{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 4.0, "eval_steps": 500, "global_step": 1804, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004434589800443459, "grad_norm": 3.654876470565796, "learning_rate": 5.494505494505495e-08, "loss": 1.8642040491104126, "step": 2 }, { "epoch": 0.008869179600886918, "grad_norm": 8.487046241760254, "learning_rate": 1.6483516483516484e-07, "loss": 2.128927230834961, "step": 4 }, { "epoch": 0.013303769401330377, "grad_norm": 5.926363945007324, "learning_rate": 2.7472527472527475e-07, "loss": 1.9033676385879517, "step": 6 }, { "epoch": 0.017738359201773836, "grad_norm": 1.700243353843689, "learning_rate": 3.846153846153847e-07, "loss": 1.8230125904083252, "step": 8 }, { "epoch": 0.022172949002217297, "grad_norm": 4.129543304443359, "learning_rate": 4.945054945054946e-07, "loss": 1.6371376514434814, "step": 10 }, { "epoch": 0.026607538802660754, "grad_norm": 2.8941972255706787, "learning_rate": 6.043956043956044e-07, "loss": 2.1972343921661377, "step": 12 }, { "epoch": 0.031042128603104215, "grad_norm": 6.371809005737305, "learning_rate": 7.142857142857143e-07, "loss": 1.9573174715042114, "step": 14 }, { "epoch": 0.03547671840354767, "grad_norm": 7.418441295623779, "learning_rate": 8.241758241758242e-07, "loss": 1.5130360126495361, "step": 16 }, { "epoch": 0.03991130820399113, "grad_norm": 1.8268234729766846, "learning_rate": 9.340659340659342e-07, "loss": 1.441575527191162, "step": 18 }, { "epoch": 0.04434589800443459, "grad_norm": 8.918134689331055, "learning_rate": 1.0439560439560442e-06, "loss": 1.6151642799377441, "step": 20 }, { "epoch": 0.04878048780487805, "grad_norm": 7.498224258422852, "learning_rate": 1.153846153846154e-06, "loss": 1.4749759435653687, "step": 22 }, { "epoch": 0.05321507760532151, "grad_norm": 1.2202322483062744, "learning_rate": 1.2637362637362637e-06, "loss": 1.5966670513153076, "step": 24 }, { "epoch": 0.057649667405764965, "grad_norm": 1.1278345584869385, "learning_rate": 1.3736263736263738e-06, "loss": 1.5051370859146118, "step": 26 }, { "epoch": 0.06208425720620843, "grad_norm": 1.166769027709961, "learning_rate": 1.4835164835164837e-06, "loss": 1.1861467361450195, "step": 28 }, { "epoch": 0.06651884700665188, "grad_norm": 1.2690566778182983, "learning_rate": 1.5934065934065933e-06, "loss": 1.3006117343902588, "step": 30 }, { "epoch": 0.07095343680709534, "grad_norm": 2.7064690589904785, "learning_rate": 1.7032967032967034e-06, "loss": 1.2063751220703125, "step": 32 }, { "epoch": 0.07538802660753881, "grad_norm": 0.8439352512359619, "learning_rate": 1.8131868131868133e-06, "loss": 1.574849247932434, "step": 34 }, { "epoch": 0.07982261640798226, "grad_norm": 3.7528631687164307, "learning_rate": 1.9230769230769234e-06, "loss": 1.334853172302246, "step": 36 }, { "epoch": 0.08425720620842572, "grad_norm": 2.2949788570404053, "learning_rate": 2.032967032967033e-06, "loss": 1.5959619283676147, "step": 38 }, { "epoch": 0.08869179600886919, "grad_norm": 2.2293429374694824, "learning_rate": 2.1428571428571427e-06, "loss": 0.8560835719108582, "step": 40 }, { "epoch": 0.09312638580931264, "grad_norm": 1.0512415170669556, "learning_rate": 2.252747252747253e-06, "loss": 1.4596399068832397, "step": 42 }, { "epoch": 0.0975609756097561, "grad_norm": 2.0517866611480713, "learning_rate": 2.362637362637363e-06, "loss": 1.403381109237671, "step": 44 }, { "epoch": 0.10199556541019955, "grad_norm": 1.8148796558380127, "learning_rate": 2.472527472527473e-06, "loss": 1.419820785522461, "step": 46 }, { "epoch": 0.10643015521064302, "grad_norm": 2.2042646408081055, "learning_rate": 2.582417582417583e-06, "loss": 1.6194192171096802, "step": 48 }, { "epoch": 0.11086474501108648, "grad_norm": 1.0148158073425293, "learning_rate": 2.6923076923076923e-06, "loss": 1.4980335235595703, "step": 50 }, { "epoch": 0.11529933481152993, "grad_norm": 2.0108230113983154, "learning_rate": 2.8021978021978024e-06, "loss": 1.4199347496032715, "step": 52 }, { "epoch": 0.1197339246119734, "grad_norm": 1.539353847503662, "learning_rate": 2.9120879120879125e-06, "loss": 1.4115248918533325, "step": 54 }, { "epoch": 0.12416851441241686, "grad_norm": 15.816386222839355, "learning_rate": 3.021978021978022e-06, "loss": 1.1549075841903687, "step": 56 }, { "epoch": 0.1286031042128603, "grad_norm": 1.0177377462387085, "learning_rate": 3.1318681318681323e-06, "loss": 1.3620848655700684, "step": 58 }, { "epoch": 0.13303769401330376, "grad_norm": 0.6448049545288086, "learning_rate": 3.2417582417582424e-06, "loss": 1.4034713506698608, "step": 60 }, { "epoch": 0.13747228381374724, "grad_norm": 1.29705810546875, "learning_rate": 3.3516483516483516e-06, "loss": 1.367940068244934, "step": 62 }, { "epoch": 0.1419068736141907, "grad_norm": 2.276944637298584, "learning_rate": 3.4615384615384617e-06, "loss": 1.4364449977874756, "step": 64 }, { "epoch": 0.14634146341463414, "grad_norm": 1.4872463941574097, "learning_rate": 3.5714285714285718e-06, "loss": 1.4937427043914795, "step": 66 }, { "epoch": 0.15077605321507762, "grad_norm": 1.1286942958831787, "learning_rate": 3.681318681318682e-06, "loss": 1.3563040494918823, "step": 68 }, { "epoch": 0.15521064301552107, "grad_norm": 1.185439109802246, "learning_rate": 3.7912087912087915e-06, "loss": 1.3079450130462646, "step": 70 }, { "epoch": 0.15964523281596452, "grad_norm": 1.4064218997955322, "learning_rate": 3.901098901098901e-06, "loss": 1.3620179891586304, "step": 72 }, { "epoch": 0.164079822616408, "grad_norm": 1.5207171440124512, "learning_rate": 4.010989010989012e-06, "loss": 1.2632296085357666, "step": 74 }, { "epoch": 0.16851441241685144, "grad_norm": 1.1961833238601685, "learning_rate": 4.120879120879121e-06, "loss": 1.3436288833618164, "step": 76 }, { "epoch": 0.1729490022172949, "grad_norm": 1.7947943210601807, "learning_rate": 4.230769230769231e-06, "loss": 1.3881783485412598, "step": 78 }, { "epoch": 0.17738359201773837, "grad_norm": 1.8594613075256348, "learning_rate": 4.340659340659341e-06, "loss": 1.3418405055999756, "step": 80 }, { "epoch": 0.18181818181818182, "grad_norm": 2.344498872756958, "learning_rate": 4.45054945054945e-06, "loss": 0.8364058136940002, "step": 82 }, { "epoch": 0.18625277161862527, "grad_norm": 1.0296517610549927, "learning_rate": 4.560439560439561e-06, "loss": 1.0285269021987915, "step": 84 }, { "epoch": 0.19068736141906872, "grad_norm": 2.831413507461548, "learning_rate": 4.6703296703296706e-06, "loss": 0.9984404444694519, "step": 86 }, { "epoch": 0.1951219512195122, "grad_norm": 1.0203207731246948, "learning_rate": 4.780219780219781e-06, "loss": 1.2625550031661987, "step": 88 }, { "epoch": 0.19955654101995565, "grad_norm": 2.5028977394104004, "learning_rate": 4.890109890109891e-06, "loss": 1.3904521465301514, "step": 90 }, { "epoch": 0.2039911308203991, "grad_norm": 1.2700505256652832, "learning_rate": 5e-06, "loss": 1.2553861141204834, "step": 92 }, { "epoch": 0.20842572062084258, "grad_norm": 0.8640641570091248, "learning_rate": 4.999984864490455e-06, "loss": 1.2549915313720703, "step": 94 }, { "epoch": 0.21286031042128603, "grad_norm": 2.820838212966919, "learning_rate": 4.999939458165447e-06, "loss": 1.7880680561065674, "step": 96 }, { "epoch": 0.21729490022172948, "grad_norm": 1.3258427381515503, "learning_rate": 4.999863781635863e-06, "loss": 0.9339628219604492, "step": 98 }, { "epoch": 0.22172949002217296, "grad_norm": 0.881152868270874, "learning_rate": 4.999757835919841e-06, "loss": 1.150363564491272, "step": 100 }, { "epoch": 0.2261640798226164, "grad_norm": 0.9821615219116211, "learning_rate": 4.9996216224427495e-06, "loss": 1.3016384840011597, "step": 102 }, { "epoch": 0.23059866962305986, "grad_norm": 2.3708696365356445, "learning_rate": 4.999455143037178e-06, "loss": 1.038110375404358, "step": 104 }, { "epoch": 0.23503325942350334, "grad_norm": 1.0569431781768799, "learning_rate": 4.999258399942903e-06, "loss": 1.2825589179992676, "step": 106 }, { "epoch": 0.2394678492239468, "grad_norm": 1.5671284198760986, "learning_rate": 4.9990313958068645e-06, "loss": 1.477828860282898, "step": 108 }, { "epoch": 0.24390243902439024, "grad_norm": 1.4664688110351562, "learning_rate": 4.998774133683127e-06, "loss": 1.0344974994659424, "step": 110 }, { "epoch": 0.24833702882483372, "grad_norm": 2.032390594482422, "learning_rate": 4.9984866170328426e-06, "loss": 1.2917076349258423, "step": 112 }, { "epoch": 0.25277161862527714, "grad_norm": 1.4232149124145508, "learning_rate": 4.998168849724196e-06, "loss": 0.7877748012542725, "step": 114 }, { "epoch": 0.2572062084257206, "grad_norm": 1.1114603281021118, "learning_rate": 4.997820836032363e-06, "loss": 1.3067116737365723, "step": 116 }, { "epoch": 0.2616407982261641, "grad_norm": 0.5859808325767517, "learning_rate": 4.997442580639443e-06, "loss": 1.0599734783172607, "step": 118 }, { "epoch": 0.2660753880266075, "grad_norm": 1.1004986763000488, "learning_rate": 4.997034088634404e-06, "loss": 1.253132700920105, "step": 120 }, { "epoch": 0.270509977827051, "grad_norm": 1.7587755918502808, "learning_rate": 4.996595365513012e-06, "loss": 1.1558163166046143, "step": 122 }, { "epoch": 0.2749445676274945, "grad_norm": 1.6989275217056274, "learning_rate": 4.9961264171777515e-06, "loss": 1.5596798658370972, "step": 124 }, { "epoch": 0.2793791574279379, "grad_norm": 1.1851608753204346, "learning_rate": 4.995627249937755e-06, "loss": 0.9473103284835815, "step": 126 }, { "epoch": 0.2838137472283814, "grad_norm": 1.4158447980880737, "learning_rate": 4.995097870508711e-06, "loss": 1.1967135667800903, "step": 128 }, { "epoch": 0.28824833702882485, "grad_norm": 1.3109447956085205, "learning_rate": 4.994538286012777e-06, "loss": 0.9262881875038147, "step": 130 }, { "epoch": 0.2926829268292683, "grad_norm": 2.214419364929199, "learning_rate": 4.993948503978484e-06, "loss": 0.9783093333244324, "step": 132 }, { "epoch": 0.29711751662971175, "grad_norm": 3.2269115447998047, "learning_rate": 4.993328532340633e-06, "loss": 0.9716333150863647, "step": 134 }, { "epoch": 0.30155210643015523, "grad_norm": 11.220888137817383, "learning_rate": 4.99267837944019e-06, "loss": 1.1295907497406006, "step": 136 }, { "epoch": 0.30598669623059865, "grad_norm": 12.861579895019531, "learning_rate": 4.991998054024172e-06, "loss": 0.8071277141571045, "step": 138 }, { "epoch": 0.31042128603104213, "grad_norm": 2.3948023319244385, "learning_rate": 4.991287565245534e-06, "loss": 1.0442757606506348, "step": 140 }, { "epoch": 0.3148558758314856, "grad_norm": 8.661370277404785, "learning_rate": 4.990546922663039e-06, "loss": 0.9572257995605469, "step": 142 }, { "epoch": 0.31929046563192903, "grad_norm": 3.8054051399230957, "learning_rate": 4.989776136241134e-06, "loss": 0.9722259044647217, "step": 144 }, { "epoch": 0.3237250554323725, "grad_norm": 1.0706456899642944, "learning_rate": 4.988975216349814e-06, "loss": 0.9358381032943726, "step": 146 }, { "epoch": 0.328159645232816, "grad_norm": 1.808540940284729, "learning_rate": 4.988144173764486e-06, "loss": 1.3917360305786133, "step": 148 }, { "epoch": 0.3325942350332594, "grad_norm": 2.059934139251709, "learning_rate": 4.987283019665817e-06, "loss": 1.1396145820617676, "step": 150 }, { "epoch": 0.3370288248337029, "grad_norm": 2.9052047729492188, "learning_rate": 4.986391765639592e-06, "loss": 1.0867761373519897, "step": 152 }, { "epoch": 0.34146341463414637, "grad_norm": 1.053331732749939, "learning_rate": 4.985470423676551e-06, "loss": 1.2601056098937988, "step": 154 }, { "epoch": 0.3458980044345898, "grad_norm": 2.696256399154663, "learning_rate": 4.984519006172232e-06, "loss": 1.2030073404312134, "step": 156 }, { "epoch": 0.35033259423503327, "grad_norm": 0.9389686584472656, "learning_rate": 4.983537525926804e-06, "loss": 1.2913192510604858, "step": 158 }, { "epoch": 0.35476718403547675, "grad_norm": 1.6440863609313965, "learning_rate": 4.982525996144891e-06, "loss": 1.0989590883255005, "step": 160 }, { "epoch": 0.35920177383592017, "grad_norm": 0.938507616519928, "learning_rate": 4.981484430435399e-06, "loss": 0.8731570839881897, "step": 162 }, { "epoch": 0.36363636363636365, "grad_norm": 3.254096508026123, "learning_rate": 4.98041284281133e-06, "loss": 0.8694003224372864, "step": 164 }, { "epoch": 0.36807095343680707, "grad_norm": 0.8564817309379578, "learning_rate": 4.979311247689596e-06, "loss": 1.2683701515197754, "step": 166 }, { "epoch": 0.37250554323725055, "grad_norm": 1.8692625761032104, "learning_rate": 4.978179659890821e-06, "loss": 1.1822130680084229, "step": 168 }, { "epoch": 0.376940133037694, "grad_norm": 1.4104257822036743, "learning_rate": 4.977018094639146e-06, "loss": 1.240437626838684, "step": 170 }, { "epoch": 0.38137472283813745, "grad_norm": 2.1901957988739014, "learning_rate": 4.975826567562023e-06, "loss": 0.7567204236984253, "step": 172 }, { "epoch": 0.3858093126385809, "grad_norm": 2.066593647003174, "learning_rate": 4.97460509469e-06, "loss": 1.6173328161239624, "step": 174 }, { "epoch": 0.3902439024390244, "grad_norm": 1.6422075033187866, "learning_rate": 4.973353692456513e-06, "loss": 1.2616726160049438, "step": 176 }, { "epoch": 0.3946784922394678, "grad_norm": 2.5441336631774902, "learning_rate": 4.972072377697661e-06, "loss": 1.3162559270858765, "step": 178 }, { "epoch": 0.3991130820399113, "grad_norm": 0.5965206027030945, "learning_rate": 4.9707611676519775e-06, "loss": 1.0434683561325073, "step": 180 }, { "epoch": 0.4035476718403548, "grad_norm": 1.4375978708267212, "learning_rate": 4.969420079960203e-06, "loss": 1.2631562948226929, "step": 182 }, { "epoch": 0.4079822616407982, "grad_norm": 1.5910781621932983, "learning_rate": 4.968049132665045e-06, "loss": 0.9169143438339233, "step": 184 }, { "epoch": 0.4124168514412417, "grad_norm": 1.1630430221557617, "learning_rate": 4.966648344210936e-06, "loss": 0.9765180945396423, "step": 186 }, { "epoch": 0.41685144124168516, "grad_norm": 0.955808699131012, "learning_rate": 4.965217733443782e-06, "loss": 0.9666871428489685, "step": 188 }, { "epoch": 0.4212860310421286, "grad_norm": 8.470755577087402, "learning_rate": 4.963757319610716e-06, "loss": 0.9839523434638977, "step": 190 }, { "epoch": 0.42572062084257206, "grad_norm": 2.580411672592163, "learning_rate": 4.962267122359835e-06, "loss": 0.8509742617607117, "step": 192 }, { "epoch": 0.43015521064301554, "grad_norm": 1.3341411352157593, "learning_rate": 4.960747161739931e-06, "loss": 1.269567608833313, "step": 194 }, { "epoch": 0.43458980044345896, "grad_norm": 1.2975329160690308, "learning_rate": 4.9591974582002324e-06, "loss": 1.5401256084442139, "step": 196 }, { "epoch": 0.43902439024390244, "grad_norm": 2.489485740661621, "learning_rate": 4.957618032590118e-06, "loss": 1.2710596323013306, "step": 198 }, { "epoch": 0.4434589800443459, "grad_norm": 0.6644977927207947, "learning_rate": 4.956008906158842e-06, "loss": 1.1192097663879395, "step": 200 }, { "epoch": 0.44789356984478934, "grad_norm": 1.3568873405456543, "learning_rate": 4.954370100555249e-06, "loss": 1.2545751333236694, "step": 202 }, { "epoch": 0.4523281596452328, "grad_norm": 1.7675485610961914, "learning_rate": 4.952701637827476e-06, "loss": 1.2129216194152832, "step": 204 }, { "epoch": 0.4567627494456763, "grad_norm": 0.9738250374794006, "learning_rate": 4.951003540422668e-06, "loss": 1.0656797885894775, "step": 206 }, { "epoch": 0.4611973392461197, "grad_norm": 1.6657801866531372, "learning_rate": 4.949275831186663e-06, "loss": 1.0429651737213135, "step": 208 }, { "epoch": 0.4656319290465632, "grad_norm": 2.380303382873535, "learning_rate": 4.947518533363691e-06, "loss": 0.6534411311149597, "step": 210 }, { "epoch": 0.4700665188470067, "grad_norm": 3.069462299346924, "learning_rate": 4.945731670596062e-06, "loss": 0.8374763131141663, "step": 212 }, { "epoch": 0.4745011086474501, "grad_norm": 0.9472932815551758, "learning_rate": 4.943915266923845e-06, "loss": 1.0585463047027588, "step": 214 }, { "epoch": 0.4789356984478936, "grad_norm": 0.9892237186431885, "learning_rate": 4.942069346784547e-06, "loss": 1.0768964290618896, "step": 216 }, { "epoch": 0.48337028824833705, "grad_norm": 0.8981955051422119, "learning_rate": 4.940193935012785e-06, "loss": 1.110266923904419, "step": 218 }, { "epoch": 0.4878048780487805, "grad_norm": 4.676793575286865, "learning_rate": 4.938289056839946e-06, "loss": 1.206817865371704, "step": 220 }, { "epoch": 0.49223946784922396, "grad_norm": 1.3366749286651611, "learning_rate": 4.936354737893854e-06, "loss": 1.227997899055481, "step": 222 }, { "epoch": 0.49667405764966743, "grad_norm": 0.8297674059867859, "learning_rate": 4.934391004198424e-06, "loss": 1.1951391696929932, "step": 224 }, { "epoch": 0.5011086474501109, "grad_norm": 0.9005066156387329, "learning_rate": 4.932397882173307e-06, "loss": 1.2028762102127075, "step": 226 }, { "epoch": 0.5055432372505543, "grad_norm": 0.83659428358078, "learning_rate": 4.930375398633543e-06, "loss": 1.2505710124969482, "step": 228 }, { "epoch": 0.5099778270509978, "grad_norm": 1.2538983821868896, "learning_rate": 4.928323580789192e-06, "loss": 1.842966914176941, "step": 230 }, { "epoch": 0.5144124168514412, "grad_norm": 1.6254911422729492, "learning_rate": 4.926242456244973e-06, "loss": 0.8636565804481506, "step": 232 }, { "epoch": 0.5188470066518847, "grad_norm": 1.2163554430007935, "learning_rate": 4.924132052999892e-06, "loss": 1.2652028799057007, "step": 234 }, { "epoch": 0.5232815964523282, "grad_norm": 0.7137370109558105, "learning_rate": 4.921992399446861e-06, "loss": 0.9469624757766724, "step": 236 }, { "epoch": 0.5277161862527716, "grad_norm": 4.001765727996826, "learning_rate": 4.919823524372323e-06, "loss": 0.9857266545295715, "step": 238 }, { "epoch": 0.532150776053215, "grad_norm": 1.0323377847671509, "learning_rate": 4.91762545695586e-06, "loss": 1.258691430091858, "step": 240 }, { "epoch": 0.5365853658536586, "grad_norm": 0.9117689728736877, "learning_rate": 4.9153982267698e-06, "loss": 1.3205041885375977, "step": 242 }, { "epoch": 0.541019955654102, "grad_norm": 3.387061357498169, "learning_rate": 4.913141863778822e-06, "loss": 0.9653130173683167, "step": 244 }, { "epoch": 0.5454545454545454, "grad_norm": 1.0343185663223267, "learning_rate": 4.910856398339553e-06, "loss": 1.261291742324829, "step": 246 }, { "epoch": 0.549889135254989, "grad_norm": 1.0249489545822144, "learning_rate": 4.9085418612001545e-06, "loss": 1.4818992614746094, "step": 248 }, { "epoch": 0.5543237250554324, "grad_norm": 1.422224521636963, "learning_rate": 4.906198283499916e-06, "loss": 1.219714879989624, "step": 250 }, { "epoch": 0.5587583148558758, "grad_norm": 4.456541538238525, "learning_rate": 4.903825696768829e-06, "loss": 0.6861237287521362, "step": 252 }, { "epoch": 0.5631929046563193, "grad_norm": 2.3371129035949707, "learning_rate": 4.901424132927172e-06, "loss": 1.4689810276031494, "step": 254 }, { "epoch": 0.5676274944567627, "grad_norm": 1.2416448593139648, "learning_rate": 4.898993624285069e-06, "loss": 1.321006417274475, "step": 256 }, { "epoch": 0.5720620842572062, "grad_norm": 0.8489322662353516, "learning_rate": 4.896534203542062e-06, "loss": 1.2481799125671387, "step": 258 }, { "epoch": 0.5764966740576497, "grad_norm": 1.086107611656189, "learning_rate": 4.894045903786675e-06, "loss": 1.280672311782837, "step": 260 }, { "epoch": 0.5809312638580931, "grad_norm": 2.334581136703491, "learning_rate": 4.891528758495961e-06, "loss": 0.7310733199119568, "step": 262 }, { "epoch": 0.5853658536585366, "grad_norm": 1.0172513723373413, "learning_rate": 4.888982801535053e-06, "loss": 1.364458680152893, "step": 264 }, { "epoch": 0.5898004434589801, "grad_norm": 1.2178974151611328, "learning_rate": 4.886408067156712e-06, "loss": 1.048864722251892, "step": 266 }, { "epoch": 0.5942350332594235, "grad_norm": 1.2515499591827393, "learning_rate": 4.883804590000865e-06, "loss": 1.5365700721740723, "step": 268 }, { "epoch": 0.5986696230598669, "grad_norm": 2.658390998840332, "learning_rate": 4.881172405094138e-06, "loss": 1.1716382503509521, "step": 270 }, { "epoch": 0.6031042128603105, "grad_norm": 0.843982458114624, "learning_rate": 4.878511547849383e-06, "loss": 1.2317594289779663, "step": 272 }, { "epoch": 0.6075388026607539, "grad_norm": 2.4913628101348877, "learning_rate": 4.875822054065203e-06, "loss": 1.2178195714950562, "step": 274 }, { "epoch": 0.6119733924611973, "grad_norm": 0.900059163570404, "learning_rate": 4.8731039599254754e-06, "loss": 1.2188351154327393, "step": 276 }, { "epoch": 0.6164079822616408, "grad_norm": 4.912473678588867, "learning_rate": 4.870357301998856e-06, "loss": 1.2045741081237793, "step": 278 }, { "epoch": 0.6208425720620843, "grad_norm": 0.8861173987388611, "learning_rate": 4.867582117238294e-06, "loss": 1.2807667255401611, "step": 280 }, { "epoch": 0.6252771618625277, "grad_norm": 13.176647186279297, "learning_rate": 4.864778442980532e-06, "loss": 0.8604080677032471, "step": 282 }, { "epoch": 0.6297117516629712, "grad_norm": 0.9435498118400574, "learning_rate": 4.861946316945605e-06, "loss": 1.248250961303711, "step": 284 }, { "epoch": 0.6341463414634146, "grad_norm": 1.3723853826522827, "learning_rate": 4.859085777236331e-06, "loss": 1.3286021947860718, "step": 286 }, { "epoch": 0.6385809312638581, "grad_norm": 0.926493227481842, "learning_rate": 4.8561968623377985e-06, "loss": 1.2437561750411987, "step": 288 }, { "epoch": 0.6430155210643016, "grad_norm": 0.6830118894577026, "learning_rate": 4.853279611116852e-06, "loss": 1.2304435968399048, "step": 290 }, { "epoch": 0.647450110864745, "grad_norm": 1.291746973991394, "learning_rate": 4.850334062821566e-06, "loss": 1.350826382637024, "step": 292 }, { "epoch": 0.6518847006651884, "grad_norm": 3.118695020675659, "learning_rate": 4.8473602570807185e-06, "loss": 0.9130444526672363, "step": 294 }, { "epoch": 0.656319290465632, "grad_norm": 1.9869314432144165, "learning_rate": 4.844358233903254e-06, "loss": 0.9922571778297424, "step": 296 }, { "epoch": 0.6607538802660754, "grad_norm": 1.162611961364746, "learning_rate": 4.841328033677753e-06, "loss": 1.2070796489715576, "step": 298 }, { "epoch": 0.6651884700665188, "grad_norm": 0.9664815664291382, "learning_rate": 4.83826969717188e-06, "loss": 1.2433284521102905, "step": 300 }, { "epoch": 0.6696230598669624, "grad_norm": 0.793887197971344, "learning_rate": 4.835183265531843e-06, "loss": 1.1951156854629517, "step": 302 }, { "epoch": 0.6740576496674058, "grad_norm": 1.1093353033065796, "learning_rate": 4.832068780281831e-06, "loss": 1.2604377269744873, "step": 304 }, { "epoch": 0.6784922394678492, "grad_norm": 1.292920470237732, "learning_rate": 4.828926283323464e-06, "loss": 1.2320196628570557, "step": 306 }, { "epoch": 0.6829268292682927, "grad_norm": 0.9268571138381958, "learning_rate": 4.8257558169352254e-06, "loss": 0.8704907894134521, "step": 308 }, { "epoch": 0.6873614190687362, "grad_norm": 1.2235312461853027, "learning_rate": 4.8225574237718906e-06, "loss": 1.2371546030044556, "step": 310 }, { "epoch": 0.6917960088691796, "grad_norm": 0.9682984352111816, "learning_rate": 4.819331146863958e-06, "loss": 1.2055768966674805, "step": 312 }, { "epoch": 0.6962305986696231, "grad_norm": 0.6748729348182678, "learning_rate": 4.8160770296170685e-06, "loss": 1.225193977355957, "step": 314 }, { "epoch": 0.7006651884700665, "grad_norm": 1.018369197845459, "learning_rate": 4.812795115811419e-06, "loss": 1.330003261566162, "step": 316 }, { "epoch": 0.70509977827051, "grad_norm": 1.0128453969955444, "learning_rate": 4.809485449601177e-06, "loss": 0.991382360458374, "step": 318 }, { "epoch": 0.7095343680709535, "grad_norm": 1.3138883113861084, "learning_rate": 4.806148075513883e-06, "loss": 0.9641591310501099, "step": 320 }, { "epoch": 0.7139689578713969, "grad_norm": 1.802852988243103, "learning_rate": 4.802783038449857e-06, "loss": 1.0050233602523804, "step": 322 }, { "epoch": 0.7184035476718403, "grad_norm": 1.2100204229354858, "learning_rate": 4.799390383681587e-06, "loss": 1.0627820491790771, "step": 324 }, { "epoch": 0.7228381374722838, "grad_norm": 2.972120761871338, "learning_rate": 4.795970156853124e-06, "loss": 1.1004713773727417, "step": 326 }, { "epoch": 0.7272727272727273, "grad_norm": 1.5077686309814453, "learning_rate": 4.792522403979471e-06, "loss": 0.8185582160949707, "step": 328 }, { "epoch": 0.7317073170731707, "grad_norm": 1.4305667877197266, "learning_rate": 4.789047171445957e-06, "loss": 0.8279497623443604, "step": 330 }, { "epoch": 0.7361419068736141, "grad_norm": 3.0829317569732666, "learning_rate": 4.785544506007619e-06, "loss": 1.3781704902648926, "step": 332 }, { "epoch": 0.7405764966740577, "grad_norm": 5.511263370513916, "learning_rate": 4.782014454788566e-06, "loss": 1.190948724746704, "step": 334 }, { "epoch": 0.7450110864745011, "grad_norm": 0.6818461418151855, "learning_rate": 4.778457065281355e-06, "loss": 1.2204951047897339, "step": 336 }, { "epoch": 0.7494456762749445, "grad_norm": 8.291729927062988, "learning_rate": 4.774872385346345e-06, "loss": 0.6817957162857056, "step": 338 }, { "epoch": 0.753880266075388, "grad_norm": 3.502612590789795, "learning_rate": 4.7712604632110524e-06, "loss": 0.32471054792404175, "step": 340 }, { "epoch": 0.7583148558758315, "grad_norm": 1.0008634328842163, "learning_rate": 4.767621347469506e-06, "loss": 0.8657422065734863, "step": 342 }, { "epoch": 0.7627494456762749, "grad_norm": 1.1472429037094116, "learning_rate": 4.7639550870815895e-06, "loss": 1.2735161781311035, "step": 344 }, { "epoch": 0.7671840354767184, "grad_norm": 0.7090339660644531, "learning_rate": 4.760261731372388e-06, "loss": 1.225376844406128, "step": 346 }, { "epoch": 0.7716186252771619, "grad_norm": 0.8595665693283081, "learning_rate": 4.75654133003152e-06, "loss": 1.0870047807693481, "step": 348 }, { "epoch": 0.7760532150776053, "grad_norm": 1.020011305809021, "learning_rate": 4.752793933112469e-06, "loss": 1.2136049270629883, "step": 350 }, { "epoch": 0.7804878048780488, "grad_norm": 2.301769971847534, "learning_rate": 4.749019591031914e-06, "loss": 1.139218807220459, "step": 352 }, { "epoch": 0.7849223946784922, "grad_norm": 1.7465238571166992, "learning_rate": 4.745218354569045e-06, "loss": 1.0103105306625366, "step": 354 }, { "epoch": 0.7893569844789357, "grad_norm": 6.574288368225098, "learning_rate": 4.741390274864885e-06, "loss": 1.2062402963638306, "step": 356 }, { "epoch": 0.7937915742793792, "grad_norm": 2.9775516986846924, "learning_rate": 4.737535403421601e-06, "loss": 1.251714825630188, "step": 358 }, { "epoch": 0.7982261640798226, "grad_norm": 1.402034044265747, "learning_rate": 4.733653792101809e-06, "loss": 1.215922474861145, "step": 360 }, { "epoch": 0.802660753880266, "grad_norm": 1.4241507053375244, "learning_rate": 4.729745493127878e-06, "loss": 0.5939327478408813, "step": 362 }, { "epoch": 0.8070953436807096, "grad_norm": 2.221510410308838, "learning_rate": 4.725810559081227e-06, "loss": 1.318565845489502, "step": 364 }, { "epoch": 0.811529933481153, "grad_norm": 1.5592412948608398, "learning_rate": 4.7218490429016175e-06, "loss": 1.1835287809371948, "step": 366 }, { "epoch": 0.8159645232815964, "grad_norm": 3.7534544467926025, "learning_rate": 4.717860997886442e-06, "loss": 0.9975278973579407, "step": 368 }, { "epoch": 0.8203991130820399, "grad_norm": 5.241509437561035, "learning_rate": 4.713846477690005e-06, "loss": 0.8571419715881348, "step": 370 }, { "epoch": 0.8248337028824834, "grad_norm": 1.2738577127456665, "learning_rate": 4.709805536322804e-06, "loss": 1.2139989137649536, "step": 372 }, { "epoch": 0.8292682926829268, "grad_norm": 0.9885940551757812, "learning_rate": 4.7057382281508e-06, "loss": 1.2157939672470093, "step": 374 }, { "epoch": 0.8337028824833703, "grad_norm": 1.920699119567871, "learning_rate": 4.701644607894687e-06, "loss": 1.1778194904327393, "step": 376 }, { "epoch": 0.8381374722838137, "grad_norm": 1.2708183526992798, "learning_rate": 4.697524730629159e-06, "loss": 1.202418327331543, "step": 378 }, { "epoch": 0.8425720620842572, "grad_norm": 8.80882740020752, "learning_rate": 4.693378651782162e-06, "loss": 0.723749041557312, "step": 380 }, { "epoch": 0.8470066518847007, "grad_norm": 0.7982382774353027, "learning_rate": 4.689206427134155e-06, "loss": 1.2849069833755493, "step": 382 }, { "epoch": 0.8514412416851441, "grad_norm": 0.8297720551490784, "learning_rate": 4.6850081128173595e-06, "loss": 1.1224342584609985, "step": 384 }, { "epoch": 0.8558758314855875, "grad_norm": 0.8830884099006653, "learning_rate": 4.680783765314994e-06, "loss": 1.2344768047332764, "step": 386 }, { "epoch": 0.8603104212860311, "grad_norm": 0.6799097657203674, "learning_rate": 4.6765334414605315e-06, "loss": 1.1405550241470337, "step": 388 }, { "epoch": 0.8647450110864745, "grad_norm": 0.9640771746635437, "learning_rate": 4.672257198436918e-06, "loss": 1.23441481590271, "step": 390 }, { "epoch": 0.8691796008869179, "grad_norm": 1.577943205833435, "learning_rate": 4.667955093775814e-06, "loss": 0.8823462128639221, "step": 392 }, { "epoch": 0.8736141906873615, "grad_norm": 1.0975431203842163, "learning_rate": 4.663627185356818e-06, "loss": 1.201162576675415, "step": 394 }, { "epoch": 0.8780487804878049, "grad_norm": 0.8264410495758057, "learning_rate": 4.65927353140668e-06, "loss": 1.1939952373504639, "step": 396 }, { "epoch": 0.8824833702882483, "grad_norm": 1.166627049446106, "learning_rate": 4.654894190498534e-06, "loss": 1.1967897415161133, "step": 398 }, { "epoch": 0.8869179600886918, "grad_norm": 0.6226066946983337, "learning_rate": 4.650489221551095e-06, "loss": 0.44957131147384644, "step": 400 }, { "epoch": 0.8913525498891353, "grad_norm": 0.6761036515235901, "learning_rate": 4.646058683827874e-06, "loss": 1.025883436203003, "step": 402 }, { "epoch": 0.8957871396895787, "grad_norm": 0.2941175103187561, "learning_rate": 4.641602636936378e-06, "loss": 0.9108548164367676, "step": 404 }, { "epoch": 0.9002217294900222, "grad_norm": 1.1719696521759033, "learning_rate": 4.637121140827311e-06, "loss": 1.254028081893921, "step": 406 }, { "epoch": 0.9046563192904656, "grad_norm": 2.666060447692871, "learning_rate": 4.632614255793762e-06, "loss": 1.1204774379730225, "step": 408 }, { "epoch": 0.9090909090909091, "grad_norm": 3.2736313343048096, "learning_rate": 4.6280820424704e-06, "loss": 1.0682605504989624, "step": 410 }, { "epoch": 0.9135254988913526, "grad_norm": 1.8158552646636963, "learning_rate": 4.623524561832653e-06, "loss": 1.22024667263031, "step": 412 }, { "epoch": 0.917960088691796, "grad_norm": 1.1710323095321655, "learning_rate": 4.618941875195893e-06, "loss": 1.233978033065796, "step": 414 }, { "epoch": 0.9223946784922394, "grad_norm": 1.603824257850647, "learning_rate": 4.614334044214606e-06, "loss": 0.9593857526779175, "step": 416 }, { "epoch": 0.926829268292683, "grad_norm": 0.8521295189857483, "learning_rate": 4.6097011308815645e-06, "loss": 1.2425235509872437, "step": 418 }, { "epoch": 0.9312638580931264, "grad_norm": 2.692030429840088, "learning_rate": 4.605043197526996e-06, "loss": 0.7656779289245605, "step": 420 }, { "epoch": 0.9356984478935698, "grad_norm": 1.0381312370300293, "learning_rate": 4.600360306817738e-06, "loss": 1.4421385526657104, "step": 422 }, { "epoch": 0.9401330376940134, "grad_norm": 21.29833984375, "learning_rate": 4.595652521756403e-06, "loss": 1.0444769859313965, "step": 424 }, { "epoch": 0.9445676274944568, "grad_norm": 0.7946411967277527, "learning_rate": 4.590919905680524e-06, "loss": 1.1843209266662598, "step": 426 }, { "epoch": 0.9490022172949002, "grad_norm": 0.4803466796875, "learning_rate": 4.5861625222617065e-06, "loss": 1.0634812116622925, "step": 428 }, { "epoch": 0.9534368070953437, "grad_norm": 6.066927909851074, "learning_rate": 4.58138043550477e-06, "loss": 0.6745222806930542, "step": 430 }, { "epoch": 0.9578713968957872, "grad_norm": 1.7354466915130615, "learning_rate": 4.576573709746887e-06, "loss": 1.2073925733566284, "step": 432 }, { "epoch": 0.9623059866962306, "grad_norm": 2.441338300704956, "learning_rate": 4.5717424096567205e-06, "loss": 1.0565319061279297, "step": 434 }, { "epoch": 0.9667405764966741, "grad_norm": 0.7328557968139648, "learning_rate": 4.566886600233547e-06, "loss": 1.2665467262268066, "step": 436 }, { "epoch": 0.9711751662971175, "grad_norm": 0.6606398820877075, "learning_rate": 4.56200634680639e-06, "loss": 1.2194955348968506, "step": 438 }, { "epoch": 0.975609756097561, "grad_norm": 3.465074062347412, "learning_rate": 4.557101715033136e-06, "loss": 0.7741403579711914, "step": 440 }, { "epoch": 0.9800443458980045, "grad_norm": 0.9509384632110596, "learning_rate": 4.552172770899652e-06, "loss": 1.027595043182373, "step": 442 }, { "epoch": 0.9844789356984479, "grad_norm": 1.1520196199417114, "learning_rate": 4.547219580718899e-06, "loss": 1.2680723667144775, "step": 444 }, { "epoch": 0.9889135254988913, "grad_norm": 0.7497501373291016, "learning_rate": 4.542242211130039e-06, "loss": 1.1927207708358765, "step": 446 }, { "epoch": 0.9933481152993349, "grad_norm": 0.9399945139884949, "learning_rate": 4.537240729097539e-06, "loss": 1.2298150062561035, "step": 448 }, { "epoch": 0.9977827050997783, "grad_norm": 0.6698287129402161, "learning_rate": 4.532215201910269e-06, "loss": 1.0293582677841187, "step": 450 }, { "epoch": 1.0022172949002217, "grad_norm": 6.488946914672852, "learning_rate": 4.527165697180598e-06, "loss": 1.0618946552276611, "step": 452 }, { "epoch": 1.0066518847006651, "grad_norm": 1.9061259031295776, "learning_rate": 4.522092282843481e-06, "loss": 1.3013073205947876, "step": 454 }, { "epoch": 1.0110864745011086, "grad_norm": 0.9116241335868835, "learning_rate": 4.516995027155554e-06, "loss": 1.2355761528015137, "step": 456 }, { "epoch": 1.0155210643015522, "grad_norm": 0.6007906198501587, "learning_rate": 4.511873998694204e-06, "loss": 0.8137620687484741, "step": 458 }, { "epoch": 1.0199556541019956, "grad_norm": 0.37421897053718567, "learning_rate": 4.506729266356651e-06, "loss": 0.8346569538116455, "step": 460 }, { "epoch": 1.024390243902439, "grad_norm": 3.830796718597412, "learning_rate": 4.5015608993590276e-06, "loss": 0.5353830456733704, "step": 462 }, { "epoch": 1.0288248337028825, "grad_norm": 1.997052550315857, "learning_rate": 4.4963689672354375e-06, "loss": 0.8425235152244568, "step": 464 }, { "epoch": 1.033259423503326, "grad_norm": 1.2142010927200317, "learning_rate": 4.491153539837026e-06, "loss": 0.7943000793457031, "step": 466 }, { "epoch": 1.0376940133037693, "grad_norm": 3.276048183441162, "learning_rate": 4.4859146873310375e-06, "loss": 0.9381541013717651, "step": 468 }, { "epoch": 1.042128603104213, "grad_norm": 0.9781183004379272, "learning_rate": 4.480652480199873e-06, "loss": 0.6260444521903992, "step": 470 }, { "epoch": 1.0465631929046564, "grad_norm": 1.1556280851364136, "learning_rate": 4.475366989240147e-06, "loss": 0.9917138814926147, "step": 472 }, { "epoch": 1.0509977827050998, "grad_norm": 0.9337510466575623, "learning_rate": 4.470058285561721e-06, "loss": 1.046325445175171, "step": 474 }, { "epoch": 1.0554323725055432, "grad_norm": 1.022441029548645, "learning_rate": 4.464726440586761e-06, "loss": 1.0449920892715454, "step": 476 }, { "epoch": 1.0598669623059866, "grad_norm": 1.4056508541107178, "learning_rate": 4.45937152604877e-06, "loss": 1.094570517539978, "step": 478 }, { "epoch": 1.06430155210643, "grad_norm": 1.2816241979599, "learning_rate": 4.453993613991622e-06, "loss": 0.6536943316459656, "step": 480 }, { "epoch": 1.0687361419068737, "grad_norm": 1.1188907623291016, "learning_rate": 4.4485927767685995e-06, "loss": 1.139634609222412, "step": 482 }, { "epoch": 1.0731707317073171, "grad_norm": 0.4301467835903168, "learning_rate": 4.443169087041409e-06, "loss": 0.923588216304779, "step": 484 }, { "epoch": 1.0776053215077606, "grad_norm": 0.6617166996002197, "learning_rate": 4.4377226177792145e-06, "loss": 1.0248123407363892, "step": 486 }, { "epoch": 1.082039911308204, "grad_norm": 1.1432987451553345, "learning_rate": 4.432253442257649e-06, "loss": 0.7850465774536133, "step": 488 }, { "epoch": 1.0864745011086474, "grad_norm": 1.8113877773284912, "learning_rate": 4.426761634057831e-06, "loss": 0.9420559406280518, "step": 490 }, { "epoch": 1.0909090909090908, "grad_norm": 1.6748836040496826, "learning_rate": 4.421247267065375e-06, "loss": 1.1039046049118042, "step": 492 }, { "epoch": 1.0953436807095343, "grad_norm": 1.795003056526184, "learning_rate": 4.415710415469394e-06, "loss": 1.091720461845398, "step": 494 }, { "epoch": 1.099778270509978, "grad_norm": 1.652651309967041, "learning_rate": 4.410151153761506e-06, "loss": 0.8766781091690063, "step": 496 }, { "epoch": 1.1042128603104213, "grad_norm": 0.6152821183204651, "learning_rate": 4.404569556734832e-06, "loss": 1.0317732095718384, "step": 498 }, { "epoch": 1.1086474501108647, "grad_norm": 0.956628680229187, "learning_rate": 4.398965699482984e-06, "loss": 0.8593730926513672, "step": 500 }, { "epoch": 1.1130820399113082, "grad_norm": 0.9794469475746155, "learning_rate": 4.39333965739906e-06, "loss": 1.025899887084961, "step": 502 }, { "epoch": 1.1175166297117516, "grad_norm": 2.0585477352142334, "learning_rate": 4.3876915061746275e-06, "loss": 0.928720235824585, "step": 504 }, { "epoch": 1.1219512195121952, "grad_norm": 1.5161011219024658, "learning_rate": 4.382021321798707e-06, "loss": 1.0593522787094116, "step": 506 }, { "epoch": 1.1263858093126387, "grad_norm": 1.4959526062011719, "learning_rate": 4.376329180556745e-06, "loss": 0.8792567849159241, "step": 508 }, { "epoch": 1.130820399113082, "grad_norm": 0.7404501438140869, "learning_rate": 4.370615159029594e-06, "loss": 1.131915807723999, "step": 510 }, { "epoch": 1.1352549889135255, "grad_norm": 8.584444999694824, "learning_rate": 4.36487933409248e-06, "loss": 0.5437202453613281, "step": 512 }, { "epoch": 1.139689578713969, "grad_norm": 1.0118581056594849, "learning_rate": 4.359121782913964e-06, "loss": 0.48725366592407227, "step": 514 }, { "epoch": 1.1441241685144123, "grad_norm": 1.0809403657913208, "learning_rate": 4.3533425829549085e-06, "loss": 0.9849007725715637, "step": 516 }, { "epoch": 1.1485587583148558, "grad_norm": 2.9192471504211426, "learning_rate": 4.347541811967436e-06, "loss": 1.1810388565063477, "step": 518 }, { "epoch": 1.1529933481152994, "grad_norm": 1.2919275760650635, "learning_rate": 4.341719547993879e-06, "loss": 1.126792550086975, "step": 520 }, { "epoch": 1.1574279379157428, "grad_norm": 1.4183093309402466, "learning_rate": 4.335875869365732e-06, "loss": 0.5291884541511536, "step": 522 }, { "epoch": 1.1618625277161863, "grad_norm": 1.3505902290344238, "learning_rate": 4.330010854702598e-06, "loss": 1.0048887729644775, "step": 524 }, { "epoch": 1.1662971175166297, "grad_norm": 1.1992731094360352, "learning_rate": 4.3241245829111324e-06, "loss": 1.1825058460235596, "step": 526 }, { "epoch": 1.170731707317073, "grad_norm": 1.0667892694473267, "learning_rate": 4.318217133183978e-06, "loss": 0.6172074675559998, "step": 528 }, { "epoch": 1.1751662971175167, "grad_norm": 0.6770420074462891, "learning_rate": 4.312288584998697e-06, "loss": 0.8084365129470825, "step": 530 }, { "epoch": 1.1796008869179602, "grad_norm": 0.7109060883522034, "learning_rate": 4.306339018116714e-06, "loss": 0.9454807043075562, "step": 532 }, { "epoch": 1.1840354767184036, "grad_norm": 0.7484174370765686, "learning_rate": 4.300368512582227e-06, "loss": 1.0386492013931274, "step": 534 }, { "epoch": 1.188470066518847, "grad_norm": 0.4899117946624756, "learning_rate": 4.294377148721144e-06, "loss": 0.8095374703407288, "step": 536 }, { "epoch": 1.1929046563192904, "grad_norm": 1.52462899684906, "learning_rate": 4.288365007139991e-06, "loss": 1.0734546184539795, "step": 538 }, { "epoch": 1.1973392461197339, "grad_norm": 3.1415209770202637, "learning_rate": 4.2823321687248386e-06, "loss": 0.6387287378311157, "step": 540 }, { "epoch": 1.2017738359201773, "grad_norm": 2.35459303855896, "learning_rate": 4.276278714640203e-06, "loss": 0.6681326627731323, "step": 542 }, { "epoch": 1.206208425720621, "grad_norm": 2.5117621421813965, "learning_rate": 4.270204726327963e-06, "loss": 1.1640082597732544, "step": 544 }, { "epoch": 1.2106430155210643, "grad_norm": 0.46196478605270386, "learning_rate": 4.264110285506259e-06, "loss": 0.8398973941802979, "step": 546 }, { "epoch": 1.2150776053215078, "grad_norm": 1.005468726158142, "learning_rate": 4.257995474168395e-06, "loss": 1.2058871984481812, "step": 548 }, { "epoch": 1.2195121951219512, "grad_norm": 6.870185852050781, "learning_rate": 4.251860374581736e-06, "loss": 0.5818393230438232, "step": 550 }, { "epoch": 1.2239467849223946, "grad_norm": 1.6000272035598755, "learning_rate": 4.245705069286601e-06, "loss": 1.0754560232162476, "step": 552 }, { "epoch": 1.2283813747228383, "grad_norm": 6.755113124847412, "learning_rate": 4.239529641095149e-06, "loss": 0.7084805965423584, "step": 554 }, { "epoch": 1.2328159645232817, "grad_norm": 0.39095139503479004, "learning_rate": 4.233334173090274e-06, "loss": 0.7805958986282349, "step": 556 }, { "epoch": 1.237250554323725, "grad_norm": 2.378875255584717, "learning_rate": 4.227118748624478e-06, "loss": 0.844260036945343, "step": 558 }, { "epoch": 1.2416851441241685, "grad_norm": 1.532080054283142, "learning_rate": 4.220883451318753e-06, "loss": 1.2891573905944824, "step": 560 }, { "epoch": 1.246119733924612, "grad_norm": 4.011655330657959, "learning_rate": 4.2146283650614545e-06, "loss": 0.9298526048660278, "step": 562 }, { "epoch": 1.2505543237250554, "grad_norm": 1.7476955652236938, "learning_rate": 4.208353574007179e-06, "loss": 0.6140811443328857, "step": 564 }, { "epoch": 1.2549889135254988, "grad_norm": 0.7454321980476379, "learning_rate": 4.202059162575622e-06, "loss": 0.9352214932441711, "step": 566 }, { "epoch": 1.2594235033259422, "grad_norm": 0.8128042221069336, "learning_rate": 4.195745215450451e-06, "loss": 0.8876186013221741, "step": 568 }, { "epoch": 1.2638580931263859, "grad_norm": 0.8655123114585876, "learning_rate": 4.189411817578159e-06, "loss": 1.137557864189148, "step": 570 }, { "epoch": 1.2682926829268293, "grad_norm": 0.7158671617507935, "learning_rate": 4.1830590541669304e-06, "loss": 0.73340904712677, "step": 572 }, { "epoch": 1.2727272727272727, "grad_norm": 1.6793097257614136, "learning_rate": 4.176687010685484e-06, "loss": 1.366833209991455, "step": 574 }, { "epoch": 1.2771618625277161, "grad_norm": 1.7137008905410767, "learning_rate": 4.170295772861931e-06, "loss": 1.051391363143921, "step": 576 }, { "epoch": 1.2815964523281598, "grad_norm": 0.8713537454605103, "learning_rate": 4.163885426682619e-06, "loss": 1.1371718645095825, "step": 578 }, { "epoch": 1.2860310421286032, "grad_norm": 0.9941657781600952, "learning_rate": 4.157456058390977e-06, "loss": 1.131047010421753, "step": 580 }, { "epoch": 1.2904656319290466, "grad_norm": 2.815027952194214, "learning_rate": 4.151007754486351e-06, "loss": 1.3203078508377075, "step": 582 }, { "epoch": 1.29490022172949, "grad_norm": 0.5185415148735046, "learning_rate": 4.144540601722843e-06, "loss": 0.7271389365196228, "step": 584 }, { "epoch": 1.2993348115299335, "grad_norm": 0.6934378147125244, "learning_rate": 4.138054687108143e-06, "loss": 0.8247404098510742, "step": 586 }, { "epoch": 1.3037694013303769, "grad_norm": 4.077749252319336, "learning_rate": 4.131550097902361e-06, "loss": 0.5715563297271729, "step": 588 }, { "epoch": 1.3082039911308203, "grad_norm": 2.7654740810394287, "learning_rate": 4.125026921616852e-06, "loss": 0.9844896197319031, "step": 590 }, { "epoch": 1.3126385809312637, "grad_norm": 1.3605704307556152, "learning_rate": 4.118485246013031e-06, "loss": 1.0650662183761597, "step": 592 }, { "epoch": 1.3170731707317074, "grad_norm": 0.6844571828842163, "learning_rate": 4.111925159101208e-06, "loss": 1.0756279230117798, "step": 594 }, { "epoch": 1.3215077605321508, "grad_norm": 0.6011850833892822, "learning_rate": 4.1053467491393864e-06, "loss": 1.0734484195709229, "step": 596 }, { "epoch": 1.3259423503325942, "grad_norm": 1.0769504308700562, "learning_rate": 4.098750104632091e-06, "loss": 1.0580254793167114, "step": 598 }, { "epoch": 1.3303769401330376, "grad_norm": 1.112815022468567, "learning_rate": 4.092135314329165e-06, "loss": 0.5043829083442688, "step": 600 }, { "epoch": 1.3348115299334813, "grad_norm": 1.8235517740249634, "learning_rate": 4.085502467224583e-06, "loss": 0.9834141135215759, "step": 602 }, { "epoch": 1.3392461197339247, "grad_norm": 0.8808879256248474, "learning_rate": 4.078851652555254e-06, "loss": 0.8073503971099854, "step": 604 }, { "epoch": 1.3436807095343681, "grad_norm": 0.6147663593292236, "learning_rate": 4.072182959799816e-06, "loss": 0.8254027366638184, "step": 606 }, { "epoch": 1.3481152993348116, "grad_norm": 2.649986743927002, "learning_rate": 4.065496478677436e-06, "loss": 1.089369297027588, "step": 608 }, { "epoch": 1.352549889135255, "grad_norm": 9.459650993347168, "learning_rate": 4.058792299146602e-06, "loss": 1.1217542886734009, "step": 610 }, { "epoch": 1.3569844789356984, "grad_norm": 1.946794033050537, "learning_rate": 4.052070511403912e-06, "loss": 0.6706306338310242, "step": 612 }, { "epoch": 1.3614190687361418, "grad_norm": 0.9328871965408325, "learning_rate": 4.045331205882863e-06, "loss": 1.1241906881332397, "step": 614 }, { "epoch": 1.3658536585365852, "grad_norm": 0.5184811949729919, "learning_rate": 4.038574473252629e-06, "loss": 0.712710976600647, "step": 616 }, { "epoch": 1.370288248337029, "grad_norm": 1.2016468048095703, "learning_rate": 4.031800404416849e-06, "loss": 1.0043390989303589, "step": 618 }, { "epoch": 1.3747228381374723, "grad_norm": 0.8439203500747681, "learning_rate": 4.025009090512394e-06, "loss": 0.08705577254295349, "step": 620 }, { "epoch": 1.3791574279379157, "grad_norm": 0.5789482593536377, "learning_rate": 4.018200622908153e-06, "loss": 1.0090532302856445, "step": 622 }, { "epoch": 1.3835920177383592, "grad_norm": 1.3330731391906738, "learning_rate": 4.011375093203793e-06, "loss": 1.034111738204956, "step": 624 }, { "epoch": 1.3880266075388026, "grad_norm": 2.7468066215515137, "learning_rate": 4.004532593228531e-06, "loss": 0.962290346622467, "step": 626 }, { "epoch": 1.3924611973392462, "grad_norm": 0.9098476767539978, "learning_rate": 3.997673215039899e-06, "loss": 1.0617891550064087, "step": 628 }, { "epoch": 1.3968957871396896, "grad_norm": 2.727142333984375, "learning_rate": 3.990797050922506e-06, "loss": 1.072065830230713, "step": 630 }, { "epoch": 1.401330376940133, "grad_norm": 0.8622321486473083, "learning_rate": 3.9839041933867954e-06, "loss": 0.8306987881660461, "step": 632 }, { "epoch": 1.4057649667405765, "grad_norm": 1.51633882522583, "learning_rate": 3.976994735167796e-06, "loss": 0.9722529649734497, "step": 634 }, { "epoch": 1.41019955654102, "grad_norm": 0.8044195771217346, "learning_rate": 3.970068769223884e-06, "loss": 1.1132667064666748, "step": 636 }, { "epoch": 1.4146341463414633, "grad_norm": 6.232460021972656, "learning_rate": 3.963126388735525e-06, "loss": 0.82004714012146, "step": 638 }, { "epoch": 1.4190687361419068, "grad_norm": 0.918382465839386, "learning_rate": 3.956167687104021e-06, "loss": 0.7192656993865967, "step": 640 }, { "epoch": 1.4235033259423504, "grad_norm": 3.0365803241729736, "learning_rate": 3.9491927579502584e-06, "loss": 0.8175387382507324, "step": 642 }, { "epoch": 1.4279379157427938, "grad_norm": 0.7935546636581421, "learning_rate": 3.9422016951134415e-06, "loss": 0.6935265064239502, "step": 644 }, { "epoch": 1.4323725055432373, "grad_norm": 0.8461658954620361, "learning_rate": 3.935194592649836e-06, "loss": 1.2383686304092407, "step": 646 }, { "epoch": 1.4368070953436807, "grad_norm": 0.6491639018058777, "learning_rate": 3.928171544831501e-06, "loss": 1.0858060121536255, "step": 648 }, { "epoch": 1.441241685144124, "grad_norm": 1.7324135303497314, "learning_rate": 3.921132646145019e-06, "loss": 1.1424576044082642, "step": 650 }, { "epoch": 1.4456762749445677, "grad_norm": 4.648967266082764, "learning_rate": 3.914077991290232e-06, "loss": 0.9448270201683044, "step": 652 }, { "epoch": 1.4501108647450112, "grad_norm": 1.9809584617614746, "learning_rate": 3.907007675178956e-06, "loss": 1.05901038646698, "step": 654 }, { "epoch": 1.4545454545454546, "grad_norm": 0.8580670356750488, "learning_rate": 3.899921792933713e-06, "loss": 0.8147414326667786, "step": 656 }, { "epoch": 1.458980044345898, "grad_norm": 0.5463111996650696, "learning_rate": 3.892820439886448e-06, "loss": 0.7859951257705688, "step": 658 }, { "epoch": 1.4634146341463414, "grad_norm": 2.406365394592285, "learning_rate": 3.885703711577249e-06, "loss": 1.037505865097046, "step": 660 }, { "epoch": 1.4678492239467849, "grad_norm": 1.347562551498413, "learning_rate": 3.8785717037530555e-06, "loss": 1.0211855173110962, "step": 662 }, { "epoch": 1.4722838137472283, "grad_norm": 0.9649538397789001, "learning_rate": 3.871424512366377e-06, "loss": 0.7922490239143372, "step": 664 }, { "epoch": 1.476718403547672, "grad_norm": 0.6426183581352234, "learning_rate": 3.864262233574e-06, "loss": 0.6275416612625122, "step": 666 }, { "epoch": 1.4811529933481153, "grad_norm": 2.499333143234253, "learning_rate": 3.857084963735689e-06, "loss": 0.6237704753875732, "step": 668 }, { "epoch": 1.4855875831485588, "grad_norm": 0.956392765045166, "learning_rate": 3.849892799412902e-06, "loss": 0.9907911419868469, "step": 670 }, { "epoch": 1.4900221729490022, "grad_norm": 1.0127171277999878, "learning_rate": 3.84268583736748e-06, "loss": 1.030133605003357, "step": 672 }, { "epoch": 1.4944567627494456, "grad_norm": 3.757286548614502, "learning_rate": 3.835464174560349e-06, "loss": 0.6812074184417725, "step": 674 }, { "epoch": 1.4988913525498893, "grad_norm": 2.872394561767578, "learning_rate": 3.828227908150217e-06, "loss": 0.7936379909515381, "step": 676 }, { "epoch": 1.5033259423503327, "grad_norm": 4.6506123542785645, "learning_rate": 3.820977135492266e-06, "loss": 1.065293312072754, "step": 678 }, { "epoch": 1.507760532150776, "grad_norm": 0.6903529167175293, "learning_rate": 3.8137119541368415e-06, "loss": 0.5796735882759094, "step": 680 }, { "epoch": 1.5121951219512195, "grad_norm": 0.7172544002532959, "learning_rate": 3.80643246182814e-06, "loss": 0.5570440888404846, "step": 682 }, { "epoch": 1.516629711751663, "grad_norm": 0.9278987646102905, "learning_rate": 3.7991387565028963e-06, "loss": 0.9937266111373901, "step": 684 }, { "epoch": 1.5210643015521064, "grad_norm": 0.6855456829071045, "learning_rate": 3.791830936289062e-06, "loss": 0.991579532623291, "step": 686 }, { "epoch": 1.5254988913525498, "grad_norm": 2.719144582748413, "learning_rate": 3.784509099504488e-06, "loss": 0.6759345531463623, "step": 688 }, { "epoch": 1.5299334811529932, "grad_norm": 1.2889043092727661, "learning_rate": 3.7771733446556025e-06, "loss": 0.3256318271160126, "step": 690 }, { "epoch": 1.5343680709534369, "grad_norm": 3.266566038131714, "learning_rate": 3.7698237704360826e-06, "loss": 0.770363986492157, "step": 692 }, { "epoch": 1.5388026607538803, "grad_norm": 1.6477800607681274, "learning_rate": 3.7624604757255297e-06, "loss": 0.9243440628051758, "step": 694 }, { "epoch": 1.5432372505543237, "grad_norm": 9.355045318603516, "learning_rate": 3.7550835595881365e-06, "loss": 0.6884693503379822, "step": 696 }, { "epoch": 1.5476718403547673, "grad_norm": 0.7756222486495972, "learning_rate": 3.747693121271355e-06, "loss": 1.0920729637145996, "step": 698 }, { "epoch": 1.5521064301552108, "grad_norm": 1.2968804836273193, "learning_rate": 3.740289260204565e-06, "loss": 1.0673658847808838, "step": 700 }, { "epoch": 1.5565410199556542, "grad_norm": 1.133268117904663, "learning_rate": 3.732872075997729e-06, "loss": 1.0402312278747559, "step": 702 }, { "epoch": 1.5609756097560976, "grad_norm": 1.2593156099319458, "learning_rate": 3.725441668440058e-06, "loss": 0.8764057159423828, "step": 704 }, { "epoch": 1.565410199556541, "grad_norm": 2.54331111907959, "learning_rate": 3.7179981374986683e-06, "loss": 0.43431326746940613, "step": 706 }, { "epoch": 1.5698447893569845, "grad_norm": 1.0765475034713745, "learning_rate": 3.710541583317233e-06, "loss": 1.0775222778320312, "step": 708 }, { "epoch": 1.5742793791574279, "grad_norm": 3.7468576431274414, "learning_rate": 3.70307210621464e-06, "loss": 0.885796844959259, "step": 710 }, { "epoch": 1.5787139689578713, "grad_norm": 7.981743335723877, "learning_rate": 3.695589806683636e-06, "loss": 0.6404878497123718, "step": 712 }, { "epoch": 1.5831485587583147, "grad_norm": 0.843375027179718, "learning_rate": 3.68809478538948e-06, "loss": 1.0314189195632935, "step": 714 }, { "epoch": 1.5875831485587582, "grad_norm": 1.4143157005310059, "learning_rate": 3.6805871431685875e-06, "loss": 1.1162283420562744, "step": 716 }, { "epoch": 1.5920177383592018, "grad_norm": 1.6812629699707031, "learning_rate": 3.6730669810271707e-06, "loss": 1.224688172340393, "step": 718 }, { "epoch": 1.5964523281596452, "grad_norm": 1.70530366897583, "learning_rate": 3.665534400139885e-06, "loss": 0.5482722520828247, "step": 720 }, { "epoch": 1.6008869179600886, "grad_norm": 0.34640756249427795, "learning_rate": 3.6579895018484635e-06, "loss": 0.5939568877220154, "step": 722 }, { "epoch": 1.6053215077605323, "grad_norm": 0.7377131581306458, "learning_rate": 3.650432387660354e-06, "loss": 1.0684458017349243, "step": 724 }, { "epoch": 1.6097560975609757, "grad_norm": 0.7918015122413635, "learning_rate": 3.6428631592473584e-06, "loss": 1.0849140882492065, "step": 726 }, { "epoch": 1.6141906873614191, "grad_norm": 0.6928529739379883, "learning_rate": 3.6352819184442552e-06, "loss": 0.7899186611175537, "step": 728 }, { "epoch": 1.6186252771618626, "grad_norm": 4.092320442199707, "learning_rate": 3.6276887672474374e-06, "loss": 1.041346549987793, "step": 730 }, { "epoch": 1.623059866962306, "grad_norm": 0.7040436863899231, "learning_rate": 3.620083807813541e-06, "loss": 1.0382251739501953, "step": 732 }, { "epoch": 1.6274944567627494, "grad_norm": 1.0411463975906372, "learning_rate": 3.6124671424580633e-06, "loss": 1.0006555318832397, "step": 734 }, { "epoch": 1.6319290465631928, "grad_norm": 0.41378095746040344, "learning_rate": 3.604838873653991e-06, "loss": 0.6166353821754456, "step": 736 }, { "epoch": 1.6363636363636362, "grad_norm": 7.036901950836182, "learning_rate": 3.597199104030424e-06, "loss": 1.1837652921676636, "step": 738 }, { "epoch": 1.6407982261640797, "grad_norm": 0.7952733039855957, "learning_rate": 3.589547936371189e-06, "loss": 1.0267434120178223, "step": 740 }, { "epoch": 1.6452328159645233, "grad_norm": 2.4951283931732178, "learning_rate": 3.58188547361346e-06, "loss": 1.2115845680236816, "step": 742 }, { "epoch": 1.6496674057649667, "grad_norm": 3.071096658706665, "learning_rate": 3.574211818846374e-06, "loss": 0.8251364231109619, "step": 744 }, { "epoch": 1.6541019955654102, "grad_norm": 2.369654655456543, "learning_rate": 3.566527075309641e-06, "loss": 0.8760843276977539, "step": 746 }, { "epoch": 1.6585365853658538, "grad_norm": 2.175527334213257, "learning_rate": 3.558831346392159e-06, "loss": 0.8911266922950745, "step": 748 }, { "epoch": 1.6629711751662972, "grad_norm": 1.2222336530685425, "learning_rate": 3.5511247356306205e-06, "loss": 1.1212302446365356, "step": 750 }, { "epoch": 1.6674057649667406, "grad_norm": 0.8364224433898926, "learning_rate": 3.5434073467081183e-06, "loss": 0.8240474462509155, "step": 752 }, { "epoch": 1.671840354767184, "grad_norm": 2.646286964416504, "learning_rate": 3.5356792834527533e-06, "loss": 0.6273259520530701, "step": 754 }, { "epoch": 1.6762749445676275, "grad_norm": 1.0103214979171753, "learning_rate": 3.527940649836238e-06, "loss": 0.9294993877410889, "step": 756 }, { "epoch": 1.680709534368071, "grad_norm": 1.3476576805114746, "learning_rate": 3.520191549972494e-06, "loss": 0.9880755543708801, "step": 758 }, { "epoch": 1.6851441241685143, "grad_norm": 2.302769899368286, "learning_rate": 3.512432088116255e-06, "loss": 0.8687876462936401, "step": 760 }, { "epoch": 1.6895787139689578, "grad_norm": 1.9795390367507935, "learning_rate": 3.5046623686616627e-06, "loss": 1.0587050914764404, "step": 762 }, { "epoch": 1.6940133037694012, "grad_norm": 1.420723557472229, "learning_rate": 3.496882496140861e-06, "loss": 1.0825788974761963, "step": 764 }, { "epoch": 1.6984478935698448, "grad_norm": 2.4798290729522705, "learning_rate": 3.4890925752225935e-06, "loss": 0.9839310050010681, "step": 766 }, { "epoch": 1.7028824833702882, "grad_norm": 1.6060822010040283, "learning_rate": 3.48129271071079e-06, "loss": 0.794252336025238, "step": 768 }, { "epoch": 1.7073170731707317, "grad_norm": 1.1123030185699463, "learning_rate": 3.4734830075431605e-06, "loss": 1.0317720174789429, "step": 770 }, { "epoch": 1.7117516629711753, "grad_norm": 2.067833423614502, "learning_rate": 3.4656635707897823e-06, "loss": 1.0553863048553467, "step": 772 }, { "epoch": 1.7161862527716187, "grad_norm": 0.981274425983429, "learning_rate": 3.457834505651687e-06, "loss": 0.9536479115486145, "step": 774 }, { "epoch": 1.7206208425720622, "grad_norm": 0.6783517003059387, "learning_rate": 3.449995917459442e-06, "loss": 1.062004566192627, "step": 776 }, { "epoch": 1.7250554323725056, "grad_norm": 0.7117043137550354, "learning_rate": 3.4421479116717394e-06, "loss": 1.0369482040405273, "step": 778 }, { "epoch": 1.729490022172949, "grad_norm": 1.9212546348571777, "learning_rate": 3.4342905938739707e-06, "loss": 0.6672749519348145, "step": 780 }, { "epoch": 1.7339246119733924, "grad_norm": 0.7695720195770264, "learning_rate": 3.4264240697768096e-06, "loss": 1.0097278356552124, "step": 782 }, { "epoch": 1.7383592017738358, "grad_norm": 0.6285500526428223, "learning_rate": 3.418548445214791e-06, "loss": 0.7331390380859375, "step": 784 }, { "epoch": 1.7427937915742793, "grad_norm": 0.6695563793182373, "learning_rate": 3.410663826144884e-06, "loss": 0.8074593544006348, "step": 786 }, { "epoch": 1.7472283813747227, "grad_norm": 0.7012442946434021, "learning_rate": 3.4027703186450672e-06, "loss": 0.7080385684967041, "step": 788 }, { "epoch": 1.7516629711751663, "grad_norm": 2.9280431270599365, "learning_rate": 3.394868028912906e-06, "loss": 0.6388112902641296, "step": 790 }, { "epoch": 1.7560975609756098, "grad_norm": 0.9185779690742493, "learning_rate": 3.386957063264115e-06, "loss": 0.8246527910232544, "step": 792 }, { "epoch": 1.7605321507760532, "grad_norm": 1.0460119247436523, "learning_rate": 3.3790375281311355e-06, "loss": 0.9118836522102356, "step": 794 }, { "epoch": 1.7649667405764968, "grad_norm": 2.923001766204834, "learning_rate": 3.3711095300617015e-06, "loss": 0.8226492404937744, "step": 796 }, { "epoch": 1.7694013303769403, "grad_norm": 0.6730989813804626, "learning_rate": 3.3631731757174048e-06, "loss": 1.0575485229492188, "step": 798 }, { "epoch": 1.7738359201773837, "grad_norm": 1.040733814239502, "learning_rate": 3.3552285718722593e-06, "loss": 1.0470877885818481, "step": 800 }, { "epoch": 1.778270509977827, "grad_norm": 0.9821973443031311, "learning_rate": 3.3472758254112662e-06, "loss": 1.0410436391830444, "step": 802 }, { "epoch": 1.7827050997782705, "grad_norm": 2.0623693466186523, "learning_rate": 3.3393150433289795e-06, "loss": 1.138871431350708, "step": 804 }, { "epoch": 1.787139689578714, "grad_norm": 0.9976066946983337, "learning_rate": 3.3313463327280576e-06, "loss": 0.8022021651268005, "step": 806 }, { "epoch": 1.7915742793791574, "grad_norm": 0.6746619343757629, "learning_rate": 3.3233698008178306e-06, "loss": 1.0426361560821533, "step": 808 }, { "epoch": 1.7960088691796008, "grad_norm": 0.7335001230239868, "learning_rate": 3.3153855549128537e-06, "loss": 0.6199694275856018, "step": 810 }, { "epoch": 1.8004434589800442, "grad_norm": 3.391047477722168, "learning_rate": 3.3073937024314647e-06, "loss": 0.5800549387931824, "step": 812 }, { "epoch": 1.8048780487804879, "grad_norm": 1.8660929203033447, "learning_rate": 3.2993943508943386e-06, "loss": 1.197942852973938, "step": 814 }, { "epoch": 1.8093126385809313, "grad_norm": 3.539306640625, "learning_rate": 3.291387607923041e-06, "loss": 0.9978748559951782, "step": 816 }, { "epoch": 1.8137472283813747, "grad_norm": 0.7452203035354614, "learning_rate": 3.283373581238582e-06, "loss": 0.509084939956665, "step": 818 }, { "epoch": 1.8181818181818183, "grad_norm": 1.6028074026107788, "learning_rate": 3.2753523786599618e-06, "loss": 1.0873044729232788, "step": 820 }, { "epoch": 1.8226164079822618, "grad_norm": 1.7422271966934204, "learning_rate": 3.2673241081027263e-06, "loss": 1.0879627466201782, "step": 822 }, { "epoch": 1.8270509977827052, "grad_norm": 1.1543694734573364, "learning_rate": 3.259288877577512e-06, "loss": 1.147214651107788, "step": 824 }, { "epoch": 1.8314855875831486, "grad_norm": 1.4722660779953003, "learning_rate": 3.251246795188592e-06, "loss": 0.933826208114624, "step": 826 }, { "epoch": 1.835920177383592, "grad_norm": 1.6987321376800537, "learning_rate": 3.243197969132425e-06, "loss": 0.7955626249313354, "step": 828 }, { "epoch": 1.8403547671840355, "grad_norm": 0.9446114897727966, "learning_rate": 3.2351425076961957e-06, "loss": 1.023888349533081, "step": 830 }, { "epoch": 1.8447893569844789, "grad_norm": 1.1627906560897827, "learning_rate": 3.22708051925636e-06, "loss": 1.0093810558319092, "step": 832 }, { "epoch": 1.8492239467849223, "grad_norm": 0.7773818373680115, "learning_rate": 3.219012112277189e-06, "loss": 0.982840895652771, "step": 834 }, { "epoch": 1.8536585365853657, "grad_norm": 0.9189027547836304, "learning_rate": 3.210937395309304e-06, "loss": 1.0559179782867432, "step": 836 }, { "epoch": 1.8580931263858091, "grad_norm": 1.0602095127105713, "learning_rate": 3.202856476988222e-06, "loss": 1.0600286722183228, "step": 838 }, { "epoch": 1.8625277161862528, "grad_norm": 1.2096672058105469, "learning_rate": 3.1947694660328914e-06, "loss": 1.1588785648345947, "step": 840 }, { "epoch": 1.8669623059866962, "grad_norm": 1.3825271129608154, "learning_rate": 3.1866764712442273e-06, "loss": 0.6686919927597046, "step": 842 }, { "epoch": 1.8713968957871396, "grad_norm": 1.1404961347579956, "learning_rate": 3.1785776015036533e-06, "loss": 0.7725078463554382, "step": 844 }, { "epoch": 1.8758314855875833, "grad_norm": 2.0521693229675293, "learning_rate": 3.1704729657716314e-06, "loss": 0.8420175313949585, "step": 846 }, { "epoch": 1.8802660753880267, "grad_norm": 1.6564451456069946, "learning_rate": 3.1623626730861996e-06, "loss": 0.9892827272415161, "step": 848 }, { "epoch": 1.8847006651884701, "grad_norm": 1.1145013570785522, "learning_rate": 3.1542468325615e-06, "loss": 1.3681321144104004, "step": 850 }, { "epoch": 1.8891352549889135, "grad_norm": 0.7389641404151917, "learning_rate": 3.1461255533863183e-06, "loss": 0.6859239339828491, "step": 852 }, { "epoch": 1.893569844789357, "grad_norm": 0.873809814453125, "learning_rate": 3.1379989448226077e-06, "loss": 1.0703860521316528, "step": 854 }, { "epoch": 1.8980044345898004, "grad_norm": 0.7670641541481018, "learning_rate": 3.1298671162040236e-06, "loss": 0.9328793883323669, "step": 856 }, { "epoch": 1.9024390243902438, "grad_norm": 0.7553779482841492, "learning_rate": 3.1217301769344488e-06, "loss": 0.7479826211929321, "step": 858 }, { "epoch": 1.9068736141906872, "grad_norm": 2.153320789337158, "learning_rate": 3.1135882364865262e-06, "loss": 0.7695887088775635, "step": 860 }, { "epoch": 1.9113082039911307, "grad_norm": 11.15374755859375, "learning_rate": 3.105441404400183e-06, "loss": 1.089734435081482, "step": 862 }, { "epoch": 1.9157427937915743, "grad_norm": 0.8938463926315308, "learning_rate": 3.097289790281155e-06, "loss": 0.805739164352417, "step": 864 }, { "epoch": 1.9201773835920177, "grad_norm": 1.704505205154419, "learning_rate": 3.089133503799517e-06, "loss": 0.6438337564468384, "step": 866 }, { "epoch": 1.9246119733924612, "grad_norm": 1.9099633693695068, "learning_rate": 3.0809726546882045e-06, "loss": 1.136403203010559, "step": 868 }, { "epoch": 1.9290465631929048, "grad_norm": 0.8499243855476379, "learning_rate": 3.0728073527415376e-06, "loss": 1.0269296169281006, "step": 870 }, { "epoch": 1.9334811529933482, "grad_norm": 0.5403093695640564, "learning_rate": 3.0646377078137424e-06, "loss": 0.6854551434516907, "step": 872 }, { "epoch": 1.9379157427937916, "grad_norm": 1.254056692123413, "learning_rate": 3.056463829817475e-06, "loss": 0.6160570383071899, "step": 874 }, { "epoch": 1.942350332594235, "grad_norm": 1.9854458570480347, "learning_rate": 3.048285828722345e-06, "loss": 0.6414442658424377, "step": 876 }, { "epoch": 1.9467849223946785, "grad_norm": 2.5461316108703613, "learning_rate": 3.0401038145534297e-06, "loss": 0.7798886299133301, "step": 878 }, { "epoch": 1.951219512195122, "grad_norm": 1.066082239151001, "learning_rate": 3.031917897389799e-06, "loss": 0.8321408629417419, "step": 880 }, { "epoch": 1.9556541019955653, "grad_norm": 1.9094276428222656, "learning_rate": 3.0237281873630335e-06, "loss": 0.637435257434845, "step": 882 }, { "epoch": 1.9600886917960088, "grad_norm": 0.6589820384979248, "learning_rate": 3.0155347946557407e-06, "loss": 0.9004865884780884, "step": 884 }, { "epoch": 1.9645232815964522, "grad_norm": 0.6076062321662903, "learning_rate": 3.007337829500075e-06, "loss": 1.0442458391189575, "step": 886 }, { "epoch": 1.9689578713968958, "grad_norm": 0.7619770169258118, "learning_rate": 2.999137402176255e-06, "loss": 1.0404667854309082, "step": 888 }, { "epoch": 1.9733924611973392, "grad_norm": 0.72157222032547, "learning_rate": 2.9909336230110747e-06, "loss": 1.0282480716705322, "step": 890 }, { "epoch": 1.9778270509977827, "grad_norm": 0.7795007824897766, "learning_rate": 2.9827266023764274e-06, "loss": 1.1448575258255005, "step": 892 }, { "epoch": 1.9822616407982263, "grad_norm": 1.1579248905181885, "learning_rate": 2.9745164506878134e-06, "loss": 1.0330946445465088, "step": 894 }, { "epoch": 1.9866962305986697, "grad_norm": 1.960567593574524, "learning_rate": 2.9663032784028596e-06, "loss": 0.8949038982391357, "step": 896 }, { "epoch": 1.9911308203991132, "grad_norm": 1.6049984693527222, "learning_rate": 2.9580871960198297e-06, "loss": 0.9902207255363464, "step": 898 }, { "epoch": 1.9955654101995566, "grad_norm": 0.6963536143302917, "learning_rate": 2.949868314076142e-06, "loss": 0.8349514007568359, "step": 900 }, { "epoch": 2.0, "grad_norm": 2.399693250656128, "learning_rate": 2.941646743146875e-06, "loss": 1.027801513671875, "step": 902 }, { "epoch": 2.0044345898004434, "grad_norm": 0.7714170813560486, "learning_rate": 2.9334225938432868e-06, "loss": 0.8111017942428589, "step": 904 }, { "epoch": 2.008869179600887, "grad_norm": 0.9238205552101135, "learning_rate": 2.925195976811326e-06, "loss": 0.8706294298171997, "step": 906 }, { "epoch": 2.0133037694013303, "grad_norm": 0.9386454224586487, "learning_rate": 2.9169670027301387e-06, "loss": 1.0718032121658325, "step": 908 }, { "epoch": 2.0177383592017737, "grad_norm": 0.6776597499847412, "learning_rate": 2.9087357823105843e-06, "loss": 0.8469350337982178, "step": 910 }, { "epoch": 2.022172949002217, "grad_norm": 0.7392479181289673, "learning_rate": 2.9005024262937427e-06, "loss": 0.565307080745697, "step": 912 }, { "epoch": 2.0266075388026605, "grad_norm": 1.9702166318893433, "learning_rate": 2.8922670454494247e-06, "loss": 0.6154354810714722, "step": 914 }, { "epoch": 2.0310421286031044, "grad_norm": 0.9764010310173035, "learning_rate": 2.8840297505746843e-06, "loss": 0.6004781126976013, "step": 916 }, { "epoch": 2.035476718403548, "grad_norm": 0.8005667924880981, "learning_rate": 2.8757906524923286e-06, "loss": 0.8735350370407104, "step": 918 }, { "epoch": 2.0399113082039912, "grad_norm": 0.9138982892036438, "learning_rate": 2.867549862049419e-06, "loss": 0.6707923412322998, "step": 920 }, { "epoch": 2.0443458980044347, "grad_norm": 0.8569697737693787, "learning_rate": 2.859307490115791e-06, "loss": 0.7545152306556702, "step": 922 }, { "epoch": 2.048780487804878, "grad_norm": 0.619215190410614, "learning_rate": 2.8510636475825533e-06, "loss": 0.30162450671195984, "step": 924 }, { "epoch": 2.0532150776053215, "grad_norm": 1.0538161993026733, "learning_rate": 2.8428184453606027e-06, "loss": 0.8686986565589905, "step": 926 }, { "epoch": 2.057649667405765, "grad_norm": 1.8079990148544312, "learning_rate": 2.8345719943791266e-06, "loss": 0.6156920790672302, "step": 928 }, { "epoch": 2.0620842572062084, "grad_norm": 0.4749872088432312, "learning_rate": 2.826324405584114e-06, "loss": 0.5743507742881775, "step": 930 }, { "epoch": 2.066518847006652, "grad_norm": 2.578096866607666, "learning_rate": 2.818075789936863e-06, "loss": 0.7628493905067444, "step": 932 }, { "epoch": 2.070953436807095, "grad_norm": 1.2346030473709106, "learning_rate": 2.8098262584124834e-06, "loss": 0.8032713532447815, "step": 934 }, { "epoch": 2.0753880266075386, "grad_norm": 0.9657310843467712, "learning_rate": 2.801575921998411e-06, "loss": 0.9190863966941833, "step": 936 }, { "epoch": 2.079822616407982, "grad_norm": 0.8309587836265564, "learning_rate": 2.7933248916929066e-06, "loss": 0.5717717409133911, "step": 938 }, { "epoch": 2.084257206208426, "grad_norm": 0.7853623628616333, "learning_rate": 2.7850732785035705e-06, "loss": 0.6060709357261658, "step": 940 }, { "epoch": 2.0886917960088693, "grad_norm": 0.9614481329917908, "learning_rate": 2.7768211934458417e-06, "loss": 0.817306399345398, "step": 942 }, { "epoch": 2.0931263858093128, "grad_norm": 0.9111508727073669, "learning_rate": 2.768568747541509e-06, "loss": 0.5221774578094482, "step": 944 }, { "epoch": 2.097560975609756, "grad_norm": 0.8565526008605957, "learning_rate": 2.7603160518172152e-06, "loss": 0.8890185356140137, "step": 946 }, { "epoch": 2.1019955654101996, "grad_norm": 1.2437005043029785, "learning_rate": 2.752063217302966e-06, "loss": 0.9257514476776123, "step": 948 }, { "epoch": 2.106430155210643, "grad_norm": 1.692129373550415, "learning_rate": 2.743810355030631e-06, "loss": 0.6258480548858643, "step": 950 }, { "epoch": 2.1108647450110865, "grad_norm": 2.0805153846740723, "learning_rate": 2.735557576032458e-06, "loss": 0.7526692152023315, "step": 952 }, { "epoch": 2.11529933481153, "grad_norm": 2.8665034770965576, "learning_rate": 2.727304991339569e-06, "loss": 0.6801300644874573, "step": 954 }, { "epoch": 2.1197339246119733, "grad_norm": 0.8256810307502747, "learning_rate": 2.7190527119804762e-06, "loss": 0.8693723678588867, "step": 956 }, { "epoch": 2.1241685144124167, "grad_norm": 0.7408389449119568, "learning_rate": 2.710800848979582e-06, "loss": 0.7428317070007324, "step": 958 }, { "epoch": 2.12860310421286, "grad_norm": 1.6947144269943237, "learning_rate": 2.702549513355687e-06, "loss": 0.688827395439148, "step": 960 }, { "epoch": 2.1330376940133036, "grad_norm": 3.077284574508667, "learning_rate": 2.694298816120497e-06, "loss": 0.4587607979774475, "step": 962 }, { "epoch": 2.1374722838137474, "grad_norm": 2.8907575607299805, "learning_rate": 2.6860488682771306e-06, "loss": 0.9636158347129822, "step": 964 }, { "epoch": 2.141906873614191, "grad_norm": 1.936044454574585, "learning_rate": 2.67779978081862e-06, "loss": 0.7787302136421204, "step": 966 }, { "epoch": 2.1463414634146343, "grad_norm": 0.9226675629615784, "learning_rate": 2.669551664726428e-06, "loss": 0.5220115780830383, "step": 968 }, { "epoch": 2.1507760532150777, "grad_norm": 0.9738346338272095, "learning_rate": 2.6613046309689433e-06, "loss": 0.6782161593437195, "step": 970 }, { "epoch": 2.155210643015521, "grad_norm": 0.9448055028915405, "learning_rate": 2.6530587904999966e-06, "loss": 0.6957781314849854, "step": 972 }, { "epoch": 2.1596452328159645, "grad_norm": 1.6226963996887207, "learning_rate": 2.6448142542573624e-06, "loss": 0.8800594806671143, "step": 974 }, { "epoch": 2.164079822616408, "grad_norm": 1.0587058067321777, "learning_rate": 2.6365711331612692e-06, "loss": 0.7791632413864136, "step": 976 }, { "epoch": 2.1685144124168514, "grad_norm": 3.0447235107421875, "learning_rate": 2.6283295381129066e-06, "loss": 0.5873762965202332, "step": 978 }, { "epoch": 2.172949002217295, "grad_norm": 1.2626818418502808, "learning_rate": 2.620089579992933e-06, "loss": 0.8509657979011536, "step": 980 }, { "epoch": 2.1773835920177382, "grad_norm": 0.7221801280975342, "learning_rate": 2.6118513696599823e-06, "loss": 0.4064200818538666, "step": 982 }, { "epoch": 2.1818181818181817, "grad_norm": 1.155705451965332, "learning_rate": 2.603615017949178e-06, "loss": 0.2613215446472168, "step": 984 }, { "epoch": 2.186252771618625, "grad_norm": 3.4410154819488525, "learning_rate": 2.595380635670634e-06, "loss": 0.6540266275405884, "step": 986 }, { "epoch": 2.1906873614190685, "grad_norm": 12.9176607131958, "learning_rate": 2.5871483336079694e-06, "loss": 0.528972864151001, "step": 988 }, { "epoch": 2.1951219512195124, "grad_norm": 1.3602675199508667, "learning_rate": 2.578918222516818e-06, "loss": 0.875016987323761, "step": 990 }, { "epoch": 2.199556541019956, "grad_norm": 1.8910794258117676, "learning_rate": 2.5706904131233336e-06, "loss": 0.9778388738632202, "step": 992 }, { "epoch": 2.203991130820399, "grad_norm": 1.9940085411071777, "learning_rate": 2.5624650161227073e-06, "loss": 0.7324192523956299, "step": 994 }, { "epoch": 2.2084257206208426, "grad_norm": 0.7409563660621643, "learning_rate": 2.5542421421776696e-06, "loss": 0.91463702917099, "step": 996 }, { "epoch": 2.212860310421286, "grad_norm": 1.0401170253753662, "learning_rate": 2.5460219019170097e-06, "loss": 0.8429087400436401, "step": 998 }, { "epoch": 2.2172949002217295, "grad_norm": 0.8627730011940002, "learning_rate": 2.5378044059340845e-06, "loss": 0.6182942986488342, "step": 1000 }, { "epoch": 2.221729490022173, "grad_norm": 1.778159737586975, "learning_rate": 2.5295897647853283e-06, "loss": 0.41667890548706055, "step": 1002 }, { "epoch": 2.2261640798226163, "grad_norm": 0.6985337734222412, "learning_rate": 2.521378088988767e-06, "loss": 0.9056693911552429, "step": 1004 }, { "epoch": 2.2305986696230597, "grad_norm": 1.2205218076705933, "learning_rate": 2.513169489022531e-06, "loss": 0.7475935816764832, "step": 1006 }, { "epoch": 2.235033259423503, "grad_norm": 0.8802860379219055, "learning_rate": 2.5049640753233705e-06, "loss": 0.9124072194099426, "step": 1008 }, { "epoch": 2.2394678492239466, "grad_norm": 1.432633876800537, "learning_rate": 2.496761958285167e-06, "loss": 0.5237014293670654, "step": 1010 }, { "epoch": 2.2439024390243905, "grad_norm": 0.8981291055679321, "learning_rate": 2.488563248257451e-06, "loss": 0.8662800192832947, "step": 1012 }, { "epoch": 2.248337028824834, "grad_norm": 3.874892234802246, "learning_rate": 2.4803680555439136e-06, "loss": 0.7132869362831116, "step": 1014 }, { "epoch": 2.2527716186252773, "grad_norm": 0.9583449959754944, "learning_rate": 2.4721764904009272e-06, "loss": 0.9416664838790894, "step": 1016 }, { "epoch": 2.2572062084257207, "grad_norm": 1.920847773551941, "learning_rate": 2.4639886630360574e-06, "loss": 0.522179901599884, "step": 1018 }, { "epoch": 2.261640798226164, "grad_norm": 0.8928440809249878, "learning_rate": 2.455804683606584e-06, "loss": 0.8632444739341736, "step": 1020 }, { "epoch": 2.2660753880266076, "grad_norm": 0.40272587537765503, "learning_rate": 2.4476246622180174e-06, "loss": 0.4794633090496063, "step": 1022 }, { "epoch": 2.270509977827051, "grad_norm": 1.993319034576416, "learning_rate": 2.4394487089226158e-06, "loss": 1.1585773229599, "step": 1024 }, { "epoch": 2.2749445676274944, "grad_norm": 0.8279446363449097, "learning_rate": 2.43127693371791e-06, "loss": 0.6182215809822083, "step": 1026 }, { "epoch": 2.279379157427938, "grad_norm": 0.7182877659797668, "learning_rate": 2.423109446545213e-06, "loss": 0.8768652677536011, "step": 1028 }, { "epoch": 2.2838137472283813, "grad_norm": 1.7738810777664185, "learning_rate": 2.4149463572881537e-06, "loss": 0.9176031351089478, "step": 1030 }, { "epoch": 2.2882483370288247, "grad_norm": 0.8209647536277771, "learning_rate": 2.4067877757711907e-06, "loss": 0.6851370930671692, "step": 1032 }, { "epoch": 2.292682926829268, "grad_norm": 1.1586294174194336, "learning_rate": 2.3986338117581357e-06, "loss": 0.5924996137619019, "step": 1034 }, { "epoch": 2.2971175166297115, "grad_norm": 1.9774837493896484, "learning_rate": 2.390484574950677e-06, "loss": 0.862289309501648, "step": 1036 }, { "epoch": 2.3015521064301554, "grad_norm": 1.9414352178573608, "learning_rate": 2.382340174986906e-06, "loss": 0.7861872911453247, "step": 1038 }, { "epoch": 2.305986696230599, "grad_norm": 2.3420515060424805, "learning_rate": 2.374200721439837e-06, "loss": 0.8478289246559143, "step": 1040 }, { "epoch": 2.3104212860310422, "grad_norm": 1.3481749296188354, "learning_rate": 2.3660663238159405e-06, "loss": 0.901607096195221, "step": 1042 }, { "epoch": 2.3148558758314857, "grad_norm": 0.6049371957778931, "learning_rate": 2.357937091553662e-06, "loss": 0.7081278562545776, "step": 1044 }, { "epoch": 2.319290465631929, "grad_norm": 1.6102485656738281, "learning_rate": 2.3498131340219554e-06, "loss": 0.8813071846961975, "step": 1046 }, { "epoch": 2.3237250554323725, "grad_norm": 0.9218488931655884, "learning_rate": 2.341694560518809e-06, "loss": 0.8351644277572632, "step": 1048 }, { "epoch": 2.328159645232816, "grad_norm": 1.1544103622436523, "learning_rate": 2.333581480269776e-06, "loss": 0.9058061838150024, "step": 1050 }, { "epoch": 2.3325942350332594, "grad_norm": 1.371621012687683, "learning_rate": 2.325474002426503e-06, "loss": 0.7822686433792114, "step": 1052 }, { "epoch": 2.337028824833703, "grad_norm": 0.9093418717384338, "learning_rate": 2.3173722360652644e-06, "loss": 0.6994078755378723, "step": 1054 }, { "epoch": 2.341463414634146, "grad_norm": 0.731285035610199, "learning_rate": 2.309276290185494e-06, "loss": 0.759069561958313, "step": 1056 }, { "epoch": 2.3458980044345896, "grad_norm": 0.32100459933280945, "learning_rate": 2.3011862737083162e-06, "loss": 0.5203639268875122, "step": 1058 }, { "epoch": 2.3503325942350335, "grad_norm": 1.7071316242218018, "learning_rate": 2.2931022954750843e-06, "loss": 0.9963219165802002, "step": 1060 }, { "epoch": 2.354767184035477, "grad_norm": 5.787060737609863, "learning_rate": 2.285024464245912e-06, "loss": 0.4076020419597626, "step": 1062 }, { "epoch": 2.3592017738359203, "grad_norm": 0.3795124590396881, "learning_rate": 2.2769528886982158e-06, "loss": 0.4680769443511963, "step": 1064 }, { "epoch": 2.3636363636363638, "grad_norm": 4.307487964630127, "learning_rate": 2.268887677425248e-06, "loss": 0.7492026090621948, "step": 1066 }, { "epoch": 2.368070953436807, "grad_norm": 0.6910419464111328, "learning_rate": 2.2608289389346362e-06, "loss": 0.9367992877960205, "step": 1068 }, { "epoch": 2.3725055432372506, "grad_norm": 0.7431702613830566, "learning_rate": 2.2527767816469263e-06, "loss": 0.8184199929237366, "step": 1070 }, { "epoch": 2.376940133037694, "grad_norm": 1.009751558303833, "learning_rate": 2.244731313894121e-06, "loss": 0.787276566028595, "step": 1072 }, { "epoch": 2.3813747228381374, "grad_norm": 0.4790377914905548, "learning_rate": 2.236692643918224e-06, "loss": 0.024766096845269203, "step": 1074 }, { "epoch": 2.385809312638581, "grad_norm": 1.139642357826233, "learning_rate": 2.2286608798697834e-06, "loss": 0.5393450856208801, "step": 1076 }, { "epoch": 2.3902439024390243, "grad_norm": 1.150428295135498, "learning_rate": 2.2206361298064343e-06, "loss": 0.373291552066803, "step": 1078 }, { "epoch": 2.3946784922394677, "grad_norm": 1.323978066444397, "learning_rate": 2.2126185016914515e-06, "loss": 0.6814523935317993, "step": 1080 }, { "epoch": 2.399113082039911, "grad_norm": 0.38711783289909363, "learning_rate": 2.2046081033922884e-06, "loss": 0.5636866092681885, "step": 1082 }, { "epoch": 2.4035476718403546, "grad_norm": 2.8012638092041016, "learning_rate": 2.1966050426791325e-06, "loss": 0.6869620084762573, "step": 1084 }, { "epoch": 2.4079822616407984, "grad_norm": 0.8223492503166199, "learning_rate": 2.1886094272234508e-06, "loss": 0.7766349911689758, "step": 1086 }, { "epoch": 2.412416851441242, "grad_norm": 0.4253004193305969, "learning_rate": 2.1806213645965457e-06, "loss": 0.3063335716724396, "step": 1088 }, { "epoch": 2.4168514412416853, "grad_norm": 2.2866053581237793, "learning_rate": 2.172640962268104e-06, "loss": 0.8616948127746582, "step": 1090 }, { "epoch": 2.4212860310421287, "grad_norm": 6.167764186859131, "learning_rate": 2.1646683276047525e-06, "loss": 1.083250641822815, "step": 1092 }, { "epoch": 2.425720620842572, "grad_norm": 2.147050142288208, "learning_rate": 2.156703567868615e-06, "loss": 0.40848734974861145, "step": 1094 }, { "epoch": 2.4301552106430155, "grad_norm": 2.4124085903167725, "learning_rate": 2.148746790215866e-06, "loss": 0.5506104826927185, "step": 1096 }, { "epoch": 2.434589800443459, "grad_norm": 0.7438501119613647, "learning_rate": 2.140798101695291e-06, "loss": 0.4622332453727722, "step": 1098 }, { "epoch": 2.4390243902439024, "grad_norm": 1.8033671379089355, "learning_rate": 2.1328576092468476e-06, "loss": 0.9211458563804626, "step": 1100 }, { "epoch": 2.443458980044346, "grad_norm": 0.6345164775848389, "learning_rate": 2.124925419700223e-06, "loss": 0.9258796572685242, "step": 1102 }, { "epoch": 2.4478935698447892, "grad_norm": 1.8896942138671875, "learning_rate": 2.1170016397734e-06, "loss": 0.4680280089378357, "step": 1104 }, { "epoch": 2.4523281596452327, "grad_norm": 0.8533465266227722, "learning_rate": 2.109086376071221e-06, "loss": 0.830375611782074, "step": 1106 }, { "epoch": 2.4567627494456765, "grad_norm": 2.495920181274414, "learning_rate": 2.1011797350839513e-06, "loss": 0.7596384286880493, "step": 1108 }, { "epoch": 2.4611973392461195, "grad_norm": 0.9585152864456177, "learning_rate": 2.093281823185848e-06, "loss": 0.8787661790847778, "step": 1110 }, { "epoch": 2.4656319290465634, "grad_norm": 0.6246011257171631, "learning_rate": 2.0853927466337315e-06, "loss": 0.578016459941864, "step": 1112 }, { "epoch": 2.470066518847007, "grad_norm": 0.9855407476425171, "learning_rate": 2.077512611565551e-06, "loss": 0.8436506986618042, "step": 1114 }, { "epoch": 2.47450110864745, "grad_norm": 2.1086971759796143, "learning_rate": 2.0696415239989593e-06, "loss": 0.35142093896865845, "step": 1116 }, { "epoch": 2.4789356984478936, "grad_norm": 0.8225948810577393, "learning_rate": 2.0617795898298855e-06, "loss": 0.8377672433853149, "step": 1118 }, { "epoch": 2.483370288248337, "grad_norm": 1.1087491512298584, "learning_rate": 2.053926914831112e-06, "loss": 0.7869824767112732, "step": 1120 }, { "epoch": 2.4878048780487805, "grad_norm": 1.0127193927764893, "learning_rate": 2.04608360465085e-06, "loss": 0.8879801034927368, "step": 1122 }, { "epoch": 2.492239467849224, "grad_norm": 6.3018717765808105, "learning_rate": 2.038249764811318e-06, "loss": 1.030903935432434, "step": 1124 }, { "epoch": 2.4966740576496673, "grad_norm": 0.7648253440856934, "learning_rate": 2.0304255007073227e-06, "loss": 0.9654337763786316, "step": 1126 }, { "epoch": 2.5011086474501107, "grad_norm": 1.2895153760910034, "learning_rate": 2.022610917604842e-06, "loss": 0.6278480291366577, "step": 1128 }, { "epoch": 2.505543237250554, "grad_norm": 2.6871118545532227, "learning_rate": 2.014806120639605e-06, "loss": 0.6305501461029053, "step": 1130 }, { "epoch": 2.5099778270509976, "grad_norm": 11.048127174377441, "learning_rate": 2.007011214815684e-06, "loss": 0.7386720776557922, "step": 1132 }, { "epoch": 2.5144124168514415, "grad_norm": 1.0972473621368408, "learning_rate": 1.9992263050040737e-06, "loss": 0.5156517028808594, "step": 1134 }, { "epoch": 2.5188470066518844, "grad_norm": 0.9979491829872131, "learning_rate": 1.991451495941289e-06, "loss": 0.908918023109436, "step": 1136 }, { "epoch": 2.5232815964523283, "grad_norm": 0.9635651707649231, "learning_rate": 1.983686892227948e-06, "loss": 0.6651601791381836, "step": 1138 }, { "epoch": 2.5277161862527717, "grad_norm": 1.025274395942688, "learning_rate": 1.975932598327369e-06, "loss": 0.8417225480079651, "step": 1140 }, { "epoch": 2.532150776053215, "grad_norm": 10.28856086730957, "learning_rate": 1.9681887185641646e-06, "loss": 0.4462983310222626, "step": 1142 }, { "epoch": 2.5365853658536586, "grad_norm": 0.5850323438644409, "learning_rate": 1.9604553571228395e-06, "loss": 0.5580345392227173, "step": 1144 }, { "epoch": 2.541019955654102, "grad_norm": 1.3211580514907837, "learning_rate": 1.9527326180463855e-06, "loss": 0.9013155102729797, "step": 1146 }, { "epoch": 2.5454545454545454, "grad_norm": 0.7220462560653687, "learning_rate": 1.9450206052348823e-06, "loss": 0.8708188533782959, "step": 1148 }, { "epoch": 2.549889135254989, "grad_norm": 0.9700856804847717, "learning_rate": 1.9373194224441028e-06, "loss": 0.8098379969596863, "step": 1150 }, { "epoch": 2.5543237250554323, "grad_norm": 1.2969111204147339, "learning_rate": 1.929629173284114e-06, "loss": 0.5333951711654663, "step": 1152 }, { "epoch": 2.5587583148558757, "grad_norm": 0.45577237010002136, "learning_rate": 1.9219499612178836e-06, "loss": 0.3139987289905548, "step": 1154 }, { "epoch": 2.5631929046563195, "grad_norm": 2.8768374919891357, "learning_rate": 1.9142818895598908e-06, "loss": 0.5258563756942749, "step": 1156 }, { "epoch": 2.5676274944567625, "grad_norm": 2.359679937362671, "learning_rate": 1.9066250614747317e-06, "loss": 0.6680082082748413, "step": 1158 }, { "epoch": 2.5720620842572064, "grad_norm": 1.424459457397461, "learning_rate": 1.8989795799757348e-06, "loss": 0.7696115970611572, "step": 1160 }, { "epoch": 2.57649667405765, "grad_norm": 1.1945898532867432, "learning_rate": 1.8913455479235754e-06, "loss": 0.86902916431427, "step": 1162 }, { "epoch": 2.5809312638580932, "grad_norm": 0.942388653755188, "learning_rate": 1.8837230680248874e-06, "loss": 0.8644537925720215, "step": 1164 }, { "epoch": 2.5853658536585367, "grad_norm": 0.9040746092796326, "learning_rate": 1.8761122428308875e-06, "loss": 0.5937469601631165, "step": 1166 }, { "epoch": 2.58980044345898, "grad_norm": 1.1163363456726074, "learning_rate": 1.8685131747359902e-06, "loss": 0.8463367819786072, "step": 1168 }, { "epoch": 2.5942350332594235, "grad_norm": 1.2768183946609497, "learning_rate": 1.8609259659764345e-06, "loss": 0.8608056306838989, "step": 1170 }, { "epoch": 2.598669623059867, "grad_norm": 1.604803204536438, "learning_rate": 1.853350718628904e-06, "loss": 0.3180133104324341, "step": 1172 }, { "epoch": 2.6031042128603104, "grad_norm": 0.94985032081604, "learning_rate": 1.845787534609157e-06, "loss": 0.5958639979362488, "step": 1174 }, { "epoch": 2.6075388026607538, "grad_norm": 0.8320684432983398, "learning_rate": 1.8382365156706566e-06, "loss": 0.6725127696990967, "step": 1176 }, { "epoch": 2.611973392461197, "grad_norm": 1.2190077304840088, "learning_rate": 1.8306977634031976e-06, "loss": 0.6454840302467346, "step": 1178 }, { "epoch": 2.6164079822616406, "grad_norm": 3.530073642730713, "learning_rate": 1.8231713792315403e-06, "loss": 0.6968674659729004, "step": 1180 }, { "epoch": 2.6208425720620845, "grad_norm": 0.7371127605438232, "learning_rate": 1.8156574644140495e-06, "loss": 0.7820730805397034, "step": 1182 }, { "epoch": 2.6252771618625275, "grad_norm": 0.9225616455078125, "learning_rate": 1.8081561200413295e-06, "loss": 0.8885502815246582, "step": 1184 }, { "epoch": 2.6297117516629713, "grad_norm": 1.0041942596435547, "learning_rate": 1.800667447034864e-06, "loss": 0.863980770111084, "step": 1186 }, { "epoch": 2.6341463414634148, "grad_norm": 2.831209421157837, "learning_rate": 1.7931915461456573e-06, "loss": 0.936083197593689, "step": 1188 }, { "epoch": 2.638580931263858, "grad_norm": 0.8209375143051147, "learning_rate": 1.7857285179528838e-06, "loss": 0.5256603360176086, "step": 1190 }, { "epoch": 2.6430155210643016, "grad_norm": 8.401679992675781, "learning_rate": 1.7782784628625305e-06, "loss": 0.807640552520752, "step": 1192 }, { "epoch": 2.647450110864745, "grad_norm": 1.9250189065933228, "learning_rate": 1.7708414811060437e-06, "loss": 0.5451607704162598, "step": 1194 }, { "epoch": 2.6518847006651884, "grad_norm": 1.3286583423614502, "learning_rate": 1.763417672738989e-06, "loss": 0.7666381001472473, "step": 1196 }, { "epoch": 2.656319290465632, "grad_norm": 0.7077732086181641, "learning_rate": 1.7560071376396953e-06, "loss": 0.258193701505661, "step": 1198 }, { "epoch": 2.6607538802660753, "grad_norm": 0.7076205611228943, "learning_rate": 1.7486099755079197e-06, "loss": 0.9763070344924927, "step": 1200 }, { "epoch": 2.6651884700665187, "grad_norm": 0.667148232460022, "learning_rate": 1.7412262858634987e-06, "loss": 0.9205498099327087, "step": 1202 }, { "epoch": 2.6696230598669626, "grad_norm": 1.1608986854553223, "learning_rate": 1.7338561680450171e-06, "loss": 0.4887681007385254, "step": 1204 }, { "epoch": 2.6740576496674056, "grad_norm": 1.135400414466858, "learning_rate": 1.7264997212084616e-06, "loss": 0.7635675668716431, "step": 1206 }, { "epoch": 2.6784922394678494, "grad_norm": 1.1827253103256226, "learning_rate": 1.7191570443258976e-06, "loss": 0.9846773147583008, "step": 1208 }, { "epoch": 2.682926829268293, "grad_norm": 1.253548502922058, "learning_rate": 1.711828236184131e-06, "loss": 0.506197988986969, "step": 1210 }, { "epoch": 2.6873614190687363, "grad_norm": 2.297689199447632, "learning_rate": 1.704513395383378e-06, "loss": 0.3404999375343323, "step": 1212 }, { "epoch": 2.6917960088691797, "grad_norm": 0.9552398920059204, "learning_rate": 1.6972126203359454e-06, "loss": 0.5362938046455383, "step": 1214 }, { "epoch": 2.696230598669623, "grad_norm": 4.347363471984863, "learning_rate": 1.6899260092648995e-06, "loss": 0.6291901469230652, "step": 1216 }, { "epoch": 2.7006651884700665, "grad_norm": 2.0356476306915283, "learning_rate": 1.6826536602027471e-06, "loss": 0.6693211197853088, "step": 1218 }, { "epoch": 2.70509977827051, "grad_norm": 0.9919900894165039, "learning_rate": 1.6753956709901202e-06, "loss": 0.9943591952323914, "step": 1220 }, { "epoch": 2.7095343680709534, "grad_norm": 1.3586797714233398, "learning_rate": 1.6681521392744515e-06, "loss": 0.6912680268287659, "step": 1222 }, { "epoch": 2.713968957871397, "grad_norm": 2.1318626403808594, "learning_rate": 1.660923162508671e-06, "loss": 0.8818514347076416, "step": 1224 }, { "epoch": 2.7184035476718402, "grad_norm": 1.702278971672058, "learning_rate": 1.6537088379498872e-06, "loss": 0.4949290454387665, "step": 1226 }, { "epoch": 2.7228381374722836, "grad_norm": 1.441737413406372, "learning_rate": 1.6465092626580787e-06, "loss": 0.991607666015625, "step": 1228 }, { "epoch": 2.7272727272727275, "grad_norm": 1.105600357055664, "learning_rate": 1.6393245334947942e-06, "loss": 0.7393255233764648, "step": 1230 }, { "epoch": 2.7317073170731705, "grad_norm": 0.6143295764923096, "learning_rate": 1.6321547471218432e-06, "loss": 0.812101423740387, "step": 1232 }, { "epoch": 2.7361419068736144, "grad_norm": 2.9823520183563232, "learning_rate": 1.6250000000000007e-06, "loss": 0.41637933254241943, "step": 1234 }, { "epoch": 2.740576496674058, "grad_norm": 0.9311825633049011, "learning_rate": 1.6178603883877032e-06, "loss": 0.8702437877655029, "step": 1236 }, { "epoch": 2.745011086474501, "grad_norm": 0.8797629475593567, "learning_rate": 1.6107360083397604e-06, "loss": 0.5236175060272217, "step": 1238 }, { "epoch": 2.7494456762749446, "grad_norm": 0.7002538442611694, "learning_rate": 1.6036269557060594e-06, "loss": 0.5518063306808472, "step": 1240 }, { "epoch": 2.753880266075388, "grad_norm": 0.7229853272438049, "learning_rate": 1.5965333261302735e-06, "loss": 0.9187084436416626, "step": 1242 }, { "epoch": 2.7583148558758315, "grad_norm": 2.7623326778411865, "learning_rate": 1.5894552150485801e-06, "loss": 0.8829126358032227, "step": 1244 }, { "epoch": 2.762749445676275, "grad_norm": 1.0560897588729858, "learning_rate": 1.5823927176883725e-06, "loss": 0.44306543469429016, "step": 1246 }, { "epoch": 2.7671840354767183, "grad_norm": 2.0120999813079834, "learning_rate": 1.5753459290669792e-06, "loss": 0.5320644974708557, "step": 1248 }, { "epoch": 2.7716186252771617, "grad_norm": 1.5977369546890259, "learning_rate": 1.5683149439903905e-06, "loss": 0.6207846403121948, "step": 1250 }, { "epoch": 2.776053215077605, "grad_norm": 1.803134560585022, "learning_rate": 1.5612998570519746e-06, "loss": 0.9645813703536987, "step": 1252 }, { "epoch": 2.7804878048780486, "grad_norm": 0.9961108565330505, "learning_rate": 1.5543007626312129e-06, "loss": 0.9654743671417236, "step": 1254 }, { "epoch": 2.7849223946784925, "grad_norm": 0.9151904582977295, "learning_rate": 1.5473177548924267e-06, "loss": 0.928931713104248, "step": 1256 }, { "epoch": 2.7893569844789354, "grad_norm": 0.7890511155128479, "learning_rate": 1.5403509277835077e-06, "loss": 0.1760758012533188, "step": 1258 }, { "epoch": 2.7937915742793793, "grad_norm": 0.9414036273956299, "learning_rate": 1.5334003750346608e-06, "loss": 0.8468573093414307, "step": 1260 }, { "epoch": 2.7982261640798227, "grad_norm": 3.476710319519043, "learning_rate": 1.5264661901571349e-06, "loss": 0.5655899047851562, "step": 1262 }, { "epoch": 2.802660753880266, "grad_norm": 0.9431162476539612, "learning_rate": 1.5195484664419732e-06, "loss": 0.4929567277431488, "step": 1264 }, { "epoch": 2.8070953436807096, "grad_norm": 1.4319041967391968, "learning_rate": 1.5126472969587502e-06, "loss": 0.8094195127487183, "step": 1266 }, { "epoch": 2.811529933481153, "grad_norm": 3.1319103240966797, "learning_rate": 1.5057627745543269e-06, "loss": 0.907342791557312, "step": 1268 }, { "epoch": 2.8159645232815964, "grad_norm": 1.1402379274368286, "learning_rate": 1.4988949918515947e-06, "loss": 0.9050721526145935, "step": 1270 }, { "epoch": 2.82039911308204, "grad_norm": 3.1753454208374023, "learning_rate": 1.4920440412482345e-06, "loss": 0.4124918282032013, "step": 1272 }, { "epoch": 2.8248337028824833, "grad_norm": 1.2776395082473755, "learning_rate": 1.485210014915473e-06, "loss": 0.540270984172821, "step": 1274 }, { "epoch": 2.8292682926829267, "grad_norm": 1.1165990829467773, "learning_rate": 1.4783930047968388e-06, "loss": 0.8869239091873169, "step": 1276 }, { "epoch": 2.8337028824833705, "grad_norm": 1.8204717636108398, "learning_rate": 1.4715931026069273e-06, "loss": 0.8854659199714661, "step": 1278 }, { "epoch": 2.8381374722838135, "grad_norm": 1.062864899635315, "learning_rate": 1.4648103998301716e-06, "loss": 0.5227654576301575, "step": 1280 }, { "epoch": 2.8425720620842574, "grad_norm": 4.4705400466918945, "learning_rate": 1.4580449877196035e-06, "loss": 0.5940520763397217, "step": 1282 }, { "epoch": 2.847006651884701, "grad_norm": 1.0326560735702515, "learning_rate": 1.4512969572956328e-06, "loss": 0.6471421122550964, "step": 1284 }, { "epoch": 2.8514412416851442, "grad_norm": 0.8020298480987549, "learning_rate": 1.4445663993448173e-06, "loss": 0.8675932884216309, "step": 1286 }, { "epoch": 2.8558758314855877, "grad_norm": 2.7269020080566406, "learning_rate": 1.437853404418646e-06, "loss": 0.2647731602191925, "step": 1288 }, { "epoch": 2.860310421286031, "grad_norm": 1.6477257013320923, "learning_rate": 1.431158062832318e-06, "loss": 0.9172856211662292, "step": 1290 }, { "epoch": 2.8647450110864745, "grad_norm": 1.286494255065918, "learning_rate": 1.4244804646635266e-06, "loss": 0.8936296105384827, "step": 1292 }, { "epoch": 2.869179600886918, "grad_norm": 2.2755205631256104, "learning_rate": 1.4178206997512522e-06, "loss": 0.8551170229911804, "step": 1294 }, { "epoch": 2.8736141906873613, "grad_norm": 0.80238938331604, "learning_rate": 1.4111788576945467e-06, "loss": 0.8603898882865906, "step": 1296 }, { "epoch": 2.8780487804878048, "grad_norm": 1.9288290739059448, "learning_rate": 1.4045550278513351e-06, "loss": 0.5612266659736633, "step": 1298 }, { "epoch": 2.882483370288248, "grad_norm": 0.8210675716400146, "learning_rate": 1.3979492993372074e-06, "loss": 0.9199106097221375, "step": 1300 }, { "epoch": 2.8869179600886916, "grad_norm": 2.33469557762146, "learning_rate": 1.391361761024222e-06, "loss": 0.26451584696769714, "step": 1302 }, { "epoch": 2.8913525498891355, "grad_norm": 0.852741539478302, "learning_rate": 1.3847925015397146e-06, "loss": 0.8316776156425476, "step": 1304 }, { "epoch": 2.8957871396895785, "grad_norm": 1.808684229850769, "learning_rate": 1.3782416092650957e-06, "loss": 0.7958760261535645, "step": 1306 }, { "epoch": 2.9002217294900223, "grad_norm": 0.3986283838748932, "learning_rate": 1.3717091723346699e-06, "loss": 0.35594817996025085, "step": 1308 }, { "epoch": 2.9046563192904657, "grad_norm": 1.0733470916748047, "learning_rate": 1.3651952786344485e-06, "loss": 0.4130232036113739, "step": 1310 }, { "epoch": 2.909090909090909, "grad_norm": 2.3315577507019043, "learning_rate": 1.3587000158009638e-06, "loss": 0.8895840048789978, "step": 1312 }, { "epoch": 2.9135254988913526, "grad_norm": 0.7047470808029175, "learning_rate": 1.3522234712200954e-06, "loss": 0.8686839938163757, "step": 1314 }, { "epoch": 2.917960088691796, "grad_norm": 5.497637748718262, "learning_rate": 1.3457657320258878e-06, "loss": 0.8700605034828186, "step": 1316 }, { "epoch": 2.9223946784922394, "grad_norm": 0.7429857850074768, "learning_rate": 1.3393268850993852e-06, "loss": 0.8899486064910889, "step": 1318 }, { "epoch": 2.926829268292683, "grad_norm": 0.9991167187690735, "learning_rate": 1.332907017067458e-06, "loss": 0.6314383745193481, "step": 1320 }, { "epoch": 2.9312638580931263, "grad_norm": 0.7007908821105957, "learning_rate": 1.3265062143016378e-06, "loss": 0.8329391479492188, "step": 1322 }, { "epoch": 2.9356984478935697, "grad_norm": 0.8860281705856323, "learning_rate": 1.3201245629169574e-06, "loss": 0.884133517742157, "step": 1324 }, { "epoch": 2.9401330376940136, "grad_norm": 1.6985708475112915, "learning_rate": 1.3137621487707902e-06, "loss": 0.8119447827339172, "step": 1326 }, { "epoch": 2.9445676274944566, "grad_norm": 1.1318223476409912, "learning_rate": 1.307419057461697e-06, "loss": 0.9324439167976379, "step": 1328 }, { "epoch": 2.9490022172949004, "grad_norm": 1.2057431936264038, "learning_rate": 1.3010953743282724e-06, "loss": 0.8887814283370972, "step": 1330 }, { "epoch": 2.953436807095344, "grad_norm": 1.5262060165405273, "learning_rate": 1.294791184447996e-06, "loss": 0.9244763255119324, "step": 1332 }, { "epoch": 2.9578713968957873, "grad_norm": 0.9449637532234192, "learning_rate": 1.2885065726360925e-06, "loss": 0.43268677592277527, "step": 1334 }, { "epoch": 2.9623059866962307, "grad_norm": 0.9329234957695007, "learning_rate": 1.282241623444386e-06, "loss": 0.8470190763473511, "step": 1336 }, { "epoch": 2.966740576496674, "grad_norm": 2.124790668487549, "learning_rate": 1.2759964211601633e-06, "loss": 0.9702441096305847, "step": 1338 }, { "epoch": 2.9711751662971175, "grad_norm": 0.800217866897583, "learning_rate": 1.269771049805042e-06, "loss": 0.6707828044891357, "step": 1340 }, { "epoch": 2.975609756097561, "grad_norm": 2.3894753456115723, "learning_rate": 1.2635655931338364e-06, "loss": 0.5933993458747864, "step": 1342 }, { "epoch": 2.9800443458980044, "grad_norm": 0.6761320233345032, "learning_rate": 1.2573801346334355e-06, "loss": 0.18841305375099182, "step": 1344 }, { "epoch": 2.984478935698448, "grad_norm": 0.9729594588279724, "learning_rate": 1.251214757521675e-06, "loss": 0.5959298610687256, "step": 1346 }, { "epoch": 2.988913525498891, "grad_norm": 0.9480107426643372, "learning_rate": 1.2450695447462214e-06, "loss": 0.506874144077301, "step": 1348 }, { "epoch": 2.9933481152993346, "grad_norm": 6.189738750457764, "learning_rate": 1.2389445789834534e-06, "loss": 0.5849905610084534, "step": 1350 }, { "epoch": 2.9977827050997785, "grad_norm": 0.7872065305709839, "learning_rate": 1.2328399426373511e-06, "loss": 0.7041124701499939, "step": 1352 }, { "epoch": 3.002217294900222, "grad_norm": 0.7769404649734497, "learning_rate": 1.2267557178383886e-06, "loss": 0.8147103786468506, "step": 1354 }, { "epoch": 3.0066518847006654, "grad_norm": 0.6591900587081909, "learning_rate": 1.220691986442424e-06, "loss": 0.41049686074256897, "step": 1356 }, { "epoch": 3.011086474501109, "grad_norm": 1.4137377738952637, "learning_rate": 1.2146488300296047e-06, "loss": 0.5945199131965637, "step": 1358 }, { "epoch": 3.015521064301552, "grad_norm": 2.8482906818389893, "learning_rate": 1.2086263299032652e-06, "loss": 0.7281069159507751, "step": 1360 }, { "epoch": 3.0199556541019956, "grad_norm": 0.9070174098014832, "learning_rate": 1.2026245670888343e-06, "loss": 0.6940351724624634, "step": 1362 }, { "epoch": 3.024390243902439, "grad_norm": 0.9107074737548828, "learning_rate": 1.196643622332747e-06, "loss": 0.8520534634590149, "step": 1364 }, { "epoch": 3.0288248337028825, "grad_norm": 0.2674312889575958, "learning_rate": 1.1906835761013547e-06, "loss": 0.34424373507499695, "step": 1366 }, { "epoch": 3.033259423503326, "grad_norm": 0.9089600443840027, "learning_rate": 1.184744508579846e-06, "loss": 0.5831412076950073, "step": 1368 }, { "epoch": 3.0376940133037693, "grad_norm": 1.4997162818908691, "learning_rate": 1.178826499671167e-06, "loss": 0.5012683272361755, "step": 1370 }, { "epoch": 3.0421286031042127, "grad_norm": 1.6579214334487915, "learning_rate": 1.172929628994943e-06, "loss": 0.7454507350921631, "step": 1372 }, { "epoch": 3.046563192904656, "grad_norm": 1.7701013088226318, "learning_rate": 1.167053975886413e-06, "loss": 0.2646133005619049, "step": 1374 }, { "epoch": 3.0509977827050996, "grad_norm": 2.8594934940338135, "learning_rate": 1.1611996193953569e-06, "loss": 0.42731595039367676, "step": 1376 }, { "epoch": 3.0554323725055434, "grad_norm": 0.9399404525756836, "learning_rate": 1.1553666382850366e-06, "loss": 0.2942492365837097, "step": 1378 }, { "epoch": 3.059866962305987, "grad_norm": 0.2747500240802765, "learning_rate": 1.1495551110311324e-06, "loss": 0.3034818172454834, "step": 1380 }, { "epoch": 3.0643015521064303, "grad_norm": 1.7954272031784058, "learning_rate": 1.1437651158206904e-06, "loss": 0.23530253767967224, "step": 1382 }, { "epoch": 3.0687361419068737, "grad_norm": 1.6788283586502075, "learning_rate": 1.137996730551069e-06, "loss": 0.5282564163208008, "step": 1384 }, { "epoch": 3.073170731707317, "grad_norm": 0.3840465843677521, "learning_rate": 1.1322500328288897e-06, "loss": 0.2809971570968628, "step": 1386 }, { "epoch": 3.0776053215077606, "grad_norm": 0.16582423448562622, "learning_rate": 1.1265250999689966e-06, "loss": 0.28406068682670593, "step": 1388 }, { "epoch": 3.082039911308204, "grad_norm": 1.3691731691360474, "learning_rate": 1.1208220089934118e-06, "loss": 0.5798223614692688, "step": 1390 }, { "epoch": 3.0864745011086474, "grad_norm": 8.64896297454834, "learning_rate": 1.1151408366303024e-06, "loss": 0.2631751298904419, "step": 1392 }, { "epoch": 3.090909090909091, "grad_norm": 3.6928718090057373, "learning_rate": 1.1094816593129475e-06, "loss": 0.40734031796455383, "step": 1394 }, { "epoch": 3.0953436807095343, "grad_norm": 1.541538119316101, "learning_rate": 1.1038445531787083e-06, "loss": 0.6400181651115417, "step": 1396 }, { "epoch": 3.0997782705099777, "grad_norm": 1.3748445510864258, "learning_rate": 1.098229594068007e-06, "loss": 0.7110243439674377, "step": 1398 }, { "epoch": 3.104212860310421, "grad_norm": 0.5643441081047058, "learning_rate": 1.0926368575233032e-06, "loss": 0.5485574007034302, "step": 1400 }, { "epoch": 3.1086474501108645, "grad_norm": 0.3888166546821594, "learning_rate": 1.087066418788078e-06, "loss": 0.215177983045578, "step": 1402 }, { "epoch": 3.1130820399113084, "grad_norm": 1.9723485708236694, "learning_rate": 1.0815183528058248e-06, "loss": 0.4210178256034851, "step": 1404 }, { "epoch": 3.117516629711752, "grad_norm": 0.8655666708946228, "learning_rate": 1.0759927342190362e-06, "loss": 0.6706216335296631, "step": 1406 }, { "epoch": 3.1219512195121952, "grad_norm": 0.9195745587348938, "learning_rate": 1.0704896373682052e-06, "loss": 0.7625486850738525, "step": 1408 }, { "epoch": 3.1263858093126387, "grad_norm": 0.7832412123680115, "learning_rate": 1.0650091362908189e-06, "loss": 0.6624658107757568, "step": 1410 }, { "epoch": 3.130820399113082, "grad_norm": 1.7871705293655396, "learning_rate": 1.0595513047203693e-06, "loss": 0.7058153748512268, "step": 1412 }, { "epoch": 3.1352549889135255, "grad_norm": 1.7586992979049683, "learning_rate": 1.0541162160853538e-06, "loss": 0.47856301069259644, "step": 1414 }, { "epoch": 3.139689578713969, "grad_norm": 0.526236891746521, "learning_rate": 1.0487039435082941e-06, "loss": 0.062277086079120636, "step": 1416 }, { "epoch": 3.1441241685144123, "grad_norm": 1.4470797777175903, "learning_rate": 1.0433145598047495e-06, "loss": 0.7115893363952637, "step": 1418 }, { "epoch": 3.1485587583148558, "grad_norm": 0.995538592338562, "learning_rate": 1.0379481374823358e-06, "loss": 0.6006544232368469, "step": 1420 }, { "epoch": 3.152993348115299, "grad_norm": 1.696830153465271, "learning_rate": 1.032604748739751e-06, "loss": 0.6471589207649231, "step": 1422 }, { "epoch": 3.1574279379157426, "grad_norm": 0.5295472145080566, "learning_rate": 1.0272844654658069e-06, "loss": 0.0932040736079216, "step": 1424 }, { "epoch": 3.1618625277161865, "grad_norm": 2.297607660293579, "learning_rate": 1.0219873592384556e-06, "loss": 0.5828940272331238, "step": 1426 }, { "epoch": 3.16629711751663, "grad_norm": 1.9336421489715576, "learning_rate": 1.016713501323834e-06, "loss": 0.7437405586242676, "step": 1428 }, { "epoch": 3.1707317073170733, "grad_norm": 1.690544605255127, "learning_rate": 1.0114629626752973e-06, "loss": 0.3497503399848938, "step": 1430 }, { "epoch": 3.1751662971175167, "grad_norm": 16.42621421813965, "learning_rate": 1.0062358139324715e-06, "loss": 0.40635061264038086, "step": 1432 }, { "epoch": 3.17960088691796, "grad_norm": 1.3304423093795776, "learning_rate": 1.0010321254202992e-06, "loss": 0.5058741569519043, "step": 1434 }, { "epoch": 3.1840354767184036, "grad_norm": 2.4488651752471924, "learning_rate": 9.958519671480919e-07, "loss": 0.20857569575309753, "step": 1436 }, { "epoch": 3.188470066518847, "grad_norm": 0.8199713826179504, "learning_rate": 9.906954088085929e-07, "loss": 0.4270777106285095, "step": 1438 }, { "epoch": 3.1929046563192904, "grad_norm": 3.093682289123535, "learning_rate": 9.85562519777035e-07, "loss": 0.5151862502098083, "step": 1440 }, { "epoch": 3.197339246119734, "grad_norm": 1.1956168413162231, "learning_rate": 9.804533691102112e-07, "loss": 0.658134400844574, "step": 1442 }, { "epoch": 3.2017738359201773, "grad_norm": 0.7333883047103882, "learning_rate": 9.75368025545542e-07, "loss": 0.7828593254089355, "step": 1444 }, { "epoch": 3.2062084257206207, "grad_norm": 0.716337263584137, "learning_rate": 9.703065575001518e-07, "loss": 0.6528302431106567, "step": 1446 }, { "epoch": 3.210643015521064, "grad_norm": 2.811972141265869, "learning_rate": 9.65269033069952e-07, "loss": 0.4046706557273865, "step": 1448 }, { "epoch": 3.2150776053215075, "grad_norm": 0.9280921816825867, "learning_rate": 9.602555200287184e-07, "loss": 0.7239767909049988, "step": 1450 }, { "epoch": 3.2195121951219514, "grad_norm": 2.487478256225586, "learning_rate": 9.552660858271835e-07, "loss": 0.5565465688705444, "step": 1452 }, { "epoch": 3.223946784922395, "grad_norm": 0.8375023603439331, "learning_rate": 9.503007975921294e-07, "loss": 0.49734872579574585, "step": 1454 }, { "epoch": 3.2283813747228383, "grad_norm": 6.227933883666992, "learning_rate": 9.453597221254821e-07, "loss": 0.7493337392807007, "step": 1456 }, { "epoch": 3.2328159645232817, "grad_norm": 2.4948275089263916, "learning_rate": 9.404429259034156e-07, "loss": 0.41658228635787964, "step": 1458 }, { "epoch": 3.237250554323725, "grad_norm": 0.9919694066047668, "learning_rate": 9.355504750754543e-07, "loss": 0.7514620423316956, "step": 1460 }, { "epoch": 3.2416851441241685, "grad_norm": 0.985115647315979, "learning_rate": 9.306824354635866e-07, "loss": 0.46349745988845825, "step": 1462 }, { "epoch": 3.246119733924612, "grad_norm": 3.361206531524658, "learning_rate": 9.258388725613776e-07, "loss": 0.6378527879714966, "step": 1464 }, { "epoch": 3.2505543237250554, "grad_norm": 1.1187552213668823, "learning_rate": 9.21019851533086e-07, "loss": 0.7121803164482117, "step": 1466 }, { "epoch": 3.254988913525499, "grad_norm": 0.5266161561012268, "learning_rate": 9.162254372127921e-07, "loss": 0.09279008209705353, "step": 1468 }, { "epoch": 3.259423503325942, "grad_norm": 2.9691877365112305, "learning_rate": 9.114556941035199e-07, "loss": 0.8856503367424011, "step": 1470 }, { "epoch": 3.2638580931263856, "grad_norm": 1.2273247241973877, "learning_rate": 9.067106863763752e-07, "loss": 0.7877327799797058, "step": 1472 }, { "epoch": 3.2682926829268295, "grad_norm": 1.129638671875, "learning_rate": 9.01990477869677e-07, "loss": 0.297911673784256, "step": 1474 }, { "epoch": 3.2727272727272725, "grad_norm": 0.7427173852920532, "learning_rate": 8.972951320881014e-07, "loss": 0.5932102203369141, "step": 1476 }, { "epoch": 3.2771618625277164, "grad_norm": 2.747760772705078, "learning_rate": 8.92624712201827e-07, "loss": 0.38971173763275146, "step": 1478 }, { "epoch": 3.2815964523281598, "grad_norm": 0.9102936387062073, "learning_rate": 8.879792810456861e-07, "loss": 0.46492668986320496, "step": 1480 }, { "epoch": 3.286031042128603, "grad_norm": 0.7271443009376526, "learning_rate": 8.833589011183147e-07, "loss": 0.6474693417549133, "step": 1482 }, { "epoch": 3.2904656319290466, "grad_norm": 0.862979531288147, "learning_rate": 8.78763634581318e-07, "loss": 0.517356276512146, "step": 1484 }, { "epoch": 3.29490022172949, "grad_norm": 0.7722979784011841, "learning_rate": 8.741935432584292e-07, "loss": 0.3972328305244446, "step": 1486 }, { "epoch": 3.2993348115299335, "grad_norm": 2.848907232284546, "learning_rate": 8.696486886346805e-07, "loss": 0.4415854513645172, "step": 1488 }, { "epoch": 3.303769401330377, "grad_norm": 7.881778240203857, "learning_rate": 8.651291318555745e-07, "loss": 0.3040315508842468, "step": 1490 }, { "epoch": 3.3082039911308203, "grad_norm": 0.8357083201408386, "learning_rate": 8.606349337262623e-07, "loss": 0.9919511675834656, "step": 1492 }, { "epoch": 3.3126385809312637, "grad_norm": 1.3582104444503784, "learning_rate": 8.561661547107243e-07, "loss": 0.5778933763504028, "step": 1494 }, { "epoch": 3.317073170731707, "grad_norm": 3.0428314208984375, "learning_rate": 8.517228549309588e-07, "loss": 0.5790684223175049, "step": 1496 }, { "epoch": 3.3215077605321506, "grad_norm": 1.9520448446273804, "learning_rate": 8.473050941661717e-07, "loss": 0.7469807267189026, "step": 1498 }, { "epoch": 3.3259423503325944, "grad_norm": 0.7510539293289185, "learning_rate": 8.429129318519711e-07, "loss": 0.4080921411514282, "step": 1500 }, { "epoch": 3.330376940133038, "grad_norm": 0.9013833999633789, "learning_rate": 8.38546427079571e-07, "loss": 0.6411795616149902, "step": 1502 }, { "epoch": 3.3348115299334813, "grad_norm": 1.3937565088272095, "learning_rate": 8.342056385949929e-07, "loss": 0.7303662300109863, "step": 1504 }, { "epoch": 3.3392461197339247, "grad_norm": 0.22746898233890533, "learning_rate": 8.298906247982768e-07, "loss": 0.4033330976963043, "step": 1506 }, { "epoch": 3.343680709534368, "grad_norm": 0.9032326936721802, "learning_rate": 8.25601443742697e-07, "loss": 0.36406025290489197, "step": 1508 }, { "epoch": 3.3481152993348116, "grad_norm": 2.841404914855957, "learning_rate": 8.213381531339776e-07, "loss": 0.8044983148574829, "step": 1510 }, { "epoch": 3.352549889135255, "grad_norm": 0.41309988498687744, "learning_rate": 8.1710081032952e-07, "loss": 0.4085044860839844, "step": 1512 }, { "epoch": 3.3569844789356984, "grad_norm": 1.5829377174377441, "learning_rate": 8.128894723376285e-07, "loss": 0.7842904925346375, "step": 1514 }, { "epoch": 3.361419068736142, "grad_norm": 1.9180912971496582, "learning_rate": 8.087041958167438e-07, "loss": 0.46436750888824463, "step": 1516 }, { "epoch": 3.3658536585365852, "grad_norm": 0.8330836296081543, "learning_rate": 8.04545037074683e-07, "loss": 0.44874808192253113, "step": 1518 }, { "epoch": 3.3702882483370287, "grad_norm": 1.4987759590148926, "learning_rate": 8.004120520678768e-07, "loss": 0.6579011678695679, "step": 1520 }, { "epoch": 3.374722838137472, "grad_norm": 0.4084889590740204, "learning_rate": 7.963052964006243e-07, "loss": 0.4690130650997162, "step": 1522 }, { "epoch": 3.3791574279379155, "grad_norm": 2.0353617668151855, "learning_rate": 7.922248253243367e-07, "loss": 0.738138735294342, "step": 1524 }, { "epoch": 3.3835920177383594, "grad_norm": 2.91652250289917, "learning_rate": 7.881706937368005e-07, "loss": 0.677200973033905, "step": 1526 }, { "epoch": 3.388026607538803, "grad_norm": 0.9351639151573181, "learning_rate": 7.84142956181436e-07, "loss": 0.4146648943424225, "step": 1528 }, { "epoch": 3.3924611973392462, "grad_norm": 0.9312740564346313, "learning_rate": 7.801416668465621e-07, "loss": 0.3662897050380707, "step": 1530 }, { "epoch": 3.3968957871396896, "grad_norm": 3.5264506340026855, "learning_rate": 7.76166879564672e-07, "loss": 0.22805796563625336, "step": 1532 }, { "epoch": 3.401330376940133, "grad_norm": 0.9523420929908752, "learning_rate": 7.722186478117031e-07, "loss": 0.5999071002006531, "step": 1534 }, { "epoch": 3.4057649667405765, "grad_norm": 2.5635905265808105, "learning_rate": 7.682970247063212e-07, "loss": 0.7036619186401367, "step": 1536 }, { "epoch": 3.41019955654102, "grad_norm": 2.3564810752868652, "learning_rate": 7.644020630092066e-07, "loss": 0.5891589522361755, "step": 1538 }, { "epoch": 3.4146341463414633, "grad_norm": 0.8324587345123291, "learning_rate": 7.605338151223401e-07, "loss": 0.667372465133667, "step": 1540 }, { "epoch": 3.4190687361419068, "grad_norm": 1.3478339910507202, "learning_rate": 7.566923330883029e-07, "loss": 0.5353263020515442, "step": 1542 }, { "epoch": 3.42350332594235, "grad_norm": 1.5044814348220825, "learning_rate": 7.528776685895731e-07, "loss": 0.6542061567306519, "step": 1544 }, { "epoch": 3.4279379157427936, "grad_norm": 2.0639114379882812, "learning_rate": 7.490898729478312e-07, "loss": 0.16641607880592346, "step": 1546 }, { "epoch": 3.4323725055432375, "grad_norm": 0.10060684382915497, "learning_rate": 7.45328997123271e-07, "loss": 0.18048889935016632, "step": 1548 }, { "epoch": 3.436807095343681, "grad_norm": 1.618093490600586, "learning_rate": 7.415950917139106e-07, "loss": 0.8383937478065491, "step": 1550 }, { "epoch": 3.4412416851441243, "grad_norm": 1.1742033958435059, "learning_rate": 7.378882069549166e-07, "loss": 0.6342257857322693, "step": 1552 }, { "epoch": 3.4456762749445677, "grad_norm": 0.2840815782546997, "learning_rate": 7.342083927179235e-07, "loss": 0.35999611020088196, "step": 1554 }, { "epoch": 3.450110864745011, "grad_norm": 1.5036356449127197, "learning_rate": 7.30555698510366e-07, "loss": 0.7260861992835999, "step": 1556 }, { "epoch": 3.4545454545454546, "grad_norm": 1.3467886447906494, "learning_rate": 7.269301734748107e-07, "loss": 0.7150126099586487, "step": 1558 }, { "epoch": 3.458980044345898, "grad_norm": 0.8913111090660095, "learning_rate": 7.233318663882968e-07, "loss": 0.7145206332206726, "step": 1560 }, { "epoch": 3.4634146341463414, "grad_norm": 1.6978760957717896, "learning_rate": 7.197608256616792e-07, "loss": 0.1996350884437561, "step": 1562 }, { "epoch": 3.467849223946785, "grad_norm": 0.8095346093177795, "learning_rate": 7.162170993389763e-07, "loss": 0.7250151038169861, "step": 1564 }, { "epoch": 3.4722838137472283, "grad_norm": 1.1986325979232788, "learning_rate": 7.127007350967241e-07, "loss": 0.40820562839508057, "step": 1566 }, { "epoch": 3.4767184035476717, "grad_norm": 1.269044041633606, "learning_rate": 7.092117802433362e-07, "loss": 0.6645058393478394, "step": 1568 }, { "epoch": 3.481152993348115, "grad_norm": 1.3065571784973145, "learning_rate": 7.057502817184648e-07, "loss": 0.4576531946659088, "step": 1570 }, { "epoch": 3.4855875831485585, "grad_norm": 0.37347811460494995, "learning_rate": 7.023162860923722e-07, "loss": 0.4664113521575928, "step": 1572 }, { "epoch": 3.4900221729490024, "grad_norm": 1.5471532344818115, "learning_rate": 6.989098395653005e-07, "loss": 0.911579430103302, "step": 1574 }, { "epoch": 3.494456762749446, "grad_norm": 3.40287709236145, "learning_rate": 6.955309879668537e-07, "loss": 0.36696523427963257, "step": 1576 }, { "epoch": 3.4988913525498893, "grad_norm": 1.022657871246338, "learning_rate": 6.921797767553794e-07, "loss": 0.42062070965766907, "step": 1578 }, { "epoch": 3.5033259423503327, "grad_norm": 1.3818333148956299, "learning_rate": 6.88856251017356e-07, "loss": 0.7136982083320618, "step": 1580 }, { "epoch": 3.507760532150776, "grad_norm": 0.9989206194877625, "learning_rate": 6.855604554667897e-07, "loss": 0.8498230576515198, "step": 1582 }, { "epoch": 3.5121951219512195, "grad_norm": 1.0440279245376587, "learning_rate": 6.822924344446081e-07, "loss": 0.44726136326789856, "step": 1584 }, { "epoch": 3.516629711751663, "grad_norm": 1.522624135017395, "learning_rate": 6.790522319180687e-07, "loss": 0.4782644510269165, "step": 1586 }, { "epoch": 3.5210643015521064, "grad_norm": 0.845657467842102, "learning_rate": 6.758398914801628e-07, "loss": 0.7009880542755127, "step": 1588 }, { "epoch": 3.52549889135255, "grad_norm": 2.187683582305908, "learning_rate": 6.726554563490321e-07, "loss": 0.39783769845962524, "step": 1590 }, { "epoch": 3.529933481152993, "grad_norm": 4.550779819488525, "learning_rate": 6.694989693673872e-07, "loss": 0.4127946197986603, "step": 1592 }, { "epoch": 3.5343680709534366, "grad_norm": 1.568524956703186, "learning_rate": 6.663704730019285e-07, "loss": 0.8160148859024048, "step": 1594 }, { "epoch": 3.5388026607538805, "grad_norm": 2.7332797050476074, "learning_rate": 6.632700093427774e-07, "loss": 0.1282457411289215, "step": 1596 }, { "epoch": 3.5432372505543235, "grad_norm": 1.79358971118927, "learning_rate": 6.601976201029095e-07, "loss": 0.3730695843696594, "step": 1598 }, { "epoch": 3.5476718403547673, "grad_norm": 0.8376679420471191, "learning_rate": 6.571533466175928e-07, "loss": 0.4683838486671448, "step": 1600 }, { "epoch": 3.5521064301552108, "grad_norm": 1.0493067502975464, "learning_rate": 6.541372298438325e-07, "loss": 0.6612682938575745, "step": 1602 }, { "epoch": 3.556541019955654, "grad_norm": 1.6749497652053833, "learning_rate": 6.511493103598184e-07, "loss": 0.8235822319984436, "step": 1604 }, { "epoch": 3.5609756097560976, "grad_norm": 0.9716708660125732, "learning_rate": 6.481896283643808e-07, "loss": 0.7026538252830505, "step": 1606 }, { "epoch": 3.565410199556541, "grad_norm": 0.8682565093040466, "learning_rate": 6.452582236764495e-07, "loss": 0.06921753287315369, "step": 1608 }, { "epoch": 3.5698447893569845, "grad_norm": 4.531189918518066, "learning_rate": 6.423551357345154e-07, "loss": 0.461900919675827, "step": 1610 }, { "epoch": 3.574279379157428, "grad_norm": 2.879300832748413, "learning_rate": 6.394804035961038e-07, "loss": 0.14274033904075623, "step": 1612 }, { "epoch": 3.5787139689578713, "grad_norm": 1.3849800825119019, "learning_rate": 6.366340659372462e-07, "loss": 0.4771314263343811, "step": 1614 }, { "epoch": 3.5831485587583147, "grad_norm": 1.026705265045166, "learning_rate": 6.338161610519618e-07, "loss": 0.7851333022117615, "step": 1616 }, { "epoch": 3.587583148558758, "grad_norm": 2.080756902694702, "learning_rate": 6.310267268517397e-07, "loss": 0.4780849516391754, "step": 1618 }, { "epoch": 3.5920177383592016, "grad_norm": 3.4350011348724365, "learning_rate": 6.282658008650318e-07, "loss": 0.4769437909126282, "step": 1620 }, { "epoch": 3.5964523281596454, "grad_norm": 1.204390287399292, "learning_rate": 6.255334202367462e-07, "loss": 0.6624370813369751, "step": 1622 }, { "epoch": 3.6008869179600884, "grad_norm": 1.616827368736267, "learning_rate": 6.228296217277481e-07, "loss": 0.5747263431549072, "step": 1624 }, { "epoch": 3.6053215077605323, "grad_norm": 0.4036061465740204, "learning_rate": 6.201544417143641e-07, "loss": 0.1593714952468872, "step": 1626 }, { "epoch": 3.6097560975609757, "grad_norm": 1.0553009510040283, "learning_rate": 6.175079161878951e-07, "loss": 0.7550400495529175, "step": 1628 }, { "epoch": 3.614190687361419, "grad_norm": 5.636652946472168, "learning_rate": 6.148900807541295e-07, "loss": 0.5534995794296265, "step": 1630 }, { "epoch": 3.6186252771618626, "grad_norm": 1.9536336660385132, "learning_rate": 6.123009706328659e-07, "loss": 0.5692697167396545, "step": 1632 }, { "epoch": 3.623059866962306, "grad_norm": 1.257670283317566, "learning_rate": 6.097406206574378e-07, "loss": 0.6251094937324524, "step": 1634 }, { "epoch": 3.6274944567627494, "grad_norm": 0.8495803475379944, "learning_rate": 6.072090652742475e-07, "loss": 0.42323750257492065, "step": 1636 }, { "epoch": 3.631929046563193, "grad_norm": 4.202381610870361, "learning_rate": 6.047063385422993e-07, "loss": 0.46832165122032166, "step": 1638 }, { "epoch": 3.6363636363636362, "grad_norm": 1.8445926904678345, "learning_rate": 6.022324741327438e-07, "loss": 0.657563328742981, "step": 1640 }, { "epoch": 3.6407982261640797, "grad_norm": 3.063267230987549, "learning_rate": 5.997875053284248e-07, "loss": 0.3927001655101776, "step": 1642 }, { "epoch": 3.6452328159645235, "grad_norm": 1.844231367111206, "learning_rate": 5.973714650234287e-07, "loss": 0.6536309123039246, "step": 1644 }, { "epoch": 3.6496674057649665, "grad_norm": 0.11124907433986664, "learning_rate": 5.949843857226466e-07, "loss": 0.2834221124649048, "step": 1646 }, { "epoch": 3.6541019955654104, "grad_norm": 0.8278182744979858, "learning_rate": 5.926262995413329e-07, "loss": 0.2620082497596741, "step": 1648 }, { "epoch": 3.658536585365854, "grad_norm": 1.227217197418213, "learning_rate": 5.902972382046742e-07, "loss": 0.44254299998283386, "step": 1650 }, { "epoch": 3.662971175166297, "grad_norm": 0.9186346530914307, "learning_rate": 5.879972330473651e-07, "loss": 0.6525332927703857, "step": 1652 }, { "epoch": 3.6674057649667406, "grad_norm": 0.9581958651542664, "learning_rate": 5.857263150131825e-07, "loss": 0.36457884311676025, "step": 1654 }, { "epoch": 3.671840354767184, "grad_norm": 1.0149691104888916, "learning_rate": 5.834845146545726e-07, "loss": 0.8156982660293579, "step": 1656 }, { "epoch": 3.6762749445676275, "grad_norm": 2.3508944511413574, "learning_rate": 5.812718621322386e-07, "loss": 0.4678148627281189, "step": 1658 }, { "epoch": 3.680709534368071, "grad_norm": 2.148775100708008, "learning_rate": 5.790883872147341e-07, "loss": 0.404410719871521, "step": 1660 }, { "epoch": 3.6851441241685143, "grad_norm": 0.22560228407382965, "learning_rate": 5.769341192780643e-07, "loss": 0.3717038035392761, "step": 1662 }, { "epoch": 3.6895787139689578, "grad_norm": 0.8757584691047668, "learning_rate": 5.748090873052892e-07, "loss": 0.32363370060920715, "step": 1664 }, { "epoch": 3.694013303769401, "grad_norm": 1.1470128297805786, "learning_rate": 5.727133198861353e-07, "loss": 0.6273210048675537, "step": 1666 }, { "epoch": 3.6984478935698446, "grad_norm": 1.020920991897583, "learning_rate": 5.706468452166091e-07, "loss": 0.5913212299346924, "step": 1668 }, { "epoch": 3.7028824833702885, "grad_norm": 1.009974718093872, "learning_rate": 5.686096910986189e-07, "loss": 0.650887131690979, "step": 1670 }, { "epoch": 3.7073170731707314, "grad_norm": 1.03592050075531, "learning_rate": 5.666018849396016e-07, "loss": 0.6401125192642212, "step": 1672 }, { "epoch": 3.7117516629711753, "grad_norm": 0.7517452239990234, "learning_rate": 5.646234537521513e-07, "loss": 0.6306463479995728, "step": 1674 }, { "epoch": 3.7161862527716187, "grad_norm": 2.245835542678833, "learning_rate": 5.626744241536589e-07, "loss": 0.71409010887146, "step": 1676 }, { "epoch": 3.720620842572062, "grad_norm": 1.8823548555374146, "learning_rate": 5.607548223659519e-07, "loss": 0.6528919339179993, "step": 1678 }, { "epoch": 3.7250554323725056, "grad_norm": 2.2317075729370117, "learning_rate": 5.58864674214942e-07, "loss": 0.30886802077293396, "step": 1680 }, { "epoch": 3.729490022172949, "grad_norm": 0.9859198331832886, "learning_rate": 5.57004005130279e-07, "loss": 0.5217846035957336, "step": 1682 }, { "epoch": 3.7339246119733924, "grad_norm": 0.8078064918518066, "learning_rate": 5.551728401450067e-07, "loss": 0.3513007164001465, "step": 1684 }, { "epoch": 3.738359201773836, "grad_norm": 2.4825408458709717, "learning_rate": 5.533712038952278e-07, "loss": 0.5929620265960693, "step": 1686 }, { "epoch": 3.7427937915742793, "grad_norm": 0.38356509804725647, "learning_rate": 5.51599120619771e-07, "loss": 0.25690025091171265, "step": 1688 }, { "epoch": 3.7472283813747227, "grad_norm": 1.4826903343200684, "learning_rate": 5.498566141598662e-07, "loss": 0.7508558034896851, "step": 1690 }, { "epoch": 3.7516629711751666, "grad_norm": 1.05094313621521, "learning_rate": 5.481437079588227e-07, "loss": 0.5309889912605286, "step": 1692 }, { "epoch": 3.7560975609756095, "grad_norm": 1.0361418724060059, "learning_rate": 5.464604250617143e-07, "loss": 0.7995379567146301, "step": 1694 }, { "epoch": 3.7605321507760534, "grad_norm": 1.1136112213134766, "learning_rate": 5.448067881150697e-07, "loss": 0.7239155769348145, "step": 1696 }, { "epoch": 3.764966740576497, "grad_norm": 0.940222978591919, "learning_rate": 5.431828193665664e-07, "loss": 0.3560809791088104, "step": 1698 }, { "epoch": 3.7694013303769403, "grad_norm": 2.683884620666504, "learning_rate": 5.415885406647334e-07, "loss": 0.44195085763931274, "step": 1700 }, { "epoch": 3.7738359201773837, "grad_norm": 2.6246378421783447, "learning_rate": 5.400239734586551e-07, "loss": 0.980012059211731, "step": 1702 }, { "epoch": 3.778270509977827, "grad_norm": 0.5143499970436096, "learning_rate": 5.384891387976845e-07, "loss": 0.14009836316108704, "step": 1704 }, { "epoch": 3.7827050997782705, "grad_norm": 0.4758577048778534, "learning_rate": 5.369840573311593e-07, "loss": 0.40948137640953064, "step": 1706 }, { "epoch": 3.787139689578714, "grad_norm": 1.033705234527588, "learning_rate": 5.355087493081236e-07, "loss": 0.4629664719104767, "step": 1708 }, { "epoch": 3.7915742793791574, "grad_norm": 0.836288571357727, "learning_rate": 5.340632345770564e-07, "loss": 0.7450593113899231, "step": 1710 }, { "epoch": 3.796008869179601, "grad_norm": 2.316535711288452, "learning_rate": 5.326475325856036e-07, "loss": 0.4111533463001251, "step": 1712 }, { "epoch": 3.800443458980044, "grad_norm": 62.51638412475586, "learning_rate": 5.312616623803174e-07, "loss": 0.5232793092727661, "step": 1714 }, { "epoch": 3.8048780487804876, "grad_norm": 1.5670796632766724, "learning_rate": 5.299056426063995e-07, "loss": 0.6640741229057312, "step": 1716 }, { "epoch": 3.8093126385809315, "grad_norm": 0.8931707739830017, "learning_rate": 5.2857949150745e-07, "loss": 0.5484420657157898, "step": 1718 }, { "epoch": 3.8137472283813745, "grad_norm": 1.2039430141448975, "learning_rate": 5.27283226925222e-07, "loss": 0.5476232767105103, "step": 1720 }, { "epoch": 3.8181818181818183, "grad_norm": 0.9757826328277588, "learning_rate": 5.260168662993824e-07, "loss": 0.7852546572685242, "step": 1722 }, { "epoch": 3.8226164079822618, "grad_norm": 1.4504204988479614, "learning_rate": 5.247804266672765e-07, "loss": 0.7212304472923279, "step": 1724 }, { "epoch": 3.827050997782705, "grad_norm": 1.1943776607513428, "learning_rate": 5.235739246636988e-07, "loss": 0.6680858731269836, "step": 1726 }, { "epoch": 3.8314855875831486, "grad_norm": 1.8303642272949219, "learning_rate": 5.223973765206694e-07, "loss": 0.3614678680896759, "step": 1728 }, { "epoch": 3.835920177383592, "grad_norm": 3.3566129207611084, "learning_rate": 5.212507980672155e-07, "loss": 0.4301706552505493, "step": 1730 }, { "epoch": 3.8403547671840355, "grad_norm": 0.91670823097229, "learning_rate": 5.201342047291587e-07, "loss": 0.7216442823410034, "step": 1732 }, { "epoch": 3.844789356984479, "grad_norm": 27.859312057495117, "learning_rate": 5.190476115289063e-07, "loss": 0.8199055194854736, "step": 1734 }, { "epoch": 3.8492239467849223, "grad_norm": 0.8166837096214294, "learning_rate": 5.179910330852521e-07, "loss": 0.7341957092285156, "step": 1736 }, { "epoch": 3.8536585365853657, "grad_norm": 1.106396198272705, "learning_rate": 5.169644836131759e-07, "loss": 0.6143337488174438, "step": 1738 }, { "epoch": 3.858093126385809, "grad_norm": 0.8808902502059937, "learning_rate": 5.159679769236553e-07, "loss": 0.37879249453544617, "step": 1740 }, { "epoch": 3.8625277161862526, "grad_norm": 1.7568862438201904, "learning_rate": 5.150015264234782e-07, "loss": 0.45216262340545654, "step": 1742 }, { "epoch": 3.8669623059866964, "grad_norm": 1.3479468822479248, "learning_rate": 5.140651451150627e-07, "loss": 0.6618800759315491, "step": 1744 }, { "epoch": 3.8713968957871394, "grad_norm": 1.1075336933135986, "learning_rate": 5.131588455962835e-07, "loss": 0.653846263885498, "step": 1746 }, { "epoch": 3.8758314855875833, "grad_norm": 1.473656415939331, "learning_rate": 5.122826400602999e-07, "loss": 0.43444833159446716, "step": 1748 }, { "epoch": 3.8802660753880267, "grad_norm": 1.5921751260757446, "learning_rate": 5.114365402953946e-07, "loss": 0.5735731720924377, "step": 1750 }, { "epoch": 3.88470066518847, "grad_norm": 3.2497620582580566, "learning_rate": 5.106205576848123e-07, "loss": 0.571108341217041, "step": 1752 }, { "epoch": 3.8891352549889135, "grad_norm": 3.123436212539673, "learning_rate": 5.09834703206609e-07, "loss": 0.7177774906158447, "step": 1754 }, { "epoch": 3.893569844789357, "grad_norm": 13.750722885131836, "learning_rate": 5.090789874335027e-07, "loss": 0.6665231585502625, "step": 1756 }, { "epoch": 3.8980044345898004, "grad_norm": 1.5528661012649536, "learning_rate": 5.083534205327321e-07, "loss": 0.7704042792320251, "step": 1758 }, { "epoch": 3.902439024390244, "grad_norm": 0.040434010326862335, "learning_rate": 5.076580122659192e-07, "loss": 0.0017574625089764595, "step": 1760 }, { "epoch": 3.9068736141906872, "grad_norm": 2.7411434650421143, "learning_rate": 5.069927719889383e-07, "loss": 0.30478376150131226, "step": 1762 }, { "epoch": 3.9113082039911307, "grad_norm": 0.1822403222322464, "learning_rate": 5.063577086517894e-07, "loss": 0.3710252046585083, "step": 1764 }, { "epoch": 3.9157427937915745, "grad_norm": 2.8029940128326416, "learning_rate": 5.057528307984792e-07, "loss": 0.47346100211143494, "step": 1766 }, { "epoch": 3.9201773835920175, "grad_norm": 1.2661375999450684, "learning_rate": 5.051781465669053e-07, "loss": 0.7573010921478271, "step": 1768 }, { "epoch": 3.9246119733924614, "grad_norm": 0.8320476412773132, "learning_rate": 5.04633663688746e-07, "loss": 0.7401853203773499, "step": 1770 }, { "epoch": 3.929046563192905, "grad_norm": 2.3888723850250244, "learning_rate": 5.04119389489358e-07, "loss": 0.2338392287492752, "step": 1772 }, { "epoch": 3.933481152993348, "grad_norm": 1.4304852485656738, "learning_rate": 5.036353308876764e-07, "loss": 0.6549674272537231, "step": 1774 }, { "epoch": 3.9379157427937916, "grad_norm": 0.8762494325637817, "learning_rate": 5.031814943961221e-07, "loss": 0.6887394785881042, "step": 1776 }, { "epoch": 3.942350332594235, "grad_norm": 0.3672865927219391, "learning_rate": 5.027578861205139e-07, "loss": 0.13220834732055664, "step": 1778 }, { "epoch": 3.9467849223946785, "grad_norm": 4.185744285583496, "learning_rate": 5.023645117599877e-07, "loss": 0.45351341366767883, "step": 1780 }, { "epoch": 3.951219512195122, "grad_norm": 0.27578166127204895, "learning_rate": 5.020013766069176e-07, "loss": 0.3945060670375824, "step": 1782 }, { "epoch": 3.9556541019955653, "grad_norm": 0.877690315246582, "learning_rate": 5.016684855468464e-07, "loss": 0.44928890466690063, "step": 1784 }, { "epoch": 3.9600886917960088, "grad_norm": 0.863924503326416, "learning_rate": 5.013658430584194e-07, "loss": 0.6446860432624817, "step": 1786 }, { "epoch": 3.964523281596452, "grad_norm": 0.9856058359146118, "learning_rate": 5.010934532133236e-07, "loss": 0.4857484996318817, "step": 1788 }, { "epoch": 3.9689578713968956, "grad_norm": 2.3645358085632324, "learning_rate": 5.008513196762342e-07, "loss": 0.5328899621963501, "step": 1790 }, { "epoch": 3.9733924611973395, "grad_norm": 1.1871687173843384, "learning_rate": 5.006394457047638e-07, "loss": 0.6613432168960571, "step": 1792 }, { "epoch": 3.9778270509977824, "grad_norm": 2.269967794418335, "learning_rate": 5.004578341494197e-07, "loss": 0.40819886326789856, "step": 1794 }, { "epoch": 3.9822616407982263, "grad_norm": 0.9505739808082581, "learning_rate": 5.003064874535649e-07, "loss": 0.5899269580841064, "step": 1796 }, { "epoch": 3.9866962305986697, "grad_norm": 1.2086498737335205, "learning_rate": 5.00185407653385e-07, "loss": 0.6620221138000488, "step": 1798 }, { "epoch": 3.991130820399113, "grad_norm": 2.2357959747314453, "learning_rate": 5.000945963778627e-07, "loss": 0.6272152662277222, "step": 1800 }, { "epoch": 3.9955654101995566, "grad_norm": 1.1447160243988037, "learning_rate": 5.000340548487528e-07, "loss": 0.7161806225776672, "step": 1802 }, { "epoch": 4.0, "grad_norm": 1.5152302980422974, "learning_rate": 5.000037838805682e-07, "loss": 0.3338135778903961, "step": 1804 }, { "epoch": 4.0, "step": 1804, "total_flos": 3.4175049861232067e+18, "train_loss": 0.8372825072394754, "train_runtime": 8301.3852, "train_samples_per_second": 6.519, "train_steps_per_second": 0.217 } ], "logging_steps": 2, "max_steps": 1804, "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": 3.4175049861232067e+18, "train_batch_size": 3, "trial_name": null, "trial_params": null }