{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 4.0, "eval_steps": 500, "global_step": 1004, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00796812749003984, "grad_norm": 1.2741408348083496, "learning_rate": 3.921568627450981e-07, "loss": 2.0917744636535645, "step": 2 }, { "epoch": 0.01593625498007968, "grad_norm": 0.810661792755127, "learning_rate": 1.1764705882352942e-06, "loss": 2.0072617530822754, "step": 4 }, { "epoch": 0.02390438247011952, "grad_norm": 3.0303120613098145, "learning_rate": 1.96078431372549e-06, "loss": 2.1259865760803223, "step": 6 }, { "epoch": 0.03187250996015936, "grad_norm": 0.4886261224746704, "learning_rate": 2.7450980392156867e-06, "loss": 1.8118433952331543, "step": 8 }, { "epoch": 0.0398406374501992, "grad_norm": 0.999951958656311, "learning_rate": 3.529411764705883e-06, "loss": 1.2686036825180054, "step": 10 }, { "epoch": 0.04780876494023904, "grad_norm": 0.44369059801101685, "learning_rate": 4.313725490196079e-06, "loss": 1.574094533920288, "step": 12 }, { "epoch": 0.055776892430278883, "grad_norm": 0.9999973177909851, "learning_rate": 5.098039215686274e-06, "loss": 1.621669888496399, "step": 14 }, { "epoch": 0.06374501992031872, "grad_norm": 2.91615629196167, "learning_rate": 5.882352941176471e-06, "loss": 1.7130111455917358, "step": 16 }, { "epoch": 0.07171314741035857, "grad_norm": 2.743251323699951, "learning_rate": 6.666666666666667e-06, "loss": 1.5403144359588623, "step": 18 }, { "epoch": 0.0796812749003984, "grad_norm": 0.40935927629470825, "learning_rate": 7.450980392156863e-06, "loss": 1.4595532417297363, "step": 20 }, { "epoch": 0.08764940239043825, "grad_norm": 0.49270394444465637, "learning_rate": 8.23529411764706e-06, "loss": 1.078918695449829, "step": 22 }, { "epoch": 0.09561752988047809, "grad_norm": 0.6997860074043274, "learning_rate": 9.019607843137256e-06, "loss": 1.272464394569397, "step": 24 }, { "epoch": 0.10358565737051793, "grad_norm": 0.2835118770599365, "learning_rate": 9.803921568627451e-06, "loss": 1.3907194137573242, "step": 26 }, { "epoch": 0.11155378486055777, "grad_norm": 0.4336991310119629, "learning_rate": 1.0588235294117648e-05, "loss": 1.6411925554275513, "step": 28 }, { "epoch": 0.11952191235059761, "grad_norm": 0.7342823147773743, "learning_rate": 1.1372549019607844e-05, "loss": 1.3065185546875, "step": 30 }, { "epoch": 0.12749003984063745, "grad_norm": 1.0185433626174927, "learning_rate": 1.215686274509804e-05, "loss": 1.1634331941604614, "step": 32 }, { "epoch": 0.13545816733067728, "grad_norm": 0.6737763285636902, "learning_rate": 1.2941176470588238e-05, "loss": 1.2271698713302612, "step": 34 }, { "epoch": 0.14342629482071714, "grad_norm": 0.4160401523113251, "learning_rate": 1.3725490196078432e-05, "loss": 1.3688286542892456, "step": 36 }, { "epoch": 0.15139442231075698, "grad_norm": 0.4553028345108032, "learning_rate": 1.4509803921568629e-05, "loss": 1.1739035844802856, "step": 38 }, { "epoch": 0.1593625498007968, "grad_norm": 0.38726070523262024, "learning_rate": 1.5294117647058822e-05, "loss": 1.2846916913986206, "step": 40 }, { "epoch": 0.16733067729083664, "grad_norm": 3.5087525844573975, "learning_rate": 1.607843137254902e-05, "loss": 0.8091318607330322, "step": 42 }, { "epoch": 0.1752988047808765, "grad_norm": 0.37687066197395325, "learning_rate": 1.686274509803922e-05, "loss": 0.9793770909309387, "step": 44 }, { "epoch": 0.18326693227091634, "grad_norm": 1.0739067792892456, "learning_rate": 1.7647058823529414e-05, "loss": 0.9566636085510254, "step": 46 }, { "epoch": 0.19123505976095617, "grad_norm": 0.47356870770454407, "learning_rate": 1.843137254901961e-05, "loss": 1.1809724569320679, "step": 48 }, { "epoch": 0.199203187250996, "grad_norm": 0.4509386718273163, "learning_rate": 1.9215686274509807e-05, "loss": 1.3403902053833008, "step": 50 }, { "epoch": 0.20717131474103587, "grad_norm": 0.5614227056503296, "learning_rate": 2e-05, "loss": 1.2854832410812378, "step": 52 }, { "epoch": 0.2151394422310757, "grad_norm": 1.6636875867843628, "learning_rate": 1.9999804392782173e-05, "loss": 1.15964937210083, "step": 54 }, { "epoch": 0.22310756972111553, "grad_norm": 0.6026492118835449, "learning_rate": 1.9999217579631398e-05, "loss": 1.5435972213745117, "step": 56 }, { "epoch": 0.23107569721115537, "grad_norm": 0.5710262656211853, "learning_rate": 1.9998239586055426e-05, "loss": 1.3572176694869995, "step": 58 }, { "epoch": 0.23904382470119523, "grad_norm": 0.4704586863517761, "learning_rate": 1.999687045456595e-05, "loss": 0.7907789349555969, "step": 60 }, { "epoch": 0.24701195219123506, "grad_norm": 0.6437126398086548, "learning_rate": 1.9995110244676744e-05, "loss": 1.3580092191696167, "step": 62 }, { "epoch": 0.2549800796812749, "grad_norm": 0.6201555132865906, "learning_rate": 1.999295903290109e-05, "loss": 1.1368566751480103, "step": 64 }, { "epoch": 0.26294820717131473, "grad_norm": 0.32955482602119446, "learning_rate": 1.999041691274844e-05, "loss": 1.2860944271087646, "step": 66 }, { "epoch": 0.27091633466135456, "grad_norm": 2.3107502460479736, "learning_rate": 1.998748399472037e-05, "loss": 1.2669298648834229, "step": 68 }, { "epoch": 0.2788844621513944, "grad_norm": 0.6270288228988647, "learning_rate": 1.9984160406305745e-05, "loss": 1.6321552991867065, "step": 70 }, { "epoch": 0.2868525896414343, "grad_norm": 0.7549951672554016, "learning_rate": 1.9980446291975217e-05, "loss": 0.9260438680648804, "step": 72 }, { "epoch": 0.2948207171314741, "grad_norm": 0.5084768533706665, "learning_rate": 1.99763418131749e-05, "loss": 1.177539587020874, "step": 74 }, { "epoch": 0.30278884462151395, "grad_norm": 0.35039380192756653, "learning_rate": 1.9971847148319392e-05, "loss": 1.518884539604187, "step": 76 }, { "epoch": 0.3107569721115538, "grad_norm": 1.3086798191070557, "learning_rate": 1.9966962492784006e-05, "loss": 1.092125654220581, "step": 78 }, { "epoch": 0.3187250996015936, "grad_norm": 0.2802942097187042, "learning_rate": 1.996168805889627e-05, "loss": 0.9195184111595154, "step": 80 }, { "epoch": 0.32669322709163345, "grad_norm": 0.2216862589120865, "learning_rate": 1.99560240759267e-05, "loss": 1.3941141366958618, "step": 82 }, { "epoch": 0.3346613545816733, "grad_norm": 0.364798903465271, "learning_rate": 1.9949970790078847e-05, "loss": 0.9815192222595215, "step": 84 }, { "epoch": 0.3426294820717131, "grad_norm": 0.3959977626800537, "learning_rate": 1.9943528464478573e-05, "loss": 1.3783819675445557, "step": 86 }, { "epoch": 0.350597609561753, "grad_norm": 0.5596943497657776, "learning_rate": 1.993669737916263e-05, "loss": 1.0107626914978027, "step": 88 }, { "epoch": 0.35856573705179284, "grad_norm": 0.3602933883666992, "learning_rate": 1.9929477831066485e-05, "loss": 1.3774622678756714, "step": 90 }, { "epoch": 0.3665338645418327, "grad_norm": 0.6483653783798218, "learning_rate": 1.992187013401141e-05, "loss": 1.1842169761657715, "step": 92 }, { "epoch": 0.3745019920318725, "grad_norm": 0.4403039216995239, "learning_rate": 1.9913874618690837e-05, "loss": 1.2730536460876465, "step": 94 }, { "epoch": 0.38247011952191234, "grad_norm": 0.4975699484348297, "learning_rate": 1.9905491632655996e-05, "loss": 1.1539090871810913, "step": 96 }, { "epoch": 0.3904382470119522, "grad_norm": 0.2979013919830322, "learning_rate": 1.989672154030078e-05, "loss": 1.29496431350708, "step": 98 }, { "epoch": 0.398406374501992, "grad_norm": 0.2749949097633362, "learning_rate": 1.988756472284595e-05, "loss": 0.9005283117294312, "step": 100 }, { "epoch": 0.4063745019920319, "grad_norm": 0.514941930770874, "learning_rate": 1.9878021578322518e-05, "loss": 1.2876659631729126, "step": 102 }, { "epoch": 0.41434262948207173, "grad_norm": 0.4066709876060486, "learning_rate": 1.9868092521554478e-05, "loss": 0.8320454955101013, "step": 104 }, { "epoch": 0.42231075697211157, "grad_norm": 0.8786472678184509, "learning_rate": 1.9857777984140746e-05, "loss": 0.8519544005393982, "step": 106 }, { "epoch": 0.4302788844621514, "grad_norm": 0.29944780468940735, "learning_rate": 1.9847078414436438e-05, "loss": 1.0755633115768433, "step": 108 }, { "epoch": 0.43824701195219123, "grad_norm": 0.318147212266922, "learning_rate": 1.983599427753334e-05, "loss": 1.3149950504302979, "step": 110 }, { "epoch": 0.44621513944223107, "grad_norm": 0.48846861720085144, "learning_rate": 1.9824526055239712e-05, "loss": 0.9347569346427917, "step": 112 }, { "epoch": 0.4541832669322709, "grad_norm": 0.6037935018539429, "learning_rate": 1.981267424605935e-05, "loss": 1.1939929723739624, "step": 114 }, { "epoch": 0.46215139442231074, "grad_norm": 0.3412390351295471, "learning_rate": 1.98004393651699e-05, "loss": 1.3140885829925537, "step": 116 }, { "epoch": 0.4701195219123506, "grad_norm": 0.19363585114479065, "learning_rate": 1.9787821944400477e-05, "loss": 1.379936695098877, "step": 118 }, { "epoch": 0.47808764940239046, "grad_norm": 0.27185797691345215, "learning_rate": 1.9774822532208537e-05, "loss": 1.2482614517211914, "step": 120 }, { "epoch": 0.4860557768924303, "grad_norm": 0.3468357026576996, "learning_rate": 1.9761441693656052e-05, "loss": 1.0234702825546265, "step": 122 }, { "epoch": 0.4940239043824701, "grad_norm": 0.6428335905075073, "learning_rate": 1.974768001038493e-05, "loss": 1.1203795671463013, "step": 124 }, { "epoch": 0.50199203187251, "grad_norm": 1.4245277643203735, "learning_rate": 1.973353808059175e-05, "loss": 0.9964794516563416, "step": 126 }, { "epoch": 0.5099601593625498, "grad_norm": 0.2785136103630066, "learning_rate": 1.9719016519001738e-05, "loss": 1.3150984048843384, "step": 128 }, { "epoch": 0.5179282868525896, "grad_norm": 0.24503813683986664, "learning_rate": 1.9704115956842066e-05, "loss": 0.9756975769996643, "step": 130 }, { "epoch": 0.5258964143426295, "grad_norm": 0.2493988424539566, "learning_rate": 1.9688837041814396e-05, "loss": 0.9220959544181824, "step": 132 }, { "epoch": 0.5338645418326693, "grad_norm": 0.4868241846561432, "learning_rate": 1.967318043806675e-05, "loss": 0.9433274269104004, "step": 134 }, { "epoch": 0.5418326693227091, "grad_norm": 0.5221350193023682, "learning_rate": 1.965714682616461e-05, "loss": 1.3711186647415161, "step": 136 }, { "epoch": 0.549800796812749, "grad_norm": 0.28495630621910095, "learning_rate": 1.9640736903061363e-05, "loss": 0.9921805262565613, "step": 138 }, { "epoch": 0.5577689243027888, "grad_norm": 1.458466649055481, "learning_rate": 1.9623951382067983e-05, "loss": 1.1294525861740112, "step": 140 }, { "epoch": 0.5657370517928287, "grad_norm": 0.4033034145832062, "learning_rate": 1.960679099282204e-05, "loss": 1.0755698680877686, "step": 142 }, { "epoch": 0.5737051792828686, "grad_norm": 0.21537722647190094, "learning_rate": 1.9589256481255984e-05, "loss": 1.2472436428070068, "step": 144 }, { "epoch": 0.5816733067729084, "grad_norm": 0.44159841537475586, "learning_rate": 1.9571348609564697e-05, "loss": 1.1674703359603882, "step": 146 }, { "epoch": 0.5896414342629482, "grad_norm": 0.32412996888160706, "learning_rate": 1.9553068156172404e-05, "loss": 1.2616956233978271, "step": 148 }, { "epoch": 0.5976095617529881, "grad_norm": 0.6924676895141602, "learning_rate": 1.9534415915698793e-05, "loss": 0.9987442493438721, "step": 150 }, { "epoch": 0.6055776892430279, "grad_norm": 1.2662639617919922, "learning_rate": 1.9515392698924504e-05, "loss": 1.029040813446045, "step": 152 }, { "epoch": 0.6135458167330677, "grad_norm": 0.40699806809425354, "learning_rate": 1.949599933275587e-05, "loss": 1.178037166595459, "step": 154 }, { "epoch": 0.6215139442231076, "grad_norm": 10.901415824890137, "learning_rate": 1.9476236660188982e-05, "loss": 1.4249886274337769, "step": 156 }, { "epoch": 0.6294820717131474, "grad_norm": 0.45006561279296875, "learning_rate": 1.9456105540273035e-05, "loss": 1.2598600387573242, "step": 158 }, { "epoch": 0.6374501992031872, "grad_norm": 0.19699808955192566, "learning_rate": 1.9435606848073003e-05, "loss": 1.1120367050170898, "step": 160 }, { "epoch": 0.6454183266932271, "grad_norm": 0.38040539622306824, "learning_rate": 1.9414741474631586e-05, "loss": 0.8465813994407654, "step": 162 }, { "epoch": 0.6533864541832669, "grad_norm": 1.709991455078125, "learning_rate": 1.939351032693048e-05, "loss": 1.173558235168457, "step": 164 }, { "epoch": 0.6613545816733067, "grad_norm": 1.1846164464950562, "learning_rate": 1.9371914327850958e-05, "loss": 0.9727553129196167, "step": 166 }, { "epoch": 0.6693227091633466, "grad_norm": 0.22328278422355652, "learning_rate": 1.934995441613376e-05, "loss": 1.2808932065963745, "step": 168 }, { "epoch": 0.6772908366533864, "grad_norm": 1.2181369066238403, "learning_rate": 1.9327631546338263e-05, "loss": 0.9919388294219971, "step": 170 }, { "epoch": 0.6852589641434262, "grad_norm": 0.20286568999290466, "learning_rate": 1.9304946688801014e-05, "loss": 0.9318987727165222, "step": 172 }, { "epoch": 0.6932270916334662, "grad_norm": 0.19301116466522217, "learning_rate": 1.9281900829593544e-05, "loss": 1.267797827720642, "step": 174 }, { "epoch": 0.701195219123506, "grad_norm": 0.5525937080383301, "learning_rate": 1.9258494970479494e-05, "loss": 0.8463788628578186, "step": 176 }, { "epoch": 0.7091633466135459, "grad_norm": 1.1420658826828003, "learning_rate": 1.923473012887109e-05, "loss": 1.0495458841323853, "step": 178 }, { "epoch": 0.7171314741035857, "grad_norm": 0.5330231189727783, "learning_rate": 1.9210607337784885e-05, "loss": 1.1506317853927612, "step": 180 }, { "epoch": 0.7250996015936255, "grad_norm": 0.3030523657798767, "learning_rate": 1.9186127645796902e-05, "loss": 0.5509636998176575, "step": 182 }, { "epoch": 0.7330677290836654, "grad_norm": 0.3389263153076172, "learning_rate": 1.916129211699701e-05, "loss": 1.436009168624878, "step": 184 }, { "epoch": 0.7410358565737052, "grad_norm": 0.24991673231124878, "learning_rate": 1.91361018309427e-05, "loss": 1.3165287971496582, "step": 186 }, { "epoch": 0.749003984063745, "grad_norm": 0.24408350884914398, "learning_rate": 1.911055788261214e-05, "loss": 1.1602749824523926, "step": 188 }, { "epoch": 0.7569721115537849, "grad_norm": 0.43527284264564514, "learning_rate": 1.9084661382356592e-05, "loss": 0.9473373293876648, "step": 190 }, { "epoch": 0.7649402390438247, "grad_norm": 0.43389058113098145, "learning_rate": 1.9058413455852142e-05, "loss": 1.2940902709960938, "step": 192 }, { "epoch": 0.7729083665338645, "grad_norm": 0.7468045949935913, "learning_rate": 1.9031815244050752e-05, "loss": 0.9381421804428101, "step": 194 }, { "epoch": 0.7808764940239044, "grad_norm": 0.7282751202583313, "learning_rate": 1.9004867903130694e-05, "loss": 0.6863753795623779, "step": 196 }, { "epoch": 0.7888446215139442, "grad_norm": 0.5961089730262756, "learning_rate": 1.897757260444628e-05, "loss": 0.8179615139961243, "step": 198 }, { "epoch": 0.796812749003984, "grad_norm": 1.3089362382888794, "learning_rate": 1.8949930534476938e-05, "loss": 1.128772258758545, "step": 200 }, { "epoch": 0.8047808764940239, "grad_norm": 0.21875956654548645, "learning_rate": 1.892194289477565e-05, "loss": 1.1042561531066895, "step": 202 }, { "epoch": 0.8127490039840638, "grad_norm": 3.4494071006774902, "learning_rate": 1.8893610901916707e-05, "loss": 1.5994261503219604, "step": 204 }, { "epoch": 0.8207171314741036, "grad_norm": 0.23538140952587128, "learning_rate": 1.886493578744284e-05, "loss": 1.2714879512786865, "step": 206 }, { "epoch": 0.8286852589641435, "grad_norm": 0.3898092806339264, "learning_rate": 1.8835918797811693e-05, "loss": 0.6736286878585815, "step": 208 }, { "epoch": 0.8366533864541833, "grad_norm": 0.21210964024066925, "learning_rate": 1.880656119434162e-05, "loss": 1.3009498119354248, "step": 210 }, { "epoch": 0.8446215139442231, "grad_norm": 0.32511070370674133, "learning_rate": 1.8776864253156875e-05, "loss": 1.2415105104446411, "step": 212 }, { "epoch": 0.852589641434263, "grad_norm": 0.19582609832286835, "learning_rate": 1.874682926513213e-05, "loss": 0.9720925688743591, "step": 214 }, { "epoch": 0.8605577689243028, "grad_norm": 0.6029711961746216, "learning_rate": 1.871645753583638e-05, "loss": 1.470245122909546, "step": 216 }, { "epoch": 0.8685258964143426, "grad_norm": 0.5851346850395203, "learning_rate": 1.8685750385476166e-05, "loss": 0.9455154538154602, "step": 218 }, { "epoch": 0.8764940239043825, "grad_norm": 0.19497381150722504, "learning_rate": 1.8654709148838218e-05, "loss": 1.2599096298217773, "step": 220 }, { "epoch": 0.8844621513944223, "grad_norm": 0.26738685369491577, "learning_rate": 1.8623335175231402e-05, "loss": 1.5198086500167847, "step": 222 }, { "epoch": 0.8924302788844621, "grad_norm": 0.5694872736930847, "learning_rate": 1.85916298284281e-05, "loss": 0.7601725459098816, "step": 224 }, { "epoch": 0.900398406374502, "grad_norm": 0.2272186130285263, "learning_rate": 1.8559594486604905e-05, "loss": 1.0718581676483154, "step": 226 }, { "epoch": 0.9083665338645418, "grad_norm": 1.221880555152893, "learning_rate": 1.8527230542282724e-05, "loss": 1.1400426626205444, "step": 228 }, { "epoch": 0.9163346613545816, "grad_norm": 0.5730668902397156, "learning_rate": 1.849453940226625e-05, "loss": 1.2088643312454224, "step": 230 }, { "epoch": 0.9243027888446215, "grad_norm": 0.4114644229412079, "learning_rate": 1.8461522487582803e-05, "loss": 1.3527557849884033, "step": 232 }, { "epoch": 0.9322709163346613, "grad_norm": 0.23788665235042572, "learning_rate": 1.8428181233420565e-05, "loss": 0.849742591381073, "step": 234 }, { "epoch": 0.9402390438247012, "grad_norm": 0.2996785640716553, "learning_rate": 1.8394517089066197e-05, "loss": 0.860381007194519, "step": 236 }, { "epoch": 0.9482071713147411, "grad_norm": 0.28780749440193176, "learning_rate": 1.8360531517841832e-05, "loss": 0.5374816656112671, "step": 238 }, { "epoch": 0.9561752988047809, "grad_norm": 5.442948341369629, "learning_rate": 1.8326225997041482e-05, "loss": 0.8819217085838318, "step": 240 }, { "epoch": 0.9641434262948207, "grad_norm": 0.31859269738197327, "learning_rate": 1.8291602017866806e-05, "loss": 1.1617459058761597, "step": 242 }, { "epoch": 0.9721115537848606, "grad_norm": 0.2222505807876587, "learning_rate": 1.8256661085362308e-05, "loss": 1.2299988269805908, "step": 244 }, { "epoch": 0.9800796812749004, "grad_norm": 1.0804269313812256, "learning_rate": 1.8221404718349888e-05, "loss": 0.9867074489593506, "step": 246 }, { "epoch": 0.9880478087649402, "grad_norm": 0.22583311796188354, "learning_rate": 1.8185834449362855e-05, "loss": 1.0669959783554077, "step": 248 }, { "epoch": 0.9960159362549801, "grad_norm": 0.7727883458137512, "learning_rate": 1.8149951824579283e-05, "loss": 1.0471503734588623, "step": 250 }, { "epoch": 1.00398406374502, "grad_norm": 1.0428727865219116, "learning_rate": 1.8113758403754823e-05, "loss": 0.9628705382347107, "step": 252 }, { "epoch": 1.0119521912350598, "grad_norm": 0.29301974177360535, "learning_rate": 1.8077255760154883e-05, "loss": 0.6730931401252747, "step": 254 }, { "epoch": 1.0199203187250996, "grad_norm": 0.2510043978691101, "learning_rate": 1.8040445480486254e-05, "loss": 1.0644416809082031, "step": 256 }, { "epoch": 1.0278884462151394, "grad_norm": 0.26433369517326355, "learning_rate": 1.8003329164828133e-05, "loss": 1.0268616676330566, "step": 258 }, { "epoch": 1.0358565737051793, "grad_norm": 0.3402881920337677, "learning_rate": 1.7965908426562582e-05, "loss": 0.9412785768508911, "step": 260 }, { "epoch": 1.043824701195219, "grad_norm": 0.3539513349533081, "learning_rate": 1.7928184892304366e-05, "loss": 1.071285605430603, "step": 262 }, { "epoch": 1.051792828685259, "grad_norm": 0.4345550239086151, "learning_rate": 1.789016020183029e-05, "loss": 1.0769709348678589, "step": 264 }, { "epoch": 1.0597609561752988, "grad_norm": 0.49914422631263733, "learning_rate": 1.7851836008007883e-05, "loss": 0.6106696128845215, "step": 266 }, { "epoch": 1.0677290836653386, "grad_norm": 0.32720446586608887, "learning_rate": 1.781321397672358e-05, "loss": 0.8539678454399109, "step": 268 }, { "epoch": 1.0756972111553784, "grad_norm": 0.5094645619392395, "learning_rate": 1.777429578681029e-05, "loss": 0.5865146517753601, "step": 270 }, { "epoch": 1.0836653386454183, "grad_norm": 0.22214379906654358, "learning_rate": 1.7735083129974423e-05, "loss": 1.206352949142456, "step": 272 }, { "epoch": 1.091633466135458, "grad_norm": 0.5591684579849243, "learning_rate": 1.769557771072236e-05, "loss": 0.6486972570419312, "step": 274 }, { "epoch": 1.099601593625498, "grad_norm": 0.20063146948814392, "learning_rate": 1.7655781246286345e-05, "loss": 0.7891363501548767, "step": 276 }, { "epoch": 1.1075697211155378, "grad_norm": 0.21085433661937714, "learning_rate": 1.761569546654988e-05, "loss": 0.7340715527534485, "step": 278 }, { "epoch": 1.1155378486055776, "grad_norm": 0.24264748394489288, "learning_rate": 1.7575322113972472e-05, "loss": 0.8897150754928589, "step": 280 }, { "epoch": 1.1235059760956174, "grad_norm": 0.22709651291370392, "learning_rate": 1.753466294351395e-05, "loss": 1.026313066482544, "step": 282 }, { "epoch": 1.1314741035856573, "grad_norm": 0.5668113827705383, "learning_rate": 1.7493719722558135e-05, "loss": 1.0943456888198853, "step": 284 }, { "epoch": 1.139442231075697, "grad_norm": 0.19547593593597412, "learning_rate": 1.7452494230836034e-05, "loss": 0.2862858474254608, "step": 286 }, { "epoch": 1.1474103585657371, "grad_norm": 0.2796744406223297, "learning_rate": 1.741098826034848e-05, "loss": 0.600908100605011, "step": 288 }, { "epoch": 1.155378486055777, "grad_norm": 4.786985397338867, "learning_rate": 1.7369203615288227e-05, "loss": 0.8700795769691467, "step": 290 }, { "epoch": 1.1633466135458168, "grad_norm": 0.29058995842933655, "learning_rate": 1.7327142111961537e-05, "loss": 0.5029220581054688, "step": 292 }, { "epoch": 1.1713147410358566, "grad_norm": 0.32093071937561035, "learning_rate": 1.7284805578709218e-05, "loss": 1.1380616426467896, "step": 294 }, { "epoch": 1.1792828685258965, "grad_norm": 0.3169378638267517, "learning_rate": 1.724219585582716e-05, "loss": 1.2196353673934937, "step": 296 }, { "epoch": 1.1872509960159363, "grad_norm": 0.2575913369655609, "learning_rate": 1.7199314795486325e-05, "loss": 1.152186632156372, "step": 298 }, { "epoch": 1.1952191235059761, "grad_norm": 0.8197821378707886, "learning_rate": 1.7156164261652247e-05, "loss": 0.5692594647407532, "step": 300 }, { "epoch": 1.203187250996016, "grad_norm": 0.3137279748916626, "learning_rate": 1.711274613000401e-05, "loss": 0.8352428674697876, "step": 302 }, { "epoch": 1.2111553784860558, "grad_norm": 0.45411720871925354, "learning_rate": 1.7069062287852717e-05, "loss": 0.530438244342804, "step": 304 }, { "epoch": 1.2191235059760956, "grad_norm": 0.28593263030052185, "learning_rate": 1.702511463405943e-05, "loss": 1.1038769483566284, "step": 306 }, { "epoch": 1.2270916334661355, "grad_norm": 1.3969101905822754, "learning_rate": 1.698090507895266e-05, "loss": 0.8672254681587219, "step": 308 }, { "epoch": 1.2350597609561753, "grad_norm": 0.2987782657146454, "learning_rate": 1.693643554424532e-05, "loss": 1.0281533002853394, "step": 310 }, { "epoch": 1.2430278884462151, "grad_norm": 2.4030439853668213, "learning_rate": 1.6891707962951173e-05, "loss": 0.9899963140487671, "step": 312 }, { "epoch": 1.250996015936255, "grad_norm": 0.3773461878299713, "learning_rate": 1.684672427930083e-05, "loss": 0.8627890348434448, "step": 314 }, { "epoch": 1.2589641434262948, "grad_norm": 0.631601870059967, "learning_rate": 1.680148644865722e-05, "loss": 0.7224826216697693, "step": 316 }, { "epoch": 1.2669322709163346, "grad_norm": 0.3479246199131012, "learning_rate": 1.6755996437430622e-05, "loss": 0.6212186813354492, "step": 318 }, { "epoch": 1.2749003984063745, "grad_norm": 0.6571335792541504, "learning_rate": 1.6710256222993137e-05, "loss": 0.5513061285018921, "step": 320 }, { "epoch": 1.2828685258964143, "grad_norm": 0.42356932163238525, "learning_rate": 1.6664267793592797e-05, "loss": 0.8942829370498657, "step": 322 }, { "epoch": 1.2908366533864541, "grad_norm": 0.30983954668045044, "learning_rate": 1.661803314826709e-05, "loss": 0.8798987865447998, "step": 324 }, { "epoch": 1.298804780876494, "grad_norm": 0.3153538107872009, "learning_rate": 1.65715542967561e-05, "loss": 1.1531648635864258, "step": 326 }, { "epoch": 1.3067729083665338, "grad_norm": 0.3276787996292114, "learning_rate": 1.652483325941511e-05, "loss": 0.6731415390968323, "step": 328 }, { "epoch": 1.3147410358565736, "grad_norm": 0.2345854789018631, "learning_rate": 1.647787206712683e-05, "loss": 0.7159542441368103, "step": 330 }, { "epoch": 1.3227091633466135, "grad_norm": 0.3460042178630829, "learning_rate": 1.6430672761213065e-05, "loss": 0.8806806206703186, "step": 332 }, { "epoch": 1.3306772908366533, "grad_norm": 0.4524310529232025, "learning_rate": 1.6383237393346025e-05, "loss": 0.6197898983955383, "step": 334 }, { "epoch": 1.3386454183266931, "grad_norm": 1.2271060943603516, "learning_rate": 1.633556802545911e-05, "loss": 0.8273814916610718, "step": 336 }, { "epoch": 1.3466135458167332, "grad_norm": 0.399169385433197, "learning_rate": 1.628766672965731e-05, "loss": 1.0281566381454468, "step": 338 }, { "epoch": 1.354581673306773, "grad_norm": 0.2849925458431244, "learning_rate": 1.6239535588127107e-05, "loss": 1.0255684852600098, "step": 340 }, { "epoch": 1.3625498007968129, "grad_norm": 0.2086225003004074, "learning_rate": 1.6191176693046e-05, "loss": 1.1102956533432007, "step": 342 }, { "epoch": 1.3705179282868527, "grad_norm": 0.2861909568309784, "learning_rate": 1.6142592146491517e-05, "loss": 1.039727807044983, "step": 344 }, { "epoch": 1.3784860557768925, "grad_norm": 0.4101890027523041, "learning_rate": 1.6093784060349876e-05, "loss": 0.6680477857589722, "step": 346 }, { "epoch": 1.3864541832669324, "grad_norm": 0.9055512547492981, "learning_rate": 1.6044754556224178e-05, "loss": 1.071424961090088, "step": 348 }, { "epoch": 1.3944223107569722, "grad_norm": 0.21851401031017303, "learning_rate": 1.5995505765342176e-05, "loss": 0.6275965571403503, "step": 350 }, { "epoch": 1.402390438247012, "grad_norm": 0.6850494742393494, "learning_rate": 1.594603982846364e-05, "loss": 1.0714225769042969, "step": 352 }, { "epoch": 1.4103585657370519, "grad_norm": 0.4336423873901367, "learning_rate": 1.5896358895787304e-05, "loss": 1.085031270980835, "step": 354 }, { "epoch": 1.4183266932270917, "grad_norm": 0.44185537099838257, "learning_rate": 1.5846465126857386e-05, "loss": 0.9013204574584961, "step": 356 }, { "epoch": 1.4262948207171315, "grad_norm": 0.5267951488494873, "learning_rate": 1.579636069046975e-05, "loss": 1.1412065029144287, "step": 358 }, { "epoch": 1.4342629482071714, "grad_norm": 0.3913382589817047, "learning_rate": 1.5746047764577586e-05, "loss": 0.556093156337738, "step": 360 }, { "epoch": 1.4422310756972112, "grad_norm": 0.1703263372182846, "learning_rate": 1.5695528536196774e-05, "loss": 0.6311008334159851, "step": 362 }, { "epoch": 1.450199203187251, "grad_norm": 0.40427079796791077, "learning_rate": 1.564480520131081e-05, "loss": 1.0373692512512207, "step": 364 }, { "epoch": 1.4581673306772909, "grad_norm": 0.23842480778694153, "learning_rate": 1.559387996477534e-05, "loss": 1.10188889503479, "step": 366 }, { "epoch": 1.4661354581673307, "grad_norm": 0.2711256742477417, "learning_rate": 1.5542755040222325e-05, "loss": 0.5743086934089661, "step": 368 }, { "epoch": 1.4741035856573705, "grad_norm": 0.28507372736930847, "learning_rate": 1.5491432649963823e-05, "loss": 0.6648173928260803, "step": 370 }, { "epoch": 1.4820717131474104, "grad_norm": 0.6098495721817017, "learning_rate": 1.543991502489538e-05, "loss": 1.278815746307373, "step": 372 }, { "epoch": 1.4900398406374502, "grad_norm": 0.29301366209983826, "learning_rate": 1.5388204404399073e-05, "loss": 1.0057001113891602, "step": 374 }, { "epoch": 1.49800796812749, "grad_norm": 0.20756776630878448, "learning_rate": 1.533630303624614e-05, "loss": 1.0227080583572388, "step": 376 }, { "epoch": 1.5059760956175299, "grad_norm": 0.5751330852508545, "learning_rate": 1.5284213176499302e-05, "loss": 0.833890974521637, "step": 378 }, { "epoch": 1.5139442231075697, "grad_norm": 0.2176685780286789, "learning_rate": 1.5231937089414675e-05, "loss": 1.1108826398849487, "step": 380 }, { "epoch": 1.5219123505976095, "grad_norm": 0.18583351373672485, "learning_rate": 1.517947704734337e-05, "loss": 0.6579040288925171, "step": 382 }, { "epoch": 1.5298804780876494, "grad_norm": 0.21181410551071167, "learning_rate": 1.5126835330632677e-05, "loss": 0.7684563398361206, "step": 384 }, { "epoch": 1.5378486055776892, "grad_norm": 2.384171962738037, "learning_rate": 1.5074014227526997e-05, "loss": 0.9445454478263855, "step": 386 }, { "epoch": 1.545816733067729, "grad_norm": 0.8749470114707947, "learning_rate": 1.502101603406833e-05, "loss": 1.0786616802215576, "step": 388 }, { "epoch": 1.5537848605577689, "grad_norm": 0.6344363689422607, "learning_rate": 1.4967843053996494e-05, "loss": 0.583028256893158, "step": 390 }, { "epoch": 1.5617529880478087, "grad_norm": 2.1179275512695312, "learning_rate": 1.4914497598648973e-05, "loss": 0.6092298030853271, "step": 392 }, { "epoch": 1.5697211155378485, "grad_norm": 0.9769160151481628, "learning_rate": 1.4860981986860464e-05, "loss": 1.0053740739822388, "step": 394 }, { "epoch": 1.5776892430278884, "grad_norm": 0.9489666223526001, "learning_rate": 1.4807298544862054e-05, "loss": 0.9802870750427246, "step": 396 }, { "epoch": 1.5856573705179282, "grad_norm": 0.18127426505088806, "learning_rate": 1.4753449606180137e-05, "loss": 1.1266390085220337, "step": 398 }, { "epoch": 1.593625498007968, "grad_norm": 0.7098649740219116, "learning_rate": 1.4699437511534947e-05, "loss": 0.572892427444458, "step": 400 }, { "epoch": 1.6015936254980079, "grad_norm": 0.29952746629714966, "learning_rate": 1.4645264608738832e-05, "loss": 1.0320390462875366, "step": 402 }, { "epoch": 1.6095617529880477, "grad_norm": 0.21195581555366516, "learning_rate": 1.4590933252594193e-05, "loss": 1.1398323774337769, "step": 404 }, { "epoch": 1.6175298804780875, "grad_norm": 2.005444049835205, "learning_rate": 1.4536445804791125e-05, "loss": 0.7902427315711975, "step": 406 }, { "epoch": 1.6254980079681274, "grad_norm": 0.17703233659267426, "learning_rate": 1.4481804633804746e-05, "loss": 0.5331188440322876, "step": 408 }, { "epoch": 1.6334661354581672, "grad_norm": 0.787456214427948, "learning_rate": 1.4427012114792269e-05, "loss": 0.7766048908233643, "step": 410 }, { "epoch": 1.641434262948207, "grad_norm": 0.8873182535171509, "learning_rate": 1.4372070629489744e-05, "loss": 0.5234718322753906, "step": 412 }, { "epoch": 1.6494023904382469, "grad_norm": 0.18768654763698578, "learning_rate": 1.4316982566108515e-05, "loss": 0.7301771640777588, "step": 414 }, { "epoch": 1.6573705179282867, "grad_norm": 0.7368947863578796, "learning_rate": 1.4261750319231432e-05, "loss": 0.7337813377380371, "step": 416 }, { "epoch": 1.6653386454183265, "grad_norm": 1.4775207042694092, "learning_rate": 1.4206376289708752e-05, "loss": 0.8572339415550232, "step": 418 }, { "epoch": 1.6733067729083664, "grad_norm": 0.47419366240501404, "learning_rate": 1.4150862884553776e-05, "loss": 1.1198369264602661, "step": 420 }, { "epoch": 1.6812749003984062, "grad_norm": 0.7228560447692871, "learning_rate": 1.4095212516838216e-05, "loss": 0.9312633872032166, "step": 422 }, { "epoch": 1.6892430278884463, "grad_norm": 0.5536262392997742, "learning_rate": 1.4039427605587326e-05, "loss": 0.551925778388977, "step": 424 }, { "epoch": 1.697211155378486, "grad_norm": 0.40303146839141846, "learning_rate": 1.398351057567472e-05, "loss": 1.0757414102554321, "step": 426 }, { "epoch": 1.705179282868526, "grad_norm": 0.4696345627307892, "learning_rate": 1.392746385771699e-05, "loss": 1.02720046043396, "step": 428 }, { "epoch": 1.7131474103585658, "grad_norm": 0.5280032157897949, "learning_rate": 1.3871289887968034e-05, "loss": 0.695672869682312, "step": 430 }, { "epoch": 1.7211155378486056, "grad_norm": 2.737807273864746, "learning_rate": 1.3814991108213173e-05, "loss": 0.8390417098999023, "step": 432 }, { "epoch": 1.7290836653386454, "grad_norm": 0.3969716429710388, "learning_rate": 1.3758569965663011e-05, "loss": 0.6193844079971313, "step": 434 }, { "epoch": 1.7370517928286853, "grad_norm": 1.296787142753601, "learning_rate": 1.370202891284703e-05, "loss": 0.42184704542160034, "step": 436 }, { "epoch": 1.745019920318725, "grad_norm": 0.3460438847541809, "learning_rate": 1.3645370407507017e-05, "loss": 0.7077634334564209, "step": 438 }, { "epoch": 1.752988047808765, "grad_norm": 1.899395227432251, "learning_rate": 1.3588596912490222e-05, "loss": 0.9189682006835938, "step": 440 }, { "epoch": 1.7609561752988048, "grad_norm": 0.5682424902915955, "learning_rate": 1.3531710895642288e-05, "loss": 1.266446828842163, "step": 442 }, { "epoch": 1.7689243027888446, "grad_norm": 0.3595385253429413, "learning_rate": 1.3474714829699987e-05, "loss": 0.7236208915710449, "step": 444 }, { "epoch": 1.7768924302788844, "grad_norm": 0.2217399626970291, "learning_rate": 1.341761119218374e-05, "loss": 1.0007444620132446, "step": 446 }, { "epoch": 1.7848605577689243, "grad_norm": 0.2751394808292389, "learning_rate": 1.3360402465289916e-05, "loss": 1.0241546630859375, "step": 448 }, { "epoch": 1.792828685258964, "grad_norm": 0.27557480335235596, "learning_rate": 1.3303091135782942e-05, "loss": 0.7780989408493042, "step": 450 }, { "epoch": 1.800796812749004, "grad_norm": 0.38681551814079285, "learning_rate": 1.3245679694887192e-05, "loss": 0.40230435132980347, "step": 452 }, { "epoch": 1.8087649402390438, "grad_norm": 0.4556889235973358, "learning_rate": 1.318817063817872e-05, "loss": 0.8858887553215027, "step": 454 }, { "epoch": 1.8167330677290838, "grad_norm": 0.3483579158782959, "learning_rate": 1.3130566465476773e-05, "loss": 0.6085517406463623, "step": 456 }, { "epoch": 1.8247011952191237, "grad_norm": 0.2960999011993408, "learning_rate": 1.307286968073511e-05, "loss": 1.0038970708847046, "step": 458 }, { "epoch": 1.8326693227091635, "grad_norm": 0.6715680360794067, "learning_rate": 1.3015082791933182e-05, "loss": 0.7282179594039917, "step": 460 }, { "epoch": 1.8406374501992033, "grad_norm": 0.22472810745239258, "learning_rate": 1.295720831096712e-05, "loss": 0.7919058203697205, "step": 462 }, { "epoch": 1.8486055776892432, "grad_norm": 0.1415836215019226, "learning_rate": 1.2899248753540518e-05, "loss": 0.12256208807229996, "step": 464 }, { "epoch": 1.856573705179283, "grad_norm": 0.21556231379508972, "learning_rate": 1.2841206639055108e-05, "loss": 1.071553349494934, "step": 466 }, { "epoch": 1.8645418326693228, "grad_norm": 0.5607351660728455, "learning_rate": 1.2783084490501229e-05, "loss": 0.505492627620697, "step": 468 }, { "epoch": 1.8725099601593627, "grad_norm": 0.6919885873794556, "learning_rate": 1.2724884834348163e-05, "loss": 1.064407467842102, "step": 470 }, { "epoch": 1.8804780876494025, "grad_norm": 0.5945007801055908, "learning_rate": 1.266661020043432e-05, "loss": 0.888563871383667, "step": 472 }, { "epoch": 1.8884462151394423, "grad_norm": 0.4733371436595917, "learning_rate": 1.2608263121857244e-05, "loss": 1.126110553741455, "step": 474 }, { "epoch": 1.8964143426294822, "grad_norm": 0.19991199672222137, "learning_rate": 1.254984613486355e-05, "loss": 0.9147279262542725, "step": 476 }, { "epoch": 1.904382470119522, "grad_norm": 0.2315262407064438, "learning_rate": 1.2491361778738631e-05, "loss": 0.7795041799545288, "step": 478 }, { "epoch": 1.9123505976095618, "grad_norm": 0.35884639620780945, "learning_rate": 1.243281259569631e-05, "loss": 0.6129409670829773, "step": 480 }, { "epoch": 1.9203187250996017, "grad_norm": 0.4923068583011627, "learning_rate": 1.2374201130768325e-05, "loss": 0.7693575620651245, "step": 482 }, { "epoch": 1.9282868525896415, "grad_norm": 0.1931680589914322, "learning_rate": 1.2315529931693682e-05, "loss": 1.0299898386001587, "step": 484 }, { "epoch": 1.9362549800796813, "grad_norm": 0.4462296962738037, "learning_rate": 1.2256801548807948e-05, "loss": 0.9366471171379089, "step": 486 }, { "epoch": 1.9442231075697212, "grad_norm": 0.2196073979139328, "learning_rate": 1.2198018534932367e-05, "loss": 1.006306767463684, "step": 488 }, { "epoch": 1.952191235059761, "grad_norm": 0.22472602128982544, "learning_rate": 1.2139183445262892e-05, "loss": 1.0169907808303833, "step": 490 }, { "epoch": 1.9601593625498008, "grad_norm": 0.2581753134727478, "learning_rate": 1.2080298837259124e-05, "loss": 0.7045720219612122, "step": 492 }, { "epoch": 1.9681274900398407, "grad_norm": 0.9599785208702087, "learning_rate": 1.2021367270533138e-05, "loss": 0.7643440961837769, "step": 494 }, { "epoch": 1.9760956175298805, "grad_norm": 0.214574933052063, "learning_rate": 1.1962391306738226e-05, "loss": 1.0821375846862793, "step": 496 }, { "epoch": 1.9840637450199203, "grad_norm": 0.7121610045433044, "learning_rate": 1.190337350945754e-05, "loss": 0.8190574049949646, "step": 498 }, { "epoch": 1.9920318725099602, "grad_norm": 0.2094918042421341, "learning_rate": 1.1844316444092667e-05, "loss": 1.1208115816116333, "step": 500 }, { "epoch": 2.0, "grad_norm": 0.4617452621459961, "learning_rate": 1.1785222677752105e-05, "loss": 0.6037846803665161, "step": 502 }, { "epoch": 2.00796812749004, "grad_norm": 0.3327796161174774, "learning_rate": 1.1726094779139685e-05, "loss": 0.5098190903663635, "step": 504 }, { "epoch": 2.0159362549800797, "grad_norm": 0.3151598870754242, "learning_rate": 1.1666935318442905e-05, "loss": 0.45420554280281067, "step": 506 }, { "epoch": 2.0239043824701195, "grad_norm": 0.1029556542634964, "learning_rate": 1.1607746867221208e-05, "loss": 0.43064481019973755, "step": 508 }, { "epoch": 2.0318725099601593, "grad_norm": 0.2831689119338989, "learning_rate": 1.1548531998294217e-05, "loss": 0.7130162119865417, "step": 510 }, { "epoch": 2.039840637450199, "grad_norm": 0.3913080096244812, "learning_rate": 1.148929328562987e-05, "loss": 0.5985983610153198, "step": 512 }, { "epoch": 2.047808764940239, "grad_norm": 0.5065242648124695, "learning_rate": 1.1430033304232569e-05, "loss": 0.41830143332481384, "step": 514 }, { "epoch": 2.055776892430279, "grad_norm": 0.4071492850780487, "learning_rate": 1.137075463003122e-05, "loss": 0.7237223386764526, "step": 516 }, { "epoch": 2.0637450199203187, "grad_norm": 0.3139268755912781, "learning_rate": 1.1311459839767278e-05, "loss": 0.5583810806274414, "step": 518 }, { "epoch": 2.0717131474103585, "grad_norm": 0.7950957417488098, "learning_rate": 1.1252151510882731e-05, "loss": 0.6916399002075195, "step": 520 }, { "epoch": 2.0796812749003983, "grad_norm": 0.2715514004230499, "learning_rate": 1.1192832221408068e-05, "loss": 0.7834231853485107, "step": 522 }, { "epoch": 2.087649402390438, "grad_norm": 0.4181157052516937, "learning_rate": 1.1133504549850218e-05, "loss": 0.7094680070877075, "step": 524 }, { "epoch": 2.095617529880478, "grad_norm": 0.8718222379684448, "learning_rate": 1.1074171075080469e-05, "loss": 0.342552125453949, "step": 526 }, { "epoch": 2.103585657370518, "grad_norm": 0.25357672572135925, "learning_rate": 1.1014834376222351e-05, "loss": 0.5705795288085938, "step": 528 }, { "epoch": 2.1115537848605577, "grad_norm": 0.11659689247608185, "learning_rate": 1.0955497032539557e-05, "loss": 0.3817054033279419, "step": 530 }, { "epoch": 2.1195219123505975, "grad_norm": 0.2290099710226059, "learning_rate": 1.0896161623323795e-05, "loss": 0.23553325235843658, "step": 532 }, { "epoch": 2.1274900398406373, "grad_norm": 0.31470999121665955, "learning_rate": 1.0836830727782692e-05, "loss": 0.6560693979263306, "step": 534 }, { "epoch": 2.135458167330677, "grad_norm": 1.0675426721572876, "learning_rate": 1.0777506924927667e-05, "loss": 0.6435872912406921, "step": 536 }, { "epoch": 2.143426294820717, "grad_norm": 2.7700421810150146, "learning_rate": 1.0718192793461849e-05, "loss": 0.6159282922744751, "step": 538 }, { "epoch": 2.151394422310757, "grad_norm": 0.23660151660442352, "learning_rate": 1.065889091166795e-05, "loss": 0.709026575088501, "step": 540 }, { "epoch": 2.1593625498007967, "grad_norm": 0.2935536801815033, "learning_rate": 1.059960385729621e-05, "loss": 0.6912015080451965, "step": 542 }, { "epoch": 2.1673306772908365, "grad_norm": 0.19206146895885468, "learning_rate": 1.0540334207452363e-05, "loss": 0.3892318606376648, "step": 544 }, { "epoch": 2.1752988047808763, "grad_norm": 0.5060867071151733, "learning_rate": 1.0481084538485589e-05, "loss": 0.5315547585487366, "step": 546 }, { "epoch": 2.183266932270916, "grad_norm": 0.2707947790622711, "learning_rate": 1.0421857425876524e-05, "loss": 0.7022973299026489, "step": 548 }, { "epoch": 2.191235059760956, "grad_norm": 0.2336021214723587, "learning_rate": 1.0362655444125334e-05, "loss": 0.7240484356880188, "step": 550 }, { "epoch": 2.199203187250996, "grad_norm": 0.22163984179496765, "learning_rate": 1.0303481166639784e-05, "loss": 0.479079008102417, "step": 552 }, { "epoch": 2.2071713147410357, "grad_norm": 0.7793411612510681, "learning_rate": 1.0244337165623378e-05, "loss": 0.4736250936985016, "step": 554 }, { "epoch": 2.2151394422310755, "grad_norm": 0.2279587686061859, "learning_rate": 1.0185226011963563e-05, "loss": 0.5858893990516663, "step": 556 }, { "epoch": 2.2231075697211153, "grad_norm": 0.6285219192504883, "learning_rate": 1.0126150275119958e-05, "loss": 0.7605037093162537, "step": 558 }, { "epoch": 2.231075697211155, "grad_norm": 0.24656905233860016, "learning_rate": 1.0067112523012686e-05, "loss": 0.7338613271713257, "step": 560 }, { "epoch": 2.239043824701195, "grad_norm": 0.3758434057235718, "learning_rate": 1.0008115321910729e-05, "loss": 0.8115689754486084, "step": 562 }, { "epoch": 2.247011952191235, "grad_norm": 0.6850261688232422, "learning_rate": 9.949161236320388e-06, "loss": 0.6612259745597839, "step": 564 }, { "epoch": 2.2549800796812747, "grad_norm": 0.2368898093700409, "learning_rate": 9.890252828873816e-06, "loss": 0.4573831260204315, "step": 566 }, { "epoch": 2.2629482071713145, "grad_norm": 0.1783859133720398, "learning_rate": 9.831392660217608e-06, "loss": 0.6498692631721497, "step": 568 }, { "epoch": 2.2709163346613543, "grad_norm": 0.20042163133621216, "learning_rate": 9.772583288901502e-06, "loss": 0.7103173136711121, "step": 570 }, { "epoch": 2.278884462151394, "grad_norm": 0.41334012150764465, "learning_rate": 9.713827271267169e-06, "loss": 0.6057206988334656, "step": 572 }, { "epoch": 2.2868525896414345, "grad_norm": 0.236058309674263, "learning_rate": 9.655127161337088e-06, "loss": 0.5545896887779236, "step": 574 }, { "epoch": 2.2948207171314743, "grad_norm": 0.1312473714351654, "learning_rate": 9.59648551070351e-06, "loss": 0.24094551801681519, "step": 576 }, { "epoch": 2.302788844621514, "grad_norm": 0.47978517413139343, "learning_rate": 9.53790486841759e-06, "loss": 0.5237395167350769, "step": 578 }, { "epoch": 2.310756972111554, "grad_norm": 0.25365832448005676, "learning_rate": 9.479387780878531e-06, "loss": 0.5055394172668457, "step": 580 }, { "epoch": 2.318725099601594, "grad_norm": 0.6471706032752991, "learning_rate": 9.42093679172294e-06, "loss": 0.4769824147224426, "step": 582 }, { "epoch": 2.3266932270916336, "grad_norm": 0.21911540627479553, "learning_rate": 9.362554441714216e-06, "loss": 0.5952439904212952, "step": 584 }, { "epoch": 2.3346613545816735, "grad_norm": 0.2562398314476013, "learning_rate": 9.304243268632165e-06, "loss": 0.5159792304039001, "step": 586 }, { "epoch": 2.3426294820717133, "grad_norm": 0.49267587065696716, "learning_rate": 9.246005807162632e-06, "loss": 0.6133958697319031, "step": 588 }, { "epoch": 2.350597609561753, "grad_norm": 0.22192488610744476, "learning_rate": 9.187844588787354e-06, "loss": 0.7292117476463318, "step": 590 }, { "epoch": 2.358565737051793, "grad_norm": 0.22662049531936646, "learning_rate": 9.12976214167391e-06, "loss": 0.7524659633636475, "step": 592 }, { "epoch": 2.366533864541833, "grad_norm": 0.2066013216972351, "learning_rate": 9.071760990565832e-06, "loss": 0.49844464659690857, "step": 594 }, { "epoch": 2.3745019920318726, "grad_norm": 0.20779338479042053, "learning_rate": 9.013843656672854e-06, "loss": 0.6315061450004578, "step": 596 }, { "epoch": 2.3824701195219125, "grad_norm": 0.16386599838733673, "learning_rate": 8.956012657561314e-06, "loss": 0.5140540599822998, "step": 598 }, { "epoch": 2.3904382470119523, "grad_norm": 0.9354786276817322, "learning_rate": 8.89827050704474e-06, "loss": 0.6017587184906006, "step": 600 }, { "epoch": 2.398406374501992, "grad_norm": 0.17998290061950684, "learning_rate": 8.840619715074553e-06, "loss": 0.716720700263977, "step": 602 }, { "epoch": 2.406374501992032, "grad_norm": 0.4825294613838196, "learning_rate": 8.78306278763098e-06, "loss": 0.46186724305152893, "step": 604 }, { "epoch": 2.414342629482072, "grad_norm": 1.1368019580841064, "learning_rate": 8.725602226614121e-06, "loss": 0.22955283522605896, "step": 606 }, { "epoch": 2.4223107569721116, "grad_norm": 0.1564987748861313, "learning_rate": 8.668240529735192e-06, "loss": 0.31519001722335815, "step": 608 }, { "epoch": 2.4302788844621515, "grad_norm": 0.1200016587972641, "learning_rate": 8.610980190407958e-06, "loss": 0.5673627257347107, "step": 610 }, { "epoch": 2.4382470119521913, "grad_norm": 0.4733831584453583, "learning_rate": 8.55382369764034e-06, "loss": 0.5735291838645935, "step": 612 }, { "epoch": 2.446215139442231, "grad_norm": 0.24809062480926514, "learning_rate": 8.496773535926242e-06, "loss": 0.48819705843925476, "step": 614 }, { "epoch": 2.454183266932271, "grad_norm": 0.23611299693584442, "learning_rate": 8.439832185137529e-06, "loss": 0.6079992055892944, "step": 616 }, { "epoch": 2.462151394422311, "grad_norm": 0.5378892421722412, "learning_rate": 8.383002120416241e-06, "loss": 0.5205312371253967, "step": 618 }, { "epoch": 2.4701195219123506, "grad_norm": 0.9542695879936218, "learning_rate": 8.326285812067023e-06, "loss": 0.6372625827789307, "step": 620 }, { "epoch": 2.4780876494023905, "grad_norm": 0.2799975872039795, "learning_rate": 8.269685725449708e-06, "loss": 0.6172505021095276, "step": 622 }, { "epoch": 2.4860557768924303, "grad_norm": 0.3862285315990448, "learning_rate": 8.213204320872176e-06, "loss": 0.5968483090400696, "step": 624 }, { "epoch": 2.49402390438247, "grad_norm": 0.5129538774490356, "learning_rate": 8.156844053483412e-06, "loss": 0.3784622848033905, "step": 626 }, { "epoch": 2.50199203187251, "grad_norm": 0.3779292404651642, "learning_rate": 8.100607373166773e-06, "loss": 0.8131450414657593, "step": 628 }, { "epoch": 2.50996015936255, "grad_norm": 0.4691997468471527, "learning_rate": 8.044496724433493e-06, "loss": 0.3125261664390564, "step": 630 }, { "epoch": 2.5179282868525896, "grad_norm": 0.5302949547767639, "learning_rate": 7.988514546316437e-06, "loss": 0.3448098301887512, "step": 632 }, { "epoch": 2.5258964143426295, "grad_norm": 0.1989057958126068, "learning_rate": 7.932663272264079e-06, "loss": 0.7431591153144836, "step": 634 }, { "epoch": 2.5338645418326693, "grad_norm": 0.5413906574249268, "learning_rate": 7.87694533003471e-06, "loss": 0.7416322231292725, "step": 636 }, { "epoch": 2.541832669322709, "grad_norm": 1.4396048784255981, "learning_rate": 7.82136314159092e-06, "loss": 0.846419095993042, "step": 638 }, { "epoch": 2.549800796812749, "grad_norm": 0.1084892749786377, "learning_rate": 7.765919122994319e-06, "loss": 0.25195181369781494, "step": 640 }, { "epoch": 2.557768924302789, "grad_norm": 0.29752662777900696, "learning_rate": 7.710615684300518e-06, "loss": 0.7382107377052307, "step": 642 }, { "epoch": 2.5657370517928286, "grad_norm": 0.24190407991409302, "learning_rate": 7.655455229454354e-06, "loss": 0.635940670967102, "step": 644 }, { "epoch": 2.5737051792828685, "grad_norm": 0.2885357439517975, "learning_rate": 7.6004401561854e-06, "loss": 0.5441352725028992, "step": 646 }, { "epoch": 2.5816733067729083, "grad_norm": 0.23748569190502167, "learning_rate": 7.545572855903756e-06, "loss": 0.7378494143486023, "step": 648 }, { "epoch": 2.589641434262948, "grad_norm": 0.2785709500312805, "learning_rate": 7.490855713596081e-06, "loss": 0.530714213848114, "step": 650 }, { "epoch": 2.597609561752988, "grad_norm": 0.5807702541351318, "learning_rate": 7.4362911077219155e-06, "loss": 0.5005159974098206, "step": 652 }, { "epoch": 2.605577689243028, "grad_norm": 0.2538289725780487, "learning_rate": 7.381881410110326e-06, "loss": 0.5463607907295227, "step": 654 }, { "epoch": 2.6135458167330676, "grad_norm": 0.22152847051620483, "learning_rate": 7.327628985856765e-06, "loss": 0.24919743835926056, "step": 656 }, { "epoch": 2.6215139442231075, "grad_norm": 0.28966838121414185, "learning_rate": 7.2735361932202965e-06, "loss": 0.4710160791873932, "step": 658 }, { "epoch": 2.6294820717131473, "grad_norm": 0.1763993799686432, "learning_rate": 7.219605383521067e-06, "loss": 0.6233411431312561, "step": 660 }, { "epoch": 2.637450199203187, "grad_norm": 0.7920465469360352, "learning_rate": 7.165838901038107e-06, "loss": 0.4598224461078644, "step": 662 }, { "epoch": 2.645418326693227, "grad_norm": 0.7094170451164246, "learning_rate": 7.112239082907433e-06, "loss": 0.4155668318271637, "step": 664 }, { "epoch": 2.653386454183267, "grad_norm": 0.632438063621521, "learning_rate": 7.058808259020442e-06, "loss": 0.7042566537857056, "step": 666 }, { "epoch": 2.6613545816733066, "grad_norm": 0.07327423244714737, "learning_rate": 7.005548751922642e-06, "loss": 0.5448852181434631, "step": 668 }, { "epoch": 2.6693227091633465, "grad_norm": 0.7148383855819702, "learning_rate": 6.952462876712707e-06, "loss": 0.555755078792572, "step": 670 }, { "epoch": 2.6772908366533863, "grad_norm": 0.16552035510540009, "learning_rate": 6.899552940941829e-06, "loss": 0.32224544882774353, "step": 672 }, { "epoch": 2.685258964143426, "grad_norm": 0.19856727123260498, "learning_rate": 6.846821244513411e-06, "loss": 0.7318635582923889, "step": 674 }, { "epoch": 2.6932270916334664, "grad_norm": 1.2825974225997925, "learning_rate": 6.794270079583101e-06, "loss": 0.5470606088638306, "step": 676 }, { "epoch": 2.7011952191235062, "grad_norm": 0.27257922291755676, "learning_rate": 6.741901730459166e-06, "loss": 0.4405728280544281, "step": 678 }, { "epoch": 2.709163346613546, "grad_norm": 0.2471430003643036, "learning_rate": 6.68971847350317e-06, "loss": 0.7528946399688721, "step": 680 }, { "epoch": 2.717131474103586, "grad_norm": 0.18716691434383392, "learning_rate": 6.6377225770310514e-06, "loss": 0.7359815239906311, "step": 682 }, { "epoch": 2.7250996015936257, "grad_norm": 0.2724993824958801, "learning_rate": 6.585916301214519e-06, "loss": 0.6166096329689026, "step": 684 }, { "epoch": 2.7330677290836656, "grad_norm": 0.5736117362976074, "learning_rate": 6.534301897982774e-06, "loss": 0.34574300050735474, "step": 686 }, { "epoch": 2.7410358565737054, "grad_norm": 0.36433547735214233, "learning_rate": 6.482881610924674e-06, "loss": 0.7370812892913818, "step": 688 }, { "epoch": 2.7490039840637452, "grad_norm": 0.6445011496543884, "learning_rate": 6.43165767519117e-06, "loss": 0.4200422465801239, "step": 690 }, { "epoch": 2.756972111553785, "grad_norm": 0.21053896844387054, "learning_rate": 6.380632317398168e-06, "loss": 0.8655040264129639, "step": 692 }, { "epoch": 2.764940239043825, "grad_norm": 0.5006321668624878, "learning_rate": 6.3298077555297245e-06, "loss": 0.6684830784797668, "step": 694 }, { "epoch": 2.7729083665338647, "grad_norm": 0.5774354934692383, "learning_rate": 6.279186198841647e-06, "loss": 0.3922826945781708, "step": 696 }, { "epoch": 2.7808764940239046, "grad_norm": 0.26995721459388733, "learning_rate": 6.228769847765468e-06, "loss": 0.5536890625953674, "step": 698 }, { "epoch": 2.7888446215139444, "grad_norm": 0.23776452243328094, "learning_rate": 6.178560893812774e-06, "loss": 0.7791992425918579, "step": 700 }, { "epoch": 2.7968127490039842, "grad_norm": 0.2904581129550934, "learning_rate": 6.1285615194799695e-06, "loss": 0.4446163773536682, "step": 702 }, { "epoch": 2.804780876494024, "grad_norm": 0.421639621257782, "learning_rate": 6.0787738981533825e-06, "loss": 0.8279755711555481, "step": 704 }, { "epoch": 2.812749003984064, "grad_norm": 0.17597387731075287, "learning_rate": 6.0292001940148174e-06, "loss": 0.6989073753356934, "step": 706 }, { "epoch": 2.8207171314741037, "grad_norm": 0.34816116094589233, "learning_rate": 5.979842561947455e-06, "loss": 0.8355804681777954, "step": 708 }, { "epoch": 2.8286852589641436, "grad_norm": 0.3496198058128357, "learning_rate": 5.9307031474422074e-06, "loss": 0.40872952342033386, "step": 710 }, { "epoch": 2.8366533864541834, "grad_norm": 0.18613150715827942, "learning_rate": 5.88178408650445e-06, "loss": 0.786512553691864, "step": 712 }, { "epoch": 2.8446215139442232, "grad_norm": 0.22731350362300873, "learning_rate": 5.833087505561148e-06, "loss": 0.515406608581543, "step": 714 }, { "epoch": 2.852589641434263, "grad_norm": 0.23196466267108917, "learning_rate": 5.784615521368468e-06, "loss": 0.7110364437103271, "step": 716 }, { "epoch": 2.860557768924303, "grad_norm": 0.5354853868484497, "learning_rate": 5.736370240919735e-06, "loss": 0.6221070289611816, "step": 718 }, { "epoch": 2.8685258964143427, "grad_norm": 0.23798024654388428, "learning_rate": 5.688353761353862e-06, "loss": 0.4548286497592926, "step": 720 }, { "epoch": 2.8764940239043826, "grad_norm": 0.3904666602611542, "learning_rate": 5.640568169864173e-06, "loss": 0.6243053674697876, "step": 722 }, { "epoch": 2.8844621513944224, "grad_norm": 0.2565165162086487, "learning_rate": 5.5930155436076875e-06, "loss": 0.5322657823562622, "step": 724 }, { "epoch": 2.8924302788844622, "grad_norm": 0.2530430555343628, "learning_rate": 5.5456979496148385e-06, "loss": 0.7663798928260803, "step": 726 }, { "epoch": 2.900398406374502, "grad_norm": 0.16959309577941895, "learning_rate": 5.498617444699603e-06, "loss": 0.43766871094703674, "step": 728 }, { "epoch": 2.908366533864542, "grad_norm": 0.22881202399730682, "learning_rate": 5.451776075370114e-06, "loss": 0.7575075626373291, "step": 730 }, { "epoch": 2.9163346613545817, "grad_norm": 0.3499610126018524, "learning_rate": 5.405175877739684e-06, "loss": 0.2167886644601822, "step": 732 }, { "epoch": 2.9243027888446216, "grad_norm": 0.2587827146053314, "learning_rate": 5.3588188774383235e-06, "loss": 0.7638062834739685, "step": 734 }, { "epoch": 2.9322709163346614, "grad_norm": 6.78230619430542, "learning_rate": 5.3127070895246604e-06, "loss": 0.38801783323287964, "step": 736 }, { "epoch": 2.9402390438247012, "grad_norm": 0.454189658164978, "learning_rate": 5.266842518398369e-06, "loss": 0.48096776008605957, "step": 738 }, { "epoch": 2.948207171314741, "grad_norm": 0.15553335845470428, "learning_rate": 5.2212271577130495e-06, "loss": 0.7670390605926514, "step": 740 }, { "epoch": 2.956175298804781, "grad_norm": 0.9639060497283936, "learning_rate": 5.1758629902895375e-06, "loss": 0.2947346568107605, "step": 742 }, { "epoch": 2.9641434262948207, "grad_norm": 0.2185724526643753, "learning_rate": 5.1307519880297385e-06, "loss": 0.6777142882347107, "step": 744 }, { "epoch": 2.9721115537848606, "grad_norm": 0.2768959105014801, "learning_rate": 5.085896111830908e-06, "loss": 0.6605843305587769, "step": 746 }, { "epoch": 2.9800796812749004, "grad_norm": 2.2936131954193115, "learning_rate": 5.041297311500417e-06, "loss": 0.3630678653717041, "step": 748 }, { "epoch": 2.9880478087649402, "grad_norm": 0.1362890899181366, "learning_rate": 4.996957525670984e-06, "loss": 0.10604195296764374, "step": 750 }, { "epoch": 2.99601593625498, "grad_norm": 0.20433849096298218, "learning_rate": 4.952878681716416e-06, "loss": 0.7345473170280457, "step": 752 }, { "epoch": 3.00398406374502, "grad_norm": 0.17004388570785522, "learning_rate": 4.9090626956678355e-06, "loss": 0.3422149419784546, "step": 754 }, { "epoch": 3.0119521912350598, "grad_norm": 0.2881888747215271, "learning_rate": 4.865511472130379e-06, "loss": 0.2987087666988373, "step": 756 }, { "epoch": 3.0199203187250996, "grad_norm": 0.19474048912525177, "learning_rate": 4.822226904200422e-06, "loss": 0.15045982599258423, "step": 758 }, { "epoch": 3.0278884462151394, "grad_norm": 0.7018445730209351, "learning_rate": 4.779210873383273e-06, "loss": 0.27087539434432983, "step": 760 }, { "epoch": 3.0358565737051793, "grad_norm": 0.8737360835075378, "learning_rate": 4.7364652495114e-06, "loss": 0.30572089552879333, "step": 762 }, { "epoch": 3.043824701195219, "grad_norm": 0.26133912801742554, "learning_rate": 4.693991890663152e-06, "loss": 0.4084738492965698, "step": 764 }, { "epoch": 3.051792828685259, "grad_norm": 8.301016807556152, "learning_rate": 4.651792643081986e-06, "loss": 0.18451657891273499, "step": 766 }, { "epoch": 3.0597609561752988, "grad_norm": 0.5378907918930054, "learning_rate": 4.609869341096217e-06, "loss": 0.3146429657936096, "step": 768 }, { "epoch": 3.0677290836653386, "grad_norm": 0.3412659168243408, "learning_rate": 4.568223807039282e-06, "loss": 0.30809056758880615, "step": 770 }, { "epoch": 3.0756972111553784, "grad_norm": 0.2771482765674591, "learning_rate": 4.52685785117052e-06, "loss": 0.4607963562011719, "step": 772 }, { "epoch": 3.0836653386454183, "grad_norm": 0.4126575291156769, "learning_rate": 4.485773271596503e-06, "loss": 0.49278274178504944, "step": 774 }, { "epoch": 3.091633466135458, "grad_norm": 0.04616294056177139, "learning_rate": 4.444971854192848e-06, "loss": 0.24597768485546112, "step": 776 }, { "epoch": 3.099601593625498, "grad_norm": 0.30448517203330994, "learning_rate": 4.404455372526615e-06, "loss": 0.2769939601421356, "step": 778 }, { "epoch": 3.1075697211155378, "grad_norm": 0.18792293965816498, "learning_rate": 4.3642255877791876e-06, "loss": 0.4143436551094055, "step": 780 }, { "epoch": 3.1155378486055776, "grad_norm": 0.06721556931734085, "learning_rate": 4.324284248669742e-06, "loss": 0.10799065977334976, "step": 782 }, { "epoch": 3.1235059760956174, "grad_norm": 0.4881384074687958, "learning_rate": 4.2846330913792136e-06, "loss": 0.4812631905078888, "step": 784 }, { "epoch": 3.1314741035856573, "grad_norm": 0.21357056498527527, "learning_rate": 4.245273839474835e-06, "loss": 0.32228830456733704, "step": 786 }, { "epoch": 3.139442231075697, "grad_norm": 0.47251421213150024, "learning_rate": 4.20620820383523e-06, "loss": 0.24772438406944275, "step": 788 }, { "epoch": 3.147410358565737, "grad_norm": 0.19209767878055573, "learning_rate": 4.167437882576009e-06, "loss": 0.23071834444999695, "step": 790 }, { "epoch": 3.1553784860557768, "grad_norm": 0.61883944272995, "learning_rate": 4.128964560975993e-06, "loss": 0.33092373609542847, "step": 792 }, { "epoch": 3.1633466135458166, "grad_norm": 0.0391608402132988, "learning_rate": 4.090789911403938e-06, "loss": 0.16050046682357788, "step": 794 }, { "epoch": 3.1713147410358564, "grad_norm": 0.5372021794319153, "learning_rate": 4.0529155932458444e-06, "loss": 0.269602507352829, "step": 796 }, { "epoch": 3.1792828685258963, "grad_norm": 0.20864246785640717, "learning_rate": 4.015343252832824e-06, "loss": 0.3460035026073456, "step": 798 }, { "epoch": 3.187250996015936, "grad_norm": 0.2803748846054077, "learning_rate": 3.978074523369533e-06, "loss": 0.37516307830810547, "step": 800 }, { "epoch": 3.195219123505976, "grad_norm": 0.2299816906452179, "learning_rate": 3.941111024863193e-06, "loss": 0.31489038467407227, "step": 802 }, { "epoch": 3.2031872509960158, "grad_norm": 0.33568426966667175, "learning_rate": 3.90445436405316e-06, "loss": 0.2012202888727188, "step": 804 }, { "epoch": 3.2111553784860556, "grad_norm": 0.9808611869812012, "learning_rate": 3.86810613434109e-06, "loss": 0.31453871726989746, "step": 806 }, { "epoch": 3.2191235059760954, "grad_norm": 0.324074387550354, "learning_rate": 3.832067915721661e-06, "loss": 0.07974754273891449, "step": 808 }, { "epoch": 3.2270916334661353, "grad_norm": 0.22336483001708984, "learning_rate": 3.7963412747139204e-06, "loss": 0.3263242840766907, "step": 810 }, { "epoch": 3.235059760956175, "grad_norm": 0.3542936444282532, "learning_rate": 3.7609277642931642e-06, "loss": 0.29607632756233215, "step": 812 }, { "epoch": 3.243027888446215, "grad_norm": 0.2759454548358917, "learning_rate": 3.725828923823447e-06, "loss": 0.33567097783088684, "step": 814 }, { "epoch": 3.2509960159362548, "grad_norm": 0.4755600690841675, "learning_rate": 3.6910462789906697e-06, "loss": 0.09431050717830658, "step": 816 }, { "epoch": 3.2589641434262946, "grad_norm": 0.20680461823940277, "learning_rate": 3.6565813417362476e-06, "loss": 0.4055401682853699, "step": 818 }, { "epoch": 3.2669322709163344, "grad_norm": 0.9138600826263428, "learning_rate": 3.622435610191398e-06, "loss": 0.20273584127426147, "step": 820 }, { "epoch": 3.2749003984063743, "grad_norm": 0.5730777978897095, "learning_rate": 3.5886105686120267e-06, "loss": 0.1780012845993042, "step": 822 }, { "epoch": 3.2828685258964145, "grad_norm": 0.7623617053031921, "learning_rate": 3.5551076873141875e-06, "loss": 0.28569450974464417, "step": 824 }, { "epoch": 3.2908366533864544, "grad_norm": 1.4828463792800903, "learning_rate": 3.5219284226101992e-06, "loss": 0.39803627133369446, "step": 826 }, { "epoch": 3.298804780876494, "grad_norm": 0.29200655221939087, "learning_rate": 3.4890742167453134e-06, "loss": 0.4793969988822937, "step": 828 }, { "epoch": 3.306772908366534, "grad_norm": 0.2444511353969574, "learning_rate": 3.4565464978350447e-06, "loss": 0.3097003102302551, "step": 830 }, { "epoch": 3.314741035856574, "grad_norm": 0.5528002381324768, "learning_rate": 3.4243466798030813e-06, "loss": 0.22890320420265198, "step": 832 }, { "epoch": 3.3227091633466137, "grad_norm": 4.4813923835754395, "learning_rate": 3.3924761623198276e-06, "loss": 0.19244921207427979, "step": 834 }, { "epoch": 3.3306772908366535, "grad_norm": 1.2906057834625244, "learning_rate": 3.360936330741563e-06, "loss": 0.29527685046195984, "step": 836 }, { "epoch": 3.3386454183266934, "grad_norm": 0.35421115159988403, "learning_rate": 3.329728556050219e-06, "loss": 0.3484296202659607, "step": 838 }, { "epoch": 3.346613545816733, "grad_norm": 0.5174968242645264, "learning_rate": 3.2988541947937948e-06, "loss": 0.07454240322113037, "step": 840 }, { "epoch": 3.354581673306773, "grad_norm": 0.40611883997917175, "learning_rate": 3.2683145890273803e-06, "loss": 0.23899097740650177, "step": 842 }, { "epoch": 3.362549800796813, "grad_norm": 0.24479374289512634, "learning_rate": 3.2381110662548244e-06, "loss": 0.27959495782852173, "step": 844 }, { "epoch": 3.3705179282868527, "grad_norm": 0.22344236075878143, "learning_rate": 3.208244939371029e-06, "loss": 0.46563243865966797, "step": 846 }, { "epoch": 3.3784860557768925, "grad_norm": 0.23267343640327454, "learning_rate": 3.178717506604878e-06, "loss": 0.4335484206676483, "step": 848 }, { "epoch": 3.3864541832669324, "grad_norm": 0.48727282881736755, "learning_rate": 3.1495300514628137e-06, "loss": 0.3037354648113251, "step": 850 }, { "epoch": 3.394422310756972, "grad_norm": 0.1937863975763321, "learning_rate": 3.120683842673029e-06, "loss": 0.39072439074516296, "step": 852 }, { "epoch": 3.402390438247012, "grad_norm": 0.17964762449264526, "learning_rate": 3.092180134130341e-06, "loss": 0.23094308376312256, "step": 854 }, { "epoch": 3.410358565737052, "grad_norm": 0.24650037288665771, "learning_rate": 3.064020164841661e-06, "loss": 0.3446482717990875, "step": 856 }, { "epoch": 3.4183266932270917, "grad_norm": 0.23646335303783417, "learning_rate": 3.03620515887216e-06, "loss": 0.35580411553382874, "step": 858 }, { "epoch": 3.4262948207171315, "grad_norm": 0.2631300985813141, "learning_rate": 3.0087363252920392e-06, "loss": 0.46033039689064026, "step": 860 }, { "epoch": 3.4342629482071714, "grad_norm": 0.2255675047636032, "learning_rate": 2.9816148581239945e-06, "loss": 0.2841128408908844, "step": 862 }, { "epoch": 3.442231075697211, "grad_norm": 0.40002599358558655, "learning_rate": 2.954841936291304e-06, "loss": 0.1989145576953888, "step": 864 }, { "epoch": 3.450199203187251, "grad_norm": 0.28726738691329956, "learning_rate": 2.9284187235665706e-06, "loss": 0.3655410408973694, "step": 866 }, { "epoch": 3.458167330677291, "grad_norm": 0.2682865560054779, "learning_rate": 2.902346368521161e-06, "loss": 0.3438742756843567, "step": 868 }, { "epoch": 3.4661354581673307, "grad_norm": 0.3565802276134491, "learning_rate": 2.8766260044752596e-06, "loss": 0.3073749542236328, "step": 870 }, { "epoch": 3.4741035856573705, "grad_norm": 0.08676426857709885, "learning_rate": 2.851258749448613e-06, "loss": 0.27122408151626587, "step": 872 }, { "epoch": 3.4820717131474104, "grad_norm": 0.05536958575248718, "learning_rate": 2.8262457061119275e-06, "loss": 0.27671733498573303, "step": 874 }, { "epoch": 3.49003984063745, "grad_norm": 0.22093825042247772, "learning_rate": 2.801587961738936e-06, "loss": 0.20797447860240936, "step": 876 }, { "epoch": 3.49800796812749, "grad_norm": 0.21359281241893768, "learning_rate": 2.7772865881591487e-06, "loss": 0.2979479730129242, "step": 878 }, { "epoch": 3.50597609561753, "grad_norm": 0.06365374475717545, "learning_rate": 2.7533426417112463e-06, "loss": 0.15932877361774445, "step": 880 }, { "epoch": 3.5139442231075697, "grad_norm": 0.24570636451244354, "learning_rate": 2.729757163197175e-06, "loss": 0.14907409250736237, "step": 882 }, { "epoch": 3.5219123505976095, "grad_norm": 0.23951196670532227, "learning_rate": 2.706531177836896e-06, "loss": 0.055431462824344635, "step": 884 }, { "epoch": 3.5298804780876494, "grad_norm": 0.32212144136428833, "learning_rate": 2.683665695223827e-06, "loss": 0.4012114405632019, "step": 886 }, { "epoch": 3.537848605577689, "grad_norm": 0.43475180864334106, "learning_rate": 2.661161709280954e-06, "loss": 0.41531142592430115, "step": 888 }, { "epoch": 3.545816733067729, "grad_norm": 0.21227002143859863, "learning_rate": 2.6390201982176284e-06, "loss": 0.23185154795646667, "step": 890 }, { "epoch": 3.553784860557769, "grad_norm": 0.4116436541080475, "learning_rate": 2.617242124487048e-06, "loss": 0.27487894892692566, "step": 892 }, { "epoch": 3.5617529880478087, "grad_norm": 0.27092114090919495, "learning_rate": 2.595828434744411e-06, "loss": 0.6053402423858643, "step": 894 }, { "epoch": 3.5697211155378485, "grad_norm": 0.14917400479316711, "learning_rate": 2.574780059805779e-06, "loss": 0.13091327250003815, "step": 896 }, { "epoch": 3.5776892430278884, "grad_norm": 0.23728926479816437, "learning_rate": 2.5540979146076145e-06, "loss": 0.22477920353412628, "step": 898 }, { "epoch": 3.585657370517928, "grad_norm": 0.18915383517742157, "learning_rate": 2.5337828981669966e-06, "loss": 0.1279153823852539, "step": 900 }, { "epoch": 3.593625498007968, "grad_norm": 5.792757511138916, "learning_rate": 2.513835893542561e-06, "loss": 0.07770077139139175, "step": 902 }, { "epoch": 3.601593625498008, "grad_norm": 0.26535969972610474, "learning_rate": 2.494257767796101e-06, "loss": 0.25552132725715637, "step": 904 }, { "epoch": 3.6095617529880477, "grad_norm": 0.2751094102859497, "learning_rate": 2.475049371954888e-06, "loss": 0.2538408041000366, "step": 906 }, { "epoch": 3.6175298804780875, "grad_norm": 0.2262134999036789, "learning_rate": 2.4562115409746662e-06, "loss": 0.39591050148010254, "step": 908 }, { "epoch": 3.6254980079681274, "grad_norm": 0.5547113418579102, "learning_rate": 2.4377450937033753e-06, "loss": 0.3465615510940552, "step": 910 }, { "epoch": 3.633466135458167, "grad_norm": 0.02718132548034191, "learning_rate": 2.419650832845541e-06, "loss": 0.035255447030067444, "step": 912 }, { "epoch": 3.641434262948207, "grad_norm": 0.24443596601486206, "learning_rate": 2.40192954492739e-06, "loss": 0.32756558060646057, "step": 914 }, { "epoch": 3.649402390438247, "grad_norm": 0.7265999913215637, "learning_rate": 2.3845820002626623e-06, "loss": 0.46350619196891785, "step": 916 }, { "epoch": 3.6573705179282867, "grad_norm": 0.4776816666126251, "learning_rate": 2.3676089529191234e-06, "loss": 0.07077661156654358, "step": 918 }, { "epoch": 3.6653386454183265, "grad_norm": 0.20232045650482178, "learning_rate": 2.3510111406857915e-06, "loss": 0.39785465598106384, "step": 920 }, { "epoch": 3.6733067729083664, "grad_norm": 0.15803422033786774, "learning_rate": 2.3347892850408575e-06, "loss": 0.04493388533592224, "step": 922 }, { "epoch": 3.681274900398406, "grad_norm": 0.5451074838638306, "learning_rate": 2.3189440911203328e-06, "loss": 0.2891377806663513, "step": 924 }, { "epoch": 3.6892430278884465, "grad_norm": 0.25214695930480957, "learning_rate": 2.3034762476873973e-06, "loss": 0.1062634289264679, "step": 926 }, { "epoch": 3.6972111553784863, "grad_norm": 0.19340242445468903, "learning_rate": 2.2883864271024524e-06, "loss": 0.24871164560317993, "step": 928 }, { "epoch": 3.705179282868526, "grad_norm": 0.08524282276630402, "learning_rate": 2.273675285293905e-06, "loss": 0.3079362213611603, "step": 930 }, { "epoch": 3.713147410358566, "grad_norm": 0.25448575615882874, "learning_rate": 2.2593434617296474e-06, "loss": 0.40055978298187256, "step": 932 }, { "epoch": 3.721115537848606, "grad_norm": 0.2659413516521454, "learning_rate": 2.2453915793892665e-06, "loss": 0.207880437374115, "step": 934 }, { "epoch": 3.7290836653386457, "grad_norm": 0.4711718261241913, "learning_rate": 2.231820244736958e-06, "loss": 0.3966074585914612, "step": 936 }, { "epoch": 3.7370517928286855, "grad_norm": 0.378316193819046, "learning_rate": 2.2186300476951693e-06, "loss": 0.13356447219848633, "step": 938 }, { "epoch": 3.7450199203187253, "grad_norm": 0.36563411355018616, "learning_rate": 2.2058215616189578e-06, "loss": 0.4002578854560852, "step": 940 }, { "epoch": 3.752988047808765, "grad_norm": 0.19255155324935913, "learning_rate": 2.1933953432710588e-06, "loss": 0.1851278692483902, "step": 942 }, { "epoch": 3.760956175298805, "grad_norm": 0.5991054177284241, "learning_rate": 2.181351932797695e-06, "loss": 0.22668001055717468, "step": 944 }, { "epoch": 3.768924302788845, "grad_norm": 0.27312520146369934, "learning_rate": 2.169691853705094e-06, "loss": 0.503513514995575, "step": 946 }, { "epoch": 3.7768924302788847, "grad_norm": 0.4142235815525055, "learning_rate": 2.1584156128367303e-06, "loss": 0.24071785807609558, "step": 948 }, { "epoch": 3.7848605577689245, "grad_norm": 0.18473252654075623, "learning_rate": 2.147523700351291e-06, "loss": 0.45482662320137024, "step": 950 }, { "epoch": 3.7928286852589643, "grad_norm": 0.5160776972770691, "learning_rate": 2.137016589701375e-06, "loss": 0.4026782214641571, "step": 952 }, { "epoch": 3.800796812749004, "grad_norm": 0.1945013701915741, "learning_rate": 2.126894737612914e-06, "loss": 0.22027313709259033, "step": 954 }, { "epoch": 3.808764940239044, "grad_norm": 0.2659922242164612, "learning_rate": 2.117158584065313e-06, "loss": 0.3094702363014221, "step": 956 }, { "epoch": 3.816733067729084, "grad_norm": 0.6263967156410217, "learning_rate": 2.107808552272329e-06, "loss": 0.22783216834068298, "step": 958 }, { "epoch": 3.8247011952191237, "grad_norm": 0.739229679107666, "learning_rate": 2.0988450486636745e-06, "loss": 0.10933537036180496, "step": 960 }, { "epoch": 3.8326693227091635, "grad_norm": 0.11796502023935318, "learning_rate": 2.090268462867351e-06, "loss": 0.2737407386302948, "step": 962 }, { "epoch": 3.8406374501992033, "grad_norm": 0.324405699968338, "learning_rate": 2.0820791676927093e-06, "loss": 0.5360243916511536, "step": 964 }, { "epoch": 3.848605577689243, "grad_norm": 0.27081164717674255, "learning_rate": 2.0742775191142496e-06, "loss": 0.11796460300683975, "step": 966 }, { "epoch": 3.856573705179283, "grad_norm": 0.24643082916736603, "learning_rate": 2.066863856256143e-06, "loss": 0.32349953055381775, "step": 968 }, { "epoch": 3.864541832669323, "grad_norm": 0.519400954246521, "learning_rate": 2.0598385013774933e-06, "loss": 0.36574849486351013, "step": 970 }, { "epoch": 3.8725099601593627, "grad_norm": 0.08175357431173325, "learning_rate": 2.053201759858327e-06, "loss": 0.2654764950275421, "step": 972 }, { "epoch": 3.8804780876494025, "grad_norm": 0.06543279439210892, "learning_rate": 2.0469539201863224e-06, "loss": 0.20511119067668915, "step": 974 }, { "epoch": 3.8884462151394423, "grad_norm": 0.2162189483642578, "learning_rate": 2.0410952539442624e-06, "loss": 0.40130627155303955, "step": 976 }, { "epoch": 3.896414342629482, "grad_norm": 0.36298590898513794, "learning_rate": 2.0356260157982393e-06, "loss": 0.24650147557258606, "step": 978 }, { "epoch": 3.904382470119522, "grad_norm": 0.10040842741727829, "learning_rate": 2.030546443486575e-06, "loss": 0.21674096584320068, "step": 980 }, { "epoch": 3.912350597609562, "grad_norm": 0.2556758522987366, "learning_rate": 2.0258567578094947e-06, "loss": 0.13943469524383545, "step": 982 }, { "epoch": 3.9203187250996017, "grad_norm": 0.29577574133872986, "learning_rate": 2.0215571626195242e-06, "loss": 0.42601150274276733, "step": 984 }, { "epoch": 3.9282868525896415, "grad_norm": 0.7589325904846191, "learning_rate": 2.0176478448126306e-06, "loss": 0.10014528036117554, "step": 986 }, { "epoch": 3.9362549800796813, "grad_norm": 1.194295048713684, "learning_rate": 2.014128974320099e-06, "loss": 0.3184215724468231, "step": 988 }, { "epoch": 3.944223107569721, "grad_norm": 0.04314267635345459, "learning_rate": 2.011000704101143e-06, "loss": 0.2435295283794403, "step": 990 }, { "epoch": 3.952191235059761, "grad_norm": 0.2504766881465912, "learning_rate": 2.00826317013626e-06, "loss": 0.39633631706237793, "step": 992 }, { "epoch": 3.960159362549801, "grad_norm": 0.12079378962516785, "learning_rate": 2.0059164914213175e-06, "loss": 0.24968433380126953, "step": 994 }, { "epoch": 3.9681274900398407, "grad_norm": 0.3718486428260803, "learning_rate": 2.00396076996238e-06, "loss": 0.3612552285194397, "step": 996 }, { "epoch": 3.9760956175298805, "grad_norm": 0.06211717054247856, "learning_rate": 2.0023960907712782e-06, "loss": 0.2819835841655731, "step": 998 }, { "epoch": 3.9840637450199203, "grad_norm": 0.26942721009254456, "learning_rate": 2.0012225218619097e-06, "loss": 0.186215341091156, "step": 1000 }, { "epoch": 3.99203187250996, "grad_norm": 0.23093514144420624, "learning_rate": 2.0004401142472857e-06, "loss": 0.3859613537788391, "step": 1002 }, { "epoch": 4.0, "grad_norm": 0.09877736121416092, "learning_rate": 2.000048901937313e-06, "loss": 0.09256474673748016, "step": 1004 }, { "epoch": 4.0, "step": 1004, "total_flos": 4.038502240003031e+18, "train_loss": 0.7221255100283964, "train_runtime": 10668.4497, "train_samples_per_second": 5.647, "train_steps_per_second": 0.094 } ], "logging_steps": 2, "max_steps": 1004, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 99999, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 4.038502240003031e+18, "train_batch_size": 3, "trial_name": null, "trial_params": null }