| { | |
| "best_global_step": 383, | |
| "best_metric": 0.3038630783557892, | |
| "best_model_checkpoint": "./lora_qwen7b_cpp_abdiff_v1/checkpoint-383", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1149, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02611818478615736, | |
| "grad_norm": 0.272135853767395, | |
| "learning_rate": 2.347826086956522e-06, | |
| "loss": 0.747, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05223636957231472, | |
| "grad_norm": 0.2994903028011322, | |
| "learning_rate": 4.956521739130435e-06, | |
| "loss": 0.729, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07835455435847209, | |
| "grad_norm": 0.3347424566745758, | |
| "learning_rate": 7.5652173913043475e-06, | |
| "loss": 0.7694, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10447273914462944, | |
| "grad_norm": 0.24008171260356903, | |
| "learning_rate": 1.017391304347826e-05, | |
| "loss": 0.6931, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1305909239307868, | |
| "grad_norm": 0.31324484944343567, | |
| "learning_rate": 1.2782608695652173e-05, | |
| "loss": 0.6601, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15670910871694418, | |
| "grad_norm": 0.3652394115924835, | |
| "learning_rate": 1.5391304347826088e-05, | |
| "loss": 0.4995, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.18282729350310153, | |
| "grad_norm": 0.18758858740329742, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.3874, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.20894547828925888, | |
| "grad_norm": 0.11186491698026657, | |
| "learning_rate": 2.0608695652173913e-05, | |
| "loss": 0.3579, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.23506366307541626, | |
| "grad_norm": 0.0821973979473114, | |
| "learning_rate": 2.3217391304347826e-05, | |
| "loss": 0.3375, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2611818478615736, | |
| "grad_norm": 0.10780682414770126, | |
| "learning_rate": 2.582608695652174e-05, | |
| "loss": 0.3286, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.28730003264773096, | |
| "grad_norm": 0.09552709758281708, | |
| "learning_rate": 2.8434782608695652e-05, | |
| "loss": 0.3135, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.31341821743388837, | |
| "grad_norm": 0.1099899634718895, | |
| "learning_rate": 2.988394584139265e-05, | |
| "loss": 0.2828, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3395364022200457, | |
| "grad_norm": 0.08481885492801666, | |
| "learning_rate": 2.9593810444874276e-05, | |
| "loss": 0.2884, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.36565458700620307, | |
| "grad_norm": 0.0872187465429306, | |
| "learning_rate": 2.93036750483559e-05, | |
| "loss": 0.2856, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3917727717923604, | |
| "grad_norm": 0.09415256232023239, | |
| "learning_rate": 2.9013539651837528e-05, | |
| "loss": 0.2958, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.41789095657851777, | |
| "grad_norm": 0.09529490023851395, | |
| "learning_rate": 2.872340425531915e-05, | |
| "loss": 0.2832, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4440091413646752, | |
| "grad_norm": 0.12695518136024475, | |
| "learning_rate": 2.8433268858800773e-05, | |
| "loss": 0.2852, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4701273261508325, | |
| "grad_norm": 0.09822621941566467, | |
| "learning_rate": 2.81431334622824e-05, | |
| "loss": 0.2647, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4962455109369899, | |
| "grad_norm": 0.11181768029928207, | |
| "learning_rate": 2.785299806576402e-05, | |
| "loss": 0.2718, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5223636957231472, | |
| "grad_norm": 0.0999976173043251, | |
| "learning_rate": 2.7562862669245647e-05, | |
| "loss": 0.287, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5484818805093046, | |
| "grad_norm": 0.11232498288154602, | |
| "learning_rate": 2.7272727272727273e-05, | |
| "loss": 0.2657, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5746000652954619, | |
| "grad_norm": 0.09556713700294495, | |
| "learning_rate": 2.69825918762089e-05, | |
| "loss": 0.2728, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6007182500816193, | |
| "grad_norm": 0.09838665276765823, | |
| "learning_rate": 2.669245647969052e-05, | |
| "loss": 0.2679, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.6268364348677767, | |
| "grad_norm": 0.12542720139026642, | |
| "learning_rate": 2.6402321083172148e-05, | |
| "loss": 0.2717, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6529546196539341, | |
| "grad_norm": 0.12866875529289246, | |
| "learning_rate": 2.6112185686653773e-05, | |
| "loss": 0.2722, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6790728044400914, | |
| "grad_norm": 0.12063395977020264, | |
| "learning_rate": 2.5822050290135396e-05, | |
| "loss": 0.2665, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.7051909892262488, | |
| "grad_norm": 0.12060956656932831, | |
| "learning_rate": 2.5531914893617022e-05, | |
| "loss": 0.2498, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.7313091740124061, | |
| "grad_norm": 0.1269434541463852, | |
| "learning_rate": 2.5241779497098648e-05, | |
| "loss": 0.2685, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7574273587985635, | |
| "grad_norm": 0.13224200904369354, | |
| "learning_rate": 2.495164410058027e-05, | |
| "loss": 0.2562, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7835455435847208, | |
| "grad_norm": 0.12492657452821732, | |
| "learning_rate": 2.4661508704061896e-05, | |
| "loss": 0.2436, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.8096637283708782, | |
| "grad_norm": 0.19281449913978577, | |
| "learning_rate": 2.4371373307543522e-05, | |
| "loss": 0.2593, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.8357819131570355, | |
| "grad_norm": 0.13644647598266602, | |
| "learning_rate": 2.408123791102515e-05, | |
| "loss": 0.2678, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.861900097943193, | |
| "grad_norm": 0.13078241050243378, | |
| "learning_rate": 2.379110251450677e-05, | |
| "loss": 0.2586, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8880182827293504, | |
| "grad_norm": 0.16267353296279907, | |
| "learning_rate": 2.3500967117988397e-05, | |
| "loss": 0.2441, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.9141364675155077, | |
| "grad_norm": 0.14218953251838684, | |
| "learning_rate": 2.321083172147002e-05, | |
| "loss": 0.2561, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.940254652301665, | |
| "grad_norm": 0.14463242888450623, | |
| "learning_rate": 2.2920696324951642e-05, | |
| "loss": 0.2437, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.9663728370878224, | |
| "grad_norm": 0.15065905451774597, | |
| "learning_rate": 2.2630560928433268e-05, | |
| "loss": 0.2448, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.9924910218739798, | |
| "grad_norm": 0.1440647393465042, | |
| "learning_rate": 2.2340425531914894e-05, | |
| "loss": 0.2407, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.3038630783557892, | |
| "eval_runtime": 46.9955, | |
| "eval_samples_per_second": 19.534, | |
| "eval_steps_per_second": 9.767, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 1.01828272935031, | |
| "grad_norm": 0.18325522541999817, | |
| "learning_rate": 2.2050290135396516e-05, | |
| "loss": 0.2475, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.0444009141364674, | |
| "grad_norm": 0.19586290419101715, | |
| "learning_rate": 2.1760154738878142e-05, | |
| "loss": 0.2269, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.070519098922625, | |
| "grad_norm": 0.1957836151123047, | |
| "learning_rate": 2.1470019342359768e-05, | |
| "loss": 0.2383, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.0966372837087823, | |
| "grad_norm": 0.20044924318790436, | |
| "learning_rate": 2.1179883945841394e-05, | |
| "loss": 0.2277, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.1227554684949397, | |
| "grad_norm": 0.17480885982513428, | |
| "learning_rate": 2.0889748549323017e-05, | |
| "loss": 0.2364, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.148873653281097, | |
| "grad_norm": 0.22346200048923492, | |
| "learning_rate": 2.0599613152804643e-05, | |
| "loss": 0.2337, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.1749918380672544, | |
| "grad_norm": 0.18232356011867523, | |
| "learning_rate": 2.030947775628627e-05, | |
| "loss": 0.2391, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.2011100228534117, | |
| "grad_norm": 0.21770867705345154, | |
| "learning_rate": 2.001934235976789e-05, | |
| "loss": 0.2219, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.227228207639569, | |
| "grad_norm": 0.23520149290561676, | |
| "learning_rate": 1.9729206963249517e-05, | |
| "loss": 0.2204, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.2533463924257264, | |
| "grad_norm": 0.2378666251897812, | |
| "learning_rate": 1.9439071566731143e-05, | |
| "loss": 0.2185, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.2794645772118838, | |
| "grad_norm": 0.23565010726451874, | |
| "learning_rate": 1.914893617021277e-05, | |
| "loss": 0.2013, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.3055827619980411, | |
| "grad_norm": 0.2177935689687729, | |
| "learning_rate": 1.885880077369439e-05, | |
| "loss": 0.2321, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.3317009467841985, | |
| "grad_norm": 0.2423669397830963, | |
| "learning_rate": 1.8568665377176018e-05, | |
| "loss": 0.2155, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.3578191315703558, | |
| "grad_norm": 0.2234184592962265, | |
| "learning_rate": 1.8278529980657643e-05, | |
| "loss": 0.207, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.3839373163565132, | |
| "grad_norm": 0.27478086948394775, | |
| "learning_rate": 1.7988394584139263e-05, | |
| "loss": 0.202, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.4100555011426705, | |
| "grad_norm": 0.23157715797424316, | |
| "learning_rate": 1.769825918762089e-05, | |
| "loss": 0.2132, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.4361736859288279, | |
| "grad_norm": 0.2137601226568222, | |
| "learning_rate": 1.7408123791102515e-05, | |
| "loss": 0.2206, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.4622918707149852, | |
| "grad_norm": 0.25221434235572815, | |
| "learning_rate": 1.7117988394584137e-05, | |
| "loss": 0.1936, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.4884100555011428, | |
| "grad_norm": 0.265802800655365, | |
| "learning_rate": 1.6827852998065763e-05, | |
| "loss": 0.1927, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.5145282402873002, | |
| "grad_norm": 0.29695677757263184, | |
| "learning_rate": 1.653771760154739e-05, | |
| "loss": 0.1901, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.5406464250734575, | |
| "grad_norm": 0.28603777289390564, | |
| "learning_rate": 1.6247582205029015e-05, | |
| "loss": 0.1817, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.5667646098596149, | |
| "grad_norm": 0.27603891491889954, | |
| "learning_rate": 1.5957446808510637e-05, | |
| "loss": 0.1796, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.5928827946457722, | |
| "grad_norm": 0.23388804495334625, | |
| "learning_rate": 1.5667311411992263e-05, | |
| "loss": 0.2099, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.6190009794319296, | |
| "grad_norm": 0.3027153015136719, | |
| "learning_rate": 1.537717601547389e-05, | |
| "loss": 0.1874, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.645119164218087, | |
| "grad_norm": 0.23569999635219574, | |
| "learning_rate": 1.5087040618955514e-05, | |
| "loss": 0.2092, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.6712373490042443, | |
| "grad_norm": 0.28446313738822937, | |
| "learning_rate": 1.4796905222437138e-05, | |
| "loss": 0.1928, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.6973555337904016, | |
| "grad_norm": 0.33438780903816223, | |
| "learning_rate": 1.4506769825918764e-05, | |
| "loss": 0.2076, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.723473718576559, | |
| "grad_norm": 0.24610307812690735, | |
| "learning_rate": 1.4216634429400386e-05, | |
| "loss": 0.1834, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.7495919033627163, | |
| "grad_norm": 0.3221604526042938, | |
| "learning_rate": 1.392649903288201e-05, | |
| "loss": 0.1886, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.7757100881488737, | |
| "grad_norm": 0.30149781703948975, | |
| "learning_rate": 1.3636363636363637e-05, | |
| "loss": 0.1903, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.801828272935031, | |
| "grad_norm": 0.26918601989746094, | |
| "learning_rate": 1.334622823984526e-05, | |
| "loss": 0.1847, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.8279464577211884, | |
| "grad_norm": 0.36477166414260864, | |
| "learning_rate": 1.3056092843326887e-05, | |
| "loss": 0.1873, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.8540646425073457, | |
| "grad_norm": 0.2950615882873535, | |
| "learning_rate": 1.2765957446808511e-05, | |
| "loss": 0.1884, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.880182827293503, | |
| "grad_norm": 0.29690101742744446, | |
| "learning_rate": 1.2475822050290135e-05, | |
| "loss": 0.1876, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.9063010120796604, | |
| "grad_norm": 0.3099982738494873, | |
| "learning_rate": 1.2185686653771761e-05, | |
| "loss": 0.1778, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.9324191968658178, | |
| "grad_norm": 0.32279762625694275, | |
| "learning_rate": 1.1895551257253385e-05, | |
| "loss": 0.1854, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.958537381651975, | |
| "grad_norm": 0.2992270588874817, | |
| "learning_rate": 1.160541586073501e-05, | |
| "loss": 0.1747, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.9846555664381325, | |
| "grad_norm": 0.27671152353286743, | |
| "learning_rate": 1.1315280464216634e-05, | |
| "loss": 0.1624, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.31829941272735596, | |
| "eval_runtime": 46.8149, | |
| "eval_samples_per_second": 19.609, | |
| "eval_steps_per_second": 9.805, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 2.0104472739144628, | |
| "grad_norm": 0.302716463804245, | |
| "learning_rate": 1.1025145067698258e-05, | |
| "loss": 0.1923, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.03656545870062, | |
| "grad_norm": 0.2851350009441376, | |
| "learning_rate": 1.0735009671179884e-05, | |
| "loss": 0.1759, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.0626836434867775, | |
| "grad_norm": 0.3431122303009033, | |
| "learning_rate": 1.0444874274661508e-05, | |
| "loss": 0.1682, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.088801828272935, | |
| "grad_norm": 0.33571285009384155, | |
| "learning_rate": 1.0154738878143134e-05, | |
| "loss": 0.1568, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.1149200130590926, | |
| "grad_norm": 0.38898637890815735, | |
| "learning_rate": 9.864603481624759e-06, | |
| "loss": 0.1543, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.14103819784525, | |
| "grad_norm": 0.30346909165382385, | |
| "learning_rate": 9.574468085106385e-06, | |
| "loss": 0.1592, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.1671563826314073, | |
| "grad_norm": 0.33506202697753906, | |
| "learning_rate": 9.284332688588009e-06, | |
| "loss": 0.1853, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.1932745674175647, | |
| "grad_norm": 0.30120134353637695, | |
| "learning_rate": 8.994197292069631e-06, | |
| "loss": 0.1621, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.219392752203722, | |
| "grad_norm": 0.35409367084503174, | |
| "learning_rate": 8.704061895551257e-06, | |
| "loss": 0.1733, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.2455109369898794, | |
| "grad_norm": 0.4092079699039459, | |
| "learning_rate": 8.413926499032882e-06, | |
| "loss": 0.1616, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.2716291217760367, | |
| "grad_norm": 0.3036758005619049, | |
| "learning_rate": 8.123791102514507e-06, | |
| "loss": 0.1703, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.297747306562194, | |
| "grad_norm": 0.40276363492012024, | |
| "learning_rate": 7.833655705996132e-06, | |
| "loss": 0.1591, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.3238654913483514, | |
| "grad_norm": 0.3477386236190796, | |
| "learning_rate": 7.543520309477757e-06, | |
| "loss": 0.1848, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.3499836761345088, | |
| "grad_norm": 0.3512537479400635, | |
| "learning_rate": 7.253384912959382e-06, | |
| "loss": 0.1668, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.376101860920666, | |
| "grad_norm": 0.3957723081111908, | |
| "learning_rate": 6.963249516441005e-06, | |
| "loss": 0.1568, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.4022200457068235, | |
| "grad_norm": 0.36369815468788147, | |
| "learning_rate": 6.67311411992263e-06, | |
| "loss": 0.164, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.428338230492981, | |
| "grad_norm": 0.37673720717430115, | |
| "learning_rate": 6.3829787234042555e-06, | |
| "loss": 0.1635, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.454456415279138, | |
| "grad_norm": 0.42920976877212524, | |
| "learning_rate": 6.092843326885881e-06, | |
| "loss": 0.1608, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.4805746000652955, | |
| "grad_norm": 0.42978808283805847, | |
| "learning_rate": 5.802707930367505e-06, | |
| "loss": 0.1638, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.506692784851453, | |
| "grad_norm": 0.4102988839149475, | |
| "learning_rate": 5.512572533849129e-06, | |
| "loss": 0.1654, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.53281096963761, | |
| "grad_norm": 0.33200573921203613, | |
| "learning_rate": 5.222437137330754e-06, | |
| "loss": 0.1587, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.5589291544237676, | |
| "grad_norm": 0.34544673562049866, | |
| "learning_rate": 4.932301740812379e-06, | |
| "loss": 0.1422, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.585047339209925, | |
| "grad_norm": 0.3770700693130493, | |
| "learning_rate": 4.642166344294004e-06, | |
| "loss": 0.1533, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.6111655239960823, | |
| "grad_norm": 0.4285246431827545, | |
| "learning_rate": 4.352030947775629e-06, | |
| "loss": 0.1667, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.6372837087822396, | |
| "grad_norm": 0.3781305253505707, | |
| "learning_rate": 4.061895551257254e-06, | |
| "loss": 0.1545, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.663401893568397, | |
| "grad_norm": 0.41318264603614807, | |
| "learning_rate": 3.7717601547388784e-06, | |
| "loss": 0.1679, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.6895200783545543, | |
| "grad_norm": 0.40817004442214966, | |
| "learning_rate": 3.4816247582205027e-06, | |
| "loss": 0.1573, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.7156382631407117, | |
| "grad_norm": 0.41028645634651184, | |
| "learning_rate": 3.1914893617021277e-06, | |
| "loss": 0.1474, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.741756447926869, | |
| "grad_norm": 0.3509976267814636, | |
| "learning_rate": 2.9013539651837524e-06, | |
| "loss": 0.1578, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.7678746327130264, | |
| "grad_norm": 0.4071323573589325, | |
| "learning_rate": 2.611218568665377e-06, | |
| "loss": 0.1496, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.7939928174991837, | |
| "grad_norm": 0.2635524570941925, | |
| "learning_rate": 2.321083172147002e-06, | |
| "loss": 0.1696, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.820111002285341, | |
| "grad_norm": 0.3947674632072449, | |
| "learning_rate": 2.030947775628627e-06, | |
| "loss": 0.1664, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.8462291870714984, | |
| "grad_norm": 0.47258490324020386, | |
| "learning_rate": 1.7408123791102513e-06, | |
| "loss": 0.1617, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.8723473718576558, | |
| "grad_norm": 0.3031919300556183, | |
| "learning_rate": 1.4506769825918762e-06, | |
| "loss": 0.1454, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.898465556643813, | |
| "grad_norm": 0.3442898988723755, | |
| "learning_rate": 1.160541586073501e-06, | |
| "loss": 0.1584, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.9245837414299705, | |
| "grad_norm": 0.46089524030685425, | |
| "learning_rate": 8.704061895551257e-07, | |
| "loss": 0.1607, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.950701926216128, | |
| "grad_norm": 0.35179299116134644, | |
| "learning_rate": 5.802707930367505e-07, | |
| "loss": 0.1668, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.9768201110022856, | |
| "grad_norm": 0.40915292501449585, | |
| "learning_rate": 2.901353965183753e-07, | |
| "loss": 0.1522, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.3278330862522125, | |
| "eval_runtime": 46.5303, | |
| "eval_samples_per_second": 19.729, | |
| "eval_steps_per_second": 9.865, | |
| "step": 1149 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1149, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1050463737748521e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |