| { | |
| "best_global_step": 1200, | |
| "best_metric": 0.01394818, | |
| "best_model_checkpoint": "/home/serusr01/new/output/v48-20251225-153152/checkpoint-1200", | |
| "epoch": 0.5176876617773943, | |
| "eval_steps": 100, | |
| "global_step": 1200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "acc": 0.5208333333333334, | |
| "epoch": 0.0004314063848144953, | |
| "grad_norm": 144.0, | |
| "learning_rate": 5.999997244730563e-06, | |
| "loss": 1.0161079168319702, | |
| "step": 1 | |
| }, | |
| { | |
| "acc": 0.8512820512820513, | |
| "epoch": 0.0021570319240724763, | |
| "grad_norm": 12.3125, | |
| "learning_rate": 5.9999311185171385e-06, | |
| "loss": 0.40382882952690125, | |
| "step": 5 | |
| }, | |
| { | |
| "acc": 0.8622047244094488, | |
| "epoch": 0.004314063848144953, | |
| "grad_norm": 18.75, | |
| "learning_rate": 5.999724477231659e-06, | |
| "loss": 0.35493576526641846, | |
| "step": 10 | |
| }, | |
| { | |
| "acc": 0.8986083499005965, | |
| "epoch": 0.0064710957722174285, | |
| "grad_norm": 17.0, | |
| "learning_rate": 5.9993800856327355e-06, | |
| "loss": 0.29610111713409426, | |
| "step": 15 | |
| }, | |
| { | |
| "acc": 0.8972868217054264, | |
| "epoch": 0.008628127696289905, | |
| "grad_norm": 9.125, | |
| "learning_rate": 5.998897959535169e-06, | |
| "loss": 0.302515435218811, | |
| "step": 20 | |
| }, | |
| { | |
| "acc": 0.876953125, | |
| "epoch": 0.010785159620362382, | |
| "grad_norm": 14.9375, | |
| "learning_rate": 5.998278121078668e-06, | |
| "loss": 0.3312162160873413, | |
| "step": 25 | |
| }, | |
| { | |
| "acc": 0.8975903614457831, | |
| "epoch": 0.012942191544434857, | |
| "grad_norm": 13.375, | |
| "learning_rate": 5.997520598726825e-06, | |
| "loss": 0.30696473121643064, | |
| "step": 30 | |
| }, | |
| { | |
| "acc": 0.8742632612966601, | |
| "epoch": 0.015099223468507334, | |
| "grad_norm": 13.25, | |
| "learning_rate": 5.996625427265816e-06, | |
| "loss": 0.36511917114257814, | |
| "step": 35 | |
| }, | |
| { | |
| "acc": 0.8631790744466801, | |
| "epoch": 0.01725625539257981, | |
| "grad_norm": 9.3125, | |
| "learning_rate": 5.995592647802802e-06, | |
| "loss": 0.338372015953064, | |
| "step": 40 | |
| }, | |
| { | |
| "acc": 0.8964803312629399, | |
| "epoch": 0.019413287316652286, | |
| "grad_norm": 6.0, | |
| "learning_rate": 5.9944223077640325e-06, | |
| "loss": 0.32863070964813235, | |
| "step": 45 | |
| }, | |
| { | |
| "acc": 0.8957915831663327, | |
| "epoch": 0.021570319240724764, | |
| "grad_norm": 7.96875, | |
| "learning_rate": 5.993114460892682e-06, | |
| "loss": 0.27804901599884035, | |
| "step": 50 | |
| }, | |
| { | |
| "acc": 0.8773006134969326, | |
| "epoch": 0.02372735116479724, | |
| "grad_norm": 8.9375, | |
| "learning_rate": 5.9916691672463725e-06, | |
| "loss": 0.31299686431884766, | |
| "step": 55 | |
| }, | |
| { | |
| "acc": 0.9154929577464789, | |
| "epoch": 0.025884383088869714, | |
| "grad_norm": 9.1875, | |
| "learning_rate": 5.990086493194415e-06, | |
| "loss": 0.2637639045715332, | |
| "step": 60 | |
| }, | |
| { | |
| "acc": 0.8927125506072875, | |
| "epoch": 0.028041415012942193, | |
| "grad_norm": 9.5, | |
| "learning_rate": 5.988366511414766e-06, | |
| "loss": 0.30198609828948975, | |
| "step": 65 | |
| }, | |
| { | |
| "acc": 0.9156118143459916, | |
| "epoch": 0.030198446937014668, | |
| "grad_norm": 9.0625, | |
| "learning_rate": 5.986509300890691e-06, | |
| "loss": 0.24096782207489015, | |
| "step": 70 | |
| }, | |
| { | |
| "acc": 0.8798449612403101, | |
| "epoch": 0.032355478861087146, | |
| "grad_norm": 7.4375, | |
| "learning_rate": 5.984514946907133e-06, | |
| "loss": 0.2953530550003052, | |
| "step": 75 | |
| }, | |
| { | |
| "acc": 0.8818737270875764, | |
| "epoch": 0.03451251078515962, | |
| "grad_norm": 15.9375, | |
| "learning_rate": 5.982383541046798e-06, | |
| "loss": 0.3139867067337036, | |
| "step": 80 | |
| }, | |
| { | |
| "acc": 0.9300567107750473, | |
| "epoch": 0.036669542709232096, | |
| "grad_norm": 6.5, | |
| "learning_rate": 5.98011518118595e-06, | |
| "loss": 0.20404579639434814, | |
| "step": 85 | |
| }, | |
| { | |
| "acc": 0.9036885245901639, | |
| "epoch": 0.03882657463330457, | |
| "grad_norm": 9.75, | |
| "learning_rate": 5.977709971489917e-06, | |
| "loss": 0.2777871131896973, | |
| "step": 90 | |
| }, | |
| { | |
| "acc": 0.8767676767676768, | |
| "epoch": 0.040983606557377046, | |
| "grad_norm": 12.3125, | |
| "learning_rate": 5.975168022408304e-06, | |
| "loss": 0.31117370128631594, | |
| "step": 95 | |
| }, | |
| { | |
| "acc": 0.9202334630350194, | |
| "epoch": 0.04314063848144953, | |
| "grad_norm": 5.9375, | |
| "learning_rate": 5.972489450669929e-06, | |
| "loss": 0.23061840534210204, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04314063848144953, | |
| "eval_acc": 0.9116072164099185, | |
| "eval_loss": 0.031446851789951324, | |
| "eval_mrr": 0.8872438524590165, | |
| "eval_ndcg": 0.9145527118078347, | |
| "eval_runtime": 92.9513, | |
| "eval_samples_per_second": 21.0, | |
| "eval_steps_per_second": 10.5, | |
| "step": 100 | |
| }, | |
| { | |
| "acc": 0.9188118811881189, | |
| "epoch": 0.045297670405522, | |
| "grad_norm": 10.6875, | |
| "learning_rate": 5.969674379277452e-06, | |
| "loss": 0.253974175453186, | |
| "step": 105 | |
| }, | |
| { | |
| "acc": 0.916030534351145, | |
| "epoch": 0.04745470232959448, | |
| "grad_norm": 8.5, | |
| "learning_rate": 5.9667229375017345e-06, | |
| "loss": 0.21623244285583496, | |
| "step": 110 | |
| }, | |
| { | |
| "acc": 0.9288461538461539, | |
| "epoch": 0.04961173425366695, | |
| "grad_norm": 9.4375, | |
| "learning_rate": 5.9636352608759e-06, | |
| "loss": 0.2198498487472534, | |
| "step": 115 | |
| }, | |
| { | |
| "acc": 0.8913480885311871, | |
| "epoch": 0.05176876617773943, | |
| "grad_norm": 10.1875, | |
| "learning_rate": 5.960411491189113e-06, | |
| "loss": 0.3081125497817993, | |
| "step": 120 | |
| }, | |
| { | |
| "acc": 0.8951612903225806, | |
| "epoch": 0.05392579810181191, | |
| "grad_norm": 10.125, | |
| "learning_rate": 5.957051776480063e-06, | |
| "loss": 0.2795823335647583, | |
| "step": 125 | |
| }, | |
| { | |
| "acc": 0.91, | |
| "epoch": 0.056082830025884385, | |
| "grad_norm": 10.375, | |
| "learning_rate": 5.953556271030172e-06, | |
| "loss": 0.24584596157073973, | |
| "step": 130 | |
| }, | |
| { | |
| "acc": 0.9195402298850575, | |
| "epoch": 0.05823986194995686, | |
| "grad_norm": 10.0, | |
| "learning_rate": 5.949925135356506e-06, | |
| "loss": 0.20374622344970703, | |
| "step": 135 | |
| }, | |
| { | |
| "acc": 0.9190283400809717, | |
| "epoch": 0.060396893874029335, | |
| "grad_norm": 13.25, | |
| "learning_rate": 5.946158536204403e-06, | |
| "loss": 0.2638064384460449, | |
| "step": 140 | |
| }, | |
| { | |
| "acc": 0.9001956947162426, | |
| "epoch": 0.06255392579810182, | |
| "grad_norm": 7.21875, | |
| "learning_rate": 5.942256646539821e-06, | |
| "loss": 0.2462130069732666, | |
| "step": 145 | |
| }, | |
| { | |
| "acc": 0.9201520912547528, | |
| "epoch": 0.06471095772217429, | |
| "grad_norm": 7.21875, | |
| "learning_rate": 5.9382196455413914e-06, | |
| "loss": 0.25420570373535156, | |
| "step": 150 | |
| }, | |
| { | |
| "acc": 0.9288702928870293, | |
| "epoch": 0.06686798964624677, | |
| "grad_norm": 10.1875, | |
| "learning_rate": 5.9340477185921895e-06, | |
| "loss": 0.2146221160888672, | |
| "step": 155 | |
| }, | |
| { | |
| "acc": 0.904397705544933, | |
| "epoch": 0.06902502157031924, | |
| "grad_norm": 27.875, | |
| "learning_rate": 5.9297410572712245e-06, | |
| "loss": 0.2619572877883911, | |
| "step": 160 | |
| }, | |
| { | |
| "acc": 0.903041825095057, | |
| "epoch": 0.07118205349439172, | |
| "grad_norm": 8.1875, | |
| "learning_rate": 5.925299859344643e-06, | |
| "loss": 0.2647380352020264, | |
| "step": 165 | |
| }, | |
| { | |
| "acc": 0.9238095238095239, | |
| "epoch": 0.07333908541846419, | |
| "grad_norm": 9.75, | |
| "learning_rate": 5.9207243287566444e-06, | |
| "loss": 0.2059628963470459, | |
| "step": 170 | |
| }, | |
| { | |
| "acc": 0.9080234833659491, | |
| "epoch": 0.07549611734253667, | |
| "grad_norm": 19.0, | |
| "learning_rate": 5.916014675620117e-06, | |
| "loss": 0.22357699871063233, | |
| "step": 175 | |
| }, | |
| { | |
| "acc": 0.9107883817427386, | |
| "epoch": 0.07765314926660914, | |
| "grad_norm": 12.125, | |
| "learning_rate": 5.911171116206986e-06, | |
| "loss": 0.23458666801452638, | |
| "step": 180 | |
| }, | |
| { | |
| "acc": 0.9092664092664092, | |
| "epoch": 0.07981018119068162, | |
| "grad_norm": 10.3125, | |
| "learning_rate": 5.9061938729382915e-06, | |
| "loss": 0.2300126552581787, | |
| "step": 185 | |
| }, | |
| { | |
| "acc": 0.924901185770751, | |
| "epoch": 0.08196721311475409, | |
| "grad_norm": 12.25, | |
| "learning_rate": 5.901083174373961e-06, | |
| "loss": 0.21468648910522461, | |
| "step": 190 | |
| }, | |
| { | |
| "acc": 0.9180327868852459, | |
| "epoch": 0.08412424503882658, | |
| "grad_norm": 9.375, | |
| "learning_rate": 5.895839255202328e-06, | |
| "loss": 0.2179854154586792, | |
| "step": 195 | |
| }, | |
| { | |
| "acc": 0.935871743486974, | |
| "epoch": 0.08628127696289906, | |
| "grad_norm": 11.9375, | |
| "learning_rate": 5.8904623562293435e-06, | |
| "loss": 0.22542862892150878, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.08628127696289906, | |
| "eval_acc": 0.9252821484471538, | |
| "eval_loss": 0.02712932601571083, | |
| "eval_mrr": 0.9001439305230289, | |
| "eval_ndcg": 0.9243608674894062, | |
| "eval_runtime": 85.9276, | |
| "eval_samples_per_second": 22.717, | |
| "eval_steps_per_second": 11.358, | |
| "step": 200 | |
| }, | |
| { | |
| "acc": 0.9358178053830227, | |
| "epoch": 0.08843830888697153, | |
| "grad_norm": 5.96875, | |
| "learning_rate": 5.884952724367524e-06, | |
| "loss": 0.20223827362060548, | |
| "step": 205 | |
| }, | |
| { | |
| "acc": 0.9375, | |
| "epoch": 0.090595340811044, | |
| "grad_norm": 7.1875, | |
| "learning_rate": 5.879310612624611e-06, | |
| "loss": 0.19913212060928345, | |
| "step": 210 | |
| }, | |
| { | |
| "acc": 0.9217557251908397, | |
| "epoch": 0.09275237273511648, | |
| "grad_norm": 18.5, | |
| "learning_rate": 5.873536280091955e-06, | |
| "loss": 0.21275293827056885, | |
| "step": 215 | |
| }, | |
| { | |
| "acc": 0.9144050104384134, | |
| "epoch": 0.09490940465918896, | |
| "grad_norm": 14.375, | |
| "learning_rate": 5.867629991932611e-06, | |
| "loss": 0.23634729385375977, | |
| "step": 220 | |
| }, | |
| { | |
| "acc": 0.9239766081871345, | |
| "epoch": 0.09706643658326143, | |
| "grad_norm": 13.125, | |
| "learning_rate": 5.861592019369172e-06, | |
| "loss": 0.2160120725631714, | |
| "step": 225 | |
| }, | |
| { | |
| "acc": 0.8967611336032388, | |
| "epoch": 0.0992234685073339, | |
| "grad_norm": 12.0625, | |
| "learning_rate": 5.855422639671309e-06, | |
| "loss": 0.25560975074768066, | |
| "step": 230 | |
| }, | |
| { | |
| "acc": 0.9405940594059405, | |
| "epoch": 0.10138050043140638, | |
| "grad_norm": 11.3125, | |
| "learning_rate": 5.849122136143034e-06, | |
| "loss": 0.20292723178863525, | |
| "step": 235 | |
| }, | |
| { | |
| "acc": 0.9289827255278311, | |
| "epoch": 0.10353753235547886, | |
| "grad_norm": 16.125, | |
| "learning_rate": 5.842690798109697e-06, | |
| "loss": 0.19165314435958863, | |
| "step": 240 | |
| }, | |
| { | |
| "acc": 0.9137931034482759, | |
| "epoch": 0.10569456427955133, | |
| "grad_norm": 14.375, | |
| "learning_rate": 5.8361289209047004e-06, | |
| "loss": 0.22526559829711915, | |
| "step": 245 | |
| }, | |
| { | |
| "acc": 0.9123505976095617, | |
| "epoch": 0.10785159620362382, | |
| "grad_norm": 11.375, | |
| "learning_rate": 5.829436805855932e-06, | |
| "loss": 0.1998949646949768, | |
| "step": 250 | |
| }, | |
| { | |
| "acc": 0.9298245614035088, | |
| "epoch": 0.1100086281276963, | |
| "grad_norm": 9.3125, | |
| "learning_rate": 5.82261476027193e-06, | |
| "loss": 0.211327862739563, | |
| "step": 255 | |
| }, | |
| { | |
| "acc": 0.9357429718875502, | |
| "epoch": 0.11216566005176877, | |
| "grad_norm": 23.375, | |
| "learning_rate": 5.8156630974277715e-06, | |
| "loss": 0.21703736782073973, | |
| "step": 260 | |
| }, | |
| { | |
| "acc": 0.9092783505154639, | |
| "epoch": 0.11432269197584125, | |
| "grad_norm": 17.875, | |
| "learning_rate": 5.808582136550686e-06, | |
| "loss": 0.2739748954772949, | |
| "step": 265 | |
| }, | |
| { | |
| "acc": 0.9468302658486708, | |
| "epoch": 0.11647972389991372, | |
| "grad_norm": 9.9375, | |
| "learning_rate": 5.8013722028053985e-06, | |
| "loss": 0.14410748481750488, | |
| "step": 270 | |
| }, | |
| { | |
| "acc": 0.9310344827586207, | |
| "epoch": 0.1186367558239862, | |
| "grad_norm": 8.5, | |
| "learning_rate": 5.794033627279193e-06, | |
| "loss": 0.1934072494506836, | |
| "step": 275 | |
| }, | |
| { | |
| "acc": 0.9155470249520153, | |
| "epoch": 0.12079378774805867, | |
| "grad_norm": 11.4375, | |
| "learning_rate": 5.786566746966714e-06, | |
| "loss": 0.20481424331665038, | |
| "step": 280 | |
| }, | |
| { | |
| "acc": 0.9216494845360824, | |
| "epoch": 0.12295081967213115, | |
| "grad_norm": 12.5, | |
| "learning_rate": 5.778971904754485e-06, | |
| "loss": 0.22041404247283936, | |
| "step": 285 | |
| }, | |
| { | |
| "acc": 0.917864476386037, | |
| "epoch": 0.12510785159620363, | |
| "grad_norm": 19.375, | |
| "learning_rate": 5.771249449405169e-06, | |
| "loss": 0.20896604061126708, | |
| "step": 290 | |
| }, | |
| { | |
| "acc": 0.950592885375494, | |
| "epoch": 0.1272648835202761, | |
| "grad_norm": 16.875, | |
| "learning_rate": 5.763399735541551e-06, | |
| "loss": 0.1629479169845581, | |
| "step": 295 | |
| }, | |
| { | |
| "acc": 0.9405737704918032, | |
| "epoch": 0.12942191544434858, | |
| "grad_norm": 13.25, | |
| "learning_rate": 5.755423123630251e-06, | |
| "loss": 0.19808459281921387, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.12942191544434858, | |
| "eval_acc": 0.9337671966389324, | |
| "eval_loss": 0.024512404575943947, | |
| "eval_mrr": 0.9131787909836067, | |
| "eval_ndcg": 0.9342680843294187, | |
| "eval_runtime": 79.6383, | |
| "eval_samples_per_second": 24.511, | |
| "eval_steps_per_second": 12.255, | |
| "step": 300 | |
| }, | |
| { | |
| "acc": 0.9308943089430894, | |
| "epoch": 0.13157894736842105, | |
| "grad_norm": 14.125, | |
| "learning_rate": 5.747319979965173e-06, | |
| "loss": 0.20357720851898192, | |
| "step": 305 | |
| }, | |
| { | |
| "acc": 0.9433962264150944, | |
| "epoch": 0.13373597929249353, | |
| "grad_norm": 14.6875, | |
| "learning_rate": 5.739090676650683e-06, | |
| "loss": 0.15039076805114746, | |
| "step": 310 | |
| }, | |
| { | |
| "acc": 0.9392712550607287, | |
| "epoch": 0.135893011216566, | |
| "grad_norm": 8.625, | |
| "learning_rate": 5.730735591584529e-06, | |
| "loss": 0.16305069923400878, | |
| "step": 315 | |
| }, | |
| { | |
| "acc": 0.9192307692307692, | |
| "epoch": 0.13805004314063848, | |
| "grad_norm": 12.75, | |
| "learning_rate": 5.722255108440474e-06, | |
| "loss": 0.2407283067703247, | |
| "step": 320 | |
| }, | |
| { | |
| "acc": 0.9298597194388778, | |
| "epoch": 0.14020707506471095, | |
| "grad_norm": 12.125, | |
| "learning_rate": 5.713649616650687e-06, | |
| "loss": 0.2122425317764282, | |
| "step": 325 | |
| }, | |
| { | |
| "acc": 0.9352226720647774, | |
| "epoch": 0.14236410698878343, | |
| "grad_norm": 11.125, | |
| "learning_rate": 5.7049195113878585e-06, | |
| "loss": 0.19069076776504518, | |
| "step": 330 | |
| }, | |
| { | |
| "acc": 0.9189765458422174, | |
| "epoch": 0.14452113891285592, | |
| "grad_norm": 17.75, | |
| "learning_rate": 5.696065193547054e-06, | |
| "loss": 0.22681286334991455, | |
| "step": 335 | |
| }, | |
| { | |
| "acc": 0.943579766536965, | |
| "epoch": 0.14667817083692838, | |
| "grad_norm": 14.8125, | |
| "learning_rate": 5.6870870697273e-06, | |
| "loss": 0.1799636721611023, | |
| "step": 340 | |
| }, | |
| { | |
| "acc": 0.9392712550607287, | |
| "epoch": 0.14883520276100087, | |
| "grad_norm": 8.0625, | |
| "learning_rate": 5.677985552212919e-06, | |
| "loss": 0.21220760345458983, | |
| "step": 345 | |
| }, | |
| { | |
| "acc": 0.9386138613861386, | |
| "epoch": 0.15099223468507333, | |
| "grad_norm": 15.0625, | |
| "learning_rate": 5.668761058954594e-06, | |
| "loss": 0.19215874671936034, | |
| "step": 350 | |
| }, | |
| { | |
| "acc": 0.9487704918032787, | |
| "epoch": 0.15314926660914582, | |
| "grad_norm": 9.75, | |
| "learning_rate": 5.659414013550172e-06, | |
| "loss": 0.17874677181243898, | |
| "step": 355 | |
| }, | |
| { | |
| "acc": 0.9449901768172888, | |
| "epoch": 0.15530629853321828, | |
| "grad_norm": 15.1875, | |
| "learning_rate": 5.649944845225219e-06, | |
| "loss": 0.17652757167816163, | |
| "step": 360 | |
| }, | |
| { | |
| "acc": 0.9281314168377823, | |
| "epoch": 0.15746333045729077, | |
| "grad_norm": 28.25, | |
| "learning_rate": 5.6403539888133056e-06, | |
| "loss": 0.2142080545425415, | |
| "step": 365 | |
| }, | |
| { | |
| "acc": 0.950920245398773, | |
| "epoch": 0.15962036238136323, | |
| "grad_norm": 12.0625, | |
| "learning_rate": 5.63064188473604e-06, | |
| "loss": 0.17437468767166137, | |
| "step": 370 | |
| }, | |
| { | |
| "acc": 0.9422680412371134, | |
| "epoch": 0.16177739430543572, | |
| "grad_norm": 19.75, | |
| "learning_rate": 5.6208089789828435e-06, | |
| "loss": 0.18122278451919555, | |
| "step": 375 | |
| }, | |
| { | |
| "acc": 0.9439071566731141, | |
| "epoch": 0.16393442622950818, | |
| "grad_norm": 13.8125, | |
| "learning_rate": 5.610855723090466e-06, | |
| "loss": 0.18091570138931273, | |
| "step": 380 | |
| }, | |
| { | |
| "acc": 0.923728813559322, | |
| "epoch": 0.16609145815358067, | |
| "grad_norm": 29.875, | |
| "learning_rate": 5.600782574122259e-06, | |
| "loss": 0.24442174434661865, | |
| "step": 385 | |
| }, | |
| { | |
| "acc": 0.9310344827586207, | |
| "epoch": 0.16824849007765316, | |
| "grad_norm": 16.75, | |
| "learning_rate": 5.590589994647182e-06, | |
| "loss": 0.20708949565887452, | |
| "step": 390 | |
| }, | |
| { | |
| "acc": 0.9395161290322581, | |
| "epoch": 0.17040552200172562, | |
| "grad_norm": 8.0625, | |
| "learning_rate": 5.58027845271856e-06, | |
| "loss": 0.21145825386047362, | |
| "step": 395 | |
| }, | |
| { | |
| "acc": 0.9618473895582329, | |
| "epoch": 0.1725625539257981, | |
| "grad_norm": 8.5, | |
| "learning_rate": 5.569848421852592e-06, | |
| "loss": 0.12078192234039306, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.1725625539257981, | |
| "eval_acc": 0.9410989373094983, | |
| "eval_loss": 0.02222530171275139, | |
| "eval_mrr": 0.9228056693989071, | |
| "eval_ndcg": 0.9416691570915218, | |
| "eval_runtime": 87.651, | |
| "eval_samples_per_second": 22.27, | |
| "eval_steps_per_second": 11.135, | |
| "step": 400 | |
| }, | |
| { | |
| "acc": 0.951310861423221, | |
| "epoch": 0.17471958584987057, | |
| "grad_norm": 9.25, | |
| "learning_rate": 5.559300381006607e-06, | |
| "loss": 0.1467392086982727, | |
| "step": 405 | |
| }, | |
| { | |
| "acc": 0.9362139917695473, | |
| "epoch": 0.17687661777394306, | |
| "grad_norm": 9.5625, | |
| "learning_rate": 5.548634814557066e-06, | |
| "loss": 0.16467268466949464, | |
| "step": 410 | |
| }, | |
| { | |
| "acc": 0.9474671669793621, | |
| "epoch": 0.17903364969801552, | |
| "grad_norm": 21.0, | |
| "learning_rate": 5.537852212277326e-06, | |
| "loss": 0.16810253858566285, | |
| "step": 415 | |
| }, | |
| { | |
| "acc": 0.9329388560157791, | |
| "epoch": 0.181190681622088, | |
| "grad_norm": 21.75, | |
| "learning_rate": 5.5269530693151425e-06, | |
| "loss": 0.15131351947784424, | |
| "step": 420 | |
| }, | |
| { | |
| "acc": 0.9265536723163842, | |
| "epoch": 0.18334771354616047, | |
| "grad_norm": 26.25, | |
| "learning_rate": 5.5159378861699356e-06, | |
| "loss": 0.2086423635482788, | |
| "step": 425 | |
| }, | |
| { | |
| "acc": 0.9393939393939394, | |
| "epoch": 0.18550474547023296, | |
| "grad_norm": 9.875, | |
| "learning_rate": 5.504807168669804e-06, | |
| "loss": 0.19425034523010254, | |
| "step": 430 | |
| }, | |
| { | |
| "acc": 0.9387351778656127, | |
| "epoch": 0.18766177739430542, | |
| "grad_norm": 40.0, | |
| "learning_rate": 5.4935614279482984e-06, | |
| "loss": 0.1988288640975952, | |
| "step": 435 | |
| }, | |
| { | |
| "acc": 0.9350912778904665, | |
| "epoch": 0.1898188093183779, | |
| "grad_norm": 29.125, | |
| "learning_rate": 5.482201180420952e-06, | |
| "loss": 0.1814996600151062, | |
| "step": 440 | |
| }, | |
| { | |
| "acc": 0.9528688524590164, | |
| "epoch": 0.1919758412424504, | |
| "grad_norm": 17.25, | |
| "learning_rate": 5.4707269477615584e-06, | |
| "loss": 0.1311618208885193, | |
| "step": 445 | |
| }, | |
| { | |
| "acc": 0.9548872180451128, | |
| "epoch": 0.19413287316652286, | |
| "grad_norm": 21.375, | |
| "learning_rate": 5.4591392568782275e-06, | |
| "loss": 0.15495063066482545, | |
| "step": 450 | |
| }, | |
| { | |
| "acc": 0.9633204633204633, | |
| "epoch": 0.19628990509059535, | |
| "grad_norm": 14.8125, | |
| "learning_rate": 5.447438639889178e-06, | |
| "loss": 0.12518519163131714, | |
| "step": 455 | |
| }, | |
| { | |
| "acc": 0.9411764705882353, | |
| "epoch": 0.1984469370146678, | |
| "grad_norm": 17.875, | |
| "learning_rate": 5.435625634098311e-06, | |
| "loss": 0.17223405838012695, | |
| "step": 460 | |
| }, | |
| { | |
| "acc": 0.9486166007905138, | |
| "epoch": 0.2006039689387403, | |
| "grad_norm": 19.0, | |
| "learning_rate": 5.423700781970527e-06, | |
| "loss": 0.14980016946792601, | |
| "step": 465 | |
| }, | |
| { | |
| "acc": 0.9354838709677419, | |
| "epoch": 0.20276100086281276, | |
| "grad_norm": 23.0, | |
| "learning_rate": 5.411664631106827e-06, | |
| "loss": 0.1699580192565918, | |
| "step": 470 | |
| }, | |
| { | |
| "acc": 0.9409368635437881, | |
| "epoch": 0.20491803278688525, | |
| "grad_norm": 11.6875, | |
| "learning_rate": 5.399517734219159e-06, | |
| "loss": 0.2162698268890381, | |
| "step": 475 | |
| }, | |
| { | |
| "acc": 0.9535353535353536, | |
| "epoch": 0.2070750647109577, | |
| "grad_norm": 16.625, | |
| "learning_rate": 5.387260649105032e-06, | |
| "loss": 0.15655677318572997, | |
| "step": 480 | |
| }, | |
| { | |
| "acc": 0.9541984732824428, | |
| "epoch": 0.2092320966350302, | |
| "grad_norm": 14.4375, | |
| "learning_rate": 5.374893938621913e-06, | |
| "loss": 0.15797934532165528, | |
| "step": 485 | |
| }, | |
| { | |
| "acc": 0.9343629343629344, | |
| "epoch": 0.21138912855910266, | |
| "grad_norm": 6.59375, | |
| "learning_rate": 5.362418170661375e-06, | |
| "loss": 0.2039581060409546, | |
| "step": 490 | |
| }, | |
| { | |
| "acc": 0.9559386973180076, | |
| "epoch": 0.21354616048317515, | |
| "grad_norm": 16.625, | |
| "learning_rate": 5.3498339181230125e-06, | |
| "loss": 0.1275785207748413, | |
| "step": 495 | |
| }, | |
| { | |
| "acc": 0.9521988527724665, | |
| "epoch": 0.21570319240724764, | |
| "grad_norm": 8.1875, | |
| "learning_rate": 5.3371417588881456e-06, | |
| "loss": 0.16547932624816894, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.21570319240724764, | |
| "eval_acc": 0.9440645852211879, | |
| "eval_loss": 0.0200980044901371, | |
| "eval_mrr": 0.9341749609679937, | |
| "eval_ndcg": 0.9502093836313069, | |
| "eval_runtime": 89.2845, | |
| "eval_samples_per_second": 21.863, | |
| "eval_steps_per_second": 10.931, | |
| "step": 500 | |
| }, | |
| { | |
| "acc": 0.9288617886178862, | |
| "epoch": 0.2178602243313201, | |
| "grad_norm": 17.0, | |
| "learning_rate": 5.324342275793272e-06, | |
| "loss": 0.22141244411468505, | |
| "step": 505 | |
| }, | |
| { | |
| "acc": 0.9502982107355865, | |
| "epoch": 0.2200172562553926, | |
| "grad_norm": 11.0, | |
| "learning_rate": 5.3114360566033085e-06, | |
| "loss": 0.13880524635314942, | |
| "step": 510 | |
| }, | |
| { | |
| "acc": 0.9284253578732107, | |
| "epoch": 0.22217428817946505, | |
| "grad_norm": 10.125, | |
| "learning_rate": 5.298423693984598e-06, | |
| "loss": 0.22597496509552, | |
| "step": 515 | |
| }, | |
| { | |
| "acc": 0.9553398058252427, | |
| "epoch": 0.22433132010353754, | |
| "grad_norm": 20.75, | |
| "learning_rate": 5.285305785477699e-06, | |
| "loss": 0.16823456287384034, | |
| "step": 520 | |
| }, | |
| { | |
| "acc": 0.9405940594059405, | |
| "epoch": 0.22648835202761, | |
| "grad_norm": 9.875, | |
| "learning_rate": 5.272082933469936e-06, | |
| "loss": 0.18091850280761718, | |
| "step": 525 | |
| }, | |
| { | |
| "acc": 0.9634888438133874, | |
| "epoch": 0.2286453839516825, | |
| "grad_norm": 9.6875, | |
| "learning_rate": 5.258755745167744e-06, | |
| "loss": 0.13490262031555175, | |
| "step": 530 | |
| }, | |
| { | |
| "acc": 0.9320754716981132, | |
| "epoch": 0.23080241587575495, | |
| "grad_norm": 18.625, | |
| "learning_rate": 5.245324832568787e-06, | |
| "loss": 0.19664840698242186, | |
| "step": 535 | |
| }, | |
| { | |
| "acc": 0.9470588235294117, | |
| "epoch": 0.23295944779982744, | |
| "grad_norm": 10.3125, | |
| "learning_rate": 5.2317908124338475e-06, | |
| "loss": 0.14916815757751464, | |
| "step": 540 | |
| }, | |
| { | |
| "acc": 0.9350912778904665, | |
| "epoch": 0.2351164797238999, | |
| "grad_norm": 12.0625, | |
| "learning_rate": 5.21815430625851e-06, | |
| "loss": 0.1888782262802124, | |
| "step": 545 | |
| }, | |
| { | |
| "acc": 0.9365079365079365, | |
| "epoch": 0.2372735116479724, | |
| "grad_norm": 14.6875, | |
| "learning_rate": 5.204415940244618e-06, | |
| "loss": 0.18109892606735228, | |
| "step": 550 | |
| }, | |
| { | |
| "acc": 0.9479768786127167, | |
| "epoch": 0.23943054357204488, | |
| "grad_norm": 35.0, | |
| "learning_rate": 5.1905763452715215e-06, | |
| "loss": 0.150074303150177, | |
| "step": 555 | |
| }, | |
| { | |
| "acc": 0.9408284023668639, | |
| "epoch": 0.24158757549611734, | |
| "grad_norm": 10.0625, | |
| "learning_rate": 5.176636156867102e-06, | |
| "loss": 0.13501374721527098, | |
| "step": 560 | |
| }, | |
| { | |
| "acc": 0.9490196078431372, | |
| "epoch": 0.24374460742018983, | |
| "grad_norm": 11.5625, | |
| "learning_rate": 5.162596015178593e-06, | |
| "loss": 0.14429715871810914, | |
| "step": 565 | |
| }, | |
| { | |
| "acc": 0.961038961038961, | |
| "epoch": 0.2459016393442623, | |
| "grad_norm": 4.53125, | |
| "learning_rate": 5.14845656494318e-06, | |
| "loss": 0.10108070373535157, | |
| "step": 570 | |
| }, | |
| { | |
| "acc": 0.9427402862985685, | |
| "epoch": 0.24805867126833478, | |
| "grad_norm": 13.5, | |
| "learning_rate": 5.134218455458396e-06, | |
| "loss": 0.16440529823303224, | |
| "step": 575 | |
| }, | |
| { | |
| "acc": 0.9512670565302144, | |
| "epoch": 0.25021570319240727, | |
| "grad_norm": 23.0, | |
| "learning_rate": 5.119882340552303e-06, | |
| "loss": 0.15792548656463623, | |
| "step": 580 | |
| }, | |
| { | |
| "acc": 0.9310344827586207, | |
| "epoch": 0.25237273511647973, | |
| "grad_norm": 20.375, | |
| "learning_rate": 5.105448878553472e-06, | |
| "loss": 0.17942277193069459, | |
| "step": 585 | |
| }, | |
| { | |
| "acc": 0.9586614173228346, | |
| "epoch": 0.2545297670405522, | |
| "grad_norm": 6.21875, | |
| "learning_rate": 5.0909187322607434e-06, | |
| "loss": 0.1267695426940918, | |
| "step": 590 | |
| }, | |
| { | |
| "acc": 0.9421157684630739, | |
| "epoch": 0.25668679896462465, | |
| "grad_norm": 10.8125, | |
| "learning_rate": 5.076292568912801e-06, | |
| "loss": 0.17552590370178223, | |
| "step": 595 | |
| }, | |
| { | |
| "acc": 0.9418837675350702, | |
| "epoch": 0.25884383088869717, | |
| "grad_norm": 15.5625, | |
| "learning_rate": 5.061571060157525e-06, | |
| "loss": 0.1582822322845459, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.25884383088869717, | |
| "eval_acc": 0.9523848751956504, | |
| "eval_loss": 0.01805831491947174, | |
| "eval_mrr": 0.9341017759562842, | |
| "eval_ndcg": 0.9502097307474537, | |
| "eval_runtime": 80.1164, | |
| "eval_samples_per_second": 24.365, | |
| "eval_steps_per_second": 12.182, | |
| "step": 600 | |
| }, | |
| { | |
| "acc": 0.9516806722689075, | |
| "epoch": 0.26100086281276963, | |
| "grad_norm": 9.5625, | |
| "learning_rate": 5.04675488202115e-06, | |
| "loss": 0.1585369348526001, | |
| "step": 605 | |
| }, | |
| { | |
| "acc": 0.967479674796748, | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 14.375, | |
| "learning_rate": 5.031844714877224e-06, | |
| "loss": 0.14685235023498536, | |
| "step": 610 | |
| }, | |
| { | |
| "acc": 0.9669902912621359, | |
| "epoch": 0.2653149266609146, | |
| "grad_norm": 11.875, | |
| "learning_rate": 5.016841243415359e-06, | |
| "loss": 0.09848676323890686, | |
| "step": 615 | |
| }, | |
| { | |
| "acc": 0.9692622950819673, | |
| "epoch": 0.26747195858498707, | |
| "grad_norm": 11.875, | |
| "learning_rate": 5.001745156609801e-06, | |
| "loss": 0.09488856792449951, | |
| "step": 620 | |
| }, | |
| { | |
| "acc": 0.962, | |
| "epoch": 0.26962899050905953, | |
| "grad_norm": 8.625, | |
| "learning_rate": 4.9865571476877775e-06, | |
| "loss": 0.10182394981384277, | |
| "step": 625 | |
| }, | |
| { | |
| "acc": 0.9538152610441767, | |
| "epoch": 0.271786022433132, | |
| "grad_norm": 13.0, | |
| "learning_rate": 4.9712779140976725e-06, | |
| "loss": 0.14965349435806274, | |
| "step": 630 | |
| }, | |
| { | |
| "acc": 0.9563567362428842, | |
| "epoch": 0.2739430543572045, | |
| "grad_norm": 15.5625, | |
| "learning_rate": 4.9559081574769965e-06, | |
| "loss": 0.14634023904800414, | |
| "step": 635 | |
| }, | |
| { | |
| "acc": 0.9402390438247012, | |
| "epoch": 0.27610008628127697, | |
| "grad_norm": 19.875, | |
| "learning_rate": 4.9404485836201695e-06, | |
| "loss": 0.15552909374237062, | |
| "step": 640 | |
| }, | |
| { | |
| "acc": 0.9487666034155597, | |
| "epoch": 0.27825711820534943, | |
| "grad_norm": 38.25, | |
| "learning_rate": 4.924899902446105e-06, | |
| "loss": 0.16740797758102416, | |
| "step": 645 | |
| }, | |
| { | |
| "acc": 0.9620253164556962, | |
| "epoch": 0.2804141501294219, | |
| "grad_norm": 8.9375, | |
| "learning_rate": 4.909262827965613e-06, | |
| "loss": 0.13096400499343872, | |
| "step": 650 | |
| }, | |
| { | |
| "acc": 0.9373737373737374, | |
| "epoch": 0.2825711820534944, | |
| "grad_norm": 23.375, | |
| "learning_rate": 4.893538078248613e-06, | |
| "loss": 0.19330756664276122, | |
| "step": 655 | |
| }, | |
| { | |
| "acc": 0.9327902240325866, | |
| "epoch": 0.28472821397756687, | |
| "grad_norm": 31.25, | |
| "learning_rate": 4.877726375391156e-06, | |
| "loss": 0.17176212072372438, | |
| "step": 660 | |
| }, | |
| { | |
| "acc": 0.9481037924151696, | |
| "epoch": 0.28688524590163933, | |
| "grad_norm": 17.125, | |
| "learning_rate": 4.861828445482269e-06, | |
| "loss": 0.15666646957397462, | |
| "step": 665 | |
| }, | |
| { | |
| "acc": 0.9557344064386318, | |
| "epoch": 0.28904227782571185, | |
| "grad_norm": 15.875, | |
| "learning_rate": 4.8458450185706095e-06, | |
| "loss": 0.12006416320800781, | |
| "step": 670 | |
| }, | |
| { | |
| "acc": 0.9530612244897959, | |
| "epoch": 0.2911993097497843, | |
| "grad_norm": 13.375, | |
| "learning_rate": 4.829776828630942e-06, | |
| "loss": 0.12216727733612061, | |
| "step": 675 | |
| }, | |
| { | |
| "acc": 0.9454545454545454, | |
| "epoch": 0.29335634167385677, | |
| "grad_norm": 12.8125, | |
| "learning_rate": 4.813624613530434e-06, | |
| "loss": 0.1579872488975525, | |
| "step": 680 | |
| }, | |
| { | |
| "acc": 0.94831013916501, | |
| "epoch": 0.29551337359792923, | |
| "grad_norm": 10.75, | |
| "learning_rate": 4.79738911499477e-06, | |
| "loss": 0.14849933385848998, | |
| "step": 685 | |
| }, | |
| { | |
| "acc": 0.958904109589041, | |
| "epoch": 0.29767040552200175, | |
| "grad_norm": 9.125, | |
| "learning_rate": 4.781071078574092e-06, | |
| "loss": 0.12549154758453368, | |
| "step": 690 | |
| }, | |
| { | |
| "acc": 0.943359375, | |
| "epoch": 0.2998274374460742, | |
| "grad_norm": 19.25, | |
| "learning_rate": 4.764671253608765e-06, | |
| "loss": 0.11965863704681397, | |
| "step": 695 | |
| }, | |
| { | |
| "acc": 0.9474747474747475, | |
| "epoch": 0.30198446937014667, | |
| "grad_norm": 24.5, | |
| "learning_rate": 4.748190393194964e-06, | |
| "loss": 0.15644127130508423, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.30198446937014667, | |
| "eval_acc": 0.9549386275640498, | |
| "eval_loss": 0.017001556232571602, | |
| "eval_mrr": 0.9429937548790007, | |
| "eval_ndcg": 0.9569733975457528, | |
| "eval_runtime": 87.9286, | |
| "eval_samples_per_second": 22.2, | |
| "eval_steps_per_second": 11.1, | |
| "step": 700 | |
| }, | |
| { | |
| "acc": 0.9433962264150944, | |
| "epoch": 0.30414150129421913, | |
| "grad_norm": 14.875, | |
| "learning_rate": 4.731629254150091e-06, | |
| "loss": 0.1656881332397461, | |
| "step": 705 | |
| }, | |
| { | |
| "acc": 0.9484536082474226, | |
| "epoch": 0.30629853321829165, | |
| "grad_norm": 16.875, | |
| "learning_rate": 4.714988596978023e-06, | |
| "loss": 0.16551544666290283, | |
| "step": 710 | |
| }, | |
| { | |
| "acc": 0.9601593625498008, | |
| "epoch": 0.3084555651423641, | |
| "grad_norm": 13.0625, | |
| "learning_rate": 4.698269185834188e-06, | |
| "loss": 0.13289109468460084, | |
| "step": 715 | |
| }, | |
| { | |
| "acc": 0.9621928166351607, | |
| "epoch": 0.31061259706643657, | |
| "grad_norm": 6.625, | |
| "learning_rate": 4.681471788490473e-06, | |
| "loss": 0.13107165098190307, | |
| "step": 720 | |
| }, | |
| { | |
| "acc": 0.9474708171206225, | |
| "epoch": 0.3127696289905091, | |
| "grad_norm": 17.125, | |
| "learning_rate": 4.664597176299972e-06, | |
| "loss": 0.15164241790771485, | |
| "step": 725 | |
| }, | |
| { | |
| "acc": 0.9386138613861386, | |
| "epoch": 0.31492666091458155, | |
| "grad_norm": 13.25, | |
| "learning_rate": 4.647646124161557e-06, | |
| "loss": 0.14998191595077515, | |
| "step": 730 | |
| }, | |
| { | |
| "acc": 0.9588014981273408, | |
| "epoch": 0.317083692838654, | |
| "grad_norm": 17.0, | |
| "learning_rate": 4.6306194104843005e-06, | |
| "loss": 0.1452179431915283, | |
| "step": 735 | |
| }, | |
| { | |
| "acc": 0.9697542533081286, | |
| "epoch": 0.31924072476272647, | |
| "grad_norm": 21.75, | |
| "learning_rate": 4.613517817151725e-06, | |
| "loss": 0.0863348662853241, | |
| "step": 740 | |
| }, | |
| { | |
| "acc": 0.9271653543307087, | |
| "epoch": 0.321397756686799, | |
| "grad_norm": 22.25, | |
| "learning_rate": 4.596342129485904e-06, | |
| "loss": 0.2219313383102417, | |
| "step": 745 | |
| }, | |
| { | |
| "acc": 0.948559670781893, | |
| "epoch": 0.32355478861087145, | |
| "grad_norm": 17.25, | |
| "learning_rate": 4.579093136211394e-06, | |
| "loss": 0.14628000259399415, | |
| "step": 750 | |
| }, | |
| { | |
| "acc": 0.9550321199143469, | |
| "epoch": 0.3257118205349439, | |
| "grad_norm": 19.375, | |
| "learning_rate": 4.561771629419018e-06, | |
| "loss": 0.14832402467727662, | |
| "step": 755 | |
| }, | |
| { | |
| "acc": 0.9540918163672655, | |
| "epoch": 0.32786885245901637, | |
| "grad_norm": 24.875, | |
| "learning_rate": 4.544378404529493e-06, | |
| "loss": 0.16552494764328002, | |
| "step": 760 | |
| }, | |
| { | |
| "acc": 0.9468302658486708, | |
| "epoch": 0.3300258843830889, | |
| "grad_norm": 11.75, | |
| "learning_rate": 4.526914260256897e-06, | |
| "loss": 0.18186469078063966, | |
| "step": 765 | |
| }, | |
| { | |
| "acc": 0.9342915811088296, | |
| "epoch": 0.33218291630716135, | |
| "grad_norm": 29.0, | |
| "learning_rate": 4.509379998572003e-06, | |
| "loss": 0.189409601688385, | |
| "step": 770 | |
| }, | |
| { | |
| "acc": 0.9652509652509652, | |
| "epoch": 0.3343399482312338, | |
| "grad_norm": 8.125, | |
| "learning_rate": 4.491776424665441e-06, | |
| "loss": 0.11067872047424317, | |
| "step": 775 | |
| }, | |
| { | |
| "acc": 0.9634408602150538, | |
| "epoch": 0.3364969801553063, | |
| "grad_norm": 19.125, | |
| "learning_rate": 4.474104346910724e-06, | |
| "loss": 0.12605880498886107, | |
| "step": 780 | |
| }, | |
| { | |
| "acc": 0.9620493358633776, | |
| "epoch": 0.3386540120793788, | |
| "grad_norm": 16.625, | |
| "learning_rate": 4.4563645768271375e-06, | |
| "loss": 0.1279581904411316, | |
| "step": 785 | |
| }, | |
| { | |
| "acc": 0.9608610567514677, | |
| "epoch": 0.34081104400345125, | |
| "grad_norm": 26.125, | |
| "learning_rate": 4.438557929042457e-06, | |
| "loss": 0.13559631109237671, | |
| "step": 790 | |
| }, | |
| { | |
| "acc": 0.963265306122449, | |
| "epoch": 0.3429680759275237, | |
| "grad_norm": 16.75, | |
| "learning_rate": 4.4206852212555544e-06, | |
| "loss": 0.11860382556915283, | |
| "step": 795 | |
| }, | |
| { | |
| "acc": 0.9424184261036468, | |
| "epoch": 0.3451251078515962, | |
| "grad_norm": 27.25, | |
| "learning_rate": 4.402747274198838e-06, | |
| "loss": 0.1454222559928894, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.3451251078515962, | |
| "eval_acc": 0.9581514128017135, | |
| "eval_loss": 0.01614278368651867, | |
| "eval_mrr": 0.9435499609679938, | |
| "eval_ndcg": 0.9573436789903933, | |
| "eval_runtime": 106.3602, | |
| "eval_samples_per_second": 18.353, | |
| "eval_steps_per_second": 9.176, | |
| "step": 800 | |
| }, | |
| { | |
| "acc": 0.9533468559837728, | |
| "epoch": 0.3472821397756687, | |
| "grad_norm": 23.125, | |
| "learning_rate": 4.384744911600571e-06, | |
| "loss": 0.15178160667419432, | |
| "step": 805 | |
| }, | |
| { | |
| "acc": 0.9653767820773931, | |
| "epoch": 0.34943917169974115, | |
| "grad_norm": 16.625, | |
| "learning_rate": 4.36667896014704e-06, | |
| "loss": 0.12023615837097168, | |
| "step": 810 | |
| }, | |
| { | |
| "acc": 0.9449715370018975, | |
| "epoch": 0.3515962036238136, | |
| "grad_norm": 15.0625, | |
| "learning_rate": 4.3485502494445945e-06, | |
| "loss": 0.1382935166358948, | |
| "step": 815 | |
| }, | |
| { | |
| "acc": 0.9700598802395209, | |
| "epoch": 0.3537532355478861, | |
| "grad_norm": 4.75, | |
| "learning_rate": 4.330359611981552e-06, | |
| "loss": 0.09947049617767334, | |
| "step": 820 | |
| }, | |
| { | |
| "acc": 0.9504132231404959, | |
| "epoch": 0.3559102674719586, | |
| "grad_norm": 11.4375, | |
| "learning_rate": 4.312107883089969e-06, | |
| "loss": 0.15309990644454957, | |
| "step": 825 | |
| }, | |
| { | |
| "acc": 0.9606625258799172, | |
| "epoch": 0.35806729939603105, | |
| "grad_norm": 13.375, | |
| "learning_rate": 4.293795900907278e-06, | |
| "loss": 0.1290311336517334, | |
| "step": 830 | |
| }, | |
| { | |
| "acc": 0.9569471624266145, | |
| "epoch": 0.36022433132010356, | |
| "grad_norm": 13.875, | |
| "learning_rate": 4.275424506337804e-06, | |
| "loss": 0.1386420726776123, | |
| "step": 835 | |
| }, | |
| { | |
| "acc": 0.9567779960707269, | |
| "epoch": 0.362381363244176, | |
| "grad_norm": 15.0, | |
| "learning_rate": 4.256994543014147e-06, | |
| "loss": 0.13683913946151732, | |
| "step": 840 | |
| }, | |
| { | |
| "acc": 0.978515625, | |
| "epoch": 0.3645383951682485, | |
| "grad_norm": 10.875, | |
| "learning_rate": 4.2385068572584416e-06, | |
| "loss": 0.07557401657104493, | |
| "step": 845 | |
| }, | |
| { | |
| "acc": 0.9506903353057199, | |
| "epoch": 0.36669542709232095, | |
| "grad_norm": 21.875, | |
| "learning_rate": 4.2199622980434965e-06, | |
| "loss": 0.15320024490356446, | |
| "step": 850 | |
| }, | |
| { | |
| "acc": 0.9474708171206225, | |
| "epoch": 0.36885245901639346, | |
| "grad_norm": 30.875, | |
| "learning_rate": 4.2013617169537995e-06, | |
| "loss": 0.15146974325180054, | |
| "step": 855 | |
| }, | |
| { | |
| "acc": 0.936127744510978, | |
| "epoch": 0.3710094909404659, | |
| "grad_norm": 13.9375, | |
| "learning_rate": 4.182705968146426e-06, | |
| "loss": 0.18005824089050293, | |
| "step": 860 | |
| }, | |
| { | |
| "acc": 0.9661354581673307, | |
| "epoch": 0.3731665228645384, | |
| "grad_norm": 11.0625, | |
| "learning_rate": 4.163995908311802e-06, | |
| "loss": 0.10441750288009644, | |
| "step": 865 | |
| }, | |
| { | |
| "acc": 0.9671179883945842, | |
| "epoch": 0.37532355478861085, | |
| "grad_norm": 11.625, | |
| "learning_rate": 4.145232396634372e-06, | |
| "loss": 0.11835912466049195, | |
| "step": 870 | |
| }, | |
| { | |
| "acc": 0.9686888454011742, | |
| "epoch": 0.37748058671268336, | |
| "grad_norm": 8.1875, | |
| "learning_rate": 4.126416294753141e-06, | |
| "loss": 0.08334695696830749, | |
| "step": 875 | |
| }, | |
| { | |
| "acc": 0.9533898305084746, | |
| "epoch": 0.3796376186367558, | |
| "grad_norm": 15.0625, | |
| "learning_rate": 4.1075484667221095e-06, | |
| "loss": 0.1570521354675293, | |
| "step": 880 | |
| }, | |
| { | |
| "acc": 0.9628865979381444, | |
| "epoch": 0.3817946505608283, | |
| "grad_norm": 11.875, | |
| "learning_rate": 4.088629778970591e-06, | |
| "loss": 0.10125092267990113, | |
| "step": 885 | |
| }, | |
| { | |
| "acc": 0.9517102615694165, | |
| "epoch": 0.3839516824849008, | |
| "grad_norm": 10.3125, | |
| "learning_rate": 4.06966110026343e-06, | |
| "loss": 0.15835769176483155, | |
| "step": 890 | |
| }, | |
| { | |
| "acc": 0.9445506692160612, | |
| "epoch": 0.38610871440897326, | |
| "grad_norm": 51.0, | |
| "learning_rate": 4.050643301661107e-06, | |
| "loss": 0.17581632137298583, | |
| "step": 895 | |
| }, | |
| { | |
| "acc": 0.9544554455445544, | |
| "epoch": 0.3882657463330457, | |
| "grad_norm": 17.75, | |
| "learning_rate": 4.0315772564797325e-06, | |
| "loss": 0.16853252649307252, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.3882657463330457, | |
| "eval_acc": 0.9614465771480353, | |
| "eval_loss": 0.015336191281676292, | |
| "eval_mrr": 0.9436902322404371, | |
| "eval_ndcg": 0.9575083647474146, | |
| "eval_runtime": 79.2201, | |
| "eval_samples_per_second": 24.64, | |
| "eval_steps_per_second": 12.32, | |
| "step": 900 | |
| }, | |
| { | |
| "acc": 0.9625984251968503, | |
| "epoch": 0.3904227782571182, | |
| "grad_norm": 9.5625, | |
| "learning_rate": 4.012463840250949e-06, | |
| "loss": 0.11725049018859864, | |
| "step": 905 | |
| }, | |
| { | |
| "acc": 0.9578313253012049, | |
| "epoch": 0.3925798101811907, | |
| "grad_norm": 26.125, | |
| "learning_rate": 3.993303930681726e-06, | |
| "loss": 0.11894035339355469, | |
| "step": 910 | |
| }, | |
| { | |
| "acc": 0.952, | |
| "epoch": 0.39473684210526316, | |
| "grad_norm": 26.375, | |
| "learning_rate": 3.974098407614051e-06, | |
| "loss": 0.14351377487182618, | |
| "step": 915 | |
| }, | |
| { | |
| "acc": 0.9588477366255144, | |
| "epoch": 0.3968938740293356, | |
| "grad_norm": 33.75, | |
| "learning_rate": 3.954848152984529e-06, | |
| "loss": 0.12398861646652222, | |
| "step": 920 | |
| }, | |
| { | |
| "acc": 0.9679358717434869, | |
| "epoch": 0.3990509059534081, | |
| "grad_norm": 10.4375, | |
| "learning_rate": 3.935554050783885e-06, | |
| "loss": 0.10695126056671142, | |
| "step": 925 | |
| }, | |
| { | |
| "acc": 0.9646365422396856, | |
| "epoch": 0.4012079378774806, | |
| "grad_norm": 9.5, | |
| "learning_rate": 3.916216987016363e-06, | |
| "loss": 0.11947808265686036, | |
| "step": 930 | |
| }, | |
| { | |
| "acc": 0.9588235294117647, | |
| "epoch": 0.40336496980155306, | |
| "grad_norm": 19.375, | |
| "learning_rate": 3.8968378496590485e-06, | |
| "loss": 0.12318050861358643, | |
| "step": 935 | |
| }, | |
| { | |
| "acc": 0.9699812382739212, | |
| "epoch": 0.4055220017256255, | |
| "grad_norm": 9.5625, | |
| "learning_rate": 3.877417528621087e-06, | |
| "loss": 0.08819143176078796, | |
| "step": 940 | |
| }, | |
| { | |
| "acc": 0.9529411764705882, | |
| "epoch": 0.40767903364969804, | |
| "grad_norm": 25.0, | |
| "learning_rate": 3.8579569157028195e-06, | |
| "loss": 0.1318346619606018, | |
| "step": 945 | |
| }, | |
| { | |
| "acc": 0.9395085066162571, | |
| "epoch": 0.4098360655737705, | |
| "grad_norm": 14.875, | |
| "learning_rate": 3.838456904554829e-06, | |
| "loss": 0.14923615455627443, | |
| "step": 950 | |
| }, | |
| { | |
| "acc": 0.9635974304068522, | |
| "epoch": 0.41199309749784296, | |
| "grad_norm": 11.25, | |
| "learning_rate": 3.8189183906369035e-06, | |
| "loss": 0.10555909872055054, | |
| "step": 955 | |
| }, | |
| { | |
| "acc": 0.9612244897959183, | |
| "epoch": 0.4141501294219154, | |
| "grad_norm": 27.0, | |
| "learning_rate": 3.799342271176918e-06, | |
| "loss": 0.11741663217544555, | |
| "step": 960 | |
| }, | |
| { | |
| "acc": 0.9591397849462365, | |
| "epoch": 0.41630716134598794, | |
| "grad_norm": 11.875, | |
| "learning_rate": 3.7797294451296307e-06, | |
| "loss": 0.1104978084564209, | |
| "step": 965 | |
| }, | |
| { | |
| "acc": 0.9538461538461539, | |
| "epoch": 0.4184641932700604, | |
| "grad_norm": 32.0, | |
| "learning_rate": 3.7600808131354033e-06, | |
| "loss": 0.12546448707580565, | |
| "step": 970 | |
| }, | |
| { | |
| "acc": 0.9642147117296223, | |
| "epoch": 0.42062122519413286, | |
| "grad_norm": 17.375, | |
| "learning_rate": 3.740397277478841e-06, | |
| "loss": 0.15062413215637208, | |
| "step": 975 | |
| }, | |
| { | |
| "acc": 0.9447731755424064, | |
| "epoch": 0.4227782571182053, | |
| "grad_norm": 20.25, | |
| "learning_rate": 3.720679742047358e-06, | |
| "loss": 0.19598883390426636, | |
| "step": 980 | |
| }, | |
| { | |
| "acc": 0.9592668024439919, | |
| "epoch": 0.42493528904227784, | |
| "grad_norm": 8.4375, | |
| "learning_rate": 3.700929112289674e-06, | |
| "loss": 0.11623775959014893, | |
| "step": 985 | |
| }, | |
| { | |
| "acc": 0.9693486590038314, | |
| "epoch": 0.4270923209663503, | |
| "grad_norm": 17.625, | |
| "learning_rate": 3.681146295174234e-06, | |
| "loss": 0.1038408637046814, | |
| "step": 990 | |
| }, | |
| { | |
| "acc": 0.9513184584178499, | |
| "epoch": 0.42924935289042276, | |
| "grad_norm": 6.40625, | |
| "learning_rate": 3.6613321991475553e-06, | |
| "loss": 0.16103934049606322, | |
| "step": 995 | |
| }, | |
| { | |
| "acc": 0.9710982658959537, | |
| "epoch": 0.4314063848144953, | |
| "grad_norm": 35.5, | |
| "learning_rate": 3.6414877340925163e-06, | |
| "loss": 0.1310266375541687, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4314063848144953, | |
| "eval_acc": 0.9601285114095065, | |
| "eval_loss": 0.01538186427205801, | |
| "eval_mrr": 0.9503037177985949, | |
| "eval_ndcg": 0.9625558802620603, | |
| "eval_runtime": 84.007, | |
| "eval_samples_per_second": 23.236, | |
| "eval_steps_per_second": 11.618, | |
| "step": 1000 | |
| }, | |
| { | |
| "acc": 0.9592668024439919, | |
| "epoch": 0.43356341673856774, | |
| "grad_norm": 14.5625, | |
| "learning_rate": 3.6216138112865695e-06, | |
| "loss": 0.11078298091888428, | |
| "step": 1005 | |
| }, | |
| { | |
| "acc": 0.9509433962264151, | |
| "epoch": 0.4357204486626402, | |
| "grad_norm": 31.75, | |
| "learning_rate": 3.601711343359897e-06, | |
| "loss": 0.12666620016098024, | |
| "step": 1010 | |
| }, | |
| { | |
| "acc": 0.958984375, | |
| "epoch": 0.43787748058671266, | |
| "grad_norm": 7.84375, | |
| "learning_rate": 3.5817812442535008e-06, | |
| "loss": 0.10231037139892578, | |
| "step": 1015 | |
| }, | |
| { | |
| "acc": 0.9519038076152304, | |
| "epoch": 0.4400345125107852, | |
| "grad_norm": 34.75, | |
| "learning_rate": 3.561824429177234e-06, | |
| "loss": 0.14617985486984253, | |
| "step": 1020 | |
| }, | |
| { | |
| "acc": 0.9489603024574669, | |
| "epoch": 0.44219154443485764, | |
| "grad_norm": 24.75, | |
| "learning_rate": 3.541841814567774e-06, | |
| "loss": 0.15405564308166503, | |
| "step": 1025 | |
| }, | |
| { | |
| "acc": 0.9458413926499033, | |
| "epoch": 0.4443485763589301, | |
| "grad_norm": 25.875, | |
| "learning_rate": 3.521834318046539e-06, | |
| "loss": 0.1635340690612793, | |
| "step": 1030 | |
| }, | |
| { | |
| "acc": 0.964509394572025, | |
| "epoch": 0.44650560828300256, | |
| "grad_norm": 10.9375, | |
| "learning_rate": 3.5018028583775472e-06, | |
| "loss": 0.10313594341278076, | |
| "step": 1035 | |
| }, | |
| { | |
| "acc": 0.9542857142857143, | |
| "epoch": 0.4486626402070751, | |
| "grad_norm": 23.375, | |
| "learning_rate": 3.481748355425229e-06, | |
| "loss": 0.13693466186523437, | |
| "step": 1040 | |
| }, | |
| { | |
| "acc": 0.9563567362428842, | |
| "epoch": 0.45081967213114754, | |
| "grad_norm": 22.875, | |
| "learning_rate": 3.4616717301121857e-06, | |
| "loss": 0.123587965965271, | |
| "step": 1045 | |
| }, | |
| { | |
| "acc": 0.9590163934426229, | |
| "epoch": 0.45297670405522, | |
| "grad_norm": 12.5, | |
| "learning_rate": 3.441573904376899e-06, | |
| "loss": 0.13192965984344482, | |
| "step": 1050 | |
| }, | |
| { | |
| "acc": 0.9732824427480916, | |
| "epoch": 0.4551337359792925, | |
| "grad_norm": 20.875, | |
| "learning_rate": 3.4214558011313937e-06, | |
| "loss": 0.09249483346939087, | |
| "step": 1055 | |
| }, | |
| { | |
| "acc": 0.9580838323353293, | |
| "epoch": 0.457290767903365, | |
| "grad_norm": 26.75, | |
| "learning_rate": 3.4013183442188606e-06, | |
| "loss": 0.11342880725860596, | |
| "step": 1060 | |
| }, | |
| { | |
| "acc": 0.9686274509803922, | |
| "epoch": 0.45944779982743744, | |
| "grad_norm": 22.375, | |
| "learning_rate": 3.381162458371229e-06, | |
| "loss": 0.08873859643936158, | |
| "step": 1065 | |
| }, | |
| { | |
| "acc": 0.969758064516129, | |
| "epoch": 0.4616048317515099, | |
| "grad_norm": 39.0, | |
| "learning_rate": 3.3609890691667005e-06, | |
| "loss": 0.0837608277797699, | |
| "step": 1070 | |
| }, | |
| { | |
| "acc": 0.962671905697446, | |
| "epoch": 0.4637618636755824, | |
| "grad_norm": 16.375, | |
| "learning_rate": 3.340799102987251e-06, | |
| "loss": 0.11619801521301269, | |
| "step": 1075 | |
| }, | |
| { | |
| "acc": 0.9606003752345216, | |
| "epoch": 0.4659188955996549, | |
| "grad_norm": 15.0625, | |
| "learning_rate": 3.320593486976088e-06, | |
| "loss": 0.10996119976043701, | |
| "step": 1080 | |
| }, | |
| { | |
| "acc": 0.955193482688391, | |
| "epoch": 0.46807592752372734, | |
| "grad_norm": 24.5, | |
| "learning_rate": 3.300373148995072e-06, | |
| "loss": 0.12069922685623169, | |
| "step": 1085 | |
| }, | |
| { | |
| "acc": 0.9691991786447639, | |
| "epoch": 0.4702329594477998, | |
| "grad_norm": 7.90625, | |
| "learning_rate": 3.280139017582113e-06, | |
| "loss": 0.14299554824829103, | |
| "step": 1090 | |
| }, | |
| { | |
| "acc": 0.9743589743589743, | |
| "epoch": 0.4723899913718723, | |
| "grad_norm": 10.875, | |
| "learning_rate": 3.2598920219085285e-06, | |
| "loss": 0.08163526654243469, | |
| "step": 1095 | |
| }, | |
| { | |
| "acc": 0.9682242990654205, | |
| "epoch": 0.4745470232959448, | |
| "grad_norm": 9.25, | |
| "learning_rate": 3.2396330917363754e-06, | |
| "loss": 0.108160400390625, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.4745470232959448, | |
| "eval_acc": 0.964494604168383, | |
| "eval_loss": 0.014143780805170536, | |
| "eval_mrr": 0.9522601971116316, | |
| "eval_ndcg": 0.963948349172127, | |
| "eval_runtime": 88.1934, | |
| "eval_samples_per_second": 22.133, | |
| "eval_steps_per_second": 11.067, | |
| "step": 1100 | |
| }, | |
| { | |
| "acc": 0.9725490196078431, | |
| "epoch": 0.47670405522001724, | |
| "grad_norm": 11.875, | |
| "learning_rate": 3.219363157375755e-06, | |
| "loss": 0.08103461265563965, | |
| "step": 1105 | |
| }, | |
| { | |
| "acc": 0.97678916827853, | |
| "epoch": 0.47886108714408976, | |
| "grad_norm": 26.5, | |
| "learning_rate": 3.1990831496420897e-06, | |
| "loss": 0.08858168721199036, | |
| "step": 1110 | |
| }, | |
| { | |
| "acc": 0.9602385685884692, | |
| "epoch": 0.4810181190681622, | |
| "grad_norm": 15.6875, | |
| "learning_rate": 3.1787939998133853e-06, | |
| "loss": 0.11988803148269653, | |
| "step": 1115 | |
| }, | |
| { | |
| "acc": 0.9718875502008032, | |
| "epoch": 0.4831751509922347, | |
| "grad_norm": 19.0, | |
| "learning_rate": 3.158496639587459e-06, | |
| "loss": 0.09709318280220032, | |
| "step": 1120 | |
| }, | |
| { | |
| "acc": 0.948559670781893, | |
| "epoch": 0.48533218291630714, | |
| "grad_norm": 17.75, | |
| "learning_rate": 3.1381920010391566e-06, | |
| "loss": 0.1310401439666748, | |
| "step": 1125 | |
| }, | |
| { | |
| "acc": 0.9658444022770398, | |
| "epoch": 0.48748921484037966, | |
| "grad_norm": 27.875, | |
| "learning_rate": 3.1178810165775532e-06, | |
| "loss": 0.11905833482742309, | |
| "step": 1130 | |
| }, | |
| { | |
| "acc": 0.967680608365019, | |
| "epoch": 0.4896462467644521, | |
| "grad_norm": 14.9375, | |
| "learning_rate": 3.0975646189031345e-06, | |
| "loss": 0.09188791513442993, | |
| "step": 1135 | |
| }, | |
| { | |
| "acc": 0.9701195219123506, | |
| "epoch": 0.4918032786885246, | |
| "grad_norm": 14.3125, | |
| "learning_rate": 3.0772437409649664e-06, | |
| "loss": 0.09571850299835205, | |
| "step": 1140 | |
| }, | |
| { | |
| "acc": 0.9606741573033708, | |
| "epoch": 0.49396031061259704, | |
| "grad_norm": 16.875, | |
| "learning_rate": 3.056919315917851e-06, | |
| "loss": 0.1439572811126709, | |
| "step": 1145 | |
| }, | |
| { | |
| "acc": 0.9613152804642167, | |
| "epoch": 0.49611734253666956, | |
| "grad_norm": 23.625, | |
| "learning_rate": 3.0365922770794798e-06, | |
| "loss": 0.11582168340682983, | |
| "step": 1150 | |
| }, | |
| { | |
| "acc": 0.980276134122288, | |
| "epoch": 0.498274374460742, | |
| "grad_norm": 18.0, | |
| "learning_rate": 3.016263557887571e-06, | |
| "loss": 0.0658139169216156, | |
| "step": 1155 | |
| }, | |
| { | |
| "acc": 0.9581673306772909, | |
| "epoch": 0.5004314063848145, | |
| "grad_norm": 9.1875, | |
| "learning_rate": 2.995934091857007e-06, | |
| "loss": 0.11524436473846436, | |
| "step": 1160 | |
| }, | |
| { | |
| "acc": 0.9642105263157895, | |
| "epoch": 0.502588438308887, | |
| "grad_norm": 28.125, | |
| "learning_rate": 2.975604812536964e-06, | |
| "loss": 0.10523393154144287, | |
| "step": 1165 | |
| }, | |
| { | |
| "acc": 0.9673076923076923, | |
| "epoch": 0.5047454702329595, | |
| "grad_norm": 14.75, | |
| "learning_rate": 2.9552766534680456e-06, | |
| "loss": 0.10329176187515259, | |
| "step": 1170 | |
| }, | |
| { | |
| "acc": 0.9471544715447154, | |
| "epoch": 0.5069025021570319, | |
| "grad_norm": 22.5, | |
| "learning_rate": 2.9349505481394128e-06, | |
| "loss": 0.15873119831085206, | |
| "step": 1175 | |
| }, | |
| { | |
| "acc": 0.9680638722554891, | |
| "epoch": 0.5090595340811044, | |
| "grad_norm": 14.25, | |
| "learning_rate": 2.914627429945915e-06, | |
| "loss": 0.10048485994338989, | |
| "step": 1180 | |
| }, | |
| { | |
| "acc": 0.9631067961165048, | |
| "epoch": 0.5112165660051768, | |
| "grad_norm": 38.25, | |
| "learning_rate": 2.894308232145232e-06, | |
| "loss": 0.10857952833175659, | |
| "step": 1185 | |
| }, | |
| { | |
| "acc": 0.9545454545454546, | |
| "epoch": 0.5133735979292493, | |
| "grad_norm": 23.125, | |
| "learning_rate": 2.8739938878150124e-06, | |
| "loss": 0.11859817504882812, | |
| "step": 1190 | |
| }, | |
| { | |
| "acc": 0.9759036144578314, | |
| "epoch": 0.5155306298533219, | |
| "grad_norm": 14.8125, | |
| "learning_rate": 2.8536853298100302e-06, | |
| "loss": 0.06508604288101197, | |
| "step": 1195 | |
| }, | |
| { | |
| "acc": 0.9620253164556962, | |
| "epoch": 0.5176876617773943, | |
| "grad_norm": 10.6875, | |
| "learning_rate": 2.833383490719347e-06, | |
| "loss": 0.13556112051010133, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.5176876617773943, | |
| "eval_acc": 0.964824120603015, | |
| "eval_loss": 0.013948180712759495, | |
| "eval_mrr": 0.9515539617486339, | |
| "eval_ndcg": 0.9634276661273489, | |
| "eval_runtime": 79.2148, | |
| "eval_samples_per_second": 24.642, | |
| "eval_steps_per_second": 12.321, | |
| "step": 1200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 2318, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 400, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.559934048421806e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |