| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9994060582062958, | |
| "eval_steps": 210, | |
| "global_step": 631, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015838447832112453, | |
| "grad_norm": 20.634467679531244, | |
| "learning_rate": 4.2105263157894733e-07, | |
| "loss": 1.0835, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031676895664224905, | |
| "grad_norm": 14.28313933877416, | |
| "learning_rate": 8.421052631578947e-07, | |
| "loss": 0.9055, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004751534349633736, | |
| "grad_norm": 24.632900629424984, | |
| "learning_rate": 1.263157894736842e-06, | |
| "loss": 0.9363, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006335379132844981, | |
| "grad_norm": 14.378103932792914, | |
| "learning_rate": 1.6842105263157893e-06, | |
| "loss": 0.9769, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007919223916056227, | |
| "grad_norm": 12.06138179201479, | |
| "learning_rate": 2.1052631578947366e-06, | |
| "loss": 0.879, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009503068699267472, | |
| "grad_norm": 8.884749518187892, | |
| "learning_rate": 2.526315789473684e-06, | |
| "loss": 0.8971, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011086913482478717, | |
| "grad_norm": 4.885104408560213, | |
| "learning_rate": 2.9473684210526313e-06, | |
| "loss": 0.8804, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.012670758265689962, | |
| "grad_norm": 6.068115898146199, | |
| "learning_rate": 3.3684210526315786e-06, | |
| "loss": 0.7672, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014254603048901207, | |
| "grad_norm": 5.471835730774232, | |
| "learning_rate": 3.789473684210526e-06, | |
| "loss": 0.7564, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015838447832112454, | |
| "grad_norm": 4.785289669398289, | |
| "learning_rate": 4.210526315789473e-06, | |
| "loss": 0.8132, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.017422292615323697, | |
| "grad_norm": 6.148192535233664, | |
| "learning_rate": 4.631578947368421e-06, | |
| "loss": 0.788, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.019006137398534944, | |
| "grad_norm": 3.1102232110909718, | |
| "learning_rate": 5.052631578947368e-06, | |
| "loss": 0.7744, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.020589982181746187, | |
| "grad_norm": 2.2116201137156697, | |
| "learning_rate": 5.473684210526316e-06, | |
| "loss": 0.705, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.022173826964957434, | |
| "grad_norm": 2.3891700304125965, | |
| "learning_rate": 5.894736842105263e-06, | |
| "loss": 0.782, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02375767174816868, | |
| "grad_norm": 2.6800168254599552, | |
| "learning_rate": 6.31578947368421e-06, | |
| "loss": 0.6875, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.025341516531379924, | |
| "grad_norm": 2.069273801603203, | |
| "learning_rate": 6.736842105263157e-06, | |
| "loss": 0.7177, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02692536131459117, | |
| "grad_norm": 1.9967678968867362, | |
| "learning_rate": 7.157894736842105e-06, | |
| "loss": 0.6317, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.028509206097802414, | |
| "grad_norm": 1.8973112856460428, | |
| "learning_rate": 7.578947368421052e-06, | |
| "loss": 0.668, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03009305088101366, | |
| "grad_norm": 1.6427223591398545, | |
| "learning_rate": 8e-06, | |
| "loss": 0.6237, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03167689566422491, | |
| "grad_norm": 1.8126563046343525, | |
| "learning_rate": 7.999947298139988e-06, | |
| "loss": 0.7286, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.033260740447436155, | |
| "grad_norm": 2.0321574723423437, | |
| "learning_rate": 7.999789193948692e-06, | |
| "loss": 0.6975, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.034844585230647394, | |
| "grad_norm": 1.6806869406461464, | |
| "learning_rate": 7.999525691592307e-06, | |
| "loss": 0.577, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03642843001385864, | |
| "grad_norm": 1.9508098776351803, | |
| "learning_rate": 7.999156798014364e-06, | |
| "loss": 0.7186, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03801227479706989, | |
| "grad_norm": 1.818938048059436, | |
| "learning_rate": 7.998682522935554e-06, | |
| "loss": 0.6235, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.039596119580281135, | |
| "grad_norm": 1.763078793834794, | |
| "learning_rate": 7.998102878853464e-06, | |
| "loss": 0.6797, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.041179964363492375, | |
| "grad_norm": 1.7024348305084676, | |
| "learning_rate": 7.997417881042254e-06, | |
| "loss": 0.6611, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04276380914670362, | |
| "grad_norm": 2.651929076311587, | |
| "learning_rate": 7.996627547552254e-06, | |
| "loss": 0.6378, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04434765392991487, | |
| "grad_norm": 1.8122638725536788, | |
| "learning_rate": 7.99573189920949e-06, | |
| "loss": 0.6018, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.045931498713126115, | |
| "grad_norm": 1.715907567678854, | |
| "learning_rate": 7.994730959615124e-06, | |
| "loss": 0.5851, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04751534349633736, | |
| "grad_norm": 4.091743172227538, | |
| "learning_rate": 7.993624755144846e-06, | |
| "loss": 0.7245, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0490991882795486, | |
| "grad_norm": 2.044771221320041, | |
| "learning_rate": 7.992413314948177e-06, | |
| "loss": 0.5109, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05068303306275985, | |
| "grad_norm": 1.7849876948071914, | |
| "learning_rate": 7.991096670947687e-06, | |
| "loss": 0.669, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.052266877845971095, | |
| "grad_norm": 2.0286922346779614, | |
| "learning_rate": 7.989674857838172e-06, | |
| "loss": 0.6604, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05385072262918234, | |
| "grad_norm": 1.5979263059089825, | |
| "learning_rate": 7.988147913085731e-06, | |
| "loss": 0.6031, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.05543456741239359, | |
| "grad_norm": 1.8983896550694437, | |
| "learning_rate": 7.986515876926776e-06, | |
| "loss": 0.6479, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05701841219560483, | |
| "grad_norm": 1.5118226263390602, | |
| "learning_rate": 7.984778792366982e-06, | |
| "loss": 0.7121, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.058602256978816075, | |
| "grad_norm": 1.654106143113525, | |
| "learning_rate": 7.982936705180138e-06, | |
| "loss": 0.5762, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06018610176202732, | |
| "grad_norm": 1.656696649887629, | |
| "learning_rate": 7.980989663906955e-06, | |
| "loss": 0.5968, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06176994654523857, | |
| "grad_norm": 1.6128252735493993, | |
| "learning_rate": 7.978937719853785e-06, | |
| "loss": 0.6237, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06335379132844982, | |
| "grad_norm": 1.8318236683351248, | |
| "learning_rate": 7.976780927091259e-06, | |
| "loss": 0.5261, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06493763611166106, | |
| "grad_norm": 1.7317276246642117, | |
| "learning_rate": 7.97451934245287e-06, | |
| "loss": 0.6436, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.06652148089487231, | |
| "grad_norm": 1.8588379937728277, | |
| "learning_rate": 7.97215302553348e-06, | |
| "loss": 0.6273, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.06810532567808354, | |
| "grad_norm": 1.478388678926987, | |
| "learning_rate": 7.969682038687744e-06, | |
| "loss": 0.6108, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.06968917046129479, | |
| "grad_norm": 1.6631272451799215, | |
| "learning_rate": 7.967106447028455e-06, | |
| "loss": 0.6865, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07127301524450604, | |
| "grad_norm": 1.736621303615563, | |
| "learning_rate": 7.964426318424854e-06, | |
| "loss": 0.6554, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07285686002771728, | |
| "grad_norm": 1.7271619263651752, | |
| "learning_rate": 7.96164172350082e-06, | |
| "loss": 0.6234, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07444070481092853, | |
| "grad_norm": 1.8475249444720505, | |
| "learning_rate": 7.958752735633022e-06, | |
| "loss": 0.6844, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.07602454959413978, | |
| "grad_norm": 1.5407374760971033, | |
| "learning_rate": 7.955759430948973e-06, | |
| "loss": 0.5816, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.07760839437735102, | |
| "grad_norm": 1.6776551127492765, | |
| "learning_rate": 7.952661888325037e-06, | |
| "loss": 0.5999, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.07919223916056227, | |
| "grad_norm": 1.674394955432216, | |
| "learning_rate": 7.949460189384344e-06, | |
| "loss": 0.6809, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08077608394377352, | |
| "grad_norm": 1.71808445149699, | |
| "learning_rate": 7.946154418494638e-06, | |
| "loss": 0.6433, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.08235992872698475, | |
| "grad_norm": 1.5598421305012693, | |
| "learning_rate": 7.942744662766056e-06, | |
| "loss": 0.6166, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.083943773510196, | |
| "grad_norm": 2.134433653759547, | |
| "learning_rate": 7.939231012048832e-06, | |
| "loss": 0.6213, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.08552761829340724, | |
| "grad_norm": 1.513738891290282, | |
| "learning_rate": 7.935613558930931e-06, | |
| "loss": 0.5797, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.08711146307661849, | |
| "grad_norm": 1.8993782752151005, | |
| "learning_rate": 7.931892398735607e-06, | |
| "loss": 0.6062, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.08869530785982974, | |
| "grad_norm": 1.6362105443395145, | |
| "learning_rate": 7.92806762951889e-06, | |
| "loss": 0.6701, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.09027915264304098, | |
| "grad_norm": 1.6152582877305293, | |
| "learning_rate": 7.92413935206701e-06, | |
| "loss": 0.5999, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.09186299742625223, | |
| "grad_norm": 1.5796190225435545, | |
| "learning_rate": 7.920107669893728e-06, | |
| "loss": 0.6414, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.09344684220946348, | |
| "grad_norm": 1.5796707579391902, | |
| "learning_rate": 7.915972689237618e-06, | |
| "loss": 0.6168, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.09503068699267472, | |
| "grad_norm": 1.4556074881511978, | |
| "learning_rate": 7.911734519059266e-06, | |
| "loss": 0.6623, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.09661453177588597, | |
| "grad_norm": 1.5078600739444816, | |
| "learning_rate": 7.907393271038402e-06, | |
| "loss": 0.6546, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0981983765590972, | |
| "grad_norm": 1.590183144064633, | |
| "learning_rate": 7.902949059570945e-06, | |
| "loss": 0.6175, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.09978222134230845, | |
| "grad_norm": 1.665920028614456, | |
| "learning_rate": 7.898402001766002e-06, | |
| "loss": 0.6758, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.1013660661255197, | |
| "grad_norm": 1.6053295719352823, | |
| "learning_rate": 7.89375221744277e-06, | |
| "loss": 0.5228, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.10294991090873094, | |
| "grad_norm": 1.538829090522207, | |
| "learning_rate": 7.888999829127398e-06, | |
| "loss": 0.5839, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.10453375569194219, | |
| "grad_norm": 1.4764506284200576, | |
| "learning_rate": 7.884144962049733e-06, | |
| "loss": 0.5371, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.10611760047515344, | |
| "grad_norm": 1.7787882173817327, | |
| "learning_rate": 7.879187744140039e-06, | |
| "loss": 0.5687, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.10770144525836468, | |
| "grad_norm": 1.6757502009522847, | |
| "learning_rate": 7.874128306025616e-06, | |
| "loss": 0.6602, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.10928529004157593, | |
| "grad_norm": 1.5384088321644194, | |
| "learning_rate": 7.868966781027365e-06, | |
| "loss": 0.5848, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.11086913482478718, | |
| "grad_norm": 1.3974387424168984, | |
| "learning_rate": 7.863703305156273e-06, | |
| "loss": 0.4492, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.11245297960799841, | |
| "grad_norm": 1.4838230417656662, | |
| "learning_rate": 7.858338017109821e-06, | |
| "loss": 0.5937, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.11403682439120966, | |
| "grad_norm": 1.4619003743991448, | |
| "learning_rate": 7.852871058268338e-06, | |
| "loss": 0.6154, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.1156206691744209, | |
| "grad_norm": 1.4943665339665302, | |
| "learning_rate": 7.847302572691277e-06, | |
| "loss": 0.6561, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.11720451395763215, | |
| "grad_norm": 1.4942484366322168, | |
| "learning_rate": 7.841632707113408e-06, | |
| "loss": 0.6133, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.1187883587408434, | |
| "grad_norm": 1.6703395416125706, | |
| "learning_rate": 7.835861610940964e-06, | |
| "loss": 0.5878, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.12037220352405464, | |
| "grad_norm": 1.5664444643827788, | |
| "learning_rate": 7.829989436247697e-06, | |
| "loss": 0.7375, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.12195604830726589, | |
| "grad_norm": 1.4638878839717737, | |
| "learning_rate": 7.824016337770871e-06, | |
| "loss": 0.5211, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.12353989309047714, | |
| "grad_norm": 1.787375030347028, | |
| "learning_rate": 7.817942472907183e-06, | |
| "loss": 0.5647, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.12512373787368838, | |
| "grad_norm": 1.884380332078967, | |
| "learning_rate": 7.811768001708626e-06, | |
| "loss": 0.6087, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.12670758265689963, | |
| "grad_norm": 1.5929236515264444, | |
| "learning_rate": 7.805493086878254e-06, | |
| "loss": 0.6642, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.12829142744011088, | |
| "grad_norm": 1.5772424009229602, | |
| "learning_rate": 7.799117893765911e-06, | |
| "loss": 0.5835, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.12987527222332212, | |
| "grad_norm": 1.7489491911949495, | |
| "learning_rate": 7.792642590363864e-06, | |
| "loss": 0.6714, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.13145911700653337, | |
| "grad_norm": 1.6319871292096388, | |
| "learning_rate": 7.786067347302378e-06, | |
| "loss": 0.6794, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.13304296178974462, | |
| "grad_norm": 1.4796412781963182, | |
| "learning_rate": 7.779392337845224e-06, | |
| "loss": 0.5173, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.13462680657295584, | |
| "grad_norm": 1.582366953055958, | |
| "learning_rate": 7.772617737885109e-06, | |
| "loss": 0.6008, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.13621065135616708, | |
| "grad_norm": 1.4986337444583717, | |
| "learning_rate": 7.765743725939044e-06, | |
| "loss": 0.6157, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.13779449613937833, | |
| "grad_norm": 1.577968697496146, | |
| "learning_rate": 7.758770483143633e-06, | |
| "loss": 0.5652, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.13937834092258958, | |
| "grad_norm": 1.6508937367068126, | |
| "learning_rate": 7.751698193250313e-06, | |
| "loss": 0.5759, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.14096218570580082, | |
| "grad_norm": 1.7727311004928359, | |
| "learning_rate": 7.744527042620495e-06, | |
| "loss": 0.621, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.14254603048901207, | |
| "grad_norm": 1.5183748104433379, | |
| "learning_rate": 7.737257220220672e-06, | |
| "loss": 0.6053, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.14412987527222332, | |
| "grad_norm": 1.5930246968878465, | |
| "learning_rate": 7.729888917617423e-06, | |
| "loss": 0.5267, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.14571372005543456, | |
| "grad_norm": 1.5445708944187808, | |
| "learning_rate": 7.722422328972375e-06, | |
| "loss": 0.5988, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.1472975648386458, | |
| "grad_norm": 1.644950232043727, | |
| "learning_rate": 7.71485765103708e-06, | |
| "loss": 0.523, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.14888140962185706, | |
| "grad_norm": 1.582899153506888, | |
| "learning_rate": 7.707195083147842e-06, | |
| "loss": 0.5703, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.1504652544050683, | |
| "grad_norm": 1.5412622272946352, | |
| "learning_rate": 7.699434827220446e-06, | |
| "loss": 0.6049, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.15204909918827955, | |
| "grad_norm": 1.3877844675757782, | |
| "learning_rate": 7.691577087744858e-06, | |
| "loss": 0.6088, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.1536329439714908, | |
| "grad_norm": 1.7758770361443341, | |
| "learning_rate": 7.683622071779814e-06, | |
| "loss": 0.5779, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.15521678875470205, | |
| "grad_norm": 1.727972351073385, | |
| "learning_rate": 7.675569988947388e-06, | |
| "loss": 0.6189, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.1568006335379133, | |
| "grad_norm": 1.726280844012036, | |
| "learning_rate": 7.66742105142745e-06, | |
| "loss": 0.6134, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.15838447832112454, | |
| "grad_norm": 1.478777494556154, | |
| "learning_rate": 7.659175473952084e-06, | |
| "loss": 0.5614, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15996832310433579, | |
| "grad_norm": 1.5790584926585527, | |
| "learning_rate": 7.65083347379992e-06, | |
| "loss": 0.659, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.16155216788754703, | |
| "grad_norm": 1.5037297538511123, | |
| "learning_rate": 7.642395270790426e-06, | |
| "loss": 0.4981, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.16313601267075828, | |
| "grad_norm": 1.5590318704111625, | |
| "learning_rate": 7.633861087278093e-06, | |
| "loss": 0.5807, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.1647198574539695, | |
| "grad_norm": 1.4332619998935698, | |
| "learning_rate": 7.6252311481465996e-06, | |
| "loss": 0.6309, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.16630370223718074, | |
| "grad_norm": 1.4427352973548397, | |
| "learning_rate": 7.616505680802863e-06, | |
| "loss": 0.6623, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.167887547020392, | |
| "grad_norm": 1.6827061244824466, | |
| "learning_rate": 7.607684915171065e-06, | |
| "loss": 0.6589, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.16947139180360324, | |
| "grad_norm": 1.5663175326090033, | |
| "learning_rate": 7.598769083686582e-06, | |
| "loss": 0.627, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.17105523658681449, | |
| "grad_norm": 1.423604206610221, | |
| "learning_rate": 7.589758421289864e-06, | |
| "loss": 0.6335, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.17263908137002573, | |
| "grad_norm": 1.4675532083940528, | |
| "learning_rate": 7.58065316542025e-06, | |
| "loss": 0.59, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.17422292615323698, | |
| "grad_norm": 1.8233813273626727, | |
| "learning_rate": 7.571453556009695e-06, | |
| "loss": 0.5213, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.17580677093644823, | |
| "grad_norm": 1.8255857113037794, | |
| "learning_rate": 7.562159835476465e-06, | |
| "loss": 0.6255, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.17739061571965947, | |
| "grad_norm": 1.4953012811749822, | |
| "learning_rate": 7.552772248718739e-06, | |
| "loss": 0.6206, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.17897446050287072, | |
| "grad_norm": 1.56255118528589, | |
| "learning_rate": 7.5432910431081586e-06, | |
| "loss": 0.5783, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.18055830528608197, | |
| "grad_norm": 1.664536250355845, | |
| "learning_rate": 7.533716468483311e-06, | |
| "loss": 0.6409, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.1821421500692932, | |
| "grad_norm": 1.4958558339075811, | |
| "learning_rate": 7.524048777143137e-06, | |
| "loss": 0.569, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.18372599485250446, | |
| "grad_norm": 1.4039476439318943, | |
| "learning_rate": 7.5142882238403e-06, | |
| "loss": 0.6021, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.1853098396357157, | |
| "grad_norm": 1.6306064613151194, | |
| "learning_rate": 7.504435065774454e-06, | |
| "loss": 0.7385, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.18689368441892695, | |
| "grad_norm": 1.668079082925941, | |
| "learning_rate": 7.494489562585478e-06, | |
| "loss": 0.5724, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.1884775292021382, | |
| "grad_norm": 1.434447147714598, | |
| "learning_rate": 7.48445197634663e-06, | |
| "loss": 0.6092, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.19006137398534945, | |
| "grad_norm": 1.984109033026855, | |
| "learning_rate": 7.474322571557644e-06, | |
| "loss": 0.6691, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.1916452187685607, | |
| "grad_norm": 1.5769599681060413, | |
| "learning_rate": 7.4641016151377545e-06, | |
| "loss": 0.6061, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.19322906355177194, | |
| "grad_norm": 1.384122268885966, | |
| "learning_rate": 7.45378937641867e-06, | |
| "loss": 0.5634, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.19481290833498316, | |
| "grad_norm": 1.498669953718918, | |
| "learning_rate": 7.44338612713747e-06, | |
| "loss": 0.5627, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.1963967531181944, | |
| "grad_norm": 1.4288041695671259, | |
| "learning_rate": 7.43289214142945e-06, | |
| "loss": 0.5726, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.19798059790140565, | |
| "grad_norm": 1.5646983954502622, | |
| "learning_rate": 7.422307695820892e-06, | |
| "loss": 0.623, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.1995644426846169, | |
| "grad_norm": 1.7202467615332813, | |
| "learning_rate": 7.411633069221782e-06, | |
| "loss": 0.6123, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.20114828746782815, | |
| "grad_norm": 1.767901675287711, | |
| "learning_rate": 7.400868542918457e-06, | |
| "loss": 0.5208, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.2027321322510394, | |
| "grad_norm": 1.5246478568278783, | |
| "learning_rate": 7.390014400566196e-06, | |
| "loss": 0.5708, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.20431597703425064, | |
| "grad_norm": 1.6477524599468607, | |
| "learning_rate": 7.379070928181746e-06, | |
| "loss": 0.5288, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.2058998218174619, | |
| "grad_norm": 1.4399111543584902, | |
| "learning_rate": 7.3680384141357805e-06, | |
| "loss": 0.5898, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.20748366660067313, | |
| "grad_norm": 1.5830239221298632, | |
| "learning_rate": 7.356917149145307e-06, | |
| "loss": 0.5797, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.20906751138388438, | |
| "grad_norm": 1.403523262072001, | |
| "learning_rate": 7.3457074262659974e-06, | |
| "loss": 0.5581, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.21065135616709563, | |
| "grad_norm": 1.7026128256384587, | |
| "learning_rate": 7.334409540884478e-06, | |
| "loss": 0.5859, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.21223520095030687, | |
| "grad_norm": 1.4478577966897537, | |
| "learning_rate": 7.323023790710534e-06, | |
| "loss": 0.6038, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.21381904573351812, | |
| "grad_norm": 1.5371200095544344, | |
| "learning_rate": 7.3115504757692715e-06, | |
| "loss": 0.5528, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.21540289051672937, | |
| "grad_norm": 1.4893093530093662, | |
| "learning_rate": 7.299989898393209e-06, | |
| "loss": 0.6717, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.21698673529994061, | |
| "grad_norm": 1.3874990168288865, | |
| "learning_rate": 7.288342363214313e-06, | |
| "loss": 0.5586, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.21857058008315186, | |
| "grad_norm": 1.5863006868461444, | |
| "learning_rate": 7.276608177155967e-06, | |
| "loss": 0.4951, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.2201544248663631, | |
| "grad_norm": 1.489868624576753, | |
| "learning_rate": 7.264787649424887e-06, | |
| "loss": 0.5833, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.22173826964957435, | |
| "grad_norm": 1.3377913662186058, | |
| "learning_rate": 7.2528810915029705e-06, | |
| "loss": 0.6079, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.22332211443278557, | |
| "grad_norm": 1.4551371038570358, | |
| "learning_rate": 7.240888817139094e-06, | |
| "loss": 0.629, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.22490595921599682, | |
| "grad_norm": 1.4800684134742632, | |
| "learning_rate": 7.228811142340838e-06, | |
| "loss": 0.5218, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.22648980399920807, | |
| "grad_norm": 1.655894288397452, | |
| "learning_rate": 7.2166483853661666e-06, | |
| "loss": 0.5851, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.2280736487824193, | |
| "grad_norm": 1.5072103166941109, | |
| "learning_rate": 7.204400866715038e-06, | |
| "loss": 0.5484, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.22965749356563056, | |
| "grad_norm": 1.5118758556170837, | |
| "learning_rate": 7.192068909120959e-06, | |
| "loss": 0.6607, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.2312413383488418, | |
| "grad_norm": 1.6979615740477183, | |
| "learning_rate": 7.179652837542479e-06, | |
| "loss": 0.6278, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.23282518313205305, | |
| "grad_norm": 1.4816588827641894, | |
| "learning_rate": 7.167152979154632e-06, | |
| "loss": 0.5747, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.2344090279152643, | |
| "grad_norm": 1.477778782495537, | |
| "learning_rate": 7.154569663340312e-06, | |
| "loss": 0.6037, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.23599287269847555, | |
| "grad_norm": 1.524987409114406, | |
| "learning_rate": 7.141903221681595e-06, | |
| "loss": 0.5202, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.2375767174816868, | |
| "grad_norm": 1.4531762635508665, | |
| "learning_rate": 7.1291539879509956e-06, | |
| "loss": 0.6053, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.23916056226489804, | |
| "grad_norm": 1.6848330098071658, | |
| "learning_rate": 7.116322298102681e-06, | |
| "loss": 0.5205, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.2407444070481093, | |
| "grad_norm": 1.53168338669591, | |
| "learning_rate": 7.1034084902636125e-06, | |
| "loss": 0.5588, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.24232825183132053, | |
| "grad_norm": 1.7084343204301633, | |
| "learning_rate": 7.090412904724635e-06, | |
| "loss": 0.6402, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.24391209661453178, | |
| "grad_norm": 1.8530857047977658, | |
| "learning_rate": 7.077335883931516e-06, | |
| "loss": 0.5897, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.24549594139774303, | |
| "grad_norm": 1.5361296146734253, | |
| "learning_rate": 7.064177772475912e-06, | |
| "loss": 0.542, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.24707978618095428, | |
| "grad_norm": 1.6919147409675659, | |
| "learning_rate": 7.050938917086298e-06, | |
| "loss": 0.6055, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.24866363096416552, | |
| "grad_norm": 1.5618314491824075, | |
| "learning_rate": 7.037619666618829e-06, | |
| "loss": 0.535, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.25024747574737677, | |
| "grad_norm": 1.4872965507690663, | |
| "learning_rate": 7.024220372048137e-06, | |
| "loss": 0.5813, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.251831320530588, | |
| "grad_norm": 1.6363093857295996, | |
| "learning_rate": 7.010741386458098e-06, | |
| "loss": 0.4529, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.25341516531379926, | |
| "grad_norm": 2.056313824339786, | |
| "learning_rate": 6.997183065032517e-06, | |
| "loss": 0.5332, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.2549990100970105, | |
| "grad_norm": 1.5062280307878337, | |
| "learning_rate": 6.983545765045774e-06, | |
| "loss": 0.5586, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.25658285488022176, | |
| "grad_norm": 1.7057261325931998, | |
| "learning_rate": 6.969829845853404e-06, | |
| "loss": 0.5615, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.258166699663433, | |
| "grad_norm": 1.5223711914805576, | |
| "learning_rate": 6.956035668882636e-06, | |
| "loss": 0.5553, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.25975054444664425, | |
| "grad_norm": 1.7269587442848504, | |
| "learning_rate": 6.942163597622862e-06, | |
| "loss": 0.5982, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.26133438922985547, | |
| "grad_norm": 1.5775708792423282, | |
| "learning_rate": 6.928213997616058e-06, | |
| "loss": 0.5816, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.26291823401306674, | |
| "grad_norm": 1.7646652820246194, | |
| "learning_rate": 6.914187236447161e-06, | |
| "loss": 0.5582, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.26450207879627796, | |
| "grad_norm": 1.5836559806147648, | |
| "learning_rate": 6.90008368373437e-06, | |
| "loss": 0.5268, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.26608592357948924, | |
| "grad_norm": 1.4526060644749479, | |
| "learning_rate": 6.885903711119417e-06, | |
| "loss": 0.5842, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.26766976836270046, | |
| "grad_norm": 1.469565911234753, | |
| "learning_rate": 6.8716476922577676e-06, | |
| "loss": 0.5691, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.2692536131459117, | |
| "grad_norm": 1.6734917590165517, | |
| "learning_rate": 6.857316002808776e-06, | |
| "loss": 0.4855, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.27083745792912295, | |
| "grad_norm": 1.5732695992638241, | |
| "learning_rate": 6.8429090204257885e-06, | |
| "loss": 0.6122, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.27242130271233417, | |
| "grad_norm": 1.4978871767664772, | |
| "learning_rate": 6.82842712474619e-06, | |
| "loss": 0.4655, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.27400514749554544, | |
| "grad_norm": 1.503094339164215, | |
| "learning_rate": 6.8138706973813995e-06, | |
| "loss": 0.6282, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.27558899227875666, | |
| "grad_norm": 2.1292899427160927, | |
| "learning_rate": 6.799240121906814e-06, | |
| "loss": 0.6792, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.27717283706196794, | |
| "grad_norm": 1.4647489604808317, | |
| "learning_rate": 6.784535783851707e-06, | |
| "loss": 0.644, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.27875668184517916, | |
| "grad_norm": 1.5780789456446127, | |
| "learning_rate": 6.7697580706890585e-06, | |
| "loss": 0.5134, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.28034052662839043, | |
| "grad_norm": 1.754003508034847, | |
| "learning_rate": 6.754907371825354e-06, | |
| "loss": 0.5424, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.28192437141160165, | |
| "grad_norm": 1.4864993829740512, | |
| "learning_rate": 6.739984078590322e-06, | |
| "loss": 0.4967, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.2835082161948129, | |
| "grad_norm": 1.4504899701696683, | |
| "learning_rate": 6.724988584226616e-06, | |
| "loss": 0.5067, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.28509206097802414, | |
| "grad_norm": 1.470233988558896, | |
| "learning_rate": 6.70992128387946e-06, | |
| "loss": 0.5655, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.2866759057612354, | |
| "grad_norm": 1.5181769899461575, | |
| "learning_rate": 6.694782574586229e-06, | |
| "loss": 0.5062, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.28825975054444664, | |
| "grad_norm": 1.4730340611570927, | |
| "learning_rate": 6.679572855265992e-06, | |
| "loss": 0.5855, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.2898435953276579, | |
| "grad_norm": 1.4595330624813205, | |
| "learning_rate": 6.664292526709001e-06, | |
| "loss": 0.4989, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.29142744011086913, | |
| "grad_norm": 1.323456475759639, | |
| "learning_rate": 6.648941991566121e-06, | |
| "loss": 0.5448, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.2930112848940804, | |
| "grad_norm": 1.6848076983535807, | |
| "learning_rate": 6.633521654338231e-06, | |
| "loss": 0.5494, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.2945951296772916, | |
| "grad_norm": 1.5461470851002552, | |
| "learning_rate": 6.618031921365557e-06, | |
| "loss": 0.5979, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.2961789744605029, | |
| "grad_norm": 1.4521318914121286, | |
| "learning_rate": 6.602473200816968e-06, | |
| "loss": 0.6329, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.2977628192437141, | |
| "grad_norm": 1.4482304443134255, | |
| "learning_rate": 6.586845902679222e-06, | |
| "loss": 0.5603, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.29934666402692534, | |
| "grad_norm": 1.729429057098183, | |
| "learning_rate": 6.571150438746157e-06, | |
| "loss": 0.5174, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.3009305088101366, | |
| "grad_norm": 1.4522833098019283, | |
| "learning_rate": 6.555387222607845e-06, | |
| "loss": 0.4707, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.30251435359334783, | |
| "grad_norm": 1.5694908204548417, | |
| "learning_rate": 6.5395566696396914e-06, | |
| "loss": 0.6268, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.3040981983765591, | |
| "grad_norm": 1.4125293528433154, | |
| "learning_rate": 6.523659196991488e-06, | |
| "loss": 0.4955, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.3056820431597703, | |
| "grad_norm": 1.5051250957949753, | |
| "learning_rate": 6.507695223576427e-06, | |
| "loss": 0.487, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.3072658879429816, | |
| "grad_norm": 1.4094675941552535, | |
| "learning_rate": 6.491665170060049e-06, | |
| "loss": 0.4969, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.3088497327261928, | |
| "grad_norm": 1.4384575522029888, | |
| "learning_rate": 6.475569458849178e-06, | |
| "loss": 0.5492, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.3104335775094041, | |
| "grad_norm": 1.7678769340548022, | |
| "learning_rate": 6.45940851408077e-06, | |
| "loss": 0.5836, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.3120174222926153, | |
| "grad_norm": 2.046226775911686, | |
| "learning_rate": 6.4431827616107514e-06, | |
| "loss": 0.5301, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.3136012670758266, | |
| "grad_norm": 1.4943535053844237, | |
| "learning_rate": 6.426892629002788e-06, | |
| "loss": 0.5501, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.3151851118590378, | |
| "grad_norm": 1.5251076879939447, | |
| "learning_rate": 6.410538545517026e-06, | |
| "loss": 0.5089, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.3167689566422491, | |
| "grad_norm": 1.8164625462077661, | |
| "learning_rate": 6.394120942098772e-06, | |
| "loss": 0.5319, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3183528014254603, | |
| "grad_norm": 1.4408492309184018, | |
| "learning_rate": 6.377640251367147e-06, | |
| "loss": 0.4609, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.31993664620867157, | |
| "grad_norm": 1.4200405326569705, | |
| "learning_rate": 6.361096907603678e-06, | |
| "loss": 0.5396, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.3215204909918828, | |
| "grad_norm": 1.471578227709618, | |
| "learning_rate": 6.344491346740859e-06, | |
| "loss": 0.546, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.32310433577509406, | |
| "grad_norm": 1.4907309711106325, | |
| "learning_rate": 6.3278240063506605e-06, | |
| "loss": 0.5093, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.3246881805583053, | |
| "grad_norm": 1.3696992488542155, | |
| "learning_rate": 6.311095325633005e-06, | |
| "loss": 0.4799, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.32627202534151656, | |
| "grad_norm": 1.7334631553518818, | |
| "learning_rate": 6.294305745404184e-06, | |
| "loss": 0.5837, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.3278558701247278, | |
| "grad_norm": 1.9680923980600566, | |
| "learning_rate": 6.277455708085254e-06, | |
| "loss": 0.6013, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.329439714907939, | |
| "grad_norm": 1.575234585905169, | |
| "learning_rate": 6.260545657690367e-06, | |
| "loss": 0.5846, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.33102355969115027, | |
| "grad_norm": 1.5428445148256473, | |
| "learning_rate": 6.243576039815079e-06, | |
| "loss": 0.4724, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.3326074044743615, | |
| "grad_norm": 1.5051331668280472, | |
| "learning_rate": 6.226547301624601e-06, | |
| "loss": 0.5778, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.3326074044743615, | |
| "eval_accuracy": 0.8062780751393809, | |
| "eval_loss": 0.6072185039520264, | |
| "eval_perplexity": 1.2109892812795882, | |
| "eval_runtime": 533.963, | |
| "eval_samples_per_second": 1.425, | |
| "eval_steps_per_second": 1.425, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.33419124925757276, | |
| "grad_norm": 1.8036724779367772, | |
| "learning_rate": 6.209459891842023e-06, | |
| "loss": 0.6231, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.335775094040784, | |
| "grad_norm": 1.622010722669537, | |
| "learning_rate": 6.192314260736483e-06, | |
| "loss": 0.4884, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.33735893882399526, | |
| "grad_norm": 1.4671354082285062, | |
| "learning_rate": 6.1751108601113065e-06, | |
| "loss": 0.4331, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.3389427836072065, | |
| "grad_norm": 1.3462750015093699, | |
| "learning_rate": 6.157850143292099e-06, | |
| "loss": 0.5651, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.34052662839041775, | |
| "grad_norm": 4.450327389512898, | |
| "learning_rate": 6.140532565114801e-06, | |
| "loss": 0.5063, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.34211047317362897, | |
| "grad_norm": 1.4358337913572403, | |
| "learning_rate": 6.123158581913703e-06, | |
| "loss": 0.5133, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.34369431795684025, | |
| "grad_norm": 1.5296654139200274, | |
| "learning_rate": 6.105728651509423e-06, | |
| "loss": 0.5617, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.34527816274005146, | |
| "grad_norm": 1.7233319268867215, | |
| "learning_rate": 6.088243233196833e-06, | |
| "loss": 0.578, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.34686200752326274, | |
| "grad_norm": 1.3545296291875666, | |
| "learning_rate": 6.07070278773297e-06, | |
| "loss": 0.6077, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.34844585230647396, | |
| "grad_norm": 1.4071408386524482, | |
| "learning_rate": 6.053107777324882e-06, | |
| "loss": 0.4709, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.35002969708968523, | |
| "grad_norm": 1.625931561657156, | |
| "learning_rate": 6.0354586656174594e-06, | |
| "loss": 0.5402, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.35161354187289645, | |
| "grad_norm": 1.4770799573957036, | |
| "learning_rate": 6.017755917681208e-06, | |
| "loss": 0.5878, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.3531973866561077, | |
| "grad_norm": 1.371967202631883, | |
| "learning_rate": 6e-06, | |
| "loss": 0.5646, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.35478123143931894, | |
| "grad_norm": 1.670286600590674, | |
| "learning_rate": 5.982191380458779e-06, | |
| "loss": 0.5459, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.3563650762225302, | |
| "grad_norm": 1.657503866936318, | |
| "learning_rate": 5.964330528331233e-06, | |
| "loss": 0.6107, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.35794892100574144, | |
| "grad_norm": 1.437798148422675, | |
| "learning_rate": 5.946417914267424e-06, | |
| "loss": 0.5283, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.35953276578895266, | |
| "grad_norm": 1.5841028963525154, | |
| "learning_rate": 5.928454010281395e-06, | |
| "loss": 0.5566, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.36111661057216393, | |
| "grad_norm": 2.912275328636749, | |
| "learning_rate": 5.91043928973872e-06, | |
| "loss": 0.5524, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.36270045535537515, | |
| "grad_norm": 1.39224219742789, | |
| "learning_rate": 5.8923742273440405e-06, | |
| "loss": 0.5018, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.3642843001385864, | |
| "grad_norm": 1.531343821785256, | |
| "learning_rate": 5.87425929912855e-06, | |
| "loss": 0.5498, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.36586814492179764, | |
| "grad_norm": 1.6907756868854458, | |
| "learning_rate": 5.856094982437453e-06, | |
| "loss": 0.6188, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.3674519897050089, | |
| "grad_norm": 1.8925539993976666, | |
| "learning_rate": 5.83788175591739e-06, | |
| "loss": 0.6473, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.36903583448822014, | |
| "grad_norm": 1.3770006280258493, | |
| "learning_rate": 5.819620099503818e-06, | |
| "loss": 0.4686, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.3706196792714314, | |
| "grad_norm": 1.5431315768010794, | |
| "learning_rate": 5.801310494408365e-06, | |
| "loss": 0.5691, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.37220352405464263, | |
| "grad_norm": 1.6551290914393502, | |
| "learning_rate": 5.782953423106153e-06, | |
| "loss": 0.5874, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.3737873688378539, | |
| "grad_norm": 1.9002502737234077, | |
| "learning_rate": 5.764549369323084e-06, | |
| "loss": 0.5529, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.3753712136210651, | |
| "grad_norm": 1.686985111412407, | |
| "learning_rate": 5.746098818023092e-06, | |
| "loss": 0.5603, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.3769550584042764, | |
| "grad_norm": 1.3657672575822837, | |
| "learning_rate": 5.727602255395364e-06, | |
| "loss": 0.5568, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.3785389031874876, | |
| "grad_norm": 1.9695232006427876, | |
| "learning_rate": 5.7090601688415235e-06, | |
| "loss": 0.5658, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.3801227479706989, | |
| "grad_norm": 1.5461356891055895, | |
| "learning_rate": 5.690473046962798e-06, | |
| "loss": 0.4673, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.3817065927539101, | |
| "grad_norm": 2.3698398593391965, | |
| "learning_rate": 5.671841379547133e-06, | |
| "loss": 0.5763, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.3832904375371214, | |
| "grad_norm": 1.6233296254529663, | |
| "learning_rate": 5.6531656575562954e-06, | |
| "loss": 0.4775, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.3848742823203326, | |
| "grad_norm": 1.5057753839519041, | |
| "learning_rate": 5.634446373112926e-06, | |
| "loss": 0.5759, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.3864581271035439, | |
| "grad_norm": 1.569673186402757, | |
| "learning_rate": 5.615684019487579e-06, | |
| "loss": 0.542, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.3880419718867551, | |
| "grad_norm": 1.4845831954568514, | |
| "learning_rate": 5.596879091085723e-06, | |
| "loss": 0.4803, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.3896258166699663, | |
| "grad_norm": 1.8705825155512474, | |
| "learning_rate": 5.57803208343471e-06, | |
| "loss": 0.5017, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.3912096614531776, | |
| "grad_norm": 1.5197093986457457, | |
| "learning_rate": 5.559143493170717e-06, | |
| "loss": 0.541, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.3927935062363888, | |
| "grad_norm": 1.5301810316128006, | |
| "learning_rate": 5.540213818025666e-06, | |
| "loss": 0.5427, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.3943773510196001, | |
| "grad_norm": 1.8516941433643899, | |
| "learning_rate": 5.5212435568141035e-06, | |
| "loss": 0.5974, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.3959611958028113, | |
| "grad_norm": 1.3334174668528216, | |
| "learning_rate": 5.5022332094200505e-06, | |
| "loss": 0.5429, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.3975450405860226, | |
| "grad_norm": 1.4702275400288973, | |
| "learning_rate": 5.483183276783843e-06, | |
| "loss": 0.5766, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.3991288853692338, | |
| "grad_norm": 1.5459152423352713, | |
| "learning_rate": 5.464094260888924e-06, | |
| "loss": 0.5527, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.4007127301524451, | |
| "grad_norm": 1.8640878576069286, | |
| "learning_rate": 5.4449666647486125e-06, | |
| "loss": 0.6205, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.4022965749356563, | |
| "grad_norm": 1.9092864583223532, | |
| "learning_rate": 5.425800992392856e-06, | |
| "loss": 0.548, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.40388041971886757, | |
| "grad_norm": 1.5276995541859555, | |
| "learning_rate": 5.406597748854947e-06, | |
| "loss": 0.5498, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.4054642645020788, | |
| "grad_norm": 1.4771875777008228, | |
| "learning_rate": 5.38735744015821e-06, | |
| "loss": 0.4411, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.40704810928529006, | |
| "grad_norm": 1.637711951004362, | |
| "learning_rate": 5.368080573302675e-06, | |
| "loss": 0.5537, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.4086319540685013, | |
| "grad_norm": 1.606555141779956, | |
| "learning_rate": 5.348767656251709e-06, | |
| "loss": 0.558, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.41021579885171255, | |
| "grad_norm": 1.4771059602395231, | |
| "learning_rate": 5.329419197918638e-06, | |
| "loss": 0.4915, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.4117996436349238, | |
| "grad_norm": 1.5943720324164687, | |
| "learning_rate": 5.310035708153335e-06, | |
| "loss": 0.583, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.41338348841813505, | |
| "grad_norm": 1.666964957956596, | |
| "learning_rate": 5.2906176977287795e-06, | |
| "loss": 0.5493, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.41496733320134627, | |
| "grad_norm": 1.4711154343447124, | |
| "learning_rate": 5.271165678327606e-06, | |
| "loss": 0.5519, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.4165511779845575, | |
| "grad_norm": 1.5995792262282518, | |
| "learning_rate": 5.251680162528617e-06, | |
| "loss": 0.5377, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.41813502276776876, | |
| "grad_norm": 1.4526790782720835, | |
| "learning_rate": 5.232161663793275e-06, | |
| "loss": 0.5335, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.41971886755098, | |
| "grad_norm": 1.5478646380088532, | |
| "learning_rate": 5.212610696452174e-06, | |
| "loss": 0.6434, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.42130271233419125, | |
| "grad_norm": 1.4956181853598964, | |
| "learning_rate": 5.193027775691485e-06, | |
| "loss": 0.498, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.4228865571174025, | |
| "grad_norm": 1.4974980436315144, | |
| "learning_rate": 5.173413417539384e-06, | |
| "loss": 0.6171, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.42447040190061375, | |
| "grad_norm": 1.466644696421707, | |
| "learning_rate": 5.153768138852449e-06, | |
| "loss": 0.501, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.42605424668382497, | |
| "grad_norm": 1.627652008126963, | |
| "learning_rate": 5.134092457302043e-06, | |
| "loss": 0.6258, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.42763809146703624, | |
| "grad_norm": 1.648118892712504, | |
| "learning_rate": 5.114386891360675e-06, | |
| "loss": 0.5565, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.42922193625024746, | |
| "grad_norm": 1.848328087802553, | |
| "learning_rate": 5.094651960288332e-06, | |
| "loss": 0.5803, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.43080578103345873, | |
| "grad_norm": 1.3558392557511212, | |
| "learning_rate": 5.074888184118801e-06, | |
| "loss": 0.4598, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.43238962581666995, | |
| "grad_norm": 1.4376325696738284, | |
| "learning_rate": 5.055096083645967e-06, | |
| "loss": 0.5144, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.43397347059988123, | |
| "grad_norm": 2.013114345583861, | |
| "learning_rate": 5.035276180410083e-06, | |
| "loss": 0.5365, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.43555731538309245, | |
| "grad_norm": 1.7720963379244992, | |
| "learning_rate": 5.015428996684031e-06, | |
| "loss": 0.5965, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.4371411601663037, | |
| "grad_norm": 1.5956864806503275, | |
| "learning_rate": 4.995555055459562e-06, | |
| "loss": 0.5399, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.43872500494951494, | |
| "grad_norm": 1.705695286576096, | |
| "learning_rate": 4.975654880433508e-06, | |
| "loss": 0.5492, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.4403088497327262, | |
| "grad_norm": 1.7149353403443588, | |
| "learning_rate": 4.95572899599399e-06, | |
| "loss": 0.6011, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.44189269451593743, | |
| "grad_norm": 1.327638735973327, | |
| "learning_rate": 4.935777927206595e-06, | |
| "loss": 0.4993, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.4434765392991487, | |
| "grad_norm": 1.5644224950432588, | |
| "learning_rate": 4.915802199800536e-06, | |
| "loss": 0.595, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.44506038408235993, | |
| "grad_norm": 1.517553789603623, | |
| "learning_rate": 4.8958023401548124e-06, | |
| "loss": 0.5383, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.44664422886557115, | |
| "grad_norm": 1.7980504027520112, | |
| "learning_rate": 4.875778875284322e-06, | |
| "loss": 0.486, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.4482280736487824, | |
| "grad_norm": 1.618198969176812, | |
| "learning_rate": 4.855732332825989e-06, | |
| "loss": 0.5041, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.44981191843199364, | |
| "grad_norm": 1.6074207482159366, | |
| "learning_rate": 4.8356632410248495e-06, | |
| "loss": 0.5225, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.4513957632152049, | |
| "grad_norm": 1.3840009026279627, | |
| "learning_rate": 4.815572128720138e-06, | |
| "loss": 0.4984, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.45297960799841613, | |
| "grad_norm": 2.0549483079657644, | |
| "learning_rate": 4.795459525331346e-06, | |
| "loss": 0.7242, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.4545634527816274, | |
| "grad_norm": 1.4634854048670438, | |
| "learning_rate": 4.77532596084428e-06, | |
| "loss": 0.5575, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.4561472975648386, | |
| "grad_norm": 1.4194408672102914, | |
| "learning_rate": 4.755171965797087e-06, | |
| "loss": 0.5493, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.4577311423480499, | |
| "grad_norm": 1.6579210683410825, | |
| "learning_rate": 4.734998071266282e-06, | |
| "loss": 0.4842, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.4593149871312611, | |
| "grad_norm": 2.2481565569431003, | |
| "learning_rate": 4.714804808852744e-06, | |
| "loss": 0.5556, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.4608988319144724, | |
| "grad_norm": 1.7503586240205726, | |
| "learning_rate": 4.694592710667722e-06, | |
| "loss": 0.5027, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.4624826766976836, | |
| "grad_norm": 1.5013077261326937, | |
| "learning_rate": 4.674362309318796e-06, | |
| "loss": 0.5387, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.4640665214808949, | |
| "grad_norm": 1.5044654112516254, | |
| "learning_rate": 4.65411413789586e-06, | |
| "loss": 0.4191, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.4656503662641061, | |
| "grad_norm": 1.4661324959060025, | |
| "learning_rate": 4.6338487299570605e-06, | |
| "loss": 0.5883, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.4672342110473174, | |
| "grad_norm": 1.7266562955889597, | |
| "learning_rate": 4.613566619514742e-06, | |
| "loss": 0.6532, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.4688180558305286, | |
| "grad_norm": 1.4130438958548992, | |
| "learning_rate": 4.593268341021378e-06, | |
| "loss": 0.5274, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.4704019006137399, | |
| "grad_norm": 1.4628610094368864, | |
| "learning_rate": 4.572954429355486e-06, | |
| "loss": 0.4546, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.4719857453969511, | |
| "grad_norm": 2.6067716280602493, | |
| "learning_rate": 4.552625419807529e-06, | |
| "loss": 0.5247, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.47356959018016237, | |
| "grad_norm": 1.5391344972032668, | |
| "learning_rate": 4.532281848065815e-06, | |
| "loss": 0.5648, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.4751534349633736, | |
| "grad_norm": 1.4085395552662021, | |
| "learning_rate": 4.5119242502023795e-06, | |
| "loss": 0.5333, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4767372797465848, | |
| "grad_norm": 1.4740227736979468, | |
| "learning_rate": 4.4915531626588566e-06, | |
| "loss": 0.4993, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.4783211245297961, | |
| "grad_norm": 1.5696976913793732, | |
| "learning_rate": 4.4711691222323505e-06, | |
| "loss": 0.5829, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.4799049693130073, | |
| "grad_norm": 1.3762468410600768, | |
| "learning_rate": 4.450772666061285e-06, | |
| "loss": 0.5585, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.4814888140962186, | |
| "grad_norm": 1.4028769788977258, | |
| "learning_rate": 4.4303643316112455e-06, | |
| "loss": 0.4688, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.4830726588794298, | |
| "grad_norm": 1.6682668294458134, | |
| "learning_rate": 4.409944656660828e-06, | |
| "loss": 0.6571, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.48465650366264107, | |
| "grad_norm": 1.413594427095901, | |
| "learning_rate": 4.389514179287455e-06, | |
| "loss": 0.5522, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.4862403484458523, | |
| "grad_norm": 1.519057639158845, | |
| "learning_rate": 4.369073437853208e-06, | |
| "loss": 0.5334, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.48782419322906356, | |
| "grad_norm": 1.6208921075298082, | |
| "learning_rate": 4.348622970990633e-06, | |
| "loss": 0.5182, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.4894080380122748, | |
| "grad_norm": 1.8501674500734415, | |
| "learning_rate": 4.328163317588551e-06, | |
| "loss": 0.6517, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.49099188279548606, | |
| "grad_norm": 1.4363229280193845, | |
| "learning_rate": 4.307695016777855e-06, | |
| "loss": 0.5416, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.4925757275786973, | |
| "grad_norm": 1.7153136971595235, | |
| "learning_rate": 4.28721860791731e-06, | |
| "loss": 0.588, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.49415957236190855, | |
| "grad_norm": 1.7049912502271836, | |
| "learning_rate": 4.2667346305793305e-06, | |
| "loss": 0.5894, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.49574341714511977, | |
| "grad_norm": 1.7928491666503086, | |
| "learning_rate": 4.246243624535772e-06, | |
| "loss": 0.5509, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.49732726192833104, | |
| "grad_norm": 1.4067335450901148, | |
| "learning_rate": 4.2257461297436975e-06, | |
| "loss": 0.5372, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.49891110671154226, | |
| "grad_norm": 1.551109249256133, | |
| "learning_rate": 4.205242686331158e-06, | |
| "loss": 0.4888, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.5004949514947535, | |
| "grad_norm": 1.5295528770849849, | |
| "learning_rate": 4.184733834582958e-06, | |
| "loss": 0.5244, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.5020787962779648, | |
| "grad_norm": 1.568867534852523, | |
| "learning_rate": 4.164220114926413e-06, | |
| "loss": 0.5243, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.503662641061176, | |
| "grad_norm": 1.5276609286295317, | |
| "learning_rate": 4.143702067917114e-06, | |
| "loss": 0.5557, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.5052464858443872, | |
| "grad_norm": 1.7692820390689328, | |
| "learning_rate": 4.123180234224682e-06, | |
| "loss": 0.5533, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.5068303306275985, | |
| "grad_norm": 1.6282684636897258, | |
| "learning_rate": 4.102655154618519e-06, | |
| "loss": 0.54, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.5084141754108097, | |
| "grad_norm": 1.4884338495205554, | |
| "learning_rate": 4.082127369953562e-06, | |
| "loss": 0.5187, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.509998020194021, | |
| "grad_norm": 1.4653962436440777, | |
| "learning_rate": 4.061597421156027e-06, | |
| "loss": 0.4915, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.5115818649772322, | |
| "grad_norm": 1.395223278506742, | |
| "learning_rate": 4.04106584920916e-06, | |
| "loss": 0.496, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.5131657097604435, | |
| "grad_norm": 2.1426438371002487, | |
| "learning_rate": 4.0205331951389745e-06, | |
| "loss": 0.6205, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.5147495545436547, | |
| "grad_norm": 1.867498513188697, | |
| "learning_rate": 4e-06, | |
| "loss": 0.4003, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.516333399326866, | |
| "grad_norm": 1.614897925155514, | |
| "learning_rate": 3.979466804861026e-06, | |
| "loss": 0.5554, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.5179172441100772, | |
| "grad_norm": 1.621850139141135, | |
| "learning_rate": 3.958934150790841e-06, | |
| "loss": 0.4116, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.5195010888932885, | |
| "grad_norm": 1.6540960382507581, | |
| "learning_rate": 3.938402578843973e-06, | |
| "loss": 0.4899, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.5210849336764997, | |
| "grad_norm": 1.4757999919149907, | |
| "learning_rate": 3.917872630046439e-06, | |
| "loss": 0.4871, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.5226687784597109, | |
| "grad_norm": 1.4101743650910379, | |
| "learning_rate": 3.8973448453814815e-06, | |
| "loss": 0.5557, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.5242526232429222, | |
| "grad_norm": 1.820304069777086, | |
| "learning_rate": 3.876819765775319e-06, | |
| "loss": 0.5178, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.5258364680261335, | |
| "grad_norm": 1.3457029032306118, | |
| "learning_rate": 3.856297932082886e-06, | |
| "loss": 0.5481, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.5274203128093446, | |
| "grad_norm": 1.2926453088911345, | |
| "learning_rate": 3.835779885073587e-06, | |
| "loss": 0.47, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.5290041575925559, | |
| "grad_norm": 1.7195140710061863, | |
| "learning_rate": 3.815266165417042e-06, | |
| "loss": 0.4018, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.5305880023757672, | |
| "grad_norm": 1.5294915569869552, | |
| "learning_rate": 3.7947573136688406e-06, | |
| "loss": 0.4889, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.5321718471589785, | |
| "grad_norm": 1.5318098339821966, | |
| "learning_rate": 3.774253870256302e-06, | |
| "loss": 0.429, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.5337556919421896, | |
| "grad_norm": 1.5322388550699502, | |
| "learning_rate": 3.7537563754642285e-06, | |
| "loss": 0.5065, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.5353395367254009, | |
| "grad_norm": 1.7066209125681409, | |
| "learning_rate": 3.7332653694206683e-06, | |
| "loss": 0.4947, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.5369233815086122, | |
| "grad_norm": 1.3425460536457656, | |
| "learning_rate": 3.7127813920826896e-06, | |
| "loss": 0.5448, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.5385072262918233, | |
| "grad_norm": 1.3885953993055378, | |
| "learning_rate": 3.6923049832221447e-06, | |
| "loss": 0.5269, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.5400910710750346, | |
| "grad_norm": 1.562252798906571, | |
| "learning_rate": 3.6718366824114497e-06, | |
| "loss": 0.5145, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.5416749158582459, | |
| "grad_norm": 1.7621418644258409, | |
| "learning_rate": 3.651377029009367e-06, | |
| "loss": 0.5345, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.5432587606414572, | |
| "grad_norm": 1.6334983556675244, | |
| "learning_rate": 3.6309265621467923e-06, | |
| "loss": 0.5435, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.5448426054246683, | |
| "grad_norm": 1.6029717902895917, | |
| "learning_rate": 3.6104858207125447e-06, | |
| "loss": 0.5734, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.5464264502078796, | |
| "grad_norm": 1.7090791562879204, | |
| "learning_rate": 3.590055343339172e-06, | |
| "loss": 0.5325, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.5480102949910909, | |
| "grad_norm": 1.5947834681663235, | |
| "learning_rate": 3.5696356683887545e-06, | |
| "loss": 0.4975, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.5495941397743022, | |
| "grad_norm": 1.4472742169549009, | |
| "learning_rate": 3.5492273339387156e-06, | |
| "loss": 0.4894, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.5511779845575133, | |
| "grad_norm": 2.0434685400743082, | |
| "learning_rate": 3.5288308777676487e-06, | |
| "loss": 0.4684, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.5527618293407246, | |
| "grad_norm": 1.9208895400830441, | |
| "learning_rate": 3.508446837341144e-06, | |
| "loss": 0.5969, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.5543456741239359, | |
| "grad_norm": 1.4909570903888723, | |
| "learning_rate": 3.488075749797622e-06, | |
| "loss": 0.5022, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5559295189071471, | |
| "grad_norm": 1.6489325052677233, | |
| "learning_rate": 3.4677181519341864e-06, | |
| "loss": 0.5895, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.5575133636903583, | |
| "grad_norm": 1.613873880473099, | |
| "learning_rate": 3.447374580192472e-06, | |
| "loss": 0.5907, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.5590972084735696, | |
| "grad_norm": 1.7320655964325145, | |
| "learning_rate": 3.427045570644515e-06, | |
| "loss": 0.4408, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.5606810532567809, | |
| "grad_norm": 1.5966735398972682, | |
| "learning_rate": 3.406731658978621e-06, | |
| "loss": 0.5518, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.5622648980399921, | |
| "grad_norm": 1.507137639160325, | |
| "learning_rate": 3.386433380485258e-06, | |
| "loss": 0.5487, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.5638487428232033, | |
| "grad_norm": 1.477023097202977, | |
| "learning_rate": 3.36615127004294e-06, | |
| "loss": 0.5277, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.5654325876064146, | |
| "grad_norm": 1.4345842364104429, | |
| "learning_rate": 3.3458858621041395e-06, | |
| "loss": 0.5825, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.5670164323896258, | |
| "grad_norm": 1.5249472435401055, | |
| "learning_rate": 3.3256376906812026e-06, | |
| "loss": 0.5686, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.568600277172837, | |
| "grad_norm": 1.652799125000088, | |
| "learning_rate": 3.3054072893322785e-06, | |
| "loss": 0.5356, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.5701841219560483, | |
| "grad_norm": 1.7523508161150247, | |
| "learning_rate": 3.285195191147255e-06, | |
| "loss": 0.558, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.5717679667392596, | |
| "grad_norm": 1.5826594727198133, | |
| "learning_rate": 3.265001928733718e-06, | |
| "loss": 0.5513, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.5733518115224708, | |
| "grad_norm": 1.4553905463035222, | |
| "learning_rate": 3.2448280342029128e-06, | |
| "loss": 0.4994, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.574935656305682, | |
| "grad_norm": 1.4388765353827664, | |
| "learning_rate": 3.2246740391557196e-06, | |
| "loss": 0.5027, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.5765195010888933, | |
| "grad_norm": 1.330505454003212, | |
| "learning_rate": 3.2045404746686542e-06, | |
| "loss": 0.508, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.5781033458721045, | |
| "grad_norm": 1.3429439845943842, | |
| "learning_rate": 3.1844278712798626e-06, | |
| "loss": 0.4263, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.5796871906553158, | |
| "grad_norm": 1.4396944573827641, | |
| "learning_rate": 3.1643367589751497e-06, | |
| "loss": 0.5179, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.581271035438527, | |
| "grad_norm": 1.414735328601168, | |
| "learning_rate": 3.1442676671740113e-06, | |
| "loss": 0.4259, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 0.5828548802217383, | |
| "grad_norm": 1.66831199255592, | |
| "learning_rate": 3.124221124715678e-06, | |
| "loss": 0.4971, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.5844387250049495, | |
| "grad_norm": 1.5810788020061641, | |
| "learning_rate": 3.104197659845188e-06, | |
| "loss": 0.5772, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.5860225697881608, | |
| "grad_norm": 1.5715742632475282, | |
| "learning_rate": 3.0841978001994645e-06, | |
| "loss": 0.5036, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.587606414571372, | |
| "grad_norm": 1.751121812265499, | |
| "learning_rate": 3.0642220727934067e-06, | |
| "loss": 0.5295, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.5891902593545832, | |
| "grad_norm": 1.5098119881063428, | |
| "learning_rate": 3.0442710040060098e-06, | |
| "loss": 0.5466, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.5907741041377945, | |
| "grad_norm": 1.5207898613100728, | |
| "learning_rate": 3.0243451195664913e-06, | |
| "loss": 0.5579, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 0.5923579489210058, | |
| "grad_norm": 1.4240138870827277, | |
| "learning_rate": 3.004444944540437e-06, | |
| "loss": 0.5507, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.593941793704217, | |
| "grad_norm": 1.506087376349933, | |
| "learning_rate": 2.9845710033159684e-06, | |
| "loss": 0.4465, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.5955256384874282, | |
| "grad_norm": 1.607368732995549, | |
| "learning_rate": 2.9647238195899164e-06, | |
| "loss": 0.5378, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.5971094832706395, | |
| "grad_norm": 1.578131220264289, | |
| "learning_rate": 2.9449039163540316e-06, | |
| "loss": 0.4516, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 0.5986933280538507, | |
| "grad_norm": 1.488407789608305, | |
| "learning_rate": 2.9251118158811984e-06, | |
| "loss": 0.5087, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.600277172837062, | |
| "grad_norm": 1.4648982592871571, | |
| "learning_rate": 2.9053480397116684e-06, | |
| "loss": 0.5531, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 0.6018610176202732, | |
| "grad_norm": 1.378206069077312, | |
| "learning_rate": 2.885613108639326e-06, | |
| "loss": 0.437, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.6034448624034845, | |
| "grad_norm": 1.4399539996573616, | |
| "learning_rate": 2.865907542697957e-06, | |
| "loss": 0.5327, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.6050287071866957, | |
| "grad_norm": 1.4113473201037952, | |
| "learning_rate": 2.846231861147551e-06, | |
| "loss": 0.5414, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.6066125519699069, | |
| "grad_norm": 1.3798536815664695, | |
| "learning_rate": 2.8265865824606165e-06, | |
| "loss": 0.5537, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 0.6081963967531182, | |
| "grad_norm": 1.6278939154714502, | |
| "learning_rate": 2.806972224308515e-06, | |
| "loss": 0.5272, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.6097802415363295, | |
| "grad_norm": 1.4122415614433053, | |
| "learning_rate": 2.787389303547826e-06, | |
| "loss": 0.5437, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.6113640863195406, | |
| "grad_norm": 1.4410982986916903, | |
| "learning_rate": 2.7678383362067257e-06, | |
| "loss": 0.6161, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.6129479311027519, | |
| "grad_norm": 1.6053888158206666, | |
| "learning_rate": 2.748319837471383e-06, | |
| "loss": 0.5462, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.6145317758859632, | |
| "grad_norm": 1.6416876364791944, | |
| "learning_rate": 2.7288343216723933e-06, | |
| "loss": 0.5041, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.6161156206691745, | |
| "grad_norm": 1.6000769765570262, | |
| "learning_rate": 2.7093823022712215e-06, | |
| "loss": 0.6001, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 0.6176994654523856, | |
| "grad_norm": 1.5229151146342543, | |
| "learning_rate": 2.6899642918466656e-06, | |
| "loss": 0.5966, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.6192833102355969, | |
| "grad_norm": 1.2082061870063965, | |
| "learning_rate": 2.6705808020813617e-06, | |
| "loss": 0.4404, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 0.6208671550188082, | |
| "grad_norm": 1.7357266576917079, | |
| "learning_rate": 2.6512323437482903e-06, | |
| "loss": 0.509, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.6224509998020195, | |
| "grad_norm": 1.4629821094699202, | |
| "learning_rate": 2.631919426697325e-06, | |
| "loss": 0.5477, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.6240348445852306, | |
| "grad_norm": 1.6391626920610356, | |
| "learning_rate": 2.612642559841789e-06, | |
| "loss": 0.5424, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.6256186893684419, | |
| "grad_norm": 1.6354675394639997, | |
| "learning_rate": 2.5934022511450525e-06, | |
| "loss": 0.4486, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.6272025341516532, | |
| "grad_norm": 1.5362602160998997, | |
| "learning_rate": 2.574199007607144e-06, | |
| "loss": 0.452, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.6287863789348643, | |
| "grad_norm": 1.4546308476604741, | |
| "learning_rate": 2.5550333352513884e-06, | |
| "loss": 0.5295, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 0.6303702237180756, | |
| "grad_norm": 1.5353573065379114, | |
| "learning_rate": 2.535905739111077e-06, | |
| "loss": 0.4627, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.6319540685012869, | |
| "grad_norm": 1.7076979214421926, | |
| "learning_rate": 2.516816723216157e-06, | |
| "loss": 0.5024, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.6335379132844982, | |
| "grad_norm": 1.8486022817022656, | |
| "learning_rate": 2.49776679057995e-06, | |
| "loss": 0.5149, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6351217580677093, | |
| "grad_norm": 1.566887589871668, | |
| "learning_rate": 2.4787564431858974e-06, | |
| "loss": 0.5059, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 0.6367056028509206, | |
| "grad_norm": 1.564549295152443, | |
| "learning_rate": 2.4597861819743334e-06, | |
| "loss": 0.4603, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.6382894476341319, | |
| "grad_norm": 1.380492154373069, | |
| "learning_rate": 2.4408565068292827e-06, | |
| "loss": 0.4929, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 0.6398732924173431, | |
| "grad_norm": 1.5407455494599405, | |
| "learning_rate": 2.4219679165652902e-06, | |
| "loss": 0.5311, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.6414571372005543, | |
| "grad_norm": 1.4174285596906695, | |
| "learning_rate": 2.403120908914277e-06, | |
| "loss": 0.4834, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.6430409819837656, | |
| "grad_norm": 1.873920827014659, | |
| "learning_rate": 2.3843159805124203e-06, | |
| "loss": 0.5017, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.6446248267669769, | |
| "grad_norm": 1.7835980447150575, | |
| "learning_rate": 2.365553626887074e-06, | |
| "loss": 0.5418, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 0.6462086715501881, | |
| "grad_norm": 1.3633583035406078, | |
| "learning_rate": 2.3468343424437055e-06, | |
| "loss": 0.4608, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.6477925163333993, | |
| "grad_norm": 1.8174838090865337, | |
| "learning_rate": 2.3281586204528677e-06, | |
| "loss": 0.5257, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 0.6493763611166106, | |
| "grad_norm": 1.5982388803586878, | |
| "learning_rate": 2.309526953037203e-06, | |
| "loss": 0.5193, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.6509602058998218, | |
| "grad_norm": 2.817392677546035, | |
| "learning_rate": 2.2909398311584775e-06, | |
| "loss": 0.4578, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.6525440506830331, | |
| "grad_norm": 1.581257330292036, | |
| "learning_rate": 2.272397744604636e-06, | |
| "loss": 0.5021, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.6541278954662443, | |
| "grad_norm": 1.6043151167776697, | |
| "learning_rate": 2.253901181976905e-06, | |
| "loss": 0.5405, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 0.6557117402494556, | |
| "grad_norm": 2.1291440852646817, | |
| "learning_rate": 2.2354506306769143e-06, | |
| "loss": 0.5301, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.6572955850326668, | |
| "grad_norm": 1.9230439043144794, | |
| "learning_rate": 2.2170465768938473e-06, | |
| "loss": 0.5709, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.658879429815878, | |
| "grad_norm": 1.472833355116063, | |
| "learning_rate": 2.1986895055916366e-06, | |
| "loss": 0.4326, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.6604632745990893, | |
| "grad_norm": 1.87905372939008, | |
| "learning_rate": 2.1803799004961824e-06, | |
| "loss": 0.462, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.6620471193823005, | |
| "grad_norm": 1.4366052509179692, | |
| "learning_rate": 2.1621182440826096e-06, | |
| "loss": 0.5735, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.6636309641655118, | |
| "grad_norm": 1.7279130546658286, | |
| "learning_rate": 2.143905017562547e-06, | |
| "loss": 0.408, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 0.665214808948723, | |
| "grad_norm": 1.536940380154465, | |
| "learning_rate": 2.12574070087145e-06, | |
| "loss": 0.5199, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.665214808948723, | |
| "eval_accuracy": 0.810934698088188, | |
| "eval_loss": 0.5862451195716858, | |
| "eval_perplexity": 1.2037860680935488, | |
| "eval_runtime": 531.3769, | |
| "eval_samples_per_second": 1.432, | |
| "eval_steps_per_second": 1.432, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.6667986537319343, | |
| "grad_norm": 1.565207882157784, | |
| "learning_rate": 2.10762577265596e-06, | |
| "loss": 0.4879, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 0.6683824985151455, | |
| "grad_norm": 1.4691468768515952, | |
| "learning_rate": 2.0895607102612803e-06, | |
| "loss": 0.5024, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 0.6699663432983568, | |
| "grad_norm": 1.3928452284838215, | |
| "learning_rate": 2.0715459897186044e-06, | |
| "loss": 0.5901, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 0.671550188081568, | |
| "grad_norm": 1.4610053346508791, | |
| "learning_rate": 2.0535820857325753e-06, | |
| "loss": 0.5062, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.6731340328647792, | |
| "grad_norm": 1.3712954252365843, | |
| "learning_rate": 2.0356694716687682e-06, | |
| "loss": 0.5479, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.6747178776479905, | |
| "grad_norm": 1.3758715850017582, | |
| "learning_rate": 2.017808619541221e-06, | |
| "loss": 0.4969, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.6763017224312018, | |
| "grad_norm": 1.2871110284961038, | |
| "learning_rate": 2.0000000000000008e-06, | |
| "loss": 0.4832, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 0.677885567214413, | |
| "grad_norm": 1.4668871631682787, | |
| "learning_rate": 1.982244082318793e-06, | |
| "loss": 0.4901, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.6794694119976242, | |
| "grad_norm": 1.515067727433541, | |
| "learning_rate": 1.9645413343825406e-06, | |
| "loss": 0.5362, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 0.6810532567808355, | |
| "grad_norm": 1.427224417336294, | |
| "learning_rate": 1.946892222675118e-06, | |
| "loss": 0.467, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.6826371015640468, | |
| "grad_norm": 1.3486800429336776, | |
| "learning_rate": 1.92929721226703e-06, | |
| "loss": 0.4614, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 0.6842209463472579, | |
| "grad_norm": 1.7205504786002677, | |
| "learning_rate": 1.9117567668031665e-06, | |
| "loss": 0.45, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.6858047911304692, | |
| "grad_norm": 1.6996871872002546, | |
| "learning_rate": 1.8942713484905761e-06, | |
| "loss": 0.5028, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 0.6873886359136805, | |
| "grad_norm": 1.5407143434367043, | |
| "learning_rate": 1.8768414180862956e-06, | |
| "loss": 0.5294, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.6889724806968917, | |
| "grad_norm": 1.3480994367623826, | |
| "learning_rate": 1.859467434885199e-06, | |
| "loss": 0.4558, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.6905563254801029, | |
| "grad_norm": 1.7334838280078013, | |
| "learning_rate": 1.8421498567079005e-06, | |
| "loss": 0.5249, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.6921401702633142, | |
| "grad_norm": 2.254316615478953, | |
| "learning_rate": 1.8248891398886936e-06, | |
| "loss": 0.6142, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 0.6937240150465255, | |
| "grad_norm": 1.5257795875613787, | |
| "learning_rate": 1.8076857392635176e-06, | |
| "loss": 0.4471, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.6953078598297366, | |
| "grad_norm": 1.700232100023801, | |
| "learning_rate": 1.7905401081579768e-06, | |
| "loss": 0.52, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 0.6968917046129479, | |
| "grad_norm": 1.33014022877584, | |
| "learning_rate": 1.7734526983753986e-06, | |
| "loss": 0.4591, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.6984755493961592, | |
| "grad_norm": 1.7591582976289475, | |
| "learning_rate": 1.7564239601849216e-06, | |
| "loss": 0.556, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.7000593941793705, | |
| "grad_norm": 1.5534876715610133, | |
| "learning_rate": 1.7394543423096325e-06, | |
| "loss": 0.4904, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 0.7016432389625816, | |
| "grad_norm": 1.4877228267210632, | |
| "learning_rate": 1.7225442919147465e-06, | |
| "loss": 0.5103, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 0.7032270837457929, | |
| "grad_norm": 1.4261700371364836, | |
| "learning_rate": 1.7056942545958167e-06, | |
| "loss": 0.4619, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.7048109285290042, | |
| "grad_norm": 1.5419799312577944, | |
| "learning_rate": 1.6889046743669955e-06, | |
| "loss": 0.5397, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.7063947733122155, | |
| "grad_norm": 1.6636001306308572, | |
| "learning_rate": 1.6721759936493398e-06, | |
| "loss": 0.5358, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 0.7079786180954266, | |
| "grad_norm": 1.5271438092360352, | |
| "learning_rate": 1.6555086532591425e-06, | |
| "loss": 0.4629, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 0.7095624628786379, | |
| "grad_norm": 1.6441451799989772, | |
| "learning_rate": 1.6389030923963221e-06, | |
| "loss": 0.4495, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.7111463076618492, | |
| "grad_norm": 1.5088562455266363, | |
| "learning_rate": 1.6223597486328533e-06, | |
| "loss": 0.4715, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 0.7127301524450604, | |
| "grad_norm": 1.4463031901473735, | |
| "learning_rate": 1.6058790579012275e-06, | |
| "loss": 0.5491, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.7143139972282716, | |
| "grad_norm": 1.471434921379099, | |
| "learning_rate": 1.5894614544829747e-06, | |
| "loss": 0.4864, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 0.7158978420114829, | |
| "grad_norm": 1.6603661388527584, | |
| "learning_rate": 1.5731073709972113e-06, | |
| "loss": 0.4506, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.7174816867946942, | |
| "grad_norm": 1.5613545052853812, | |
| "learning_rate": 1.5568172383892488e-06, | |
| "loss": 0.5735, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 0.7190655315779053, | |
| "grad_norm": 1.6697903304969928, | |
| "learning_rate": 1.54059148591923e-06, | |
| "loss": 0.539, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 0.7206493763611166, | |
| "grad_norm": 1.4866099563811799, | |
| "learning_rate": 1.5244305411508215e-06, | |
| "loss": 0.5165, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.7222332211443279, | |
| "grad_norm": 1.5688875196040748, | |
| "learning_rate": 1.5083348299399506e-06, | |
| "loss": 0.4431, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.7238170659275391, | |
| "grad_norm": 1.470987976048739, | |
| "learning_rate": 1.492304776423575e-06, | |
| "loss": 0.4692, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 0.7254009107107503, | |
| "grad_norm": 1.373015781073825, | |
| "learning_rate": 1.4763408030085112e-06, | |
| "loss": 0.4408, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 0.7269847554939616, | |
| "grad_norm": 1.7939617236990213, | |
| "learning_rate": 1.460443330360309e-06, | |
| "loss": 0.4836, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 0.7285686002771729, | |
| "grad_norm": 1.7961810685183246, | |
| "learning_rate": 1.4446127773921557e-06, | |
| "loss": 0.5373, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.7301524450603841, | |
| "grad_norm": 1.8372334481084611, | |
| "learning_rate": 1.4288495612538425e-06, | |
| "loss": 0.4675, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 0.7317362898435953, | |
| "grad_norm": 1.4460691785589137, | |
| "learning_rate": 1.413154097320778e-06, | |
| "loss": 0.4537, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.7333201346268066, | |
| "grad_norm": 1.54932404541608, | |
| "learning_rate": 1.3975267991830327e-06, | |
| "loss": 0.4473, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 0.7349039794100178, | |
| "grad_norm": 1.4531601052014125, | |
| "learning_rate": 1.3819680786344434e-06, | |
| "loss": 0.5499, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 0.7364878241932291, | |
| "grad_norm": 1.6713295832702009, | |
| "learning_rate": 1.3664783456617702e-06, | |
| "loss": 0.4369, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.7380716689764403, | |
| "grad_norm": 1.4987250866458606, | |
| "learning_rate": 1.3510580084338803e-06, | |
| "loss": 0.5176, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 0.7396555137596516, | |
| "grad_norm": 1.7331331058430652, | |
| "learning_rate": 1.3357074732909995e-06, | |
| "loss": 0.4903, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 0.7412393585428628, | |
| "grad_norm": 1.6659137598021865, | |
| "learning_rate": 1.320427144734008e-06, | |
| "loss": 0.4823, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.7428232033260741, | |
| "grad_norm": 1.5499926208087895, | |
| "learning_rate": 1.3052174254137712e-06, | |
| "loss": 0.3442, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.7444070481092853, | |
| "grad_norm": 1.92051205057408, | |
| "learning_rate": 1.2900787161205404e-06, | |
| "loss": 0.5399, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.7459908928924965, | |
| "grad_norm": 1.3472536176738465, | |
| "learning_rate": 1.2750114157733829e-06, | |
| "loss": 0.4111, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 0.7475747376757078, | |
| "grad_norm": 1.71412692276887, | |
| "learning_rate": 1.2600159214096775e-06, | |
| "loss": 0.5043, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 0.749158582458919, | |
| "grad_norm": 1.3640389981993508, | |
| "learning_rate": 1.2450926281746456e-06, | |
| "loss": 0.5684, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 0.7507424272421303, | |
| "grad_norm": 1.4068613006077029, | |
| "learning_rate": 1.2302419293109414e-06, | |
| "loss": 0.5849, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.7523262720253415, | |
| "grad_norm": 1.430129815588007, | |
| "learning_rate": 1.2154642161482937e-06, | |
| "loss": 0.5287, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.7539101168085528, | |
| "grad_norm": 1.2831468841594065, | |
| "learning_rate": 1.2007598780931863e-06, | |
| "loss": 0.4214, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.755493961591764, | |
| "grad_norm": 1.49905785043907, | |
| "learning_rate": 1.1861293026186006e-06, | |
| "loss": 0.4839, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 0.7570778063749752, | |
| "grad_norm": 1.7028591333085308, | |
| "learning_rate": 1.1715728752538101e-06, | |
| "loss": 0.5414, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 0.7586616511581865, | |
| "grad_norm": 1.4586336430125626, | |
| "learning_rate": 1.1570909795742116e-06, | |
| "loss": 0.4434, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 0.7602454959413978, | |
| "grad_norm": 1.5067616302391904, | |
| "learning_rate": 1.1426839971912236e-06, | |
| "loss": 0.4858, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.761829340724609, | |
| "grad_norm": 1.3432603589549863, | |
| "learning_rate": 1.1283523077422325e-06, | |
| "loss": 0.4768, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 0.7634131855078202, | |
| "grad_norm": 1.6178725773986766, | |
| "learning_rate": 1.1140962888805834e-06, | |
| "loss": 0.5535, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 0.7649970302910315, | |
| "grad_norm": 1.4689663997635967, | |
| "learning_rate": 1.0999163162656295e-06, | |
| "loss": 0.5227, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.7665808750742428, | |
| "grad_norm": 1.5383027461516126, | |
| "learning_rate": 1.0858127635528394e-06, | |
| "loss": 0.4011, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 0.7681647198574539, | |
| "grad_norm": 1.5160653262215487, | |
| "learning_rate": 1.0717860023839421e-06, | |
| "loss": 0.5865, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.7697485646406652, | |
| "grad_norm": 1.667492242744668, | |
| "learning_rate": 1.0578364023771382e-06, | |
| "loss": 0.5631, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.7713324094238765, | |
| "grad_norm": 1.5597231965693572, | |
| "learning_rate": 1.043964331117364e-06, | |
| "loss": 0.4257, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 0.7729162542070878, | |
| "grad_norm": 1.4809241793279104, | |
| "learning_rate": 1.0301701541465954e-06, | |
| "loss": 0.4555, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 0.7745000989902989, | |
| "grad_norm": 1.539628448856408, | |
| "learning_rate": 1.016454234954227e-06, | |
| "loss": 0.5371, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 0.7760839437735102, | |
| "grad_norm": 1.507321371340315, | |
| "learning_rate": 1.0028169349674827e-06, | |
| "loss": 0.43, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.7776677885567215, | |
| "grad_norm": 1.6940747096415172, | |
| "learning_rate": 9.892586135419021e-07, | |
| "loss": 0.531, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 0.7792516333399326, | |
| "grad_norm": 1.458267308736236, | |
| "learning_rate": 9.757796279518636e-07, | |
| "loss": 0.5206, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.7808354781231439, | |
| "grad_norm": 1.510680045767434, | |
| "learning_rate": 9.623803333811712e-07, | |
| "loss": 0.4083, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 0.7824193229063552, | |
| "grad_norm": 1.5237051298755062, | |
| "learning_rate": 9.490610829137007e-07, | |
| "loss": 0.4753, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 0.7840031676895665, | |
| "grad_norm": 1.9004733408315109, | |
| "learning_rate": 9.358222275240884e-07, | |
| "loss": 0.4432, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.7855870124727776, | |
| "grad_norm": 1.4568257328395944, | |
| "learning_rate": 9.226641160684842e-07, | |
| "loss": 0.5099, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 0.7871708572559889, | |
| "grad_norm": 1.7318874449726016, | |
| "learning_rate": 9.095870952753646e-07, | |
| "loss": 0.4351, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 0.7887547020392002, | |
| "grad_norm": 1.6137017147533719, | |
| "learning_rate": 8.965915097363881e-07, | |
| "loss": 0.5928, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 0.7903385468224114, | |
| "grad_norm": 1.5650409842133206, | |
| "learning_rate": 8.83677701897318e-07, | |
| "loss": 0.3981, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 0.7919223916056226, | |
| "grad_norm": 1.5782538718757142, | |
| "learning_rate": 8.708460120490037e-07, | |
| "loss": 0.5337, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7935062363888339, | |
| "grad_norm": 1.5981195947747417, | |
| "learning_rate": 8.580967783184055e-07, | |
| "loss": 0.5147, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 0.7950900811720452, | |
| "grad_norm": 1.5440200056277393, | |
| "learning_rate": 8.454303366596866e-07, | |
| "loss": 0.5308, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 0.7966739259552564, | |
| "grad_norm": 1.5571076654650473, | |
| "learning_rate": 8.328470208453682e-07, | |
| "loss": 0.4665, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 0.7982577707384676, | |
| "grad_norm": 1.4953480568816988, | |
| "learning_rate": 8.203471624575224e-07, | |
| "loss": 0.5417, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 0.7998416155216789, | |
| "grad_norm": 1.4524866840898938, | |
| "learning_rate": 8.079310908790419e-07, | |
| "loss": 0.4489, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.8014254603048901, | |
| "grad_norm": 2.045243169901501, | |
| "learning_rate": 7.955991332849623e-07, | |
| "loss": 0.6222, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 0.8030093050881013, | |
| "grad_norm": 1.4598656015711513, | |
| "learning_rate": 7.833516146338329e-07, | |
| "loss": 0.4226, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 0.8045931498713126, | |
| "grad_norm": 1.3467480479408616, | |
| "learning_rate": 7.711888576591618e-07, | |
| "loss": 0.4603, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 0.8061769946545239, | |
| "grad_norm": 1.5045994773603517, | |
| "learning_rate": 7.591111828609058e-07, | |
| "loss": 0.4625, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 0.8077608394377351, | |
| "grad_norm": 1.7584779249154874, | |
| "learning_rate": 7.471189084970291e-07, | |
| "loss": 0.4409, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.8093446842209463, | |
| "grad_norm": 1.4108080454193086, | |
| "learning_rate": 7.352123505751135e-07, | |
| "loss": 0.4703, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 0.8109285290041576, | |
| "grad_norm": 1.8380506141002417, | |
| "learning_rate": 7.233918228440323e-07, | |
| "loss": 0.449, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 0.8125123737873688, | |
| "grad_norm": 1.58792661941251, | |
| "learning_rate": 7.116576367856871e-07, | |
| "loss": 0.5837, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 0.8140962185705801, | |
| "grad_norm": 1.450768559703693, | |
| "learning_rate": 7.000101016067912e-07, | |
| "loss": 0.4332, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 0.8156800633537913, | |
| "grad_norm": 1.4028521815647677, | |
| "learning_rate": 6.884495242307284e-07, | |
| "loss": 0.4748, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.8172639081370026, | |
| "grad_norm": 1.6546175297694308, | |
| "learning_rate": 6.769762092894664e-07, | |
| "loss": 0.5074, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 0.8188477529202138, | |
| "grad_norm": 1.56576785928193, | |
| "learning_rate": 6.655904591155223e-07, | |
| "loss": 0.5381, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 0.8204315977034251, | |
| "grad_norm": 1.387565724939211, | |
| "learning_rate": 6.542925737340019e-07, | |
| "loss": 0.4561, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 0.8220154424866363, | |
| "grad_norm": 1.528956816316375, | |
| "learning_rate": 6.430828508546935e-07, | |
| "loss": 0.4937, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 0.8235992872698475, | |
| "grad_norm": 1.4223442587210688, | |
| "learning_rate": 6.319615858642193e-07, | |
| "loss": 0.5643, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.8251831320530588, | |
| "grad_norm": 1.6114797659220879, | |
| "learning_rate": 6.209290718182538e-07, | |
| "loss": 0.4748, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 0.8267669768362701, | |
| "grad_norm": 1.440732361602322, | |
| "learning_rate": 6.09985599433804e-07, | |
| "loss": 0.4529, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 0.8283508216194813, | |
| "grad_norm": 1.7456468155042586, | |
| "learning_rate": 5.99131457081544e-07, | |
| "loss": 0.4569, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 0.8299346664026925, | |
| "grad_norm": 1.5548170916399435, | |
| "learning_rate": 5.883669307782182e-07, | |
| "loss": 0.4917, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 0.8315185111859038, | |
| "grad_norm": 1.5325320661573854, | |
| "learning_rate": 5.776923041791076e-07, | |
| "loss": 0.4514, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.833102355969115, | |
| "grad_norm": 1.7221755053166576, | |
| "learning_rate": 5.671078585705489e-07, | |
| "loss": 0.5491, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 0.8346862007523262, | |
| "grad_norm": 1.3704260247894937, | |
| "learning_rate": 5.566138728625293e-07, | |
| "loss": 0.4455, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 0.8362700455355375, | |
| "grad_norm": 1.538307339121543, | |
| "learning_rate": 5.462106235813296e-07, | |
| "loss": 0.5443, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 0.8378538903187488, | |
| "grad_norm": 1.4697584276805509, | |
| "learning_rate": 5.358983848622451e-07, | |
| "loss": 0.4608, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 0.83943773510196, | |
| "grad_norm": 1.8369715460955707, | |
| "learning_rate": 5.256774284423561e-07, | |
| "loss": 0.5062, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.8410215798851712, | |
| "grad_norm": 1.4372888694581465, | |
| "learning_rate": 5.155480236533689e-07, | |
| "loss": 0.4203, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 0.8426054246683825, | |
| "grad_norm": 1.4932893467966832, | |
| "learning_rate": 5.055104374145221e-07, | |
| "loss": 0.4823, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 0.8441892694515938, | |
| "grad_norm": 1.4880388898611958, | |
| "learning_rate": 4.955649342255462e-07, | |
| "loss": 0.4552, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 0.845773114234805, | |
| "grad_norm": 1.6481037142268005, | |
| "learning_rate": 4.857117761596994e-07, | |
| "loss": 0.5839, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 0.8473569590180162, | |
| "grad_norm": 1.3437637677463443, | |
| "learning_rate": 4.759512228568621e-07, | |
| "loss": 0.4662, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.8489408038012275, | |
| "grad_norm": 1.4761647343726298, | |
| "learning_rate": 4.6628353151668995e-07, | |
| "loss": 0.568, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 0.8505246485844388, | |
| "grad_norm": 1.4720639230416912, | |
| "learning_rate": 4.567089568918403e-07, | |
| "loss": 0.5371, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 0.8521084933676499, | |
| "grad_norm": 1.5747841685012622, | |
| "learning_rate": 4.472277512812606e-07, | |
| "loss": 0.441, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 0.8536923381508612, | |
| "grad_norm": 1.650334451611286, | |
| "learning_rate": 4.378401645235352e-07, | |
| "loss": 0.5202, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 0.8552761829340725, | |
| "grad_norm": 1.5611475616764667, | |
| "learning_rate": 4.2854644399030526e-07, | |
| "loss": 0.4419, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.8568600277172838, | |
| "grad_norm": 1.4489741710945974, | |
| "learning_rate": 4.193468345797511e-07, | |
| "loss": 0.4335, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 0.8584438725004949, | |
| "grad_norm": 1.410090306645375, | |
| "learning_rate": 4.1024157871013586e-07, | |
| "loss": 0.5519, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 0.8600277172837062, | |
| "grad_norm": 2.1083504219892966, | |
| "learning_rate": 4.0123091631341933e-07, | |
| "loss": 0.5082, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 0.8616115620669175, | |
| "grad_norm": 1.513783834747692, | |
| "learning_rate": 3.9231508482893584e-07, | |
| "loss": 0.5122, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 0.8631954068501286, | |
| "grad_norm": 1.5251998914887834, | |
| "learning_rate": 3.834943191971365e-07, | |
| "loss": 0.4445, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.8647792516333399, | |
| "grad_norm": 1.5084805197178865, | |
| "learning_rate": 3.7476885185340023e-07, | |
| "loss": 0.5231, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 0.8663630964165512, | |
| "grad_norm": 1.6145093162288873, | |
| "learning_rate": 3.66138912721905e-07, | |
| "loss": 0.4943, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 0.8679469411997625, | |
| "grad_norm": 1.6928224805035605, | |
| "learning_rate": 3.5760472920957387e-07, | |
| "loss": 0.4923, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 0.8695307859829736, | |
| "grad_norm": 1.5962608727170904, | |
| "learning_rate": 3.491665262000789e-07, | |
| "loss": 0.4839, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 0.8711146307661849, | |
| "grad_norm": 1.606681077130113, | |
| "learning_rate": 3.4082452604791587e-07, | |
| "loss": 0.5515, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.8726984755493962, | |
| "grad_norm": 1.746327383134502, | |
| "learning_rate": 3.3257894857254877e-07, | |
| "loss": 0.4445, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 0.8742823203326074, | |
| "grad_norm": 1.6535392291397746, | |
| "learning_rate": 3.2443001105261127e-07, | |
| "loss": 0.3439, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 0.8758661651158186, | |
| "grad_norm": 1.5448042422189747, | |
| "learning_rate": 3.163779282201853e-07, | |
| "loss": 0.4854, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 0.8774500098990299, | |
| "grad_norm": 1.634766739227388, | |
| "learning_rate": 3.0842291225514314e-07, | |
| "loss": 0.4817, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 0.8790338546822412, | |
| "grad_norm": 1.7014309371471963, | |
| "learning_rate": 3.005651727795535e-07, | |
| "loss": 0.5209, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.8806176994654524, | |
| "grad_norm": 1.4990930673709706, | |
| "learning_rate": 2.9280491685215847e-07, | |
| "loss": 0.4922, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 0.8822015442486636, | |
| "grad_norm": 1.6902362872195928, | |
| "learning_rate": 2.85142348962919e-07, | |
| "loss": 0.5189, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 0.8837853890318749, | |
| "grad_norm": 1.5111021907783055, | |
| "learning_rate": 2.7757767102762587e-07, | |
| "loss": 0.5379, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 0.8853692338150861, | |
| "grad_norm": 1.4445290757135123, | |
| "learning_rate": 2.701110823825772e-07, | |
| "loss": 0.464, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 0.8869530785982974, | |
| "grad_norm": 1.4484298586379043, | |
| "learning_rate": 2.62742779779328e-07, | |
| "loss": 0.4532, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.8885369233815086, | |
| "grad_norm": 1.8044306708569506, | |
| "learning_rate": 2.5547295737950467e-07, | |
| "loss": 0.4846, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 0.8901207681647199, | |
| "grad_norm": 1.6320763637605389, | |
| "learning_rate": 2.483018067496885e-07, | |
| "loss": 0.4102, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 0.8917046129479311, | |
| "grad_norm": 1.513426697301029, | |
| "learning_rate": 2.412295168563667e-07, | |
| "loss": 0.3977, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 0.8932884577311423, | |
| "grad_norm": 1.739063565024179, | |
| "learning_rate": 2.3425627406095682e-07, | |
| "loss": 0.4883, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 0.8948723025143536, | |
| "grad_norm": 1.4344210490396612, | |
| "learning_rate": 2.273822621148902e-07, | |
| "loss": 0.523, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.8964561472975648, | |
| "grad_norm": 1.503570765479746, | |
| "learning_rate": 2.206076621547752e-07, | |
| "loss": 0.4387, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 0.8980399920807761, | |
| "grad_norm": 1.3957138101279774, | |
| "learning_rate": 2.1393265269762194e-07, | |
| "loss": 0.4629, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 0.8996238368639873, | |
| "grad_norm": 1.5135178225024162, | |
| "learning_rate": 2.0735740963613656e-07, | |
| "loss": 0.5019, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 0.9012076816471986, | |
| "grad_norm": 1.7552187868476394, | |
| "learning_rate": 2.0088210623408907e-07, | |
| "loss": 0.5353, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 0.9027915264304098, | |
| "grad_norm": 1.5773847982428775, | |
| "learning_rate": 1.9450691312174538e-07, | |
| "loss": 0.4794, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.9043753712136211, | |
| "grad_norm": 1.4347191250584008, | |
| "learning_rate": 1.8823199829137405e-07, | |
| "loss": 0.5398, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 0.9059592159968323, | |
| "grad_norm": 1.4568382476735973, | |
| "learning_rate": 1.8205752709281597e-07, | |
| "loss": 0.4439, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 0.9075430607800435, | |
| "grad_norm": 1.7936484686086873, | |
| "learning_rate": 1.759836622291293e-07, | |
| "loss": 0.4999, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 0.9091269055632548, | |
| "grad_norm": 1.5069741923698488, | |
| "learning_rate": 1.700105637523026e-07, | |
| "loss": 0.4889, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 0.9107107503464661, | |
| "grad_norm": 1.3815954432502042, | |
| "learning_rate": 1.6413838905903554e-07, | |
| "loss": 0.4927, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.9122945951296773, | |
| "grad_norm": 1.4408197785033354, | |
| "learning_rate": 1.58367292886592e-07, | |
| "loss": 0.4667, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 0.9138784399128885, | |
| "grad_norm": 1.5272866153375004, | |
| "learning_rate": 1.526974273087238e-07, | |
| "loss": 0.5076, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 0.9154622846960998, | |
| "grad_norm": 1.478729805351153, | |
| "learning_rate": 1.4712894173166192e-07, | |
| "loss": 0.461, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 0.9170461294793111, | |
| "grad_norm": 1.5805538071531569, | |
| "learning_rate": 1.416619828901795e-07, | |
| "loss": 0.5271, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 0.9186299742625222, | |
| "grad_norm": 1.5508552013902985, | |
| "learning_rate": 1.3629669484372718e-07, | |
| "loss": 0.5267, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.9202138190457335, | |
| "grad_norm": 1.8225403408379726, | |
| "learning_rate": 1.310332189726342e-07, | |
| "loss": 0.461, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 0.9217976638289448, | |
| "grad_norm": 1.4608984268403977, | |
| "learning_rate": 1.2587169397438425e-07, | |
| "loss": 0.4602, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 0.923381508612156, | |
| "grad_norm": 1.5279726414031836, | |
| "learning_rate": 1.2081225585996246e-07, | |
| "loss": 0.4588, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 0.9249653533953672, | |
| "grad_norm": 1.515611028063376, | |
| "learning_rate": 1.1585503795026718e-07, | |
| "loss": 0.5179, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 0.9265491981785785, | |
| "grad_norm": 1.5467139023737668, | |
| "learning_rate": 1.1100017087260205e-07, | |
| "loss": 0.5355, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.9281330429617898, | |
| "grad_norm": 1.4948762852593562, | |
| "learning_rate": 1.0624778255722855e-07, | |
| "loss": 0.4236, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 0.9297168877450009, | |
| "grad_norm": 1.7477468489012902, | |
| "learning_rate": 1.0159799823399939e-07, | |
| "loss": 0.4904, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 0.9313007325282122, | |
| "grad_norm": 1.5893000765049863, | |
| "learning_rate": 9.705094042905492e-08, | |
| "loss": 0.5515, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 0.9328845773114235, | |
| "grad_norm": 1.702578584367335, | |
| "learning_rate": 9.260672896159727e-08, | |
| "loss": 0.4751, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 0.9344684220946348, | |
| "grad_norm": 1.6463785462145422, | |
| "learning_rate": 8.826548094073194e-08, | |
| "loss": 0.4154, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.9360522668778459, | |
| "grad_norm": 1.3759922290335456, | |
| "learning_rate": 8.402731076238189e-08, | |
| "loss": 0.4738, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 0.9376361116610572, | |
| "grad_norm": 1.5640512221883043, | |
| "learning_rate": 7.989233010627261e-08, | |
| "loss": 0.416, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 0.9392199564442685, | |
| "grad_norm": 1.6313053854796913, | |
| "learning_rate": 7.586064793298997e-08, | |
| "loss": 0.4193, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 0.9408038012274798, | |
| "grad_norm": 1.7183629342589013, | |
| "learning_rate": 7.193237048110879e-08, | |
| "loss": 0.5383, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 0.9423876460106909, | |
| "grad_norm": 1.8057345431306828, | |
| "learning_rate": 6.810760126439285e-08, | |
| "loss": 0.4636, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.9439714907939022, | |
| "grad_norm": 1.581711206380294, | |
| "learning_rate": 6.438644106906866e-08, | |
| "loss": 0.4735, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 0.9455553355771135, | |
| "grad_norm": 2.0406365820491277, | |
| "learning_rate": 6.076898795116792e-08, | |
| "loss": 0.5349, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 0.9471391803603247, | |
| "grad_norm": 1.3665960620474567, | |
| "learning_rate": 5.7255337233944376e-08, | |
| "loss": 0.5118, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 0.9487230251435359, | |
| "grad_norm": 1.4545280151752455, | |
| "learning_rate": 5.3845581505362005e-08, | |
| "loss": 0.4706, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 0.9503068699267472, | |
| "grad_norm": 1.6568106629852815, | |
| "learning_rate": 5.05398106156556e-08, | |
| "loss": 0.4208, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.9518907147099585, | |
| "grad_norm": 1.3009128558987804, | |
| "learning_rate": 4.733811167496249e-08, | |
| "loss": 0.4618, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 0.9534745594931696, | |
| "grad_norm": 1.6350507056865986, | |
| "learning_rate": 4.4240569051027466e-08, | |
| "loss": 0.4818, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 0.9550584042763809, | |
| "grad_norm": 1.7692229180589922, | |
| "learning_rate": 4.124726436697878e-08, | |
| "loss": 0.4662, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 0.9566422490595922, | |
| "grad_norm": 1.4494075240429927, | |
| "learning_rate": 3.8358276499179664e-08, | |
| "loss": 0.6283, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 0.9582260938428034, | |
| "grad_norm": 1.5176956748111556, | |
| "learning_rate": 3.557368157514595e-08, | |
| "loss": 0.4618, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.9598099386260146, | |
| "grad_norm": 1.5615472024568975, | |
| "learning_rate": 3.2893552971545056e-08, | |
| "loss": 0.3706, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 0.9613937834092259, | |
| "grad_norm": 2.0109994652257055, | |
| "learning_rate": 3.031796131225706e-08, | |
| "loss": 0.4617, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 0.9629776281924372, | |
| "grad_norm": 1.6571285729822172, | |
| "learning_rate": 2.7846974466517957e-08, | |
| "loss": 0.4621, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 0.9645614729756484, | |
| "grad_norm": 1.9648211635566186, | |
| "learning_rate": 2.5480657547129135e-08, | |
| "loss": 0.5031, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 0.9661453177588596, | |
| "grad_norm": 1.3759221221620814, | |
| "learning_rate": 2.3219072908742253e-08, | |
| "loss": 0.4284, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.9677291625420709, | |
| "grad_norm": 1.5776287851272248, | |
| "learning_rate": 2.106228014621525e-08, | |
| "loss": 0.4965, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 0.9693130073252821, | |
| "grad_norm": 1.4564588215310144, | |
| "learning_rate": 1.901033609304381e-08, | |
| "loss": 0.5313, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 0.9708968521084934, | |
| "grad_norm": 1.4650178606419144, | |
| "learning_rate": 1.706329481986213e-08, | |
| "loss": 0.4695, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 0.9724806968917046, | |
| "grad_norm": 8.364306128275436, | |
| "learning_rate": 1.522120763301782e-08, | |
| "loss": 0.5742, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 0.9740645416749159, | |
| "grad_norm": 1.5436098149612576, | |
| "learning_rate": 1.348412307322233e-08, | |
| "loss": 0.4163, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.9756483864581271, | |
| "grad_norm": 1.4282895143928616, | |
| "learning_rate": 1.1852086914268423e-08, | |
| "loss": 0.5281, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 0.9772322312413384, | |
| "grad_norm": 1.2864356451763799, | |
| "learning_rate": 1.032514216182756e-08, | |
| "loss": 0.6423, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 0.9788160760245496, | |
| "grad_norm": 1.3530070123033577, | |
| "learning_rate": 8.903329052313502e-09, | |
| "loss": 0.4773, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 0.9803999208077608, | |
| "grad_norm": 1.4191474026879363, | |
| "learning_rate": 7.586685051823583e-09, | |
| "loss": 0.5286, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 0.9819837655909721, | |
| "grad_norm": 1.6895691048157127, | |
| "learning_rate": 6.375244855152839e-09, | |
| "loss": 0.5007, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.9835676103741833, | |
| "grad_norm": 1.414899383758995, | |
| "learning_rate": 5.269040384876078e-09, | |
| "loss": 0.4556, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 0.9851514551573946, | |
| "grad_norm": 1.8800481913954115, | |
| "learning_rate": 4.2681007905103206e-09, | |
| "loss": 0.5251, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 0.9867352999406058, | |
| "grad_norm": 1.3389313374375587, | |
| "learning_rate": 3.372452447744756e-09, | |
| "loss": 0.3714, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 0.9883191447238171, | |
| "grad_norm": 1.274196273086913, | |
| "learning_rate": 2.582118957745738e-09, | |
| "loss": 0.4538, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.9899029895070283, | |
| "grad_norm": 1.5641909121422626, | |
| "learning_rate": 1.8971211465363955e-09, | |
| "loss": 0.445, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.9914868342902395, | |
| "grad_norm": 1.431529316600778, | |
| "learning_rate": 1.31747706444596e-09, | |
| "loss": 0.4297, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 0.9930706790734508, | |
| "grad_norm": 1.3641264104243216, | |
| "learning_rate": 8.432019856345896e-10, | |
| "loss": 0.4418, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 0.9946545238566621, | |
| "grad_norm": 1.409407684955624, | |
| "learning_rate": 4.743084076923587e-10, | |
| "loss": 0.5325, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 0.9962383686398733, | |
| "grad_norm": 1.4066497217484986, | |
| "learning_rate": 2.108060513075216e-10, | |
| "loss": 0.4452, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 0.9978222134230845, | |
| "grad_norm": 1.5846124004550377, | |
| "learning_rate": 5.270186001249399e-11, | |
| "loss": 0.3571, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.9978222134230845, | |
| "eval_accuracy": 0.8122857271681789, | |
| "eval_loss": 0.5811628699302673, | |
| "eval_perplexity": 1.2019592776188088, | |
| "eval_runtime": 530.5565, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 1.434, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.9994060582062958, | |
| "grad_norm": 1.4491753654503536, | |
| "learning_rate": 0.0, | |
| "loss": 0.5137, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 0.9994060582062958, | |
| "step": 631, | |
| "total_flos": 132105476505600.0, | |
| "train_loss": 0.5424914620757669, | |
| "train_runtime": 50500.2662, | |
| "train_samples_per_second": 0.2, | |
| "train_steps_per_second": 0.012 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 631, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 132105476505600.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |