| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 200, | |
| "global_step": 1480, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006760182524928173, | |
| "grad_norm": 15.915069580078125, | |
| "learning_rate": 6.081081081081082e-07, | |
| "loss": 1.028, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013520365049856346, | |
| "grad_norm": 7.203866004943848, | |
| "learning_rate": 1.2837837837837838e-06, | |
| "loss": 0.8412, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.020280547574784518, | |
| "grad_norm": 4.731671333312988, | |
| "learning_rate": 1.9594594594594595e-06, | |
| "loss": 0.6928, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.027040730099712692, | |
| "grad_norm": 4.059757709503174, | |
| "learning_rate": 2.6351351351351353e-06, | |
| "loss": 0.5823, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03380091262464086, | |
| "grad_norm": 3.655268430709839, | |
| "learning_rate": 3.310810810810811e-06, | |
| "loss": 0.5195, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.040561095149569036, | |
| "grad_norm": 3.749523401260376, | |
| "learning_rate": 3.986486486486487e-06, | |
| "loss": 0.4697, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04732127767449721, | |
| "grad_norm": 3.336225748062134, | |
| "learning_rate": 4.6621621621621625e-06, | |
| "loss": 0.4567, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.054081460199425384, | |
| "grad_norm": 3.8789913654327393, | |
| "learning_rate": 5.337837837837838e-06, | |
| "loss": 0.4675, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06084164272435356, | |
| "grad_norm": 3.631592035293579, | |
| "learning_rate": 6.013513513513514e-06, | |
| "loss": 0.4531, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.06760182524928172, | |
| "grad_norm": 3.175447702407837, | |
| "learning_rate": 6.689189189189191e-06, | |
| "loss": 0.4368, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0743620077742099, | |
| "grad_norm": 3.1399242877960205, | |
| "learning_rate": 7.3648648648648655e-06, | |
| "loss": 0.4185, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.08112219029913807, | |
| "grad_norm": 3.3930342197418213, | |
| "learning_rate": 8.040540540540541e-06, | |
| "loss": 0.4202, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.08788237282406625, | |
| "grad_norm": 3.535984516143799, | |
| "learning_rate": 8.716216216216217e-06, | |
| "loss": 0.4299, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.09464255534899442, | |
| "grad_norm": 3.0242111682891846, | |
| "learning_rate": 9.391891891891893e-06, | |
| "loss": 0.4134, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1014027378739226, | |
| "grad_norm": 3.216952085494995, | |
| "learning_rate": 9.999986093075303e-06, | |
| "loss": 0.4138, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.10816292039885077, | |
| "grad_norm": 2.8959848880767822, | |
| "learning_rate": 9.998317355716393e-06, | |
| "loss": 0.4063, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.11492310292377894, | |
| "grad_norm": 2.8924849033355713, | |
| "learning_rate": 9.993868297034709e-06, | |
| "loss": 0.4265, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.12168328544870712, | |
| "grad_norm": 3.100831985473633, | |
| "learning_rate": 9.986641391825633e-06, | |
| "loss": 0.4437, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.1284434679736353, | |
| "grad_norm": 2.6609292030334473, | |
| "learning_rate": 9.976640660065733e-06, | |
| "loss": 0.3854, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.13520365049856345, | |
| "grad_norm": 2.6647753715515137, | |
| "learning_rate": 9.963871664676647e-06, | |
| "loss": 0.3906, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13520365049856345, | |
| "eval_loss": 0.4129255712032318, | |
| "eval_runtime": 1274.8086, | |
| "eval_samples_per_second": 4.126, | |
| "eval_steps_per_second": 0.516, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14196383302349164, | |
| "grad_norm": 2.908745765686035, | |
| "learning_rate": 9.948341508430691e-06, | |
| "loss": 0.416, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.1487240155484198, | |
| "grad_norm": 2.6044161319732666, | |
| "learning_rate": 9.93005882999994e-06, | |
| "loss": 0.4055, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.15548419807334798, | |
| "grad_norm": 2.6734066009521484, | |
| "learning_rate": 9.909033799150947e-06, | |
| "loss": 0.4093, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.16224438059827614, | |
| "grad_norm": 2.681687116622925, | |
| "learning_rate": 9.885278111087803e-06, | |
| "loss": 0.4183, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.16900456312320433, | |
| "grad_norm": 2.633845806121826, | |
| "learning_rate": 9.85880497994666e-06, | |
| "loss": 0.3845, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.1757647456481325, | |
| "grad_norm": 2.317528486251831, | |
| "learning_rate": 9.829629131445342e-06, | |
| "loss": 0.3886, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.18252492817306068, | |
| "grad_norm": 2.4552831649780273, | |
| "learning_rate": 9.797766794692156e-06, | |
| "loss": 0.4016, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.18928511069798884, | |
| "grad_norm": 2.5544655323028564, | |
| "learning_rate": 9.76323569315841e-06, | |
| "loss": 0.3855, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.19604529322291703, | |
| "grad_norm": 2.6713716983795166, | |
| "learning_rate": 9.726055034819726e-06, | |
| "loss": 0.3987, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.2028054757478452, | |
| "grad_norm": 2.450104236602783, | |
| "learning_rate": 9.686245501471555e-06, | |
| "loss": 0.3903, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.20956565827277338, | |
| "grad_norm": 2.417210340499878, | |
| "learning_rate": 9.64382923722492e-06, | |
| "loss": 0.4012, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.21632584079770154, | |
| "grad_norm": 2.1763546466827393, | |
| "learning_rate": 9.598829836188694e-06, | |
| "loss": 0.3823, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.22308602332262972, | |
| "grad_norm": 2.173384428024292, | |
| "learning_rate": 9.551272329345373e-06, | |
| "loss": 0.3722, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.22984620584755788, | |
| "grad_norm": 2.3560631275177, | |
| "learning_rate": 9.501183170627535e-06, | |
| "loss": 0.3863, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.23660638837248607, | |
| "grad_norm": 2.427529811859131, | |
| "learning_rate": 9.448590222202808e-06, | |
| "loss": 0.3713, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.24336657089741423, | |
| "grad_norm": 2.119920492172241, | |
| "learning_rate": 9.393522738975497e-06, | |
| "loss": 0.3817, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.2501267534223424, | |
| "grad_norm": 2.0783591270446777, | |
| "learning_rate": 9.336011352313502e-06, | |
| "loss": 0.3826, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.2568869359472706, | |
| "grad_norm": 2.054614543914795, | |
| "learning_rate": 9.276088053009578e-06, | |
| "loss": 0.3629, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.26364711847219874, | |
| "grad_norm": 2.3898072242736816, | |
| "learning_rate": 9.213786173486403e-06, | |
| "loss": 0.3887, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.2704073009971269, | |
| "grad_norm": 2.4764063358306885, | |
| "learning_rate": 9.149140369255377e-06, | |
| "loss": 0.3823, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.2704073009971269, | |
| "eval_loss": 0.3794357478618622, | |
| "eval_runtime": 1274.964, | |
| "eval_samples_per_second": 4.126, | |
| "eval_steps_per_second": 0.516, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.2771674835220551, | |
| "grad_norm": 2.2685487270355225, | |
| "learning_rate": 9.082186599639429e-06, | |
| "loss": 0.3783, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.2839276660469833, | |
| "grad_norm": 2.163623332977295, | |
| "learning_rate": 9.012962107770615e-06, | |
| "loss": 0.3824, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.29068784857191143, | |
| "grad_norm": 2.4199347496032715, | |
| "learning_rate": 8.941505399873549e-06, | |
| "loss": 0.3722, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.2974480310968396, | |
| "grad_norm": 2.7932002544403076, | |
| "learning_rate": 8.86785622384627e-06, | |
| "loss": 0.3725, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.3042082136217678, | |
| "grad_norm": 2.3451616764068604, | |
| "learning_rate": 8.792055547150413e-06, | |
| "loss": 0.368, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.31096839614669597, | |
| "grad_norm": 2.3174757957458496, | |
| "learning_rate": 8.714145534022999e-06, | |
| "loss": 0.3576, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.31772857867162413, | |
| "grad_norm": 2.2395827770233154, | |
| "learning_rate": 8.634169522022522e-06, | |
| "loss": 0.3585, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.3244887611965523, | |
| "grad_norm": 2.222054958343506, | |
| "learning_rate": 8.552171997922358e-06, | |
| "loss": 0.3495, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.3312489437214805, | |
| "grad_norm": 2.371980667114258, | |
| "learning_rate": 8.46819857296494e-06, | |
| "loss": 0.3662, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.33800912624640866, | |
| "grad_norm": 2.1474437713623047, | |
| "learning_rate": 8.382295957490435e-06, | |
| "loss": 0.3616, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3447693087713368, | |
| "grad_norm": 2.476712465286255, | |
| "learning_rate": 8.294511934954054e-06, | |
| "loss": 0.3595, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.351529491296265, | |
| "grad_norm": 2.175936698913574, | |
| "learning_rate": 8.20489533534643e-06, | |
| "loss": 0.3549, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.3582896738211932, | |
| "grad_norm": 1.8972084522247314, | |
| "learning_rate": 8.113496008031863e-06, | |
| "loss": 0.3426, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.36504985634612136, | |
| "grad_norm": 1.9858911037445068, | |
| "learning_rate": 8.020364794019546e-06, | |
| "loss": 0.351, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.3718100388710495, | |
| "grad_norm": 1.843750238418579, | |
| "learning_rate": 7.925553497683169e-06, | |
| "loss": 0.3413, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.3785702213959777, | |
| "grad_norm": 2.026078224182129, | |
| "learning_rate": 7.829114857944672e-06, | |
| "loss": 0.3589, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.38533040392090584, | |
| "grad_norm": 2.246981620788574, | |
| "learning_rate": 7.731102518938137e-06, | |
| "loss": 0.3483, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.39209058644583406, | |
| "grad_norm": 2.0345938205718994, | |
| "learning_rate": 7.631571000170156e-06, | |
| "loss": 0.356, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.3988507689707622, | |
| "grad_norm": 2.166692018508911, | |
| "learning_rate": 7.530575666193283e-06, | |
| "loss": 0.3544, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.4056109514956904, | |
| "grad_norm": 2.0450754165649414, | |
| "learning_rate": 7.4281726958094146e-06, | |
| "loss": 0.3507, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.4056109514956904, | |
| "eval_loss": 0.35060280561447144, | |
| "eval_runtime": 1270.966, | |
| "eval_samples_per_second": 4.139, | |
| "eval_steps_per_second": 0.518, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.41237113402061853, | |
| "grad_norm": 2.1229889392852783, | |
| "learning_rate": 7.32441905082026e-06, | |
| "loss": 0.3511, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.41913131654554675, | |
| "grad_norm": 1.8597893714904785, | |
| "learning_rate": 7.2193724443422405e-06, | |
| "loss": 0.3547, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.4258914990704749, | |
| "grad_norm": 1.9739303588867188, | |
| "learning_rate": 7.113091308703498e-06, | |
| "loss": 0.3313, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.43265168159540307, | |
| "grad_norm": 1.9213026762008667, | |
| "learning_rate": 7.005634762940818e-06, | |
| "loss": 0.3513, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.43941186412033123, | |
| "grad_norm": 1.9261809587478638, | |
| "learning_rate": 6.897062579914587e-06, | |
| "loss": 0.3311, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.44617204664525945, | |
| "grad_norm": 1.9443905353546143, | |
| "learning_rate": 6.787435153060039e-06, | |
| "loss": 0.3335, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.4529322291701876, | |
| "grad_norm": 2.0720746517181396, | |
| "learning_rate": 6.676813462793337e-06, | |
| "loss": 0.3339, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.45969241169511577, | |
| "grad_norm": 1.9223897457122803, | |
| "learning_rate": 6.565259042591112e-06, | |
| "loss": 0.3446, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.4664525942200439, | |
| "grad_norm": 2.407301664352417, | |
| "learning_rate": 6.452833944762385e-06, | |
| "loss": 0.3475, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.47321277674497214, | |
| "grad_norm": 1.946742057800293, | |
| "learning_rate": 6.339600705931876e-06, | |
| "loss": 0.3274, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.4799729592699003, | |
| "grad_norm": 1.9959310293197632, | |
| "learning_rate": 6.225622312253916e-06, | |
| "loss": 0.3347, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.48673314179482846, | |
| "grad_norm": 1.8777397871017456, | |
| "learning_rate": 6.110962164376309e-06, | |
| "loss": 0.3419, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.4934933243197566, | |
| "grad_norm": 2.0931403636932373, | |
| "learning_rate": 5.995684042173626e-06, | |
| "loss": 0.3344, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.5002535068446848, | |
| "grad_norm": 1.7780061960220337, | |
| "learning_rate": 5.8798520692695605e-06, | |
| "loss": 0.3115, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.507013689369613, | |
| "grad_norm": 1.8530755043029785, | |
| "learning_rate": 5.763530677368065e-06, | |
| "loss": 0.3248, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.5137738718945412, | |
| "grad_norm": 2.074946165084839, | |
| "learning_rate": 5.64678457041312e-06, | |
| "loss": 0.3381, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.5205340544194693, | |
| "grad_norm": 2.1300790309906006, | |
| "learning_rate": 5.529678688597081e-06, | |
| "loss": 0.3272, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.5272942369443975, | |
| "grad_norm": 1.9701505899429321, | |
| "learning_rate": 5.412278172237591e-06, | |
| "loss": 0.3283, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.5340544194693256, | |
| "grad_norm": 1.8419865369796753, | |
| "learning_rate": 5.294648325543188e-06, | |
| "loss": 0.3201, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.5408146019942538, | |
| "grad_norm": 1.948057770729065, | |
| "learning_rate": 5.176854580287744e-06, | |
| "loss": 0.3065, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.5408146019942538, | |
| "eval_loss": 0.329855740070343, | |
| "eval_runtime": 1276.1984, | |
| "eval_samples_per_second": 4.122, | |
| "eval_steps_per_second": 0.516, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.5475747845191821, | |
| "grad_norm": 1.8223614692687988, | |
| "learning_rate": 5.0589624594139455e-06, | |
| "loss": 0.3207, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.5543349670441102, | |
| "grad_norm": 2.12894606590271, | |
| "learning_rate": 4.941037540586057e-06, | |
| "loss": 0.3062, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.5610951495690384, | |
| "grad_norm": 1.7402645349502563, | |
| "learning_rate": 4.8231454197122575e-06, | |
| "loss": 0.3114, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.5678553320939665, | |
| "grad_norm": 1.9146500825881958, | |
| "learning_rate": 4.705351674456813e-06, | |
| "loss": 0.3267, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.5746155146188947, | |
| "grad_norm": 1.9016306400299072, | |
| "learning_rate": 4.587721827762411e-06, | |
| "loss": 0.3231, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.5813756971438229, | |
| "grad_norm": 1.9831342697143555, | |
| "learning_rate": 4.47032131140292e-06, | |
| "loss": 0.328, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.588135879668751, | |
| "grad_norm": 1.9523651599884033, | |
| "learning_rate": 4.353215429586882e-06, | |
| "loss": 0.3215, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.5948960621936792, | |
| "grad_norm": 2.0452113151550293, | |
| "learning_rate": 4.236469322631938e-06, | |
| "loss": 0.328, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.6016562447186073, | |
| "grad_norm": 1.8030444383621216, | |
| "learning_rate": 4.12014793073044e-06, | |
| "loss": 0.3036, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.6084164272435356, | |
| "grad_norm": 1.8724502325057983, | |
| "learning_rate": 4.004315957826375e-06, | |
| "loss": 0.3024, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.6151766097684638, | |
| "grad_norm": 1.9722743034362793, | |
| "learning_rate": 3.889037835623693e-06, | |
| "loss": 0.3144, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.6219367922933919, | |
| "grad_norm": 1.9698827266693115, | |
| "learning_rate": 3.7743776877460864e-06, | |
| "loss": 0.3228, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.6286969748183201, | |
| "grad_norm": 1.863534688949585, | |
| "learning_rate": 3.6603992940681263e-06, | |
| "loss": 0.3055, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.6354571573432483, | |
| "grad_norm": 1.9991436004638672, | |
| "learning_rate": 3.5471660552376176e-06, | |
| "loss": 0.3264, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.6422173398681764, | |
| "grad_norm": 1.981311559677124, | |
| "learning_rate": 3.4347409574088896e-06, | |
| "loss": 0.316, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.6489775223931046, | |
| "grad_norm": 1.8221795558929443, | |
| "learning_rate": 3.323186537206665e-06, | |
| "loss": 0.3071, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.6557377049180327, | |
| "grad_norm": 1.8596502542495728, | |
| "learning_rate": 3.2125648469399628e-06, | |
| "loss": 0.3193, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.662497887442961, | |
| "grad_norm": 1.6564629077911377, | |
| "learning_rate": 3.1029374200854167e-06, | |
| "loss": 0.3001, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.6692580699678892, | |
| "grad_norm": 2.0445966720581055, | |
| "learning_rate": 2.9943652370591835e-06, | |
| "loss": 0.3059, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.6760182524928173, | |
| "grad_norm": 1.694770336151123, | |
| "learning_rate": 2.886908691296504e-06, | |
| "loss": 0.3042, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.6760182524928173, | |
| "eval_loss": 0.30882763862609863, | |
| "eval_runtime": 1270.5948, | |
| "eval_samples_per_second": 4.14, | |
| "eval_steps_per_second": 0.518, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.6827784350177455, | |
| "grad_norm": 2.0789783000946045, | |
| "learning_rate": 2.7806275556577624e-06, | |
| "loss": 0.3064, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.6895386175426736, | |
| "grad_norm": 1.8919354677200317, | |
| "learning_rate": 2.6755809491797426e-06, | |
| "loss": 0.3103, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.6962988000676018, | |
| "grad_norm": 1.8415489196777344, | |
| "learning_rate": 2.5718273041905863e-06, | |
| "loss": 0.2969, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.70305898259253, | |
| "grad_norm": 1.8690521717071533, | |
| "learning_rate": 2.469424333806718e-06, | |
| "loss": 0.3062, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.7098191651174581, | |
| "grad_norm": 2.0415210723876953, | |
| "learning_rate": 2.3684289998298453e-06, | |
| "loss": 0.317, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.7165793476423864, | |
| "grad_norm": 1.8409037590026855, | |
| "learning_rate": 2.268897481061863e-06, | |
| "loss": 0.2845, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.7233395301673146, | |
| "grad_norm": 2.023800849914551, | |
| "learning_rate": 2.1708851420553277e-06, | |
| "loss": 0.3041, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.7300997126922427, | |
| "grad_norm": 1.9210608005523682, | |
| "learning_rate": 2.0744465023168313e-06, | |
| "loss": 0.3023, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.7368598952171709, | |
| "grad_norm": 1.8132646083831787, | |
| "learning_rate": 1.9796352059804565e-06, | |
| "loss": 0.3089, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.743620077742099, | |
| "grad_norm": 1.9919142723083496, | |
| "learning_rate": 1.8865039919681377e-06, | |
| "loss": 0.2941, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.7503802602670272, | |
| "grad_norm": 2.0446407794952393, | |
| "learning_rate": 1.7951046646535714e-06, | |
| "loss": 0.2856, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.7571404427919554, | |
| "grad_norm": 2.0371832847595215, | |
| "learning_rate": 1.705488065045946e-06, | |
| "loss": 0.2919, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.7639006253168835, | |
| "grad_norm": 1.980812430381775, | |
| "learning_rate": 1.6177040425095664e-06, | |
| "loss": 0.2985, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.7706608078418117, | |
| "grad_norm": 1.756753921508789, | |
| "learning_rate": 1.5318014270350617e-06, | |
| "loss": 0.2893, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.77742099036674, | |
| "grad_norm": 1.7378242015838623, | |
| "learning_rate": 1.4478280020776442e-06, | |
| "loss": 0.2862, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.7841811728916681, | |
| "grad_norm": 1.8673665523529053, | |
| "learning_rate": 1.3658304779774784e-06, | |
| "loss": 0.2967, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.7909413554165963, | |
| "grad_norm": 2.001669406890869, | |
| "learning_rate": 1.2858544659770001e-06, | |
| "loss": 0.2924, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.7977015379415244, | |
| "grad_norm": 2.087536573410034, | |
| "learning_rate": 1.2079444528495887e-06, | |
| "loss": 0.2921, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.8044617204664526, | |
| "grad_norm": 1.8734593391418457, | |
| "learning_rate": 1.1321437761537307e-06, | |
| "loss": 0.2805, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.8112219029913807, | |
| "grad_norm": 1.8164645433425903, | |
| "learning_rate": 1.0584946001264523e-06, | |
| "loss": 0.2977, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.8112219029913807, | |
| "eval_loss": 0.294592946767807, | |
| "eval_runtime": 1271.0164, | |
| "eval_samples_per_second": 4.138, | |
| "eval_steps_per_second": 0.518, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.8179820855163089, | |
| "grad_norm": 1.854030966758728, | |
| "learning_rate": 9.870378922293855e-07, | |
| "loss": 0.2859, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.8247422680412371, | |
| "grad_norm": 1.7828032970428467, | |
| "learning_rate": 9.178134003605721e-07, | |
| "loss": 0.2916, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.8315024505661653, | |
| "grad_norm": 2.0216519832611084, | |
| "learning_rate": 8.508596307446254e-07, | |
| "loss": 0.2867, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.8382626330910935, | |
| "grad_norm": 1.7878661155700684, | |
| "learning_rate": 7.862138265135983e-07, | |
| "loss": 0.2886, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.8450228156160217, | |
| "grad_norm": 1.789251685142517, | |
| "learning_rate": 7.239119469904227e-07, | |
| "loss": 0.2814, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.8517829981409498, | |
| "grad_norm": 1.7281427383422852, | |
| "learning_rate": 6.639886476864993e-07, | |
| "loss": 0.2806, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.858543180665878, | |
| "grad_norm": 1.7876800298690796, | |
| "learning_rate": 6.064772610245051e-07, | |
| "loss": 0.2778, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.8653033631908061, | |
| "grad_norm": 1.909987449645996, | |
| "learning_rate": 5.514097777971939e-07, | |
| "loss": 0.2966, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.8720635457157343, | |
| "grad_norm": 1.9117987155914307, | |
| "learning_rate": 4.988168293724654e-07, | |
| "loss": 0.2858, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.8788237282406625, | |
| "grad_norm": 1.9773385524749756, | |
| "learning_rate": 4.4872767065462787e-07, | |
| "loss": 0.2871, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.8855839107655906, | |
| "grad_norm": 1.7200452089309692, | |
| "learning_rate": 4.0117016381130636e-07, | |
| "loss": 0.2982, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.8923440932905189, | |
| "grad_norm": 1.9773083925247192, | |
| "learning_rate": 3.561707627750827e-07, | |
| "loss": 0.2772, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.899104275815447, | |
| "grad_norm": 1.8127182722091675, | |
| "learning_rate": 3.137544985284441e-07, | |
| "loss": 0.2939, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.9058644583403752, | |
| "grad_norm": 1.8259408473968506, | |
| "learning_rate": 2.739449651802756e-07, | |
| "loss": 0.2912, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.9126246408653034, | |
| "grad_norm": 1.96041738986969, | |
| "learning_rate": 2.3676430684159035e-07, | |
| "loss": 0.28, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.9193848233902315, | |
| "grad_norm": 2.008439302444458, | |
| "learning_rate": 2.0223320530784574e-07, | |
| "loss": 0.2832, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.9261450059151597, | |
| "grad_norm": 1.8017557859420776, | |
| "learning_rate": 1.7037086855465902e-07, | |
| "loss": 0.2857, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.9329051884400879, | |
| "grad_norm": 1.8403921127319336, | |
| "learning_rate": 1.4119502005334185e-07, | |
| "loss": 0.2933, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.939665370965016, | |
| "grad_norm": 1.755980134010315, | |
| "learning_rate": 1.1472188891219816e-07, | |
| "loss": 0.289, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.9464255534899443, | |
| "grad_norm": 1.820554256439209, | |
| "learning_rate": 9.096620084905472e-08, | |
| "loss": 0.2908, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.9464255534899443, | |
| "eval_loss": 0.2895006537437439, | |
| "eval_runtime": 1270.2472, | |
| "eval_samples_per_second": 4.141, | |
| "eval_steps_per_second": 0.518, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.9531857360148724, | |
| "grad_norm": 2.062675952911377, | |
| "learning_rate": 6.994117000006185e-08, | |
| "loss": 0.2998, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.9599459185398006, | |
| "grad_norm": 1.8810018301010132, | |
| "learning_rate": 5.165849156930969e-08, | |
| "loss": 0.276, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.9667061010647288, | |
| "grad_norm": 2.032048225402832, | |
| "learning_rate": 3.6128335323353804e-08, | |
| "loss": 0.2761, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.9734662835896569, | |
| "grad_norm": 1.843258023262024, | |
| "learning_rate": 2.335933993426687e-08, | |
| "loss": 0.2995, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.9802264661145851, | |
| "grad_norm": 1.7969026565551758, | |
| "learning_rate": 1.3358608174368626e-08, | |
| "loss": 0.2772, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.9869866486395132, | |
| "grad_norm": 2.0245614051818848, | |
| "learning_rate": 6.1317029652929734e-09, | |
| "loss": 0.3069, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.9937468311644414, | |
| "grad_norm": 1.9319560527801514, | |
| "learning_rate": 1.6826442836082035e-09, | |
| "loss": 0.2764, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 4.367832660675049, | |
| "learning_rate": 1.3906924697382195e-11, | |
| "loss": 0.2913, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 1480, | |
| "total_flos": 760407761879040.0, | |
| "train_loss": 0.35166695085731714, | |
| "train_runtime": 62991.4895, | |
| "train_samples_per_second": 0.751, | |
| "train_steps_per_second": 0.023 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1480, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 760407761879040.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |