| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6036217303822937, | |
| "eval_steps": 500, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002012072434607646, | |
| "grad_norm": 46.70955276489258, | |
| "learning_rate": 6.5e-06, | |
| "loss": 1.4376, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004024144869215292, | |
| "grad_norm": 25.710079193115234, | |
| "learning_rate": 1.3e-05, | |
| "loss": 1.2619, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006036217303822937, | |
| "grad_norm": 26.04344940185547, | |
| "learning_rate": 1.9499999999999996e-05, | |
| "loss": 1.2208, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008048289738430584, | |
| "grad_norm": 8.251016616821289, | |
| "learning_rate": 2.6e-05, | |
| "loss": 1.0171, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01006036217303823, | |
| "grad_norm": 4.199310302734375, | |
| "learning_rate": 3.25e-05, | |
| "loss": 0.9699, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012072434607645875, | |
| "grad_norm": 6.134476661682129, | |
| "learning_rate": 3.899999999999999e-05, | |
| "loss": 0.9899, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014084507042253521, | |
| "grad_norm": 4.348274230957031, | |
| "learning_rate": 4.5499999999999995e-05, | |
| "loss": 0.9959, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01609657947686117, | |
| "grad_norm": 3.9475340843200684, | |
| "learning_rate": 5.2e-05, | |
| "loss": 0.8857, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.018108651911468814, | |
| "grad_norm": 3.1918065547943115, | |
| "learning_rate": 5.85e-05, | |
| "loss": 0.9008, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02012072434607646, | |
| "grad_norm": 2.7590606212615967, | |
| "learning_rate": 6.5e-05, | |
| "loss": 0.8703, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.022132796780684104, | |
| "grad_norm": 3.0539116859436035, | |
| "learning_rate": 6.499932377117017e-05, | |
| "loss": 0.8258, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02414486921529175, | |
| "grad_norm": 2.821988344192505, | |
| "learning_rate": 6.499729511282135e-05, | |
| "loss": 0.9071, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.026156941649899398, | |
| "grad_norm": 2.776759147644043, | |
| "learning_rate": 6.499391410937425e-05, | |
| "loss": 0.8496, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.028169014084507043, | |
| "grad_norm": 2.897883176803589, | |
| "learning_rate": 6.498918090152627e-05, | |
| "loss": 0.8339, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.030181086519114688, | |
| "grad_norm": 2.511650562286377, | |
| "learning_rate": 6.498309568624549e-05, | |
| "loss": 0.8398, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03219315895372234, | |
| "grad_norm": 2.69217848777771, | |
| "learning_rate": 6.497565871676255e-05, | |
| "loss": 0.8373, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03420523138832998, | |
| "grad_norm": 2.5202300548553467, | |
| "learning_rate": 6.496687030256012e-05, | |
| "loss": 0.8418, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03621730382293763, | |
| "grad_norm": 2.4313321113586426, | |
| "learning_rate": 6.495673080935999e-05, | |
| "loss": 0.8482, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03822937625754527, | |
| "grad_norm": 2.278684139251709, | |
| "learning_rate": 6.494524065910784e-05, | |
| "loss": 0.8059, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04024144869215292, | |
| "grad_norm": 2.2294907569885254, | |
| "learning_rate": 6.493240032995573e-05, | |
| "loss": 0.8085, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04225352112676056, | |
| "grad_norm": 2.446382999420166, | |
| "learning_rate": 6.491821035624218e-05, | |
| "loss": 0.8298, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04426559356136821, | |
| "grad_norm": 2.4150474071502686, | |
| "learning_rate": 6.490267132846992e-05, | |
| "loss": 0.9265, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04627766599597585, | |
| "grad_norm": 2.170037269592285, | |
| "learning_rate": 6.488578389328129e-05, | |
| "loss": 0.8323, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0482897384305835, | |
| "grad_norm": 2.010956287384033, | |
| "learning_rate": 6.486754875343145e-05, | |
| "loss": 0.8646, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05030181086519115, | |
| "grad_norm": 1.8752851486206055, | |
| "learning_rate": 6.484796666775895e-05, | |
| "loss": 0.8402, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.052313883299798795, | |
| "grad_norm": 1.8610150814056396, | |
| "learning_rate": 6.482703845115434e-05, | |
| "loss": 0.8256, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05432595573440644, | |
| "grad_norm": 1.8047019243240356, | |
| "learning_rate": 6.480476497452613e-05, | |
| "loss": 0.819, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.056338028169014086, | |
| "grad_norm": 1.6434446573257446, | |
| "learning_rate": 6.47811471647646e-05, | |
| "loss": 0.8671, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.05835010060362173, | |
| "grad_norm": 1.5787513256072998, | |
| "learning_rate": 6.475618600470322e-05, | |
| "loss": 0.7992, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.060362173038229376, | |
| "grad_norm": 1.4350961446762085, | |
| "learning_rate": 6.472988253307773e-05, | |
| "loss": 0.7524, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06237424547283702, | |
| "grad_norm": 1.391878604888916, | |
| "learning_rate": 6.470223784448298e-05, | |
| "loss": 0.7541, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06438631790744467, | |
| "grad_norm": 1.4117164611816406, | |
| "learning_rate": 6.467325308932728e-05, | |
| "loss": 0.7899, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.06639839034205232, | |
| "grad_norm": 1.3123915195465088, | |
| "learning_rate": 6.464292947378462e-05, | |
| "loss": 0.7402, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06841046277665996, | |
| "grad_norm": 1.4149091243743896, | |
| "learning_rate": 6.46112682597444e-05, | |
| "loss": 0.8195, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07042253521126761, | |
| "grad_norm": 1.2951886653900146, | |
| "learning_rate": 6.457827076475899e-05, | |
| "loss": 0.7179, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07243460764587525, | |
| "grad_norm": 1.3390341997146606, | |
| "learning_rate": 6.454393836198883e-05, | |
| "loss": 0.7973, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0744466800804829, | |
| "grad_norm": 1.307084560394287, | |
| "learning_rate": 6.450827248014535e-05, | |
| "loss": 0.7591, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.07645875251509054, | |
| "grad_norm": 1.3605775833129883, | |
| "learning_rate": 6.447127460343148e-05, | |
| "loss": 0.8085, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.07847082494969819, | |
| "grad_norm": 1.4956183433532715, | |
| "learning_rate": 6.443294627147988e-05, | |
| "loss": 0.735, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.08048289738430583, | |
| "grad_norm": 1.371940016746521, | |
| "learning_rate": 6.439328907928889e-05, | |
| "loss": 0.8025, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08249496981891348, | |
| "grad_norm": 1.4716073274612427, | |
| "learning_rate": 6.435230467715615e-05, | |
| "loss": 0.7381, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.08450704225352113, | |
| "grad_norm": 1.3676444292068481, | |
| "learning_rate": 6.430999477060994e-05, | |
| "loss": 0.7601, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.08651911468812877, | |
| "grad_norm": 1.5072672367095947, | |
| "learning_rate": 6.426636112033818e-05, | |
| "loss": 0.8209, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.08853118712273642, | |
| "grad_norm": 1.3186477422714233, | |
| "learning_rate": 6.422140554211511e-05, | |
| "loss": 0.777, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.09054325955734406, | |
| "grad_norm": 1.4689198732376099, | |
| "learning_rate": 6.417512990672591e-05, | |
| "loss": 0.871, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0925553319919517, | |
| "grad_norm": 1.287394642829895, | |
| "learning_rate": 6.412753613988862e-05, | |
| "loss": 0.7281, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.09456740442655935, | |
| "grad_norm": 1.1629823446273804, | |
| "learning_rate": 6.407862622217414e-05, | |
| "loss": 0.715, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.096579476861167, | |
| "grad_norm": 1.2146556377410889, | |
| "learning_rate": 6.402840218892381e-05, | |
| "loss": 0.6985, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.09859154929577464, | |
| "grad_norm": 1.3280084133148193, | |
| "learning_rate": 6.397686613016466e-05, | |
| "loss": 0.8195, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1006036217303823, | |
| "grad_norm": 1.157867193222046, | |
| "learning_rate": 6.392402019052244e-05, | |
| "loss": 0.7529, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10261569416498995, | |
| "grad_norm": 1.1449801921844482, | |
| "learning_rate": 6.386986656913242e-05, | |
| "loss": 0.7834, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.10462776659959759, | |
| "grad_norm": 1.2190605401992798, | |
| "learning_rate": 6.381440751954782e-05, | |
| "loss": 0.8203, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.10663983903420524, | |
| "grad_norm": 1.2562769651412964, | |
| "learning_rate": 6.375764534964608e-05, | |
| "loss": 0.7338, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.10865191146881288, | |
| "grad_norm": 1.1834882497787476, | |
| "learning_rate": 6.369958242153278e-05, | |
| "loss": 0.7489, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.11066398390342053, | |
| "grad_norm": 1.2381786108016968, | |
| "learning_rate": 6.364022115144337e-05, | |
| "loss": 0.7537, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.11267605633802817, | |
| "grad_norm": 1.256866693496704, | |
| "learning_rate": 6.357956400964259e-05, | |
| "loss": 0.7725, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.11468812877263582, | |
| "grad_norm": 1.2332978248596191, | |
| "learning_rate": 6.351761352032171e-05, | |
| "loss": 0.774, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.11670020120724346, | |
| "grad_norm": 1.3557363748550415, | |
| "learning_rate": 6.345437226149345e-05, | |
| "loss": 0.7877, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.11871227364185111, | |
| "grad_norm": 1.1381844282150269, | |
| "learning_rate": 6.338984286488472e-05, | |
| "loss": 0.7152, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.12072434607645875, | |
| "grad_norm": 1.147226095199585, | |
| "learning_rate": 6.332402801582716e-05, | |
| "loss": 0.7713, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1227364185110664, | |
| "grad_norm": 1.0942986011505127, | |
| "learning_rate": 6.325693045314524e-05, | |
| "loss": 0.7446, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.12474849094567404, | |
| "grad_norm": 1.233619213104248, | |
| "learning_rate": 6.318855296904246e-05, | |
| "loss": 0.8107, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.1267605633802817, | |
| "grad_norm": 1.1866984367370605, | |
| "learning_rate": 6.311889840898498e-05, | |
| "loss": 0.8206, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.12877263581488935, | |
| "grad_norm": 1.176274061203003, | |
| "learning_rate": 6.304796967158343e-05, | |
| "loss": 0.7813, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.13078470824949698, | |
| "grad_norm": 1.1214070320129395, | |
| "learning_rate": 6.297576970847205e-05, | |
| "loss": 0.6908, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.13279678068410464, | |
| "grad_norm": 1.0725229978561401, | |
| "learning_rate": 6.290230152418603e-05, | |
| "loss": 0.756, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.13480885311871227, | |
| "grad_norm": 1.1194369792938232, | |
| "learning_rate": 6.28275681760364e-05, | |
| "loss": 0.7766, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.13682092555331993, | |
| "grad_norm": 1.090072512626648, | |
| "learning_rate": 6.275157277398282e-05, | |
| "loss": 0.7856, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.13883299798792756, | |
| "grad_norm": 1.1602994203567505, | |
| "learning_rate": 6.267431848050418e-05, | |
| "loss": 0.7597, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.14084507042253522, | |
| "grad_norm": 1.0984241962432861, | |
| "learning_rate": 6.259580851046697e-05, | |
| "loss": 0.7318, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 1.0639097690582275, | |
| "learning_rate": 6.251604613099149e-05, | |
| "loss": 0.7265, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.1448692152917505, | |
| "grad_norm": 1.0951672792434692, | |
| "learning_rate": 6.243503466131597e-05, | |
| "loss": 0.7312, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.14688128772635814, | |
| "grad_norm": 1.092551827430725, | |
| "learning_rate": 6.235277747265828e-05, | |
| "loss": 0.7556, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.1488933601609658, | |
| "grad_norm": 1.1054296493530273, | |
| "learning_rate": 6.226927798807585e-05, | |
| "loss": 0.8489, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.15090543259557343, | |
| "grad_norm": 1.0174497365951538, | |
| "learning_rate": 6.218453968232303e-05, | |
| "loss": 0.7104, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1529175050301811, | |
| "grad_norm": 1.146209716796875, | |
| "learning_rate": 6.209856608170663e-05, | |
| "loss": 0.7276, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.15492957746478872, | |
| "grad_norm": 1.0379316806793213, | |
| "learning_rate": 6.201136076393911e-05, | |
| "loss": 0.7243, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.15694164989939638, | |
| "grad_norm": 1.0034286975860596, | |
| "learning_rate": 6.192292735798967e-05, | |
| "loss": 0.7085, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.158953722334004, | |
| "grad_norm": 1.0072968006134033, | |
| "learning_rate": 6.183326954393332e-05, | |
| "loss": 0.6865, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.16096579476861167, | |
| "grad_norm": 1.0766922235488892, | |
| "learning_rate": 6.174239105279768e-05, | |
| "loss": 0.7628, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.16297786720321933, | |
| "grad_norm": 1.014816403388977, | |
| "learning_rate": 6.16502956664077e-05, | |
| "loss": 0.7356, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.16498993963782696, | |
| "grad_norm": 1.055881142616272, | |
| "learning_rate": 6.155698721722834e-05, | |
| "loss": 0.7763, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.16700201207243462, | |
| "grad_norm": 1.0576510429382324, | |
| "learning_rate": 6.146246958820503e-05, | |
| "loss": 0.6852, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.16901408450704225, | |
| "grad_norm": 1.2542794942855835, | |
| "learning_rate": 6.136674671260213e-05, | |
| "loss": 0.7956, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.1710261569416499, | |
| "grad_norm": 1.0826421976089478, | |
| "learning_rate": 6.12698225738392e-05, | |
| "loss": 0.7285, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.17303822937625754, | |
| "grad_norm": 1.0286874771118164, | |
| "learning_rate": 6.11717012053253e-05, | |
| "loss": 0.7363, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.1750503018108652, | |
| "grad_norm": 1.1285161972045898, | |
| "learning_rate": 6.107238669029108e-05, | |
| "loss": 0.7807, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.17706237424547283, | |
| "grad_norm": 2.394617795944214, | |
| "learning_rate": 6.0971883161618906e-05, | |
| "loss": 0.663, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.1790744466800805, | |
| "grad_norm": 1.0971828699111938, | |
| "learning_rate": 6.0870194801670825e-05, | |
| "loss": 0.7331, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.18108651911468812, | |
| "grad_norm": 1.0546624660491943, | |
| "learning_rate": 6.076732584211459e-05, | |
| "loss": 0.7244, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.18309859154929578, | |
| "grad_norm": 1.0969500541687012, | |
| "learning_rate": 6.06632805637475e-05, | |
| "loss": 0.8122, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.1851106639839034, | |
| "grad_norm": 1.0038318634033203, | |
| "learning_rate": 6.055806329631827e-05, | |
| "loss": 0.752, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.18712273641851107, | |
| "grad_norm": 1.017544150352478, | |
| "learning_rate": 6.045167841834689e-05, | |
| "loss": 0.7629, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.1891348088531187, | |
| "grad_norm": 1.0679768323898315, | |
| "learning_rate": 6.034413035694237e-05, | |
| "loss": 0.7533, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.19114688128772636, | |
| "grad_norm": 1.1002590656280518, | |
| "learning_rate": 6.023542358761855e-05, | |
| "loss": 0.7566, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.193158953722334, | |
| "grad_norm": 1.0083142518997192, | |
| "learning_rate": 6.01255626341078e-05, | |
| "loss": 0.6873, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.19517102615694165, | |
| "grad_norm": 1.897566318511963, | |
| "learning_rate": 6.0014552068172866e-05, | |
| "loss": 0.8056, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.19718309859154928, | |
| "grad_norm": 0.995782732963562, | |
| "learning_rate": 5.990239650941649e-05, | |
| "loss": 0.7062, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.19919517102615694, | |
| "grad_norm": 0.9380747079849243, | |
| "learning_rate": 5.97891006250893e-05, | |
| "loss": 0.6674, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.2012072434607646, | |
| "grad_norm": 1.0377370119094849, | |
| "learning_rate": 5.967466912989547e-05, | |
| "loss": 0.7425, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.20321931589537223, | |
| "grad_norm": 0.9492895603179932, | |
| "learning_rate": 5.955910678579663e-05, | |
| "loss": 0.7232, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.2052313883299799, | |
| "grad_norm": 0.9299039244651794, | |
| "learning_rate": 5.9442418401813614e-05, | |
| "loss": 0.6996, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.20724346076458752, | |
| "grad_norm": 1.0433120727539062, | |
| "learning_rate": 5.932460883382638e-05, | |
| "loss": 0.7504, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.20925553319919518, | |
| "grad_norm": 1.02601158618927, | |
| "learning_rate": 5.920568298437193e-05, | |
| "loss": 0.7691, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.2112676056338028, | |
| "grad_norm": 1.0401028394699097, | |
| "learning_rate": 5.90856458024403e-05, | |
| "loss": 0.7038, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.21327967806841047, | |
| "grad_norm": 0.9615976214408875, | |
| "learning_rate": 5.8964502283268614e-05, | |
| "loss": 0.6894, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.2152917505030181, | |
| "grad_norm": 1.0715394020080566, | |
| "learning_rate": 5.884225746813317e-05, | |
| "loss": 0.762, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.21730382293762576, | |
| "grad_norm": 1.0785269737243652, | |
| "learning_rate": 5.871891644413972e-05, | |
| "loss": 0.7538, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.2193158953722334, | |
| "grad_norm": 0.9964181780815125, | |
| "learning_rate": 5.8594484344011724e-05, | |
| "loss": 0.7205, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.22132796780684105, | |
| "grad_norm": 1.0187814235687256, | |
| "learning_rate": 5.84689663458768e-05, | |
| "loss": 0.6946, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.22334004024144868, | |
| "grad_norm": 0.949118435382843, | |
| "learning_rate": 5.834236767305117e-05, | |
| "loss": 0.6963, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.22535211267605634, | |
| "grad_norm": 0.9602085947990417, | |
| "learning_rate": 5.821469359382237e-05, | |
| "loss": 0.7319, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.22736418511066397, | |
| "grad_norm": 0.9620065689086914, | |
| "learning_rate": 5.808594942122999e-05, | |
| "loss": 0.7442, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.22937625754527163, | |
| "grad_norm": 0.9228153228759766, | |
| "learning_rate": 5.795614051284457e-05, | |
| "loss": 0.7212, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.23138832997987926, | |
| "grad_norm": 1.029982328414917, | |
| "learning_rate": 5.782527227054462e-05, | |
| "loss": 0.7445, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.23340040241448692, | |
| "grad_norm": 1.0322256088256836, | |
| "learning_rate": 5.769335014029191e-05, | |
| "loss": 0.6763, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.23541247484909456, | |
| "grad_norm": 1.071828007698059, | |
| "learning_rate": 5.7560379611904754e-05, | |
| "loss": 0.7681, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.23742454728370221, | |
| "grad_norm": 1.0592682361602783, | |
| "learning_rate": 5.7426366218829596e-05, | |
| "loss": 0.7557, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.23943661971830985, | |
| "grad_norm": 1.019776701927185, | |
| "learning_rate": 5.729131553791076e-05, | |
| "loss": 0.7524, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.2414486921529175, | |
| "grad_norm": 1.0034253597259521, | |
| "learning_rate": 5.715523318915832e-05, | |
| "loss": 0.7844, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.24346076458752516, | |
| "grad_norm": 1.0709611177444458, | |
| "learning_rate": 5.701812483551428e-05, | |
| "loss": 0.7771, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.2454728370221328, | |
| "grad_norm": 1.089322805404663, | |
| "learning_rate": 5.687999618261688e-05, | |
| "loss": 0.7913, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.24748490945674045, | |
| "grad_norm": 0.981561005115509, | |
| "learning_rate": 5.6740852978563204e-05, | |
| "loss": 0.744, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.24949698189134809, | |
| "grad_norm": 0.9540185928344727, | |
| "learning_rate": 5.66007010136699e-05, | |
| "loss": 0.7201, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.2515090543259557, | |
| "grad_norm": 1.0497649908065796, | |
| "learning_rate": 5.645954612023233e-05, | |
| "loss": 0.7942, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.2535211267605634, | |
| "grad_norm": 0.9719651341438293, | |
| "learning_rate": 5.631739417228178e-05, | |
| "loss": 0.7133, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.25553319919517103, | |
| "grad_norm": 0.9591907858848572, | |
| "learning_rate": 5.6174251085341044e-05, | |
| "loss": 0.7118, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.2575452716297787, | |
| "grad_norm": 0.999717652797699, | |
| "learning_rate": 5.603012281617824e-05, | |
| "loss": 0.745, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.2595573440643863, | |
| "grad_norm": 0.984555184841156, | |
| "learning_rate": 5.5885015362558974e-05, | |
| "loss": 0.7398, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.26156941649899396, | |
| "grad_norm": 1.0207607746124268, | |
| "learning_rate": 5.573893476299669e-05, | |
| "loss": 0.7432, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.2635814889336016, | |
| "grad_norm": 1.0601558685302734, | |
| "learning_rate": 5.55918870965014e-05, | |
| "loss": 0.7713, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.2655935613682093, | |
| "grad_norm": 1.0741450786590576, | |
| "learning_rate": 5.544387848232677e-05, | |
| "loss": 0.7851, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.2676056338028169, | |
| "grad_norm": 1.0342241525650024, | |
| "learning_rate": 5.5294915079715334e-05, | |
| "loss": 0.7593, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.26961770623742454, | |
| "grad_norm": 0.983668863773346, | |
| "learning_rate": 5.514500308764235e-05, | |
| "loss": 0.7426, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.2716297786720322, | |
| "grad_norm": 0.9781654477119446, | |
| "learning_rate": 5.499414874455771e-05, | |
| "loss": 0.7306, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.27364185110663986, | |
| "grad_norm": 1.0362467765808105, | |
| "learning_rate": 5.48423583281264e-05, | |
| "loss": 0.7742, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.27565392354124746, | |
| "grad_norm": 0.9543638229370117, | |
| "learning_rate": 5.4689638154967235e-05, | |
| "loss": 0.6956, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.2776659959758551, | |
| "grad_norm": 1.0143051147460938, | |
| "learning_rate": 5.453599458038998e-05, | |
| "loss": 0.7562, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.2796780684104628, | |
| "grad_norm": 0.9799973368644714, | |
| "learning_rate": 5.438143399813095e-05, | |
| "loss": 0.7326, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.28169014084507044, | |
| "grad_norm": 0.9217185974121094, | |
| "learning_rate": 5.422596284008683e-05, | |
| "loss": 0.7464, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2837022132796781, | |
| "grad_norm": 0.8847222328186035, | |
| "learning_rate": 5.4069587576047144e-05, | |
| "loss": 0.7148, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 0.8999807834625244, | |
| "learning_rate": 5.39123147134249e-05, | |
| "loss": 0.7207, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.28772635814889336, | |
| "grad_norm": 0.9449793100357056, | |
| "learning_rate": 5.3754150796985895e-05, | |
| "loss": 0.738, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.289738430583501, | |
| "grad_norm": 1.1088876724243164, | |
| "learning_rate": 5.359510240857628e-05, | |
| "loss": 0.7431, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.2917505030181087, | |
| "grad_norm": 0.931364119052887, | |
| "learning_rate": 5.343517616684872e-05, | |
| "loss": 0.7132, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.2937625754527163, | |
| "grad_norm": 1.0146406888961792, | |
| "learning_rate": 5.327437872698691e-05, | |
| "loss": 0.7916, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.29577464788732394, | |
| "grad_norm": 1.0176244974136353, | |
| "learning_rate": 5.3112716780428674e-05, | |
| "loss": 0.7131, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.2977867203219316, | |
| "grad_norm": 0.9973041415214539, | |
| "learning_rate": 5.295019705458749e-05, | |
| "loss": 0.7689, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.29979879275653926, | |
| "grad_norm": 1.0221103429794312, | |
| "learning_rate": 5.278682631257252e-05, | |
| "loss": 0.7762, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.30181086519114686, | |
| "grad_norm": 0.9501760601997375, | |
| "learning_rate": 5.2622611352907214e-05, | |
| "loss": 0.7103, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3038229376257545, | |
| "grad_norm": 0.9289485216140747, | |
| "learning_rate": 5.245755900924631e-05, | |
| "loss": 0.6982, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.3058350100603622, | |
| "grad_norm": 1.4150779247283936, | |
| "learning_rate": 5.2291676150091576e-05, | |
| "loss": 0.7035, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.30784708249496984, | |
| "grad_norm": 0.9871881008148193, | |
| "learning_rate": 5.2124969678505864e-05, | |
| "loss": 0.7388, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.30985915492957744, | |
| "grad_norm": 0.9766415357589722, | |
| "learning_rate": 5.195744653182594e-05, | |
| "loss": 0.7142, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.3118712273641851, | |
| "grad_norm": 0.9838590621948242, | |
| "learning_rate": 5.178911368137373e-05, | |
| "loss": 0.6978, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.31388329979879276, | |
| "grad_norm": 0.9251114726066589, | |
| "learning_rate": 5.1619978132166254e-05, | |
| "loss": 0.6737, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.3158953722334004, | |
| "grad_norm": 0.9593889117240906, | |
| "learning_rate": 5.145004692262411e-05, | |
| "loss": 0.7233, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.317907444668008, | |
| "grad_norm": 0.9678305387496948, | |
| "learning_rate": 5.127932712427851e-05, | |
| "loss": 0.702, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.3199195171026157, | |
| "grad_norm": 0.9605986475944519, | |
| "learning_rate": 5.110782584147718e-05, | |
| "loss": 0.7678, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.32193158953722334, | |
| "grad_norm": 0.9980550408363342, | |
| "learning_rate": 5.093555021108849e-05, | |
| "loss": 0.7299, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.323943661971831, | |
| "grad_norm": 0.9018529057502747, | |
| "learning_rate": 5.0762507402204637e-05, | |
| "loss": 0.7109, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.32595573440643866, | |
| "grad_norm": 1.1389586925506592, | |
| "learning_rate": 5.058870461584322e-05, | |
| "loss": 0.7371, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.32796780684104626, | |
| "grad_norm": 1.0409871339797974, | |
| "learning_rate": 5.0414149084647644e-05, | |
| "loss": 0.8062, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.3299798792756539, | |
| "grad_norm": 0.9527642130851746, | |
| "learning_rate": 5.0238848072586037e-05, | |
| "loss": 0.7692, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.3319919517102616, | |
| "grad_norm": 0.9563398361206055, | |
| "learning_rate": 5.0062808874649074e-05, | |
| "loss": 0.737, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.33400402414486924, | |
| "grad_norm": 1.0413488149642944, | |
| "learning_rate": 4.9886038816546355e-05, | |
| "loss": 0.7503, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.33601609657947684, | |
| "grad_norm": 0.9624356031417847, | |
| "learning_rate": 4.970854525440152e-05, | |
| "loss": 0.7034, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.3380281690140845, | |
| "grad_norm": 0.9548975229263306, | |
| "learning_rate": 4.9530335574446196e-05, | |
| "loss": 0.7213, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.34004024144869216, | |
| "grad_norm": 0.8841491937637329, | |
| "learning_rate": 4.9351417192712596e-05, | |
| "loss": 0.685, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.3420523138832998, | |
| "grad_norm": 0.989604115486145, | |
| "learning_rate": 4.917179755472491e-05, | |
| "loss": 0.6952, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3440643863179074, | |
| "grad_norm": 0.8883060216903687, | |
| "learning_rate": 4.899148413518942e-05, | |
| "loss": 0.697, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.3460764587525151, | |
| "grad_norm": 0.8740846514701843, | |
| "learning_rate": 4.881048443768356e-05, | |
| "loss": 0.7045, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.34808853118712274, | |
| "grad_norm": 0.8820964097976685, | |
| "learning_rate": 4.862880599434353e-05, | |
| "loss": 0.7007, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.3501006036217304, | |
| "grad_norm": 0.882949709892273, | |
| "learning_rate": 4.844645636555094e-05, | |
| "loss": 0.693, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.352112676056338, | |
| "grad_norm": 0.952804684638977, | |
| "learning_rate": 4.8263443139618176e-05, | |
| "loss": 0.7319, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.35412474849094566, | |
| "grad_norm": 0.9323515295982361, | |
| "learning_rate": 4.8079773932472584e-05, | |
| "loss": 0.7206, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.3561368209255533, | |
| "grad_norm": 1.0918467044830322, | |
| "learning_rate": 4.78954563873396e-05, | |
| "loss": 0.7152, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.358148893360161, | |
| "grad_norm": 2.0716049671173096, | |
| "learning_rate": 4.7710498174424614e-05, | |
| "loss": 0.7769, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.36016096579476864, | |
| "grad_norm": 0.9245615601539612, | |
| "learning_rate": 4.7524906990593844e-05, | |
| "loss": 0.7085, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.36217303822937624, | |
| "grad_norm": 1.0692616701126099, | |
| "learning_rate": 4.7338690559054004e-05, | |
| "loss": 0.6948, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3641851106639839, | |
| "grad_norm": 0.8987394571304321, | |
| "learning_rate": 4.71518566290309e-05, | |
| "loss": 0.7167, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.36619718309859156, | |
| "grad_norm": 0.946850061416626, | |
| "learning_rate": 4.6964412975447e-05, | |
| "loss": 0.7227, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.3682092555331992, | |
| "grad_norm": 0.9121927618980408, | |
| "learning_rate": 4.6776367398597846e-05, | |
| "loss": 0.6868, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.3702213279678068, | |
| "grad_norm": 0.8747940063476562, | |
| "learning_rate": 4.658772772382744e-05, | |
| "loss": 0.6797, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.3722334004024145, | |
| "grad_norm": 0.9101600646972656, | |
| "learning_rate": 4.639850180120268e-05, | |
| "loss": 0.7636, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.37424547283702214, | |
| "grad_norm": 0.9515472054481506, | |
| "learning_rate": 4.620869750518656e-05, | |
| "loss": 0.7357, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.3762575452716298, | |
| "grad_norm": 0.9573916792869568, | |
| "learning_rate": 4.60183227343106e-05, | |
| "loss": 0.7303, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.3782696177062374, | |
| "grad_norm": 0.942021369934082, | |
| "learning_rate": 4.582738541084612e-05, | |
| "loss": 0.709, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.38028169014084506, | |
| "grad_norm": 0.8716509342193604, | |
| "learning_rate": 4.5635893480474474e-05, | |
| "loss": 0.6681, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.3822937625754527, | |
| "grad_norm": 0.8702856302261353, | |
| "learning_rate": 4.544385491195658e-05, | |
| "loss": 0.6902, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3843058350100604, | |
| "grad_norm": 0.9312735795974731, | |
| "learning_rate": 4.525127769680109e-05, | |
| "loss": 0.6895, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.386317907444668, | |
| "grad_norm": 0.9693159461021423, | |
| "learning_rate": 4.505816984893203e-05, | |
| "loss": 0.7286, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.38832997987927564, | |
| "grad_norm": 1.0244489908218384, | |
| "learning_rate": 4.486453940435518e-05, | |
| "loss": 0.7899, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.3903420523138833, | |
| "grad_norm": 0.970856249332428, | |
| "learning_rate": 4.46703944208237e-05, | |
| "loss": 0.7176, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.39235412474849096, | |
| "grad_norm": 0.9749726057052612, | |
| "learning_rate": 4.447574297750281e-05, | |
| "loss": 0.6914, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.39436619718309857, | |
| "grad_norm": 0.9390575885772705, | |
| "learning_rate": 4.428059317463363e-05, | |
| "loss": 0.7125, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.3963782696177062, | |
| "grad_norm": 0.9480944871902466, | |
| "learning_rate": 4.4084953133196e-05, | |
| "loss": 0.681, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.3983903420523139, | |
| "grad_norm": 0.9078746438026428, | |
| "learning_rate": 4.388883099457064e-05, | |
| "loss": 0.6917, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.40040241448692154, | |
| "grad_norm": 0.9508323073387146, | |
| "learning_rate": 4.369223492020026e-05, | |
| "loss": 0.7082, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.4024144869215292, | |
| "grad_norm": 0.8641968965530396, | |
| "learning_rate": 4.3495173091249974e-05, | |
| "loss": 0.6343, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4044265593561368, | |
| "grad_norm": 0.9805442094802856, | |
| "learning_rate": 4.329765370826689e-05, | |
| "loss": 0.7091, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.40643863179074446, | |
| "grad_norm": 0.9265369772911072, | |
| "learning_rate": 4.309968499083876e-05, | |
| "loss": 0.6812, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.4084507042253521, | |
| "grad_norm": 0.9390007257461548, | |
| "learning_rate": 4.290127517725199e-05, | |
| "loss": 0.7208, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.4104627766599598, | |
| "grad_norm": 0.918609619140625, | |
| "learning_rate": 4.27024325241488e-05, | |
| "loss": 0.6829, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.4124748490945674, | |
| "grad_norm": 0.9491612315177917, | |
| "learning_rate": 4.250316530618363e-05, | |
| "loss": 0.749, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.41448692152917505, | |
| "grad_norm": 0.9603286385536194, | |
| "learning_rate": 4.23034818156788e-05, | |
| "loss": 0.7192, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.4164989939637827, | |
| "grad_norm": 0.8992831110954285, | |
| "learning_rate": 4.210339036227942e-05, | |
| "loss": 0.6715, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.41851106639839036, | |
| "grad_norm": 0.9181328415870667, | |
| "learning_rate": 4.1902899272607605e-05, | |
| "loss": 0.7586, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.42052313883299797, | |
| "grad_norm": 0.9009472131729126, | |
| "learning_rate": 4.1702016889915974e-05, | |
| "loss": 0.7139, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.4225352112676056, | |
| "grad_norm": 0.9172364473342896, | |
| "learning_rate": 4.150075157374043e-05, | |
| "loss": 0.7403, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.4245472837022133, | |
| "grad_norm": 0.9123634099960327, | |
| "learning_rate": 4.1299111699552316e-05, | |
| "loss": 0.7326, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.42655935613682094, | |
| "grad_norm": 0.8299218416213989, | |
| "learning_rate": 4.109710565840987e-05, | |
| "loss": 0.6788, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 0.9061017632484436, | |
| "learning_rate": 4.0894741856608986e-05, | |
| "loss": 0.6942, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.4305835010060362, | |
| "grad_norm": 0.8914936184883118, | |
| "learning_rate": 4.069202871533352e-05, | |
| "loss": 0.6633, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.43259557344064387, | |
| "grad_norm": 0.8976927995681763, | |
| "learning_rate": 4.048897467030468e-05, | |
| "loss": 0.6815, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.4346076458752515, | |
| "grad_norm": 0.869555652141571, | |
| "learning_rate": 4.028558817143013e-05, | |
| "loss": 0.6925, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.43661971830985913, | |
| "grad_norm": 0.8817659020423889, | |
| "learning_rate": 4.008187768245229e-05, | |
| "loss": 0.6621, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.4386317907444668, | |
| "grad_norm": 0.9075917601585388, | |
| "learning_rate": 3.98778516805961e-05, | |
| "loss": 0.6926, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.44064386317907445, | |
| "grad_norm": 0.8682200312614441, | |
| "learning_rate": 3.967351865621631e-05, | |
| "loss": 0.6613, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.4426559356136821, | |
| "grad_norm": 0.8848491311073303, | |
| "learning_rate": 3.94688871124441e-05, | |
| "loss": 0.7014, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.44466800804828976, | |
| "grad_norm": 0.8899165391921997, | |
| "learning_rate": 3.9263965564833295e-05, | |
| "loss": 0.6684, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.44668008048289737, | |
| "grad_norm": 0.8962348699569702, | |
| "learning_rate": 3.905876254100594e-05, | |
| "loss": 0.7285, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.448692152917505, | |
| "grad_norm": 0.8958956599235535, | |
| "learning_rate": 3.885328658029748e-05, | |
| "loss": 0.7128, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.4507042253521127, | |
| "grad_norm": 0.9015375375747681, | |
| "learning_rate": 3.8647546233401336e-05, | |
| "loss": 0.6767, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.45271629778672035, | |
| "grad_norm": 0.9416881203651428, | |
| "learning_rate": 3.8441550062013143e-05, | |
| "loss": 0.7186, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.45472837022132795, | |
| "grad_norm": 0.9649824500083923, | |
| "learning_rate": 3.8235306638474455e-05, | |
| "loss": 0.7352, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.4567404426559356, | |
| "grad_norm": 0.8740935325622559, | |
| "learning_rate": 3.802882454541594e-05, | |
| "loss": 0.6633, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.45875251509054327, | |
| "grad_norm": 0.9129350185394287, | |
| "learning_rate": 3.782211237540036e-05, | |
| "loss": 0.7051, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.4607645875251509, | |
| "grad_norm": 0.8774951100349426, | |
| "learning_rate": 3.7615178730564845e-05, | |
| "loss": 0.7249, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.46277665995975853, | |
| "grad_norm": 0.9072405099868774, | |
| "learning_rate": 3.740803222226304e-05, | |
| "loss": 0.6891, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.4647887323943662, | |
| "grad_norm": 1.0077128410339355, | |
| "learning_rate": 3.720068147070668e-05, | |
| "loss": 0.724, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.46680080482897385, | |
| "grad_norm": 0.9419925808906555, | |
| "learning_rate": 3.6993135104606915e-05, | |
| "loss": 0.7281, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.4688128772635815, | |
| "grad_norm": 0.9003535509109497, | |
| "learning_rate": 3.678540176081521e-05, | |
| "loss": 0.6508, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.4708249496981891, | |
| "grad_norm": 0.9552720785140991, | |
| "learning_rate": 3.657749008396394e-05, | |
| "loss": 0.7385, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.47283702213279677, | |
| "grad_norm": 0.9708763957023621, | |
| "learning_rate": 3.636940872610662e-05, | |
| "loss": 0.762, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.47484909456740443, | |
| "grad_norm": 0.8927114605903625, | |
| "learning_rate": 3.6161166346357934e-05, | |
| "loss": 0.7123, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.4768611670020121, | |
| "grad_norm": 0.869623601436615, | |
| "learning_rate": 3.595277161053328e-05, | |
| "loss": 0.6986, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.4788732394366197, | |
| "grad_norm": 0.8514843583106995, | |
| "learning_rate": 3.574423319078829e-05, | |
| "loss": 0.6689, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.48088531187122735, | |
| "grad_norm": 0.88021320104599, | |
| "learning_rate": 3.5535559765257785e-05, | |
| "loss": 0.6539, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.482897384305835, | |
| "grad_norm": 0.869594931602478, | |
| "learning_rate": 3.5326760017694795e-05, | |
| "loss": 0.7198, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.48490945674044267, | |
| "grad_norm": 0.9412367939949036, | |
| "learning_rate": 3.511784263710911e-05, | |
| "loss": 0.73, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.4869215291750503, | |
| "grad_norm": 0.8942079544067383, | |
| "learning_rate": 3.4908816317405686e-05, | |
| "loss": 0.7009, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.48893360160965793, | |
| "grad_norm": 0.901075541973114, | |
| "learning_rate": 3.46996897570229e-05, | |
| "loss": 0.7044, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.4909456740442656, | |
| "grad_norm": 0.9331154227256775, | |
| "learning_rate": 3.4490471658570554e-05, | |
| "loss": 0.7393, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.49295774647887325, | |
| "grad_norm": 0.9193384647369385, | |
| "learning_rate": 3.428117072846772e-05, | |
| "loss": 0.6808, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.4949698189134809, | |
| "grad_norm": 0.9850835800170898, | |
| "learning_rate": 3.407179567658043e-05, | |
| "loss": 0.7291, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.4969818913480885, | |
| "grad_norm": 0.9162485003471375, | |
| "learning_rate": 3.3862355215859225e-05, | |
| "loss": 0.7291, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.49899396378269617, | |
| "grad_norm": 0.8797596096992493, | |
| "learning_rate": 3.3652858061976584e-05, | |
| "loss": 0.7091, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.5010060362173038, | |
| "grad_norm": 0.8453248739242554, | |
| "learning_rate": 3.3443312932964194e-05, | |
| "loss": 0.6448, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.5030181086519114, | |
| "grad_norm": 0.9353291392326355, | |
| "learning_rate": 3.323372854885023e-05, | |
| "loss": 0.7358, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5050301810865191, | |
| "grad_norm": 0.8059361577033997, | |
| "learning_rate": 3.3024113631296376e-05, | |
| "loss": 0.6646, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.5070422535211268, | |
| "grad_norm": 1.006386160850525, | |
| "learning_rate": 3.281447690323499e-05, | |
| "loss": 0.709, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.5090543259557344, | |
| "grad_norm": 1.0037897825241089, | |
| "learning_rate": 3.260482708850601e-05, | |
| "loss": 0.7314, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.5110663983903421, | |
| "grad_norm": 0.857748806476593, | |
| "learning_rate": 3.239517291149399e-05, | |
| "loss": 0.6773, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.5130784708249497, | |
| "grad_norm": 0.8884151577949524, | |
| "learning_rate": 3.218552309676501e-05, | |
| "loss": 0.6952, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.5150905432595574, | |
| "grad_norm": 0.8516953587532043, | |
| "learning_rate": 3.197588636870362e-05, | |
| "loss": 0.6202, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.5171026156941649, | |
| "grad_norm": 0.8813678026199341, | |
| "learning_rate": 3.176627145114977e-05, | |
| "loss": 0.697, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.5191146881287726, | |
| "grad_norm": 0.8686804175376892, | |
| "learning_rate": 3.15566870670358e-05, | |
| "loss": 0.6814, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.5211267605633803, | |
| "grad_norm": 0.8625949025154114, | |
| "learning_rate": 3.134714193802342e-05, | |
| "loss": 0.6673, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.5231388329979879, | |
| "grad_norm": 0.8244426250457764, | |
| "learning_rate": 3.113764478414077e-05, | |
| "loss": 0.631, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5251509054325956, | |
| "grad_norm": 0.8436176180839539, | |
| "learning_rate": 3.092820432341956e-05, | |
| "loss": 0.6734, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.5271629778672032, | |
| "grad_norm": 0.8252584934234619, | |
| "learning_rate": 3.0718829271532275e-05, | |
| "loss": 0.6562, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.5291750503018109, | |
| "grad_norm": 0.845025897026062, | |
| "learning_rate": 3.0509528341429443e-05, | |
| "loss": 0.7029, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.5311871227364185, | |
| "grad_norm": 0.8654035925865173, | |
| "learning_rate": 3.03003102429771e-05, | |
| "loss": 0.6654, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.5331991951710262, | |
| "grad_norm": 0.8877770304679871, | |
| "learning_rate": 3.009118368259431e-05, | |
| "loss": 0.6565, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.5352112676056338, | |
| "grad_norm": 0.8893894553184509, | |
| "learning_rate": 2.9882157362890886e-05, | |
| "loss": 0.6163, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.5372233400402414, | |
| "grad_norm": 0.9666234254837036, | |
| "learning_rate": 2.9673239982305202e-05, | |
| "loss": 0.6895, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.5392354124748491, | |
| "grad_norm": 0.9029472470283508, | |
| "learning_rate": 2.9464440234742216e-05, | |
| "loss": 0.6978, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.5412474849094567, | |
| "grad_norm": 0.9182049036026001, | |
| "learning_rate": 2.9255766809211712e-05, | |
| "loss": 0.6729, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.5432595573440644, | |
| "grad_norm": 0.9030729532241821, | |
| "learning_rate": 2.9047228389466707e-05, | |
| "loss": 0.7138, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.545271629778672, | |
| "grad_norm": 0.9141706228256226, | |
| "learning_rate": 2.8838833653642064e-05, | |
| "loss": 0.7274, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.5472837022132797, | |
| "grad_norm": 0.9512321949005127, | |
| "learning_rate": 2.8630591273893377e-05, | |
| "loss": 0.7714, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.5492957746478874, | |
| "grad_norm": 0.972109854221344, | |
| "learning_rate": 2.842250991603607e-05, | |
| "loss": 0.6968, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.5513078470824949, | |
| "grad_norm": 0.9172069430351257, | |
| "learning_rate": 2.8214598239184785e-05, | |
| "loss": 0.7382, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.5533199195171026, | |
| "grad_norm": 0.8818020820617676, | |
| "learning_rate": 2.800686489539308e-05, | |
| "loss": 0.6968, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.5553319919517102, | |
| "grad_norm": 0.8782933354377747, | |
| "learning_rate": 2.7799318529293317e-05, | |
| "loss": 0.662, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.5573440643863179, | |
| "grad_norm": 0.8515357375144958, | |
| "learning_rate": 2.7591967777736968e-05, | |
| "loss": 0.6968, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.5593561368209256, | |
| "grad_norm": 0.9061254858970642, | |
| "learning_rate": 2.7384821269435143e-05, | |
| "loss": 0.723, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.5613682092555332, | |
| "grad_norm": 0.90815269947052, | |
| "learning_rate": 2.7177887624599636e-05, | |
| "loss": 0.7091, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.5633802816901409, | |
| "grad_norm": 0.8476876616477966, | |
| "learning_rate": 2.6971175454584048e-05, | |
| "loss": 0.6615, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5653923541247485, | |
| "grad_norm": 0.8543688058853149, | |
| "learning_rate": 2.676469336152555e-05, | |
| "loss": 0.665, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.5674044265593562, | |
| "grad_norm": 0.8241449594497681, | |
| "learning_rate": 2.6558449937986858e-05, | |
| "loss": 0.6665, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.5694164989939637, | |
| "grad_norm": 0.9415947794914246, | |
| "learning_rate": 2.6352453766598655e-05, | |
| "loss": 0.6802, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.8769863843917847, | |
| "learning_rate": 2.614671341970252e-05, | |
| "loss": 0.7162, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.5734406438631791, | |
| "grad_norm": 0.8706234097480774, | |
| "learning_rate": 2.5941237458994048e-05, | |
| "loss": 0.6951, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.5754527162977867, | |
| "grad_norm": 0.807435929775238, | |
| "learning_rate": 2.5736034435166702e-05, | |
| "loss": 0.636, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.5774647887323944, | |
| "grad_norm": 0.8227114081382751, | |
| "learning_rate": 2.5531112887555894e-05, | |
| "loss": 0.6926, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.579476861167002, | |
| "grad_norm": 0.8422671556472778, | |
| "learning_rate": 2.532648134378369e-05, | |
| "loss": 0.672, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.5814889336016097, | |
| "grad_norm": 0.913819432258606, | |
| "learning_rate": 2.5122148319403903e-05, | |
| "loss": 0.7599, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.5835010060362174, | |
| "grad_norm": 0.848904013633728, | |
| "learning_rate": 2.491812231754771e-05, | |
| "loss": 0.7112, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.5855130784708249, | |
| "grad_norm": 0.857905924320221, | |
| "learning_rate": 2.4714411828569864e-05, | |
| "loss": 0.6655, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.5875251509054326, | |
| "grad_norm": 0.8949502110481262, | |
| "learning_rate": 2.451102532969531e-05, | |
| "loss": 0.7178, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.5895372233400402, | |
| "grad_norm": 0.8601780533790588, | |
| "learning_rate": 2.4307971284666478e-05, | |
| "loss": 0.6953, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.5915492957746479, | |
| "grad_norm": 0.8672630786895752, | |
| "learning_rate": 2.4105258143391005e-05, | |
| "loss": 0.6621, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.5935613682092555, | |
| "grad_norm": 0.8478452563285828, | |
| "learning_rate": 2.3902894341590137e-05, | |
| "loss": 0.6971, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.5955734406438632, | |
| "grad_norm": 0.8357344269752502, | |
| "learning_rate": 2.3700888300447675e-05, | |
| "loss": 0.6876, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.5975855130784709, | |
| "grad_norm": 0.8916183710098267, | |
| "learning_rate": 2.3499248426259564e-05, | |
| "loss": 0.6754, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.5995975855130785, | |
| "grad_norm": 0.9368688464164734, | |
| "learning_rate": 2.3297983110084027e-05, | |
| "loss": 0.757, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.6016096579476862, | |
| "grad_norm": 0.8134625554084778, | |
| "learning_rate": 2.3097100727392396e-05, | |
| "loss": 0.6631, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.6036217303822937, | |
| "grad_norm": 0.9809048771858215, | |
| "learning_rate": 2.2896609637720577e-05, | |
| "loss": 0.718, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 497, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.37451134518272e+18, | |
| "train_batch_size": 15, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |