| { | |
| "best_metric": 0.21331782639026642, | |
| "best_model_checkpoint": "./xlam_lora_new_ete_over_size_3epoch_multi_mix/checkpoint-1640", | |
| "epoch": 2.9986264435061303, | |
| "eval_steps": 205, | |
| "global_step": 1842, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.016279188075494735, | |
| "grad_norm": 0.7572630643844604, | |
| "learning_rate": 2.688172043010753e-06, | |
| "loss": 0.5223, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03255837615098947, | |
| "grad_norm": 0.417061984539032, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 0.4858, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.048837564226484206, | |
| "grad_norm": 0.3718095123767853, | |
| "learning_rate": 8.064516129032258e-06, | |
| "loss": 0.4246, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06511675230197894, | |
| "grad_norm": 0.2949349582195282, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 0.4405, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08139594037747368, | |
| "grad_norm": 0.3159159719944, | |
| "learning_rate": 1.3440860215053763e-05, | |
| "loss": 0.4148, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09767512845296841, | |
| "grad_norm": 0.4167034327983856, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 0.3393, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11395431652846315, | |
| "grad_norm": 0.39410400390625, | |
| "learning_rate": 1.881720430107527e-05, | |
| "loss": 0.2464, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.13023350460395788, | |
| "grad_norm": 0.3644021153450012, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.2294, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1465126926794526, | |
| "grad_norm": 0.30372634530067444, | |
| "learning_rate": 2.4193548387096777e-05, | |
| "loss": 0.2315, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.16279188075494735, | |
| "grad_norm": 0.2586315870285034, | |
| "learning_rate": 2.4999011923655086e-05, | |
| "loss": 0.1932, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17907106883044208, | |
| "grad_norm": 0.37825971841812134, | |
| "learning_rate": 2.4994172742085852e-05, | |
| "loss": 0.2204, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.19535025690593683, | |
| "grad_norm": 0.21422357857227325, | |
| "learning_rate": 2.4985302531208654e-05, | |
| "loss": 0.1795, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.21162944498143155, | |
| "grad_norm": 0.2566869854927063, | |
| "learning_rate": 2.4972404152844008e-05, | |
| "loss": 0.1668, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.2279086330569263, | |
| "grad_norm": 0.28194501996040344, | |
| "learning_rate": 2.49554817684312e-05, | |
| "loss": 0.1476, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.24418782113242102, | |
| "grad_norm": 0.24139340221881866, | |
| "learning_rate": 2.4934540837685647e-05, | |
| "loss": 0.1609, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.26046700920791577, | |
| "grad_norm": 0.3306334614753723, | |
| "learning_rate": 2.490958811683741e-05, | |
| "loss": 0.1638, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.2767461972834105, | |
| "grad_norm": 0.27301114797592163, | |
| "learning_rate": 2.4880631656451447e-05, | |
| "loss": 0.1494, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.2930253853589052, | |
| "grad_norm": 0.34037259221076965, | |
| "learning_rate": 2.484768079883018e-05, | |
| "loss": 0.1534, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.30930457343439993, | |
| "grad_norm": 0.2306762933731079, | |
| "learning_rate": 2.4810746174999418e-05, | |
| "loss": 0.1749, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3255837615098947, | |
| "grad_norm": 0.3183388113975525, | |
| "learning_rate": 2.476983970127841e-05, | |
| "loss": 0.1482, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.33372335554764204, | |
| "eval_loss": 0.3089325428009033, | |
| "eval_runtime": 34.8769, | |
| "eval_samples_per_second": 5.419, | |
| "eval_steps_per_second": 5.419, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.34186294958538943, | |
| "grad_norm": 0.28704971075057983, | |
| "learning_rate": 2.472497457543525e-05, | |
| "loss": 0.1471, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.35814213766088415, | |
| "grad_norm": 0.2939195930957794, | |
| "learning_rate": 2.4676165272428866e-05, | |
| "loss": 0.1631, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.3744213257363789, | |
| "grad_norm": 0.31506845355033875, | |
| "learning_rate": 2.4623427539738897e-05, | |
| "loss": 0.1353, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.39070051381187365, | |
| "grad_norm": 0.3761660158634186, | |
| "learning_rate": 2.456677839228506e-05, | |
| "loss": 0.1716, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.4069797018873684, | |
| "grad_norm": 0.29187777638435364, | |
| "learning_rate": 2.450623610693757e-05, | |
| "loss": 0.1195, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4232588899628631, | |
| "grad_norm": 0.46237581968307495, | |
| "learning_rate": 2.4441820216620425e-05, | |
| "loss": 0.1484, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.4395380780383578, | |
| "grad_norm": 0.4580917954444885, | |
| "learning_rate": 2.437355150400945e-05, | |
| "loss": 0.1009, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.4558172661138526, | |
| "grad_norm": 0.4181467890739441, | |
| "learning_rate": 2.4301451994827112e-05, | |
| "loss": 0.1376, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.4720964541893473, | |
| "grad_norm": 0.3629908561706543, | |
| "learning_rate": 2.422554495073633e-05, | |
| "loss": 0.1083, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.48837564226484204, | |
| "grad_norm": 0.4282682240009308, | |
| "learning_rate": 2.4145854861835447e-05, | |
| "loss": 0.1373, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5046548303403368, | |
| "grad_norm": 0.4914080500602722, | |
| "learning_rate": 2.406240743875699e-05, | |
| "loss": 0.156, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.5209340184158315, | |
| "grad_norm": 0.3880573511123657, | |
| "learning_rate": 2.3975229604372526e-05, | |
| "loss": 0.1415, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.5372132064913262, | |
| "grad_norm": 0.42599862813949585, | |
| "learning_rate": 2.3884349485106477e-05, | |
| "loss": 0.1338, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.553492394566821, | |
| "grad_norm": 0.4339046776294708, | |
| "learning_rate": 2.378979640186163e-05, | |
| "loss": 0.1368, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.5697715826423158, | |
| "grad_norm": 0.30713170766830444, | |
| "learning_rate": 2.3691600860559222e-05, | |
| "loss": 0.1154, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5860507707178104, | |
| "grad_norm": 0.4618566036224365, | |
| "learning_rate": 2.3589794542296764e-05, | |
| "loss": 0.1203, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.6023299587933052, | |
| "grad_norm": 0.40802672505378723, | |
| "learning_rate": 2.3484410293126664e-05, | |
| "loss": 0.1144, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.6186091468687999, | |
| "grad_norm": 0.5242702960968018, | |
| "learning_rate": 2.3375482113459014e-05, | |
| "loss": 0.1281, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.6348883349442946, | |
| "grad_norm": 0.4045926630496979, | |
| "learning_rate": 2.3263045147091944e-05, | |
| "loss": 0.1145, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.6511675230197894, | |
| "grad_norm": 0.5347346067428589, | |
| "learning_rate": 2.3147135669873096e-05, | |
| "loss": 0.1256, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6674467110952841, | |
| "grad_norm": 0.4755608141422272, | |
| "learning_rate": 2.302779107799583e-05, | |
| "loss": 0.1251, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.6674467110952841, | |
| "eval_loss": 0.26128318905830383, | |
| "eval_runtime": 34.9177, | |
| "eval_samples_per_second": 5.413, | |
| "eval_steps_per_second": 5.413, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.6837258991707789, | |
| "grad_norm": 0.4720211923122406, | |
| "learning_rate": 2.290504987593399e-05, | |
| "loss": 0.1399, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.7000050872462736, | |
| "grad_norm": 0.709035336971283, | |
| "learning_rate": 2.2778951664019105e-05, | |
| "loss": 0.1375, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.7162842753217683, | |
| "grad_norm": 0.534866213798523, | |
| "learning_rate": 2.2649537125664034e-05, | |
| "loss": 0.1125, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.7325634633972631, | |
| "grad_norm": 0.522056519985199, | |
| "learning_rate": 2.2516848014237146e-05, | |
| "loss": 0.0943, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.7488426514727577, | |
| "grad_norm": 0.2830965518951416, | |
| "learning_rate": 2.238092713959133e-05, | |
| "loss": 0.1248, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.7651218395482525, | |
| "grad_norm": 0.39431601762771606, | |
| "learning_rate": 2.2241818354252113e-05, | |
| "loss": 0.1248, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.7814010276237473, | |
| "grad_norm": 0.4821482002735138, | |
| "learning_rate": 2.209956653926944e-05, | |
| "loss": 0.1359, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.797680215699242, | |
| "grad_norm": 0.4956236481666565, | |
| "learning_rate": 2.1954217589737535e-05, | |
| "loss": 0.1232, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.8139594037747367, | |
| "grad_norm": 0.49444642663002014, | |
| "learning_rate": 2.180581839998766e-05, | |
| "loss": 0.1031, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8302385918502315, | |
| "grad_norm": 0.3857091963291168, | |
| "learning_rate": 2.165441684845847e-05, | |
| "loss": 0.1023, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.8465177799257262, | |
| "grad_norm": 0.4830643832683563, | |
| "learning_rate": 2.150006178224886e-05, | |
| "loss": 0.1067, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.862796968001221, | |
| "grad_norm": 0.5119408965110779, | |
| "learning_rate": 2.1342803001358278e-05, | |
| "loss": 0.1209, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.8790761560767156, | |
| "grad_norm": 0.46363013982772827, | |
| "learning_rate": 2.118269124261963e-05, | |
| "loss": 0.1134, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.8953553441522104, | |
| "grad_norm": 0.42933255434036255, | |
| "learning_rate": 2.1019778163329912e-05, | |
| "loss": 0.1101, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.9116345322277052, | |
| "grad_norm": 0.5474070906639099, | |
| "learning_rate": 2.0854116324583867e-05, | |
| "loss": 0.1291, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.9279137203031999, | |
| "grad_norm": 0.43502509593963623, | |
| "learning_rate": 2.0685759174316066e-05, | |
| "loss": 0.0936, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.9441929083786946, | |
| "grad_norm": 0.632621169090271, | |
| "learning_rate": 2.051476103005684e-05, | |
| "loss": 0.1196, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.9604720964541893, | |
| "grad_norm": 0.553187906742096, | |
| "learning_rate": 2.034117706140768e-05, | |
| "loss": 0.1186, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.9767512845296841, | |
| "grad_norm": 0.48446330428123474, | |
| "learning_rate": 2.0165063272241712e-05, | |
| "loss": 0.1249, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.9930304726051788, | |
| "grad_norm": 0.47837090492248535, | |
| "learning_rate": 1.9986476482635003e-05, | |
| "loss": 0.1097, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.0011700666429262, | |
| "eval_loss": 0.2388339340686798, | |
| "eval_runtime": 34.8769, | |
| "eval_samples_per_second": 5.419, | |
| "eval_steps_per_second": 5.419, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 1.0093096606806735, | |
| "grad_norm": 0.5520356893539429, | |
| "learning_rate": 1.980547431053456e-05, | |
| "loss": 0.131, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.0255888487561682, | |
| "grad_norm": 0.6150078177452087, | |
| "learning_rate": 1.9622115153168884e-05, | |
| "loss": 0.1187, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.041868036831663, | |
| "grad_norm": 0.5100656151771545, | |
| "learning_rate": 1.9436458168207117e-05, | |
| "loss": 0.114, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.0581472249071577, | |
| "grad_norm": 0.5156052112579346, | |
| "learning_rate": 1.9248563254672825e-05, | |
| "loss": 0.1099, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.0744264129826524, | |
| "grad_norm": 0.4662775993347168, | |
| "learning_rate": 1.9058491033618632e-05, | |
| "loss": 0.1135, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.0907056010581473, | |
| "grad_norm": 0.4357255697250366, | |
| "learning_rate": 1.886630282856787e-05, | |
| "loss": 0.1036, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.106984789133642, | |
| "grad_norm": 0.3861764967441559, | |
| "learning_rate": 1.867206064572962e-05, | |
| "loss": 0.1145, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.1232639772091366, | |
| "grad_norm": 0.4562045633792877, | |
| "learning_rate": 1.8475827153993447e-05, | |
| "loss": 0.1107, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.1395431652846315, | |
| "grad_norm": 0.332917720079422, | |
| "learning_rate": 1.8277665664710387e-05, | |
| "loss": 0.1266, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.1558223533601262, | |
| "grad_norm": 0.5971720814704895, | |
| "learning_rate": 1.807764011126663e-05, | |
| "loss": 0.1122, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.1721015414356208, | |
| "grad_norm": 0.6102172136306763, | |
| "learning_rate": 1.787581502845651e-05, | |
| "loss": 0.1046, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.1883807295111157, | |
| "grad_norm": 0.5294010043144226, | |
| "learning_rate": 1.767225553166146e-05, | |
| "loss": 0.1044, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.2046599175866104, | |
| "grad_norm": 0.5074148178100586, | |
| "learning_rate": 1.7467027295841688e-05, | |
| "loss": 0.1251, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.220939105662105, | |
| "grad_norm": 0.6349917650222778, | |
| "learning_rate": 1.7260196534347235e-05, | |
| "loss": 0.1037, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.2372182937376, | |
| "grad_norm": 0.34580153226852417, | |
| "learning_rate": 1.7051829977555426e-05, | |
| "loss": 0.0831, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.2534974818130946, | |
| "grad_norm": 0.4629954993724823, | |
| "learning_rate": 1.684199485134144e-05, | |
| "loss": 0.1068, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.2697766698885893, | |
| "grad_norm": 0.6406750082969666, | |
| "learning_rate": 1.6630758855389055e-05, | |
| "loss": 0.1192, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.286055857964084, | |
| "grad_norm": 0.4982251226902008, | |
| "learning_rate": 1.6418190141348485e-05, | |
| "loss": 0.123, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.3023350460395788, | |
| "grad_norm": 0.5146717429161072, | |
| "learning_rate": 1.6204357290848464e-05, | |
| "loss": 0.0831, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.3186142341150735, | |
| "grad_norm": 0.4735712707042694, | |
| "learning_rate": 1.5989329293369538e-05, | |
| "loss": 0.0971, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.3348934221905682, | |
| "grad_norm": 0.7393200397491455, | |
| "learning_rate": 1.5773175523985818e-05, | |
| "loss": 0.0923, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.3348934221905682, | |
| "eval_loss": 0.22815725207328796, | |
| "eval_runtime": 34.8794, | |
| "eval_samples_per_second": 5.419, | |
| "eval_steps_per_second": 5.419, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.351172610266063, | |
| "grad_norm": 0.8956180214881897, | |
| "learning_rate": 1.5555965720982284e-05, | |
| "loss": 0.0817, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.3674517983415577, | |
| "grad_norm": 0.7423743009567261, | |
| "learning_rate": 1.533776996335497e-05, | |
| "loss": 0.1178, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.3837309864170524, | |
| "grad_norm": 0.7034802436828613, | |
| "learning_rate": 1.5118658648201145e-05, | |
| "loss": 0.1289, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.400010174492547, | |
| "grad_norm": 0.48646238446235657, | |
| "learning_rate": 1.4898702468006922e-05, | |
| "loss": 0.0839, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.416289362568042, | |
| "grad_norm": 0.28704097867012024, | |
| "learning_rate": 1.4677972387839548e-05, | |
| "loss": 0.0974, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.4325685506435366, | |
| "grad_norm": 0.674045205116272, | |
| "learning_rate": 1.4456539622451748e-05, | |
| "loss": 0.1006, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.4488477387190315, | |
| "grad_norm": 0.3513787090778351, | |
| "learning_rate": 1.4234475613305509e-05, | |
| "loss": 0.1104, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.4651269267945262, | |
| "grad_norm": 0.8029477596282959, | |
| "learning_rate": 1.4011852005522727e-05, | |
| "loss": 0.1131, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.4814061148700208, | |
| "grad_norm": 0.5420731902122498, | |
| "learning_rate": 1.378874062477015e-05, | |
| "loss": 0.0943, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.4976853029455155, | |
| "grad_norm": 0.7574429512023926, | |
| "learning_rate": 1.3565213454086048e-05, | |
| "loss": 0.1234, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.5139644910210102, | |
| "grad_norm": 0.5867305994033813, | |
| "learning_rate": 1.3341342610656157e-05, | |
| "loss": 0.1036, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.530243679096505, | |
| "grad_norm": 0.47744086384773254, | |
| "learning_rate": 1.311720032254629e-05, | |
| "loss": 0.1082, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.546522867172, | |
| "grad_norm": 0.6975990533828735, | |
| "learning_rate": 1.289285890539919e-05, | |
| "loss": 0.0967, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.5628020552474946, | |
| "grad_norm": 0.7781053781509399, | |
| "learning_rate": 1.2668390739103172e-05, | |
| "loss": 0.1219, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.5790812433229893, | |
| "grad_norm": 0.5423984527587891, | |
| "learning_rate": 1.2443868244439958e-05, | |
| "loss": 0.1085, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.595360431398484, | |
| "grad_norm": 0.5535146594047546, | |
| "learning_rate": 1.2219363859719392e-05, | |
| "loss": 0.0942, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.6116396194739786, | |
| "grad_norm": 0.30531561374664307, | |
| "learning_rate": 1.1994950017408451e-05, | |
| "loss": 0.0944, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.6279188075494735, | |
| "grad_norm": 0.7325620055198669, | |
| "learning_rate": 1.1770699120762161e-05, | |
| "loss": 0.1126, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.6441979956249682, | |
| "grad_norm": 1.1568708419799805, | |
| "learning_rate": 1.1546683520463961e-05, | |
| "loss": 0.1073, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.660477183700463, | |
| "grad_norm": 0.6926931142807007, | |
| "learning_rate": 1.1322975491282961e-05, | |
| "loss": 0.0825, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.6686167777382104, | |
| "eval_loss": 0.22156645357608795, | |
| "eval_runtime": 34.8778, | |
| "eval_samples_per_second": 5.419, | |
| "eval_steps_per_second": 5.419, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 1.6767563717759577, | |
| "grad_norm": 0.41277509927749634, | |
| "learning_rate": 1.1099647208755764e-05, | |
| "loss": 0.0991, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.6930355598514524, | |
| "grad_norm": 0.4389091730117798, | |
| "learning_rate": 1.0876770725900265e-05, | |
| "loss": 0.088, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.709314747926947, | |
| "grad_norm": 0.48445749282836914, | |
| "learning_rate": 1.0654417949968986e-05, | |
| "loss": 0.1158, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.725593936002442, | |
| "grad_norm": 0.6507833003997803, | |
| "learning_rate": 1.0432660619249448e-05, | |
| "loss": 0.1099, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.7418731240779366, | |
| "grad_norm": 0.6933814883232117, | |
| "learning_rate": 1.0211570279919044e-05, | |
| "loss": 0.0757, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.7581523121534315, | |
| "grad_norm": 0.7795721292495728, | |
| "learning_rate": 9.991218262961901e-06, | |
| "loss": 0.1017, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.7744315002289262, | |
| "grad_norm": 0.594406008720398, | |
| "learning_rate": 9.771675661155165e-06, | |
| "loss": 0.1144, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.7907106883044208, | |
| "grad_norm": 0.34790194034576416, | |
| "learning_rate": 9.553013306132158e-06, | |
| "loss": 0.0904, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.8069898763799155, | |
| "grad_norm": 0.4349744915962219, | |
| "learning_rate": 9.335301745529751e-06, | |
| "loss": 0.1085, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.8232690644554101, | |
| "grad_norm": 0.5773786306381226, | |
| "learning_rate": 9.118611220227399e-06, | |
| "loss": 0.1038, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.839548252530905, | |
| "grad_norm": 0.4364662766456604, | |
| "learning_rate": 8.903011641685128e-06, | |
| "loss": 0.097, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.8558274406063997, | |
| "grad_norm": 0.7753048539161682, | |
| "learning_rate": 8.688572569387817e-06, | |
| "loss": 0.1045, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.8721066286818946, | |
| "grad_norm": 0.48441290855407715, | |
| "learning_rate": 8.475363188403022e-06, | |
| "loss": 0.095, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.8883858167573893, | |
| "grad_norm": 0.6351140141487122, | |
| "learning_rate": 8.263452287059607e-06, | |
| "loss": 0.0977, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.904665004832884, | |
| "grad_norm": 0.8837946057319641, | |
| "learning_rate": 8.052908234754376e-06, | |
| "loss": 0.0987, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.9209441929083786, | |
| "grad_norm": 0.48196184635162354, | |
| "learning_rate": 7.84379895989388e-06, | |
| "loss": 0.088, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.9372233809838735, | |
| "grad_norm": 0.5001464486122131, | |
| "learning_rate": 7.636191927978465e-06, | |
| "loss": 0.1161, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.9535025690593681, | |
| "grad_norm": 0.6405985951423645, | |
| "learning_rate": 7.430154119835716e-06, | |
| "loss": 0.1023, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.969781757134863, | |
| "grad_norm": 0.7047804594039917, | |
| "learning_rate": 7.225752010010231e-06, | |
| "loss": 0.1131, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.9860609452103577, | |
| "grad_norm": 0.5221819281578064, | |
| "learning_rate": 7.023051545316763e-06, | |
| "loss": 0.0948, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.0023401332858524, | |
| "grad_norm": 0.4171787202358246, | |
| "learning_rate": 6.822118123563614e-06, | |
| "loss": 0.0995, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.0023401332858524, | |
| "eval_loss": 0.21631866693496704, | |
| "eval_runtime": 34.8988, | |
| "eval_samples_per_second": 5.416, | |
| "eval_steps_per_second": 5.416, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.018619321361347, | |
| "grad_norm": 0.7596387267112732, | |
| "learning_rate": 6.623016572453172e-06, | |
| "loss": 0.104, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.0348985094368417, | |
| "grad_norm": 0.3702397346496582, | |
| "learning_rate": 6.425811128666353e-06, | |
| "loss": 0.0693, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.0511776975123364, | |
| "grad_norm": 0.605099081993103, | |
| "learning_rate": 6.230565417137758e-06, | |
| "loss": 0.097, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.0674568855878315, | |
| "grad_norm": 0.4555053412914276, | |
| "learning_rate": 6.03734243052818e-06, | |
| "loss": 0.0976, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.083736073663326, | |
| "grad_norm": 0.7848448157310486, | |
| "learning_rate": 5.8462045089011066e-06, | |
| "loss": 0.1013, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.100015261738821, | |
| "grad_norm": 0.6905212998390198, | |
| "learning_rate": 5.657213319609776e-06, | |
| "loss": 0.1094, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.1162944498143155, | |
| "grad_norm": 0.5153264999389648, | |
| "learning_rate": 5.4704298374012834e-06, | |
| "loss": 0.0789, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.13257363788981, | |
| "grad_norm": 0.8393344879150391, | |
| "learning_rate": 5.2859143247441e-06, | |
| "loss": 0.0904, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.148852825965305, | |
| "grad_norm": 0.7440715432167053, | |
| "learning_rate": 5.103726312385452e-06, | |
| "loss": 0.0938, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.1651320140408, | |
| "grad_norm": 0.8069117069244385, | |
| "learning_rate": 4.923924580144743e-06, | |
| "loss": 0.0908, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.1814112021162946, | |
| "grad_norm": 0.5500065088272095, | |
| "learning_rate": 4.746567137949261e-06, | |
| "loss": 0.0976, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.1976903901917892, | |
| "grad_norm": 0.51816725730896, | |
| "learning_rate": 4.5717112071182715e-06, | |
| "loss": 0.0889, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.213969578267284, | |
| "grad_norm": 0.4226435124874115, | |
| "learning_rate": 4.399413201901559e-06, | |
| "loss": 0.0814, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.2302487663427786, | |
| "grad_norm": 0.4923081398010254, | |
| "learning_rate": 4.229728711278325e-06, | |
| "loss": 0.086, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.2465279544182732, | |
| "grad_norm": 0.5883035659790039, | |
| "learning_rate": 4.062712481022371e-06, | |
| "loss": 0.095, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.2628071424937684, | |
| "grad_norm": 0.5114026069641113, | |
| "learning_rate": 3.898418396039323e-06, | |
| "loss": 0.1038, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.279086330569263, | |
| "grad_norm": 0.5486142039299011, | |
| "learning_rate": 3.7368994629815953e-06, | |
| "loss": 0.0902, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.2953655186447577, | |
| "grad_norm": 0.756912350654602, | |
| "learning_rate": 3.5782077931467e-06, | |
| "loss": 0.0706, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.3116447067202524, | |
| "grad_norm": 0.6888672709465027, | |
| "learning_rate": 3.42239458566444e-06, | |
| "loss": 0.1065, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.327923894795747, | |
| "grad_norm": 0.5472647547721863, | |
| "learning_rate": 3.269510110978398e-06, | |
| "loss": 0.0815, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.3360634888334944, | |
| "eval_loss": 0.21516536176204681, | |
| "eval_runtime": 34.891, | |
| "eval_samples_per_second": 5.417, | |
| "eval_steps_per_second": 5.417, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 2.3442030828712417, | |
| "grad_norm": 0.5613276958465576, | |
| "learning_rate": 3.119603694627042e-06, | |
| "loss": 0.0923, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.3604822709467363, | |
| "grad_norm": 0.8540468811988831, | |
| "learning_rate": 2.9727237013296854e-06, | |
| "loss": 0.1192, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.3767614590222315, | |
| "grad_norm": 0.7269755005836487, | |
| "learning_rate": 2.828917519382457e-06, | |
| "loss": 0.0889, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 2.393040647097726, | |
| "grad_norm": 0.6140917539596558, | |
| "learning_rate": 2.6882315453692686e-06, | |
| "loss": 0.0936, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.409319835173221, | |
| "grad_norm": 0.4730454981327057, | |
| "learning_rate": 2.550711169192775e-06, | |
| "loss": 0.0976, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 2.4255990232487155, | |
| "grad_norm": 0.5974939465522766, | |
| "learning_rate": 2.4164007594300875e-06, | |
| "loss": 0.0913, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 2.44187821132421, | |
| "grad_norm": 0.6668256521224976, | |
| "learning_rate": 2.2853436490180374e-06, | |
| "loss": 0.0982, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.458157399399705, | |
| "grad_norm": 0.6182997226715088, | |
| "learning_rate": 2.1575821212725334e-06, | |
| "loss": 0.0861, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 2.4744365874752, | |
| "grad_norm": 0.5460255146026611, | |
| "learning_rate": 2.0331573962465864e-06, | |
| "loss": 0.086, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 2.4907157755506946, | |
| "grad_norm": 0.6361858248710632, | |
| "learning_rate": 1.912109617431372e-06, | |
| "loss": 0.0911, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 2.5069949636261892, | |
| "grad_norm": 0.8699812889099121, | |
| "learning_rate": 1.7944778388046243e-06, | |
| "loss": 0.0884, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 2.523274151701684, | |
| "grad_norm": 0.5886068344116211, | |
| "learning_rate": 1.680300012230543e-06, | |
| "loss": 0.1027, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.5395533397771786, | |
| "grad_norm": 0.6138848066329956, | |
| "learning_rate": 1.5696129752152774e-06, | |
| "loss": 0.0939, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 2.5558325278526732, | |
| "grad_norm": 0.7268607020378113, | |
| "learning_rate": 1.4624524390219455e-06, | |
| "loss": 0.083, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 2.572111715928168, | |
| "grad_norm": 0.619888961315155, | |
| "learning_rate": 1.3588529771490054e-06, | |
| "loss": 0.1087, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 2.5883909040036626, | |
| "grad_norm": 0.5299406051635742, | |
| "learning_rate": 1.2588480141757204e-06, | |
| "loss": 0.0997, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 2.6046700920791577, | |
| "grad_norm": 0.6051465272903442, | |
| "learning_rate": 1.1624698149782842e-06, | |
| "loss": 0.0953, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.6209492801546523, | |
| "grad_norm": 0.6585546135902405, | |
| "learning_rate": 1.0697494743201226e-06, | |
| "loss": 0.1057, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 2.637228468230147, | |
| "grad_norm": 0.5243381261825562, | |
| "learning_rate": 9.807169068197008e-07, | |
| "loss": 0.09, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 2.6535076563056417, | |
| "grad_norm": 0.6636092066764832, | |
| "learning_rate": 8.95400837299093e-07, | |
| "loss": 0.061, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 2.6697868443811363, | |
| "grad_norm": 0.6529124975204468, | |
| "learning_rate": 8.138287915164078e-07, | |
| "loss": 0.0897, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 2.6697868443811363, | |
| "eval_loss": 0.21331782639026642, | |
| "eval_runtime": 34.9348, | |
| "eval_samples_per_second": 5.41, | |
| "eval_steps_per_second": 5.41, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 2.6860660324566314, | |
| "grad_norm": 0.7361763715744019, | |
| "learning_rate": 7.360270872850808e-07, | |
| "loss": 0.0983, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.702345220532126, | |
| "grad_norm": 0.7820421457290649, | |
| "learning_rate": 6.620208259828855e-07, | |
| "loss": 0.0724, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 2.718624408607621, | |
| "grad_norm": 0.47821661829948425, | |
| "learning_rate": 5.918338844534077e-07, | |
| "loss": 0.0906, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 2.7349035966831154, | |
| "grad_norm": 0.5179721713066101, | |
| "learning_rate": 5.25488907302589e-07, | |
| "loss": 0.0851, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 2.75118278475861, | |
| "grad_norm": 0.7704452872276306, | |
| "learning_rate": 4.63007299592845e-07, | |
| "loss": 0.0765, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 2.7674619728341048, | |
| "grad_norm": 0.6302313208580017, | |
| "learning_rate": 4.044092199370797e-07, | |
| "loss": 0.093, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.7837411609095994, | |
| "grad_norm": 0.43464457988739014, | |
| "learning_rate": 3.497135739948657e-07, | |
| "loss": 0.0949, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 2.800020348985094, | |
| "grad_norm": 0.6571847796440125, | |
| "learning_rate": 2.98938008372851e-07, | |
| "loss": 0.0897, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 2.816299537060589, | |
| "grad_norm": 0.542305052280426, | |
| "learning_rate": 2.520989049313957e-07, | |
| "loss": 0.0968, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 2.832578725136084, | |
| "grad_norm": 0.5765232443809509, | |
| "learning_rate": 2.0921137549923946e-07, | |
| "loss": 0.0782, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 2.8488579132115786, | |
| "grad_norm": 0.6098420023918152, | |
| "learning_rate": 1.702892569979353e-07, | |
| "loss": 0.0808, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.865137101287073, | |
| "grad_norm": 0.5190752148628235, | |
| "learning_rate": 1.353451069776024e-07, | |
| "loss": 0.106, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 2.881416289362568, | |
| "grad_norm": 0.5709157586097717, | |
| "learning_rate": 1.0439019956544893e-07, | |
| "loss": 0.104, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 2.897695477438063, | |
| "grad_norm": 0.6572442054748535, | |
| "learning_rate": 7.743452182837202e-08, | |
| "loss": 0.1155, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 2.9139746655135577, | |
| "grad_norm": 0.8765654563903809, | |
| "learning_rate": 5.448677055080453e-08, | |
| "loss": 0.1118, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 2.9302538535890523, | |
| "grad_norm": 0.3849591910839081, | |
| "learning_rate": 3.555434942884156e-08, | |
| "loss": 0.097, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.946533041664547, | |
| "grad_norm": 0.6078172922134399, | |
| "learning_rate": 2.06433666815678e-08, | |
| "loss": 0.0987, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 2.9628122297400417, | |
| "grad_norm": 0.7132030129432678, | |
| "learning_rate": 9.758633080352019e-09, | |
| "loss": 0.0866, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 2.9790914178155363, | |
| "grad_norm": 0.879240870475769, | |
| "learning_rate": 2.903660396723351e-09, | |
| "loss": 0.0863, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 2.995370605891031, | |
| "grad_norm": 0.6857780814170837, | |
| "learning_rate": 8.066026937064709e-11, | |
| "loss": 0.1078, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 2.9986264435061303, | |
| "step": 1842, | |
| "total_flos": 1.5737761155189965e+18, | |
| "train_loss": 0.12212386991865083, | |
| "train_runtime": 37466.128, | |
| "train_samples_per_second": 1.574, | |
| "train_steps_per_second": 0.049 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1842, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 205, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5737761155189965e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |