0.404317697228145, + "grad_norm": 0.31125556680152966, + "learning_rate": 9.665546326989576e-06, + "loss": 0.4243, + "step": 3034 + }, + { + "epoch": 0.4044509594882729, + "grad_norm": 0.3236416722744449, + "learning_rate": 9.665290240834747e-06, + "loss": 0.475, + "step": 3035 + }, + { + "epoch": 0.40458422174840086, + "grad_norm": 0.3207021462407511, + "learning_rate": 9.665034060071878e-06, + "loss": 0.4402, + "step": 3036 + }, + { + "epoch": 0.4047174840085288, + "grad_norm": 0.3071246784816296, + "learning_rate": 9.664777784706172e-06, + "loss": 0.3833, + "step": 3037 + }, + { + "epoch": 0.4048507462686567, + "grad_norm": 0.3163680617349988, + "learning_rate": 9.664521414742823e-06, + "loss": 0.5174, + "step": 3038 + }, + { + "epoch": 0.40498400852878463, + "grad_norm": 0.32083704634604854, + "learning_rate": 9.664264950187028e-06, + "loss": 0.4765, + "step": 3039 + }, + { + "epoch": 0.4051172707889126, + "grad_norm": 0.32098701564126625, + "learning_rate": 9.664008391043991e-06, + "loss": 0.3953, + "step": 3040 + }, + { + "epoch": 0.4052505330490405, + "grad_norm": 0.28746143507100036, + "learning_rate": 9.663751737318914e-06, + "loss": 0.4027, + "step": 3041 + }, + { + "epoch": 0.40538379530916846, + "grad_norm": 0.31341285557993476, + "learning_rate": 9.663494989017001e-06, + "loss": 0.3826, + "step": 3042 + }, + { + "epoch": 0.4055170575692964, + "grad_norm": 0.3402229277778395, + "learning_rate": 9.66323814614346e-06, + "loss": 0.4706, + "step": 3043 + }, + { + "epoch": 0.4056503198294243, + "grad_norm": 0.30645865719158116, + "learning_rate": 9.662981208703496e-06, + "loss": 0.3323, + "step": 3044 + }, + { + "epoch": 0.40578358208955223, + "grad_norm": 0.3055233574799892, + "learning_rate": 9.662724176702324e-06, + "loss": 0.4497, + "step": 3045 + }, + { + "epoch": 0.4059168443496802, + "grad_norm": 0.2960031652840903, + "learning_rate": 9.662467050145153e-06, + "loss": 0.4723, + "step": 3046 + }, + { + "epoch": 0.4060501066098081, + "grad_norm": 0.30333050144482737, + "learning_rate": 9.6622098290372e-06, + "loss": 0.3651, + "step": 3047 + }, + { + "epoch": 0.40618336886993606, + "grad_norm": 0.3146405521178438, + "learning_rate": 9.66195251338368e-06, + "loss": 0.4242, + "step": 3048 + }, + { + "epoch": 0.40631663113006394, + "grad_norm": 0.2957515704310865, + "learning_rate": 9.66169510318981e-06, + "loss": 0.4633, + "step": 3049 + }, + { + "epoch": 0.4064498933901919, + "grad_norm": 0.31394174262561797, + "learning_rate": 9.661437598460812e-06, + "loss": 0.4007, + "step": 3050 + }, + { + "epoch": 0.4065831556503198, + "grad_norm": 0.31369078073169926, + "learning_rate": 9.661179999201905e-06, + "loss": 0.5027, + "step": 3051 + }, + { + "epoch": 0.40671641791044777, + "grad_norm": 0.30508007481434807, + "learning_rate": 9.660922305418318e-06, + "loss": 0.4576, + "step": 3052 + }, + { + "epoch": 0.4068496801705757, + "grad_norm": 0.3126567821480784, + "learning_rate": 9.660664517115273e-06, + "loss": 0.433, + "step": 3053 + }, + { + "epoch": 0.4069829424307036, + "grad_norm": 0.4824002840460639, + "learning_rate": 9.660406634297998e-06, + "loss": 0.3823, + "step": 3054 + }, + { + "epoch": 0.40711620469083154, + "grad_norm": 0.3130911224542581, + "learning_rate": 9.660148656971724e-06, + "loss": 0.5334, + "step": 3055 + }, + { + "epoch": 0.4072494669509595, + "grad_norm": 0.3022820107844558, + "learning_rate": 9.65989058514168e-06, + "loss": 0.4607, + "step": 3056 + }, + { + "epoch": 0.4073827292110874, + "grad_norm": 0.30001961382071085, + "learning_rate": 9.659632418813104e-06, + "loss": 0.4986, + "step": 3057 + }, + { + "epoch": 0.40751599147121537, + "grad_norm": 0.31191612617947073, + "learning_rate": 9.659374157991226e-06, + "loss": 0.4759, + "step": 3058 + }, + { + "epoch": 0.4076492537313433, + "grad_norm": 0.3073887844039203, + "learning_rate": 9.659115802681285e-06, + "loss": 0.3926, + "step": 3059 + }, + { + "epoch": 0.4077825159914712, + "grad_norm": 0.3228908190819538, + "learning_rate": 9.658857352888524e-06, + "loss": 0.4305, + "step": 3060 + }, + { + "epoch": 0.40791577825159914, + "grad_norm": 0.31478038398681446, + "learning_rate": 9.65859880861818e-06, + "loss": 0.4006, + "step": 3061 + }, + { + "epoch": 0.4080490405117271, + "grad_norm": 0.3754583569602496, + "learning_rate": 9.658340169875498e-06, + "loss": 0.4338, + "step": 3062 + }, + { + "epoch": 0.408182302771855, + "grad_norm": 0.3173640686465143, + "learning_rate": 9.658081436665721e-06, + "loss": 0.452, + "step": 3063 + }, + { + "epoch": 0.40831556503198296, + "grad_norm": 0.363216491087387, + "learning_rate": 9.657822608994096e-06, + "loss": 0.4272, + "step": 3064 + }, + { + "epoch": 0.40844882729211085, + "grad_norm": 0.32602366294907087, + "learning_rate": 9.657563686865875e-06, + "loss": 0.4381, + "step": 3065 + }, + { + "epoch": 0.4085820895522388, + "grad_norm": 0.32236290509358195, + "learning_rate": 9.657304670286307e-06, + "loss": 0.4089, + "step": 3066 + }, + { + "epoch": 0.40871535181236673, + "grad_norm": 0.3411218317432699, + "learning_rate": 9.657045559260643e-06, + "loss": 0.4258, + "step": 3067 + }, + { + "epoch": 0.4088486140724947, + "grad_norm": 0.3260044251125263, + "learning_rate": 9.65678635379414e-06, + "loss": 0.435, + "step": 3068 + }, + { + "epoch": 0.4089818763326226, + "grad_norm": 0.3351803217927281, + "learning_rate": 9.656527053892051e-06, + "loss": 0.4121, + "step": 3069 + }, + { + "epoch": 0.40911513859275056, + "grad_norm": 0.32714578704788944, + "learning_rate": 9.656267659559639e-06, + "loss": 0.4078, + "step": 3070 + }, + { + "epoch": 0.40924840085287845, + "grad_norm": 0.34444133817492995, + "learning_rate": 9.656008170802162e-06, + "loss": 0.4517, + "step": 3071 + }, + { + "epoch": 0.4093816631130064, + "grad_norm": 0.3044102110380734, + "learning_rate": 9.65574858762488e-06, + "loss": 0.3912, + "step": 3072 + }, + { + "epoch": 0.40951492537313433, + "grad_norm": 0.3310113404635759, + "learning_rate": 9.655488910033062e-06, + "loss": 0.3918, + "step": 3073 + }, + { + "epoch": 0.4096481876332623, + "grad_norm": 0.30985149015592445, + "learning_rate": 9.65522913803197e-06, + "loss": 0.4094, + "step": 3074 + }, + { + "epoch": 0.4097814498933902, + "grad_norm": 0.3229293740132226, + "learning_rate": 9.654969271626873e-06, + "loss": 0.3887, + "step": 3075 + }, + { + "epoch": 0.4099147121535181, + "grad_norm": 0.3268418744222901, + "learning_rate": 9.654709310823042e-06, + "loss": 0.4362, + "step": 3076 + }, + { + "epoch": 0.41004797441364604, + "grad_norm": 0.33788655311958526, + "learning_rate": 9.654449255625745e-06, + "loss": 0.4334, + "step": 3077 + }, + { + "epoch": 0.410181236673774, + "grad_norm": 0.31876520272029113, + "learning_rate": 9.654189106040264e-06, + "loss": 0.4274, + "step": 3078 + }, + { + "epoch": 0.4103144989339019, + "grad_norm": 0.32728141659394844, + "learning_rate": 9.653928862071866e-06, + "loss": 0.3667, + "step": 3079 + }, + { + "epoch": 0.41044776119402987, + "grad_norm": 0.3264332041173235, + "learning_rate": 9.653668523725831e-06, + "loss": 0.4396, + "step": 3080 + }, + { + "epoch": 0.41058102345415776, + "grad_norm": 0.333101990766264, + "learning_rate": 9.65340809100744e-06, + "loss": 0.4517, + "step": 3081 + }, + { + "epoch": 0.4107142857142857, + "grad_norm": 0.32211341297078444, + "learning_rate": 9.653147563921974e-06, + "loss": 0.5057, + "step": 3082 + }, + { + "epoch": 0.41084754797441364, + "grad_norm": 0.3324787001240408, + "learning_rate": 9.652886942474714e-06, + "loss": 0.4985, + "step": 3083 + }, + { + "epoch": 0.4109808102345416, + "grad_norm": 0.32198139988777846, + "learning_rate": 9.652626226670949e-06, + "loss": 0.4846, + "step": 3084 + }, + { + "epoch": 0.4111140724946695, + "grad_norm": 0.3261855018692153, + "learning_rate": 9.652365416515963e-06, + "loss": 0.4706, + "step": 3085 + }, + { + "epoch": 0.41124733475479747, + "grad_norm": 0.3274418747457782, + "learning_rate": 9.652104512015048e-06, + "loss": 0.4499, + "step": 3086 + }, + { + "epoch": 0.41138059701492535, + "grad_norm": 0.30826303127149096, + "learning_rate": 9.65184351317349e-06, + "loss": 0.421, + "step": 3087 + }, + { + "epoch": 0.4115138592750533, + "grad_norm": 0.31771629959908715, + "learning_rate": 9.651582419996588e-06, + "loss": 0.3548, + "step": 3088 + }, + { + "epoch": 0.41164712153518124, + "grad_norm": 0.34672598111607195, + "learning_rate": 9.651321232489632e-06, + "loss": 0.4878, + "step": 3089 + }, + { + "epoch": 0.4117803837953092, + "grad_norm": 0.3395771737344425, + "learning_rate": 9.651059950657919e-06, + "loss": 0.4661, + "step": 3090 + }, + { + "epoch": 0.4119136460554371, + "grad_norm": 0.301002778274029, + "learning_rate": 9.65079857450675e-06, + "loss": 0.3828, + "step": 3091 + }, + { + "epoch": 0.412046908315565, + "grad_norm": 0.3168069520325891, + "learning_rate": 9.650537104041424e-06, + "loss": 0.5051, + "step": 3092 + }, + { + "epoch": 0.41218017057569295, + "grad_norm": 0.3075637506265076, + "learning_rate": 9.650275539267244e-06, + "loss": 0.4219, + "step": 3093 + }, + { + "epoch": 0.4123134328358209, + "grad_norm": 0.29261838829890163, + "learning_rate": 9.650013880189515e-06, + "loss": 0.3807, + "step": 3094 + }, + { + "epoch": 0.41244669509594883, + "grad_norm": 0.3172226107412056, + "learning_rate": 9.64975212681354e-06, + "loss": 0.5167, + "step": 3095 + }, + { + "epoch": 0.4125799573560768, + "grad_norm": 0.30069411782571687, + "learning_rate": 9.649490279144631e-06, + "loss": 0.3975, + "step": 3096 + }, + { + "epoch": 0.4127132196162047, + "grad_norm": 0.311675484503204, + "learning_rate": 9.649228337188094e-06, + "loss": 0.3846, + "step": 3097 + }, + { + "epoch": 0.4128464818763326, + "grad_norm": 0.29810614739860547, + "learning_rate": 9.648966300949247e-06, + "loss": 0.3913, + "step": 3098 + }, + { + "epoch": 0.41297974413646055, + "grad_norm": 0.30663913675520926, + "learning_rate": 9.648704170433397e-06, + "loss": 0.3443, + "step": 3099 + }, + { + "epoch": 0.4131130063965885, + "grad_norm": 0.34036426798358416, + "learning_rate": 9.648441945645864e-06, + "loss": 0.3553, + "step": 3100 + }, + { + "epoch": 0.41324626865671643, + "grad_norm": 0.3115275062000373, + "learning_rate": 9.648179626591965e-06, + "loss": 0.38, + "step": 3101 + }, + { + "epoch": 0.4133795309168444, + "grad_norm": 0.30727686426642703, + "learning_rate": 9.647917213277019e-06, + "loss": 0.4163, + "step": 3102 + }, + { + "epoch": 0.41351279317697226, + "grad_norm": 0.32077354118863005, + "learning_rate": 9.647654705706349e-06, + "loss": 0.38, + "step": 3103 + }, + { + "epoch": 0.4136460554371002, + "grad_norm": 0.32949054504610054, + "learning_rate": 9.647392103885274e-06, + "loss": 0.4125, + "step": 3104 + }, + { + "epoch": 0.41377931769722814, + "grad_norm": 0.3072297110768822, + "learning_rate": 9.647129407819124e-06, + "loss": 0.3857, + "step": 3105 + }, + { + "epoch": 0.4139125799573561, + "grad_norm": 0.34734642566300705, + "learning_rate": 9.646866617513227e-06, + "loss": 0.4924, + "step": 3106 + }, + { + "epoch": 0.41404584221748403, + "grad_norm": 0.320600771186401, + "learning_rate": 9.646603732972908e-06, + "loss": 0.4303, + "step": 3107 + }, + { + "epoch": 0.4141791044776119, + "grad_norm": 0.3181771276367656, + "learning_rate": 9.6463407542035e-06, + "loss": 0.3578, + "step": 3108 + }, + { + "epoch": 0.41431236673773986, + "grad_norm": 0.3549203253693984, + "learning_rate": 9.646077681210335e-06, + "loss": 0.3984, + "step": 3109 + }, + { + "epoch": 0.4144456289978678, + "grad_norm": 0.3278846910826466, + "learning_rate": 9.64581451399875e-06, + "loss": 0.4014, + "step": 3110 + }, + { + "epoch": 0.41457889125799574, + "grad_norm": 0.34719160427200957, + "learning_rate": 9.645551252574082e-06, + "loss": 0.3808, + "step": 3111 + }, + { + "epoch": 0.4147121535181237, + "grad_norm": 0.3168228955471757, + "learning_rate": 9.645287896941667e-06, + "loss": 0.3905, + "step": 3112 + }, + { + "epoch": 0.4148454157782516, + "grad_norm": 0.3304954626195459, + "learning_rate": 9.645024447106847e-06, + "loss": 0.4199, + "step": 3113 + }, + { + "epoch": 0.4149786780383795, + "grad_norm": 0.30485001125242583, + "learning_rate": 9.644760903074965e-06, + "loss": 0.3384, + "step": 3114 + }, + { + "epoch": 0.41511194029850745, + "grad_norm": 0.3092084298630967, + "learning_rate": 9.644497264851364e-06, + "loss": 0.4571, + "step": 3115 + }, + { + "epoch": 0.4152452025586354, + "grad_norm": 0.33854679427787365, + "learning_rate": 9.644233532441392e-06, + "loss": 0.3944, + "step": 3116 + }, + { + "epoch": 0.41537846481876334, + "grad_norm": 0.30162999815652336, + "learning_rate": 9.643969705850397e-06, + "loss": 0.3833, + "step": 3117 + }, + { + "epoch": 0.4155117270788913, + "grad_norm": 0.3653548306142915, + "learning_rate": 9.643705785083728e-06, + "loss": 0.4329, + "step": 3118 + }, + { + "epoch": 0.41564498933901917, + "grad_norm": 0.3069055369803933, + "learning_rate": 9.643441770146737e-06, + "loss": 0.4345, + "step": 3119 + }, + { + "epoch": 0.4157782515991471, + "grad_norm": 0.32101070536354015, + "learning_rate": 9.643177661044781e-06, + "loss": 0.4371, + "step": 3120 + }, + { + "epoch": 0.41591151385927505, + "grad_norm": 0.3176339303367354, + "learning_rate": 9.642913457783215e-06, + "loss": 0.332, + "step": 3121 + }, + { + "epoch": 0.416044776119403, + "grad_norm": 0.29636231413593767, + "learning_rate": 9.642649160367391e-06, + "loss": 0.4488, + "step": 3122 + }, + { + "epoch": 0.41617803837953093, + "grad_norm": 0.32754868728294007, + "learning_rate": 9.642384768802677e-06, + "loss": 0.4359, + "step": 3123 + }, + { + "epoch": 0.4163113006396588, + "grad_norm": 0.31696560861339074, + "learning_rate": 9.64212028309443e-06, + "loss": 0.3669, + "step": 3124 + }, + { + "epoch": 0.41644456289978676, + "grad_norm": 0.3229990689104932, + "learning_rate": 9.641855703248014e-06, + "loss": 0.4123, + "step": 3125 + }, + { + "epoch": 0.4165778251599147, + "grad_norm": 0.29712298587566494, + "learning_rate": 9.641591029268795e-06, + "loss": 0.3493, + "step": 3126 + }, + { + "epoch": 0.41671108742004265, + "grad_norm": 0.311791724952957, + "learning_rate": 9.641326261162141e-06, + "loss": 0.3518, + "step": 3127 + }, + { + "epoch": 0.4168443496801706, + "grad_norm": 0.3153102435123241, + "learning_rate": 9.641061398933419e-06, + "loss": 0.4679, + "step": 3128 + }, + { + "epoch": 0.41697761194029853, + "grad_norm": 0.3098789588477304, + "learning_rate": 9.640796442588003e-06, + "loss": 0.5044, + "step": 3129 + }, + { + "epoch": 0.4171108742004264, + "grad_norm": 0.2992710655395572, + "learning_rate": 9.640531392131264e-06, + "loss": 0.4722, + "step": 3130 + }, + { + "epoch": 0.41724413646055436, + "grad_norm": 0.30296720967174956, + "learning_rate": 9.640266247568578e-06, + "loss": 0.4137, + "step": 3131 + }, + { + "epoch": 0.4173773987206823, + "grad_norm": 0.30238658167532134, + "learning_rate": 9.640001008905322e-06, + "loss": 0.4013, + "step": 3132 + }, + { + "epoch": 0.41751066098081024, + "grad_norm": 0.3409092900994564, + "learning_rate": 9.639735676146875e-06, + "loss": 0.4375, + "step": 3133 + }, + { + "epoch": 0.4176439232409382, + "grad_norm": 0.3129354441570362, + "learning_rate": 9.639470249298616e-06, + "loss": 0.4426, + "step": 3134 + }, + { + "epoch": 0.4177771855010661, + "grad_norm": 0.30866618483471703, + "learning_rate": 9.63920472836593e-06, + "loss": 0.4172, + "step": 3135 + }, + { + "epoch": 0.417910447761194, + "grad_norm": 0.3052655467956009, + "learning_rate": 9.6389391133542e-06, + "loss": 0.4158, + "step": 3136 + }, + { + "epoch": 0.41804371002132196, + "grad_norm": 0.32124663830349953, + "learning_rate": 9.638673404268813e-06, + "loss": 0.401, + "step": 3137 + }, + { + "epoch": 0.4181769722814499, + "grad_norm": 0.3031249109158004, + "learning_rate": 9.638407601115156e-06, + "loss": 0.3819, + "step": 3138 + }, + { + "epoch": 0.41831023454157784, + "grad_norm": 0.3030257018215924, + "learning_rate": 9.638141703898622e-06, + "loss": 0.3671, + "step": 3139 + }, + { + "epoch": 0.4184434968017058, + "grad_norm": 0.30640976632697375, + "learning_rate": 9.637875712624602e-06, + "loss": 0.4291, + "step": 3140 + }, + { + "epoch": 0.41857675906183367, + "grad_norm": 0.3040014230370388, + "learning_rate": 9.637609627298488e-06, + "loss": 0.3711, + "step": 3141 + }, + { + "epoch": 0.4187100213219616, + "grad_norm": 0.3094937730764659, + "learning_rate": 9.637343447925677e-06, + "loss": 0.3963, + "step": 3142 + }, + { + "epoch": 0.41884328358208955, + "grad_norm": 0.30685238023298034, + "learning_rate": 9.63707717451157e-06, + "loss": 0.425, + "step": 3143 + }, + { + "epoch": 0.4189765458422175, + "grad_norm": 0.3555374336134009, + "learning_rate": 9.636810807061562e-06, + "loss": 0.4022, + "step": 3144 + }, + { + "epoch": 0.41910980810234544, + "grad_norm": 0.3177523363943752, + "learning_rate": 9.63654434558106e-06, + "loss": 0.4185, + "step": 3145 + }, + { + "epoch": 0.4192430703624733, + "grad_norm": 0.31972128960394924, + "learning_rate": 9.636277790075464e-06, + "loss": 0.4184, + "step": 3146 + }, + { + "epoch": 0.41937633262260127, + "grad_norm": 0.31882313341368856, + "learning_rate": 9.636011140550178e-06, + "loss": 0.452, + "step": 3147 + }, + { + "epoch": 0.4195095948827292, + "grad_norm": 0.3614571621542522, + "learning_rate": 9.635744397010612e-06, + "loss": 0.4522, + "step": 3148 + }, + { + "epoch": 0.41964285714285715, + "grad_norm": 0.3228701406336915, + "learning_rate": 9.635477559462177e-06, + "loss": 0.4748, + "step": 3149 + }, + { + "epoch": 0.4197761194029851, + "grad_norm": 0.2869551851891917, + "learning_rate": 9.63521062791028e-06, + "loss": 0.364, + "step": 3150 + }, + { + "epoch": 0.419909381663113, + "grad_norm": 0.32185497580340866, + "learning_rate": 9.634943602360337e-06, + "loss": 0.3732, + "step": 3151 + }, + { + "epoch": 0.4200426439232409, + "grad_norm": 0.33062648781185644, + "learning_rate": 9.634676482817762e-06, + "loss": 0.4223, + "step": 3152 + }, + { + "epoch": 0.42017590618336886, + "grad_norm": 0.3067450970922184, + "learning_rate": 9.634409269287973e-06, + "loss": 0.4163, + "step": 3153 + }, + { + "epoch": 0.4203091684434968, + "grad_norm": 0.3065678570789806, + "learning_rate": 9.634141961776388e-06, + "loss": 0.4139, + "step": 3154 + }, + { + "epoch": 0.42044243070362475, + "grad_norm": 0.2922201116795896, + "learning_rate": 9.633874560288427e-06, + "loss": 0.3959, + "step": 3155 + }, + { + "epoch": 0.4205756929637527, + "grad_norm": 0.5921510060470417, + "learning_rate": 9.633607064829514e-06, + "loss": 0.4924, + "step": 3156 + }, + { + "epoch": 0.4207089552238806, + "grad_norm": 0.32116510902733847, + "learning_rate": 9.633339475405075e-06, + "loss": 0.4042, + "step": 3157 + }, + { + "epoch": 0.4208422174840085, + "grad_norm": 0.3128403152857649, + "learning_rate": 9.633071792020532e-06, + "loss": 0.4928, + "step": 3158 + }, + { + "epoch": 0.42097547974413646, + "grad_norm": 0.32385061660974396, + "learning_rate": 9.632804014681317e-06, + "loss": 0.4102, + "step": 3159 + }, + { + "epoch": 0.4211087420042644, + "grad_norm": 0.31262760189990335, + "learning_rate": 9.632536143392859e-06, + "loss": 0.4671, + "step": 3160 + }, + { + "epoch": 0.42124200426439234, + "grad_norm": 0.31644307222360946, + "learning_rate": 9.63226817816059e-06, + "loss": 0.4393, + "step": 3161 + }, + { + "epoch": 0.42137526652452023, + "grad_norm": 0.30230138044236327, + "learning_rate": 9.632000118989945e-06, + "loss": 0.3747, + "step": 3162 + }, + { + "epoch": 0.4215085287846482, + "grad_norm": 0.29973277426757133, + "learning_rate": 9.631731965886362e-06, + "loss": 0.4657, + "step": 3163 + }, + { + "epoch": 0.4216417910447761, + "grad_norm": 0.3057327815365407, + "learning_rate": 9.631463718855274e-06, + "loss": 0.4093, + "step": 3164 + }, + { + "epoch": 0.42177505330490406, + "grad_norm": 0.3107803259978553, + "learning_rate": 9.631195377902125e-06, + "loss": 0.409, + "step": 3165 + }, + { + "epoch": 0.421908315565032, + "grad_norm": 0.2910994496402051, + "learning_rate": 9.630926943032352e-06, + "loss": 0.3884, + "step": 3166 + }, + { + "epoch": 0.42204157782515994, + "grad_norm": 0.28575380213346924, + "learning_rate": 9.630658414251405e-06, + "loss": 0.4609, + "step": 3167 + }, + { + "epoch": 0.42217484008528783, + "grad_norm": 0.32082355691558306, + "learning_rate": 9.630389791564725e-06, + "loss": 0.4448, + "step": 3168 + }, + { + "epoch": 0.42230810234541577, + "grad_norm": 0.30687222467043057, + "learning_rate": 9.630121074977761e-06, + "loss": 0.3705, + "step": 3169 + }, + { + "epoch": 0.4224413646055437, + "grad_norm": 0.3063604026994756, + "learning_rate": 9.629852264495961e-06, + "loss": 0.4301, + "step": 3170 + }, + { + "epoch": 0.42257462686567165, + "grad_norm": 0.33026756061390605, + "learning_rate": 9.629583360124777e-06, + "loss": 0.4648, + "step": 3171 + }, + { + "epoch": 0.4227078891257996, + "grad_norm": 0.31882468691386817, + "learning_rate": 9.629314361869664e-06, + "loss": 0.3873, + "step": 3172 + }, + { + "epoch": 0.4228411513859275, + "grad_norm": 0.30966319958345767, + "learning_rate": 9.629045269736075e-06, + "loss": 0.4756, + "step": 3173 + }, + { + "epoch": 0.4229744136460554, + "grad_norm": 0.34404100727838277, + "learning_rate": 9.628776083729467e-06, + "loss": 0.452, + "step": 3174 + }, + { + "epoch": 0.42310767590618337, + "grad_norm": 0.3348706048375773, + "learning_rate": 9.628506803855298e-06, + "loss": 0.415, + "step": 3175 + }, + { + "epoch": 0.4232409381663113, + "grad_norm": 0.3600550112679073, + "learning_rate": 9.628237430119031e-06, + "loss": 0.4783, + "step": 3176 + }, + { + "epoch": 0.42337420042643925, + "grad_norm": 0.35398942920610915, + "learning_rate": 9.62796796252613e-06, + "loss": 0.5545, + "step": 3177 + }, + { + "epoch": 0.42350746268656714, + "grad_norm": 0.3285488427391353, + "learning_rate": 9.627698401082054e-06, + "loss": 0.406, + "step": 3178 + }, + { + "epoch": 0.4236407249466951, + "grad_norm": 0.3322641879895249, + "learning_rate": 9.627428745792273e-06, + "loss": 0.416, + "step": 3179 + }, + { + "epoch": 0.423773987206823, + "grad_norm": 0.3359085676531739, + "learning_rate": 9.627158996662258e-06, + "loss": 0.4101, + "step": 3180 + }, + { + "epoch": 0.42390724946695096, + "grad_norm": 0.3127696583081647, + "learning_rate": 9.626889153697473e-06, + "loss": 0.3802, + "step": 3181 + }, + { + "epoch": 0.4240405117270789, + "grad_norm": 0.30337575943258255, + "learning_rate": 9.626619216903395e-06, + "loss": 0.3773, + "step": 3182 + }, + { + "epoch": 0.42417377398720685, + "grad_norm": 0.31646921136366796, + "learning_rate": 9.626349186285497e-06, + "loss": 0.4486, + "step": 3183 + }, + { + "epoch": 0.42430703624733473, + "grad_norm": 0.3177649231399271, + "learning_rate": 9.626079061849253e-06, + "loss": 0.4601, + "step": 3184 + }, + { + "epoch": 0.4244402985074627, + "grad_norm": 0.30266148169336515, + "learning_rate": 9.625808843600143e-06, + "loss": 0.3446, + "step": 3185 + }, + { + "epoch": 0.4245735607675906, + "grad_norm": 0.3410073086044827, + "learning_rate": 9.62553853154365e-06, + "loss": 0.4338, + "step": 3186 + }, + { + "epoch": 0.42470682302771856, + "grad_norm": 0.2912557226851546, + "learning_rate": 9.625268125685247e-06, + "loss": 0.3987, + "step": 3187 + }, + { + "epoch": 0.4248400852878465, + "grad_norm": 0.2962991122379683, + "learning_rate": 9.624997626030425e-06, + "loss": 0.4049, + "step": 3188 + }, + { + "epoch": 0.4249733475479744, + "grad_norm": 0.31118004757460976, + "learning_rate": 9.624727032584666e-06, + "loss": 0.3726, + "step": 3189 + }, + { + "epoch": 0.42510660980810233, + "grad_norm": 0.3295903046063104, + "learning_rate": 9.62445634535346e-06, + "loss": 0.4442, + "step": 3190 + }, + { + "epoch": 0.4252398720682303, + "grad_norm": 0.29778097814689847, + "learning_rate": 9.624185564342295e-06, + "loss": 0.3645, + "step": 3191 + }, + { + "epoch": 0.4253731343283582, + "grad_norm": 0.30738956898436454, + "learning_rate": 9.62391468955666e-06, + "loss": 0.3968, + "step": 3192 + }, + { + "epoch": 0.42550639658848616, + "grad_norm": 0.3049503478158165, + "learning_rate": 9.623643721002053e-06, + "loss": 0.4583, + "step": 3193 + }, + { + "epoch": 0.4256396588486141, + "grad_norm": 0.3182263769071979, + "learning_rate": 9.623372658683962e-06, + "loss": 0.345, + "step": 3194 + }, + { + "epoch": 0.425772921108742, + "grad_norm": 0.33304434705120356, + "learning_rate": 9.62310150260789e-06, + "loss": 0.3809, + "step": 3195 + }, + { + "epoch": 0.42590618336886993, + "grad_norm": 0.2932955036703427, + "learning_rate": 9.622830252779335e-06, + "loss": 0.4234, + "step": 3196 + }, + { + "epoch": 0.42603944562899787, + "grad_norm": 0.31449988753152425, + "learning_rate": 9.622558909203795e-06, + "loss": 0.4042, + "step": 3197 + }, + { + "epoch": 0.4261727078891258, + "grad_norm": 0.30757416121253645, + "learning_rate": 9.622287471886775e-06, + "loss": 0.3898, + "step": 3198 + }, + { + "epoch": 0.42630597014925375, + "grad_norm": 0.3034553530424194, + "learning_rate": 9.622015940833777e-06, + "loss": 0.3858, + "step": 3199 + }, + { + "epoch": 0.42643923240938164, + "grad_norm": 0.31155588927217365, + "learning_rate": 9.621744316050312e-06, + "loss": 0.4224, + "step": 3200 + }, + { + "epoch": 0.4265724946695096, + "grad_norm": 0.31808585882456186, + "learning_rate": 9.621472597541884e-06, + "loss": 0.4483, + "step": 3201 + }, + { + "epoch": 0.4267057569296375, + "grad_norm": 0.2907115845115845, + "learning_rate": 9.621200785314004e-06, + "loss": 0.3418, + "step": 3202 + }, + { + "epoch": 0.42683901918976547, + "grad_norm": 0.3107983354153807, + "learning_rate": 9.620928879372185e-06, + "loss": 0.4767, + "step": 3203 + }, + { + "epoch": 0.4269722814498934, + "grad_norm": 0.3012142011351843, + "learning_rate": 9.620656879721941e-06, + "loss": 0.4442, + "step": 3204 + }, + { + "epoch": 0.4271055437100213, + "grad_norm": 0.31030982453507366, + "learning_rate": 9.620384786368788e-06, + "loss": 0.425, + "step": 3205 + }, + { + "epoch": 0.42723880597014924, + "grad_norm": 0.30895951875900685, + "learning_rate": 9.620112599318244e-06, + "loss": 0.411, + "step": 3206 + }, + { + "epoch": 0.4273720682302772, + "grad_norm": 0.29760002102890065, + "learning_rate": 9.619840318575825e-06, + "loss": 0.4033, + "step": 3207 + }, + { + "epoch": 0.4275053304904051, + "grad_norm": 0.32705327289939645, + "learning_rate": 9.619567944147058e-06, + "loss": 0.418, + "step": 3208 + }, + { + "epoch": 0.42763859275053306, + "grad_norm": 0.3252433553737172, + "learning_rate": 9.619295476037466e-06, + "loss": 0.3783, + "step": 3209 + }, + { + "epoch": 0.427771855010661, + "grad_norm": 0.298713311157755, + "learning_rate": 9.619022914252571e-06, + "loss": 0.4171, + "step": 3210 + }, + { + "epoch": 0.4279051172707889, + "grad_norm": 0.30649261862965577, + "learning_rate": 9.618750258797902e-06, + "loss": 0.4041, + "step": 3211 + }, + { + "epoch": 0.42803837953091683, + "grad_norm": 0.2949042708434229, + "learning_rate": 9.61847750967899e-06, + "loss": 0.4344, + "step": 3212 + }, + { + "epoch": 0.4281716417910448, + "grad_norm": 0.33250288031417174, + "learning_rate": 9.61820466690136e-06, + "loss": 0.4537, + "step": 3213 + }, + { + "epoch": 0.4283049040511727, + "grad_norm": 0.3061851131146276, + "learning_rate": 9.617931730470553e-06, + "loss": 0.4352, + "step": 3214 + }, + { + "epoch": 0.42843816631130066, + "grad_norm": 0.3138691545569912, + "learning_rate": 9.6176587003921e-06, + "loss": 0.528, + "step": 3215 + }, + { + "epoch": 0.42857142857142855, + "grad_norm": 0.3020859072292144, + "learning_rate": 9.617385576671538e-06, + "loss": 0.3588, + "step": 3216 + }, + { + "epoch": 0.4287046908315565, + "grad_norm": 0.3051319191367697, + "learning_rate": 9.617112359314406e-06, + "loss": 0.4771, + "step": 3217 + }, + { + "epoch": 0.42883795309168443, + "grad_norm": 0.2971124519363711, + "learning_rate": 9.616839048326243e-06, + "loss": 0.414, + "step": 3218 + }, + { + "epoch": 0.4289712153518124, + "grad_norm": 0.3164240809685875, + "learning_rate": 9.616565643712595e-06, + "loss": 0.4151, + "step": 3219 + }, + { + "epoch": 0.4291044776119403, + "grad_norm": 0.3189235477351881, + "learning_rate": 9.616292145479003e-06, + "loss": 0.4439, + "step": 3220 + }, + { + "epoch": 0.42923773987206826, + "grad_norm": 0.30941431331169367, + "learning_rate": 9.616018553631014e-06, + "loss": 0.3853, + "step": 3221 + }, + { + "epoch": 0.42937100213219614, + "grad_norm": 0.3115109322092907, + "learning_rate": 9.615744868174179e-06, + "loss": 0.411, + "step": 3222 + }, + { + "epoch": 0.4295042643923241, + "grad_norm": 0.32573726982359047, + "learning_rate": 9.615471089114045e-06, + "loss": 0.4364, + "step": 3223 + }, + { + "epoch": 0.42963752665245203, + "grad_norm": 0.3418104882080978, + "learning_rate": 9.615197216456165e-06, + "loss": 0.6107, + "step": 3224 + }, + { + "epoch": 0.42977078891257997, + "grad_norm": 0.31474478985395643, + "learning_rate": 9.614923250206092e-06, + "loss": 0.4204, + "step": 3225 + }, + { + "epoch": 0.4299040511727079, + "grad_norm": 0.3428341452302718, + "learning_rate": 9.614649190369384e-06, + "loss": 0.422, + "step": 3226 + }, + { + "epoch": 0.4300373134328358, + "grad_norm": 0.3016257419048095, + "learning_rate": 9.614375036951596e-06, + "loss": 0.5096, + "step": 3227 + }, + { + "epoch": 0.43017057569296374, + "grad_norm": 0.3274276581133474, + "learning_rate": 9.61410078995829e-06, + "loss": 0.4461, + "step": 3228 + }, + { + "epoch": 0.4303038379530917, + "grad_norm": 0.311595605573115, + "learning_rate": 9.613826449395028e-06, + "loss": 0.3888, + "step": 3229 + }, + { + "epoch": 0.4304371002132196, + "grad_norm": 0.32670055148093796, + "learning_rate": 9.613552015267368e-06, + "loss": 0.3253, + "step": 3230 + }, + { + "epoch": 0.43057036247334757, + "grad_norm": 0.31404816240837946, + "learning_rate": 9.613277487580883e-06, + "loss": 0.5756, + "step": 3231 + }, + { + "epoch": 0.43070362473347545, + "grad_norm": 0.32430632061067055, + "learning_rate": 9.613002866341134e-06, + "loss": 0.3664, + "step": 3232 + }, + { + "epoch": 0.4308368869936034, + "grad_norm": 0.2992150883706025, + "learning_rate": 9.612728151553693e-06, + "loss": 0.4054, + "step": 3233 + }, + { + "epoch": 0.43097014925373134, + "grad_norm": 0.2916647298368342, + "learning_rate": 9.612453343224131e-06, + "loss": 0.3588, + "step": 3234 + }, + { + "epoch": 0.4311034115138593, + "grad_norm": 0.31431327066091364, + "learning_rate": 9.612178441358019e-06, + "loss": 0.4314, + "step": 3235 + }, + { + "epoch": 0.4312366737739872, + "grad_norm": 0.29626794693053815, + "learning_rate": 9.611903445960933e-06, + "loss": 0.3284, + "step": 3236 + }, + { + "epoch": 0.43136993603411516, + "grad_norm": 0.31247580189580176, + "learning_rate": 9.611628357038451e-06, + "loss": 0.4108, + "step": 3237 + }, + { + "epoch": 0.43150319829424305, + "grad_norm": 0.3142256621750742, + "learning_rate": 9.61135317459615e-06, + "loss": 0.4243, + "step": 3238 + }, + { + "epoch": 0.431636460554371, + "grad_norm": 0.3090326495847045, + "learning_rate": 9.61107789863961e-06, + "loss": 0.4148, + "step": 3239 + }, + { + "epoch": 0.43176972281449894, + "grad_norm": 0.3208662918452176, + "learning_rate": 9.610802529174415e-06, + "loss": 0.3995, + "step": 3240 + }, + { + "epoch": 0.4319029850746269, + "grad_norm": 0.31229960523785183, + "learning_rate": 9.610527066206146e-06, + "loss": 0.4748, + "step": 3241 + }, + { + "epoch": 0.4320362473347548, + "grad_norm": 0.31950699811617134, + "learning_rate": 9.610251509740393e-06, + "loss": 0.4663, + "step": 3242 + }, + { + "epoch": 0.4321695095948827, + "grad_norm": 0.31300208077731956, + "learning_rate": 9.609975859782742e-06, + "loss": 0.4596, + "step": 3243 + }, + { + "epoch": 0.43230277185501065, + "grad_norm": 0.29186677591698557, + "learning_rate": 9.609700116338787e-06, + "loss": 0.422, + "step": 3244 + }, + { + "epoch": 0.4324360341151386, + "grad_norm": 0.3027632101919025, + "learning_rate": 9.609424279414113e-06, + "loss": 0.3984, + "step": 3245 + }, + { + "epoch": 0.43256929637526653, + "grad_norm": 0.3067320165271092, + "learning_rate": 9.609148349014317e-06, + "loss": 0.4262, + "step": 3246 + }, + { + "epoch": 0.4327025586353945, + "grad_norm": 0.3085917216239767, + "learning_rate": 9.608872325144995e-06, + "loss": 0.4165, + "step": 3247 + }, + { + "epoch": 0.43283582089552236, + "grad_norm": 0.3334852657720315, + "learning_rate": 9.608596207811745e-06, + "loss": 0.3891, + "step": 3248 + }, + { + "epoch": 0.4329690831556503, + "grad_norm": 0.2956698379226907, + "learning_rate": 9.608319997020164e-06, + "loss": 0.4272, + "step": 3249 + }, + { + "epoch": 0.43310234541577824, + "grad_norm": 0.3124406501274155, + "learning_rate": 9.608043692775857e-06, + "loss": 0.4312, + "step": 3250 + }, + { + "epoch": 0.4332356076759062, + "grad_norm": 0.32104064949732836, + "learning_rate": 9.607767295084423e-06, + "loss": 0.5411, + "step": 3251 + }, + { + "epoch": 0.43336886993603413, + "grad_norm": 0.3190649854944662, + "learning_rate": 9.607490803951471e-06, + "loss": 0.4571, + "step": 3252 + }, + { + "epoch": 0.43350213219616207, + "grad_norm": 0.31499375144955255, + "learning_rate": 9.607214219382606e-06, + "loss": 0.4031, + "step": 3253 + }, + { + "epoch": 0.43363539445628996, + "grad_norm": 0.3032027197301449, + "learning_rate": 9.606937541383437e-06, + "loss": 0.3983, + "step": 3254 + }, + { + "epoch": 0.4337686567164179, + "grad_norm": 0.2979056421063339, + "learning_rate": 9.606660769959574e-06, + "loss": 0.4446, + "step": 3255 + }, + { + "epoch": 0.43390191897654584, + "grad_norm": 0.3114452873699311, + "learning_rate": 9.606383905116631e-06, + "loss": 0.377, + "step": 3256 + }, + { + "epoch": 0.4340351812366738, + "grad_norm": 0.3028146934122497, + "learning_rate": 9.606106946860223e-06, + "loss": 0.3879, + "step": 3257 + }, + { + "epoch": 0.4341684434968017, + "grad_norm": 1.3018973191402023, + "learning_rate": 9.605829895195964e-06, + "loss": 0.4545, + "step": 3258 + }, + { + "epoch": 0.4343017057569296, + "grad_norm": 0.30502063992425227, + "learning_rate": 9.605552750129475e-06, + "loss": 0.3641, + "step": 3259 + }, + { + "epoch": 0.43443496801705755, + "grad_norm": 0.34245932046127364, + "learning_rate": 9.605275511666377e-06, + "loss": 0.4692, + "step": 3260 + }, + { + "epoch": 0.4345682302771855, + "grad_norm": 0.3006496317257969, + "learning_rate": 9.604998179812287e-06, + "loss": 0.3827, + "step": 3261 + }, + { + "epoch": 0.43470149253731344, + "grad_norm": 0.32324379466246217, + "learning_rate": 9.604720754572836e-06, + "loss": 0.46, + "step": 3262 + }, + { + "epoch": 0.4348347547974414, + "grad_norm": 0.3573316047866089, + "learning_rate": 9.604443235953645e-06, + "loss": 0.412, + "step": 3263 + }, + { + "epoch": 0.4349680170575693, + "grad_norm": 0.30131488949204344, + "learning_rate": 9.604165623960342e-06, + "loss": 0.4004, + "step": 3264 + }, + { + "epoch": 0.4351012793176972, + "grad_norm": 0.37360273056614707, + "learning_rate": 9.603887918598558e-06, + "loss": 0.3679, + "step": 3265 + }, + { + "epoch": 0.43523454157782515, + "grad_norm": 0.3207359902786208, + "learning_rate": 9.603610119873927e-06, + "loss": 0.369, + "step": 3266 + }, + { + "epoch": 0.4353678038379531, + "grad_norm": 0.30747414188613925, + "learning_rate": 9.60333222779208e-06, + "loss": 0.4019, + "step": 3267 + }, + { + "epoch": 0.43550106609808104, + "grad_norm": 0.3065229482530607, + "learning_rate": 9.60305424235865e-06, + "loss": 0.4107, + "step": 3268 + }, + { + "epoch": 0.435634328358209, + "grad_norm": 0.3296684837061897, + "learning_rate": 9.602776163579279e-06, + "loss": 0.3986, + "step": 3269 + }, + { + "epoch": 0.43576759061833686, + "grad_norm": 0.29681545194786174, + "learning_rate": 9.602497991459603e-06, + "loss": 0.3832, + "step": 3270 + }, + { + "epoch": 0.4359008528784648, + "grad_norm": 0.34003365184699236, + "learning_rate": 9.602219726005264e-06, + "loss": 0.4333, + "step": 3271 + }, + { + "epoch": 0.43603411513859275, + "grad_norm": 0.3135364664575141, + "learning_rate": 9.601941367221906e-06, + "loss": 0.4525, + "step": 3272 + }, + { + "epoch": 0.4361673773987207, + "grad_norm": 0.3008683087642803, + "learning_rate": 9.601662915115173e-06, + "loss": 0.3791, + "step": 3273 + }, + { + "epoch": 0.43630063965884863, + "grad_norm": 0.3208741676422345, + "learning_rate": 9.60138436969071e-06, + "loss": 0.552, + "step": 3274 + }, + { + "epoch": 0.4364339019189765, + "grad_norm": 0.31076533240912274, + "learning_rate": 9.60110573095417e-06, + "loss": 0.3615, + "step": 3275 + }, + { + "epoch": 0.43656716417910446, + "grad_norm": 0.28783446734462437, + "learning_rate": 9.600826998911199e-06, + "loss": 0.4163, + "step": 3276 + }, + { + "epoch": 0.4367004264392324, + "grad_norm": 0.30669350946977686, + "learning_rate": 9.600548173567453e-06, + "loss": 0.3759, + "step": 3277 + }, + { + "epoch": 0.43683368869936035, + "grad_norm": 0.3203559692307345, + "learning_rate": 9.600269254928583e-06, + "loss": 0.4243, + "step": 3278 + }, + { + "epoch": 0.4369669509594883, + "grad_norm": 0.3133275161678737, + "learning_rate": 9.599990243000248e-06, + "loss": 0.4224, + "step": 3279 + }, + { + "epoch": 0.43710021321961623, + "grad_norm": 0.30010832548256267, + "learning_rate": 9.599711137788106e-06, + "loss": 0.3535, + "step": 3280 + }, + { + "epoch": 0.4372334754797441, + "grad_norm": 0.300635379677257, + "learning_rate": 9.599431939297815e-06, + "loss": 0.4283, + "step": 3281 + }, + { + "epoch": 0.43736673773987206, + "grad_norm": 0.301375266127825, + "learning_rate": 9.599152647535038e-06, + "loss": 0.4608, + "step": 3282 + }, + { + "epoch": 0.4375, + "grad_norm": 0.2877805888743608, + "learning_rate": 9.598873262505438e-06, + "loss": 0.4265, + "step": 3283 + }, + { + "epoch": 0.43763326226012794, + "grad_norm": 0.302312998668618, + "learning_rate": 9.598593784214682e-06, + "loss": 0.3676, + "step": 3284 + }, + { + "epoch": 0.4377665245202559, + "grad_norm": 0.29790014106717083, + "learning_rate": 9.598314212668437e-06, + "loss": 0.3457, + "step": 3285 + }, + { + "epoch": 0.43789978678038377, + "grad_norm": 0.3018640072996557, + "learning_rate": 9.598034547872374e-06, + "loss": 0.3948, + "step": 3286 + }, + { + "epoch": 0.4380330490405117, + "grad_norm": 0.3154875415019355, + "learning_rate": 9.597754789832162e-06, + "loss": 0.4028, + "step": 3287 + }, + { + "epoch": 0.43816631130063965, + "grad_norm": 0.30875311091005425, + "learning_rate": 9.597474938553475e-06, + "loss": 0.4184, + "step": 3288 + }, + { + "epoch": 0.4382995735607676, + "grad_norm": 0.6283952263185653, + "learning_rate": 9.597194994041989e-06, + "loss": 0.5006, + "step": 3289 + }, + { + "epoch": 0.43843283582089554, + "grad_norm": 0.29959677424306125, + "learning_rate": 9.59691495630338e-06, + "loss": 0.3578, + "step": 3290 + }, + { + "epoch": 0.4385660980810235, + "grad_norm": 0.33187604685365835, + "learning_rate": 9.596634825343327e-06, + "loss": 0.4067, + "step": 3291 + }, + { + "epoch": 0.43869936034115137, + "grad_norm": 0.32520694215431806, + "learning_rate": 9.59635460116751e-06, + "loss": 0.4103, + "step": 3292 + }, + { + "epoch": 0.4388326226012793, + "grad_norm": 0.3086167259993393, + "learning_rate": 9.596074283781614e-06, + "loss": 0.4291, + "step": 3293 + }, + { + "epoch": 0.43896588486140725, + "grad_norm": 0.34235886623161316, + "learning_rate": 9.595793873191323e-06, + "loss": 0.4701, + "step": 3294 + }, + { + "epoch": 0.4390991471215352, + "grad_norm": 0.30462690417062166, + "learning_rate": 9.595513369402322e-06, + "loss": 0.4795, + "step": 3295 + }, + { + "epoch": 0.43923240938166314, + "grad_norm": 0.312853746092711, + "learning_rate": 9.5952327724203e-06, + "loss": 0.4134, + "step": 3296 + }, + { + "epoch": 0.439365671641791, + "grad_norm": 0.338362392313541, + "learning_rate": 9.594952082250947e-06, + "loss": 0.4067, + "step": 3297 + }, + { + "epoch": 0.43949893390191896, + "grad_norm": 0.29288199954832134, + "learning_rate": 9.594671298899959e-06, + "loss": 0.3534, + "step": 3298 + }, + { + "epoch": 0.4396321961620469, + "grad_norm": 0.29983539336644416, + "learning_rate": 9.594390422373022e-06, + "loss": 0.3416, + "step": 3299 + }, + { + "epoch": 0.43976545842217485, + "grad_norm": 0.31552792572393035, + "learning_rate": 9.59410945267584e-06, + "loss": 0.4524, + "step": 3300 + }, + { + "epoch": 0.4398987206823028, + "grad_norm": 0.29836681962157396, + "learning_rate": 9.593828389814104e-06, + "loss": 0.4837, + "step": 3301 + }, + { + "epoch": 0.4400319829424307, + "grad_norm": 0.43558056630461806, + "learning_rate": 9.59354723379352e-06, + "loss": 0.4353, + "step": 3302 + }, + { + "epoch": 0.4401652452025586, + "grad_norm": 0.3082096692582151, + "learning_rate": 9.593265984619786e-06, + "loss": 0.4485, + "step": 3303 + }, + { + "epoch": 0.44029850746268656, + "grad_norm": 0.3080871908784335, + "learning_rate": 9.592984642298607e-06, + "loss": 0.3848, + "step": 3304 + }, + { + "epoch": 0.4404317697228145, + "grad_norm": 0.4034632267231707, + "learning_rate": 9.592703206835687e-06, + "loss": 0.3816, + "step": 3305 + }, + { + "epoch": 0.44056503198294245, + "grad_norm": 0.2953698807472642, + "learning_rate": 9.592421678236734e-06, + "loss": 0.4756, + "step": 3306 + }, + { + "epoch": 0.4406982942430704, + "grad_norm": 0.3223220361763655, + "learning_rate": 9.592140056507455e-06, + "loss": 0.4107, + "step": 3307 + }, + { + "epoch": 0.4408315565031983, + "grad_norm": 0.3073828057846316, + "learning_rate": 9.591858341653566e-06, + "loss": 0.4842, + "step": 3308 + }, + { + "epoch": 0.4409648187633262, + "grad_norm": 0.2991971677351295, + "learning_rate": 9.591576533680775e-06, + "loss": 0.4495, + "step": 3309 + }, + { + "epoch": 0.44109808102345416, + "grad_norm": 0.3365100420974153, + "learning_rate": 9.5912946325948e-06, + "loss": 0.6005, + "step": 3310 + }, + { + "epoch": 0.4412313432835821, + "grad_norm": 0.30464379112484496, + "learning_rate": 9.591012638401356e-06, + "loss": 0.3607, + "step": 3311 + }, + { + "epoch": 0.44136460554371004, + "grad_norm": 0.37135979757764476, + "learning_rate": 9.590730551106163e-06, + "loss": 0.3905, + "step": 3312 + }, + { + "epoch": 0.44149786780383793, + "grad_norm": 0.31026635102840583, + "learning_rate": 9.590448370714939e-06, + "loss": 0.3759, + "step": 3313 + }, + { + "epoch": 0.44163113006396587, + "grad_norm": 0.3226050567792663, + "learning_rate": 9.59016609723341e-06, + "loss": 0.4416, + "step": 3314 + }, + { + "epoch": 0.4417643923240938, + "grad_norm": 0.3069790519036847, + "learning_rate": 9.589883730667295e-06, + "loss": 0.4461, + "step": 3315 + }, + { + "epoch": 0.44189765458422176, + "grad_norm": 0.28333957255441306, + "learning_rate": 9.589601271022327e-06, + "loss": 0.3758, + "step": 3316 + }, + { + "epoch": 0.4420309168443497, + "grad_norm": 0.3027464678591748, + "learning_rate": 9.589318718304228e-06, + "loss": 0.4771, + "step": 3317 + }, + { + "epoch": 0.44216417910447764, + "grad_norm": 0.3271260680014228, + "learning_rate": 9.589036072518732e-06, + "loss": 0.44, + "step": 3318 + }, + { + "epoch": 0.4422974413646055, + "grad_norm": 0.32502517893454563, + "learning_rate": 9.588753333671567e-06, + "loss": 0.5214, + "step": 3319 + }, + { + "epoch": 0.44243070362473347, + "grad_norm": 0.30221592297436284, + "learning_rate": 9.588470501768472e-06, + "loss": 0.6004, + "step": 3320 + }, + { + "epoch": 0.4425639658848614, + "grad_norm": 0.31035844349185177, + "learning_rate": 9.588187576815178e-06, + "loss": 0.4638, + "step": 3321 + }, + { + "epoch": 0.44269722814498935, + "grad_norm": 0.31178996423255917, + "learning_rate": 9.587904558817423e-06, + "loss": 0.4412, + "step": 3322 + }, + { + "epoch": 0.4428304904051173, + "grad_norm": 0.32735634656092577, + "learning_rate": 9.587621447780947e-06, + "loss": 0.4466, + "step": 3323 + }, + { + "epoch": 0.4429637526652452, + "grad_norm": 0.3407781403509041, + "learning_rate": 9.587338243711492e-06, + "loss": 0.4701, + "step": 3324 + }, + { + "epoch": 0.4430970149253731, + "grad_norm": 0.3303104116575553, + "learning_rate": 9.587054946614802e-06, + "loss": 0.505, + "step": 3325 + }, + { + "epoch": 0.44323027718550106, + "grad_norm": 0.3414588117631741, + "learning_rate": 9.58677155649662e-06, + "loss": 0.4282, + "step": 3326 + }, + { + "epoch": 0.443363539445629, + "grad_norm": 0.3333051673817665, + "learning_rate": 9.586488073362693e-06, + "loss": 0.4078, + "step": 3327 + }, + { + "epoch": 0.44349680170575695, + "grad_norm": 0.31080805218992097, + "learning_rate": 9.586204497218771e-06, + "loss": 0.3759, + "step": 3328 + }, + { + "epoch": 0.44363006396588484, + "grad_norm": 0.3347283485963559, + "learning_rate": 9.585920828070606e-06, + "loss": 0.3723, + "step": 3329 + }, + { + "epoch": 0.4437633262260128, + "grad_norm": 0.3151203320808902, + "learning_rate": 9.585637065923946e-06, + "loss": 0.3943, + "step": 3330 + }, + { + "epoch": 0.4438965884861407, + "grad_norm": 0.340470648259725, + "learning_rate": 9.585353210784547e-06, + "loss": 0.3999, + "step": 3331 + }, + { + "epoch": 0.44402985074626866, + "grad_norm": 0.29452134457365364, + "learning_rate": 9.585069262658169e-06, + "loss": 0.4539, + "step": 3332 + }, + { + "epoch": 0.4441631130063966, + "grad_norm": 0.3064907503538289, + "learning_rate": 9.584785221550565e-06, + "loss": 0.3719, + "step": 3333 + }, + { + "epoch": 0.44429637526652455, + "grad_norm": 0.30040687898362906, + "learning_rate": 9.584501087467501e-06, + "loss": 0.3794, + "step": 3334 + }, + { + "epoch": 0.44442963752665243, + "grad_norm": 0.3205006524273865, + "learning_rate": 9.584216860414734e-06, + "loss": 0.3653, + "step": 3335 + }, + { + "epoch": 0.4445628997867804, + "grad_norm": 0.34907384902608724, + "learning_rate": 9.583932540398029e-06, + "loss": 0.3856, + "step": 3336 + }, + { + "epoch": 0.4446961620469083, + "grad_norm": 0.30143077315950817, + "learning_rate": 9.583648127423153e-06, + "loss": 0.3618, + "step": 3337 + }, + { + "epoch": 0.44482942430703626, + "grad_norm": 0.3191765228422461, + "learning_rate": 9.583363621495874e-06, + "loss": 0.3953, + "step": 3338 + }, + { + "epoch": 0.4449626865671642, + "grad_norm": 0.3356792543256465, + "learning_rate": 9.583079022621959e-06, + "loss": 0.3987, + "step": 3339 + }, + { + "epoch": 0.4450959488272921, + "grad_norm": 0.30137731242471233, + "learning_rate": 9.582794330807182e-06, + "loss": 0.3413, + "step": 3340 + }, + { + "epoch": 0.44522921108742003, + "grad_norm": 0.3445085194586502, + "learning_rate": 9.582509546057314e-06, + "loss": 0.4551, + "step": 3341 + }, + { + "epoch": 0.44536247334754797, + "grad_norm": 0.32648097668965864, + "learning_rate": 9.582224668378132e-06, + "loss": 0.4433, + "step": 3342 + }, + { + "epoch": 0.4454957356076759, + "grad_norm": 0.334971198796897, + "learning_rate": 9.581939697775414e-06, + "loss": 0.4498, + "step": 3343 + }, + { + "epoch": 0.44562899786780386, + "grad_norm": 0.3593139607006059, + "learning_rate": 9.581654634254936e-06, + "loss": 0.4834, + "step": 3344 + }, + { + "epoch": 0.44576226012793174, + "grad_norm": 0.3019534161599678, + "learning_rate": 9.581369477822481e-06, + "loss": 0.4574, + "step": 3345 + }, + { + "epoch": 0.4458955223880597, + "grad_norm": 0.29844586700340775, + "learning_rate": 9.58108422848383e-06, + "loss": 0.3972, + "step": 3346 + }, + { + "epoch": 0.4460287846481876, + "grad_norm": 0.33932047413685634, + "learning_rate": 9.580798886244772e-06, + "loss": 0.3509, + "step": 3347 + }, + { + "epoch": 0.44616204690831557, + "grad_norm": 0.31136632920294227, + "learning_rate": 9.580513451111086e-06, + "loss": 0.433, + "step": 3348 + }, + { + "epoch": 0.4462953091684435, + "grad_norm": 0.3224344630535366, + "learning_rate": 9.580227923088565e-06, + "loss": 0.3554, + "step": 3349 + }, + { + "epoch": 0.44642857142857145, + "grad_norm": 0.3079682672391091, + "learning_rate": 9.579942302183001e-06, + "loss": 0.4268, + "step": 3350 + }, + { + "epoch": 0.44656183368869934, + "grad_norm": 0.3065874311079467, + "learning_rate": 9.579656588400184e-06, + "loss": 0.3508, + "step": 3351 + }, + { + "epoch": 0.4466950959488273, + "grad_norm": 0.28675953195174536, + "learning_rate": 9.579370781745906e-06, + "loss": 0.3524, + "step": 3352 + }, + { + "epoch": 0.4468283582089552, + "grad_norm": 0.3071491226548561, + "learning_rate": 9.579084882225966e-06, + "loss": 0.4945, + "step": 3353 + }, + { + "epoch": 0.44696162046908317, + "grad_norm": 0.3059886689739266, + "learning_rate": 9.57879888984616e-06, + "loss": 0.4288, + "step": 3354 + }, + { + "epoch": 0.4470948827292111, + "grad_norm": 0.2865038182797471, + "learning_rate": 9.578512804612288e-06, + "loss": 0.3393, + "step": 3355 + }, + { + "epoch": 0.447228144989339, + "grad_norm": 0.3055219950985256, + "learning_rate": 9.578226626530154e-06, + "loss": 0.4201, + "step": 3356 + }, + { + "epoch": 0.44736140724946694, + "grad_norm": 0.31266018496527404, + "learning_rate": 9.577940355605558e-06, + "loss": 0.39, + "step": 3357 + }, + { + "epoch": 0.4474946695095949, + "grad_norm": 0.3030556543630478, + "learning_rate": 9.577653991844305e-06, + "loss": 0.3656, + "step": 3358 + }, + { + "epoch": 0.4476279317697228, + "grad_norm": 0.2973073832077453, + "learning_rate": 9.577367535252207e-06, + "loss": 0.435, + "step": 3359 + }, + { + "epoch": 0.44776119402985076, + "grad_norm": 0.30094645419741733, + "learning_rate": 9.577080985835068e-06, + "loss": 0.5726, + "step": 3360 + }, + { + "epoch": 0.4478944562899787, + "grad_norm": 0.3161686354086411, + "learning_rate": 9.576794343598701e-06, + "loss": 0.4466, + "step": 3361 + }, + { + "epoch": 0.4480277185501066, + "grad_norm": 0.31150374116078533, + "learning_rate": 9.57650760854892e-06, + "loss": 0.4125, + "step": 3362 + }, + { + "epoch": 0.44816098081023453, + "grad_norm": 0.3314135259921446, + "learning_rate": 9.576220780691536e-06, + "loss": 0.4754, + "step": 3363 + }, + { + "epoch": 0.4482942430703625, + "grad_norm": 0.3188667647830613, + "learning_rate": 9.575933860032372e-06, + "loss": 0.516, + "step": 3364 + }, + { + "epoch": 0.4484275053304904, + "grad_norm": 0.29981144954858047, + "learning_rate": 9.57564684657724e-06, + "loss": 0.4012, + "step": 3365 + }, + { + "epoch": 0.44856076759061836, + "grad_norm": 0.3344463158191342, + "learning_rate": 9.575359740331964e-06, + "loss": 0.4238, + "step": 3366 + }, + { + "epoch": 0.44869402985074625, + "grad_norm": 0.294016929859014, + "learning_rate": 9.575072541302364e-06, + "loss": 0.4609, + "step": 3367 + }, + { + "epoch": 0.4488272921108742, + "grad_norm": 0.3254161162847429, + "learning_rate": 9.574785249494267e-06, + "loss": 0.4189, + "step": 3368 + }, + { + "epoch": 0.44896055437100213, + "grad_norm": 0.3206984989492954, + "learning_rate": 9.574497864913497e-06, + "loss": 0.4242, + "step": 3369 + }, + { + "epoch": 0.44909381663113007, + "grad_norm": 0.2978094776451243, + "learning_rate": 9.574210387565883e-06, + "loss": 0.3904, + "step": 3370 + }, + { + "epoch": 0.449227078891258, + "grad_norm": 0.29665786837227, + "learning_rate": 9.573922817457252e-06, + "loss": 0.4154, + "step": 3371 + }, + { + "epoch": 0.4493603411513859, + "grad_norm": 0.3115403686129873, + "learning_rate": 9.573635154593438e-06, + "loss": 0.3916, + "step": 3372 + }, + { + "epoch": 0.44949360341151384, + "grad_norm": 0.2922259750827447, + "learning_rate": 9.573347398980278e-06, + "loss": 0.3936, + "step": 3373 + }, + { + "epoch": 0.4496268656716418, + "grad_norm": 0.30241056324739995, + "learning_rate": 9.5730595506236e-06, + "loss": 0.4074, + "step": 3374 + }, + { + "epoch": 0.4497601279317697, + "grad_norm": 0.31756965833432277, + "learning_rate": 9.572771609529247e-06, + "loss": 0.4181, + "step": 3375 + }, + { + "epoch": 0.44989339019189767, + "grad_norm": 0.32200552732746074, + "learning_rate": 9.572483575703058e-06, + "loss": 0.5171, + "step": 3376 + }, + { + "epoch": 0.4500266524520256, + "grad_norm": 0.3064705106512402, + "learning_rate": 9.57219544915087e-06, + "loss": 0.4599, + "step": 3377 + }, + { + "epoch": 0.4501599147121535, + "grad_norm": 0.30138993880051446, + "learning_rate": 9.57190722987853e-06, + "loss": 0.3812, + "step": 3378 + }, + { + "epoch": 0.45029317697228144, + "grad_norm": 0.31039675513268844, + "learning_rate": 9.571618917891879e-06, + "loss": 0.3714, + "step": 3379 + }, + { + "epoch": 0.4504264392324094, + "grad_norm": 0.2925724706378597, + "learning_rate": 9.571330513196768e-06, + "loss": 0.4664, + "step": 3380 + }, + { + "epoch": 0.4505597014925373, + "grad_norm": 0.3099413618728973, + "learning_rate": 9.571042015799042e-06, + "loss": 0.3906, + "step": 3381 + }, + { + "epoch": 0.45069296375266527, + "grad_norm": 0.32166552115916014, + "learning_rate": 9.570753425704553e-06, + "loss": 0.4371, + "step": 3382 + }, + { + "epoch": 0.45082622601279315, + "grad_norm": 0.3026743611418499, + "learning_rate": 9.570464742919155e-06, + "loss": 0.4077, + "step": 3383 + }, + { + "epoch": 0.4509594882729211, + "grad_norm": 0.3196459558617698, + "learning_rate": 9.5701759674487e-06, + "loss": 0.4027, + "step": 3384 + }, + { + "epoch": 0.45109275053304904, + "grad_norm": 0.3011285298460388, + "learning_rate": 9.569887099299044e-06, + "loss": 0.3992, + "step": 3385 + }, + { + "epoch": 0.451226012793177, + "grad_norm": 0.30057601181434124, + "learning_rate": 9.569598138476047e-06, + "loss": 0.3717, + "step": 3386 + }, + { + "epoch": 0.4513592750533049, + "grad_norm": 0.30361070997543144, + "learning_rate": 9.569309084985565e-06, + "loss": 0.3784, + "step": 3387 + }, + { + "epoch": 0.45149253731343286, + "grad_norm": 0.2804430605056365, + "learning_rate": 9.569019938833465e-06, + "loss": 0.3209, + "step": 3388 + }, + { + "epoch": 0.45162579957356075, + "grad_norm": 0.297453308527404, + "learning_rate": 9.568730700025606e-06, + "loss": 0.463, + "step": 3389 + }, + { + "epoch": 0.4517590618336887, + "grad_norm": 0.29566330155519266, + "learning_rate": 9.568441368567858e-06, + "loss": 0.4219, + "step": 3390 + }, + { + "epoch": 0.45189232409381663, + "grad_norm": 0.2976294621867144, + "learning_rate": 9.568151944466084e-06, + "loss": 0.417, + "step": 3391 + }, + { + "epoch": 0.4520255863539446, + "grad_norm": 0.3050729652192756, + "learning_rate": 9.567862427726156e-06, + "loss": 0.3791, + "step": 3392 + }, + { + "epoch": 0.4521588486140725, + "grad_norm": 0.31439812484604895, + "learning_rate": 9.567572818353943e-06, + "loss": 0.3492, + "step": 3393 + }, + { + "epoch": 0.4522921108742004, + "grad_norm": 0.29383772054795065, + "learning_rate": 9.567283116355321e-06, + "loss": 0.3568, + "step": 3394 + }, + { + "epoch": 0.45242537313432835, + "grad_norm": 0.3243738589050154, + "learning_rate": 9.566993321736162e-06, + "loss": 0.3901, + "step": 3395 + }, + { + "epoch": 0.4525586353944563, + "grad_norm": 0.31353226195403605, + "learning_rate": 9.566703434502345e-06, + "loss": 0.4835, + "step": 3396 + }, + { + "epoch": 0.45269189765458423, + "grad_norm": 0.30863967129707864, + "learning_rate": 9.566413454659747e-06, + "loss": 0.4223, + "step": 3397 + }, + { + "epoch": 0.45282515991471217, + "grad_norm": 0.29983732593258006, + "learning_rate": 9.566123382214249e-06, + "loss": 0.4463, + "step": 3398 + }, + { + "epoch": 0.45295842217484006, + "grad_norm": 0.2955603434113951, + "learning_rate": 9.565833217171734e-06, + "loss": 0.436, + "step": 3399 + }, + { + "epoch": 0.453091684434968, + "grad_norm": 0.3314222155611883, + "learning_rate": 9.565542959538086e-06, + "loss": 0.4689, + "step": 3400 + }, + { + "epoch": 0.45322494669509594, + "grad_norm": 0.2996504866294065, + "learning_rate": 9.565252609319192e-06, + "loss": 0.413, + "step": 3401 + }, + { + "epoch": 0.4533582089552239, + "grad_norm": 0.3127009556049752, + "learning_rate": 9.564962166520936e-06, + "loss": 0.4639, + "step": 3402 + }, + { + "epoch": 0.4534914712153518, + "grad_norm": 0.3723802171637502, + "learning_rate": 9.564671631149214e-06, + "loss": 0.4835, + "step": 3403 + }, + { + "epoch": 0.45362473347547977, + "grad_norm": 0.3149484260799451, + "learning_rate": 9.564381003209915e-06, + "loss": 0.4391, + "step": 3404 + }, + { + "epoch": 0.45375799573560766, + "grad_norm": 0.3176484183923987, + "learning_rate": 9.564090282708932e-06, + "loss": 0.3676, + "step": 3405 + }, + { + "epoch": 0.4538912579957356, + "grad_norm": 0.29629446727882697, + "learning_rate": 9.56379946965216e-06, + "loss": 0.3793, + "step": 3406 + }, + { + "epoch": 0.45402452025586354, + "grad_norm": 0.3327302484125545, + "learning_rate": 9.563508564045499e-06, + "loss": 0.4905, + "step": 3407 + }, + { + "epoch": 0.4541577825159915, + "grad_norm": 0.2985379163760058, + "learning_rate": 9.563217565894845e-06, + "loss": 0.4126, + "step": 3408 + }, + { + "epoch": 0.4542910447761194, + "grad_norm": 0.32505461806690156, + "learning_rate": 9.562926475206103e-06, + "loss": 0.3857, + "step": 3409 + }, + { + "epoch": 0.4544243070362473, + "grad_norm": 0.3176483167021513, + "learning_rate": 9.562635291985174e-06, + "loss": 0.377, + "step": 3410 + }, + { + "epoch": 0.45455756929637525, + "grad_norm": 0.2977149215525266, + "learning_rate": 9.56234401623796e-06, + "loss": 0.4102, + "step": 3411 + }, + { + "epoch": 0.4546908315565032, + "grad_norm": 0.3061866127323332, + "learning_rate": 9.562052647970374e-06, + "loss": 0.3757, + "step": 3412 + }, + { + "epoch": 0.45482409381663114, + "grad_norm": 0.3178378613918582, + "learning_rate": 9.561761187188322e-06, + "loss": 0.4873, + "step": 3413 + }, + { + "epoch": 0.4549573560767591, + "grad_norm": 0.307154203274294, + "learning_rate": 9.561469633897713e-06, + "loss": 0.4163, + "step": 3414 + }, + { + "epoch": 0.455090618336887, + "grad_norm": 0.31344345932128875, + "learning_rate": 9.561177988104461e-06, + "loss": 0.4216, + "step": 3415 + }, + { + "epoch": 0.4552238805970149, + "grad_norm": 0.2831107180462461, + "learning_rate": 9.56088624981448e-06, + "loss": 0.3257, + "step": 3416 + }, + { + "epoch": 0.45535714285714285, + "grad_norm": 0.2946217792150883, + "learning_rate": 9.560594419033687e-06, + "loss": 0.4459, + "step": 3417 + }, + { + "epoch": 0.4554904051172708, + "grad_norm": 0.3094189945753503, + "learning_rate": 9.560302495767997e-06, + "loss": 0.431, + "step": 3418 + }, + { + "epoch": 0.45562366737739873, + "grad_norm": 0.29532087008059665, + "learning_rate": 9.560010480023335e-06, + "loss": 0.3999, + "step": 3419 + }, + { + "epoch": 0.4557569296375267, + "grad_norm": 0.30110315207232685, + "learning_rate": 9.559718371805616e-06, + "loss": 0.4342, + "step": 3420 + }, + { + "epoch": 0.45589019189765456, + "grad_norm": 0.2908144469734922, + "learning_rate": 9.55942617112077e-06, + "loss": 0.4154, + "step": 3421 + }, + { + "epoch": 0.4560234541577825, + "grad_norm": 0.30883930715639035, + "learning_rate": 9.55913387797472e-06, + "loss": 0.4342, + "step": 3422 + }, + { + "epoch": 0.45615671641791045, + "grad_norm": 0.29577312747832435, + "learning_rate": 9.558841492373394e-06, + "loss": 0.4358, + "step": 3423 + }, + { + "epoch": 0.4562899786780384, + "grad_norm": 0.3156826431520583, + "learning_rate": 9.558549014322721e-06, + "loss": 0.4029, + "step": 3424 + }, + { + "epoch": 0.45642324093816633, + "grad_norm": 0.2871802327985457, + "learning_rate": 9.558256443828633e-06, + "loss": 0.3602, + "step": 3425 + }, + { + "epoch": 0.4565565031982942, + "grad_norm": 0.2969313507455623, + "learning_rate": 9.557963780897061e-06, + "loss": 0.3928, + "step": 3426 + }, + { + "epoch": 0.45668976545842216, + "grad_norm": 0.2950307616221191, + "learning_rate": 9.557671025533941e-06, + "loss": 0.3567, + "step": 3427 + }, + { + "epoch": 0.4568230277185501, + "grad_norm": 0.3086457225678582, + "learning_rate": 9.557378177745211e-06, + "loss": 0.6092, + "step": 3428 + }, + { + "epoch": 0.45695628997867804, + "grad_norm": 0.30372111146084496, + "learning_rate": 9.55708523753681e-06, + "loss": 0.3834, + "step": 3429 + }, + { + "epoch": 0.457089552238806, + "grad_norm": 0.30675421994157714, + "learning_rate": 9.556792204914676e-06, + "loss": 0.3812, + "step": 3430 + }, + { + "epoch": 0.4572228144989339, + "grad_norm": 0.3202144482921119, + "learning_rate": 9.556499079884751e-06, + "loss": 0.4327, + "step": 3431 + }, + { + "epoch": 0.4573560767590618, + "grad_norm": 0.3024208614880115, + "learning_rate": 9.556205862452983e-06, + "loss": 0.4729, + "step": 3432 + }, + { + "epoch": 0.45748933901918976, + "grad_norm": 0.31369718410042186, + "learning_rate": 9.555912552625317e-06, + "loss": 0.44, + "step": 3433 + }, + { + "epoch": 0.4576226012793177, + "grad_norm": 0.3003359186863028, + "learning_rate": 9.5556191504077e-06, + "loss": 0.4253, + "step": 3434 + }, + { + "epoch": 0.45775586353944564, + "grad_norm": 0.2970162851287775, + "learning_rate": 9.55532565580608e-06, + "loss": 0.3809, + "step": 3435 + }, + { + "epoch": 0.4578891257995736, + "grad_norm": 0.32137809757571134, + "learning_rate": 9.555032068826416e-06, + "loss": 0.4386, + "step": 3436 + }, + { + "epoch": 0.45802238805970147, + "grad_norm": 0.2872861327081604, + "learning_rate": 9.554738389474652e-06, + "loss": 0.3702, + "step": 3437 + }, + { + "epoch": 0.4581556503198294, + "grad_norm": 0.3326980898583532, + "learning_rate": 9.554444617756751e-06, + "loss": 0.4191, + "step": 3438 + }, + { + "epoch": 0.45828891257995735, + "grad_norm": 0.2958165038231267, + "learning_rate": 9.554150753678667e-06, + "loss": 0.3943, + "step": 3439 + }, + { + "epoch": 0.4584221748400853, + "grad_norm": 0.2842061602208027, + "learning_rate": 9.553856797246361e-06, + "loss": 0.3765, + "step": 3440 + }, + { + "epoch": 0.45855543710021324, + "grad_norm": 0.32154351613162424, + "learning_rate": 9.553562748465792e-06, + "loss": 0.3833, + "step": 3441 + }, + { + "epoch": 0.4586886993603412, + "grad_norm": 0.30441664145492137, + "learning_rate": 9.553268607342924e-06, + "loss": 0.4161, + "step": 3442 + }, + { + "epoch": 0.45882196162046907, + "grad_norm": 0.3378670650322089, + "learning_rate": 9.552974373883725e-06, + "loss": 0.4483, + "step": 3443 + }, + { + "epoch": 0.458955223880597, + "grad_norm": 0.30007893401462826, + "learning_rate": 9.552680048094158e-06, + "loss": 0.3827, + "step": 3444 + }, + { + "epoch": 0.45908848614072495, + "grad_norm": 0.3212016765406694, + "learning_rate": 9.552385629980191e-06, + "loss": 0.4444, + "step": 3445 + }, + { + "epoch": 0.4592217484008529, + "grad_norm": 0.32013960798080143, + "learning_rate": 9.552091119547797e-06, + "loss": 0.3714, + "step": 3446 + }, + { + "epoch": 0.45935501066098083, + "grad_norm": 0.28670093016167425, + "learning_rate": 9.55179651680295e-06, + "loss": 0.385, + "step": 3447 + }, + { + "epoch": 0.4594882729211087, + "grad_norm": 0.31196250853669205, + "learning_rate": 9.551501821751619e-06, + "loss": 0.4066, + "step": 3448 + }, + { + "epoch": 0.45962153518123666, + "grad_norm": 0.3621708003478437, + "learning_rate": 9.551207034399785e-06, + "loss": 0.3639, + "step": 3449 + }, + { + "epoch": 0.4597547974413646, + "grad_norm": 0.30016403007713344, + "learning_rate": 9.550912154753424e-06, + "loss": 0.3894, + "step": 3450 + }, + { + "epoch": 0.45988805970149255, + "grad_norm": 0.39108158008412014, + "learning_rate": 9.550617182818515e-06, + "loss": 0.4528, + "step": 3451 + }, + { + "epoch": 0.4600213219616205, + "grad_norm": 0.29337062429526284, + "learning_rate": 9.550322118601043e-06, + "loss": 0.379, + "step": 3452 + }, + { + "epoch": 0.4601545842217484, + "grad_norm": 0.2863128955678805, + "learning_rate": 9.550026962106987e-06, + "loss": 0.3345, + "step": 3453 + }, + { + "epoch": 0.4602878464818763, + "grad_norm": 0.31936741619928893, + "learning_rate": 9.549731713342336e-06, + "loss": 0.4388, + "step": 3454 + }, + { + "epoch": 0.46042110874200426, + "grad_norm": 0.31934179085540404, + "learning_rate": 9.549436372313078e-06, + "loss": 0.4283, + "step": 3455 + }, + { + "epoch": 0.4605543710021322, + "grad_norm": 0.31154451333802397, + "learning_rate": 9.549140939025199e-06, + "loss": 0.4073, + "step": 3456 + }, + { + "epoch": 0.46068763326226014, + "grad_norm": 0.3212735390704742, + "learning_rate": 9.548845413484694e-06, + "loss": 0.4459, + "step": 3457 + }, + { + "epoch": 0.4608208955223881, + "grad_norm": 0.3272023543857216, + "learning_rate": 9.54854979569755e-06, + "loss": 0.4128, + "step": 3458 + }, + { + "epoch": 0.46095415778251597, + "grad_norm": 0.33521626871734683, + "learning_rate": 9.548254085669768e-06, + "loss": 0.4862, + "step": 3459 + }, + { + "epoch": 0.4610874200426439, + "grad_norm": 0.3273834365339642, + "learning_rate": 9.547958283407342e-06, + "loss": 0.4163, + "step": 3460 + }, + { + "epoch": 0.46122068230277186, + "grad_norm": 0.3025679203024174, + "learning_rate": 9.547662388916272e-06, + "loss": 0.4005, + "step": 3461 + }, + { + "epoch": 0.4613539445628998, + "grad_norm": 0.317383307962939, + "learning_rate": 9.547366402202558e-06, + "loss": 0.4494, + "step": 3462 + }, + { + "epoch": 0.46148720682302774, + "grad_norm": 0.30344497464059916, + "learning_rate": 9.547070323272201e-06, + "loss": 0.3829, + "step": 3463 + }, + { + "epoch": 0.4616204690831556, + "grad_norm": 0.3223527149729879, + "learning_rate": 9.546774152131205e-06, + "loss": 0.4267, + "step": 3464 + }, + { + "epoch": 0.46175373134328357, + "grad_norm": 0.30160481953415513, + "learning_rate": 9.546477888785578e-06, + "loss": 0.39, + "step": 3465 + }, + { + "epoch": 0.4618869936034115, + "grad_norm": 0.3047564374563705, + "learning_rate": 9.546181533241328e-06, + "loss": 0.3986, + "step": 3466 + }, + { + "epoch": 0.46202025586353945, + "grad_norm": 0.29721937052358394, + "learning_rate": 9.545885085504463e-06, + "loss": 0.4422, + "step": 3467 + }, + { + "epoch": 0.4621535181236674, + "grad_norm": 0.2927092560650387, + "learning_rate": 9.545588545580997e-06, + "loss": 0.3764, + "step": 3468 + }, + { + "epoch": 0.4622867803837953, + "grad_norm": 0.3135585236311785, + "learning_rate": 9.545291913476941e-06, + "loss": 0.4182, + "step": 3469 + }, + { + "epoch": 0.4624200426439232, + "grad_norm": 0.31233486803003185, + "learning_rate": 9.544995189198311e-06, + "loss": 0.418, + "step": 3470 + }, + { + "epoch": 0.46255330490405117, + "grad_norm": 0.30382237017412517, + "learning_rate": 9.544698372751126e-06, + "loss": 0.4221, + "step": 3471 + }, + { + "epoch": 0.4626865671641791, + "grad_norm": 0.3163296240342692, + "learning_rate": 9.544401464141404e-06, + "loss": 0.4273, + "step": 3472 + }, + { + "epoch": 0.46281982942430705, + "grad_norm": 0.29658708687019847, + "learning_rate": 9.544104463375167e-06, + "loss": 0.4858, + "step": 3473 + }, + { + "epoch": 0.462953091684435, + "grad_norm": 0.30594952756451516, + "learning_rate": 9.543807370458437e-06, + "loss": 0.4131, + "step": 3474 + }, + { + "epoch": 0.4630863539445629, + "grad_norm": 0.2904863109991791, + "learning_rate": 9.54351018539724e-06, + "loss": 0.4186, + "step": 3475 + }, + { + "epoch": 0.4632196162046908, + "grad_norm": 0.2865009854049972, + "learning_rate": 9.5432129081976e-06, + "loss": 0.4379, + "step": 3476 + }, + { + "epoch": 0.46335287846481876, + "grad_norm": 0.3237929212402273, + "learning_rate": 9.542915538865547e-06, + "loss": 0.3882, + "step": 3477 + }, + { + "epoch": 0.4634861407249467, + "grad_norm": 0.31987357163565344, + "learning_rate": 9.542618077407114e-06, + "loss": 0.4482, + "step": 3478 + }, + { + "epoch": 0.46361940298507465, + "grad_norm": 0.28469489930893066, + "learning_rate": 9.542320523828327e-06, + "loss": 0.3338, + "step": 3479 + }, + { + "epoch": 0.46375266524520253, + "grad_norm": 0.2922312231570652, + "learning_rate": 9.542022878135226e-06, + "loss": 0.3786, + "step": 3480 + }, + { + "epoch": 0.4638859275053305, + "grad_norm": 0.28424051637948816, + "learning_rate": 9.541725140333846e-06, + "loss": 0.3517, + "step": 3481 + }, + { + "epoch": 0.4640191897654584, + "grad_norm": 0.3202458422516539, + "learning_rate": 9.541427310430222e-06, + "loss": 0.4066, + "step": 3482 + }, + { + "epoch": 0.46415245202558636, + "grad_norm": 0.2945857914373953, + "learning_rate": 9.541129388430397e-06, + "loss": 0.3824, + "step": 3483 + }, + { + "epoch": 0.4642857142857143, + "grad_norm": 0.3248672786741445, + "learning_rate": 9.540831374340409e-06, + "loss": 0.3882, + "step": 3484 + }, + { + "epoch": 0.46441897654584224, + "grad_norm": 0.28131291833525474, + "learning_rate": 9.540533268166306e-06, + "loss": 0.4239, + "step": 3485 + }, + { + "epoch": 0.46455223880597013, + "grad_norm": 0.3070411088002489, + "learning_rate": 9.54023506991413e-06, + "loss": 0.4168, + "step": 3486 + }, + { + "epoch": 0.4646855010660981, + "grad_norm": 0.3045209123020421, + "learning_rate": 9.53993677958993e-06, + "loss": 0.3898, + "step": 3487 + }, + { + "epoch": 0.464818763326226, + "grad_norm": 0.34275847585640995, + "learning_rate": 9.539638397199751e-06, + "loss": 0.4234, + "step": 3488 + }, + { + "epoch": 0.46495202558635396, + "grad_norm": 0.30552071008019666, + "learning_rate": 9.53933992274965e-06, + "loss": 0.4474, + "step": 3489 + }, + { + "epoch": 0.4650852878464819, + "grad_norm": 0.33345044686921094, + "learning_rate": 9.539041356245674e-06, + "loss": 0.3708, + "step": 3490 + }, + { + "epoch": 0.4652185501066098, + "grad_norm": 0.30709665704122413, + "learning_rate": 9.538742697693885e-06, + "loss": 0.3928, + "step": 3491 + }, + { + "epoch": 0.4653518123667377, + "grad_norm": 0.31951939221915, + "learning_rate": 9.538443947100333e-06, + "loss": 0.4425, + "step": 3492 + }, + { + "epoch": 0.46548507462686567, + "grad_norm": 0.3317248053265188, + "learning_rate": 9.538145104471078e-06, + "loss": 0.4221, + "step": 3493 + }, + { + "epoch": 0.4656183368869936, + "grad_norm": 0.3007093038732292, + "learning_rate": 9.537846169812182e-06, + "loss": 0.3602, + "step": 3494 + }, + { + "epoch": 0.46575159914712155, + "grad_norm": 0.3220559951357805, + "learning_rate": 9.537547143129705e-06, + "loss": 0.4065, + "step": 3495 + }, + { + "epoch": 0.46588486140724944, + "grad_norm": 0.3211496231037527, + "learning_rate": 9.537248024429711e-06, + "loss": 0.4317, + "step": 3496 + }, + { + "epoch": 0.4660181236673774, + "grad_norm": 0.30400491290713916, + "learning_rate": 9.536948813718269e-06, + "loss": 0.4272, + "step": 3497 + }, + { + "epoch": 0.4661513859275053, + "grad_norm": 2.309099725243627, + "learning_rate": 9.536649511001443e-06, + "loss": 0.5062, + "step": 3498 + }, + { + "epoch": 0.46628464818763327, + "grad_norm": 0.3588755711167787, + "learning_rate": 9.536350116285305e-06, + "loss": 0.4367, + "step": 3499 + }, + { + "epoch": 0.4664179104477612, + "grad_norm": 0.30893621379365255, + "learning_rate": 9.536050629575925e-06, + "loss": 0.3907, + "step": 3500 + }, + { + "epoch": 0.46655117270788915, + "grad_norm": 0.33213957260834165, + "learning_rate": 9.535751050879379e-06, + "loss": 0.4542, + "step": 3501 + }, + { + "epoch": 0.46668443496801704, + "grad_norm": 0.33265135380465954, + "learning_rate": 9.535451380201736e-06, + "loss": 0.4138, + "step": 3502 + }, + { + "epoch": 0.466817697228145, + "grad_norm": 0.3122087924383557, + "learning_rate": 9.535151617549081e-06, + "loss": 0.4384, + "step": 3503 + }, + { + "epoch": 0.4669509594882729, + "grad_norm": 0.31292003668430746, + "learning_rate": 9.534851762927488e-06, + "loss": 0.4204, + "step": 3504 + }, + { + "epoch": 0.46708422174840086, + "grad_norm": 0.31143441779826114, + "learning_rate": 9.534551816343039e-06, + "loss": 0.3434, + "step": 3505 + }, + { + "epoch": 0.4672174840085288, + "grad_norm": 0.3034648532573624, + "learning_rate": 9.534251777801814e-06, + "loss": 0.4637, + "step": 3506 + }, + { + "epoch": 0.4673507462686567, + "grad_norm": 0.2900883933265194, + "learning_rate": 9.533951647309903e-06, + "loss": 0.4211, + "step": 3507 + }, + { + "epoch": 0.46748400852878463, + "grad_norm": 0.28363620106155346, + "learning_rate": 9.533651424873389e-06, + "loss": 0.4047, + "step": 3508 + }, + { + "epoch": 0.4676172707889126, + "grad_norm": 0.3094334350226694, + "learning_rate": 9.533351110498362e-06, + "loss": 0.3778, + "step": 3509 + }, + { + "epoch": 0.4677505330490405, + "grad_norm": 0.29660459257222466, + "learning_rate": 9.533050704190909e-06, + "loss": 0.4954, + "step": 3510 + }, + { + "epoch": 0.46788379530916846, + "grad_norm": 0.29877859156946657, + "learning_rate": 9.532750205957124e-06, + "loss": 0.3804, + "step": 3511 + }, + { + "epoch": 0.4680170575692964, + "grad_norm": 0.28451618270552065, + "learning_rate": 9.532449615803101e-06, + "loss": 0.4041, + "step": 3512 + }, + { + "epoch": 0.4681503198294243, + "grad_norm": 0.3066600097118418, + "learning_rate": 9.532148933734934e-06, + "loss": 0.4197, + "step": 3513 + }, + { + "epoch": 0.46828358208955223, + "grad_norm": 0.34200890397798295, + "learning_rate": 9.531848159758724e-06, + "loss": 0.4249, + "step": 3514 + }, + { + "epoch": 0.4684168443496802, + "grad_norm": 0.33508429293439346, + "learning_rate": 9.531547293880568e-06, + "loss": 0.4562, + "step": 3515 + }, + { + "epoch": 0.4685501066098081, + "grad_norm": 0.2989232143151716, + "learning_rate": 9.531246336106568e-06, + "loss": 0.446, + "step": 3516 + }, + { + "epoch": 0.46868336886993606, + "grad_norm": 0.3129297266736807, + "learning_rate": 9.530945286442826e-06, + "loss": 0.3649, + "step": 3517 + }, + { + "epoch": 0.46881663113006394, + "grad_norm": 0.31201734168976214, + "learning_rate": 9.530644144895447e-06, + "loss": 0.3802, + "step": 3518 + }, + { + "epoch": 0.4689498933901919, + "grad_norm": 0.29104325370898093, + "learning_rate": 9.53034291147054e-06, + "loss": 0.4108, + "step": 3519 + }, + { + "epoch": 0.4690831556503198, + "grad_norm": 0.3241536523850515, + "learning_rate": 9.530041586174212e-06, + "loss": 0.4597, + "step": 3520 + }, + { + "epoch": 0.46921641791044777, + "grad_norm": 0.29909322283506073, + "learning_rate": 9.529740169012576e-06, + "loss": 0.3968, + "step": 3521 + }, + { + "epoch": 0.4693496801705757, + "grad_norm": 0.32424471741162214, + "learning_rate": 9.52943865999174e-06, + "loss": 0.4439, + "step": 3522 + }, + { + "epoch": 0.4694829424307036, + "grad_norm": 0.31644922411819854, + "learning_rate": 9.529137059117822e-06, + "loss": 0.5265, + "step": 3523 + }, + { + "epoch": 0.46961620469083154, + "grad_norm": 0.3203175026051181, + "learning_rate": 9.528835366396937e-06, + "loss": 0.5316, + "step": 3524 + }, + { + "epoch": 0.4697494669509595, + "grad_norm": 0.32155789603107343, + "learning_rate": 9.528533581835204e-06, + "loss": 0.3925, + "step": 3525 + }, + { + "epoch": 0.4698827292110874, + "grad_norm": 0.9704354109819867, + "learning_rate": 9.528231705438742e-06, + "loss": 0.3706, + "step": 3526 + }, + { + "epoch": 0.47001599147121537, + "grad_norm": 0.3217142955095522, + "learning_rate": 9.527929737213672e-06, + "loss": 0.4253, + "step": 3527 + }, + { + "epoch": 0.4701492537313433, + "grad_norm": 0.31226942512386363, + "learning_rate": 9.527627677166118e-06, + "loss": 0.3873, + "step": 3528 + }, + { + "epoch": 0.4702825159914712, + "grad_norm": 0.3293074121440186, + "learning_rate": 9.527325525302208e-06, + "loss": 0.4187, + "step": 3529 + }, + { + "epoch": 0.47041577825159914, + "grad_norm": 0.35308376105913514, + "learning_rate": 9.527023281628065e-06, + "loss": 0.3818, + "step": 3530 + }, + { + "epoch": 0.4705490405117271, + "grad_norm": 0.3017556969561064, + "learning_rate": 9.526720946149823e-06, + "loss": 0.4415, + "step": 3531 + }, + { + "epoch": 0.470682302771855, + "grad_norm": 0.3107915798060207, + "learning_rate": 9.52641851887361e-06, + "loss": 0.374, + "step": 3532 + }, + { + "epoch": 0.47081556503198296, + "grad_norm": 0.31439288124468867, + "learning_rate": 9.52611599980556e-06, + "loss": 0.4601, + "step": 3533 + }, + { + "epoch": 0.47094882729211085, + "grad_norm": 0.3038948040192519, + "learning_rate": 9.525813388951809e-06, + "loss": 0.4331, + "step": 3534 + }, + { + "epoch": 0.4710820895522388, + "grad_norm": 0.3156447305680929, + "learning_rate": 9.525510686318491e-06, + "loss": 0.377, + "step": 3535 + }, + { + "epoch": 0.47121535181236673, + "grad_norm": 0.3275278687417676, + "learning_rate": 9.525207891911745e-06, + "loss": 0.4869, + "step": 3536 + }, + { + "epoch": 0.4713486140724947, + "grad_norm": 0.3506151133001465, + "learning_rate": 9.524905005737713e-06, + "loss": 0.4543, + "step": 3537 + }, + { + "epoch": 0.4714818763326226, + "grad_norm": 0.2857942972759958, + "learning_rate": 9.524602027802536e-06, + "loss": 0.4277, + "step": 3538 + }, + { + "epoch": 0.47161513859275056, + "grad_norm": 0.36916847180827816, + "learning_rate": 9.52429895811236e-06, + "loss": 0.3952, + "step": 3539 + }, + { + "epoch": 0.47174840085287845, + "grad_norm": 0.28107847406108627, + "learning_rate": 9.523995796673329e-06, + "loss": 0.4292, + "step": 3540 + }, + { + "epoch": 0.4718816631130064, + "grad_norm": 0.34914202152815715, + "learning_rate": 9.52369254349159e-06, + "loss": 0.426, + "step": 3541 + }, + { + "epoch": 0.47201492537313433, + "grad_norm": 0.3134027588231443, + "learning_rate": 9.523389198573296e-06, + "loss": 0.3866, + "step": 3542 + }, + { + "epoch": 0.4721481876332623, + "grad_norm": 0.3415840501431343, + "learning_rate": 9.523085761924596e-06, + "loss": 0.4842, + "step": 3543 + }, + { + "epoch": 0.4722814498933902, + "grad_norm": 0.30428018601660545, + "learning_rate": 9.522782233551645e-06, + "loss": 0.4354, + "step": 3544 + }, + { + "epoch": 0.4724147121535181, + "grad_norm": 0.3169211663183359, + "learning_rate": 9.522478613460597e-06, + "loss": 0.4561, + "step": 3545 + }, + { + "epoch": 0.47254797441364604, + "grad_norm": 0.3170581599682477, + "learning_rate": 9.52217490165761e-06, + "loss": 0.427, + "step": 3546 + }, + { + "epoch": 0.472681236673774, + "grad_norm": 0.3098607741702277, + "learning_rate": 9.521871098148842e-06, + "loss": 0.4151, + "step": 3547 + }, + { + "epoch": 0.4728144989339019, + "grad_norm": 0.3091613452962797, + "learning_rate": 9.521567202940455e-06, + "loss": 0.3882, + "step": 3548 + }, + { + "epoch": 0.47294776119402987, + "grad_norm": 0.321645943141699, + "learning_rate": 9.52126321603861e-06, + "loss": 0.4049, + "step": 3549 + }, + { + "epoch": 0.47308102345415776, + "grad_norm": 0.30780828906314045, + "learning_rate": 9.520959137449475e-06, + "loss": 0.4312, + "step": 3550 + }, + { + "epoch": 0.4732142857142857, + "grad_norm": 0.3326732907088182, + "learning_rate": 9.520654967179212e-06, + "loss": 0.5525, + "step": 3551 + }, + { + "epoch": 0.47334754797441364, + "grad_norm": 0.3379242897981982, + "learning_rate": 9.520350705233993e-06, + "loss": 0.4802, + "step": 3552 + }, + { + "epoch": 0.4734808102345416, + "grad_norm": 0.31254063472037047, + "learning_rate": 9.520046351619986e-06, + "loss": 0.3536, + "step": 3553 + }, + { + "epoch": 0.4736140724946695, + "grad_norm": 0.30811952853427105, + "learning_rate": 9.519741906343365e-06, + "loss": 0.4375, + "step": 3554 + }, + { + "epoch": 0.47374733475479747, + "grad_norm": 0.3053071682973712, + "learning_rate": 9.519437369410303e-06, + "loss": 0.467, + "step": 3555 + }, + { + "epoch": 0.47388059701492535, + "grad_norm": 0.31516704700178266, + "learning_rate": 9.519132740826973e-06, + "loss": 0.5125, + "step": 3556 + }, + { + "epoch": 0.4740138592750533, + "grad_norm": 0.29671337128078706, + "learning_rate": 9.518828020599558e-06, + "loss": 0.3876, + "step": 3557 + }, + { + "epoch": 0.47414712153518124, + "grad_norm": 0.31881229387712645, + "learning_rate": 9.518523208734231e-06, + "loss": 0.3614, + "step": 3558 + }, + { + "epoch": 0.4742803837953092, + "grad_norm": 0.306990831037769, + "learning_rate": 9.51821830523718e-06, + "loss": 0.374, + "step": 3559 + }, + { + "epoch": 0.4744136460554371, + "grad_norm": 0.30541427914380165, + "learning_rate": 9.517913310114584e-06, + "loss": 0.448, + "step": 3560 + }, + { + "epoch": 0.474546908315565, + "grad_norm": 0.30929879440978564, + "learning_rate": 9.51760822337263e-06, + "loss": 0.4263, + "step": 3561 + }, + { + "epoch": 0.47468017057569295, + "grad_norm": 0.2993799049664525, + "learning_rate": 9.517303045017502e-06, + "loss": 0.3323, + "step": 3562 + }, + { + "epoch": 0.4748134328358209, + "grad_norm": 0.3034594645287998, + "learning_rate": 9.516997775055391e-06, + "loss": 0.5297, + "step": 3563 + }, + { + "epoch": 0.47494669509594883, + "grad_norm": 0.3016283674760541, + "learning_rate": 9.516692413492487e-06, + "loss": 0.427, + "step": 3564 + }, + { + "epoch": 0.4750799573560768, + "grad_norm": 0.30141384104240204, + "learning_rate": 9.516386960334984e-06, + "loss": 0.3917, + "step": 3565 + }, + { + "epoch": 0.4752132196162047, + "grad_norm": 0.63726926129213, + "learning_rate": 9.516081415589075e-06, + "loss": 0.3892, + "step": 3566 + }, + { + "epoch": 0.4753464818763326, + "grad_norm": 0.5800523211214993, + "learning_rate": 9.515775779260956e-06, + "loss": 0.369, + "step": 3567 + }, + { + "epoch": 0.47547974413646055, + "grad_norm": 0.31411682838903565, + "learning_rate": 9.515470051356826e-06, + "loss": 0.4152, + "step": 3568 + }, + { + "epoch": 0.4756130063965885, + "grad_norm": 0.2916295070279165, + "learning_rate": 9.515164231882882e-06, + "loss": 0.4895, + "step": 3569 + }, + { + "epoch": 0.47574626865671643, + "grad_norm": 0.2931302985596623, + "learning_rate": 9.514858320845331e-06, + "loss": 0.4646, + "step": 3570 + }, + { + "epoch": 0.4758795309168444, + "grad_norm": 0.2979551988274242, + "learning_rate": 9.514552318250372e-06, + "loss": 0.46, + "step": 3571 + }, + { + "epoch": 0.47601279317697226, + "grad_norm": 0.3003900311134971, + "learning_rate": 9.514246224104212e-06, + "loss": 0.4634, + "step": 3572 + }, + { + "epoch": 0.4761460554371002, + "grad_norm": 0.3005141305775318, + "learning_rate": 9.513940038413058e-06, + "loss": 0.4794, + "step": 3573 + }, + { + "epoch": 0.47627931769722814, + "grad_norm": 0.29668805228853345, + "learning_rate": 9.513633761183119e-06, + "loss": 0.3965, + "step": 3574 + }, + { + "epoch": 0.4764125799573561, + "grad_norm": 0.3011948713734113, + "learning_rate": 9.513327392420608e-06, + "loss": 0.4272, + "step": 3575 + }, + { + "epoch": 0.47654584221748403, + "grad_norm": 0.27891176890074093, + "learning_rate": 9.513020932131735e-06, + "loss": 0.3831, + "step": 3576 + }, + { + "epoch": 0.4766791044776119, + "grad_norm": 0.30172842537359845, + "learning_rate": 9.51271438032272e-06, + "loss": 0.3517, + "step": 3577 + }, + { + "epoch": 0.47681236673773986, + "grad_norm": 0.3005406016052358, + "learning_rate": 9.51240773699977e-06, + "loss": 0.3674, + "step": 3578 + }, + { + "epoch": 0.4769456289978678, + "grad_norm": 0.4837005198494371, + "learning_rate": 9.512101002169114e-06, + "loss": 0.426, + "step": 3579 + }, + { + "epoch": 0.47707889125799574, + "grad_norm": 0.3044648508247261, + "learning_rate": 9.511794175836965e-06, + "loss": 0.3863, + "step": 3580 + }, + { + "epoch": 0.4772121535181237, + "grad_norm": 0.3092081763682342, + "learning_rate": 9.511487258009549e-06, + "loss": 0.5361, + "step": 3581 + }, + { + "epoch": 0.4773454157782516, + "grad_norm": 0.3102885330215372, + "learning_rate": 9.511180248693088e-06, + "loss": 0.4259, + "step": 3582 + }, + { + "epoch": 0.4774786780383795, + "grad_norm": 0.3080232815549374, + "learning_rate": 9.51087314789381e-06, + "loss": 0.4007, + "step": 3583 + }, + { + "epoch": 0.47761194029850745, + "grad_norm": 0.30538345676556516, + "learning_rate": 9.510565955617939e-06, + "loss": 0.4318, + "step": 3584 + }, + { + "epoch": 0.4777452025586354, + "grad_norm": 0.3112374286284828, + "learning_rate": 9.510258671871709e-06, + "loss": 0.3924, + "step": 3585 + }, + { + "epoch": 0.47787846481876334, + "grad_norm": 0.3176455742490306, + "learning_rate": 9.509951296661348e-06, + "loss": 0.3978, + "step": 3586 + }, + { + "epoch": 0.4780117270788913, + "grad_norm": 0.29513412828249036, + "learning_rate": 9.509643829993091e-06, + "loss": 0.3838, + "step": 3587 + }, + { + "epoch": 0.47814498933901917, + "grad_norm": 0.32676968308676874, + "learning_rate": 9.509336271873175e-06, + "loss": 0.371, + "step": 3588 + }, + { + "epoch": 0.4782782515991471, + "grad_norm": 0.30775151189875366, + "learning_rate": 9.509028622307834e-06, + "loss": 0.3901, + "step": 3589 + }, + { + "epoch": 0.47841151385927505, + "grad_norm": 0.2895555694424238, + "learning_rate": 9.508720881303306e-06, + "loss": 0.3996, + "step": 3590 + }, + { + "epoch": 0.478544776119403, + "grad_norm": 0.3244368285664439, + "learning_rate": 9.508413048865835e-06, + "loss": 0.3992, + "step": 3591 + }, + { + "epoch": 0.47867803837953093, + "grad_norm": 0.3950852813343269, + "learning_rate": 9.508105125001661e-06, + "loss": 0.4137, + "step": 3592 + }, + { + "epoch": 0.4788113006396588, + "grad_norm": 0.3127232972845745, + "learning_rate": 9.507797109717032e-06, + "loss": 0.4546, + "step": 3593 + }, + { + "epoch": 0.47894456289978676, + "grad_norm": 0.33976975328690334, + "learning_rate": 9.50748900301819e-06, + "loss": 0.4196, + "step": 3594 + }, + { + "epoch": 0.4790778251599147, + "grad_norm": 0.3146831376098811, + "learning_rate": 9.507180804911384e-06, + "loss": 0.446, + "step": 3595 + }, + { + "epoch": 0.47921108742004265, + "grad_norm": 0.3350256722674776, + "learning_rate": 9.506872515402867e-06, + "loss": 0.5205, + "step": 3596 + }, + { + "epoch": 0.4793443496801706, + "grad_norm": 0.3241780498562537, + "learning_rate": 9.506564134498887e-06, + "loss": 0.3897, + "step": 3597 + }, + { + "epoch": 0.47947761194029853, + "grad_norm": 0.3028216631797115, + "learning_rate": 9.5062556622057e-06, + "loss": 0.3483, + "step": 3598 + }, + { + "epoch": 0.4796108742004264, + "grad_norm": 0.3219873350694656, + "learning_rate": 9.505947098529563e-06, + "loss": 0.3374, + "step": 3599 + }, + { + "epoch": 0.47974413646055436, + "grad_norm": 0.2938957171196704, + "learning_rate": 9.505638443476729e-06, + "loss": 0.387, + "step": 3600 + }, + { + "epoch": 0.4798773987206823, + "grad_norm": 0.47175902377791296, + "learning_rate": 9.50532969705346e-06, + "loss": 0.4226, + "step": 3601 + }, + { + "epoch": 0.48001066098081024, + "grad_norm": 0.30573630488447057, + "learning_rate": 9.505020859266018e-06, + "loss": 0.4045, + "step": 3602 + }, + { + "epoch": 0.4801439232409382, + "grad_norm": 0.3220289430789326, + "learning_rate": 9.504711930120663e-06, + "loss": 0.4302, + "step": 3603 + }, + { + "epoch": 0.4802771855010661, + "grad_norm": 0.32878876341403107, + "learning_rate": 9.504402909623663e-06, + "loss": 0.4164, + "step": 3604 + }, + { + "epoch": 0.480410447761194, + "grad_norm": 0.3079066375361395, + "learning_rate": 9.504093797781282e-06, + "loss": 0.4032, + "step": 3605 + }, + { + "epoch": 0.48054371002132196, + "grad_norm": 0.2921904806525948, + "learning_rate": 9.50378459459979e-06, + "loss": 0.371, + "step": 3606 + }, + { + "epoch": 0.4806769722814499, + "grad_norm": 0.33222150836521547, + "learning_rate": 9.503475300085458e-06, + "loss": 0.409, + "step": 3607 + }, + { + "epoch": 0.48081023454157784, + "grad_norm": 0.29087068791519555, + "learning_rate": 9.503165914244558e-06, + "loss": 0.3877, + "step": 3608 + }, + { + "epoch": 0.4809434968017058, + "grad_norm": 0.2957733303521565, + "learning_rate": 9.502856437083363e-06, + "loss": 0.4418, + "step": 3609 + }, + { + "epoch": 0.48107675906183367, + "grad_norm": 0.30342107039327465, + "learning_rate": 9.502546868608147e-06, + "loss": 0.4388, + "step": 3610 + }, + { + "epoch": 0.4812100213219616, + "grad_norm": 0.3015673007639056, + "learning_rate": 9.502237208825192e-06, + "loss": 0.359, + "step": 3611 + }, + { + "epoch": 0.48134328358208955, + "grad_norm": 0.2817959525787583, + "learning_rate": 9.501927457740776e-06, + "loss": 0.368, + "step": 3612 + }, + { + "epoch": 0.4814765458422175, + "grad_norm": 0.2892185180249637, + "learning_rate": 9.50161761536118e-06, + "loss": 0.4408, + "step": 3613 + }, + { + "epoch": 0.48160980810234544, + "grad_norm": 0.3040048578002885, + "learning_rate": 9.501307681692686e-06, + "loss": 0.3826, + "step": 3614 + }, + { + "epoch": 0.4817430703624733, + "grad_norm": 0.30087286388905565, + "learning_rate": 9.500997656741583e-06, + "loss": 0.4183, + "step": 3615 + }, + { + "epoch": 0.48187633262260127, + "grad_norm": 0.3015933359647624, + "learning_rate": 9.500687540514155e-06, + "loss": 0.4007, + "step": 3616 + }, + { + "epoch": 0.4820095948827292, + "grad_norm": 0.2969913699270101, + "learning_rate": 9.500377333016692e-06, + "loss": 0.4006, + "step": 3617 + }, + { + "epoch": 0.48214285714285715, + "grad_norm": 5.225027869698489, + "learning_rate": 9.500067034255483e-06, + "loss": 0.4371, + "step": 3618 + }, + { + "epoch": 0.4822761194029851, + "grad_norm": 0.3048650519911186, + "learning_rate": 9.499756644236824e-06, + "loss": 0.4108, + "step": 3619 + }, + { + "epoch": 0.482409381663113, + "grad_norm": 0.31449993046229646, + "learning_rate": 9.499446162967005e-06, + "loss": 0.4129, + "step": 3620 + }, + { + "epoch": 0.4825426439232409, + "grad_norm": 0.3048997560104447, + "learning_rate": 9.499135590452328e-06, + "loss": 0.3695, + "step": 3621 + }, + { + "epoch": 0.48267590618336886, + "grad_norm": 0.29580407263496117, + "learning_rate": 9.498824926699086e-06, + "loss": 0.3652, + "step": 3622 + }, + { + "epoch": 0.4828091684434968, + "grad_norm": 0.3166596240126211, + "learning_rate": 9.498514171713579e-06, + "loss": 0.4313, + "step": 3623 + }, + { + "epoch": 0.48294243070362475, + "grad_norm": 0.29307300116290375, + "learning_rate": 9.498203325502115e-06, + "loss": 0.3743, + "step": 3624 + }, + { + "epoch": 0.4830756929637527, + "grad_norm": 0.29146712597919694, + "learning_rate": 9.49789238807099e-06, + "loss": 0.3983, + "step": 3625 + }, + { + "epoch": 0.4832089552238806, + "grad_norm": 0.3083177050112134, + "learning_rate": 9.497581359426513e-06, + "loss": 0.4227, + "step": 3626 + }, + { + "epoch": 0.4833422174840085, + "grad_norm": 0.2950886061084282, + "learning_rate": 9.497270239574995e-06, + "loss": 0.3507, + "step": 3627 + }, + { + "epoch": 0.48347547974413646, + "grad_norm": 0.3054837766083258, + "learning_rate": 9.496959028522737e-06, + "loss": 0.3691, + "step": 3628 + }, + { + "epoch": 0.4836087420042644, + "grad_norm": 0.29338119297709947, + "learning_rate": 9.496647726276058e-06, + "loss": 0.406, + "step": 3629 + }, + { + "epoch": 0.48374200426439234, + "grad_norm": 0.30101775373164485, + "learning_rate": 9.496336332841266e-06, + "loss": 0.382, + "step": 3630 + }, + { + "epoch": 0.48387526652452023, + "grad_norm": 0.29480722923535246, + "learning_rate": 9.496024848224678e-06, + "loss": 0.3685, + "step": 3631 + }, + { + "epoch": 0.4840085287846482, + "grad_norm": 0.29334031101217267, + "learning_rate": 9.49571327243261e-06, + "loss": 0.3833, + "step": 3632 + }, + { + "epoch": 0.4841417910447761, + "grad_norm": 0.30964230392495984, + "learning_rate": 9.49540160547138e-06, + "loss": 0.4039, + "step": 3633 + }, + { + "epoch": 0.48427505330490406, + "grad_norm": 0.30220515128137326, + "learning_rate": 9.495089847347308e-06, + "loss": 0.3953, + "step": 3634 + }, + { + "epoch": 0.484408315565032, + "grad_norm": 0.3151811637848868, + "learning_rate": 9.49477799806672e-06, + "loss": 0.3905, + "step": 3635 + }, + { + "epoch": 0.48454157782515994, + "grad_norm": 0.3375305369453304, + "learning_rate": 9.494466057635934e-06, + "loss": 0.4964, + "step": 3636 + }, + { + "epoch": 0.48467484008528783, + "grad_norm": 0.3204048637449564, + "learning_rate": 9.49415402606128e-06, + "loss": 0.4265, + "step": 3637 + }, + { + "epoch": 0.48480810234541577, + "grad_norm": 0.2871021023219705, + "learning_rate": 9.493841903349084e-06, + "loss": 0.3576, + "step": 3638 + }, + { + "epoch": 0.4849413646055437, + "grad_norm": 0.3247327919407417, + "learning_rate": 9.493529689505679e-06, + "loss": 0.5562, + "step": 3639 + }, + { + "epoch": 0.48507462686567165, + "grad_norm": 0.30885960120292405, + "learning_rate": 9.49321738453739e-06, + "loss": 0.391, + "step": 3640 + }, + { + "epoch": 0.4852078891257996, + "grad_norm": 0.31616959773371806, + "learning_rate": 9.492904988450557e-06, + "loss": 0.508, + "step": 3641 + }, + { + "epoch": 0.4853411513859275, + "grad_norm": 0.3110596330403686, + "learning_rate": 9.492592501251509e-06, + "loss": 0.4274, + "step": 3642 + }, + { + "epoch": 0.4854744136460554, + "grad_norm": 0.3023919341830144, + "learning_rate": 9.49227992294659e-06, + "loss": 0.388, + "step": 3643 + }, + { + "epoch": 0.48560767590618337, + "grad_norm": 0.3121160733438509, + "learning_rate": 9.491967253542131e-06, + "loss": 0.4697, + "step": 3644 + }, + { + "epoch": 0.4857409381663113, + "grad_norm": 0.29962369561836993, + "learning_rate": 9.49165449304448e-06, + "loss": 0.3868, + "step": 3645 + }, + { + "epoch": 0.48587420042643925, + "grad_norm": 0.3090543299135154, + "learning_rate": 9.491341641459974e-06, + "loss": 0.4592, + "step": 3646 + }, + { + "epoch": 0.48600746268656714, + "grad_norm": 0.31976715587114785, + "learning_rate": 9.491028698794959e-06, + "loss": 0.4281, + "step": 3647 + }, + { + "epoch": 0.4861407249466951, + "grad_norm": 0.31836736997318993, + "learning_rate": 9.490715665055782e-06, + "loss": 0.4365, + "step": 3648 + }, + { + "epoch": 0.486273987206823, + "grad_norm": 0.30818584466950694, + "learning_rate": 9.490402540248791e-06, + "loss": 0.4698, + "step": 3649 + }, + { + "epoch": 0.48640724946695096, + "grad_norm": 0.32675310963912635, + "learning_rate": 9.490089324380336e-06, + "loss": 0.4089, + "step": 3650 + }, + { + "epoch": 0.4865405117270789, + "grad_norm": 0.3070234158674327, + "learning_rate": 9.48977601745677e-06, + "loss": 0.4276, + "step": 3651 + }, + { + "epoch": 0.48667377398720685, + "grad_norm": 0.3055314063788205, + "learning_rate": 9.489462619484441e-06, + "loss": 0.3909, + "step": 3652 + }, + { + "epoch": 0.48680703624733473, + "grad_norm": 0.3319729438396959, + "learning_rate": 9.48914913046971e-06, + "loss": 0.4157, + "step": 3653 + }, + { + "epoch": 0.4869402985074627, + "grad_norm": 0.31950194009320143, + "learning_rate": 9.488835550418933e-06, + "loss": 0.3907, + "step": 3654 + }, + { + "epoch": 0.4870735607675906, + "grad_norm": 0.313137198288136, + "learning_rate": 9.488521879338469e-06, + "loss": 0.387, + "step": 3655 + }, + { + "epoch": 0.48720682302771856, + "grad_norm": 0.318571514834879, + "learning_rate": 9.488208117234678e-06, + "loss": 0.3891, + "step": 3656 + }, + { + "epoch": 0.4873400852878465, + "grad_norm": 0.29667292139854734, + "learning_rate": 9.487894264113924e-06, + "loss": 0.3953, + "step": 3657 + }, + { + "epoch": 0.4874733475479744, + "grad_norm": 0.32416680308280305, + "learning_rate": 9.48758031998257e-06, + "loss": 0.5889, + "step": 3658 + }, + { + "epoch": 0.48760660980810233, + "grad_norm": 0.3257859074067119, + "learning_rate": 9.487266284846985e-06, + "loss": 0.4142, + "step": 3659 + }, + { + "epoch": 0.4877398720682303, + "grad_norm": 0.30752551867638195, + "learning_rate": 9.486952158713537e-06, + "loss": 0.4849, + "step": 3660 + }, + { + "epoch": 0.4878731343283582, + "grad_norm": 0.33457154601517514, + "learning_rate": 9.486637941588593e-06, + "loss": 0.4348, + "step": 3661 + }, + { + "epoch": 0.48800639658848616, + "grad_norm": 0.29815089582637105, + "learning_rate": 9.486323633478529e-06, + "loss": 0.3853, + "step": 3662 + }, + { + "epoch": 0.4881396588486141, + "grad_norm": 0.32372407374454715, + "learning_rate": 9.486009234389717e-06, + "loss": 0.4272, + "step": 3663 + }, + { + "epoch": 0.488272921108742, + "grad_norm": 0.31634727567132603, + "learning_rate": 9.485694744328534e-06, + "loss": 0.3852, + "step": 3664 + }, + { + "epoch": 0.48840618336886993, + "grad_norm": 0.3015847762366042, + "learning_rate": 9.485380163301355e-06, + "loss": 0.471, + "step": 3665 + }, + { + "epoch": 0.48853944562899787, + "grad_norm": 0.32427029772323196, + "learning_rate": 9.48506549131456e-06, + "loss": 0.4263, + "step": 3666 + }, + { + "epoch": 0.4886727078891258, + "grad_norm": 0.325810522742853, + "learning_rate": 9.484750728374532e-06, + "loss": 0.3487, + "step": 3667 + }, + { + "epoch": 0.48880597014925375, + "grad_norm": 0.30291380939764334, + "learning_rate": 9.484435874487654e-06, + "loss": 0.4494, + "step": 3668 + }, + { + "epoch": 0.48893923240938164, + "grad_norm": 0.2921857640110884, + "learning_rate": 9.484120929660311e-06, + "loss": 0.3733, + "step": 3669 + }, + { + "epoch": 0.4890724946695096, + "grad_norm": 0.3175883767485715, + "learning_rate": 9.483805893898888e-06, + "loss": 0.4512, + "step": 3670 + }, + { + "epoch": 0.4892057569296375, + "grad_norm": 0.2903357359009746, + "learning_rate": 9.483490767209776e-06, + "loss": 0.4791, + "step": 3671 + }, + { + "epoch": 0.48933901918976547, + "grad_norm": 0.3136001990527624, + "learning_rate": 9.483175549599363e-06, + "loss": 0.576, + "step": 3672 + }, + { + "epoch": 0.4894722814498934, + "grad_norm": 0.2946899307360831, + "learning_rate": 9.482860241074043e-06, + "loss": 0.3288, + "step": 3673 + }, + { + "epoch": 0.4896055437100213, + "grad_norm": 0.2936223776622006, + "learning_rate": 9.482544841640212e-06, + "loss": 0.4145, + "step": 3674 + }, + { + "epoch": 0.48973880597014924, + "grad_norm": 0.34404609585441404, + "learning_rate": 9.48222935130426e-06, + "loss": 0.3665, + "step": 3675 + }, + { + "epoch": 0.4898720682302772, + "grad_norm": 0.29958339916540694, + "learning_rate": 9.481913770072591e-06, + "loss": 0.3794, + "step": 3676 + }, + { + "epoch": 0.4900053304904051, + "grad_norm": 0.2823440732396056, + "learning_rate": 9.481598097951604e-06, + "loss": 0.3483, + "step": 3677 + }, + { + "epoch": 0.49013859275053306, + "grad_norm": 0.3019403203089761, + "learning_rate": 9.481282334947698e-06, + "loss": 0.4043, + "step": 3678 + }, + { + "epoch": 0.490271855010661, + "grad_norm": 0.2988022945496719, + "learning_rate": 9.480966481067275e-06, + "loss": 0.4166, + "step": 3679 + }, + { + "epoch": 0.4904051172707889, + "grad_norm": 0.3172735472640967, + "learning_rate": 9.480650536316744e-06, + "loss": 0.3994, + "step": 3680 + }, + { + "epoch": 0.49053837953091683, + "grad_norm": 0.3087791032485042, + "learning_rate": 9.480334500702511e-06, + "loss": 0.4313, + "step": 3681 + }, + { + "epoch": 0.4906716417910448, + "grad_norm": 0.3066046475933907, + "learning_rate": 9.480018374230984e-06, + "loss": 0.435, + "step": 3682 + }, + { + "epoch": 0.4908049040511727, + "grad_norm": 0.3090185464879969, + "learning_rate": 9.479702156908575e-06, + "loss": 0.4781, + "step": 3683 + }, + { + "epoch": 0.49093816631130066, + "grad_norm": 0.3065852254902929, + "learning_rate": 9.479385848741697e-06, + "loss": 0.4125, + "step": 3684 + }, + { + "epoch": 0.49107142857142855, + "grad_norm": 0.28881330181192627, + "learning_rate": 9.479069449736762e-06, + "loss": 0.3802, + "step": 3685 + }, + { + "epoch": 0.4912046908315565, + "grad_norm": 0.32750137347451785, + "learning_rate": 9.478752959900188e-06, + "loss": 0.4605, + "step": 3686 + }, + { + "epoch": 0.49133795309168443, + "grad_norm": 0.31100311564753247, + "learning_rate": 9.478436379238395e-06, + "loss": 0.5068, + "step": 3687 + }, + { + "epoch": 0.4914712153518124, + "grad_norm": 0.2926222161049701, + "learning_rate": 9.478119707757798e-06, + "loss": 0.3749, + "step": 3688 + }, + { + "epoch": 0.4916044776119403, + "grad_norm": 0.304482762938606, + "learning_rate": 9.477802945464823e-06, + "loss": 0.3911, + "step": 3689 + }, + { + "epoch": 0.49173773987206826, + "grad_norm": 0.291003711854089, + "learning_rate": 9.477486092365892e-06, + "loss": 0.3445, + "step": 3690 + }, + { + "epoch": 0.49187100213219614, + "grad_norm": 0.2870763995906838, + "learning_rate": 9.477169148467432e-06, + "loss": 0.4031, + "step": 3691 + }, + { + "epoch": 0.4920042643923241, + "grad_norm": 0.30280891220807177, + "learning_rate": 9.476852113775869e-06, + "loss": 0.6213, + "step": 3692 + }, + { + "epoch": 0.49213752665245203, + "grad_norm": 0.2973384980965891, + "learning_rate": 9.476534988297632e-06, + "loss": 0.363, + "step": 3693 + }, + { + "epoch": 0.49227078891257997, + "grad_norm": 0.3044451755146986, + "learning_rate": 9.476217772039153e-06, + "loss": 0.4557, + "step": 3694 + }, + { + "epoch": 0.4924040511727079, + "grad_norm": 0.3068068427776947, + "learning_rate": 9.475900465006863e-06, + "loss": 0.4046, + "step": 3695 + }, + { + "epoch": 0.4925373134328358, + "grad_norm": 0.31323466743094586, + "learning_rate": 9.475583067207199e-06, + "loss": 0.4207, + "step": 3696 + }, + { + "epoch": 0.49267057569296374, + "grad_norm": 0.32281533176728605, + "learning_rate": 9.475265578646597e-06, + "loss": 0.4503, + "step": 3697 + }, + { + "epoch": 0.4928038379530917, + "grad_norm": 0.3145173653562003, + "learning_rate": 9.474947999331494e-06, + "loss": 0.4515, + "step": 3698 + }, + { + "epoch": 0.4929371002132196, + "grad_norm": 0.31351080330995834, + "learning_rate": 9.474630329268332e-06, + "loss": 0.3927, + "step": 3699 + }, + { + "epoch": 0.49307036247334757, + "grad_norm": 0.31360197065231077, + "learning_rate": 9.474312568463551e-06, + "loss": 0.4157, + "step": 3700 + }, + { + "epoch": 0.49320362473347545, + "grad_norm": 0.30302696537137414, + "learning_rate": 9.473994716923597e-06, + "loss": 0.4252, + "step": 3701 + }, + { + "epoch": 0.4933368869936034, + "grad_norm": 0.33065378908764487, + "learning_rate": 9.473676774654917e-06, + "loss": 0.5175, + "step": 3702 + }, + { + "epoch": 0.49347014925373134, + "grad_norm": 0.29353420770334454, + "learning_rate": 9.473358741663954e-06, + "loss": 0.4587, + "step": 3703 + }, + { + "epoch": 0.4936034115138593, + "grad_norm": 0.322202366116927, + "learning_rate": 9.47304061795716e-06, + "loss": 0.4157, + "step": 3704 + }, + { + "epoch": 0.4937366737739872, + "grad_norm": 0.3322981136440845, + "learning_rate": 9.472722403540989e-06, + "loss": 0.5044, + "step": 3705 + }, + { + "epoch": 0.49386993603411516, + "grad_norm": 0.3056143854837829, + "learning_rate": 9.472404098421888e-06, + "loss": 0.4293, + "step": 3706 + }, + { + "epoch": 0.49400319829424305, + "grad_norm": 0.3184500801918459, + "learning_rate": 9.472085702606318e-06, + "loss": 0.3942, + "step": 3707 + }, + { + "epoch": 0.494136460554371, + "grad_norm": 0.30269950447518756, + "learning_rate": 9.471767216100732e-06, + "loss": 0.3798, + "step": 3708 + }, + { + "epoch": 0.49426972281449894, + "grad_norm": 0.32329336511839923, + "learning_rate": 9.471448638911589e-06, + "loss": 0.4885, + "step": 3709 + }, + { + "epoch": 0.4944029850746269, + "grad_norm": 0.2937299848611595, + "learning_rate": 9.47112997104535e-06, + "loss": 0.3697, + "step": 3710 + }, + { + "epoch": 0.4945362473347548, + "grad_norm": 0.29689107951740856, + "learning_rate": 9.47081121250848e-06, + "loss": 0.3648, + "step": 3711 + }, + { + "epoch": 0.4946695095948827, + "grad_norm": 0.289240754612723, + "learning_rate": 9.470492363307437e-06, + "loss": 0.4615, + "step": 3712 + }, + { + "epoch": 0.49480277185501065, + "grad_norm": 0.29872317892619116, + "learning_rate": 9.470173423448695e-06, + "loss": 0.4155, + "step": 3713 + }, + { + "epoch": 0.4949360341151386, + "grad_norm": 0.29890214446340707, + "learning_rate": 9.469854392938713e-06, + "loss": 0.3797, + "step": 3714 + }, + { + "epoch": 0.49506929637526653, + "grad_norm": 0.29386509426934165, + "learning_rate": 9.469535271783969e-06, + "loss": 0.3981, + "step": 3715 + }, + { + "epoch": 0.4952025586353945, + "grad_norm": 0.2820083475211163, + "learning_rate": 9.469216059990928e-06, + "loss": 0.3844, + "step": 3716 + }, + { + "epoch": 0.49533582089552236, + "grad_norm": 0.2868858703535895, + "learning_rate": 9.468896757566067e-06, + "loss": 0.3824, + "step": 3717 + }, + { + "epoch": 0.4954690831556503, + "grad_norm": 0.29308846184594595, + "learning_rate": 9.46857736451586e-06, + "loss": 0.4278, + "step": 3718 + }, + { + "epoch": 0.49560234541577824, + "grad_norm": 0.28575442604527573, + "learning_rate": 9.468257880846785e-06, + "loss": 0.3447, + "step": 3719 + }, + { + "epoch": 0.4957356076759062, + "grad_norm": 0.28861234502469274, + "learning_rate": 9.467938306565319e-06, + "loss": 0.393, + "step": 3720 + }, + { + "epoch": 0.49586886993603413, + "grad_norm": 0.35396789283746527, + "learning_rate": 9.467618641677944e-06, + "loss": 0.4255, + "step": 3721 + }, + { + "epoch": 0.49600213219616207, + "grad_norm": 0.29389778783299625, + "learning_rate": 9.467298886191143e-06, + "loss": 0.4224, + "step": 3722 + }, + { + "epoch": 0.49613539445628996, + "grad_norm": 0.30288955367867604, + "learning_rate": 9.466979040111398e-06, + "loss": 0.4081, + "step": 3723 + }, + { + "epoch": 0.4962686567164179, + "grad_norm": 0.29180685091622316, + "learning_rate": 9.466659103445198e-06, + "loss": 0.3752, + "step": 3724 + }, + { + "epoch": 0.49640191897654584, + "grad_norm": 0.30132071171976, + "learning_rate": 9.46633907619903e-06, + "loss": 0.4462, + "step": 3725 + }, + { + "epoch": 0.4965351812366738, + "grad_norm": 0.3172255473883409, + "learning_rate": 9.466018958379382e-06, + "loss": 0.4317, + "step": 3726 + }, + { + "epoch": 0.4966684434968017, + "grad_norm": 0.2932209792623189, + "learning_rate": 9.46569874999275e-06, + "loss": 0.4045, + "step": 3727 + }, + { + "epoch": 0.4968017057569296, + "grad_norm": 0.31502713972901386, + "learning_rate": 9.465378451045624e-06, + "loss": 0.3781, + "step": 3728 + }, + { + "epoch": 0.49693496801705755, + "grad_norm": 0.3099911794305886, + "learning_rate": 9.4650580615445e-06, + "loss": 0.4628, + "step": 3729 + }, + { + "epoch": 0.4970682302771855, + "grad_norm": 0.30619345621926203, + "learning_rate": 9.464737581495876e-06, + "loss": 0.3649, + "step": 3730 + }, + { + "epoch": 0.49720149253731344, + "grad_norm": 0.3235196370808332, + "learning_rate": 9.464417010906249e-06, + "loss": 0.4605, + "step": 3731 + }, + { + "epoch": 0.4973347547974414, + "grad_norm": 0.30271800853917485, + "learning_rate": 9.464096349782122e-06, + "loss": 0.4023, + "step": 3732 + }, + { + "epoch": 0.4974680170575693, + "grad_norm": 0.29970379899472704, + "learning_rate": 9.463775598129999e-06, + "loss": 0.5486, + "step": 3733 + }, + { + "epoch": 0.4976012793176972, + "grad_norm": 0.3097097896353313, + "learning_rate": 9.463454755956381e-06, + "loss": 0.3916, + "step": 3734 + }, + { + "epoch": 0.49773454157782515, + "grad_norm": 0.29813274536043516, + "learning_rate": 9.463133823267779e-06, + "loss": 0.4425, + "step": 3735 + }, + { + "epoch": 0.4978678038379531, + "grad_norm": 0.298543550999318, + "learning_rate": 9.462812800070696e-06, + "loss": 0.3676, + "step": 3736 + }, + { + "epoch": 0.49800106609808104, + "grad_norm": 0.30055815984448986, + "learning_rate": 9.462491686371644e-06, + "loss": 0.4035, + "step": 3737 + }, + { + "epoch": 0.498134328358209, + "grad_norm": 0.30321446293629545, + "learning_rate": 9.462170482177138e-06, + "loss": 0.4022, + "step": 3738 + }, + { + "epoch": 0.49826759061833686, + "grad_norm": 0.3096883487902814, + "learning_rate": 9.461849187493686e-06, + "loss": 0.4732, + "step": 3739 + }, + { + "epoch": 0.4984008528784648, + "grad_norm": 0.32165268567015326, + "learning_rate": 9.461527802327808e-06, + "loss": 0.428, + "step": 3740 + }, + { + "epoch": 0.49853411513859275, + "grad_norm": 0.29533043411937515, + "learning_rate": 9.461206326686022e-06, + "loss": 0.3951, + "step": 3741 + }, + { + "epoch": 0.4986673773987207, + "grad_norm": 0.3133127682699611, + "learning_rate": 9.460884760574845e-06, + "loss": 0.4291, + "step": 3742 + }, + { + "epoch": 0.49880063965884863, + "grad_norm": 0.3326766030381267, + "learning_rate": 9.460563104000797e-06, + "loss": 0.643, + "step": 3743 + }, + { + "epoch": 0.4989339019189765, + "grad_norm": 0.3142658912675116, + "learning_rate": 9.460241356970403e-06, + "loss": 0.4827, + "step": 3744 + }, + { + "epoch": 0.49906716417910446, + "grad_norm": 0.2958528823479575, + "learning_rate": 9.459919519490186e-06, + "loss": 0.4041, + "step": 3745 + }, + { + "epoch": 0.4992004264392324, + "grad_norm": 0.28824281301756616, + "learning_rate": 9.459597591566675e-06, + "loss": 0.5012, + "step": 3746 + }, + { + "epoch": 0.49933368869936035, + "grad_norm": 0.28681308395258626, + "learning_rate": 9.459275573206397e-06, + "loss": 0.3611, + "step": 3747 + }, + { + "epoch": 0.4994669509594883, + "grad_norm": 0.30497671273123406, + "learning_rate": 9.458953464415883e-06, + "loss": 0.3841, + "step": 3748 + }, + { + "epoch": 0.49960021321961623, + "grad_norm": 0.29970251400986, + "learning_rate": 9.458631265201663e-06, + "loss": 0.4423, + "step": 3749 + }, + { + "epoch": 0.4997334754797441, + "grad_norm": 0.2992899738759635, + "learning_rate": 9.458308975570274e-06, + "loss": 0.3989, + "step": 3750 + }, + { + "epoch": 0.49986673773987206, + "grad_norm": 0.3115292462382761, + "learning_rate": 9.45798659552825e-06, + "loss": 0.389, + "step": 3751 + }, + { + "epoch": 0.5, + "grad_norm": 0.2885428470156356, + "learning_rate": 9.457664125082129e-06, + "loss": 0.3683, + "step": 3752 + }, + { + "epoch": 0.5001332622601279, + "grad_norm": 0.31719957368909646, + "learning_rate": 9.457341564238449e-06, + "loss": 0.4325, + "step": 3753 + }, + { + "epoch": 0.5002665245202559, + "grad_norm": 0.3298052109858013, + "learning_rate": 9.457018913003753e-06, + "loss": 0.4086, + "step": 3754 + }, + { + "epoch": 0.5003997867803838, + "grad_norm": 0.2996525018598632, + "learning_rate": 9.456696171384584e-06, + "loss": 0.3695, + "step": 3755 + }, + { + "epoch": 0.5005330490405118, + "grad_norm": 0.3059495041506234, + "learning_rate": 9.456373339387485e-06, + "loss": 0.3578, + "step": 3756 + }, + { + "epoch": 0.5006663113006397, + "grad_norm": 0.29959161446390536, + "learning_rate": 9.456050417019007e-06, + "loss": 0.4384, + "step": 3757 + }, + { + "epoch": 0.5007995735607675, + "grad_norm": 0.2964490843727657, + "learning_rate": 9.455727404285692e-06, + "loss": 0.4157, + "step": 3758 + }, + { + "epoch": 0.5009328358208955, + "grad_norm": 0.28945084304494145, + "learning_rate": 9.455404301194098e-06, + "loss": 0.4044, + "step": 3759 + }, + { + "epoch": 0.5010660980810234, + "grad_norm": 0.30442022193693935, + "learning_rate": 9.455081107750772e-06, + "loss": 0.4484, + "step": 3760 + }, + { + "epoch": 0.5011993603411514, + "grad_norm": 0.2856373265123475, + "learning_rate": 9.454757823962269e-06, + "loss": 0.5154, + "step": 3761 + }, + { + "epoch": 0.5013326226012793, + "grad_norm": 0.3081525269200153, + "learning_rate": 9.454434449835144e-06, + "loss": 0.4426, + "step": 3762 + }, + { + "epoch": 0.5014658848614072, + "grad_norm": 0.2883649816890939, + "learning_rate": 9.454110985375959e-06, + "loss": 0.435, + "step": 3763 + }, + { + "epoch": 0.5015991471215352, + "grad_norm": 0.32530252925206693, + "learning_rate": 9.45378743059127e-06, + "loss": 0.4245, + "step": 3764 + }, + { + "epoch": 0.5017324093816631, + "grad_norm": 0.2969841031396913, + "learning_rate": 9.453463785487637e-06, + "loss": 0.3775, + "step": 3765 + }, + { + "epoch": 0.5018656716417911, + "grad_norm": 0.3251908863174161, + "learning_rate": 9.453140050071628e-06, + "loss": 0.4443, + "step": 3766 + }, + { + "epoch": 0.501998933901919, + "grad_norm": 0.30064994138226825, + "learning_rate": 9.452816224349806e-06, + "loss": 0.4519, + "step": 3767 + }, + { + "epoch": 0.502132196162047, + "grad_norm": 0.2964958092827214, + "learning_rate": 9.452492308328735e-06, + "loss": 0.4545, + "step": 3768 + }, + { + "epoch": 0.5022654584221748, + "grad_norm": 0.30390854339853235, + "learning_rate": 9.452168302014988e-06, + "loss": 0.3877, + "step": 3769 + }, + { + "epoch": 0.5023987206823027, + "grad_norm": 0.30841804982355553, + "learning_rate": 9.451844205415133e-06, + "loss": 0.3919, + "step": 3770 + }, + { + "epoch": 0.5025319829424307, + "grad_norm": 0.2951257011116944, + "learning_rate": 9.451520018535743e-06, + "loss": 0.389, + "step": 3771 + }, + { + "epoch": 0.5026652452025586, + "grad_norm": 0.28377678272321794, + "learning_rate": 9.451195741383392e-06, + "loss": 0.3622, + "step": 3772 + }, + { + "epoch": 0.5027985074626866, + "grad_norm": 0.29977281478935663, + "learning_rate": 9.450871373964657e-06, + "loss": 0.468, + "step": 3773 + }, + { + "epoch": 0.5029317697228145, + "grad_norm": 0.2940838625139021, + "learning_rate": 9.450546916286117e-06, + "loss": 0.4031, + "step": 3774 + }, + { + "epoch": 0.5030650319829424, + "grad_norm": 0.2885464362701278, + "learning_rate": 9.450222368354347e-06, + "loss": 0.3839, + "step": 3775 + }, + { + "epoch": 0.5031982942430704, + "grad_norm": 0.3083661381009217, + "learning_rate": 9.449897730175932e-06, + "loss": 0.404, + "step": 3776 + }, + { + "epoch": 0.5033315565031983, + "grad_norm": 0.5615173757872923, + "learning_rate": 9.449573001757456e-06, + "loss": 0.4404, + "step": 3777 + }, + { + "epoch": 0.5034648187633263, + "grad_norm": 0.30240866358031293, + "learning_rate": 9.449248183105503e-06, + "loss": 0.4139, + "step": 3778 + }, + { + "epoch": 0.5035980810234542, + "grad_norm": 0.3029838987432406, + "learning_rate": 9.44892327422666e-06, + "loss": 0.4081, + "step": 3779 + }, + { + "epoch": 0.503731343283582, + "grad_norm": 0.29489296407968335, + "learning_rate": 9.448598275127517e-06, + "loss": 0.4658, + "step": 3780 + }, + { + "epoch": 0.50386460554371, + "grad_norm": 0.2976856680027763, + "learning_rate": 9.448273185814663e-06, + "loss": 0.3885, + "step": 3781 + }, + { + "epoch": 0.5039978678038379, + "grad_norm": 0.29713302124808316, + "learning_rate": 9.447948006294691e-06, + "loss": 0.4079, + "step": 3782 + }, + { + "epoch": 0.5041311300639659, + "grad_norm": 0.29735023100011326, + "learning_rate": 9.447622736574195e-06, + "loss": 0.4326, + "step": 3783 + }, + { + "epoch": 0.5042643923240938, + "grad_norm": 0.2989461603310716, + "learning_rate": 9.447297376659772e-06, + "loss": 0.4288, + "step": 3784 + }, + { + "epoch": 0.5043976545842217, + "grad_norm": 0.278539293173464, + "learning_rate": 9.446971926558021e-06, + "loss": 0.4437, + "step": 3785 + }, + { + "epoch": 0.5045309168443497, + "grad_norm": 0.2912782874233409, + "learning_rate": 9.44664638627554e-06, + "loss": 0.4012, + "step": 3786 + }, + { + "epoch": 0.5046641791044776, + "grad_norm": 0.3044945325541919, + "learning_rate": 9.446320755818931e-06, + "loss": 0.5326, + "step": 3787 + }, + { + "epoch": 0.5047974413646056, + "grad_norm": 0.31919279589227373, + "learning_rate": 9.445995035194799e-06, + "loss": 0.386, + "step": 3788 + }, + { + "epoch": 0.5049307036247335, + "grad_norm": 0.2946600048397472, + "learning_rate": 9.445669224409748e-06, + "loss": 0.3914, + "step": 3789 + }, + { + "epoch": 0.5050639658848614, + "grad_norm": 0.29362284457619525, + "learning_rate": 9.445343323470383e-06, + "loss": 0.3839, + "step": 3790 + }, + { + "epoch": 0.5051972281449894, + "grad_norm": 0.30087988784383046, + "learning_rate": 9.44501733238332e-06, + "loss": 0.3741, + "step": 3791 + }, + { + "epoch": 0.5053304904051172, + "grad_norm": 0.3001081909233907, + "learning_rate": 9.444691251155162e-06, + "loss": 0.44, + "step": 3792 + }, + { + "epoch": 0.5054637526652452, + "grad_norm": 0.32256342793581977, + "learning_rate": 9.444365079792526e-06, + "loss": 0.4356, + "step": 3793 + }, + { + "epoch": 0.5055970149253731, + "grad_norm": 0.30254545067832367, + "learning_rate": 9.444038818302024e-06, + "loss": 0.4776, + "step": 3794 + }, + { + "epoch": 0.5057302771855011, + "grad_norm": 0.3071747270398943, + "learning_rate": 9.443712466690273e-06, + "loss": 0.4417, + "step": 3795 + }, + { + "epoch": 0.505863539445629, + "grad_norm": 0.31146128676551016, + "learning_rate": 9.443386024963894e-06, + "loss": 0.3818, + "step": 3796 + }, + { + "epoch": 0.5059968017057569, + "grad_norm": 0.30050335812993406, + "learning_rate": 9.443059493129503e-06, + "loss": 0.3829, + "step": 3797 + }, + { + "epoch": 0.5061300639658849, + "grad_norm": 0.3036348078817961, + "learning_rate": 9.442732871193725e-06, + "loss": 0.4828, + "step": 3798 + }, + { + "epoch": 0.5062633262260128, + "grad_norm": 0.32777579318000805, + "learning_rate": 9.44240615916318e-06, + "loss": 0.4646, + "step": 3799 + }, + { + "epoch": 0.5063965884861408, + "grad_norm": 0.2969683808569435, + "learning_rate": 9.442079357044497e-06, + "loss": 0.4085, + "step": 3800 + }, + { + "epoch": 0.5065298507462687, + "grad_norm": 0.29308510538825006, + "learning_rate": 9.4417524648443e-06, + "loss": 0.4157, + "step": 3801 + }, + { + "epoch": 0.5066631130063965, + "grad_norm": 0.32488005166123224, + "learning_rate": 9.441425482569221e-06, + "loss": 0.4781, + "step": 3802 + }, + { + "epoch": 0.5067963752665245, + "grad_norm": 0.3078269637017965, + "learning_rate": 9.441098410225891e-06, + "loss": 0.3885, + "step": 3803 + }, + { + "epoch": 0.5069296375266524, + "grad_norm": 0.3387329788701014, + "learning_rate": 9.44077124782094e-06, + "loss": 0.4267, + "step": 3804 + }, + { + "epoch": 0.5070628997867804, + "grad_norm": 0.30286383813594453, + "learning_rate": 9.440443995361004e-06, + "loss": 0.3409, + "step": 3805 + }, + { + "epoch": 0.5071961620469083, + "grad_norm": 0.304859464306483, + "learning_rate": 9.440116652852721e-06, + "loss": 0.4848, + "step": 3806 + }, + { + "epoch": 0.5073294243070362, + "grad_norm": 0.31630589392543484, + "learning_rate": 9.439789220302726e-06, + "loss": 0.4142, + "step": 3807 + }, + { + "epoch": 0.5074626865671642, + "grad_norm": 0.2947857161184157, + "learning_rate": 9.439461697717663e-06, + "loss": 0.4012, + "step": 3808 + }, + { + "epoch": 0.5075959488272921, + "grad_norm": 0.29923157605123735, + "learning_rate": 9.439134085104169e-06, + "loss": 0.4422, + "step": 3809 + }, + { + "epoch": 0.5077292110874201, + "grad_norm": 0.3161459202914652, + "learning_rate": 9.438806382468891e-06, + "loss": 0.3821, + "step": 3810 + }, + { + "epoch": 0.507862473347548, + "grad_norm": 0.3040461318173592, + "learning_rate": 9.438478589818473e-06, + "loss": 0.445, + "step": 3811 + }, + { + "epoch": 0.5079957356076759, + "grad_norm": 0.31650485490249364, + "learning_rate": 9.438150707159566e-06, + "loss": 0.4925, + "step": 3812 + }, + { + "epoch": 0.5081289978678039, + "grad_norm": 0.2954940215792081, + "learning_rate": 9.437822734498814e-06, + "loss": 0.393, + "step": 3813 + }, + { + "epoch": 0.5082622601279317, + "grad_norm": 0.33108629199965695, + "learning_rate": 9.437494671842872e-06, + "loss": 0.4414, + "step": 3814 + }, + { + "epoch": 0.5083955223880597, + "grad_norm": 0.2970350383829398, + "learning_rate": 9.437166519198391e-06, + "loss": 0.4021, + "step": 3815 + }, + { + "epoch": 0.5085287846481876, + "grad_norm": 0.2951057777451278, + "learning_rate": 9.436838276572024e-06, + "loss": 0.3299, + "step": 3816 + }, + { + "epoch": 0.5086620469083155, + "grad_norm": 0.31936421968550516, + "learning_rate": 9.436509943970432e-06, + "loss": 0.3879, + "step": 3817 + }, + { + "epoch": 0.5087953091684435, + "grad_norm": 0.3301334315441213, + "learning_rate": 9.436181521400268e-06, + "loss": 0.4291, + "step": 3818 + }, + { + "epoch": 0.5089285714285714, + "grad_norm": 0.29452201832569574, + "learning_rate": 9.435853008868195e-06, + "loss": 0.423, + "step": 3819 + }, + { + "epoch": 0.5090618336886994, + "grad_norm": 0.29825216728737236, + "learning_rate": 9.435524406380875e-06, + "loss": 0.4308, + "step": 3820 + }, + { + "epoch": 0.5091950959488273, + "grad_norm": 0.3141261438758251, + "learning_rate": 9.435195713944973e-06, + "loss": 0.3987, + "step": 3821 + }, + { + "epoch": 0.5093283582089553, + "grad_norm": 0.32401208371569057, + "learning_rate": 9.434866931567151e-06, + "loss": 0.4574, + "step": 3822 + }, + { + "epoch": 0.5094616204690832, + "grad_norm": 0.31405166854552186, + "learning_rate": 9.43453805925408e-06, + "loss": 0.4025, + "step": 3823 + }, + { + "epoch": 0.509594882729211, + "grad_norm": 0.32672520280237316, + "learning_rate": 9.434209097012428e-06, + "loss": 0.4241, + "step": 3824 + }, + { + "epoch": 0.509728144989339, + "grad_norm": 0.2921385117590517, + "learning_rate": 9.433880044848865e-06, + "loss": 0.4331, + "step": 3825 + }, + { + "epoch": 0.5098614072494669, + "grad_norm": 113.53717965678437, + "learning_rate": 9.433550902770064e-06, + "loss": 0.4039, + "step": 3826 + }, + { + "epoch": 0.5099946695095949, + "grad_norm": 0.3706729519816535, + "learning_rate": 9.433221670782701e-06, + "loss": 0.3468, + "step": 3827 + }, + { + "epoch": 0.5101279317697228, + "grad_norm": 0.30807942037822783, + "learning_rate": 9.432892348893453e-06, + "loss": 0.4127, + "step": 3828 + }, + { + "epoch": 0.5102611940298507, + "grad_norm": 0.3634078481318686, + "learning_rate": 9.432562937108995e-06, + "loss": 0.5601, + "step": 3829 + }, + { + "epoch": 0.5103944562899787, + "grad_norm": 0.3111918114608444, + "learning_rate": 9.43223343543601e-06, + "loss": 0.3629, + "step": 3830 + }, + { + "epoch": 0.5105277185501066, + "grad_norm": 0.3101039352616341, + "learning_rate": 9.431903843881182e-06, + "loss": 0.4236, + "step": 3831 + }, + { + "epoch": 0.5106609808102346, + "grad_norm": 0.350178104095906, + "learning_rate": 9.43157416245119e-06, + "loss": 0.3811, + "step": 3832 + }, + { + "epoch": 0.5107942430703625, + "grad_norm": 0.30993605570901067, + "learning_rate": 9.431244391152723e-06, + "loss": 0.3987, + "step": 3833 + }, + { + "epoch": 0.5109275053304904, + "grad_norm": 0.3307352668625462, + "learning_rate": 9.430914529992467e-06, + "loss": 0.3951, + "step": 3834 + }, + { + "epoch": 0.5110607675906184, + "grad_norm": 0.31309744136266415, + "learning_rate": 9.430584578977112e-06, + "loss": 0.3547, + "step": 3835 + }, + { + "epoch": 0.5111940298507462, + "grad_norm": 0.31872022123402244, + "learning_rate": 9.430254538113348e-06, + "loss": 0.394, + "step": 3836 + }, + { + "epoch": 0.5113272921108742, + "grad_norm": 0.32231999686067014, + "learning_rate": 9.42992440740787e-06, + "loss": 0.4111, + "step": 3837 + }, + { + "epoch": 0.5114605543710021, + "grad_norm": 0.3339083421796603, + "learning_rate": 9.429594186867371e-06, + "loss": 0.362, + "step": 3838 + }, + { + "epoch": 0.51159381663113, + "grad_norm": 0.35107865654090903, + "learning_rate": 9.429263876498549e-06, + "loss": 0.4899, + "step": 3839 + }, + { + "epoch": 0.511727078891258, + "grad_norm": 0.30656102187573825, + "learning_rate": 9.428933476308101e-06, + "loss": 0.378, + "step": 3840 + }, + { + "epoch": 0.5118603411513859, + "grad_norm": 0.31363600008494064, + "learning_rate": 9.428602986302726e-06, + "loss": 0.3706, + "step": 3841 + }, + { + "epoch": 0.5119936034115139, + "grad_norm": 0.3252100444394991, + "learning_rate": 9.42827240648913e-06, + "loss": 0.4551, + "step": 3842 + }, + { + "epoch": 0.5121268656716418, + "grad_norm": 0.31918620865846165, + "learning_rate": 9.427941736874016e-06, + "loss": 0.4368, + "step": 3843 + }, + { + "epoch": 0.5122601279317697, + "grad_norm": 0.3217861268138169, + "learning_rate": 9.427610977464085e-06, + "loss": 0.3717, + "step": 3844 + }, + { + "epoch": 0.5123933901918977, + "grad_norm": 0.324908004420512, + "learning_rate": 9.427280128266049e-06, + "loss": 0.3839, + "step": 3845 + }, + { + "epoch": 0.5125266524520256, + "grad_norm": 0.3030046191668241, + "learning_rate": 9.426949189286619e-06, + "loss": 0.4122, + "step": 3846 + }, + { + "epoch": 0.5126599147121536, + "grad_norm": 0.3344102566361503, + "learning_rate": 9.4266181605325e-06, + "loss": 0.3984, + "step": 3847 + }, + { + "epoch": 0.5127931769722814, + "grad_norm": 0.36726742839602855, + "learning_rate": 9.426287042010411e-06, + "loss": 0.4442, + "step": 3848 + }, + { + "epoch": 0.5129264392324094, + "grad_norm": 0.3180763527347732, + "learning_rate": 9.425955833727062e-06, + "loss": 0.4134, + "step": 3849 + }, + { + "epoch": 0.5130597014925373, + "grad_norm": 0.3102809872689804, + "learning_rate": 9.425624535689173e-06, + "loss": 0.3578, + "step": 3850 + }, + { + "epoch": 0.5131929637526652, + "grad_norm": 0.3201016066988559, + "learning_rate": 9.42529314790346e-06, + "loss": 0.5577, + "step": 3851 + }, + { + "epoch": 0.5133262260127932, + "grad_norm": 0.3129508758514857, + "learning_rate": 9.424961670376647e-06, + "loss": 0.3906, + "step": 3852 + }, + { + "epoch": 0.5134594882729211, + "grad_norm": 0.3153649821271738, + "learning_rate": 9.424630103115451e-06, + "loss": 0.4147, + "step": 3853 + }, + { + "epoch": 0.5135927505330491, + "grad_norm": 0.3192465546590689, + "learning_rate": 9.4242984461266e-06, + "loss": 0.4869, + "step": 3854 + }, + { + "epoch": 0.513726012793177, + "grad_norm": 0.2945229655815656, + "learning_rate": 9.423966699416818e-06, + "loss": 0.3835, + "step": 3855 + }, + { + "epoch": 0.5138592750533049, + "grad_norm": 0.3310377157845876, + "learning_rate": 9.423634862992832e-06, + "loss": 0.5405, + "step": 3856 + }, + { + "epoch": 0.5139925373134329, + "grad_norm": 0.31868278796333227, + "learning_rate": 9.423302936861371e-06, + "loss": 0.3882, + "step": 3857 + }, + { + "epoch": 0.5141257995735607, + "grad_norm": 0.30947176867422055, + "learning_rate": 9.42297092102917e-06, + "loss": 0.4566, + "step": 3858 + }, + { + "epoch": 0.5142590618336887, + "grad_norm": 0.32650005030640267, + "learning_rate": 9.422638815502958e-06, + "loss": 0.4404, + "step": 3859 + }, + { + "epoch": 0.5143923240938166, + "grad_norm": 0.2921776461100202, + "learning_rate": 9.42230662028947e-06, + "loss": 0.4363, + "step": 3860 + }, + { + "epoch": 0.5145255863539445, + "grad_norm": 0.29089539206684617, + "learning_rate": 9.421974335395444e-06, + "loss": 0.4064, + "step": 3861 + }, + { + "epoch": 0.5146588486140725, + "grad_norm": 0.28788664142689535, + "learning_rate": 9.421641960827621e-06, + "loss": 0.359, + "step": 3862 + }, + { + "epoch": 0.5147921108742004, + "grad_norm": 0.29409023120630695, + "learning_rate": 9.421309496592735e-06, + "loss": 0.427, + "step": 3863 + }, + { + "epoch": 0.5149253731343284, + "grad_norm": 0.30782696039654056, + "learning_rate": 9.420976942697532e-06, + "loss": 0.3939, + "step": 3864 + }, + { + "epoch": 0.5150586353944563, + "grad_norm": 0.2862319559354791, + "learning_rate": 9.420644299148758e-06, + "loss": 0.4684, + "step": 3865 + }, + { + "epoch": 0.5151918976545842, + "grad_norm": 4.24282138880379, + "learning_rate": 9.420311565953153e-06, + "loss": 0.4237, + "step": 3866 + }, + { + "epoch": 0.5153251599147122, + "grad_norm": 0.3014088019534942, + "learning_rate": 9.41997874311747e-06, + "loss": 0.3756, + "step": 3867 + }, + { + "epoch": 0.5154584221748401, + "grad_norm": 0.29572329075083786, + "learning_rate": 9.419645830648454e-06, + "loss": 0.4194, + "step": 3868 + }, + { + "epoch": 0.5155916844349681, + "grad_norm": 0.2823749526171483, + "learning_rate": 9.41931282855286e-06, + "loss": 0.4105, + "step": 3869 + }, + { + "epoch": 0.5157249466950959, + "grad_norm": 0.31343005952429825, + "learning_rate": 9.418979736837439e-06, + "loss": 0.4065, + "step": 3870 + }, + { + "epoch": 0.5158582089552238, + "grad_norm": 0.3246353733387519, + "learning_rate": 9.418646555508944e-06, + "loss": 0.5033, + "step": 3871 + }, + { + "epoch": 0.5159914712153518, + "grad_norm": 0.2961937653654219, + "learning_rate": 9.418313284574135e-06, + "loss": 0.3569, + "step": 3872 + }, + { + "epoch": 0.5161247334754797, + "grad_norm": 0.33696376416668267, + "learning_rate": 9.417979924039768e-06, + "loss": 0.4537, + "step": 3873 + }, + { + "epoch": 0.5162579957356077, + "grad_norm": 0.34437020784952926, + "learning_rate": 9.417646473912607e-06, + "loss": 0.4481, + "step": 3874 + }, + { + "epoch": 0.5163912579957356, + "grad_norm": 0.2991395726957454, + "learning_rate": 9.41731293419941e-06, + "loss": 0.4021, + "step": 3875 + }, + { + "epoch": 0.5165245202558635, + "grad_norm": 0.30399274388108866, + "learning_rate": 9.416979304906942e-06, + "loss": 0.392, + "step": 3876 + }, + { + "epoch": 0.5166577825159915, + "grad_norm": 0.5135274123473241, + "learning_rate": 9.416645586041968e-06, + "loss": 0.3841, + "step": 3877 + }, + { + "epoch": 0.5167910447761194, + "grad_norm": 0.302724120582415, + "learning_rate": 9.416311777611259e-06, + "loss": 0.4133, + "step": 3878 + }, + { + "epoch": 0.5169243070362474, + "grad_norm": 0.3119875516313626, + "learning_rate": 9.415977879621579e-06, + "loss": 0.4283, + "step": 3879 + }, + { + "epoch": 0.5170575692963753, + "grad_norm": 0.2947656677874087, + "learning_rate": 9.415643892079704e-06, + "loss": 0.4407, + "step": 3880 + }, + { + "epoch": 0.5171908315565032, + "grad_norm": 0.3399351765654186, + "learning_rate": 9.415309814992406e-06, + "loss": 0.4504, + "step": 3881 + }, + { + "epoch": 0.5173240938166311, + "grad_norm": 0.28009761059369054, + "learning_rate": 9.414975648366455e-06, + "loss": 0.3497, + "step": 3882 + }, + { + "epoch": 0.517457356076759, + "grad_norm": 0.30182398524743576, + "learning_rate": 9.414641392208635e-06, + "loss": 0.3743, + "step": 3883 + }, + { + "epoch": 0.517590618336887, + "grad_norm": 0.313975170989843, + "learning_rate": 9.414307046525719e-06, + "loss": 0.4144, + "step": 3884 + }, + { + "epoch": 0.5177238805970149, + "grad_norm": 0.3216654761683483, + "learning_rate": 9.413972611324491e-06, + "loss": 0.3941, + "step": 3885 + }, + { + "epoch": 0.5178571428571429, + "grad_norm": 0.29599380405464903, + "learning_rate": 9.413638086611729e-06, + "loss": 0.391, + "step": 3886 + }, + { + "epoch": 0.5179904051172708, + "grad_norm": 0.31043580739936144, + "learning_rate": 9.41330347239422e-06, + "loss": 0.3949, + "step": 3887 + }, + { + "epoch": 0.5181236673773987, + "grad_norm": 0.30802012145507013, + "learning_rate": 9.41296876867875e-06, + "loss": 0.4237, + "step": 3888 + }, + { + "epoch": 0.5182569296375267, + "grad_norm": 0.30365453719507274, + "learning_rate": 9.412633975472103e-06, + "loss": 0.3468, + "step": 3889 + }, + { + "epoch": 0.5183901918976546, + "grad_norm": 0.31746603812412727, + "learning_rate": 9.412299092781072e-06, + "loss": 0.4806, + "step": 3890 + }, + { + "epoch": 0.5185234541577826, + "grad_norm": 0.30126382535600005, + "learning_rate": 9.411964120612446e-06, + "loss": 0.4847, + "step": 3891 + }, + { + "epoch": 0.5186567164179104, + "grad_norm": 0.3100866775189723, + "learning_rate": 9.411629058973018e-06, + "loss": 0.492, + "step": 3892 + }, + { + "epoch": 0.5187899786780383, + "grad_norm": 0.31609525436562314, + "learning_rate": 9.411293907869586e-06, + "loss": 0.4406, + "step": 3893 + }, + { + "epoch": 0.5189232409381663, + "grad_norm": 0.3139562976111654, + "learning_rate": 9.410958667308941e-06, + "loss": 0.3895, + "step": 3894 + }, + { + "epoch": 0.5190565031982942, + "grad_norm": 0.29316209027058443, + "learning_rate": 9.410623337297885e-06, + "loss": 0.4011, + "step": 3895 + }, + { + "epoch": 0.5191897654584222, + "grad_norm": 0.3365375937520549, + "learning_rate": 9.410287917843218e-06, + "loss": 0.4159, + "step": 3896 + }, + { + "epoch": 0.5193230277185501, + "grad_norm": 0.3154081046553866, + "learning_rate": 9.409952408951742e-06, + "loss": 0.3213, + "step": 3897 + }, + { + "epoch": 0.519456289978678, + "grad_norm": 0.312902267203383, + "learning_rate": 9.409616810630259e-06, + "loss": 0.422, + "step": 3898 + }, + { + "epoch": 0.519589552238806, + "grad_norm": 0.31339404421195316, + "learning_rate": 9.409281122885576e-06, + "loss": 0.4414, + "step": 3899 + }, + { + "epoch": 0.5197228144989339, + "grad_norm": 0.29438877428432714, + "learning_rate": 9.408945345724502e-06, + "loss": 0.4055, + "step": 3900 + }, + { + "epoch": 0.5198560767590619, + "grad_norm": 0.3178386298284714, + "learning_rate": 9.408609479153843e-06, + "loss": 0.5136, + "step": 3901 + }, + { + "epoch": 0.5199893390191898, + "grad_norm": 0.2994979844342436, + "learning_rate": 9.408273523180414e-06, + "loss": 0.3714, + "step": 3902 + }, + { + "epoch": 0.5201226012793176, + "grad_norm": 0.3632866850674331, + "learning_rate": 9.407937477811024e-06, + "loss": 0.3776, + "step": 3903 + }, + { + "epoch": 0.5202558635394456, + "grad_norm": 0.2910553181276391, + "learning_rate": 9.40760134305249e-06, + "loss": 0.5061, + "step": 3904 + }, + { + "epoch": 0.5203891257995735, + "grad_norm": 0.3173260579706901, + "learning_rate": 9.407265118911628e-06, + "loss": 0.3619, + "step": 3905 + }, + { + "epoch": 0.5205223880597015, + "grad_norm": 0.29251011755000855, + "learning_rate": 9.406928805395257e-06, + "loss": 0.4036, + "step": 3906 + }, + { + "epoch": 0.5206556503198294, + "grad_norm": 0.3128306250011345, + "learning_rate": 9.406592402510196e-06, + "loss": 0.4226, + "step": 3907 + }, + { + "epoch": 0.5207889125799574, + "grad_norm": 0.3350639321193403, + "learning_rate": 9.406255910263266e-06, + "loss": 0.4207, + "step": 3908 + }, + { + "epoch": 0.5209221748400853, + "grad_norm": 0.3109582793078425, + "learning_rate": 9.405919328661292e-06, + "loss": 0.4424, + "step": 3909 + }, + { + "epoch": 0.5210554371002132, + "grad_norm": 0.3408973409554909, + "learning_rate": 9.405582657711101e-06, + "loss": 0.4008, + "step": 3910 + }, + { + "epoch": 0.5211886993603412, + "grad_norm": 0.306461399718333, + "learning_rate": 9.40524589741952e-06, + "loss": 0.4176, + "step": 3911 + }, + { + "epoch": 0.5213219616204691, + "grad_norm": 0.3165664099141557, + "learning_rate": 9.404909047793375e-06, + "loss": 0.4084, + "step": 3912 + }, + { + "epoch": 0.5214552238805971, + "grad_norm": 0.3275110008808765, + "learning_rate": 9.4045721088395e-06, + "loss": 0.4298, + "step": 3913 + }, + { + "epoch": 0.521588486140725, + "grad_norm": 0.2920728584299376, + "learning_rate": 9.40423508056473e-06, + "loss": 0.3793, + "step": 3914 + }, + { + "epoch": 0.5217217484008528, + "grad_norm": 0.35953298467937606, + "learning_rate": 9.403897962975894e-06, + "loss": 0.4999, + "step": 3915 + }, + { + "epoch": 0.5218550106609808, + "grad_norm": 0.29037927466760866, + "learning_rate": 9.403560756079832e-06, + "loss": 0.3663, + "step": 3916 + }, + { + "epoch": 0.5219882729211087, + "grad_norm": 0.3010392068500362, + "learning_rate": 9.403223459883382e-06, + "loss": 0.4549, + "step": 3917 + }, + { + "epoch": 0.5221215351812367, + "grad_norm": 0.3300068114702094, + "learning_rate": 9.402886074393382e-06, + "loss": 0.4179, + "step": 3918 + }, + { + "epoch": 0.5222547974413646, + "grad_norm": 0.3039625000278832, + "learning_rate": 9.402548599616676e-06, + "loss": 0.4405, + "step": 3919 + }, + { + "epoch": 0.5223880597014925, + "grad_norm": 0.30901324891419313, + "learning_rate": 9.402211035560108e-06, + "loss": 0.3364, + "step": 3920 + }, + { + "epoch": 0.5225213219616205, + "grad_norm": 0.7527619742675649, + "learning_rate": 9.401873382230522e-06, + "loss": 0.3879, + "step": 3921 + }, + { + "epoch": 0.5226545842217484, + "grad_norm": 0.3172685917338281, + "learning_rate": 9.401535639634767e-06, + "loss": 0.4019, + "step": 3922 + }, + { + "epoch": 0.5227878464818764, + "grad_norm": 0.3185862590208956, + "learning_rate": 9.401197807779691e-06, + "loss": 0.4043, + "step": 3923 + }, + { + "epoch": 0.5229211087420043, + "grad_norm": 0.34160527323824846, + "learning_rate": 9.400859886672144e-06, + "loss": 0.4428, + "step": 3924 + }, + { + "epoch": 0.5230543710021321, + "grad_norm": 0.2989467904529278, + "learning_rate": 9.400521876318981e-06, + "loss": 0.4476, + "step": 3925 + }, + { + "epoch": 0.5231876332622601, + "grad_norm": 0.29973008191847555, + "learning_rate": 9.400183776727055e-06, + "loss": 0.403, + "step": 3926 + }, + { + "epoch": 0.523320895522388, + "grad_norm": 0.313844682827764, + "learning_rate": 9.399845587903223e-06, + "loss": 0.39, + "step": 3927 + }, + { + "epoch": 0.523454157782516, + "grad_norm": 0.32287350818391203, + "learning_rate": 9.399507309854342e-06, + "loss": 0.4238, + "step": 3928 + }, + { + "epoch": 0.5235874200426439, + "grad_norm": 0.33729137195010317, + "learning_rate": 9.399168942587273e-06, + "loss": 0.4575, + "step": 3929 + }, + { + "epoch": 0.5237206823027718, + "grad_norm": 0.34403237902846284, + "learning_rate": 9.398830486108879e-06, + "loss": 0.4152, + "step": 3930 + }, + { + "epoch": 0.5238539445628998, + "grad_norm": 0.34164408404867, + "learning_rate": 9.398491940426021e-06, + "loss": 0.3944, + "step": 3931 + }, + { + "epoch": 0.5239872068230277, + "grad_norm": 0.3357153753848656, + "learning_rate": 9.398153305545566e-06, + "loss": 0.4133, + "step": 3932 + }, + { + "epoch": 0.5241204690831557, + "grad_norm": 0.3075518693386064, + "learning_rate": 9.397814581474381e-06, + "loss": 0.4285, + "step": 3933 + }, + { + "epoch": 0.5242537313432836, + "grad_norm": 0.3374317018044367, + "learning_rate": 9.397475768219335e-06, + "loss": 0.4035, + "step": 3934 + }, + { + "epoch": 0.5243869936034116, + "grad_norm": 0.33150498649011134, + "learning_rate": 9.397136865787299e-06, + "loss": 0.5057, + "step": 3935 + }, + { + "epoch": 0.5245202558635395, + "grad_norm": 0.3244648760460506, + "learning_rate": 9.396797874185145e-06, + "loss": 0.4138, + "step": 3936 + }, + { + "epoch": 0.5246535181236673, + "grad_norm": 0.3115290355483225, + "learning_rate": 9.396458793419749e-06, + "loss": 0.3644, + "step": 3937 + }, + { + "epoch": 0.5247867803837953, + "grad_norm": 0.326163156730722, + "learning_rate": 9.396119623497986e-06, + "loss": 0.3996, + "step": 3938 + }, + { + "epoch": 0.5249200426439232, + "grad_norm": 3.2764478846844702, + "learning_rate": 9.395780364426733e-06, + "loss": 0.3804, + "step": 3939 + }, + { + "epoch": 0.5250533049040512, + "grad_norm": 0.3312916397104013, + "learning_rate": 9.395441016212872e-06, + "loss": 0.4011, + "step": 3940 + }, + { + "epoch": 0.5251865671641791, + "grad_norm": 0.32408762576497535, + "learning_rate": 9.395101578863284e-06, + "loss": 0.4179, + "step": 3941 + }, + { + "epoch": 0.525319829424307, + "grad_norm": 0.30830666138123647, + "learning_rate": 9.394762052384852e-06, + "loss": 0.3878, + "step": 3942 + }, + { + "epoch": 0.525453091684435, + "grad_norm": 0.3220493445698525, + "learning_rate": 9.39442243678446e-06, + "loss": 0.4123, + "step": 3943 + }, + { + "epoch": 0.5255863539445629, + "grad_norm": 0.3277597900484625, + "learning_rate": 9.394082732068998e-06, + "loss": 0.4191, + "step": 3944 + }, + { + "epoch": 0.5257196162046909, + "grad_norm": 0.30518823374221515, + "learning_rate": 9.393742938245356e-06, + "loss": 0.4581, + "step": 3945 + }, + { + "epoch": 0.5258528784648188, + "grad_norm": 0.3084223540405994, + "learning_rate": 9.393403055320418e-06, + "loss": 0.3635, + "step": 3946 + }, + { + "epoch": 0.5259861407249466, + "grad_norm": 0.32023803132844114, + "learning_rate": 9.393063083301085e-06, + "loss": 0.4705, + "step": 3947 + }, + { + "epoch": 0.5261194029850746, + "grad_norm": 0.31707812416457193, + "learning_rate": 9.392723022194246e-06, + "loss": 0.4017, + "step": 3948 + }, + { + "epoch": 0.5262526652452025, + "grad_norm": 0.3188436467360053, + "learning_rate": 9.392382872006796e-06, + "loss": 0.3646, + "step": 3949 + }, + { + "epoch": 0.5263859275053305, + "grad_norm": 0.3001617132151864, + "learning_rate": 9.392042632745637e-06, + "loss": 0.376, + "step": 3950 + }, + { + "epoch": 0.5265191897654584, + "grad_norm": 0.3192119252993388, + "learning_rate": 9.391702304417667e-06, + "loss": 0.4157, + "step": 3951 + }, + { + "epoch": 0.5266524520255863, + "grad_norm": 0.31963927338092935, + "learning_rate": 9.391361887029788e-06, + "loss": 0.4753, + "step": 3952 + }, + { + "epoch": 0.5267857142857143, + "grad_norm": 0.3158130747470134, + "learning_rate": 9.391021380588903e-06, + "loss": 0.4575, + "step": 3953 + }, + { + "epoch": 0.5269189765458422, + "grad_norm": 0.29608093395318635, + "learning_rate": 9.390680785101918e-06, + "loss": 0.4282, + "step": 3954 + }, + { + "epoch": 0.5270522388059702, + "grad_norm": 0.299361512012682, + "learning_rate": 9.390340100575737e-06, + "loss": 0.4381, + "step": 3955 + }, + { + "epoch": 0.5271855010660981, + "grad_norm": 0.28523548711787766, + "learning_rate": 9.389999327017272e-06, + "loss": 0.4261, + "step": 3956 + }, + { + "epoch": 0.527318763326226, + "grad_norm": 0.349332624156611, + "learning_rate": 9.389658464433433e-06, + "loss": 0.4488, + "step": 3957 + }, + { + "epoch": 0.527452025586354, + "grad_norm": 0.29329764965004823, + "learning_rate": 9.38931751283113e-06, + "loss": 0.4612, + "step": 3958 + }, + { + "epoch": 0.5275852878464818, + "grad_norm": 0.2924839282664526, + "learning_rate": 9.388976472217282e-06, + "loss": 0.4234, + "step": 3959 + }, + { + "epoch": 0.5277185501066098, + "grad_norm": 0.29086560394363503, + "learning_rate": 9.388635342598802e-06, + "loss": 0.4206, + "step": 3960 + }, + { + "epoch": 0.5278518123667377, + "grad_norm": 0.315205743377714, + "learning_rate": 9.388294123982606e-06, + "loss": 0.4535, + "step": 3961 + }, + { + "epoch": 0.5279850746268657, + "grad_norm": 0.3004660547563838, + "learning_rate": 9.387952816375616e-06, + "loss": 0.3711, + "step": 3962 + }, + { + "epoch": 0.5281183368869936, + "grad_norm": 0.2738102679271473, + "learning_rate": 9.387611419784755e-06, + "loss": 0.364, + "step": 3963 + }, + { + "epoch": 0.5282515991471215, + "grad_norm": 0.29880811784211797, + "learning_rate": 9.38726993421694e-06, + "loss": 0.4737, + "step": 3964 + }, + { + "epoch": 0.5283848614072495, + "grad_norm": 0.2929473951066113, + "learning_rate": 9.386928359679104e-06, + "loss": 0.4075, + "step": 3965 + }, + { + "epoch": 0.5285181236673774, + "grad_norm": 0.2985472321414964, + "learning_rate": 9.38658669617817e-06, + "loss": 0.3839, + "step": 3966 + }, + { + "epoch": 0.5286513859275054, + "grad_norm": 10.024478426368098, + "learning_rate": 9.386244943721064e-06, + "loss": 0.5252, + "step": 3967 + }, + { + "epoch": 0.5287846481876333, + "grad_norm": 1.807803377618182, + "learning_rate": 9.385903102314722e-06, + "loss": 0.3735, + "step": 3968 + }, + { + "epoch": 0.5289179104477612, + "grad_norm": 0.3292859541948107, + "learning_rate": 9.385561171966073e-06, + "loss": 0.4326, + "step": 3969 + }, + { + "epoch": 0.5290511727078892, + "grad_norm": 0.29757609059085927, + "learning_rate": 9.38521915268205e-06, + "loss": 0.4239, + "step": 3970 + }, + { + "epoch": 0.529184434968017, + "grad_norm": 0.2993562853291602, + "learning_rate": 9.384877044469592e-06, + "loss": 0.4396, + "step": 3971 + }, + { + "epoch": 0.529317697228145, + "grad_norm": 0.3274949812028125, + "learning_rate": 9.384534847335634e-06, + "loss": 0.4024, + "step": 3972 + }, + { + "epoch": 0.5294509594882729, + "grad_norm": 0.3043501741140123, + "learning_rate": 9.384192561287115e-06, + "loss": 0.3828, + "step": 3973 + }, + { + "epoch": 0.5295842217484008, + "grad_norm": 0.31378703558254245, + "learning_rate": 9.38385018633098e-06, + "loss": 0.4634, + "step": 3974 + }, + { + "epoch": 0.5297174840085288, + "grad_norm": 0.3061569676525469, + "learning_rate": 9.383507722474169e-06, + "loss": 0.3753, + "step": 3975 + }, + { + "epoch": 0.5298507462686567, + "grad_norm": 0.2979096952325163, + "learning_rate": 9.383165169723627e-06, + "loss": 0.4912, + "step": 3976 + }, + { + "epoch": 0.5299840085287847, + "grad_norm": 0.36333660614989005, + "learning_rate": 9.382822528086302e-06, + "loss": 0.4669, + "step": 3977 + }, + { + "epoch": 0.5301172707889126, + "grad_norm": 0.3100505639836017, + "learning_rate": 9.382479797569142e-06, + "loss": 0.4278, + "step": 3978 + }, + { + "epoch": 0.5302505330490405, + "grad_norm": 0.30472693937369516, + "learning_rate": 9.382136978179097e-06, + "loss": 0.3731, + "step": 3979 + }, + { + "epoch": 0.5303837953091685, + "grad_norm": 0.33106295980184797, + "learning_rate": 9.38179406992312e-06, + "loss": 0.4448, + "step": 3980 + }, + { + "epoch": 0.5305170575692963, + "grad_norm": 0.3077354523149631, + "learning_rate": 9.381451072808163e-06, + "loss": 0.3853, + "step": 3981 + }, + { + "epoch": 0.5306503198294243, + "grad_norm": 0.2962424100876137, + "learning_rate": 9.381107986841183e-06, + "loss": 0.4189, + "step": 3982 + }, + { + "epoch": 0.5307835820895522, + "grad_norm": 0.30273678922497005, + "learning_rate": 9.380764812029136e-06, + "loss": 0.3607, + "step": 3983 + }, + { + "epoch": 0.5309168443496801, + "grad_norm": 0.30835901443256925, + "learning_rate": 9.380421548378984e-06, + "loss": 0.5374, + "step": 3984 + }, + { + "epoch": 0.5310501066098081, + "grad_norm": 0.33785582808901476, + "learning_rate": 9.380078195897685e-06, + "loss": 0.4296, + "step": 3985 + }, + { + "epoch": 0.531183368869936, + "grad_norm": 0.2947900644559445, + "learning_rate": 9.379734754592205e-06, + "loss": 0.4356, + "step": 3986 + }, + { + "epoch": 0.531316631130064, + "grad_norm": 0.28850683845792036, + "learning_rate": 9.379391224469507e-06, + "loss": 0.3629, + "step": 3987 + }, + { + "epoch": 0.5314498933901919, + "grad_norm": 0.3023915910509797, + "learning_rate": 9.379047605536557e-06, + "loss": 0.4932, + "step": 3988 + }, + { + "epoch": 0.5315831556503199, + "grad_norm": 0.2931556040202939, + "learning_rate": 9.378703897800325e-06, + "loss": 0.431, + "step": 3989 + }, + { + "epoch": 0.5317164179104478, + "grad_norm": 0.31358525986896857, + "learning_rate": 9.378360101267778e-06, + "loss": 0.3748, + "step": 3990 + }, + { + "epoch": 0.5318496801705757, + "grad_norm": 0.2933318972686083, + "learning_rate": 9.378016215945893e-06, + "loss": 0.3637, + "step": 3991 + }, + { + "epoch": 0.5319829424307037, + "grad_norm": 0.30129082957404163, + "learning_rate": 9.377672241841637e-06, + "loss": 0.4165, + "step": 3992 + }, + { + "epoch": 0.5321162046908315, + "grad_norm": 0.30229020423510683, + "learning_rate": 9.377328178961991e-06, + "loss": 0.3752, + "step": 3993 + }, + { + "epoch": 0.5322494669509595, + "grad_norm": 0.2993994012019332, + "learning_rate": 9.37698402731393e-06, + "loss": 0.4925, + "step": 3994 + }, + { + "epoch": 0.5323827292110874, + "grad_norm": 0.31999787576684197, + "learning_rate": 9.376639786904436e-06, + "loss": 0.4326, + "step": 3995 + }, + { + "epoch": 0.5325159914712153, + "grad_norm": 0.30870076322796625, + "learning_rate": 9.376295457740484e-06, + "loss": 0.3851, + "step": 3996 + }, + { + "epoch": 0.5326492537313433, + "grad_norm": 0.3472513455292188, + "learning_rate": 9.375951039829062e-06, + "loss": 0.4158, + "step": 3997 + }, + { + "epoch": 0.5327825159914712, + "grad_norm": 0.32413277257315914, + "learning_rate": 9.375606533177152e-06, + "loss": 0.4215, + "step": 3998 + }, + { + "epoch": 0.5329157782515992, + "grad_norm": 0.28814712434017037, + "learning_rate": 9.375261937791741e-06, + "loss": 0.4394, + "step": 3999 + }, + { + "epoch": 0.5330490405117271, + "grad_norm": 0.2973616225979961, + "learning_rate": 9.374917253679816e-06, + "loss": 0.399, + "step": 4000 + }, + { + "epoch": 0.533182302771855, + "grad_norm": 0.28642302600856356, + "learning_rate": 9.37457248084837e-06, + "loss": 0.3982, + "step": 4001 + }, + { + "epoch": 0.533315565031983, + "grad_norm": 0.2964129306087151, + "learning_rate": 9.37422761930439e-06, + "loss": 0.4157, + "step": 4002 + }, + { + "epoch": 0.5334488272921108, + "grad_norm": 0.3139173887851647, + "learning_rate": 9.373882669054875e-06, + "loss": 0.3604, + "step": 4003 + }, + { + "epoch": 0.5335820895522388, + "grad_norm": 0.30190342474438886, + "learning_rate": 9.373537630106816e-06, + "loss": 0.4061, + "step": 4004 + }, + { + "epoch": 0.5337153518123667, + "grad_norm": 0.29803638378760966, + "learning_rate": 9.37319250246721e-06, + "loss": 0.3882, + "step": 4005 + }, + { + "epoch": 0.5338486140724946, + "grad_norm": 0.3059672158654086, + "learning_rate": 9.37284728614306e-06, + "loss": 0.4417, + "step": 4006 + }, + { + "epoch": 0.5339818763326226, + "grad_norm": 0.28771310605261957, + "learning_rate": 9.372501981141361e-06, + "loss": 0.3787, + "step": 4007 + }, + { + "epoch": 0.5341151385927505, + "grad_norm": 0.31117921503474716, + "learning_rate": 9.37215658746912e-06, + "loss": 0.3952, + "step": 4008 + }, + { + "epoch": 0.5342484008528785, + "grad_norm": 0.3110497241206738, + "learning_rate": 9.371811105133342e-06, + "loss": 0.4118, + "step": 4009 + }, + { + "epoch": 0.5343816631130064, + "grad_norm": 0.3421113849439782, + "learning_rate": 9.371465534141029e-06, + "loss": 0.4901, + "step": 4010 + }, + { + "epoch": 0.5345149253731343, + "grad_norm": 0.2970600870052872, + "learning_rate": 9.371119874499191e-06, + "loss": 0.442, + "step": 4011 + }, + { + "epoch": 0.5346481876332623, + "grad_norm": 0.29853038221282513, + "learning_rate": 9.370774126214837e-06, + "loss": 0.3714, + "step": 4012 + }, + { + "epoch": 0.5347814498933902, + "grad_norm": 0.33873852335813004, + "learning_rate": 9.37042828929498e-06, + "loss": 0.3864, + "step": 4013 + }, + { + "epoch": 0.5349147121535182, + "grad_norm": 0.2999583060903659, + "learning_rate": 9.370082363746632e-06, + "loss": 0.4008, + "step": 4014 + }, + { + "epoch": 0.535047974413646, + "grad_norm": 0.2796379203539539, + "learning_rate": 9.369736349576806e-06, + "loss": 0.347, + "step": 4015 + }, + { + "epoch": 0.535181236673774, + "grad_norm": 0.2998691397208659, + "learning_rate": 9.369390246792522e-06, + "loss": 0.3844, + "step": 4016 + }, + { + "epoch": 0.5353144989339019, + "grad_norm": 0.38636391492279376, + "learning_rate": 9.369044055400798e-06, + "loss": 0.4191, + "step": 4017 + }, + { + "epoch": 0.5354477611940298, + "grad_norm": 0.32161407143331794, + "learning_rate": 9.368697775408655e-06, + "loss": 0.3861, + "step": 4018 + }, + { + "epoch": 0.5355810234541578, + "grad_norm": 0.30629642424445985, + "learning_rate": 9.368351406823115e-06, + "loss": 0.415, + "step": 4019 + }, + { + "epoch": 0.5357142857142857, + "grad_norm": 0.32009604114482876, + "learning_rate": 9.368004949651202e-06, + "loss": 0.4106, + "step": 4020 + }, + { + "epoch": 0.5358475479744137, + "grad_norm": 0.31868055396422884, + "learning_rate": 9.36765840389994e-06, + "loss": 0.4129, + "step": 4021 + }, + { + "epoch": 0.5359808102345416, + "grad_norm": 0.300808532382258, + "learning_rate": 9.367311769576358e-06, + "loss": 0.3632, + "step": 4022 + }, + { + "epoch": 0.5361140724946695, + "grad_norm": 0.3381624335002536, + "learning_rate": 9.366965046687487e-06, + "loss": 0.4828, + "step": 4023 + }, + { + "epoch": 0.5362473347547975, + "grad_norm": 0.30246138925923544, + "learning_rate": 9.366618235240355e-06, + "loss": 0.4164, + "step": 4024 + }, + { + "epoch": 0.5363805970149254, + "grad_norm": 0.3284614615209332, + "learning_rate": 9.366271335241996e-06, + "loss": 0.4334, + "step": 4025 + }, + { + "epoch": 0.5365138592750534, + "grad_norm": 0.3178705265158152, + "learning_rate": 9.365924346699447e-06, + "loss": 0.4085, + "step": 4026 + }, + { + "epoch": 0.5366471215351812, + "grad_norm": 0.33070438796859064, + "learning_rate": 9.365577269619743e-06, + "loss": 0.3883, + "step": 4027 + }, + { + "epoch": 0.5367803837953091, + "grad_norm": 0.29475839798997416, + "learning_rate": 9.365230104009923e-06, + "loss": 0.4785, + "step": 4028 + }, + { + "epoch": 0.5369136460554371, + "grad_norm": 0.32907111411820067, + "learning_rate": 9.364882849877028e-06, + "loss": 0.401, + "step": 4029 + }, + { + "epoch": 0.537046908315565, + "grad_norm": 0.3072536602493598, + "learning_rate": 9.364535507228097e-06, + "loss": 0.4262, + "step": 4030 + }, + { + "epoch": 0.537180170575693, + "grad_norm": 0.29479501718045886, + "learning_rate": 9.364188076070177e-06, + "loss": 0.3978, + "step": 4031 + }, + { + "epoch": 0.5373134328358209, + "grad_norm": 0.29998749886442644, + "learning_rate": 9.363840556410311e-06, + "loss": 0.3906, + "step": 4032 + }, + { + "epoch": 0.5374466950959488, + "grad_norm": 0.32010524924343847, + "learning_rate": 9.363492948255549e-06, + "loss": 0.5018, + "step": 4033 + }, + { + "epoch": 0.5375799573560768, + "grad_norm": 0.3035193748751774, + "learning_rate": 9.363145251612938e-06, + "loss": 0.3834, + "step": 4034 + }, + { + "epoch": 0.5377132196162047, + "grad_norm": 0.31356835111442355, + "learning_rate": 9.36279746648953e-06, + "loss": 0.4697, + "step": 4035 + }, + { + "epoch": 0.5378464818763327, + "grad_norm": 0.2938967750391331, + "learning_rate": 9.362449592892378e-06, + "loss": 0.4035, + "step": 4036 + }, + { + "epoch": 0.5379797441364605, + "grad_norm": 0.3008878552513233, + "learning_rate": 9.362101630828535e-06, + "loss": 0.4129, + "step": 4037 + }, + { + "epoch": 0.5381130063965884, + "grad_norm": 0.2999797868496625, + "learning_rate": 9.36175358030506e-06, + "loss": 0.4673, + "step": 4038 + }, + { + "epoch": 0.5382462686567164, + "grad_norm": 0.31530191730926166, + "learning_rate": 9.361405441329011e-06, + "loss": 0.398, + "step": 4039 + }, + { + "epoch": 0.5383795309168443, + "grad_norm": 0.299106227489708, + "learning_rate": 9.361057213907442e-06, + "loss": 0.4133, + "step": 4040 + }, + { + "epoch": 0.5385127931769723, + "grad_norm": 0.30247668142354633, + "learning_rate": 9.360708898047424e-06, + "loss": 0.374, + "step": 4041 + }, + { + "epoch": 0.5386460554371002, + "grad_norm": 0.30766807046993433, + "learning_rate": 9.360360493756015e-06, + "loss": 0.4574, + "step": 4042 + }, + { + "epoch": 0.5387793176972282, + "grad_norm": 0.31040672308743494, + "learning_rate": 9.36001200104028e-06, + "loss": 0.4541, + "step": 4043 + }, + { + "epoch": 0.5389125799573561, + "grad_norm": 0.3101216664575006, + "learning_rate": 9.359663419907288e-06, + "loss": 0.3992, + "step": 4044 + }, + { + "epoch": 0.539045842217484, + "grad_norm": 0.3100634835258424, + "learning_rate": 9.359314750364108e-06, + "loss": 0.3885, + "step": 4045 + }, + { + "epoch": 0.539179104477612, + "grad_norm": 0.3000536240557585, + "learning_rate": 9.35896599241781e-06, + "loss": 0.363, + "step": 4046 + }, + { + "epoch": 0.5393123667377399, + "grad_norm": 0.3031578212069414, + "learning_rate": 9.358617146075465e-06, + "loss": 0.4211, + "step": 4047 + }, + { + "epoch": 0.5394456289978679, + "grad_norm": 0.2951866707736916, + "learning_rate": 9.358268211344152e-06, + "loss": 0.3921, + "step": 4048 + }, + { + "epoch": 0.5395788912579957, + "grad_norm": 0.3089761787565455, + "learning_rate": 9.357919188230942e-06, + "loss": 0.3641, + "step": 4049 + }, + { + "epoch": 0.5397121535181236, + "grad_norm": 0.29719645190178645, + "learning_rate": 9.357570076742916e-06, + "loss": 0.4108, + "step": 4050 + }, + { + "epoch": 0.5398454157782516, + "grad_norm": 0.2889350217830756, + "learning_rate": 9.357220876887153e-06, + "loss": 0.4051, + "step": 4051 + }, + { + "epoch": 0.5399786780383795, + "grad_norm": 0.31075334789747827, + "learning_rate": 9.356871588670733e-06, + "loss": 0.4511, + "step": 4052 + }, + { + "epoch": 0.5401119402985075, + "grad_norm": 0.3190620461547281, + "learning_rate": 9.356522212100739e-06, + "loss": 0.4766, + "step": 4053 + }, + { + "epoch": 0.5402452025586354, + "grad_norm": 0.2912399352621627, + "learning_rate": 9.356172747184258e-06, + "loss": 0.3531, + "step": 4054 + }, + { + "epoch": 0.5403784648187633, + "grad_norm": 0.31088707638280927, + "learning_rate": 9.355823193928377e-06, + "loss": 0.4065, + "step": 4055 + }, + { + "epoch": 0.5405117270788913, + "grad_norm": 0.29882302852091924, + "learning_rate": 9.355473552340185e-06, + "loss": 0.4322, + "step": 4056 + }, + { + "epoch": 0.5406449893390192, + "grad_norm": 0.2983199383918009, + "learning_rate": 9.35512382242677e-06, + "loss": 0.3374, + "step": 4057 + }, + { + "epoch": 0.5407782515991472, + "grad_norm": 0.3240752965093766, + "learning_rate": 9.354774004195225e-06, + "loss": 0.5265, + "step": 4058 + }, + { + "epoch": 0.540911513859275, + "grad_norm": 0.29090633067182475, + "learning_rate": 9.354424097652645e-06, + "loss": 0.4097, + "step": 4059 + }, + { + "epoch": 0.5410447761194029, + "grad_norm": 0.30307206655877394, + "learning_rate": 9.354074102806125e-06, + "loss": 0.3647, + "step": 4060 + }, + { + "epoch": 0.5411780383795309, + "grad_norm": 0.27981672845114314, + "learning_rate": 9.353724019662763e-06, + "loss": 0.3314, + "step": 4061 + }, + { + "epoch": 0.5413113006396588, + "grad_norm": 0.2988940675261515, + "learning_rate": 9.35337384822966e-06, + "loss": 0.377, + "step": 4062 + }, + { + "epoch": 0.5414445628997868, + "grad_norm": 0.30331207692906403, + "learning_rate": 9.353023588513912e-06, + "loss": 0.3822, + "step": 4063 + }, + { + "epoch": 0.5415778251599147, + "grad_norm": 0.2958960668076388, + "learning_rate": 9.352673240522628e-06, + "loss": 0.4393, + "step": 4064 + }, + { + "epoch": 0.5417110874200426, + "grad_norm": 0.32057909262008444, + "learning_rate": 9.35232280426291e-06, + "loss": 0.4644, + "step": 4065 + }, + { + "epoch": 0.5418443496801706, + "grad_norm": 0.2941670069363381, + "learning_rate": 9.351972279741863e-06, + "loss": 0.4091, + "step": 4066 + }, + { + "epoch": 0.5419776119402985, + "grad_norm": 0.3028627891661417, + "learning_rate": 9.3516216669666e-06, + "loss": 0.4024, + "step": 4067 + }, + { + "epoch": 0.5421108742004265, + "grad_norm": 0.32604369530062893, + "learning_rate": 9.351270965944226e-06, + "loss": 0.4584, + "step": 4068 + }, + { + "epoch": 0.5422441364605544, + "grad_norm": 0.3099679403088744, + "learning_rate": 9.350920176681854e-06, + "loss": 0.4946, + "step": 4069 + }, + { + "epoch": 0.5423773987206824, + "grad_norm": 0.3049960969180065, + "learning_rate": 9.350569299186601e-06, + "loss": 0.4216, + "step": 4070 + }, + { + "epoch": 0.5425106609808102, + "grad_norm": 0.28210623498000176, + "learning_rate": 9.350218333465579e-06, + "loss": 0.4169, + "step": 4071 + }, + { + "epoch": 0.5426439232409381, + "grad_norm": 0.28701467841014355, + "learning_rate": 9.349867279525909e-06, + "loss": 0.4076, + "step": 4072 + }, + { + "epoch": 0.5427771855010661, + "grad_norm": 0.3232317840331931, + "learning_rate": 9.349516137374705e-06, + "loss": 0.4277, + "step": 4073 + }, + { + "epoch": 0.542910447761194, + "grad_norm": 0.289164713781185, + "learning_rate": 9.34916490701909e-06, + "loss": 0.3468, + "step": 4074 + }, + { + "epoch": 0.543043710021322, + "grad_norm": 0.31679872961841316, + "learning_rate": 9.348813588466189e-06, + "loss": 0.4012, + "step": 4075 + }, + { + "epoch": 0.5431769722814499, + "grad_norm": 0.2982595616696829, + "learning_rate": 9.348462181723124e-06, + "loss": 0.4205, + "step": 4076 + }, + { + "epoch": 0.5433102345415778, + "grad_norm": 0.29818523823677123, + "learning_rate": 9.348110686797021e-06, + "loss": 0.4133, + "step": 4077 + }, + { + "epoch": 0.5434434968017058, + "grad_norm": 0.3236965545763597, + "learning_rate": 9.34775910369501e-06, + "loss": 0.383, + "step": 4078 + }, + { + "epoch": 0.5435767590618337, + "grad_norm": 0.3141369843732777, + "learning_rate": 9.34740743242422e-06, + "loss": 0.493, + "step": 4079 + }, + { + "epoch": 0.5437100213219617, + "grad_norm": 0.3169609878146188, + "learning_rate": 9.34705567299178e-06, + "loss": 0.4254, + "step": 4080 + }, + { + "epoch": 0.5438432835820896, + "grad_norm": 0.32428056024621343, + "learning_rate": 9.346703825404826e-06, + "loss": 0.3828, + "step": 4081 + }, + { + "epoch": 0.5439765458422174, + "grad_norm": 0.30778214440448487, + "learning_rate": 9.346351889670495e-06, + "loss": 0.3969, + "step": 4082 + }, + { + "epoch": 0.5441098081023454, + "grad_norm": 0.2964352372368992, + "learning_rate": 9.34599986579592e-06, + "loss": 0.377, + "step": 4083 + }, + { + "epoch": 0.5442430703624733, + "grad_norm": 0.30269604168529896, + "learning_rate": 9.345647753788241e-06, + "loss": 0.3657, + "step": 4084 + }, + { + "epoch": 0.5443763326226013, + "grad_norm": 0.2954188302353459, + "learning_rate": 9.3452955536546e-06, + "loss": 0.4453, + "step": 4085 + }, + { + "epoch": 0.5445095948827292, + "grad_norm": 0.30483765946038627, + "learning_rate": 9.344943265402138e-06, + "loss": 0.3843, + "step": 4086 + }, + { + "epoch": 0.5446428571428571, + "grad_norm": 0.30559332518198534, + "learning_rate": 9.344590889037998e-06, + "loss": 0.4192, + "step": 4087 + }, + { + "epoch": 0.5447761194029851, + "grad_norm": 0.3166018170571522, + "learning_rate": 9.344238424569329e-06, + "loss": 0.4341, + "step": 4088 + }, + { + "epoch": 0.544909381663113, + "grad_norm": 0.3175951470315658, + "learning_rate": 9.343885872003276e-06, + "loss": 0.4575, + "step": 4089 + }, + { + "epoch": 0.545042643923241, + "grad_norm": 0.29561534851341176, + "learning_rate": 9.34353323134699e-06, + "loss": 0.4325, + "step": 4090 + }, + { + "epoch": 0.5451759061833689, + "grad_norm": 0.3059057315598574, + "learning_rate": 9.34318050260762e-06, + "loss": 0.4248, + "step": 4091 + }, + { + "epoch": 0.5453091684434968, + "grad_norm": 0.2835440616206816, + "learning_rate": 9.342827685792323e-06, + "loss": 0.4576, + "step": 4092 + }, + { + "epoch": 0.5454424307036247, + "grad_norm": 0.302029268394066, + "learning_rate": 9.342474780908251e-06, + "loss": 0.4735, + "step": 4093 + }, + { + "epoch": 0.5455756929637526, + "grad_norm": 0.4797163900793932, + "learning_rate": 9.34212178796256e-06, + "loss": 0.4362, + "step": 4094 + }, + { + "epoch": 0.5457089552238806, + "grad_norm": 0.31458724785101433, + "learning_rate": 9.34176870696241e-06, + "loss": 0.4266, + "step": 4095 + }, + { + "epoch": 0.5458422174840085, + "grad_norm": 0.3172292001464248, + "learning_rate": 9.34141553791496e-06, + "loss": 0.4274, + "step": 4096 + }, + { + "epoch": 0.5459754797441365, + "grad_norm": 0.2920505830818255, + "learning_rate": 9.341062280827374e-06, + "loss": 0.5476, + "step": 4097 + }, + { + "epoch": 0.5461087420042644, + "grad_norm": 0.2959323588695094, + "learning_rate": 9.340708935706813e-06, + "loss": 0.359, + "step": 4098 + }, + { + "epoch": 0.5462420042643923, + "grad_norm": 0.30831762112335953, + "learning_rate": 9.340355502560445e-06, + "loss": 0.4513, + "step": 4099 + }, + { + "epoch": 0.5463752665245203, + "grad_norm": 0.30054806199014716, + "learning_rate": 9.340001981395434e-06, + "loss": 0.4563, + "step": 4100 + }, + { + "epoch": 0.5465085287846482, + "grad_norm": 0.314255538940733, + "learning_rate": 9.339648372218955e-06, + "loss": 0.3845, + "step": 4101 + }, + { + "epoch": 0.5466417910447762, + "grad_norm": 0.30829810022373566, + "learning_rate": 9.339294675038171e-06, + "loss": 0.4189, + "step": 4102 + }, + { + "epoch": 0.5467750533049041, + "grad_norm": 0.3115659615238544, + "learning_rate": 9.338940889860262e-06, + "loss": 0.3738, + "step": 4103 + }, + { + "epoch": 0.5469083155650319, + "grad_norm": 0.3116733515193796, + "learning_rate": 9.338587016692397e-06, + "loss": 0.4059, + "step": 4104 + }, + { + "epoch": 0.5470415778251599, + "grad_norm": 0.3200710211138949, + "learning_rate": 9.338233055541756e-06, + "loss": 0.4192, + "step": 4105 + }, + { + "epoch": 0.5471748400852878, + "grad_norm": 0.30723514629158266, + "learning_rate": 9.337879006415516e-06, + "loss": 0.3754, + "step": 4106 + }, + { + "epoch": 0.5473081023454158, + "grad_norm": 0.29856937305007625, + "learning_rate": 9.337524869320855e-06, + "loss": 0.4086, + "step": 4107 + }, + { + "epoch": 0.5474413646055437, + "grad_norm": 0.31435031147005477, + "learning_rate": 9.337170644264958e-06, + "loss": 0.3673, + "step": 4108 + }, + { + "epoch": 0.5475746268656716, + "grad_norm": 0.2898673014252637, + "learning_rate": 9.336816331255005e-06, + "loss": 0.3462, + "step": 4109 + }, + { + "epoch": 0.5477078891257996, + "grad_norm": 0.2958167061693339, + "learning_rate": 9.336461930298181e-06, + "loss": 0.4246, + "step": 4110 + }, + { + "epoch": 0.5478411513859275, + "grad_norm": 0.31528149412883605, + "learning_rate": 9.336107441401679e-06, + "loss": 0.384, + "step": 4111 + }, + { + "epoch": 0.5479744136460555, + "grad_norm": 0.28664580827265634, + "learning_rate": 9.335752864572679e-06, + "loss": 0.3841, + "step": 4112 + }, + { + "epoch": 0.5481076759061834, + "grad_norm": 0.2890815969487574, + "learning_rate": 9.335398199818377e-06, + "loss": 0.4104, + "step": 4113 + }, + { + "epoch": 0.5482409381663113, + "grad_norm": 0.2923423459077692, + "learning_rate": 9.335043447145964e-06, + "loss": 0.386, + "step": 4114 + }, + { + "epoch": 0.5483742004264393, + "grad_norm": 0.2928297357933255, + "learning_rate": 9.334688606562634e-06, + "loss": 0.3813, + "step": 4115 + }, + { + "epoch": 0.5485074626865671, + "grad_norm": 0.297106677292881, + "learning_rate": 9.334333678075582e-06, + "loss": 0.4476, + "step": 4116 + }, + { + "epoch": 0.5486407249466951, + "grad_norm": 0.3121506736100921, + "learning_rate": 9.333978661692008e-06, + "loss": 0.4431, + "step": 4117 + }, + { + "epoch": 0.548773987206823, + "grad_norm": 0.30377225480938247, + "learning_rate": 9.333623557419109e-06, + "loss": 0.4004, + "step": 4118 + }, + { + "epoch": 0.5489072494669509, + "grad_norm": 0.29541266215652684, + "learning_rate": 9.333268365264088e-06, + "loss": 0.3971, + "step": 4119 + }, + { + "epoch": 0.5490405117270789, + "grad_norm": 0.3372608203543863, + "learning_rate": 9.332913085234148e-06, + "loss": 0.4786, + "step": 4120 + }, + { + "epoch": 0.5491737739872068, + "grad_norm": 0.30391447614308, + "learning_rate": 9.33255771733649e-06, + "loss": 0.3844, + "step": 4121 + }, + { + "epoch": 0.5493070362473348, + "grad_norm": 0.3113887872943458, + "learning_rate": 9.332202261578327e-06, + "loss": 0.3867, + "step": 4122 + }, + { + "epoch": 0.5494402985074627, + "grad_norm": 0.30539585066656133, + "learning_rate": 9.331846717966861e-06, + "loss": 0.4229, + "step": 4123 + }, + { + "epoch": 0.5495735607675906, + "grad_norm": 0.32529860521050974, + "learning_rate": 9.331491086509307e-06, + "loss": 0.4262, + "step": 4124 + }, + { + "epoch": 0.5497068230277186, + "grad_norm": 0.3107001516535157, + "learning_rate": 9.331135367212874e-06, + "loss": 0.4033, + "step": 4125 + }, + { + "epoch": 0.5498400852878464, + "grad_norm": 0.3165824591606159, + "learning_rate": 9.330779560084778e-06, + "loss": 0.3864, + "step": 4126 + }, + { + "epoch": 0.5499733475479744, + "grad_norm": 0.27743431544537683, + "learning_rate": 9.33042366513223e-06, + "loss": 0.346, + "step": 4127 + }, + { + "epoch": 0.5501066098081023, + "grad_norm": 0.31819473143284943, + "learning_rate": 9.330067682362451e-06, + "loss": 0.4681, + "step": 4128 + }, + { + "epoch": 0.5502398720682303, + "grad_norm": 0.32297924737053546, + "learning_rate": 9.329711611782662e-06, + "loss": 0.4062, + "step": 4129 + }, + { + "epoch": 0.5503731343283582, + "grad_norm": 0.30779631043041317, + "learning_rate": 9.329355453400077e-06, + "loss": 0.4074, + "step": 4130 + }, + { + "epoch": 0.5505063965884861, + "grad_norm": 0.3119978264207765, + "learning_rate": 9.328999207221925e-06, + "loss": 0.3872, + "step": 4131 + }, + { + "epoch": 0.5506396588486141, + "grad_norm": 0.3000040175317837, + "learning_rate": 9.32864287325543e-06, + "loss": 0.4049, + "step": 4132 + }, + { + "epoch": 0.550772921108742, + "grad_norm": 0.30267907576605707, + "learning_rate": 9.328286451507813e-06, + "loss": 0.3763, + "step": 4133 + }, + { + "epoch": 0.55090618336887, + "grad_norm": 0.2951953131844107, + "learning_rate": 9.327929941986305e-06, + "loss": 0.4467, + "step": 4134 + }, + { + "epoch": 0.5510394456289979, + "grad_norm": 0.2938606750105366, + "learning_rate": 9.327573344698138e-06, + "loss": 0.3763, + "step": 4135 + }, + { + "epoch": 0.5511727078891258, + "grad_norm": 0.2981520930394845, + "learning_rate": 9.32721665965054e-06, + "loss": 0.4228, + "step": 4136 + }, + { + "epoch": 0.5513059701492538, + "grad_norm": 0.3020087590858695, + "learning_rate": 9.326859886850745e-06, + "loss": 0.4541, + "step": 4137 + }, + { + "epoch": 0.5514392324093816, + "grad_norm": 0.3030231920617196, + "learning_rate": 9.326503026305988e-06, + "loss": 0.4537, + "step": 4138 + }, + { + "epoch": 0.5515724946695096, + "grad_norm": 0.29377172007458224, + "learning_rate": 9.326146078023508e-06, + "loss": 0.4265, + "step": 4139 + }, + { + "epoch": 0.5517057569296375, + "grad_norm": 0.2935357959715923, + "learning_rate": 9.325789042010542e-06, + "loss": 0.405, + "step": 4140 + }, + { + "epoch": 0.5518390191897654, + "grad_norm": 0.3022653673254795, + "learning_rate": 9.32543191827433e-06, + "loss": 0.4511, + "step": 4141 + }, + { + "epoch": 0.5519722814498934, + "grad_norm": 0.3057318500173686, + "learning_rate": 9.325074706822113e-06, + "loss": 0.4268, + "step": 4142 + }, + { + "epoch": 0.5521055437100213, + "grad_norm": 0.30024330243850783, + "learning_rate": 9.324717407661139e-06, + "loss": 0.4605, + "step": 4143 + }, + { + "epoch": 0.5522388059701493, + "grad_norm": 0.30003130848155163, + "learning_rate": 9.324360020798649e-06, + "loss": 0.3699, + "step": 4144 + }, + { + "epoch": 0.5523720682302772, + "grad_norm": 0.2997811371885642, + "learning_rate": 9.324002546241895e-06, + "loss": 0.3722, + "step": 4145 + }, + { + "epoch": 0.5525053304904051, + "grad_norm": 0.3088497081305803, + "learning_rate": 9.323644983998121e-06, + "loss": 0.4098, + "step": 4146 + }, + { + "epoch": 0.5526385927505331, + "grad_norm": 0.32914629976978005, + "learning_rate": 9.323287334074584e-06, + "loss": 0.5299, + "step": 4147 + }, + { + "epoch": 0.552771855010661, + "grad_norm": 0.32115999950832763, + "learning_rate": 9.32292959647853e-06, + "loss": 0.531, + "step": 4148 + }, + { + "epoch": 0.552905117270789, + "grad_norm": 0.2964172169599508, + "learning_rate": 9.322571771217222e-06, + "loss": 0.3702, + "step": 4149 + }, + { + "epoch": 0.5530383795309168, + "grad_norm": 0.3157810676684566, + "learning_rate": 9.32221385829791e-06, + "loss": 0.3232, + "step": 4150 + }, + { + "epoch": 0.5531716417910447, + "grad_norm": 0.3339995640341295, + "learning_rate": 9.321855857727854e-06, + "loss": 0.4048, + "step": 4151 + }, + { + "epoch": 0.5533049040511727, + "grad_norm": 0.3150541342663874, + "learning_rate": 9.321497769514314e-06, + "loss": 0.4419, + "step": 4152 + }, + { + "epoch": 0.5534381663113006, + "grad_norm": 0.3237642304579031, + "learning_rate": 9.32113959366455e-06, + "loss": 0.4058, + "step": 4153 + }, + { + "epoch": 0.5535714285714286, + "grad_norm": 0.33234726447988694, + "learning_rate": 9.320781330185828e-06, + "loss": 0.42, + "step": 4154 + }, + { + "epoch": 0.5537046908315565, + "grad_norm": 0.3107883678819548, + "learning_rate": 9.320422979085414e-06, + "loss": 0.5488, + "step": 4155 + }, + { + "epoch": 0.5538379530916845, + "grad_norm": 0.30579306918701793, + "learning_rate": 9.320064540370573e-06, + "loss": 0.5467, + "step": 4156 + }, + { + "epoch": 0.5539712153518124, + "grad_norm": 0.3424644510465776, + "learning_rate": 9.319706014048573e-06, + "loss": 0.3714, + "step": 4157 + }, + { + "epoch": 0.5541044776119403, + "grad_norm": 0.3002559353889269, + "learning_rate": 9.319347400126686e-06, + "loss": 0.374, + "step": 4158 + }, + { + "epoch": 0.5542377398720683, + "grad_norm": 0.32353105728596315, + "learning_rate": 9.318988698612186e-06, + "loss": 0.4684, + "step": 4159 + }, + { + "epoch": 0.5543710021321961, + "grad_norm": 0.29600531850732786, + "learning_rate": 9.318629909512344e-06, + "loss": 0.3845, + "step": 4160 + }, + { + "epoch": 0.5545042643923241, + "grad_norm": 0.29280778564925775, + "learning_rate": 9.318271032834437e-06, + "loss": 0.423, + "step": 4161 + }, + { + "epoch": 0.554637526652452, + "grad_norm": 0.30706626849776875, + "learning_rate": 9.317912068585744e-06, + "loss": 0.4305, + "step": 4162 + }, + { + "epoch": 0.5547707889125799, + "grad_norm": 0.29956955427796816, + "learning_rate": 9.317553016773543e-06, + "loss": 0.387, + "step": 4163 + }, + { + "epoch": 0.5549040511727079, + "grad_norm": 0.3131270463967278, + "learning_rate": 9.317193877405116e-06, + "loss": 0.4144, + "step": 4164 + }, + { + "epoch": 0.5550373134328358, + "grad_norm": 0.2992521370261341, + "learning_rate": 9.316834650487746e-06, + "loss": 0.4122, + "step": 4165 + }, + { + "epoch": 0.5551705756929638, + "grad_norm": 0.3123525466001825, + "learning_rate": 9.316475336028717e-06, + "loss": 0.4555, + "step": 4166 + }, + { + "epoch": 0.5553038379530917, + "grad_norm": 0.3089170297519453, + "learning_rate": 9.316115934035316e-06, + "loss": 0.4646, + "step": 4167 + }, + { + "epoch": 0.5554371002132196, + "grad_norm": 0.306846612531139, + "learning_rate": 9.315756444514835e-06, + "loss": 0.564, + "step": 4168 + }, + { + "epoch": 0.5555703624733476, + "grad_norm": 0.312129279470961, + "learning_rate": 9.315396867474557e-06, + "loss": 0.4251, + "step": 4169 + }, + { + "epoch": 0.5557036247334755, + "grad_norm": 0.30834656794147053, + "learning_rate": 9.315037202921778e-06, + "loss": 0.3789, + "step": 4170 + }, + { + "epoch": 0.5558368869936035, + "grad_norm": 0.3233627186094929, + "learning_rate": 9.314677450863792e-06, + "loss": 0.4085, + "step": 4171 + }, + { + "epoch": 0.5559701492537313, + "grad_norm": 0.32208725019378526, + "learning_rate": 9.314317611307894e-06, + "loss": 0.4525, + "step": 4172 + }, + { + "epoch": 0.5561034115138592, + "grad_norm": 0.32236503684015066, + "learning_rate": 9.31395768426138e-06, + "loss": 0.4297, + "step": 4173 + }, + { + "epoch": 0.5562366737739872, + "grad_norm": 0.3048815977988327, + "learning_rate": 9.313597669731552e-06, + "loss": 0.403, + "step": 4174 + }, + { + "epoch": 0.5563699360341151, + "grad_norm": 0.2820841123362094, + "learning_rate": 9.313237567725709e-06, + "loss": 0.4014, + "step": 4175 + }, + { + "epoch": 0.5565031982942431, + "grad_norm": 0.29977579610404204, + "learning_rate": 9.31287737825115e-06, + "loss": 0.4395, + "step": 4176 + }, + { + "epoch": 0.556636460554371, + "grad_norm": 0.3210270404580631, + "learning_rate": 9.312517101315185e-06, + "loss": 0.4415, + "step": 4177 + }, + { + "epoch": 0.5567697228144989, + "grad_norm": 0.3036414451886915, + "learning_rate": 9.312156736925117e-06, + "loss": 0.4812, + "step": 4178 + }, + { + "epoch": 0.5569029850746269, + "grad_norm": 0.2963404930189992, + "learning_rate": 9.311796285088258e-06, + "loss": 0.3684, + "step": 4179 + }, + { + "epoch": 0.5570362473347548, + "grad_norm": 0.2988923805258216, + "learning_rate": 9.31143574581191e-06, + "loss": 0.3764, + "step": 4180 + }, + { + "epoch": 0.5571695095948828, + "grad_norm": 0.30055133737638207, + "learning_rate": 9.31107511910339e-06, + "loss": 0.4037, + "step": 4181 + }, + { + "epoch": 0.5573027718550106, + "grad_norm": 0.31234804746384215, + "learning_rate": 9.310714404970012e-06, + "loss": 0.4476, + "step": 4182 + }, + { + "epoch": 0.5574360341151386, + "grad_norm": 0.30401829188060064, + "learning_rate": 9.310353603419087e-06, + "loss": 0.4203, + "step": 4183 + }, + { + "epoch": 0.5575692963752665, + "grad_norm": 0.29403985429600776, + "learning_rate": 9.309992714457933e-06, + "loss": 0.4528, + "step": 4184 + }, + { + "epoch": 0.5577025586353944, + "grad_norm": 0.28802477510619, + "learning_rate": 9.30963173809387e-06, + "loss": 0.3791, + "step": 4185 + }, + { + "epoch": 0.5578358208955224, + "grad_norm": 0.2930734089702176, + "learning_rate": 9.309270674334217e-06, + "loss": 0.3883, + "step": 4186 + }, + { + "epoch": 0.5579690831556503, + "grad_norm": 0.30615639339935385, + "learning_rate": 9.308909523186298e-06, + "loss": 0.4491, + "step": 4187 + }, + { + "epoch": 0.5581023454157783, + "grad_norm": 0.30294359739537613, + "learning_rate": 9.308548284657433e-06, + "loss": 0.4089, + "step": 4188 + }, + { + "epoch": 0.5582356076759062, + "grad_norm": 0.331711593235351, + "learning_rate": 9.308186958754952e-06, + "loss": 0.3871, + "step": 4189 + }, + { + "epoch": 0.5583688699360341, + "grad_norm": 0.2891946399151122, + "learning_rate": 9.30782554548618e-06, + "loss": 0.391, + "step": 4190 + }, + { + "epoch": 0.5585021321961621, + "grad_norm": 0.30193810339801436, + "learning_rate": 9.307464044858447e-06, + "loss": 0.4067, + "step": 4191 + }, + { + "epoch": 0.55863539445629, + "grad_norm": 0.284441323986355, + "learning_rate": 9.307102456879082e-06, + "loss": 0.3902, + "step": 4192 + }, + { + "epoch": 0.558768656716418, + "grad_norm": 0.3042655163680413, + "learning_rate": 9.30674078155542e-06, + "loss": 0.4494, + "step": 4193 + }, + { + "epoch": 0.5589019189765458, + "grad_norm": 0.2929076463240345, + "learning_rate": 9.306379018894793e-06, + "loss": 0.4157, + "step": 4194 + }, + { + "epoch": 0.5590351812366737, + "grad_norm": 0.2923919394770715, + "learning_rate": 9.30601716890454e-06, + "loss": 0.4382, + "step": 4195 + }, + { + "epoch": 0.5591684434968017, + "grad_norm": 0.30032226776558485, + "learning_rate": 9.305655231591998e-06, + "loss": 0.4616, + "step": 4196 + }, + { + "epoch": 0.5593017057569296, + "grad_norm": 0.29709511424345314, + "learning_rate": 9.305293206964508e-06, + "loss": 0.3818, + "step": 4197 + }, + { + "epoch": 0.5594349680170576, + "grad_norm": 0.2865942070673364, + "learning_rate": 9.304931095029407e-06, + "loss": 0.407, + "step": 4198 + }, + { + "epoch": 0.5595682302771855, + "grad_norm": 0.3132619023133202, + "learning_rate": 9.304568895794044e-06, + "loss": 0.4364, + "step": 4199 + }, + { + "epoch": 0.5597014925373134, + "grad_norm": 0.29198675022378157, + "learning_rate": 9.304206609265759e-06, + "loss": 0.4526, + "step": 4200 + }, + { + "epoch": 0.5598347547974414, + "grad_norm": 0.31286893879574673, + "learning_rate": 9.303844235451902e-06, + "loss": 0.3672, + "step": 4201 + }, + { + "epoch": 0.5599680170575693, + "grad_norm": 0.2926211084784335, + "learning_rate": 9.303481774359822e-06, + "loss": 0.385, + "step": 4202 + }, + { + "epoch": 0.5601012793176973, + "grad_norm": 0.296526619023565, + "learning_rate": 9.303119225996869e-06, + "loss": 0.4008, + "step": 4203 + }, + { + "epoch": 0.5602345415778252, + "grad_norm": 0.31142101918060344, + "learning_rate": 9.302756590370394e-06, + "loss": 0.4235, + "step": 4204 + }, + { + "epoch": 0.560367803837953, + "grad_norm": 0.28277102358514694, + "learning_rate": 9.302393867487751e-06, + "loss": 0.4388, + "step": 4205 + }, + { + "epoch": 0.560501066098081, + "grad_norm": 0.29646294515213095, + "learning_rate": 9.302031057356295e-06, + "loss": 0.406, + "step": 4206 + }, + { + "epoch": 0.5606343283582089, + "grad_norm": 0.3049404358521109, + "learning_rate": 9.301668159983387e-06, + "loss": 0.4051, + "step": 4207 + }, + { + "epoch": 0.5607675906183369, + "grad_norm": 0.3053830672411501, + "learning_rate": 9.301305175376383e-06, + "loss": 0.4886, + "step": 4208 + }, + { + "epoch": 0.5609008528784648, + "grad_norm": 0.3017749592459168, + "learning_rate": 9.300942103542645e-06, + "loss": 0.5588, + "step": 4209 + }, + { + "epoch": 0.5610341151385928, + "grad_norm": 0.2990555195099179, + "learning_rate": 9.300578944489536e-06, + "loss": 0.411, + "step": 4210 + }, + { + "epoch": 0.5611673773987207, + "grad_norm": 0.3041801326914281, + "learning_rate": 9.30021569822442e-06, + "loss": 0.3668, + "step": 4211 + }, + { + "epoch": 0.5613006396588486, + "grad_norm": 0.30481630865239384, + "learning_rate": 9.299852364754662e-06, + "loss": 0.491, + "step": 4212 + }, + { + "epoch": 0.5614339019189766, + "grad_norm": 0.2905257684580788, + "learning_rate": 9.299488944087634e-06, + "loss": 0.5307, + "step": 4213 + }, + { + "epoch": 0.5615671641791045, + "grad_norm": 0.30917609926516715, + "learning_rate": 9.299125436230703e-06, + "loss": 0.4131, + "step": 4214 + }, + { + "epoch": 0.5617004264392325, + "grad_norm": 0.29501308897255085, + "learning_rate": 9.29876184119124e-06, + "loss": 0.5175, + "step": 4215 + }, + { + "epoch": 0.5618336886993603, + "grad_norm": 0.2852555775269226, + "learning_rate": 9.29839815897662e-06, + "loss": 0.3844, + "step": 4216 + }, + { + "epoch": 0.5619669509594882, + "grad_norm": 0.32345502520043323, + "learning_rate": 9.298034389594218e-06, + "loss": 0.404, + "step": 4217 + }, + { + "epoch": 0.5621002132196162, + "grad_norm": 0.3085403899366482, + "learning_rate": 9.29767053305141e-06, + "loss": 0.4543, + "step": 4218 + }, + { + "epoch": 0.5622334754797441, + "grad_norm": 0.3109405748011334, + "learning_rate": 9.297306589355577e-06, + "loss": 0.4154, + "step": 4219 + }, + { + "epoch": 0.5623667377398721, + "grad_norm": 0.3042128130086737, + "learning_rate": 9.296942558514097e-06, + "loss": 0.4131, + "step": 4220 + }, + { + "epoch": 0.5625, + "grad_norm": 0.29037069107873514, + "learning_rate": 9.296578440534351e-06, + "loss": 0.3932, + "step": 4221 + }, + { + "epoch": 0.5626332622601279, + "grad_norm": 0.29992030213578513, + "learning_rate": 9.296214235423727e-06, + "loss": 0.3962, + "step": 4222 + }, + { + "epoch": 0.5627665245202559, + "grad_norm": 0.29939546621427177, + "learning_rate": 9.295849943189609e-06, + "loss": 0.4122, + "step": 4223 + }, + { + "epoch": 0.5628997867803838, + "grad_norm": 0.31956304981768724, + "learning_rate": 9.295485563839384e-06, + "loss": 0.3993, + "step": 4224 + }, + { + "epoch": 0.5630330490405118, + "grad_norm": 0.29528139196793446, + "learning_rate": 9.295121097380441e-06, + "loss": 0.4103, + "step": 4225 + }, + { + "epoch": 0.5631663113006397, + "grad_norm": 0.28796206849207373, + "learning_rate": 9.294756543820171e-06, + "loss": 0.4886, + "step": 4226 + }, + { + "epoch": 0.5632995735607675, + "grad_norm": 0.2885235158370423, + "learning_rate": 9.294391903165969e-06, + "loss": 0.3466, + "step": 4227 + }, + { + "epoch": 0.5634328358208955, + "grad_norm": 0.3118798173007294, + "learning_rate": 9.294027175425228e-06, + "loss": 0.382, + "step": 4228 + }, + { + "epoch": 0.5635660980810234, + "grad_norm": 0.30729405164235113, + "learning_rate": 9.293662360605344e-06, + "loss": 0.4615, + "step": 4229 + }, + { + "epoch": 0.5636993603411514, + "grad_norm": 0.31629897852552435, + "learning_rate": 9.293297458713715e-06, + "loss": 0.4734, + "step": 4230 + }, + { + "epoch": 0.5638326226012793, + "grad_norm": 0.30411316374659475, + "learning_rate": 9.292932469757743e-06, + "loss": 0.4476, + "step": 4231 + }, + { + "epoch": 0.5639658848614072, + "grad_norm": 0.34723805144952, + "learning_rate": 9.292567393744827e-06, + "loss": 0.4335, + "step": 4232 + }, + { + "epoch": 0.5640991471215352, + "grad_norm": 0.3010414092122208, + "learning_rate": 9.292202230682372e-06, + "loss": 0.4142, + "step": 4233 + }, + { + "epoch": 0.5642324093816631, + "grad_norm": 0.3022253928068139, + "learning_rate": 9.291836980577781e-06, + "loss": 0.4342, + "step": 4234 + }, + { + "epoch": 0.5643656716417911, + "grad_norm": 0.28905384613364893, + "learning_rate": 9.291471643438465e-06, + "loss": 0.4, + "step": 4235 + }, + { + "epoch": 0.564498933901919, + "grad_norm": 0.3049012555143693, + "learning_rate": 9.291106219271829e-06, + "loss": 0.4218, + "step": 4236 + }, + { + "epoch": 0.564632196162047, + "grad_norm": 0.298192116894071, + "learning_rate": 9.290740708085285e-06, + "loss": 0.4069, + "step": 4237 + }, + { + "epoch": 0.5647654584221748, + "grad_norm": 0.30694336335458267, + "learning_rate": 9.290375109886247e-06, + "loss": 0.4085, + "step": 4238 + }, + { + "epoch": 0.5648987206823027, + "grad_norm": 0.30414695374645884, + "learning_rate": 9.290009424682125e-06, + "loss": 0.3649, + "step": 4239 + }, + { + "epoch": 0.5650319829424307, + "grad_norm": 0.30553596823358226, + "learning_rate": 9.289643652480337e-06, + "loss": 0.3952, + "step": 4240 + }, + { + "epoch": 0.5651652452025586, + "grad_norm": 0.30857924074049076, + "learning_rate": 9.289277793288302e-06, + "loss": 0.3586, + "step": 4241 + }, + { + "epoch": 0.5652985074626866, + "grad_norm": 0.29324620636644533, + "learning_rate": 9.288911847113436e-06, + "loss": 0.4196, + "step": 4242 + }, + { + "epoch": 0.5654317697228145, + "grad_norm": 0.30633916697796976, + "learning_rate": 9.288545813963164e-06, + "loss": 0.4167, + "step": 4243 + }, + { + "epoch": 0.5655650319829424, + "grad_norm": 0.29693668870706563, + "learning_rate": 9.288179693844905e-06, + "loss": 0.4046, + "step": 4244 + }, + { + "epoch": 0.5656982942430704, + "grad_norm": 0.2754937682774936, + "learning_rate": 9.287813486766086e-06, + "loss": 0.3891, + "step": 4245 + }, + { + "epoch": 0.5658315565031983, + "grad_norm": 0.31991093848872404, + "learning_rate": 9.287447192734131e-06, + "loss": 0.5443, + "step": 4246 + }, + { + "epoch": 0.5659648187633263, + "grad_norm": 0.30625133710673985, + "learning_rate": 9.287080811756473e-06, + "loss": 0.4179, + "step": 4247 + }, + { + "epoch": 0.5660980810234542, + "grad_norm": 0.2804804216192961, + "learning_rate": 9.286714343840537e-06, + "loss": 0.4621, + "step": 4248 + }, + { + "epoch": 0.566231343283582, + "grad_norm": 0.2999505808387833, + "learning_rate": 9.286347788993755e-06, + "loss": 0.4532, + "step": 4249 + }, + { + "epoch": 0.56636460554371, + "grad_norm": 0.2820903775753632, + "learning_rate": 9.285981147223564e-06, + "loss": 0.4385, + "step": 4250 + }, + { + "epoch": 0.5664978678038379, + "grad_norm": 0.3303236283645343, + "learning_rate": 9.285614418537395e-06, + "loss": 0.3991, + "step": 4251 + }, + { + "epoch": 0.5666311300639659, + "grad_norm": 0.2913000433940295, + "learning_rate": 9.28524760294269e-06, + "loss": 0.3714, + "step": 4252 + }, + { + "epoch": 0.5667643923240938, + "grad_norm": 0.3241696068533316, + "learning_rate": 9.28488070044688e-06, + "loss": 0.4744, + "step": 4253 + }, + { + "epoch": 0.5668976545842217, + "grad_norm": 0.3116414719588649, + "learning_rate": 9.284513711057413e-06, + "loss": 0.5207, + "step": 4254 + }, + { + "epoch": 0.5670309168443497, + "grad_norm": 0.30200018347899826, + "learning_rate": 9.284146634781728e-06, + "loss": 0.4311, + "step": 4255 + }, + { + "epoch": 0.5671641791044776, + "grad_norm": 0.3048798167224883, + "learning_rate": 9.283779471627267e-06, + "loss": 0.5071, + "step": 4256 + }, + { + "epoch": 0.5672974413646056, + "grad_norm": 0.2931635370247949, + "learning_rate": 9.28341222160148e-06, + "loss": 0.3652, + "step": 4257 + }, + { + "epoch": 0.5674307036247335, + "grad_norm": 0.2997525970915807, + "learning_rate": 9.283044884711813e-06, + "loss": 0.4474, + "step": 4258 + }, + { + "epoch": 0.5675639658848614, + "grad_norm": 0.2968000805239186, + "learning_rate": 9.282677460965713e-06, + "loss": 0.4056, + "step": 4259 + }, + { + "epoch": 0.5676972281449894, + "grad_norm": 0.2835674768389855, + "learning_rate": 9.282309950370634e-06, + "loss": 0.4557, + "step": 4260 + }, + { + "epoch": 0.5678304904051172, + "grad_norm": 0.28802433069007277, + "learning_rate": 9.281942352934028e-06, + "loss": 0.4101, + "step": 4261 + }, + { + "epoch": 0.5679637526652452, + "grad_norm": 0.27892482742631114, + "learning_rate": 9.281574668663348e-06, + "loss": 0.3849, + "step": 4262 + }, + { + "epoch": 0.5680970149253731, + "grad_norm": 0.288367948078906, + "learning_rate": 9.281206897566052e-06, + "loss": 0.3867, + "step": 4263 + }, + { + "epoch": 0.5682302771855011, + "grad_norm": 0.29712056222146865, + "learning_rate": 9.280839039649598e-06, + "loss": 0.3936, + "step": 4264 + }, + { + "epoch": 0.568363539445629, + "grad_norm": 0.3226504887207955, + "learning_rate": 9.280471094921444e-06, + "loss": 0.3737, + "step": 4265 + }, + { + "epoch": 0.5684968017057569, + "grad_norm": 0.3049571761880182, + "learning_rate": 9.280103063389055e-06, + "loss": 0.4413, + "step": 4266 + }, + { + "epoch": 0.5686300639658849, + "grad_norm": 0.30128287639621676, + "learning_rate": 9.27973494505989e-06, + "loss": 0.4131, + "step": 4267 + }, + { + "epoch": 0.5687633262260128, + "grad_norm": 0.29560995525307837, + "learning_rate": 9.279366739941418e-06, + "loss": 0.3908, + "step": 4268 + }, + { + "epoch": 0.5688965884861408, + "grad_norm": 0.3191893133784181, + "learning_rate": 9.278998448041105e-06, + "loss": 0.4583, + "step": 4269 + }, + { + "epoch": 0.5690298507462687, + "grad_norm": 0.3001153278441784, + "learning_rate": 9.278630069366418e-06, + "loss": 0.4342, + "step": 4270 + }, + { + "epoch": 0.5691631130063965, + "grad_norm": 0.3071348925616083, + "learning_rate": 9.278261603924827e-06, + "loss": 0.3708, + "step": 4271 + }, + { + "epoch": 0.5692963752665245, + "grad_norm": 0.2882125480096824, + "learning_rate": 9.277893051723808e-06, + "loss": 0.3782, + "step": 4272 + }, + { + "epoch": 0.5694296375266524, + "grad_norm": 0.2997316621240523, + "learning_rate": 9.27752441277083e-06, + "loss": 0.393, + "step": 4273 + }, + { + "epoch": 0.5695628997867804, + "grad_norm": 0.3150644738065403, + "learning_rate": 9.277155687073374e-06, + "loss": 0.5139, + "step": 4274 + }, + { + "epoch": 0.5696961620469083, + "grad_norm": 0.3098884225904476, + "learning_rate": 9.276786874638912e-06, + "loss": 0.4232, + "step": 4275 + }, + { + "epoch": 0.5698294243070362, + "grad_norm": 0.29856526646299014, + "learning_rate": 9.276417975474927e-06, + "loss": 0.4062, + "step": 4276 + }, + { + "epoch": 0.5699626865671642, + "grad_norm": 0.3072493466301344, + "learning_rate": 9.2760489895889e-06, + "loss": 0.3907, + "step": 4277 + }, + { + "epoch": 0.5700959488272921, + "grad_norm": 0.2901776347712786, + "learning_rate": 9.27567991698831e-06, + "loss": 0.3663, + "step": 4278 + }, + { + "epoch": 0.5702292110874201, + "grad_norm": 0.3047597947447709, + "learning_rate": 9.275310757680646e-06, + "loss": 0.3825, + "step": 4279 + }, + { + "epoch": 0.570362473347548, + "grad_norm": 0.2951640275109556, + "learning_rate": 9.274941511673391e-06, + "loss": 0.3829, + "step": 4280 + }, + { + "epoch": 0.5704957356076759, + "grad_norm": 0.30263075377558274, + "learning_rate": 9.274572178974034e-06, + "loss": 0.4617, + "step": 4281 + }, + { + "epoch": 0.5706289978678039, + "grad_norm": 0.3405580375295882, + "learning_rate": 9.274202759590066e-06, + "loss": 0.5028, + "step": 4282 + }, + { + "epoch": 0.5707622601279317, + "grad_norm": 0.3086557985173903, + "learning_rate": 9.273833253528977e-06, + "loss": 0.4074, + "step": 4283 + }, + { + "epoch": 0.5708955223880597, + "grad_norm": 0.29129477835535506, + "learning_rate": 9.273463660798258e-06, + "loss": 0.3806, + "step": 4284 + }, + { + "epoch": 0.5710287846481876, + "grad_norm": 0.28630846837197205, + "learning_rate": 9.27309398140541e-06, + "loss": 0.3912, + "step": 4285 + }, + { + "epoch": 0.5711620469083155, + "grad_norm": 0.30787318777846223, + "learning_rate": 9.272724215357926e-06, + "loss": 0.427, + "step": 4286 + }, + { + "epoch": 0.5712953091684435, + "grad_norm": 0.29323221078318007, + "learning_rate": 9.272354362663303e-06, + "loss": 0.3692, + "step": 4287 + }, + { + "epoch": 0.5714285714285714, + "grad_norm": 0.3171282606507464, + "learning_rate": 9.271984423329045e-06, + "loss": 0.431, + "step": 4288 + }, + { + "epoch": 0.5715618336886994, + "grad_norm": 0.2917343779798907, + "learning_rate": 9.271614397362652e-06, + "loss": 0.4535, + "step": 4289 + }, + { + "epoch": 0.5716950959488273, + "grad_norm": 0.31202935089314693, + "learning_rate": 9.271244284771627e-06, + "loss": 0.3911, + "step": 4290 + }, + { + "epoch": 0.5718283582089553, + "grad_norm": 0.29324078351819277, + "learning_rate": 9.270874085563479e-06, + "loss": 0.4485, + "step": 4291 + }, + { + "epoch": 0.5719616204690832, + "grad_norm": 0.29713365811817616, + "learning_rate": 9.270503799745712e-06, + "loss": 0.382, + "step": 4292 + }, + { + "epoch": 0.572094882729211, + "grad_norm": 0.31945417744153237, + "learning_rate": 9.270133427325835e-06, + "loss": 0.4501, + "step": 4293 + }, + { + "epoch": 0.572228144989339, + "grad_norm": 0.3016490898340514, + "learning_rate": 9.26976296831136e-06, + "loss": 0.507, + "step": 4294 + }, + { + "epoch": 0.5723614072494669, + "grad_norm": 0.31197448938939754, + "learning_rate": 9.269392422709801e-06, + "loss": 0.4054, + "step": 4295 + }, + { + "epoch": 0.5724946695095949, + "grad_norm": 0.33053594977019735, + "learning_rate": 9.26902179052867e-06, + "loss": 0.3864, + "step": 4296 + }, + { + "epoch": 0.5726279317697228, + "grad_norm": 0.31056124021400505, + "learning_rate": 9.268651071775482e-06, + "loss": 0.4126, + "step": 4297 + }, + { + "epoch": 0.5727611940298507, + "grad_norm": 0.3194399224617017, + "learning_rate": 9.26828026645776e-06, + "loss": 0.3954, + "step": 4298 + }, + { + "epoch": 0.5728944562899787, + "grad_norm": 0.33171615660494413, + "learning_rate": 9.267909374583019e-06, + "loss": 0.4596, + "step": 4299 + }, + { + "epoch": 0.5730277185501066, + "grad_norm": 0.30002808238423506, + "learning_rate": 9.267538396158781e-06, + "loss": 0.4197, + "step": 4300 + }, + { + "epoch": 0.5731609808102346, + "grad_norm": 0.2909901936019757, + "learning_rate": 9.267167331192572e-06, + "loss": 0.3841, + "step": 4301 + }, + { + "epoch": 0.5732942430703625, + "grad_norm": 0.3036085578329698, + "learning_rate": 9.266796179691914e-06, + "loss": 0.4308, + "step": 4302 + }, + { + "epoch": 0.5734275053304904, + "grad_norm": 0.3035977488923226, + "learning_rate": 9.266424941664334e-06, + "loss": 0.3827, + "step": 4303 + }, + { + "epoch": 0.5735607675906184, + "grad_norm": 0.31080385185978443, + "learning_rate": 9.26605361711736e-06, + "loss": 0.4303, + "step": 4304 + }, + { + "epoch": 0.5736940298507462, + "grad_norm": 0.29809373325567595, + "learning_rate": 9.265682206058524e-06, + "loss": 0.3949, + "step": 4305 + }, + { + "epoch": 0.5738272921108742, + "grad_norm": 0.29569696436724646, + "learning_rate": 9.265310708495357e-06, + "loss": 0.3798, + "step": 4306 + }, + { + "epoch": 0.5739605543710021, + "grad_norm": 0.2957627641655612, + "learning_rate": 9.264939124435391e-06, + "loss": 0.4161, + "step": 4307 + }, + { + "epoch": 0.57409381663113, + "grad_norm": 0.31149687757795474, + "learning_rate": 9.264567453886165e-06, + "loss": 0.5262, + "step": 4308 + }, + { + "epoch": 0.574227078891258, + "grad_norm": 0.2959325978142516, + "learning_rate": 9.264195696855212e-06, + "loss": 0.4433, + "step": 4309 + }, + { + "epoch": 0.5743603411513859, + "grad_norm": 0.30644538552921236, + "learning_rate": 9.263823853350074e-06, + "loss": 0.4499, + "step": 4310 + }, + { + "epoch": 0.5744936034115139, + "grad_norm": 0.2998945760792872, + "learning_rate": 9.26345192337829e-06, + "loss": 0.3912, + "step": 4311 + }, + { + "epoch": 0.5746268656716418, + "grad_norm": 0.29781872361326694, + "learning_rate": 9.263079906947403e-06, + "loss": 0.4459, + "step": 4312 + }, + { + "epoch": 0.5747601279317697, + "grad_norm": 0.29471290532447886, + "learning_rate": 9.262707804064956e-06, + "loss": 0.3716, + "step": 4313 + }, + { + "epoch": 0.5748933901918977, + "grad_norm": 0.3096549470933574, + "learning_rate": 9.262335614738498e-06, + "loss": 0.4353, + "step": 4314 + }, + { + "epoch": 0.5750266524520256, + "grad_norm": 0.5586008306991315, + "learning_rate": 9.261963338975575e-06, + "loss": 0.3841, + "step": 4315 + }, + { + "epoch": 0.5751599147121536, + "grad_norm": 0.2919520333730535, + "learning_rate": 9.261590976783737e-06, + "loss": 0.4045, + "step": 4316 + }, + { + "epoch": 0.5752931769722814, + "grad_norm": 0.28042991763938646, + "learning_rate": 9.261218528170533e-06, + "loss": 0.3471, + "step": 4317 + }, + { + "epoch": 0.5754264392324094, + "grad_norm": 0.2920796405817095, + "learning_rate": 9.260845993143518e-06, + "loss": 0.4222, + "step": 4318 + }, + { + "epoch": 0.5755597014925373, + "grad_norm": 0.30447973967920117, + "learning_rate": 9.260473371710243e-06, + "loss": 0.3903, + "step": 4319 + }, + { + "epoch": 0.5756929637526652, + "grad_norm": 0.2890093891201857, + "learning_rate": 9.260100663878269e-06, + "loss": 0.4064, + "step": 4320 + }, + { + "epoch": 0.5758262260127932, + "grad_norm": 0.30617089792236774, + "learning_rate": 9.259727869655155e-06, + "loss": 0.4381, + "step": 4321 + }, + { + "epoch": 0.5759594882729211, + "grad_norm": 0.30439020183267956, + "learning_rate": 9.259354989048455e-06, + "loss": 0.4489, + "step": 4322 + }, + { + "epoch": 0.5760927505330491, + "grad_norm": 0.29191313806797486, + "learning_rate": 9.258982022065737e-06, + "loss": 0.4053, + "step": 4323 + }, + { + "epoch": 0.576226012793177, + "grad_norm": 0.29221132526558197, + "learning_rate": 9.258608968714561e-06, + "loss": 0.3423, + "step": 4324 + }, + { + "epoch": 0.5763592750533049, + "grad_norm": 0.29916266058285873, + "learning_rate": 9.258235829002494e-06, + "loss": 0.3861, + "step": 4325 + }, + { + "epoch": 0.5764925373134329, + "grad_norm": 0.33733346437866124, + "learning_rate": 9.2578626029371e-06, + "loss": 0.5141, + "step": 4326 + }, + { + "epoch": 0.5766257995735607, + "grad_norm": 0.2985784353355321, + "learning_rate": 9.257489290525949e-06, + "loss": 0.5501, + "step": 4327 + }, + { + "epoch": 0.5767590618336887, + "grad_norm": 0.30043627491966923, + "learning_rate": 9.257115891776613e-06, + "loss": 0.441, + "step": 4328 + }, + { + "epoch": 0.5768923240938166, + "grad_norm": 0.3122888760663614, + "learning_rate": 9.256742406696665e-06, + "loss": 0.4673, + "step": 4329 + }, + { + "epoch": 0.5770255863539445, + "grad_norm": 0.3021378861452271, + "learning_rate": 9.256368835293676e-06, + "loss": 0.4025, + "step": 4330 + }, + { + "epoch": 0.5771588486140725, + "grad_norm": 0.29858026015601136, + "learning_rate": 9.255995177575222e-06, + "loss": 0.3895, + "step": 4331 + }, + { + "epoch": 0.5772921108742004, + "grad_norm": 0.3082969911203288, + "learning_rate": 9.255621433548883e-06, + "loss": 0.4199, + "step": 4332 + }, + { + "epoch": 0.5774253731343284, + "grad_norm": 0.29111904283617324, + "learning_rate": 9.255247603222234e-06, + "loss": 0.4957, + "step": 4333 + }, + { + "epoch": 0.5775586353944563, + "grad_norm": 0.3119508317336123, + "learning_rate": 9.25487368660286e-06, + "loss": 0.4244, + "step": 4334 + }, + { + "epoch": 0.5776918976545842, + "grad_norm": 0.2820693879453226, + "learning_rate": 9.254499683698342e-06, + "loss": 0.3323, + "step": 4335 + }, + { + "epoch": 0.5778251599147122, + "grad_norm": 0.3173491638203787, + "learning_rate": 9.254125594516266e-06, + "loss": 0.4019, + "step": 4336 + }, + { + "epoch": 0.5779584221748401, + "grad_norm": 0.2917399673757159, + "learning_rate": 9.253751419064215e-06, + "loss": 0.3517, + "step": 4337 + }, + { + "epoch": 0.5780916844349681, + "grad_norm": 0.29856701686016696, + "learning_rate": 9.253377157349779e-06, + "loss": 0.4014, + "step": 4338 + }, + { + "epoch": 0.5782249466950959, + "grad_norm": 0.3284557214239416, + "learning_rate": 9.253002809380549e-06, + "loss": 0.4265, + "step": 4339 + }, + { + "epoch": 0.5783582089552238, + "grad_norm": 0.31469489428991926, + "learning_rate": 9.252628375164115e-06, + "loss": 0.4292, + "step": 4340 + }, + { + "epoch": 0.5784914712153518, + "grad_norm": 0.2884294624958398, + "learning_rate": 9.252253854708068e-06, + "loss": 0.3942, + "step": 4341 + }, + { + "epoch": 0.5786247334754797, + "grad_norm": 0.3310494441210565, + "learning_rate": 9.251879248020006e-06, + "loss": 0.3797, + "step": 4342 + }, + { + "epoch": 0.5787579957356077, + "grad_norm": 0.3203448526907549, + "learning_rate": 9.251504555107525e-06, + "loss": 0.4583, + "step": 4343 + }, + { + "epoch": 0.5788912579957356, + "grad_norm": 0.30671595334116, + "learning_rate": 9.251129775978223e-06, + "loss": 0.4453, + "step": 4344 + }, + { + "epoch": 0.5790245202558635, + "grad_norm": 0.7638012539297289, + "learning_rate": 9.250754910639701e-06, + "loss": 0.4408, + "step": 4345 + }, + { + "epoch": 0.5791577825159915, + "grad_norm": 0.31284860855966545, + "learning_rate": 9.25037995909956e-06, + "loss": 0.3643, + "step": 4346 + }, + { + "epoch": 0.5792910447761194, + "grad_norm": 0.31727928556013124, + "learning_rate": 9.250004921365405e-06, + "loss": 0.4962, + "step": 4347 + }, + { + "epoch": 0.5794243070362474, + "grad_norm": 0.3102731837868754, + "learning_rate": 9.24962979744484e-06, + "loss": 0.4502, + "step": 4348 + }, + { + "epoch": 0.5795575692963753, + "grad_norm": 0.30772563919884705, + "learning_rate": 9.249254587345472e-06, + "loss": 0.3838, + "step": 4349 + }, + { + "epoch": 0.5796908315565032, + "grad_norm": 0.33176918712972664, + "learning_rate": 9.248879291074912e-06, + "loss": 0.4745, + "step": 4350 + }, + { + "epoch": 0.5798240938166311, + "grad_norm": 0.3266240490229838, + "learning_rate": 9.248503908640768e-06, + "loss": 0.3849, + "step": 4351 + }, + { + "epoch": 0.579957356076759, + "grad_norm": 0.3127585379148585, + "learning_rate": 9.248128440050654e-06, + "loss": 0.3809, + "step": 4352 + }, + { + "epoch": 0.580090618336887, + "grad_norm": 0.3106772041275057, + "learning_rate": 9.247752885312184e-06, + "loss": 0.4237, + "step": 4353 + }, + { + "epoch": 0.5802238805970149, + "grad_norm": 0.29570530294818836, + "learning_rate": 9.247377244432974e-06, + "loss": 0.3659, + "step": 4354 + }, + { + "epoch": 0.5803571428571429, + "grad_norm": 0.30118543995860697, + "learning_rate": 9.247001517420643e-06, + "loss": 0.4426, + "step": 4355 + }, + { + "epoch": 0.5804904051172708, + "grad_norm": 0.29951601441889336, + "learning_rate": 9.246625704282807e-06, + "loss": 0.4006, + "step": 4356 + }, + { + "epoch": 0.5806236673773987, + "grad_norm": 0.30075072849839757, + "learning_rate": 9.24624980502709e-06, + "loss": 0.4827, + "step": 4357 + }, + { + "epoch": 0.5807569296375267, + "grad_norm": 0.31216145745942675, + "learning_rate": 9.245873819661113e-06, + "loss": 0.446, + "step": 4358 + }, + { + "epoch": 0.5808901918976546, + "grad_norm": 1.8329198068174837, + "learning_rate": 9.245497748192503e-06, + "loss": 0.4079, + "step": 4359 + }, + { + "epoch": 0.5810234541577826, + "grad_norm": 0.31214565259688065, + "learning_rate": 9.245121590628884e-06, + "loss": 0.3748, + "step": 4360 + }, + { + "epoch": 0.5811567164179104, + "grad_norm": 0.31402912096750063, + "learning_rate": 9.244745346977887e-06, + "loss": 0.4391, + "step": 4361 + }, + { + "epoch": 0.5812899786780383, + "grad_norm": 0.33001948039803786, + "learning_rate": 9.244369017247137e-06, + "loss": 0.406, + "step": 4362 + }, + { + "epoch": 0.5814232409381663, + "grad_norm": 0.307663810067437, + "learning_rate": 9.243992601444272e-06, + "loss": 0.4036, + "step": 4363 + }, + { + "epoch": 0.5815565031982942, + "grad_norm": 0.313555976971244, + "learning_rate": 9.24361609957692e-06, + "loss": 0.4249, + "step": 4364 + }, + { + "epoch": 0.5816897654584222, + "grad_norm": 0.2979368873146161, + "learning_rate": 9.24323951165272e-06, + "loss": 0.4352, + "step": 4365 + }, + { + "epoch": 0.5818230277185501, + "grad_norm": 0.3155546473488915, + "learning_rate": 9.242862837679305e-06, + "loss": 0.3734, + "step": 4366 + }, + { + "epoch": 0.581956289978678, + "grad_norm": 0.31475242284628696, + "learning_rate": 9.242486077664317e-06, + "loss": 0.3961, + "step": 4367 + }, + { + "epoch": 0.582089552238806, + "grad_norm": 0.29005622206752774, + "learning_rate": 9.242109231615395e-06, + "loss": 0.3696, + "step": 4368 + }, + { + "epoch": 0.5822228144989339, + "grad_norm": 0.31492116664032227, + "learning_rate": 9.241732299540182e-06, + "loss": 0.4327, + "step": 4369 + }, + { + "epoch": 0.5823560767590619, + "grad_norm": 0.3096923575822817, + "learning_rate": 9.24135528144632e-06, + "loss": 0.495, + "step": 4370 + }, + { + "epoch": 0.5824893390191898, + "grad_norm": 0.28678611618197214, + "learning_rate": 9.240978177341457e-06, + "loss": 0.386, + "step": 4371 + }, + { + "epoch": 0.5826226012793176, + "grad_norm": 0.28062904322959326, + "learning_rate": 9.240600987233239e-06, + "loss": 0.3231, + "step": 4372 + }, + { + "epoch": 0.5827558635394456, + "grad_norm": 0.34479064087718914, + "learning_rate": 9.240223711129314e-06, + "loss": 0.5067, + "step": 4373 + }, + { + "epoch": 0.5828891257995735, + "grad_norm": 0.31989025350327427, + "learning_rate": 9.239846349037334e-06, + "loss": 0.4136, + "step": 4374 + }, + { + "epoch": 0.5830223880597015, + "grad_norm": 0.3189616914817856, + "learning_rate": 9.239468900964952e-06, + "loss": 0.443, + "step": 4375 + }, + { + "epoch": 0.5831556503198294, + "grad_norm": 0.3045941370867639, + "learning_rate": 9.239091366919822e-06, + "loss": 0.4136, + "step": 4376 + }, + { + "epoch": 0.5832889125799574, + "grad_norm": 0.2895762008574046, + "learning_rate": 9.2387137469096e-06, + "loss": 0.4688, + "step": 4377 + }, + { + "epoch": 0.5834221748400853, + "grad_norm": 0.29417166844532694, + "learning_rate": 9.238336040941943e-06, + "loss": 0.3618, + "step": 4378 + }, + { + "epoch": 0.5835554371002132, + "grad_norm": 0.30564571654853834, + "learning_rate": 9.237958249024512e-06, + "loss": 0.52, + "step": 4379 + }, + { + "epoch": 0.5836886993603412, + "grad_norm": 0.30675193180913024, + "learning_rate": 9.237580371164968e-06, + "loss": 0.4079, + "step": 4380 + }, + { + "epoch": 0.5838219616204691, + "grad_norm": 0.2962192195250451, + "learning_rate": 9.237202407370973e-06, + "loss": 0.4119, + "step": 4381 + }, + { + "epoch": 0.5839552238805971, + "grad_norm": 0.3057138183715094, + "learning_rate": 9.236824357650192e-06, + "loss": 0.4945, + "step": 4382 + }, + { + "epoch": 0.584088486140725, + "grad_norm": 0.29530730651431136, + "learning_rate": 9.236446222010293e-06, + "loss": 0.3768, + "step": 4383 + }, + { + "epoch": 0.5842217484008528, + "grad_norm": 0.2892548784205192, + "learning_rate": 9.236068000458941e-06, + "loss": 0.3586, + "step": 4384 + }, + { + "epoch": 0.5843550106609808, + "grad_norm": 0.28622437592377026, + "learning_rate": 9.235689693003811e-06, + "loss": 0.3828, + "step": 4385 + }, + { + "epoch": 0.5844882729211087, + "grad_norm": 0.2985833923559637, + "learning_rate": 9.235311299652572e-06, + "loss": 0.3926, + "step": 4386 + }, + { + "epoch": 0.5846215351812367, + "grad_norm": 0.30428191227376167, + "learning_rate": 9.234932820412895e-06, + "loss": 0.4303, + "step": 4387 + }, + { + "epoch": 0.5847547974413646, + "grad_norm": 0.29082765096589613, + "learning_rate": 9.23455425529246e-06, + "loss": 0.3619, + "step": 4388 + }, + { + "epoch": 0.5848880597014925, + "grad_norm": 0.30798433416422655, + "learning_rate": 9.23417560429894e-06, + "loss": 0.4562, + "step": 4389 + }, + { + "epoch": 0.5850213219616205, + "grad_norm": 0.30266569575601704, + "learning_rate": 9.233796867440014e-06, + "loss": 0.4024, + "step": 4390 + }, + { + "epoch": 0.5851545842217484, + "grad_norm": 0.28946864716369314, + "learning_rate": 9.233418044723366e-06, + "loss": 0.3648, + "step": 4391 + }, + { + "epoch": 0.5852878464818764, + "grad_norm": 0.3346760917674361, + "learning_rate": 9.233039136156677e-06, + "loss": 0.3829, + "step": 4392 + }, + { + "epoch": 0.5854211087420043, + "grad_norm": 0.2844284346606074, + "learning_rate": 9.232660141747628e-06, + "loss": 0.3665, + "step": 4393 + }, + { + "epoch": 0.5855543710021321, + "grad_norm": 0.29752318644810377, + "learning_rate": 9.232281061503907e-06, + "loss": 0.352, + "step": 4394 + }, + { + "epoch": 0.5856876332622601, + "grad_norm": 0.31362771612154167, + "learning_rate": 9.231901895433201e-06, + "loss": 0.3912, + "step": 4395 + }, + { + "epoch": 0.585820895522388, + "grad_norm": 0.3248378551457802, + "learning_rate": 9.231522643543199e-06, + "loss": 0.4603, + "step": 4396 + }, + { + "epoch": 0.585954157782516, + "grad_norm": 0.30617204966714157, + "learning_rate": 9.231143305841593e-06, + "loss": 0.5125, + "step": 4397 + }, + { + "epoch": 0.5860874200426439, + "grad_norm": 0.3243498650767072, + "learning_rate": 9.230763882336073e-06, + "loss": 0.4346, + "step": 4398 + }, + { + "epoch": 0.5862206823027718, + "grad_norm": 0.3422295530177092, + "learning_rate": 9.230384373034337e-06, + "loss": 0.4636, + "step": 4399 + }, + { + "epoch": 0.5863539445628998, + "grad_norm": 0.4756525416805954, + "learning_rate": 9.230004777944079e-06, + "loss": 0.3823, + "step": 4400 + }, + { + "epoch": 0.5864872068230277, + "grad_norm": 0.3269984474512653, + "learning_rate": 9.229625097072997e-06, + "loss": 0.3703, + "step": 4401 + }, + { + "epoch": 0.5866204690831557, + "grad_norm": 0.31970384974375204, + "learning_rate": 9.229245330428789e-06, + "loss": 0.4476, + "step": 4402 + }, + { + "epoch": 0.5867537313432836, + "grad_norm": 0.3008372025617851, + "learning_rate": 9.22886547801916e-06, + "loss": 0.449, + "step": 4403 + }, + { + "epoch": 0.5868869936034116, + "grad_norm": 0.32679026864671795, + "learning_rate": 9.228485539851808e-06, + "loss": 0.4024, + "step": 4404 + }, + { + "epoch": 0.5870202558635395, + "grad_norm": 0.2866919217956752, + "learning_rate": 9.228105515934444e-06, + "loss": 0.3635, + "step": 4405 + }, + { + "epoch": 0.5871535181236673, + "grad_norm": 0.3372709554423533, + "learning_rate": 9.22772540627477e-06, + "loss": 0.387, + "step": 4406 + }, + { + "epoch": 0.5872867803837953, + "grad_norm": 0.2951244187475266, + "learning_rate": 9.227345210880496e-06, + "loss": 0.442, + "step": 4407 + }, + { + "epoch": 0.5874200426439232, + "grad_norm": 0.2894521575845558, + "learning_rate": 9.226964929759333e-06, + "loss": 0.3753, + "step": 4408 + }, + { + "epoch": 0.5875533049040512, + "grad_norm": 0.30656458766075334, + "learning_rate": 9.22658456291899e-06, + "loss": 0.3743, + "step": 4409 + }, + { + "epoch": 0.5876865671641791, + "grad_norm": 0.30676681596765204, + "learning_rate": 9.226204110367183e-06, + "loss": 0.4317, + "step": 4410 + }, + { + "epoch": 0.587819829424307, + "grad_norm": 0.3042048456564734, + "learning_rate": 9.225823572111626e-06, + "loss": 0.3783, + "step": 4411 + }, + { + "epoch": 0.587953091684435, + "grad_norm": 0.3007506717082846, + "learning_rate": 9.225442948160038e-06, + "loss": 0.5123, + "step": 4412 + }, + { + "epoch": 0.5880863539445629, + "grad_norm": 0.28414568239100463, + "learning_rate": 9.225062238520133e-06, + "loss": 0.3648, + "step": 4413 + }, + { + "epoch": 0.5882196162046909, + "grad_norm": 0.2908110447165305, + "learning_rate": 9.224681443199635e-06, + "loss": 0.3934, + "step": 4414 + }, + { + "epoch": 0.5883528784648188, + "grad_norm": 0.33514333246379013, + "learning_rate": 9.224300562206268e-06, + "loss": 0.4545, + "step": 4415 + }, + { + "epoch": 0.5884861407249466, + "grad_norm": 0.2884264854130263, + "learning_rate": 9.223919595547752e-06, + "loss": 0.3483, + "step": 4416 + }, + { + "epoch": 0.5886194029850746, + "grad_norm": 0.30087046355717373, + "learning_rate": 9.223538543231814e-06, + "loss": 0.4789, + "step": 4417 + }, + { + "epoch": 0.5887526652452025, + "grad_norm": 0.3077902413423485, + "learning_rate": 9.223157405266182e-06, + "loss": 0.3913, + "step": 4418 + }, + { + "epoch": 0.5888859275053305, + "grad_norm": 0.28736304211238384, + "learning_rate": 9.222776181658584e-06, + "loss": 0.3677, + "step": 4419 + }, + { + "epoch": 0.5890191897654584, + "grad_norm": 0.3228797557890736, + "learning_rate": 9.222394872416753e-06, + "loss": 0.423, + "step": 4420 + }, + { + "epoch": 0.5891524520255863, + "grad_norm": 0.2947883179782341, + "learning_rate": 9.22201347754842e-06, + "loss": 0.4039, + "step": 4421 + }, + { + "epoch": 0.5892857142857143, + "grad_norm": 0.3013222587507768, + "learning_rate": 9.22163199706132e-06, + "loss": 0.4536, + "step": 4422 + }, + { + "epoch": 0.5894189765458422, + "grad_norm": 0.2924516775702169, + "learning_rate": 9.221250430963188e-06, + "loss": 0.433, + "step": 4423 + }, + { + "epoch": 0.5895522388059702, + "grad_norm": 0.2868136599060071, + "learning_rate": 9.220868779261764e-06, + "loss": 0.4096, + "step": 4424 + }, + { + "epoch": 0.5896855010660981, + "grad_norm": 0.2907636540063251, + "learning_rate": 9.220487041964786e-06, + "loss": 0.4035, + "step": 4425 + }, + { + "epoch": 0.589818763326226, + "grad_norm": 0.2996720826847557, + "learning_rate": 9.220105219079993e-06, + "loss": 0.3438, + "step": 4426 + }, + { + "epoch": 0.589952025586354, + "grad_norm": 0.2790554914094769, + "learning_rate": 9.219723310615134e-06, + "loss": 0.3683, + "step": 4427 + }, + { + "epoch": 0.5900852878464818, + "grad_norm": 0.2897163733967521, + "learning_rate": 9.219341316577948e-06, + "loss": 0.3704, + "step": 4428 + }, + { + "epoch": 0.5902185501066098, + "grad_norm": 0.29719755266198566, + "learning_rate": 9.218959236976185e-06, + "loss": 0.4414, + "step": 4429 + }, + { + "epoch": 0.5903518123667377, + "grad_norm": 0.3165231471881966, + "learning_rate": 9.218577071817591e-06, + "loss": 0.4354, + "step": 4430 + }, + { + "epoch": 0.5904850746268657, + "grad_norm": 0.28087441357090476, + "learning_rate": 9.218194821109918e-06, + "loss": 0.4033, + "step": 4431 + }, + { + "epoch": 0.5906183368869936, + "grad_norm": 0.31585826546444484, + "learning_rate": 9.217812484860917e-06, + "loss": 0.4792, + "step": 4432 + }, + { + "epoch": 0.5907515991471215, + "grad_norm": 0.29548905438405193, + "learning_rate": 9.21743006307834e-06, + "loss": 0.4626, + "step": 4433 + }, + { + "epoch": 0.5908848614072495, + "grad_norm": 0.2819630072037684, + "learning_rate": 9.217047555769943e-06, + "loss": 0.4039, + "step": 4434 + }, + { + "epoch": 0.5910181236673774, + "grad_norm": 0.29761578314799797, + "learning_rate": 9.216664962943485e-06, + "loss": 0.4169, + "step": 4435 + }, + { + "epoch": 0.5911513859275054, + "grad_norm": 0.33761107348598546, + "learning_rate": 9.216282284606722e-06, + "loss": 0.5173, + "step": 4436 + }, + { + "epoch": 0.5912846481876333, + "grad_norm": 0.3048926899936652, + "learning_rate": 9.215899520767414e-06, + "loss": 0.3986, + "step": 4437 + }, + { + "epoch": 0.5914179104477612, + "grad_norm": 0.286383555774553, + "learning_rate": 9.215516671433326e-06, + "loss": 0.383, + "step": 4438 + }, + { + "epoch": 0.5915511727078892, + "grad_norm": 0.29124316067494244, + "learning_rate": 9.21513373661222e-06, + "loss": 0.3662, + "step": 4439 + }, + { + "epoch": 0.591684434968017, + "grad_norm": 0.28597248371601885, + "learning_rate": 9.214750716311864e-06, + "loss": 0.3411, + "step": 4440 + }, + { + "epoch": 0.591817697228145, + "grad_norm": 0.3250230943120858, + "learning_rate": 9.214367610540021e-06, + "loss": 0.4418, + "step": 4441 + }, + { + "epoch": 0.5919509594882729, + "grad_norm": 0.3113210490434825, + "learning_rate": 9.213984419304463e-06, + "loss": 0.412, + "step": 4442 + }, + { + "epoch": 0.5920842217484008, + "grad_norm": 0.28162818778017845, + "learning_rate": 9.213601142612957e-06, + "loss": 0.3694, + "step": 4443 + }, + { + "epoch": 0.5922174840085288, + "grad_norm": 0.30852968794111957, + "learning_rate": 9.213217780473283e-06, + "loss": 0.3725, + "step": 4444 + }, + { + "epoch": 0.5923507462686567, + "grad_norm": 0.28687451108706336, + "learning_rate": 9.212834332893209e-06, + "loss": 0.4125, + "step": 4445 + }, + { + "epoch": 0.5924840085287847, + "grad_norm": 0.31199226048096723, + "learning_rate": 9.212450799880512e-06, + "loss": 0.5117, + "step": 4446 + }, + { + "epoch": 0.5926172707889126, + "grad_norm": 0.2934367239912251, + "learning_rate": 9.212067181442973e-06, + "loss": 0.35, + "step": 4447 + }, + { + "epoch": 0.5927505330490405, + "grad_norm": 0.2809973329042656, + "learning_rate": 9.211683477588366e-06, + "loss": 0.3263, + "step": 4448 + }, + { + "epoch": 0.5928837953091685, + "grad_norm": 0.30639808296861565, + "learning_rate": 9.211299688324475e-06, + "loss": 0.4252, + "step": 4449 + }, + { + "epoch": 0.5930170575692963, + "grad_norm": 0.29205291443545, + "learning_rate": 9.210915813659085e-06, + "loss": 0.4331, + "step": 4450 + }, + { + "epoch": 0.5931503198294243, + "grad_norm": 0.29255542430984, + "learning_rate": 9.210531853599978e-06, + "loss": 0.48, + "step": 4451 + }, + { + "epoch": 0.5932835820895522, + "grad_norm": 0.3226560145892831, + "learning_rate": 9.210147808154942e-06, + "loss": 0.4208, + "step": 4452 + }, + { + "epoch": 0.5934168443496801, + "grad_norm": 0.30223118284152023, + "learning_rate": 9.209763677331763e-06, + "loss": 0.4086, + "step": 4453 + }, + { + "epoch": 0.5935501066098081, + "grad_norm": 0.2956705354844232, + "learning_rate": 9.209379461138233e-06, + "loss": 0.3974, + "step": 4454 + }, + { + "epoch": 0.593683368869936, + "grad_norm": 0.326139790990575, + "learning_rate": 9.20899515958214e-06, + "loss": 0.4046, + "step": 4455 + }, + { + "epoch": 0.593816631130064, + "grad_norm": 0.3086557792598455, + "learning_rate": 9.208610772671282e-06, + "loss": 0.4548, + "step": 4456 + }, + { + "epoch": 0.5939498933901919, + "grad_norm": 0.29360362874171564, + "learning_rate": 9.208226300413452e-06, + "loss": 0.408, + "step": 4457 + }, + { + "epoch": 0.5940831556503199, + "grad_norm": 0.5889717119283799, + "learning_rate": 9.207841742816445e-06, + "loss": 0.486, + "step": 4458 + }, + { + "epoch": 0.5942164179104478, + "grad_norm": 0.30111825919722446, + "learning_rate": 9.207457099888065e-06, + "loss": 0.4604, + "step": 4459 + }, + { + "epoch": 0.5943496801705757, + "grad_norm": 0.3135321498938549, + "learning_rate": 9.207072371636106e-06, + "loss": 0.3787, + "step": 4460 + }, + { + "epoch": 0.5944829424307037, + "grad_norm": 0.2969384758540885, + "learning_rate": 9.206687558068371e-06, + "loss": 0.4272, + "step": 4461 + }, + { + "epoch": 0.5946162046908315, + "grad_norm": 0.3305549730283711, + "learning_rate": 9.206302659192667e-06, + "loss": 0.4023, + "step": 4462 + }, + { + "epoch": 0.5947494669509595, + "grad_norm": 0.29424223736722926, + "learning_rate": 9.205917675016796e-06, + "loss": 0.433, + "step": 4463 + }, + { + "epoch": 0.5948827292110874, + "grad_norm": 0.30816705676455836, + "learning_rate": 9.205532605548568e-06, + "loss": 0.4424, + "step": 4464 + }, + { + "epoch": 0.5950159914712153, + "grad_norm": 0.3139175642647941, + "learning_rate": 9.20514745079579e-06, + "loss": 0.4613, + "step": 4465 + }, + { + "epoch": 0.5951492537313433, + "grad_norm": 0.2968286010541385, + "learning_rate": 9.204762210766273e-06, + "loss": 0.4699, + "step": 4466 + }, + { + "epoch": 0.5952825159914712, + "grad_norm": 0.3186285728775898, + "learning_rate": 9.20437688546783e-06, + "loss": 0.4185, + "step": 4467 + }, + { + "epoch": 0.5954157782515992, + "grad_norm": 0.2962349487638099, + "learning_rate": 9.203991474908274e-06, + "loss": 0.5343, + "step": 4468 + }, + { + "epoch": 0.5955490405117271, + "grad_norm": 0.30458460033545354, + "learning_rate": 9.203605979095421e-06, + "loss": 0.3956, + "step": 4469 + }, + { + "epoch": 0.595682302771855, + "grad_norm": 0.3013936488056713, + "learning_rate": 9.203220398037089e-06, + "loss": 0.3992, + "step": 4470 + }, + { + "epoch": 0.595815565031983, + "grad_norm": 0.32426157154802177, + "learning_rate": 9.202834731741096e-06, + "loss": 0.4413, + "step": 4471 + }, + { + "epoch": 0.5959488272921108, + "grad_norm": 0.3192986131365142, + "learning_rate": 9.202448980215265e-06, + "loss": 0.452, + "step": 4472 + }, + { + "epoch": 0.5960820895522388, + "grad_norm": 0.3127093757468314, + "learning_rate": 9.202063143467418e-06, + "loss": 0.4601, + "step": 4473 + }, + { + "epoch": 0.5962153518123667, + "grad_norm": 0.30180094931134716, + "learning_rate": 9.201677221505378e-06, + "loss": 0.4132, + "step": 4474 + }, + { + "epoch": 0.5963486140724946, + "grad_norm": 0.29182133911633584, + "learning_rate": 9.201291214336974e-06, + "loss": 0.4238, + "step": 4475 + }, + { + "epoch": 0.5964818763326226, + "grad_norm": 0.28720238793812697, + "learning_rate": 9.200905121970031e-06, + "loss": 0.3776, + "step": 4476 + }, + { + "epoch": 0.5966151385927505, + "grad_norm": 0.30619721821997187, + "learning_rate": 9.20051894441238e-06, + "loss": 0.4555, + "step": 4477 + }, + { + "epoch": 0.5967484008528785, + "grad_norm": 0.3075797273005157, + "learning_rate": 9.200132681671853e-06, + "loss": 0.4079, + "step": 4478 + }, + { + "epoch": 0.5968816631130064, + "grad_norm": 0.28082363218876566, + "learning_rate": 9.19974633375628e-06, + "loss": 0.3635, + "step": 4479 + }, + { + "epoch": 0.5970149253731343, + "grad_norm": 0.30433778604276457, + "learning_rate": 9.1993599006735e-06, + "loss": 0.4423, + "step": 4480 + }, + { + "epoch": 0.5971481876332623, + "grad_norm": 0.3028605275061149, + "learning_rate": 9.19897338243135e-06, + "loss": 0.414, + "step": 4481 + }, + { + "epoch": 0.5972814498933902, + "grad_norm": 0.33649140193288657, + "learning_rate": 9.19858677903766e-06, + "loss": 0.5095, + "step": 4482 + }, + { + "epoch": 0.5974147121535182, + "grad_norm": 0.3020999389418181, + "learning_rate": 9.19820009050028e-06, + "loss": 0.3848, + "step": 4483 + }, + { + "epoch": 0.597547974413646, + "grad_norm": 0.3235557830116592, + "learning_rate": 9.197813316827047e-06, + "loss": 0.4374, + "step": 4484 + }, + { + "epoch": 0.597681236673774, + "grad_norm": 0.307949537713971, + "learning_rate": 9.197426458025804e-06, + "loss": 0.4403, + "step": 4485 + }, + { + "epoch": 0.5978144989339019, + "grad_norm": 0.30328909555803374, + "learning_rate": 9.197039514104398e-06, + "loss": 0.4409, + "step": 4486 + }, + { + "epoch": 0.5979477611940298, + "grad_norm": 0.3115181669953531, + "learning_rate": 9.196652485070675e-06, + "loss": 0.5056, + "step": 4487 + }, + { + "epoch": 0.5980810234541578, + "grad_norm": 0.3067269674852536, + "learning_rate": 9.196265370932482e-06, + "loss": 0.4079, + "step": 4488 + }, + { + "epoch": 0.5982142857142857, + "grad_norm": 0.3076845978074874, + "learning_rate": 9.195878171697672e-06, + "loss": 0.413, + "step": 4489 + }, + { + "epoch": 0.5983475479744137, + "grad_norm": 0.3091797785406333, + "learning_rate": 9.195490887374097e-06, + "loss": 0.4271, + "step": 4490 + }, + { + "epoch": 0.5984808102345416, + "grad_norm": 0.3204729142926071, + "learning_rate": 9.195103517969608e-06, + "loss": 0.4695, + "step": 4491 + }, + { + "epoch": 0.5986140724946695, + "grad_norm": 0.29161372636652966, + "learning_rate": 9.194716063492064e-06, + "loss": 0.3844, + "step": 4492 + }, + { + "epoch": 0.5987473347547975, + "grad_norm": 0.3062280172283507, + "learning_rate": 9.19432852394932e-06, + "loss": 0.3777, + "step": 4493 + }, + { + "epoch": 0.5988805970149254, + "grad_norm": 0.2975291310956458, + "learning_rate": 9.193940899349235e-06, + "loss": 0.3713, + "step": 4494 + }, + { + "epoch": 0.5990138592750534, + "grad_norm": 0.2912295987830034, + "learning_rate": 9.19355318969967e-06, + "loss": 0.4076, + "step": 4495 + }, + { + "epoch": 0.5991471215351812, + "grad_norm": 0.31465054837972345, + "learning_rate": 9.193165395008488e-06, + "loss": 0.4613, + "step": 4496 + }, + { + "epoch": 0.5992803837953091, + "grad_norm": 0.3353166773279937, + "learning_rate": 9.192777515283554e-06, + "loss": 0.4202, + "step": 4497 + }, + { + "epoch": 0.5994136460554371, + "grad_norm": 0.28414419865075446, + "learning_rate": 9.19238955053273e-06, + "loss": 0.3755, + "step": 4498 + }, + { + "epoch": 0.599546908315565, + "grad_norm": 0.3226100423524362, + "learning_rate": 9.19200150076389e-06, + "loss": 0.3721, + "step": 4499 + }, + { + "epoch": 0.599680170575693, + "grad_norm": 0.32149320453342145, + "learning_rate": 9.191613365984896e-06, + "loss": 0.3885, + "step": 4500 + }, + { + "epoch": 0.5998134328358209, + "grad_norm": 0.2945043672086387, + "learning_rate": 9.191225146203624e-06, + "loss": 0.4219, + "step": 4501 + }, + { + "epoch": 0.5999466950959488, + "grad_norm": 0.29960935590557175, + "learning_rate": 9.190836841427946e-06, + "loss": 0.4135, + "step": 4502 + }, + { + "epoch": 0.6000799573560768, + "grad_norm": 0.2902786965884055, + "learning_rate": 9.190448451665734e-06, + "loss": 0.4582, + "step": 4503 + }, + { + "epoch": 0.6002132196162047, + "grad_norm": 0.3044228503481755, + "learning_rate": 9.190059976924868e-06, + "loss": 0.4209, + "step": 4504 + }, + { + "epoch": 0.6003464818763327, + "grad_norm": 0.3034009575437721, + "learning_rate": 9.189671417213222e-06, + "loss": 0.3778, + "step": 4505 + }, + { + "epoch": 0.6004797441364605, + "grad_norm": 0.29113238905487115, + "learning_rate": 9.189282772538679e-06, + "loss": 0.3726, + "step": 4506 + }, + { + "epoch": 0.6006130063965884, + "grad_norm": 0.7490248829017959, + "learning_rate": 9.188894042909118e-06, + "loss": 0.4227, + "step": 4507 + }, + { + "epoch": 0.6007462686567164, + "grad_norm": 0.3244026864266445, + "learning_rate": 9.188505228332426e-06, + "loss": 0.4222, + "step": 4508 + }, + { + "epoch": 0.6008795309168443, + "grad_norm": 0.2889473836824485, + "learning_rate": 9.18811632881648e-06, + "loss": 0.4314, + "step": 4509 + }, + { + "epoch": 0.6010127931769723, + "grad_norm": 0.3166094009912049, + "learning_rate": 9.187727344369175e-06, + "loss": 0.3544, + "step": 4510 + }, + { + "epoch": 0.6011460554371002, + "grad_norm": 0.29618692524058593, + "learning_rate": 9.187338274998394e-06, + "loss": 0.3907, + "step": 4511 + }, + { + "epoch": 0.6012793176972282, + "grad_norm": 0.31526569137802923, + "learning_rate": 9.18694912071203e-06, + "loss": 0.3544, + "step": 4512 + }, + { + "epoch": 0.6014125799573561, + "grad_norm": 0.3255581320859579, + "learning_rate": 9.186559881517973e-06, + "loss": 0.4386, + "step": 4513 + }, + { + "epoch": 0.601545842217484, + "grad_norm": 0.29382170509284583, + "learning_rate": 9.186170557424117e-06, + "loss": 0.3634, + "step": 4514 + }, + { + "epoch": 0.601679104477612, + "grad_norm": 0.34546814078246296, + "learning_rate": 9.185781148438356e-06, + "loss": 0.4229, + "step": 4515 + }, + { + "epoch": 0.6018123667377399, + "grad_norm": 0.2938363146546126, + "learning_rate": 9.18539165456859e-06, + "loss": 0.4057, + "step": 4516 + }, + { + "epoch": 0.6019456289978679, + "grad_norm": 0.34482652131396474, + "learning_rate": 9.185002075822713e-06, + "loss": 0.5042, + "step": 4517 + }, + { + "epoch": 0.6020788912579957, + "grad_norm": 0.3329544318296996, + "learning_rate": 9.184612412208629e-06, + "loss": 0.4464, + "step": 4518 + }, + { + "epoch": 0.6022121535181236, + "grad_norm": 0.31225029139037086, + "learning_rate": 9.18422266373424e-06, + "loss": 0.3621, + "step": 4519 + }, + { + "epoch": 0.6023454157782516, + "grad_norm": 0.3277565167576372, + "learning_rate": 9.183832830407446e-06, + "loss": 0.4547, + "step": 4520 + }, + { + "epoch": 0.6024786780383795, + "grad_norm": 0.28518629278107893, + "learning_rate": 9.183442912236155e-06, + "loss": 0.351, + "step": 4521 + }, + { + "epoch": 0.6026119402985075, + "grad_norm": 0.30721795958594456, + "learning_rate": 9.183052909228277e-06, + "loss": 0.3783, + "step": 4522 + }, + { + "epoch": 0.6027452025586354, + "grad_norm": 0.3073524476070771, + "learning_rate": 9.182662821391717e-06, + "loss": 0.3892, + "step": 4523 + }, + { + "epoch": 0.6028784648187633, + "grad_norm": 0.3264562072939877, + "learning_rate": 9.182272648734388e-06, + "loss": 0.4502, + "step": 4524 + }, + { + "epoch": 0.6030117270788913, + "grad_norm": 0.3196212522872842, + "learning_rate": 9.181882391264198e-06, + "loss": 0.4418, + "step": 4525 + }, + { + "epoch": 0.6031449893390192, + "grad_norm": 0.3137683620268104, + "learning_rate": 9.181492048989067e-06, + "loss": 0.3879, + "step": 4526 + }, + { + "epoch": 0.6032782515991472, + "grad_norm": 0.32729465168901617, + "learning_rate": 9.181101621916908e-06, + "loss": 0.3899, + "step": 4527 + }, + { + "epoch": 0.603411513859275, + "grad_norm": 0.279299832472213, + "learning_rate": 9.180711110055636e-06, + "loss": 0.3681, + "step": 4528 + }, + { + "epoch": 0.6035447761194029, + "grad_norm": 0.3385642962597084, + "learning_rate": 9.180320513413175e-06, + "loss": 0.4247, + "step": 4529 + }, + { + "epoch": 0.6036780383795309, + "grad_norm": 0.29262636667640096, + "learning_rate": 9.179929831997444e-06, + "loss": 0.3749, + "step": 4530 + }, + { + "epoch": 0.6038113006396588, + "grad_norm": 0.3058042112211886, + "learning_rate": 9.179539065816365e-06, + "loss": 0.4403, + "step": 4531 + }, + { + "epoch": 0.6039445628997868, + "grad_norm": 0.32326048511821887, + "learning_rate": 9.179148214877864e-06, + "loss": 0.4326, + "step": 4532 + }, + { + "epoch": 0.6040778251599147, + "grad_norm": 0.3143509587301751, + "learning_rate": 9.178757279189866e-06, + "loss": 0.4002, + "step": 4533 + }, + { + "epoch": 0.6042110874200426, + "grad_norm": 0.307855479544445, + "learning_rate": 9.178366258760295e-06, + "loss": 0.4468, + "step": 4534 + }, + { + "epoch": 0.6043443496801706, + "grad_norm": 0.300960652167455, + "learning_rate": 9.177975153597088e-06, + "loss": 0.4047, + "step": 4535 + }, + { + "epoch": 0.6044776119402985, + "grad_norm": 0.28252469661155905, + "learning_rate": 9.177583963708172e-06, + "loss": 0.4753, + "step": 4536 + }, + { + "epoch": 0.6046108742004265, + "grad_norm": 0.3002189349605835, + "learning_rate": 9.177192689101481e-06, + "loss": 0.397, + "step": 4537 + }, + { + "epoch": 0.6047441364605544, + "grad_norm": 0.30137020207057563, + "learning_rate": 9.176801329784949e-06, + "loss": 0.4089, + "step": 4538 + }, + { + "epoch": 0.6048773987206824, + "grad_norm": 0.2911621979312847, + "learning_rate": 9.176409885766512e-06, + "loss": 0.4023, + "step": 4539 + }, + { + "epoch": 0.6050106609808102, + "grad_norm": 0.28850856571458583, + "learning_rate": 9.17601835705411e-06, + "loss": 0.3732, + "step": 4540 + }, + { + "epoch": 0.6051439232409381, + "grad_norm": 0.2906130586072505, + "learning_rate": 9.175626743655681e-06, + "loss": 0.3835, + "step": 4541 + }, + { + "epoch": 0.6052771855010661, + "grad_norm": 0.30043219453425757, + "learning_rate": 9.175235045579169e-06, + "loss": 0.444, + "step": 4542 + }, + { + "epoch": 0.605410447761194, + "grad_norm": 0.2906418552897936, + "learning_rate": 9.174843262832514e-06, + "loss": 0.428, + "step": 4543 + }, + { + "epoch": 0.605543710021322, + "grad_norm": 0.8548401251953377, + "learning_rate": 9.174451395423663e-06, + "loss": 0.4438, + "step": 4544 + }, + { + "epoch": 0.6056769722814499, + "grad_norm": 0.30747377909580176, + "learning_rate": 9.174059443360564e-06, + "loss": 0.4897, + "step": 4545 + }, + { + "epoch": 0.6058102345415778, + "grad_norm": 0.28836018359428983, + "learning_rate": 9.173667406651163e-06, + "loss": 0.4417, + "step": 4546 + }, + { + "epoch": 0.6059434968017058, + "grad_norm": 0.30049281056307797, + "learning_rate": 9.17327528530341e-06, + "loss": 0.4014, + "step": 4547 + }, + { + "epoch": 0.6060767590618337, + "grad_norm": 0.27683594100990117, + "learning_rate": 9.172883079325259e-06, + "loss": 0.4163, + "step": 4548 + }, + { + "epoch": 0.6062100213219617, + "grad_norm": 0.29778289336900504, + "learning_rate": 9.172490788724661e-06, + "loss": 0.436, + "step": 4549 + }, + { + "epoch": 0.6063432835820896, + "grad_norm": 0.32597653049992203, + "learning_rate": 9.172098413509573e-06, + "loss": 0.4326, + "step": 4550 + }, + { + "epoch": 0.6064765458422174, + "grad_norm": 0.29084215244511924, + "learning_rate": 9.171705953687956e-06, + "loss": 0.391, + "step": 4551 + }, + { + "epoch": 0.6066098081023454, + "grad_norm": 0.3031023399539701, + "learning_rate": 9.171313409267759e-06, + "loss": 0.4178, + "step": 4552 + }, + { + "epoch": 0.6067430703624733, + "grad_norm": 0.30815894723733744, + "learning_rate": 9.170920780256951e-06, + "loss": 0.3657, + "step": 4553 + }, + { + "epoch": 0.6068763326226013, + "grad_norm": 0.295092177951065, + "learning_rate": 9.170528066663492e-06, + "loss": 0.415, + "step": 4554 + }, + { + "epoch": 0.6070095948827292, + "grad_norm": 0.31744362550702787, + "learning_rate": 9.170135268495344e-06, + "loss": 0.5319, + "step": 4555 + }, + { + "epoch": 0.6071428571428571, + "grad_norm": 0.2863359761608436, + "learning_rate": 9.169742385760473e-06, + "loss": 0.4573, + "step": 4556 + }, + { + "epoch": 0.6072761194029851, + "grad_norm": 0.2963594841031226, + "learning_rate": 9.169349418466847e-06, + "loss": 0.3552, + "step": 4557 + }, + { + "epoch": 0.607409381663113, + "grad_norm": 0.2781525504736556, + "learning_rate": 9.168956366622436e-06, + "loss": 0.4165, + "step": 4558 + }, + { + "epoch": 0.607542643923241, + "grad_norm": 0.5727468888100278, + "learning_rate": 9.16856323023521e-06, + "loss": 0.3904, + "step": 4559 + }, + { + "epoch": 0.6076759061833689, + "grad_norm": 0.3048195350039247, + "learning_rate": 9.16817000931314e-06, + "loss": 0.4144, + "step": 4560 + }, + { + "epoch": 0.6078091684434968, + "grad_norm": 0.2809918835739576, + "learning_rate": 9.167776703864203e-06, + "loss": 0.3889, + "step": 4561 + }, + { + "epoch": 0.6079424307036247, + "grad_norm": 0.32844667366032293, + "learning_rate": 9.167383313896371e-06, + "loss": 0.3907, + "step": 4562 + }, + { + "epoch": 0.6080756929637526, + "grad_norm": 0.2852980368804995, + "learning_rate": 9.166989839417628e-06, + "loss": 0.3783, + "step": 4563 + }, + { + "epoch": 0.6082089552238806, + "grad_norm": 0.30855897612243205, + "learning_rate": 9.166596280435946e-06, + "loss": 0.3615, + "step": 4564 + }, + { + "epoch": 0.6083422174840085, + "grad_norm": 0.3033824927818867, + "learning_rate": 9.16620263695931e-06, + "loss": 0.441, + "step": 4565 + }, + { + "epoch": 0.6084754797441365, + "grad_norm": 0.28099412797650225, + "learning_rate": 9.165808908995704e-06, + "loss": 0.3831, + "step": 4566 + }, + { + "epoch": 0.6086087420042644, + "grad_norm": 0.28687105091445275, + "learning_rate": 9.16541509655311e-06, + "loss": 0.3941, + "step": 4567 + }, + { + "epoch": 0.6087420042643923, + "grad_norm": 0.2883551474474119, + "learning_rate": 9.165021199639511e-06, + "loss": 0.3872, + "step": 4568 + }, + { + "epoch": 0.6088752665245203, + "grad_norm": 0.30494701569514504, + "learning_rate": 9.164627218262902e-06, + "loss": 0.4563, + "step": 4569 + }, + { + "epoch": 0.6090085287846482, + "grad_norm": 0.2955484274724626, + "learning_rate": 9.16423315243127e-06, + "loss": 0.4156, + "step": 4570 + }, + { + "epoch": 0.6091417910447762, + "grad_norm": 0.2966529061651724, + "learning_rate": 9.163839002152604e-06, + "loss": 0.3717, + "step": 4571 + }, + { + "epoch": 0.6092750533049041, + "grad_norm": 0.2958828786935552, + "learning_rate": 9.163444767434898e-06, + "loss": 0.4288, + "step": 4572 + }, + { + "epoch": 0.6094083155650319, + "grad_norm": 0.2954638336983744, + "learning_rate": 9.163050448286148e-06, + "loss": 0.3619, + "step": 4573 + }, + { + "epoch": 0.6095415778251599, + "grad_norm": 0.2997723222452193, + "learning_rate": 9.16265604471435e-06, + "loss": 0.3747, + "step": 4574 + }, + { + "epoch": 0.6096748400852878, + "grad_norm": 0.31446727536370983, + "learning_rate": 9.1622615567275e-06, + "loss": 0.3602, + "step": 4575 + }, + { + "epoch": 0.6098081023454158, + "grad_norm": 0.30019993956567687, + "learning_rate": 9.161866984333603e-06, + "loss": 0.3846, + "step": 4576 + }, + { + "epoch": 0.6099413646055437, + "grad_norm": 0.34935006617144304, + "learning_rate": 9.161472327540656e-06, + "loss": 0.4178, + "step": 4577 + }, + { + "epoch": 0.6100746268656716, + "grad_norm": 0.2902023893815808, + "learning_rate": 9.161077586356664e-06, + "loss": 0.459, + "step": 4578 + }, + { + "epoch": 0.6102078891257996, + "grad_norm": 0.2983693422027648, + "learning_rate": 9.160682760789629e-06, + "loss": 0.3959, + "step": 4579 + }, + { + "epoch": 0.6103411513859275, + "grad_norm": 0.29525902892153144, + "learning_rate": 9.160287850847564e-06, + "loss": 0.4988, + "step": 4580 + }, + { + "epoch": 0.6104744136460555, + "grad_norm": 0.3164164662639336, + "learning_rate": 9.159892856538473e-06, + "loss": 0.3903, + "step": 4581 + }, + { + "epoch": 0.6106076759061834, + "grad_norm": 0.3090131124072898, + "learning_rate": 9.159497777870365e-06, + "loss": 0.4301, + "step": 4582 + }, + { + "epoch": 0.6107409381663113, + "grad_norm": 0.29352222383697313, + "learning_rate": 9.159102614851256e-06, + "loss": 0.5415, + "step": 4583 + }, + { + "epoch": 0.6108742004264393, + "grad_norm": 0.29895151558928396, + "learning_rate": 9.158707367489158e-06, + "loss": 0.414, + "step": 4584 + }, + { + "epoch": 0.6110074626865671, + "grad_norm": 0.3227668510976282, + "learning_rate": 9.158312035792083e-06, + "loss": 0.4893, + "step": 4585 + }, + { + "epoch": 0.6111407249466951, + "grad_norm": 0.3045678244272146, + "learning_rate": 9.15791661976805e-06, + "loss": 0.3877, + "step": 4586 + }, + { + "epoch": 0.611273987206823, + "grad_norm": 0.29919154025982225, + "learning_rate": 9.157521119425082e-06, + "loss": 0.4473, + "step": 4587 + }, + { + "epoch": 0.6114072494669509, + "grad_norm": 0.30884967910031785, + "learning_rate": 9.157125534771193e-06, + "loss": 0.4145, + "step": 4588 + }, + { + "epoch": 0.6115405117270789, + "grad_norm": 0.30322048442611926, + "learning_rate": 9.15672986581441e-06, + "loss": 0.3969, + "step": 4589 + }, + { + "epoch": 0.6116737739872068, + "grad_norm": 0.30089836894376965, + "learning_rate": 9.156334112562753e-06, + "loss": 0.3888, + "step": 4590 + }, + { + "epoch": 0.6118070362473348, + "grad_norm": 0.3031689103218178, + "learning_rate": 9.155938275024248e-06, + "loss": 0.4858, + "step": 4591 + }, + { + "epoch": 0.6119402985074627, + "grad_norm": 0.3028074107958423, + "learning_rate": 9.155542353206926e-06, + "loss": 0.4378, + "step": 4592 + }, + { + "epoch": 0.6120735607675906, + "grad_norm": 0.2976293984274277, + "learning_rate": 9.155146347118812e-06, + "loss": 0.4309, + "step": 4593 + }, + { + "epoch": 0.6122068230277186, + "grad_norm": 0.3065680512076902, + "learning_rate": 9.154750256767939e-06, + "loss": 0.4261, + "step": 4594 + }, + { + "epoch": 0.6123400852878464, + "grad_norm": 0.3117558592250879, + "learning_rate": 9.154354082162337e-06, + "loss": 0.4101, + "step": 4595 + }, + { + "epoch": 0.6124733475479744, + "grad_norm": 0.3082023682953954, + "learning_rate": 9.153957823310043e-06, + "loss": 0.4433, + "step": 4596 + }, + { + "epoch": 0.6126066098081023, + "grad_norm": 0.30912980913295557, + "learning_rate": 9.15356148021909e-06, + "loss": 0.421, + "step": 4597 + }, + { + "epoch": 0.6127398720682303, + "grad_norm": 0.3869359030343325, + "learning_rate": 9.153165052897518e-06, + "loss": 0.3874, + "step": 4598 + }, + { + "epoch": 0.6128731343283582, + "grad_norm": 0.2991769089807416, + "learning_rate": 9.152768541353363e-06, + "loss": 0.3884, + "step": 4599 + }, + { + "epoch": 0.6130063965884861, + "grad_norm": 0.3096978924949219, + "learning_rate": 9.15237194559467e-06, + "loss": 0.4497, + "step": 4600 + }, + { + "epoch": 0.6131396588486141, + "grad_norm": 0.30240369200057404, + "learning_rate": 9.151975265629478e-06, + "loss": 0.4225, + "step": 4601 + }, + { + "epoch": 0.613272921108742, + "grad_norm": 0.27906046843391596, + "learning_rate": 9.151578501465835e-06, + "loss": 0.3847, + "step": 4602 + }, + { + "epoch": 0.61340618336887, + "grad_norm": 0.3141824424197975, + "learning_rate": 9.151181653111782e-06, + "loss": 0.4086, + "step": 4603 + }, + { + "epoch": 0.6135394456289979, + "grad_norm": 0.3026619393389897, + "learning_rate": 9.150784720575372e-06, + "loss": 0.4559, + "step": 4604 + }, + { + "epoch": 0.6136727078891258, + "grad_norm": 0.3074881862391018, + "learning_rate": 9.150387703864651e-06, + "loss": 0.4344, + "step": 4605 + }, + { + "epoch": 0.6138059701492538, + "grad_norm": 0.30787528705073347, + "learning_rate": 9.149990602987671e-06, + "loss": 0.3956, + "step": 4606 + }, + { + "epoch": 0.6139392324093816, + "grad_norm": 0.2982773778796981, + "learning_rate": 9.149593417952484e-06, + "loss": 0.5121, + "step": 4607 + }, + { + "epoch": 0.6140724946695096, + "grad_norm": 0.30325400112154216, + "learning_rate": 9.149196148767147e-06, + "loss": 0.3937, + "step": 4608 + }, + { + "epoch": 0.6142057569296375, + "grad_norm": 0.2836930392568758, + "learning_rate": 9.148798795439715e-06, + "loss": 0.3617, + "step": 4609 + }, + { + "epoch": 0.6143390191897654, + "grad_norm": 0.27402000333980797, + "learning_rate": 9.148401357978248e-06, + "loss": 0.3567, + "step": 4610 + }, + { + "epoch": 0.6144722814498934, + "grad_norm": 0.3017006102885076, + "learning_rate": 9.1480038363908e-06, + "loss": 0.4031, + "step": 4611 + }, + { + "epoch": 0.6146055437100213, + "grad_norm": 0.32046361945876267, + "learning_rate": 9.147606230685437e-06, + "loss": 0.3282, + "step": 4612 + }, + { + "epoch": 0.6147388059701493, + "grad_norm": 0.2853450536579377, + "learning_rate": 9.147208540870222e-06, + "loss": 0.4028, + "step": 4613 + }, + { + "epoch": 0.6148720682302772, + "grad_norm": 0.3013835843223865, + "learning_rate": 9.146810766953218e-06, + "loss": 0.3844, + "step": 4614 + }, + { + "epoch": 0.6150053304904051, + "grad_norm": 0.39149295346057716, + "learning_rate": 9.146412908942493e-06, + "loss": 0.3474, + "step": 4615 + }, + { + "epoch": 0.6151385927505331, + "grad_norm": 0.2931679547320162, + "learning_rate": 9.146014966846114e-06, + "loss": 0.3643, + "step": 4616 + }, + { + "epoch": 0.615271855010661, + "grad_norm": 0.32379430513480134, + "learning_rate": 9.145616940672151e-06, + "loss": 0.4693, + "step": 4617 + }, + { + "epoch": 0.615405117270789, + "grad_norm": 0.2982005402491038, + "learning_rate": 9.145218830428677e-06, + "loss": 0.4138, + "step": 4618 + }, + { + "epoch": 0.6155383795309168, + "grad_norm": 0.31113509013929663, + "learning_rate": 9.144820636123765e-06, + "loss": 0.3904, + "step": 4619 + }, + { + "epoch": 0.6156716417910447, + "grad_norm": 0.2809371266795364, + "learning_rate": 9.144422357765487e-06, + "loss": 0.3705, + "step": 4620 + }, + { + "epoch": 0.6158049040511727, + "grad_norm": 0.295452869879388, + "learning_rate": 9.144023995361925e-06, + "loss": 0.3912, + "step": 4621 + }, + { + "epoch": 0.6159381663113006, + "grad_norm": 1.121659962728362, + "learning_rate": 9.143625548921155e-06, + "loss": 0.4618, + "step": 4622 + }, + { + "epoch": 0.6160714285714286, + "grad_norm": 0.31092360566805144, + "learning_rate": 9.143227018451255e-06, + "loss": 0.4147, + "step": 4623 + }, + { + "epoch": 0.6162046908315565, + "grad_norm": 0.28985484655050214, + "learning_rate": 9.142828403960309e-06, + "loss": 0.4513, + "step": 4624 + }, + { + "epoch": 0.6163379530916845, + "grad_norm": 0.30043736599490906, + "learning_rate": 9.142429705456401e-06, + "loss": 0.3694, + "step": 4625 + }, + { + "epoch": 0.6164712153518124, + "grad_norm": 0.2997420925395298, + "learning_rate": 9.142030922947615e-06, + "loss": 0.3847, + "step": 4626 + }, + { + "epoch": 0.6166044776119403, + "grad_norm": 0.28850074869900516, + "learning_rate": 9.141632056442039e-06, + "loss": 0.3531, + "step": 4627 + }, + { + "epoch": 0.6167377398720683, + "grad_norm": 0.30107401569021136, + "learning_rate": 9.14123310594776e-06, + "loss": 0.4371, + "step": 4628 + }, + { + "epoch": 0.6168710021321961, + "grad_norm": 0.29471153321669374, + "learning_rate": 9.140834071472869e-06, + "loss": 0.3729, + "step": 4629 + }, + { + "epoch": 0.6170042643923241, + "grad_norm": 0.3094055512049228, + "learning_rate": 9.140434953025459e-06, + "loss": 0.5639, + "step": 4630 + }, + { + "epoch": 0.617137526652452, + "grad_norm": 0.30710795846029076, + "learning_rate": 9.140035750613625e-06, + "loss": 0.3911, + "step": 4631 + }, + { + "epoch": 0.6172707889125799, + "grad_norm": 0.48419013319293774, + "learning_rate": 9.13963646424546e-06, + "loss": 0.3457, + "step": 4632 + }, + { + "epoch": 0.6174040511727079, + "grad_norm": 0.30664091848922176, + "learning_rate": 9.139237093929062e-06, + "loss": 0.4928, + "step": 4633 + }, + { + "epoch": 0.6175373134328358, + "grad_norm": 0.3073657264305015, + "learning_rate": 9.13883763967253e-06, + "loss": 0.4558, + "step": 4634 + }, + { + "epoch": 0.6176705756929638, + "grad_norm": 0.3030230691802012, + "learning_rate": 9.138438101483964e-06, + "loss": 0.3841, + "step": 4635 + }, + { + "epoch": 0.6178038379530917, + "grad_norm": 0.3009810463509389, + "learning_rate": 9.138038479371468e-06, + "loss": 0.3834, + "step": 4636 + }, + { + "epoch": 0.6179371002132196, + "grad_norm": 0.3251888129034682, + "learning_rate": 9.137638773343142e-06, + "loss": 0.4985, + "step": 4637 + }, + { + "epoch": 0.6180703624733476, + "grad_norm": 0.2956359282459882, + "learning_rate": 9.137238983407097e-06, + "loss": 0.3567, + "step": 4638 + }, + { + "epoch": 0.6182036247334755, + "grad_norm": 0.2918214080365932, + "learning_rate": 9.136839109571435e-06, + "loss": 0.3638, + "step": 4639 + }, + { + "epoch": 0.6183368869936035, + "grad_norm": 0.2934036221303613, + "learning_rate": 9.136439151844272e-06, + "loss": 0.3822, + "step": 4640 + }, + { + "epoch": 0.6184701492537313, + "grad_norm": 0.27493161754799084, + "learning_rate": 9.136039110233712e-06, + "loss": 0.3754, + "step": 4641 + }, + { + "epoch": 0.6186034115138592, + "grad_norm": 0.3110014050360361, + "learning_rate": 9.135638984747872e-06, + "loss": 0.4378, + "step": 4642 + }, + { + "epoch": 0.6187366737739872, + "grad_norm": 0.3069279962754727, + "learning_rate": 9.135238775394862e-06, + "loss": 0.3812, + "step": 4643 + }, + { + "epoch": 0.6188699360341151, + "grad_norm": 0.30393845879669357, + "learning_rate": 9.134838482182802e-06, + "loss": 0.387, + "step": 4644 + }, + { + "epoch": 0.6190031982942431, + "grad_norm": 0.4203156700264114, + "learning_rate": 9.134438105119807e-06, + "loss": 0.415, + "step": 4645 + }, + { + "epoch": 0.619136460554371, + "grad_norm": 0.30785214621376744, + "learning_rate": 9.134037644213999e-06, + "loss": 0.4027, + "step": 4646 + }, + { + "epoch": 0.6192697228144989, + "grad_norm": 0.3054282893792082, + "learning_rate": 9.133637099473496e-06, + "loss": 0.3971, + "step": 4647 + }, + { + "epoch": 0.6194029850746269, + "grad_norm": 0.3058343338139778, + "learning_rate": 9.133236470906421e-06, + "loss": 0.4323, + "step": 4648 + }, + { + "epoch": 0.6195362473347548, + "grad_norm": 0.2956156936417135, + "learning_rate": 9.1328357585209e-06, + "loss": 0.4117, + "step": 4649 + }, + { + "epoch": 0.6196695095948828, + "grad_norm": 0.30210064268142967, + "learning_rate": 9.13243496232506e-06, + "loss": 0.4557, + "step": 4650 + }, + { + "epoch": 0.6198027718550106, + "grad_norm": 0.3190928490462912, + "learning_rate": 9.132034082327025e-06, + "loss": 0.4187, + "step": 4651 + }, + { + "epoch": 0.6199360341151386, + "grad_norm": 0.29442301102727236, + "learning_rate": 9.131633118534928e-06, + "loss": 0.4468, + "step": 4652 + }, + { + "epoch": 0.6200692963752665, + "grad_norm": 0.3159215594913533, + "learning_rate": 9.1312320709569e-06, + "loss": 0.4293, + "step": 4653 + }, + { + "epoch": 0.6202025586353944, + "grad_norm": 0.3085073408406414, + "learning_rate": 9.13083093960107e-06, + "loss": 0.4307, + "step": 4654 + }, + { + "epoch": 0.6203358208955224, + "grad_norm": 0.30467676650785686, + "learning_rate": 9.130429724475576e-06, + "loss": 0.3907, + "step": 4655 + }, + { + "epoch": 0.6204690831556503, + "grad_norm": 0.3119244020269961, + "learning_rate": 9.130028425588556e-06, + "loss": 0.3686, + "step": 4656 + }, + { + "epoch": 0.6206023454157783, + "grad_norm": 0.29666241606630617, + "learning_rate": 9.129627042948142e-06, + "loss": 0.3804, + "step": 4657 + }, + { + "epoch": 0.6207356076759062, + "grad_norm": 0.30512947440485166, + "learning_rate": 9.12922557656248e-06, + "loss": 0.4008, + "step": 4658 + }, + { + "epoch": 0.6208688699360341, + "grad_norm": 0.31138721802167457, + "learning_rate": 9.128824026439709e-06, + "loss": 0.4681, + "step": 4659 + }, + { + "epoch": 0.6210021321961621, + "grad_norm": 0.3058455774836182, + "learning_rate": 9.12842239258797e-06, + "loss": 0.3786, + "step": 4660 + }, + { + "epoch": 0.62113539445629, + "grad_norm": 0.31712489316585685, + "learning_rate": 9.12802067501541e-06, + "loss": 0.3642, + "step": 4661 + }, + { + "epoch": 0.621268656716418, + "grad_norm": 0.302540068884379, + "learning_rate": 9.127618873730177e-06, + "loss": 0.3636, + "step": 4662 + }, + { + "epoch": 0.6214019189765458, + "grad_norm": 0.30199902093958, + "learning_rate": 9.127216988740416e-06, + "loss": 0.3479, + "step": 4663 + }, + { + "epoch": 0.6215351812366737, + "grad_norm": 0.31284529131392397, + "learning_rate": 9.126815020054279e-06, + "loss": 0.4224, + "step": 4664 + }, + { + "epoch": 0.6216684434968017, + "grad_norm": 0.3175228275190392, + "learning_rate": 9.126412967679915e-06, + "loss": 0.3944, + "step": 4665 + }, + { + "epoch": 0.6218017057569296, + "grad_norm": 0.30573994445646296, + "learning_rate": 9.12601083162548e-06, + "loss": 0.3881, + "step": 4666 + }, + { + "epoch": 0.6219349680170576, + "grad_norm": 0.3063713541018842, + "learning_rate": 9.125608611899128e-06, + "loss": 0.4141, + "step": 4667 + }, + { + "epoch": 0.6220682302771855, + "grad_norm": 0.2989412645307815, + "learning_rate": 9.125206308509017e-06, + "loss": 0.4243, + "step": 4668 + }, + { + "epoch": 0.6222014925373134, + "grad_norm": 0.3046426269329806, + "learning_rate": 9.124803921463302e-06, + "loss": 0.4805, + "step": 4669 + }, + { + "epoch": 0.6223347547974414, + "grad_norm": 0.3190480711053629, + "learning_rate": 9.124401450770146e-06, + "loss": 0.4634, + "step": 4670 + }, + { + "epoch": 0.6224680170575693, + "grad_norm": 0.29762057026465416, + "learning_rate": 9.12399889643771e-06, + "loss": 0.3739, + "step": 4671 + }, + { + "epoch": 0.6226012793176973, + "grad_norm": 0.2941341631688347, + "learning_rate": 9.123596258474156e-06, + "loss": 0.3539, + "step": 4672 + }, + { + "epoch": 0.6227345415778252, + "grad_norm": 0.2996684518485539, + "learning_rate": 9.123193536887653e-06, + "loss": 0.3477, + "step": 4673 + }, + { + "epoch": 0.622867803837953, + "grad_norm": 0.3222991931336168, + "learning_rate": 9.122790731686363e-06, + "loss": 0.4837, + "step": 4674 + }, + { + "epoch": 0.623001066098081, + "grad_norm": 0.29065016813751604, + "learning_rate": 9.122387842878458e-06, + "loss": 0.3872, + "step": 4675 + }, + { + "epoch": 0.6231343283582089, + "grad_norm": 0.2940596527210554, + "learning_rate": 9.121984870472107e-06, + "loss": 0.3952, + "step": 4676 + }, + { + "epoch": 0.6232675906183369, + "grad_norm": 0.2841544354918305, + "learning_rate": 9.121581814475481e-06, + "loss": 0.3415, + "step": 4677 + }, + { + "epoch": 0.6234008528784648, + "grad_norm": 0.2856986167984417, + "learning_rate": 9.121178674896755e-06, + "loss": 0.3876, + "step": 4678 + }, + { + "epoch": 0.6235341151385928, + "grad_norm": 0.3103735661192847, + "learning_rate": 9.120775451744105e-06, + "loss": 0.4297, + "step": 4679 + }, + { + "epoch": 0.6236673773987207, + "grad_norm": 0.3170862394785753, + "learning_rate": 9.120372145025707e-06, + "loss": 0.403, + "step": 4680 + }, + { + "epoch": 0.6238006396588486, + "grad_norm": 0.3158140091246068, + "learning_rate": 9.11996875474974e-06, + "loss": 0.3917, + "step": 4681 + }, + { + "epoch": 0.6239339019189766, + "grad_norm": 0.2873255453291981, + "learning_rate": 9.11956528092438e-06, + "loss": 0.4221, + "step": 4682 + }, + { + "epoch": 0.6240671641791045, + "grad_norm": 0.3135668795731578, + "learning_rate": 9.119161723557816e-06, + "loss": 0.4524, + "step": 4683 + }, + { + "epoch": 0.6242004264392325, + "grad_norm": 0.2842758110168657, + "learning_rate": 9.11875808265823e-06, + "loss": 0.4375, + "step": 4684 + }, + { + "epoch": 0.6243336886993603, + "grad_norm": 0.30005587590256466, + "learning_rate": 9.118354358233806e-06, + "loss": 0.3852, + "step": 4685 + }, + { + "epoch": 0.6244669509594882, + "grad_norm": 0.3021170778730105, + "learning_rate": 9.117950550292731e-06, + "loss": 0.3943, + "step": 4686 + }, + { + "epoch": 0.6246002132196162, + "grad_norm": 0.3037232747789392, + "learning_rate": 9.117546658843195e-06, + "loss": 0.5079, + "step": 4687 + }, + { + "epoch": 0.6247334754797441, + "grad_norm": 0.575345565565463, + "learning_rate": 9.117142683893388e-06, + "loss": 0.4014, + "step": 4688 + }, + { + "epoch": 0.6248667377398721, + "grad_norm": 0.2956586314747177, + "learning_rate": 9.116738625451503e-06, + "loss": 0.3889, + "step": 4689 + }, + { + "epoch": 0.625, + "grad_norm": 0.2937381892835503, + "learning_rate": 9.116334483525731e-06, + "loss": 0.4103, + "step": 4690 + }, + { + "epoch": 0.6251332622601279, + "grad_norm": 0.3321005772982718, + "learning_rate": 9.115930258124272e-06, + "loss": 0.5224, + "step": 4691 + }, + { + "epoch": 0.6252665245202559, + "grad_norm": 0.30001499210502763, + "learning_rate": 9.115525949255322e-06, + "loss": 0.3923, + "step": 4692 + }, + { + "epoch": 0.6253997867803838, + "grad_norm": 0.2915946644405399, + "learning_rate": 9.115121556927078e-06, + "loss": 0.3723, + "step": 4693 + }, + { + "epoch": 0.6255330490405118, + "grad_norm": 0.3176363430791092, + "learning_rate": 9.114717081147741e-06, + "loss": 0.4007, + "step": 4694 + }, + { + "epoch": 0.6256663113006397, + "grad_norm": 0.28507637811718645, + "learning_rate": 9.114312521925515e-06, + "loss": 0.3881, + "step": 4695 + }, + { + "epoch": 0.6257995735607675, + "grad_norm": 0.3008407425570111, + "learning_rate": 9.113907879268604e-06, + "loss": 0.3507, + "step": 4696 + }, + { + "epoch": 0.6259328358208955, + "grad_norm": 0.3248977329153712, + "learning_rate": 9.113503153185214e-06, + "loss": 0.4033, + "step": 4697 + }, + { + "epoch": 0.6260660980810234, + "grad_norm": 0.2997644600530031, + "learning_rate": 9.113098343683551e-06, + "loss": 0.3487, + "step": 4698 + }, + { + "epoch": 0.6261993603411514, + "grad_norm": 0.3034823765021573, + "learning_rate": 9.112693450771826e-06, + "loss": 0.5546, + "step": 4699 + }, + { + "epoch": 0.6263326226012793, + "grad_norm": 0.2900583380772156, + "learning_rate": 9.112288474458248e-06, + "loss": 0.378, + "step": 4700 + }, + { + "epoch": 0.6264658848614072, + "grad_norm": 0.3074085681413579, + "learning_rate": 9.111883414751031e-06, + "loss": 0.4476, + "step": 4701 + }, + { + "epoch": 0.6265991471215352, + "grad_norm": 0.3012614406136484, + "learning_rate": 9.111478271658388e-06, + "loss": 0.3877, + "step": 4702 + }, + { + "epoch": 0.6267324093816631, + "grad_norm": 0.2831771686484376, + "learning_rate": 9.111073045188536e-06, + "loss": 0.5048, + "step": 4703 + }, + { + "epoch": 0.6268656716417911, + "grad_norm": 0.29417312408603064, + "learning_rate": 9.110667735349694e-06, + "loss": 0.3919, + "step": 4704 + }, + { + "epoch": 0.626998933901919, + "grad_norm": 0.29963334450997164, + "learning_rate": 9.110262342150078e-06, + "loss": 0.3943, + "step": 4705 + }, + { + "epoch": 0.627132196162047, + "grad_norm": 0.29078203915466, + "learning_rate": 9.10985686559791e-06, + "loss": 0.3873, + "step": 4706 + }, + { + "epoch": 0.6272654584221748, + "grad_norm": 0.304401042545531, + "learning_rate": 9.109451305701415e-06, + "loss": 0.5107, + "step": 4707 + }, + { + "epoch": 0.6273987206823027, + "grad_norm": 0.2972216006568279, + "learning_rate": 9.109045662468815e-06, + "loss": 0.3807, + "step": 4708 + }, + { + "epoch": 0.6275319829424307, + "grad_norm": 0.29969833308861077, + "learning_rate": 9.108639935908336e-06, + "loss": 0.3654, + "step": 4709 + }, + { + "epoch": 0.6276652452025586, + "grad_norm": 0.2875172489848434, + "learning_rate": 9.108234126028208e-06, + "loss": 0.3775, + "step": 4710 + }, + { + "epoch": 0.6277985074626866, + "grad_norm": 0.299593208684471, + "learning_rate": 9.10782823283666e-06, + "loss": 0.4711, + "step": 4711 + }, + { + "epoch": 0.6279317697228145, + "grad_norm": 0.2992683838945427, + "learning_rate": 9.107422256341921e-06, + "loss": 0.4747, + "step": 4712 + }, + { + "epoch": 0.6280650319829424, + "grad_norm": 0.2985684377344161, + "learning_rate": 9.107016196552225e-06, + "loss": 0.4112, + "step": 4713 + }, + { + "epoch": 0.6281982942430704, + "grad_norm": 0.2778366904563271, + "learning_rate": 9.106610053475808e-06, + "loss": 0.3688, + "step": 4714 + }, + { + "epoch": 0.6283315565031983, + "grad_norm": 0.30393089223762687, + "learning_rate": 9.106203827120903e-06, + "loss": 0.3551, + "step": 4715 + }, + { + "epoch": 0.6284648187633263, + "grad_norm": 0.2802953592518272, + "learning_rate": 9.105797517495752e-06, + "loss": 0.4285, + "step": 4716 + }, + { + "epoch": 0.6285980810234542, + "grad_norm": 0.301573871011601, + "learning_rate": 9.105391124608592e-06, + "loss": 0.501, + "step": 4717 + }, + { + "epoch": 0.628731343283582, + "grad_norm": 0.3032649605207745, + "learning_rate": 9.104984648467663e-06, + "loss": 0.3656, + "step": 4718 + }, + { + "epoch": 0.62886460554371, + "grad_norm": 0.30937165217741186, + "learning_rate": 9.10457808908121e-06, + "loss": 0.4207, + "step": 4719 + }, + { + "epoch": 0.6289978678038379, + "grad_norm": 0.28474121101541866, + "learning_rate": 9.104171446457479e-06, + "loss": 0.4308, + "step": 4720 + }, + { + "epoch": 0.6291311300639659, + "grad_norm": 0.3015480737684838, + "learning_rate": 9.103764720604715e-06, + "loss": 0.4373, + "step": 4721 + }, + { + "epoch": 0.6292643923240938, + "grad_norm": 0.3013203196159392, + "learning_rate": 9.103357911531164e-06, + "loss": 0.4186, + "step": 4722 + }, + { + "epoch": 0.6293976545842217, + "grad_norm": 0.3169029704581022, + "learning_rate": 9.102951019245078e-06, + "loss": 0.4451, + "step": 4723 + }, + { + "epoch": 0.6295309168443497, + "grad_norm": 0.29357237630037275, + "learning_rate": 9.102544043754708e-06, + "loss": 0.3555, + "step": 4724 + }, + { + "epoch": 0.6296641791044776, + "grad_norm": 0.28788800272876425, + "learning_rate": 9.102136985068308e-06, + "loss": 0.3821, + "step": 4725 + }, + { + "epoch": 0.6297974413646056, + "grad_norm": 0.31656998440398043, + "learning_rate": 9.101729843194132e-06, + "loss": 0.4423, + "step": 4726 + }, + { + "epoch": 0.6299307036247335, + "grad_norm": 0.3051197171419816, + "learning_rate": 9.101322618140436e-06, + "loss": 0.4867, + "step": 4727 + }, + { + "epoch": 0.6300639658848614, + "grad_norm": 0.3224867003799037, + "learning_rate": 9.100915309915478e-06, + "loss": 0.4285, + "step": 4728 + }, + { + "epoch": 0.6301972281449894, + "grad_norm": 0.319970992812858, + "learning_rate": 9.10050791852752e-06, + "loss": 0.4291, + "step": 4729 + }, + { + "epoch": 0.6303304904051172, + "grad_norm": 0.29463717037087406, + "learning_rate": 9.10010044398482e-06, + "loss": 0.3616, + "step": 4730 + }, + { + "epoch": 0.6304637526652452, + "grad_norm": 0.3094866312944029, + "learning_rate": 9.099692886295643e-06, + "loss": 0.4315, + "step": 4731 + }, + { + "epoch": 0.6305970149253731, + "grad_norm": 0.30993825685017845, + "learning_rate": 9.099285245468254e-06, + "loss": 0.4359, + "step": 4732 + }, + { + "epoch": 0.6307302771855011, + "grad_norm": 0.28815456426774133, + "learning_rate": 9.098877521510922e-06, + "loss": 0.3941, + "step": 4733 + }, + { + "epoch": 0.630863539445629, + "grad_norm": 0.3081722154418499, + "learning_rate": 9.098469714431913e-06, + "loss": 0.3961, + "step": 4734 + }, + { + "epoch": 0.6309968017057569, + "grad_norm": 0.3016865468761068, + "learning_rate": 9.098061824239494e-06, + "loss": 0.4256, + "step": 4735 + }, + { + "epoch": 0.6311300639658849, + "grad_norm": 0.29119859314157986, + "learning_rate": 9.09765385094194e-06, + "loss": 0.4267, + "step": 4736 + }, + { + "epoch": 0.6312633262260128, + "grad_norm": 0.31250498583851793, + "learning_rate": 9.097245794547526e-06, + "loss": 0.3513, + "step": 4737 + }, + { + "epoch": 0.6313965884861408, + "grad_norm": 0.31977374233275985, + "learning_rate": 9.096837655064524e-06, + "loss": 0.4064, + "step": 4738 + }, + { + "epoch": 0.6315298507462687, + "grad_norm": 0.3078936171456759, + "learning_rate": 9.096429432501212e-06, + "loss": 0.4111, + "step": 4739 + }, + { + "epoch": 0.6316631130063965, + "grad_norm": 0.3128242986345266, + "learning_rate": 9.096021126865869e-06, + "loss": 0.4357, + "step": 4740 + }, + { + "epoch": 0.6317963752665245, + "grad_norm": 0.3027338257570722, + "learning_rate": 9.095612738166773e-06, + "loss": 0.4219, + "step": 4741 + }, + { + "epoch": 0.6319296375266524, + "grad_norm": 0.2873234307084417, + "learning_rate": 9.095204266412206e-06, + "loss": 0.3806, + "step": 4742 + }, + { + "epoch": 0.6320628997867804, + "grad_norm": 0.3070936190765417, + "learning_rate": 9.094795711610454e-06, + "loss": 0.5065, + "step": 4743 + }, + { + "epoch": 0.6321961620469083, + "grad_norm": 0.2852267442936268, + "learning_rate": 9.094387073769798e-06, + "loss": 0.3367, + "step": 4744 + }, + { + "epoch": 0.6323294243070362, + "grad_norm": 0.30620739903365873, + "learning_rate": 9.09397835289853e-06, + "loss": 0.4353, + "step": 4745 + }, + { + "epoch": 0.6324626865671642, + "grad_norm": 0.30626300566120856, + "learning_rate": 9.093569549004934e-06, + "loss": 0.4199, + "step": 4746 + }, + { + "epoch": 0.6325959488272921, + "grad_norm": 0.28913343384811785, + "learning_rate": 9.093160662097305e-06, + "loss": 0.3537, + "step": 4747 + }, + { + "epoch": 0.6327292110874201, + "grad_norm": 0.3167461360582485, + "learning_rate": 9.09275169218393e-06, + "loss": 0.5115, + "step": 4748 + }, + { + "epoch": 0.632862473347548, + "grad_norm": 0.302887866962692, + "learning_rate": 9.092342639273103e-06, + "loss": 0.3859, + "step": 4749 + }, + { + "epoch": 0.6329957356076759, + "grad_norm": 0.29191688075348626, + "learning_rate": 9.091933503373122e-06, + "loss": 0.369, + "step": 4750 + }, + { + "epoch": 0.6331289978678039, + "grad_norm": 0.2909598256136728, + "learning_rate": 9.091524284492285e-06, + "loss": 0.3708, + "step": 4751 + }, + { + "epoch": 0.6332622601279317, + "grad_norm": 0.30319319233556086, + "learning_rate": 9.091114982638885e-06, + "loss": 0.348, + "step": 4752 + }, + { + "epoch": 0.6333955223880597, + "grad_norm": 0.31408304861536085, + "learning_rate": 9.090705597821227e-06, + "loss": 0.3781, + "step": 4753 + }, + { + "epoch": 0.6335287846481876, + "grad_norm": 0.3069143262229145, + "learning_rate": 9.090296130047612e-06, + "loss": 0.3875, + "step": 4754 + }, + { + "epoch": 0.6336620469083155, + "grad_norm": 0.3039909607124537, + "learning_rate": 9.089886579326342e-06, + "loss": 0.37, + "step": 4755 + }, + { + "epoch": 0.6337953091684435, + "grad_norm": 0.3104991717792806, + "learning_rate": 9.089476945665724e-06, + "loss": 0.3994, + "step": 4756 + }, + { + "epoch": 0.6339285714285714, + "grad_norm": 0.31038934107799465, + "learning_rate": 9.089067229074064e-06, + "loss": 0.4681, + "step": 4757 + }, + { + "epoch": 0.6340618336886994, + "grad_norm": 0.30182986376988746, + "learning_rate": 9.088657429559671e-06, + "loss": 0.4503, + "step": 4758 + }, + { + "epoch": 0.6341950959488273, + "grad_norm": 0.32504603614611605, + "learning_rate": 9.088247547130855e-06, + "loss": 0.4103, + "step": 4759 + }, + { + "epoch": 0.6343283582089553, + "grad_norm": 0.3057502285413218, + "learning_rate": 9.087837581795931e-06, + "loss": 0.4209, + "step": 4760 + }, + { + "epoch": 0.6344616204690832, + "grad_norm": 0.3116816784739642, + "learning_rate": 9.087427533563209e-06, + "loss": 0.4006, + "step": 4761 + }, + { + "epoch": 0.634594882729211, + "grad_norm": 4.817004185398904, + "learning_rate": 9.087017402441006e-06, + "loss": 0.3928, + "step": 4762 + }, + { + "epoch": 0.634728144989339, + "grad_norm": 0.3139756245373485, + "learning_rate": 9.086607188437637e-06, + "loss": 0.4605, + "step": 4763 + }, + { + "epoch": 0.6348614072494669, + "grad_norm": 0.30355879948574516, + "learning_rate": 9.086196891561425e-06, + "loss": 0.3727, + "step": 4764 + }, + { + "epoch": 0.6349946695095949, + "grad_norm": 0.3380458596649249, + "learning_rate": 9.085786511820687e-06, + "loss": 0.4095, + "step": 4765 + }, + { + "epoch": 0.6351279317697228, + "grad_norm": 0.3173648478111416, + "learning_rate": 9.085376049223748e-06, + "loss": 0.3832, + "step": 4766 + }, + { + "epoch": 0.6352611940298507, + "grad_norm": 0.3106238350357636, + "learning_rate": 9.084965503778928e-06, + "loss": 0.415, + "step": 4767 + }, + { + "epoch": 0.6353944562899787, + "grad_norm": 0.43775156079279887, + "learning_rate": 9.084554875494556e-06, + "loss": 0.4867, + "step": 4768 + }, + { + "epoch": 0.6355277185501066, + "grad_norm": 0.30146197352488985, + "learning_rate": 9.084144164378956e-06, + "loss": 0.3469, + "step": 4769 + }, + { + "epoch": 0.6356609808102346, + "grad_norm": 0.30782520758050175, + "learning_rate": 9.083733370440462e-06, + "loss": 0.3879, + "step": 4770 + }, + { + "epoch": 0.6357942430703625, + "grad_norm": 0.3024611255958111, + "learning_rate": 9.083322493687399e-06, + "loss": 0.4224, + "step": 4771 + }, + { + "epoch": 0.6359275053304904, + "grad_norm": 0.3211154520580942, + "learning_rate": 9.0829115341281e-06, + "loss": 0.4097, + "step": 4772 + }, + { + "epoch": 0.6360607675906184, + "grad_norm": 0.30033743859280077, + "learning_rate": 9.082500491770903e-06, + "loss": 0.4377, + "step": 4773 + }, + { + "epoch": 0.6361940298507462, + "grad_norm": 0.3105657170166613, + "learning_rate": 9.08208936662414e-06, + "loss": 0.4714, + "step": 4774 + }, + { + "epoch": 0.6363272921108742, + "grad_norm": 0.36399006524825417, + "learning_rate": 9.081678158696147e-06, + "loss": 0.4997, + "step": 4775 + }, + { + "epoch": 0.6364605543710021, + "grad_norm": 0.31543882354484926, + "learning_rate": 9.081266867995269e-06, + "loss": 0.3276, + "step": 4776 + }, + { + "epoch": 0.63659381663113, + "grad_norm": 0.5796524004608091, + "learning_rate": 9.08085549452984e-06, + "loss": 0.4654, + "step": 4777 + }, + { + "epoch": 0.636727078891258, + "grad_norm": 0.3553185089352353, + "learning_rate": 9.080444038308206e-06, + "loss": 0.3801, + "step": 4778 + }, + { + "epoch": 0.6368603411513859, + "grad_norm": 0.30094250654714905, + "learning_rate": 9.080032499338711e-06, + "loss": 0.4364, + "step": 4779 + }, + { + "epoch": 0.6369936034115139, + "grad_norm": 0.29772934098314147, + "learning_rate": 9.079620877629698e-06, + "loss": 0.3943, + "step": 4780 + }, + { + "epoch": 0.6371268656716418, + "grad_norm": 0.30944803785145647, + "learning_rate": 9.079209173189516e-06, + "loss": 0.4239, + "step": 4781 + }, + { + "epoch": 0.6372601279317697, + "grad_norm": 0.342603748329595, + "learning_rate": 9.078797386026515e-06, + "loss": 0.3817, + "step": 4782 + }, + { + "epoch": 0.6373933901918977, + "grad_norm": 0.3117214919004045, + "learning_rate": 9.078385516149044e-06, + "loss": 0.4262, + "step": 4783 + }, + { + "epoch": 0.6375266524520256, + "grad_norm": 0.3334516745851088, + "learning_rate": 9.077973563565456e-06, + "loss": 0.3786, + "step": 4784 + }, + { + "epoch": 0.6376599147121536, + "grad_norm": 0.29644044404251185, + "learning_rate": 9.077561528284106e-06, + "loss": 0.3227, + "step": 4785 + }, + { + "epoch": 0.6377931769722814, + "grad_norm": 0.3107157823109424, + "learning_rate": 9.077149410313348e-06, + "loss": 0.4407, + "step": 4786 + }, + { + "epoch": 0.6379264392324094, + "grad_norm": 0.2778248831273655, + "learning_rate": 9.07673720966154e-06, + "loss": 0.3476, + "step": 4787 + }, + { + "epoch": 0.6380597014925373, + "grad_norm": 0.2952002845982489, + "learning_rate": 9.076324926337043e-06, + "loss": 0.4733, + "step": 4788 + }, + { + "epoch": 0.6381929637526652, + "grad_norm": 0.302577035465443, + "learning_rate": 9.075912560348214e-06, + "loss": 0.3698, + "step": 4789 + }, + { + "epoch": 0.6383262260127932, + "grad_norm": 0.3105534204736976, + "learning_rate": 9.075500111703418e-06, + "loss": 0.4004, + "step": 4790 + }, + { + "epoch": 0.6384594882729211, + "grad_norm": 0.31465087186825424, + "learning_rate": 9.07508758041102e-06, + "loss": 0.4207, + "step": 4791 + }, + { + "epoch": 0.6385927505330491, + "grad_norm": 0.30578292128518736, + "learning_rate": 9.074674966479382e-06, + "loss": 0.3811, + "step": 4792 + }, + { + "epoch": 0.638726012793177, + "grad_norm": 0.30589001251266446, + "learning_rate": 9.074262269916874e-06, + "loss": 0.4271, + "step": 4793 + }, + { + "epoch": 0.6388592750533049, + "grad_norm": 0.29196977004382707, + "learning_rate": 9.073849490731867e-06, + "loss": 0.4467, + "step": 4794 + }, + { + "epoch": 0.6389925373134329, + "grad_norm": 0.3210488309423485, + "learning_rate": 9.073436628932728e-06, + "loss": 0.4136, + "step": 4795 + }, + { + "epoch": 0.6391257995735607, + "grad_norm": 0.3147692118735806, + "learning_rate": 9.07302368452783e-06, + "loss": 0.3883, + "step": 4796 + }, + { + "epoch": 0.6392590618336887, + "grad_norm": 0.2746568579424913, + "learning_rate": 9.072610657525552e-06, + "loss": 0.3221, + "step": 4797 + }, + { + "epoch": 0.6393923240938166, + "grad_norm": 0.3769123802014426, + "learning_rate": 9.072197547934263e-06, + "loss": 0.445, + "step": 4798 + }, + { + "epoch": 0.6395255863539445, + "grad_norm": 0.30448559331675185, + "learning_rate": 9.071784355762345e-06, + "loss": 0.4117, + "step": 4799 + }, + { + "epoch": 0.6396588486140725, + "grad_norm": 0.308020108545317, + "learning_rate": 9.071371081018174e-06, + "loss": 0.3865, + "step": 4800 + }, + { + "epoch": 0.6397921108742004, + "grad_norm": 0.30360171649395384, + "learning_rate": 9.070957723710135e-06, + "loss": 0.4114, + "step": 4801 + }, + { + "epoch": 0.6399253731343284, + "grad_norm": 0.6821388419858913, + "learning_rate": 9.070544283846607e-06, + "loss": 0.3827, + "step": 4802 + }, + { + "epoch": 0.6400586353944563, + "grad_norm": 0.34648637294840795, + "learning_rate": 9.070130761435979e-06, + "loss": 0.4125, + "step": 4803 + }, + { + "epoch": 0.6401918976545842, + "grad_norm": 0.3095585747318106, + "learning_rate": 9.069717156486629e-06, + "loss": 0.4202, + "step": 4804 + }, + { + "epoch": 0.6403251599147122, + "grad_norm": 0.30138849139930324, + "learning_rate": 9.069303469006949e-06, + "loss": 0.4176, + "step": 4805 + }, + { + "epoch": 0.6404584221748401, + "grad_norm": 0.31385039997714687, + "learning_rate": 9.06888969900533e-06, + "loss": 0.396, + "step": 4806 + }, + { + "epoch": 0.6405916844349681, + "grad_norm": 0.6775260829917507, + "learning_rate": 9.06847584649016e-06, + "loss": 0.3942, + "step": 4807 + }, + { + "epoch": 0.6407249466950959, + "grad_norm": 0.3201849126344524, + "learning_rate": 9.068061911469832e-06, + "loss": 0.3736, + "step": 4808 + }, + { + "epoch": 0.6408582089552238, + "grad_norm": 0.30106027640706884, + "learning_rate": 9.067647893952743e-06, + "loss": 0.4426, + "step": 4809 + }, + { + "epoch": 0.6409914712153518, + "grad_norm": 0.3102873430039818, + "learning_rate": 9.067233793947284e-06, + "loss": 0.4211, + "step": 4810 + }, + { + "epoch": 0.6411247334754797, + "grad_norm": 0.2889101707018944, + "learning_rate": 9.066819611461856e-06, + "loss": 0.3557, + "step": 4811 + }, + { + "epoch": 0.6412579957356077, + "grad_norm": 0.2955816487866101, + "learning_rate": 9.066405346504859e-06, + "loss": 0.3635, + "step": 4812 + }, + { + "epoch": 0.6413912579957356, + "grad_norm": 0.3079353951565923, + "learning_rate": 9.06599099908469e-06, + "loss": 0.3762, + "step": 4813 + }, + { + "epoch": 0.6415245202558635, + "grad_norm": 0.31005739865557785, + "learning_rate": 9.065576569209757e-06, + "loss": 0.3944, + "step": 4814 + }, + { + "epoch": 0.6416577825159915, + "grad_norm": 0.29715808230562357, + "learning_rate": 9.065162056888461e-06, + "loss": 0.4637, + "step": 4815 + }, + { + "epoch": 0.6417910447761194, + "grad_norm": 0.31888060687696707, + "learning_rate": 9.064747462129206e-06, + "loss": 0.5238, + "step": 4816 + }, + { + "epoch": 0.6419243070362474, + "grad_norm": 0.3194666940576439, + "learning_rate": 9.064332784940404e-06, + "loss": 0.3964, + "step": 4817 + }, + { + "epoch": 0.6420575692963753, + "grad_norm": 0.3085854403213107, + "learning_rate": 9.06391802533046e-06, + "loss": 0.3797, + "step": 4818 + }, + { + "epoch": 0.6421908315565032, + "grad_norm": 0.34660421299962635, + "learning_rate": 9.06350318330779e-06, + "loss": 0.4212, + "step": 4819 + }, + { + "epoch": 0.6423240938166311, + "grad_norm": 0.323425170944032, + "learning_rate": 9.063088258880803e-06, + "loss": 0.4781, + "step": 4820 + }, + { + "epoch": 0.642457356076759, + "grad_norm": 1.5119052187745323, + "learning_rate": 9.062673252057913e-06, + "loss": 0.509, + "step": 4821 + }, + { + "epoch": 0.642590618336887, + "grad_norm": 0.35453550987027443, + "learning_rate": 9.062258162847539e-06, + "loss": 0.4712, + "step": 4822 + }, + { + "epoch": 0.6427238805970149, + "grad_norm": 0.2910262722477831, + "learning_rate": 9.061842991258094e-06, + "loss": 0.3649, + "step": 4823 + }, + { + "epoch": 0.6428571428571429, + "grad_norm": 0.3275117456567277, + "learning_rate": 9.061427737298003e-06, + "loss": 0.4335, + "step": 4824 + }, + { + "epoch": 0.6429904051172708, + "grad_norm": 0.3072669969746707, + "learning_rate": 9.061012400975681e-06, + "loss": 0.4846, + "step": 4825 + }, + { + "epoch": 0.6431236673773987, + "grad_norm": 0.3153483736388604, + "learning_rate": 9.060596982299557e-06, + "loss": 0.3708, + "step": 4826 + }, + { + "epoch": 0.6432569296375267, + "grad_norm": 0.32161909719432147, + "learning_rate": 9.06018148127805e-06, + "loss": 0.4332, + "step": 4827 + }, + { + "epoch": 0.6433901918976546, + "grad_norm": 0.3115848935866543, + "learning_rate": 9.059765897919588e-06, + "loss": 0.4059, + "step": 4828 + }, + { + "epoch": 0.6435234541577826, + "grad_norm": 0.32065345197785683, + "learning_rate": 9.0593502322326e-06, + "loss": 0.476, + "step": 4829 + }, + { + "epoch": 0.6436567164179104, + "grad_norm": 0.4287833735863429, + "learning_rate": 9.058934484225514e-06, + "loss": 0.452, + "step": 4830 + }, + { + "epoch": 0.6437899786780383, + "grad_norm": 0.30399909514553675, + "learning_rate": 9.058518653906761e-06, + "loss": 0.3952, + "step": 4831 + }, + { + "epoch": 0.6439232409381663, + "grad_norm": 0.29272469836911125, + "learning_rate": 9.058102741284773e-06, + "loss": 0.3311, + "step": 4832 + }, + { + "epoch": 0.6440565031982942, + "grad_norm": 0.3023290954015927, + "learning_rate": 9.057686746367984e-06, + "loss": 0.3663, + "step": 4833 + }, + { + "epoch": 0.6441897654584222, + "grad_norm": 0.30902108650883864, + "learning_rate": 9.057270669164834e-06, + "loss": 0.3645, + "step": 4834 + }, + { + "epoch": 0.6443230277185501, + "grad_norm": 0.2901266581576591, + "learning_rate": 9.056854509683755e-06, + "loss": 0.4537, + "step": 4835 + }, + { + "epoch": 0.644456289978678, + "grad_norm": 0.3187101786239376, + "learning_rate": 9.056438267933192e-06, + "loss": 0.407, + "step": 4836 + }, + { + "epoch": 0.644589552238806, + "grad_norm": 0.294825207331862, + "learning_rate": 9.05602194392158e-06, + "loss": 0.3893, + "step": 4837 + }, + { + "epoch": 0.6447228144989339, + "grad_norm": 0.31071444877399407, + "learning_rate": 9.055605537657369e-06, + "loss": 0.4473, + "step": 4838 + }, + { + "epoch": 0.6448560767590619, + "grad_norm": 0.2887681253929978, + "learning_rate": 9.055189049148996e-06, + "loss": 0.3511, + "step": 4839 + }, + { + "epoch": 0.6449893390191898, + "grad_norm": 0.303715654899446, + "learning_rate": 9.05477247840491e-06, + "loss": 0.3881, + "step": 4840 + }, + { + "epoch": 0.6451226012793176, + "grad_norm": 0.2951719411825157, + "learning_rate": 9.05435582543356e-06, + "loss": 0.4334, + "step": 4841 + }, + { + "epoch": 0.6452558635394456, + "grad_norm": 0.311123699859458, + "learning_rate": 9.053939090243395e-06, + "loss": 0.4252, + "step": 4842 + }, + { + "epoch": 0.6453891257995735, + "grad_norm": 0.30948473050948866, + "learning_rate": 9.053522272842864e-06, + "loss": 0.3905, + "step": 4843 + }, + { + "epoch": 0.6455223880597015, + "grad_norm": 0.293290099882546, + "learning_rate": 9.053105373240422e-06, + "loss": 0.3519, + "step": 4844 + }, + { + "epoch": 0.6456556503198294, + "grad_norm": 0.28115049528322, + "learning_rate": 9.052688391444523e-06, + "loss": 0.3918, + "step": 4845 + }, + { + "epoch": 0.6457889125799574, + "grad_norm": 0.29303069261589093, + "learning_rate": 9.05227132746362e-06, + "loss": 0.4667, + "step": 4846 + }, + { + "epoch": 0.6459221748400853, + "grad_norm": 0.28609681906042644, + "learning_rate": 9.051854181306174e-06, + "loss": 0.5249, + "step": 4847 + }, + { + "epoch": 0.6460554371002132, + "grad_norm": 0.29657239471712543, + "learning_rate": 9.051436952980646e-06, + "loss": 0.403, + "step": 4848 + }, + { + "epoch": 0.6461886993603412, + "grad_norm": 0.3135799314357385, + "learning_rate": 9.051019642495492e-06, + "loss": 0.3868, + "step": 4849 + }, + { + "epoch": 0.6463219616204691, + "grad_norm": 0.2897216384196557, + "learning_rate": 9.050602249859178e-06, + "loss": 0.4125, + "step": 4850 + }, + { + "epoch": 0.6464552238805971, + "grad_norm": 0.3008113788414117, + "learning_rate": 9.050184775080168e-06, + "loss": 0.4147, + "step": 4851 + }, + { + "epoch": 0.646588486140725, + "grad_norm": 0.2889913042528193, + "learning_rate": 9.049767218166926e-06, + "loss": 0.3942, + "step": 4852 + }, + { + "epoch": 0.6467217484008528, + "grad_norm": 0.2989818665655635, + "learning_rate": 9.049349579127923e-06, + "loss": 0.3468, + "step": 4853 + }, + { + "epoch": 0.6468550106609808, + "grad_norm": 0.3231162619644462, + "learning_rate": 9.048931857971626e-06, + "loss": 0.5513, + "step": 4854 + }, + { + "epoch": 0.6469882729211087, + "grad_norm": 0.2863964680676845, + "learning_rate": 9.048514054706505e-06, + "loss": 0.3591, + "step": 4855 + }, + { + "epoch": 0.6471215351812367, + "grad_norm": 0.29678846775139517, + "learning_rate": 9.048096169341037e-06, + "loss": 0.3301, + "step": 4856 + }, + { + "epoch": 0.6472547974413646, + "grad_norm": 0.3082462865749706, + "learning_rate": 9.047678201883692e-06, + "loss": 0.3734, + "step": 4857 + }, + { + "epoch": 0.6473880597014925, + "grad_norm": 0.2912414938764704, + "learning_rate": 9.04726015234295e-06, + "loss": 0.3669, + "step": 4858 + }, + { + "epoch": 0.6475213219616205, + "grad_norm": 0.32038115810021567, + "learning_rate": 9.046842020727285e-06, + "loss": 0.444, + "step": 4859 + }, + { + "epoch": 0.6476545842217484, + "grad_norm": 0.3050653384359616, + "learning_rate": 9.046423807045177e-06, + "loss": 0.4023, + "step": 4860 + }, + { + "epoch": 0.6477878464818764, + "grad_norm": 0.29549665303567957, + "learning_rate": 9.046005511305108e-06, + "loss": 0.3791, + "step": 4861 + }, + { + "epoch": 0.6479211087420043, + "grad_norm": 0.29351631460144095, + "learning_rate": 9.04558713351556e-06, + "loss": 0.3795, + "step": 4862 + }, + { + "epoch": 0.6480543710021321, + "grad_norm": 0.2994442413226341, + "learning_rate": 9.045168673685019e-06, + "loss": 0.425, + "step": 4863 + }, + { + "epoch": 0.6481876332622601, + "grad_norm": 0.27922220498355277, + "learning_rate": 9.044750131821969e-06, + "loss": 0.3516, + "step": 4864 + }, + { + "epoch": 0.648320895522388, + "grad_norm": 0.3043763638889056, + "learning_rate": 9.044331507934898e-06, + "loss": 0.3429, + "step": 4865 + }, + { + "epoch": 0.648454157782516, + "grad_norm": 0.3177383579156202, + "learning_rate": 9.043912802032297e-06, + "loss": 0.396, + "step": 4866 + }, + { + "epoch": 0.6485874200426439, + "grad_norm": 0.31661244360861285, + "learning_rate": 9.043494014122656e-06, + "loss": 0.4415, + "step": 4867 + }, + { + "epoch": 0.6487206823027718, + "grad_norm": 0.3008210169326578, + "learning_rate": 9.043075144214466e-06, + "loss": 0.4082, + "step": 4868 + }, + { + "epoch": 0.6488539445628998, + "grad_norm": 0.3082289022822132, + "learning_rate": 9.042656192316224e-06, + "loss": 0.4058, + "step": 4869 + }, + { + "epoch": 0.6489872068230277, + "grad_norm": 0.3356054442769785, + "learning_rate": 9.042237158436423e-06, + "loss": 0.4282, + "step": 4870 + }, + { + "epoch": 0.6491204690831557, + "grad_norm": 0.2885811149377334, + "learning_rate": 9.041818042583563e-06, + "loss": 0.3609, + "step": 4871 + }, + { + "epoch": 0.6492537313432836, + "grad_norm": 0.298939761752422, + "learning_rate": 9.041398844766144e-06, + "loss": 0.3792, + "step": 4872 + }, + { + "epoch": 0.6493869936034116, + "grad_norm": 0.28301263710380087, + "learning_rate": 9.040979564992664e-06, + "loss": 0.3885, + "step": 4873 + }, + { + "epoch": 0.6495202558635395, + "grad_norm": 0.2828642500785133, + "learning_rate": 9.040560203271629e-06, + "loss": 0.3758, + "step": 4874 + }, + { + "epoch": 0.6496535181236673, + "grad_norm": 0.4506903066928057, + "learning_rate": 9.04014075961154e-06, + "loss": 0.3329, + "step": 4875 + }, + { + "epoch": 0.6497867803837953, + "grad_norm": 0.30416611094748036, + "learning_rate": 9.039721234020905e-06, + "loss": 0.4076, + "step": 4876 + }, + { + "epoch": 0.6499200426439232, + "grad_norm": 0.28393404615515533, + "learning_rate": 9.03930162650823e-06, + "loss": 0.4949, + "step": 4877 + }, + { + "epoch": 0.6500533049040512, + "grad_norm": 0.29619670688626276, + "learning_rate": 9.038881937082028e-06, + "loss": 0.4943, + "step": 4878 + }, + { + "epoch": 0.6501865671641791, + "grad_norm": 0.29647688963105917, + "learning_rate": 9.038462165750805e-06, + "loss": 0.4139, + "step": 4879 + }, + { + "epoch": 0.650319829424307, + "grad_norm": 0.2904923281253783, + "learning_rate": 9.038042312523076e-06, + "loss": 0.381, + "step": 4880 + }, + { + "epoch": 0.650453091684435, + "grad_norm": 0.30729977944845605, + "learning_rate": 9.037622377407357e-06, + "loss": 0.4092, + "step": 4881 + }, + { + "epoch": 0.6505863539445629, + "grad_norm": 0.28622032129092045, + "learning_rate": 9.037202360412161e-06, + "loss": 0.3901, + "step": 4882 + }, + { + "epoch": 0.6507196162046909, + "grad_norm": 0.31213595335759814, + "learning_rate": 9.036782261546007e-06, + "loss": 0.3968, + "step": 4883 + }, + { + "epoch": 0.6508528784648188, + "grad_norm": 0.2799896839406331, + "learning_rate": 9.036362080817414e-06, + "loss": 0.3287, + "step": 4884 + }, + { + "epoch": 0.6509861407249466, + "grad_norm": 0.30447976031901114, + "learning_rate": 9.035941818234903e-06, + "loss": 0.3982, + "step": 4885 + }, + { + "epoch": 0.6511194029850746, + "grad_norm": 0.2968680705813589, + "learning_rate": 9.035521473806996e-06, + "loss": 0.3855, + "step": 4886 + }, + { + "epoch": 0.6512526652452025, + "grad_norm": 0.29079843712962844, + "learning_rate": 9.035101047542216e-06, + "loss": 0.4257, + "step": 4887 + }, + { + "epoch": 0.6513859275053305, + "grad_norm": 0.3059170782164559, + "learning_rate": 9.034680539449093e-06, + "loss": 0.4057, + "step": 4888 + }, + { + "epoch": 0.6515191897654584, + "grad_norm": 0.30432175297356795, + "learning_rate": 9.03425994953615e-06, + "loss": 0.416, + "step": 4889 + }, + { + "epoch": 0.6516524520255863, + "grad_norm": 0.4346189008244637, + "learning_rate": 9.03383927781192e-06, + "loss": 0.4253, + "step": 4890 + }, + { + "epoch": 0.6517857142857143, + "grad_norm": 0.30574861933490194, + "learning_rate": 9.033418524284932e-06, + "loss": 0.4192, + "step": 4891 + }, + { + "epoch": 0.6519189765458422, + "grad_norm": 0.29018786087521536, + "learning_rate": 9.032997688963717e-06, + "loss": 0.4331, + "step": 4892 + }, + { + "epoch": 0.6520522388059702, + "grad_norm": 0.34400592357347964, + "learning_rate": 9.032576771856813e-06, + "loss": 0.4097, + "step": 4893 + }, + { + "epoch": 0.6521855010660981, + "grad_norm": 0.3005690921185033, + "learning_rate": 9.032155772972752e-06, + "loss": 0.3748, + "step": 4894 + }, + { + "epoch": 0.652318763326226, + "grad_norm": 0.2978825468140314, + "learning_rate": 9.031734692320074e-06, + "loss": 0.3897, + "step": 4895 + }, + { + "epoch": 0.652452025586354, + "grad_norm": 0.29880504758008697, + "learning_rate": 9.031313529907315e-06, + "loss": 0.4338, + "step": 4896 + }, + { + "epoch": 0.6525852878464818, + "grad_norm": 0.32907211393409813, + "learning_rate": 9.03089228574302e-06, + "loss": 0.467, + "step": 4897 + }, + { + "epoch": 0.6527185501066098, + "grad_norm": 0.2950768654540496, + "learning_rate": 9.030470959835729e-06, + "loss": 0.3837, + "step": 4898 + }, + { + "epoch": 0.6528518123667377, + "grad_norm": 0.29934456025745704, + "learning_rate": 9.030049552193988e-06, + "loss": 0.3859, + "step": 4899 + }, + { + "epoch": 0.6529850746268657, + "grad_norm": 0.29983025570093624, + "learning_rate": 9.02962806282634e-06, + "loss": 0.5509, + "step": 4900 + }, + { + "epoch": 0.6531183368869936, + "grad_norm": 0.29747081348219745, + "learning_rate": 9.029206491741333e-06, + "loss": 0.3857, + "step": 4901 + }, + { + "epoch": 0.6532515991471215, + "grad_norm": 0.30648967374920427, + "learning_rate": 9.02878483894752e-06, + "loss": 0.4994, + "step": 4902 + }, + { + "epoch": 0.6533848614072495, + "grad_norm": 0.3011785500196284, + "learning_rate": 9.028363104453445e-06, + "loss": 0.3742, + "step": 4903 + }, + { + "epoch": 0.6535181236673774, + "grad_norm": 0.2995336285783722, + "learning_rate": 9.027941288267668e-06, + "loss": 0.4413, + "step": 4904 + }, + { + "epoch": 0.6536513859275054, + "grad_norm": 0.30388840883175106, + "learning_rate": 9.027519390398735e-06, + "loss": 0.3581, + "step": 4905 + }, + { + "epoch": 0.6537846481876333, + "grad_norm": 0.28598622014727093, + "learning_rate": 9.02709741085521e-06, + "loss": 0.4628, + "step": 4906 + }, + { + "epoch": 0.6539179104477612, + "grad_norm": 0.308212714516204, + "learning_rate": 9.026675349645644e-06, + "loss": 0.5217, + "step": 4907 + }, + { + "epoch": 0.6540511727078892, + "grad_norm": 0.2952993458693689, + "learning_rate": 9.0262532067786e-06, + "loss": 0.3997, + "step": 4908 + }, + { + "epoch": 0.654184434968017, + "grad_norm": 0.29287136889112353, + "learning_rate": 9.025830982262634e-06, + "loss": 0.4005, + "step": 4909 + }, + { + "epoch": 0.654317697228145, + "grad_norm": 0.32820544147015407, + "learning_rate": 9.025408676106313e-06, + "loss": 0.3813, + "step": 4910 + }, + { + "epoch": 0.6544509594882729, + "grad_norm": 0.3331345288449429, + "learning_rate": 9.0249862883182e-06, + "loss": 0.4631, + "step": 4911 + }, + { + "epoch": 0.6545842217484008, + "grad_norm": 0.3087711367414891, + "learning_rate": 9.02456381890686e-06, + "loss": 0.4254, + "step": 4912 + }, + { + "epoch": 0.6547174840085288, + "grad_norm": 0.3031057108864099, + "learning_rate": 9.024141267880859e-06, + "loss": 0.3801, + "step": 4913 + }, + { + "epoch": 0.6548507462686567, + "grad_norm": 0.3123043307244204, + "learning_rate": 9.023718635248768e-06, + "loss": 0.4258, + "step": 4914 + }, + { + "epoch": 0.6549840085287847, + "grad_norm": 0.34965571955669106, + "learning_rate": 9.023295921019158e-06, + "loss": 0.4128, + "step": 4915 + }, + { + "epoch": 0.6551172707889126, + "grad_norm": 0.3058641258986822, + "learning_rate": 9.022873125200598e-06, + "loss": 0.377, + "step": 4916 + }, + { + "epoch": 0.6552505330490405, + "grad_norm": 0.34311734735381055, + "learning_rate": 9.022450247801666e-06, + "loss": 0.4293, + "step": 4917 + }, + { + "epoch": 0.6553837953091685, + "grad_norm": 0.3035326832569546, + "learning_rate": 9.022027288830935e-06, + "loss": 0.4333, + "step": 4918 + }, + { + "epoch": 0.6555170575692963, + "grad_norm": 0.3197538096832667, + "learning_rate": 9.021604248296983e-06, + "loss": 0.3545, + "step": 4919 + }, + { + "epoch": 0.6556503198294243, + "grad_norm": 0.30180413675336926, + "learning_rate": 9.02118112620839e-06, + "loss": 0.5264, + "step": 4920 + }, + { + "epoch": 0.6557835820895522, + "grad_norm": 0.3068082895673954, + "learning_rate": 9.020757922573733e-06, + "loss": 0.4641, + "step": 4921 + }, + { + "epoch": 0.6559168443496801, + "grad_norm": 0.32191128786283085, + "learning_rate": 9.020334637401597e-06, + "loss": 0.4334, + "step": 4922 + }, + { + "epoch": 0.6560501066098081, + "grad_norm": 0.3086073072242534, + "learning_rate": 9.019911270700568e-06, + "loss": 0.4735, + "step": 4923 + }, + { + "epoch": 0.656183368869936, + "grad_norm": 0.295917856471956, + "learning_rate": 9.019487822479227e-06, + "loss": 0.3964, + "step": 4924 + }, + { + "epoch": 0.656316631130064, + "grad_norm": 0.3056152366082291, + "learning_rate": 9.019064292746163e-06, + "loss": 0.4601, + "step": 4925 + }, + { + "epoch": 0.6564498933901919, + "grad_norm": 0.31065788821203655, + "learning_rate": 9.018640681509966e-06, + "loss": 0.3939, + "step": 4926 + }, + { + "epoch": 0.6565831556503199, + "grad_norm": 0.3218370038440538, + "learning_rate": 9.018216988779225e-06, + "loss": 0.3936, + "step": 4927 + }, + { + "epoch": 0.6567164179104478, + "grad_norm": 0.30814603900518817, + "learning_rate": 9.017793214562532e-06, + "loss": 0.4229, + "step": 4928 + }, + { + "epoch": 0.6568496801705757, + "grad_norm": 0.3019253684481759, + "learning_rate": 9.017369358868483e-06, + "loss": 0.4031, + "step": 4929 + }, + { + "epoch": 0.6569829424307037, + "grad_norm": 0.30427810479888173, + "learning_rate": 9.01694542170567e-06, + "loss": 0.4365, + "step": 4930 + }, + { + "epoch": 0.6571162046908315, + "grad_norm": 0.297172701809709, + "learning_rate": 9.016521403082691e-06, + "loss": 0.4124, + "step": 4931 + }, + { + "epoch": 0.6572494669509595, + "grad_norm": 0.29934319032370554, + "learning_rate": 9.016097303008148e-06, + "loss": 0.4138, + "step": 4932 + }, + { + "epoch": 0.6573827292110874, + "grad_norm": 0.34777470380478304, + "learning_rate": 9.015673121490637e-06, + "loss": 0.4738, + "step": 4933 + }, + { + "epoch": 0.6575159914712153, + "grad_norm": 0.28270172307952923, + "learning_rate": 9.015248858538763e-06, + "loss": 0.3684, + "step": 4934 + }, + { + "epoch": 0.6576492537313433, + "grad_norm": 0.3145530679326235, + "learning_rate": 9.01482451416113e-06, + "loss": 0.5138, + "step": 4935 + }, + { + "epoch": 0.6577825159914712, + "grad_norm": 0.29858255027382036, + "learning_rate": 9.014400088366339e-06, + "loss": 0.3889, + "step": 4936 + }, + { + "epoch": 0.6579157782515992, + "grad_norm": 1.6881831146485438, + "learning_rate": 9.013975581163002e-06, + "loss": 0.469, + "step": 4937 + }, + { + "epoch": 0.6580490405117271, + "grad_norm": 0.2703711921263907, + "learning_rate": 9.013550992559722e-06, + "loss": 0.3405, + "step": 4938 + }, + { + "epoch": 0.658182302771855, + "grad_norm": 0.30283416774325006, + "learning_rate": 9.013126322565118e-06, + "loss": 0.4149, + "step": 4939 + }, + { + "epoch": 0.658315565031983, + "grad_norm": 0.300678647810219, + "learning_rate": 9.012701571187795e-06, + "loss": 0.3543, + "step": 4940 + }, + { + "epoch": 0.6584488272921108, + "grad_norm": 0.3159063583554709, + "learning_rate": 9.012276738436367e-06, + "loss": 0.3749, + "step": 4941 + }, + { + "epoch": 0.6585820895522388, + "grad_norm": 0.28045827597658884, + "learning_rate": 9.011851824319452e-06, + "loss": 0.3672, + "step": 4942 + }, + { + "epoch": 0.6587153518123667, + "grad_norm": 0.2974694329133613, + "learning_rate": 9.011426828845665e-06, + "loss": 0.3945, + "step": 4943 + }, + { + "epoch": 0.6588486140724946, + "grad_norm": 0.2897646423110347, + "learning_rate": 9.011001752023625e-06, + "loss": 0.3691, + "step": 4944 + }, + { + "epoch": 0.6589818763326226, + "grad_norm": 0.2890418971427102, + "learning_rate": 9.010576593861952e-06, + "loss": 0.4178, + "step": 4945 + }, + { + "epoch": 0.6591151385927505, + "grad_norm": 0.2985427514393942, + "learning_rate": 9.01015135436927e-06, + "loss": 0.5087, + "step": 4946 + }, + { + "epoch": 0.6592484008528785, + "grad_norm": 0.3110921905721793, + "learning_rate": 9.0097260335542e-06, + "loss": 0.3579, + "step": 4947 + }, + { + "epoch": 0.6593816631130064, + "grad_norm": 0.29660904390572757, + "learning_rate": 9.009300631425366e-06, + "loss": 0.4337, + "step": 4948 + }, + { + "epoch": 0.6595149253731343, + "grad_norm": 0.3617621096656369, + "learning_rate": 9.008875147991399e-06, + "loss": 0.4298, + "step": 4949 + }, + { + "epoch": 0.6596481876332623, + "grad_norm": 0.28668207625583386, + "learning_rate": 9.008449583260923e-06, + "loss": 0.4295, + "step": 4950 + }, + { + "epoch": 0.6597814498933902, + "grad_norm": 0.30279989981769473, + "learning_rate": 9.00802393724257e-06, + "loss": 0.3677, + "step": 4951 + }, + { + "epoch": 0.6599147121535182, + "grad_norm": 0.27926619886345977, + "learning_rate": 9.007598209944973e-06, + "loss": 0.3491, + "step": 4952 + }, + { + "epoch": 0.660047974413646, + "grad_norm": 0.30222561391436226, + "learning_rate": 9.007172401376763e-06, + "loss": 0.3822, + "step": 4953 + }, + { + "epoch": 0.660181236673774, + "grad_norm": 0.2821322048977694, + "learning_rate": 9.006746511546577e-06, + "loss": 0.4306, + "step": 4954 + }, + { + "epoch": 0.6603144989339019, + "grad_norm": 0.30050393597746017, + "learning_rate": 9.00632054046305e-06, + "loss": 0.4133, + "step": 4955 + }, + { + "epoch": 0.6604477611940298, + "grad_norm": 0.28735431375674814, + "learning_rate": 9.005894488134821e-06, + "loss": 0.3616, + "step": 4956 + }, + { + "epoch": 0.6605810234541578, + "grad_norm": 0.2819240473099812, + "learning_rate": 9.005468354570532e-06, + "loss": 0.417, + "step": 4957 + }, + { + "epoch": 0.6607142857142857, + "grad_norm": 0.28851778031404, + "learning_rate": 9.005042139778821e-06, + "loss": 0.3497, + "step": 4958 + }, + { + "epoch": 0.6608475479744137, + "grad_norm": 0.2874917374046726, + "learning_rate": 9.004615843768334e-06, + "loss": 0.4908, + "step": 4959 + }, + { + "epoch": 0.6609808102345416, + "grad_norm": 0.3239086521076259, + "learning_rate": 9.004189466547715e-06, + "loss": 0.393, + "step": 4960 + }, + { + "epoch": 0.6611140724946695, + "grad_norm": 0.2919311589857561, + "learning_rate": 9.00376300812561e-06, + "loss": 0.3918, + "step": 4961 + }, + { + "epoch": 0.6612473347547975, + "grad_norm": 0.2821106196342315, + "learning_rate": 9.003336468510668e-06, + "loss": 0.3563, + "step": 4962 + }, + { + "epoch": 0.6613805970149254, + "grad_norm": 0.3232449671152786, + "learning_rate": 9.002909847711539e-06, + "loss": 0.4659, + "step": 4963 + }, + { + "epoch": 0.6615138592750534, + "grad_norm": 0.31901259173511654, + "learning_rate": 9.002483145736873e-06, + "loss": 0.4519, + "step": 4964 + }, + { + "epoch": 0.6616471215351812, + "grad_norm": 0.3099998313793846, + "learning_rate": 9.002056362595324e-06, + "loss": 0.4057, + "step": 4965 + }, + { + "epoch": 0.6617803837953091, + "grad_norm": 0.3065219162563495, + "learning_rate": 9.001629498295547e-06, + "loss": 0.3567, + "step": 4966 + }, + { + "epoch": 0.6619136460554371, + "grad_norm": 0.30937838053551386, + "learning_rate": 9.0012025528462e-06, + "loss": 0.439, + "step": 4967 + }, + { + "epoch": 0.662046908315565, + "grad_norm": 0.3498266221284562, + "learning_rate": 9.00077552625594e-06, + "loss": 0.4221, + "step": 4968 + }, + { + "epoch": 0.662180170575693, + "grad_norm": 0.3071165029331511, + "learning_rate": 9.000348418533425e-06, + "loss": 0.4242, + "step": 4969 + }, + { + "epoch": 0.6623134328358209, + "grad_norm": 0.3009157174374177, + "learning_rate": 8.999921229687316e-06, + "loss": 0.4312, + "step": 4970 + }, + { + "epoch": 0.6624466950959488, + "grad_norm": 0.28287929068973416, + "learning_rate": 8.99949395972628e-06, + "loss": 0.4333, + "step": 4971 + }, + { + "epoch": 0.6625799573560768, + "grad_norm": 0.29547153715999913, + "learning_rate": 8.999066608658979e-06, + "loss": 0.4355, + "step": 4972 + }, + { + "epoch": 0.6627132196162047, + "grad_norm": 0.30608193598821487, + "learning_rate": 8.998639176494079e-06, + "loss": 0.3969, + "step": 4973 + }, + { + "epoch": 0.6628464818763327, + "grad_norm": 0.29326648890874757, + "learning_rate": 8.998211663240248e-06, + "loss": 0.4109, + "step": 4974 + }, + { + "epoch": 0.6629797441364605, + "grad_norm": 0.30230403112146603, + "learning_rate": 8.997784068906157e-06, + "loss": 0.4314, + "step": 4975 + }, + { + "epoch": 0.6631130063965884, + "grad_norm": 0.30004609638670776, + "learning_rate": 8.997356393500476e-06, + "loss": 0.4203, + "step": 4976 + }, + { + "epoch": 0.6632462686567164, + "grad_norm": 0.30040037245, + "learning_rate": 8.996928637031879e-06, + "loss": 0.4145, + "step": 4977 + }, + { + "epoch": 0.6633795309168443, + "grad_norm": 0.29489710024003973, + "learning_rate": 8.99650079950904e-06, + "loss": 0.4114, + "step": 4978 + }, + { + "epoch": 0.6635127931769723, + "grad_norm": 0.294842560270498, + "learning_rate": 8.996072880940634e-06, + "loss": 0.4088, + "step": 4979 + }, + { + "epoch": 0.6636460554371002, + "grad_norm": 0.2830426089533507, + "learning_rate": 8.99564488133534e-06, + "loss": 0.4462, + "step": 4980 + }, + { + "epoch": 0.6637793176972282, + "grad_norm": 0.30921905632991153, + "learning_rate": 8.995216800701838e-06, + "loss": 0.4523, + "step": 4981 + }, + { + "epoch": 0.6639125799573561, + "grad_norm": 0.30810305375358266, + "learning_rate": 8.994788639048808e-06, + "loss": 0.4585, + "step": 4982 + }, + { + "epoch": 0.664045842217484, + "grad_norm": 0.29478064262623893, + "learning_rate": 8.994360396384933e-06, + "loss": 0.4141, + "step": 4983 + }, + { + "epoch": 0.664179104477612, + "grad_norm": 0.3043787771209828, + "learning_rate": 8.993932072718898e-06, + "loss": 0.4797, + "step": 4984 + }, + { + "epoch": 0.6643123667377399, + "grad_norm": 0.3124494448901599, + "learning_rate": 8.993503668059388e-06, + "loss": 0.3857, + "step": 4985 + }, + { + "epoch": 0.6644456289978679, + "grad_norm": 0.29146827006478054, + "learning_rate": 8.993075182415091e-06, + "loss": 0.3788, + "step": 4986 + }, + { + "epoch": 0.6645788912579957, + "grad_norm": 0.3834455634197925, + "learning_rate": 8.992646615794696e-06, + "loss": 0.3917, + "step": 4987 + }, + { + "epoch": 0.6647121535181236, + "grad_norm": 0.2829389205326635, + "learning_rate": 8.992217968206895e-06, + "loss": 0.4473, + "step": 4988 + }, + { + "epoch": 0.6648454157782516, + "grad_norm": 0.29295057528014606, + "learning_rate": 8.991789239660382e-06, + "loss": 0.3803, + "step": 4989 + }, + { + "epoch": 0.6649786780383795, + "grad_norm": 0.29190540187055575, + "learning_rate": 8.991360430163846e-06, + "loss": 0.4, + "step": 4990 + }, + { + "epoch": 0.6651119402985075, + "grad_norm": 0.29000226806403717, + "learning_rate": 8.99093153972599e-06, + "loss": 0.4439, + "step": 4991 + }, + { + "epoch": 0.6652452025586354, + "grad_norm": 0.2843578143851472, + "learning_rate": 8.990502568355506e-06, + "loss": 0.4088, + "step": 4992 + }, + { + "epoch": 0.6653784648187633, + "grad_norm": 0.3004420971917516, + "learning_rate": 8.990073516061095e-06, + "loss": 0.3936, + "step": 4993 + }, + { + "epoch": 0.6655117270788913, + "grad_norm": 0.30765845140958104, + "learning_rate": 8.989644382851457e-06, + "loss": 0.452, + "step": 4994 + }, + { + "epoch": 0.6656449893390192, + "grad_norm": 0.2899184343013991, + "learning_rate": 8.989215168735295e-06, + "loss": 0.3977, + "step": 4995 + }, + { + "epoch": 0.6657782515991472, + "grad_norm": 0.28351592419993366, + "learning_rate": 8.988785873721314e-06, + "loss": 0.4771, + "step": 4996 + }, + { + "epoch": 0.665911513859275, + "grad_norm": 0.2967224051815637, + "learning_rate": 8.988356497818219e-06, + "loss": 0.3684, + "step": 4997 + }, + { + "epoch": 0.6660447761194029, + "grad_norm": 0.2887504450385638, + "learning_rate": 8.987927041034717e-06, + "loss": 0.3956, + "step": 4998 + }, + { + "epoch": 0.6661780383795309, + "grad_norm": 0.35344530231022075, + "learning_rate": 8.987497503379519e-06, + "loss": 0.439, + "step": 4999 + }, + { + "epoch": 0.6663113006396588, + "grad_norm": 0.28559853772047133, + "learning_rate": 8.98706788486133e-06, + "loss": 0.3856, + "step": 5000 + }, + { + "epoch": 0.6664445628997868, + "grad_norm": 0.7505594340355296, + "learning_rate": 8.98663818548887e-06, + "loss": 0.3412, + "step": 5001 + }, + { + "epoch": 0.6665778251599147, + "grad_norm": 0.2792289591983652, + "learning_rate": 8.98620840527085e-06, + "loss": 0.3761, + "step": 5002 + }, + { + "epoch": 0.6667110874200426, + "grad_norm": 0.2858681550866572, + "learning_rate": 8.985778544215981e-06, + "loss": 0.3895, + "step": 5003 + }, + { + "epoch": 0.6668443496801706, + "grad_norm": 0.3004546190624793, + "learning_rate": 8.985348602332987e-06, + "loss": 0.4475, + "step": 5004 + }, + { + "epoch": 0.6669776119402985, + "grad_norm": 0.31538020574873943, + "learning_rate": 8.984918579630584e-06, + "loss": 0.4479, + "step": 5005 + }, + { + "epoch": 0.6671108742004265, + "grad_norm": 0.2818783821493866, + "learning_rate": 8.98448847611749e-06, + "loss": 0.3532, + "step": 5006 + }, + { + "epoch": 0.6672441364605544, + "grad_norm": 0.2793067462775516, + "learning_rate": 8.984058291802431e-06, + "loss": 0.3471, + "step": 5007 + }, + { + "epoch": 0.6673773987206824, + "grad_norm": 0.2832152873929585, + "learning_rate": 8.98362802669413e-06, + "loss": 0.3596, + "step": 5008 + }, + { + "epoch": 0.6675106609808102, + "grad_norm": 0.29916112737228423, + "learning_rate": 8.983197680801309e-06, + "loss": 0.4104, + "step": 5009 + }, + { + "epoch": 0.6676439232409381, + "grad_norm": 0.2975037170861778, + "learning_rate": 8.982767254132701e-06, + "loss": 0.3764, + "step": 5010 + }, + { + "epoch": 0.6677771855010661, + "grad_norm": 0.30626610006442323, + "learning_rate": 8.98233674669703e-06, + "loss": 0.4606, + "step": 5011 + }, + { + "epoch": 0.667910447761194, + "grad_norm": 0.27281079651136236, + "learning_rate": 8.981906158503027e-06, + "loss": 0.3431, + "step": 5012 + }, + { + "epoch": 0.668043710021322, + "grad_norm": 0.2830896741457985, + "learning_rate": 8.981475489559424e-06, + "loss": 0.3714, + "step": 5013 + }, + { + "epoch": 0.6681769722814499, + "grad_norm": 0.2892296958585928, + "learning_rate": 8.981044739874958e-06, + "loss": 0.3903, + "step": 5014 + }, + { + "epoch": 0.6683102345415778, + "grad_norm": 0.2983711408037519, + "learning_rate": 8.98061390945836e-06, + "loss": 0.3711, + "step": 5015 + }, + { + "epoch": 0.6684434968017058, + "grad_norm": 0.29058878802330285, + "learning_rate": 8.980182998318368e-06, + "loss": 0.426, + "step": 5016 + }, + { + "epoch": 0.6685767590618337, + "grad_norm": 0.2913633826280383, + "learning_rate": 8.97975200646372e-06, + "loss": 0.4397, + "step": 5017 + }, + { + "epoch": 0.6687100213219617, + "grad_norm": 0.3184333023850207, + "learning_rate": 8.97932093390316e-06, + "loss": 0.4278, + "step": 5018 + }, + { + "epoch": 0.6688432835820896, + "grad_norm": 0.315475208807849, + "learning_rate": 8.978889780645423e-06, + "loss": 0.4274, + "step": 5019 + }, + { + "epoch": 0.6689765458422174, + "grad_norm": 0.28877787161082197, + "learning_rate": 8.978458546699258e-06, + "loss": 0.36, + "step": 5020 + }, + { + "epoch": 0.6691098081023454, + "grad_norm": 0.29738456747220215, + "learning_rate": 8.978027232073407e-06, + "loss": 0.4397, + "step": 5021 + }, + { + "epoch": 0.6692430703624733, + "grad_norm": 0.2915731460472577, + "learning_rate": 8.97759583677662e-06, + "loss": 0.3677, + "step": 5022 + }, + { + "epoch": 0.6693763326226013, + "grad_norm": 0.2833710849182227, + "learning_rate": 8.977164360817642e-06, + "loss": 0.3445, + "step": 5023 + }, + { + "epoch": 0.6695095948827292, + "grad_norm": 0.297309325843715, + "learning_rate": 8.976732804205224e-06, + "loss": 0.3519, + "step": 5024 + }, + { + "epoch": 0.6696428571428571, + "grad_norm": 0.31816604062862364, + "learning_rate": 8.976301166948119e-06, + "loss": 0.3976, + "step": 5025 + }, + { + "epoch": 0.6697761194029851, + "grad_norm": 0.32294841233296956, + "learning_rate": 8.97586944905508e-06, + "loss": 0.4278, + "step": 5026 + }, + { + "epoch": 0.669909381663113, + "grad_norm": 0.30874486828834335, + "learning_rate": 8.975437650534858e-06, + "loss": 0.4289, + "step": 5027 + }, + { + "epoch": 0.670042643923241, + "grad_norm": 0.2949202588885264, + "learning_rate": 8.975005771396214e-06, + "loss": 0.4977, + "step": 5028 + }, + { + "epoch": 0.6701759061833689, + "grad_norm": 0.2908935434113545, + "learning_rate": 8.974573811647904e-06, + "loss": 0.3863, + "step": 5029 + }, + { + "epoch": 0.6703091684434968, + "grad_norm": 0.2827135073090375, + "learning_rate": 8.974141771298688e-06, + "loss": 0.4522, + "step": 5030 + }, + { + "epoch": 0.6704424307036247, + "grad_norm": 0.29082895792886204, + "learning_rate": 8.973709650357328e-06, + "loss": 0.3957, + "step": 5031 + }, + { + "epoch": 0.6705756929637526, + "grad_norm": 0.282752914784539, + "learning_rate": 8.973277448832587e-06, + "loss": 0.3829, + "step": 5032 + }, + { + "epoch": 0.6707089552238806, + "grad_norm": 0.29481257838915903, + "learning_rate": 8.972845166733228e-06, + "loss": 0.3543, + "step": 5033 + }, + { + "epoch": 0.6708422174840085, + "grad_norm": 0.2936521914192448, + "learning_rate": 8.972412804068021e-06, + "loss": 0.3629, + "step": 5034 + }, + { + "epoch": 0.6709754797441365, + "grad_norm": 0.3048999813543963, + "learning_rate": 8.971980360845729e-06, + "loss": 0.4181, + "step": 5035 + }, + { + "epoch": 0.6711087420042644, + "grad_norm": 0.3178471137646692, + "learning_rate": 8.971547837075127e-06, + "loss": 0.4661, + "step": 5036 + }, + { + "epoch": 0.6712420042643923, + "grad_norm": 0.2931843123210355, + "learning_rate": 8.971115232764981e-06, + "loss": 0.4412, + "step": 5037 + }, + { + "epoch": 0.6713752665245203, + "grad_norm": 0.3032304230287285, + "learning_rate": 8.970682547924068e-06, + "loss": 0.3652, + "step": 5038 + }, + { + "epoch": 0.6715085287846482, + "grad_norm": 0.2945971443693623, + "learning_rate": 8.97024978256116e-06, + "loss": 0.428, + "step": 5039 + }, + { + "epoch": 0.6716417910447762, + "grad_norm": 0.28820840293110106, + "learning_rate": 8.969816936685034e-06, + "loss": 0.374, + "step": 5040 + }, + { + "epoch": 0.6717750533049041, + "grad_norm": 0.27634056664939616, + "learning_rate": 8.969384010304468e-06, + "loss": 0.3599, + "step": 5041 + }, + { + "epoch": 0.6719083155650319, + "grad_norm": 0.31149124962744695, + "learning_rate": 8.96895100342824e-06, + "loss": 0.4008, + "step": 5042 + }, + { + "epoch": 0.6720415778251599, + "grad_norm": 0.29293951328099355, + "learning_rate": 8.968517916065132e-06, + "loss": 0.3964, + "step": 5043 + }, + { + "epoch": 0.6721748400852878, + "grad_norm": 0.30435148968336645, + "learning_rate": 8.968084748223926e-06, + "loss": 0.401, + "step": 5044 + }, + { + "epoch": 0.6723081023454158, + "grad_norm": 0.2965378362040566, + "learning_rate": 8.967651499913407e-06, + "loss": 0.3792, + "step": 5045 + }, + { + "epoch": 0.6724413646055437, + "grad_norm": 0.3739795905834512, + "learning_rate": 8.967218171142362e-06, + "loss": 0.4109, + "step": 5046 + }, + { + "epoch": 0.6725746268656716, + "grad_norm": 0.2988618734257992, + "learning_rate": 8.966784761919578e-06, + "loss": 0.471, + "step": 5047 + }, + { + "epoch": 0.6727078891257996, + "grad_norm": 0.26872421060880786, + "learning_rate": 8.966351272253842e-06, + "loss": 0.3823, + "step": 5048 + }, + { + "epoch": 0.6728411513859275, + "grad_norm": 0.29659761132710666, + "learning_rate": 8.965917702153945e-06, + "loss": 0.4772, + "step": 5049 + }, + { + "epoch": 0.6729744136460555, + "grad_norm": 0.30035962191279364, + "learning_rate": 8.965484051628683e-06, + "loss": 0.4087, + "step": 5050 + }, + { + "epoch": 0.6731076759061834, + "grad_norm": 0.2820266545092343, + "learning_rate": 8.965050320686846e-06, + "loss": 0.3756, + "step": 5051 + }, + { + "epoch": 0.6732409381663113, + "grad_norm": 0.2920292352862108, + "learning_rate": 8.964616509337233e-06, + "loss": 0.3851, + "step": 5052 + }, + { + "epoch": 0.6733742004264393, + "grad_norm": 0.313145659255056, + "learning_rate": 8.96418261758864e-06, + "loss": 0.4594, + "step": 5053 + }, + { + "epoch": 0.6735074626865671, + "grad_norm": 0.2973960663661426, + "learning_rate": 8.963748645449863e-06, + "loss": 0.4421, + "step": 5054 + }, + { + "epoch": 0.6736407249466951, + "grad_norm": 0.286382636823264, + "learning_rate": 8.963314592929707e-06, + "loss": 0.4236, + "step": 5055 + }, + { + "epoch": 0.673773987206823, + "grad_norm": 0.44824552487146135, + "learning_rate": 8.962880460036974e-06, + "loss": 0.4113, + "step": 5056 + }, + { + "epoch": 0.6739072494669509, + "grad_norm": 0.3068649997811044, + "learning_rate": 8.962446246780462e-06, + "loss": 0.4468, + "step": 5057 + }, + { + "epoch": 0.6740405117270789, + "grad_norm": 0.29017386516021754, + "learning_rate": 8.962011953168986e-06, + "loss": 0.3917, + "step": 5058 + }, + { + "epoch": 0.6741737739872068, + "grad_norm": 0.2883904406451823, + "learning_rate": 8.961577579211344e-06, + "loss": 0.372, + "step": 5059 + }, + { + "epoch": 0.6743070362473348, + "grad_norm": 0.3047163706306178, + "learning_rate": 8.961143124916349e-06, + "loss": 0.4009, + "step": 5060 + }, + { + "epoch": 0.6744402985074627, + "grad_norm": 0.3102483586739483, + "learning_rate": 8.960708590292813e-06, + "loss": 0.5319, + "step": 5061 + }, + { + "epoch": 0.6745735607675906, + "grad_norm": 0.2981076603265513, + "learning_rate": 8.960273975349546e-06, + "loss": 0.3747, + "step": 5062 + }, + { + "epoch": 0.6747068230277186, + "grad_norm": 0.2993148573427276, + "learning_rate": 8.959839280095358e-06, + "loss": 0.4626, + "step": 5063 + }, + { + "epoch": 0.6748400852878464, + "grad_norm": 0.3031210074504411, + "learning_rate": 8.959404504539072e-06, + "loss": 0.4246, + "step": 5064 + }, + { + "epoch": 0.6749733475479744, + "grad_norm": 0.274423236308494, + "learning_rate": 8.958969648689497e-06, + "loss": 0.3992, + "step": 5065 + }, + { + "epoch": 0.6751066098081023, + "grad_norm": 0.29372212595248526, + "learning_rate": 8.958534712555458e-06, + "loss": 0.3481, + "step": 5066 + }, + { + "epoch": 0.6752398720682303, + "grad_norm": 0.31297985464260186, + "learning_rate": 8.95809969614577e-06, + "loss": 0.4092, + "step": 5067 + }, + { + "epoch": 0.6753731343283582, + "grad_norm": 0.29339675056460096, + "learning_rate": 8.957664599469258e-06, + "loss": 0.4246, + "step": 5068 + }, + { + "epoch": 0.6755063965884861, + "grad_norm": 0.2994986888631642, + "learning_rate": 8.957229422534744e-06, + "loss": 0.3872, + "step": 5069 + }, + { + "epoch": 0.6756396588486141, + "grad_norm": 0.3046810549754585, + "learning_rate": 8.956794165351056e-06, + "loss": 0.4096, + "step": 5070 + }, + { + "epoch": 0.675772921108742, + "grad_norm": 0.29728008012881724, + "learning_rate": 8.956358827927014e-06, + "loss": 0.4017, + "step": 5071 + }, + { + "epoch": 0.67590618336887, + "grad_norm": 0.31763899719772415, + "learning_rate": 8.955923410271451e-06, + "loss": 0.3829, + "step": 5072 + }, + { + "epoch": 0.6760394456289979, + "grad_norm": 0.2914242279060369, + "learning_rate": 8.9554879123932e-06, + "loss": 0.4571, + "step": 5073 + }, + { + "epoch": 0.6761727078891258, + "grad_norm": 0.30374984177931874, + "learning_rate": 8.955052334301086e-06, + "loss": 0.4598, + "step": 5074 + }, + { + "epoch": 0.6763059701492538, + "grad_norm": 0.27817857767202997, + "learning_rate": 8.954616676003945e-06, + "loss": 0.3274, + "step": 5075 + }, + { + "epoch": 0.6764392324093816, + "grad_norm": 0.2874482027948314, + "learning_rate": 8.954180937510611e-06, + "loss": 0.5825, + "step": 5076 + }, + { + "epoch": 0.6765724946695096, + "grad_norm": 0.3256532771183425, + "learning_rate": 8.953745118829922e-06, + "loss": 0.3785, + "step": 5077 + }, + { + "epoch": 0.6767057569296375, + "grad_norm": 0.28929739151153605, + "learning_rate": 8.953309219970717e-06, + "loss": 0.4075, + "step": 5078 + }, + { + "epoch": 0.6768390191897654, + "grad_norm": 0.3077269198525678, + "learning_rate": 8.95287324094183e-06, + "loss": 0.4285, + "step": 5079 + }, + { + "epoch": 0.6769722814498934, + "grad_norm": 0.30197710331821676, + "learning_rate": 8.952437181752107e-06, + "loss": 0.4308, + "step": 5080 + }, + { + "epoch": 0.6771055437100213, + "grad_norm": 0.291485058919932, + "learning_rate": 8.952001042410392e-06, + "loss": 0.5306, + "step": 5081 + }, + { + "epoch": 0.6772388059701493, + "grad_norm": 0.2894073588026472, + "learning_rate": 8.951564822925525e-06, + "loss": 0.3784, + "step": 5082 + }, + { + "epoch": 0.6773720682302772, + "grad_norm": 0.27116498216234264, + "learning_rate": 8.951128523306357e-06, + "loss": 0.3653, + "step": 5083 + }, + { + "epoch": 0.6775053304904051, + "grad_norm": 0.30085502994160446, + "learning_rate": 8.95069214356173e-06, + "loss": 0.4029, + "step": 5084 + }, + { + "epoch": 0.6776385927505331, + "grad_norm": 0.27238478384108733, + "learning_rate": 8.950255683700499e-06, + "loss": 0.3865, + "step": 5085 + }, + { + "epoch": 0.677771855010661, + "grad_norm": 0.30253063907321065, + "learning_rate": 8.949819143731514e-06, + "loss": 0.4208, + "step": 5086 + }, + { + "epoch": 0.677905117270789, + "grad_norm": 0.2908066500035185, + "learning_rate": 8.949382523663624e-06, + "loss": 0.3988, + "step": 5087 + }, + { + "epoch": 0.6780383795309168, + "grad_norm": 0.2833549947105277, + "learning_rate": 8.948945823505687e-06, + "loss": 0.405, + "step": 5088 + }, + { + "epoch": 0.6781716417910447, + "grad_norm": 0.28302858579117135, + "learning_rate": 8.948509043266559e-06, + "loss": 0.4124, + "step": 5089 + }, + { + "epoch": 0.6783049040511727, + "grad_norm": 0.3000409488011235, + "learning_rate": 8.948072182955093e-06, + "loss": 0.3719, + "step": 5090 + }, + { + "epoch": 0.6784381663113006, + "grad_norm": 0.2959990802561218, + "learning_rate": 8.947635242580153e-06, + "loss": 0.4384, + "step": 5091 + }, + { + "epoch": 0.6785714285714286, + "grad_norm": 0.3068831942706833, + "learning_rate": 8.947198222150597e-06, + "loss": 0.4406, + "step": 5092 + }, + { + "epoch": 0.6787046908315565, + "grad_norm": 0.3119157369033349, + "learning_rate": 8.946761121675289e-06, + "loss": 0.4152, + "step": 5093 + }, + { + "epoch": 0.6788379530916845, + "grad_norm": 0.28664142408635884, + "learning_rate": 8.946323941163093e-06, + "loss": 0.4246, + "step": 5094 + }, + { + "epoch": 0.6789712153518124, + "grad_norm": 0.29474098916049135, + "learning_rate": 8.945886680622874e-06, + "loss": 0.3321, + "step": 5095 + }, + { + "epoch": 0.6791044776119403, + "grad_norm": 0.2896111368842266, + "learning_rate": 8.9454493400635e-06, + "loss": 0.4544, + "step": 5096 + }, + { + "epoch": 0.6792377398720683, + "grad_norm": 0.2896744312162264, + "learning_rate": 8.945011919493838e-06, + "loss": 0.4562, + "step": 5097 + }, + { + "epoch": 0.6793710021321961, + "grad_norm": 0.34457672050085136, + "learning_rate": 8.94457441892276e-06, + "loss": 0.3577, + "step": 5098 + }, + { + "epoch": 0.6795042643923241, + "grad_norm": 0.2989568115205234, + "learning_rate": 8.944136838359138e-06, + "loss": 0.4589, + "step": 5099 + }, + { + "epoch": 0.679637526652452, + "grad_norm": 0.2874277168047621, + "learning_rate": 8.943699177811846e-06, + "loss": 0.4993, + "step": 5100 + }, + { + "epoch": 0.6797707889125799, + "grad_norm": 0.29929869840239565, + "learning_rate": 8.943261437289759e-06, + "loss": 0.4365, + "step": 5101 + }, + { + "epoch": 0.6799040511727079, + "grad_norm": 0.29284099801387775, + "learning_rate": 8.942823616801755e-06, + "loss": 0.436, + "step": 5102 + }, + { + "epoch": 0.6800373134328358, + "grad_norm": 0.28716406884990525, + "learning_rate": 8.94238571635671e-06, + "loss": 0.4018, + "step": 5103 + }, + { + "epoch": 0.6801705756929638, + "grad_norm": 0.2926079331852875, + "learning_rate": 8.941947735963508e-06, + "loss": 0.4467, + "step": 5104 + }, + { + "epoch": 0.6803038379530917, + "grad_norm": 0.298088111053922, + "learning_rate": 8.941509675631026e-06, + "loss": 0.3479, + "step": 5105 + }, + { + "epoch": 0.6804371002132196, + "grad_norm": 0.27938781648816924, + "learning_rate": 8.941071535368152e-06, + "loss": 0.3853, + "step": 5106 + }, + { + "epoch": 0.6805703624733476, + "grad_norm": 0.2836895787746405, + "learning_rate": 8.940633315183769e-06, + "loss": 0.3896, + "step": 5107 + }, + { + "epoch": 0.6807036247334755, + "grad_norm": 0.27613154564015513, + "learning_rate": 8.940195015086764e-06, + "loss": 0.3417, + "step": 5108 + }, + { + "epoch": 0.6808368869936035, + "grad_norm": 0.29504296450171574, + "learning_rate": 8.939756635086025e-06, + "loss": 0.4278, + "step": 5109 + }, + { + "epoch": 0.6809701492537313, + "grad_norm": 0.31594632710083187, + "learning_rate": 8.939318175190444e-06, + "loss": 0.4433, + "step": 5110 + }, + { + "epoch": 0.6811034115138592, + "grad_norm": 0.3098762172649528, + "learning_rate": 8.938879635408909e-06, + "loss": 0.5242, + "step": 5111 + }, + { + "epoch": 0.6812366737739872, + "grad_norm": 0.2928217449426616, + "learning_rate": 8.938441015750316e-06, + "loss": 0.4222, + "step": 5112 + }, + { + "epoch": 0.6813699360341151, + "grad_norm": 0.3027904389294148, + "learning_rate": 8.93800231622356e-06, + "loss": 0.4232, + "step": 5113 + }, + { + "epoch": 0.6815031982942431, + "grad_norm": 0.2922287532552515, + "learning_rate": 8.937563536837533e-06, + "loss": 0.3992, + "step": 5114 + }, + { + "epoch": 0.681636460554371, + "grad_norm": 0.2829600957148137, + "learning_rate": 8.93712467760114e-06, + "loss": 0.3873, + "step": 5115 + }, + { + "epoch": 0.6817697228144989, + "grad_norm": 0.3119399369430087, + "learning_rate": 8.936685738523276e-06, + "loss": 0.3705, + "step": 5116 + }, + { + "epoch": 0.6819029850746269, + "grad_norm": 0.30206051918676774, + "learning_rate": 8.936246719612843e-06, + "loss": 0.4566, + "step": 5117 + }, + { + "epoch": 0.6820362473347548, + "grad_norm": 0.3061397212447149, + "learning_rate": 8.935807620878746e-06, + "loss": 0.4006, + "step": 5118 + }, + { + "epoch": 0.6821695095948828, + "grad_norm": 0.30213692774005807, + "learning_rate": 8.935368442329885e-06, + "loss": 0.385, + "step": 5119 + }, + { + "epoch": 0.6823027718550106, + "grad_norm": 0.2854465052077693, + "learning_rate": 8.934929183975172e-06, + "loss": 0.3647, + "step": 5120 + }, + { + "epoch": 0.6824360341151386, + "grad_norm": 0.2929205256066236, + "learning_rate": 8.934489845823512e-06, + "loss": 0.4264, + "step": 5121 + }, + { + "epoch": 0.6825692963752665, + "grad_norm": 0.2847222935695435, + "learning_rate": 8.934050427883814e-06, + "loss": 0.3836, + "step": 5122 + }, + { + "epoch": 0.6827025586353944, + "grad_norm": 0.29845564473498976, + "learning_rate": 8.933610930164987e-06, + "loss": 0.4128, + "step": 5123 + }, + { + "epoch": 0.6828358208955224, + "grad_norm": 0.30541159562527126, + "learning_rate": 8.933171352675949e-06, + "loss": 0.423, + "step": 5124 + }, + { + "epoch": 0.6829690831556503, + "grad_norm": 0.31268484282547704, + "learning_rate": 8.93273169542561e-06, + "loss": 0.4036, + "step": 5125 + }, + { + "epoch": 0.6831023454157783, + "grad_norm": 0.2860067607159941, + "learning_rate": 8.932291958422885e-06, + "loss": 0.4234, + "step": 5126 + }, + { + "epoch": 0.6832356076759062, + "grad_norm": 0.2960299195420007, + "learning_rate": 8.931852141676696e-06, + "loss": 0.3768, + "step": 5127 + }, + { + "epoch": 0.6833688699360341, + "grad_norm": 0.26952379327297576, + "learning_rate": 8.931412245195959e-06, + "loss": 0.31, + "step": 5128 + }, + { + "epoch": 0.6835021321961621, + "grad_norm": 0.29579168599540046, + "learning_rate": 8.930972268989595e-06, + "loss": 0.3681, + "step": 5129 + }, + { + "epoch": 0.68363539445629, + "grad_norm": 0.2887046731940426, + "learning_rate": 8.930532213066528e-06, + "loss": 0.3696, + "step": 5130 + }, + { + "epoch": 0.683768656716418, + "grad_norm": 0.30812245438155816, + "learning_rate": 8.930092077435678e-06, + "loss": 0.4344, + "step": 5131 + }, + { + "epoch": 0.6839019189765458, + "grad_norm": 0.295462326365524, + "learning_rate": 8.929651862105976e-06, + "loss": 0.4463, + "step": 5132 + }, + { + "epoch": 0.6840351812366737, + "grad_norm": 0.29730893611098536, + "learning_rate": 8.929211567086345e-06, + "loss": 0.3741, + "step": 5133 + }, + { + "epoch": 0.6841684434968017, + "grad_norm": 0.30340887814142814, + "learning_rate": 8.928771192385716e-06, + "loss": 0.4371, + "step": 5134 + }, + { + "epoch": 0.6843017057569296, + "grad_norm": 0.30786608009680194, + "learning_rate": 8.928330738013018e-06, + "loss": 0.4093, + "step": 5135 + }, + { + "epoch": 0.6844349680170576, + "grad_norm": 0.27931531333074583, + "learning_rate": 8.927890203977183e-06, + "loss": 0.4078, + "step": 5136 + }, + { + "epoch": 0.6845682302771855, + "grad_norm": 0.36076974822022023, + "learning_rate": 8.927449590287147e-06, + "loss": 0.4215, + "step": 5137 + }, + { + "epoch": 0.6847014925373134, + "grad_norm": 0.2976522409018292, + "learning_rate": 8.927008896951843e-06, + "loss": 0.4161, + "step": 5138 + }, + { + "epoch": 0.6848347547974414, + "grad_norm": 0.30480994109019005, + "learning_rate": 8.926568123980208e-06, + "loss": 0.4003, + "step": 5139 + }, + { + "epoch": 0.6849680170575693, + "grad_norm": 0.28918823556265305, + "learning_rate": 8.92612727138118e-06, + "loss": 0.3738, + "step": 5140 + }, + { + "epoch": 0.6851012793176973, + "grad_norm": 0.309714153867034, + "learning_rate": 8.925686339163701e-06, + "loss": 0.441, + "step": 5141 + }, + { + "epoch": 0.6852345415778252, + "grad_norm": 0.2690558337846731, + "learning_rate": 8.925245327336713e-06, + "loss": 0.3774, + "step": 5142 + }, + { + "epoch": 0.685367803837953, + "grad_norm": 0.2913099493685389, + "learning_rate": 8.924804235909158e-06, + "loss": 0.4192, + "step": 5143 + }, + { + "epoch": 0.685501066098081, + "grad_norm": 0.3025146876436645, + "learning_rate": 8.924363064889979e-06, + "loss": 0.4357, + "step": 5144 + }, + { + "epoch": 0.6856343283582089, + "grad_norm": 0.3054296918085051, + "learning_rate": 8.923921814288126e-06, + "loss": 0.4496, + "step": 5145 + }, + { + "epoch": 0.6857675906183369, + "grad_norm": 0.3012495686777285, + "learning_rate": 8.923480484112545e-06, + "loss": 0.3728, + "step": 5146 + }, + { + "epoch": 0.6859008528784648, + "grad_norm": 0.308536508060014, + "learning_rate": 8.923039074372187e-06, + "loss": 0.4293, + "step": 5147 + }, + { + "epoch": 0.6860341151385928, + "grad_norm": 0.29899813410946763, + "learning_rate": 8.922597585076003e-06, + "loss": 0.368, + "step": 5148 + }, + { + "epoch": 0.6861673773987207, + "grad_norm": 0.2984894804549691, + "learning_rate": 8.922156016232946e-06, + "loss": 0.423, + "step": 5149 + }, + { + "epoch": 0.6863006396588486, + "grad_norm": 0.30646733257793385, + "learning_rate": 8.92171436785197e-06, + "loss": 0.4906, + "step": 5150 + }, + { + "epoch": 0.6864339019189766, + "grad_norm": 0.28109735168384153, + "learning_rate": 8.921272639942034e-06, + "loss": 0.3428, + "step": 5151 + }, + { + "epoch": 0.6865671641791045, + "grad_norm": 0.3019739176380229, + "learning_rate": 8.920830832512092e-06, + "loss": 0.4704, + "step": 5152 + }, + { + "epoch": 0.6867004264392325, + "grad_norm": 0.28548960336492185, + "learning_rate": 8.920388945571106e-06, + "loss": 0.3955, + "step": 5153 + }, + { + "epoch": 0.6868336886993603, + "grad_norm": 0.27431093866078793, + "learning_rate": 8.919946979128035e-06, + "loss": 0.3966, + "step": 5154 + }, + { + "epoch": 0.6869669509594882, + "grad_norm": 0.3170006748477586, + "learning_rate": 8.919504933191845e-06, + "loss": 0.4347, + "step": 5155 + }, + { + "epoch": 0.6871002132196162, + "grad_norm": 0.27416891184675507, + "learning_rate": 8.919062807771496e-06, + "loss": 0.4484, + "step": 5156 + }, + { + "epoch": 0.6872334754797441, + "grad_norm": 0.2949667626800131, + "learning_rate": 8.918620602875959e-06, + "loss": 0.3862, + "step": 5157 + }, + { + "epoch": 0.6873667377398721, + "grad_norm": 0.28878424831668775, + "learning_rate": 8.918178318514197e-06, + "loss": 0.4521, + "step": 5158 + }, + { + "epoch": 0.6875, + "grad_norm": 0.2958494933937597, + "learning_rate": 8.91773595469518e-06, + "loss": 0.3945, + "step": 5159 + }, + { + "epoch": 0.6876332622601279, + "grad_norm": 0.29619531506705654, + "learning_rate": 8.917293511427881e-06, + "loss": 0.4127, + "step": 5160 + }, + { + "epoch": 0.6877665245202559, + "grad_norm": 0.2917100866288228, + "learning_rate": 8.91685098872127e-06, + "loss": 0.5048, + "step": 5161 + }, + { + "epoch": 0.6878997867803838, + "grad_norm": 0.2810661438110275, + "learning_rate": 8.916408386584323e-06, + "loss": 0.3814, + "step": 5162 + }, + { + "epoch": 0.6880330490405118, + "grad_norm": 0.30800710899985645, + "learning_rate": 8.915965705026015e-06, + "loss": 0.4263, + "step": 5163 + }, + { + "epoch": 0.6881663113006397, + "grad_norm": 0.27367203615071023, + "learning_rate": 8.915522944055323e-06, + "loss": 0.356, + "step": 5164 + }, + { + "epoch": 0.6882995735607675, + "grad_norm": 0.30624238557642564, + "learning_rate": 8.915080103681224e-06, + "loss": 0.3575, + "step": 5165 + }, + { + "epoch": 0.6884328358208955, + "grad_norm": 0.3150637030020296, + "learning_rate": 8.914637183912702e-06, + "loss": 0.3728, + "step": 5166 + }, + { + "epoch": 0.6885660980810234, + "grad_norm": 0.5212806977193041, + "learning_rate": 8.914194184758735e-06, + "loss": 0.4569, + "step": 5167 + }, + { + "epoch": 0.6886993603411514, + "grad_norm": 0.31084980836973813, + "learning_rate": 8.91375110622831e-06, + "loss": 0.4236, + "step": 5168 + }, + { + "epoch": 0.6888326226012793, + "grad_norm": 0.3015246547694665, + "learning_rate": 8.91330794833041e-06, + "loss": 0.4451, + "step": 5169 + }, + { + "epoch": 0.6889658848614072, + "grad_norm": 0.30794884271727013, + "learning_rate": 8.912864711074022e-06, + "loss": 0.3962, + "step": 5170 + }, + { + "epoch": 0.6890991471215352, + "grad_norm": 0.31554843903934704, + "learning_rate": 8.912421394468138e-06, + "loss": 0.4979, + "step": 5171 + }, + { + "epoch": 0.6892324093816631, + "grad_norm": 0.30428641624758596, + "learning_rate": 8.911977998521743e-06, + "loss": 0.398, + "step": 5172 + }, + { + "epoch": 0.6893656716417911, + "grad_norm": 0.301073162147377, + "learning_rate": 8.911534523243833e-06, + "loss": 0.3682, + "step": 5173 + }, + { + "epoch": 0.689498933901919, + "grad_norm": 0.4515674306933941, + "learning_rate": 8.911090968643398e-06, + "loss": 0.4257, + "step": 5174 + }, + { + "epoch": 0.689632196162047, + "grad_norm": 0.30096538098707243, + "learning_rate": 8.910647334729434e-06, + "loss": 0.3974, + "step": 5175 + }, + { + "epoch": 0.6897654584221748, + "grad_norm": 0.2965964587387632, + "learning_rate": 8.910203621510938e-06, + "loss": 0.3688, + "step": 5176 + }, + { + "epoch": 0.6898987206823027, + "grad_norm": 0.31407604941890604, + "learning_rate": 8.909759828996907e-06, + "loss": 0.4651, + "step": 5177 + }, + { + "epoch": 0.6900319829424307, + "grad_norm": 0.3172287461038046, + "learning_rate": 8.909315957196342e-06, + "loss": 0.4707, + "step": 5178 + }, + { + "epoch": 0.6901652452025586, + "grad_norm": 0.2929512372911254, + "learning_rate": 8.908872006118245e-06, + "loss": 0.443, + "step": 5179 + }, + { + "epoch": 0.6902985074626866, + "grad_norm": 0.29311286127914254, + "learning_rate": 8.908427975771618e-06, + "loss": 0.377, + "step": 5180 + }, + { + "epoch": 0.6904317697228145, + "grad_norm": 0.28458687551952677, + "learning_rate": 8.907983866165465e-06, + "loss": 0.4006, + "step": 5181 + }, + { + "epoch": 0.6905650319829424, + "grad_norm": 0.31436370509669503, + "learning_rate": 8.907539677308792e-06, + "loss": 0.4255, + "step": 5182 + }, + { + "epoch": 0.6906982942430704, + "grad_norm": 0.2978290902147076, + "learning_rate": 8.907095409210607e-06, + "loss": 0.3839, + "step": 5183 + }, + { + "epoch": 0.6908315565031983, + "grad_norm": 0.3050301980791214, + "learning_rate": 8.90665106187992e-06, + "loss": 0.3641, + "step": 5184 + }, + { + "epoch": 0.6909648187633263, + "grad_norm": 0.29344397303564235, + "learning_rate": 8.906206635325742e-06, + "loss": 0.4414, + "step": 5185 + }, + { + "epoch": 0.6910980810234542, + "grad_norm": 0.2858793220569583, + "learning_rate": 8.905762129557086e-06, + "loss": 0.4221, + "step": 5186 + }, + { + "epoch": 0.691231343283582, + "grad_norm": 0.2924027491229947, + "learning_rate": 8.905317544582963e-06, + "loss": 0.4033, + "step": 5187 + }, + { + "epoch": 0.69136460554371, + "grad_norm": 0.29898063020819426, + "learning_rate": 8.904872880412395e-06, + "loss": 0.3896, + "step": 5188 + }, + { + "epoch": 0.6914978678038379, + "grad_norm": 0.2938450268131626, + "learning_rate": 8.904428137054394e-06, + "loss": 0.4242, + "step": 5189 + }, + { + "epoch": 0.6916311300639659, + "grad_norm": 0.2966452385541446, + "learning_rate": 8.903983314517978e-06, + "loss": 0.3842, + "step": 5190 + }, + { + "epoch": 0.6917643923240938, + "grad_norm": 0.30569949409520625, + "learning_rate": 8.903538412812172e-06, + "loss": 0.4489, + "step": 5191 + }, + { + "epoch": 0.6918976545842217, + "grad_norm": 0.31483496966178415, + "learning_rate": 8.903093431945997e-06, + "loss": 0.4232, + "step": 5192 + }, + { + "epoch": 0.6920309168443497, + "grad_norm": 0.28083834308220385, + "learning_rate": 8.902648371928476e-06, + "loss": 0.3547, + "step": 5193 + }, + { + "epoch": 0.6921641791044776, + "grad_norm": 0.29348009036856987, + "learning_rate": 8.902203232768636e-06, + "loss": 0.3756, + "step": 5194 + }, + { + "epoch": 0.6922974413646056, + "grad_norm": 0.2947404463642178, + "learning_rate": 8.901758014475502e-06, + "loss": 0.3874, + "step": 5195 + }, + { + "epoch": 0.6924307036247335, + "grad_norm": 0.3147862142403737, + "learning_rate": 8.901312717058101e-06, + "loss": 0.5209, + "step": 5196 + }, + { + "epoch": 0.6925639658848614, + "grad_norm": 0.28550927287397715, + "learning_rate": 8.900867340525469e-06, + "loss": 0.3928, + "step": 5197 + }, + { + "epoch": 0.6926972281449894, + "grad_norm": 0.29794149684911114, + "learning_rate": 8.900421884886632e-06, + "loss": 0.4188, + "step": 5198 + }, + { + "epoch": 0.6928304904051172, + "grad_norm": 0.28214499530622933, + "learning_rate": 8.899976350150627e-06, + "loss": 0.4215, + "step": 5199 + }, + { + "epoch": 0.6929637526652452, + "grad_norm": 0.29302324454163675, + "learning_rate": 8.899530736326489e-06, + "loss": 0.3806, + "step": 5200 + }, + { + "epoch": 0.6930970149253731, + "grad_norm": 0.2813254047058758, + "learning_rate": 8.899085043423252e-06, + "loss": 0.3693, + "step": 5201 + }, + { + "epoch": 0.6932302771855011, + "grad_norm": 0.3004527105871705, + "learning_rate": 8.898639271449958e-06, + "loss": 0.3619, + "step": 5202 + }, + { + "epoch": 0.693363539445629, + "grad_norm": 0.28939445546038467, + "learning_rate": 8.898193420415643e-06, + "loss": 0.4715, + "step": 5203 + }, + { + "epoch": 0.6934968017057569, + "grad_norm": 0.30188237049654965, + "learning_rate": 8.897747490329351e-06, + "loss": 0.3419, + "step": 5204 + }, + { + "epoch": 0.6936300639658849, + "grad_norm": 0.30175715130324454, + "learning_rate": 8.897301481200125e-06, + "loss": 0.4574, + "step": 5205 + }, + { + "epoch": 0.6937633262260128, + "grad_norm": 0.3008281893178958, + "learning_rate": 8.896855393037007e-06, + "loss": 0.4014, + "step": 5206 + }, + { + "epoch": 0.6938965884861408, + "grad_norm": 0.3061551576029868, + "learning_rate": 8.896409225849048e-06, + "loss": 0.5933, + "step": 5207 + }, + { + "epoch": 0.6940298507462687, + "grad_norm": 0.2939809524466369, + "learning_rate": 8.895962979645291e-06, + "loss": 0.4104, + "step": 5208 + }, + { + "epoch": 0.6941631130063965, + "grad_norm": 0.3126752675176107, + "learning_rate": 8.895516654434787e-06, + "loss": 0.421, + "step": 5209 + }, + { + "epoch": 0.6942963752665245, + "grad_norm": 0.2770315035379097, + "learning_rate": 8.895070250226592e-06, + "loss": 0.4196, + "step": 5210 + }, + { + "epoch": 0.6944296375266524, + "grad_norm": 0.31113016729778303, + "learning_rate": 8.894623767029751e-06, + "loss": 0.3821, + "step": 5211 + }, + { + "epoch": 0.6945628997867804, + "grad_norm": 0.29871927546091454, + "learning_rate": 8.894177204853323e-06, + "loss": 0.3813, + "step": 5212 + }, + { + "epoch": 0.6946961620469083, + "grad_norm": 0.3103312345798898, + "learning_rate": 8.893730563706362e-06, + "loss": 0.4502, + "step": 5213 + }, + { + "epoch": 0.6948294243070362, + "grad_norm": 0.2844888541404034, + "learning_rate": 8.893283843597926e-06, + "loss": 0.3942, + "step": 5214 + }, + { + "epoch": 0.6949626865671642, + "grad_norm": 0.32367422998864875, + "learning_rate": 8.892837044537076e-06, + "loss": 0.4143, + "step": 5215 + }, + { + "epoch": 0.6950959488272921, + "grad_norm": 0.32349359618447704, + "learning_rate": 8.892390166532868e-06, + "loss": 0.439, + "step": 5216 + }, + { + "epoch": 0.6952292110874201, + "grad_norm": 0.311199362819866, + "learning_rate": 8.891943209594369e-06, + "loss": 0.4155, + "step": 5217 + }, + { + "epoch": 0.695362473347548, + "grad_norm": 0.2955371731714667, + "learning_rate": 8.89149617373064e-06, + "loss": 0.3628, + "step": 5218 + }, + { + "epoch": 0.6954957356076759, + "grad_norm": 0.3367726559354223, + "learning_rate": 8.89104905895075e-06, + "loss": 0.4847, + "step": 5219 + }, + { + "epoch": 0.6956289978678039, + "grad_norm": 0.30944266449953006, + "learning_rate": 8.890601865263761e-06, + "loss": 0.342, + "step": 5220 + }, + { + "epoch": 0.6957622601279317, + "grad_norm": 0.28761601672599885, + "learning_rate": 8.890154592678746e-06, + "loss": 0.4013, + "step": 5221 + }, + { + "epoch": 0.6958955223880597, + "grad_norm": 0.31303285073382703, + "learning_rate": 8.889707241204773e-06, + "loss": 0.4381, + "step": 5222 + }, + { + "epoch": 0.6960287846481876, + "grad_norm": 0.30013672814128, + "learning_rate": 8.889259810850916e-06, + "loss": 0.4444, + "step": 5223 + }, + { + "epoch": 0.6961620469083155, + "grad_norm": 0.29745964591189805, + "learning_rate": 8.888812301626247e-06, + "loss": 0.3798, + "step": 5224 + }, + { + "epoch": 0.6962953091684435, + "grad_norm": 0.3049122747457529, + "learning_rate": 8.88836471353984e-06, + "loss": 0.5039, + "step": 5225 + }, + { + "epoch": 0.6964285714285714, + "grad_norm": 0.2964114239015825, + "learning_rate": 8.887917046600773e-06, + "loss": 0.3982, + "step": 5226 + }, + { + "epoch": 0.6965618336886994, + "grad_norm": 0.30102118156126595, + "learning_rate": 8.887469300818123e-06, + "loss": 0.3853, + "step": 5227 + }, + { + "epoch": 0.6966950959488273, + "grad_norm": 0.3053781760308365, + "learning_rate": 8.887021476200973e-06, + "loss": 0.4001, + "step": 5228 + }, + { + "epoch": 0.6968283582089553, + "grad_norm": 0.29263897766615854, + "learning_rate": 8.886573572758404e-06, + "loss": 0.4957, + "step": 5229 + }, + { + "epoch": 0.6969616204690832, + "grad_norm": 0.29835510465388315, + "learning_rate": 8.886125590499495e-06, + "loss": 0.4169, + "step": 5230 + }, + { + "epoch": 0.697094882729211, + "grad_norm": 0.2929911710026108, + "learning_rate": 8.885677529433335e-06, + "loss": 0.4817, + "step": 5231 + }, + { + "epoch": 0.697228144989339, + "grad_norm": 0.28083361475548174, + "learning_rate": 8.885229389569008e-06, + "loss": 0.3605, + "step": 5232 + }, + { + "epoch": 0.6973614072494669, + "grad_norm": 0.27226989947662683, + "learning_rate": 8.884781170915602e-06, + "loss": 0.4106, + "step": 5233 + }, + { + "epoch": 0.6974946695095949, + "grad_norm": 0.2876874291396565, + "learning_rate": 8.884332873482208e-06, + "loss": 0.3421, + "step": 5234 + }, + { + "epoch": 0.6976279317697228, + "grad_norm": 0.33991996623773807, + "learning_rate": 8.883884497277916e-06, + "loss": 0.5711, + "step": 5235 + }, + { + "epoch": 0.6977611940298507, + "grad_norm": 0.30596449906783724, + "learning_rate": 8.883436042311819e-06, + "loss": 0.4243, + "step": 5236 + }, + { + "epoch": 0.6978944562899787, + "grad_norm": 0.28964167949020897, + "learning_rate": 8.88298750859301e-06, + "loss": 0.3513, + "step": 5237 + }, + { + "epoch": 0.6980277185501066, + "grad_norm": 0.28288406558109536, + "learning_rate": 8.882538896130588e-06, + "loss": 0.4068, + "step": 5238 + }, + { + "epoch": 0.6981609808102346, + "grad_norm": 0.30784584078840604, + "learning_rate": 8.882090204933647e-06, + "loss": 0.4343, + "step": 5239 + }, + { + "epoch": 0.6982942430703625, + "grad_norm": 0.3102063428122273, + "learning_rate": 8.881641435011287e-06, + "loss": 0.4633, + "step": 5240 + }, + { + "epoch": 0.6984275053304904, + "grad_norm": 0.28777473032077466, + "learning_rate": 8.88119258637261e-06, + "loss": 0.3274, + "step": 5241 + }, + { + "epoch": 0.6985607675906184, + "grad_norm": 0.2907788363920398, + "learning_rate": 8.880743659026718e-06, + "loss": 0.3703, + "step": 5242 + }, + { + "epoch": 0.6986940298507462, + "grad_norm": 0.31152384732229116, + "learning_rate": 8.880294652982712e-06, + "loss": 0.4487, + "step": 5243 + }, + { + "epoch": 0.6988272921108742, + "grad_norm": 0.28406089871704976, + "learning_rate": 8.879845568249704e-06, + "loss": 0.4714, + "step": 5244 + }, + { + "epoch": 0.6989605543710021, + "grad_norm": 0.2922029915901856, + "learning_rate": 8.879396404836792e-06, + "loss": 0.3908, + "step": 5245 + }, + { + "epoch": 0.69909381663113, + "grad_norm": 0.3001144901777051, + "learning_rate": 8.878947162753094e-06, + "loss": 0.4025, + "step": 5246 + }, + { + "epoch": 0.699227078891258, + "grad_norm": 0.28866634507494715, + "learning_rate": 8.878497842007712e-06, + "loss": 0.418, + "step": 5247 + }, + { + "epoch": 0.6993603411513859, + "grad_norm": 0.2860840014945005, + "learning_rate": 8.878048442609762e-06, + "loss": 0.4193, + "step": 5248 + }, + { + "epoch": 0.6994936034115139, + "grad_norm": 0.2950116822464853, + "learning_rate": 8.87759896456836e-06, + "loss": 0.4237, + "step": 5249 + }, + { + "epoch": 0.6996268656716418, + "grad_norm": 0.29236752576826924, + "learning_rate": 8.877149407892613e-06, + "loss": 0.4154, + "step": 5250 + }, + { + "epoch": 0.6997601279317697, + "grad_norm": 0.2935256439148458, + "learning_rate": 8.876699772591646e-06, + "loss": 0.4324, + "step": 5251 + }, + { + "epoch": 0.6998933901918977, + "grad_norm": 0.3076047987011852, + "learning_rate": 8.876250058674574e-06, + "loss": 0.3506, + "step": 5252 + }, + { + "epoch": 0.7000266524520256, + "grad_norm": 0.29228395009519265, + "learning_rate": 8.875800266150516e-06, + "loss": 0.4107, + "step": 5253 + }, + { + "epoch": 0.7001599147121536, + "grad_norm": 0.29025756657362256, + "learning_rate": 8.875350395028592e-06, + "loss": 0.4112, + "step": 5254 + }, + { + "epoch": 0.7002931769722814, + "grad_norm": 0.2922432343948555, + "learning_rate": 8.87490044531793e-06, + "loss": 0.4571, + "step": 5255 + }, + { + "epoch": 0.7004264392324094, + "grad_norm": 0.29016458843480386, + "learning_rate": 8.87445041702765e-06, + "loss": 0.4502, + "step": 5256 + }, + { + "epoch": 0.7005597014925373, + "grad_norm": 0.29435665422310986, + "learning_rate": 8.87400031016688e-06, + "loss": 0.4675, + "step": 5257 + }, + { + "epoch": 0.7006929637526652, + "grad_norm": 0.29836289405194544, + "learning_rate": 8.873550124744747e-06, + "loss": 0.4634, + "step": 5258 + }, + { + "epoch": 0.7008262260127932, + "grad_norm": 0.2894509601819786, + "learning_rate": 8.873099860770382e-06, + "loss": 0.4547, + "step": 5259 + }, + { + "epoch": 0.7009594882729211, + "grad_norm": 0.29648294566522454, + "learning_rate": 8.872649518252915e-06, + "loss": 0.4079, + "step": 5260 + }, + { + "epoch": 0.7010927505330491, + "grad_norm": 0.2993695438086002, + "learning_rate": 8.872199097201478e-06, + "loss": 0.4006, + "step": 5261 + }, + { + "epoch": 0.701226012793177, + "grad_norm": 0.29723560305090624, + "learning_rate": 8.871748597625205e-06, + "loss": 0.4154, + "step": 5262 + }, + { + "epoch": 0.7013592750533049, + "grad_norm": 0.28703806176636554, + "learning_rate": 8.871298019533234e-06, + "loss": 0.4572, + "step": 5263 + }, + { + "epoch": 0.7014925373134329, + "grad_norm": 0.30876631572652713, + "learning_rate": 8.870847362934699e-06, + "loss": 0.4332, + "step": 5264 + }, + { + "epoch": 0.7016257995735607, + "grad_norm": 0.2949760037795116, + "learning_rate": 8.870396627838742e-06, + "loss": 0.3897, + "step": 5265 + }, + { + "epoch": 0.7017590618336887, + "grad_norm": 0.2873280566274309, + "learning_rate": 8.869945814254501e-06, + "loss": 0.4552, + "step": 5266 + }, + { + "epoch": 0.7018923240938166, + "grad_norm": 0.29525980876287256, + "learning_rate": 8.86949492219112e-06, + "loss": 0.3966, + "step": 5267 + }, + { + "epoch": 0.7020255863539445, + "grad_norm": 0.30799269680434394, + "learning_rate": 8.86904395165774e-06, + "loss": 0.3914, + "step": 5268 + }, + { + "epoch": 0.7021588486140725, + "grad_norm": 0.29081737311688505, + "learning_rate": 8.868592902663511e-06, + "loss": 0.4454, + "step": 5269 + }, + { + "epoch": 0.7022921108742004, + "grad_norm": 0.3067328937296575, + "learning_rate": 8.868141775217575e-06, + "loss": 0.4046, + "step": 5270 + }, + { + "epoch": 0.7024253731343284, + "grad_norm": 0.31658873817669, + "learning_rate": 8.867690569329083e-06, + "loss": 0.3914, + "step": 5271 + }, + { + "epoch": 0.7025586353944563, + "grad_norm": 2.3441057690263385, + "learning_rate": 8.867239285007185e-06, + "loss": 0.3746, + "step": 5272 + }, + { + "epoch": 0.7026918976545842, + "grad_norm": 0.33856184243721915, + "learning_rate": 8.866787922261032e-06, + "loss": 0.5088, + "step": 5273 + }, + { + "epoch": 0.7028251599147122, + "grad_norm": 0.3135926883179743, + "learning_rate": 8.866336481099778e-06, + "loss": 0.3727, + "step": 5274 + }, + { + "epoch": 0.7029584221748401, + "grad_norm": 0.29377599684048555, + "learning_rate": 8.865884961532576e-06, + "loss": 0.3962, + "step": 5275 + }, + { + "epoch": 0.7030916844349681, + "grad_norm": 0.40401928006244714, + "learning_rate": 8.865433363568586e-06, + "loss": 0.3508, + "step": 5276 + }, + { + "epoch": 0.7032249466950959, + "grad_norm": 0.29115273333245756, + "learning_rate": 8.864981687216963e-06, + "loss": 0.3928, + "step": 5277 + }, + { + "epoch": 0.7033582089552238, + "grad_norm": 0.29035555287847997, + "learning_rate": 8.864529932486866e-06, + "loss": 0.3864, + "step": 5278 + }, + { + "epoch": 0.7034914712153518, + "grad_norm": 0.309591413851136, + "learning_rate": 8.864078099387458e-06, + "loss": 0.3457, + "step": 5279 + }, + { + "epoch": 0.7036247334754797, + "grad_norm": 0.5445434971662197, + "learning_rate": 8.863626187927902e-06, + "loss": 0.3754, + "step": 5280 + }, + { + "epoch": 0.7037579957356077, + "grad_norm": 0.29467083450822407, + "learning_rate": 8.863174198117361e-06, + "loss": 0.4302, + "step": 5281 + }, + { + "epoch": 0.7038912579957356, + "grad_norm": 0.2975631195282216, + "learning_rate": 8.862722129965004e-06, + "loss": 0.3781, + "step": 5282 + }, + { + "epoch": 0.7040245202558635, + "grad_norm": 0.2981310910091826, + "learning_rate": 8.862269983479994e-06, + "loss": 0.3655, + "step": 5283 + }, + { + "epoch": 0.7041577825159915, + "grad_norm": 0.2921298335494083, + "learning_rate": 8.861817758671502e-06, + "loss": 0.4392, + "step": 5284 + }, + { + "epoch": 0.7042910447761194, + "grad_norm": 0.3172117210752064, + "learning_rate": 8.861365455548702e-06, + "loss": 0.4645, + "step": 5285 + }, + { + "epoch": 0.7044243070362474, + "grad_norm": 0.300906237741845, + "learning_rate": 8.86091307412076e-06, + "loss": 0.4661, + "step": 5286 + }, + { + "epoch": 0.7045575692963753, + "grad_norm": 0.29245406050808526, + "learning_rate": 8.860460614396856e-06, + "loss": 0.3794, + "step": 5287 + }, + { + "epoch": 0.7046908315565032, + "grad_norm": 0.2902433539112904, + "learning_rate": 8.860008076386161e-06, + "loss": 0.3447, + "step": 5288 + }, + { + "epoch": 0.7048240938166311, + "grad_norm": 0.2827926020878739, + "learning_rate": 8.859555460097856e-06, + "loss": 0.505, + "step": 5289 + }, + { + "epoch": 0.704957356076759, + "grad_norm": 0.2771727308594021, + "learning_rate": 8.859102765541117e-06, + "loss": 0.3377, + "step": 5290 + }, + { + "epoch": 0.705090618336887, + "grad_norm": 0.2973398600482398, + "learning_rate": 8.858649992725124e-06, + "loss": 0.3954, + "step": 5291 + }, + { + "epoch": 0.7052238805970149, + "grad_norm": 0.2821040877551941, + "learning_rate": 8.858197141659058e-06, + "loss": 0.3633, + "step": 5292 + }, + { + "epoch": 0.7053571428571429, + "grad_norm": 0.2884857177474393, + "learning_rate": 8.857744212352105e-06, + "loss": 0.3992, + "step": 5293 + }, + { + "epoch": 0.7054904051172708, + "grad_norm": 0.7830549787074723, + "learning_rate": 8.857291204813452e-06, + "loss": 0.4797, + "step": 5294 + }, + { + "epoch": 0.7056236673773987, + "grad_norm": 0.3233253479825919, + "learning_rate": 8.85683811905228e-06, + "loss": 0.4522, + "step": 5295 + }, + { + "epoch": 0.7057569296375267, + "grad_norm": 0.494468948583227, + "learning_rate": 8.856384955077782e-06, + "loss": 0.3639, + "step": 5296 + }, + { + "epoch": 0.7058901918976546, + "grad_norm": 0.2886013464932244, + "learning_rate": 8.855931712899142e-06, + "loss": 0.3885, + "step": 5297 + }, + { + "epoch": 0.7060234541577826, + "grad_norm": 0.28406834104848677, + "learning_rate": 8.855478392525559e-06, + "loss": 0.4203, + "step": 5298 + }, + { + "epoch": 0.7061567164179104, + "grad_norm": 0.2859502017127484, + "learning_rate": 8.85502499396622e-06, + "loss": 0.4635, + "step": 5299 + }, + { + "epoch": 0.7062899786780383, + "grad_norm": 0.2890731181683728, + "learning_rate": 8.85457151723032e-06, + "loss": 0.4033, + "step": 5300 + }, + { + "epoch": 0.7064232409381663, + "grad_norm": 0.29609104880318793, + "learning_rate": 8.854117962327059e-06, + "loss": 0.4069, + "step": 5301 + }, + { + "epoch": 0.7065565031982942, + "grad_norm": 0.2880760070192578, + "learning_rate": 8.853664329265631e-06, + "loss": 0.4258, + "step": 5302 + }, + { + "epoch": 0.7066897654584222, + "grad_norm": 0.2958040357113161, + "learning_rate": 8.853210618055236e-06, + "loss": 0.4844, + "step": 5303 + }, + { + "epoch": 0.7068230277185501, + "grad_norm": 0.3293436168235177, + "learning_rate": 8.852756828705078e-06, + "loss": 0.4215, + "step": 5304 + }, + { + "epoch": 0.706956289978678, + "grad_norm": 0.30630390776522, + "learning_rate": 8.852302961224356e-06, + "loss": 0.4682, + "step": 5305 + }, + { + "epoch": 0.707089552238806, + "grad_norm": 0.2840109588141836, + "learning_rate": 8.851849015622275e-06, + "loss": 0.3324, + "step": 5306 + }, + { + "epoch": 0.7072228144989339, + "grad_norm": 0.28911825489657067, + "learning_rate": 8.85139499190804e-06, + "loss": 0.3733, + "step": 5307 + }, + { + "epoch": 0.7073560767590619, + "grad_norm": 0.31060603724289343, + "learning_rate": 8.850940890090857e-06, + "loss": 0.5137, + "step": 5308 + }, + { + "epoch": 0.7074893390191898, + "grad_norm": 0.2995660338082708, + "learning_rate": 8.850486710179939e-06, + "loss": 0.404, + "step": 5309 + }, + { + "epoch": 0.7076226012793176, + "grad_norm": 0.3026586906455877, + "learning_rate": 8.850032452184494e-06, + "loss": 0.4952, + "step": 5310 + }, + { + "epoch": 0.7077558635394456, + "grad_norm": 0.2938639459624839, + "learning_rate": 8.849578116113733e-06, + "loss": 0.4198, + "step": 5311 + }, + { + "epoch": 0.7078891257995735, + "grad_norm": 0.2829132928785348, + "learning_rate": 8.849123701976872e-06, + "loss": 0.4161, + "step": 5312 + }, + { + "epoch": 0.7080223880597015, + "grad_norm": 0.3024445240602178, + "learning_rate": 8.848669209783123e-06, + "loss": 0.4401, + "step": 5313 + }, + { + "epoch": 0.7081556503198294, + "grad_norm": 0.29614688654428706, + "learning_rate": 8.848214639541703e-06, + "loss": 0.3927, + "step": 5314 + }, + { + "epoch": 0.7082889125799574, + "grad_norm": 0.28551952926890656, + "learning_rate": 8.847759991261834e-06, + "loss": 0.381, + "step": 5315 + }, + { + "epoch": 0.7084221748400853, + "grad_norm": 0.2987503613973746, + "learning_rate": 8.847305264952732e-06, + "loss": 0.4393, + "step": 5316 + }, + { + "epoch": 0.7085554371002132, + "grad_norm": 0.29419851950608406, + "learning_rate": 8.846850460623621e-06, + "loss": 0.416, + "step": 5317 + }, + { + "epoch": 0.7086886993603412, + "grad_norm": 0.3092642482935171, + "learning_rate": 8.846395578283723e-06, + "loss": 0.4095, + "step": 5318 + }, + { + "epoch": 0.7088219616204691, + "grad_norm": 0.28618665249059455, + "learning_rate": 8.845940617942262e-06, + "loss": 0.3846, + "step": 5319 + }, + { + "epoch": 0.7089552238805971, + "grad_norm": 0.2842370597377377, + "learning_rate": 8.845485579608463e-06, + "loss": 0.388, + "step": 5320 + }, + { + "epoch": 0.709088486140725, + "grad_norm": 0.2905826326895081, + "learning_rate": 8.84503046329156e-06, + "loss": 0.4021, + "step": 5321 + }, + { + "epoch": 0.7092217484008528, + "grad_norm": 0.289337502714871, + "learning_rate": 8.844575269000774e-06, + "loss": 0.4667, + "step": 5322 + }, + { + "epoch": 0.7093550106609808, + "grad_norm": 0.2900486235590866, + "learning_rate": 8.84411999674534e-06, + "loss": 0.3793, + "step": 5323 + }, + { + "epoch": 0.7094882729211087, + "grad_norm": 0.3034275557565662, + "learning_rate": 8.843664646534492e-06, + "loss": 0.3933, + "step": 5324 + }, + { + "epoch": 0.7096215351812367, + "grad_norm": 0.2922253338604206, + "learning_rate": 8.843209218377462e-06, + "loss": 0.439, + "step": 5325 + }, + { + "epoch": 0.7097547974413646, + "grad_norm": 0.2975957068085643, + "learning_rate": 8.842753712283484e-06, + "loss": 0.3579, + "step": 5326 + }, + { + "epoch": 0.7098880597014925, + "grad_norm": 0.2975011136744589, + "learning_rate": 8.842298128261801e-06, + "loss": 0.5093, + "step": 5327 + }, + { + "epoch": 0.7100213219616205, + "grad_norm": 0.2907198585731135, + "learning_rate": 8.841842466321647e-06, + "loss": 0.4024, + "step": 5328 + }, + { + "epoch": 0.7101545842217484, + "grad_norm": 0.29753700780653036, + "learning_rate": 8.841386726472262e-06, + "loss": 0.3783, + "step": 5329 + }, + { + "epoch": 0.7102878464818764, + "grad_norm": 0.3026325035813526, + "learning_rate": 8.840930908722893e-06, + "loss": 0.4305, + "step": 5330 + }, + { + "epoch": 0.7104211087420043, + "grad_norm": 0.2987958838317973, + "learning_rate": 8.840475013082777e-06, + "loss": 0.4887, + "step": 5331 + }, + { + "epoch": 0.7105543710021321, + "grad_norm": 0.3124125039312853, + "learning_rate": 8.840019039561165e-06, + "loss": 0.4113, + "step": 5332 + }, + { + "epoch": 0.7106876332622601, + "grad_norm": 0.3065089226156107, + "learning_rate": 8.8395629881673e-06, + "loss": 0.4362, + "step": 5333 + }, + { + "epoch": 0.710820895522388, + "grad_norm": 0.2998283670746233, + "learning_rate": 8.83910685891043e-06, + "loss": 0.4298, + "step": 5334 + }, + { + "epoch": 0.710954157782516, + "grad_norm": 0.30493475354477917, + "learning_rate": 8.838650651799809e-06, + "loss": 0.3994, + "step": 5335 + }, + { + "epoch": 0.7110874200426439, + "grad_norm": 0.2922752437377031, + "learning_rate": 8.838194366844685e-06, + "loss": 0.4566, + "step": 5336 + }, + { + "epoch": 0.7112206823027718, + "grad_norm": 0.29955961564376926, + "learning_rate": 8.837738004054312e-06, + "loss": 0.4413, + "step": 5337 + }, + { + "epoch": 0.7113539445628998, + "grad_norm": 0.2797462264057065, + "learning_rate": 8.837281563437945e-06, + "loss": 0.3977, + "step": 5338 + }, + { + "epoch": 0.7114872068230277, + "grad_norm": 0.3009404968950196, + "learning_rate": 8.836825045004839e-06, + "loss": 0.4161, + "step": 5339 + }, + { + "epoch": 0.7116204690831557, + "grad_norm": 0.2897909532953327, + "learning_rate": 8.836368448764254e-06, + "loss": 0.4261, + "step": 5340 + }, + { + "epoch": 0.7117537313432836, + "grad_norm": 0.29773264973275243, + "learning_rate": 8.835911774725447e-06, + "loss": 0.4179, + "step": 5341 + }, + { + "epoch": 0.7118869936034116, + "grad_norm": 0.31195031884684166, + "learning_rate": 8.835455022897681e-06, + "loss": 0.4718, + "step": 5342 + }, + { + "epoch": 0.7120202558635395, + "grad_norm": 0.29192112989319574, + "learning_rate": 8.834998193290217e-06, + "loss": 0.4958, + "step": 5343 + }, + { + "epoch": 0.7121535181236673, + "grad_norm": 0.29582002485662373, + "learning_rate": 8.834541285912318e-06, + "loss": 0.3713, + "step": 5344 + }, + { + "epoch": 0.7122867803837953, + "grad_norm": 0.29563381758941487, + "learning_rate": 8.834084300773253e-06, + "loss": 0.3571, + "step": 5345 + }, + { + "epoch": 0.7124200426439232, + "grad_norm": 0.2912255908580053, + "learning_rate": 8.833627237882288e-06, + "loss": 0.3637, + "step": 5346 + }, + { + "epoch": 0.7125533049040512, + "grad_norm": 0.28757738696221885, + "learning_rate": 8.83317009724869e-06, + "loss": 0.3642, + "step": 5347 + }, + { + "epoch": 0.7126865671641791, + "grad_norm": 0.3127270066842902, + "learning_rate": 8.83271287888173e-06, + "loss": 0.4553, + "step": 5348 + }, + { + "epoch": 0.712819829424307, + "grad_norm": 0.31049894890051044, + "learning_rate": 8.832255582790683e-06, + "loss": 0.4263, + "step": 5349 + }, + { + "epoch": 0.712953091684435, + "grad_norm": 1.081616629361141, + "learning_rate": 8.831798208984819e-06, + "loss": 0.4598, + "step": 5350 + }, + { + "epoch": 0.7130863539445629, + "grad_norm": 0.29952772439098085, + "learning_rate": 8.831340757473415e-06, + "loss": 0.3855, + "step": 5351 + }, + { + "epoch": 0.7132196162046909, + "grad_norm": 0.2982305740664533, + "learning_rate": 8.830883228265749e-06, + "loss": 0.4578, + "step": 5352 + }, + { + "epoch": 0.7133528784648188, + "grad_norm": 0.2983268908938647, + "learning_rate": 8.830425621371094e-06, + "loss": 0.3845, + "step": 5353 + }, + { + "epoch": 0.7134861407249466, + "grad_norm": 0.29013491007052455, + "learning_rate": 8.829967936798736e-06, + "loss": 0.3914, + "step": 5354 + }, + { + "epoch": 0.7136194029850746, + "grad_norm": 0.2959185077718259, + "learning_rate": 8.829510174557954e-06, + "loss": 0.4218, + "step": 5355 + }, + { + "epoch": 0.7137526652452025, + "grad_norm": 0.2888223628588334, + "learning_rate": 8.82905233465803e-06, + "loss": 0.3277, + "step": 5356 + }, + { + "epoch": 0.7138859275053305, + "grad_norm": 0.3202904093564012, + "learning_rate": 8.82859441710825e-06, + "loss": 0.4609, + "step": 5357 + }, + { + "epoch": 0.7140191897654584, + "grad_norm": 0.3084298941644939, + "learning_rate": 8.828136421917898e-06, + "loss": 0.3747, + "step": 5358 + }, + { + "epoch": 0.7141524520255863, + "grad_norm": 0.2850436750276943, + "learning_rate": 8.827678349096264e-06, + "loss": 0.4094, + "step": 5359 + }, + { + "epoch": 0.7142857142857143, + "grad_norm": 0.29839973924990904, + "learning_rate": 8.827220198652639e-06, + "loss": 0.4522, + "step": 5360 + }, + { + "epoch": 0.7144189765458422, + "grad_norm": 0.3053612155403706, + "learning_rate": 8.82676197059631e-06, + "loss": 0.3745, + "step": 5361 + }, + { + "epoch": 0.7145522388059702, + "grad_norm": 0.28260650481167104, + "learning_rate": 8.826303664936571e-06, + "loss": 0.4423, + "step": 5362 + }, + { + "epoch": 0.7146855010660981, + "grad_norm": 0.2952243946881756, + "learning_rate": 8.825845281682715e-06, + "loss": 0.4117, + "step": 5363 + }, + { + "epoch": 0.714818763326226, + "grad_norm": 0.3048044560758731, + "learning_rate": 8.825386820844039e-06, + "loss": 0.3859, + "step": 5364 + }, + { + "epoch": 0.714952025586354, + "grad_norm": 0.5266401115412951, + "learning_rate": 8.82492828242984e-06, + "loss": 0.4253, + "step": 5365 + }, + { + "epoch": 0.7150852878464818, + "grad_norm": 0.2937414509599131, + "learning_rate": 8.824469666449418e-06, + "loss": 0.4353, + "step": 5366 + }, + { + "epoch": 0.7152185501066098, + "grad_norm": 0.3130234599466819, + "learning_rate": 8.824010972912072e-06, + "loss": 0.3813, + "step": 5367 + }, + { + "epoch": 0.7153518123667377, + "grad_norm": 0.2981041984993521, + "learning_rate": 8.823552201827104e-06, + "loss": 0.4745, + "step": 5368 + }, + { + "epoch": 0.7154850746268657, + "grad_norm": 0.3045054089789046, + "learning_rate": 8.823093353203816e-06, + "loss": 0.4142, + "step": 5369 + }, + { + "epoch": 0.7156183368869936, + "grad_norm": 0.2868745401800479, + "learning_rate": 8.822634427051515e-06, + "loss": 0.4245, + "step": 5370 + }, + { + "epoch": 0.7157515991471215, + "grad_norm": 0.30802934732774545, + "learning_rate": 8.822175423379507e-06, + "loss": 0.4764, + "step": 5371 + }, + { + "epoch": 0.7158848614072495, + "grad_norm": 0.31074035310653897, + "learning_rate": 8.8217163421971e-06, + "loss": 0.4099, + "step": 5372 + }, + { + "epoch": 0.7160181236673774, + "grad_norm": 0.29725329626855446, + "learning_rate": 8.821257183513605e-06, + "loss": 0.3993, + "step": 5373 + }, + { + "epoch": 0.7161513859275054, + "grad_norm": 0.30115690072820267, + "learning_rate": 8.82079794733833e-06, + "loss": 0.3646, + "step": 5374 + }, + { + "epoch": 0.7162846481876333, + "grad_norm": 0.3052603328332479, + "learning_rate": 8.820338633680594e-06, + "loss": 0.3874, + "step": 5375 + }, + { + "epoch": 0.7164179104477612, + "grad_norm": 0.3364319042676492, + "learning_rate": 8.819879242549705e-06, + "loss": 0.3469, + "step": 5376 + }, + { + "epoch": 0.7165511727078892, + "grad_norm": 0.29570717404721775, + "learning_rate": 8.819419773954982e-06, + "loss": 0.3801, + "step": 5377 + }, + { + "epoch": 0.716684434968017, + "grad_norm": 0.3273716291808322, + "learning_rate": 8.818960227905745e-06, + "loss": 0.3556, + "step": 5378 + }, + { + "epoch": 0.716817697228145, + "grad_norm": 0.2979443926198818, + "learning_rate": 8.818500604411307e-06, + "loss": 0.3833, + "step": 5379 + }, + { + "epoch": 0.7169509594882729, + "grad_norm": 0.3023642908958993, + "learning_rate": 8.818040903480995e-06, + "loss": 0.3938, + "step": 5380 + }, + { + "epoch": 0.7170842217484008, + "grad_norm": 0.30277100389307765, + "learning_rate": 8.817581125124129e-06, + "loss": 0.3364, + "step": 5381 + }, + { + "epoch": 0.7172174840085288, + "grad_norm": 0.285506136446785, + "learning_rate": 8.817121269350031e-06, + "loss": 0.3984, + "step": 5382 + }, + { + "epoch": 0.7173507462686567, + "grad_norm": 0.3124314003373563, + "learning_rate": 8.816661336168027e-06, + "loss": 0.473, + "step": 5383 + }, + { + "epoch": 0.7174840085287847, + "grad_norm": 0.3187807208961935, + "learning_rate": 8.816201325587449e-06, + "loss": 0.4307, + "step": 5384 + }, + { + "epoch": 0.7176172707889126, + "grad_norm": 0.3050038926927997, + "learning_rate": 8.815741237617617e-06, + "loss": 0.3927, + "step": 5385 + }, + { + "epoch": 0.7177505330490405, + "grad_norm": 0.3052104026589066, + "learning_rate": 8.81528107226787e-06, + "loss": 0.5292, + "step": 5386 + }, + { + "epoch": 0.7178837953091685, + "grad_norm": 0.33304002319437703, + "learning_rate": 8.814820829547533e-06, + "loss": 0.4946, + "step": 5387 + }, + { + "epoch": 0.7180170575692963, + "grad_norm": 0.29327406400406414, + "learning_rate": 8.814360509465944e-06, + "loss": 0.4045, + "step": 5388 + }, + { + "epoch": 0.7181503198294243, + "grad_norm": 0.3288683420809859, + "learning_rate": 8.813900112032434e-06, + "loss": 0.4584, + "step": 5389 + }, + { + "epoch": 0.7182835820895522, + "grad_norm": 0.30528923893079485, + "learning_rate": 8.813439637256343e-06, + "loss": 0.36, + "step": 5390 + }, + { + "epoch": 0.7184168443496801, + "grad_norm": 0.312997321600083, + "learning_rate": 8.812979085147007e-06, + "loss": 0.3877, + "step": 5391 + }, + { + "epoch": 0.7185501066098081, + "grad_norm": 0.31796550395385637, + "learning_rate": 8.812518455713766e-06, + "loss": 0.4303, + "step": 5392 + }, + { + "epoch": 0.718683368869936, + "grad_norm": 0.2846232727931987, + "learning_rate": 8.81205774896596e-06, + "loss": 0.3493, + "step": 5393 + }, + { + "epoch": 0.718816631130064, + "grad_norm": 0.2932278010883423, + "learning_rate": 8.811596964912936e-06, + "loss": 0.3665, + "step": 5394 + }, + { + "epoch": 0.7189498933901919, + "grad_norm": 0.30685357340648334, + "learning_rate": 8.811136103564033e-06, + "loss": 0.3687, + "step": 5395 + }, + { + "epoch": 0.7190831556503199, + "grad_norm": 0.31840135424319244, + "learning_rate": 8.810675164928599e-06, + "loss": 0.419, + "step": 5396 + }, + { + "epoch": 0.7192164179104478, + "grad_norm": 0.3160760142334374, + "learning_rate": 8.810214149015981e-06, + "loss": 0.4878, + "step": 5397 + }, + { + "epoch": 0.7193496801705757, + "grad_norm": 0.30857431412283864, + "learning_rate": 8.80975305583553e-06, + "loss": 0.4169, + "step": 5398 + }, + { + "epoch": 0.7194829424307037, + "grad_norm": 0.2963550697415604, + "learning_rate": 8.809291885396595e-06, + "loss": 0.4144, + "step": 5399 + }, + { + "epoch": 0.7196162046908315, + "grad_norm": 0.29522548564444706, + "learning_rate": 8.808830637708527e-06, + "loss": 0.4476, + "step": 5400 + }, + { + "epoch": 0.7197494669509595, + "grad_norm": 0.30387133439037706, + "learning_rate": 8.808369312780682e-06, + "loss": 0.4021, + "step": 5401 + }, + { + "epoch": 0.7198827292110874, + "grad_norm": 0.3788579381021055, + "learning_rate": 8.807907910622414e-06, + "loss": 0.4295, + "step": 5402 + }, + { + "epoch": 0.7200159914712153, + "grad_norm": 0.2971391934205738, + "learning_rate": 8.80744643124308e-06, + "loss": 0.409, + "step": 5403 + }, + { + "epoch": 0.7201492537313433, + "grad_norm": 0.2945509451455383, + "learning_rate": 8.806984874652039e-06, + "loss": 0.4076, + "step": 5404 + }, + { + "epoch": 0.7202825159914712, + "grad_norm": 0.29599292991087367, + "learning_rate": 8.806523240858649e-06, + "loss": 0.4079, + "step": 5405 + }, + { + "epoch": 0.7204157782515992, + "grad_norm": 0.28050058213653045, + "learning_rate": 8.806061529872274e-06, + "loss": 0.3594, + "step": 5406 + }, + { + "epoch": 0.7205490405117271, + "grad_norm": 0.30892754960903224, + "learning_rate": 8.805599741702276e-06, + "loss": 0.513, + "step": 5407 + }, + { + "epoch": 0.720682302771855, + "grad_norm": 0.3076912123861805, + "learning_rate": 8.805137876358018e-06, + "loss": 0.4012, + "step": 5408 + }, + { + "epoch": 0.720815565031983, + "grad_norm": 0.3478608409888788, + "learning_rate": 8.80467593384887e-06, + "loss": 0.4676, + "step": 5409 + }, + { + "epoch": 0.7209488272921108, + "grad_norm": 0.29594246596759294, + "learning_rate": 8.804213914184196e-06, + "loss": 0.3993, + "step": 5410 + }, + { + "epoch": 0.7210820895522388, + "grad_norm": 0.29118701969886945, + "learning_rate": 8.80375181737337e-06, + "loss": 0.4437, + "step": 5411 + }, + { + "epoch": 0.7212153518123667, + "grad_norm": 0.28138161050361893, + "learning_rate": 8.803289643425757e-06, + "loss": 0.3501, + "step": 5412 + }, + { + "epoch": 0.7213486140724946, + "grad_norm": 0.290833905525822, + "learning_rate": 8.802827392350734e-06, + "loss": 0.4392, + "step": 5413 + }, + { + "epoch": 0.7214818763326226, + "grad_norm": 0.297609889913964, + "learning_rate": 8.802365064157672e-06, + "loss": 0.4858, + "step": 5414 + }, + { + "epoch": 0.7216151385927505, + "grad_norm": 0.2966297823270785, + "learning_rate": 8.80190265885595e-06, + "loss": 0.3326, + "step": 5415 + }, + { + "epoch": 0.7217484008528785, + "grad_norm": 0.29452848207944, + "learning_rate": 8.801440176454943e-06, + "loss": 0.3899, + "step": 5416 + }, + { + "epoch": 0.7218816631130064, + "grad_norm": 0.2810860581331998, + "learning_rate": 8.800977616964028e-06, + "loss": 0.3716, + "step": 5417 + }, + { + "epoch": 0.7220149253731343, + "grad_norm": 0.30870847974723886, + "learning_rate": 8.80051498039259e-06, + "loss": 0.4282, + "step": 5418 + }, + { + "epoch": 0.7221481876332623, + "grad_norm": 0.2937575363979316, + "learning_rate": 8.800052266750007e-06, + "loss": 0.4287, + "step": 5419 + }, + { + "epoch": 0.7222814498933902, + "grad_norm": 0.2827328886143848, + "learning_rate": 8.799589476045663e-06, + "loss": 0.4682, + "step": 5420 + }, + { + "epoch": 0.7224147121535182, + "grad_norm": 0.3148207939466167, + "learning_rate": 8.799126608288945e-06, + "loss": 0.4415, + "step": 5421 + }, + { + "epoch": 0.722547974413646, + "grad_norm": 0.2875369759504889, + "learning_rate": 8.798663663489237e-06, + "loss": 0.3715, + "step": 5422 + }, + { + "epoch": 0.722681236673774, + "grad_norm": 0.3026119271028546, + "learning_rate": 8.79820064165593e-06, + "loss": 0.437, + "step": 5423 + }, + { + "epoch": 0.7228144989339019, + "grad_norm": 0.3129630635639386, + "learning_rate": 8.79773754279841e-06, + "loss": 0.4038, + "step": 5424 + }, + { + "epoch": 0.7229477611940298, + "grad_norm": 0.30606970748404905, + "learning_rate": 8.797274366926072e-06, + "loss": 0.4222, + "step": 5425 + }, + { + "epoch": 0.7230810234541578, + "grad_norm": 0.3018515289061379, + "learning_rate": 8.796811114048308e-06, + "loss": 0.4637, + "step": 5426 + }, + { + "epoch": 0.7232142857142857, + "grad_norm": 0.285027387543353, + "learning_rate": 8.796347784174508e-06, + "loss": 0.4723, + "step": 5427 + }, + { + "epoch": 0.7233475479744137, + "grad_norm": 0.31754909608450915, + "learning_rate": 8.795884377314073e-06, + "loss": 0.4755, + "step": 5428 + }, + { + "epoch": 0.7234808102345416, + "grad_norm": 0.2970931775550493, + "learning_rate": 8.7954208934764e-06, + "loss": 0.3976, + "step": 5429 + }, + { + "epoch": 0.7236140724946695, + "grad_norm": 0.27909804126272814, + "learning_rate": 8.794957332670886e-06, + "loss": 0.4169, + "step": 5430 + }, + { + "epoch": 0.7237473347547975, + "grad_norm": 0.3082461855376357, + "learning_rate": 8.794493694906932e-06, + "loss": 0.3979, + "step": 5431 + }, + { + "epoch": 0.7238805970149254, + "grad_norm": 0.3258590024309925, + "learning_rate": 8.794029980193942e-06, + "loss": 0.444, + "step": 5432 + }, + { + "epoch": 0.7240138592750534, + "grad_norm": 0.2963069326517378, + "learning_rate": 8.793566188541316e-06, + "loss": 0.4264, + "step": 5433 + }, + { + "epoch": 0.7241471215351812, + "grad_norm": 0.31101416366274615, + "learning_rate": 8.793102319958464e-06, + "loss": 0.427, + "step": 5434 + }, + { + "epoch": 0.7242803837953091, + "grad_norm": 0.2979383593365887, + "learning_rate": 8.792638374454789e-06, + "loss": 0.3962, + "step": 5435 + }, + { + "epoch": 0.7244136460554371, + "grad_norm": 0.28473151534040075, + "learning_rate": 8.792174352039703e-06, + "loss": 0.4258, + "step": 5436 + }, + { + "epoch": 0.724546908315565, + "grad_norm": 0.31050572789858333, + "learning_rate": 8.791710252722612e-06, + "loss": 0.3854, + "step": 5437 + }, + { + "epoch": 0.724680170575693, + "grad_norm": 0.301690321829593, + "learning_rate": 8.791246076512929e-06, + "loss": 0.4265, + "step": 5438 + }, + { + "epoch": 0.7248134328358209, + "grad_norm": 0.29192015757048595, + "learning_rate": 8.79078182342007e-06, + "loss": 0.3733, + "step": 5439 + }, + { + "epoch": 0.7249466950959488, + "grad_norm": 0.3001908644883471, + "learning_rate": 8.790317493453446e-06, + "loss": 0.49, + "step": 5440 + }, + { + "epoch": 0.7250799573560768, + "grad_norm": 0.2862725483805938, + "learning_rate": 8.789853086622473e-06, + "loss": 0.4426, + "step": 5441 + }, + { + "epoch": 0.7252132196162047, + "grad_norm": 0.2967939169859203, + "learning_rate": 8.789388602936573e-06, + "loss": 0.476, + "step": 5442 + }, + { + "epoch": 0.7253464818763327, + "grad_norm": 0.3168974122693253, + "learning_rate": 8.78892404240516e-06, + "loss": 0.5101, + "step": 5443 + }, + { + "epoch": 0.7254797441364605, + "grad_norm": 0.28498890404883137, + "learning_rate": 8.788459405037659e-06, + "loss": 0.3733, + "step": 5444 + }, + { + "epoch": 0.7256130063965884, + "grad_norm": 0.3178398610071369, + "learning_rate": 8.78799469084349e-06, + "loss": 0.4227, + "step": 5445 + }, + { + "epoch": 0.7257462686567164, + "grad_norm": 0.3049890817004672, + "learning_rate": 8.787529899832076e-06, + "loss": 0.3635, + "step": 5446 + }, + { + "epoch": 0.7258795309168443, + "grad_norm": 0.29787788426089107, + "learning_rate": 8.787065032012848e-06, + "loss": 0.3743, + "step": 5447 + }, + { + "epoch": 0.7260127931769723, + "grad_norm": 0.3059814944566445, + "learning_rate": 8.786600087395228e-06, + "loss": 0.4233, + "step": 5448 + }, + { + "epoch": 0.7261460554371002, + "grad_norm": 0.286605422827235, + "learning_rate": 8.786135065988645e-06, + "loss": 0.4124, + "step": 5449 + }, + { + "epoch": 0.7262793176972282, + "grad_norm": 0.29881053071055635, + "learning_rate": 8.785669967802532e-06, + "loss": 0.3771, + "step": 5450 + }, + { + "epoch": 0.7264125799573561, + "grad_norm": 0.2859038885011914, + "learning_rate": 8.78520479284632e-06, + "loss": 0.3753, + "step": 5451 + }, + { + "epoch": 0.726545842217484, + "grad_norm": 0.313128684851825, + "learning_rate": 8.784739541129439e-06, + "loss": 0.4009, + "step": 5452 + }, + { + "epoch": 0.726679104477612, + "grad_norm": 0.29845550240307533, + "learning_rate": 8.784274212661329e-06, + "loss": 0.3829, + "step": 5453 + }, + { + "epoch": 0.7268123667377399, + "grad_norm": 0.3243206837001026, + "learning_rate": 8.783808807451422e-06, + "loss": 0.4241, + "step": 5454 + }, + { + "epoch": 0.7269456289978679, + "grad_norm": 0.30076246746350027, + "learning_rate": 8.78334332550916e-06, + "loss": 0.4553, + "step": 5455 + }, + { + "epoch": 0.7270788912579957, + "grad_norm": 0.294231925489563, + "learning_rate": 8.782877766843978e-06, + "loss": 0.4163, + "step": 5456 + }, + { + "epoch": 0.7272121535181236, + "grad_norm": 0.29943434141941067, + "learning_rate": 8.782412131465321e-06, + "loss": 0.4001, + "step": 5457 + }, + { + "epoch": 0.7273454157782516, + "grad_norm": 0.30966760144714084, + "learning_rate": 8.78194641938263e-06, + "loss": 0.5111, + "step": 5458 + }, + { + "epoch": 0.7274786780383795, + "grad_norm": 0.2995592688381887, + "learning_rate": 8.781480630605349e-06, + "loss": 0.4262, + "step": 5459 + }, + { + "epoch": 0.7276119402985075, + "grad_norm": 0.326985520370535, + "learning_rate": 8.781014765142926e-06, + "loss": 0.4009, + "step": 5460 + }, + { + "epoch": 0.7277452025586354, + "grad_norm": 2.521506281309436, + "learning_rate": 8.780548823004804e-06, + "loss": 0.4143, + "step": 5461 + }, + { + "epoch": 0.7278784648187633, + "grad_norm": 0.3013111210527837, + "learning_rate": 8.780082804200436e-06, + "loss": 0.3565, + "step": 5462 + }, + { + "epoch": 0.7280117270788913, + "grad_norm": 0.3033267187250251, + "learning_rate": 8.77961670873927e-06, + "loss": 0.4215, + "step": 5463 + }, + { + "epoch": 0.7281449893390192, + "grad_norm": 0.3085019640003942, + "learning_rate": 8.779150536630762e-06, + "loss": 0.3188, + "step": 5464 + }, + { + "epoch": 0.7282782515991472, + "grad_norm": 0.3078392117601788, + "learning_rate": 8.77868428788436e-06, + "loss": 0.4327, + "step": 5465 + }, + { + "epoch": 0.728411513859275, + "grad_norm": 0.28994161330481755, + "learning_rate": 8.778217962509523e-06, + "loss": 0.3776, + "step": 5466 + }, + { + "epoch": 0.7285447761194029, + "grad_norm": 0.3020109772077665, + "learning_rate": 8.777751560515706e-06, + "loss": 0.3909, + "step": 5467 + }, + { + "epoch": 0.7286780383795309, + "grad_norm": 0.2938285371483003, + "learning_rate": 8.777285081912367e-06, + "loss": 0.3779, + "step": 5468 + }, + { + "epoch": 0.7288113006396588, + "grad_norm": 0.2842109827316778, + "learning_rate": 8.776818526708967e-06, + "loss": 0.3921, + "step": 5469 + }, + { + "epoch": 0.7289445628997868, + "grad_norm": 0.3031445566799852, + "learning_rate": 8.776351894914968e-06, + "loss": 0.5316, + "step": 5470 + }, + { + "epoch": 0.7290778251599147, + "grad_norm": 0.3067107449613997, + "learning_rate": 8.77588518653983e-06, + "loss": 0.3879, + "step": 5471 + }, + { + "epoch": 0.7292110874200426, + "grad_norm": 0.30088659666996004, + "learning_rate": 8.77541840159302e-06, + "loss": 0.4135, + "step": 5472 + }, + { + "epoch": 0.7293443496801706, + "grad_norm": 0.3141931182984069, + "learning_rate": 8.774951540084e-06, + "loss": 0.5348, + "step": 5473 + }, + { + "epoch": 0.7294776119402985, + "grad_norm": 0.28854740336289164, + "learning_rate": 8.774484602022243e-06, + "loss": 0.423, + "step": 5474 + }, + { + "epoch": 0.7296108742004265, + "grad_norm": 0.29642222547657593, + "learning_rate": 8.774017587417216e-06, + "loss": 0.4599, + "step": 5475 + }, + { + "epoch": 0.7297441364605544, + "grad_norm": 0.3157648202887049, + "learning_rate": 8.77355049627839e-06, + "loss": 0.3961, + "step": 5476 + }, + { + "epoch": 0.7298773987206824, + "grad_norm": 0.26935482808201616, + "learning_rate": 8.773083328615235e-06, + "loss": 0.3592, + "step": 5477 + }, + { + "epoch": 0.7300106609808102, + "grad_norm": 0.2951597284283199, + "learning_rate": 8.772616084437227e-06, + "loss": 0.3446, + "step": 5478 + }, + { + "epoch": 0.7301439232409381, + "grad_norm": 0.29318307953277595, + "learning_rate": 8.77214876375384e-06, + "loss": 0.4571, + "step": 5479 + }, + { + "epoch": 0.7302771855010661, + "grad_norm": 0.30171311633757375, + "learning_rate": 8.771681366574552e-06, + "loss": 0.3907, + "step": 5480 + }, + { + "epoch": 0.730410447761194, + "grad_norm": 0.30682485532619375, + "learning_rate": 8.77121389290884e-06, + "loss": 0.3622, + "step": 5481 + }, + { + "epoch": 0.730543710021322, + "grad_norm": 0.30830846788140887, + "learning_rate": 8.770746342766188e-06, + "loss": 0.3557, + "step": 5482 + }, + { + "epoch": 0.7306769722814499, + "grad_norm": 0.3217213516053239, + "learning_rate": 8.770278716156072e-06, + "loss": 0.4495, + "step": 5483 + }, + { + "epoch": 0.7308102345415778, + "grad_norm": 0.3247561392704851, + "learning_rate": 8.769811013087976e-06, + "loss": 0.4273, + "step": 5484 + }, + { + "epoch": 0.7309434968017058, + "grad_norm": 0.30871061992887766, + "learning_rate": 8.769343233571389e-06, + "loss": 0.5053, + "step": 5485 + }, + { + "epoch": 0.7310767590618337, + "grad_norm": 0.3141934151699905, + "learning_rate": 8.768875377615792e-06, + "loss": 0.4249, + "step": 5486 + }, + { + "epoch": 0.7312100213219617, + "grad_norm": 0.3106426725952821, + "learning_rate": 8.768407445230676e-06, + "loss": 0.4289, + "step": 5487 + }, + { + "epoch": 0.7313432835820896, + "grad_norm": 0.2819232400456206, + "learning_rate": 8.767939436425528e-06, + "loss": 0.3342, + "step": 5488 + }, + { + "epoch": 0.7314765458422174, + "grad_norm": 0.3182194777028708, + "learning_rate": 8.767471351209843e-06, + "loss": 0.363, + "step": 5489 + }, + { + "epoch": 0.7316098081023454, + "grad_norm": 0.3045275755656941, + "learning_rate": 8.767003189593107e-06, + "loss": 0.4237, + "step": 5490 + }, + { + "epoch": 0.7317430703624733, + "grad_norm": 0.327354398115919, + "learning_rate": 8.766534951584817e-06, + "loss": 0.4172, + "step": 5491 + }, + { + "epoch": 0.7318763326226013, + "grad_norm": 0.3000660208541733, + "learning_rate": 8.766066637194471e-06, + "loss": 0.3232, + "step": 5492 + }, + { + "epoch": 0.7320095948827292, + "grad_norm": 0.30531464915427986, + "learning_rate": 8.765598246431563e-06, + "loss": 0.4187, + "step": 5493 + }, + { + "epoch": 0.7321428571428571, + "grad_norm": 0.33790620047576925, + "learning_rate": 8.765129779305592e-06, + "loss": 0.3777, + "step": 5494 + }, + { + "epoch": 0.7322761194029851, + "grad_norm": 0.2849828341821753, + "learning_rate": 8.764661235826059e-06, + "loss": 0.3834, + "step": 5495 + }, + { + "epoch": 0.732409381663113, + "grad_norm": 0.3304773774326145, + "learning_rate": 8.764192616002464e-06, + "loss": 0.4554, + "step": 5496 + }, + { + "epoch": 0.732542643923241, + "grad_norm": 0.2850842268977038, + "learning_rate": 8.763723919844311e-06, + "loss": 0.3736, + "step": 5497 + }, + { + "epoch": 0.7326759061833689, + "grad_norm": 0.3095231018854161, + "learning_rate": 8.763255147361107e-06, + "loss": 0.441, + "step": 5498 + }, + { + "epoch": 0.7328091684434968, + "grad_norm": 0.32842404800817904, + "learning_rate": 8.762786298562356e-06, + "loss": 0.4351, + "step": 5499 + }, + { + "epoch": 0.7329424307036247, + "grad_norm": 0.3019337007056546, + "learning_rate": 8.762317373457564e-06, + "loss": 0.3718, + "step": 5500 + }, + { + "epoch": 0.7330756929637526, + "grad_norm": 0.30770801037273254, + "learning_rate": 8.761848372056245e-06, + "loss": 0.4538, + "step": 5501 + }, + { + "epoch": 0.7332089552238806, + "grad_norm": 0.3175464597151547, + "learning_rate": 8.761379294367905e-06, + "loss": 0.3998, + "step": 5502 + }, + { + "epoch": 0.7333422174840085, + "grad_norm": 0.287167163629234, + "learning_rate": 8.76091014040206e-06, + "loss": 0.3817, + "step": 5503 + }, + { + "epoch": 0.7334754797441365, + "grad_norm": 0.2828619885600494, + "learning_rate": 8.760440910168225e-06, + "loss": 0.3488, + "step": 5504 + }, + { + "epoch": 0.7336087420042644, + "grad_norm": 0.2987008657092539, + "learning_rate": 8.759971603675909e-06, + "loss": 0.4138, + "step": 5505 + }, + { + "epoch": 0.7337420042643923, + "grad_norm": 0.30146539888437845, + "learning_rate": 8.759502220934638e-06, + "loss": 0.4017, + "step": 5506 + }, + { + "epoch": 0.7338752665245203, + "grad_norm": 0.28459516945688973, + "learning_rate": 8.759032761953925e-06, + "loss": 0.4507, + "step": 5507 + }, + { + "epoch": 0.7340085287846482, + "grad_norm": 0.2971299921922986, + "learning_rate": 8.758563226743291e-06, + "loss": 0.3742, + "step": 5508 + }, + { + "epoch": 0.7341417910447762, + "grad_norm": 0.28762173712220784, + "learning_rate": 8.758093615312259e-06, + "loss": 0.4669, + "step": 5509 + }, + { + "epoch": 0.7342750533049041, + "grad_norm": 0.3063567130710873, + "learning_rate": 8.757623927670352e-06, + "loss": 0.3991, + "step": 5510 + }, + { + "epoch": 0.7344083155650319, + "grad_norm": 0.32957170713444783, + "learning_rate": 8.757154163827094e-06, + "loss": 0.3809, + "step": 5511 + }, + { + "epoch": 0.7345415778251599, + "grad_norm": 0.2789190223508102, + "learning_rate": 8.756684323792012e-06, + "loss": 0.3955, + "step": 5512 + }, + { + "epoch": 0.7346748400852878, + "grad_norm": 0.30002420777392985, + "learning_rate": 8.756214407574635e-06, + "loss": 0.4026, + "step": 5513 + }, + { + "epoch": 0.7348081023454158, + "grad_norm": 0.2915972437975249, + "learning_rate": 8.75574441518449e-06, + "loss": 0.3892, + "step": 5514 + }, + { + "epoch": 0.7349413646055437, + "grad_norm": 0.2945178221612057, + "learning_rate": 8.755274346631108e-06, + "loss": 0.4214, + "step": 5515 + }, + { + "epoch": 0.7350746268656716, + "grad_norm": 0.28888684455627134, + "learning_rate": 8.754804201924026e-06, + "loss": 0.3792, + "step": 5516 + }, + { + "epoch": 0.7352078891257996, + "grad_norm": 0.2886581655813204, + "learning_rate": 8.754333981072774e-06, + "loss": 0.4454, + "step": 5517 + }, + { + "epoch": 0.7353411513859275, + "grad_norm": 0.3128766350499407, + "learning_rate": 8.75386368408689e-06, + "loss": 0.4641, + "step": 5518 + }, + { + "epoch": 0.7354744136460555, + "grad_norm": 0.2866099180019104, + "learning_rate": 8.753393310975908e-06, + "loss": 0.3622, + "step": 5519 + }, + { + "epoch": 0.7356076759061834, + "grad_norm": 0.2903489250228836, + "learning_rate": 8.75292286174937e-06, + "loss": 0.3711, + "step": 5520 + }, + { + "epoch": 0.7357409381663113, + "grad_norm": 0.27813994008795195, + "learning_rate": 8.752452336416814e-06, + "loss": 0.3871, + "step": 5521 + }, + { + "epoch": 0.7358742004264393, + "grad_norm": 0.3152180343737203, + "learning_rate": 8.751981734987783e-06, + "loss": 0.4407, + "step": 5522 + }, + { + "epoch": 0.7360074626865671, + "grad_norm": 0.30905379878704237, + "learning_rate": 8.75151105747182e-06, + "loss": 0.4395, + "step": 5523 + }, + { + "epoch": 0.7361407249466951, + "grad_norm": 0.2874619230857773, + "learning_rate": 8.751040303878471e-06, + "loss": 0.4118, + "step": 5524 + }, + { + "epoch": 0.736273987206823, + "grad_norm": 0.29735130711993984, + "learning_rate": 8.750569474217283e-06, + "loss": 0.4711, + "step": 5525 + }, + { + "epoch": 0.7364072494669509, + "grad_norm": 0.29641071410093833, + "learning_rate": 8.7500985684978e-06, + "loss": 0.3802, + "step": 5526 + }, + { + "epoch": 0.7365405117270789, + "grad_norm": 0.2875435151934828, + "learning_rate": 8.749627586729577e-06, + "loss": 0.3796, + "step": 5527 + }, + { + "epoch": 0.7366737739872068, + "grad_norm": 0.30271826775739347, + "learning_rate": 8.74915652892216e-06, + "loss": 0.409, + "step": 5528 + }, + { + "epoch": 0.7368070362473348, + "grad_norm": 0.27400177825884925, + "learning_rate": 8.748685395085105e-06, + "loss": 0.3998, + "step": 5529 + }, + { + "epoch": 0.7369402985074627, + "grad_norm": 0.2943636857844511, + "learning_rate": 8.748214185227968e-06, + "loss": 0.3303, + "step": 5530 + }, + { + "epoch": 0.7370735607675906, + "grad_norm": 0.2699859682520475, + "learning_rate": 8.747742899360299e-06, + "loss": 0.3454, + "step": 5531 + }, + { + "epoch": 0.7372068230277186, + "grad_norm": 0.2945008187137847, + "learning_rate": 8.747271537491657e-06, + "loss": 0.3655, + "step": 5532 + }, + { + "epoch": 0.7373400852878464, + "grad_norm": 0.2855796974380345, + "learning_rate": 8.746800099631606e-06, + "loss": 0.4594, + "step": 5533 + }, + { + "epoch": 0.7374733475479744, + "grad_norm": 0.30772065444284213, + "learning_rate": 8.746328585789698e-06, + "loss": 0.4167, + "step": 5534 + }, + { + "epoch": 0.7376066098081023, + "grad_norm": 0.2901315247939871, + "learning_rate": 8.745856995975502e-06, + "loss": 0.4523, + "step": 5535 + }, + { + "epoch": 0.7377398720682303, + "grad_norm": 0.2784783901291735, + "learning_rate": 8.745385330198578e-06, + "loss": 0.3569, + "step": 5536 + }, + { + "epoch": 0.7378731343283582, + "grad_norm": 0.3060036008937321, + "learning_rate": 8.744913588468492e-06, + "loss": 0.451, + "step": 5537 + }, + { + "epoch": 0.7380063965884861, + "grad_norm": 0.2926674501462459, + "learning_rate": 8.74444177079481e-06, + "loss": 0.3936, + "step": 5538 + }, + { + "epoch": 0.7381396588486141, + "grad_norm": 0.294868450463898, + "learning_rate": 8.7439698771871e-06, + "loss": 0.4411, + "step": 5539 + }, + { + "epoch": 0.738272921108742, + "grad_norm": 0.28356540279139447, + "learning_rate": 8.743497907654931e-06, + "loss": 0.3647, + "step": 5540 + }, + { + "epoch": 0.73840618336887, + "grad_norm": 0.30405946516285476, + "learning_rate": 8.743025862207875e-06, + "loss": 0.4264, + "step": 5541 + }, + { + "epoch": 0.7385394456289979, + "grad_norm": 0.29689878975565215, + "learning_rate": 8.742553740855507e-06, + "loss": 0.4323, + "step": 5542 + }, + { + "epoch": 0.7386727078891258, + "grad_norm": 0.2923610754542337, + "learning_rate": 8.742081543607397e-06, + "loss": 0.3986, + "step": 5543 + }, + { + "epoch": 0.7388059701492538, + "grad_norm": 0.31618555184328645, + "learning_rate": 8.741609270473123e-06, + "loss": 0.5296, + "step": 5544 + }, + { + "epoch": 0.7389392324093816, + "grad_norm": 0.3018418636444305, + "learning_rate": 8.741136921462261e-06, + "loss": 0.3952, + "step": 5545 + }, + { + "epoch": 0.7390724946695096, + "grad_norm": 0.29172778503531693, + "learning_rate": 8.740664496584393e-06, + "loss": 0.3011, + "step": 5546 + }, + { + "epoch": 0.7392057569296375, + "grad_norm": 0.2986583029839505, + "learning_rate": 8.740191995849094e-06, + "loss": 0.4134, + "step": 5547 + }, + { + "epoch": 0.7393390191897654, + "grad_norm": 0.3092632927323457, + "learning_rate": 8.739719419265951e-06, + "loss": 0.3661, + "step": 5548 + }, + { + "epoch": 0.7394722814498934, + "grad_norm": 0.29845709896569633, + "learning_rate": 8.739246766844545e-06, + "loss": 0.444, + "step": 5549 + }, + { + "epoch": 0.7396055437100213, + "grad_norm": 0.3160631423430756, + "learning_rate": 8.738774038594462e-06, + "loss": 0.3869, + "step": 5550 + }, + { + "epoch": 0.7397388059701493, + "grad_norm": 0.3119111813228327, + "learning_rate": 8.738301234525287e-06, + "loss": 0.5057, + "step": 5551 + }, + { + "epoch": 0.7398720682302772, + "grad_norm": 0.28388649946472133, + "learning_rate": 8.73782835464661e-06, + "loss": 0.3533, + "step": 5552 + }, + { + "epoch": 0.7400053304904051, + "grad_norm": 0.3063304733383136, + "learning_rate": 8.737355398968018e-06, + "loss": 0.5052, + "step": 5553 + }, + { + "epoch": 0.7401385927505331, + "grad_norm": 0.30282852078355776, + "learning_rate": 8.736882367499105e-06, + "loss": 0.4449, + "step": 5554 + }, + { + "epoch": 0.740271855010661, + "grad_norm": 0.2989388689143279, + "learning_rate": 8.736409260249461e-06, + "loss": 0.4097, + "step": 5555 + }, + { + "epoch": 0.740405117270789, + "grad_norm": 0.2966985695101635, + "learning_rate": 8.735936077228684e-06, + "loss": 0.3749, + "step": 5556 + }, + { + "epoch": 0.7405383795309168, + "grad_norm": 0.2774560587076015, + "learning_rate": 8.735462818446365e-06, + "loss": 0.3416, + "step": 5557 + }, + { + "epoch": 0.7406716417910447, + "grad_norm": 0.30480061454498836, + "learning_rate": 8.734989483912105e-06, + "loss": 0.3717, + "step": 5558 + }, + { + "epoch": 0.7408049040511727, + "grad_norm": 0.3114877606527589, + "learning_rate": 8.734516073635501e-06, + "loss": 0.5146, + "step": 5559 + }, + { + "epoch": 0.7409381663113006, + "grad_norm": 0.2972244589612327, + "learning_rate": 8.734042587626152e-06, + "loss": 0.4421, + "step": 5560 + }, + { + "epoch": 0.7410714285714286, + "grad_norm": 0.31923471080576454, + "learning_rate": 8.733569025893664e-06, + "loss": 0.37, + "step": 5561 + }, + { + "epoch": 0.7412046908315565, + "grad_norm": 0.28844103864239984, + "learning_rate": 8.733095388447638e-06, + "loss": 0.4147, + "step": 5562 + }, + { + "epoch": 0.7413379530916845, + "grad_norm": 0.28466137157216037, + "learning_rate": 8.732621675297677e-06, + "loss": 0.3916, + "step": 5563 + }, + { + "epoch": 0.7414712153518124, + "grad_norm": 0.2868217503608342, + "learning_rate": 8.732147886453392e-06, + "loss": 0.4061, + "step": 5564 + }, + { + "epoch": 0.7416044776119403, + "grad_norm": 0.28801577580293636, + "learning_rate": 8.731674021924388e-06, + "loss": 0.4082, + "step": 5565 + }, + { + "epoch": 0.7417377398720683, + "grad_norm": 0.2904798256022756, + "learning_rate": 8.731200081720274e-06, + "loss": 0.3822, + "step": 5566 + }, + { + "epoch": 0.7418710021321961, + "grad_norm": 0.2965411781307276, + "learning_rate": 8.730726065850663e-06, + "loss": 0.3484, + "step": 5567 + }, + { + "epoch": 0.7420042643923241, + "grad_norm": 0.2981601977327739, + "learning_rate": 8.730251974325166e-06, + "loss": 0.4975, + "step": 5568 + }, + { + "epoch": 0.742137526652452, + "grad_norm": 0.293431645010317, + "learning_rate": 8.729777807153399e-06, + "loss": 0.3786, + "step": 5569 + }, + { + "epoch": 0.7422707889125799, + "grad_norm": 0.30251967396834695, + "learning_rate": 8.729303564344976e-06, + "loss": 0.3923, + "step": 5570 + }, + { + "epoch": 0.7424040511727079, + "grad_norm": 0.2972053993458738, + "learning_rate": 8.728829245909515e-06, + "loss": 0.412, + "step": 5571 + }, + { + "epoch": 0.7425373134328358, + "grad_norm": 0.29033964874423485, + "learning_rate": 8.728354851856636e-06, + "loss": 0.4799, + "step": 5572 + }, + { + "epoch": 0.7426705756929638, + "grad_norm": 0.2850046874756709, + "learning_rate": 8.727880382195955e-06, + "loss": 0.4157, + "step": 5573 + }, + { + "epoch": 0.7428038379530917, + "grad_norm": 0.29363871550746495, + "learning_rate": 8.7274058369371e-06, + "loss": 0.4888, + "step": 5574 + }, + { + "epoch": 0.7429371002132196, + "grad_norm": 0.2930960898775856, + "learning_rate": 8.72693121608969e-06, + "loss": 0.4322, + "step": 5575 + }, + { + "epoch": 0.7430703624733476, + "grad_norm": 0.3083273050554051, + "learning_rate": 8.72645651966335e-06, + "loss": 0.4196, + "step": 5576 + }, + { + "epoch": 0.7432036247334755, + "grad_norm": 0.28810462700661166, + "learning_rate": 8.72598174766771e-06, + "loss": 0.4071, + "step": 5577 + }, + { + "epoch": 0.7433368869936035, + "grad_norm": 0.2954757553274047, + "learning_rate": 8.725506900112393e-06, + "loss": 0.4456, + "step": 5578 + }, + { + "epoch": 0.7434701492537313, + "grad_norm": 0.3049327390905497, + "learning_rate": 8.725031977007031e-06, + "loss": 0.4603, + "step": 5579 + }, + { + "epoch": 0.7436034115138592, + "grad_norm": 0.2590326815229293, + "learning_rate": 8.724556978361256e-06, + "loss": 0.3374, + "step": 5580 + }, + { + "epoch": 0.7437366737739872, + "grad_norm": 0.2924686225115959, + "learning_rate": 8.7240819041847e-06, + "loss": 0.3708, + "step": 5581 + }, + { + "epoch": 0.7438699360341151, + "grad_norm": 0.28156937967076234, + "learning_rate": 8.723606754486995e-06, + "loss": 0.4023, + "step": 5582 + }, + { + "epoch": 0.7440031982942431, + "grad_norm": 0.30626708063479563, + "learning_rate": 8.72313152927778e-06, + "loss": 0.4608, + "step": 5583 + }, + { + "epoch": 0.744136460554371, + "grad_norm": 0.29460795367522785, + "learning_rate": 8.72265622856669e-06, + "loss": 0.4124, + "step": 5584 + }, + { + "epoch": 0.7442697228144989, + "grad_norm": 0.306499235799307, + "learning_rate": 8.722180852363364e-06, + "loss": 0.439, + "step": 5585 + }, + { + "epoch": 0.7444029850746269, + "grad_norm": 0.30224443836331083, + "learning_rate": 8.721705400677442e-06, + "loss": 0.4389, + "step": 5586 + }, + { + "epoch": 0.7445362473347548, + "grad_norm": 0.2981867336709381, + "learning_rate": 8.721229873518566e-06, + "loss": 0.4083, + "step": 5587 + }, + { + "epoch": 0.7446695095948828, + "grad_norm": 0.2831778025448375, + "learning_rate": 8.720754270896378e-06, + "loss": 0.4008, + "step": 5588 + }, + { + "epoch": 0.7448027718550106, + "grad_norm": 0.2910820141164477, + "learning_rate": 8.720278592820526e-06, + "loss": 0.3575, + "step": 5589 + }, + { + "epoch": 0.7449360341151386, + "grad_norm": 0.2869338569087795, + "learning_rate": 8.719802839300656e-06, + "loss": 0.3925, + "step": 5590 + }, + { + "epoch": 0.7450692963752665, + "grad_norm": 0.3022091756275784, + "learning_rate": 8.719327010346413e-06, + "loss": 0.4046, + "step": 5591 + }, + { + "epoch": 0.7452025586353944, + "grad_norm": 0.2907588253572345, + "learning_rate": 8.718851105967447e-06, + "loss": 0.4255, + "step": 5592 + }, + { + "epoch": 0.7453358208955224, + "grad_norm": 0.28224186641767596, + "learning_rate": 8.718375126173409e-06, + "loss": 0.3399, + "step": 5593 + }, + { + "epoch": 0.7454690831556503, + "grad_norm": 0.2856593202787731, + "learning_rate": 8.717899070973953e-06, + "loss": 0.4265, + "step": 5594 + }, + { + "epoch": 0.7456023454157783, + "grad_norm": 0.29749446891127673, + "learning_rate": 8.717422940378733e-06, + "loss": 0.3941, + "step": 5595 + }, + { + "epoch": 0.7457356076759062, + "grad_norm": 0.2797286552771317, + "learning_rate": 8.716946734397403e-06, + "loss": 0.4006, + "step": 5596 + }, + { + "epoch": 0.7458688699360341, + "grad_norm": 0.29858710078405304, + "learning_rate": 8.716470453039622e-06, + "loss": 0.3841, + "step": 5597 + }, + { + "epoch": 0.7460021321961621, + "grad_norm": 0.2929425785400949, + "learning_rate": 8.715994096315045e-06, + "loss": 0.4388, + "step": 5598 + }, + { + "epoch": 0.74613539445629, + "grad_norm": 0.28906242939791205, + "learning_rate": 8.715517664233337e-06, + "loss": 0.4006, + "step": 5599 + }, + { + "epoch": 0.746268656716418, + "grad_norm": 0.3055391156490115, + "learning_rate": 8.715041156804153e-06, + "loss": 0.4091, + "step": 5600 + }, + { + "epoch": 0.7464019189765458, + "grad_norm": 0.2946180679834262, + "learning_rate": 8.714564574037164e-06, + "loss": 0.4156, + "step": 5601 + }, + { + "epoch": 0.7465351812366737, + "grad_norm": 0.3022375497542744, + "learning_rate": 8.714087915942028e-06, + "loss": 0.618, + "step": 5602 + }, + { + "epoch": 0.7466684434968017, + "grad_norm": 0.28637540072170414, + "learning_rate": 8.713611182528416e-06, + "loss": 0.4099, + "step": 5603 + }, + { + "epoch": 0.7468017057569296, + "grad_norm": 0.3009275521656022, + "learning_rate": 8.713134373805993e-06, + "loss": 0.4466, + "step": 5604 + }, + { + "epoch": 0.7469349680170576, + "grad_norm": 0.2949927870389127, + "learning_rate": 8.712657489784431e-06, + "loss": 0.4307, + "step": 5605 + }, + { + "epoch": 0.7470682302771855, + "grad_norm": 0.29719846428354857, + "learning_rate": 8.712180530473397e-06, + "loss": 0.3672, + "step": 5606 + }, + { + "epoch": 0.7472014925373134, + "grad_norm": 0.2749101296241964, + "learning_rate": 8.711703495882566e-06, + "loss": 0.3303, + "step": 5607 + }, + { + "epoch": 0.7473347547974414, + "grad_norm": 0.29751912904573463, + "learning_rate": 8.71122638602161e-06, + "loss": 0.3908, + "step": 5608 + }, + { + "epoch": 0.7474680170575693, + "grad_norm": 11.704990034668967, + "learning_rate": 8.710749200900206e-06, + "loss": 0.3343, + "step": 5609 + }, + { + "epoch": 0.7476012793176973, + "grad_norm": 0.3097344462319457, + "learning_rate": 8.71027194052803e-06, + "loss": 0.4261, + "step": 5610 + }, + { + "epoch": 0.7477345415778252, + "grad_norm": 0.3005437073412865, + "learning_rate": 8.70979460491476e-06, + "loss": 0.4666, + "step": 5611 + }, + { + "epoch": 0.747867803837953, + "grad_norm": 0.2836565660280253, + "learning_rate": 8.709317194070078e-06, + "loss": 0.3993, + "step": 5612 + }, + { + "epoch": 0.748001066098081, + "grad_norm": 0.284476510801799, + "learning_rate": 8.708839708003665e-06, + "loss": 0.4598, + "step": 5613 + }, + { + "epoch": 0.7481343283582089, + "grad_norm": 0.29562376288822806, + "learning_rate": 8.708362146725199e-06, + "loss": 0.3845, + "step": 5614 + }, + { + "epoch": 0.7482675906183369, + "grad_norm": 0.2839227771042708, + "learning_rate": 8.707884510244373e-06, + "loss": 0.3879, + "step": 5615 + }, + { + "epoch": 0.7484008528784648, + "grad_norm": 0.29313091927497886, + "learning_rate": 8.707406798570867e-06, + "loss": 0.3952, + "step": 5616 + }, + { + "epoch": 0.7485341151385928, + "grad_norm": 0.29493397669457266, + "learning_rate": 8.706929011714371e-06, + "loss": 0.4157, + "step": 5617 + }, + { + "epoch": 0.7486673773987207, + "grad_norm": 0.30027249169768, + "learning_rate": 8.706451149684574e-06, + "loss": 0.4437, + "step": 5618 + }, + { + "epoch": 0.7488006396588486, + "grad_norm": 0.29444093492072954, + "learning_rate": 8.705973212491165e-06, + "loss": 0.4099, + "step": 5619 + }, + { + "epoch": 0.7489339019189766, + "grad_norm": 0.28715652845009654, + "learning_rate": 8.705495200143836e-06, + "loss": 0.4152, + "step": 5620 + }, + { + "epoch": 0.7490671641791045, + "grad_norm": 0.3156764455006885, + "learning_rate": 8.705017112652284e-06, + "loss": 0.4027, + "step": 5621 + }, + { + "epoch": 0.7492004264392325, + "grad_norm": 0.2955144914530533, + "learning_rate": 8.7045389500262e-06, + "loss": 0.4695, + "step": 5622 + }, + { + "epoch": 0.7493336886993603, + "grad_norm": 0.3042563903221142, + "learning_rate": 8.704060712275285e-06, + "loss": 0.5131, + "step": 5623 + }, + { + "epoch": 0.7494669509594882, + "grad_norm": 0.28228504071424665, + "learning_rate": 8.703582399409233e-06, + "loss": 0.3855, + "step": 5624 + }, + { + "epoch": 0.7496002132196162, + "grad_norm": 0.29427126497389205, + "learning_rate": 8.70310401143775e-06, + "loss": 0.4018, + "step": 5625 + }, + { + "epoch": 0.7497334754797441, + "grad_norm": 0.2812018952089409, + "learning_rate": 8.702625548370528e-06, + "loss": 0.3411, + "step": 5626 + }, + { + "epoch": 0.7498667377398721, + "grad_norm": 0.28756989629865637, + "learning_rate": 8.702147010217277e-06, + "loss": 0.4449, + "step": 5627 + }, + { + "epoch": 0.75, + "grad_norm": 0.2993349227310545, + "learning_rate": 8.701668396987699e-06, + "loss": 0.5099, + "step": 5628 + }, + { + "epoch": 0.7501332622601279, + "grad_norm": 0.5782036061017778, + "learning_rate": 8.7011897086915e-06, + "loss": 0.4115, + "step": 5629 + }, + { + "epoch": 0.7502665245202559, + "grad_norm": 0.2854281734323256, + "learning_rate": 8.700710945338387e-06, + "loss": 0.4578, + "step": 5630 + }, + { + "epoch": 0.7503997867803838, + "grad_norm": 0.29276814066015994, + "learning_rate": 8.700232106938072e-06, + "loss": 0.4458, + "step": 5631 + }, + { + "epoch": 0.7505330490405118, + "grad_norm": 0.2931503513221152, + "learning_rate": 8.69975319350026e-06, + "loss": 0.5078, + "step": 5632 + }, + { + "epoch": 0.7506663113006397, + "grad_norm": 0.29212797384918743, + "learning_rate": 8.699274205034668e-06, + "loss": 0.5459, + "step": 5633 + }, + { + "epoch": 0.7507995735607675, + "grad_norm": 0.29048039860469793, + "learning_rate": 8.698795141551005e-06, + "loss": 0.4183, + "step": 5634 + }, + { + "epoch": 0.7509328358208955, + "grad_norm": 0.2946731705232509, + "learning_rate": 8.698316003058988e-06, + "loss": 0.3882, + "step": 5635 + }, + { + "epoch": 0.7510660980810234, + "grad_norm": 0.2925165166065579, + "learning_rate": 8.697836789568337e-06, + "loss": 0.3847, + "step": 5636 + }, + { + "epoch": 0.7511993603411514, + "grad_norm": 0.2833981387124328, + "learning_rate": 8.697357501088764e-06, + "loss": 0.3636, + "step": 5637 + }, + { + "epoch": 0.7513326226012793, + "grad_norm": 0.2908719438181974, + "learning_rate": 8.696878137629992e-06, + "loss": 0.378, + "step": 5638 + }, + { + "epoch": 0.7514658848614072, + "grad_norm": 0.28109301978047263, + "learning_rate": 8.696398699201742e-06, + "loss": 0.3868, + "step": 5639 + }, + { + "epoch": 0.7515991471215352, + "grad_norm": 0.2928935837908414, + "learning_rate": 8.695919185813734e-06, + "loss": 0.4201, + "step": 5640 + }, + { + "epoch": 0.7517324093816631, + "grad_norm": 0.28070655998168387, + "learning_rate": 8.695439597475697e-06, + "loss": 0.3301, + "step": 5641 + }, + { + "epoch": 0.7518656716417911, + "grad_norm": 0.29418205139151726, + "learning_rate": 8.694959934197352e-06, + "loss": 0.3958, + "step": 5642 + }, + { + "epoch": 0.751998933901919, + "grad_norm": 0.301128501056737, + "learning_rate": 8.694480195988428e-06, + "loss": 0.4894, + "step": 5643 + }, + { + "epoch": 0.752132196162047, + "grad_norm": 0.28249048574135577, + "learning_rate": 8.694000382858655e-06, + "loss": 0.3673, + "step": 5644 + }, + { + "epoch": 0.7522654584221748, + "grad_norm": 0.2774442948440786, + "learning_rate": 8.69352049481776e-06, + "loss": 0.3645, + "step": 5645 + }, + { + "epoch": 0.7523987206823027, + "grad_norm": 0.29598364732078997, + "learning_rate": 8.693040531875477e-06, + "loss": 0.4071, + "step": 5646 + }, + { + "epoch": 0.7525319829424307, + "grad_norm": 0.28496966824424197, + "learning_rate": 8.692560494041539e-06, + "loss": 0.4336, + "step": 5647 + }, + { + "epoch": 0.7526652452025586, + "grad_norm": 0.2835722438227122, + "learning_rate": 8.69208038132568e-06, + "loss": 0.363, + "step": 5648 + }, + { + "epoch": 0.7527985074626866, + "grad_norm": 0.2795954506305685, + "learning_rate": 8.691600193737638e-06, + "loss": 0.4148, + "step": 5649 + }, + { + "epoch": 0.7529317697228145, + "grad_norm": 0.2958470459277078, + "learning_rate": 8.69111993128715e-06, + "loss": 0.3757, + "step": 5650 + }, + { + "epoch": 0.7530650319829424, + "grad_norm": 0.2886913686685417, + "learning_rate": 8.690639593983953e-06, + "loss": 0.4207, + "step": 5651 + }, + { + "epoch": 0.7531982942430704, + "grad_norm": 0.27775321291752386, + "learning_rate": 8.690159181837789e-06, + "loss": 0.3682, + "step": 5652 + }, + { + "epoch": 0.7533315565031983, + "grad_norm": 0.2840954441949615, + "learning_rate": 8.689678694858404e-06, + "loss": 0.3901, + "step": 5653 + }, + { + "epoch": 0.7534648187633263, + "grad_norm": 0.2912623719729442, + "learning_rate": 8.689198133055536e-06, + "loss": 0.3745, + "step": 5654 + }, + { + "epoch": 0.7535980810234542, + "grad_norm": 0.2742861402093627, + "learning_rate": 8.688717496438934e-06, + "loss": 0.3877, + "step": 5655 + }, + { + "epoch": 0.753731343283582, + "grad_norm": 0.31645480730494735, + "learning_rate": 8.688236785018344e-06, + "loss": 0.466, + "step": 5656 + }, + { + "epoch": 0.75386460554371, + "grad_norm": 0.2706608621354398, + "learning_rate": 8.687755998803517e-06, + "loss": 0.3235, + "step": 5657 + }, + { + "epoch": 0.7539978678038379, + "grad_norm": 0.29714774561333, + "learning_rate": 8.687275137804197e-06, + "loss": 0.4844, + "step": 5658 + }, + { + "epoch": 0.7541311300639659, + "grad_norm": 0.28742709381471093, + "learning_rate": 8.686794202030141e-06, + "loss": 0.4174, + "step": 5659 + }, + { + "epoch": 0.7542643923240938, + "grad_norm": 0.2683116237345391, + "learning_rate": 8.6863131914911e-06, + "loss": 0.3556, + "step": 5660 + }, + { + "epoch": 0.7543976545842217, + "grad_norm": 0.30653810099537954, + "learning_rate": 8.685832106196827e-06, + "loss": 0.4363, + "step": 5661 + }, + { + "epoch": 0.7545309168443497, + "grad_norm": 0.32111073343584084, + "learning_rate": 8.685350946157081e-06, + "loss": 0.4184, + "step": 5662 + }, + { + "epoch": 0.7546641791044776, + "grad_norm": 0.3056904524029563, + "learning_rate": 8.684869711381616e-06, + "loss": 0.3539, + "step": 5663 + }, + { + "epoch": 0.7547974413646056, + "grad_norm": 0.2919280242326953, + "learning_rate": 8.684388401880194e-06, + "loss": 0.5256, + "step": 5664 + }, + { + "epoch": 0.7549307036247335, + "grad_norm": 0.2960610433670491, + "learning_rate": 8.683907017662574e-06, + "loss": 0.4405, + "step": 5665 + }, + { + "epoch": 0.7550639658848614, + "grad_norm": 0.288627156490186, + "learning_rate": 8.683425558738518e-06, + "loss": 0.4814, + "step": 5666 + }, + { + "epoch": 0.7551972281449894, + "grad_norm": 0.2998808705052273, + "learning_rate": 8.682944025117793e-06, + "loss": 0.3945, + "step": 5667 + }, + { + "epoch": 0.7553304904051172, + "grad_norm": 0.3178171384711371, + "learning_rate": 8.682462416810156e-06, + "loss": 0.3306, + "step": 5668 + }, + { + "epoch": 0.7554637526652452, + "grad_norm": 0.2841308396582505, + "learning_rate": 8.681980733825384e-06, + "loss": 0.3946, + "step": 5669 + }, + { + "epoch": 0.7555970149253731, + "grad_norm": 0.2881088835268116, + "learning_rate": 8.681498976173236e-06, + "loss": 0.3285, + "step": 5670 + }, + { + "epoch": 0.7557302771855011, + "grad_norm": 0.29257174519578677, + "learning_rate": 8.681017143863486e-06, + "loss": 0.3654, + "step": 5671 + }, + { + "epoch": 0.755863539445629, + "grad_norm": 0.31868094340644587, + "learning_rate": 8.680535236905906e-06, + "loss": 0.4053, + "step": 5672 + }, + { + "epoch": 0.7559968017057569, + "grad_norm": 0.2794635662240324, + "learning_rate": 8.680053255310269e-06, + "loss": 0.3887, + "step": 5673 + }, + { + "epoch": 0.7561300639658849, + "grad_norm": 0.3057466853563871, + "learning_rate": 8.679571199086342e-06, + "loss": 0.4567, + "step": 5674 + }, + { + "epoch": 0.7562633262260128, + "grad_norm": 0.305085536693694, + "learning_rate": 8.679089068243911e-06, + "loss": 0.3838, + "step": 5675 + }, + { + "epoch": 0.7563965884861408, + "grad_norm": 0.29734875074058004, + "learning_rate": 8.678606862792746e-06, + "loss": 0.4399, + "step": 5676 + }, + { + "epoch": 0.7565298507462687, + "grad_norm": 0.28235903784452737, + "learning_rate": 8.678124582742628e-06, + "loss": 0.4141, + "step": 5677 + }, + { + "epoch": 0.7566631130063965, + "grad_norm": 0.3010396765209118, + "learning_rate": 8.677642228103338e-06, + "loss": 0.3803, + "step": 5678 + }, + { + "epoch": 0.7567963752665245, + "grad_norm": 0.3182478777675529, + "learning_rate": 8.677159798884657e-06, + "loss": 0.6131, + "step": 5679 + }, + { + "epoch": 0.7569296375266524, + "grad_norm": 0.2899282467799193, + "learning_rate": 8.676677295096367e-06, + "loss": 0.3944, + "step": 5680 + }, + { + "epoch": 0.7570628997867804, + "grad_norm": 0.31148011185445984, + "learning_rate": 8.676194716748255e-06, + "loss": 0.5248, + "step": 5681 + }, + { + "epoch": 0.7571961620469083, + "grad_norm": 0.2861157649809625, + "learning_rate": 8.675712063850106e-06, + "loss": 0.4548, + "step": 5682 + }, + { + "epoch": 0.7573294243070362, + "grad_norm": 0.28218612744196225, + "learning_rate": 8.675229336411707e-06, + "loss": 0.4831, + "step": 5683 + }, + { + "epoch": 0.7574626865671642, + "grad_norm": 0.33491827349528414, + "learning_rate": 8.67474653444285e-06, + "loss": 0.3132, + "step": 5684 + }, + { + "epoch": 0.7575959488272921, + "grad_norm": 0.2812466629534615, + "learning_rate": 8.674263657953324e-06, + "loss": 0.3901, + "step": 5685 + }, + { + "epoch": 0.7577292110874201, + "grad_norm": 0.2881851777736386, + "learning_rate": 8.67378070695292e-06, + "loss": 0.3737, + "step": 5686 + }, + { + "epoch": 0.757862473347548, + "grad_norm": 0.29813579441230825, + "learning_rate": 8.673297681451436e-06, + "loss": 0.3811, + "step": 5687 + }, + { + "epoch": 0.7579957356076759, + "grad_norm": 0.2739090637086975, + "learning_rate": 8.672814581458661e-06, + "loss": 0.3615, + "step": 5688 + }, + { + "epoch": 0.7581289978678039, + "grad_norm": 0.29103918935267076, + "learning_rate": 8.672331406984398e-06, + "loss": 0.4189, + "step": 5689 + }, + { + "epoch": 0.7582622601279317, + "grad_norm": 0.2838879166860792, + "learning_rate": 8.671848158038444e-06, + "loss": 0.3688, + "step": 5690 + }, + { + "epoch": 0.7583955223880597, + "grad_norm": 0.29682006218343115, + "learning_rate": 8.671364834630594e-06, + "loss": 0.4975, + "step": 5691 + }, + { + "epoch": 0.7585287846481876, + "grad_norm": 0.2878296560966435, + "learning_rate": 8.670881436770655e-06, + "loss": 0.4095, + "step": 5692 + }, + { + "epoch": 0.7586620469083155, + "grad_norm": 0.2797119901205977, + "learning_rate": 8.670397964468429e-06, + "loss": 0.3925, + "step": 5693 + }, + { + "epoch": 0.7587953091684435, + "grad_norm": 0.2728584219151111, + "learning_rate": 8.669914417733715e-06, + "loss": 0.3675, + "step": 5694 + }, + { + "epoch": 0.7589285714285714, + "grad_norm": 0.296097289023632, + "learning_rate": 8.669430796576329e-06, + "loss": 0.3896, + "step": 5695 + }, + { + "epoch": 0.7590618336886994, + "grad_norm": 0.28446212865354725, + "learning_rate": 8.66894710100607e-06, + "loss": 0.3781, + "step": 5696 + }, + { + "epoch": 0.7591950959488273, + "grad_norm": 0.2911921413753372, + "learning_rate": 8.668463331032748e-06, + "loss": 0.4928, + "step": 5697 + }, + { + "epoch": 0.7593283582089553, + "grad_norm": 0.30237961410512904, + "learning_rate": 8.667979486666176e-06, + "loss": 0.417, + "step": 5698 + }, + { + "epoch": 0.7594616204690832, + "grad_norm": 0.2974933822336144, + "learning_rate": 8.667495567916166e-06, + "loss": 0.4283, + "step": 5699 + }, + { + "epoch": 0.759594882729211, + "grad_norm": 0.3048297609142939, + "learning_rate": 8.66701157479253e-06, + "loss": 0.5494, + "step": 5700 + }, + { + "epoch": 0.759728144989339, + "grad_norm": 0.28895743473656366, + "learning_rate": 8.666527507305084e-06, + "loss": 0.3973, + "step": 5701 + }, + { + "epoch": 0.7598614072494669, + "grad_norm": 0.280153975455359, + "learning_rate": 8.666043365463643e-06, + "loss": 0.3557, + "step": 5702 + }, + { + "epoch": 0.7599946695095949, + "grad_norm": 0.276945180848034, + "learning_rate": 8.665559149278025e-06, + "loss": 0.3693, + "step": 5703 + }, + { + "epoch": 0.7601279317697228, + "grad_norm": 0.2842890087009692, + "learning_rate": 8.665074858758052e-06, + "loss": 0.4435, + "step": 5704 + }, + { + "epoch": 0.7602611940298507, + "grad_norm": 0.2984884468000578, + "learning_rate": 8.664590493913542e-06, + "loss": 0.3949, + "step": 5705 + }, + { + "epoch": 0.7603944562899787, + "grad_norm": 0.2827079717270555, + "learning_rate": 8.66410605475432e-06, + "loss": 0.4031, + "step": 5706 + }, + { + "epoch": 0.7605277185501066, + "grad_norm": 0.31342329931262225, + "learning_rate": 8.663621541290208e-06, + "loss": 0.3965, + "step": 5707 + }, + { + "epoch": 0.7606609808102346, + "grad_norm": 0.30804710166980537, + "learning_rate": 8.663136953531034e-06, + "loss": 0.3735, + "step": 5708 + }, + { + "epoch": 0.7607942430703625, + "grad_norm": 0.3197954222351504, + "learning_rate": 8.66265229148662e-06, + "loss": 0.4, + "step": 5709 + }, + { + "epoch": 0.7609275053304904, + "grad_norm": 0.2949717017034879, + "learning_rate": 8.662167555166801e-06, + "loss": 0.4228, + "step": 5710 + }, + { + "epoch": 0.7610607675906184, + "grad_norm": 0.29767670676762387, + "learning_rate": 8.661682744581401e-06, + "loss": 0.3757, + "step": 5711 + }, + { + "epoch": 0.7611940298507462, + "grad_norm": 0.29879506141303697, + "learning_rate": 8.661197859740255e-06, + "loss": 0.4178, + "step": 5712 + }, + { + "epoch": 0.7613272921108742, + "grad_norm": 0.2827976481344236, + "learning_rate": 8.660712900653198e-06, + "loss": 0.4511, + "step": 5713 + }, + { + "epoch": 0.7614605543710021, + "grad_norm": 0.287668644127378, + "learning_rate": 8.66022786733006e-06, + "loss": 0.3946, + "step": 5714 + }, + { + "epoch": 0.76159381663113, + "grad_norm": 0.30314453440249756, + "learning_rate": 8.65974275978068e-06, + "loss": 0.4553, + "step": 5715 + }, + { + "epoch": 0.761727078891258, + "grad_norm": 0.2848883274838985, + "learning_rate": 8.659257578014895e-06, + "loss": 0.3938, + "step": 5716 + }, + { + "epoch": 0.7618603411513859, + "grad_norm": 0.2839954865120156, + "learning_rate": 8.658772322042542e-06, + "loss": 0.4361, + "step": 5717 + }, + { + "epoch": 0.7619936034115139, + "grad_norm": 0.2989476102675714, + "learning_rate": 8.658286991873463e-06, + "loss": 0.4528, + "step": 5718 + }, + { + "epoch": 0.7621268656716418, + "grad_norm": 0.29081209598200014, + "learning_rate": 8.657801587517502e-06, + "loss": 0.4346, + "step": 5719 + }, + { + "epoch": 0.7622601279317697, + "grad_norm": 0.396509296024594, + "learning_rate": 8.657316108984502e-06, + "loss": 0.3953, + "step": 5720 + }, + { + "epoch": 0.7623933901918977, + "grad_norm": 0.2924759149316114, + "learning_rate": 8.656830556284304e-06, + "loss": 0.443, + "step": 5721 + }, + { + "epoch": 0.7625266524520256, + "grad_norm": 0.28925919754145274, + "learning_rate": 8.65634492942676e-06, + "loss": 0.4391, + "step": 5722 + }, + { + "epoch": 0.7626599147121536, + "grad_norm": 0.2858164312556903, + "learning_rate": 8.655859228421715e-06, + "loss": 0.5408, + "step": 5723 + }, + { + "epoch": 0.7627931769722814, + "grad_norm": 0.2918139486298275, + "learning_rate": 8.655373453279019e-06, + "loss": 0.4853, + "step": 5724 + }, + { + "epoch": 0.7629264392324094, + "grad_norm": 0.2880229860055546, + "learning_rate": 8.654887604008522e-06, + "loss": 0.3291, + "step": 5725 + }, + { + "epoch": 0.7630597014925373, + "grad_norm": 0.26514505445724673, + "learning_rate": 8.65440168062008e-06, + "loss": 0.4464, + "step": 5726 + }, + { + "epoch": 0.7631929637526652, + "grad_norm": 0.27587556461364354, + "learning_rate": 8.653915683123544e-06, + "loss": 0.3239, + "step": 5727 + }, + { + "epoch": 0.7633262260127932, + "grad_norm": 0.316543240865332, + "learning_rate": 8.653429611528772e-06, + "loss": 0.4524, + "step": 5728 + }, + { + "epoch": 0.7634594882729211, + "grad_norm": 0.2835457184051772, + "learning_rate": 8.652943465845618e-06, + "loss": 0.4391, + "step": 5729 + }, + { + "epoch": 0.7635927505330491, + "grad_norm": 0.2848465545521516, + "learning_rate": 8.652457246083945e-06, + "loss": 0.3972, + "step": 5730 + }, + { + "epoch": 0.763726012793177, + "grad_norm": 0.28632368602578673, + "learning_rate": 8.651970952253608e-06, + "loss": 0.4672, + "step": 5731 + }, + { + "epoch": 0.7638592750533049, + "grad_norm": 0.400146970959472, + "learning_rate": 8.65148458436447e-06, + "loss": 0.4121, + "step": 5732 + }, + { + "epoch": 0.7639925373134329, + "grad_norm": 0.2834132186301059, + "learning_rate": 8.650998142426398e-06, + "loss": 0.3864, + "step": 5733 + }, + { + "epoch": 0.7641257995735607, + "grad_norm": 0.27139460654909525, + "learning_rate": 8.650511626449254e-06, + "loss": 0.3808, + "step": 5734 + }, + { + "epoch": 0.7642590618336887, + "grad_norm": 0.2958185133183705, + "learning_rate": 8.650025036442903e-06, + "loss": 0.435, + "step": 5735 + }, + { + "epoch": 0.7643923240938166, + "grad_norm": 0.2779488899709842, + "learning_rate": 8.649538372417215e-06, + "loss": 0.3882, + "step": 5736 + }, + { + "epoch": 0.7645255863539445, + "grad_norm": 0.295781063529939, + "learning_rate": 8.649051634382055e-06, + "loss": 0.4166, + "step": 5737 + }, + { + "epoch": 0.7646588486140725, + "grad_norm": 0.30043026052837996, + "learning_rate": 8.648564822347299e-06, + "loss": 0.4003, + "step": 5738 + }, + { + "epoch": 0.7647921108742004, + "grad_norm": 0.2865698828321632, + "learning_rate": 8.648077936322815e-06, + "loss": 0.3627, + "step": 5739 + }, + { + "epoch": 0.7649253731343284, + "grad_norm": 0.2855891971363135, + "learning_rate": 8.647590976318479e-06, + "loss": 0.3758, + "step": 5740 + }, + { + "epoch": 0.7650586353944563, + "grad_norm": 0.29815440229948226, + "learning_rate": 8.647103942344165e-06, + "loss": 0.402, + "step": 5741 + }, + { + "epoch": 0.7651918976545842, + "grad_norm": 0.29856957688815355, + "learning_rate": 8.646616834409749e-06, + "loss": 0.3764, + "step": 5742 + }, + { + "epoch": 0.7653251599147122, + "grad_norm": 0.28701776928600015, + "learning_rate": 8.64612965252511e-06, + "loss": 0.449, + "step": 5743 + }, + { + "epoch": 0.7654584221748401, + "grad_norm": 0.30138665299754025, + "learning_rate": 8.64564239670013e-06, + "loss": 0.3784, + "step": 5744 + }, + { + "epoch": 0.7655916844349681, + "grad_norm": 0.2841164386839325, + "learning_rate": 8.645155066944685e-06, + "loss": 0.3388, + "step": 5745 + }, + { + "epoch": 0.7657249466950959, + "grad_norm": 0.29852555750773363, + "learning_rate": 8.644667663268662e-06, + "loss": 0.4418, + "step": 5746 + }, + { + "epoch": 0.7658582089552238, + "grad_norm": 0.3038498060058671, + "learning_rate": 8.644180185681943e-06, + "loss": 0.3706, + "step": 5747 + }, + { + "epoch": 0.7659914712153518, + "grad_norm": 0.29893651206356125, + "learning_rate": 8.643692634194414e-06, + "loss": 0.4951, + "step": 5748 + }, + { + "epoch": 0.7661247334754797, + "grad_norm": 0.2962801402893498, + "learning_rate": 8.643205008815962e-06, + "loss": 0.4349, + "step": 5749 + }, + { + "epoch": 0.7662579957356077, + "grad_norm": 0.3368719790915191, + "learning_rate": 8.642717309556477e-06, + "loss": 0.4127, + "step": 5750 + }, + { + "epoch": 0.7663912579957356, + "grad_norm": 0.3188659308310971, + "learning_rate": 8.642229536425846e-06, + "loss": 0.4526, + "step": 5751 + }, + { + "epoch": 0.7665245202558635, + "grad_norm": 0.3090127982068144, + "learning_rate": 8.641741689433964e-06, + "loss": 0.4511, + "step": 5752 + }, + { + "epoch": 0.7666577825159915, + "grad_norm": 0.3047471047178376, + "learning_rate": 8.641253768590723e-06, + "loss": 0.4333, + "step": 5753 + }, + { + "epoch": 0.7667910447761194, + "grad_norm": 0.29499027409902023, + "learning_rate": 8.640765773906018e-06, + "loss": 0.4231, + "step": 5754 + }, + { + "epoch": 0.7669243070362474, + "grad_norm": 0.3014640085708351, + "learning_rate": 8.640277705389741e-06, + "loss": 0.4164, + "step": 5755 + }, + { + "epoch": 0.7670575692963753, + "grad_norm": 0.28573788633381036, + "learning_rate": 8.639789563051795e-06, + "loss": 0.3928, + "step": 5756 + }, + { + "epoch": 0.7671908315565032, + "grad_norm": 0.29914416721086184, + "learning_rate": 8.639301346902077e-06, + "loss": 0.4458, + "step": 5757 + }, + { + "epoch": 0.7673240938166311, + "grad_norm": 0.31481544877992146, + "learning_rate": 8.63881305695049e-06, + "loss": 0.3867, + "step": 5758 + }, + { + "epoch": 0.767457356076759, + "grad_norm": 1.74833630668846, + "learning_rate": 8.638324693206931e-06, + "loss": 0.379, + "step": 5759 + }, + { + "epoch": 0.767590618336887, + "grad_norm": 0.32023210173793526, + "learning_rate": 8.637836255681307e-06, + "loss": 0.4386, + "step": 5760 + }, + { + "epoch": 0.7677238805970149, + "grad_norm": 0.32212177725111235, + "learning_rate": 8.637347744383525e-06, + "loss": 0.4355, + "step": 5761 + }, + { + "epoch": 0.7678571428571429, + "grad_norm": 0.33644465826535386, + "learning_rate": 8.636859159323485e-06, + "loss": 0.4512, + "step": 5762 + }, + { + "epoch": 0.7679904051172708, + "grad_norm": 0.30209152604173595, + "learning_rate": 8.636370500511102e-06, + "loss": 0.3445, + "step": 5763 + }, + { + "epoch": 0.7681236673773987, + "grad_norm": 0.3062318432238421, + "learning_rate": 8.635881767956282e-06, + "loss": 0.4817, + "step": 5764 + }, + { + "epoch": 0.7682569296375267, + "grad_norm": 0.31485799816067983, + "learning_rate": 8.635392961668936e-06, + "loss": 0.4679, + "step": 5765 + }, + { + "epoch": 0.7683901918976546, + "grad_norm": 0.34397572258680814, + "learning_rate": 8.634904081658979e-06, + "loss": 0.4102, + "step": 5766 + }, + { + "epoch": 0.7685234541577826, + "grad_norm": 0.3029577263733524, + "learning_rate": 8.634415127936321e-06, + "loss": 0.3599, + "step": 5767 + }, + { + "epoch": 0.7686567164179104, + "grad_norm": 0.3076651029913636, + "learning_rate": 8.633926100510883e-06, + "loss": 0.3875, + "step": 5768 + }, + { + "epoch": 0.7687899786780383, + "grad_norm": 0.3252186032426671, + "learning_rate": 8.633436999392576e-06, + "loss": 0.3908, + "step": 5769 + }, + { + "epoch": 0.7689232409381663, + "grad_norm": 0.28890706292612245, + "learning_rate": 8.632947824591325e-06, + "loss": 0.3814, + "step": 5770 + }, + { + "epoch": 0.7690565031982942, + "grad_norm": 0.30557920413999357, + "learning_rate": 8.632458576117046e-06, + "loss": 0.4828, + "step": 5771 + }, + { + "epoch": 0.7691897654584222, + "grad_norm": 0.3102344206947754, + "learning_rate": 8.63196925397966e-06, + "loss": 0.392, + "step": 5772 + }, + { + "epoch": 0.7693230277185501, + "grad_norm": 0.2951502194661398, + "learning_rate": 8.63147985818909e-06, + "loss": 0.426, + "step": 5773 + }, + { + "epoch": 0.769456289978678, + "grad_norm": 0.30904487405331393, + "learning_rate": 8.630990388755265e-06, + "loss": 0.4499, + "step": 5774 + }, + { + "epoch": 0.769589552238806, + "grad_norm": 0.2810613492442456, + "learning_rate": 8.630500845688104e-06, + "loss": 0.3928, + "step": 5775 + }, + { + "epoch": 0.7697228144989339, + "grad_norm": 0.29432326958117916, + "learning_rate": 8.630011228997541e-06, + "loss": 0.3938, + "step": 5776 + }, + { + "epoch": 0.7698560767590619, + "grad_norm": 0.31183934961014426, + "learning_rate": 8.629521538693502e-06, + "loss": 0.376, + "step": 5777 + }, + { + "epoch": 0.7699893390191898, + "grad_norm": 0.2930461493332897, + "learning_rate": 8.629031774785917e-06, + "loss": 0.4283, + "step": 5778 + }, + { + "epoch": 0.7701226012793176, + "grad_norm": 0.3094314651241573, + "learning_rate": 8.628541937284719e-06, + "loss": 0.3995, + "step": 5779 + }, + { + "epoch": 0.7702558635394456, + "grad_norm": 0.304400893524043, + "learning_rate": 8.62805202619984e-06, + "loss": 0.372, + "step": 5780 + }, + { + "epoch": 0.7703891257995735, + "grad_norm": 0.2976023647320764, + "learning_rate": 8.627562041541218e-06, + "loss": 0.4143, + "step": 5781 + }, + { + "epoch": 0.7705223880597015, + "grad_norm": 0.29974148238131126, + "learning_rate": 8.627071983318786e-06, + "loss": 0.4253, + "step": 5782 + }, + { + "epoch": 0.7706556503198294, + "grad_norm": 0.30304877599718744, + "learning_rate": 8.626581851542486e-06, + "loss": 0.3858, + "step": 5783 + }, + { + "epoch": 0.7707889125799574, + "grad_norm": 0.2823479090614616, + "learning_rate": 8.626091646222253e-06, + "loss": 0.3343, + "step": 5784 + }, + { + "epoch": 0.7709221748400853, + "grad_norm": 0.35942379986960526, + "learning_rate": 8.62560136736803e-06, + "loss": 0.4275, + "step": 5785 + }, + { + "epoch": 0.7710554371002132, + "grad_norm": 0.29502142319622043, + "learning_rate": 8.62511101498976e-06, + "loss": 0.3752, + "step": 5786 + }, + { + "epoch": 0.7711886993603412, + "grad_norm": 0.30152318623155455, + "learning_rate": 8.624620589097388e-06, + "loss": 0.3964, + "step": 5787 + }, + { + "epoch": 0.7713219616204691, + "grad_norm": 0.28819722458514796, + "learning_rate": 8.624130089700855e-06, + "loss": 0.3993, + "step": 5788 + }, + { + "epoch": 0.7714552238805971, + "grad_norm": 0.29524823782685694, + "learning_rate": 8.623639516810112e-06, + "loss": 0.3913, + "step": 5789 + }, + { + "epoch": 0.771588486140725, + "grad_norm": 0.30803168477446063, + "learning_rate": 8.623148870435107e-06, + "loss": 0.4915, + "step": 5790 + }, + { + "epoch": 0.7717217484008528, + "grad_norm": 0.29608501661515596, + "learning_rate": 8.622658150585788e-06, + "loss": 0.3394, + "step": 5791 + }, + { + "epoch": 0.7718550106609808, + "grad_norm": 0.28600999859200266, + "learning_rate": 8.622167357272107e-06, + "loss": 0.3711, + "step": 5792 + }, + { + "epoch": 0.7719882729211087, + "grad_norm": 0.31298888954723236, + "learning_rate": 8.621676490504017e-06, + "loss": 0.4322, + "step": 5793 + }, + { + "epoch": 0.7721215351812367, + "grad_norm": 0.2816651548878782, + "learning_rate": 8.621185550291473e-06, + "loss": 0.3365, + "step": 5794 + }, + { + "epoch": 0.7722547974413646, + "grad_norm": 0.3139133897873522, + "learning_rate": 8.62069453664443e-06, + "loss": 0.4796, + "step": 5795 + }, + { + "epoch": 0.7723880597014925, + "grad_norm": 0.27973087230794974, + "learning_rate": 8.620203449572846e-06, + "loss": 0.447, + "step": 5796 + }, + { + "epoch": 0.7725213219616205, + "grad_norm": 0.28584954027256587, + "learning_rate": 8.61971228908668e-06, + "loss": 0.4384, + "step": 5797 + }, + { + "epoch": 0.7726545842217484, + "grad_norm": 0.2928046879069372, + "learning_rate": 8.61922105519589e-06, + "loss": 0.434, + "step": 5798 + }, + { + "epoch": 0.7727878464818764, + "grad_norm": 0.27042793707055923, + "learning_rate": 8.618729747910442e-06, + "loss": 0.3791, + "step": 5799 + }, + { + "epoch": 0.7729211087420043, + "grad_norm": 0.2971449221868918, + "learning_rate": 8.618238367240295e-06, + "loss": 0.4119, + "step": 5800 + }, + { + "epoch": 0.7730543710021321, + "grad_norm": 0.29935369435386233, + "learning_rate": 8.617746913195417e-06, + "loss": 0.3805, + "step": 5801 + }, + { + "epoch": 0.7731876332622601, + "grad_norm": 0.29043874184477547, + "learning_rate": 8.617255385785772e-06, + "loss": 0.4042, + "step": 5802 + }, + { + "epoch": 0.773320895522388, + "grad_norm": 0.3063581507785727, + "learning_rate": 8.616763785021329e-06, + "loss": 0.4281, + "step": 5803 + }, + { + "epoch": 0.773454157782516, + "grad_norm": 0.2859055617524806, + "learning_rate": 8.616272110912057e-06, + "loss": 0.4781, + "step": 5804 + }, + { + "epoch": 0.7735874200426439, + "grad_norm": 0.28926596481166744, + "learning_rate": 8.615780363467928e-06, + "loss": 0.3964, + "step": 5805 + }, + { + "epoch": 0.7737206823027718, + "grad_norm": 0.29586104150878195, + "learning_rate": 8.61528854269891e-06, + "loss": 0.4554, + "step": 5806 + }, + { + "epoch": 0.7738539445628998, + "grad_norm": 0.3021992961352176, + "learning_rate": 8.614796648614981e-06, + "loss": 0.3738, + "step": 5807 + }, + { + "epoch": 0.7739872068230277, + "grad_norm": 0.288792939820102, + "learning_rate": 8.614304681226115e-06, + "loss": 0.4439, + "step": 5808 + }, + { + "epoch": 0.7741204690831557, + "grad_norm": 0.30470345153664385, + "learning_rate": 8.613812640542288e-06, + "loss": 0.402, + "step": 5809 + }, + { + "epoch": 0.7742537313432836, + "grad_norm": 0.2871688339168724, + "learning_rate": 8.613320526573479e-06, + "loss": 0.3704, + "step": 5810 + }, + { + "epoch": 0.7743869936034116, + "grad_norm": 0.3000129109803862, + "learning_rate": 8.612828339329667e-06, + "loss": 0.4013, + "step": 5811 + }, + { + "epoch": 0.7745202558635395, + "grad_norm": 0.2829787950818607, + "learning_rate": 8.612336078820833e-06, + "loss": 0.3736, + "step": 5812 + }, + { + "epoch": 0.7746535181236673, + "grad_norm": 0.3130811683013629, + "learning_rate": 8.61184374505696e-06, + "loss": 0.4252, + "step": 5813 + }, + { + "epoch": 0.7747867803837953, + "grad_norm": 0.2935568193557736, + "learning_rate": 8.611351338048033e-06, + "loss": 0.44, + "step": 5814 + }, + { + "epoch": 0.7749200426439232, + "grad_norm": 0.29921270753712387, + "learning_rate": 8.610858857804036e-06, + "loss": 0.4483, + "step": 5815 + }, + { + "epoch": 0.7750533049040512, + "grad_norm": 0.29101226142468417, + "learning_rate": 8.610366304334957e-06, + "loss": 0.3744, + "step": 5816 + }, + { + "epoch": 0.7751865671641791, + "grad_norm": 0.3032746121038978, + "learning_rate": 8.609873677650784e-06, + "loss": 0.4042, + "step": 5817 + }, + { + "epoch": 0.775319829424307, + "grad_norm": 0.28462473720135006, + "learning_rate": 8.609380977761508e-06, + "loss": 0.4063, + "step": 5818 + }, + { + "epoch": 0.775453091684435, + "grad_norm": 0.2892224396505486, + "learning_rate": 8.60888820467712e-06, + "loss": 0.4103, + "step": 5819 + }, + { + "epoch": 0.7755863539445629, + "grad_norm": 0.3247152738194831, + "learning_rate": 8.60839535840761e-06, + "loss": 0.4703, + "step": 5820 + }, + { + "epoch": 0.7757196162046909, + "grad_norm": 0.27776744851402874, + "learning_rate": 8.607902438962978e-06, + "loss": 0.3644, + "step": 5821 + }, + { + "epoch": 0.7758528784648188, + "grad_norm": 0.282048117580801, + "learning_rate": 8.607409446353217e-06, + "loss": 0.3903, + "step": 5822 + }, + { + "epoch": 0.7759861407249466, + "grad_norm": 0.2958978458903089, + "learning_rate": 8.606916380588323e-06, + "loss": 0.3779, + "step": 5823 + }, + { + "epoch": 0.7761194029850746, + "grad_norm": 0.29414677581141385, + "learning_rate": 8.6064232416783e-06, + "loss": 0.3195, + "step": 5824 + }, + { + "epoch": 0.7762526652452025, + "grad_norm": 0.293528554641161, + "learning_rate": 8.605930029633143e-06, + "loss": 0.3975, + "step": 5825 + }, + { + "epoch": 0.7763859275053305, + "grad_norm": 0.2933330011345483, + "learning_rate": 8.605436744462855e-06, + "loss": 0.3733, + "step": 5826 + }, + { + "epoch": 0.7765191897654584, + "grad_norm": 0.30481579264590947, + "learning_rate": 8.604943386177444e-06, + "loss": 0.4662, + "step": 5827 + }, + { + "epoch": 0.7766524520255863, + "grad_norm": 0.29370534308404717, + "learning_rate": 8.604449954786908e-06, + "loss": 0.3886, + "step": 5828 + }, + { + "epoch": 0.7767857142857143, + "grad_norm": 0.28429081025582287, + "learning_rate": 8.603956450301259e-06, + "loss": 0.3817, + "step": 5829 + }, + { + "epoch": 0.7769189765458422, + "grad_norm": 0.3130418335967956, + "learning_rate": 8.603462872730501e-06, + "loss": 0.4193, + "step": 5830 + }, + { + "epoch": 0.7770522388059702, + "grad_norm": 0.2928927590648936, + "learning_rate": 8.602969222084647e-06, + "loss": 0.4734, + "step": 5831 + }, + { + "epoch": 0.7771855010660981, + "grad_norm": 0.27946627173376026, + "learning_rate": 8.602475498373704e-06, + "loss": 0.4246, + "step": 5832 + }, + { + "epoch": 0.777318763326226, + "grad_norm": 0.29496865808992623, + "learning_rate": 8.601981701607685e-06, + "loss": 0.3905, + "step": 5833 + }, + { + "epoch": 0.777452025586354, + "grad_norm": 0.28319710533830017, + "learning_rate": 8.601487831796607e-06, + "loss": 0.4748, + "step": 5834 + }, + { + "epoch": 0.7775852878464818, + "grad_norm": 0.2955854607227631, + "learning_rate": 8.60099388895048e-06, + "loss": 0.4298, + "step": 5835 + }, + { + "epoch": 0.7777185501066098, + "grad_norm": 0.28459651524156, + "learning_rate": 8.600499873079326e-06, + "loss": 0.4288, + "step": 5836 + }, + { + "epoch": 0.7778518123667377, + "grad_norm": 0.2968870383857437, + "learning_rate": 8.600005784193161e-06, + "loss": 0.4225, + "step": 5837 + }, + { + "epoch": 0.7779850746268657, + "grad_norm": 0.2892066127914351, + "learning_rate": 8.599511622302004e-06, + "loss": 0.3734, + "step": 5838 + }, + { + "epoch": 0.7781183368869936, + "grad_norm": 0.29522243228660894, + "learning_rate": 8.599017387415879e-06, + "loss": 0.4942, + "step": 5839 + }, + { + "epoch": 0.7782515991471215, + "grad_norm": 0.292560604475214, + "learning_rate": 8.598523079544803e-06, + "loss": 0.4463, + "step": 5840 + }, + { + "epoch": 0.7783848614072495, + "grad_norm": 0.27820861578845807, + "learning_rate": 8.598028698698804e-06, + "loss": 0.343, + "step": 5841 + }, + { + "epoch": 0.7785181236673774, + "grad_norm": 0.3012507246629109, + "learning_rate": 8.597534244887908e-06, + "loss": 0.4422, + "step": 5842 + }, + { + "epoch": 0.7786513859275054, + "grad_norm": 0.28358562450292374, + "learning_rate": 8.597039718122142e-06, + "loss": 0.3854, + "step": 5843 + }, + { + "epoch": 0.7787846481876333, + "grad_norm": 0.303780681738846, + "learning_rate": 8.596545118411535e-06, + "loss": 0.4394, + "step": 5844 + }, + { + "epoch": 0.7789179104477612, + "grad_norm": 0.30222238348509023, + "learning_rate": 8.596050445766114e-06, + "loss": 0.4428, + "step": 5845 + }, + { + "epoch": 0.7790511727078892, + "grad_norm": 0.2956526216276988, + "learning_rate": 8.595555700195913e-06, + "loss": 0.3985, + "step": 5846 + }, + { + "epoch": 0.779184434968017, + "grad_norm": 0.29724885090593084, + "learning_rate": 8.595060881710963e-06, + "loss": 0.5285, + "step": 5847 + }, + { + "epoch": 0.779317697228145, + "grad_norm": 0.27685361778602197, + "learning_rate": 8.594565990321301e-06, + "loss": 0.361, + "step": 5848 + }, + { + "epoch": 0.7794509594882729, + "grad_norm": 0.3116721962827333, + "learning_rate": 8.594071026036961e-06, + "loss": 0.358, + "step": 5849 + }, + { + "epoch": 0.7795842217484008, + "grad_norm": 0.2938073809200767, + "learning_rate": 8.593575988867984e-06, + "loss": 0.4351, + "step": 5850 + }, + { + "epoch": 0.7797174840085288, + "grad_norm": 0.3001271087169402, + "learning_rate": 8.593080878824404e-06, + "loss": 0.492, + "step": 5851 + }, + { + "epoch": 0.7798507462686567, + "grad_norm": 0.30074554795716185, + "learning_rate": 8.592585695916264e-06, + "loss": 0.4273, + "step": 5852 + }, + { + "epoch": 0.7799840085287847, + "grad_norm": 0.29767318843916357, + "learning_rate": 8.592090440153606e-06, + "loss": 0.381, + "step": 5853 + }, + { + "epoch": 0.7801172707889126, + "grad_norm": 0.2993215769367902, + "learning_rate": 8.591595111546474e-06, + "loss": 0.4924, + "step": 5854 + }, + { + "epoch": 0.7802505330490405, + "grad_norm": 0.31451839671342446, + "learning_rate": 8.591099710104912e-06, + "loss": 0.4218, + "step": 5855 + }, + { + "epoch": 0.7803837953091685, + "grad_norm": 0.3024835473631723, + "learning_rate": 8.590604235838965e-06, + "loss": 0.4048, + "step": 5856 + }, + { + "epoch": 0.7805170575692963, + "grad_norm": 0.2895079674485717, + "learning_rate": 8.590108688758681e-06, + "loss": 0.3745, + "step": 5857 + }, + { + "epoch": 0.7806503198294243, + "grad_norm": 0.2869964556679277, + "learning_rate": 8.58961306887411e-06, + "loss": 0.4476, + "step": 5858 + }, + { + "epoch": 0.7807835820895522, + "grad_norm": 0.2817746019570452, + "learning_rate": 8.589117376195305e-06, + "loss": 0.4079, + "step": 5859 + }, + { + "epoch": 0.7809168443496801, + "grad_norm": 0.3071810482947524, + "learning_rate": 8.588621610732314e-06, + "loss": 0.4541, + "step": 5860 + }, + { + "epoch": 0.7810501066098081, + "grad_norm": 0.2753717530465785, + "learning_rate": 8.588125772495193e-06, + "loss": 0.34, + "step": 5861 + }, + { + "epoch": 0.781183368869936, + "grad_norm": 0.2842615424910386, + "learning_rate": 8.587629861493998e-06, + "loss": 0.4184, + "step": 5862 + }, + { + "epoch": 0.781316631130064, + "grad_norm": 0.2898505568458919, + "learning_rate": 8.587133877738784e-06, + "loss": 0.4217, + "step": 5863 + }, + { + "epoch": 0.7814498933901919, + "grad_norm": 0.29095050277906387, + "learning_rate": 8.58663782123961e-06, + "loss": 0.3865, + "step": 5864 + }, + { + "epoch": 0.7815831556503199, + "grad_norm": 0.29747468359522855, + "learning_rate": 8.586141692006534e-06, + "loss": 0.3746, + "step": 5865 + }, + { + "epoch": 0.7817164179104478, + "grad_norm": 0.2824130336083889, + "learning_rate": 8.585645490049622e-06, + "loss": 0.4463, + "step": 5866 + }, + { + "epoch": 0.7818496801705757, + "grad_norm": 0.28549106857815215, + "learning_rate": 8.58514921537893e-06, + "loss": 0.416, + "step": 5867 + }, + { + "epoch": 0.7819829424307037, + "grad_norm": 0.30590585351987426, + "learning_rate": 8.584652868004524e-06, + "loss": 0.4312, + "step": 5868 + }, + { + "epoch": 0.7821162046908315, + "grad_norm": 0.30312539456740434, + "learning_rate": 8.584156447936472e-06, + "loss": 0.3766, + "step": 5869 + }, + { + "epoch": 0.7822494669509595, + "grad_norm": 0.28127112226055195, + "learning_rate": 8.583659955184838e-06, + "loss": 0.3405, + "step": 5870 + }, + { + "epoch": 0.7823827292110874, + "grad_norm": 0.2768491192028654, + "learning_rate": 8.583163389759695e-06, + "loss": 0.35, + "step": 5871 + }, + { + "epoch": 0.7825159914712153, + "grad_norm": 0.29412209876150475, + "learning_rate": 8.582666751671107e-06, + "loss": 0.3527, + "step": 5872 + }, + { + "epoch": 0.7826492537313433, + "grad_norm": 0.2808141049578202, + "learning_rate": 8.582170040929149e-06, + "loss": 0.3871, + "step": 5873 + }, + { + "epoch": 0.7827825159914712, + "grad_norm": 0.29462158331560734, + "learning_rate": 8.581673257543894e-06, + "loss": 0.4005, + "step": 5874 + }, + { + "epoch": 0.7829157782515992, + "grad_norm": 0.27927775124835974, + "learning_rate": 8.581176401525414e-06, + "loss": 0.3648, + "step": 5875 + }, + { + "epoch": 0.7830490405117271, + "grad_norm": 0.28422082463280895, + "learning_rate": 8.580679472883786e-06, + "loss": 0.3617, + "step": 5876 + }, + { + "epoch": 0.783182302771855, + "grad_norm": 0.2939140427608309, + "learning_rate": 8.580182471629089e-06, + "loss": 0.4551, + "step": 5877 + }, + { + "epoch": 0.783315565031983, + "grad_norm": 0.3035016326798621, + "learning_rate": 8.579685397771398e-06, + "loss": 0.4545, + "step": 5878 + }, + { + "epoch": 0.7834488272921108, + "grad_norm": 0.2945987235832751, + "learning_rate": 8.579188251320797e-06, + "loss": 0.3994, + "step": 5879 + }, + { + "epoch": 0.7835820895522388, + "grad_norm": 0.30206543388303064, + "learning_rate": 8.578691032287365e-06, + "loss": 0.4384, + "step": 5880 + }, + { + "epoch": 0.7837153518123667, + "grad_norm": 0.2878707741521098, + "learning_rate": 8.578193740681187e-06, + "loss": 0.4365, + "step": 5881 + }, + { + "epoch": 0.7838486140724946, + "grad_norm": 0.29880316193410605, + "learning_rate": 8.577696376512347e-06, + "loss": 0.411, + "step": 5882 + }, + { + "epoch": 0.7839818763326226, + "grad_norm": 0.31858664573707374, + "learning_rate": 8.577198939790932e-06, + "loss": 0.4618, + "step": 5883 + }, + { + "epoch": 0.7841151385927505, + "grad_norm": 0.2786369276986239, + "learning_rate": 8.576701430527028e-06, + "loss": 0.3548, + "step": 5884 + }, + { + "epoch": 0.7842484008528785, + "grad_norm": 0.29242421510040245, + "learning_rate": 8.576203848730724e-06, + "loss": 0.365, + "step": 5885 + }, + { + "epoch": 0.7843816631130064, + "grad_norm": 0.28962784120378515, + "learning_rate": 8.57570619441211e-06, + "loss": 0.3846, + "step": 5886 + }, + { + "epoch": 0.7845149253731343, + "grad_norm": 0.28681886095362563, + "learning_rate": 8.575208467581281e-06, + "loss": 0.3928, + "step": 5887 + }, + { + "epoch": 0.7846481876332623, + "grad_norm": 0.27321357656491313, + "learning_rate": 8.57471066824833e-06, + "loss": 0.3921, + "step": 5888 + }, + { + "epoch": 0.7847814498933902, + "grad_norm": 0.29189003509514166, + "learning_rate": 8.574212796423348e-06, + "loss": 0.4088, + "step": 5889 + }, + { + "epoch": 0.7849147121535182, + "grad_norm": 0.29894725202672096, + "learning_rate": 8.573714852116435e-06, + "loss": 0.393, + "step": 5890 + }, + { + "epoch": 0.785047974413646, + "grad_norm": 0.29453588021468075, + "learning_rate": 8.573216835337687e-06, + "loss": 0.3857, + "step": 5891 + }, + { + "epoch": 0.785181236673774, + "grad_norm": 0.2823542892501614, + "learning_rate": 8.572718746097206e-06, + "loss": 0.3607, + "step": 5892 + }, + { + "epoch": 0.7853144989339019, + "grad_norm": 0.2763941529871003, + "learning_rate": 8.572220584405092e-06, + "loss": 0.4282, + "step": 5893 + }, + { + "epoch": 0.7854477611940298, + "grad_norm": 0.30051044648887204, + "learning_rate": 8.571722350271442e-06, + "loss": 0.3769, + "step": 5894 + }, + { + "epoch": 0.7855810234541578, + "grad_norm": 0.27901483142318684, + "learning_rate": 8.571224043706367e-06, + "loss": 0.3697, + "step": 5895 + }, + { + "epoch": 0.7857142857142857, + "grad_norm": 0.2868876643946153, + "learning_rate": 8.57072566471997e-06, + "loss": 0.4642, + "step": 5896 + }, + { + "epoch": 0.7858475479744137, + "grad_norm": 0.3025283058767266, + "learning_rate": 8.570227213322356e-06, + "loss": 0.3866, + "step": 5897 + }, + { + "epoch": 0.7859808102345416, + "grad_norm": 0.2852682841646312, + "learning_rate": 8.569728689523635e-06, + "loss": 0.4095, + "step": 5898 + }, + { + "epoch": 0.7861140724946695, + "grad_norm": 0.3031514524212606, + "learning_rate": 8.569230093333915e-06, + "loss": 0.419, + "step": 5899 + }, + { + "epoch": 0.7862473347547975, + "grad_norm": 0.3289993578961353, + "learning_rate": 8.568731424763307e-06, + "loss": 0.4504, + "step": 5900 + }, + { + "epoch": 0.7863805970149254, + "grad_norm": 0.2955975817711201, + "learning_rate": 8.568232683821927e-06, + "loss": 0.3525, + "step": 5901 + }, + { + "epoch": 0.7865138592750534, + "grad_norm": 0.3021313465896159, + "learning_rate": 8.567733870519883e-06, + "loss": 0.4702, + "step": 5902 + }, + { + "epoch": 0.7866471215351812, + "grad_norm": 0.30141706111919736, + "learning_rate": 8.567234984867298e-06, + "loss": 0.4305, + "step": 5903 + }, + { + "epoch": 0.7867803837953091, + "grad_norm": 0.31467284385106614, + "learning_rate": 8.566736026874283e-06, + "loss": 0.4177, + "step": 5904 + }, + { + "epoch": 0.7869136460554371, + "grad_norm": 0.2748687740882475, + "learning_rate": 8.566236996550957e-06, + "loss": 0.3682, + "step": 5905 + }, + { + "epoch": 0.787046908315565, + "grad_norm": 0.29981009237255346, + "learning_rate": 8.565737893907443e-06, + "loss": 0.4166, + "step": 5906 + }, + { + "epoch": 0.787180170575693, + "grad_norm": 0.3185321664213318, + "learning_rate": 8.56523871895386e-06, + "loss": 0.3741, + "step": 5907 + }, + { + "epoch": 0.7873134328358209, + "grad_norm": 0.2851237296677824, + "learning_rate": 8.564739471700334e-06, + "loss": 0.3804, + "step": 5908 + }, + { + "epoch": 0.7874466950959488, + "grad_norm": 0.2890885483055719, + "learning_rate": 8.564240152156983e-06, + "loss": 0.4279, + "step": 5909 + }, + { + "epoch": 0.7875799573560768, + "grad_norm": 0.2965047940600119, + "learning_rate": 8.56374076033394e-06, + "loss": 0.4051, + "step": 5910 + }, + { + "epoch": 0.7877132196162047, + "grad_norm": 0.300755875773267, + "learning_rate": 8.563241296241327e-06, + "loss": 0.4236, + "step": 5911 + }, + { + "epoch": 0.7878464818763327, + "grad_norm": 0.31618008289966176, + "learning_rate": 8.562741759889275e-06, + "loss": 0.4357, + "step": 5912 + }, + { + "epoch": 0.7879797441364605, + "grad_norm": 0.31422399793762046, + "learning_rate": 8.562242151287913e-06, + "loss": 0.3501, + "step": 5913 + }, + { + "epoch": 0.7881130063965884, + "grad_norm": 0.2939252104291399, + "learning_rate": 8.561742470447374e-06, + "loss": 0.3978, + "step": 5914 + }, + { + "epoch": 0.7882462686567164, + "grad_norm": 0.31153392608403313, + "learning_rate": 8.561242717377789e-06, + "loss": 0.3926, + "step": 5915 + }, + { + "epoch": 0.7883795309168443, + "grad_norm": 0.2970805607319262, + "learning_rate": 8.560742892089295e-06, + "loss": 0.4647, + "step": 5916 + }, + { + "epoch": 0.7885127931769723, + "grad_norm": 0.32078896510011934, + "learning_rate": 8.560242994592027e-06, + "loss": 0.4123, + "step": 5917 + }, + { + "epoch": 0.7886460554371002, + "grad_norm": 0.298164511624333, + "learning_rate": 8.559743024896123e-06, + "loss": 0.3242, + "step": 5918 + }, + { + "epoch": 0.7887793176972282, + "grad_norm": 0.27315561943933997, + "learning_rate": 8.559242983011721e-06, + "loss": 0.3283, + "step": 5919 + }, + { + "epoch": 0.7889125799573561, + "grad_norm": 0.2945346353791465, + "learning_rate": 8.558742868948962e-06, + "loss": 0.3856, + "step": 5920 + }, + { + "epoch": 0.789045842217484, + "grad_norm": 0.3109714314982451, + "learning_rate": 8.558242682717988e-06, + "loss": 0.4978, + "step": 5921 + }, + { + "epoch": 0.789179104477612, + "grad_norm": 0.2793398684203144, + "learning_rate": 8.55774242432894e-06, + "loss": 0.4417, + "step": 5922 + }, + { + "epoch": 0.7893123667377399, + "grad_norm": 0.2953848520175421, + "learning_rate": 8.557242093791968e-06, + "loss": 0.432, + "step": 5923 + }, + { + "epoch": 0.7894456289978679, + "grad_norm": 0.2829802441629665, + "learning_rate": 8.556741691117214e-06, + "loss": 0.3541, + "step": 5924 + }, + { + "epoch": 0.7895788912579957, + "grad_norm": 0.30958868304027903, + "learning_rate": 8.556241216314827e-06, + "loss": 0.4638, + "step": 5925 + }, + { + "epoch": 0.7897121535181236, + "grad_norm": 0.3096627750071306, + "learning_rate": 8.555740669394954e-06, + "loss": 0.4013, + "step": 5926 + }, + { + "epoch": 0.7898454157782516, + "grad_norm": 0.3014267381425478, + "learning_rate": 8.55524005036775e-06, + "loss": 0.3712, + "step": 5927 + }, + { + "epoch": 0.7899786780383795, + "grad_norm": 0.30994761033629836, + "learning_rate": 8.554739359243364e-06, + "loss": 0.4268, + "step": 5928 + }, + { + "epoch": 0.7901119402985075, + "grad_norm": 0.315546400306692, + "learning_rate": 8.554238596031951e-06, + "loss": 0.4703, + "step": 5929 + }, + { + "epoch": 0.7902452025586354, + "grad_norm": 0.3006044581443457, + "learning_rate": 8.553737760743665e-06, + "loss": 0.3648, + "step": 5930 + }, + { + "epoch": 0.7903784648187633, + "grad_norm": 0.3147058144109173, + "learning_rate": 8.553236853388662e-06, + "loss": 0.4123, + "step": 5931 + }, + { + "epoch": 0.7905117270788913, + "grad_norm": 0.29759299747427725, + "learning_rate": 8.552735873977102e-06, + "loss": 0.3784, + "step": 5932 + }, + { + "epoch": 0.7906449893390192, + "grad_norm": 0.3123919687905491, + "learning_rate": 8.552234822519143e-06, + "loss": 0.4657, + "step": 5933 + }, + { + "epoch": 0.7907782515991472, + "grad_norm": 0.3004276702136384, + "learning_rate": 8.551733699024948e-06, + "loss": 0.4139, + "step": 5934 + }, + { + "epoch": 0.790911513859275, + "grad_norm": 0.3018741496628442, + "learning_rate": 8.551232503504676e-06, + "loss": 0.3922, + "step": 5935 + }, + { + "epoch": 0.7910447761194029, + "grad_norm": 0.33224548111307156, + "learning_rate": 8.550731235968492e-06, + "loss": 0.4481, + "step": 5936 + }, + { + "epoch": 0.7911780383795309, + "grad_norm": 0.2989443060870029, + "learning_rate": 8.550229896426563e-06, + "loss": 0.4036, + "step": 5937 + }, + { + "epoch": 0.7913113006396588, + "grad_norm": 0.2900851566199714, + "learning_rate": 8.549728484889053e-06, + "loss": 0.3478, + "step": 5938 + }, + { + "epoch": 0.7914445628997868, + "grad_norm": 0.30672452069648526, + "learning_rate": 8.549227001366132e-06, + "loss": 0.4314, + "step": 5939 + }, + { + "epoch": 0.7915778251599147, + "grad_norm": 0.306053196397504, + "learning_rate": 8.54872544586797e-06, + "loss": 0.4112, + "step": 5940 + }, + { + "epoch": 0.7917110874200426, + "grad_norm": 0.3052896820401719, + "learning_rate": 8.548223818404736e-06, + "loss": 0.4294, + "step": 5941 + }, + { + "epoch": 0.7918443496801706, + "grad_norm": 0.29545817240714395, + "learning_rate": 8.547722118986606e-06, + "loss": 0.3761, + "step": 5942 + }, + { + "epoch": 0.7919776119402985, + "grad_norm": 0.32870404795752417, + "learning_rate": 8.547220347623751e-06, + "loss": 0.3813, + "step": 5943 + }, + { + "epoch": 0.7921108742004265, + "grad_norm": 0.28313951773183044, + "learning_rate": 8.546718504326347e-06, + "loss": 0.3886, + "step": 5944 + }, + { + "epoch": 0.7922441364605544, + "grad_norm": 0.30177321696773496, + "learning_rate": 8.546216589104573e-06, + "loss": 0.4415, + "step": 5945 + }, + { + "epoch": 0.7923773987206824, + "grad_norm": 0.30171898552791687, + "learning_rate": 8.545714601968603e-06, + "loss": 0.4264, + "step": 5946 + }, + { + "epoch": 0.7925106609808102, + "grad_norm": 0.3011695889277406, + "learning_rate": 8.54521254292862e-06, + "loss": 0.3642, + "step": 5947 + }, + { + "epoch": 0.7926439232409381, + "grad_norm": 0.30583542403099484, + "learning_rate": 8.544710411994808e-06, + "loss": 0.4844, + "step": 5948 + }, + { + "epoch": 0.7927771855010661, + "grad_norm": 0.27846173932218743, + "learning_rate": 8.544208209177345e-06, + "loss": 0.3932, + "step": 5949 + }, + { + "epoch": 0.792910447761194, + "grad_norm": 0.30481555183719217, + "learning_rate": 8.543705934486415e-06, + "loss": 0.3676, + "step": 5950 + }, + { + "epoch": 0.793043710021322, + "grad_norm": 0.3073163255806777, + "learning_rate": 8.543203587932209e-06, + "loss": 0.4216, + "step": 5951 + }, + { + "epoch": 0.7931769722814499, + "grad_norm": 0.31422931066204435, + "learning_rate": 8.54270116952491e-06, + "loss": 0.5388, + "step": 5952 + }, + { + "epoch": 0.7933102345415778, + "grad_norm": 0.2919671479965594, + "learning_rate": 8.542198679274706e-06, + "loss": 0.3662, + "step": 5953 + }, + { + "epoch": 0.7934434968017058, + "grad_norm": 0.29825221288890963, + "learning_rate": 8.54169611719179e-06, + "loss": 0.4146, + "step": 5954 + }, + { + "epoch": 0.7935767590618337, + "grad_norm": 0.30044569875442917, + "learning_rate": 8.54119348328635e-06, + "loss": 0.4358, + "step": 5955 + }, + { + "epoch": 0.7937100213219617, + "grad_norm": 0.2913148404243087, + "learning_rate": 8.540690777568584e-06, + "loss": 0.3809, + "step": 5956 + }, + { + "epoch": 0.7938432835820896, + "grad_norm": 0.28526962489487695, + "learning_rate": 8.540188000048681e-06, + "loss": 0.4085, + "step": 5957 + }, + { + "epoch": 0.7939765458422174, + "grad_norm": 0.29418110158265887, + "learning_rate": 8.539685150736841e-06, + "loss": 0.4045, + "step": 5958 + }, + { + "epoch": 0.7941098081023454, + "grad_norm": 0.2926181914870645, + "learning_rate": 8.539182229643258e-06, + "loss": 0.4461, + "step": 5959 + }, + { + "epoch": 0.7942430703624733, + "grad_norm": 0.2881306222346603, + "learning_rate": 8.538679236778134e-06, + "loss": 0.4367, + "step": 5960 + }, + { + "epoch": 0.7943763326226013, + "grad_norm": 0.295821960921986, + "learning_rate": 8.538176172151666e-06, + "loss": 0.3877, + "step": 5961 + }, + { + "epoch": 0.7945095948827292, + "grad_norm": 0.2995154315198624, + "learning_rate": 8.53767303577406e-06, + "loss": 0.4694, + "step": 5962 + }, + { + "epoch": 0.7946428571428571, + "grad_norm": 6.209013914793114, + "learning_rate": 8.537169827655516e-06, + "loss": 0.4106, + "step": 5963 + }, + { + "epoch": 0.7947761194029851, + "grad_norm": 0.3210461457402983, + "learning_rate": 8.536666547806239e-06, + "loss": 0.4438, + "step": 5964 + }, + { + "epoch": 0.794909381663113, + "grad_norm": 0.2827177337762957, + "learning_rate": 8.536163196236433e-06, + "loss": 0.4262, + "step": 5965 + }, + { + "epoch": 0.795042643923241, + "grad_norm": 0.2796410735065964, + "learning_rate": 8.53565977295631e-06, + "loss": 0.3529, + "step": 5966 + }, + { + "epoch": 0.7951759061833689, + "grad_norm": 0.27995084558087785, + "learning_rate": 8.535156277976078e-06, + "loss": 0.3539, + "step": 5967 + }, + { + "epoch": 0.7953091684434968, + "grad_norm": 0.29702583434221985, + "learning_rate": 8.534652711305945e-06, + "loss": 0.4186, + "step": 5968 + }, + { + "epoch": 0.7954424307036247, + "grad_norm": 0.3110161998301323, + "learning_rate": 8.534149072956124e-06, + "loss": 0.3769, + "step": 5969 + }, + { + "epoch": 0.7955756929637526, + "grad_norm": 0.27470346141384205, + "learning_rate": 8.533645362936829e-06, + "loss": 0.3448, + "step": 5970 + }, + { + "epoch": 0.7957089552238806, + "grad_norm": 0.2903713652009486, + "learning_rate": 8.533141581258273e-06, + "loss": 0.4508, + "step": 5971 + }, + { + "epoch": 0.7958422174840085, + "grad_norm": 0.30712731880004934, + "learning_rate": 8.532637727930675e-06, + "loss": 0.4087, + "step": 5972 + }, + { + "epoch": 0.7959754797441365, + "grad_norm": 0.3046621230285037, + "learning_rate": 8.53213380296425e-06, + "loss": 0.3881, + "step": 5973 + }, + { + "epoch": 0.7961087420042644, + "grad_norm": 0.30240954531269315, + "learning_rate": 8.531629806369219e-06, + "loss": 0.4262, + "step": 5974 + }, + { + "epoch": 0.7962420042643923, + "grad_norm": 0.4120141504591388, + "learning_rate": 8.531125738155804e-06, + "loss": 0.4056, + "step": 5975 + }, + { + "epoch": 0.7963752665245203, + "grad_norm": 0.33040479107129, + "learning_rate": 8.530621598334223e-06, + "loss": 0.451, + "step": 5976 + }, + { + "epoch": 0.7965085287846482, + "grad_norm": 0.26632285335383543, + "learning_rate": 8.530117386914702e-06, + "loss": 0.3329, + "step": 5977 + }, + { + "epoch": 0.7966417910447762, + "grad_norm": 0.31351610917305706, + "learning_rate": 8.529613103907467e-06, + "loss": 0.3381, + "step": 5978 + }, + { + "epoch": 0.7967750533049041, + "grad_norm": 0.3597790735292226, + "learning_rate": 8.529108749322743e-06, + "loss": 0.4377, + "step": 5979 + }, + { + "epoch": 0.7969083155650319, + "grad_norm": 0.29081323071060233, + "learning_rate": 8.528604323170756e-06, + "loss": 0.3668, + "step": 5980 + }, + { + "epoch": 0.7970415778251599, + "grad_norm": 0.2917276318932773, + "learning_rate": 8.528099825461738e-06, + "loss": 0.484, + "step": 5981 + }, + { + "epoch": 0.7971748400852878, + "grad_norm": 0.36483520659771373, + "learning_rate": 8.52759525620592e-06, + "loss": 0.3826, + "step": 5982 + }, + { + "epoch": 0.7973081023454158, + "grad_norm": 0.2920308047106725, + "learning_rate": 8.527090615413532e-06, + "loss": 0.4612, + "step": 5983 + }, + { + "epoch": 0.7974413646055437, + "grad_norm": 0.2939359896203875, + "learning_rate": 8.52658590309481e-06, + "loss": 0.4424, + "step": 5984 + }, + { + "epoch": 0.7975746268656716, + "grad_norm": 0.3028165484870629, + "learning_rate": 8.526081119259989e-06, + "loss": 0.5288, + "step": 5985 + }, + { + "epoch": 0.7977078891257996, + "grad_norm": 0.29422810528262444, + "learning_rate": 8.525576263919301e-06, + "loss": 0.3837, + "step": 5986 + }, + { + "epoch": 0.7978411513859275, + "grad_norm": 0.3028377075873604, + "learning_rate": 8.52507133708299e-06, + "loss": 0.5089, + "step": 5987 + }, + { + "epoch": 0.7979744136460555, + "grad_norm": 0.2837420421281917, + "learning_rate": 8.524566338761295e-06, + "loss": 0.4086, + "step": 5988 + }, + { + "epoch": 0.7981076759061834, + "grad_norm": 0.2849000133842295, + "learning_rate": 8.524061268964452e-06, + "loss": 0.412, + "step": 5989 + }, + { + "epoch": 0.7982409381663113, + "grad_norm": 0.2880183091863341, + "learning_rate": 8.523556127702708e-06, + "loss": 0.4548, + "step": 5990 + }, + { + "epoch": 0.7983742004264393, + "grad_norm": 0.294958670622799, + "learning_rate": 8.523050914986306e-06, + "loss": 0.373, + "step": 5991 + }, + { + "epoch": 0.7985074626865671, + "grad_norm": 0.2846038234824071, + "learning_rate": 8.522545630825487e-06, + "loss": 0.3641, + "step": 5992 + }, + { + "epoch": 0.7986407249466951, + "grad_norm": 0.30780826054102106, + "learning_rate": 8.522040275230505e-06, + "loss": 0.4149, + "step": 5993 + }, + { + "epoch": 0.798773987206823, + "grad_norm": 0.3144528887325615, + "learning_rate": 8.521534848211603e-06, + "loss": 0.5145, + "step": 5994 + }, + { + "epoch": 0.7989072494669509, + "grad_norm": 0.287911791967244, + "learning_rate": 8.521029349779031e-06, + "loss": 0.4014, + "step": 5995 + }, + { + "epoch": 0.7990405117270789, + "grad_norm": 0.29892471445998353, + "learning_rate": 8.520523779943044e-06, + "loss": 0.3985, + "step": 5996 + }, + { + "epoch": 0.7991737739872068, + "grad_norm": 0.27865308131729494, + "learning_rate": 8.52001813871389e-06, + "loss": 0.4133, + "step": 5997 + }, + { + "epoch": 0.7993070362473348, + "grad_norm": 0.27200665955838477, + "learning_rate": 8.519512426101823e-06, + "loss": 0.3218, + "step": 5998 + }, + { + "epoch": 0.7994402985074627, + "grad_norm": 0.2915451390805236, + "learning_rate": 8.519006642117103e-06, + "loss": 0.4606, + "step": 5999 + }, + { + "epoch": 0.7995735607675906, + "grad_norm": 0.28883387469313715, + "learning_rate": 8.518500786769983e-06, + "loss": 0.4844, + "step": 6000 + } + ], + "logging_steps": 1, + "max_steps": 22512, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 9436580020224000.0, + "train_batch_size": 3, + "trial_name": null, + "trial_params": null +}