| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.995305164319249, | |
| "eval_steps": 500, | |
| "global_step": 957, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003129890453834116, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006259780907668232, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009389671361502348, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012519561815336464, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01564945226917058, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.018779342723004695, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02190923317683881, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.025039123630672927, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.028169014084507043, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03129890453834116, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03442879499217527, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999972486908167e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03755868544600939, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999889947935455e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0406885758998435, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999752383990224e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04381846635367762, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999559796586399e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.046948356807511735, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99931218784345e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.050078247261345854, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99900956048637e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.053208137715179966, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.998651917845645e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.056338028169014086, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.998239263857216e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0594679186228482, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997771603062438e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06259780907668232, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997248940608029e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06572769953051644, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99667128224601e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06885758998435054, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.996038634333654e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07198748043818466, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.995351003833398e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07511737089201878, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.994608398312777e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0782472613458529, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.993810825944343e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.081377151799687, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.992958295505567e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08450704225352113, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.992050816378749e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08763693270735524, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991088398550913e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09076682316118936, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.990071052613693e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09389671361502347, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.988998789763222e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09702660406885759, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987871621800006e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10015649452269171, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.986689561128798e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10328638497652583, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.985452620758453e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10641627543035993, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.984160814301794e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.10954616588419405, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.982814155975455e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11267605633802817, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.981412660599732e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11580594679186229, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.979956343598413e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1189358372456964, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.97844522099861e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12206572769953052, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.976879309430586e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12519561815336464, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.975258626127568e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12832550860719874, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.97358318892556e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13145539906103287, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.971853016263143e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13458528951486698, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.97006812718128e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13771517996870108, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.968228541323094e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.14084507042253522, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.96633427893367e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14397496087636932, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.964385360859805e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.14710485133020346, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.962381808549807e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.15023474178403756, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.960323644053248e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15336463223787167, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.95821089002071e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1564945226917058, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.956043569703553e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1596244131455399, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.953821706953651e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.162754303599374, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.951545326223128e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.16588419405320814, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.949214452564096e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.16901408450704225, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.946829111628367e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.17214397496087636, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.944389329667187e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.1752738654147105, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.941895133530929e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.1784037558685446, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.939346550668817e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.18153364632237873, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.936743609128607e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.18466353677621283, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.934086337556285e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.18779342723004694, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.931374765195756e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.19092331768388107, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.928608921888514e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.19405320813771518, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.925788838073322e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.19718309859154928, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.922914544785867e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.20031298904538342, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.919986073658429e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.20344287949921752, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.917003456919524e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.20657276995305165, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.913966727393558e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.20970266040688576, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.910875918500456e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.21283255086071987, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.907731064255304e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.215962441314554, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.904532199267966e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.2190923317683881, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.901279358742706e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.897972578477809e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.22535211267605634, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.894611894865171e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.22848200312989045, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.891197344889913e-05, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.23161189358372458, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.887728966129963e-05, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.2347417840375587, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.884206796755654e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2378716744913928, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.880630875529291e-05, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.24100156494522693, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.877001241804735e-05, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.24413145539906103, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.873317935526963e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.24726134585289514, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.869580997231634e-05, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.25039123630672927, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.865790468044637e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2535211267605634, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.861946389681645e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.2566510172143975, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.85804880444765e-05, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.2597809076682316, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.854097755236499e-05, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.26291079812206575, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.850093285530424e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.26604068857589985, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.846035439399564e-05, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.26917057902973396, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.841924261501474e-05, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.27230046948356806, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.837759797080641e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.27543035993740217, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.833542091967982e-05, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.27856025039123633, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.82927119258034e-05, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.28169014084507044, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.824947145919974e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.28482003129890454, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.820569999574041e-05, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.28794992175273865, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.816139801714073e-05, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.29107981220657275, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.811656601095446e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.2942097026604069, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.807120447056844e-05, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.297339593114241, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.802531389519716e-05, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.3004694835680751, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.797889478987727e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.30359937402190923, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.793194766546201e-05, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.30672926447574334, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.78844730386156e-05, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.30985915492957744, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.783647143180754e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.3129890453834116, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.77879433733069e-05, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3161189358372457, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.773888939717641e-05, | |
| "loss": 0.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.3192488262910798, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.768931004326674e-05, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.3223787167449139, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.763920585721037e-05, | |
| "loss": 0.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.325508607198748, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.758857739041575e-05, | |
| "loss": 0.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.3286384976525822, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.753742520006117e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.3317683881064163, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.748574984908854e-05, | |
| "loss": 0.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.3348982785602504, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.743355190619737e-05, | |
| "loss": 0.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.3380281690140845, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.738083194583836e-05, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.3411580594679186, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.732759054820718e-05, | |
| "loss": 0.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.3442879499217527, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.727382829923797e-05, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3474178403755869, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.721954579059705e-05, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.350547730829421, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.716474361967625e-05, | |
| "loss": 0.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.3536776212832551, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.710942238958645e-05, | |
| "loss": 0.0, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.3568075117370892, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.705358270915086e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.3599374021909233, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.699722519289843e-05, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.36306729264475746, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.694035046105693e-05, | |
| "loss": 0.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.36619718309859156, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.688295913954625e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.36932707355242567, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.68250518599715e-05, | |
| "loss": 0.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.37245696400625977, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.676662925961595e-05, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.3755868544600939, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.670769198143418e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.37871674491392804, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.66482406740449e-05, | |
| "loss": 0.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.38184663536776214, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.65882759917238e-05, | |
| "loss": 0.0, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.38497652582159625, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.65277985943964e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.38810641627543035, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.64668091476308e-05, | |
| "loss": 0.0, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.39123630672926446, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.640530832263027e-05, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.39436619718309857, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.634329679622598e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.3974960876369327, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.628077525086942e-05, | |
| "loss": 0.0, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.40062597809076683, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.621774437462503e-05, | |
| "loss": 0.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.40375586854460094, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.615420486116251e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.40688575899843504, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.609015740974925e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.41001564945226915, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.602560272524263e-05, | |
| "loss": 0.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.4131455399061033, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.596054151808222e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.4162754303599374, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.5894974504282e-05, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.4194053208137715, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.582890240542249e-05, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.4225352112676056, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.576232594864277e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.42566510172143973, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.569524586663253e-05, | |
| "loss": 0.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.4287949921752739, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.562766289762392e-05, | |
| "loss": 0.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.431924882629108, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.555957778538354e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.4350547730829421, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549099127920414e-05, | |
| "loss": 0.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.4381846635367762, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.542190413389649e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4413145539906103, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.535231710978097e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.528223097267924e-05, | |
| "loss": 0.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.4475743348982786, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.521164649390585e-05, | |
| "loss": 0.0, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.4507042253521127, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.514056445025967e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.4538341158059468, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.506898562401545e-05, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.4569640062597809, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.499691080291511e-05, | |
| "loss": 0.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.460093896713615, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.492434078015911e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.46322378716744916, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.485127635439772e-05, | |
| "loss": 0.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.46635367762128327, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.477771832972226e-05, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.4694835680751174, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.47036675156562e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4726134585289515, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.462912472714627e-05, | |
| "loss": 0.0, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.4757433489827856, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.455409078455353e-05, | |
| "loss": 0.0, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.4788732394366197, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.447856651364426e-05, | |
| "loss": 0.0, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.48200312989045385, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.440255274558094e-05, | |
| "loss": 0.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.48513302034428796, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.432605031691309e-05, | |
| "loss": 0.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.48826291079812206, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.424906006956805e-05, | |
| "loss": 0.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.49139280125195617, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.41715828508417e-05, | |
| "loss": 0.0, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.4945226917057903, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.40936195133892e-05, | |
| "loss": 0.0, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.49765258215962443, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.401517091521553e-05, | |
| "loss": 0.0, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.5007824726134585, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.393623791966607e-05, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5039123630672926, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.385682139541713e-05, | |
| "loss": 0.0, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.5070422535211268, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.377692221646635e-05, | |
| "loss": 0.0, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.5101721439749609, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.369654126212313e-05, | |
| "loss": 0.0, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.513302034428795, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.361567941699889e-05, | |
| "loss": 0.0, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.5164319248826291, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.353433757099736e-05, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.5195618153364632, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.345251661930486e-05, | |
| "loss": 0.0, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.5226917057902973, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.337021746238028e-05, | |
| "loss": 0.0, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.5258215962441315, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.328744100594535e-05, | |
| "loss": 0.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.5289514866979655, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.320418816097456e-05, | |
| "loss": 0.0, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.5320813771517997, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.31204598436852e-05, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.5352112676056338, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.303625697552721e-05, | |
| "loss": 0.0, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.5383411580594679, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.295158048317307e-05, | |
| "loss": 0.0, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.5414710485133021, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.286643129850765e-05, | |
| "loss": 0.0, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.5446009389671361, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.278081035861787e-05, | |
| "loss": 0.0, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.5477308294209703, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.269471860578245e-05, | |
| "loss": 0.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.5508607198748043, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.26081569874615e-05, | |
| "loss": 0.0, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.5539906103286385, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.252112645628615e-05, | |
| "loss": 0.0, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.5571205007824727, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.243362797004795e-05, | |
| "loss": 0.0, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.5602503912363067, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.23456624916885e-05, | |
| "loss": 0.0, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.5633802816901409, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.225723098928869e-05, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5665101721439749, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.216833443605814e-05, | |
| "loss": 0.0, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.5696400625978091, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.207897381032449e-05, | |
| "loss": 0.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.5727699530516432, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.198915009552253e-05, | |
| "loss": 0.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.5758998435054773, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.189886428018355e-05, | |
| "loss": 0.0, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.5790297339593115, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.180811735792431e-05, | |
| "loss": 0.0, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.5821596244131455, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.171691032743615e-05, | |
| "loss": 0.0, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.5852895148669797, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.162524419247407e-05, | |
| "loss": 0.0, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.5884194053208138, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.153311996184557e-05, | |
| "loss": 0.0, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.5915492957746479, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.144053864939958e-05, | |
| "loss": 0.0, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.594679186228482, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.134750127401544e-05, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5978090766823161, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.125400885959141e-05, | |
| "loss": 0.0, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.6009389671361502, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.11600624350337e-05, | |
| "loss": 0.0, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.6040688575899843, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.106566303424492e-05, | |
| "loss": 0.0, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.6071987480438185, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.097081169611283e-05, | |
| "loss": 0.0, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.6103286384976526, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.087550946449888e-05, | |
| "loss": 0.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.6134585289514867, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.077975738822666e-05, | |
| "loss": 0.0, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.6165884194053208, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.068355652107045e-05, | |
| "loss": 0.0, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.6197183098591549, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.058690792174358e-05, | |
| "loss": 0.0, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.622848200312989, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.048981265388676e-05, | |
| "loss": 0.0, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.6259780907668232, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.039227178605639e-05, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6291079812206573, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.029428639171281e-05, | |
| "loss": 0.0, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.6322378716744914, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.019585754920847e-05, | |
| "loss": 0.0, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.6353677621283255, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.009698634177613e-05, | |
| "loss": 0.0, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.6384976525821596, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.999767385751678e-05, | |
| "loss": 0.0, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.6416275430359938, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.989792118938784e-05, | |
| "loss": 0.0, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.6447574334898278, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.979772943519106e-05, | |
| "loss": 0.0, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.647887323943662, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.96970996975604e-05, | |
| "loss": 0.0, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.651017214397496, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.959603308394991e-05, | |
| "loss": 0.0, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.6541471048513302, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.949453070662165e-05, | |
| "loss": 0.0, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.6572769953051644, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.939259368263329e-05, | |
| "loss": 0.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.6604068857589984, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.929022313382589e-05, | |
| "loss": 0.0, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.6635367762128326, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.918742018681161e-05, | |
| "loss": 0.0, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.90841859729612e-05, | |
| "loss": 0.0, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.6697965571205008, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.898052162839162e-05, | |
| "loss": 0.0, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.672926447574335, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.887642829395353e-05, | |
| "loss": 0.0, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.676056338028169, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.877190711521872e-05, | |
| "loss": 0.0, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.6791862284820032, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.86669592424675e-05, | |
| "loss": 0.0, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.6823161189358372, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.856158583067607e-05, | |
| "loss": 0.0, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.6854460093896714, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.845578803950373e-05, | |
| "loss": 0.0, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.6885758998435054, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.834956703328026e-05, | |
| "loss": 0.0, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6917057902973396, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.824292398099298e-05, | |
| "loss": 0.0, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.6948356807511737, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.813586005627389e-05, | |
| "loss": 0.0, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.6979655712050078, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.802837643738686e-05, | |
| "loss": 0.0, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.701095461658842, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.792047430721456e-05, | |
| "loss": 0.0, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.704225352112676, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.781215485324544e-05, | |
| "loss": 0.0, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.7073552425665102, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.770341926756078e-05, | |
| "loss": 0.0, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.7104851330203443, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.759426874682142e-05, | |
| "loss": 0.0, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.7136150234741784, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.748470449225467e-05, | |
| "loss": 0.0, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.7167449139280125, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.737472770964112e-05, | |
| "loss": 0.0, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.7198748043818466, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.726433960930126e-05, | |
| "loss": 0.0, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.7230046948356808, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.715354140608229e-05, | |
| "loss": 0.0, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.7261345852895149, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.704233431934468e-05, | |
| "loss": 0.0, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.729264475743349, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.693071957294871e-05, | |
| "loss": 0.0, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.7323943661971831, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.68186983952411e-05, | |
| "loss": 0.0, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.7355242566510172, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.670627201904144e-05, | |
| "loss": 0.0, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.7386541471048513, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.659344168162861e-05, | |
| "loss": 0.0, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.7417840375586855, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.64802086247272e-05, | |
| "loss": 0.0, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.7449139280125195, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.636657409449378e-05, | |
| "loss": 0.0, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.7480438184663537, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.625253934150328e-05, | |
| "loss": 0.0, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.7511737089201878, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.613810562073512e-05, | |
| "loss": 0.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.7543035993740219, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.602327419155951e-05, | |
| "loss": 0.0, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.7574334898278561, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.590804631772352e-05, | |
| "loss": 0.0, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.7605633802816901, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.579242326733716e-05, | |
| "loss": 0.0, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.7636932707355243, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.56764063128595e-05, | |
| "loss": 0.0, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.7668231611893583, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.555999673108455e-05, | |
| "loss": 0.0, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.7699530516431925, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.544319580312734e-05, | |
| "loss": 0.0, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.7730829420970265, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.532600481440974e-05, | |
| "loss": 0.0, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.7762128325508607, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.52084250546463e-05, | |
| "loss": 0.0, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.7793427230046949, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.509045781783011e-05, | |
| "loss": 0.0, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.7824726134585289, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.497210440221857e-05, | |
| "loss": 0.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.7856025039123631, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.485336611031902e-05, | |
| "loss": 0.0, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.7887323943661971, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.473424424887447e-05, | |
| "loss": 0.0, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.7918622848200313, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.46147401288492e-05, | |
| "loss": 0.0, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.7949921752738655, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.449485506541434e-05, | |
| "loss": 0.0, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.7981220657276995, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.437459037793342e-05, | |
| "loss": 0.0, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.8012519561815337, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.425394738994776e-05, | |
| "loss": 0.0, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.8043818466353677, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.413292742916203e-05, | |
| "loss": 0.0, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.8075117370892019, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.401153182742954e-05, | |
| "loss": 0.0, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.810641627543036, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.388976192073761e-05, | |
| "loss": 0.0, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.8137715179968701, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.376761904919293e-05, | |
| "loss": 0.0, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.8169014084507042, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.364510455700666e-05, | |
| "loss": 0.0, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.8200312989045383, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.352221979247983e-05, | |
| "loss": 0.0, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.8231611893583725, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.339896610798836e-05, | |
| "loss": 0.0, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.8262910798122066, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.327534485996822e-05, | |
| "loss": 0.0, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.8294209702660407, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.315135740890052e-05, | |
| "loss": 0.0, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.8325508607198748, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.302700511929648e-05, | |
| "loss": 0.0, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.8356807511737089, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.290228935968252e-05, | |
| "loss": 0.0, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.838810641627543, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.277721150258508e-05, | |
| "loss": 0.0, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.8419405320813772, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.265177292451562e-05, | |
| "loss": 0.0, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.8450704225352113, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.252597500595534e-05, | |
| "loss": 0.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.8482003129890454, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.239981913134012e-05, | |
| "loss": 0.0, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.8513302034428795, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.227330668904527e-05, | |
| "loss": 0.0, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.8544600938967136, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.214643907137012e-05, | |
| "loss": 0.0, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.8575899843505478, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.201921767452286e-05, | |
| "loss": 0.0, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.8607198748043818, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.189164389860507e-05, | |
| "loss": 0.0, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.863849765258216, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.176371914759635e-05, | |
| "loss": 0.0, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.86697965571205, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.163544482933888e-05, | |
| "loss": 0.0, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.8701095461658842, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.150682235552191e-05, | |
| "loss": 0.0, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.8732394366197183, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.137785314166619e-05, | |
| "loss": 0.0, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.8763693270735524, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.124853860710846e-05, | |
| "loss": 0.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.8794992175273866, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.111888017498578e-05, | |
| "loss": 0.0, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.8826291079812206, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.098887927221993e-05, | |
| "loss": 0.0, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.8857589984350548, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.085853732950155e-05, | |
| "loss": 0.0, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.072785578127462e-05, | |
| "loss": 0.0, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.892018779342723, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.059683606572053e-05, | |
| "loss": 0.0, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.8951486697965572, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.046547962474221e-05, | |
| "loss": 0.0, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.8982785602503912, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.033378790394843e-05, | |
| "loss": 0.0, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.9014084507042254, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.020176235263776e-05, | |
| "loss": 0.0, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.9045383411580594, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.006940442378264e-05, | |
| "loss": 0.0, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.9076682316118936, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.993671557401339e-05, | |
| "loss": 0.0, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.9107981220657277, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.980369726360224e-05, | |
| "loss": 0.0, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.9139280125195618, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.967035095644716e-05, | |
| "loss": 0.0, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.917057902973396, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.953667812005584e-05, | |
| "loss": 0.0, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.92018779342723, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.94026802255295e-05, | |
| "loss": 0.0, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.9233176838810642, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.926835874754668e-05, | |
| "loss": 0.0, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.9264475743348983, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.913371516434704e-05, | |
| "loss": 0.0, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.9295774647887324, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.89987509577151e-05, | |
| "loss": 0.0, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.9327073552425665, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.886346761296389e-05, | |
| "loss": 0.0, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.9358372456964006, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.872786661891866e-05, | |
| "loss": 0.0, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.9389671361502347, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.859194946790043e-05, | |
| "loss": 0.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9420970266040689, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.845571765570966e-05, | |
| "loss": 0.0, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.945226917057903, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.831917268160966e-05, | |
| "loss": 0.0, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.9483568075117371, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.81823160483102e-05, | |
| "loss": 0.0, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.9514866979655712, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.804514926195093e-05, | |
| "loss": 0.0, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.9546165884194053, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.790767383208481e-05, | |
| "loss": 0.0, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.9577464788732394, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.77698912716615e-05, | |
| "loss": 0.0, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.9608763693270735, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.763180309701068e-05, | |
| "loss": 0.0, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.9640062597809077, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.74934108278254e-05, | |
| "loss": 0.0, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.9671361502347418, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.735471598714535e-05, | |
| "loss": 0.0, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.9702660406885759, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.72157201013401e-05, | |
| "loss": 0.0, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.97339593114241, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.707642470009227e-05, | |
| "loss": 0.0, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.9765258215962441, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.69368313163807e-05, | |
| "loss": 0.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.9796557120500783, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.679694148646366e-05, | |
| "loss": 0.0, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.9827856025039123, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.665675674986181e-05, | |
| "loss": 0.0, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.9859154929577465, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.65162786493414e-05, | |
| "loss": 0.0, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.9890453834115805, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.637550873089718e-05, | |
| "loss": 0.0, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.9921752738654147, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.623444854373539e-05, | |
| "loss": 0.0, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.9953051643192489, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.609309964025681e-05, | |
| "loss": 0.0, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.9984350547730829, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.595146357603958e-05, | |
| "loss": 0.0, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.9984350547730829, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.1685, | |
| "eval_samples_per_second": 35.534, | |
| "eval_steps_per_second": 8.9, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 1.001564945226917, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.580954190982213e-05, | |
| "loss": 0.0, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.0046948356807512, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.566733620348596e-05, | |
| "loss": 0.0, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 1.0078247261345852, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.552484802203858e-05, | |
| "loss": 0.0, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 1.0109546165884193, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.538207893359611e-05, | |
| "loss": 0.0, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 1.0140845070422535, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.523903050936621e-05, | |
| "loss": 0.0, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.0172143974960877, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.509570432363061e-05, | |
| "loss": 0.0, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.0203442879499218, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.495210195372795e-05, | |
| "loss": 0.0, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 1.0234741784037558, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.48082249800363e-05, | |
| "loss": 0.0, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 1.02660406885759, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.46640749859558e-05, | |
| "loss": 0.0, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 1.029733959311424, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.451965355789129e-05, | |
| "loss": 0.0, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 1.0328638497652582, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.437496228523473e-05, | |
| "loss": 0.0, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.0359937402190924, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.423000276034786e-05, | |
| "loss": 0.0, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 1.0391236306729263, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.408477657854458e-05, | |
| "loss": 0.0, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 1.0422535211267605, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.393928533807334e-05, | |
| "loss": 0.0, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0453834115805947, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.379353064009976e-05, | |
| "loss": 0.0, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 1.0485133020344288, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.364751408868877e-05, | |
| "loss": 0.0, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 1.051643192488263, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.350123729078705e-05, | |
| "loss": 0.0, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 1.054773082942097, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.335470185620543e-05, | |
| "loss": 0.0, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 1.057902973395931, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.320790939760105e-05, | |
| "loss": 0.0, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 1.0610328638497653, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.306086153045965e-05, | |
| "loss": 0.0, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 1.0641627543035994, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.291355987307784e-05, | |
| "loss": 0.0, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.0672926447574336, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.276600604654522e-05, | |
| "loss": 0.0, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 1.0704225352112675, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.261820167472658e-05, | |
| "loss": 0.0, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 1.0735524256651017, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.247014838424404e-05, | |
| "loss": 0.0, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 1.0766823161189358, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.232184780445907e-05, | |
| "loss": 0.0, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 1.07981220657277, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.217330156745471e-05, | |
| "loss": 0.0, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 1.0829420970266042, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.202451130801742e-05, | |
| "loss": 0.0, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 1.086071987480438, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.187547866361925e-05, | |
| "loss": 0.0, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 1.0892018779342723, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.172620527439976e-05, | |
| "loss": 0.0, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 1.0923317683881064, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.157669278314789e-05, | |
| "loss": 0.0, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 1.0954616588419406, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.1426942835284e-05, | |
| "loss": 0.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.0985915492957747, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.127695707884176e-05, | |
| "loss": 0.0, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 1.1017214397496087, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.112673716444988e-05, | |
| "loss": 0.0, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 1.1048513302034428, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.09762847453141e-05, | |
| "loss": 0.0, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 1.107981220657277, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.082560147719893e-05, | |
| "loss": 0.0, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.067468901840937e-05, | |
| "loss": 0.0, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 1.1142410015649453, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.052354902977278e-05, | |
| "loss": 0.0, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 1.1173708920187793, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.037218317462051e-05, | |
| "loss": 0.0, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 1.1205007824726134, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.022059311876962e-05, | |
| "loss": 0.0, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 1.1236306729264476, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.006878053050459e-05, | |
| "loss": 0.0, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 1.1267605633802817, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.991674708055885e-05, | |
| "loss": 0.0, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.1298904538341157, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.976449444209654e-05, | |
| "loss": 0.0, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 1.1330203442879498, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.961202429069396e-05, | |
| "loss": 0.0, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 1.136150234741784, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.945933830432127e-05, | |
| "loss": 0.0, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 1.1392801251956182, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.930643816332385e-05, | |
| "loss": 0.0, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 1.1424100156494523, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.915332555040396e-05, | |
| "loss": 0.0, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 1.1455399061032865, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.900000215060216e-05, | |
| "loss": 0.0, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 1.1486697965571204, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.884646965127876e-05, | |
| "loss": 0.0, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 1.1517996870109546, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.869272974209525e-05, | |
| "loss": 0.0, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 1.1549295774647887, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.853878411499574e-05, | |
| "loss": 0.0, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 1.158059467918623, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.83846344641883e-05, | |
| "loss": 0.0, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.1611893583724568, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.823028248612632e-05, | |
| "loss": 0.0, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 1.164319248826291, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.807572987948986e-05, | |
| "loss": 0.0, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 1.1674491392801252, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.792097834516697e-05, | |
| "loss": 0.0, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 1.1705790297339593, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.776602958623487e-05, | |
| "loss": 0.0, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 1.1737089201877935, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.761088530794136e-05, | |
| "loss": 0.0, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.1768388106416277, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.745554721768597e-05, | |
| "loss": 0.0, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 1.1799687010954616, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.730001702500113e-05, | |
| "loss": 0.0, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 1.1830985915492958, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.714429644153344e-05, | |
| "loss": 0.0, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.18622848200313, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.698838718102478e-05, | |
| "loss": 0.0, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 1.189358372456964, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.683229095929347e-05, | |
| "loss": 0.0, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.192488262910798, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.66760094942154e-05, | |
| "loss": 0.0, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 1.1956181533646322, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.651954450570508e-05, | |
| "loss": 0.0, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 1.1987480438184663, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.636289771569673e-05, | |
| "loss": 0.0, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 1.2018779342723005, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.620607084812538e-05, | |
| "loss": 0.0, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 1.2050078247261347, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.604906562890783e-05, | |
| "loss": 0.0, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 1.2081377151799688, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.589188378592369e-05, | |
| "loss": 0.0, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 1.2112676056338028, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.573452704899633e-05, | |
| "loss": 0.0, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 1.214397496087637, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.557699714987393e-05, | |
| "loss": 0.0, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 1.217527386541471, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.541929582221027e-05, | |
| "loss": 0.0, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 1.2206572769953052, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.526142480154584e-05, | |
| "loss": 0.0, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.2237871674491392, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.51033858252886e-05, | |
| "loss": 0.0, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 1.2269170579029733, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.494518063269486e-05, | |
| "loss": 0.0, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 1.2300469483568075, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.478681096485022e-05, | |
| "loss": 0.0, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 1.2331768388106417, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.46282785646504e-05, | |
| "loss": 0.0, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 1.2363067292644758, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.446958517678197e-05, | |
| "loss": 0.0, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 1.2394366197183098, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.431073254770323e-05, | |
| "loss": 0.0, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 1.242566510172144, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.415172242562497e-05, | |
| "loss": 0.0, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 1.245696400625978, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.399255656049125e-05, | |
| "loss": 0.0, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 1.2488262910798122, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.383323670396006e-05, | |
| "loss": 0.0, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 1.2519561815336462, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.367376460938416e-05, | |
| "loss": 0.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.2550860719874803, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.35141420317917e-05, | |
| "loss": 0.0, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 1.2582159624413145, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.335437072786692e-05, | |
| "loss": 0.0, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 1.2613458528951487, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.319445245593087e-05, | |
| "loss": 0.0, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 1.2644757433489828, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.303438897592197e-05, | |
| "loss": 0.0, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 1.267605633802817, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.28741820493767e-05, | |
| "loss": 0.0, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 1.2707355242566511, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.271383343941024e-05, | |
| "loss": 0.0, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 1.273865414710485, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.2553344910697e-05, | |
| "loss": 0.0, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 1.2769953051643192, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.23927182294512e-05, | |
| "loss": 0.0, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 1.2801251956181534, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.223195516340752e-05, | |
| "loss": 0.0, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 1.2832550860719873, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.207105748180158e-05, | |
| "loss": 0.0, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.2863849765258215, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.19100269553504e-05, | |
| "loss": 0.0, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 1.2895148669796557, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.174886535623307e-05, | |
| "loss": 0.0, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 1.2926447574334898, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.158757445807118e-05, | |
| "loss": 0.0, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 1.295774647887324, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.142615603590919e-05, | |
| "loss": 0.0, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 1.2989045383411582, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.126461186619508e-05, | |
| "loss": 0.0, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 1.302034428794992, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.110294372676065e-05, | |
| "loss": 0.0, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 1.3051643192488263, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.094115339680209e-05, | |
| "loss": 0.0, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 1.3082942097026604, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.077924265686027e-05, | |
| "loss": 0.0, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 1.3114241001564946, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.061721328880119e-05, | |
| "loss": 0.0, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 1.3145539906103285, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.0455067075796424e-05, | |
| "loss": 0.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.3176838810641627, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.029280580230342e-05, | |
| "loss": 0.0, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 1.3208137715179968, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.0130431254045904e-05, | |
| "loss": 0.0, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 1.323943661971831, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.996794521799425e-05, | |
| "loss": 0.0, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 1.3270735524256652, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9805349482345706e-05, | |
| "loss": 0.0, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 1.3302034428794993, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.964264583650486e-05, | |
| "loss": 0.0, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.947983607106385e-05, | |
| "loss": 0.0, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 1.3364632237871674, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.931692197778269e-05, | |
| "loss": 0.0, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 1.3395931142410016, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9153905349569525e-05, | |
| "loss": 0.0, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 1.3427230046948357, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8990787980460974e-05, | |
| "loss": 0.0, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 1.3458528951486697, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.882757166560226e-05, | |
| "loss": 0.0, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.3489827856025038, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.866425820122758e-05, | |
| "loss": 0.0, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 1.352112676056338, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8500849384640285e-05, | |
| "loss": 0.0, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 1.3552425665101722, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.833734701419308e-05, | |
| "loss": 0.0, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 1.3583724569640063, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.817375288926825e-05, | |
| "loss": 0.0, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 1.3615023474178405, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.801006881025788e-05, | |
| "loss": 0.0, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.3646322378716744, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.784629657854399e-05, | |
| "loss": 0.0, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 1.3677621283255086, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.768243799647879e-05, | |
| "loss": 0.0, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 1.3708920187793427, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.7518494867364725e-05, | |
| "loss": 0.0, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 1.374021909233177, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.7354468995434794e-05, | |
| "loss": 0.0, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 1.3771517996870108, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.71903621858325e-05, | |
| "loss": 0.0, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.380281690140845, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.7026176244592155e-05, | |
| "loss": 0.0, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 1.3834115805946792, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.686191297861892e-05, | |
| "loss": 0.0, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 1.3865414710485133, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.66975741956689e-05, | |
| "loss": 0.0, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 1.3896713615023475, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.653316170432932e-05, | |
| "loss": 0.0, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 1.3928012519561817, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.636867731399856e-05, | |
| "loss": 0.0, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 1.3959311424100156, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.620412283486629e-05, | |
| "loss": 0.0, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 1.3990610328638498, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.603950007789349e-05, | |
| "loss": 0.0, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 1.402190923317684, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.5874810854792606e-05, | |
| "loss": 0.0, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 1.405320813771518, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.571005697800748e-05, | |
| "loss": 0.0, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 1.408450704225352, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.554524026069354e-05, | |
| "loss": 0.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.4115805946791862, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.5380362516697794e-05, | |
| "loss": 0.0, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 1.4147104851330203, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.521542556053885e-05, | |
| "loss": 0.0, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 1.4178403755868545, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.505043120738693e-05, | |
| "loss": 0.0, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 1.4209702660406887, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.488538127304399e-05, | |
| "loss": 0.0, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 1.4241001564945228, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4720277573923595e-05, | |
| "loss": 0.0, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 1.4272300469483568, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.455512192703105e-05, | |
| "loss": 0.0, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 1.430359937402191, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4389916149943354e-05, | |
| "loss": 0.0, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 1.433489827856025, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.422466206078919e-05, | |
| "loss": 0.0, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 1.436619718309859, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.405936147822892e-05, | |
| "loss": 0.0, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 1.4397496087636932, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.3894016221434605e-05, | |
| "loss": 0.0, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.4428794992175273, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.372862811006992e-05, | |
| "loss": 0.0, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 1.4460093896713615, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.35631989642702e-05, | |
| "loss": 0.0, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 1.4491392801251957, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.3397730604622344e-05, | |
| "loss": 0.0, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 1.4522691705790298, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.323222485214484e-05, | |
| "loss": 0.0, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 1.455399061032864, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.306668352826765e-05, | |
| "loss": 0.0, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 1.458528951486698, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.290110845481224e-05, | |
| "loss": 0.0, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 1.461658841940532, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2735501453971516e-05, | |
| "loss": 0.0, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 1.4647887323943662, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.256986434828969e-05, | |
| "loss": 0.0, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 1.4679186228482002, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.240419896064235e-05, | |
| "loss": 0.0, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 1.4710485133020343, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2238507114216285e-05, | |
| "loss": 0.0, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.4741784037558685, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2072790632489497e-05, | |
| "loss": 0.0, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 1.4773082942097027, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.19070513392111e-05, | |
| "loss": 0.0, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 1.4804381846635368, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.174129105838127e-05, | |
| "loss": 0.0, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 1.483568075117371, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.1575511614231096e-05, | |
| "loss": 0.0, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 1.486697965571205, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.140971483120265e-05, | |
| "loss": 0.0, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.489827856025039, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.1243902533928754e-05, | |
| "loss": 0.0, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 1.4929577464788732, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.1078076547212994e-05, | |
| "loss": 0.0, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 1.4960876369327074, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.0912238696009616e-05, | |
| "loss": 0.0, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 1.4992175273865413, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.0746390805403445e-05, | |
| "loss": 0.0, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 1.5023474178403755, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.058053470058974e-05, | |
| "loss": 0.0, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.5054773082942097, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.041467220685424e-05, | |
| "loss": 0.0, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 1.5086071987480438, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.024880514955292e-05, | |
| "loss": 0.0, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 1.511737089201878, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.0082935354092044e-05, | |
| "loss": 0.0, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 1.5148669796557122, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.991706464590797e-05, | |
| "loss": 0.0, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 1.5179968701095463, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.975119485044709e-05, | |
| "loss": 0.0, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 1.5211267605633803, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.958532779314578e-05, | |
| "loss": 0.0, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 1.5242566510172144, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9419465299410264e-05, | |
| "loss": 0.0, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 1.5273865414710484, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9253609194596574e-05, | |
| "loss": 0.0, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 1.5305164319248825, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.908776130399039e-05, | |
| "loss": 0.0, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 1.5336463223787167, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8921923452787025e-05, | |
| "loss": 0.0, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.5367762128325508, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.875609746607127e-05, | |
| "loss": 0.0, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 1.539906103286385, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.859028516879737e-05, | |
| "loss": 0.0, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 1.5430359937402192, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.842448838576891e-05, | |
| "loss": 0.0, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 1.5461658841940533, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.825870894161874e-05, | |
| "loss": 0.0, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 1.5492957746478875, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8092948660788894e-05, | |
| "loss": 0.0, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 1.5524256651017214, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.79272093675105e-05, | |
| "loss": 0.0, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 1.5555555555555556, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7761492885783734e-05, | |
| "loss": 0.0, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 1.5586854460093895, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.759580103935767e-05, | |
| "loss": 0.0, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 1.5618153364632237, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7430135651710315e-05, | |
| "loss": 0.0, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 1.5649452269170578, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7264498546028496e-05, | |
| "loss": 0.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.568075117370892, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7098891545187755e-05, | |
| "loss": 0.0, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 1.5712050078247262, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.693331647173235e-05, | |
| "loss": 0.0, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 1.5743348982785603, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6767775147855186e-05, | |
| "loss": 0.0, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 1.5774647887323945, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.660226939537767e-05, | |
| "loss": 0.0, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 1.5805946791862286, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.643680103572981e-05, | |
| "loss": 0.0, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 1.5837245696400626, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.627137188993009e-05, | |
| "loss": 0.0, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 1.5868544600938967, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6105983778565406e-05, | |
| "loss": 0.0, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 1.5899843505477307, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.594063852177108e-05, | |
| "loss": 0.0, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 1.5931142410015648, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.577533793921083e-05, | |
| "loss": 0.0, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 1.596244131455399, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5610083850056664e-05, | |
| "loss": 0.0, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.5993740219092332, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5444878072968963e-05, | |
| "loss": 0.0, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 1.6025039123630673, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.527972242607642e-05, | |
| "loss": 0.0, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 1.6056338028169015, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.511461872695602e-05, | |
| "loss": 0.0, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 1.6087636932707357, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4949568792613066e-05, | |
| "loss": 0.0, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 1.6118935837245696, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.478457443946117e-05, | |
| "loss": 0.0, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 1.6150234741784038, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.461963748330221e-05, | |
| "loss": 0.0, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 1.618153364632238, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.445475973930647e-05, | |
| "loss": 0.0, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 1.6212832550860719, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.428994302199254e-05, | |
| "loss": 0.0, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 1.624413145539906, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.412518914520741e-05, | |
| "loss": 0.0, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 1.6275430359937402, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.396049992210652e-05, | |
| "loss": 0.0, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.6306729264475743, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.379587716513372e-05, | |
| "loss": 0.0, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 1.6338028169014085, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.363132268600145e-05, | |
| "loss": 0.0, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 1.6369327073552427, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.34668382956707e-05, | |
| "loss": 0.0, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 1.6400625978090768, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.330242580433111e-05, | |
| "loss": 0.0, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 1.6431924882629108, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.313808702138109e-05, | |
| "loss": 0.0, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.646322378716745, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.297382375540784e-05, | |
| "loss": 0.0, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 1.649452269170579, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2809637814167505e-05, | |
| "loss": 0.0, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 1.652582159624413, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.264553100456523e-05, | |
| "loss": 0.0, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 1.6557120500782472, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.248150513263528e-05, | |
| "loss": 0.0, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 1.6588419405320813, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.231756200352123e-05, | |
| "loss": 0.0, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.6619718309859155, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.215370342145601e-05, | |
| "loss": 0.0, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 1.6651017214397497, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.198993118974212e-05, | |
| "loss": 0.0, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 1.6682316118935838, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1826247110731755e-05, | |
| "loss": 0.0, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 1.671361502347418, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.166265298580694e-05, | |
| "loss": 0.0, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 1.674491392801252, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1499150615359726e-05, | |
| "loss": 0.0, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 1.677621283255086, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.133574179877243e-05, | |
| "loss": 0.0, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 1.6807511737089202, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1172428334397754e-05, | |
| "loss": 0.0, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 1.6838810641627542, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1009212019539044e-05, | |
| "loss": 0.0, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 1.6870109546165883, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.084609465043047e-05, | |
| "loss": 0.0, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 1.6901408450704225, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.068307802221734e-05, | |
| "loss": 0.0, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.6932707355242567, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.052016392893616e-05, | |
| "loss": 0.0, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 1.6964006259780908, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.035735416349515e-05, | |
| "loss": 0.0, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 1.699530516431925, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.0194650517654306e-05, | |
| "loss": 0.0, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 1.7026604068857591, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.003205478200576e-05, | |
| "loss": 0.0, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 1.705790297339593, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.986956874595409e-05, | |
| "loss": 0.0, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 1.7089201877934272, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9707194197696584e-05, | |
| "loss": 0.0, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 1.7120500782472612, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9544932924203594e-05, | |
| "loss": 0.0, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 1.7151799687010953, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9382786711198814e-05, | |
| "loss": 0.0, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 1.7183098591549295, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.922075734313974e-05, | |
| "loss": 0.0, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 1.7214397496087637, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.905884660319792e-05, | |
| "loss": 0.0, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.7245696400625978, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8897056273239354e-05, | |
| "loss": 0.0, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 1.727699530516432, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8735388133804936e-05, | |
| "loss": 0.0, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 1.7308294209702662, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.857384396409083e-05, | |
| "loss": 0.0, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 1.7339593114241003, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.841242554192884e-05, | |
| "loss": 0.0, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 1.7370892018779343, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.825113464376693e-05, | |
| "loss": 0.0, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 1.7402190923317684, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.808997304464961e-05, | |
| "loss": 0.0, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 1.7433489827856024, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7928942518198444e-05, | |
| "loss": 0.0, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 1.7464788732394365, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7768044836592475e-05, | |
| "loss": 0.0, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 1.7496087636932707, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7607281770548816e-05, | |
| "loss": 0.0, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 1.7527386541471048, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.744665508930303e-05, | |
| "loss": 0.0, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.755868544600939, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.728616656058977e-05, | |
| "loss": 0.0, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 1.7589984350547732, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.712581795062331e-05, | |
| "loss": 0.0, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 1.7621283255086073, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.696561102407805e-05, | |
| "loss": 0.0, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 1.7652582159624415, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6805547544069144e-05, | |
| "loss": 0.0, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 1.7683881064162754, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.664562927213308e-05, | |
| "loss": 0.0, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 1.7715179968701096, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.648585796820833e-05, | |
| "loss": 0.0, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 1.7746478873239435, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.632623539061585e-05, | |
| "loss": 0.0, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.616676329603995e-05, | |
| "loss": 0.0, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 1.7809076682316118, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.600744343950876e-05, | |
| "loss": 0.0, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 1.784037558685446, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5848277574375024e-05, | |
| "loss": 0.0, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.7871674491392802, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.568926745229677e-05, | |
| "loss": 0.0, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 1.7902973395931143, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.553041482321805e-05, | |
| "loss": 0.0, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 1.7934272300469485, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5371721435349615e-05, | |
| "loss": 0.0, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 1.7965571205007824, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.521318903514979e-05, | |
| "loss": 0.0, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 1.7996870109546166, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.505481936730516e-05, | |
| "loss": 0.0, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.8028169014084507, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.489661417471142e-05, | |
| "loss": 0.0, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 1.8059467918622847, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.473857519845415e-05, | |
| "loss": 0.0, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 1.8090766823161188, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.458070417778974e-05, | |
| "loss": 0.0, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 1.812206572769953, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.442300285012609e-05, | |
| "loss": 0.0, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 1.8153364632237872, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4265472951003676e-05, | |
| "loss": 0.0, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.8184663536776213, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.410811621407633e-05, | |
| "loss": 0.0, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 1.8215962441314555, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.395093437109219e-05, | |
| "loss": 0.0, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 1.8247261345852896, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3793929151874635e-05, | |
| "loss": 0.0, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 1.8278560250391236, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.363710228430329e-05, | |
| "loss": 0.0, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 1.8309859154929577, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.348045549429495e-05, | |
| "loss": 0.0, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 1.834115805946792, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.332399050578462e-05, | |
| "loss": 0.0, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 1.8372456964006258, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3167709040706535e-05, | |
| "loss": 0.0, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 1.84037558685446, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.301161281897523e-05, | |
| "loss": 0.0, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 1.8435054773082942, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.285570355846657e-05, | |
| "loss": 0.0, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 1.8466353677621283, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.269998297499887e-05, | |
| "loss": 0.0, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.8497652582159625, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.254445278231405e-05, | |
| "loss": 0.0, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 1.8528951486697967, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.238911469205865e-05, | |
| "loss": 0.0, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 1.8560250391236308, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.223397041376515e-05, | |
| "loss": 0.0, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 1.8591549295774648, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.207902165483305e-05, | |
| "loss": 0.0, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 1.862284820031299, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1924270120510135e-05, | |
| "loss": 0.0, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 1.8654147104851329, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.176971751387368e-05, | |
| "loss": 0.0, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 1.868544600938967, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.161536553581172e-05, | |
| "loss": 0.0, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 1.8716744913928012, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1461215885004266e-05, | |
| "loss": 0.0, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 1.8748043818466353, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1307270257904763e-05, | |
| "loss": 0.0, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 1.8779342723004695, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1153530348721257e-05, | |
| "loss": 0.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.8810641627543037, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.099999784939784e-05, | |
| "loss": 0.0, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 1.8841940532081378, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.084667444959605e-05, | |
| "loss": 0.0, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 1.887323943661972, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0693561836676174e-05, | |
| "loss": 0.0, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 1.890453834115806, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0540661695678755e-05, | |
| "loss": 0.0, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 1.89358372456964, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0387975709306043e-05, | |
| "loss": 0.0, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 1.896713615023474, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0235505557903478e-05, | |
| "loss": 0.0, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 1.8998435054773082, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0083252919441158e-05, | |
| "loss": 0.0, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 1.9029733959311423, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.993121946949542e-05, | |
| "loss": 0.0, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 1.9061032863849765, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9779406881230383e-05, | |
| "loss": 0.0, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 1.9092331768388107, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9627816825379497e-05, | |
| "loss": 0.0, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.9123630672926448, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9476450970227233e-05, | |
| "loss": 0.0, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 1.915492957746479, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9325310981590642e-05, | |
| "loss": 0.0, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 1.9186228482003131, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.917439852280108e-05, | |
| "loss": 0.0, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 1.921752738654147, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9023715254685903e-05, | |
| "loss": 0.0, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 1.9248826291079812, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8873262835550118e-05, | |
| "loss": 0.0, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 1.9280125195618152, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.872304292115828e-05, | |
| "loss": 0.0, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 1.9311424100156493, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.857305716471601e-05, | |
| "loss": 0.0, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 1.9342723004694835, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8423307216852142e-05, | |
| "loss": 0.0, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 1.9374021909233177, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8273794725600255e-05, | |
| "loss": 0.0, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 1.9405320813771518, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.812452133638075e-05, | |
| "loss": 0.0, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.943661971830986, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7975488691982578e-05, | |
| "loss": 0.0, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 1.9467918622848202, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7826698432545317e-05, | |
| "loss": 0.0, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 1.9499217527386543, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.767815219554094e-05, | |
| "loss": 0.0, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 1.9530516431924883, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7529851615755993e-05, | |
| "loss": 0.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 1.9561815336463224, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.738179832527343e-05, | |
| "loss": 0.0, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.9593114241001564, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7233993953454795e-05, | |
| "loss": 0.0, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 1.9624413145539905, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7086440126922163e-05, | |
| "loss": 0.0, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 1.9655712050078247, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.693913846954036e-05, | |
| "loss": 0.0, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 1.9687010954616588, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6792090602398966e-05, | |
| "loss": 0.0, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 1.971830985915493, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.664529814379457e-05, | |
| "loss": 0.0, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.9749608763693272, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6498762709212956e-05, | |
| "loss": 0.0, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 1.9780907668231613, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6352485911311253e-05, | |
| "loss": 0.0, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 1.9812206572769953, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6206469359900236e-05, | |
| "loss": 0.0, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 1.9843505477308294, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6060714661926654e-05, | |
| "loss": 0.0, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 1.9874804381846636, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5915223421455448e-05, | |
| "loss": 0.0, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 1.9906103286384975, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5769997239652137e-05, | |
| "loss": 0.0, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 1.9937402190923317, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5625037714765277e-05, | |
| "loss": 0.0, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 1.9968701095461658, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5480346442108714e-05, | |
| "loss": 0.0, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5335925014044193e-05, | |
| "loss": 0.0, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.1515, | |
| "eval_samples_per_second": 35.574, | |
| "eval_steps_per_second": 8.91, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 2.003129890453834, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5191775019963686e-05, | |
| "loss": 0.0, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.0062597809076683, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5047898046272057e-05, | |
| "loss": 0.0, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 2.0093896713615025, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.490429567636939e-05, | |
| "loss": 0.0, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 2.0125195618153366, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4760969490633807e-05, | |
| "loss": 0.0, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 2.0156494522691704, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4617921066403888e-05, | |
| "loss": 0.0, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 2.0187793427230045, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4475151977961437e-05, | |
| "loss": 0.0, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 2.0219092331768387, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4332663796514032e-05, | |
| "loss": 0.0, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 2.025039123630673, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.41904580901779e-05, | |
| "loss": 0.0, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 2.028169014084507, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4048536423960428e-05, | |
| "loss": 0.0, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 2.031298904538341, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.390690035974321e-05, | |
| "loss": 0.0, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 2.0344287949921753, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3765551456264618e-05, | |
| "loss": 0.0, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.0375586854460095, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3624491269102844e-05, | |
| "loss": 0.0, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 2.0406885758998436, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3483721350658593e-05, | |
| "loss": 0.0, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 2.043818466353678, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.334324325013821e-05, | |
| "loss": 0.0, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 2.0469483568075115, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3203058513536364e-05, | |
| "loss": 0.0, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 2.0500782472613457, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3063168683619325e-05, | |
| "loss": 0.0, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 2.05320813771518, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2923575299907753e-05, | |
| "loss": 0.0, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 2.056338028169014, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2784279898659914e-05, | |
| "loss": 0.0, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 2.059467918622848, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2645284012854644e-05, | |
| "loss": 0.0, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 2.0625978090766823, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2506589172174607e-05, | |
| "loss": 0.0, | |
| "step": 659 | |
| }, | |
| { | |
| "epoch": 2.0657276995305165, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2368196902989342e-05, | |
| "loss": 0.0, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.0688575899843507, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2230108728338506e-05, | |
| "loss": 0.0, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 2.071987480438185, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2092326167915194e-05, | |
| "loss": 0.0, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 2.075117370892019, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1954850738049086e-05, | |
| "loss": 0.0, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 2.0782472613458527, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.181768395168981e-05, | |
| "loss": 0.0, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 2.081377151799687, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1680827318390355e-05, | |
| "loss": 0.0, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 2.084507042253521, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1544282344290362e-05, | |
| "loss": 0.0, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.087636932707355, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1408050532099568e-05, | |
| "loss": 0.0, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 2.0907668231611893, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1272133381081356e-05, | |
| "loss": 0.0, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 2.0938967136150235, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1136532387036107e-05, | |
| "loss": 0.0, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 2.0970266040688577, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.100124904228491e-05, | |
| "loss": 0.0, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.100156494522692, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0866284835652955e-05, | |
| "loss": 0.0, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 2.103286384976526, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0731641252453344e-05, | |
| "loss": 0.0, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 2.10641627543036, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0597319774470507e-05, | |
| "loss": 0.0, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 2.109546165884194, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.046332187994417e-05, | |
| "loss": 0.0, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 2.112676056338028, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0329649043552845e-05, | |
| "loss": 0.0, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 2.115805946791862, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0196302736397777e-05, | |
| "loss": 0.0, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 2.1189358372456963, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0063284425986606e-05, | |
| "loss": 0.0, | |
| "step": 677 | |
| }, | |
| { | |
| "epoch": 2.1220657276995305, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9930595576217383e-05, | |
| "loss": 0.0, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 2.1251956181533647, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9798237647362244e-05, | |
| "loss": 0.0, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 2.128325508607199, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9666212096051572e-05, | |
| "loss": 0.0, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.131455399061033, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9534520375257793e-05, | |
| "loss": 0.0, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 2.134585289514867, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9403163934279495e-05, | |
| "loss": 0.0, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 2.1377151799687013, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9272144218725376e-05, | |
| "loss": 0.0, | |
| "step": 683 | |
| }, | |
| { | |
| "epoch": 2.140845070422535, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9141462670498456e-05, | |
| "loss": 0.0, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 2.143974960876369, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9011120727780096e-05, | |
| "loss": 0.0, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 2.1471048513302033, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8881119825014227e-05, | |
| "loss": 0.0, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 2.1502347417840375, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8751461392891545e-05, | |
| "loss": 0.0, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 2.1533646322378717, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.862214685833383e-05, | |
| "loss": 0.0, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 2.156494522691706, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8493177644478098e-05, | |
| "loss": 0.0, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 2.15962441314554, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.836455517066113e-05, | |
| "loss": 0.0, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.162754303599374, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.823628085240367e-05, | |
| "loss": 0.0, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 2.1658841940532083, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8108356101394964e-05, | |
| "loss": 0.0, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 2.169014084507042, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7980782325477163e-05, | |
| "loss": 0.0, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 2.172143974960876, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7853560928629903e-05, | |
| "loss": 0.0, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 2.1752738654147104, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7726693310954745e-05, | |
| "loss": 0.0, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 2.1784037558685445, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7600180868659887e-05, | |
| "loss": 0.0, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 2.1815336463223787, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7474024994044685e-05, | |
| "loss": 0.0, | |
| "step": 697 | |
| }, | |
| { | |
| "epoch": 2.184663536776213, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7348227075484396e-05, | |
| "loss": 0.0, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 2.187793427230047, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7222788497414922e-05, | |
| "loss": 0.0, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 2.190923317683881, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.709771064031747e-05, | |
| "loss": 0.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.1940532081377153, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.697299488070352e-05, | |
| "loss": 0.0, | |
| "step": 701 | |
| }, | |
| { | |
| "epoch": 2.1971830985915495, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6848642591099477e-05, | |
| "loss": 0.0, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 2.2003129890453836, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6724655140031774e-05, | |
| "loss": 0.0, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 2.2034428794992174, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6601033892011643e-05, | |
| "loss": 0.0, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 2.2065727699530515, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6477780207520177e-05, | |
| "loss": 0.0, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 2.2097026604068857, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.635489544299334e-05, | |
| "loss": 0.0, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 2.21283255086072, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.623238095080709e-05, | |
| "loss": 0.0, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 2.215962441314554, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6110238079262386e-05, | |
| "loss": 0.0, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 2.219092331768388, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.598846817257047e-05, | |
| "loss": 0.0, | |
| "step": 709 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5867072570837983e-05, | |
| "loss": 0.0, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.2253521126760565, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.574605261005225e-05, | |
| "loss": 0.0, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 2.2284820031298906, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.562540962206659e-05, | |
| "loss": 0.0, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 2.2316118935837244, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5505144934585663e-05, | |
| "loss": 0.0, | |
| "step": 713 | |
| }, | |
| { | |
| "epoch": 2.2347417840375585, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5385259871150802e-05, | |
| "loss": 0.0, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 2.2378716744913927, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5265755751125544e-05, | |
| "loss": 0.0, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 2.241001564945227, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5146633889680994e-05, | |
| "loss": 0.0, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 2.244131455399061, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5027895597781444e-05, | |
| "loss": 0.0, | |
| "step": 717 | |
| }, | |
| { | |
| "epoch": 2.247261345852895, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4909542182169889e-05, | |
| "loss": 0.0, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 2.2503912363067293, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4791574945353726e-05, | |
| "loss": 0.0, | |
| "step": 719 | |
| }, | |
| { | |
| "epoch": 2.2535211267605635, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4673995185590277e-05, | |
| "loss": 0.0, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.2566510172143976, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.455680419687267e-05, | |
| "loss": 0.0, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 2.2597809076682314, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.444000326891547e-05, | |
| "loss": 0.0, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 2.262910798122066, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.432359368714053e-05, | |
| "loss": 0.0, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 2.2660406885758997, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4207576732662847e-05, | |
| "loss": 0.0, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 2.269170579029734, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4091953682276494e-05, | |
| "loss": 0.0, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 2.272300469483568, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3976725808440488e-05, | |
| "loss": 0.0, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 2.275430359937402, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.386189437926489e-05, | |
| "loss": 0.0, | |
| "step": 727 | |
| }, | |
| { | |
| "epoch": 2.2785602503912363, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3747460658496731e-05, | |
| "loss": 0.0, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 2.2816901408450705, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3633425905506219e-05, | |
| "loss": 0.0, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 2.2848200312989047, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3519791375272805e-05, | |
| "loss": 0.0, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.287949921752739, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3406558318371377e-05, | |
| "loss": 0.0, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 2.291079812206573, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.329372798095856e-05, | |
| "loss": 0.0, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 2.2942097026604067, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3181301604758895e-05, | |
| "loss": 0.0, | |
| "step": 733 | |
| }, | |
| { | |
| "epoch": 2.297339593114241, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.30692804270513e-05, | |
| "loss": 0.0, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 2.300469483568075, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.295766568065534e-05, | |
| "loss": 0.0, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 2.303599374021909, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.284645859391772e-05, | |
| "loss": 0.0, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 2.3067292644757433, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2735660390698744e-05, | |
| "loss": 0.0, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 2.3098591549295775, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2625272290358902e-05, | |
| "loss": 0.0, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 2.3129890453834117, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2515295507745328e-05, | |
| "loss": 0.0, | |
| "step": 739 | |
| }, | |
| { | |
| "epoch": 2.316118935837246, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2405731253178594e-05, | |
| "loss": 0.0, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.31924882629108, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2296580732439234e-05, | |
| "loss": 0.0, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 2.3223787167449137, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2187845146754572e-05, | |
| "loss": 0.0, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 2.325508607198748, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.207952569278546e-05, | |
| "loss": 0.0, | |
| "step": 743 | |
| }, | |
| { | |
| "epoch": 2.328638497652582, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1971623562613155e-05, | |
| "loss": 0.0, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 2.331768388106416, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.186413994372611e-05, | |
| "loss": 0.0, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 2.3348982785602503, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1757076019007035e-05, | |
| "loss": 0.0, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 2.3380281690140845, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1650432966719748e-05, | |
| "loss": 0.0, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 2.3411580594679187, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1544211960496282e-05, | |
| "loss": 0.0, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 2.344287949921753, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1438414169323947e-05, | |
| "loss": 0.0, | |
| "step": 749 | |
| }, | |
| { | |
| "epoch": 2.347417840375587, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.133304075753251e-05, | |
| "loss": 0.0, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.350547730829421, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1228092884781282e-05, | |
| "loss": 0.0, | |
| "step": 751 | |
| }, | |
| { | |
| "epoch": 2.3536776212832553, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1123571706046477e-05, | |
| "loss": 0.0, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 2.356807511737089, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1019478371608377e-05, | |
| "loss": 0.0, | |
| "step": 753 | |
| }, | |
| { | |
| "epoch": 2.359937402190923, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0915814027038823e-05, | |
| "loss": 0.0, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 2.3630672926447573, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0812579813188406e-05, | |
| "loss": 0.0, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 2.3661971830985915, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0709776866174126e-05, | |
| "loss": 0.0, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 2.3693270735524257, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0607406317366726e-05, | |
| "loss": 0.0, | |
| "step": 757 | |
| }, | |
| { | |
| "epoch": 2.37245696400626, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0505469293378362e-05, | |
| "loss": 0.0, | |
| "step": 758 | |
| }, | |
| { | |
| "epoch": 2.375586854460094, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0403966916050089e-05, | |
| "loss": 0.0, | |
| "step": 759 | |
| }, | |
| { | |
| "epoch": 2.378716744913928, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0302900302439617e-05, | |
| "loss": 0.0, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.3818466353677623, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0202270564808947e-05, | |
| "loss": 0.0, | |
| "step": 761 | |
| }, | |
| { | |
| "epoch": 2.384976525821596, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0102078810612148e-05, | |
| "loss": 0.0, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 2.38810641627543, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0002326142483226e-05, | |
| "loss": 0.0, | |
| "step": 763 | |
| }, | |
| { | |
| "epoch": 2.3912363067292643, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.903013658223886e-06, | |
| "loss": 0.0, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 2.3943661971830985, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.804142450791526e-06, | |
| "loss": 0.0, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 2.3974960876369327, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.705713608287204e-06, | |
| "loss": 0.0, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 2.400625978090767, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.607728213943629e-06, | |
| "loss": 0.0, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 2.403755868544601, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.510187346113248e-06, | |
| "loss": 0.0, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 2.406885758998435, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.413092078256425e-06, | |
| "loss": 0.0, | |
| "step": 769 | |
| }, | |
| { | |
| "epoch": 2.4100156494522693, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.316443478929542e-06, | |
| "loss": 0.0, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.4131455399061035, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.220242611773344e-06, | |
| "loss": 0.0, | |
| "step": 771 | |
| }, | |
| { | |
| "epoch": 2.4162754303599376, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.124490535501134e-06, | |
| "loss": 0.0, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 2.4194053208137714, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.029188303887182e-06, | |
| "loss": 0.0, | |
| "step": 773 | |
| }, | |
| { | |
| "epoch": 2.4225352112676055, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.934336965755091e-06, | |
| "loss": 0.0, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 2.4256651017214397, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.839937564966317e-06, | |
| "loss": 0.0, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 2.428794992175274, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.745991140408589e-06, | |
| "loss": 0.0, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 2.431924882629108, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.652498725984575e-06, | |
| "loss": 0.0, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 2.435054773082942, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.559461350600406e-06, | |
| "loss": 0.0, | |
| "step": 778 | |
| }, | |
| { | |
| "epoch": 2.4381846635367763, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.466880038154457e-06, | |
| "loss": 0.0, | |
| "step": 779 | |
| }, | |
| { | |
| "epoch": 2.4413145539906105, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.374755807525936e-06, | |
| "loss": 0.0, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.4444444444444446, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.283089672563854e-06, | |
| "loss": 0.0, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 2.4475743348982784, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.191882642075698e-06, | |
| "loss": 0.0, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 2.4507042253521125, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.101135719816461e-06, | |
| "loss": 0.0, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 2.4538341158059467, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.010849904477468e-06, | |
| "loss": 0.0, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 2.456964006259781, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.92102618967554e-06, | |
| "loss": 0.0, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 2.460093896713615, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.831665563941864e-06, | |
| "loss": 0.0, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 2.463223787167449, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.742769010711326e-06, | |
| "loss": 0.0, | |
| "step": 787 | |
| }, | |
| { | |
| "epoch": 2.4663536776212833, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.65433750831151e-06, | |
| "loss": 0.0, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 2.4694835680751175, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.566372029952057e-06, | |
| "loss": 0.0, | |
| "step": 789 | |
| }, | |
| { | |
| "epoch": 2.4726134585289516, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.47887354371386e-06, | |
| "loss": 0.0, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.4757433489827854, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.391843012538502e-06, | |
| "loss": 0.0, | |
| "step": 791 | |
| }, | |
| { | |
| "epoch": 2.4788732394366195, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.3052813942175615e-06, | |
| "loss": 0.0, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 2.4820031298904537, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.219189641382129e-06, | |
| "loss": 0.0, | |
| "step": 793 | |
| }, | |
| { | |
| "epoch": 2.485133020344288, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.1335687014923545e-06, | |
| "loss": 0.0, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 2.488262910798122, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.048419516826932e-06, | |
| "loss": 0.0, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 2.491392801251956, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.963743024472791e-06, | |
| "loss": 0.0, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 2.4945226917057903, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.879540156314801e-06, | |
| "loss": 0.0, | |
| "step": 797 | |
| }, | |
| { | |
| "epoch": 2.4976525821596245, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.79581183902544e-06, | |
| "loss": 0.0, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 2.5007824726134587, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.7125589940546514e-06, | |
| "loss": 0.0, | |
| "step": 799 | |
| }, | |
| { | |
| "epoch": 2.5039123630672924, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.6297825376197275e-06, | |
| "loss": 0.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.507042253521127, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.547483380695146e-06, | |
| "loss": 0.0, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 2.5101721439749607, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.465662429002633e-06, | |
| "loss": 0.0, | |
| "step": 802 | |
| }, | |
| { | |
| "epoch": 2.513302034428795, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.384320583001113e-06, | |
| "loss": 0.0, | |
| "step": 803 | |
| }, | |
| { | |
| "epoch": 2.516431924882629, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.303458737876883e-06, | |
| "loss": 0.0, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 2.519561815336463, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.223077783533649e-06, | |
| "loss": 0.0, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 2.5226917057902973, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.143178604582883e-06, | |
| "loss": 0.0, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 2.5258215962441315, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.063762080333934e-06, | |
| "loss": 0.0, | |
| "step": 807 | |
| }, | |
| { | |
| "epoch": 2.5289514866979657, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.984829084784477e-06, | |
| "loss": 0.0, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 2.5320813771518, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.906380486610791e-06, | |
| "loss": 0.0, | |
| "step": 809 | |
| }, | |
| { | |
| "epoch": 2.535211267605634, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.828417149158305e-06, | |
| "loss": 0.0, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.5383411580594677, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.750939930431959e-06, | |
| "loss": 0.0, | |
| "step": 811 | |
| }, | |
| { | |
| "epoch": 2.5414710485133023, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.673949683086921e-06, | |
| "loss": 0.0, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 2.544600938967136, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.597447254419064e-06, | |
| "loss": 0.0, | |
| "step": 813 | |
| }, | |
| { | |
| "epoch": 2.54773082942097, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.521433486355748e-06, | |
| "loss": 0.0, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 2.5508607198748043, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.445909215446471e-06, | |
| "loss": 0.0, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 2.5539906103286385, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.370875272853737e-06, | |
| "loss": 0.0, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 2.5571205007824727, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.296332484343813e-06, | |
| "loss": 0.0, | |
| "step": 817 | |
| }, | |
| { | |
| "epoch": 2.560250391236307, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.222281670277756e-06, | |
| "loss": 0.0, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 2.563380281690141, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.148723645602288e-06, | |
| "loss": 0.0, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 2.5665101721439747, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.075659219840911e-06, | |
| "loss": 0.0, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.5696400625978093, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.003089197084898e-06, | |
| "loss": 0.0, | |
| "step": 821 | |
| }, | |
| { | |
| "epoch": 2.572769953051643, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.93101437598455e-06, | |
| "loss": 0.0, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 2.575899843505477, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.859435549740332e-06, | |
| "loss": 0.0, | |
| "step": 823 | |
| }, | |
| { | |
| "epoch": 2.5790297339593113, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7883535060941565e-06, | |
| "loss": 0.0, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 2.5821596244131455, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.717769027320762e-06, | |
| "loss": 0.0, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 2.5852895148669797, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.647682890219041e-06, | |
| "loss": 0.0, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 2.588419405320814, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.57809586610351e-06, | |
| "loss": 0.0, | |
| "step": 827 | |
| }, | |
| { | |
| "epoch": 2.591549295774648, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.50900872079586e-06, | |
| "loss": 0.0, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 2.594679186228482, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.44042221461648e-06, | |
| "loss": 0.0, | |
| "step": 829 | |
| }, | |
| { | |
| "epoch": 2.5978090766823163, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.372337102376089e-06, | |
| "loss": 0.0, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.60093896713615, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.304754133367489e-06, | |
| "loss": 0.0, | |
| "step": 831 | |
| }, | |
| { | |
| "epoch": 2.604068857589984, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.237674051357232e-06, | |
| "loss": 0.0, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 2.6071987480438183, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1710975945775224e-06, | |
| "loss": 0.0, | |
| "step": 833 | |
| }, | |
| { | |
| "epoch": 2.6103286384976525, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1050254957180065e-06, | |
| "loss": 0.0, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 2.6134585289514867, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.039458481917796e-06, | |
| "loss": 0.0, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 2.616588419405321, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.974397274757374e-06, | |
| "loss": 0.0, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 2.619718309859155, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9098425902507505e-06, | |
| "loss": 0.0, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 2.622848200312989, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.845795138837488e-06, | |
| "loss": 0.0, | |
| "step": 838 | |
| }, | |
| { | |
| "epoch": 2.6259780907668233, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.782255625374975e-06, | |
| "loss": 0.0, | |
| "step": 839 | |
| }, | |
| { | |
| "epoch": 2.629107981220657, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.719224749130579e-06, | |
| "loss": 0.0, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.6322378716744916, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6567032037740424e-06, | |
| "loss": 0.0, | |
| "step": 841 | |
| }, | |
| { | |
| "epoch": 2.6353677621283254, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.594691677369738e-06, | |
| "loss": 0.0, | |
| "step": 842 | |
| }, | |
| { | |
| "epoch": 2.6384976525821595, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.533190852369217e-06, | |
| "loss": 0.0, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 2.6416275430359937, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4722014056036036e-06, | |
| "loss": 0.0, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 2.644757433489828, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4117240082762125e-06, | |
| "loss": 0.0, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 2.647887323943662, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3517593259551004e-06, | |
| "loss": 0.0, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 2.651017214397496, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.292308018565815e-06, | |
| "loss": 0.0, | |
| "step": 847 | |
| }, | |
| { | |
| "epoch": 2.6541471048513303, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.233370740384056e-06, | |
| "loss": 0.0, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 2.6572769953051645, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1749481400285162e-06, | |
| "loss": 0.0, | |
| "step": 849 | |
| }, | |
| { | |
| "epoch": 2.6604068857589986, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.117040860453746e-06, | |
| "loss": 0.0, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.6635367762128324, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.059649538943077e-06, | |
| "loss": 0.0, | |
| "step": 851 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0027748071015716e-06, | |
| "loss": 0.0, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 2.6697965571205007, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.946417290849135e-06, | |
| "loss": 0.0, | |
| "step": 853 | |
| }, | |
| { | |
| "epoch": 2.672926447574335, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8905776104135696e-06, | |
| "loss": 0.0, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 2.676056338028169, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.83525638032377e-06, | |
| "loss": 0.0, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 2.679186228482003, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7804542094029663e-06, | |
| "loss": 0.0, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 2.6823161189358373, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7261717007620426e-06, | |
| "loss": 0.0, | |
| "step": 857 | |
| }, | |
| { | |
| "epoch": 2.6854460093896715, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.67240945179284e-06, | |
| "loss": 0.0, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 2.6885758998435056, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.619168054161647e-06, | |
| "loss": 0.0, | |
| "step": 859 | |
| }, | |
| { | |
| "epoch": 2.6917057902973394, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5664480938026425e-06, | |
| "loss": 0.0, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.694835680751174, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.514250150911468e-06, | |
| "loss": 0.0, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 2.6979655712050077, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4625747999388493e-06, | |
| "loss": 0.0, | |
| "step": 862 | |
| }, | |
| { | |
| "epoch": 2.701095461658842, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.411422609584246e-06, | |
| "loss": 0.0, | |
| "step": 863 | |
| }, | |
| { | |
| "epoch": 2.704225352112676, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.360794142789635e-06, | |
| "loss": 0.0, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 2.70735524256651, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.31068995673327e-06, | |
| "loss": 0.0, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 2.7104851330203443, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.261110602823591e-06, | |
| "loss": 0.0, | |
| "step": 866 | |
| }, | |
| { | |
| "epoch": 2.7136150234741785, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.212056626693115e-06, | |
| "loss": 0.0, | |
| "step": 867 | |
| }, | |
| { | |
| "epoch": 2.7167449139280127, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1635285681924632e-06, | |
| "loss": 0.0, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 2.7198748043818464, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1155269613844066e-06, | |
| "loss": 0.0, | |
| "step": 869 | |
| }, | |
| { | |
| "epoch": 2.723004694835681, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0680523345379953e-06, | |
| "loss": 0.0, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.7261345852895147, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0211052101227313e-06, | |
| "loss": 0.0, | |
| "step": 871 | |
| }, | |
| { | |
| "epoch": 2.729264475743349, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.974686104802842e-06, | |
| "loss": 0.0, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 2.732394366197183, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9287955294315652e-06, | |
| "loss": 0.0, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 2.735524256651017, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8834339890455466e-06, | |
| "loss": 0.0, | |
| "step": 874 | |
| }, | |
| { | |
| "epoch": 2.7386541471048513, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8386019828592726e-06, | |
| "loss": 0.0, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 2.7417840375586855, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7943000042595914e-06, | |
| "loss": 0.0, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 2.7449139280125197, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7505285408002615e-06, | |
| "loss": 0.0, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 2.748043818466354, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7072880741966002e-06, | |
| "loss": 0.0, | |
| "step": 878 | |
| }, | |
| { | |
| "epoch": 2.751173708920188, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6645790803201889e-06, | |
| "loss": 0.0, | |
| "step": 879 | |
| }, | |
| { | |
| "epoch": 2.7543035993740217, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6224020291935982e-06, | |
| "loss": 0.0, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.7574334898278563, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5807573849852653e-06, | |
| "loss": 0.0, | |
| "step": 881 | |
| }, | |
| { | |
| "epoch": 2.76056338028169, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5396456060043695e-06, | |
| "loss": 0.0, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 2.763693270735524, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4990671446957594e-06, | |
| "loss": 0.0, | |
| "step": 883 | |
| }, | |
| { | |
| "epoch": 2.7668231611893583, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4590224476350167e-06, | |
| "loss": 0.0, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 2.7699530516431925, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4195119555235114e-06, | |
| "loss": 0.0, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 2.7730829420970267, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3805361031835552e-06, | |
| "loss": 0.0, | |
| "step": 886 | |
| }, | |
| { | |
| "epoch": 2.776212832550861, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3420953195536323e-06, | |
| "loss": 0.0, | |
| "step": 887 | |
| }, | |
| { | |
| "epoch": 2.779342723004695, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3041900276836715e-06, | |
| "loss": 0.0, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 2.7824726134585287, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2668206447303766e-06, | |
| "loss": 0.0, | |
| "step": 889 | |
| }, | |
| { | |
| "epoch": 2.7856025039123633, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2299875819526629e-06, | |
| "loss": 0.0, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.788732394366197, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1936912447070903e-06, | |
| "loss": 0.0, | |
| "step": 891 | |
| }, | |
| { | |
| "epoch": 2.791862284820031, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.157932032443465e-06, | |
| "loss": 0.0, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 2.7949921752738653, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1227103387003667e-06, | |
| "loss": 0.0, | |
| "step": 893 | |
| }, | |
| { | |
| "epoch": 2.7981220657276995, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0880265511008736e-06, | |
| "loss": 0.0, | |
| "step": 894 | |
| }, | |
| { | |
| "epoch": 2.8012519561815337, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0538810513482933e-06, | |
| "loss": 0.0, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 2.804381846635368, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0202742152219114e-06, | |
| "loss": 0.0, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 2.807511737089202, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.872064125729386e-07, | |
| "loss": 0.0, | |
| "step": 897 | |
| }, | |
| { | |
| "epoch": 2.810641627543036, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.546780073203588e-07, | |
| "loss": 0.0, | |
| "step": 898 | |
| }, | |
| { | |
| "epoch": 2.8137715179968703, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.226893574469708e-07, | |
| "loss": 0.0, | |
| "step": 899 | |
| }, | |
| { | |
| "epoch": 2.816901408450704, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.912408149954421e-07, | |
| "loss": 0.0, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.820031298904538, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.603327260644278e-07, | |
| "loss": 0.0, | |
| "step": 901 | |
| }, | |
| { | |
| "epoch": 2.8231611893583723, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.299654308047633e-07, | |
| "loss": 0.0, | |
| "step": 902 | |
| }, | |
| { | |
| "epoch": 2.8262910798122065, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.001392634157223e-07, | |
| "loss": 0.0, | |
| "step": 903 | |
| }, | |
| { | |
| "epoch": 2.8294209702660407, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.708545521413424e-07, | |
| "loss": 0.0, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 2.832550860719875, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.421116192667943e-07, | |
| "loss": 0.0, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 2.835680751173709, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.139107811148626e-07, | |
| "loss": 0.0, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 2.838810641627543, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.862523480424488e-07, | |
| "loss": 0.0, | |
| "step": 907 | |
| }, | |
| { | |
| "epoch": 2.8419405320813773, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.591366244371566e-07, | |
| "loss": 0.0, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 2.845070422535211, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.325639087139401e-07, | |
| "loss": 0.0, | |
| "step": 909 | |
| }, | |
| { | |
| "epoch": 2.8482003129890456, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.065344933118333e-07, | |
| "loss": 0.0, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.8513302034428794, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.810486646907087e-07, | |
| "loss": 0.0, | |
| "step": 911 | |
| }, | |
| { | |
| "epoch": 2.8544600938967135, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.561067033281464e-07, | |
| "loss": 0.0, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 2.8575899843505477, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.317088837163309e-07, | |
| "loss": 0.0, | |
| "step": 913 | |
| }, | |
| { | |
| "epoch": 2.860719874804382, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.07855474359048e-07, | |
| "loss": 0.0, | |
| "step": 914 | |
| }, | |
| { | |
| "epoch": 2.863849765258216, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.845467377687152e-07, | |
| "loss": 0.0, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 2.86697965571205, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.617829304634891e-07, | |
| "loss": 0.0, | |
| "step": 916 | |
| }, | |
| { | |
| "epoch": 2.8701095461658843, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.395643029644736e-07, | |
| "loss": 0.0, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 2.873239436619718, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1789109979291083e-07, | |
| "loss": 0.0, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 2.8763693270735526, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.967635594675334e-07, | |
| "loss": 0.0, | |
| "step": 919 | |
| }, | |
| { | |
| "epoch": 2.8794992175273864, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7618191450192185e-07, | |
| "loss": 0.0, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.8826291079812205, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.561463914019625e-07, | |
| "loss": 0.0, | |
| "step": 921 | |
| }, | |
| { | |
| "epoch": 2.8857589984350547, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3665721066332144e-07, | |
| "loss": 0.0, | |
| "step": 922 | |
| }, | |
| { | |
| "epoch": 2.888888888888889, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.177145867690523e-07, | |
| "loss": 0.0, | |
| "step": 923 | |
| }, | |
| { | |
| "epoch": 2.892018779342723, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9931872818720895e-07, | |
| "loss": 0.0, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 2.895148669796557, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8146983736857536e-07, | |
| "loss": 0.0, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 2.8982785602503913, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6416811074441717e-07, | |
| "loss": 0.0, | |
| "step": 926 | |
| }, | |
| { | |
| "epoch": 2.9014084507042255, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.474137387243336e-07, | |
| "loss": 0.0, | |
| "step": 927 | |
| }, | |
| { | |
| "epoch": 2.9045383411580596, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3120690569414793e-07, | |
| "loss": 0.0, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 2.9076682316118934, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1554779001390357e-07, | |
| "loss": 0.0, | |
| "step": 929 | |
| }, | |
| { | |
| "epoch": 2.910798122065728, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0043656401587675e-07, | |
| "loss": 0.0, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.9139280125195617, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.85873394002678e-07, | |
| "loss": 0.0, | |
| "step": 931 | |
| }, | |
| { | |
| "epoch": 2.917057902973396, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7185844024544816e-07, | |
| "loss": 0.0, | |
| "step": 932 | |
| }, | |
| { | |
| "epoch": 2.92018779342723, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5839185698206526e-07, | |
| "loss": 0.0, | |
| "step": 933 | |
| }, | |
| { | |
| "epoch": 2.923317683881064, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4547379241547364e-07, | |
| "loss": 0.0, | |
| "step": 934 | |
| }, | |
| { | |
| "epoch": 2.9264475743348983, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3310438871202424e-07, | |
| "loss": 0.0, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 2.9295774647887325, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.212837819999424e-07, | |
| "loss": 0.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 2.9327073552425666, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1001210236779025e-07, | |
| "loss": 0.0, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 2.9358372456964004, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.928947386308452e-08, | |
| "loss": 0.0, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 2.938967136150235, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.911601449087537e-08, | |
| "loss": 0.0, | |
| "step": 939 | |
| }, | |
| { | |
| "epoch": 2.9420970266040687, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.949183621250856e-08, | |
| "loss": 0.0, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.945226917057903, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.0417044944332e-08, | |
| "loss": 0.0, | |
| "step": 941 | |
| }, | |
| { | |
| "epoch": 2.948356807511737, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.189174055657442e-08, | |
| "loss": 0.0, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 2.951486697965571, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.391601687222969e-08, | |
| "loss": 0.0, | |
| "step": 943 | |
| }, | |
| { | |
| "epoch": 2.9546165884194053, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.64899616660297e-08, | |
| "loss": 0.0, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 2.9577464788732395, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.961365666346195e-08, | |
| "loss": 0.0, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 2.9608763693270737, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3287177539892414e-08, | |
| "loss": 0.0, | |
| "step": 946 | |
| }, | |
| { | |
| "epoch": 2.964006259780908, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7510593919727323e-08, | |
| "loss": 0.0, | |
| "step": 947 | |
| }, | |
| { | |
| "epoch": 2.967136150234742, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2283969375630488e-08, | |
| "loss": 0.0, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 2.9702660406885757, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7607361427846026e-08, | |
| "loss": 0.0, | |
| "step": 949 | |
| }, | |
| { | |
| "epoch": 2.97339593114241, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3480821543554457e-08, | |
| "loss": 0.0, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.976525821596244, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.904395136295374e-09, | |
| "loss": 0.0, | |
| "step": 951 | |
| }, | |
| { | |
| "epoch": 2.979655712050078, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.87812156549561e-09, | |
| "loss": 0.0, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 2.9827856025039123, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.402034136008482e-09, | |
| "loss": 0.0, | |
| "step": 953 | |
| }, | |
| { | |
| "epoch": 2.9859154929577465, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.47616009776408e-09, | |
| "loss": 0.0, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 2.9890453834115807, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1005206454584027e-09, | |
| "loss": 0.0, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 2.992175273865415, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7513091833686334e-10, | |
| "loss": 0.0, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 2.995305164319249, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 957 | |
| }, | |
| { | |
| "epoch": 2.995305164319249, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.1608, | |
| "eval_samples_per_second": 35.552, | |
| "eval_steps_per_second": 8.905, | |
| "step": 957 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 957, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.534775174117458e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |