| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.6388500698742264, |
| "eval_steps": 500, |
| "global_step": 1600, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0019964064683569574, |
| "grad_norm": 12.8033447265625, |
| "learning_rate": 4.917142857142858e-06, |
| "loss": 0.8518, |
| "mean_token_accuracy": 0.8612988531589508, |
| "num_tokens": 714370.0, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.003992812936713915, |
| "grad_norm": 2.9046072959899902, |
| "learning_rate": 1.106357142857143e-05, |
| "loss": 0.3973, |
| "mean_token_accuracy": 0.9099577963352203, |
| "num_tokens": 1435512.0, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.005989219405070872, |
| "grad_norm": 0.9405294060707092, |
| "learning_rate": 1.7210000000000003e-05, |
| "loss": 0.163, |
| "mean_token_accuracy": 0.9522678524255752, |
| "num_tokens": 2137491.0, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.00798562587342783, |
| "grad_norm": 0.823198139667511, |
| "learning_rate": 2.3356428571428574e-05, |
| "loss": 0.088, |
| "mean_token_accuracy": 0.967251580953598, |
| "num_tokens": 2873053.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.009982032341784788, |
| "grad_norm": 0.5476183891296387, |
| "learning_rate": 2.950285714285715e-05, |
| "loss": 0.0762, |
| "mean_token_accuracy": 0.9689888685941697, |
| "num_tokens": 3597110.0, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.011978438810141745, |
| "grad_norm": 0.3753618001937866, |
| "learning_rate": 3.5649285714285724e-05, |
| "loss": 0.0748, |
| "mean_token_accuracy": 0.9682164311408996, |
| "num_tokens": 4317113.0, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.013974845278498703, |
| "grad_norm": 0.3772870600223541, |
| "learning_rate": 4.179571428571429e-05, |
| "loss": 0.0753, |
| "mean_token_accuracy": 0.9693712830543518, |
| "num_tokens": 5051360.0, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.01597125174685566, |
| "grad_norm": 0.4375256597995758, |
| "learning_rate": 4.302497723128185e-05, |
| "loss": 0.07, |
| "mean_token_accuracy": 0.9718590974807739, |
| "num_tokens": 5762813.0, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.017967658215212616, |
| "grad_norm": 0.31170469522476196, |
| "learning_rate": 4.302488473347447e-05, |
| "loss": 0.0701, |
| "mean_token_accuracy": 0.9706808269023895, |
| "num_tokens": 6478762.0, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.019964064683569576, |
| "grad_norm": 0.2859897017478943, |
| "learning_rate": 4.302472108394058e-05, |
| "loss": 0.0684, |
| "mean_token_accuracy": 0.972345557808876, |
| "num_tokens": 7204763.0, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.021960471151926533, |
| "grad_norm": 0.25486132502555847, |
| "learning_rate": 4.302448628340187e-05, |
| "loss": 0.064, |
| "mean_token_accuracy": 0.9740626871585846, |
| "num_tokens": 7925022.0, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.02395687762028349, |
| "grad_norm": 0.23721954226493835, |
| "learning_rate": 4.302418033289381e-05, |
| "loss": 0.0676, |
| "mean_token_accuracy": 0.9731216758489609, |
| "num_tokens": 8632030.0, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.025953284088640446, |
| "grad_norm": 0.26267364621162415, |
| "learning_rate": 4.302380323376563e-05, |
| "loss": 0.0626, |
| "mean_token_accuracy": 0.9742462456226348, |
| "num_tokens": 9364700.0, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.027949690556997406, |
| "grad_norm": 0.2607436776161194, |
| "learning_rate": 4.3023354987680335e-05, |
| "loss": 0.0603, |
| "mean_token_accuracy": 0.9749193072319031, |
| "num_tokens": 10097255.0, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.029946097025354362, |
| "grad_norm": 0.3435736298561096, |
| "learning_rate": 4.3022835596614676e-05, |
| "loss": 0.0634, |
| "mean_token_accuracy": 0.9741163223981857, |
| "num_tokens": 10823103.0, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.03194250349371132, |
| "grad_norm": 0.19693654775619507, |
| "learning_rate": 4.3022245062859155e-05, |
| "loss": 0.0623, |
| "mean_token_accuracy": 0.9742611676454545, |
| "num_tokens": 11548942.0, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.033938909962068275, |
| "grad_norm": 0.23240900039672852, |
| "learning_rate": 4.302158338901801e-05, |
| "loss": 0.0585, |
| "mean_token_accuracy": 0.9767142593860626, |
| "num_tokens": 12284271.0, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.03593531643042523, |
| "grad_norm": 0.35469600558280945, |
| "learning_rate": 4.302085057800922e-05, |
| "loss": 0.0605, |
| "mean_token_accuracy": 0.9750521361827851, |
| "num_tokens": 13007855.0, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.03793172289878219, |
| "grad_norm": 0.1484885960817337, |
| "learning_rate": 4.3020046633064446e-05, |
| "loss": 0.0484, |
| "mean_token_accuracy": 0.9796449035406113, |
| "num_tokens": 13722879.0, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.03992812936713915, |
| "grad_norm": 0.23631541430950165, |
| "learning_rate": 4.3019171557729085e-05, |
| "loss": 0.059, |
| "mean_token_accuracy": 0.9753597110509873, |
| "num_tokens": 14450221.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.04192453583549611, |
| "grad_norm": 0.17381513118743896, |
| "learning_rate": 4.301822535586219e-05, |
| "loss": 0.053, |
| "mean_token_accuracy": 0.979637861251831, |
| "num_tokens": 15193852.0, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.043920942303853065, |
| "grad_norm": 0.21713939309120178, |
| "learning_rate": 4.3017208031636505e-05, |
| "loss": 0.0521, |
| "mean_token_accuracy": 0.9779550462961197, |
| "num_tokens": 15920797.0, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.04591734877221002, |
| "grad_norm": 0.21581998467445374, |
| "learning_rate": 4.301611958953839e-05, |
| "loss": 0.0614, |
| "mean_token_accuracy": 0.9744587689638138, |
| "num_tokens": 16647447.0, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.04791375524056698, |
| "grad_norm": 0.19825442135334015, |
| "learning_rate": 4.301496003436785e-05, |
| "loss": 0.06, |
| "mean_token_accuracy": 0.9741028487682343, |
| "num_tokens": 17362711.0, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.049910161708923935, |
| "grad_norm": 0.15317484736442566, |
| "learning_rate": 4.301372937123851e-05, |
| "loss": 0.0571, |
| "mean_token_accuracy": 0.9771378487348557, |
| "num_tokens": 18088486.0, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.05190656817728089, |
| "grad_norm": 0.1307675838470459, |
| "learning_rate": 4.301242760557756e-05, |
| "loss": 0.0531, |
| "mean_token_accuracy": 0.9786365628242493, |
| "num_tokens": 18815433.0, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.053902974645637855, |
| "grad_norm": 0.1721351146697998, |
| "learning_rate": 4.301105474312576e-05, |
| "loss": 0.0642, |
| "mean_token_accuracy": 0.973665738105774, |
| "num_tokens": 19530903.0, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.05589938111399481, |
| "grad_norm": 0.2096928358078003, |
| "learning_rate": 4.30096107899374e-05, |
| "loss": 0.0548, |
| "mean_token_accuracy": 0.976664736866951, |
| "num_tokens": 20252280.0, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.05789578758235177, |
| "grad_norm": 0.13824060559272766, |
| "learning_rate": 4.3008095752380274e-05, |
| "loss": 0.0548, |
| "mean_token_accuracy": 0.9776088953018188, |
| "num_tokens": 20966598.0, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.059892194050708725, |
| "grad_norm": 0.1322195678949356, |
| "learning_rate": 4.3006509637135676e-05, |
| "loss": 0.0515, |
| "mean_token_accuracy": 0.9775060802698136, |
| "num_tokens": 21688849.0, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.06188860051906568, |
| "grad_norm": 0.15910562872886658, |
| "learning_rate": 4.3004852451198345e-05, |
| "loss": 0.0533, |
| "mean_token_accuracy": 0.9776766180992127, |
| "num_tokens": 22414160.0, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.06388500698742264, |
| "grad_norm": 0.17499415576457977, |
| "learning_rate": 4.300312420187642e-05, |
| "loss": 0.0543, |
| "mean_token_accuracy": 0.9780311793088913, |
| "num_tokens": 23140905.0, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.0658814134557796, |
| "grad_norm": 0.08447716385126114, |
| "learning_rate": 4.300132489679144e-05, |
| "loss": 0.0586, |
| "mean_token_accuracy": 0.9748361557722092, |
| "num_tokens": 23858350.0, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.06787781992413655, |
| "grad_norm": 0.1828007698059082, |
| "learning_rate": 4.299945454387832e-05, |
| "loss": 0.0582, |
| "mean_token_accuracy": 0.9753214448690415, |
| "num_tokens": 24578746.0, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.06987422639249351, |
| "grad_norm": 0.12954303622245789, |
| "learning_rate": 4.299751315138525e-05, |
| "loss": 0.0588, |
| "mean_token_accuracy": 0.9755947411060333, |
| "num_tokens": 25290190.0, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.07187063286085046, |
| "grad_norm": 0.17280645668506622, |
| "learning_rate": 4.299550072787375e-05, |
| "loss": 0.0522, |
| "mean_token_accuracy": 0.9782574236392975, |
| "num_tokens": 26013434.0, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.07386703932920742, |
| "grad_norm": 0.27445533871650696, |
| "learning_rate": 4.2993417282218544e-05, |
| "loss": 0.0536, |
| "mean_token_accuracy": 0.9775886803865432, |
| "num_tokens": 26742045.0, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.07586344579756438, |
| "grad_norm": 0.1881956309080124, |
| "learning_rate": 4.2991262823607586e-05, |
| "loss": 0.056, |
| "mean_token_accuracy": 0.976248922944069, |
| "num_tokens": 27466859.0, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.07785985226592135, |
| "grad_norm": 0.15925268828868866, |
| "learning_rate": 4.2989037361542e-05, |
| "loss": 0.0486, |
| "mean_token_accuracy": 0.9797779828310013, |
| "num_tokens": 28194806.0, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.0798562587342783, |
| "grad_norm": 0.2537769675254822, |
| "learning_rate": 4.2986740905836017e-05, |
| "loss": 0.0545, |
| "mean_token_accuracy": 0.9779761880636215, |
| "num_tokens": 28920879.0, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.08185266520263526, |
| "grad_norm": 0.18168781697750092, |
| "learning_rate": 4.298437346661695e-05, |
| "loss": 0.0516, |
| "mean_token_accuracy": 0.9782940000295639, |
| "num_tokens": 29652234.0, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.08384907167099222, |
| "grad_norm": 0.34930142760276794, |
| "learning_rate": 4.2981935054325175e-05, |
| "loss": 0.0528, |
| "mean_token_accuracy": 0.9776461899280549, |
| "num_tokens": 30368616.0, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.08584547813934917, |
| "grad_norm": 0.16720351576805115, |
| "learning_rate": 4.2979425679714015e-05, |
| "loss": 0.0545, |
| "mean_token_accuracy": 0.9776774793863297, |
| "num_tokens": 31086040.0, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.08784188460770613, |
| "grad_norm": 0.12502144277095795, |
| "learning_rate": 4.2976845353849757e-05, |
| "loss": 0.0578, |
| "mean_token_accuracy": 0.9754776805639267, |
| "num_tokens": 31814127.0, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.08983829107606309, |
| "grad_norm": 0.18173851072788239, |
| "learning_rate": 4.2974194088111596e-05, |
| "loss": 0.0549, |
| "mean_token_accuracy": 0.977699363231659, |
| "num_tokens": 32532899.0, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.09183469754442004, |
| "grad_norm": 0.21796411275863647, |
| "learning_rate": 4.297147189419153e-05, |
| "loss": 0.0526, |
| "mean_token_accuracy": 0.9780656516551971, |
| "num_tokens": 33254862.0, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.093831104012777, |
| "grad_norm": 0.158290296792984, |
| "learning_rate": 4.29686787840944e-05, |
| "loss": 0.0502, |
| "mean_token_accuracy": 0.9777401953935623, |
| "num_tokens": 33982840.0, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.09582751048113396, |
| "grad_norm": 0.15952068567276, |
| "learning_rate": 4.2965814770137744e-05, |
| "loss": 0.0502, |
| "mean_token_accuracy": 0.978219535946846, |
| "num_tokens": 34703620.0, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.09782391694949091, |
| "grad_norm": 0.1635027974843979, |
| "learning_rate": 4.2962879864951805e-05, |
| "loss": 0.0413, |
| "mean_token_accuracy": 0.982021626830101, |
| "num_tokens": 35440685.0, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.09982032341784787, |
| "grad_norm": 0.13409432768821716, |
| "learning_rate": 4.2959874081479444e-05, |
| "loss": 0.047, |
| "mean_token_accuracy": 0.9794367611408233, |
| "num_tokens": 36169768.0, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.10181672988620483, |
| "grad_norm": 0.11007480323314667, |
| "learning_rate": 4.295679743297611e-05, |
| "loss": 0.0473, |
| "mean_token_accuracy": 0.9799829065799713, |
| "num_tokens": 36903528.0, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.10381313635456178, |
| "grad_norm": 0.1296682208776474, |
| "learning_rate": 4.295364993300975e-05, |
| "loss": 0.0567, |
| "mean_token_accuracy": 0.9754694372415542, |
| "num_tokens": 37627586.0, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.10580954282291874, |
| "grad_norm": 0.12024891376495361, |
| "learning_rate": 4.295043159546076e-05, |
| "loss": 0.0535, |
| "mean_token_accuracy": 0.9779273867607117, |
| "num_tokens": 38352739.0, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.10780594929127571, |
| "grad_norm": 0.09559287130832672, |
| "learning_rate": 4.294714243452194e-05, |
| "loss": 0.0437, |
| "mean_token_accuracy": 0.9822638213634491, |
| "num_tokens": 39085149.0, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.10980235575963267, |
| "grad_norm": 0.19117465615272522, |
| "learning_rate": 4.2943782464698434e-05, |
| "loss": 0.0597, |
| "mean_token_accuracy": 0.975782060623169, |
| "num_tokens": 39805827.0, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.11179876222798962, |
| "grad_norm": 0.10707342624664307, |
| "learning_rate": 4.294035170080761e-05, |
| "loss": 0.0567, |
| "mean_token_accuracy": 0.9762091904878616, |
| "num_tokens": 40530685.0, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.11379516869634658, |
| "grad_norm": 0.08280737698078156, |
| "learning_rate": 4.2936850157979074e-05, |
| "loss": 0.05, |
| "mean_token_accuracy": 0.9792889416217804, |
| "num_tokens": 41255430.0, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.11579157516470354, |
| "grad_norm": 0.1256619095802307, |
| "learning_rate": 4.2933277851654543e-05, |
| "loss": 0.0624, |
| "mean_token_accuracy": 0.9729855686426163, |
| "num_tokens": 41976078.0, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.11778798163306049, |
| "grad_norm": 0.3224167227745056, |
| "learning_rate": 4.292963479758782e-05, |
| "loss": 0.0497, |
| "mean_token_accuracy": 0.9796846657991409, |
| "num_tokens": 42689118.0, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.11978438810141745, |
| "grad_norm": 0.22343389689922333, |
| "learning_rate": 4.292592101184469e-05, |
| "loss": 0.0425, |
| "mean_token_accuracy": 0.9820985406637192, |
| "num_tokens": 43419497.0, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.1217807945697744, |
| "grad_norm": 0.10838128626346588, |
| "learning_rate": 4.292213651080286e-05, |
| "loss": 0.0454, |
| "mean_token_accuracy": 0.9795959055423736, |
| "num_tokens": 44144729.0, |
| "step": 305 |
| }, |
| { |
| "epoch": 0.12377720103813136, |
| "grad_norm": 0.1953747570514679, |
| "learning_rate": 4.2918281311151895e-05, |
| "loss": 0.046, |
| "mean_token_accuracy": 0.9807391226291656, |
| "num_tokens": 44869333.0, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.12577360750648833, |
| "grad_norm": 0.14303229749202728, |
| "learning_rate": 4.291435542989315e-05, |
| "loss": 0.0477, |
| "mean_token_accuracy": 0.9790458828210831, |
| "num_tokens": 45601423.0, |
| "step": 315 |
| }, |
| { |
| "epoch": 0.12777001397484528, |
| "grad_norm": 0.13903263211250305, |
| "learning_rate": 4.291035888433965e-05, |
| "loss": 0.0486, |
| "mean_token_accuracy": 0.9791201978921891, |
| "num_tokens": 46331465.0, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.12976642044320225, |
| "grad_norm": 0.1759800761938095, |
| "learning_rate": 4.2906291692116105e-05, |
| "loss": 0.0544, |
| "mean_token_accuracy": 0.9773983508348465, |
| "num_tokens": 47056177.0, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.1317628269115592, |
| "grad_norm": 0.15405182540416718, |
| "learning_rate": 4.290215387115872e-05, |
| "loss": 0.0598, |
| "mean_token_accuracy": 0.9750259101390839, |
| "num_tokens": 47770978.0, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.13375923337991616, |
| "grad_norm": 0.10629483312368393, |
| "learning_rate": 4.28979454397152e-05, |
| "loss": 0.0583, |
| "mean_token_accuracy": 0.9750337392091751, |
| "num_tokens": 48484907.0, |
| "step": 335 |
| }, |
| { |
| "epoch": 0.1357556398482731, |
| "grad_norm": 0.11660145968198776, |
| "learning_rate": 4.2893666416344625e-05, |
| "loss": 0.0524, |
| "mean_token_accuracy": 0.9774013131856918, |
| "num_tokens": 49205502.0, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.13775204631663007, |
| "grad_norm": 0.1357419788837433, |
| "learning_rate": 4.288931681991741e-05, |
| "loss": 0.047, |
| "mean_token_accuracy": 0.9805745542049408, |
| "num_tokens": 49932020.0, |
| "step": 345 |
| }, |
| { |
| "epoch": 0.13974845278498702, |
| "grad_norm": 0.18027786910533905, |
| "learning_rate": 4.288489666961517e-05, |
| "loss": 0.0521, |
| "mean_token_accuracy": 0.9769169509410858, |
| "num_tokens": 50646806.0, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.14174485925334399, |
| "grad_norm": 0.09403052926063538, |
| "learning_rate": 4.288040598493066e-05, |
| "loss": 0.052, |
| "mean_token_accuracy": 0.9778335362672805, |
| "num_tokens": 51368374.0, |
| "step": 355 |
| }, |
| { |
| "epoch": 0.14374126572170093, |
| "grad_norm": 0.10531823337078094, |
| "learning_rate": 4.287584478566772e-05, |
| "loss": 0.0475, |
| "mean_token_accuracy": 0.9801982522010804, |
| "num_tokens": 52082189.0, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.1457376721900579, |
| "grad_norm": 0.08720994740724564, |
| "learning_rate": 4.2871213091941116e-05, |
| "loss": 0.0487, |
| "mean_token_accuracy": 0.9790406972169876, |
| "num_tokens": 52804371.0, |
| "step": 365 |
| }, |
| { |
| "epoch": 0.14773407865841484, |
| "grad_norm": 0.12209278345108032, |
| "learning_rate": 4.286651092417653e-05, |
| "loss": 0.0489, |
| "mean_token_accuracy": 0.9786169439554214, |
| "num_tokens": 53526886.0, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.1497304851267718, |
| "grad_norm": 0.1360856592655182, |
| "learning_rate": 4.286173830311041e-05, |
| "loss": 0.0551, |
| "mean_token_accuracy": 0.9743523508310318, |
| "num_tokens": 54238089.0, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.15172689159512875, |
| "grad_norm": 0.1499907374382019, |
| "learning_rate": 4.285689524978991e-05, |
| "loss": 0.0551, |
| "mean_token_accuracy": 0.9762009382247925, |
| "num_tokens": 54966900.0, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.15372329806348572, |
| "grad_norm": 0.06996061652898788, |
| "learning_rate": 4.285198178557278e-05, |
| "loss": 0.0442, |
| "mean_token_accuracy": 0.9815765887498855, |
| "num_tokens": 55692180.0, |
| "step": 385 |
| }, |
| { |
| "epoch": 0.1557197045318427, |
| "grad_norm": 0.09069187194108963, |
| "learning_rate": 4.284699793212731e-05, |
| "loss": 0.0521, |
| "mean_token_accuracy": 0.9776074826717377, |
| "num_tokens": 56403496.0, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.15771611100019964, |
| "grad_norm": 0.12922468781471252, |
| "learning_rate": 4.284194371143216e-05, |
| "loss": 0.0423, |
| "mean_token_accuracy": 0.9815239191055298, |
| "num_tokens": 57130425.0, |
| "step": 395 |
| }, |
| { |
| "epoch": 0.1597125174685566, |
| "grad_norm": 0.1596469283103943, |
| "learning_rate": 4.283681914577634e-05, |
| "loss": 0.0514, |
| "mean_token_accuracy": 0.9776736199855804, |
| "num_tokens": 57846781.0, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.16170892393691355, |
| "grad_norm": 0.1281159520149231, |
| "learning_rate": 4.283162425775907e-05, |
| "loss": 0.0475, |
| "mean_token_accuracy": 0.9804576992988586, |
| "num_tokens": 58576699.0, |
| "step": 405 |
| }, |
| { |
| "epoch": 0.16370533040527052, |
| "grad_norm": 0.18816827237606049, |
| "learning_rate": 4.282635907028968e-05, |
| "loss": 0.0491, |
| "mean_token_accuracy": 0.9774960219860077, |
| "num_tokens": 59299296.0, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.16570173687362746, |
| "grad_norm": 0.1441081166267395, |
| "learning_rate": 4.282102360658755e-05, |
| "loss": 0.05, |
| "mean_token_accuracy": 0.9789826661348343, |
| "num_tokens": 60019189.0, |
| "step": 415 |
| }, |
| { |
| "epoch": 0.16769814334198443, |
| "grad_norm": 0.11921107023954391, |
| "learning_rate": 4.2815617890181955e-05, |
| "loss": 0.0535, |
| "mean_token_accuracy": 0.9768732756376266, |
| "num_tokens": 60742418.0, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.16969454981034138, |
| "grad_norm": 0.14515455067157745, |
| "learning_rate": 4.281014194491196e-05, |
| "loss": 0.046, |
| "mean_token_accuracy": 0.9810800284147263, |
| "num_tokens": 61472413.0, |
| "step": 425 |
| }, |
| { |
| "epoch": 0.17169095627869835, |
| "grad_norm": 0.1529640555381775, |
| "learning_rate": 4.280459579492638e-05, |
| "loss": 0.0494, |
| "mean_token_accuracy": 0.9782395333051681, |
| "num_tokens": 62200026.0, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.1736873627470553, |
| "grad_norm": 0.1236916184425354, |
| "learning_rate": 4.279897946468361e-05, |
| "loss": 0.0505, |
| "mean_token_accuracy": 0.978915536403656, |
| "num_tokens": 62919468.0, |
| "step": 435 |
| }, |
| { |
| "epoch": 0.17568376921541226, |
| "grad_norm": 0.1317927986383438, |
| "learning_rate": 4.2793292978951546e-05, |
| "loss": 0.0434, |
| "mean_token_accuracy": 0.9814162343740463, |
| "num_tokens": 63654252.0, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.1776801756837692, |
| "grad_norm": 0.12080615013837814, |
| "learning_rate": 4.278753636280745e-05, |
| "loss": 0.0458, |
| "mean_token_accuracy": 0.9800752550363541, |
| "num_tokens": 64372681.0, |
| "step": 445 |
| }, |
| { |
| "epoch": 0.17967658215212617, |
| "grad_norm": 0.12699449062347412, |
| "learning_rate": 4.2781709641637895e-05, |
| "loss": 0.0557, |
| "mean_token_accuracy": 0.9758878946304321, |
| "num_tokens": 65084161.0, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.18167298862048312, |
| "grad_norm": 0.10154750943183899, |
| "learning_rate": 4.277581284113856e-05, |
| "loss": 0.0468, |
| "mean_token_accuracy": 0.9790953069925308, |
| "num_tokens": 65814662.0, |
| "step": 455 |
| }, |
| { |
| "epoch": 0.1836693950888401, |
| "grad_norm": 0.14240600168704987, |
| "learning_rate": 4.276984598731423e-05, |
| "loss": 0.0469, |
| "mean_token_accuracy": 0.979536834359169, |
| "num_tokens": 66530926.0, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.18566580155719706, |
| "grad_norm": 0.1021113321185112, |
| "learning_rate": 4.2763809106478584e-05, |
| "loss": 0.0425, |
| "mean_token_accuracy": 0.9820678532123566, |
| "num_tokens": 67265232.0, |
| "step": 465 |
| }, |
| { |
| "epoch": 0.187662208025554, |
| "grad_norm": 0.11665349453687668, |
| "learning_rate": 4.2757702225254146e-05, |
| "loss": 0.0566, |
| "mean_token_accuracy": 0.9761783987283706, |
| "num_tokens": 67983627.0, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.18965861449391097, |
| "grad_norm": 0.12766194343566895, |
| "learning_rate": 4.2751525370572104e-05, |
| "loss": 0.046, |
| "mean_token_accuracy": 0.9804826110601426, |
| "num_tokens": 68713941.0, |
| "step": 475 |
| }, |
| { |
| "epoch": 0.1916550209622679, |
| "grad_norm": 0.11255398392677307, |
| "learning_rate": 4.274527856967227e-05, |
| "loss": 0.0549, |
| "mean_token_accuracy": 0.9781402915716171, |
| "num_tokens": 69417633.0, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.19365142743062488, |
| "grad_norm": 0.08928117156028748, |
| "learning_rate": 4.273896185010289e-05, |
| "loss": 0.0509, |
| "mean_token_accuracy": 0.9780146718025208, |
| "num_tokens": 70130429.0, |
| "step": 485 |
| }, |
| { |
| "epoch": 0.19564783389898183, |
| "grad_norm": 0.13495980203151703, |
| "learning_rate": 4.273257523972056e-05, |
| "loss": 0.0451, |
| "mean_token_accuracy": 0.980745604634285, |
| "num_tokens": 70864111.0, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.1976442403673388, |
| "grad_norm": 0.14102225005626678, |
| "learning_rate": 4.2726118766690076e-05, |
| "loss": 0.05, |
| "mean_token_accuracy": 0.979128223657608, |
| "num_tokens": 71589024.0, |
| "step": 495 |
| }, |
| { |
| "epoch": 0.19964064683569574, |
| "grad_norm": 0.12552976608276367, |
| "learning_rate": 4.271959245948436e-05, |
| "loss": 0.0514, |
| "mean_token_accuracy": 0.9778478264808654, |
| "num_tokens": 72306095.0, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.2016370533040527, |
| "grad_norm": 0.11777975410223007, |
| "learning_rate": 4.271299634688427e-05, |
| "loss": 0.0433, |
| "mean_token_accuracy": 0.9815191090106964, |
| "num_tokens": 73021001.0, |
| "step": 505 |
| }, |
| { |
| "epoch": 0.20363345977240965, |
| "grad_norm": 0.13376499712467194, |
| "learning_rate": 4.2706330457978514e-05, |
| "loss": 0.0503, |
| "mean_token_accuracy": 0.9786869913339615, |
| "num_tokens": 73750995.0, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.20562986624076662, |
| "grad_norm": 0.10142122209072113, |
| "learning_rate": 4.269959482216352e-05, |
| "loss": 0.0455, |
| "mean_token_accuracy": 0.9812999993562699, |
| "num_tokens": 74474430.0, |
| "step": 515 |
| }, |
| { |
| "epoch": 0.20762627270912357, |
| "grad_norm": 0.1251404732465744, |
| "learning_rate": 4.26927894691433e-05, |
| "loss": 0.0433, |
| "mean_token_accuracy": 0.9818032503128051, |
| "num_tokens": 75193736.0, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.20962267917748054, |
| "grad_norm": 0.09525765478610992, |
| "learning_rate": 4.268591442892929e-05, |
| "loss": 0.0467, |
| "mean_token_accuracy": 0.9807555198669433, |
| "num_tokens": 75927216.0, |
| "step": 525 |
| }, |
| { |
| "epoch": 0.21161908564583748, |
| "grad_norm": 0.09515196830034256, |
| "learning_rate": 4.267896973184027e-05, |
| "loss": 0.0447, |
| "mean_token_accuracy": 0.9803880721330642, |
| "num_tokens": 76655961.0, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.21361549211419445, |
| "grad_norm": 0.09553889185190201, |
| "learning_rate": 4.267195540850221e-05, |
| "loss": 0.0505, |
| "mean_token_accuracy": 0.9782146096229554, |
| "num_tokens": 77379698.0, |
| "step": 535 |
| }, |
| { |
| "epoch": 0.21561189858255142, |
| "grad_norm": 0.09350269287824631, |
| "learning_rate": 4.266487148984811e-05, |
| "loss": 0.047, |
| "mean_token_accuracy": 0.9799423426389694, |
| "num_tokens": 78096171.0, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.21760830505090836, |
| "grad_norm": 0.12444101274013519, |
| "learning_rate": 4.26577180071179e-05, |
| "loss": 0.0503, |
| "mean_token_accuracy": 0.9797710835933685, |
| "num_tokens": 78816545.0, |
| "step": 545 |
| }, |
| { |
| "epoch": 0.21960471151926533, |
| "grad_norm": 0.120224229991436, |
| "learning_rate": 4.265049499185827e-05, |
| "loss": 0.0476, |
| "mean_token_accuracy": 0.9791944712400437, |
| "num_tokens": 79543200.0, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.22160111798762228, |
| "grad_norm": 0.08200144022703171, |
| "learning_rate": 4.2643202475922576e-05, |
| "loss": 0.0469, |
| "mean_token_accuracy": 0.9800705790519715, |
| "num_tokens": 80267808.0, |
| "step": 555 |
| }, |
| { |
| "epoch": 0.22359752445597925, |
| "grad_norm": 0.08492100983858109, |
| "learning_rate": 4.263584049147063e-05, |
| "loss": 0.053, |
| "mean_token_accuracy": 0.9771294265985488, |
| "num_tokens": 80995420.0, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.2255939309243362, |
| "grad_norm": 0.12120378762483597, |
| "learning_rate": 4.2628409070968626e-05, |
| "loss": 0.047, |
| "mean_token_accuracy": 0.9804543852806091, |
| "num_tokens": 81723889.0, |
| "step": 565 |
| }, |
| { |
| "epoch": 0.22759033739269316, |
| "grad_norm": 0.10692359507083893, |
| "learning_rate": 4.2620908247188973e-05, |
| "loss": 0.0373, |
| "mean_token_accuracy": 0.9842275649309158, |
| "num_tokens": 82455710.0, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.2295867438610501, |
| "grad_norm": 0.12830841541290283, |
| "learning_rate": 4.261333805321012e-05, |
| "loss": 0.0485, |
| "mean_token_accuracy": 0.9796034336090088, |
| "num_tokens": 83167210.0, |
| "step": 575 |
| }, |
| { |
| "epoch": 0.23158315032940707, |
| "grad_norm": 0.08063813298940659, |
| "learning_rate": 4.260569852241647e-05, |
| "loss": 0.0534, |
| "mean_token_accuracy": 0.9783318549394607, |
| "num_tokens": 83881816.0, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.23357955679776402, |
| "grad_norm": 0.09200415760278702, |
| "learning_rate": 4.259798968849818e-05, |
| "loss": 0.0475, |
| "mean_token_accuracy": 0.980060550570488, |
| "num_tokens": 84607610.0, |
| "step": 585 |
| }, |
| { |
| "epoch": 0.23557596326612099, |
| "grad_norm": 0.09657726436853409, |
| "learning_rate": 4.259021158545102e-05, |
| "loss": 0.0534, |
| "mean_token_accuracy": 0.9768508076667786, |
| "num_tokens": 85315518.0, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.23757236973447793, |
| "grad_norm": 0.09629404544830322, |
| "learning_rate": 4.2582364247576274e-05, |
| "loss": 0.0508, |
| "mean_token_accuracy": 0.9782411873340606, |
| "num_tokens": 86038324.0, |
| "step": 595 |
| }, |
| { |
| "epoch": 0.2395687762028349, |
| "grad_norm": 0.12929849326610565, |
| "learning_rate": 4.257444770948052e-05, |
| "loss": 0.0406, |
| "mean_token_accuracy": 0.9815934479236603, |
| "num_tokens": 86774837.0, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.24156518267119184, |
| "grad_norm": 0.10552412271499634, |
| "learning_rate": 4.256646200607551e-05, |
| "loss": 0.0533, |
| "mean_token_accuracy": 0.9769379138946533, |
| "num_tokens": 87493367.0, |
| "step": 605 |
| }, |
| { |
| "epoch": 0.2435615891395488, |
| "grad_norm": 0.10751223564147949, |
| "learning_rate": 4.255840717257802e-05, |
| "loss": 0.0475, |
| "mean_token_accuracy": 0.9801900714635849, |
| "num_tokens": 88212585.0, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.24555799560790578, |
| "grad_norm": 0.08181528747081757, |
| "learning_rate": 4.255028324450969e-05, |
| "loss": 0.0483, |
| "mean_token_accuracy": 0.9792672157287597, |
| "num_tokens": 88921923.0, |
| "step": 615 |
| }, |
| { |
| "epoch": 0.24755440207626273, |
| "grad_norm": 0.11906848847866058, |
| "learning_rate": 4.254209025769686e-05, |
| "loss": 0.0531, |
| "mean_token_accuracy": 0.9773639112710952, |
| "num_tokens": 89635881.0, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.2495508085446197, |
| "grad_norm": 0.09037422388792038, |
| "learning_rate": 4.253382824827042e-05, |
| "loss": 0.0494, |
| "mean_token_accuracy": 0.978655782341957, |
| "num_tokens": 90355134.0, |
| "step": 625 |
| }, |
| { |
| "epoch": 0.25154721501297667, |
| "grad_norm": 0.10041050612926483, |
| "learning_rate": 4.252549725266565e-05, |
| "loss": 0.0511, |
| "mean_token_accuracy": 0.9785868495702743, |
| "num_tokens": 91079403.0, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.2535436214813336, |
| "grad_norm": 0.10690242052078247, |
| "learning_rate": 4.251709730762204e-05, |
| "loss": 0.0475, |
| "mean_token_accuracy": 0.9794499009847641, |
| "num_tokens": 91799983.0, |
| "step": 635 |
| }, |
| { |
| "epoch": 0.25554002794969055, |
| "grad_norm": 0.08654764294624329, |
| "learning_rate": 4.250862845018319e-05, |
| "loss": 0.0548, |
| "mean_token_accuracy": 0.9768476873636246, |
| "num_tokens": 92520960.0, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.2575364344180475, |
| "grad_norm": 0.08682254701852798, |
| "learning_rate": 4.250009071769655e-05, |
| "loss": 0.043, |
| "mean_token_accuracy": 0.9821657538414001, |
| "num_tokens": 93247191.0, |
| "step": 645 |
| }, |
| { |
| "epoch": 0.2595328408864045, |
| "grad_norm": 0.1060463935136795, |
| "learning_rate": 4.2491484147813335e-05, |
| "loss": 0.0539, |
| "mean_token_accuracy": 0.9773279428482056, |
| "num_tokens": 93959062.0, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.2615292473547614, |
| "grad_norm": 0.12649336457252502, |
| "learning_rate": 4.2482808778488325e-05, |
| "loss": 0.0497, |
| "mean_token_accuracy": 0.978519856929779, |
| "num_tokens": 94685020.0, |
| "step": 655 |
| }, |
| { |
| "epoch": 0.2635256538231184, |
| "grad_norm": 0.09485338628292084, |
| "learning_rate": 4.247406464797971e-05, |
| "loss": 0.0415, |
| "mean_token_accuracy": 0.9826800882816314, |
| "num_tokens": 95415113.0, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.26552206029147535, |
| "grad_norm": 0.15739619731903076, |
| "learning_rate": 4.2465251794848915e-05, |
| "loss": 0.0461, |
| "mean_token_accuracy": 0.9801017135381699, |
| "num_tokens": 96135551.0, |
| "step": 665 |
| }, |
| { |
| "epoch": 0.2675184667598323, |
| "grad_norm": 0.07750169187784195, |
| "learning_rate": 4.245637025796042e-05, |
| "loss": 0.051, |
| "mean_token_accuracy": 0.9799440085887909, |
| "num_tokens": 96865552.0, |
| "step": 670 |
| }, |
| { |
| "epoch": 0.26951487322818923, |
| "grad_norm": 0.09401772171258926, |
| "learning_rate": 4.2447420076481604e-05, |
| "loss": 0.0466, |
| "mean_token_accuracy": 0.980428883433342, |
| "num_tokens": 97601834.0, |
| "step": 675 |
| }, |
| { |
| "epoch": 0.2715112796965462, |
| "grad_norm": 0.09588310122489929, |
| "learning_rate": 4.243840128988257e-05, |
| "loss": 0.0501, |
| "mean_token_accuracy": 0.979182380437851, |
| "num_tokens": 98332558.0, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.2735076861649032, |
| "grad_norm": 0.09605035930871964, |
| "learning_rate": 4.2429313937935974e-05, |
| "loss": 0.0411, |
| "mean_token_accuracy": 0.9825141876935959, |
| "num_tokens": 99053033.0, |
| "step": 685 |
| }, |
| { |
| "epoch": 0.27550409263326014, |
| "grad_norm": 0.11407220363616943, |
| "learning_rate": 4.242015806071682e-05, |
| "loss": 0.0514, |
| "mean_token_accuracy": 0.977407693862915, |
| "num_tokens": 99777487.0, |
| "step": 690 |
| }, |
| { |
| "epoch": 0.2775004991016171, |
| "grad_norm": 0.10052948445081711, |
| "learning_rate": 4.241093369860234e-05, |
| "loss": 0.046, |
| "mean_token_accuracy": 0.9803170651197434, |
| "num_tokens": 100498662.0, |
| "step": 695 |
| }, |
| { |
| "epoch": 0.27949690556997403, |
| "grad_norm": 0.08085839450359344, |
| "learning_rate": 4.240164089227176e-05, |
| "loss": 0.0439, |
| "mean_token_accuracy": 0.9825191229581833, |
| "num_tokens": 101232839.0, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.281493312038331, |
| "grad_norm": 0.08980093151330948, |
| "learning_rate": 4.2392279682706136e-05, |
| "loss": 0.051, |
| "mean_token_accuracy": 0.9787484467029571, |
| "num_tokens": 101948467.0, |
| "step": 705 |
| }, |
| { |
| "epoch": 0.28348971850668797, |
| "grad_norm": 0.19071196019649506, |
| "learning_rate": 4.2382850111188206e-05, |
| "loss": 0.0496, |
| "mean_token_accuracy": 0.9789243370294571, |
| "num_tokens": 102662104.0, |
| "step": 710 |
| }, |
| { |
| "epoch": 0.28548612497504494, |
| "grad_norm": 0.13858772814273834, |
| "learning_rate": 4.237335221930217e-05, |
| "loss": 0.084, |
| "mean_token_accuracy": 0.9728131413459777, |
| "num_tokens": 103381345.0, |
| "step": 715 |
| }, |
| { |
| "epoch": 0.28748253144340186, |
| "grad_norm": 4.443481922149658, |
| "learning_rate": 4.2363786048933525e-05, |
| "loss": 0.1013, |
| "mean_token_accuracy": 0.9748282253742218, |
| "num_tokens": 104104350.0, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.2894789379117588, |
| "grad_norm": 0.45772096514701843, |
| "learning_rate": 4.2354151642268866e-05, |
| "loss": 0.103, |
| "mean_token_accuracy": 0.970191091299057, |
| "num_tokens": 104827954.0, |
| "step": 725 |
| }, |
| { |
| "epoch": 0.2914753443801158, |
| "grad_norm": 0.15262044966220856, |
| "learning_rate": 4.234444904179569e-05, |
| "loss": 0.0504, |
| "mean_token_accuracy": 0.9785544484853744, |
| "num_tokens": 105554646.0, |
| "step": 730 |
| }, |
| { |
| "epoch": 0.29347175084847277, |
| "grad_norm": 0.118346206843853, |
| "learning_rate": 4.233467829030229e-05, |
| "loss": 0.0502, |
| "mean_token_accuracy": 0.979259392619133, |
| "num_tokens": 106267067.0, |
| "step": 735 |
| }, |
| { |
| "epoch": 0.2954681573168297, |
| "grad_norm": 0.36983075737953186, |
| "learning_rate": 4.232483943087743e-05, |
| "loss": 0.0508, |
| "mean_token_accuracy": 0.9795638442039489, |
| "num_tokens": 107005215.0, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.29746456378518665, |
| "grad_norm": 0.09854412823915482, |
| "learning_rate": 4.231493250691028e-05, |
| "loss": 0.0544, |
| "mean_token_accuracy": 0.9789934754371643, |
| "num_tokens": 107731301.0, |
| "step": 745 |
| }, |
| { |
| "epoch": 0.2994609702535436, |
| "grad_norm": 0.12738491594791412, |
| "learning_rate": 4.230495756209015e-05, |
| "loss": 0.0506, |
| "mean_token_accuracy": 0.979388102889061, |
| "num_tokens": 108450353.0, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.3014573767219006, |
| "grad_norm": 0.15874311327934265, |
| "learning_rate": 4.229491464040631e-05, |
| "loss": 0.0465, |
| "mean_token_accuracy": 0.9797900915145874, |
| "num_tokens": 109180817.0, |
| "step": 755 |
| }, |
| { |
| "epoch": 0.3034537831902575, |
| "grad_norm": 0.11495564132928848, |
| "learning_rate": 4.228480378614784e-05, |
| "loss": 0.0487, |
| "mean_token_accuracy": 0.9790915966033935, |
| "num_tokens": 109903855.0, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.3054501896586145, |
| "grad_norm": 0.10626127570867538, |
| "learning_rate": 4.227462504390338e-05, |
| "loss": 0.0508, |
| "mean_token_accuracy": 0.978978967666626, |
| "num_tokens": 110631560.0, |
| "step": 765 |
| }, |
| { |
| "epoch": 0.30744659612697145, |
| "grad_norm": 0.14091414213180542, |
| "learning_rate": 4.2264378458560945e-05, |
| "loss": 0.0496, |
| "mean_token_accuracy": 0.9777703315019608, |
| "num_tokens": 111349333.0, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.3094430025953284, |
| "grad_norm": 0.14497868716716766, |
| "learning_rate": 4.225406407530776e-05, |
| "loss": 0.0535, |
| "mean_token_accuracy": 0.9772404164075852, |
| "num_tokens": 112073813.0, |
| "step": 775 |
| }, |
| { |
| "epoch": 0.3114394090636854, |
| "grad_norm": 0.08627774566411972, |
| "learning_rate": 4.224368193963002e-05, |
| "loss": 0.0486, |
| "mean_token_accuracy": 0.9789620161056518, |
| "num_tokens": 112785897.0, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.3134358155320423, |
| "grad_norm": 0.09868915379047394, |
| "learning_rate": 4.223323209731272e-05, |
| "loss": 0.046, |
| "mean_token_accuracy": 0.9802429288625717, |
| "num_tokens": 113516646.0, |
| "step": 785 |
| }, |
| { |
| "epoch": 0.3154322220003993, |
| "grad_norm": 0.12950965762138367, |
| "learning_rate": 4.222271459443941e-05, |
| "loss": 0.0578, |
| "mean_token_accuracy": 0.9762585014104843, |
| "num_tokens": 114227110.0, |
| "step": 790 |
| }, |
| { |
| "epoch": 0.31742862846875625, |
| "grad_norm": 0.12167847901582718, |
| "learning_rate": 4.221212947739207e-05, |
| "loss": 0.0487, |
| "mean_token_accuracy": 0.9791981846094131, |
| "num_tokens": 114939687.0, |
| "step": 795 |
| }, |
| { |
| "epoch": 0.3194250349371132, |
| "grad_norm": 0.07483931630849838, |
| "learning_rate": 4.2201476792850825e-05, |
| "loss": 0.0449, |
| "mean_token_accuracy": 0.9802095115184783, |
| "num_tokens": 115657868.0, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.32142144140547013, |
| "grad_norm": 0.11723718047142029, |
| "learning_rate": 4.2190756587793766e-05, |
| "loss": 0.0451, |
| "mean_token_accuracy": 0.9806903630495072, |
| "num_tokens": 116383524.0, |
| "step": 805 |
| }, |
| { |
| "epoch": 0.3234178478738271, |
| "grad_norm": 0.0941113531589508, |
| "learning_rate": 4.217996890949677e-05, |
| "loss": 0.0417, |
| "mean_token_accuracy": 0.9814288556575775, |
| "num_tokens": 117097427.0, |
| "step": 810 |
| }, |
| { |
| "epoch": 0.3254142543421841, |
| "grad_norm": 0.08885961025953293, |
| "learning_rate": 4.216911380553325e-05, |
| "loss": 0.0482, |
| "mean_token_accuracy": 0.9794678062200546, |
| "num_tokens": 117814344.0, |
| "step": 815 |
| }, |
| { |
| "epoch": 0.32741066081054104, |
| "grad_norm": 0.08935556560754776, |
| "learning_rate": 4.2158191323773974e-05, |
| "loss": 0.0489, |
| "mean_token_accuracy": 0.9792770773172379, |
| "num_tokens": 118527584.0, |
| "step": 820 |
| }, |
| { |
| "epoch": 0.32940706727889796, |
| "grad_norm": 0.10772611200809479, |
| "learning_rate": 4.214720151238686e-05, |
| "loss": 0.0487, |
| "mean_token_accuracy": 0.9791043639183045, |
| "num_tokens": 119252755.0, |
| "step": 825 |
| }, |
| { |
| "epoch": 0.33140347374725493, |
| "grad_norm": 0.0967428907752037, |
| "learning_rate": 4.21361444198367e-05, |
| "loss": 0.048, |
| "mean_token_accuracy": 0.9792734861373902, |
| "num_tokens": 119986842.0, |
| "step": 830 |
| }, |
| { |
| "epoch": 0.3333998802156119, |
| "grad_norm": 0.06611617654561996, |
| "learning_rate": 4.212502009488505e-05, |
| "loss": 0.0413, |
| "mean_token_accuracy": 0.9816345155239106, |
| "num_tokens": 120729067.0, |
| "step": 835 |
| }, |
| { |
| "epoch": 0.33539628668396887, |
| "grad_norm": 0.07611052691936493, |
| "learning_rate": 4.211382858658993e-05, |
| "loss": 0.0448, |
| "mean_token_accuracy": 0.9809937328100204, |
| "num_tokens": 121455408.0, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.33739269315232584, |
| "grad_norm": 0.09330687671899796, |
| "learning_rate": 4.210256994430565e-05, |
| "loss": 0.046, |
| "mean_token_accuracy": 0.9798675775527954, |
| "num_tokens": 122187578.0, |
| "step": 845 |
| }, |
| { |
| "epoch": 0.33938909962068275, |
| "grad_norm": 0.08592524379491806, |
| "learning_rate": 4.209124421768255e-05, |
| "loss": 0.0462, |
| "mean_token_accuracy": 0.9799050241708755, |
| "num_tokens": 122915846.0, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.3413855060890397, |
| "grad_norm": 0.08495519310235977, |
| "learning_rate": 4.207985145666686e-05, |
| "loss": 0.0514, |
| "mean_token_accuracy": 0.9777328252792359, |
| "num_tokens": 123631558.0, |
| "step": 855 |
| }, |
| { |
| "epoch": 0.3433819125573967, |
| "grad_norm": 0.08593793958425522, |
| "learning_rate": 4.206839171150038e-05, |
| "loss": 0.051, |
| "mean_token_accuracy": 0.9783249199390411, |
| "num_tokens": 124349450.0, |
| "step": 860 |
| }, |
| { |
| "epoch": 0.34537831902575367, |
| "grad_norm": 0.1147531196475029, |
| "learning_rate": 4.2056865032720345e-05, |
| "loss": 0.0466, |
| "mean_token_accuracy": 0.9806852877140045, |
| "num_tokens": 125074783.0, |
| "step": 865 |
| }, |
| { |
| "epoch": 0.3473747254941106, |
| "grad_norm": 0.12205598503351212, |
| "learning_rate": 4.2045271471159146e-05, |
| "loss": 0.0512, |
| "mean_token_accuracy": 0.9779225885868073, |
| "num_tokens": 125790435.0, |
| "step": 870 |
| }, |
| { |
| "epoch": 0.34937113196246755, |
| "grad_norm": 0.08975517749786377, |
| "learning_rate": 4.2033611077944135e-05, |
| "loss": 0.0385, |
| "mean_token_accuracy": 0.9832260310649872, |
| "num_tokens": 126520091.0, |
| "step": 875 |
| }, |
| { |
| "epoch": 0.3513675384308245, |
| "grad_norm": 0.08298907428979874, |
| "learning_rate": 4.202188390449738e-05, |
| "loss": 0.0422, |
| "mean_token_accuracy": 0.9818367391824723, |
| "num_tokens": 127243561.0, |
| "step": 880 |
| }, |
| { |
| "epoch": 0.3533639448991815, |
| "grad_norm": 0.08749652653932571, |
| "learning_rate": 4.2010090002535467e-05, |
| "loss": 0.0431, |
| "mean_token_accuracy": 0.9816054284572602, |
| "num_tokens": 127979804.0, |
| "step": 885 |
| }, |
| { |
| "epoch": 0.3553603513675384, |
| "grad_norm": 0.10358402132987976, |
| "learning_rate": 4.199822942406923e-05, |
| "loss": 0.058, |
| "mean_token_accuracy": 0.9758305728435517, |
| "num_tokens": 128699074.0, |
| "step": 890 |
| }, |
| { |
| "epoch": 0.3573567578358954, |
| "grad_norm": 0.11131475865840912, |
| "learning_rate": 4.198630222140356e-05, |
| "loss": 0.0522, |
| "mean_token_accuracy": 0.9782269984483719, |
| "num_tokens": 129412928.0, |
| "step": 895 |
| }, |
| { |
| "epoch": 0.35935316430425235, |
| "grad_norm": 0.07659720629453659, |
| "learning_rate": 4.197430844713716e-05, |
| "loss": 0.0503, |
| "mean_token_accuracy": 0.9786783039569855, |
| "num_tokens": 130133772.0, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.3613495707726093, |
| "grad_norm": 0.11637573689222336, |
| "learning_rate": 4.1962248154162294e-05, |
| "loss": 0.0511, |
| "mean_token_accuracy": 0.9778418868780137, |
| "num_tokens": 130848319.0, |
| "step": 905 |
| }, |
| { |
| "epoch": 0.36334597724096623, |
| "grad_norm": 0.10833151638507843, |
| "learning_rate": 4.19501213956646e-05, |
| "loss": 0.0504, |
| "mean_token_accuracy": 0.9788612067699433, |
| "num_tokens": 131575172.0, |
| "step": 910 |
| }, |
| { |
| "epoch": 0.3653423837093232, |
| "grad_norm": 0.07982037216424942, |
| "learning_rate": 4.193792822512281e-05, |
| "loss": 0.0385, |
| "mean_token_accuracy": 0.9827957212924957, |
| "num_tokens": 132312213.0, |
| "step": 915 |
| }, |
| { |
| "epoch": 0.3673387901776802, |
| "grad_norm": 0.07653510570526123, |
| "learning_rate": 4.192566869630854e-05, |
| "loss": 0.0504, |
| "mean_token_accuracy": 0.978272557258606, |
| "num_tokens": 133035272.0, |
| "step": 920 |
| }, |
| { |
| "epoch": 0.36933519664603714, |
| "grad_norm": 0.06979475170373917, |
| "learning_rate": 4.191334286328602e-05, |
| "loss": 0.0436, |
| "mean_token_accuracy": 0.982032772898674, |
| "num_tokens": 133762349.0, |
| "step": 925 |
| }, |
| { |
| "epoch": 0.3713316031143941, |
| "grad_norm": 0.12790125608444214, |
| "learning_rate": 4.190095078041192e-05, |
| "loss": 0.0483, |
| "mean_token_accuracy": 0.9800712436437606, |
| "num_tokens": 134495209.0, |
| "step": 930 |
| }, |
| { |
| "epoch": 0.37332800958275103, |
| "grad_norm": 0.11297880858182907, |
| "learning_rate": 4.188849250233504e-05, |
| "loss": 0.0436, |
| "mean_token_accuracy": 0.9812392681837082, |
| "num_tokens": 135215123.0, |
| "step": 935 |
| }, |
| { |
| "epoch": 0.375324416051108, |
| "grad_norm": 0.10094229876995087, |
| "learning_rate": 4.1875968083996106e-05, |
| "loss": 0.0466, |
| "mean_token_accuracy": 0.9796725332736969, |
| "num_tokens": 135940243.0, |
| "step": 940 |
| }, |
| { |
| "epoch": 0.37732082251946497, |
| "grad_norm": 0.13492746651172638, |
| "learning_rate": 4.186337758062754e-05, |
| "loss": 0.0482, |
| "mean_token_accuracy": 0.9795497447252274, |
| "num_tokens": 136658519.0, |
| "step": 945 |
| }, |
| { |
| "epoch": 0.37931722898782194, |
| "grad_norm": 0.13884606957435608, |
| "learning_rate": 4.185072104775316e-05, |
| "loss": 0.0479, |
| "mean_token_accuracy": 0.97914038002491, |
| "num_tokens": 137384244.0, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.38131363545617886, |
| "grad_norm": 0.10219676047563553, |
| "learning_rate": 4.183799854118801e-05, |
| "loss": 0.0509, |
| "mean_token_accuracy": 0.9788306951522827, |
| "num_tokens": 138107181.0, |
| "step": 955 |
| }, |
| { |
| "epoch": 0.3833100419245358, |
| "grad_norm": 0.10559409856796265, |
| "learning_rate": 4.1825210117038054e-05, |
| "loss": 0.0414, |
| "mean_token_accuracy": 0.9829078048467637, |
| "num_tokens": 138827438.0, |
| "step": 960 |
| }, |
| { |
| "epoch": 0.3853064483928928, |
| "grad_norm": 0.07543619722127914, |
| "learning_rate": 4.181235583169997e-05, |
| "loss": 0.0384, |
| "mean_token_accuracy": 0.983868607878685, |
| "num_tokens": 139563400.0, |
| "step": 965 |
| }, |
| { |
| "epoch": 0.38730285486124977, |
| "grad_norm": 0.08595782518386841, |
| "learning_rate": 4.179943574186085e-05, |
| "loss": 0.0475, |
| "mean_token_accuracy": 0.9790930688381195, |
| "num_tokens": 140283779.0, |
| "step": 970 |
| }, |
| { |
| "epoch": 0.3892992613296067, |
| "grad_norm": 0.08979545533657074, |
| "learning_rate": 4.178644990449802e-05, |
| "loss": 0.0481, |
| "mean_token_accuracy": 0.97889164686203, |
| "num_tokens": 141018466.0, |
| "step": 975 |
| }, |
| { |
| "epoch": 0.39129566779796365, |
| "grad_norm": 0.11952298134565353, |
| "learning_rate": 4.177339837687873e-05, |
| "loss": 0.0527, |
| "mean_token_accuracy": 0.9777220457792282, |
| "num_tokens": 141730333.0, |
| "step": 980 |
| }, |
| { |
| "epoch": 0.3932920742663206, |
| "grad_norm": 0.08510354906320572, |
| "learning_rate": 4.1760281216559906e-05, |
| "loss": 0.0456, |
| "mean_token_accuracy": 0.9804279118776321, |
| "num_tokens": 142456339.0, |
| "step": 985 |
| }, |
| { |
| "epoch": 0.3952884807346776, |
| "grad_norm": 0.09229864180088043, |
| "learning_rate": 4.174709848138797e-05, |
| "loss": 0.0492, |
| "mean_token_accuracy": 0.9791429519653321, |
| "num_tokens": 143186609.0, |
| "step": 990 |
| }, |
| { |
| "epoch": 0.39728488720303456, |
| "grad_norm": 0.2251962572336197, |
| "learning_rate": 4.173385022949847e-05, |
| "loss": 0.049, |
| "mean_token_accuracy": 0.9791528820991516, |
| "num_tokens": 143911008.0, |
| "step": 995 |
| }, |
| { |
| "epoch": 0.3992812936713915, |
| "grad_norm": 0.08839277178049088, |
| "learning_rate": 4.17205365193159e-05, |
| "loss": 0.0438, |
| "mean_token_accuracy": 0.9804649889469147, |
| "num_tokens": 144637806.0, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.40127770013974845, |
| "grad_norm": 0.08728329837322235, |
| "learning_rate": 4.170715740955343e-05, |
| "loss": 0.0441, |
| "mean_token_accuracy": 0.9821651369333267, |
| "num_tokens": 145370197.0, |
| "step": 1005 |
| }, |
| { |
| "epoch": 0.4032741066081054, |
| "grad_norm": 0.06770054250955582, |
| "learning_rate": 4.169371295921263e-05, |
| "loss": 0.0467, |
| "mean_token_accuracy": 0.979771289229393, |
| "num_tokens": 146089153.0, |
| "step": 1010 |
| }, |
| { |
| "epoch": 0.4052705130764624, |
| "grad_norm": 0.08927344530820847, |
| "learning_rate": 4.168020322758324e-05, |
| "loss": 0.0453, |
| "mean_token_accuracy": 0.981076043844223, |
| "num_tokens": 146814893.0, |
| "step": 1015 |
| }, |
| { |
| "epoch": 0.4072669195448193, |
| "grad_norm": 0.07860483974218369, |
| "learning_rate": 4.166662827424287e-05, |
| "loss": 0.0459, |
| "mean_token_accuracy": 0.9803457111120224, |
| "num_tokens": 147538626.0, |
| "step": 1020 |
| }, |
| { |
| "epoch": 0.4092633260131763, |
| "grad_norm": 0.11667665839195251, |
| "learning_rate": 4.165298815905676e-05, |
| "loss": 0.0437, |
| "mean_token_accuracy": 0.9804121345281601, |
| "num_tokens": 148265722.0, |
| "step": 1025 |
| }, |
| { |
| "epoch": 0.41125973248153325, |
| "grad_norm": 0.09357365220785141, |
| "learning_rate": 4.163928294217751e-05, |
| "loss": 0.0456, |
| "mean_token_accuracy": 0.9804595738649369, |
| "num_tokens": 149001428.0, |
| "step": 1030 |
| }, |
| { |
| "epoch": 0.4132561389498902, |
| "grad_norm": 0.073987677693367, |
| "learning_rate": 4.162551268404484e-05, |
| "loss": 0.0405, |
| "mean_token_accuracy": 0.9826260536909104, |
| "num_tokens": 149741467.0, |
| "step": 1035 |
| }, |
| { |
| "epoch": 0.41525254541824713, |
| "grad_norm": 0.11584579944610596, |
| "learning_rate": 4.161167744538526e-05, |
| "loss": 0.05, |
| "mean_token_accuracy": 0.9772036731243133, |
| "num_tokens": 150482060.0, |
| "step": 1040 |
| }, |
| { |
| "epoch": 0.4172489518866041, |
| "grad_norm": 0.08994850516319275, |
| "learning_rate": 4.159777728721188e-05, |
| "loss": 0.0438, |
| "mean_token_accuracy": 0.9802421748638153, |
| "num_tokens": 151207290.0, |
| "step": 1045 |
| }, |
| { |
| "epoch": 0.4192453583549611, |
| "grad_norm": 0.06240738928318024, |
| "learning_rate": 4.158381227082408e-05, |
| "loss": 0.0373, |
| "mean_token_accuracy": 0.9844264835119247, |
| "num_tokens": 151948018.0, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.42124176482331804, |
| "grad_norm": 0.08201232552528381, |
| "learning_rate": 4.1569782457807275e-05, |
| "loss": 0.0498, |
| "mean_token_accuracy": 0.9776235729455948, |
| "num_tokens": 152662400.0, |
| "step": 1055 |
| }, |
| { |
| "epoch": 0.42323817129167496, |
| "grad_norm": 0.16132792830467224, |
| "learning_rate": 4.155568791003262e-05, |
| "loss": 0.0462, |
| "mean_token_accuracy": 0.9798346608877182, |
| "num_tokens": 153382255.0, |
| "step": 1060 |
| }, |
| { |
| "epoch": 0.42523457776003193, |
| "grad_norm": 0.12460800260305405, |
| "learning_rate": 4.154152868965677e-05, |
| "loss": 0.0453, |
| "mean_token_accuracy": 0.9792943328619004, |
| "num_tokens": 154107481.0, |
| "step": 1065 |
| }, |
| { |
| "epoch": 0.4272309842283889, |
| "grad_norm": 0.08316458016633987, |
| "learning_rate": 4.152730485912157e-05, |
| "loss": 0.0421, |
| "mean_token_accuracy": 0.9824769467115402, |
| "num_tokens": 154810936.0, |
| "step": 1070 |
| }, |
| { |
| "epoch": 0.42922739069674587, |
| "grad_norm": 0.09391912817955017, |
| "learning_rate": 4.15130164811538e-05, |
| "loss": 0.0405, |
| "mean_token_accuracy": 0.9815963953733444, |
| "num_tokens": 155537857.0, |
| "step": 1075 |
| }, |
| { |
| "epoch": 0.43122379716510284, |
| "grad_norm": 0.05126833915710449, |
| "learning_rate": 4.149866361876487e-05, |
| "loss": 0.041, |
| "mean_token_accuracy": 0.9826298028230667, |
| "num_tokens": 156251631.0, |
| "step": 1080 |
| }, |
| { |
| "epoch": 0.43322020363345976, |
| "grad_norm": 0.05620391294360161, |
| "learning_rate": 4.1484246335250596e-05, |
| "loss": 0.0424, |
| "mean_token_accuracy": 0.9817048490047455, |
| "num_tokens": 156978372.0, |
| "step": 1085 |
| }, |
| { |
| "epoch": 0.4352166101018167, |
| "grad_norm": 0.08917587250471115, |
| "learning_rate": 4.146976469419087e-05, |
| "loss": 0.0431, |
| "mean_token_accuracy": 0.9803878009319306, |
| "num_tokens": 157708445.0, |
| "step": 1090 |
| }, |
| { |
| "epoch": 0.4372130165701737, |
| "grad_norm": 0.09579002112150192, |
| "learning_rate": 4.145521875944943e-05, |
| "loss": 0.043, |
| "mean_token_accuracy": 0.9806773096323014, |
| "num_tokens": 158431867.0, |
| "step": 1095 |
| }, |
| { |
| "epoch": 0.43920942303853067, |
| "grad_norm": 0.08360281586647034, |
| "learning_rate": 4.14406085951735e-05, |
| "loss": 0.0478, |
| "mean_token_accuracy": 0.9791438162326813, |
| "num_tokens": 159157025.0, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.4412058295068876, |
| "grad_norm": 0.11798866093158722, |
| "learning_rate": 4.142593426579359e-05, |
| "loss": 0.0492, |
| "mean_token_accuracy": 0.9781560689210892, |
| "num_tokens": 159878274.0, |
| "step": 1105 |
| }, |
| { |
| "epoch": 0.44320223597524455, |
| "grad_norm": 0.07982130348682404, |
| "learning_rate": 4.1411195836023166e-05, |
| "loss": 0.042, |
| "mean_token_accuracy": 0.9814552158117295, |
| "num_tokens": 160594976.0, |
| "step": 1110 |
| }, |
| { |
| "epoch": 0.4451986424436015, |
| "grad_norm": 0.08481776714324951, |
| "learning_rate": 4.139639337085837e-05, |
| "loss": 0.0531, |
| "mean_token_accuracy": 0.9776395380496978, |
| "num_tokens": 161305109.0, |
| "step": 1115 |
| }, |
| { |
| "epoch": 0.4471950489119585, |
| "grad_norm": 0.08173475414514542, |
| "learning_rate": 4.138152693557775e-05, |
| "loss": 0.0382, |
| "mean_token_accuracy": 0.983448275923729, |
| "num_tokens": 162027934.0, |
| "step": 1120 |
| }, |
| { |
| "epoch": 0.4491914553803154, |
| "grad_norm": 0.0663527399301529, |
| "learning_rate": 4.136659659574195e-05, |
| "loss": 0.0474, |
| "mean_token_accuracy": 0.9785608291625977, |
| "num_tokens": 162742550.0, |
| "step": 1125 |
| }, |
| { |
| "epoch": 0.4511878618486724, |
| "grad_norm": 0.10211747139692307, |
| "learning_rate": 4.1351602417193445e-05, |
| "loss": 0.0439, |
| "mean_token_accuracy": 0.9815158486366272, |
| "num_tokens": 163461292.0, |
| "step": 1130 |
| }, |
| { |
| "epoch": 0.45318426831702935, |
| "grad_norm": 0.08372879028320312, |
| "learning_rate": 4.133654446605622e-05, |
| "loss": 0.0455, |
| "mean_token_accuracy": 0.9801951259374618, |
| "num_tokens": 164176893.0, |
| "step": 1135 |
| }, |
| { |
| "epoch": 0.4551806747853863, |
| "grad_norm": 0.09567493945360184, |
| "learning_rate": 4.1321422808735505e-05, |
| "loss": 0.0441, |
| "mean_token_accuracy": 0.9820766746997833, |
| "num_tokens": 164909213.0, |
| "step": 1140 |
| }, |
| { |
| "epoch": 0.4571770812537433, |
| "grad_norm": 0.10552221536636353, |
| "learning_rate": 4.1306237511917476e-05, |
| "loss": 0.038, |
| "mean_token_accuracy": 0.9834578722715378, |
| "num_tokens": 165628392.0, |
| "step": 1145 |
| }, |
| { |
| "epoch": 0.4591734877221002, |
| "grad_norm": 0.13832643628120422, |
| "learning_rate": 4.129098864256896e-05, |
| "loss": 0.0477, |
| "mean_token_accuracy": 0.9799725502729416, |
| "num_tokens": 166348245.0, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.4611698941904572, |
| "grad_norm": 0.0993349552154541, |
| "learning_rate": 4.127567626793712e-05, |
| "loss": 0.0478, |
| "mean_token_accuracy": 0.9796446442604065, |
| "num_tokens": 167080014.0, |
| "step": 1155 |
| }, |
| { |
| "epoch": 0.46316630065881415, |
| "grad_norm": 0.0669255256652832, |
| "learning_rate": 4.126030045554919e-05, |
| "loss": 0.0413, |
| "mean_token_accuracy": 0.9815053075551987, |
| "num_tokens": 167806975.0, |
| "step": 1160 |
| }, |
| { |
| "epoch": 0.4651627071271711, |
| "grad_norm": 0.059534091502428055, |
| "learning_rate": 4.1244861273212167e-05, |
| "loss": 0.0482, |
| "mean_token_accuracy": 0.9796302795410157, |
| "num_tokens": 168521774.0, |
| "step": 1165 |
| }, |
| { |
| "epoch": 0.46715911359552803, |
| "grad_norm": 0.1345037966966629, |
| "learning_rate": 4.122935878901249e-05, |
| "loss": 0.0427, |
| "mean_token_accuracy": 0.9822476923465728, |
| "num_tokens": 169240278.0, |
| "step": 1170 |
| }, |
| { |
| "epoch": 0.469155520063885, |
| "grad_norm": 0.09438323974609375, |
| "learning_rate": 4.1213793071315786e-05, |
| "loss": 0.0421, |
| "mean_token_accuracy": 0.9817219495773315, |
| "num_tokens": 169969278.0, |
| "step": 1175 |
| }, |
| { |
| "epoch": 0.47115192653224197, |
| "grad_norm": 0.09831586480140686, |
| "learning_rate": 4.1198164188766506e-05, |
| "loss": 0.0415, |
| "mean_token_accuracy": 0.9811917096376419, |
| "num_tokens": 170694898.0, |
| "step": 1180 |
| }, |
| { |
| "epoch": 0.47314833300059894, |
| "grad_norm": 0.10349370539188385, |
| "learning_rate": 4.11824722102877e-05, |
| "loss": 0.0447, |
| "mean_token_accuracy": 0.9804620027542115, |
| "num_tokens": 171421794.0, |
| "step": 1185 |
| }, |
| { |
| "epoch": 0.47514473946895586, |
| "grad_norm": 0.07256416231393814, |
| "learning_rate": 4.11667172050806e-05, |
| "loss": 0.0504, |
| "mean_token_accuracy": 0.9791789770126342, |
| "num_tokens": 172134789.0, |
| "step": 1190 |
| }, |
| { |
| "epoch": 0.4771411459373128, |
| "grad_norm": 0.08856100589036942, |
| "learning_rate": 4.115089924262448e-05, |
| "loss": 0.0524, |
| "mean_token_accuracy": 0.9780719757080079, |
| "num_tokens": 172843426.0, |
| "step": 1195 |
| }, |
| { |
| "epoch": 0.4791375524056698, |
| "grad_norm": 0.06250528991222382, |
| "learning_rate": 4.113501839267616e-05, |
| "loss": 0.0427, |
| "mean_token_accuracy": 0.9813639312982559, |
| "num_tokens": 173581290.0, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.48113395887402677, |
| "grad_norm": 0.14334551990032196, |
| "learning_rate": 4.111907472526987e-05, |
| "loss": 0.0479, |
| "mean_token_accuracy": 0.978913527727127, |
| "num_tokens": 174301236.0, |
| "step": 1205 |
| }, |
| { |
| "epoch": 0.4831303653423837, |
| "grad_norm": 0.09056934714317322, |
| "learning_rate": 4.11030683107168e-05, |
| "loss": 0.0448, |
| "mean_token_accuracy": 0.9799034684896469, |
| "num_tokens": 175031206.0, |
| "step": 1210 |
| }, |
| { |
| "epoch": 0.48512677181074065, |
| "grad_norm": 0.08644259721040726, |
| "learning_rate": 4.10869992196049e-05, |
| "loss": 0.048, |
| "mean_token_accuracy": 0.9799766391515732, |
| "num_tokens": 175748771.0, |
| "step": 1215 |
| }, |
| { |
| "epoch": 0.4871231782790976, |
| "grad_norm": 0.06306669861078262, |
| "learning_rate": 4.107086752279849e-05, |
| "loss": 0.0393, |
| "mean_token_accuracy": 0.9826879143714905, |
| "num_tokens": 176482262.0, |
| "step": 1220 |
| }, |
| { |
| "epoch": 0.4891195847474546, |
| "grad_norm": 0.12182262539863586, |
| "learning_rate": 4.1054673291438014e-05, |
| "loss": 0.0431, |
| "mean_token_accuracy": 0.9814256817102432, |
| "num_tokens": 177204272.0, |
| "step": 1225 |
| }, |
| { |
| "epoch": 0.49111599121581156, |
| "grad_norm": 0.10804204642772675, |
| "learning_rate": 4.1038416596939646e-05, |
| "loss": 0.0455, |
| "mean_token_accuracy": 0.9802686542272567, |
| "num_tokens": 177923746.0, |
| "step": 1230 |
| }, |
| { |
| "epoch": 0.4931123976841685, |
| "grad_norm": 0.08272804319858551, |
| "learning_rate": 4.1022097510995075e-05, |
| "loss": 0.0463, |
| "mean_token_accuracy": 0.9803291648626328, |
| "num_tokens": 178646214.0, |
| "step": 1235 |
| }, |
| { |
| "epoch": 0.49510880415252545, |
| "grad_norm": 0.08051120489835739, |
| "learning_rate": 4.1005716105571086e-05, |
| "loss": 0.0406, |
| "mean_token_accuracy": 0.9827998161315918, |
| "num_tokens": 179361163.0, |
| "step": 1240 |
| }, |
| { |
| "epoch": 0.4971052106208824, |
| "grad_norm": 0.07553274929523468, |
| "learning_rate": 4.0989272452909324e-05, |
| "loss": 0.058, |
| "mean_token_accuracy": 0.9754190474748612, |
| "num_tokens": 180077232.0, |
| "step": 1245 |
| }, |
| { |
| "epoch": 0.4991016170892394, |
| "grad_norm": 0.07851612567901611, |
| "learning_rate": 4.097276662552592e-05, |
| "loss": 0.0525, |
| "mean_token_accuracy": 0.9774915635585785, |
| "num_tokens": 180800542.0, |
| "step": 1250 |
| }, |
| { |
| "epoch": 0.5010980235575964, |
| "grad_norm": 0.09802480787038803, |
| "learning_rate": 4.095619869621122e-05, |
| "loss": 0.0403, |
| "mean_token_accuracy": 0.9810875445604325, |
| "num_tokens": 181523489.0, |
| "step": 1255 |
| }, |
| { |
| "epoch": 0.5030944300259533, |
| "grad_norm": 0.07821514457464218, |
| "learning_rate": 4.093956873802941e-05, |
| "loss": 0.0418, |
| "mean_token_accuracy": 0.981935253739357, |
| "num_tokens": 182252055.0, |
| "step": 1260 |
| }, |
| { |
| "epoch": 0.5050908364943102, |
| "grad_norm": 0.07127466797828674, |
| "learning_rate": 4.092287682431825e-05, |
| "loss": 0.0468, |
| "mean_token_accuracy": 0.9807193636894226, |
| "num_tokens": 182978186.0, |
| "step": 1265 |
| }, |
| { |
| "epoch": 0.5070872429626672, |
| "grad_norm": 0.09551110118627548, |
| "learning_rate": 4.0906123028688695e-05, |
| "loss": 0.0412, |
| "mean_token_accuracy": 0.9831303149461746, |
| "num_tokens": 183702199.0, |
| "step": 1270 |
| }, |
| { |
| "epoch": 0.5090836494310241, |
| "grad_norm": 0.3869798481464386, |
| "learning_rate": 4.088930742502462e-05, |
| "loss": 0.0405, |
| "mean_token_accuracy": 0.9830111473798752, |
| "num_tokens": 184428583.0, |
| "step": 1275 |
| }, |
| { |
| "epoch": 0.5110800558993811, |
| "grad_norm": 0.09185118973255157, |
| "learning_rate": 4.087243008748246e-05, |
| "loss": 0.048, |
| "mean_token_accuracy": 0.9796857953071594, |
| "num_tokens": 185144789.0, |
| "step": 1280 |
| }, |
| { |
| "epoch": 0.5130764623677381, |
| "grad_norm": 0.09394432604312897, |
| "learning_rate": 4.085549109049089e-05, |
| "loss": 0.0415, |
| "mean_token_accuracy": 0.982088240981102, |
| "num_tokens": 185873049.0, |
| "step": 1285 |
| }, |
| { |
| "epoch": 0.515072868836095, |
| "grad_norm": 0.1030714362859726, |
| "learning_rate": 4.083849050875053e-05, |
| "loss": 0.0494, |
| "mean_token_accuracy": 0.9779442816972732, |
| "num_tokens": 186592320.0, |
| "step": 1290 |
| }, |
| { |
| "epoch": 0.517069275304452, |
| "grad_norm": 0.11340459436178207, |
| "learning_rate": 4.082142841723355e-05, |
| "loss": 0.0441, |
| "mean_token_accuracy": 0.9800026804208756, |
| "num_tokens": 187318624.0, |
| "step": 1295 |
| }, |
| { |
| "epoch": 0.519065681772809, |
| "grad_norm": 0.09892936795949936, |
| "learning_rate": 4.080430489118339e-05, |
| "loss": 0.0503, |
| "mean_token_accuracy": 0.9789821773767471, |
| "num_tokens": 188042877.0, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.521062088241166, |
| "grad_norm": 0.08861280232667923, |
| "learning_rate": 4.0787120006114435e-05, |
| "loss": 0.0455, |
| "mean_token_accuracy": 0.980542853474617, |
| "num_tokens": 188765158.0, |
| "step": 1305 |
| }, |
| { |
| "epoch": 0.5230584947095228, |
| "grad_norm": 0.06914465874433517, |
| "learning_rate": 4.076987383781164e-05, |
| "loss": 0.0427, |
| "mean_token_accuracy": 0.9810645192861557, |
| "num_tokens": 189480211.0, |
| "step": 1310 |
| }, |
| { |
| "epoch": 0.5250549011778798, |
| "grad_norm": 0.07803887873888016, |
| "learning_rate": 4.075256646233022e-05, |
| "loss": 0.0477, |
| "mean_token_accuracy": 0.9788318306207657, |
| "num_tokens": 190199406.0, |
| "step": 1315 |
| }, |
| { |
| "epoch": 0.5270513076462368, |
| "grad_norm": 0.08014380186796188, |
| "learning_rate": 4.073519795599532e-05, |
| "loss": 0.0425, |
| "mean_token_accuracy": 0.9804257869720459, |
| "num_tokens": 190934259.0, |
| "step": 1320 |
| }, |
| { |
| "epoch": 0.5290477141145937, |
| "grad_norm": 0.11968166381120682, |
| "learning_rate": 4.071776839540166e-05, |
| "loss": 0.0421, |
| "mean_token_accuracy": 0.9820073306560516, |
| "num_tokens": 191651169.0, |
| "step": 1325 |
| }, |
| { |
| "epoch": 0.5310441205829507, |
| "grad_norm": 0.11703905463218689, |
| "learning_rate": 4.0700277857413225e-05, |
| "loss": 0.0515, |
| "mean_token_accuracy": 0.9788607507944107, |
| "num_tokens": 192367327.0, |
| "step": 1330 |
| }, |
| { |
| "epoch": 0.5330405270513077, |
| "grad_norm": 0.09883023053407669, |
| "learning_rate": 4.0682726419162894e-05, |
| "loss": 0.0509, |
| "mean_token_accuracy": 0.9784328937530518, |
| "num_tokens": 193093958.0, |
| "step": 1335 |
| }, |
| { |
| "epoch": 0.5350369335196646, |
| "grad_norm": 0.07223407179117203, |
| "learning_rate": 4.0665114158052116e-05, |
| "loss": 0.0465, |
| "mean_token_accuracy": 0.9799530595541001, |
| "num_tokens": 193823330.0, |
| "step": 1340 |
| }, |
| { |
| "epoch": 0.5370333399880216, |
| "grad_norm": 0.0919746458530426, |
| "learning_rate": 4.0647441151750566e-05, |
| "loss": 0.044, |
| "mean_token_accuracy": 0.981145116686821, |
| "num_tokens": 194553648.0, |
| "step": 1345 |
| }, |
| { |
| "epoch": 0.5390297464563785, |
| "grad_norm": 0.07844650745391846, |
| "learning_rate": 4.062970747819582e-05, |
| "loss": 0.0379, |
| "mean_token_accuracy": 0.9831986397504806, |
| "num_tokens": 195270519.0, |
| "step": 1350 |
| }, |
| { |
| "epoch": 0.5410261529247354, |
| "grad_norm": 0.09186799079179764, |
| "learning_rate": 4.061191321559298e-05, |
| "loss": 0.0417, |
| "mean_token_accuracy": 0.9822646319866181, |
| "num_tokens": 195994606.0, |
| "step": 1355 |
| }, |
| { |
| "epoch": 0.5430225593930924, |
| "grad_norm": 0.08641962707042694, |
| "learning_rate": 4.0594058442414344e-05, |
| "loss": 0.0485, |
| "mean_token_accuracy": 0.9796275526285172, |
| "num_tokens": 196717658.0, |
| "step": 1360 |
| }, |
| { |
| "epoch": 0.5450189658614494, |
| "grad_norm": 0.08504263311624527, |
| "learning_rate": 4.0576143237399066e-05, |
| "loss": 0.0538, |
| "mean_token_accuracy": 0.9767540097236633, |
| "num_tokens": 197424512.0, |
| "step": 1365 |
| }, |
| { |
| "epoch": 0.5470153723298063, |
| "grad_norm": 0.12139827013015747, |
| "learning_rate": 4.055816767955281e-05, |
| "loss": 0.0489, |
| "mean_token_accuracy": 0.9788673222064972, |
| "num_tokens": 198158443.0, |
| "step": 1370 |
| }, |
| { |
| "epoch": 0.5490117787981633, |
| "grad_norm": 0.08939183503389359, |
| "learning_rate": 4.054013184814738e-05, |
| "loss": 0.0479, |
| "mean_token_accuracy": 0.9796740025281906, |
| "num_tokens": 198875760.0, |
| "step": 1375 |
| }, |
| { |
| "epoch": 0.5510081852665203, |
| "grad_norm": 0.07606673240661621, |
| "learning_rate": 4.052203582272039e-05, |
| "loss": 0.0435, |
| "mean_token_accuracy": 0.9809995740652084, |
| "num_tokens": 199601401.0, |
| "step": 1380 |
| }, |
| { |
| "epoch": 0.5530045917348773, |
| "grad_norm": 0.09385755658149719, |
| "learning_rate": 4.05038796830749e-05, |
| "loss": 0.0414, |
| "mean_token_accuracy": 0.9815231949090958, |
| "num_tokens": 200336207.0, |
| "step": 1385 |
| }, |
| { |
| "epoch": 0.5550009982032342, |
| "grad_norm": 0.10867508500814438, |
| "learning_rate": 4.048566350927911e-05, |
| "loss": 0.0484, |
| "mean_token_accuracy": 0.9797090023756028, |
| "num_tokens": 201057681.0, |
| "step": 1390 |
| }, |
| { |
| "epoch": 0.5569974046715911, |
| "grad_norm": 0.10143137723207474, |
| "learning_rate": 4.0467387381665907e-05, |
| "loss": 0.0562, |
| "mean_token_accuracy": 0.9756572872400284, |
| "num_tokens": 201776862.0, |
| "step": 1395 |
| }, |
| { |
| "epoch": 0.5589938111399481, |
| "grad_norm": 0.10667003691196442, |
| "learning_rate": 4.044905138083263e-05, |
| "loss": 0.0463, |
| "mean_token_accuracy": 0.9798533678054809, |
| "num_tokens": 202492946.0, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.560990217608305, |
| "grad_norm": 0.07327716052532196, |
| "learning_rate": 4.0430655587640636e-05, |
| "loss": 0.0466, |
| "mean_token_accuracy": 0.9800977617502212, |
| "num_tokens": 203220129.0, |
| "step": 1405 |
| }, |
| { |
| "epoch": 0.562986624076662, |
| "grad_norm": 0.0714830830693245, |
| "learning_rate": 4.041220008321495e-05, |
| "loss": 0.0412, |
| "mean_token_accuracy": 0.9820256412029267, |
| "num_tokens": 203950333.0, |
| "step": 1410 |
| }, |
| { |
| "epoch": 0.564983030545019, |
| "grad_norm": 0.08165636658668518, |
| "learning_rate": 4.039368494894394e-05, |
| "loss": 0.0484, |
| "mean_token_accuracy": 0.9786020785570144, |
| "num_tokens": 204665955.0, |
| "step": 1415 |
| }, |
| { |
| "epoch": 0.5669794370133759, |
| "grad_norm": 0.0785563662648201, |
| "learning_rate": 4.0375110266478943e-05, |
| "loss": 0.0439, |
| "mean_token_accuracy": 0.9812197864055634, |
| "num_tokens": 205388850.0, |
| "step": 1420 |
| }, |
| { |
| "epoch": 0.5689758434817329, |
| "grad_norm": 0.1614316999912262, |
| "learning_rate": 4.0356476117733887e-05, |
| "loss": 0.0431, |
| "mean_token_accuracy": 0.981093293428421, |
| "num_tokens": 206109175.0, |
| "step": 1425 |
| }, |
| { |
| "epoch": 0.5709722499500899, |
| "grad_norm": 0.09200597554445267, |
| "learning_rate": 4.033778258488496e-05, |
| "loss": 0.0488, |
| "mean_token_accuracy": 0.9786974668502808, |
| "num_tokens": 206830366.0, |
| "step": 1430 |
| }, |
| { |
| "epoch": 0.5729686564184467, |
| "grad_norm": 0.08983796834945679, |
| "learning_rate": 4.031902975037023e-05, |
| "loss": 0.0464, |
| "mean_token_accuracy": 0.9802830934524536, |
| "num_tokens": 207549827.0, |
| "step": 1435 |
| }, |
| { |
| "epoch": 0.5749650628868037, |
| "grad_norm": 0.07297132909297943, |
| "learning_rate": 4.030021769688926e-05, |
| "loss": 0.0458, |
| "mean_token_accuracy": 0.9810631215572357, |
| "num_tokens": 208264895.0, |
| "step": 1440 |
| }, |
| { |
| "epoch": 0.5769614693551607, |
| "grad_norm": 0.0987749695777893, |
| "learning_rate": 4.028134650740281e-05, |
| "loss": 0.046, |
| "mean_token_accuracy": 0.981097549200058, |
| "num_tokens": 208997043.0, |
| "step": 1445 |
| }, |
| { |
| "epoch": 0.5789578758235177, |
| "grad_norm": 0.09348510205745697, |
| "learning_rate": 4.026241626513239e-05, |
| "loss": 0.048, |
| "mean_token_accuracy": 0.9792329996824265, |
| "num_tokens": 209725133.0, |
| "step": 1450 |
| }, |
| { |
| "epoch": 0.5809542822918746, |
| "grad_norm": 0.092249795794487, |
| "learning_rate": 4.024342705355996e-05, |
| "loss": 0.0401, |
| "mean_token_accuracy": 0.982272133231163, |
| "num_tokens": 210465190.0, |
| "step": 1455 |
| }, |
| { |
| "epoch": 0.5829506887602316, |
| "grad_norm": 0.09076627343893051, |
| "learning_rate": 4.022437895642752e-05, |
| "loss": 0.0412, |
| "mean_token_accuracy": 0.9813473641872406, |
| "num_tokens": 211191938.0, |
| "step": 1460 |
| }, |
| { |
| "epoch": 0.5849470952285886, |
| "grad_norm": 0.10411449521780014, |
| "learning_rate": 4.020527205773674e-05, |
| "loss": 0.0468, |
| "mean_token_accuracy": 0.9788929164409638, |
| "num_tokens": 211915014.0, |
| "step": 1465 |
| }, |
| { |
| "epoch": 0.5869435016969455, |
| "grad_norm": 0.08393626660108566, |
| "learning_rate": 4.0186106441748635e-05, |
| "loss": 0.0405, |
| "mean_token_accuracy": 0.9831263810396195, |
| "num_tokens": 212639731.0, |
| "step": 1470 |
| }, |
| { |
| "epoch": 0.5889399081653025, |
| "grad_norm": 0.12234524637460709, |
| "learning_rate": 4.016688219298313e-05, |
| "loss": 0.0441, |
| "mean_token_accuracy": 0.9801553189754486, |
| "num_tokens": 213354106.0, |
| "step": 1475 |
| }, |
| { |
| "epoch": 0.5909363146336594, |
| "grad_norm": 0.19468314945697784, |
| "learning_rate": 4.014759939621874e-05, |
| "loss": 0.0527, |
| "mean_token_accuracy": 0.978853377699852, |
| "num_tokens": 214069931.0, |
| "step": 1480 |
| }, |
| { |
| "epoch": 0.5929327211020163, |
| "grad_norm": 0.07654144614934921, |
| "learning_rate": 4.012825813649218e-05, |
| "loss": 0.0447, |
| "mean_token_accuracy": 0.9811176121234894, |
| "num_tokens": 214801602.0, |
| "step": 1485 |
| }, |
| { |
| "epoch": 0.5949291275703733, |
| "grad_norm": 0.08197729289531708, |
| "learning_rate": 4.0108858499097965e-05, |
| "loss": 0.0436, |
| "mean_token_accuracy": 0.9811263650655746, |
| "num_tokens": 215525744.0, |
| "step": 1490 |
| }, |
| { |
| "epoch": 0.5969255340387303, |
| "grad_norm": 0.09118011593818665, |
| "learning_rate": 4.008940056958806e-05, |
| "loss": 0.0453, |
| "mean_token_accuracy": 0.9803959131240845, |
| "num_tokens": 216250126.0, |
| "step": 1495 |
| }, |
| { |
| "epoch": 0.5989219405070872, |
| "grad_norm": 0.12226779013872147, |
| "learning_rate": 4.006988443377151e-05, |
| "loss": 0.0447, |
| "mean_token_accuracy": 0.9816070884466171, |
| "num_tokens": 216985436.0, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.6009183469754442, |
| "grad_norm": 0.07873986661434174, |
| "learning_rate": 4.0050310177714044e-05, |
| "loss": 0.048, |
| "mean_token_accuracy": 0.978963452577591, |
| "num_tokens": 217695643.0, |
| "step": 1505 |
| }, |
| { |
| "epoch": 0.6029147534438012, |
| "grad_norm": 0.10712873935699463, |
| "learning_rate": 4.0030677887737685e-05, |
| "loss": 0.0464, |
| "mean_token_accuracy": 0.9787706166505814, |
| "num_tokens": 218425340.0, |
| "step": 1510 |
| }, |
| { |
| "epoch": 0.6049111599121582, |
| "grad_norm": 0.06610714644193649, |
| "learning_rate": 4.00109876504204e-05, |
| "loss": 0.0412, |
| "mean_token_accuracy": 0.9825782984495163, |
| "num_tokens": 219145127.0, |
| "step": 1515 |
| }, |
| { |
| "epoch": 0.606907566380515, |
| "grad_norm": 0.1649412214756012, |
| "learning_rate": 3.99912395525957e-05, |
| "loss": 0.0451, |
| "mean_token_accuracy": 0.9816054254770279, |
| "num_tokens": 219875374.0, |
| "step": 1520 |
| }, |
| { |
| "epoch": 0.608903972848872, |
| "grad_norm": 0.09525147825479507, |
| "learning_rate": 3.997143368135225e-05, |
| "loss": 0.0456, |
| "mean_token_accuracy": 0.9800587654113769, |
| "num_tokens": 220598857.0, |
| "step": 1525 |
| }, |
| { |
| "epoch": 0.610900379317229, |
| "grad_norm": 0.08931232988834381, |
| "learning_rate": 3.99515701240335e-05, |
| "loss": 0.0416, |
| "mean_token_accuracy": 0.9814909934997559, |
| "num_tokens": 221323896.0, |
| "step": 1530 |
| }, |
| { |
| "epoch": 0.6128967857855859, |
| "grad_norm": 0.07063008844852448, |
| "learning_rate": 3.993164896823731e-05, |
| "loss": 0.0459, |
| "mean_token_accuracy": 0.979477858543396, |
| "num_tokens": 222047987.0, |
| "step": 1535 |
| }, |
| { |
| "epoch": 0.6148931922539429, |
| "grad_norm": 0.06190071254968643, |
| "learning_rate": 3.991167030181552e-05, |
| "loss": 0.0487, |
| "mean_token_accuracy": 0.9796573609113693, |
| "num_tokens": 222776362.0, |
| "step": 1540 |
| }, |
| { |
| "epoch": 0.6168895987222999, |
| "grad_norm": 0.07348193973302841, |
| "learning_rate": 3.989163421287362e-05, |
| "loss": 0.0444, |
| "mean_token_accuracy": 0.9801139563322068, |
| "num_tokens": 223501685.0, |
| "step": 1545 |
| }, |
| { |
| "epoch": 0.6188860051906568, |
| "grad_norm": 0.09044871479272842, |
| "learning_rate": 3.987154078977029e-05, |
| "loss": 0.0432, |
| "mean_token_accuracy": 0.9818701952695846, |
| "num_tokens": 224224314.0, |
| "step": 1550 |
| }, |
| { |
| "epoch": 0.6208824116590138, |
| "grad_norm": 0.0657450407743454, |
| "learning_rate": 3.985139012111711e-05, |
| "loss": 0.0383, |
| "mean_token_accuracy": 0.983964490890503, |
| "num_tokens": 224952530.0, |
| "step": 1555 |
| }, |
| { |
| "epoch": 0.6228788181273708, |
| "grad_norm": 0.10462448000907898, |
| "learning_rate": 3.9831182295778054e-05, |
| "loss": 0.0464, |
| "mean_token_accuracy": 0.9802037477493286, |
| "num_tokens": 225670583.0, |
| "step": 1560 |
| }, |
| { |
| "epoch": 0.6248752245957276, |
| "grad_norm": 0.10816384106874466, |
| "learning_rate": 3.98109174028692e-05, |
| "loss": 0.0431, |
| "mean_token_accuracy": 0.9816061168909073, |
| "num_tokens": 226405728.0, |
| "step": 1565 |
| }, |
| { |
| "epoch": 0.6268716310640846, |
| "grad_norm": 0.07350475341081619, |
| "learning_rate": 3.979059553175826e-05, |
| "loss": 0.0421, |
| "mean_token_accuracy": 0.9821370601654053, |
| "num_tokens": 227131753.0, |
| "step": 1570 |
| }, |
| { |
| "epoch": 0.6288680375324416, |
| "grad_norm": 0.1497100442647934, |
| "learning_rate": 3.9770216772064254e-05, |
| "loss": 0.0493, |
| "mean_token_accuracy": 0.979113084077835, |
| "num_tokens": 227854770.0, |
| "step": 1575 |
| }, |
| { |
| "epoch": 0.6308644440007986, |
| "grad_norm": 0.08558464050292969, |
| "learning_rate": 3.9749781213657046e-05, |
| "loss": 0.041, |
| "mean_token_accuracy": 0.9826665192842483, |
| "num_tokens": 228579635.0, |
| "step": 1580 |
| }, |
| { |
| "epoch": 0.6328608504691555, |
| "grad_norm": 0.0670614242553711, |
| "learning_rate": 3.972928894665699e-05, |
| "loss": 0.0421, |
| "mean_token_accuracy": 0.9823820263147354, |
| "num_tokens": 229300584.0, |
| "step": 1585 |
| }, |
| { |
| "epoch": 0.6348572569375125, |
| "grad_norm": 0.10730074346065521, |
| "learning_rate": 3.970874006143454e-05, |
| "loss": 0.0436, |
| "mean_token_accuracy": 0.9802110999822616, |
| "num_tokens": 230025120.0, |
| "step": 1590 |
| }, |
| { |
| "epoch": 0.6368536634058695, |
| "grad_norm": 0.06655887514352798, |
| "learning_rate": 3.9688134648609804e-05, |
| "loss": 0.0445, |
| "mean_token_accuracy": 0.9799957931041717, |
| "num_tokens": 230748778.0, |
| "step": 1595 |
| }, |
| { |
| "epoch": 0.6388500698742264, |
| "grad_norm": 0.058215994387865067, |
| "learning_rate": 3.966747279905222e-05, |
| "loss": 0.0402, |
| "mean_token_accuracy": 0.98234643638134, |
| "num_tokens": 231469920.0, |
| "step": 1600 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 7515, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.333398891906728e+19, |
| "train_batch_size": 6, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
