| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9930394431554523, | |
| "eval_steps": 50, | |
| "global_step": 645, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02320185614849188, | |
| "grad_norm": 27.06661296487487, | |
| "learning_rate": 5e-07, | |
| "loss": 1.6534, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04640371229698376, | |
| "grad_norm": 14.570294011958959, | |
| "learning_rate": 1e-06, | |
| "loss": 1.5286, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06960556844547564, | |
| "grad_norm": 7.608713229824519, | |
| "learning_rate": 9.998470286265414e-07, | |
| "loss": 1.2854, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09280742459396751, | |
| "grad_norm": 6.212274190189952, | |
| "learning_rate": 9.993882081071305e-07, | |
| "loss": 1.2312, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11600928074245939, | |
| "grad_norm": 5.767015997797787, | |
| "learning_rate": 9.986238191873872e-07, | |
| "loss": 1.1896, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13921113689095127, | |
| "grad_norm": 5.073635902534103, | |
| "learning_rate": 9.975543295858033e-07, | |
| "loss": 1.1918, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16241299303944315, | |
| "grad_norm": 4.788195681953361, | |
| "learning_rate": 9.961803937075514e-07, | |
| "loss": 1.1547, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.18561484918793503, | |
| "grad_norm": 4.642283394950232, | |
| "learning_rate": 9.945028522440653e-07, | |
| "loss": 1.1326, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2088167053364269, | |
| "grad_norm": 4.915483171626106, | |
| "learning_rate": 9.925227316586314e-07, | |
| "loss": 1.1409, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.23201856148491878, | |
| "grad_norm": 4.785752094079727, | |
| "learning_rate": 9.902412435583125e-07, | |
| "loss": 1.1348, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.23201856148491878, | |
| "eval_loss": 1.1267675161361694, | |
| "eval_runtime": 105.5696, | |
| "eval_samples_per_second": 58.056, | |
| "eval_steps_per_second": 0.909, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2552204176334107, | |
| "grad_norm": 4.914635335083288, | |
| "learning_rate": 9.876597839525813e-07, | |
| "loss": 1.1167, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.27842227378190254, | |
| "grad_norm": 4.9477576848370095, | |
| "learning_rate": 9.847799323991233e-07, | |
| "loss": 1.1059, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.30162412993039445, | |
| "grad_norm": 4.9360133375019295, | |
| "learning_rate": 9.816034510373285e-07, | |
| "loss": 1.1173, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.3248259860788863, | |
| "grad_norm": 4.7405884580433675, | |
| "learning_rate": 9.781322835100637e-07, | |
| "loss": 1.1091, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3480278422273782, | |
| "grad_norm": 4.835669121473599, | |
| "learning_rate": 9.743685537743856e-07, | |
| "loss": 1.0967, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.37122969837587005, | |
| "grad_norm": 4.6796771647856055, | |
| "learning_rate": 9.70314564801922e-07, | |
| "loss": 1.0758, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.39443155452436196, | |
| "grad_norm": 4.984167856345103, | |
| "learning_rate": 9.659727971697173e-07, | |
| "loss": 1.0862, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.4176334106728538, | |
| "grad_norm": 4.771046487158264, | |
| "learning_rate": 9.613459075424033e-07, | |
| "loss": 1.0795, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4408352668213457, | |
| "grad_norm": 4.605260375673115, | |
| "learning_rate": 9.564367270466245e-07, | |
| "loss": 1.0677, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.46403712296983757, | |
| "grad_norm": 4.698279384122072, | |
| "learning_rate": 9.51248259538713e-07, | |
| "loss": 1.08, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.46403712296983757, | |
| "eval_loss": 1.0813250541687012, | |
| "eval_runtime": 104.9985, | |
| "eval_samples_per_second": 58.372, | |
| "eval_steps_per_second": 0.914, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4872389791183295, | |
| "grad_norm": 5.05046913930874, | |
| "learning_rate": 9.457836797666721e-07, | |
| "loss": 1.0944, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.5104408352668214, | |
| "grad_norm": 5.042019310011314, | |
| "learning_rate": 9.400463314275941e-07, | |
| "loss": 1.0946, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5336426914153132, | |
| "grad_norm": 4.6774297543026435, | |
| "learning_rate": 9.340397251217008e-07, | |
| "loss": 1.067, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.5568445475638051, | |
| "grad_norm": 5.124932810617846, | |
| "learning_rate": 9.27767536204258e-07, | |
| "loss": 1.0664, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.580046403712297, | |
| "grad_norm": 5.129237449751678, | |
| "learning_rate": 9.212336025366787e-07, | |
| "loss": 1.0635, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.6032482598607889, | |
| "grad_norm": 5.116692236159179, | |
| "learning_rate": 9.144419221381918e-07, | |
| "loss": 1.0667, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.6264501160092807, | |
| "grad_norm": 4.99964002013004, | |
| "learning_rate": 9.073966507395121e-07, | |
| "loss": 1.0637, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.6496519721577726, | |
| "grad_norm": 5.177637510626285, | |
| "learning_rate": 9.001020992400085e-07, | |
| "loss": 1.0634, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6728538283062645, | |
| "grad_norm": 5.4138117417423075, | |
| "learning_rate": 8.925627310699274e-07, | |
| "loss": 1.0637, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.6960556844547564, | |
| "grad_norm": 5.246483799648231, | |
| "learning_rate": 8.84783159459285e-07, | |
| "loss": 1.0619, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6960556844547564, | |
| "eval_loss": 1.055559754371643, | |
| "eval_runtime": 104.7917, | |
| "eval_samples_per_second": 58.487, | |
| "eval_steps_per_second": 0.916, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.7192575406032483, | |
| "grad_norm": 5.122602649783386, | |
| "learning_rate": 8.767681446150976e-07, | |
| "loss": 1.0575, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.7424593967517401, | |
| "grad_norm": 5.29929198962553, | |
| "learning_rate": 8.68522590808682e-07, | |
| "loss": 1.0505, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.765661252900232, | |
| "grad_norm": 4.828480264754899, | |
| "learning_rate": 8.600515433748001e-07, | |
| "loss": 1.0518, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.7888631090487239, | |
| "grad_norm": 5.567752966669097, | |
| "learning_rate": 8.51360185624495e-07, | |
| "loss": 1.0378, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.8120649651972158, | |
| "grad_norm": 5.249257083574839, | |
| "learning_rate": 8.424538356734956e-07, | |
| "loss": 1.0358, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.8352668213457076, | |
| "grad_norm": 5.3602912051067575, | |
| "learning_rate": 8.333379431881397e-07, | |
| "loss": 1.0199, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.8584686774941995, | |
| "grad_norm": 5.127092342189952, | |
| "learning_rate": 8.240180860508026e-07, | |
| "loss": 1.0404, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.8816705336426914, | |
| "grad_norm": 4.841085798771151, | |
| "learning_rate": 8.144999669468713e-07, | |
| "loss": 1.0537, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.9048723897911833, | |
| "grad_norm": 4.891876601750079, | |
| "learning_rate": 8.047894098753539e-07, | |
| "loss": 1.0461, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.9280742459396751, | |
| "grad_norm": 5.235026926317955, | |
| "learning_rate": 7.948923565852597e-07, | |
| "loss": 1.0468, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.9280742459396751, | |
| "eval_loss": 1.0335279703140259, | |
| "eval_runtime": 104.9086, | |
| "eval_samples_per_second": 58.422, | |
| "eval_steps_per_second": 0.915, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.951276102088167, | |
| "grad_norm": 5.158788907122558, | |
| "learning_rate": 7.848148629399285e-07, | |
| "loss": 1.0159, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.974477958236659, | |
| "grad_norm": 5.333986831951347, | |
| "learning_rate": 7.745630952115363e-07, | |
| "loss": 1.0224, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.9976798143851509, | |
| "grad_norm": 4.977110057341932, | |
| "learning_rate": 7.641433263080418e-07, | |
| "loss": 1.0242, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.0208816705336428, | |
| "grad_norm": 5.799017323239554, | |
| "learning_rate": 7.535619319348865e-07, | |
| "loss": 0.9359, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.0440835266821347, | |
| "grad_norm": 5.8085173406660955, | |
| "learning_rate": 7.428253866937918e-07, | |
| "loss": 0.9014, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.0672853828306264, | |
| "grad_norm": 5.888836993626545, | |
| "learning_rate": 7.319402601210447e-07, | |
| "loss": 0.8932, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.0904872389791183, | |
| "grad_norm": 5.701985019154487, | |
| "learning_rate": 7.209132126676933e-07, | |
| "loss": 0.8953, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.1136890951276102, | |
| "grad_norm": 5.4287275730825, | |
| "learning_rate": 7.097509916241145e-07, | |
| "loss": 0.9011, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.136890951276102, | |
| "grad_norm": 5.486828404933326, | |
| "learning_rate": 6.984604269914436e-07, | |
| "loss": 0.879, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.160092807424594, | |
| "grad_norm": 5.841423335192377, | |
| "learning_rate": 6.870484273023967e-07, | |
| "loss": 0.8999, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.160092807424594, | |
| "eval_loss": 1.0276210308074951, | |
| "eval_runtime": 104.8459, | |
| "eval_samples_per_second": 58.457, | |
| "eval_steps_per_second": 0.916, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.1832946635730859, | |
| "grad_norm": 6.104179231791857, | |
| "learning_rate": 6.755219753940388e-07, | |
| "loss": 0.8799, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.2064965197215778, | |
| "grad_norm": 5.683759928140861, | |
| "learning_rate": 6.638881241350883e-07, | |
| "loss": 0.8848, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.2296983758700697, | |
| "grad_norm": 6.2781173429736565, | |
| "learning_rate": 6.52153992110368e-07, | |
| "loss": 0.8753, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.2529002320185616, | |
| "grad_norm": 5.1836939832127555, | |
| "learning_rate": 6.403267592650466e-07, | |
| "loss": 0.8898, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.2761020881670533, | |
| "grad_norm": 5.855887931011074, | |
| "learning_rate": 6.28413662511334e-07, | |
| "loss": 0.8782, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.2993039443155452, | |
| "grad_norm": 5.740445426512396, | |
| "learning_rate": 6.164219913003207e-07, | |
| "loss": 0.8931, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.322505800464037, | |
| "grad_norm": 5.566584948356301, | |
| "learning_rate": 6.043590831616676e-07, | |
| "loss": 0.8696, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 1.345707656612529, | |
| "grad_norm": 6.107582813588156, | |
| "learning_rate": 5.92232319213878e-07, | |
| "loss": 0.8822, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.368909512761021, | |
| "grad_norm": 5.795907587506582, | |
| "learning_rate": 5.800491196478988e-07, | |
| "loss": 0.8995, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 1.3921113689095128, | |
| "grad_norm": 5.6643118349028425, | |
| "learning_rate": 5.678169391868127e-07, | |
| "loss": 0.8818, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.3921113689095128, | |
| "eval_loss": 1.016647219657898, | |
| "eval_runtime": 104.7971, | |
| "eval_samples_per_second": 58.484, | |
| "eval_steps_per_second": 0.916, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.4153132250580047, | |
| "grad_norm": 5.390536356888803, | |
| "learning_rate": 5.555432625244023e-07, | |
| "loss": 0.866, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 1.4385150812064964, | |
| "grad_norm": 5.526626348796313, | |
| "learning_rate": 5.432355997453728e-07, | |
| "loss": 0.8807, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.4617169373549883, | |
| "grad_norm": 5.944664241466763, | |
| "learning_rate": 5.309014817300421e-07, | |
| "loss": 0.8874, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.4849187935034802, | |
| "grad_norm": 5.3905922077833335, | |
| "learning_rate": 5.185484555463026e-07, | |
| "loss": 0.8798, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.5081206496519721, | |
| "grad_norm": 6.160504369378942, | |
| "learning_rate": 5.061840798316814e-07, | |
| "loss": 0.8941, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.531322505800464, | |
| "grad_norm": 5.8405554397510695, | |
| "learning_rate": 4.938159201683186e-07, | |
| "loss": 0.8825, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.554524361948956, | |
| "grad_norm": 5.674379527635317, | |
| "learning_rate": 4.814515444536974e-07, | |
| "loss": 0.8648, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 1.5777262180974478, | |
| "grad_norm": 5.647819914588787, | |
| "learning_rate": 4.69098518269958e-07, | |
| "loss": 0.8767, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.6009280742459397, | |
| "grad_norm": 5.823124283337199, | |
| "learning_rate": 4.5676440025462726e-07, | |
| "loss": 0.8819, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 1.6241299303944317, | |
| "grad_norm": 5.627075817812563, | |
| "learning_rate": 4.444567374755977e-07, | |
| "loss": 0.8729, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.6241299303944317, | |
| "eval_loss": 1.0092262029647827, | |
| "eval_runtime": 104.5371, | |
| "eval_samples_per_second": 58.63, | |
| "eval_steps_per_second": 0.918, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.6473317865429236, | |
| "grad_norm": 5.606729222247986, | |
| "learning_rate": 4.3218306081318713e-07, | |
| "loss": 0.8701, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 1.6705336426914155, | |
| "grad_norm": 5.850125242783924, | |
| "learning_rate": 4.199508803521012e-07, | |
| "loss": 0.8668, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.6937354988399071, | |
| "grad_norm": 5.9911899428687265, | |
| "learning_rate": 4.0776768078612207e-07, | |
| "loss": 0.8746, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 1.716937354988399, | |
| "grad_norm": 5.521154120946142, | |
| "learning_rate": 3.9564091683833244e-07, | |
| "loss": 0.8796, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.740139211136891, | |
| "grad_norm": 5.8275802651476525, | |
| "learning_rate": 3.835780086996793e-07, | |
| "loss": 0.8694, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.7633410672853829, | |
| "grad_norm": 5.543421042435622, | |
| "learning_rate": 3.7158633748866607e-07, | |
| "loss": 0.8807, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.7865429234338746, | |
| "grad_norm": 5.701862114223059, | |
| "learning_rate": 3.596732407349536e-07, | |
| "loss": 0.8759, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 1.8097447795823665, | |
| "grad_norm": 6.043389558191902, | |
| "learning_rate": 3.4784600788963193e-07, | |
| "loss": 0.8809, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.8329466357308584, | |
| "grad_norm": 5.976724503752257, | |
| "learning_rate": 3.3611187586491157e-07, | |
| "loss": 0.8709, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 1.8561484918793503, | |
| "grad_norm": 5.509505876146179, | |
| "learning_rate": 3.244780246059612e-07, | |
| "loss": 0.8653, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.8561484918793503, | |
| "eval_loss": 1.0026302337646484, | |
| "eval_runtime": 104.9261, | |
| "eval_samples_per_second": 58.413, | |
| "eval_steps_per_second": 0.915, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.8793503480278422, | |
| "grad_norm": 5.4679176985684075, | |
| "learning_rate": 3.129515726976034e-07, | |
| "loss": 0.8623, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 1.902552204176334, | |
| "grad_norm": 5.2503978399283495, | |
| "learning_rate": 3.015395730085565e-07, | |
| "loss": 0.8675, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.925754060324826, | |
| "grad_norm": 5.67660650040009, | |
| "learning_rate": 2.902490083758856e-07, | |
| "loss": 0.8593, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 1.948955916473318, | |
| "grad_norm": 5.817460747815204, | |
| "learning_rate": 2.790867873323067e-07, | |
| "loss": 0.8802, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.9721577726218098, | |
| "grad_norm": 5.711721871686218, | |
| "learning_rate": 2.680597398789554e-07, | |
| "loss": 0.866, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.9953596287703017, | |
| "grad_norm": 5.71044846682499, | |
| "learning_rate": 2.5717461330620815e-07, | |
| "loss": 0.8874, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.0185614849187936, | |
| "grad_norm": 6.131631291570077, | |
| "learning_rate": 2.464380680651134e-07, | |
| "loss": 0.8141, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 2.0417633410672855, | |
| "grad_norm": 6.411927697119563, | |
| "learning_rate": 2.358566736919581e-07, | |
| "loss": 0.7797, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.0649651972157774, | |
| "grad_norm": 6.319794142930513, | |
| "learning_rate": 2.2543690478846388e-07, | |
| "loss": 0.7814, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 2.0881670533642693, | |
| "grad_norm": 6.218375120452989, | |
| "learning_rate": 2.1518513706007152e-07, | |
| "loss": 0.7781, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.0881670533642693, | |
| "eval_loss": 1.0152158737182617, | |
| "eval_runtime": 104.5587, | |
| "eval_samples_per_second": 58.618, | |
| "eval_steps_per_second": 0.918, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.111368909512761, | |
| "grad_norm": 6.087242686632992, | |
| "learning_rate": 2.051076434147403e-07, | |
| "loss": 0.7741, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 2.1345707656612527, | |
| "grad_norm": 5.953785056646644, | |
| "learning_rate": 1.9521059012464607e-07, | |
| "loss": 0.7806, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.1577726218097446, | |
| "grad_norm": 5.8793630013973095, | |
| "learning_rate": 1.855000330531289e-07, | |
| "loss": 0.7808, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 2.1809744779582365, | |
| "grad_norm": 5.810194372043576, | |
| "learning_rate": 1.7598191394919737e-07, | |
| "loss": 0.7805, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.2041763341067284, | |
| "grad_norm": 5.9259754232937665, | |
| "learning_rate": 1.666620568118603e-07, | |
| "loss": 0.7951, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 2.2273781902552203, | |
| "grad_norm": 5.746190339722776, | |
| "learning_rate": 1.5754616432650443e-07, | |
| "loss": 0.776, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.2505800464037122, | |
| "grad_norm": 5.8343296636667175, | |
| "learning_rate": 1.4863981437550498e-07, | |
| "loss": 0.7721, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 2.273781902552204, | |
| "grad_norm": 6.355429399217548, | |
| "learning_rate": 1.3994845662519983e-07, | |
| "loss": 0.7755, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.296983758700696, | |
| "grad_norm": 6.250949867364635, | |
| "learning_rate": 1.3147740919131812e-07, | |
| "loss": 0.786, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 2.320185614849188, | |
| "grad_norm": 5.784318706374051, | |
| "learning_rate": 1.2323185538490228e-07, | |
| "loss": 0.7742, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.320185614849188, | |
| "eval_loss": 1.0131419897079468, | |
| "eval_runtime": 104.864, | |
| "eval_samples_per_second": 58.447, | |
| "eval_steps_per_second": 0.915, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.34338747099768, | |
| "grad_norm": 5.9222096032764435, | |
| "learning_rate": 1.1521684054071523e-07, | |
| "loss": 0.7683, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 2.3665893271461718, | |
| "grad_norm": 6.101554765204232, | |
| "learning_rate": 1.0743726893007254e-07, | |
| "loss": 0.7757, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.3897911832946637, | |
| "grad_norm": 6.042489298416156, | |
| "learning_rate": 9.989790075999144e-08, | |
| "loss": 0.7705, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 2.4129930394431556, | |
| "grad_norm": 5.908756215523099, | |
| "learning_rate": 9.260334926048785e-08, | |
| "loss": 0.7732, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.4361948955916475, | |
| "grad_norm": 6.244145835259339, | |
| "learning_rate": 8.555807786180813e-08, | |
| "loss": 0.789, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 2.4593967517401394, | |
| "grad_norm": 6.142728167500032, | |
| "learning_rate": 7.876639746332131e-08, | |
| "loss": 0.7868, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.4825986078886313, | |
| "grad_norm": 6.195576909414474, | |
| "learning_rate": 7.223246379574205e-08, | |
| "loss": 0.7794, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 2.505800464037123, | |
| "grad_norm": 6.114972696221882, | |
| "learning_rate": 6.596027487829913e-08, | |
| "loss": 0.7786, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.529002320185615, | |
| "grad_norm": 5.970384712179319, | |
| "learning_rate": 5.995366857240591e-08, | |
| "loss": 0.7677, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 2.5522041763341066, | |
| "grad_norm": 5.792971865825656, | |
| "learning_rate": 5.421632023332778e-08, | |
| "loss": 0.7689, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.5522041763341066, | |
| "eval_loss": 1.0137938261032104, | |
| "eval_runtime": 104.8642, | |
| "eval_samples_per_second": 58.447, | |
| "eval_steps_per_second": 0.915, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.5754060324825985, | |
| "grad_norm": 5.910460030086388, | |
| "learning_rate": 4.8751740461286826e-08, | |
| "loss": 0.775, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 2.5986078886310904, | |
| "grad_norm": 6.1429755184015535, | |
| "learning_rate": 4.356327295337542e-08, | |
| "loss": 0.7699, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.6218097447795823, | |
| "grad_norm": 6.192833297686972, | |
| "learning_rate": 3.865409245759671e-08, | |
| "loss": 0.7733, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 2.645011600928074, | |
| "grad_norm": 6.234290188401347, | |
| "learning_rate": 3.402720283028277e-08, | |
| "loss": 0.7685, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.668213457076566, | |
| "grad_norm": 6.340392302497708, | |
| "learning_rate": 2.968543519807809e-08, | |
| "loss": 0.7884, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 2.691415313225058, | |
| "grad_norm": 6.2140159508315955, | |
| "learning_rate": 2.5631446225614527e-08, | |
| "loss": 0.7837, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.71461716937355, | |
| "grad_norm": 6.1288577970328575, | |
| "learning_rate": 2.1867716489936294e-08, | |
| "loss": 0.7813, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 2.737819025522042, | |
| "grad_norm": 6.397654652667995, | |
| "learning_rate": 1.8396548962671454e-08, | |
| "loss": 0.7775, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.7610208816705337, | |
| "grad_norm": 6.034802257671803, | |
| "learning_rate": 1.5220067600876684e-08, | |
| "loss": 0.7674, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 2.7842227378190256, | |
| "grad_norm": 6.568866077043727, | |
| "learning_rate": 1.2340216047418694e-08, | |
| "loss": 0.7824, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.7842227378190256, | |
| "eval_loss": 1.0129340887069702, | |
| "eval_runtime": 104.6371, | |
| "eval_samples_per_second": 58.574, | |
| "eval_steps_per_second": 0.917, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.8074245939675175, | |
| "grad_norm": 5.954722052193834, | |
| "learning_rate": 9.758756441687332e-09, | |
| "loss": 0.7668, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 2.8306264501160094, | |
| "grad_norm": 5.969817376300994, | |
| "learning_rate": 7.477268341368359e-09, | |
| "loss": 0.7727, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.853828306264501, | |
| "grad_norm": 6.216712316873081, | |
| "learning_rate": 5.497147755934628e-09, | |
| "loss": 0.7749, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 2.877030162412993, | |
| "grad_norm": 5.796077454156364, | |
| "learning_rate": 3.819606292448541e-09, | |
| "loss": 0.7734, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.9002320185614847, | |
| "grad_norm": 6.10165963135605, | |
| "learning_rate": 2.4456704141967433e-09, | |
| "loss": 0.7798, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 2.9234338747099766, | |
| "grad_norm": 5.84098005395959, | |
| "learning_rate": 1.3761808126126483e-09, | |
| "loss": 0.7684, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.9466357308584685, | |
| "grad_norm": 6.284934992265928, | |
| "learning_rate": 6.117918928693622e-10, | |
| "loss": 0.7664, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 2.9698375870069604, | |
| "grad_norm": 6.05781836596347, | |
| "learning_rate": 1.529713734584326e-10, | |
| "loss": 0.7692, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.9930394431554523, | |
| "grad_norm": 6.23938718298016, | |
| "learning_rate": 0.0, | |
| "loss": 0.7789, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 2.9930394431554523, | |
| "step": 645, | |
| "total_flos": 3802978389590016.0, | |
| "train_loss": 0.923209237682727, | |
| "train_runtime": 9905.6925, | |
| "train_samples_per_second": 16.704, | |
| "train_steps_per_second": 0.065 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 645, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3802978389590016.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |