| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 30.0, | |
| "eval_steps": 500, | |
| "global_step": 461010, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.8920122621319915e-08, | |
| "loss": 14.3504, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 5.000289201226213e-05, | |
| "loss": 2.1001, | |
| "step": 1729 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00010000578402452426, | |
| "loss": 0.3756, | |
| "step": 3458 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0001500086760367864, | |
| "loss": 0.2527, | |
| "step": 5187 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00020001156804904852, | |
| "loss": 0.2076, | |
| "step": 6916 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00025001446006131067, | |
| "loss": 0.1864, | |
| "step": 8645 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0003000173520735728, | |
| "loss": 0.199, | |
| "step": 10374 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.8173184990882874, | |
| "eval_max_distance": 167, | |
| "eval_mean_distance": 17, | |
| "eval_runtime": 64.0638, | |
| "eval_samples_per_second": 15.609, | |
| "eval_steps_per_second": 0.78, | |
| "step": 11526 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0003500202440858349, | |
| "loss": 0.2481, | |
| "step": 12103 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00040002313609809704, | |
| "loss": 0.1244, | |
| "step": 13832 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.0004500260281103592, | |
| "loss": 0.1055, | |
| "step": 15561 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0005000289201226213, | |
| "loss": 0.102, | |
| "step": 17290 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.0005500318121348835, | |
| "loss": 0.102, | |
| "step": 19019 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.0006000347041471456, | |
| "loss": 0.1083, | |
| "step": 20748 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0006500375961594078, | |
| "loss": 0.1286, | |
| "step": 22477 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.5452634692192078, | |
| "eval_max_distance": 158, | |
| "eval_mean_distance": 14, | |
| "eval_runtime": 30.4268, | |
| "eval_samples_per_second": 32.866, | |
| "eval_steps_per_second": 1.643, | |
| "step": 23052 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.0007000404881716698, | |
| "loss": 0.1449, | |
| "step": 24206 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.000750043380183932, | |
| "loss": 0.0747, | |
| "step": 25935 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0008000462721961941, | |
| "loss": 0.0744, | |
| "step": 27664 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 0.0008500491642084563, | |
| "loss": 0.0742, | |
| "step": 29393 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.0009000520562207184, | |
| "loss": 0.0792, | |
| "step": 31122 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.0009500549482329805, | |
| "loss": 0.0891, | |
| "step": 32851 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.3629104495048523, | |
| "eval_max_distance": 122, | |
| "eval_mean_distance": 10, | |
| "eval_runtime": 35.1149, | |
| "eval_samples_per_second": 28.478, | |
| "eval_steps_per_second": 1.424, | |
| "step": 34578 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0009999935733060843, | |
| "loss": 0.1079, | |
| "step": 34580 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 0.000994437696415833, | |
| "loss": 0.0962, | |
| "step": 36309 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 0.0009888818195255813, | |
| "loss": 0.059, | |
| "step": 38038 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 0.0009833259426353302, | |
| "loss": 0.0576, | |
| "step": 39767 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 0.0009777700657450789, | |
| "loss": 0.058, | |
| "step": 41496 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 0.0009722141888548275, | |
| "loss": 0.0611, | |
| "step": 43225 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 0.0009666583119645761, | |
| "loss": 0.0711, | |
| "step": 44954 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.4011004865169525, | |
| "eval_max_distance": 114, | |
| "eval_mean_distance": 12, | |
| "eval_runtime": 24.9859, | |
| "eval_samples_per_second": 40.022, | |
| "eval_steps_per_second": 2.001, | |
| "step": 46104 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 0.0009611024350743247, | |
| "loss": 0.0991, | |
| "step": 46683 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 0.0009555465581840734, | |
| "loss": 0.0481, | |
| "step": 48412 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 0.0009499906812938221, | |
| "loss": 0.044, | |
| "step": 50141 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 0.0009444348044035706, | |
| "loss": 0.0435, | |
| "step": 51870 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 0.0009388789275133194, | |
| "loss": 0.0454, | |
| "step": 53599 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 0.000933323050623068, | |
| "loss": 0.0483, | |
| "step": 55328 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 0.0009277671737328166, | |
| "loss": 0.0566, | |
| "step": 57057 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.29974234104156494, | |
| "eval_max_distance": 100, | |
| "eval_mean_distance": 7, | |
| "eval_runtime": 25.609, | |
| "eval_samples_per_second": 39.049, | |
| "eval_steps_per_second": 1.952, | |
| "step": 57630 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 0.0009222112968425653, | |
| "loss": 0.0724, | |
| "step": 58786 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 0.000916655419952314, | |
| "loss": 0.0364, | |
| "step": 60515 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 0.0009110995430620625, | |
| "loss": 0.035, | |
| "step": 62244 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 0.0009055436661718113, | |
| "loss": 0.0353, | |
| "step": 63973 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 0.0008999877892815599, | |
| "loss": 0.0364, | |
| "step": 65702 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 0.0008944319123913086, | |
| "loss": 0.0402, | |
| "step": 67431 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.15522713959217072, | |
| "eval_max_distance": 75, | |
| "eval_mean_distance": 4, | |
| "eval_runtime": 24.8618, | |
| "eval_samples_per_second": 40.222, | |
| "eval_steps_per_second": 2.011, | |
| "step": 69156 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.0008888760355010572, | |
| "loss": 0.0506, | |
| "step": 69160 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 0.0008833201586108059, | |
| "loss": 0.0514, | |
| "step": 70889 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 0.0008777642817205546, | |
| "loss": 0.0298, | |
| "step": 72618 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 0.0008722084048303031, | |
| "loss": 0.0287, | |
| "step": 74347 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 0.0008666525279400518, | |
| "loss": 0.0289, | |
| "step": 76076 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "learning_rate": 0.0008610966510498005, | |
| "loss": 0.0303, | |
| "step": 77805 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 0.0008555407741595491, | |
| "loss": 0.0348, | |
| "step": 79534 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.15130603313446045, | |
| "eval_max_distance": 79, | |
| "eval_mean_distance": 3, | |
| "eval_runtime": 25.5455, | |
| "eval_samples_per_second": 39.146, | |
| "eval_steps_per_second": 1.957, | |
| "step": 80682 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 0.0008499848972692977, | |
| "loss": 0.0527, | |
| "step": 81263 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 0.0008444290203790465, | |
| "loss": 0.0293, | |
| "step": 82992 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 0.000838873143488795, | |
| "loss": 0.0247, | |
| "step": 84721 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 0.0008333172665985437, | |
| "loss": 0.024, | |
| "step": 86450 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 0.0008277613897082924, | |
| "loss": 0.0243, | |
| "step": 88179 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 0.000822205512818041, | |
| "loss": 0.0263, | |
| "step": 89908 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 0.0008166496359277897, | |
| "loss": 0.0302, | |
| "step": 91637 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.14522188901901245, | |
| "eval_max_distance": 76, | |
| "eval_mean_distance": 3, | |
| "eval_runtime": 25.6271, | |
| "eval_samples_per_second": 39.021, | |
| "eval_steps_per_second": 1.951, | |
| "step": 92208 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 0.0008110937590375384, | |
| "loss": 0.0445, | |
| "step": 93366 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 0.0008055378821472869, | |
| "loss": 0.0229, | |
| "step": 95095 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 0.0007999820052570357, | |
| "loss": 0.0207, | |
| "step": 96824 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 0.0007944261283667843, | |
| "loss": 0.0203, | |
| "step": 98553 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 0.000788870251476533, | |
| "loss": 0.021, | |
| "step": 100282 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 0.0007833143745862816, | |
| "loss": 0.0223, | |
| "step": 102011 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.08658243715763092, | |
| "eval_max_distance": 76, | |
| "eval_mean_distance": 1, | |
| "eval_runtime": 23.498, | |
| "eval_samples_per_second": 42.557, | |
| "eval_steps_per_second": 2.128, | |
| "step": 103734 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 0.0007777584976960303, | |
| "loss": 0.0284, | |
| "step": 103740 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 0.0007722026208057789, | |
| "loss": 0.034, | |
| "step": 105469 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 0.0007666467439155275, | |
| "loss": 0.0193, | |
| "step": 107198 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 0.0007610908670252762, | |
| "loss": 0.0175, | |
| "step": 108927 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 0.0007555349901350248, | |
| "loss": 0.0172, | |
| "step": 110656 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 0.0007499791132447735, | |
| "loss": 0.018, | |
| "step": 112385 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 0.0007444232363545221, | |
| "loss": 0.0202, | |
| "step": 114114 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.10908353328704834, | |
| "eval_max_distance": 71, | |
| "eval_mean_distance": 2, | |
| "eval_runtime": 25.0909, | |
| "eval_samples_per_second": 39.855, | |
| "eval_steps_per_second": 1.993, | |
| "step": 115260 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 0.0007388673594642709, | |
| "loss": 0.0342, | |
| "step": 115843 | |
| }, | |
| { | |
| "epoch": 10.2, | |
| "learning_rate": 0.0007333114825740194, | |
| "loss": 0.0202, | |
| "step": 117572 | |
| }, | |
| { | |
| "epoch": 10.35, | |
| "learning_rate": 0.0007277556056837681, | |
| "loss": 0.0159, | |
| "step": 119301 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "learning_rate": 0.0007221997287935168, | |
| "loss": 0.0149, | |
| "step": 121030 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 0.0007166438519032654, | |
| "loss": 0.015, | |
| "step": 122759 | |
| }, | |
| { | |
| "epoch": 10.8, | |
| "learning_rate": 0.000711087975013014, | |
| "loss": 0.0155, | |
| "step": 124488 | |
| }, | |
| { | |
| "epoch": 10.95, | |
| "learning_rate": 0.0007055320981227628, | |
| "loss": 0.0175, | |
| "step": 126217 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.06553788483142853, | |
| "eval_max_distance": 66, | |
| "eval_mean_distance": 1, | |
| "eval_runtime": 22.988, | |
| "eval_samples_per_second": 43.501, | |
| "eval_steps_per_second": 2.175, | |
| "step": 126786 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "learning_rate": 0.0006999762212325114, | |
| "loss": 0.0305, | |
| "step": 127946 | |
| }, | |
| { | |
| "epoch": 11.25, | |
| "learning_rate": 0.00069442034434226, | |
| "loss": 0.0157, | |
| "step": 129675 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "learning_rate": 0.0006888644674520087, | |
| "loss": 0.0134, | |
| "step": 131404 | |
| }, | |
| { | |
| "epoch": 11.55, | |
| "learning_rate": 0.0006833085905617574, | |
| "loss": 0.0124, | |
| "step": 133133 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "learning_rate": 0.0006777527136715059, | |
| "loss": 0.0131, | |
| "step": 134862 | |
| }, | |
| { | |
| "epoch": 11.85, | |
| "learning_rate": 0.0006721968367812547, | |
| "loss": 0.014, | |
| "step": 136591 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.04735955968499184, | |
| "eval_max_distance": 44, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 22.5236, | |
| "eval_samples_per_second": 44.398, | |
| "eval_steps_per_second": 2.22, | |
| "step": 138312 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 0.0006666409598910033, | |
| "loss": 0.0182, | |
| "step": 138320 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "learning_rate": 0.000661085083000752, | |
| "loss": 0.025, | |
| "step": 140049 | |
| }, | |
| { | |
| "epoch": 12.3, | |
| "learning_rate": 0.0006555292061105006, | |
| "loss": 0.0128, | |
| "step": 141778 | |
| }, | |
| { | |
| "epoch": 12.45, | |
| "learning_rate": 0.0006499733292202492, | |
| "loss": 0.0114, | |
| "step": 143507 | |
| }, | |
| { | |
| "epoch": 12.6, | |
| "learning_rate": 0.0006444174523299979, | |
| "loss": 0.011, | |
| "step": 145236 | |
| }, | |
| { | |
| "epoch": 12.75, | |
| "learning_rate": 0.0006388615754397465, | |
| "loss": 0.0117, | |
| "step": 146965 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 0.0006333056985494952, | |
| "loss": 0.0122, | |
| "step": 148694 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.05152251571416855, | |
| "eval_max_distance": 42, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 23.898, | |
| "eval_samples_per_second": 41.845, | |
| "eval_steps_per_second": 2.092, | |
| "step": 149838 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "learning_rate": 0.0006277498216592438, | |
| "loss": 0.0241, | |
| "step": 150423 | |
| }, | |
| { | |
| "epoch": 13.2, | |
| "learning_rate": 0.0006221939447689925, | |
| "loss": 0.0148, | |
| "step": 152152 | |
| }, | |
| { | |
| "epoch": 13.35, | |
| "learning_rate": 0.0006166380678787411, | |
| "loss": 0.0106, | |
| "step": 153881 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "learning_rate": 0.0006110821909884899, | |
| "loss": 0.0096, | |
| "step": 155610 | |
| }, | |
| { | |
| "epoch": 13.65, | |
| "learning_rate": 0.0006055263140982384, | |
| "loss": 0.0098, | |
| "step": 157339 | |
| }, | |
| { | |
| "epoch": 13.8, | |
| "learning_rate": 0.0005999704372079872, | |
| "loss": 0.0104, | |
| "step": 159068 | |
| }, | |
| { | |
| "epoch": 13.95, | |
| "learning_rate": 0.0005944145603177358, | |
| "loss": 0.0117, | |
| "step": 160797 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.047906968742609024, | |
| "eval_max_distance": 30, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 23.3531, | |
| "eval_samples_per_second": 42.821, | |
| "eval_steps_per_second": 2.141, | |
| "step": 161364 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "learning_rate": 0.0005888586834274844, | |
| "loss": 0.0224, | |
| "step": 162526 | |
| }, | |
| { | |
| "epoch": 14.25, | |
| "learning_rate": 0.0005833028065372331, | |
| "loss": 0.0111, | |
| "step": 164255 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 0.0005777469296469818, | |
| "loss": 0.009, | |
| "step": 165984 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "learning_rate": 0.0005721910527567303, | |
| "loss": 0.0086, | |
| "step": 167713 | |
| }, | |
| { | |
| "epoch": 14.7, | |
| "learning_rate": 0.000566635175866479, | |
| "loss": 0.0088, | |
| "step": 169442 | |
| }, | |
| { | |
| "epoch": 14.85, | |
| "learning_rate": 0.0005610792989762277, | |
| "loss": 0.0093, | |
| "step": 171171 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.05651288107037544, | |
| "eval_max_distance": 56, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 23.6545, | |
| "eval_samples_per_second": 42.275, | |
| "eval_steps_per_second": 2.114, | |
| "step": 172890 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 0.0005555234220859762, | |
| "loss": 0.0124, | |
| "step": 172900 | |
| }, | |
| { | |
| "epoch": 15.15, | |
| "learning_rate": 0.000549967545195725, | |
| "loss": 0.0181, | |
| "step": 174629 | |
| }, | |
| { | |
| "epoch": 15.3, | |
| "learning_rate": 0.0005444116683054736, | |
| "loss": 0.0091, | |
| "step": 176358 | |
| }, | |
| { | |
| "epoch": 15.45, | |
| "learning_rate": 0.0005388557914152222, | |
| "loss": 0.0075, | |
| "step": 178087 | |
| }, | |
| { | |
| "epoch": 15.6, | |
| "learning_rate": 0.0005332999145249709, | |
| "loss": 0.0075, | |
| "step": 179816 | |
| }, | |
| { | |
| "epoch": 15.75, | |
| "learning_rate": 0.0005277440376347196, | |
| "loss": 0.0075, | |
| "step": 181545 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "learning_rate": 0.0005221881607444683, | |
| "loss": 0.0085, | |
| "step": 183274 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.047154366970062256, | |
| "eval_max_distance": 34, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 23.554, | |
| "eval_samples_per_second": 42.456, | |
| "eval_steps_per_second": 2.123, | |
| "step": 184416 | |
| }, | |
| { | |
| "epoch": 16.05, | |
| "learning_rate": 0.0005166322838542169, | |
| "loss": 0.0169, | |
| "step": 185003 | |
| }, | |
| { | |
| "epoch": 16.2, | |
| "learning_rate": 0.0005110764069639655, | |
| "loss": 0.0104, | |
| "step": 186732 | |
| }, | |
| { | |
| "epoch": 16.35, | |
| "learning_rate": 0.0005055205300737143, | |
| "loss": 0.0072, | |
| "step": 188461 | |
| }, | |
| { | |
| "epoch": 16.5, | |
| "learning_rate": 0.0004999646531834628, | |
| "loss": 0.0068, | |
| "step": 190190 | |
| }, | |
| { | |
| "epoch": 16.65, | |
| "learning_rate": 0.0004944087762932115, | |
| "loss": 0.0064, | |
| "step": 191919 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 0.0004888528994029601, | |
| "loss": 0.0068, | |
| "step": 193648 | |
| }, | |
| { | |
| "epoch": 16.95, | |
| "learning_rate": 0.0004832970225127088, | |
| "loss": 0.0075, | |
| "step": 195377 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.04200902581214905, | |
| "eval_max_distance": 28, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 22.1607, | |
| "eval_samples_per_second": 45.125, | |
| "eval_steps_per_second": 2.256, | |
| "step": 195942 | |
| }, | |
| { | |
| "epoch": 17.1, | |
| "learning_rate": 0.00047774114562245746, | |
| "loss": 0.0162, | |
| "step": 197106 | |
| }, | |
| { | |
| "epoch": 17.25, | |
| "learning_rate": 0.00047218526873220605, | |
| "loss": 0.0077, | |
| "step": 198835 | |
| }, | |
| { | |
| "epoch": 17.4, | |
| "learning_rate": 0.00046662939184195475, | |
| "loss": 0.0063, | |
| "step": 200564 | |
| }, | |
| { | |
| "epoch": 17.55, | |
| "learning_rate": 0.0004610735149517034, | |
| "loss": 0.0058, | |
| "step": 202293 | |
| }, | |
| { | |
| "epoch": 17.7, | |
| "learning_rate": 0.0004555176380614521, | |
| "loss": 0.0057, | |
| "step": 204022 | |
| }, | |
| { | |
| "epoch": 17.85, | |
| "learning_rate": 0.0004499617611712007, | |
| "loss": 0.0059, | |
| "step": 205751 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.04149915650486946, | |
| "eval_max_distance": 32, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 22.9895, | |
| "eval_samples_per_second": 43.498, | |
| "eval_steps_per_second": 2.175, | |
| "step": 207468 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 0.00044440588428094934, | |
| "loss": 0.0082, | |
| "step": 207480 | |
| }, | |
| { | |
| "epoch": 18.15, | |
| "learning_rate": 0.00043885000739069804, | |
| "loss": 0.0133, | |
| "step": 209209 | |
| }, | |
| { | |
| "epoch": 18.3, | |
| "learning_rate": 0.00043329413050044663, | |
| "loss": 0.0063, | |
| "step": 210938 | |
| }, | |
| { | |
| "epoch": 18.45, | |
| "learning_rate": 0.0004277382536101953, | |
| "loss": 0.0051, | |
| "step": 212667 | |
| }, | |
| { | |
| "epoch": 18.6, | |
| "learning_rate": 0.000422182376719944, | |
| "loss": 0.0051, | |
| "step": 214396 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "learning_rate": 0.00041662649982969263, | |
| "loss": 0.0051, | |
| "step": 216125 | |
| }, | |
| { | |
| "epoch": 18.9, | |
| "learning_rate": 0.0004110706229394413, | |
| "loss": 0.0054, | |
| "step": 217854 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.0405677855014801, | |
| "eval_max_distance": 28, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 21.777, | |
| "eval_samples_per_second": 45.92, | |
| "eval_steps_per_second": 2.296, | |
| "step": 218994 | |
| }, | |
| { | |
| "epoch": 19.05, | |
| "learning_rate": 0.0004055147460491899, | |
| "loss": 0.0117, | |
| "step": 219583 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 0.00039995886915893857, | |
| "loss": 0.0075, | |
| "step": 221312 | |
| }, | |
| { | |
| "epoch": 19.35, | |
| "learning_rate": 0.00039440299226868727, | |
| "loss": 0.0051, | |
| "step": 223041 | |
| }, | |
| { | |
| "epoch": 19.5, | |
| "learning_rate": 0.00038884711537843586, | |
| "loss": 0.0046, | |
| "step": 224770 | |
| }, | |
| { | |
| "epoch": 19.65, | |
| "learning_rate": 0.0003832912384881845, | |
| "loss": 0.0043, | |
| "step": 226499 | |
| }, | |
| { | |
| "epoch": 19.8, | |
| "learning_rate": 0.0003777353615979332, | |
| "loss": 0.0044, | |
| "step": 228228 | |
| }, | |
| { | |
| "epoch": 19.95, | |
| "learning_rate": 0.0003721794847076818, | |
| "loss": 0.0046, | |
| "step": 229957 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.03926468640565872, | |
| "eval_max_distance": 24, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 23.1294, | |
| "eval_samples_per_second": 43.235, | |
| "eval_steps_per_second": 2.162, | |
| "step": 230520 | |
| }, | |
| { | |
| "epoch": 20.1, | |
| "learning_rate": 0.0003666236078174305, | |
| "loss": 0.0118, | |
| "step": 231686 | |
| }, | |
| { | |
| "epoch": 20.25, | |
| "learning_rate": 0.00036106773092717915, | |
| "loss": 0.0056, | |
| "step": 233415 | |
| }, | |
| { | |
| "epoch": 20.4, | |
| "learning_rate": 0.0003555118540369278, | |
| "loss": 0.0043, | |
| "step": 235144 | |
| }, | |
| { | |
| "epoch": 20.55, | |
| "learning_rate": 0.00034995597714667645, | |
| "loss": 0.0039, | |
| "step": 236873 | |
| }, | |
| { | |
| "epoch": 20.7, | |
| "learning_rate": 0.0003444001002564251, | |
| "loss": 0.0037, | |
| "step": 238602 | |
| }, | |
| { | |
| "epoch": 20.85, | |
| "learning_rate": 0.00033884422336617374, | |
| "loss": 0.004, | |
| "step": 240331 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 0.04168349876999855, | |
| "eval_max_distance": 24, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 22.786, | |
| "eval_samples_per_second": 43.887, | |
| "eval_steps_per_second": 2.194, | |
| "step": 242046 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 0.0003332883464759224, | |
| "loss": 0.0053, | |
| "step": 242060 | |
| }, | |
| { | |
| "epoch": 21.15, | |
| "learning_rate": 0.00032773246958567103, | |
| "loss": 0.0097, | |
| "step": 243789 | |
| }, | |
| { | |
| "epoch": 21.3, | |
| "learning_rate": 0.00032217659269541973, | |
| "loss": 0.0044, | |
| "step": 245518 | |
| }, | |
| { | |
| "epoch": 21.45, | |
| "learning_rate": 0.0003166207158051684, | |
| "loss": 0.0036, | |
| "step": 247247 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "learning_rate": 0.000311064838914917, | |
| "loss": 0.0031, | |
| "step": 248976 | |
| }, | |
| { | |
| "epoch": 21.75, | |
| "learning_rate": 0.0003055089620246657, | |
| "loss": 0.0031, | |
| "step": 250705 | |
| }, | |
| { | |
| "epoch": 21.9, | |
| "learning_rate": 0.0002999530851344143, | |
| "loss": 0.0034, | |
| "step": 252434 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 0.040287140756845474, | |
| "eval_max_distance": 18, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 21.6664, | |
| "eval_samples_per_second": 46.155, | |
| "eval_steps_per_second": 2.308, | |
| "step": 253572 | |
| }, | |
| { | |
| "epoch": 22.05, | |
| "learning_rate": 0.0002943972082441629, | |
| "loss": 0.0082, | |
| "step": 254163 | |
| }, | |
| { | |
| "epoch": 22.2, | |
| "learning_rate": 0.0002888413313539116, | |
| "loss": 0.0053, | |
| "step": 255892 | |
| }, | |
| { | |
| "epoch": 22.35, | |
| "learning_rate": 0.00028328545446366026, | |
| "loss": 0.0034, | |
| "step": 257621 | |
| }, | |
| { | |
| "epoch": 22.5, | |
| "learning_rate": 0.00027772957757340896, | |
| "loss": 0.0031, | |
| "step": 259350 | |
| }, | |
| { | |
| "epoch": 22.65, | |
| "learning_rate": 0.00027217370068315756, | |
| "loss": 0.0029, | |
| "step": 261079 | |
| }, | |
| { | |
| "epoch": 22.8, | |
| "learning_rate": 0.0002666178237929062, | |
| "loss": 0.0027, | |
| "step": 262808 | |
| }, | |
| { | |
| "epoch": 22.95, | |
| "learning_rate": 0.0002610619469026549, | |
| "loss": 0.0029, | |
| "step": 264537 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 0.04222797229886055, | |
| "eval_max_distance": 21, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 22.874, | |
| "eval_samples_per_second": 43.718, | |
| "eval_steps_per_second": 2.186, | |
| "step": 265098 | |
| }, | |
| { | |
| "epoch": 23.1, | |
| "learning_rate": 0.0002555060700124035, | |
| "loss": 0.0081, | |
| "step": 266266 | |
| }, | |
| { | |
| "epoch": 23.25, | |
| "learning_rate": 0.00024995019312215214, | |
| "loss": 0.0038, | |
| "step": 267995 | |
| }, | |
| { | |
| "epoch": 23.4, | |
| "learning_rate": 0.00024439431623190085, | |
| "loss": 0.0028, | |
| "step": 269724 | |
| }, | |
| { | |
| "epoch": 23.55, | |
| "learning_rate": 0.00023883843934164947, | |
| "loss": 0.0025, | |
| "step": 271453 | |
| }, | |
| { | |
| "epoch": 23.7, | |
| "learning_rate": 0.00023328256245139814, | |
| "loss": 0.0026, | |
| "step": 273182 | |
| }, | |
| { | |
| "epoch": 23.85, | |
| "learning_rate": 0.0002277266855611468, | |
| "loss": 0.0024, | |
| "step": 274911 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.04101773351430893, | |
| "eval_max_distance": 21, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 22.8008, | |
| "eval_samples_per_second": 43.858, | |
| "eval_steps_per_second": 2.193, | |
| "step": 276624 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 0.00022217080867089543, | |
| "loss": 0.0033, | |
| "step": 276640 | |
| }, | |
| { | |
| "epoch": 24.15, | |
| "learning_rate": 0.00021661493178064408, | |
| "loss": 0.0069, | |
| "step": 278369 | |
| }, | |
| { | |
| "epoch": 24.3, | |
| "learning_rate": 0.00021105905489039273, | |
| "loss": 0.0029, | |
| "step": 280098 | |
| }, | |
| { | |
| "epoch": 24.45, | |
| "learning_rate": 0.0002055031780001414, | |
| "loss": 0.0024, | |
| "step": 281827 | |
| }, | |
| { | |
| "epoch": 24.6, | |
| "learning_rate": 0.00019994730110989005, | |
| "loss": 0.0021, | |
| "step": 283556 | |
| }, | |
| { | |
| "epoch": 24.75, | |
| "learning_rate": 0.0001943914242196387, | |
| "loss": 0.002, | |
| "step": 285285 | |
| }, | |
| { | |
| "epoch": 24.9, | |
| "learning_rate": 0.00018883554732938734, | |
| "loss": 0.002, | |
| "step": 287014 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 0.043479613959789276, | |
| "eval_max_distance": 15, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 21.481, | |
| "eval_samples_per_second": 46.553, | |
| "eval_steps_per_second": 2.328, | |
| "step": 288150 | |
| }, | |
| { | |
| "epoch": 25.05, | |
| "learning_rate": 0.000183279670439136, | |
| "loss": 0.0055, | |
| "step": 288743 | |
| }, | |
| { | |
| "epoch": 25.2, | |
| "learning_rate": 0.00017772379354888466, | |
| "loss": 0.0038, | |
| "step": 290472 | |
| }, | |
| { | |
| "epoch": 25.35, | |
| "learning_rate": 0.00017216791665863328, | |
| "loss": 0.0023, | |
| "step": 292201 | |
| }, | |
| { | |
| "epoch": 25.5, | |
| "learning_rate": 0.00016661203976838196, | |
| "loss": 0.002, | |
| "step": 293930 | |
| }, | |
| { | |
| "epoch": 25.65, | |
| "learning_rate": 0.0001610561628781306, | |
| "loss": 0.0017, | |
| "step": 295659 | |
| }, | |
| { | |
| "epoch": 25.8, | |
| "learning_rate": 0.00015550028598787928, | |
| "loss": 0.0018, | |
| "step": 297388 | |
| }, | |
| { | |
| "epoch": 25.95, | |
| "learning_rate": 0.0001499444090976279, | |
| "loss": 0.0016, | |
| "step": 299117 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 0.04517431557178497, | |
| "eval_max_distance": 15, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 22.7192, | |
| "eval_samples_per_second": 44.016, | |
| "eval_steps_per_second": 2.201, | |
| "step": 299676 | |
| }, | |
| { | |
| "epoch": 26.1, | |
| "learning_rate": 0.00014438853220737654, | |
| "loss": 0.0054, | |
| "step": 300846 | |
| }, | |
| { | |
| "epoch": 26.25, | |
| "learning_rate": 0.00013883265531712522, | |
| "loss": 0.0026, | |
| "step": 302575 | |
| }, | |
| { | |
| "epoch": 26.4, | |
| "learning_rate": 0.00013327677842687387, | |
| "loss": 0.0018, | |
| "step": 304304 | |
| }, | |
| { | |
| "epoch": 26.55, | |
| "learning_rate": 0.0001277209015366225, | |
| "loss": 0.0016, | |
| "step": 306033 | |
| }, | |
| { | |
| "epoch": 26.7, | |
| "learning_rate": 0.00012216502464637116, | |
| "loss": 0.0015, | |
| "step": 307762 | |
| }, | |
| { | |
| "epoch": 26.85, | |
| "learning_rate": 0.00011660914775611982, | |
| "loss": 0.0013, | |
| "step": 309491 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 0.04144546017050743, | |
| "eval_max_distance": 14, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 22.686, | |
| "eval_samples_per_second": 44.08, | |
| "eval_steps_per_second": 2.204, | |
| "step": 311202 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 0.00011105327086586847, | |
| "loss": 0.0021, | |
| "step": 311220 | |
| }, | |
| { | |
| "epoch": 27.15, | |
| "learning_rate": 0.00010549739397561713, | |
| "loss": 0.0046, | |
| "step": 312949 | |
| }, | |
| { | |
| "epoch": 27.3, | |
| "learning_rate": 9.994151708536577e-05, | |
| "loss": 0.002, | |
| "step": 314678 | |
| }, | |
| { | |
| "epoch": 27.45, | |
| "learning_rate": 9.438564019511443e-05, | |
| "loss": 0.0016, | |
| "step": 316407 | |
| }, | |
| { | |
| "epoch": 27.6, | |
| "learning_rate": 8.882976330486308e-05, | |
| "loss": 0.0013, | |
| "step": 318136 | |
| }, | |
| { | |
| "epoch": 27.75, | |
| "learning_rate": 8.327388641461173e-05, | |
| "loss": 0.0013, | |
| "step": 319865 | |
| }, | |
| { | |
| "epoch": 27.9, | |
| "learning_rate": 7.771800952436038e-05, | |
| "loss": 0.0012, | |
| "step": 321594 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 0.04387975484132767, | |
| "eval_max_distance": 14, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 21.586, | |
| "eval_samples_per_second": 46.326, | |
| "eval_steps_per_second": 2.316, | |
| "step": 322728 | |
| }, | |
| { | |
| "epoch": 28.05, | |
| "learning_rate": 7.216213263410904e-05, | |
| "loss": 0.0037, | |
| "step": 323323 | |
| }, | |
| { | |
| "epoch": 28.2, | |
| "learning_rate": 6.660625574385768e-05, | |
| "loss": 0.0027, | |
| "step": 325052 | |
| }, | |
| { | |
| "epoch": 28.35, | |
| "learning_rate": 6.105037885360634e-05, | |
| "loss": 0.0016, | |
| "step": 326781 | |
| }, | |
| { | |
| "epoch": 28.5, | |
| "learning_rate": 5.5494501963355e-05, | |
| "loss": 0.0013, | |
| "step": 328510 | |
| }, | |
| { | |
| "epoch": 28.65, | |
| "learning_rate": 4.9938625073103644e-05, | |
| "loss": 0.0011, | |
| "step": 330239 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 4.43827481828523e-05, | |
| "loss": 0.001, | |
| "step": 331968 | |
| }, | |
| { | |
| "epoch": 28.95, | |
| "learning_rate": 3.882687129260095e-05, | |
| "loss": 0.001, | |
| "step": 333697 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 0.044395141303539276, | |
| "eval_max_distance": 15, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 22.6289, | |
| "eval_samples_per_second": 44.191, | |
| "eval_steps_per_second": 2.21, | |
| "step": 334254 | |
| }, | |
| { | |
| "epoch": 29.1, | |
| "learning_rate": 3.32709944023496e-05, | |
| "loss": 0.0039, | |
| "step": 335426 | |
| }, | |
| { | |
| "epoch": 29.25, | |
| "learning_rate": 2.771511751209825e-05, | |
| "loss": 0.0017, | |
| "step": 337155 | |
| }, | |
| { | |
| "epoch": 29.4, | |
| "learning_rate": 2.2159240621846906e-05, | |
| "loss": 0.0012, | |
| "step": 338884 | |
| }, | |
| { | |
| "epoch": 29.55, | |
| "learning_rate": 1.6603363731595556e-05, | |
| "loss": 0.0011, | |
| "step": 340613 | |
| }, | |
| { | |
| "epoch": 29.7, | |
| "learning_rate": 1.1047486841344207e-05, | |
| "loss": 0.001, | |
| "step": 342342 | |
| }, | |
| { | |
| "epoch": 29.85, | |
| "learning_rate": 0.0004477394104151002, | |
| "loss": 0.0026, | |
| "step": 344071 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 0.042660146951675415, | |
| "eval_max_distance": 19, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 48.9711, | |
| "eval_samples_per_second": 20.42, | |
| "eval_steps_per_second": 1.021, | |
| "step": 345780 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 0.00044440588428094934, | |
| "loss": 0.0045, | |
| "step": 345800 | |
| }, | |
| { | |
| "epoch": 30.15, | |
| "learning_rate": 0.00044107235814679855, | |
| "loss": 0.0068, | |
| "step": 347529 | |
| }, | |
| { | |
| "epoch": 30.3, | |
| "learning_rate": 0.00043773883201264776, | |
| "loss": 0.0036, | |
| "step": 349258 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 0.0004344053058784969, | |
| "loss": 0.0032, | |
| "step": 350987 | |
| }, | |
| { | |
| "epoch": 30.6, | |
| "learning_rate": 0.0004310717797443461, | |
| "loss": 0.0033, | |
| "step": 352716 | |
| }, | |
| { | |
| "epoch": 30.75, | |
| "learning_rate": 0.0004277382536101953, | |
| "loss": 0.0034, | |
| "step": 354445 | |
| }, | |
| { | |
| "epoch": 30.9, | |
| "learning_rate": 0.00042440472747604454, | |
| "loss": 0.004, | |
| "step": 356174 | |
| }, | |
| { | |
| "epoch": 23.29, | |
| "learning_rate": 0.000593547500777279, | |
| "loss": 0.0057, | |
| "step": 357903 | |
| }, | |
| { | |
| "epoch": 23.4, | |
| "learning_rate": 0.0005910471934809801, | |
| "loss": 0.0053, | |
| "step": 359632 | |
| }, | |
| { | |
| "epoch": 23.52, | |
| "learning_rate": 0.0005885468861846814, | |
| "loss": 0.0055, | |
| "step": 361361 | |
| }, | |
| { | |
| "epoch": 23.63, | |
| "learning_rate": 0.0005860465788883828, | |
| "loss": 0.0056, | |
| "step": 363090 | |
| }, | |
| { | |
| "epoch": 23.74, | |
| "learning_rate": 0.0005835462715920841, | |
| "loss": 0.006, | |
| "step": 364819 | |
| }, | |
| { | |
| "epoch": 23.85, | |
| "learning_rate": 0.0005810459642957853, | |
| "loss": 0.0064, | |
| "step": 366548 | |
| }, | |
| { | |
| "epoch": 23.97, | |
| "learning_rate": 0.0005785456569994867, | |
| "loss": 0.0077, | |
| "step": 368277 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.049542564898729324, | |
| "eval_max_distance": 27, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 72.4399, | |
| "eval_samples_per_second": 13.805, | |
| "eval_steps_per_second": 0.925, | |
| "step": 368808 | |
| }, | |
| { | |
| "epoch": 24.08, | |
| "learning_rate": 0.0005760453497031879, | |
| "loss": 0.0158, | |
| "step": 370006 | |
| }, | |
| { | |
| "epoch": 24.19, | |
| "learning_rate": 0.0005735450424068892, | |
| "loss": 0.0082, | |
| "step": 371735 | |
| }, | |
| { | |
| "epoch": 24.3, | |
| "learning_rate": 0.0005710447351105905, | |
| "loss": 0.0057, | |
| "step": 373464 | |
| }, | |
| { | |
| "epoch": 24.42, | |
| "learning_rate": 0.0005685444278142918, | |
| "loss": 0.0059, | |
| "step": 375193 | |
| }, | |
| { | |
| "epoch": 24.53, | |
| "learning_rate": 0.0005660441205179932, | |
| "loss": 0.0055, | |
| "step": 376922 | |
| }, | |
| { | |
| "epoch": 24.64, | |
| "learning_rate": 0.0005635438132216944, | |
| "loss": 0.0062, | |
| "step": 378651 | |
| }, | |
| { | |
| "epoch": 24.75, | |
| "learning_rate": 0.0005610435059253957, | |
| "loss": 0.0059, | |
| "step": 380380 | |
| }, | |
| { | |
| "epoch": 24.87, | |
| "learning_rate": 0.000558543198629097, | |
| "loss": 0.0062, | |
| "step": 382109 | |
| }, | |
| { | |
| "epoch": 24.98, | |
| "learning_rate": 0.0005560428913327982, | |
| "loss": 0.0083, | |
| "step": 383838 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 0.044624801725149155, | |
| "eval_max_distance": 37, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 35.859, | |
| "eval_samples_per_second": 27.887, | |
| "eval_steps_per_second": 1.868, | |
| "step": 384175 | |
| }, | |
| { | |
| "epoch": 25.09, | |
| "learning_rate": 0.0005535425840364996, | |
| "loss": 0.0154, | |
| "step": 385567 | |
| }, | |
| { | |
| "epoch": 25.2, | |
| "learning_rate": 0.0005510422767402009, | |
| "loss": 0.0075, | |
| "step": 387296 | |
| }, | |
| { | |
| "epoch": 25.32, | |
| "learning_rate": 0.0005485419694439023, | |
| "loss": 0.006, | |
| "step": 389025 | |
| }, | |
| { | |
| "epoch": 25.43, | |
| "learning_rate": 0.0005460416621476034, | |
| "loss": 0.0057, | |
| "step": 390754 | |
| }, | |
| { | |
| "epoch": 25.54, | |
| "learning_rate": 0.0005435413548513047, | |
| "loss": 0.0057, | |
| "step": 392483 | |
| }, | |
| { | |
| "epoch": 25.65, | |
| "learning_rate": 0.0005410410475550061, | |
| "loss": 0.0056, | |
| "step": 394212 | |
| }, | |
| { | |
| "epoch": 25.77, | |
| "learning_rate": 0.0005385407402587073, | |
| "loss": 0.0059, | |
| "step": 395941 | |
| }, | |
| { | |
| "epoch": 25.88, | |
| "learning_rate": 0.0005360404329624087, | |
| "loss": 0.0067, | |
| "step": 397670 | |
| }, | |
| { | |
| "epoch": 25.99, | |
| "learning_rate": 0.0005335401256661099, | |
| "loss": 0.0078, | |
| "step": 399399 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 0.048115409910678864, | |
| "eval_max_distance": 47, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 35.8872, | |
| "eval_samples_per_second": 27.865, | |
| "eval_steps_per_second": 1.867, | |
| "step": 399542 | |
| }, | |
| { | |
| "epoch": 26.1, | |
| "learning_rate": 0.0005310398183698112, | |
| "loss": 0.0151, | |
| "step": 401128 | |
| }, | |
| { | |
| "epoch": 26.22, | |
| "learning_rate": 0.0005285395110735125, | |
| "loss": 0.0068, | |
| "step": 402857 | |
| }, | |
| { | |
| "epoch": 26.33, | |
| "learning_rate": 0.0005260392037772138, | |
| "loss": 0.0055, | |
| "step": 404586 | |
| }, | |
| { | |
| "epoch": 26.44, | |
| "learning_rate": 0.0005235388964809152, | |
| "loss": 0.0052, | |
| "step": 406315 | |
| }, | |
| { | |
| "epoch": 26.55, | |
| "learning_rate": 0.0005210385891846165, | |
| "loss": 0.0054, | |
| "step": 408044 | |
| }, | |
| { | |
| "epoch": 26.67, | |
| "learning_rate": 0.0005185382818883176, | |
| "loss": 0.0053, | |
| "step": 409773 | |
| }, | |
| { | |
| "epoch": 26.78, | |
| "learning_rate": 0.000516037974592019, | |
| "loss": 0.0052, | |
| "step": 411502 | |
| }, | |
| { | |
| "epoch": 26.89, | |
| "learning_rate": 0.0005135376672957203, | |
| "loss": 0.006, | |
| "step": 413231 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 0.042408570647239685, | |
| "eval_max_distance": 37, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 14.3824, | |
| "eval_samples_per_second": 69.529, | |
| "eval_steps_per_second": 4.658, | |
| "step": 414909 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 0.0005110373599994215, | |
| "loss": 0.0095, | |
| "step": 414960 | |
| }, | |
| { | |
| "epoch": 27.12, | |
| "learning_rate": 0.0005085370527031229, | |
| "loss": 0.0115, | |
| "step": 416689 | |
| }, | |
| { | |
| "epoch": 27.23, | |
| "learning_rate": 0.0005060367454068242, | |
| "loss": 0.006, | |
| "step": 418418 | |
| }, | |
| { | |
| "epoch": 27.34, | |
| "learning_rate": 0.0005035364381105254, | |
| "loss": 0.0051, | |
| "step": 420147 | |
| }, | |
| { | |
| "epoch": 27.45, | |
| "learning_rate": 0.0005010361308142267, | |
| "loss": 0.0047, | |
| "step": 421876 | |
| }, | |
| { | |
| "epoch": 27.57, | |
| "learning_rate": 0.000498535823517928, | |
| "loss": 0.0047, | |
| "step": 423605 | |
| }, | |
| { | |
| "epoch": 27.68, | |
| "learning_rate": 0.0004960355162216294, | |
| "loss": 0.0054, | |
| "step": 425334 | |
| }, | |
| { | |
| "epoch": 27.79, | |
| "learning_rate": 0.0004935352089253306, | |
| "loss": 0.0052, | |
| "step": 427063 | |
| }, | |
| { | |
| "epoch": 27.9, | |
| "learning_rate": 0.000491034901629032, | |
| "loss": 0.0056, | |
| "step": 428792 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 0.04393070191144943, | |
| "eval_max_distance": 22, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 26.5483, | |
| "eval_samples_per_second": 37.667, | |
| "eval_steps_per_second": 2.524, | |
| "step": 430276 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "learning_rate": 0.0004885345943327332, | |
| "loss": 0.0105, | |
| "step": 430521 | |
| }, | |
| { | |
| "epoch": 28.13, | |
| "learning_rate": 0.0004860342870364345, | |
| "loss": 0.0093, | |
| "step": 432250 | |
| }, | |
| { | |
| "epoch": 28.24, | |
| "learning_rate": 0.0004835339797401358, | |
| "loss": 0.0055, | |
| "step": 433979 | |
| }, | |
| { | |
| "epoch": 28.35, | |
| "learning_rate": 0.0004810336724438371, | |
| "loss": 0.0049, | |
| "step": 435708 | |
| }, | |
| { | |
| "epoch": 28.47, | |
| "learning_rate": 0.00047853336514753835, | |
| "loss": 0.0044, | |
| "step": 437437 | |
| }, | |
| { | |
| "epoch": 28.58, | |
| "learning_rate": 0.0004760330578512397, | |
| "loss": 0.0044, | |
| "step": 439166 | |
| }, | |
| { | |
| "epoch": 28.69, | |
| "learning_rate": 0.000473532750554941, | |
| "loss": 0.0047, | |
| "step": 440895 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 0.0004710324432586423, | |
| "loss": 0.0047, | |
| "step": 442624 | |
| }, | |
| { | |
| "epoch": 28.92, | |
| "learning_rate": 0.00046853213596234356, | |
| "loss": 0.0054, | |
| "step": 444353 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 0.04814203828573227, | |
| "eval_max_distance": 23, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 35.122, | |
| "eval_samples_per_second": 28.472, | |
| "eval_steps_per_second": 1.908, | |
| "step": 445643 | |
| }, | |
| { | |
| "epoch": 29.03, | |
| "learning_rate": 0.00046603182866604485, | |
| "loss": 0.0103, | |
| "step": 446082 | |
| }, | |
| { | |
| "epoch": 29.14, | |
| "learning_rate": 0.00046353152136974614, | |
| "loss": 0.0076, | |
| "step": 447811 | |
| }, | |
| { | |
| "epoch": 29.25, | |
| "learning_rate": 0.00046103121407344743, | |
| "loss": 0.005, | |
| "step": 449540 | |
| }, | |
| { | |
| "epoch": 29.37, | |
| "learning_rate": 0.00045853090677714877, | |
| "loss": 0.0043, | |
| "step": 451269 | |
| }, | |
| { | |
| "epoch": 29.48, | |
| "learning_rate": 0.00045603059948085, | |
| "loss": 0.0043, | |
| "step": 452998 | |
| }, | |
| { | |
| "epoch": 29.59, | |
| "learning_rate": 0.00045353029218455135, | |
| "loss": 0.004, | |
| "step": 454727 | |
| }, | |
| { | |
| "epoch": 29.7, | |
| "learning_rate": 0.0004510299848882526, | |
| "loss": 0.0042, | |
| "step": 456456 | |
| }, | |
| { | |
| "epoch": 29.82, | |
| "learning_rate": 6.808721912515757e-06, | |
| "loss": 0.0039, | |
| "step": 458185 | |
| }, | |
| { | |
| "epoch": 29.93, | |
| "learning_rate": 2.641543085351246e-06, | |
| "loss": 0.004, | |
| "step": 459914 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 0.04417673125863075, | |
| "eval_max_distance": 25, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 68.6071, | |
| "eval_samples_per_second": 14.576, | |
| "eval_steps_per_second": 0.977, | |
| "step": 461010 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "step": 461010, | |
| "total_flos": 1.1619438964958822e+17, | |
| "train_loss": 3.931375028864634e-05, | |
| "train_runtime": 411.3459, | |
| "train_samples_per_second": 16810.814, | |
| "train_steps_per_second": 1120.736 | |
| } | |
| ], | |
| "logging_steps": 1729, | |
| "max_steps": 461010, | |
| "num_train_epochs": 30, | |
| "save_steps": 3458, | |
| "total_flos": 1.1619438964958822e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |