| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 200, | |
| "global_step": 5676, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 0.32236674427986145, | |
| "learning_rate": 3.5087719298245616e-07, | |
| "loss": 1.2677, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.43721142411231995, | |
| "learning_rate": 3.5087719298245615e-06, | |
| "loss": 1.49, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.5593733191490173, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.5415, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.7312427163124084, | |
| "learning_rate": 1.017543859649123e-05, | |
| "loss": 1.4717, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.6353623867034912, | |
| "learning_rate": 1.3684210526315791e-05, | |
| "loss": 1.3929, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.9831274747848511, | |
| "learning_rate": 1.719298245614035e-05, | |
| "loss": 1.3707, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.7431375980377197, | |
| "learning_rate": 1.99928812956042e-05, | |
| "loss": 1.3745, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 1.1057510375976562, | |
| "learning_rate": 1.9957287773625203e-05, | |
| "loss": 1.3297, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.6114487648010254, | |
| "learning_rate": 1.99216942516462e-05, | |
| "loss": 1.1219, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.6235300898551941, | |
| "learning_rate": 1.98861007296672e-05, | |
| "loss": 1.2106, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.6816346645355225, | |
| "learning_rate": 1.9850507207688204e-05, | |
| "loss": 1.1522, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 1.3229148387908936, | |
| "learning_rate": 1.98149136857092e-05, | |
| "loss": 1.1312, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.7912402749061584, | |
| "learning_rate": 1.9779320163730202e-05, | |
| "loss": 1.1403, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.7789133787155151, | |
| "learning_rate": 1.9743726641751202e-05, | |
| "loss": 1.1448, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.82552170753479, | |
| "learning_rate": 1.9708133119772202e-05, | |
| "loss": 1.1366, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.9393932223320007, | |
| "learning_rate": 1.9672539597793203e-05, | |
| "loss": 1.0548, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.806780993938446, | |
| "learning_rate": 1.9636946075814203e-05, | |
| "loss": 1.1919, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 1.5307499170303345, | |
| "learning_rate": 1.9601352553835204e-05, | |
| "loss": 1.1351, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.6021313071250916, | |
| "learning_rate": 1.9565759031856204e-05, | |
| "loss": 1.085, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 1.5088614225387573, | |
| "learning_rate": 1.9530165509877204e-05, | |
| "loss": 1.1905, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.8093414306640625, | |
| "learning_rate": 1.9494571987898205e-05, | |
| "loss": 1.1223, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.2636756896972656, | |
| "eval_runtime": 12.3973, | |
| "eval_samples_per_second": 8.066, | |
| "eval_steps_per_second": 1.371, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.963275671005249, | |
| "learning_rate": 1.9458978465919205e-05, | |
| "loss": 1.1124, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 1.1342049837112427, | |
| "learning_rate": 1.9423384943940205e-05, | |
| "loss": 1.1384, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.8273957967758179, | |
| "learning_rate": 1.9387791421961206e-05, | |
| "loss": 1.1795, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.5721972584724426, | |
| "learning_rate": 1.9352197899982206e-05, | |
| "loss": 1.0944, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.7850355505943298, | |
| "learning_rate": 1.9316604378003206e-05, | |
| "loss": 1.1657, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.7827191352844238, | |
| "learning_rate": 1.9281010856024203e-05, | |
| "loss": 1.1118, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 1.3664053678512573, | |
| "learning_rate": 1.9245417334045204e-05, | |
| "loss": 1.0771, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 1.035074234008789, | |
| "learning_rate": 1.9209823812066207e-05, | |
| "loss": 1.1575, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.6814565062522888, | |
| "learning_rate": 1.9174230290087204e-05, | |
| "loss": 1.1488, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 2.5698676109313965, | |
| "learning_rate": 1.9138636768108205e-05, | |
| "loss": 1.0869, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.7751450538635254, | |
| "learning_rate": 1.910304324612921e-05, | |
| "loss": 0.9997, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.9140933752059937, | |
| "learning_rate": 1.9067449724150205e-05, | |
| "loss": 1.1402, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.750944197177887, | |
| "learning_rate": 1.9031856202171206e-05, | |
| "loss": 1.1022, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 1.1410951614379883, | |
| "learning_rate": 1.8996262680192206e-05, | |
| "loss": 1.0894, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.7307860255241394, | |
| "learning_rate": 1.8960669158213206e-05, | |
| "loss": 1.0518, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.6405724287033081, | |
| "learning_rate": 1.8925075636234207e-05, | |
| "loss": 1.0727, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 2.046175956726074, | |
| "learning_rate": 1.8889482114255207e-05, | |
| "loss": 1.0753, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 1.1144558191299438, | |
| "learning_rate": 1.8853888592276207e-05, | |
| "loss": 1.0566, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.770236611366272, | |
| "learning_rate": 1.8818295070297208e-05, | |
| "loss": 0.9932, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.972495436668396, | |
| "learning_rate": 1.8782701548318208e-05, | |
| "loss": 1.1034, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.2242885828018188, | |
| "eval_runtime": 12.55, | |
| "eval_samples_per_second": 7.968, | |
| "eval_steps_per_second": 1.355, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.7233368158340454, | |
| "learning_rate": 1.874710802633921e-05, | |
| "loss": 1.0944, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 1.1819795370101929, | |
| "learning_rate": 1.871151450436021e-05, | |
| "loss": 1.0212, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.8385196328163147, | |
| "learning_rate": 1.867592098238121e-05, | |
| "loss": 1.1335, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 1.0911675691604614, | |
| "learning_rate": 1.8640327460402206e-05, | |
| "loss": 1.0992, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.9316151142120361, | |
| "learning_rate": 1.860473393842321e-05, | |
| "loss": 1.0696, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.7146535515785217, | |
| "learning_rate": 1.856914041644421e-05, | |
| "loss": 1.101, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 1.1494003534317017, | |
| "learning_rate": 1.8533546894465207e-05, | |
| "loss": 1.0597, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.7938774228096008, | |
| "learning_rate": 1.8497953372486208e-05, | |
| "loss": 1.1357, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.9449957609176636, | |
| "learning_rate": 1.846235985050721e-05, | |
| "loss": 1.0505, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.9485340118408203, | |
| "learning_rate": 1.8426766328528208e-05, | |
| "loss": 1.1575, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.7425325512886047, | |
| "learning_rate": 1.839117280654921e-05, | |
| "loss": 1.0895, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.831925630569458, | |
| "learning_rate": 1.8355579284570212e-05, | |
| "loss": 1.0369, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 1.1724563837051392, | |
| "learning_rate": 1.831998576259121e-05, | |
| "loss": 1.051, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.7532387375831604, | |
| "learning_rate": 1.828439224061221e-05, | |
| "loss": 1.0732, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.8664720058441162, | |
| "learning_rate": 1.824879871863321e-05, | |
| "loss": 1.0675, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.68962562084198, | |
| "learning_rate": 1.821676454885211e-05, | |
| "loss": 1.0546, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.967743992805481, | |
| "learning_rate": 1.818117102687311e-05, | |
| "loss": 1.0626, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 1.1372209787368774, | |
| "learning_rate": 1.8145577504894112e-05, | |
| "loss": 1.0407, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.5581480264663696, | |
| "learning_rate": 1.8109983982915112e-05, | |
| "loss": 1.1016, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.9006016254425049, | |
| "learning_rate": 1.807439046093611e-05, | |
| "loss": 1.0865, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.2136958837509155, | |
| "eval_runtime": 14.6836, | |
| "eval_samples_per_second": 6.81, | |
| "eval_steps_per_second": 1.158, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 1.167442798614502, | |
| "learning_rate": 1.803879693895711e-05, | |
| "loss": 1.0588, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 2.120898723602295, | |
| "learning_rate": 1.8003203416978113e-05, | |
| "loss": 1.071, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 2.142792224884033, | |
| "learning_rate": 1.796760989499911e-05, | |
| "loss": 1.0821, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 2.748411178588867, | |
| "learning_rate": 1.793201637302011e-05, | |
| "loss": 1.0804, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 1.100048303604126, | |
| "learning_rate": 1.789642285104111e-05, | |
| "loss": 1.1814, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 1.0551257133483887, | |
| "learning_rate": 1.786082932906211e-05, | |
| "loss": 1.1621, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.9872214794158936, | |
| "learning_rate": 1.7825235807083112e-05, | |
| "loss": 1.1294, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.9092286825180054, | |
| "learning_rate": 1.7789642285104112e-05, | |
| "loss": 1.126, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.5403127074241638, | |
| "learning_rate": 1.7754048763125112e-05, | |
| "loss": 1.0491, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 1.4916988611221313, | |
| "learning_rate": 1.7718455241146113e-05, | |
| "loss": 1.0754, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 1.0109350681304932, | |
| "learning_rate": 1.7682861719167113e-05, | |
| "loss": 1.1069, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.6402379274368286, | |
| "learning_rate": 1.7647268197188113e-05, | |
| "loss": 1.0733, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.9078841805458069, | |
| "learning_rate": 1.7611674675209114e-05, | |
| "loss": 1.1404, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.8853003978729248, | |
| "learning_rate": 1.7576081153230114e-05, | |
| "loss": 1.074, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.9647941589355469, | |
| "learning_rate": 1.7540487631251115e-05, | |
| "loss": 1.0247, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.1798278093338013, | |
| "learning_rate": 1.7504894109272115e-05, | |
| "loss": 0.9628, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 1.4496029615402222, | |
| "learning_rate": 1.7469300587293115e-05, | |
| "loss": 1.1417, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 1.0010195970535278, | |
| "learning_rate": 1.7433707065314112e-05, | |
| "loss": 1.1053, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 1.33387291431427, | |
| "learning_rate": 1.7398113543335113e-05, | |
| "loss": 1.0656, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.702763020992279, | |
| "learning_rate": 1.7366079373554014e-05, | |
| "loss": 1.1234, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.1928606033325195, | |
| "eval_runtime": 11.8371, | |
| "eval_samples_per_second": 8.448, | |
| "eval_steps_per_second": 1.436, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.9783468246459961, | |
| "learning_rate": 1.7330485851575014e-05, | |
| "loss": 1.0128, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 1.159887671470642, | |
| "learning_rate": 1.7294892329596015e-05, | |
| "loss": 1.1542, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 1.5634437799453735, | |
| "learning_rate": 1.7259298807617015e-05, | |
| "loss": 1.0528, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 1.3583545684814453, | |
| "learning_rate": 1.7223705285638015e-05, | |
| "loss": 1.0614, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.5114862322807312, | |
| "learning_rate": 1.7188111763659016e-05, | |
| "loss": 1.0185, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 1.1469477415084839, | |
| "learning_rate": 1.7152518241680016e-05, | |
| "loss": 1.1334, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 2.432640552520752, | |
| "learning_rate": 1.7116924719701016e-05, | |
| "loss": 1.0236, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 2.076552152633667, | |
| "learning_rate": 1.7081331197722017e-05, | |
| "loss": 0.9322, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 1.0589828491210938, | |
| "learning_rate": 1.7045737675743017e-05, | |
| "loss": 1.1597, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 1.1427756547927856, | |
| "learning_rate": 1.7010144153764017e-05, | |
| "loss": 0.9755, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.731461763381958, | |
| "learning_rate": 1.6974550631785018e-05, | |
| "loss": 1.1121, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 1.1905068159103394, | |
| "learning_rate": 1.6938957109806015e-05, | |
| "loss": 1.032, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 1.1865007877349854, | |
| "learning_rate": 1.690336358782702e-05, | |
| "loss": 1.0955, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 1.258158802986145, | |
| "learning_rate": 1.6867770065848015e-05, | |
| "loss": 0.9775, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 4.213527202606201, | |
| "learning_rate": 1.6832176543869016e-05, | |
| "loss": 1.0948, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.5976575613021851, | |
| "learning_rate": 1.679658302189002e-05, | |
| "loss": 1.0867, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.9984912276268005, | |
| "learning_rate": 1.6760989499911016e-05, | |
| "loss": 1.0302, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 1.3806593418121338, | |
| "learning_rate": 1.6725395977932017e-05, | |
| "loss": 1.1168, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.886235773563385, | |
| "learning_rate": 1.6689802455953017e-05, | |
| "loss": 1.0597, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 1.479944109916687, | |
| "learning_rate": 1.6654208933974017e-05, | |
| "loss": 1.1343, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.1987661123275757, | |
| "eval_runtime": 11.8887, | |
| "eval_samples_per_second": 8.411, | |
| "eval_steps_per_second": 1.43, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.913791298866272, | |
| "learning_rate": 1.6618615411995018e-05, | |
| "loss": 1.0946, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 1.08577299118042, | |
| "learning_rate": 1.6583021890016018e-05, | |
| "loss": 1.0837, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 1.308807134628296, | |
| "learning_rate": 1.654742836803702e-05, | |
| "loss": 1.0332, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.9155540466308594, | |
| "learning_rate": 1.651183484605802e-05, | |
| "loss": 1.014, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 1.1873680353164673, | |
| "learning_rate": 1.647624132407902e-05, | |
| "loss": 1.039, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 1.0363208055496216, | |
| "learning_rate": 1.644064780210002e-05, | |
| "loss": 1.1289, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.9621215462684631, | |
| "learning_rate": 1.640505428012102e-05, | |
| "loss": 1.0474, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 2.1917757987976074, | |
| "learning_rate": 1.636946075814202e-05, | |
| "loss": 1.0863, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 1.169842004776001, | |
| "learning_rate": 1.633386723616302e-05, | |
| "loss": 1.1294, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 2.551154851913452, | |
| "learning_rate": 1.629827371418402e-05, | |
| "loss": 0.9399, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 1.1329141855239868, | |
| "learning_rate": 1.626268019220502e-05, | |
| "loss": 1.1022, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 1.281090497970581, | |
| "learning_rate": 1.622708667022602e-05, | |
| "loss": 1.0408, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 1.2209128141403198, | |
| "learning_rate": 1.619149314824702e-05, | |
| "loss": 1.072, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 1.1982104778289795, | |
| "learning_rate": 1.6155899626268022e-05, | |
| "loss": 0.9529, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 1.8364869356155396, | |
| "learning_rate": 1.612030610428902e-05, | |
| "loss": 1.0717, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.9978988766670227, | |
| "learning_rate": 1.608471258231002e-05, | |
| "loss": 1.0509, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 1.0802960395812988, | |
| "learning_rate": 1.6049119060331023e-05, | |
| "loss": 1.1194, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 1.579270601272583, | |
| "learning_rate": 1.601352553835202e-05, | |
| "loss": 1.0528, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 1.7609140872955322, | |
| "learning_rate": 1.597793201637302e-05, | |
| "loss": 1.0603, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.9313896298408508, | |
| "learning_rate": 1.594233849439402e-05, | |
| "loss": 1.0369, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 1.1840168237686157, | |
| "eval_runtime": 12.2051, | |
| "eval_samples_per_second": 8.193, | |
| "eval_steps_per_second": 1.393, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.758716881275177, | |
| "learning_rate": 1.590674497241502e-05, | |
| "loss": 0.9948, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 1.4738125801086426, | |
| "learning_rate": 1.587115145043602e-05, | |
| "loss": 1.076, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 1.0415221452713013, | |
| "learning_rate": 1.5835557928457022e-05, | |
| "loss": 1.1402, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 1.328813076019287, | |
| "learning_rate": 1.5799964406478022e-05, | |
| "loss": 1.0151, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 1.275273084640503, | |
| "learning_rate": 1.5764370884499023e-05, | |
| "loss": 1.0228, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 2.3015737533569336, | |
| "learning_rate": 1.5728777362520023e-05, | |
| "loss": 1.0643, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 1.2387661933898926, | |
| "learning_rate": 1.5693183840541023e-05, | |
| "loss": 1.0901, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 1.456081748008728, | |
| "learning_rate": 1.5657590318562024e-05, | |
| "loss": 1.0395, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.6578852534294128, | |
| "learning_rate": 1.5621996796583024e-05, | |
| "loss": 0.9833, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 2.0976483821868896, | |
| "learning_rate": 1.5586403274604024e-05, | |
| "loss": 1.0774, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.9041242003440857, | |
| "learning_rate": 1.5550809752625025e-05, | |
| "loss": 0.9858, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 1.627486228942871, | |
| "learning_rate": 1.5515216230646025e-05, | |
| "loss": 1.1047, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 1.6745047569274902, | |
| "learning_rate": 1.5479622708667022e-05, | |
| "loss": 1.0766, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.7612773180007935, | |
| "learning_rate": 1.5444029186688022e-05, | |
| "loss": 1.0028, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.9367202520370483, | |
| "learning_rate": 1.5408435664709026e-05, | |
| "loss": 1.0505, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.9992938041687012, | |
| "learning_rate": 1.5372842142730023e-05, | |
| "loss": 1.0432, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.8286828398704529, | |
| "learning_rate": 1.5337248620751024e-05, | |
| "loss": 1.0698, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 1.2160322666168213, | |
| "learning_rate": 1.5301655098772027e-05, | |
| "loss": 1.091, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 2.774073600769043, | |
| "learning_rate": 1.5266061576793024e-05, | |
| "loss": 1.0411, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 1.472316026687622, | |
| "learning_rate": 1.5230468054814025e-05, | |
| "loss": 0.9933, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.1851048469543457, | |
| "eval_runtime": 12.0394, | |
| "eval_samples_per_second": 8.306, | |
| "eval_steps_per_second": 1.412, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 1.7815942764282227, | |
| "learning_rate": 1.5194874532835025e-05, | |
| "loss": 1.0632, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 1.523148775100708, | |
| "learning_rate": 1.5159281010856027e-05, | |
| "loss": 1.0111, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.7297208905220032, | |
| "learning_rate": 1.5123687488877026e-05, | |
| "loss": 0.9971, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 1.1453901529312134, | |
| "learning_rate": 1.5088093966898026e-05, | |
| "loss": 1.0045, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 1.1769226789474487, | |
| "learning_rate": 1.5052500444919026e-05, | |
| "loss": 0.9591, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 1.251314401626587, | |
| "learning_rate": 1.5016906922940027e-05, | |
| "loss": 1.1478, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.9563061594963074, | |
| "learning_rate": 1.4981313400961025e-05, | |
| "loss": 1.0645, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 1.0183663368225098, | |
| "learning_rate": 1.4945719878982026e-05, | |
| "loss": 1.0006, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 1.0434117317199707, | |
| "learning_rate": 1.4910126357003028e-05, | |
| "loss": 1.0085, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.9190971851348877, | |
| "learning_rate": 1.4874532835024026e-05, | |
| "loss": 1.0313, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.1930954456329346, | |
| "learning_rate": 1.4838939313045027e-05, | |
| "loss": 1.0238, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.223698377609253, | |
| "learning_rate": 1.4803345791066025e-05, | |
| "loss": 1.0293, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 1.43943190574646, | |
| "learning_rate": 1.4767752269087027e-05, | |
| "loss": 1.0669, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 1.0293264389038086, | |
| "learning_rate": 1.4732158747108028e-05, | |
| "loss": 1.0086, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 1.025455355644226, | |
| "learning_rate": 1.4696565225129026e-05, | |
| "loss": 1.0138, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.9345937371253967, | |
| "learning_rate": 1.4660971703150028e-05, | |
| "loss": 0.9701, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 1.0753653049468994, | |
| "learning_rate": 1.4625378181171029e-05, | |
| "loss": 1.0806, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 4.404356479644775, | |
| "learning_rate": 1.4589784659192027e-05, | |
| "loss": 0.9779, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.7831115126609802, | |
| "learning_rate": 1.4554191137213028e-05, | |
| "loss": 0.9878, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 1.2919056415557861, | |
| "learning_rate": 1.451859761523403e-05, | |
| "loss": 1.0194, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 1.1717853546142578, | |
| "eval_runtime": 12.4892, | |
| "eval_samples_per_second": 8.007, | |
| "eval_steps_per_second": 1.361, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.8066655397415161, | |
| "learning_rate": 1.4483004093255028e-05, | |
| "loss": 1.0165, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.6934823989868164, | |
| "learning_rate": 1.4447410571276029e-05, | |
| "loss": 1.0252, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 1.0509413480758667, | |
| "learning_rate": 1.441181704929703e-05, | |
| "loss": 1.0394, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 1.0531914234161377, | |
| "learning_rate": 1.437622352731803e-05, | |
| "loss": 1.0567, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 1.3348867893218994, | |
| "learning_rate": 1.434063000533903e-05, | |
| "loss": 1.0966, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.7294674515724182, | |
| "learning_rate": 1.4305036483360029e-05, | |
| "loss": 1.0479, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.6675371527671814, | |
| "learning_rate": 1.426944296138103e-05, | |
| "loss": 1.084, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.986166775226593, | |
| "learning_rate": 1.423384943940203e-05, | |
| "loss": 1.0608, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 1.313966989517212, | |
| "learning_rate": 1.419825591742303e-05, | |
| "loss": 0.9762, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 1.4158449172973633, | |
| "learning_rate": 1.4162662395444032e-05, | |
| "loss": 0.9521, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 1.436147689819336, | |
| "learning_rate": 1.412706887346503e-05, | |
| "loss": 1.0874, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 1.1787075996398926, | |
| "learning_rate": 1.409147535148603e-05, | |
| "loss": 1.1035, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.9145377278327942, | |
| "learning_rate": 1.405588182950703e-05, | |
| "loss": 1.0028, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.8889722228050232, | |
| "learning_rate": 1.4020288307528031e-05, | |
| "loss": 1.2045, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 1.4678986072540283, | |
| "learning_rate": 1.3984694785549032e-05, | |
| "loss": 1.015, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 2.1600582599639893, | |
| "learning_rate": 1.394910126357003e-05, | |
| "loss": 1.0651, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 1.826326608657837, | |
| "learning_rate": 1.3913507741591032e-05, | |
| "loss": 1.0574, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 1.3350718021392822, | |
| "learning_rate": 1.3877914219612033e-05, | |
| "loss": 1.0038, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 1.0555437803268433, | |
| "learning_rate": 1.3842320697633031e-05, | |
| "loss": 1.0608, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 1.3009488582611084, | |
| "learning_rate": 1.3806727175654032e-05, | |
| "loss": 0.9814, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 1.1766358613967896, | |
| "eval_runtime": 11.4487, | |
| "eval_samples_per_second": 8.735, | |
| "eval_steps_per_second": 1.485, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 1.571081280708313, | |
| "learning_rate": 1.3771133653675032e-05, | |
| "loss": 1.1209, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.9949061870574951, | |
| "learning_rate": 1.3735540131696032e-05, | |
| "loss": 1.0788, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 1.3611658811569214, | |
| "learning_rate": 1.3699946609717033e-05, | |
| "loss": 1.0404, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 1.0979316234588623, | |
| "learning_rate": 1.3664353087738033e-05, | |
| "loss": 1.0733, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.8498410582542419, | |
| "learning_rate": 1.3628759565759033e-05, | |
| "loss": 1.0052, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 1.0681723356246948, | |
| "learning_rate": 1.3593166043780032e-05, | |
| "loss": 1.0663, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 1.0206513404846191, | |
| "learning_rate": 1.3557572521801032e-05, | |
| "loss": 1.0119, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.9764016270637512, | |
| "learning_rate": 1.3521978999822034e-05, | |
| "loss": 1.0362, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.1894639730453491, | |
| "learning_rate": 1.3486385477843033e-05, | |
| "loss": 1.0472, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.9249853491783142, | |
| "learning_rate": 1.3450791955864034e-05, | |
| "loss": 1.0191, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 1.786095142364502, | |
| "learning_rate": 1.3415198433885036e-05, | |
| "loss": 1.1259, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 1.1381618976593018, | |
| "learning_rate": 1.3379604911906034e-05, | |
| "loss": 1.0385, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 1.0195496082305908, | |
| "learning_rate": 1.3344011389927035e-05, | |
| "loss": 0.9556, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 2.8120012283325195, | |
| "learning_rate": 1.3308417867948033e-05, | |
| "loss": 1.0085, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 1.8221272230148315, | |
| "learning_rate": 1.3272824345969035e-05, | |
| "loss": 1.0554, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 1.707749366760254, | |
| "learning_rate": 1.3237230823990036e-05, | |
| "loss": 1.0642, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 1.8655564785003662, | |
| "learning_rate": 1.3201637302011034e-05, | |
| "loss": 1.0366, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.8413867950439453, | |
| "learning_rate": 1.3166043780032036e-05, | |
| "loss": 1.0646, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 1.0647209882736206, | |
| "learning_rate": 1.3130450258053035e-05, | |
| "loss": 1.079, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 1.2801264524459839, | |
| "learning_rate": 1.3094856736074035e-05, | |
| "loss": 1.049, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 1.1730597019195557, | |
| "eval_runtime": 11.9706, | |
| "eval_samples_per_second": 8.354, | |
| "eval_steps_per_second": 1.42, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 1.2153600454330444, | |
| "learning_rate": 1.3059263214095036e-05, | |
| "loss": 1.0286, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 1.0132453441619873, | |
| "learning_rate": 1.3023669692116036e-05, | |
| "loss": 1.0218, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 1.4758011102676392, | |
| "learning_rate": 1.2988076170137036e-05, | |
| "loss": 1.0544, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.7948209643363953, | |
| "learning_rate": 1.2952482648158035e-05, | |
| "loss": 1.0017, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.9743032455444336, | |
| "learning_rate": 1.2916889126179037e-05, | |
| "loss": 0.9907, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 3.579349994659424, | |
| "learning_rate": 1.2881295604200037e-05, | |
| "loss": 1.0299, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 1.6663838624954224, | |
| "learning_rate": 1.2845702082221036e-05, | |
| "loss": 0.974, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.850301206111908, | |
| "learning_rate": 1.2810108560242036e-05, | |
| "loss": 1.0182, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 1.1403268575668335, | |
| "learning_rate": 1.2774515038263038e-05, | |
| "loss": 1.0108, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 1.1878316402435303, | |
| "learning_rate": 1.2738921516284037e-05, | |
| "loss": 0.9969, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 2.075212001800537, | |
| "learning_rate": 1.2703327994305037e-05, | |
| "loss": 1.0504, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 1.278403639793396, | |
| "learning_rate": 1.266773447232604e-05, | |
| "loss": 1.033, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.7736448645591736, | |
| "learning_rate": 1.2632140950347038e-05, | |
| "loss": 0.9618, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 1.0779714584350586, | |
| "learning_rate": 1.2596547428368038e-05, | |
| "loss": 0.9947, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 1.1325520277023315, | |
| "learning_rate": 1.2560953906389037e-05, | |
| "loss": 1.0903, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 2.208906888961792, | |
| "learning_rate": 1.252536038441004e-05, | |
| "loss": 1.0425, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 1.1757577657699585, | |
| "learning_rate": 1.2489766862431038e-05, | |
| "loss": 1.0689, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 0.7692458629608154, | |
| "learning_rate": 1.2454173340452038e-05, | |
| "loss": 1.0108, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 1.0259288549423218, | |
| "learning_rate": 1.241857981847304e-05, | |
| "loss": 1.0601, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 1.3639546632766724, | |
| "learning_rate": 1.2382986296494039e-05, | |
| "loss": 0.9756, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 1.168999433517456, | |
| "eval_runtime": 12.537, | |
| "eval_samples_per_second": 7.976, | |
| "eval_steps_per_second": 1.356, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 0.726823627948761, | |
| "learning_rate": 1.234739277451504e-05, | |
| "loss": 0.9996, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 1.4610772132873535, | |
| "learning_rate": 1.2311799252536038e-05, | |
| "loss": 1.046, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 1.0037659406661987, | |
| "learning_rate": 1.227620573055704e-05, | |
| "loss": 1.0877, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 1.1849032640457153, | |
| "learning_rate": 1.224061220857804e-05, | |
| "loss": 0.9626, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 1.4240535497665405, | |
| "learning_rate": 1.2205018686599039e-05, | |
| "loss": 0.9858, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 1.5655783414840698, | |
| "learning_rate": 1.2169425164620041e-05, | |
| "loss": 1.0518, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 2.311018228530884, | |
| "learning_rate": 1.2133831642641041e-05, | |
| "loss": 1.1071, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 1.3174004554748535, | |
| "learning_rate": 1.209823812066204e-05, | |
| "loss": 1.0349, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.9538156986236572, | |
| "learning_rate": 1.206264459868304e-05, | |
| "loss": 0.9582, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 1.9227030277252197, | |
| "learning_rate": 1.2027051076704042e-05, | |
| "loss": 1.0858, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 1.4896920919418335, | |
| "learning_rate": 1.1991457554725041e-05, | |
| "loss": 1.0289, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 1.1001384258270264, | |
| "learning_rate": 1.1955864032746041e-05, | |
| "loss": 1.0056, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 1.0513100624084473, | |
| "learning_rate": 1.1920270510767042e-05, | |
| "loss": 0.9581, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 1.7394877672195435, | |
| "learning_rate": 1.1884676988788042e-05, | |
| "loss": 1.0419, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.8548335433006287, | |
| "learning_rate": 1.184908346680904e-05, | |
| "loss": 1.0181, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.7628202438354492, | |
| "learning_rate": 1.1813489944830041e-05, | |
| "loss": 1.0619, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.9310820698738098, | |
| "learning_rate": 1.1777896422851043e-05, | |
| "loss": 1.0152, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 1.7227360010147095, | |
| "learning_rate": 1.1742302900872042e-05, | |
| "loss": 1.0126, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 1.2895365953445435, | |
| "learning_rate": 1.1706709378893042e-05, | |
| "loss": 0.9622, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 2.133793354034424, | |
| "learning_rate": 1.1671115856914044e-05, | |
| "loss": 0.9682, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 1.1656237840652466, | |
| "eval_runtime": 11.3341, | |
| "eval_samples_per_second": 8.823, | |
| "eval_steps_per_second": 1.5, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 1.140449047088623, | |
| "learning_rate": 1.1635522334935043e-05, | |
| "loss": 1.083, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.818942666053772, | |
| "learning_rate": 1.1599928812956043e-05, | |
| "loss": 1.0021, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 2.086158037185669, | |
| "learning_rate": 1.1564335290977042e-05, | |
| "loss": 1.0785, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 1.4004687070846558, | |
| "learning_rate": 1.1528741768998044e-05, | |
| "loss": 1.0641, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 1.2870811223983765, | |
| "learning_rate": 1.1493148247019044e-05, | |
| "loss": 1.0093, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 1.077475905418396, | |
| "learning_rate": 1.1457554725040043e-05, | |
| "loss": 1.0282, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 1.348465085029602, | |
| "learning_rate": 1.1421961203061043e-05, | |
| "loss": 1.0077, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 2.4972736835479736, | |
| "learning_rate": 1.1386367681082045e-05, | |
| "loss": 1.0516, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 1.054648995399475, | |
| "learning_rate": 1.1350774159103044e-05, | |
| "loss": 0.9948, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 3.2947356700897217, | |
| "learning_rate": 1.1315180637124044e-05, | |
| "loss": 0.9517, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 2.8229053020477295, | |
| "learning_rate": 1.1279587115145045e-05, | |
| "loss": 1.0321, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.8427309393882751, | |
| "learning_rate": 1.1243993593166045e-05, | |
| "loss": 1.0386, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 2.0756163597106934, | |
| "learning_rate": 1.1208400071187045e-05, | |
| "loss": 0.9872, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.876058042049408, | |
| "learning_rate": 1.1172806549208044e-05, | |
| "loss": 1.0212, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 3.1672606468200684, | |
| "learning_rate": 1.1137213027229046e-05, | |
| "loss": 1.094, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 1.792658805847168, | |
| "learning_rate": 1.1101619505250045e-05, | |
| "loss": 1.0177, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 1.8805761337280273, | |
| "learning_rate": 1.1066025983271045e-05, | |
| "loss": 0.9905, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 2.549272298812866, | |
| "learning_rate": 1.1030432461292047e-05, | |
| "loss": 1.0836, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 1.2442760467529297, | |
| "learning_rate": 1.0994838939313046e-05, | |
| "loss": 1.0382, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.8658510446548462, | |
| "learning_rate": 1.0959245417334046e-05, | |
| "loss": 1.0956, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_loss": 1.1738361120224, | |
| "eval_runtime": 14.0561, | |
| "eval_samples_per_second": 7.114, | |
| "eval_steps_per_second": 1.209, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 1.1395150423049927, | |
| "learning_rate": 1.0923651895355045e-05, | |
| "loss": 1.0546, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.9584295153617859, | |
| "learning_rate": 1.0888058373376047e-05, | |
| "loss": 1.0546, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 0.770491361618042, | |
| "learning_rate": 1.0852464851397047e-05, | |
| "loss": 1.0307, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 1.555954098701477, | |
| "learning_rate": 1.0816871329418046e-05, | |
| "loss": 1.0875, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.8969519138336182, | |
| "learning_rate": 1.0781277807439048e-05, | |
| "loss": 1.004, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 1.184382438659668, | |
| "learning_rate": 1.0745684285460048e-05, | |
| "loss": 1.0966, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 1.942267894744873, | |
| "learning_rate": 1.0710090763481047e-05, | |
| "loss": 0.9683, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 1.51211416721344, | |
| "learning_rate": 1.0674497241502047e-05, | |
| "loss": 1.0637, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 2.1240007877349854, | |
| "learning_rate": 1.0638903719523047e-05, | |
| "loss": 1.0362, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 1.1192448139190674, | |
| "learning_rate": 1.0603310197544048e-05, | |
| "loss": 1.0569, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 1.3807482719421387, | |
| "learning_rate": 1.0567716675565048e-05, | |
| "loss": 1.0341, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 1.2013037204742432, | |
| "learning_rate": 1.0532123153586048e-05, | |
| "loss": 1.101, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 1.2412744760513306, | |
| "learning_rate": 1.0496529631607049e-05, | |
| "loss": 1.0797, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.8929006457328796, | |
| "learning_rate": 1.0460936109628047e-05, | |
| "loss": 1.0133, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 1.822242021560669, | |
| "learning_rate": 1.0425342587649048e-05, | |
| "loss": 1.0136, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 6.889304161071777, | |
| "learning_rate": 1.038974906567005e-05, | |
| "loss": 0.9998, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 2.523271083831787, | |
| "learning_rate": 1.0354155543691049e-05, | |
| "loss": 1.1461, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 1.6396363973617554, | |
| "learning_rate": 1.0318562021712049e-05, | |
| "loss": 1.0318, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 0.8493086099624634, | |
| "learning_rate": 1.0282968499733051e-05, | |
| "loss": 0.9634, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 1.6316001415252686, | |
| "learning_rate": 1.024737497775405e-05, | |
| "loss": 1.082, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 1.1678745746612549, | |
| "eval_runtime": 11.5233, | |
| "eval_samples_per_second": 8.678, | |
| "eval_steps_per_second": 1.475, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 1.672155499458313, | |
| "learning_rate": 1.021178145577505e-05, | |
| "loss": 1.0492, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.9142770171165466, | |
| "learning_rate": 1.0176187933796049e-05, | |
| "loss": 1.0306, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 1.615238070487976, | |
| "learning_rate": 1.014059441181705e-05, | |
| "loss": 1.0163, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 1.753221035003662, | |
| "learning_rate": 1.0105000889838051e-05, | |
| "loss": 1.0014, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 1.0352283716201782, | |
| "learning_rate": 1.006940736785905e-05, | |
| "loss": 0.974, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 1.3456447124481201, | |
| "learning_rate": 1.0033813845880052e-05, | |
| "loss": 0.9724, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 1.1102288961410522, | |
| "learning_rate": 9.99822032390105e-06, | |
| "loss": 0.9948, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 2.233786106109619, | |
| "learning_rate": 9.96262680192205e-06, | |
| "loss": 1.0096, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 1.2956023216247559, | |
| "learning_rate": 9.927033279943051e-06, | |
| "loss": 0.9885, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 1.8314197063446045, | |
| "learning_rate": 9.891439757964051e-06, | |
| "loss": 1.0218, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 1.4119048118591309, | |
| "learning_rate": 9.855846235985052e-06, | |
| "loss": 1.0131, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 1.5489697456359863, | |
| "learning_rate": 9.820252714006052e-06, | |
| "loss": 1.1121, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 1.2193057537078857, | |
| "learning_rate": 9.784659192027052e-06, | |
| "loss": 0.9923, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 1.6736855506896973, | |
| "learning_rate": 9.749065670048053e-06, | |
| "loss": 1.0686, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 1.6176037788391113, | |
| "learning_rate": 9.713472148069051e-06, | |
| "loss": 1.0737, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 1.4361757040023804, | |
| "learning_rate": 9.677878626090052e-06, | |
| "loss": 1.0024, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 1.2182648181915283, | |
| "learning_rate": 9.642285104111052e-06, | |
| "loss": 1.0402, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 1.053998589515686, | |
| "learning_rate": 9.606691582132052e-06, | |
| "loss": 1.0613, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 1.5341476202011108, | |
| "learning_rate": 9.571098060153053e-06, | |
| "loss": 1.0076, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 8.025810241699219, | |
| "learning_rate": 9.535504538174053e-06, | |
| "loss": 0.9547, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 1.167173147201538, | |
| "eval_runtime": 12.0558, | |
| "eval_samples_per_second": 8.295, | |
| "eval_steps_per_second": 1.41, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 3.604372262954712, | |
| "learning_rate": 9.499911016195054e-06, | |
| "loss": 1.0729, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 1.0205352306365967, | |
| "learning_rate": 9.464317494216054e-06, | |
| "loss": 1.0052, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 1.416934847831726, | |
| "learning_rate": 9.428723972237054e-06, | |
| "loss": 0.9479, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 1.6272101402282715, | |
| "learning_rate": 9.393130450258053e-06, | |
| "loss": 1.0534, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 2.0268421173095703, | |
| "learning_rate": 9.357536928279053e-06, | |
| "loss": 0.9867, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 1.7837485074996948, | |
| "learning_rate": 9.321943406300055e-06, | |
| "loss": 1.0303, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 0.9231889247894287, | |
| "learning_rate": 9.286349884321054e-06, | |
| "loss": 1.0281, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 1.4698116779327393, | |
| "learning_rate": 9.250756362342054e-06, | |
| "loss": 1.0086, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 1.5415983200073242, | |
| "learning_rate": 9.215162840363055e-06, | |
| "loss": 0.968, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 2.9887442588806152, | |
| "learning_rate": 9.179569318384055e-06, | |
| "loss": 1.0502, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 0.8950912356376648, | |
| "learning_rate": 9.143975796405055e-06, | |
| "loss": 0.9871, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 1.7082128524780273, | |
| "learning_rate": 9.108382274426056e-06, | |
| "loss": 1.0669, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 1.7318546772003174, | |
| "learning_rate": 9.072788752447056e-06, | |
| "loss": 1.0341, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 1.563758373260498, | |
| "learning_rate": 9.037195230468055e-06, | |
| "loss": 0.9197, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 1.3384774923324585, | |
| "learning_rate": 9.001601708489057e-06, | |
| "loss": 1.0405, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 1.3503774404525757, | |
| "learning_rate": 8.966008186510055e-06, | |
| "loss": 0.9949, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 2.785569906234741, | |
| "learning_rate": 8.930414664531056e-06, | |
| "loss": 1.0465, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 1.2717375755310059, | |
| "learning_rate": 8.894821142552056e-06, | |
| "loss": 0.9682, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 1.6232516765594482, | |
| "learning_rate": 8.859227620573056e-06, | |
| "loss": 0.991, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 0.9230126738548279, | |
| "learning_rate": 8.823634098594057e-06, | |
| "loss": 1.0318, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_loss": 1.1669833660125732, | |
| "eval_runtime": 14.4877, | |
| "eval_samples_per_second": 6.902, | |
| "eval_steps_per_second": 1.173, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 1.075516700744629, | |
| "learning_rate": 8.788040576615057e-06, | |
| "loss": 0.9927, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 2.448676586151123, | |
| "learning_rate": 8.752447054636057e-06, | |
| "loss": 0.9613, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 1.9621632099151611, | |
| "learning_rate": 8.716853532657056e-06, | |
| "loss": 0.9791, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 1.549564003944397, | |
| "learning_rate": 8.681260010678058e-06, | |
| "loss": 0.9625, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 1.1136493682861328, | |
| "learning_rate": 8.645666488699057e-06, | |
| "loss": 1.0116, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 1.2811715602874756, | |
| "learning_rate": 8.610072966720057e-06, | |
| "loss": 0.9325, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 1.7887396812438965, | |
| "learning_rate": 8.574479444741057e-06, | |
| "loss": 1.0223, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 1.7710087299346924, | |
| "learning_rate": 8.538885922762058e-06, | |
| "loss": 0.9543, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 1.246333122253418, | |
| "learning_rate": 8.503292400783058e-06, | |
| "loss": 1.0441, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 1.6336215734481812, | |
| "learning_rate": 8.467698878804059e-06, | |
| "loss": 1.0195, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.9342829585075378, | |
| "learning_rate": 8.432105356825059e-06, | |
| "loss": 0.9669, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 1.7016915082931519, | |
| "learning_rate": 8.396511834846058e-06, | |
| "loss": 1.0536, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 1.6587010622024536, | |
| "learning_rate": 8.36091831286706e-06, | |
| "loss": 1.027, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 2.1545305252075195, | |
| "learning_rate": 8.32888414308596e-06, | |
| "loss": 1.085, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 1.4667984247207642, | |
| "learning_rate": 8.29329062110696e-06, | |
| "loss": 0.9357, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 1.3683239221572876, | |
| "learning_rate": 8.25769709912796e-06, | |
| "loss": 1.0305, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 1.442145586013794, | |
| "learning_rate": 8.22210357714896e-06, | |
| "loss": 0.9828, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.9183376431465149, | |
| "learning_rate": 8.186510055169959e-06, | |
| "loss": 0.9694, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 2.5838961601257324, | |
| "learning_rate": 8.150916533190961e-06, | |
| "loss": 1.0816, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 3.1676299571990967, | |
| "learning_rate": 8.11532301121196e-06, | |
| "loss": 1.0709, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 1.1651499271392822, | |
| "eval_runtime": 14.7555, | |
| "eval_samples_per_second": 6.777, | |
| "eval_steps_per_second": 1.152, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 1.3480502367019653, | |
| "learning_rate": 8.07972948923296e-06, | |
| "loss": 1.0395, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 1.970110535621643, | |
| "learning_rate": 8.04413596725396e-06, | |
| "loss": 1.0403, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 1.939119815826416, | |
| "learning_rate": 8.00854244527496e-06, | |
| "loss": 1.0462, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 1.0092109441757202, | |
| "learning_rate": 7.972948923295961e-06, | |
| "loss": 0.945, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 1.2960870265960693, | |
| "learning_rate": 7.937355401316961e-06, | |
| "loss": 1.0166, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 1.6596951484680176, | |
| "learning_rate": 7.901761879337962e-06, | |
| "loss": 1.0435, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 1.5653300285339355, | |
| "learning_rate": 7.86616835735896e-06, | |
| "loss": 0.9338, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 1.1446584463119507, | |
| "learning_rate": 7.830574835379962e-06, | |
| "loss": 0.9931, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 1.4240318536758423, | |
| "learning_rate": 7.794981313400963e-06, | |
| "loss": 1.0212, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 1.9296810626983643, | |
| "learning_rate": 7.759387791421961e-06, | |
| "loss": 0.9796, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 13.544081687927246, | |
| "learning_rate": 7.723794269442962e-06, | |
| "loss": 1.0302, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 1.1591352224349976, | |
| "learning_rate": 7.688200747463962e-06, | |
| "loss": 1.0298, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 3.9198384284973145, | |
| "learning_rate": 7.652607225484962e-06, | |
| "loss": 0.9812, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 0.8258339166641235, | |
| "learning_rate": 7.617013703505962e-06, | |
| "loss": 0.9859, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 1.6080282926559448, | |
| "learning_rate": 7.581420181526963e-06, | |
| "loss": 1.0145, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 1.2886918783187866, | |
| "learning_rate": 7.545826659547963e-06, | |
| "loss": 1.02, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 1.2763543128967285, | |
| "learning_rate": 7.510233137568963e-06, | |
| "loss": 0.9468, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 1.6748079061508179, | |
| "learning_rate": 7.474639615589963e-06, | |
| "loss": 0.9984, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 1.4993281364440918, | |
| "learning_rate": 7.439046093610963e-06, | |
| "loss": 1.0399, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 2.088698387145996, | |
| "learning_rate": 7.403452571631964e-06, | |
| "loss": 0.9605, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_loss": 1.162919521331787, | |
| "eval_runtime": 13.377, | |
| "eval_samples_per_second": 7.476, | |
| "eval_steps_per_second": 1.271, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 1.106220006942749, | |
| "learning_rate": 7.3678590496529635e-06, | |
| "loss": 1.0742, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 1.3157674074172974, | |
| "learning_rate": 7.332265527673964e-06, | |
| "loss": 1.0554, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 1.8124706745147705, | |
| "learning_rate": 7.296672005694963e-06, | |
| "loss": 1.0263, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 1.8762173652648926, | |
| "learning_rate": 7.2610784837159646e-06, | |
| "loss": 1.0804, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 1.3837264776229858, | |
| "learning_rate": 7.225484961736965e-06, | |
| "loss": 1.0903, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 1.9930856227874756, | |
| "learning_rate": 7.189891439757964e-06, | |
| "loss": 0.9999, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 1.039360761642456, | |
| "learning_rate": 7.154297917778965e-06, | |
| "loss": 0.9495, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 1.507487416267395, | |
| "learning_rate": 7.118704395799964e-06, | |
| "loss": 0.9733, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 2.35772442817688, | |
| "learning_rate": 7.0831108738209655e-06, | |
| "loss": 0.993, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.9598217010498047, | |
| "learning_rate": 7.047517351841965e-06, | |
| "loss": 1.0205, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 1.6586556434631348, | |
| "learning_rate": 7.011923829862965e-06, | |
| "loss": 1.0024, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 0.7763048410415649, | |
| "learning_rate": 6.9763303078839665e-06, | |
| "loss": 1.0401, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 1.7073131799697876, | |
| "learning_rate": 6.940736785904966e-06, | |
| "loss": 1.0223, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 1.3588405847549438, | |
| "learning_rate": 6.905143263925966e-06, | |
| "loss": 0.9046, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 1.4482187032699585, | |
| "learning_rate": 6.869549741946966e-06, | |
| "loss": 0.998, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "grad_norm": 1.2404558658599854, | |
| "learning_rate": 6.833956219967966e-06, | |
| "loss": 1.0567, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "grad_norm": 1.2091312408447266, | |
| "learning_rate": 6.798362697988966e-06, | |
| "loss": 0.9242, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.8551199436187744, | |
| "learning_rate": 6.762769176009967e-06, | |
| "loss": 1.0697, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.5485138893127441, | |
| "learning_rate": 6.727175654030967e-06, | |
| "loss": 1.0074, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "grad_norm": 1.3497625589370728, | |
| "learning_rate": 6.691582132051967e-06, | |
| "loss": 1.0102, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_loss": 1.1609885692596436, | |
| "eval_runtime": 13.6368, | |
| "eval_samples_per_second": 7.333, | |
| "eval_steps_per_second": 1.247, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "grad_norm": 1.1230766773223877, | |
| "learning_rate": 6.655988610072968e-06, | |
| "loss": 1.0483, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 2.081467866897583, | |
| "learning_rate": 6.6203950880939674e-06, | |
| "loss": 0.9596, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 0.8617948293685913, | |
| "learning_rate": 6.584801566114968e-06, | |
| "loss": 0.94, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "grad_norm": 1.836197018623352, | |
| "learning_rate": 6.549208044135967e-06, | |
| "loss": 0.9454, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "grad_norm": 2.8985273838043213, | |
| "learning_rate": 6.513614522156968e-06, | |
| "loss": 1.0424, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "grad_norm": 1.3102891445159912, | |
| "learning_rate": 6.478021000177969e-06, | |
| "loss": 0.9523, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "grad_norm": 0.842078685760498, | |
| "learning_rate": 6.442427478198968e-06, | |
| "loss": 0.9469, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "grad_norm": 1.4160736799240112, | |
| "learning_rate": 6.406833956219969e-06, | |
| "loss": 0.9739, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "grad_norm": 1.9377883672714233, | |
| "learning_rate": 6.371240434240968e-06, | |
| "loss": 1.0697, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "grad_norm": 2.061891555786133, | |
| "learning_rate": 6.335646912261969e-06, | |
| "loss": 0.9722, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "grad_norm": 1.2579915523529053, | |
| "learning_rate": 6.300053390282969e-06, | |
| "loss": 1.0028, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "grad_norm": 1.0546413660049438, | |
| "learning_rate": 6.264459868303969e-06, | |
| "loss": 1.0934, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 1.1178855895996094, | |
| "learning_rate": 6.2288663463249696e-06, | |
| "loss": 0.954, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 1.8618718385696411, | |
| "learning_rate": 6.193272824345969e-06, | |
| "loss": 0.9866, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "grad_norm": 2.457610607147217, | |
| "learning_rate": 6.15767930236697e-06, | |
| "loss": 0.9913, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "grad_norm": 2.2423577308654785, | |
| "learning_rate": 6.12208578038797e-06, | |
| "loss": 0.9979, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 1.3875080347061157, | |
| "learning_rate": 6.08649225840897e-06, | |
| "loss": 0.9362, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 1.4954562187194824, | |
| "learning_rate": 6.05089873642997e-06, | |
| "loss": 1.0557, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "grad_norm": 1.3206604719161987, | |
| "learning_rate": 6.015305214450971e-06, | |
| "loss": 1.03, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "grad_norm": 1.724668025970459, | |
| "learning_rate": 5.979711692471971e-06, | |
| "loss": 1.0514, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_loss": 1.161750316619873, | |
| "eval_runtime": 13.4773, | |
| "eval_samples_per_second": 7.42, | |
| "eval_steps_per_second": 1.261, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "grad_norm": 1.0254956483840942, | |
| "learning_rate": 5.944118170492971e-06, | |
| "loss": 1.0042, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "grad_norm": 1.6368863582611084, | |
| "learning_rate": 5.908524648513971e-06, | |
| "loss": 0.8746, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "grad_norm": 1.2903077602386475, | |
| "learning_rate": 5.8729311265349705e-06, | |
| "loss": 0.9594, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "grad_norm": 1.9890704154968262, | |
| "learning_rate": 5.837337604555972e-06, | |
| "loss": 1.0567, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "grad_norm": 1.1513025760650635, | |
| "learning_rate": 5.801744082576971e-06, | |
| "loss": 0.9188, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "grad_norm": 2.7853498458862305, | |
| "learning_rate": 5.7661505605979716e-06, | |
| "loss": 0.9767, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "grad_norm": 1.0868607759475708, | |
| "learning_rate": 5.730557038618971e-06, | |
| "loss": 0.9702, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 1.431562900543213, | |
| "learning_rate": 5.694963516639972e-06, | |
| "loss": 0.9558, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 1.6991177797317505, | |
| "learning_rate": 5.659369994660973e-06, | |
| "loss": 0.9392, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "grad_norm": 2.4089505672454834, | |
| "learning_rate": 5.623776472681972e-06, | |
| "loss": 1.0216, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "grad_norm": 2.0749993324279785, | |
| "learning_rate": 5.5881829507029725e-06, | |
| "loss": 0.9553, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "grad_norm": 2.4475717544555664, | |
| "learning_rate": 5.552589428723972e-06, | |
| "loss": 1.0029, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "grad_norm": 1.7227658033370972, | |
| "learning_rate": 5.516995906744973e-06, | |
| "loss": 1.0064, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "grad_norm": 0.9725387096405029, | |
| "learning_rate": 5.481402384765973e-06, | |
| "loss": 1.0266, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "grad_norm": 1.44870126247406, | |
| "learning_rate": 5.445808862786973e-06, | |
| "loss": 1.0485, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 1.3988876342773438, | |
| "learning_rate": 5.410215340807974e-06, | |
| "loss": 0.9349, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 1.7776734828948975, | |
| "learning_rate": 5.374621818828974e-06, | |
| "loss": 0.9242, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "grad_norm": 2.8275084495544434, | |
| "learning_rate": 5.339028296849974e-06, | |
| "loss": 0.9266, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "grad_norm": 1.22096848487854, | |
| "learning_rate": 5.3034347748709735e-06, | |
| "loss": 1.0717, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "grad_norm": 2.101590633392334, | |
| "learning_rate": 5.267841252891974e-06, | |
| "loss": 0.9854, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 1.1640130281448364, | |
| "eval_runtime": 13.1977, | |
| "eval_samples_per_second": 7.577, | |
| "eval_steps_per_second": 1.288, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "grad_norm": 1.4337748289108276, | |
| "learning_rate": 5.232247730912973e-06, | |
| "loss": 1.0291, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "grad_norm": 1.1524966955184937, | |
| "learning_rate": 5.196654208933975e-06, | |
| "loss": 0.919, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 1.1609076261520386, | |
| "learning_rate": 5.161060686954975e-06, | |
| "loss": 0.9831, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 1.6320583820343018, | |
| "learning_rate": 5.1254671649759744e-06, | |
| "loss": 0.9761, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 1.5667961835861206, | |
| "learning_rate": 5.089873642996976e-06, | |
| "loss": 0.9194, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 1.1753573417663574, | |
| "learning_rate": 5.054280121017975e-06, | |
| "loss": 0.935, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "grad_norm": 1.4314757585525513, | |
| "learning_rate": 5.0186865990389755e-06, | |
| "loss": 0.9999, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "grad_norm": 1.4544209241867065, | |
| "learning_rate": 4.983093077059976e-06, | |
| "loss": 0.8888, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "grad_norm": 1.1437524557113647, | |
| "learning_rate": 4.947499555080975e-06, | |
| "loss": 0.9426, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "grad_norm": 1.463649868965149, | |
| "learning_rate": 4.911906033101976e-06, | |
| "loss": 1.0143, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "grad_norm": 1.1386024951934814, | |
| "learning_rate": 4.876312511122976e-06, | |
| "loss": 0.9169, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "grad_norm": 1.9671331644058228, | |
| "learning_rate": 4.840718989143976e-06, | |
| "loss": 0.95, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "grad_norm": 1.2009460926055908, | |
| "learning_rate": 4.805125467164977e-06, | |
| "loss": 0.94, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "grad_norm": 1.27320396900177, | |
| "learning_rate": 4.769531945185977e-06, | |
| "loss": 1.0101, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "grad_norm": 1.4841572046279907, | |
| "learning_rate": 4.7339384232069766e-06, | |
| "loss": 0.9558, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "grad_norm": 1.7961384057998657, | |
| "learning_rate": 4.698344901227977e-06, | |
| "loss": 0.9712, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "grad_norm": 2.371077537536621, | |
| "learning_rate": 4.662751379248977e-06, | |
| "loss": 1.0331, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "grad_norm": 2.2065269947052, | |
| "learning_rate": 4.627157857269977e-06, | |
| "loss": 0.9936, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "grad_norm": 3.1182281970977783, | |
| "learning_rate": 4.591564335290977e-06, | |
| "loss": 0.9885, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "grad_norm": 1.7887283563613892, | |
| "learning_rate": 4.5559708133119775e-06, | |
| "loss": 1.0582, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_loss": 1.1613891124725342, | |
| "eval_runtime": 11.9447, | |
| "eval_samples_per_second": 8.372, | |
| "eval_steps_per_second": 1.423, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "grad_norm": 2.338524341583252, | |
| "learning_rate": 4.520377291332978e-06, | |
| "loss": 0.9832, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "grad_norm": 1.2669458389282227, | |
| "learning_rate": 4.484783769353978e-06, | |
| "loss": 1.0049, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "grad_norm": 1.7712314128875732, | |
| "learning_rate": 4.4491902473749785e-06, | |
| "loss": 0.9604, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "grad_norm": 1.566402792930603, | |
| "learning_rate": 4.413596725395978e-06, | |
| "loss": 0.9524, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "grad_norm": 1.5929316282272339, | |
| "learning_rate": 4.378003203416978e-06, | |
| "loss": 0.9041, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "grad_norm": 1.3010576963424683, | |
| "learning_rate": 4.342409681437979e-06, | |
| "loss": 0.9712, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "grad_norm": 0.9732819199562073, | |
| "learning_rate": 4.306816159458978e-06, | |
| "loss": 1.0099, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "grad_norm": 1.4127236604690552, | |
| "learning_rate": 4.271222637479979e-06, | |
| "loss": 0.922, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "grad_norm": 1.22177255153656, | |
| "learning_rate": 4.235629115500979e-06, | |
| "loss": 0.9695, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "grad_norm": 1.7447412014007568, | |
| "learning_rate": 4.200035593521979e-06, | |
| "loss": 0.9961, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "grad_norm": 2.136455535888672, | |
| "learning_rate": 4.16444207154298e-06, | |
| "loss": 0.888, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "grad_norm": 1.90965735912323, | |
| "learning_rate": 4.12884854956398e-06, | |
| "loss": 1.018, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "grad_norm": 2.555187702178955, | |
| "learning_rate": 4.0932550275849794e-06, | |
| "loss": 0.9774, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 1.4400557279586792, | |
| "learning_rate": 4.05766150560598e-06, | |
| "loss": 0.9672, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 1.466086506843567, | |
| "learning_rate": 4.02206798362698e-06, | |
| "loss": 0.9483, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "grad_norm": 2.2688674926757812, | |
| "learning_rate": 3.9864744616479805e-06, | |
| "loss": 1.0634, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "grad_norm": 0.8676767349243164, | |
| "learning_rate": 3.950880939668981e-06, | |
| "loss": 1.0066, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "grad_norm": 1.6627092361450195, | |
| "learning_rate": 3.915287417689981e-06, | |
| "loss": 0.9845, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "grad_norm": 1.3078960180282593, | |
| "learning_rate": 3.879693895710981e-06, | |
| "loss": 0.983, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "grad_norm": 1.4487115144729614, | |
| "learning_rate": 3.844100373731981e-06, | |
| "loss": 1.0135, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_loss": 1.15835702419281, | |
| "eval_runtime": 13.5659, | |
| "eval_samples_per_second": 7.371, | |
| "eval_steps_per_second": 1.253, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "grad_norm": 0.8685252070426941, | |
| "learning_rate": 3.808506851752981e-06, | |
| "loss": 0.9408, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "grad_norm": 1.8986152410507202, | |
| "learning_rate": 3.7729133297739813e-06, | |
| "loss": 0.968, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "grad_norm": 1.0574278831481934, | |
| "learning_rate": 3.7373198077949817e-06, | |
| "loss": 0.9682, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "grad_norm": 2.0325381755828857, | |
| "learning_rate": 3.701726285815982e-06, | |
| "loss": 0.9812, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "grad_norm": 1.9169801473617554, | |
| "learning_rate": 3.666132763836982e-06, | |
| "loss": 1.012, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "grad_norm": 1.4800165891647339, | |
| "learning_rate": 3.6305392418579823e-06, | |
| "loss": 1.0304, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "grad_norm": 3.802342414855957, | |
| "learning_rate": 3.594945719878982e-06, | |
| "loss": 1.0096, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "grad_norm": 2.613722324371338, | |
| "learning_rate": 3.559352197899982e-06, | |
| "loss": 1.045, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "grad_norm": 1.7029653787612915, | |
| "learning_rate": 3.5237586759209825e-06, | |
| "loss": 0.9554, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "grad_norm": 1.325801134109497, | |
| "learning_rate": 3.4881651539419832e-06, | |
| "loss": 1.0085, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "grad_norm": 1.2473498582839966, | |
| "learning_rate": 3.452571631962983e-06, | |
| "loss": 0.9567, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "grad_norm": 2.2527365684509277, | |
| "learning_rate": 3.416978109983983e-06, | |
| "loss": 0.9985, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 1.9998990297317505, | |
| "learning_rate": 3.3813845880049834e-06, | |
| "loss": 1.0336, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "grad_norm": 1.9317282438278198, | |
| "learning_rate": 3.3457910660259834e-06, | |
| "loss": 0.9559, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "grad_norm": 4.795856475830078, | |
| "learning_rate": 3.3101975440469837e-06, | |
| "loss": 1.0393, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "grad_norm": 1.1122263669967651, | |
| "learning_rate": 3.2746040220679836e-06, | |
| "loss": 0.951, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "grad_norm": 2.3446075916290283, | |
| "learning_rate": 3.2390105000889844e-06, | |
| "loss": 0.9974, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "grad_norm": 2.7562146186828613, | |
| "learning_rate": 3.2034169781099843e-06, | |
| "loss": 0.9916, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "grad_norm": 1.4365904331207275, | |
| "learning_rate": 3.1678234561309847e-06, | |
| "loss": 1.0309, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "grad_norm": 1.3124241828918457, | |
| "learning_rate": 3.1322299341519846e-06, | |
| "loss": 1.0013, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 1.16012442111969, | |
| "eval_runtime": 13.7896, | |
| "eval_samples_per_second": 7.252, | |
| "eval_steps_per_second": 1.233, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "grad_norm": 1.3323286771774292, | |
| "learning_rate": 3.0966364121729845e-06, | |
| "loss": 0.971, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "grad_norm": 1.2511714696884155, | |
| "learning_rate": 3.061042890193985e-06, | |
| "loss": 1.0844, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "grad_norm": 2.229656219482422, | |
| "learning_rate": 3.025449368214985e-06, | |
| "loss": 1.0072, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 2.332063674926758, | |
| "learning_rate": 2.9898558462359856e-06, | |
| "loss": 1.0607, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 1.929748773574829, | |
| "learning_rate": 2.9542623242569855e-06, | |
| "loss": 1.0062, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "grad_norm": 1.4503644704818726, | |
| "learning_rate": 2.918668802277986e-06, | |
| "loss": 1.0506, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "grad_norm": 2.660996675491333, | |
| "learning_rate": 2.8830752802989858e-06, | |
| "loss": 1.0435, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "grad_norm": 0.9322425723075867, | |
| "learning_rate": 2.847481758319986e-06, | |
| "loss": 1.0058, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "grad_norm": 4.1567559242248535, | |
| "learning_rate": 2.811888236340986e-06, | |
| "loss": 0.958, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "grad_norm": 1.2448021173477173, | |
| "learning_rate": 2.776294714361986e-06, | |
| "loss": 0.9408, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "grad_norm": 1.7736376523971558, | |
| "learning_rate": 2.7407011923829863e-06, | |
| "loss": 1.015, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "grad_norm": 1.5714516639709473, | |
| "learning_rate": 2.708667022601887e-06, | |
| "loss": 1.0656, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "grad_norm": 1.4286383390426636, | |
| "learning_rate": 2.673073500622887e-06, | |
| "loss": 0.9776, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "grad_norm": 1.5273995399475098, | |
| "learning_rate": 2.637479978643887e-06, | |
| "loss": 1.0234, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "grad_norm": 1.81285560131073, | |
| "learning_rate": 2.601886456664887e-06, | |
| "loss": 0.9473, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "grad_norm": 2.331578016281128, | |
| "learning_rate": 2.5662929346858874e-06, | |
| "loss": 0.9876, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "grad_norm": 1.8531678915023804, | |
| "learning_rate": 2.5306994127068873e-06, | |
| "loss": 0.9827, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "grad_norm": 1.585017204284668, | |
| "learning_rate": 2.4951058907278876e-06, | |
| "loss": 1.0027, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 2.8233871459960938, | |
| "learning_rate": 2.459512368748888e-06, | |
| "loss": 0.8794, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 1.7453246116638184, | |
| "learning_rate": 2.4239188467698883e-06, | |
| "loss": 1.0395, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_loss": 1.1599169969558716, | |
| "eval_runtime": 12.4272, | |
| "eval_samples_per_second": 8.047, | |
| "eval_steps_per_second": 1.368, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "grad_norm": 2.2966630458831787, | |
| "learning_rate": 2.3883253247908882e-06, | |
| "loss": 0.9596, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "grad_norm": 0.7523658871650696, | |
| "learning_rate": 2.3527318028118886e-06, | |
| "loss": 0.9644, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "grad_norm": 1.4369229078292847, | |
| "learning_rate": 2.3171382808328885e-06, | |
| "loss": 0.945, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "grad_norm": 1.8070347309112549, | |
| "learning_rate": 2.281544758853889e-06, | |
| "loss": 0.9897, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "grad_norm": 2.5753636360168457, | |
| "learning_rate": 2.245951236874889e-06, | |
| "loss": 1.0562, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "grad_norm": 1.2860183715820312, | |
| "learning_rate": 2.210357714895889e-06, | |
| "loss": 0.9963, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "grad_norm": 1.8132985830307007, | |
| "learning_rate": 2.174764192916889e-06, | |
| "loss": 0.9935, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "grad_norm": 1.8976044654846191, | |
| "learning_rate": 2.1391706709378894e-06, | |
| "loss": 0.9989, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "grad_norm": 1.7451097965240479, | |
| "learning_rate": 2.1035771489588898e-06, | |
| "loss": 1.0119, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "grad_norm": 2.4621028900146484, | |
| "learning_rate": 2.0679836269798897e-06, | |
| "loss": 1.004, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "grad_norm": 1.7527494430541992, | |
| "learning_rate": 2.03239010500089e-06, | |
| "loss": 0.989, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "grad_norm": 1.0558561086654663, | |
| "learning_rate": 1.9967965830218904e-06, | |
| "loss": 1.1025, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "grad_norm": 2.148247003555298, | |
| "learning_rate": 1.9612030610428903e-06, | |
| "loss": 0.9396, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "grad_norm": 10.502469062805176, | |
| "learning_rate": 1.9256095390638902e-06, | |
| "loss": 0.9003, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "grad_norm": 0.9534296989440918, | |
| "learning_rate": 1.8900160170848908e-06, | |
| "loss": 0.987, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "grad_norm": 3.3257527351379395, | |
| "learning_rate": 1.854422495105891e-06, | |
| "loss": 0.9776, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "grad_norm": 1.3868440389633179, | |
| "learning_rate": 1.818828973126891e-06, | |
| "loss": 1.014, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "grad_norm": 1.3265607357025146, | |
| "learning_rate": 1.7832354511478912e-06, | |
| "loss": 1.0634, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "grad_norm": 1.5899776220321655, | |
| "learning_rate": 1.7476419291688915e-06, | |
| "loss": 0.9643, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "grad_norm": 1.557444453239441, | |
| "learning_rate": 1.7120484071898915e-06, | |
| "loss": 1.0392, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "eval_loss": 1.156779408454895, | |
| "eval_runtime": 14.8405, | |
| "eval_samples_per_second": 6.738, | |
| "eval_steps_per_second": 1.146, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "grad_norm": 1.55242919921875, | |
| "learning_rate": 1.6764548852108916e-06, | |
| "loss": 1.0324, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "grad_norm": 1.481826901435852, | |
| "learning_rate": 1.640861363231892e-06, | |
| "loss": 0.9135, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "grad_norm": 2.6127266883850098, | |
| "learning_rate": 1.605267841252892e-06, | |
| "loss": 0.9412, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "grad_norm": 2.1064672470092773, | |
| "learning_rate": 1.5696743192738922e-06, | |
| "loss": 0.9689, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "grad_norm": 2.2469394207000732, | |
| "learning_rate": 1.5340807972948924e-06, | |
| "loss": 1.007, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "grad_norm": 0.9521136283874512, | |
| "learning_rate": 1.4984872753158927e-06, | |
| "loss": 0.9976, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "grad_norm": 1.5350151062011719, | |
| "learning_rate": 1.4628937533368929e-06, | |
| "loss": 1.0005, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "grad_norm": 1.3114089965820312, | |
| "learning_rate": 1.427300231357893e-06, | |
| "loss": 0.9421, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 0.9704638719558716, | |
| "learning_rate": 1.3917067093788931e-06, | |
| "loss": 1.0226, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 1.6371724605560303, | |
| "learning_rate": 1.3561131873998935e-06, | |
| "loss": 0.9881, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "grad_norm": 3.217449188232422, | |
| "learning_rate": 1.3205196654208934e-06, | |
| "loss": 1.021, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "grad_norm": 2.0828139781951904, | |
| "learning_rate": 1.2849261434418935e-06, | |
| "loss": 1.0501, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "grad_norm": 1.8479018211364746, | |
| "learning_rate": 1.2493326214628939e-06, | |
| "loss": 1.0131, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "grad_norm": 1.9492244720458984, | |
| "learning_rate": 1.213739099483894e-06, | |
| "loss": 0.9778, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "grad_norm": 2.842820167541504, | |
| "learning_rate": 1.1781455775048942e-06, | |
| "loss": 1.0111, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "grad_norm": 1.3288770914077759, | |
| "learning_rate": 1.1425520555258945e-06, | |
| "loss": 0.9857, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "grad_norm": 2.700355291366577, | |
| "learning_rate": 1.1069585335468944e-06, | |
| "loss": 1.0172, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "grad_norm": 2.112562417984009, | |
| "learning_rate": 1.0713650115678948e-06, | |
| "loss": 1.054, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "grad_norm": 1.465253233909607, | |
| "learning_rate": 1.035771489588895e-06, | |
| "loss": 0.9786, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "grad_norm": 2.0991272926330566, | |
| "learning_rate": 1.000177967609895e-06, | |
| "loss": 0.8889, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "eval_loss": 1.1569619178771973, | |
| "eval_runtime": 14.2065, | |
| "eval_samples_per_second": 7.039, | |
| "eval_steps_per_second": 1.197, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "grad_norm": 1.3020269870758057, | |
| "learning_rate": 9.645844456308954e-07, | |
| "loss": 1.0231, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "grad_norm": 1.6459860801696777, | |
| "learning_rate": 9.289909236518954e-07, | |
| "loss": 0.9698, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "grad_norm": 1.1114197969436646, | |
| "learning_rate": 8.933974016728957e-07, | |
| "loss": 0.9582, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 2.048380136489868, | |
| "learning_rate": 8.578038796938958e-07, | |
| "loss": 0.9718, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 1.1526697874069214, | |
| "learning_rate": 8.222103577148959e-07, | |
| "loss": 0.9839, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "grad_norm": 2.1239702701568604, | |
| "learning_rate": 7.866168357358961e-07, | |
| "loss": 1.0422, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "grad_norm": 1.2227742671966553, | |
| "learning_rate": 7.510233137568963e-07, | |
| "loss": 0.9376, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "grad_norm": 1.4168696403503418, | |
| "learning_rate": 7.154297917778965e-07, | |
| "loss": 0.9721, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "grad_norm": 2.351637601852417, | |
| "learning_rate": 6.798362697988967e-07, | |
| "loss": 0.954, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "grad_norm": 5.140621185302734, | |
| "learning_rate": 6.442427478198967e-07, | |
| "loss": 0.9834, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "grad_norm": 1.1832178831100464, | |
| "learning_rate": 6.08649225840897e-07, | |
| "loss": 1.0458, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "grad_norm": 1.1384241580963135, | |
| "learning_rate": 5.730557038618972e-07, | |
| "loss": 0.9409, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "grad_norm": 1.3158063888549805, | |
| "learning_rate": 5.374621818828973e-07, | |
| "loss": 1.0056, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "grad_norm": 4.167950630187988, | |
| "learning_rate": 5.018686599038975e-07, | |
| "loss": 0.9683, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "grad_norm": 1.7835837602615356, | |
| "learning_rate": 4.662751379248977e-07, | |
| "loss": 1.0068, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "grad_norm": 2.4926586151123047, | |
| "learning_rate": 4.306816159458979e-07, | |
| "loss": 0.9478, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "grad_norm": 1.1643342971801758, | |
| "learning_rate": 3.950880939668981e-07, | |
| "loss": 0.9561, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "grad_norm": 1.3222092390060425, | |
| "learning_rate": 3.5949457198789824e-07, | |
| "loss": 0.9847, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "grad_norm": 5.045548439025879, | |
| "learning_rate": 3.2390105000889843e-07, | |
| "loss": 0.941, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "grad_norm": 1.3581608533859253, | |
| "learning_rate": 2.8830752802989857e-07, | |
| "loss": 0.96, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_loss": 1.15603506565094, | |
| "eval_runtime": 14.4584, | |
| "eval_samples_per_second": 6.916, | |
| "eval_steps_per_second": 1.176, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "grad_norm": 2.679894208908081, | |
| "learning_rate": 2.5271400605089876e-07, | |
| "loss": 1.0037, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "grad_norm": 1.8320685625076294, | |
| "learning_rate": 2.1712048407189892e-07, | |
| "loss": 1.0009, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "grad_norm": 1.3590574264526367, | |
| "learning_rate": 1.8152696209289908e-07, | |
| "loss": 0.9628, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "grad_norm": 1.7923482656478882, | |
| "learning_rate": 1.4593344011389927e-07, | |
| "loss": 0.9196, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "grad_norm": 1.0079306364059448, | |
| "learning_rate": 1.1033991813489946e-07, | |
| "loss": 0.9957, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "grad_norm": 1.6627614498138428, | |
| "learning_rate": 7.474639615589964e-08, | |
| "loss": 0.9808, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 2.8701133728027344, | |
| "learning_rate": 3.9152874176899806e-08, | |
| "loss": 0.9034, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 5676, | |
| "total_flos": 3.0259456312449434e+18, | |
| "train_loss": 1.0295689908697037, | |
| "train_runtime": 35618.949, | |
| "train_samples_per_second": 1.912, | |
| "train_steps_per_second": 0.159 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 5676, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 3.0259456312449434e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |