| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.99749049974905, |
| "eval_steps": 50, |
| "global_step": 8715, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.005736000573600057, |
| "grad_norm": 2.3000271320343018, |
| "learning_rate": 1.1467889908256882e-07, |
| "loss": 0.3103, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.011472001147200114, |
| "grad_norm": 0.23891927301883698, |
| "learning_rate": 2.2935779816513764e-07, |
| "loss": 0.2101, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.017208001720800174, |
| "grad_norm": 3.7850193977355957, |
| "learning_rate": 3.4403669724770646e-07, |
| "loss": 0.3158, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.022944002294400228, |
| "grad_norm": 10.902544021606445, |
| "learning_rate": 4.587155963302753e-07, |
| "loss": 0.3107, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.028680002868000286, |
| "grad_norm": 12.402349472045898, |
| "learning_rate": 5.733944954128441e-07, |
| "loss": 0.3895, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.028680002868000286, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 1.0573054552078247, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 17.8757, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 36.53, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 18.293, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.03441600344160035, |
| "grad_norm": 1.5937564373016357, |
| "learning_rate": 6.880733944954129e-07, |
| "loss": 0.2534, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.0401520040152004, |
| "grad_norm": 3.687685012817383, |
| "learning_rate": 8.027522935779817e-07, |
| "loss": 0.3795, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.045888004588800456, |
| "grad_norm": 0.03578287363052368, |
| "learning_rate": 9.174311926605506e-07, |
| "loss": 0.4276, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.05162400516240052, |
| "grad_norm": 0.022680282592773438, |
| "learning_rate": 1.0321100917431195e-06, |
| "loss": 0.277, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.05736000573600057, |
| "grad_norm": 1.7502835988998413, |
| "learning_rate": 1.1467889908256882e-06, |
| "loss": 0.2279, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.05736000573600057, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.9872124791145325, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.223, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.768, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.408, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.06309600630960063, |
| "grad_norm": 4.763681411743164, |
| "learning_rate": 1.261467889908257e-06, |
| "loss": 0.3441, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.0688320068832007, |
| "grad_norm": 7.319093704223633, |
| "learning_rate": 1.3761467889908258e-06, |
| "loss": 0.4273, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.07456800745680074, |
| "grad_norm": 9.32235336303711, |
| "learning_rate": 1.4908256880733945e-06, |
| "loss": 0.3338, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.0803040080304008, |
| "grad_norm": 2.0044586658477783, |
| "learning_rate": 1.6055045871559635e-06, |
| "loss": 0.1364, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.08604000860400086, |
| "grad_norm": 10.962570190429688, |
| "learning_rate": 1.7201834862385322e-06, |
| "loss": 0.2404, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.08604000860400086, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.7815765738487244, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2921, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.669, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.358, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.09177600917760091, |
| "grad_norm": 4.845127105712891, |
| "learning_rate": 1.8348623853211011e-06, |
| "loss": 0.3601, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.09751200975120097, |
| "grad_norm": 3.165642738342285, |
| "learning_rate": 1.94954128440367e-06, |
| "loss": 0.1938, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.10324801032480103, |
| "grad_norm": 3.4738926887512207, |
| "learning_rate": 2.064220183486239e-06, |
| "loss": 0.1979, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.1089840108984011, |
| "grad_norm": 0.34281352162361145, |
| "learning_rate": 2.1788990825688075e-06, |
| "loss": 0.2278, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.11472001147200114, |
| "grad_norm": 9.631810188293457, |
| "learning_rate": 2.2935779816513764e-06, |
| "loss": 0.1642, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.11472001147200114, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.32764628529548645, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1681, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.848, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.448, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.1204560120456012, |
| "grad_norm": 4.584328651428223, |
| "learning_rate": 2.4082568807339453e-06, |
| "loss": 0.1721, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.12619201261920127, |
| "grad_norm": 7.435701370239258, |
| "learning_rate": 2.522935779816514e-06, |
| "loss": 0.1632, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.1319280131928013, |
| "grad_norm": 2.957846164703369, |
| "learning_rate": 2.6376146788990823e-06, |
| "loss": 0.1175, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.1376640137664014, |
| "grad_norm": 4.342548847198486, |
| "learning_rate": 2.7522935779816517e-06, |
| "loss": 0.0877, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.14340001434000144, |
| "grad_norm": 2.2145071029663086, |
| "learning_rate": 2.8669724770642206e-06, |
| "loss": 0.0692, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.14340001434000144, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.14406049251556396, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2632, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.71, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.379, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.14913601491360148, |
| "grad_norm": 0.3610692620277405, |
| "learning_rate": 2.981651376146789e-06, |
| "loss": 0.1079, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.15487201548720156, |
| "grad_norm": 6.997246265411377, |
| "learning_rate": 3.0963302752293576e-06, |
| "loss": 0.0748, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.1606080160608016, |
| "grad_norm": 2.0748515129089355, |
| "learning_rate": 3.211009174311927e-06, |
| "loss": 0.0749, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.16634401663440165, |
| "grad_norm": 3.6645171642303467, |
| "learning_rate": 3.325688073394496e-06, |
| "loss": 0.097, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.17208001720800173, |
| "grad_norm": 8.085243225097656, |
| "learning_rate": 3.4403669724770644e-06, |
| "loss": 0.0722, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.17208001720800173, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.11341650038957596, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2959, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.663, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.355, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.17781601778160178, |
| "grad_norm": 2.7256767749786377, |
| "learning_rate": 3.5550458715596333e-06, |
| "loss": 0.0707, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.18355201835520182, |
| "grad_norm": 2.6183135509490967, |
| "learning_rate": 3.6697247706422022e-06, |
| "loss": 0.0418, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.1892880189288019, |
| "grad_norm": 1.0414828062057495, |
| "learning_rate": 3.784403669724771e-06, |
| "loss": 0.041, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.19502401950240195, |
| "grad_norm": 1.9375965595245361, |
| "learning_rate": 3.89908256880734e-06, |
| "loss": 0.0742, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.200760020076002, |
| "grad_norm": 1.6328781843185425, |
| "learning_rate": 4.013761467889909e-06, |
| "loss": 0.0426, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.200760020076002, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.11491454392671585, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2047, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.795, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.421, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.20649602064960207, |
| "grad_norm": 0.45767122507095337, |
| "learning_rate": 4.128440366972478e-06, |
| "loss": 0.0771, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.21223202122320212, |
| "grad_norm": 2.768129825592041, |
| "learning_rate": 4.2431192660550464e-06, |
| "loss": 0.0869, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.2179680217968022, |
| "grad_norm": 1.4702483415603638, |
| "learning_rate": 4.357798165137615e-06, |
| "loss": 0.0536, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.22370402237040224, |
| "grad_norm": 1.277462124824524, |
| "learning_rate": 4.4724770642201834e-06, |
| "loss": 0.0329, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.2294400229440023, |
| "grad_norm": 1.8748779296875, |
| "learning_rate": 4.587155963302753e-06, |
| "loss": 0.045, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.2294400229440023, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.12494589388370514, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2877, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.675, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.361, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.23517602351760236, |
| "grad_norm": 2.339601516723633, |
| "learning_rate": 4.701834862385321e-06, |
| "loss": 0.0546, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.2409120240912024, |
| "grad_norm": 0.9202137589454651, |
| "learning_rate": 4.816513761467891e-06, |
| "loss": 0.1038, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.24664802466480246, |
| "grad_norm": 2.0663821697235107, |
| "learning_rate": 4.931192660550459e-06, |
| "loss": 0.0418, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.25238402523840253, |
| "grad_norm": 2.6615207195281982, |
| "learning_rate": 5.045871559633028e-06, |
| "loss": 0.0414, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.2581200258120026, |
| "grad_norm": 2.298173427581787, |
| "learning_rate": 5.160550458715596e-06, |
| "loss": 0.063, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.2581200258120026, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.1194896399974823, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.3177, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.632, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.339, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.2638560263856026, |
| "grad_norm": 0.9054094552993774, |
| "learning_rate": 5.275229357798165e-06, |
| "loss": 0.0572, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.2695920269592027, |
| "grad_norm": 0.5312202572822571, |
| "learning_rate": 5.389908256880735e-06, |
| "loss": 0.0697, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.2753280275328028, |
| "grad_norm": 1.5197083950042725, |
| "learning_rate": 5.504587155963303e-06, |
| "loss": 0.047, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.2810640281064028, |
| "grad_norm": 1.341577410697937, |
| "learning_rate": 5.619266055045872e-06, |
| "loss": 0.0285, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.28680002868000287, |
| "grad_norm": 1.6182245016098022, |
| "learning_rate": 5.733944954128441e-06, |
| "loss": 0.0402, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.28680002868000287, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.12436391413211823, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.3365, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.605, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.326, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.29253602925360295, |
| "grad_norm": 2.623664140701294, |
| "learning_rate": 5.84862385321101e-06, |
| "loss": 0.0552, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.29827202982720297, |
| "grad_norm": 1.9711512327194214, |
| "learning_rate": 5.963302752293578e-06, |
| "loss": 0.0534, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.30400803040080304, |
| "grad_norm": 1.4279474020004272, |
| "learning_rate": 6.077981651376147e-06, |
| "loss": 0.0356, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.3097440309744031, |
| "grad_norm": 1.5085383653640747, |
| "learning_rate": 6.192660550458715e-06, |
| "loss": 0.0389, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.31548003154800314, |
| "grad_norm": 1.8550148010253906, |
| "learning_rate": 6.307339449541285e-06, |
| "loss": 0.0342, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.31548003154800314, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.16011035442352295, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2066, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.792, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.42, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.3212160321216032, |
| "grad_norm": 0.8617078065872192, |
| "learning_rate": 6.422018348623854e-06, |
| "loss": 0.0351, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.3269520326952033, |
| "grad_norm": 1.7970987558364868, |
| "learning_rate": 6.536697247706422e-06, |
| "loss": 0.0328, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.3326880332688033, |
| "grad_norm": 1.319393515586853, |
| "learning_rate": 6.651376146788992e-06, |
| "loss": 0.0348, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.3384240338424034, |
| "grad_norm": 3.622856855392456, |
| "learning_rate": 6.76605504587156e-06, |
| "loss": 0.035, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.34416003441600346, |
| "grad_norm": 2.2089531421661377, |
| "learning_rate": 6.880733944954129e-06, |
| "loss": 0.0485, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.34416003441600346, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.12377385795116425, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2989, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.659, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.353, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.3498960349896035, |
| "grad_norm": 1.3465012311935425, |
| "learning_rate": 6.995412844036697e-06, |
| "loss": 0.0448, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.35563203556320355, |
| "grad_norm": 1.0101594924926758, |
| "learning_rate": 7.110091743119267e-06, |
| "loss": 0.0298, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.3613680361368036, |
| "grad_norm": 3.003561019897461, |
| "learning_rate": 7.224770642201836e-06, |
| "loss": 0.052, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.36710403671040365, |
| "grad_norm": 2.2370080947875977, |
| "learning_rate": 7.3394495412844045e-06, |
| "loss": 0.0241, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.3728400372840037, |
| "grad_norm": 3.373074531555176, |
| "learning_rate": 7.454128440366973e-06, |
| "loss": 0.0446, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.3728400372840037, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.11963505297899246, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1731, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.841, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.444, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.3785760378576038, |
| "grad_norm": 0.6863628029823303, |
| "learning_rate": 7.568807339449542e-06, |
| "loss": 0.0116, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.3843120384312038, |
| "grad_norm": 2.9094369411468506, |
| "learning_rate": 7.68348623853211e-06, |
| "loss": 0.0657, |
| "step": 670 |
| }, |
| { |
| "epoch": 0.3900480390048039, |
| "grad_norm": 0.2047434151172638, |
| "learning_rate": 7.79816513761468e-06, |
| "loss": 0.0319, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.39578403957840397, |
| "grad_norm": 1.523390531539917, |
| "learning_rate": 7.912844036697249e-06, |
| "loss": 0.0492, |
| "step": 690 |
| }, |
| { |
| "epoch": 0.401520040152004, |
| "grad_norm": 0.10014928132295609, |
| "learning_rate": 8.027522935779817e-06, |
| "loss": 0.0333, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.401520040152004, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.10763221979141235, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.342, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.597, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.322, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.40725604072560406, |
| "grad_norm": 0.24312058091163635, |
| "learning_rate": 8.142201834862386e-06, |
| "loss": 0.0248, |
| "step": 710 |
| }, |
| { |
| "epoch": 0.41299204129920414, |
| "grad_norm": 0.08946532011032104, |
| "learning_rate": 8.256880733944956e-06, |
| "loss": 0.0133, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.4187280418728042, |
| "grad_norm": 0.13466329872608185, |
| "learning_rate": 8.371559633027524e-06, |
| "loss": 0.0226, |
| "step": 730 |
| }, |
| { |
| "epoch": 0.42446404244640423, |
| "grad_norm": 0.4071923792362213, |
| "learning_rate": 8.486238532110093e-06, |
| "loss": 0.0353, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.4302000430200043, |
| "grad_norm": 1.2394853830337524, |
| "learning_rate": 8.600917431192661e-06, |
| "loss": 0.0199, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.4302000430200043, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09811359643936157, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.3072, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.647, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.347, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.4359360435936044, |
| "grad_norm": 2.9703874588012695, |
| "learning_rate": 8.71559633027523e-06, |
| "loss": 0.0259, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.4416720441672044, |
| "grad_norm": 1.3356784582138062, |
| "learning_rate": 8.830275229357798e-06, |
| "loss": 0.0496, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.4474080447408045, |
| "grad_norm": 0.7478968501091003, |
| "learning_rate": 8.944954128440367e-06, |
| "loss": 0.0383, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.45314404531440455, |
| "grad_norm": 0.418811172246933, |
| "learning_rate": 9.059633027522935e-06, |
| "loss": 0.0173, |
| "step": 790 |
| }, |
| { |
| "epoch": 0.4588800458880046, |
| "grad_norm": 0.6638255715370178, |
| "learning_rate": 9.174311926605506e-06, |
| "loss": 0.0271, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.4588800458880046, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.11180277168750763, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2311, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.757, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.402, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.46461604646160465, |
| "grad_norm": 0.21615058183670044, |
| "learning_rate": 9.288990825688074e-06, |
| "loss": 0.0175, |
| "step": 810 |
| }, |
| { |
| "epoch": 0.4703520470352047, |
| "grad_norm": 1.2093310356140137, |
| "learning_rate": 9.403669724770643e-06, |
| "loss": 0.0215, |
| "step": 820 |
| }, |
| { |
| "epoch": 0.47608804760880474, |
| "grad_norm": 0.2247300148010254, |
| "learning_rate": 9.518348623853211e-06, |
| "loss": 0.0486, |
| "step": 830 |
| }, |
| { |
| "epoch": 0.4818240481824048, |
| "grad_norm": 0.6988762617111206, |
| "learning_rate": 9.633027522935781e-06, |
| "loss": 0.0161, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.4875600487560049, |
| "grad_norm": 1.2162249088287354, |
| "learning_rate": 9.74770642201835e-06, |
| "loss": 0.0277, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.4875600487560049, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08368796855211258, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2199, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.773, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.41, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.4932960493296049, |
| "grad_norm": 1.0620274543762207, |
| "learning_rate": 9.862385321100918e-06, |
| "loss": 0.0566, |
| "step": 860 |
| }, |
| { |
| "epoch": 0.499032049903205, |
| "grad_norm": 0.23082388937473297, |
| "learning_rate": 9.977064220183487e-06, |
| "loss": 0.0247, |
| "step": 870 |
| }, |
| { |
| "epoch": 0.5047680504768051, |
| "grad_norm": 0.9556642770767212, |
| "learning_rate": 9.999974328282418e-06, |
| "loss": 0.0242, |
| "step": 880 |
| }, |
| { |
| "epoch": 0.5105040510504051, |
| "grad_norm": 0.6304249167442322, |
| "learning_rate": 9.999870037381541e-06, |
| "loss": 0.0268, |
| "step": 890 |
| }, |
| { |
| "epoch": 0.5162400516240052, |
| "grad_norm": 0.07784967124462128, |
| "learning_rate": 9.99968552448706e-06, |
| "loss": 0.033, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.5162400516240052, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.06569766253232956, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2473, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.733, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.39, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.5219760521976052, |
| "grad_norm": 1.320080280303955, |
| "learning_rate": 9.999420792559453e-06, |
| "loss": 0.0623, |
| "step": 910 |
| }, |
| { |
| "epoch": 0.5277120527712053, |
| "grad_norm": 0.24600175023078918, |
| "learning_rate": 9.999075845846292e-06, |
| "loss": 0.022, |
| "step": 920 |
| }, |
| { |
| "epoch": 0.5334480533448054, |
| "grad_norm": 1.860329031944275, |
| "learning_rate": 9.998650689882184e-06, |
| "loss": 0.0186, |
| "step": 930 |
| }, |
| { |
| "epoch": 0.5391840539184054, |
| "grad_norm": 1.9470009803771973, |
| "learning_rate": 9.99814533148868e-06, |
| "loss": 0.023, |
| "step": 940 |
| }, |
| { |
| "epoch": 0.5449200544920054, |
| "grad_norm": 0.3151063919067383, |
| "learning_rate": 9.997559778774162e-06, |
| "loss": 0.0111, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.5449200544920054, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07853744179010391, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2659, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.706, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.377, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.5506560550656056, |
| "grad_norm": 1.4308031797409058, |
| "learning_rate": 9.996894041133715e-06, |
| "loss": 0.0239, |
| "step": 960 |
| }, |
| { |
| "epoch": 0.5563920556392056, |
| "grad_norm": 0.32267820835113525, |
| "learning_rate": 9.996148129248975e-06, |
| "loss": 0.0365, |
| "step": 970 |
| }, |
| { |
| "epoch": 0.5621280562128056, |
| "grad_norm": 0.026730485260486603, |
| "learning_rate": 9.995322055087963e-06, |
| "loss": 0.0255, |
| "step": 980 |
| }, |
| { |
| "epoch": 0.5678640567864057, |
| "grad_norm": 4.146325588226318, |
| "learning_rate": 9.994415831904886e-06, |
| "loss": 0.06, |
| "step": 990 |
| }, |
| { |
| "epoch": 0.5736000573600057, |
| "grad_norm": 0.9087633490562439, |
| "learning_rate": 9.993429474239928e-06, |
| "loss": 0.0371, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.5736000573600057, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08875266462564468, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2636, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.71, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.378, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.5793360579336058, |
| "grad_norm": 1.1552188396453857, |
| "learning_rate": 9.992362997919016e-06, |
| "loss": 0.0419, |
| "step": 1010 |
| }, |
| { |
| "epoch": 0.5850720585072059, |
| "grad_norm": 0.8535066246986389, |
| "learning_rate": 9.991216420053565e-06, |
| "loss": 0.0162, |
| "step": 1020 |
| }, |
| { |
| "epoch": 0.5908080590808059, |
| "grad_norm": 1.3267903327941895, |
| "learning_rate": 9.989989759040208e-06, |
| "loss": 0.0375, |
| "step": 1030 |
| }, |
| { |
| "epoch": 0.5965440596544059, |
| "grad_norm": 2.629297971725464, |
| "learning_rate": 9.988683034560494e-06, |
| "loss": 0.0097, |
| "step": 1040 |
| }, |
| { |
| "epoch": 0.6022800602280061, |
| "grad_norm": 2.267737627029419, |
| "learning_rate": 9.987296267580575e-06, |
| "loss": 0.0267, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.6022800602280061, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.10149678587913513, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2648, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.708, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.377, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.6080160608016061, |
| "grad_norm": 0.04809356853365898, |
| "learning_rate": 9.985829480350874e-06, |
| "loss": 0.0104, |
| "step": 1060 |
| }, |
| { |
| "epoch": 0.6137520613752061, |
| "grad_norm": 2.897101640701294, |
| "learning_rate": 9.98428269640572e-06, |
| "loss": 0.0313, |
| "step": 1070 |
| }, |
| { |
| "epoch": 0.6194880619488062, |
| "grad_norm": 0.2844018340110779, |
| "learning_rate": 9.982655940562978e-06, |
| "loss": 0.0202, |
| "step": 1080 |
| }, |
| { |
| "epoch": 0.6252240625224063, |
| "grad_norm": 1.7705107927322388, |
| "learning_rate": 9.980949238923646e-06, |
| "loss": 0.0151, |
| "step": 1090 |
| }, |
| { |
| "epoch": 0.6309600630960063, |
| "grad_norm": 2.162916421890259, |
| "learning_rate": 9.979162618871435e-06, |
| "loss": 0.021, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.6309600630960063, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.087111696600914, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.3134, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.638, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.342, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.6366960636696064, |
| "grad_norm": 3.3192200660705566, |
| "learning_rate": 9.977296109072337e-06, |
| "loss": 0.0182, |
| "step": 1110 |
| }, |
| { |
| "epoch": 0.6424320642432064, |
| "grad_norm": 0.3482876718044281, |
| "learning_rate": 9.975349739474156e-06, |
| "loss": 0.0309, |
| "step": 1120 |
| }, |
| { |
| "epoch": 0.6481680648168064, |
| "grad_norm": 2.682620048522949, |
| "learning_rate": 9.973323541306032e-06, |
| "loss": 0.0299, |
| "step": 1130 |
| }, |
| { |
| "epoch": 0.6539040653904066, |
| "grad_norm": 2.5474138259887695, |
| "learning_rate": 9.971217547077947e-06, |
| "loss": 0.0337, |
| "step": 1140 |
| }, |
| { |
| "epoch": 0.6596400659640066, |
| "grad_norm": 0.5940343141555786, |
| "learning_rate": 9.969031790580185e-06, |
| "loss": 0.0294, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.6596400659640066, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07855822145938873, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1855, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.823, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.435, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.6653760665376066, |
| "grad_norm": 1.4965182542800903, |
| "learning_rate": 9.966766306882811e-06, |
| "loss": 0.0257, |
| "step": 1160 |
| }, |
| { |
| "epoch": 0.6711120671112067, |
| "grad_norm": 0.10210319608449936, |
| "learning_rate": 9.964421132335091e-06, |
| "loss": 0.0214, |
| "step": 1170 |
| }, |
| { |
| "epoch": 0.6768480676848068, |
| "grad_norm": 1.594895362854004, |
| "learning_rate": 9.961996304564916e-06, |
| "loss": 0.0182, |
| "step": 1180 |
| }, |
| { |
| "epoch": 0.6825840682584068, |
| "grad_norm": 1.8244154453277588, |
| "learning_rate": 9.959491862478206e-06, |
| "loss": 0.0195, |
| "step": 1190 |
| }, |
| { |
| "epoch": 0.6883200688320069, |
| "grad_norm": 3.9240288734436035, |
| "learning_rate": 9.956907846258268e-06, |
| "loss": 0.0426, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.6883200688320069, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08573708683252335, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1456, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.881, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.464, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.6940560694056069, |
| "grad_norm": 0.06307424604892731, |
| "learning_rate": 9.954244297365169e-06, |
| "loss": 0.0592, |
| "step": 1210 |
| }, |
| { |
| "epoch": 0.699792069979207, |
| "grad_norm": 0.44088277220726013, |
| "learning_rate": 9.951501258535061e-06, |
| "loss": 0.0267, |
| "step": 1220 |
| }, |
| { |
| "epoch": 0.7055280705528071, |
| "grad_norm": 2.217980146408081, |
| "learning_rate": 9.948678773779495e-06, |
| "loss": 0.0171, |
| "step": 1230 |
| }, |
| { |
| "epoch": 0.7112640711264071, |
| "grad_norm": 1.3680331707000732, |
| "learning_rate": 9.94577688838472e-06, |
| "loss": 0.0369, |
| "step": 1240 |
| }, |
| { |
| "epoch": 0.7170000717000071, |
| "grad_norm": 0.043984800577163696, |
| "learning_rate": 9.94279564891095e-06, |
| "loss": 0.0173, |
| "step": 1250 |
| }, |
| { |
| "epoch": 0.7170000717000071, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.06791304796934128, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1924, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.813, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.43, |
| "step": 1250 |
| }, |
| { |
| "epoch": 0.7227360722736073, |
| "grad_norm": 0.05398892983794212, |
| "learning_rate": 9.939735103191625e-06, |
| "loss": 0.0151, |
| "step": 1260 |
| }, |
| { |
| "epoch": 0.7284720728472073, |
| "grad_norm": 0.26481369137763977, |
| "learning_rate": 9.936595300332638e-06, |
| "loss": 0.0242, |
| "step": 1270 |
| }, |
| { |
| "epoch": 0.7342080734208073, |
| "grad_norm": 0.0726240873336792, |
| "learning_rate": 9.933376290711546e-06, |
| "loss": 0.0128, |
| "step": 1280 |
| }, |
| { |
| "epoch": 0.7399440739944074, |
| "grad_norm": 0.21732382476329803, |
| "learning_rate": 9.930078125976767e-06, |
| "loss": 0.0268, |
| "step": 1290 |
| }, |
| { |
| "epoch": 0.7456800745680074, |
| "grad_norm": 1.968591332435608, |
| "learning_rate": 9.926700859046745e-06, |
| "loss": 0.0264, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.7456800745680074, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08293525129556656, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2805, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.685, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.366, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.7514160751416075, |
| "grad_norm": 0.12683559954166412, |
| "learning_rate": 9.923244544109107e-06, |
| "loss": 0.0107, |
| "step": 1310 |
| }, |
| { |
| "epoch": 0.7571520757152076, |
| "grad_norm": 0.07375319302082062, |
| "learning_rate": 9.919709236619786e-06, |
| "loss": 0.0237, |
| "step": 1320 |
| }, |
| { |
| "epoch": 0.7628880762888076, |
| "grad_norm": 0.09353283792734146, |
| "learning_rate": 9.916094993302144e-06, |
| "loss": 0.0247, |
| "step": 1330 |
| }, |
| { |
| "epoch": 0.7686240768624076, |
| "grad_norm": 2.4819159507751465, |
| "learning_rate": 9.912401872146047e-06, |
| "loss": 0.0361, |
| "step": 1340 |
| }, |
| { |
| "epoch": 0.7743600774360078, |
| "grad_norm": 1.608819842338562, |
| "learning_rate": 9.908629932406943e-06, |
| "loss": 0.0123, |
| "step": 1350 |
| }, |
| { |
| "epoch": 0.7743600774360078, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.11693766713142395, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2248, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.766, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.407, |
| "step": 1350 |
| }, |
| { |
| "epoch": 0.7800960780096078, |
| "grad_norm": 0.044521648436784744, |
| "learning_rate": 9.90477923460491e-06, |
| "loss": 0.0559, |
| "step": 1360 |
| }, |
| { |
| "epoch": 0.7858320785832078, |
| "grad_norm": 1.6780263185501099, |
| "learning_rate": 9.900849840523686e-06, |
| "loss": 0.016, |
| "step": 1370 |
| }, |
| { |
| "epoch": 0.7915680791568079, |
| "grad_norm": 0.20249976217746735, |
| "learning_rate": 9.896841813209675e-06, |
| "loss": 0.0103, |
| "step": 1380 |
| }, |
| { |
| "epoch": 0.797304079730408, |
| "grad_norm": 0.5444568991661072, |
| "learning_rate": 9.892755216970937e-06, |
| "loss": 0.0265, |
| "step": 1390 |
| }, |
| { |
| "epoch": 0.803040080304008, |
| "grad_norm": 0.39745691418647766, |
| "learning_rate": 9.888590117376154e-06, |
| "loss": 0.0305, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.803040080304008, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07220673561096191, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2419, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.741, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.394, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.8087760808776081, |
| "grad_norm": 3.1255667209625244, |
| "learning_rate": 9.884346581253584e-06, |
| "loss": 0.0155, |
| "step": 1410 |
| }, |
| { |
| "epoch": 0.8145120814512081, |
| "grad_norm": 0.28445881605148315, |
| "learning_rate": 9.88002467668998e-06, |
| "loss": 0.0543, |
| "step": 1420 |
| }, |
| { |
| "epoch": 0.8202480820248083, |
| "grad_norm": 2.316286087036133, |
| "learning_rate": 9.875624473029508e-06, |
| "loss": 0.0208, |
| "step": 1430 |
| }, |
| { |
| "epoch": 0.8259840825984083, |
| "grad_norm": 0.3444057106971741, |
| "learning_rate": 9.871146040872621e-06, |
| "loss": 0.0375, |
| "step": 1440 |
| }, |
| { |
| "epoch": 0.8317200831720083, |
| "grad_norm": 0.36751267313957214, |
| "learning_rate": 9.86658945207494e-06, |
| "loss": 0.0273, |
| "step": 1450 |
| }, |
| { |
| "epoch": 0.8317200831720083, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.06544554233551025, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1664, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.851, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.449, |
| "step": 1450 |
| }, |
| { |
| "epoch": 0.8374560837456084, |
| "grad_norm": 0.6214566230773926, |
| "learning_rate": 9.861954779746092e-06, |
| "loss": 0.0095, |
| "step": 1460 |
| }, |
| { |
| "epoch": 0.8431920843192084, |
| "grad_norm": 0.6569352149963379, |
| "learning_rate": 9.857242098248543e-06, |
| "loss": 0.024, |
| "step": 1470 |
| }, |
| { |
| "epoch": 0.8489280848928085, |
| "grad_norm": 1.6928707361221313, |
| "learning_rate": 9.852451483196394e-06, |
| "loss": 0.0158, |
| "step": 1480 |
| }, |
| { |
| "epoch": 0.8546640854664086, |
| "grad_norm": 1.0950285196304321, |
| "learning_rate": 9.847583011454187e-06, |
| "loss": 0.0099, |
| "step": 1490 |
| }, |
| { |
| "epoch": 0.8604000860400086, |
| "grad_norm": 1.4251108169555664, |
| "learning_rate": 9.842636761135651e-06, |
| "loss": 0.0677, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.8604000860400086, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.11534915119409561, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2226, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.769, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.408, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.8661360866136086, |
| "grad_norm": 0.9497309923171997, |
| "learning_rate": 9.837612811602462e-06, |
| "loss": 0.0282, |
| "step": 1510 |
| }, |
| { |
| "epoch": 0.8718720871872088, |
| "grad_norm": 0.9512405395507812, |
| "learning_rate": 9.832511243462962e-06, |
| "loss": 0.0079, |
| "step": 1520 |
| }, |
| { |
| "epoch": 0.8776080877608088, |
| "grad_norm": 0.04131248593330383, |
| "learning_rate": 9.827332138570878e-06, |
| "loss": 0.0051, |
| "step": 1530 |
| }, |
| { |
| "epoch": 0.8833440883344088, |
| "grad_norm": 1.3209096193313599, |
| "learning_rate": 9.822075580023987e-06, |
| "loss": 0.0132, |
| "step": 1540 |
| }, |
| { |
| "epoch": 0.8890800889080089, |
| "grad_norm": 0.05282355472445488, |
| "learning_rate": 9.816741652162807e-06, |
| "loss": 0.0592, |
| "step": 1550 |
| }, |
| { |
| "epoch": 0.8890800889080089, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08604957163333893, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.3059, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.649, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.348, |
| "step": 1550 |
| }, |
| { |
| "epoch": 0.894816089481609, |
| "grad_norm": 0.5249603390693665, |
| "learning_rate": 9.811330440569226e-06, |
| "loss": 0.0169, |
| "step": 1560 |
| }, |
| { |
| "epoch": 0.900552090055209, |
| "grad_norm": 1.4722495079040527, |
| "learning_rate": 9.805842032065135e-06, |
| "loss": 0.0257, |
| "step": 1570 |
| }, |
| { |
| "epoch": 0.9062880906288091, |
| "grad_norm": 1.664174199104309, |
| "learning_rate": 9.800276514711044e-06, |
| "loss": 0.0318, |
| "step": 1580 |
| }, |
| { |
| "epoch": 0.9120240912024091, |
| "grad_norm": 0.017392676323652267, |
| "learning_rate": 9.794633977804646e-06, |
| "loss": 0.0165, |
| "step": 1590 |
| }, |
| { |
| "epoch": 0.9177600917760091, |
| "grad_norm": 0.18038752675056458, |
| "learning_rate": 9.788914511879412e-06, |
| "loss": 0.0488, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.9177600917760091, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08364205807447433, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2219, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.77, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.409, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.9234960923496093, |
| "grad_norm": 1.785083293914795, |
| "learning_rate": 9.783118208703115e-06, |
| "loss": 0.0212, |
| "step": 1610 |
| }, |
| { |
| "epoch": 0.9292320929232093, |
| "grad_norm": 0.36738669872283936, |
| "learning_rate": 9.777245161276372e-06, |
| "loss": 0.0221, |
| "step": 1620 |
| }, |
| { |
| "epoch": 0.9349680934968093, |
| "grad_norm": 0.9083078503608704, |
| "learning_rate": 9.77129546383115e-06, |
| "loss": 0.0261, |
| "step": 1630 |
| }, |
| { |
| "epoch": 0.9407040940704094, |
| "grad_norm": 0.5853396058082581, |
| "learning_rate": 9.765269211829245e-06, |
| "loss": 0.011, |
| "step": 1640 |
| }, |
| { |
| "epoch": 0.9464400946440095, |
| "grad_norm": 0.027249574661254883, |
| "learning_rate": 9.759166501960762e-06, |
| "loss": 0.0156, |
| "step": 1650 |
| }, |
| { |
| "epoch": 0.9464400946440095, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07951950281858444, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2513, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.727, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.387, |
| "step": 1650 |
| }, |
| { |
| "epoch": 0.9521760952176095, |
| "grad_norm": 0.5655274987220764, |
| "learning_rate": 9.752987432142556e-06, |
| "loss": 0.0141, |
| "step": 1660 |
| }, |
| { |
| "epoch": 0.9579120957912096, |
| "grad_norm": 0.20478393137454987, |
| "learning_rate": 9.746732101516665e-06, |
| "loss": 0.0225, |
| "step": 1670 |
| }, |
| { |
| "epoch": 0.9636480963648096, |
| "grad_norm": 0.38293856382369995, |
| "learning_rate": 9.740400610448714e-06, |
| "loss": 0.0228, |
| "step": 1680 |
| }, |
| { |
| "epoch": 0.9693840969384097, |
| "grad_norm": 0.4184674918651581, |
| "learning_rate": 9.733993060526313e-06, |
| "loss": 0.0278, |
| "step": 1690 |
| }, |
| { |
| "epoch": 0.9751200975120098, |
| "grad_norm": 0.6761838793754578, |
| "learning_rate": 9.727509554557416e-06, |
| "loss": 0.0148, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.9751200975120098, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.0835602656006813, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2977, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.661, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.354, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.9808560980856098, |
| "grad_norm": 0.10887222737073898, |
| "learning_rate": 9.720950196568689e-06, |
| "loss": 0.0065, |
| "step": 1710 |
| }, |
| { |
| "epoch": 0.9865920986592098, |
| "grad_norm": 0.13018013536930084, |
| "learning_rate": 9.714315091803815e-06, |
| "loss": 0.0083, |
| "step": 1720 |
| }, |
| { |
| "epoch": 0.99232809923281, |
| "grad_norm": 0.1999017894268036, |
| "learning_rate": 9.707604346721833e-06, |
| "loss": 0.0097, |
| "step": 1730 |
| }, |
| { |
| "epoch": 0.99806409980641, |
| "grad_norm": 0.06055552884936333, |
| "learning_rate": 9.700818068995407e-06, |
| "loss": 0.0255, |
| "step": 1740 |
| }, |
| { |
| "epoch": 1.00344160034416, |
| "grad_norm": 2.305107831954956, |
| "learning_rate": 9.693956367509117e-06, |
| "loss": 0.021, |
| "step": 1750 |
| }, |
| { |
| "epoch": 1.00344160034416, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.11077206581830978, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.3027, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.653, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.35, |
| "step": 1750 |
| }, |
| { |
| "epoch": 1.00917760091776, |
| "grad_norm": 2.2754151821136475, |
| "learning_rate": 9.687019352357699e-06, |
| "loss": 0.0398, |
| "step": 1760 |
| }, |
| { |
| "epoch": 1.0149136014913602, |
| "grad_norm": 0.03042173944413662, |
| "learning_rate": 9.680007134844279e-06, |
| "loss": 0.0189, |
| "step": 1770 |
| }, |
| { |
| "epoch": 1.0206496020649602, |
| "grad_norm": 1.6503928899765015, |
| "learning_rate": 9.672919827478598e-06, |
| "loss": 0.0111, |
| "step": 1780 |
| }, |
| { |
| "epoch": 1.0263856026385603, |
| "grad_norm": 1.7391407489776611, |
| "learning_rate": 9.665757543975196e-06, |
| "loss": 0.0204, |
| "step": 1790 |
| }, |
| { |
| "epoch": 1.0321216032121603, |
| "grad_norm": 1.6538548469543457, |
| "learning_rate": 9.658520399251592e-06, |
| "loss": 0.0165, |
| "step": 1800 |
| }, |
| { |
| "epoch": 1.0321216032121603, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07668553292751312, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1222, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.915, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.481, |
| "step": 1800 |
| }, |
| { |
| "epoch": 1.0378576037857603, |
| "grad_norm": 0.022262316197156906, |
| "learning_rate": 9.651208509426442e-06, |
| "loss": 0.0053, |
| "step": 1810 |
| }, |
| { |
| "epoch": 1.0435936043593603, |
| "grad_norm": 1.768957495689392, |
| "learning_rate": 9.64382199181767e-06, |
| "loss": 0.0164, |
| "step": 1820 |
| }, |
| { |
| "epoch": 1.0493296049329606, |
| "grad_norm": 0.11224523931741714, |
| "learning_rate": 9.63636096494059e-06, |
| "loss": 0.0216, |
| "step": 1830 |
| }, |
| { |
| "epoch": 1.0550656055065606, |
| "grad_norm": 0.022123126313090324, |
| "learning_rate": 9.628825548506002e-06, |
| "loss": 0.0069, |
| "step": 1840 |
| }, |
| { |
| "epoch": 1.0608016060801606, |
| "grad_norm": 4.303464412689209, |
| "learning_rate": 9.621215863418276e-06, |
| "loss": 0.0253, |
| "step": 1850 |
| }, |
| { |
| "epoch": 1.0608016060801606, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.0671575739979744, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2804, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.686, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.366, |
| "step": 1850 |
| }, |
| { |
| "epoch": 1.0665376066537606, |
| "grad_norm": 0.08216200768947601, |
| "learning_rate": 9.61353203177341e-06, |
| "loss": 0.0052, |
| "step": 1860 |
| }, |
| { |
| "epoch": 1.0722736072273606, |
| "grad_norm": 1.3728184700012207, |
| "learning_rate": 9.605774176857062e-06, |
| "loss": 0.0176, |
| "step": 1870 |
| }, |
| { |
| "epoch": 1.078009607800961, |
| "grad_norm": 0.0963163748383522, |
| "learning_rate": 9.597942423142586e-06, |
| "loss": 0.0165, |
| "step": 1880 |
| }, |
| { |
| "epoch": 1.083745608374561, |
| "grad_norm": 0.09453441202640533, |
| "learning_rate": 9.59003689628903e-06, |
| "loss": 0.0212, |
| "step": 1890 |
| }, |
| { |
| "epoch": 1.089481608948161, |
| "grad_norm": 0.0946192815899849, |
| "learning_rate": 9.582057723139115e-06, |
| "loss": 0.0258, |
| "step": 1900 |
| }, |
| { |
| "epoch": 1.089481608948161, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07539978623390198, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2173, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.777, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.412, |
| "step": 1900 |
| }, |
| { |
| "epoch": 1.095217609521761, |
| "grad_norm": 0.011775615625083447, |
| "learning_rate": 9.574005031717203e-06, |
| "loss": 0.0093, |
| "step": 1910 |
| }, |
| { |
| "epoch": 1.100953610095361, |
| "grad_norm": 0.06459964066743851, |
| "learning_rate": 9.565878951227247e-06, |
| "loss": 0.0082, |
| "step": 1920 |
| }, |
| { |
| "epoch": 1.106689610668961, |
| "grad_norm": 0.020801063627004623, |
| "learning_rate": 9.557679612050708e-06, |
| "loss": 0.0067, |
| "step": 1930 |
| }, |
| { |
| "epoch": 1.112425611242561, |
| "grad_norm": 0.048270970582962036, |
| "learning_rate": 9.549407145744473e-06, |
| "loss": 0.0442, |
| "step": 1940 |
| }, |
| { |
| "epoch": 1.1181616118161612, |
| "grad_norm": 1.6280121803283691, |
| "learning_rate": 9.541061685038742e-06, |
| "loss": 0.0258, |
| "step": 1950 |
| }, |
| { |
| "epoch": 1.1181616118161612, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.0749003142118454, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1385, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.891, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.469, |
| "step": 1950 |
| }, |
| { |
| "epoch": 1.1238976123897613, |
| "grad_norm": 0.4389003813266754, |
| "learning_rate": 9.532643363834891e-06, |
| "loss": 0.0165, |
| "step": 1960 |
| }, |
| { |
| "epoch": 1.1296336129633613, |
| "grad_norm": 0.07638214528560638, |
| "learning_rate": 9.524152317203337e-06, |
| "loss": 0.0339, |
| "step": 1970 |
| }, |
| { |
| "epoch": 1.1353696135369613, |
| "grad_norm": 0.26499396562576294, |
| "learning_rate": 9.515588681381356e-06, |
| "loss": 0.0229, |
| "step": 1980 |
| }, |
| { |
| "epoch": 1.1411056141105613, |
| "grad_norm": 0.7412366271018982, |
| "learning_rate": 9.506952593770908e-06, |
| "loss": 0.0157, |
| "step": 1990 |
| }, |
| { |
| "epoch": 1.1468416146841616, |
| "grad_norm": 0.16746670007705688, |
| "learning_rate": 9.498244192936428e-06, |
| "loss": 0.0102, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.1468416146841616, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09212490171194077, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1271, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.908, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.478, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.1525776152577616, |
| "grad_norm": 0.182969868183136, |
| "learning_rate": 9.489463618602602e-06, |
| "loss": 0.0111, |
| "step": 2010 |
| }, |
| { |
| "epoch": 1.1583136158313616, |
| "grad_norm": 1.3869882822036743, |
| "learning_rate": 9.480611011652128e-06, |
| "loss": 0.0146, |
| "step": 2020 |
| }, |
| { |
| "epoch": 1.1640496164049616, |
| "grad_norm": 0.0466344878077507, |
| "learning_rate": 9.471686514123455e-06, |
| "loss": 0.009, |
| "step": 2030 |
| }, |
| { |
| "epoch": 1.1697856169785616, |
| "grad_norm": 0.07296488434076309, |
| "learning_rate": 9.462690269208498e-06, |
| "loss": 0.0354, |
| "step": 2040 |
| }, |
| { |
| "epoch": 1.1755216175521617, |
| "grad_norm": 1.9699822664260864, |
| "learning_rate": 9.453622421250353e-06, |
| "loss": 0.0114, |
| "step": 2050 |
| }, |
| { |
| "epoch": 1.1755216175521617, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09612752497196198, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1568, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.865, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.456, |
| "step": 2050 |
| }, |
| { |
| "epoch": 1.1812576181257617, |
| "grad_norm": 2.4988596439361572, |
| "learning_rate": 9.444483115740968e-06, |
| "loss": 0.0235, |
| "step": 2060 |
| }, |
| { |
| "epoch": 1.186993618699362, |
| "grad_norm": 0.0865960419178009, |
| "learning_rate": 9.435272499318815e-06, |
| "loss": 0.0197, |
| "step": 2070 |
| }, |
| { |
| "epoch": 1.192729619272962, |
| "grad_norm": 0.7196880578994751, |
| "learning_rate": 9.425990719766542e-06, |
| "loss": 0.0085, |
| "step": 2080 |
| }, |
| { |
| "epoch": 1.198465619846562, |
| "grad_norm": 0.4979308843612671, |
| "learning_rate": 9.416637926008587e-06, |
| "loss": 0.0177, |
| "step": 2090 |
| }, |
| { |
| "epoch": 1.204201620420162, |
| "grad_norm": 1.3404853343963623, |
| "learning_rate": 9.407214268108805e-06, |
| "loss": 0.0079, |
| "step": 2100 |
| }, |
| { |
| "epoch": 1.204201620420162, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07606372237205505, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2379, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.747, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.397, |
| "step": 2100 |
| }, |
| { |
| "epoch": 1.209937620993762, |
| "grad_norm": 0.007559036836028099, |
| "learning_rate": 9.397719897268049e-06, |
| "loss": 0.0122, |
| "step": 2110 |
| }, |
| { |
| "epoch": 1.2156736215673623, |
| "grad_norm": 0.036009229719638824, |
| "learning_rate": 9.388154965821754e-06, |
| "loss": 0.0195, |
| "step": 2120 |
| }, |
| { |
| "epoch": 1.2214096221409623, |
| "grad_norm": 0.23815706372261047, |
| "learning_rate": 9.37851962723748e-06, |
| "loss": 0.0311, |
| "step": 2130 |
| }, |
| { |
| "epoch": 1.2271456227145623, |
| "grad_norm": 0.32620975375175476, |
| "learning_rate": 9.36881403611246e-06, |
| "loss": 0.0235, |
| "step": 2140 |
| }, |
| { |
| "epoch": 1.2328816232881623, |
| "grad_norm": 0.6975133419036865, |
| "learning_rate": 9.359038348171113e-06, |
| "loss": 0.0398, |
| "step": 2150 |
| }, |
| { |
| "epoch": 1.2328816232881623, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07932226359844208, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1766, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.836, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.442, |
| "step": 2150 |
| }, |
| { |
| "epoch": 1.2386176238617623, |
| "grad_norm": 0.055091869086027145, |
| "learning_rate": 9.349192720262556e-06, |
| "loss": 0.031, |
| "step": 2160 |
| }, |
| { |
| "epoch": 1.2443536244353623, |
| "grad_norm": 0.07653547823429108, |
| "learning_rate": 9.33927731035807e-06, |
| "loss": 0.0188, |
| "step": 2170 |
| }, |
| { |
| "epoch": 1.2500896250089624, |
| "grad_norm": 1.0113948583602905, |
| "learning_rate": 9.329292277548584e-06, |
| "loss": 0.023, |
| "step": 2180 |
| }, |
| { |
| "epoch": 1.2558256255825626, |
| "grad_norm": 0.38709500432014465, |
| "learning_rate": 9.319237782042108e-06, |
| "loss": 0.0134, |
| "step": 2190 |
| }, |
| { |
| "epoch": 1.2615616261561626, |
| "grad_norm": 1.0346875190734863, |
| "learning_rate": 9.309113985161169e-06, |
| "loss": 0.0272, |
| "step": 2200 |
| }, |
| { |
| "epoch": 1.2615616261561626, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.06406532227993011, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1643, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.854, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.451, |
| "step": 2200 |
| }, |
| { |
| "epoch": 1.2672976267297626, |
| "grad_norm": 3.084003448486328, |
| "learning_rate": 9.298921049340226e-06, |
| "loss": 0.0134, |
| "step": 2210 |
| }, |
| { |
| "epoch": 1.2730336273033627, |
| "grad_norm": 0.3186517059803009, |
| "learning_rate": 9.288659138123053e-06, |
| "loss": 0.0142, |
| "step": 2220 |
| }, |
| { |
| "epoch": 1.278769627876963, |
| "grad_norm": 0.02311491221189499, |
| "learning_rate": 9.278328416160125e-06, |
| "loss": 0.0116, |
| "step": 2230 |
| }, |
| { |
| "epoch": 1.284505628450563, |
| "grad_norm": 0.021789675578475, |
| "learning_rate": 9.267929049205976e-06, |
| "loss": 0.003, |
| "step": 2240 |
| }, |
| { |
| "epoch": 1.290241629024163, |
| "grad_norm": 0.004828541073948145, |
| "learning_rate": 9.25746120411653e-06, |
| "loss": 0.0074, |
| "step": 2250 |
| }, |
| { |
| "epoch": 1.290241629024163, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09356704354286194, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1187, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.92, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.484, |
| "step": 2250 |
| }, |
| { |
| "epoch": 1.295977629597763, |
| "grad_norm": 4.326236248016357, |
| "learning_rate": 9.246925048846433e-06, |
| "loss": 0.0318, |
| "step": 2260 |
| }, |
| { |
| "epoch": 1.301713630171363, |
| "grad_norm": 0.10032517462968826, |
| "learning_rate": 9.236320752446357e-06, |
| "loss": 0.0248, |
| "step": 2270 |
| }, |
| { |
| "epoch": 1.307449630744963, |
| "grad_norm": 1.968422293663025, |
| "learning_rate": 9.225648485060283e-06, |
| "loss": 0.0245, |
| "step": 2280 |
| }, |
| { |
| "epoch": 1.313185631318563, |
| "grad_norm": 0.9600183367729187, |
| "learning_rate": 9.214908417922774e-06, |
| "loss": 0.0169, |
| "step": 2290 |
| }, |
| { |
| "epoch": 1.3189216318921633, |
| "grad_norm": 0.41536957025527954, |
| "learning_rate": 9.20410072335623e-06, |
| "loss": 0.0103, |
| "step": 2300 |
| }, |
| { |
| "epoch": 1.3189216318921633, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.06794232130050659, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1585, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.862, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.455, |
| "step": 2300 |
| }, |
| { |
| "epoch": 1.3246576324657633, |
| "grad_norm": 0.7403652667999268, |
| "learning_rate": 9.19322557476812e-06, |
| "loss": 0.0141, |
| "step": 2310 |
| }, |
| { |
| "epoch": 1.3303936330393633, |
| "grad_norm": 0.03548659384250641, |
| "learning_rate": 9.182283146648197e-06, |
| "loss": 0.0214, |
| "step": 2320 |
| }, |
| { |
| "epoch": 1.3361296336129633, |
| "grad_norm": 2.034658193588257, |
| "learning_rate": 9.171273614565704e-06, |
| "loss": 0.008, |
| "step": 2330 |
| }, |
| { |
| "epoch": 1.3418656341865633, |
| "grad_norm": 1.0196254253387451, |
| "learning_rate": 9.160197155166559e-06, |
| "loss": 0.0459, |
| "step": 2340 |
| }, |
| { |
| "epoch": 1.3476016347601636, |
| "grad_norm": 0.014422023668885231, |
| "learning_rate": 9.149053946170507e-06, |
| "loss": 0.0198, |
| "step": 2350 |
| }, |
| { |
| "epoch": 1.3476016347601636, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.058592408895492554, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2196, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.773, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.41, |
| "step": 2350 |
| }, |
| { |
| "epoch": 1.3533376353337636, |
| "grad_norm": 0.019738655537366867, |
| "learning_rate": 9.137844166368289e-06, |
| "loss": 0.0233, |
| "step": 2360 |
| }, |
| { |
| "epoch": 1.3590736359073636, |
| "grad_norm": 0.03966844826936722, |
| "learning_rate": 9.126567995618752e-06, |
| "loss": 0.0082, |
| "step": 2370 |
| }, |
| { |
| "epoch": 1.3648096364809637, |
| "grad_norm": 0.10851484537124634, |
| "learning_rate": 9.115225614845979e-06, |
| "loss": 0.0132, |
| "step": 2380 |
| }, |
| { |
| "epoch": 1.3705456370545637, |
| "grad_norm": 2.611233711242676, |
| "learning_rate": 9.103817206036383e-06, |
| "loss": 0.0062, |
| "step": 2390 |
| }, |
| { |
| "epoch": 1.3762816376281637, |
| "grad_norm": 2.288485050201416, |
| "learning_rate": 9.092342952235777e-06, |
| "loss": 0.0476, |
| "step": 2400 |
| }, |
| { |
| "epoch": 1.3762816376281637, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07158029079437256, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1533, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.87, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.459, |
| "step": 2400 |
| }, |
| { |
| "epoch": 1.3820176382017637, |
| "grad_norm": 0.04291702061891556, |
| "learning_rate": 9.080803037546454e-06, |
| "loss": 0.0031, |
| "step": 2410 |
| }, |
| { |
| "epoch": 1.387753638775364, |
| "grad_norm": 0.008397878147661686, |
| "learning_rate": 9.069197647124216e-06, |
| "loss": 0.0121, |
| "step": 2420 |
| }, |
| { |
| "epoch": 1.393489639348964, |
| "grad_norm": 0.015200245194137096, |
| "learning_rate": 9.057526967175415e-06, |
| "loss": 0.0047, |
| "step": 2430 |
| }, |
| { |
| "epoch": 1.399225639922564, |
| "grad_norm": 3.2773385047912598, |
| "learning_rate": 9.04579118495396e-06, |
| "loss": 0.005, |
| "step": 2440 |
| }, |
| { |
| "epoch": 1.404961640496164, |
| "grad_norm": 0.5176500678062439, |
| "learning_rate": 9.033990488758317e-06, |
| "loss": 0.0329, |
| "step": 2450 |
| }, |
| { |
| "epoch": 1.404961640496164, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.1131686270236969, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1939, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.811, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.429, |
| "step": 2450 |
| }, |
| { |
| "epoch": 1.410697641069764, |
| "grad_norm": 0.002755386522039771, |
| "learning_rate": 9.02212506792848e-06, |
| "loss": 0.0164, |
| "step": 2460 |
| }, |
| { |
| "epoch": 1.4164336416433643, |
| "grad_norm": 0.0466199554502964, |
| "learning_rate": 9.01019511284294e-06, |
| "loss": 0.0233, |
| "step": 2470 |
| }, |
| { |
| "epoch": 1.4221696422169643, |
| "grad_norm": 0.8431953191757202, |
| "learning_rate": 8.99820081491563e-06, |
| "loss": 0.0051, |
| "step": 2480 |
| }, |
| { |
| "epoch": 1.4279056427905643, |
| "grad_norm": 0.035143181681632996, |
| "learning_rate": 8.98614236659285e-06, |
| "loss": 0.0283, |
| "step": 2490 |
| }, |
| { |
| "epoch": 1.4336416433641643, |
| "grad_norm": 0.05582081899046898, |
| "learning_rate": 8.97401996135018e-06, |
| "loss": 0.0073, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.4336416433641643, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09689504653215408, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.294, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.666, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.356, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.4393776439377644, |
| "grad_norm": 2.2861459255218506, |
| "learning_rate": 8.961833793689384e-06, |
| "loss": 0.0107, |
| "step": 2510 |
| }, |
| { |
| "epoch": 1.4451136445113644, |
| "grad_norm": 2.3350398540496826, |
| "learning_rate": 8.94958405913527e-06, |
| "loss": 0.0128, |
| "step": 2520 |
| }, |
| { |
| "epoch": 1.4508496450849644, |
| "grad_norm": 0.019439250230789185, |
| "learning_rate": 8.937270954232576e-06, |
| "loss": 0.0061, |
| "step": 2530 |
| }, |
| { |
| "epoch": 1.4565856456585646, |
| "grad_norm": 0.002678696997463703, |
| "learning_rate": 8.924894676542801e-06, |
| "loss": 0.0085, |
| "step": 2540 |
| }, |
| { |
| "epoch": 1.4623216462321647, |
| "grad_norm": 0.03475391864776611, |
| "learning_rate": 8.91245542464104e-06, |
| "loss": 0.0234, |
| "step": 2550 |
| }, |
| { |
| "epoch": 1.4623216462321647, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.10303693264722824, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1871, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.821, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.434, |
| "step": 2550 |
| }, |
| { |
| "epoch": 1.4680576468057647, |
| "grad_norm": 0.09974029660224915, |
| "learning_rate": 8.8999533981128e-06, |
| "loss": 0.013, |
| "step": 2560 |
| }, |
| { |
| "epoch": 1.4737936473793647, |
| "grad_norm": 0.19927239418029785, |
| "learning_rate": 8.887388797550791e-06, |
| "loss": 0.0033, |
| "step": 2570 |
| }, |
| { |
| "epoch": 1.479529647952965, |
| "grad_norm": 0.03026706352829933, |
| "learning_rate": 8.874761824551717e-06, |
| "loss": 0.0219, |
| "step": 2580 |
| }, |
| { |
| "epoch": 1.485265648526565, |
| "grad_norm": 0.8363674879074097, |
| "learning_rate": 8.862072681713027e-06, |
| "loss": 0.0167, |
| "step": 2590 |
| }, |
| { |
| "epoch": 1.491001649100165, |
| "grad_norm": 2.117938280105591, |
| "learning_rate": 8.84932157262969e-06, |
| "loss": 0.0365, |
| "step": 2600 |
| }, |
| { |
| "epoch": 1.491001649100165, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.11520245671272278, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2361, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.75, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.398, |
| "step": 2600 |
| }, |
| { |
| "epoch": 1.496737649673765, |
| "grad_norm": 0.14108580350875854, |
| "learning_rate": 8.836508701890892e-06, |
| "loss": 0.0196, |
| "step": 2610 |
| }, |
| { |
| "epoch": 1.502473650247365, |
| "grad_norm": 2.1537435054779053, |
| "learning_rate": 8.823634275076792e-06, |
| "loss": 0.0207, |
| "step": 2620 |
| }, |
| { |
| "epoch": 1.508209650820965, |
| "grad_norm": 0.93586665391922, |
| "learning_rate": 8.81069849875519e-06, |
| "loss": 0.0125, |
| "step": 2630 |
| }, |
| { |
| "epoch": 1.513945651394565, |
| "grad_norm": 3.1711156368255615, |
| "learning_rate": 8.797701580478235e-06, |
| "loss": 0.0094, |
| "step": 2640 |
| }, |
| { |
| "epoch": 1.519681651968165, |
| "grad_norm": 0.0233930516988039, |
| "learning_rate": 8.784643728779089e-06, |
| "loss": 0.0152, |
| "step": 2650 |
| }, |
| { |
| "epoch": 1.519681651968165, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07520527392625809, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2328, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.754, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.401, |
| "step": 2650 |
| }, |
| { |
| "epoch": 1.525417652541765, |
| "grad_norm": 0.14535315334796906, |
| "learning_rate": 8.771525153168576e-06, |
| "loss": 0.0035, |
| "step": 2660 |
| }, |
| { |
| "epoch": 1.5311536531153653, |
| "grad_norm": 0.3828493654727936, |
| "learning_rate": 8.758346064131824e-06, |
| "loss": 0.0026, |
| "step": 2670 |
| }, |
| { |
| "epoch": 1.5368896536889654, |
| "grad_norm": 2.7801029682159424, |
| "learning_rate": 8.745106673124888e-06, |
| "loss": 0.0215, |
| "step": 2680 |
| }, |
| { |
| "epoch": 1.5426256542625654, |
| "grad_norm": 1.6995360851287842, |
| "learning_rate": 8.731807192571359e-06, |
| "loss": 0.022, |
| "step": 2690 |
| }, |
| { |
| "epoch": 1.5483616548361656, |
| "grad_norm": 0.24279280006885529, |
| "learning_rate": 8.718447835858951e-06, |
| "loss": 0.0109, |
| "step": 2700 |
| }, |
| { |
| "epoch": 1.5483616548361656, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08999116718769073, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1893, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.817, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.432, |
| "step": 2700 |
| }, |
| { |
| "epoch": 1.5540976554097656, |
| "grad_norm": 0.015813475474715233, |
| "learning_rate": 8.705028817336083e-06, |
| "loss": 0.0019, |
| "step": 2710 |
| }, |
| { |
| "epoch": 1.5598336559833657, |
| "grad_norm": 0.017328623682260513, |
| "learning_rate": 8.691550352308431e-06, |
| "loss": 0.0044, |
| "step": 2720 |
| }, |
| { |
| "epoch": 1.5655696565569657, |
| "grad_norm": 1.36957585811615, |
| "learning_rate": 8.678012657035487e-06, |
| "loss": 0.0033, |
| "step": 2730 |
| }, |
| { |
| "epoch": 1.5713056571305657, |
| "grad_norm": 0.8026090264320374, |
| "learning_rate": 8.664415948727076e-06, |
| "loss": 0.0063, |
| "step": 2740 |
| }, |
| { |
| "epoch": 1.5770416577041657, |
| "grad_norm": 0.038070451468229294, |
| "learning_rate": 8.65076044553988e-06, |
| "loss": 0.02, |
| "step": 2750 |
| }, |
| { |
| "epoch": 1.5770416577041657, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09743982553482056, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1673, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.849, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.448, |
| "step": 2750 |
| }, |
| { |
| "epoch": 1.5827776582777657, |
| "grad_norm": 2.638280153274536, |
| "learning_rate": 8.63704636657393e-06, |
| "loss": 0.0205, |
| "step": 2760 |
| }, |
| { |
| "epoch": 1.5885136588513658, |
| "grad_norm": 0.08616320043802261, |
| "learning_rate": 8.623273931869094e-06, |
| "loss": 0.0151, |
| "step": 2770 |
| }, |
| { |
| "epoch": 1.594249659424966, |
| "grad_norm": 0.0016790858935564756, |
| "learning_rate": 8.609443362401553e-06, |
| "loss": 0.0077, |
| "step": 2780 |
| }, |
| { |
| "epoch": 1.599985659998566, |
| "grad_norm": 0.0031273786444216967, |
| "learning_rate": 8.595554880080246e-06, |
| "loss": 0.0014, |
| "step": 2790 |
| }, |
| { |
| "epoch": 1.605721660572166, |
| "grad_norm": 2.3747873306274414, |
| "learning_rate": 8.581608707743312e-06, |
| "loss": 0.0387, |
| "step": 2800 |
| }, |
| { |
| "epoch": 1.605721660572166, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.10180775076150894, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1502, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.874, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.461, |
| "step": 2800 |
| }, |
| { |
| "epoch": 1.6114576611457663, |
| "grad_norm": 0.03558593988418579, |
| "learning_rate": 8.567605069154517e-06, |
| "loss": 0.0009, |
| "step": 2810 |
| }, |
| { |
| "epoch": 1.6171936617193663, |
| "grad_norm": 0.005191161762923002, |
| "learning_rate": 8.55354418899966e-06, |
| "loss": 0.0349, |
| "step": 2820 |
| }, |
| { |
| "epoch": 1.6229296622929663, |
| "grad_norm": 1.5500961542129517, |
| "learning_rate": 8.539426292882976e-06, |
| "loss": 0.0296, |
| "step": 2830 |
| }, |
| { |
| "epoch": 1.6286656628665663, |
| "grad_norm": 0.12692737579345703, |
| "learning_rate": 8.525251607323506e-06, |
| "loss": 0.0076, |
| "step": 2840 |
| }, |
| { |
| "epoch": 1.6344016634401664, |
| "grad_norm": 0.034373391419649124, |
| "learning_rate": 8.511020359751467e-06, |
| "loss": 0.0125, |
| "step": 2850 |
| }, |
| { |
| "epoch": 1.6344016634401664, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07807676494121552, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1709, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.844, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.446, |
| "step": 2850 |
| }, |
| { |
| "epoch": 1.6401376640137664, |
| "grad_norm": 0.3334125876426697, |
| "learning_rate": 8.496732778504608e-06, |
| "loss": 0.007, |
| "step": 2860 |
| }, |
| { |
| "epoch": 1.6458736645873664, |
| "grad_norm": 1.8848798274993896, |
| "learning_rate": 8.482389092824535e-06, |
| "loss": 0.0279, |
| "step": 2870 |
| }, |
| { |
| "epoch": 1.6516096651609664, |
| "grad_norm": 0.0071907006204128265, |
| "learning_rate": 8.46798953285304e-06, |
| "loss": 0.0058, |
| "step": 2880 |
| }, |
| { |
| "epoch": 1.6573456657345664, |
| "grad_norm": 0.01580858789384365, |
| "learning_rate": 8.453534329628414e-06, |
| "loss": 0.0111, |
| "step": 2890 |
| }, |
| { |
| "epoch": 1.6630816663081667, |
| "grad_norm": 0.5010847449302673, |
| "learning_rate": 8.439023715081729e-06, |
| "loss": 0.0205, |
| "step": 2900 |
| }, |
| { |
| "epoch": 1.6630816663081667, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.0824664756655693, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2284, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.761, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.404, |
| "step": 2900 |
| }, |
| { |
| "epoch": 1.6688176668817667, |
| "grad_norm": 0.16337744891643524, |
| "learning_rate": 8.42445792203312e-06, |
| "loss": 0.0175, |
| "step": 2910 |
| }, |
| { |
| "epoch": 1.6745536674553667, |
| "grad_norm": 0.054014191031455994, |
| "learning_rate": 8.409837184188056e-06, |
| "loss": 0.0073, |
| "step": 2920 |
| }, |
| { |
| "epoch": 1.680289668028967, |
| "grad_norm": 3.6512198448181152, |
| "learning_rate": 8.395161736133579e-06, |
| "loss": 0.0226, |
| "step": 2930 |
| }, |
| { |
| "epoch": 1.686025668602567, |
| "grad_norm": 0.6102538704872131, |
| "learning_rate": 8.380431813334548e-06, |
| "loss": 0.0033, |
| "step": 2940 |
| }, |
| { |
| "epoch": 1.691761669176167, |
| "grad_norm": 2.3051533699035645, |
| "learning_rate": 8.365647652129865e-06, |
| "loss": 0.0327, |
| "step": 2950 |
| }, |
| { |
| "epoch": 1.691761669176167, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.0759689062833786, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.5562, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.293, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.17, |
| "step": 2950 |
| }, |
| { |
| "epoch": 1.697497669749767, |
| "grad_norm": 0.008392853662371635, |
| "learning_rate": 8.350809489728673e-06, |
| "loss": 0.0279, |
| "step": 2960 |
| }, |
| { |
| "epoch": 1.703233670323367, |
| "grad_norm": 1.614988088607788, |
| "learning_rate": 8.33591756420655e-06, |
| "loss": 0.0102, |
| "step": 2970 |
| }, |
| { |
| "epoch": 1.708969670896967, |
| "grad_norm": 0.04466373473405838, |
| "learning_rate": 8.320972114501698e-06, |
| "loss": 0.0158, |
| "step": 2980 |
| }, |
| { |
| "epoch": 1.714705671470567, |
| "grad_norm": 1.4472012519836426, |
| "learning_rate": 8.305973380411107e-06, |
| "loss": 0.0437, |
| "step": 2990 |
| }, |
| { |
| "epoch": 1.720441672044167, |
| "grad_norm": 0.0326494500041008, |
| "learning_rate": 8.290921602586699e-06, |
| "loss": 0.0188, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.720441672044167, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.06277668476104736, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2361, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.75, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.398, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.7261776726177671, |
| "grad_norm": 2.090261697769165, |
| "learning_rate": 8.275817022531479e-06, |
| "loss": 0.0229, |
| "step": 3010 |
| }, |
| { |
| "epoch": 1.7319136731913674, |
| "grad_norm": 1.1351670026779175, |
| "learning_rate": 8.260659882595647e-06, |
| "loss": 0.005, |
| "step": 3020 |
| }, |
| { |
| "epoch": 1.7376496737649674, |
| "grad_norm": 0.0521712526679039, |
| "learning_rate": 8.245450425972728e-06, |
| "loss": 0.0126, |
| "step": 3030 |
| }, |
| { |
| "epoch": 1.7433856743385674, |
| "grad_norm": 0.04499056562781334, |
| "learning_rate": 8.230188896695643e-06, |
| "loss": 0.0133, |
| "step": 3040 |
| }, |
| { |
| "epoch": 1.7491216749121676, |
| "grad_norm": 0.007846461609005928, |
| "learning_rate": 8.214875539632825e-06, |
| "loss": 0.0191, |
| "step": 3050 |
| }, |
| { |
| "epoch": 1.7491216749121676, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07422397285699844, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1752, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.838, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.443, |
| "step": 3050 |
| }, |
| { |
| "epoch": 1.7548576754857677, |
| "grad_norm": 0.055605433881282806, |
| "learning_rate": 8.199510600484261e-06, |
| "loss": 0.0148, |
| "step": 3060 |
| }, |
| { |
| "epoch": 1.7605936760593677, |
| "grad_norm": 0.27163052558898926, |
| "learning_rate": 8.184094325777573e-06, |
| "loss": 0.0075, |
| "step": 3070 |
| }, |
| { |
| "epoch": 1.7663296766329677, |
| "grad_norm": 0.11399796605110168, |
| "learning_rate": 8.168626962864045e-06, |
| "loss": 0.0016, |
| "step": 3080 |
| }, |
| { |
| "epoch": 1.7720656772065677, |
| "grad_norm": 0.07731972634792328, |
| "learning_rate": 8.153108759914669e-06, |
| "loss": 0.0141, |
| "step": 3090 |
| }, |
| { |
| "epoch": 1.7778016777801677, |
| "grad_norm": 0.2923997938632965, |
| "learning_rate": 8.13753996591615e-06, |
| "loss": 0.0047, |
| "step": 3100 |
| }, |
| { |
| "epoch": 1.7778016777801677, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.06707713752985, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.4009, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.513, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.28, |
| "step": 3100 |
| }, |
| { |
| "epoch": 1.7835376783537678, |
| "grad_norm": 0.26035454869270325, |
| "learning_rate": 8.121920830666918e-06, |
| "loss": 0.0092, |
| "step": 3110 |
| }, |
| { |
| "epoch": 1.7892736789273678, |
| "grad_norm": 3.143533706665039, |
| "learning_rate": 8.106251604773125e-06, |
| "loss": 0.0141, |
| "step": 3120 |
| }, |
| { |
| "epoch": 1.7950096795009678, |
| "grad_norm": 1.8246173858642578, |
| "learning_rate": 8.090532539644608e-06, |
| "loss": 0.0249, |
| "step": 3130 |
| }, |
| { |
| "epoch": 1.800745680074568, |
| "grad_norm": 0.01822010800242424, |
| "learning_rate": 8.074763887490878e-06, |
| "loss": 0.0182, |
| "step": 3140 |
| }, |
| { |
| "epoch": 1.806481680648168, |
| "grad_norm": 1.8796803951263428, |
| "learning_rate": 8.058945901317047e-06, |
| "loss": 0.0276, |
| "step": 3150 |
| }, |
| { |
| "epoch": 1.806481680648168, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.06196051836013794, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1882, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.819, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.433, |
| "step": 3150 |
| }, |
| { |
| "epoch": 1.812217681221768, |
| "grad_norm": 0.3315775692462921, |
| "learning_rate": 8.043078834919792e-06, |
| "loss": 0.0053, |
| "step": 3160 |
| }, |
| { |
| "epoch": 1.8179536817953683, |
| "grad_norm": 0.6810622215270996, |
| "learning_rate": 8.027162942883271e-06, |
| "loss": 0.0027, |
| "step": 3170 |
| }, |
| { |
| "epoch": 1.8236896823689683, |
| "grad_norm": 0.04800894856452942, |
| "learning_rate": 8.011198480575037e-06, |
| "loss": 0.0104, |
| "step": 3180 |
| }, |
| { |
| "epoch": 1.8294256829425684, |
| "grad_norm": 0.21183735132217407, |
| "learning_rate": 7.995185704141948e-06, |
| "loss": 0.0139, |
| "step": 3190 |
| }, |
| { |
| "epoch": 1.8351616835161684, |
| "grad_norm": 0.05010043457150459, |
| "learning_rate": 7.979124870506052e-06, |
| "loss": 0.013, |
| "step": 3200 |
| }, |
| { |
| "epoch": 1.8351616835161684, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08539190888404846, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2295, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.759, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.403, |
| "step": 3200 |
| }, |
| { |
| "epoch": 1.8408976840897684, |
| "grad_norm": 0.05234100669622421, |
| "learning_rate": 7.963016237360465e-06, |
| "loss": 0.0113, |
| "step": 3210 |
| }, |
| { |
| "epoch": 1.8466336846633684, |
| "grad_norm": 0.7740063071250916, |
| "learning_rate": 7.946860063165238e-06, |
| "loss": 0.0115, |
| "step": 3220 |
| }, |
| { |
| "epoch": 1.8523696852369684, |
| "grad_norm": 0.007312777452170849, |
| "learning_rate": 7.93065660714321e-06, |
| "loss": 0.0378, |
| "step": 3230 |
| }, |
| { |
| "epoch": 1.8581056858105685, |
| "grad_norm": 0.014250587671995163, |
| "learning_rate": 7.914406129275847e-06, |
| "loss": 0.0188, |
| "step": 3240 |
| }, |
| { |
| "epoch": 1.8638416863841685, |
| "grad_norm": 0.0380655862390995, |
| "learning_rate": 7.898108890299072e-06, |
| "loss": 0.013, |
| "step": 3250 |
| }, |
| { |
| "epoch": 1.8638416863841685, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07671073824167252, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.182, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.828, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.438, |
| "step": 3250 |
| }, |
| { |
| "epoch": 1.8695776869577687, |
| "grad_norm": 0.034287262707948685, |
| "learning_rate": 7.881765151699085e-06, |
| "loss": 0.0237, |
| "step": 3260 |
| }, |
| { |
| "epoch": 1.8753136875313687, |
| "grad_norm": 0.014141724444925785, |
| "learning_rate": 7.865375175708158e-06, |
| "loss": 0.0294, |
| "step": 3270 |
| }, |
| { |
| "epoch": 1.881049688104969, |
| "grad_norm": 2.08565616607666, |
| "learning_rate": 7.848939225300436e-06, |
| "loss": 0.0229, |
| "step": 3280 |
| }, |
| { |
| "epoch": 1.886785688678569, |
| "grad_norm": 1.476799726486206, |
| "learning_rate": 7.832457564187715e-06, |
| "loss": 0.0257, |
| "step": 3290 |
| }, |
| { |
| "epoch": 1.892521689252169, |
| "grad_norm": 1.641891598701477, |
| "learning_rate": 7.815930456815212e-06, |
| "loss": 0.0171, |
| "step": 3300 |
| }, |
| { |
| "epoch": 1.892521689252169, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.06915121525526047, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.0913, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.961, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.504, |
| "step": 3300 |
| }, |
| { |
| "epoch": 1.898257689825769, |
| "grad_norm": 0.03908121585845947, |
| "learning_rate": 7.799358168357323e-06, |
| "loss": 0.0208, |
| "step": 3310 |
| }, |
| { |
| "epoch": 1.903993690399369, |
| "grad_norm": 0.27976372838020325, |
| "learning_rate": 7.782740964713358e-06, |
| "loss": 0.0079, |
| "step": 3320 |
| }, |
| { |
| "epoch": 1.909729690972969, |
| "grad_norm": 0.1647738814353943, |
| "learning_rate": 7.76607911250329e-06, |
| "loss": 0.0284, |
| "step": 3330 |
| }, |
| { |
| "epoch": 1.915465691546569, |
| "grad_norm": 0.009193528443574905, |
| "learning_rate": 7.749372879063468e-06, |
| "loss": 0.0219, |
| "step": 3340 |
| }, |
| { |
| "epoch": 1.9212016921201691, |
| "grad_norm": 0.08929289132356644, |
| "learning_rate": 7.73262253244233e-06, |
| "loss": 0.0136, |
| "step": 3350 |
| }, |
| { |
| "epoch": 1.9212016921201691, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.06728994846343994, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1919, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.814, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.43, |
| "step": 3350 |
| }, |
| { |
| "epoch": 1.9269376926937691, |
| "grad_norm": 1.6335256099700928, |
| "learning_rate": 7.715828341396102e-06, |
| "loss": 0.0322, |
| "step": 3360 |
| }, |
| { |
| "epoch": 1.9326736932673694, |
| "grad_norm": 0.2756313979625702, |
| "learning_rate": 7.698990575384483e-06, |
| "loss": 0.0282, |
| "step": 3370 |
| }, |
| { |
| "epoch": 1.9384096938409694, |
| "grad_norm": 0.5282019376754761, |
| "learning_rate": 7.68210950456633e-06, |
| "loss": 0.0059, |
| "step": 3380 |
| }, |
| { |
| "epoch": 1.9441456944145694, |
| "grad_norm": 0.013134743086993694, |
| "learning_rate": 7.66518539979531e-06, |
| "loss": 0.0088, |
| "step": 3390 |
| }, |
| { |
| "epoch": 1.9498816949881697, |
| "grad_norm": 0.020495153963565826, |
| "learning_rate": 7.648218532615572e-06, |
| "loss": 0.0275, |
| "step": 3400 |
| }, |
| { |
| "epoch": 1.9498816949881697, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.06392066925764084, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1842, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.825, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.436, |
| "step": 3400 |
| }, |
| { |
| "epoch": 1.9556176955617697, |
| "grad_norm": 0.030520539730787277, |
| "learning_rate": 7.631209175257368e-06, |
| "loss": 0.0176, |
| "step": 3410 |
| }, |
| { |
| "epoch": 1.9613536961353697, |
| "grad_norm": 0.356724351644516, |
| "learning_rate": 7.614157600632706e-06, |
| "loss": 0.0306, |
| "step": 3420 |
| }, |
| { |
| "epoch": 1.9670896967089697, |
| "grad_norm": 0.5876423716545105, |
| "learning_rate": 7.597064082330961e-06, |
| "loss": 0.0178, |
| "step": 3430 |
| }, |
| { |
| "epoch": 1.9728256972825697, |
| "grad_norm": 0.04390386864542961, |
| "learning_rate": 7.579928894614479e-06, |
| "loss": 0.0099, |
| "step": 3440 |
| }, |
| { |
| "epoch": 1.9785616978561698, |
| "grad_norm": 0.026595573872327805, |
| "learning_rate": 7.562752312414196e-06, |
| "loss": 0.0097, |
| "step": 3450 |
| }, |
| { |
| "epoch": 1.9785616978561698, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08633749186992645, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1407, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.888, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.468, |
| "step": 3450 |
| }, |
| { |
| "epoch": 1.9842976984297698, |
| "grad_norm": 0.4078025221824646, |
| "learning_rate": 7.545534611325207e-06, |
| "loss": 0.0189, |
| "step": 3460 |
| }, |
| { |
| "epoch": 1.9900336990033698, |
| "grad_norm": 0.4737612307071686, |
| "learning_rate": 7.528276067602352e-06, |
| "loss": 0.0019, |
| "step": 3470 |
| }, |
| { |
| "epoch": 1.9957696995769698, |
| "grad_norm": 0.0031162798404693604, |
| "learning_rate": 7.510976958155789e-06, |
| "loss": 0.0037, |
| "step": 3480 |
| }, |
| { |
| "epoch": 2.00114720011472, |
| "grad_norm": 1.097615361213684, |
| "learning_rate": 7.493637560546539e-06, |
| "loss": 0.0127, |
| "step": 3490 |
| }, |
| { |
| "epoch": 2.00688320068832, |
| "grad_norm": 0.005019227508455515, |
| "learning_rate": 7.476258152982043e-06, |
| "loss": 0.0019, |
| "step": 3500 |
| }, |
| { |
| "epoch": 2.00688320068832, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07848720997571945, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.177, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.835, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.441, |
| "step": 3500 |
| }, |
| { |
| "epoch": 2.01261920126192, |
| "grad_norm": 0.016102029010653496, |
| "learning_rate": 7.458839014311696e-06, |
| "loss": 0.0057, |
| "step": 3510 |
| }, |
| { |
| "epoch": 2.01835520183552, |
| "grad_norm": 0.009885331615805626, |
| "learning_rate": 7.441380424022364e-06, |
| "loss": 0.0089, |
| "step": 3520 |
| }, |
| { |
| "epoch": 2.0240912024091204, |
| "grad_norm": 2.9838740825653076, |
| "learning_rate": 7.423882662233915e-06, |
| "loss": 0.0142, |
| "step": 3530 |
| }, |
| { |
| "epoch": 2.0298272029827205, |
| "grad_norm": 0.29027923941612244, |
| "learning_rate": 7.406346009694713e-06, |
| "loss": 0.0033, |
| "step": 3540 |
| }, |
| { |
| "epoch": 2.0355632035563205, |
| "grad_norm": 0.004921222571283579, |
| "learning_rate": 7.388770747777116e-06, |
| "loss": 0.0108, |
| "step": 3550 |
| }, |
| { |
| "epoch": 2.0355632035563205, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.0910039097070694, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.144, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.883, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.465, |
| "step": 3550 |
| }, |
| { |
| "epoch": 2.0412992041299205, |
| "grad_norm": 0.012345495633780956, |
| "learning_rate": 7.371157158472965e-06, |
| "loss": 0.0186, |
| "step": 3560 |
| }, |
| { |
| "epoch": 2.0470352047035205, |
| "grad_norm": 0.013729539699852467, |
| "learning_rate": 7.353505524389052e-06, |
| "loss": 0.0038, |
| "step": 3570 |
| }, |
| { |
| "epoch": 2.0527712052771205, |
| "grad_norm": 3.2665841579437256, |
| "learning_rate": 7.335816128742599e-06, |
| "loss": 0.0203, |
| "step": 3580 |
| }, |
| { |
| "epoch": 2.0585072058507206, |
| "grad_norm": 0.0018614591099321842, |
| "learning_rate": 7.318089255356695e-06, |
| "loss": 0.0093, |
| "step": 3590 |
| }, |
| { |
| "epoch": 2.0642432064243206, |
| "grad_norm": 0.10742621123790741, |
| "learning_rate": 7.300325188655762e-06, |
| "loss": 0.0093, |
| "step": 3600 |
| }, |
| { |
| "epoch": 2.0642432064243206, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07848691940307617, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1618, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.858, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.452, |
| "step": 3600 |
| }, |
| { |
| "epoch": 2.0699792069979206, |
| "grad_norm": 0.6563161611557007, |
| "learning_rate": 7.282524213660974e-06, |
| "loss": 0.001, |
| "step": 3610 |
| }, |
| { |
| "epoch": 2.0757152075715206, |
| "grad_norm": 0.12672875821590424, |
| "learning_rate": 7.264686615985697e-06, |
| "loss": 0.0008, |
| "step": 3620 |
| }, |
| { |
| "epoch": 2.0814512081451206, |
| "grad_norm": 0.004448240157216787, |
| "learning_rate": 7.246812681830899e-06, |
| "loss": 0.0139, |
| "step": 3630 |
| }, |
| { |
| "epoch": 2.0871872087187207, |
| "grad_norm": 0.007188173942267895, |
| "learning_rate": 7.228902697980562e-06, |
| "loss": 0.0106, |
| "step": 3640 |
| }, |
| { |
| "epoch": 2.092923209292321, |
| "grad_norm": 0.006886759772896767, |
| "learning_rate": 7.210956951797074e-06, |
| "loss": 0.0076, |
| "step": 3650 |
| }, |
| { |
| "epoch": 2.092923209292321, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08482418954372406, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1827, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.827, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.437, |
| "step": 3650 |
| }, |
| { |
| "epoch": 2.098659209865921, |
| "grad_norm": 3.8101847171783447, |
| "learning_rate": 7.19297573121663e-06, |
| "loss": 0.0089, |
| "step": 3660 |
| }, |
| { |
| "epoch": 2.104395210439521, |
| "grad_norm": 0.002013096585869789, |
| "learning_rate": 7.174959324744599e-06, |
| "loss": 0.0123, |
| "step": 3670 |
| }, |
| { |
| "epoch": 2.110131211013121, |
| "grad_norm": 3.1393046379089355, |
| "learning_rate": 7.156908021450904e-06, |
| "loss": 0.01, |
| "step": 3680 |
| }, |
| { |
| "epoch": 2.115867211586721, |
| "grad_norm": 0.07943509519100189, |
| "learning_rate": 7.138822110965381e-06, |
| "loss": 0.0016, |
| "step": 3690 |
| }, |
| { |
| "epoch": 2.121603212160321, |
| "grad_norm": 2.5405237674713135, |
| "learning_rate": 7.120701883473131e-06, |
| "loss": 0.0148, |
| "step": 3700 |
| }, |
| { |
| "epoch": 2.121603212160321, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.10251594334840775, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2361, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.75, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.398, |
| "step": 3700 |
| }, |
| { |
| "epoch": 2.1273392127339212, |
| "grad_norm": 0.006140326615422964, |
| "learning_rate": 7.102547629709867e-06, |
| "loss": 0.0163, |
| "step": 3710 |
| }, |
| { |
| "epoch": 2.1330752133075213, |
| "grad_norm": 0.04222610965371132, |
| "learning_rate": 7.084359640957246e-06, |
| "loss": 0.017, |
| "step": 3720 |
| }, |
| { |
| "epoch": 2.1388112138811213, |
| "grad_norm": 0.03461828827857971, |
| "learning_rate": 7.066138209038194e-06, |
| "loss": 0.0162, |
| "step": 3730 |
| }, |
| { |
| "epoch": 2.1445472144547213, |
| "grad_norm": 0.9535601139068604, |
| "learning_rate": 7.047883626312233e-06, |
| "loss": 0.0266, |
| "step": 3740 |
| }, |
| { |
| "epoch": 2.1502832150283213, |
| "grad_norm": 0.8345515131950378, |
| "learning_rate": 7.029596185670778e-06, |
| "loss": 0.0446, |
| "step": 3750 |
| }, |
| { |
| "epoch": 2.1502832150283213, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07697154581546783, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1863, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.822, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.435, |
| "step": 3750 |
| }, |
| { |
| "epoch": 2.156019215601922, |
| "grad_norm": 0.14290325343608856, |
| "learning_rate": 7.011276180532445e-06, |
| "loss": 0.0218, |
| "step": 3760 |
| }, |
| { |
| "epoch": 2.161755216175522, |
| "grad_norm": 0.05109575018286705, |
| "learning_rate": 6.992923904838341e-06, |
| "loss": 0.0032, |
| "step": 3770 |
| }, |
| { |
| "epoch": 2.167491216749122, |
| "grad_norm": 3.4320428371429443, |
| "learning_rate": 6.974539653047346e-06, |
| "loss": 0.0107, |
| "step": 3780 |
| }, |
| { |
| "epoch": 2.173227217322722, |
| "grad_norm": 0.9100053310394287, |
| "learning_rate": 6.956123720131398e-06, |
| "loss": 0.0162, |
| "step": 3790 |
| }, |
| { |
| "epoch": 2.178963217896322, |
| "grad_norm": 0.09293865412473679, |
| "learning_rate": 6.937676401570744e-06, |
| "loss": 0.0175, |
| "step": 3800 |
| }, |
| { |
| "epoch": 2.178963217896322, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07296475023031235, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.156, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.866, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.457, |
| "step": 3800 |
| }, |
| { |
| "epoch": 2.184699218469922, |
| "grad_norm": 0.25332963466644287, |
| "learning_rate": 6.9191979933492135e-06, |
| "loss": 0.0107, |
| "step": 3810 |
| }, |
| { |
| "epoch": 2.190435219043522, |
| "grad_norm": 0.47701334953308105, |
| "learning_rate": 6.900688791949463e-06, |
| "loss": 0.0087, |
| "step": 3820 |
| }, |
| { |
| "epoch": 2.196171219617122, |
| "grad_norm": 0.019721075892448425, |
| "learning_rate": 6.882149094348215e-06, |
| "loss": 0.0178, |
| "step": 3830 |
| }, |
| { |
| "epoch": 2.201907220190722, |
| "grad_norm": 0.057930897921323776, |
| "learning_rate": 6.863579198011506e-06, |
| "loss": 0.0291, |
| "step": 3840 |
| }, |
| { |
| "epoch": 2.207643220764322, |
| "grad_norm": 0.03594127669930458, |
| "learning_rate": 6.8449794008899e-06, |
| "loss": 0.005, |
| "step": 3850 |
| }, |
| { |
| "epoch": 2.207643220764322, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07210449874401093, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1052, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.94, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.494, |
| "step": 3850 |
| }, |
| { |
| "epoch": 2.213379221337922, |
| "grad_norm": 2.532087802886963, |
| "learning_rate": 6.826350001413713e-06, |
| "loss": 0.0085, |
| "step": 3860 |
| }, |
| { |
| "epoch": 2.219115221911522, |
| "grad_norm": 0.3755287230014801, |
| "learning_rate": 6.807691298488231e-06, |
| "loss": 0.0014, |
| "step": 3870 |
| }, |
| { |
| "epoch": 2.224851222485122, |
| "grad_norm": 0.09285666048526764, |
| "learning_rate": 6.789003591488902e-06, |
| "loss": 0.0013, |
| "step": 3880 |
| }, |
| { |
| "epoch": 2.2305872230587225, |
| "grad_norm": 3.115718126296997, |
| "learning_rate": 6.770287180256545e-06, |
| "loss": 0.0045, |
| "step": 3890 |
| }, |
| { |
| "epoch": 2.2363232236323225, |
| "grad_norm": 1.7172398567199707, |
| "learning_rate": 6.751542365092527e-06, |
| "loss": 0.0085, |
| "step": 3900 |
| }, |
| { |
| "epoch": 2.2363232236323225, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08293686807155609, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1262, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.909, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.478, |
| "step": 3900 |
| }, |
| { |
| "epoch": 2.2420592242059225, |
| "grad_norm": 0.004544651135802269, |
| "learning_rate": 6.732769446753954e-06, |
| "loss": 0.021, |
| "step": 3910 |
| }, |
| { |
| "epoch": 2.2477952247795225, |
| "grad_norm": 3.599937677383423, |
| "learning_rate": 6.713968726448844e-06, |
| "loss": 0.0067, |
| "step": 3920 |
| }, |
| { |
| "epoch": 2.2535312253531226, |
| "grad_norm": 0.9228914976119995, |
| "learning_rate": 6.69514050583129e-06, |
| "loss": 0.0097, |
| "step": 3930 |
| }, |
| { |
| "epoch": 2.2592672259267226, |
| "grad_norm": 0.005351903382688761, |
| "learning_rate": 6.676285086996623e-06, |
| "loss": 0.0353, |
| "step": 3940 |
| }, |
| { |
| "epoch": 2.2650032265003226, |
| "grad_norm": 0.07884957641363144, |
| "learning_rate": 6.657402772476563e-06, |
| "loss": 0.0092, |
| "step": 3950 |
| }, |
| { |
| "epoch": 2.2650032265003226, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09563428908586502, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.7675, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 29.999, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.022, |
| "step": 3950 |
| }, |
| { |
| "epoch": 2.2707392270739226, |
| "grad_norm": 1.1882566213607788, |
| "learning_rate": 6.638493865234369e-06, |
| "loss": 0.0132, |
| "step": 3960 |
| }, |
| { |
| "epoch": 2.2764752276475226, |
| "grad_norm": 0.13506627082824707, |
| "learning_rate": 6.619558668659975e-06, |
| "loss": 0.0219, |
| "step": 3970 |
| }, |
| { |
| "epoch": 2.2822112282211227, |
| "grad_norm": 0.007426030468195677, |
| "learning_rate": 6.600597486565119e-06, |
| "loss": 0.0216, |
| "step": 3980 |
| }, |
| { |
| "epoch": 2.2879472287947227, |
| "grad_norm": 0.27120983600616455, |
| "learning_rate": 6.581610623178476e-06, |
| "loss": 0.0153, |
| "step": 3990 |
| }, |
| { |
| "epoch": 2.293683229368323, |
| "grad_norm": 1.4845871925354004, |
| "learning_rate": 6.562598383140773e-06, |
| "loss": 0.0059, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2.293683229368323, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07171830534934998, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2153, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.78, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.413, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2.299419229941923, |
| "grad_norm": 1.7247122526168823, |
| "learning_rate": 6.543561071499893e-06, |
| "loss": 0.0216, |
| "step": 4010 |
| }, |
| { |
| "epoch": 2.305155230515523, |
| "grad_norm": 0.02364450879395008, |
| "learning_rate": 6.524498993706e-06, |
| "loss": 0.0244, |
| "step": 4020 |
| }, |
| { |
| "epoch": 2.310891231089123, |
| "grad_norm": 0.048632461577653885, |
| "learning_rate": 6.505412455606617e-06, |
| "loss": 0.0029, |
| "step": 4030 |
| }, |
| { |
| "epoch": 2.316627231662723, |
| "grad_norm": 0.12222401797771454, |
| "learning_rate": 6.486301763441732e-06, |
| "loss": 0.0027, |
| "step": 4040 |
| }, |
| { |
| "epoch": 2.3223632322363232, |
| "grad_norm": 0.07429647445678711, |
| "learning_rate": 6.467167223838879e-06, |
| "loss": 0.0119, |
| "step": 4050 |
| }, |
| { |
| "epoch": 2.3223632322363232, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09189260751008987, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1514, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.873, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.46, |
| "step": 4050 |
| }, |
| { |
| "epoch": 2.3280992328099233, |
| "grad_norm": 0.10564873367547989, |
| "learning_rate": 6.4480091438082225e-06, |
| "loss": 0.0328, |
| "step": 4060 |
| }, |
| { |
| "epoch": 2.3338352333835233, |
| "grad_norm": 0.01708606630563736, |
| "learning_rate": 6.4288278307376265e-06, |
| "loss": 0.015, |
| "step": 4070 |
| }, |
| { |
| "epoch": 2.3395712339571233, |
| "grad_norm": 0.25011512637138367, |
| "learning_rate": 6.4096235923877256e-06, |
| "loss": 0.0061, |
| "step": 4080 |
| }, |
| { |
| "epoch": 2.3453072345307233, |
| "grad_norm": 0.055370282381772995, |
| "learning_rate": 6.390396736886986e-06, |
| "loss": 0.007, |
| "step": 4090 |
| }, |
| { |
| "epoch": 2.3510432351043233, |
| "grad_norm": 0.030733373016119003, |
| "learning_rate": 6.371147572726761e-06, |
| "loss": 0.0017, |
| "step": 4100 |
| }, |
| { |
| "epoch": 2.3510432351043233, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08482550084590912, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1309, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.903, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.475, |
| "step": 4100 |
| }, |
| { |
| "epoch": 2.356779235677924, |
| "grad_norm": 0.17796050012111664, |
| "learning_rate": 6.351876408756344e-06, |
| "loss": 0.0053, |
| "step": 4110 |
| }, |
| { |
| "epoch": 2.3625152362515234, |
| "grad_norm": 0.0136833805590868, |
| "learning_rate": 6.332583554178009e-06, |
| "loss": 0.0044, |
| "step": 4120 |
| }, |
| { |
| "epoch": 2.368251236825124, |
| "grad_norm": 4.209476470947266, |
| "learning_rate": 6.313269318542057e-06, |
| "loss": 0.0259, |
| "step": 4130 |
| }, |
| { |
| "epoch": 2.373987237398724, |
| "grad_norm": 3.9427716732025146, |
| "learning_rate": 6.2939340117418355e-06, |
| "loss": 0.0237, |
| "step": 4140 |
| }, |
| { |
| "epoch": 2.379723237972324, |
| "grad_norm": 0.008540840819478035, |
| "learning_rate": 6.274577944008785e-06, |
| "loss": 0.0044, |
| "step": 4150 |
| }, |
| { |
| "epoch": 2.379723237972324, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07825496047735214, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1875, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.82, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.434, |
| "step": 4150 |
| }, |
| { |
| "epoch": 2.385459238545924, |
| "grad_norm": 0.01801919937133789, |
| "learning_rate": 6.255201425907442e-06, |
| "loss": 0.0002, |
| "step": 4160 |
| }, |
| { |
| "epoch": 2.391195239119524, |
| "grad_norm": 0.7031999230384827, |
| "learning_rate": 6.235804768330472e-06, |
| "loss": 0.0198, |
| "step": 4170 |
| }, |
| { |
| "epoch": 2.396931239693124, |
| "grad_norm": 0.03624948486685753, |
| "learning_rate": 6.21638828249367e-06, |
| "loss": 0.0096, |
| "step": 4180 |
| }, |
| { |
| "epoch": 2.402667240266724, |
| "grad_norm": 0.010821559466421604, |
| "learning_rate": 6.196952279930977e-06, |
| "loss": 0.0089, |
| "step": 4190 |
| }, |
| { |
| "epoch": 2.408403240840324, |
| "grad_norm": 0.01340206153690815, |
| "learning_rate": 6.177497072489473e-06, |
| "loss": 0.0227, |
| "step": 4200 |
| }, |
| { |
| "epoch": 2.408403240840324, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07348810136318207, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1832, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.826, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.437, |
| "step": 4200 |
| }, |
| { |
| "epoch": 2.414139241413924, |
| "grad_norm": 0.006387198343873024, |
| "learning_rate": 6.158022972324375e-06, |
| "loss": 0.0112, |
| "step": 4210 |
| }, |
| { |
| "epoch": 2.419875241987524, |
| "grad_norm": 0.1088046282529831, |
| "learning_rate": 6.138530291894033e-06, |
| "loss": 0.015, |
| "step": 4220 |
| }, |
| { |
| "epoch": 2.425611242561124, |
| "grad_norm": 0.010532280430197716, |
| "learning_rate": 6.119019343954914e-06, |
| "loss": 0.0012, |
| "step": 4230 |
| }, |
| { |
| "epoch": 2.4313472431347245, |
| "grad_norm": 2.5161547660827637, |
| "learning_rate": 6.099490441556582e-06, |
| "loss": 0.0054, |
| "step": 4240 |
| }, |
| { |
| "epoch": 2.4370832437083245, |
| "grad_norm": 0.41214823722839355, |
| "learning_rate": 6.07994389803668e-06, |
| "loss": 0.0067, |
| "step": 4250 |
| }, |
| { |
| "epoch": 2.4370832437083245, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08171182125806808, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1867, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.821, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.434, |
| "step": 4250 |
| }, |
| { |
| "epoch": 2.4428192442819245, |
| "grad_norm": 3.9505116939544678, |
| "learning_rate": 6.060380027015897e-06, |
| "loss": 0.0205, |
| "step": 4260 |
| }, |
| { |
| "epoch": 2.4485552448555246, |
| "grad_norm": 2.172741651535034, |
| "learning_rate": 6.040799142392937e-06, |
| "loss": 0.015, |
| "step": 4270 |
| }, |
| { |
| "epoch": 2.4542912454291246, |
| "grad_norm": 0.003915698733180761, |
| "learning_rate": 6.02120155833949e-06, |
| "loss": 0.0047, |
| "step": 4280 |
| }, |
| { |
| "epoch": 2.4600272460027246, |
| "grad_norm": 0.027446260675787926, |
| "learning_rate": 6.001587589295179e-06, |
| "loss": 0.0172, |
| "step": 4290 |
| }, |
| { |
| "epoch": 2.4657632465763246, |
| "grad_norm": 0.9420067667961121, |
| "learning_rate": 5.981957549962524e-06, |
| "loss": 0.0132, |
| "step": 4300 |
| }, |
| { |
| "epoch": 2.4657632465763246, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.06599417328834534, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2262, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.764, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.405, |
| "step": 4300 |
| }, |
| { |
| "epoch": 2.4714992471499246, |
| "grad_norm": 2.6476902961730957, |
| "learning_rate": 5.96231175530189e-06, |
| "loss": 0.01, |
| "step": 4310 |
| }, |
| { |
| "epoch": 2.4772352477235247, |
| "grad_norm": 0.03741572052240372, |
| "learning_rate": 5.942650520526432e-06, |
| "loss": 0.0102, |
| "step": 4320 |
| }, |
| { |
| "epoch": 2.4829712482971247, |
| "grad_norm": 0.012345872819423676, |
| "learning_rate": 5.9229741610970425e-06, |
| "loss": 0.0154, |
| "step": 4330 |
| }, |
| { |
| "epoch": 2.4887072488707247, |
| "grad_norm": 0.006493984255939722, |
| "learning_rate": 5.903282992717281e-06, |
| "loss": 0.0063, |
| "step": 4340 |
| }, |
| { |
| "epoch": 2.494443249444325, |
| "grad_norm": 0.011486309580504894, |
| "learning_rate": 5.883577331328316e-06, |
| "loss": 0.0005, |
| "step": 4350 |
| }, |
| { |
| "epoch": 2.494443249444325, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.0845269188284874, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1186, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.921, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.484, |
| "step": 4350 |
| }, |
| { |
| "epoch": 2.5001792500179247, |
| "grad_norm": 0.05512839928269386, |
| "learning_rate": 5.863857493103855e-06, |
| "loss": 0.0249, |
| "step": 4360 |
| }, |
| { |
| "epoch": 2.505915250591525, |
| "grad_norm": 0.010474382899701595, |
| "learning_rate": 5.84412379444507e-06, |
| "loss": 0.0007, |
| "step": 4370 |
| }, |
| { |
| "epoch": 2.511651251165125, |
| "grad_norm": 0.8734518885612488, |
| "learning_rate": 5.824376551975519e-06, |
| "loss": 0.0081, |
| "step": 4380 |
| }, |
| { |
| "epoch": 2.5173872517387252, |
| "grad_norm": 0.11771434545516968, |
| "learning_rate": 5.804616082536071e-06, |
| "loss": 0.0074, |
| "step": 4390 |
| }, |
| { |
| "epoch": 2.5231232523123253, |
| "grad_norm": 1.922683835029602, |
| "learning_rate": 5.784842703179814e-06, |
| "loss": 0.0328, |
| "step": 4400 |
| }, |
| { |
| "epoch": 2.5231232523123253, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07923904061317444, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.0857, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.969, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.508, |
| "step": 4400 |
| }, |
| { |
| "epoch": 2.5288592528859253, |
| "grad_norm": 4.321990013122559, |
| "learning_rate": 5.765056731166982e-06, |
| "loss": 0.0237, |
| "step": 4410 |
| }, |
| { |
| "epoch": 2.5345952534595253, |
| "grad_norm": 0.01736987754702568, |
| "learning_rate": 5.745258483959847e-06, |
| "loss": 0.0064, |
| "step": 4420 |
| }, |
| { |
| "epoch": 2.5403312540331253, |
| "grad_norm": 0.07172615826129913, |
| "learning_rate": 5.725448279217638e-06, |
| "loss": 0.0118, |
| "step": 4430 |
| }, |
| { |
| "epoch": 2.5460672546067253, |
| "grad_norm": 0.1578182578086853, |
| "learning_rate": 5.705626434791444e-06, |
| "loss": 0.0016, |
| "step": 4440 |
| }, |
| { |
| "epoch": 2.5518032551803254, |
| "grad_norm": 0.005266325548291206, |
| "learning_rate": 5.6857932687191e-06, |
| "loss": 0.0023, |
| "step": 4450 |
| }, |
| { |
| "epoch": 2.5518032551803254, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07244950532913208, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2865, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.677, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.362, |
| "step": 4450 |
| }, |
| { |
| "epoch": 2.557539255753926, |
| "grad_norm": 0.21443744003772736, |
| "learning_rate": 5.66594909922011e-06, |
| "loss": 0.0114, |
| "step": 4460 |
| }, |
| { |
| "epoch": 2.5632752563275254, |
| "grad_norm": 0.08916337788105011, |
| "learning_rate": 5.646094244690511e-06, |
| "loss": 0.0064, |
| "step": 4470 |
| }, |
| { |
| "epoch": 2.569011256901126, |
| "grad_norm": 2.983360528945923, |
| "learning_rate": 5.626229023697789e-06, |
| "loss": 0.0159, |
| "step": 4480 |
| }, |
| { |
| "epoch": 2.574747257474726, |
| "grad_norm": 0.06603588908910751, |
| "learning_rate": 5.606353754975755e-06, |
| "loss": 0.0104, |
| "step": 4490 |
| }, |
| { |
| "epoch": 2.580483258048326, |
| "grad_norm": 0.9153593182563782, |
| "learning_rate": 5.586468757419433e-06, |
| "loss": 0.0012, |
| "step": 4500 |
| }, |
| { |
| "epoch": 2.580483258048326, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07681399583816528, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.3831, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.538, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.292, |
| "step": 4500 |
| }, |
| { |
| "epoch": 2.586219258621926, |
| "grad_norm": 0.030913453549146652, |
| "learning_rate": 5.566574350079946e-06, |
| "loss": 0.0139, |
| "step": 4510 |
| }, |
| { |
| "epoch": 2.591955259195526, |
| "grad_norm": 3.312136650085449, |
| "learning_rate": 5.546670852159396e-06, |
| "loss": 0.0074, |
| "step": 4520 |
| }, |
| { |
| "epoch": 2.597691259769126, |
| "grad_norm": 0.008490420877933502, |
| "learning_rate": 5.526758583005736e-06, |
| "loss": 0.008, |
| "step": 4530 |
| }, |
| { |
| "epoch": 2.603427260342726, |
| "grad_norm": 0.010648602619767189, |
| "learning_rate": 5.50683786210766e-06, |
| "loss": 0.0051, |
| "step": 4540 |
| }, |
| { |
| "epoch": 2.609163260916326, |
| "grad_norm": 2.533731460571289, |
| "learning_rate": 5.486909009089463e-06, |
| "loss": 0.0185, |
| "step": 4550 |
| }, |
| { |
| "epoch": 2.609163260916326, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07284829020500183, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1938, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.811, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.429, |
| "step": 4550 |
| }, |
| { |
| "epoch": 2.614899261489926, |
| "grad_norm": 0.0175775233656168, |
| "learning_rate": 5.4669723437059194e-06, |
| "loss": 0.0015, |
| "step": 4560 |
| }, |
| { |
| "epoch": 2.6206352620635265, |
| "grad_norm": 0.00764029985293746, |
| "learning_rate": 5.4470281858371555e-06, |
| "loss": 0.0014, |
| "step": 4570 |
| }, |
| { |
| "epoch": 2.626371262637126, |
| "grad_norm": 0.4708549380302429, |
| "learning_rate": 5.4270768554835056e-06, |
| "loss": 0.0023, |
| "step": 4580 |
| }, |
| { |
| "epoch": 2.6321072632107265, |
| "grad_norm": 0.06411808729171753, |
| "learning_rate": 5.407118672760393e-06, |
| "loss": 0.0037, |
| "step": 4590 |
| }, |
| { |
| "epoch": 2.6378432637843265, |
| "grad_norm": 0.009167805314064026, |
| "learning_rate": 5.387153957893181e-06, |
| "loss": 0.0016, |
| "step": 4600 |
| }, |
| { |
| "epoch": 2.6378432637843265, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09603765606880188, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2377, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.747, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.397, |
| "step": 4600 |
| }, |
| { |
| "epoch": 2.6435792643579266, |
| "grad_norm": 0.0018381074769422412, |
| "learning_rate": 5.367183031212041e-06, |
| "loss": 0.007, |
| "step": 4610 |
| }, |
| { |
| "epoch": 2.6493152649315266, |
| "grad_norm": 0.0011304231593385339, |
| "learning_rate": 5.347206213146813e-06, |
| "loss": 0.0277, |
| "step": 4620 |
| }, |
| { |
| "epoch": 2.6550512655051266, |
| "grad_norm": 4.376464366912842, |
| "learning_rate": 5.327223824221862e-06, |
| "loss": 0.0093, |
| "step": 4630 |
| }, |
| { |
| "epoch": 2.6607872660787266, |
| "grad_norm": 0.031111005693674088, |
| "learning_rate": 5.307236185050937e-06, |
| "loss": 0.0029, |
| "step": 4640 |
| }, |
| { |
| "epoch": 2.6665232666523266, |
| "grad_norm": 2.6803221702575684, |
| "learning_rate": 5.287243616332027e-06, |
| "loss": 0.0145, |
| "step": 4650 |
| }, |
| { |
| "epoch": 2.6665232666523266, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.10255688428878784, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2291, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.76, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.403, |
| "step": 4650 |
| }, |
| { |
| "epoch": 2.6722592672259267, |
| "grad_norm": 0.03457150608301163, |
| "learning_rate": 5.267246438842213e-06, |
| "loss": 0.005, |
| "step": 4660 |
| }, |
| { |
| "epoch": 2.6779952677995267, |
| "grad_norm": 4.120417594909668, |
| "learning_rate": 5.247244973432524e-06, |
| "loss": 0.0141, |
| "step": 4670 |
| }, |
| { |
| "epoch": 2.6837312683731267, |
| "grad_norm": 0.005652038846164942, |
| "learning_rate": 5.227239541022786e-06, |
| "loss": 0.0034, |
| "step": 4680 |
| }, |
| { |
| "epoch": 2.6894672689467267, |
| "grad_norm": 2.9149153232574463, |
| "learning_rate": 5.2072304625964785e-06, |
| "loss": 0.0061, |
| "step": 4690 |
| }, |
| { |
| "epoch": 2.695203269520327, |
| "grad_norm": 0.0008329672855325043, |
| "learning_rate": 5.187218059195578e-06, |
| "loss": 0.0047, |
| "step": 4700 |
| }, |
| { |
| "epoch": 2.695203269520327, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.10345083475112915, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2387, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.746, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.396, |
| "step": 4700 |
| }, |
| { |
| "epoch": 2.7009392700939268, |
| "grad_norm": 1.024248480796814, |
| "learning_rate": 5.167202651915409e-06, |
| "loss": 0.0071, |
| "step": 4710 |
| }, |
| { |
| "epoch": 2.7066752706675272, |
| "grad_norm": 0.014447176828980446, |
| "learning_rate": 5.147184561899495e-06, |
| "loss": 0.0076, |
| "step": 4720 |
| }, |
| { |
| "epoch": 2.7124112712411272, |
| "grad_norm": 5.958902835845947, |
| "learning_rate": 5.1271641103344e-06, |
| "loss": 0.0116, |
| "step": 4730 |
| }, |
| { |
| "epoch": 2.7181472718147273, |
| "grad_norm": 0.016329055652022362, |
| "learning_rate": 5.1071416184445845e-06, |
| "loss": 0.0105, |
| "step": 4740 |
| }, |
| { |
| "epoch": 2.7238832723883273, |
| "grad_norm": 0.4175659716129303, |
| "learning_rate": 5.087117407487239e-06, |
| "loss": 0.0166, |
| "step": 4750 |
| }, |
| { |
| "epoch": 2.7238832723883273, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08455558121204376, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2591, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.716, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.382, |
| "step": 4750 |
| }, |
| { |
| "epoch": 2.7296192729619273, |
| "grad_norm": 0.022596385329961777, |
| "learning_rate": 5.06709179874714e-06, |
| "loss": 0.0009, |
| "step": 4760 |
| }, |
| { |
| "epoch": 2.7353552735355273, |
| "grad_norm": 0.0726088285446167, |
| "learning_rate": 5.047065113531493e-06, |
| "loss": 0.0254, |
| "step": 4770 |
| }, |
| { |
| "epoch": 2.7410912741091273, |
| "grad_norm": 0.035875000059604645, |
| "learning_rate": 5.02703767316477e-06, |
| "loss": 0.0244, |
| "step": 4780 |
| }, |
| { |
| "epoch": 2.7468272746827274, |
| "grad_norm": 3.32077956199646, |
| "learning_rate": 5.00700979898356e-06, |
| "loss": 0.006, |
| "step": 4790 |
| }, |
| { |
| "epoch": 2.7525632752563274, |
| "grad_norm": 1.0301790237426758, |
| "learning_rate": 4.98698181233142e-06, |
| "loss": 0.0059, |
| "step": 4800 |
| }, |
| { |
| "epoch": 2.7525632752563274, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07655075937509537, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2238, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.767, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.407, |
| "step": 4800 |
| }, |
| { |
| "epoch": 2.758299275829928, |
| "grad_norm": 0.446961373090744, |
| "learning_rate": 4.966954034553699e-06, |
| "loss": 0.0087, |
| "step": 4810 |
| }, |
| { |
| "epoch": 2.7640352764035274, |
| "grad_norm": 0.33151447772979736, |
| "learning_rate": 4.946926786992407e-06, |
| "loss": 0.0009, |
| "step": 4820 |
| }, |
| { |
| "epoch": 2.769771276977128, |
| "grad_norm": 0.12154054641723633, |
| "learning_rate": 4.9269003909810405e-06, |
| "loss": 0.0055, |
| "step": 4830 |
| }, |
| { |
| "epoch": 2.775507277550728, |
| "grad_norm": 0.016543418169021606, |
| "learning_rate": 4.906875167839433e-06, |
| "loss": 0.0373, |
| "step": 4840 |
| }, |
| { |
| "epoch": 2.781243278124328, |
| "grad_norm": 0.018002478405833244, |
| "learning_rate": 4.886851438868599e-06, |
| "loss": 0.0133, |
| "step": 4850 |
| }, |
| { |
| "epoch": 2.781243278124328, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07717321813106537, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.202, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.799, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.423, |
| "step": 4850 |
| }, |
| { |
| "epoch": 2.786979278697928, |
| "grad_norm": 0.01707332953810692, |
| "learning_rate": 4.866829525345585e-06, |
| "loss": 0.0166, |
| "step": 4860 |
| }, |
| { |
| "epoch": 2.792715279271528, |
| "grad_norm": 0.00804219115525484, |
| "learning_rate": 4.846809748518302e-06, |
| "loss": 0.0015, |
| "step": 4870 |
| }, |
| { |
| "epoch": 2.798451279845128, |
| "grad_norm": 0.02389547787606716, |
| "learning_rate": 4.826792429600381e-06, |
| "loss": 0.0021, |
| "step": 4880 |
| }, |
| { |
| "epoch": 2.804187280418728, |
| "grad_norm": 0.005223631393164396, |
| "learning_rate": 4.806777889766016e-06, |
| "loss": 0.0136, |
| "step": 4890 |
| }, |
| { |
| "epoch": 2.809923280992328, |
| "grad_norm": 0.20156431198120117, |
| "learning_rate": 4.78676645014481e-06, |
| "loss": 0.0093, |
| "step": 4900 |
| }, |
| { |
| "epoch": 2.809923280992328, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.0736735612154007, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.151, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.873, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.46, |
| "step": 4900 |
| }, |
| { |
| "epoch": 2.815659281565928, |
| "grad_norm": 0.0024203194770962, |
| "learning_rate": 4.766758431816629e-06, |
| "loss": 0.0052, |
| "step": 4910 |
| }, |
| { |
| "epoch": 2.821395282139528, |
| "grad_norm": 0.031604766845703125, |
| "learning_rate": 4.746754155806437e-06, |
| "loss": 0.0095, |
| "step": 4920 |
| }, |
| { |
| "epoch": 2.827131282713128, |
| "grad_norm": 3.787029266357422, |
| "learning_rate": 4.72675394307916e-06, |
| "loss": 0.0139, |
| "step": 4930 |
| }, |
| { |
| "epoch": 2.8328672832867285, |
| "grad_norm": 0.07122969627380371, |
| "learning_rate": 4.7067581145345226e-06, |
| "loss": 0.0139, |
| "step": 4940 |
| }, |
| { |
| "epoch": 2.838603283860328, |
| "grad_norm": 3.0758485794067383, |
| "learning_rate": 4.686766991001913e-06, |
| "loss": 0.0161, |
| "step": 4950 |
| }, |
| { |
| "epoch": 2.838603283860328, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08140452206134796, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.151, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.873, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.46, |
| "step": 4950 |
| }, |
| { |
| "epoch": 2.8443392844339286, |
| "grad_norm": 0.07921534031629562, |
| "learning_rate": 4.666780893235227e-06, |
| "loss": 0.0006, |
| "step": 4960 |
| }, |
| { |
| "epoch": 2.8500752850075286, |
| "grad_norm": 0.12975841760635376, |
| "learning_rate": 4.646800141907717e-06, |
| "loss": 0.0154, |
| "step": 4970 |
| }, |
| { |
| "epoch": 2.8558112855811286, |
| "grad_norm": 0.0262366384267807, |
| "learning_rate": 4.626825057606859e-06, |
| "loss": 0.0093, |
| "step": 4980 |
| }, |
| { |
| "epoch": 2.8615472861547286, |
| "grad_norm": 0.00262279505841434, |
| "learning_rate": 4.606855960829199e-06, |
| "loss": 0.0202, |
| "step": 4990 |
| }, |
| { |
| "epoch": 2.8672832867283287, |
| "grad_norm": 0.01955203339457512, |
| "learning_rate": 4.586893171975218e-06, |
| "loss": 0.0266, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.8672832867283287, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07921645790338516, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.3258, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.62, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.334, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.8730192873019287, |
| "grad_norm": 0.10377766937017441, |
| "learning_rate": 4.566937011344184e-06, |
| "loss": 0.0017, |
| "step": 5010 |
| }, |
| { |
| "epoch": 2.8787552878755287, |
| "grad_norm": 0.784302294254303, |
| "learning_rate": 4.546987799129018e-06, |
| "loss": 0.0046, |
| "step": 5020 |
| }, |
| { |
| "epoch": 2.8844912884491287, |
| "grad_norm": 2.035209894180298, |
| "learning_rate": 4.527045855411153e-06, |
| "loss": 0.0119, |
| "step": 5030 |
| }, |
| { |
| "epoch": 2.8902272890227287, |
| "grad_norm": 3.6558942794799805, |
| "learning_rate": 4.507111500155407e-06, |
| "loss": 0.0123, |
| "step": 5040 |
| }, |
| { |
| "epoch": 2.895963289596329, |
| "grad_norm": 3.73490309715271, |
| "learning_rate": 4.487185053204832e-06, |
| "loss": 0.0073, |
| "step": 5050 |
| }, |
| { |
| "epoch": 2.895963289596329, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07410901039838791, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.3293, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.615, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.331, |
| "step": 5050 |
| }, |
| { |
| "epoch": 2.901699290169929, |
| "grad_norm": 0.008407690562307835, |
| "learning_rate": 4.467266834275601e-06, |
| "loss": 0.0191, |
| "step": 5060 |
| }, |
| { |
| "epoch": 2.9074352907435292, |
| "grad_norm": 0.03255997970700264, |
| "learning_rate": 4.447357162951865e-06, |
| "loss": 0.0458, |
| "step": 5070 |
| }, |
| { |
| "epoch": 2.9131712913171293, |
| "grad_norm": 1.6957069635391235, |
| "learning_rate": 4.427456358680635e-06, |
| "loss": 0.0236, |
| "step": 5080 |
| }, |
| { |
| "epoch": 2.9189072918907293, |
| "grad_norm": 0.1675146073102951, |
| "learning_rate": 4.407564740766648e-06, |
| "loss": 0.0177, |
| "step": 5090 |
| }, |
| { |
| "epoch": 2.9246432924643293, |
| "grad_norm": 0.04229651764035225, |
| "learning_rate": 4.3876826283672485e-06, |
| "loss": 0.0116, |
| "step": 5100 |
| }, |
| { |
| "epoch": 2.9246432924643293, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.06259483098983765, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.178, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.834, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.441, |
| "step": 5100 |
| }, |
| { |
| "epoch": 2.9303792930379293, |
| "grad_norm": 0.04005512595176697, |
| "learning_rate": 4.367810340487267e-06, |
| "loss": 0.0099, |
| "step": 5110 |
| }, |
| { |
| "epoch": 2.9361152936115293, |
| "grad_norm": 0.1425451785326004, |
| "learning_rate": 4.347948195973901e-06, |
| "loss": 0.0033, |
| "step": 5120 |
| }, |
| { |
| "epoch": 2.9418512941851294, |
| "grad_norm": 0.10147175192832947, |
| "learning_rate": 4.328096513511601e-06, |
| "loss": 0.0076, |
| "step": 5130 |
| }, |
| { |
| "epoch": 2.9475872947587294, |
| "grad_norm": 0.13407284021377563, |
| "learning_rate": 4.308255611616954e-06, |
| "loss": 0.0034, |
| "step": 5140 |
| }, |
| { |
| "epoch": 2.9533232953323294, |
| "grad_norm": 0.12246271222829819, |
| "learning_rate": 4.2884258086335755e-06, |
| "loss": 0.0077, |
| "step": 5150 |
| }, |
| { |
| "epoch": 2.9533232953323294, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07015232741832733, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2126, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.784, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.415, |
| "step": 5150 |
| }, |
| { |
| "epoch": 2.95905929590593, |
| "grad_norm": 0.06634827703237534, |
| "learning_rate": 4.268607422727e-06, |
| "loss": 0.0131, |
| "step": 5160 |
| }, |
| { |
| "epoch": 2.9647952964795294, |
| "grad_norm": 2.3556761741638184, |
| "learning_rate": 4.248800771879581e-06, |
| "loss": 0.029, |
| "step": 5170 |
| }, |
| { |
| "epoch": 2.97053129705313, |
| "grad_norm": 0.03471173346042633, |
| "learning_rate": 4.229006173885381e-06, |
| "loss": 0.0021, |
| "step": 5180 |
| }, |
| { |
| "epoch": 2.97626729762673, |
| "grad_norm": 0.006328817922621965, |
| "learning_rate": 4.2092239463450775e-06, |
| "loss": 0.0212, |
| "step": 5190 |
| }, |
| { |
| "epoch": 2.98200329820033, |
| "grad_norm": 0.02347049117088318, |
| "learning_rate": 4.189454406660865e-06, |
| "loss": 0.0056, |
| "step": 5200 |
| }, |
| { |
| "epoch": 2.98200329820033, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.06551730632781982, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.5411, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.314, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.18, |
| "step": 5200 |
| }, |
| { |
| "epoch": 2.98773929877393, |
| "grad_norm": 0.012669041752815247, |
| "learning_rate": 4.169697872031368e-06, |
| "loss": 0.012, |
| "step": 5210 |
| }, |
| { |
| "epoch": 2.99347529934753, |
| "grad_norm": 0.07477905601263046, |
| "learning_rate": 4.1499546594465465e-06, |
| "loss": 0.0215, |
| "step": 5220 |
| }, |
| { |
| "epoch": 2.99921129992113, |
| "grad_norm": 1.7680764198303223, |
| "learning_rate": 4.1302250856826045e-06, |
| "loss": 0.0107, |
| "step": 5230 |
| }, |
| { |
| "epoch": 3.00458880045888, |
| "grad_norm": 0.19178365170955658, |
| "learning_rate": 4.110509467296923e-06, |
| "loss": 0.006, |
| "step": 5240 |
| }, |
| { |
| "epoch": 3.01032480103248, |
| "grad_norm": 0.025907142087817192, |
| "learning_rate": 4.090808120622961e-06, |
| "loss": 0.0139, |
| "step": 5250 |
| }, |
| { |
| "epoch": 3.01032480103248, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07205013185739517, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2727, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.697, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.372, |
| "step": 5250 |
| }, |
| { |
| "epoch": 3.01606080160608, |
| "grad_norm": 0.018714534118771553, |
| "learning_rate": 4.071121361765201e-06, |
| "loss": 0.0033, |
| "step": 5260 |
| }, |
| { |
| "epoch": 3.02179680217968, |
| "grad_norm": 2.1166880130767822, |
| "learning_rate": 4.05144950659406e-06, |
| "loss": 0.0081, |
| "step": 5270 |
| }, |
| { |
| "epoch": 3.02753280275328, |
| "grad_norm": 0.07031437754631042, |
| "learning_rate": 4.031792870740831e-06, |
| "loss": 0.0086, |
| "step": 5280 |
| }, |
| { |
| "epoch": 3.03326880332688, |
| "grad_norm": 0.24249830842018127, |
| "learning_rate": 4.012151769592612e-06, |
| "loss": 0.0132, |
| "step": 5290 |
| }, |
| { |
| "epoch": 3.0390048039004802, |
| "grad_norm": 0.009602251462638378, |
| "learning_rate": 3.992526518287258e-06, |
| "loss": 0.0075, |
| "step": 5300 |
| }, |
| { |
| "epoch": 3.0390048039004802, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07945062220096588, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1773, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.835, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.441, |
| "step": 5300 |
| }, |
| { |
| "epoch": 3.0447408044740802, |
| "grad_norm": 0.1440117210149765, |
| "learning_rate": 3.972917431708305e-06, |
| "loss": 0.0013, |
| "step": 5310 |
| }, |
| { |
| "epoch": 3.0504768050476807, |
| "grad_norm": 0.013155910186469555, |
| "learning_rate": 3.9533248244799375e-06, |
| "loss": 0.0049, |
| "step": 5320 |
| }, |
| { |
| "epoch": 3.0562128056212807, |
| "grad_norm": 0.1568404585123062, |
| "learning_rate": 3.933749010961927e-06, |
| "loss": 0.0024, |
| "step": 5330 |
| }, |
| { |
| "epoch": 3.0619488061948807, |
| "grad_norm": 0.00445369491353631, |
| "learning_rate": 3.914190305244595e-06, |
| "loss": 0.0024, |
| "step": 5340 |
| }, |
| { |
| "epoch": 3.0676848067684808, |
| "grad_norm": 0.15039828419685364, |
| "learning_rate": 3.8946490211437735e-06, |
| "loss": 0.02, |
| "step": 5350 |
| }, |
| { |
| "epoch": 3.0676848067684808, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08091636747121811, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2042, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.796, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.421, |
| "step": 5350 |
| }, |
| { |
| "epoch": 3.073420807342081, |
| "grad_norm": 0.13300937414169312, |
| "learning_rate": 3.875125472195764e-06, |
| "loss": 0.0012, |
| "step": 5360 |
| }, |
| { |
| "epoch": 3.079156807915681, |
| "grad_norm": 2.184394121170044, |
| "learning_rate": 3.855619971652314e-06, |
| "loss": 0.0117, |
| "step": 5370 |
| }, |
| { |
| "epoch": 3.084892808489281, |
| "grad_norm": 0.02020282857120037, |
| "learning_rate": 3.836132832475583e-06, |
| "loss": 0.0014, |
| "step": 5380 |
| }, |
| { |
| "epoch": 3.090628809062881, |
| "grad_norm": 0.008466456085443497, |
| "learning_rate": 3.816664367333131e-06, |
| "loss": 0.009, |
| "step": 5390 |
| }, |
| { |
| "epoch": 3.096364809636481, |
| "grad_norm": 5.091494560241699, |
| "learning_rate": 3.797214888592896e-06, |
| "loss": 0.0128, |
| "step": 5400 |
| }, |
| { |
| "epoch": 3.096364809636481, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07716992497444153, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2065, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.792, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.42, |
| "step": 5400 |
| }, |
| { |
| "epoch": 3.102100810210081, |
| "grad_norm": 0.20820866525173187, |
| "learning_rate": 3.777784708318178e-06, |
| "loss": 0.0184, |
| "step": 5410 |
| }, |
| { |
| "epoch": 3.107836810783681, |
| "grad_norm": 1.1382921934127808, |
| "learning_rate": 3.7583741382626402e-06, |
| "loss": 0.0093, |
| "step": 5420 |
| }, |
| { |
| "epoch": 3.113572811357281, |
| "grad_norm": 0.38132885098457336, |
| "learning_rate": 3.7389834898653067e-06, |
| "loss": 0.0117, |
| "step": 5430 |
| }, |
| { |
| "epoch": 3.1193088119308814, |
| "grad_norm": 0.009956207126379013, |
| "learning_rate": 3.719613074245555e-06, |
| "loss": 0.0017, |
| "step": 5440 |
| }, |
| { |
| "epoch": 3.1250448125044814, |
| "grad_norm": 5.792750358581543, |
| "learning_rate": 3.7002632021981368e-06, |
| "loss": 0.0146, |
| "step": 5450 |
| }, |
| { |
| "epoch": 3.1250448125044814, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.0894627794623375, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2897, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.672, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.36, |
| "step": 5450 |
| }, |
| { |
| "epoch": 3.1307808130780814, |
| "grad_norm": 1.089165210723877, |
| "learning_rate": 3.680934184188182e-06, |
| "loss": 0.0032, |
| "step": 5460 |
| }, |
| { |
| "epoch": 3.1365168136516814, |
| "grad_norm": 0.020885087549686432, |
| "learning_rate": 3.661626330346224e-06, |
| "loss": 0.0037, |
| "step": 5470 |
| }, |
| { |
| "epoch": 3.1422528142252815, |
| "grad_norm": 0.09390339255332947, |
| "learning_rate": 3.642339950463224e-06, |
| "loss": 0.0083, |
| "step": 5480 |
| }, |
| { |
| "epoch": 3.1479888147988815, |
| "grad_norm": 0.0025120277423411608, |
| "learning_rate": 3.62307535398559e-06, |
| "loss": 0.0108, |
| "step": 5490 |
| }, |
| { |
| "epoch": 3.1537248153724815, |
| "grad_norm": 0.06790509074926376, |
| "learning_rate": 3.603832850010226e-06, |
| "loss": 0.0012, |
| "step": 5500 |
| }, |
| { |
| "epoch": 3.1537248153724815, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08822309225797653, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.3502, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.585, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.316, |
| "step": 5500 |
| }, |
| { |
| "epoch": 3.1594608159460815, |
| "grad_norm": 0.07959645241498947, |
| "learning_rate": 3.58461274727956e-06, |
| "loss": 0.0075, |
| "step": 5510 |
| }, |
| { |
| "epoch": 3.1651968165196815, |
| "grad_norm": 3.0567445755004883, |
| "learning_rate": 3.5654153541766023e-06, |
| "loss": 0.008, |
| "step": 5520 |
| }, |
| { |
| "epoch": 3.1709328170932816, |
| "grad_norm": 0.20890028774738312, |
| "learning_rate": 3.546240978719988e-06, |
| "loss": 0.0006, |
| "step": 5530 |
| }, |
| { |
| "epoch": 3.1766688176668816, |
| "grad_norm": 2.681074619293213, |
| "learning_rate": 3.5270899285590375e-06, |
| "loss": 0.0027, |
| "step": 5540 |
| }, |
| { |
| "epoch": 3.1824048182404816, |
| "grad_norm": 0.04251394048333168, |
| "learning_rate": 3.5079625109688243e-06, |
| "loss": 0.0005, |
| "step": 5550 |
| }, |
| { |
| "epoch": 3.1824048182404816, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09866516292095184, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2324, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.755, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.401, |
| "step": 5550 |
| }, |
| { |
| "epoch": 3.188140818814082, |
| "grad_norm": 4.062971591949463, |
| "learning_rate": 3.4888590328452353e-06, |
| "loss": 0.0178, |
| "step": 5560 |
| }, |
| { |
| "epoch": 3.193876819387682, |
| "grad_norm": 0.0014892960898578167, |
| "learning_rate": 3.4697798007000624e-06, |
| "loss": 0.0126, |
| "step": 5570 |
| }, |
| { |
| "epoch": 3.199612819961282, |
| "grad_norm": 0.005618450231850147, |
| "learning_rate": 3.450725120656069e-06, |
| "loss": 0.0261, |
| "step": 5580 |
| }, |
| { |
| "epoch": 3.205348820534882, |
| "grad_norm": 1.2523528337478638, |
| "learning_rate": 3.431695298442084e-06, |
| "loss": 0.0061, |
| "step": 5590 |
| }, |
| { |
| "epoch": 3.211084821108482, |
| "grad_norm": 3.6290197372436523, |
| "learning_rate": 3.4126906393881e-06, |
| "loss": 0.0177, |
| "step": 5600 |
| }, |
| { |
| "epoch": 3.211084821108482, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07931295037269592, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2163, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.778, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.413, |
| "step": 5600 |
| }, |
| { |
| "epoch": 3.216820821682082, |
| "grad_norm": 0.015163871459662914, |
| "learning_rate": 3.393711448420372e-06, |
| "loss": 0.0057, |
| "step": 5610 |
| }, |
| { |
| "epoch": 3.222556822255682, |
| "grad_norm": 0.059904176741838455, |
| "learning_rate": 3.37475803005652e-06, |
| "loss": 0.0017, |
| "step": 5620 |
| }, |
| { |
| "epoch": 3.228292822829282, |
| "grad_norm": 0.3671509623527527, |
| "learning_rate": 3.355830688400652e-06, |
| "loss": 0.0211, |
| "step": 5630 |
| }, |
| { |
| "epoch": 3.2340288234028822, |
| "grad_norm": 2.3451545238494873, |
| "learning_rate": 3.336929727138474e-06, |
| "loss": 0.0221, |
| "step": 5640 |
| }, |
| { |
| "epoch": 3.2397648239764822, |
| "grad_norm": 0.00577126070857048, |
| "learning_rate": 3.31805544953243e-06, |
| "loss": 0.0082, |
| "step": 5650 |
| }, |
| { |
| "epoch": 3.2397648239764822, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07332266122102737, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1867, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.821, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.434, |
| "step": 5650 |
| }, |
| { |
| "epoch": 3.2455008245500823, |
| "grad_norm": 1.244507074356079, |
| "learning_rate": 3.299208158416829e-06, |
| "loss": 0.0177, |
| "step": 5660 |
| }, |
| { |
| "epoch": 3.2512368251236827, |
| "grad_norm": 1.7493702173233032, |
| "learning_rate": 3.2803881561929806e-06, |
| "loss": 0.0182, |
| "step": 5670 |
| }, |
| { |
| "epoch": 3.2569728256972827, |
| "grad_norm": 0.03632393479347229, |
| "learning_rate": 3.2615957448243562e-06, |
| "loss": 0.0075, |
| "step": 5680 |
| }, |
| { |
| "epoch": 3.2627088262708828, |
| "grad_norm": 0.021715901792049408, |
| "learning_rate": 3.2428312258317306e-06, |
| "loss": 0.0044, |
| "step": 5690 |
| }, |
| { |
| "epoch": 3.268444826844483, |
| "grad_norm": 0.7747498154640198, |
| "learning_rate": 3.224094900288357e-06, |
| "loss": 0.0071, |
| "step": 5700 |
| }, |
| { |
| "epoch": 3.268444826844483, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08630760759115219, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1329, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.9, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.474, |
| "step": 5700 |
| }, |
| { |
| "epoch": 3.274180827418083, |
| "grad_norm": 0.003438598709180951, |
| "learning_rate": 3.205387068815127e-06, |
| "loss": 0.0025, |
| "step": 5710 |
| }, |
| { |
| "epoch": 3.279916827991683, |
| "grad_norm": 0.02451498433947563, |
| "learning_rate": 3.1867080315757477e-06, |
| "loss": 0.0004, |
| "step": 5720 |
| }, |
| { |
| "epoch": 3.285652828565283, |
| "grad_norm": 0.4422462582588196, |
| "learning_rate": 3.1680580882719304e-06, |
| "loss": 0.0206, |
| "step": 5730 |
| }, |
| { |
| "epoch": 3.291388829138883, |
| "grad_norm": 3.2265453338623047, |
| "learning_rate": 3.149437538138583e-06, |
| "loss": 0.0142, |
| "step": 5740 |
| }, |
| { |
| "epoch": 3.297124829712483, |
| "grad_norm": 0.015962867066264153, |
| "learning_rate": 3.130846679938998e-06, |
| "loss": 0.0099, |
| "step": 5750 |
| }, |
| { |
| "epoch": 3.297124829712483, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07895597815513611, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1289, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.906, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.476, |
| "step": 5750 |
| }, |
| { |
| "epoch": 3.302860830286083, |
| "grad_norm": 0.470051109790802, |
| "learning_rate": 3.1122858119600726e-06, |
| "loss": 0.0031, |
| "step": 5760 |
| }, |
| { |
| "epoch": 3.308596830859683, |
| "grad_norm": 0.002947809174656868, |
| "learning_rate": 3.0937552320075116e-06, |
| "loss": 0.0005, |
| "step": 5770 |
| }, |
| { |
| "epoch": 3.3143328314332834, |
| "grad_norm": 4.272603511810303, |
| "learning_rate": 3.0752552374010567e-06, |
| "loss": 0.0185, |
| "step": 5780 |
| }, |
| { |
| "epoch": 3.320068832006883, |
| "grad_norm": 0.0015301775420084596, |
| "learning_rate": 3.056786124969716e-06, |
| "loss": 0.0012, |
| "step": 5790 |
| }, |
| { |
| "epoch": 3.3258048325804834, |
| "grad_norm": 0.002659064019098878, |
| "learning_rate": 3.0383481910469936e-06, |
| "loss": 0.004, |
| "step": 5800 |
| }, |
| { |
| "epoch": 3.3258048325804834, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08382538706064224, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1553, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.867, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.457, |
| "step": 5800 |
| }, |
| { |
| "epoch": 3.3315408331540834, |
| "grad_norm": 0.25469204783439636, |
| "learning_rate": 3.019941731466143e-06, |
| "loss": 0.0005, |
| "step": 5810 |
| }, |
| { |
| "epoch": 3.3372768337276835, |
| "grad_norm": 0.5178417563438416, |
| "learning_rate": 3.0015670415554143e-06, |
| "loss": 0.016, |
| "step": 5820 |
| }, |
| { |
| "epoch": 3.3430128343012835, |
| "grad_norm": 0.07551216334104538, |
| "learning_rate": 2.9832244161333257e-06, |
| "loss": 0.0202, |
| "step": 5830 |
| }, |
| { |
| "epoch": 3.3487488348748835, |
| "grad_norm": 0.008605745621025562, |
| "learning_rate": 2.9649141495039225e-06, |
| "loss": 0.0009, |
| "step": 5840 |
| }, |
| { |
| "epoch": 3.3544848354484835, |
| "grad_norm": 0.0697212815284729, |
| "learning_rate": 2.9466365354520564e-06, |
| "loss": 0.0204, |
| "step": 5850 |
| }, |
| { |
| "epoch": 3.3544848354484835, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07445970177650452, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2129, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.783, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.415, |
| "step": 5850 |
| }, |
| { |
| "epoch": 3.3602208360220835, |
| "grad_norm": 0.017461596056818962, |
| "learning_rate": 2.928391867238679e-06, |
| "loss": 0.0012, |
| "step": 5860 |
| }, |
| { |
| "epoch": 3.3659568365956836, |
| "grad_norm": 0.0013357176212593913, |
| "learning_rate": 2.910180437596132e-06, |
| "loss": 0.0036, |
| "step": 5870 |
| }, |
| { |
| "epoch": 3.3716928371692836, |
| "grad_norm": 0.00179756130091846, |
| "learning_rate": 2.8920025387234484e-06, |
| "loss": 0.0131, |
| "step": 5880 |
| }, |
| { |
| "epoch": 3.3774288377428836, |
| "grad_norm": 0.005055127199739218, |
| "learning_rate": 2.8738584622816656e-06, |
| "loss": 0.0133, |
| "step": 5890 |
| }, |
| { |
| "epoch": 3.3831648383164836, |
| "grad_norm": 0.778300940990448, |
| "learning_rate": 2.8557484993891484e-06, |
| "loss": 0.007, |
| "step": 5900 |
| }, |
| { |
| "epoch": 3.3831648383164836, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08228859305381775, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2282, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.761, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.404, |
| "step": 5900 |
| }, |
| { |
| "epoch": 3.388900838890084, |
| "grad_norm": 0.05169231817126274, |
| "learning_rate": 2.837672940616911e-06, |
| "loss": 0.0088, |
| "step": 5910 |
| }, |
| { |
| "epoch": 3.394636839463684, |
| "grad_norm": 0.0016457217279821634, |
| "learning_rate": 2.8196320759839677e-06, |
| "loss": 0.0173, |
| "step": 5920 |
| }, |
| { |
| "epoch": 3.400372840037284, |
| "grad_norm": 0.11143210530281067, |
| "learning_rate": 2.801626194952669e-06, |
| "loss": 0.0015, |
| "step": 5930 |
| }, |
| { |
| "epoch": 3.406108840610884, |
| "grad_norm": 0.03351111710071564, |
| "learning_rate": 2.7836555864240566e-06, |
| "loss": 0.0079, |
| "step": 5940 |
| }, |
| { |
| "epoch": 3.411844841184484, |
| "grad_norm": 0.22604842483997345, |
| "learning_rate": 2.7657205387332313e-06, |
| "loss": 0.0124, |
| "step": 5950 |
| }, |
| { |
| "epoch": 3.411844841184484, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08073882758617401, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2042, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.796, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.421, |
| "step": 5950 |
| }, |
| { |
| "epoch": 3.417580841758084, |
| "grad_norm": 0.1360362470149994, |
| "learning_rate": 2.747821339644734e-06, |
| "loss": 0.028, |
| "step": 5960 |
| }, |
| { |
| "epoch": 3.423316842331684, |
| "grad_norm": 0.015132960863411427, |
| "learning_rate": 2.7299582763479115e-06, |
| "loss": 0.0041, |
| "step": 5970 |
| }, |
| { |
| "epoch": 3.4290528429052842, |
| "grad_norm": 0.06472807377576828, |
| "learning_rate": 2.7121316354523286e-06, |
| "loss": 0.0017, |
| "step": 5980 |
| }, |
| { |
| "epoch": 3.4347888434788842, |
| "grad_norm": 3.1584267616271973, |
| "learning_rate": 2.6943417029831504e-06, |
| "loss": 0.0232, |
| "step": 5990 |
| }, |
| { |
| "epoch": 3.4405248440524843, |
| "grad_norm": 0.004198137205094099, |
| "learning_rate": 2.6765887643765653e-06, |
| "loss": 0.0052, |
| "step": 6000 |
| }, |
| { |
| "epoch": 3.4405248440524843, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08295302093029022, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2169, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.777, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.412, |
| "step": 6000 |
| }, |
| { |
| "epoch": 3.4462608446260843, |
| "grad_norm": 0.018915435299277306, |
| "learning_rate": 2.6588731044752057e-06, |
| "loss": 0.0153, |
| "step": 6010 |
| }, |
| { |
| "epoch": 3.4519968451996847, |
| "grad_norm": 3.4281928539276123, |
| "learning_rate": 2.641195007523568e-06, |
| "loss": 0.0099, |
| "step": 6020 |
| }, |
| { |
| "epoch": 3.4577328457732848, |
| "grad_norm": 0.0030478844419121742, |
| "learning_rate": 2.623554757163464e-06, |
| "loss": 0.0004, |
| "step": 6030 |
| }, |
| { |
| "epoch": 3.463468846346885, |
| "grad_norm": 0.022162869572639465, |
| "learning_rate": 2.605952636429456e-06, |
| "loss": 0.0114, |
| "step": 6040 |
| }, |
| { |
| "epoch": 3.469204846920485, |
| "grad_norm": 0.009365621022880077, |
| "learning_rate": 2.5883889277443347e-06, |
| "loss": 0.0009, |
| "step": 6050 |
| }, |
| { |
| "epoch": 3.469204846920485, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07579995691776276, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2596, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.716, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.381, |
| "step": 6050 |
| }, |
| { |
| "epoch": 3.474940847494085, |
| "grad_norm": 0.29800668358802795, |
| "learning_rate": 2.570863912914566e-06, |
| "loss": 0.018, |
| "step": 6060 |
| }, |
| { |
| "epoch": 3.480676848067685, |
| "grad_norm": 3.4592084884643555, |
| "learning_rate": 2.5533778731257824e-06, |
| "loss": 0.0041, |
| "step": 6070 |
| }, |
| { |
| "epoch": 3.486412848641285, |
| "grad_norm": 0.03675074130296707, |
| "learning_rate": 2.535931088938274e-06, |
| "loss": 0.0129, |
| "step": 6080 |
| }, |
| { |
| "epoch": 3.492148849214885, |
| "grad_norm": 0.5131600499153137, |
| "learning_rate": 2.518523840282479e-06, |
| "loss": 0.0069, |
| "step": 6090 |
| }, |
| { |
| "epoch": 3.497884849788485, |
| "grad_norm": 0.19048012793064117, |
| "learning_rate": 2.5011564064544945e-06, |
| "loss": 0.0061, |
| "step": 6100 |
| }, |
| { |
| "epoch": 3.497884849788485, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07761486619710922, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2658, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.707, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.377, |
| "step": 6100 |
| }, |
| { |
| "epoch": 3.503620850362085, |
| "grad_norm": 0.37152099609375, |
| "learning_rate": 2.483829066111596e-06, |
| "loss": 0.0108, |
| "step": 6110 |
| }, |
| { |
| "epoch": 3.509356850935685, |
| "grad_norm": 4.403800964355469, |
| "learning_rate": 2.466542097267765e-06, |
| "loss": 0.0119, |
| "step": 6120 |
| }, |
| { |
| "epoch": 3.5150928515092854, |
| "grad_norm": 0.008035624399781227, |
| "learning_rate": 2.4492957772892345e-06, |
| "loss": 0.0192, |
| "step": 6130 |
| }, |
| { |
| "epoch": 3.520828852082885, |
| "grad_norm": 1.8271785974502563, |
| "learning_rate": 2.432090382890032e-06, |
| "loss": 0.0159, |
| "step": 6140 |
| }, |
| { |
| "epoch": 3.5265648526564854, |
| "grad_norm": 0.00973561592400074, |
| "learning_rate": 2.4149261901275393e-06, |
| "loss": 0.0184, |
| "step": 6150 |
| }, |
| { |
| "epoch": 3.5265648526564854, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07000607997179031, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.3198, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.629, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.338, |
| "step": 6150 |
| }, |
| { |
| "epoch": 3.5323008532300855, |
| "grad_norm": 0.3272586464881897, |
| "learning_rate": 2.3978034743980676e-06, |
| "loss": 0.0014, |
| "step": 6160 |
| }, |
| { |
| "epoch": 3.5380368538036855, |
| "grad_norm": 0.015382179990410805, |
| "learning_rate": 2.3807225104324337e-06, |
| "loss": 0.0099, |
| "step": 6170 |
| }, |
| { |
| "epoch": 3.5437728543772855, |
| "grad_norm": 0.016446420922875404, |
| "learning_rate": 2.36368357229156e-06, |
| "loss": 0.0039, |
| "step": 6180 |
| }, |
| { |
| "epoch": 3.5495088549508855, |
| "grad_norm": 0.006563331466168165, |
| "learning_rate": 2.34668693336207e-06, |
| "loss": 0.0035, |
| "step": 6190 |
| }, |
| { |
| "epoch": 3.5552448555244855, |
| "grad_norm": 0.024284416809678078, |
| "learning_rate": 2.3297328663519044e-06, |
| "loss": 0.0117, |
| "step": 6200 |
| }, |
| { |
| "epoch": 3.5552448555244855, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07584439218044281, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.3203, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.628, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.337, |
| "step": 6200 |
| }, |
| { |
| "epoch": 3.5609808560980856, |
| "grad_norm": 0.011505261063575745, |
| "learning_rate": 2.3128216432859435e-06, |
| "loss": 0.0192, |
| "step": 6210 |
| }, |
| { |
| "epoch": 3.5667168566716856, |
| "grad_norm": 0.01848476566374302, |
| "learning_rate": 2.2959535355016436e-06, |
| "loss": 0.0003, |
| "step": 6220 |
| }, |
| { |
| "epoch": 3.5724528572452856, |
| "grad_norm": 0.007101431954652071, |
| "learning_rate": 2.27912881364469e-06, |
| "loss": 0.0098, |
| "step": 6230 |
| }, |
| { |
| "epoch": 3.5781888578188856, |
| "grad_norm": 0.9875366687774658, |
| "learning_rate": 2.2623477476646447e-06, |
| "loss": 0.0014, |
| "step": 6240 |
| }, |
| { |
| "epoch": 3.5839248583924856, |
| "grad_norm": 0.07821710407733917, |
| "learning_rate": 2.2456106068106206e-06, |
| "loss": 0.0007, |
| "step": 6250 |
| }, |
| { |
| "epoch": 3.5839248583924856, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08138631284236908, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2288, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.76, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.404, |
| "step": 6250 |
| }, |
| { |
| "epoch": 3.589660858966086, |
| "grad_norm": 0.8070231676101685, |
| "learning_rate": 2.2289176596269545e-06, |
| "loss": 0.0015, |
| "step": 6260 |
| }, |
| { |
| "epoch": 3.5953968595396857, |
| "grad_norm": 0.0035041391383856535, |
| "learning_rate": 2.2122691739489143e-06, |
| "loss": 0.0021, |
| "step": 6270 |
| }, |
| { |
| "epoch": 3.601132860113286, |
| "grad_norm": 0.013247767463326454, |
| "learning_rate": 2.195665416898381e-06, |
| "loss": 0.0026, |
| "step": 6280 |
| }, |
| { |
| "epoch": 3.606868860686886, |
| "grad_norm": 3.3201675415039062, |
| "learning_rate": 2.179106654879581e-06, |
| "loss": 0.0236, |
| "step": 6290 |
| }, |
| { |
| "epoch": 3.612604861260486, |
| "grad_norm": 0.00799557100981474, |
| "learning_rate": 2.1625931535747964e-06, |
| "loss": 0.0078, |
| "step": 6300 |
| }, |
| { |
| "epoch": 3.612604861260486, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07524015754461288, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.3312, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.613, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.33, |
| "step": 6300 |
| }, |
| { |
| "epoch": 3.618340861834086, |
| "grad_norm": 0.796405553817749, |
| "learning_rate": 2.1461251779401175e-06, |
| "loss": 0.0028, |
| "step": 6310 |
| }, |
| { |
| "epoch": 3.6240768624076862, |
| "grad_norm": 0.0037477288860827684, |
| "learning_rate": 2.1297029922011775e-06, |
| "loss": 0.0093, |
| "step": 6320 |
| }, |
| { |
| "epoch": 3.6298128629812862, |
| "grad_norm": 0.07188570499420166, |
| "learning_rate": 2.113326859848919e-06, |
| "loss": 0.0031, |
| "step": 6330 |
| }, |
| { |
| "epoch": 3.6355488635548863, |
| "grad_norm": 2.5588748455047607, |
| "learning_rate": 2.0969970436353725e-06, |
| "loss": 0.0074, |
| "step": 6340 |
| }, |
| { |
| "epoch": 3.6412848641284863, |
| "grad_norm": 0.008328588679432869, |
| "learning_rate": 2.080713805569427e-06, |
| "loss": 0.0025, |
| "step": 6350 |
| }, |
| { |
| "epoch": 3.6412848641284863, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.07739181071519852, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2601, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.715, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.381, |
| "step": 6350 |
| }, |
| { |
| "epoch": 3.6470208647020863, |
| "grad_norm": 0.0075204516761004925, |
| "learning_rate": 2.0644774069126406e-06, |
| "loss": 0.0109, |
| "step": 6360 |
| }, |
| { |
| "epoch": 3.6527568652756868, |
| "grad_norm": 0.003392142942175269, |
| "learning_rate": 2.048288108175036e-06, |
| "loss": 0.0091, |
| "step": 6370 |
| }, |
| { |
| "epoch": 3.6584928658492863, |
| "grad_norm": 0.00919413473457098, |
| "learning_rate": 2.0321461691109288e-06, |
| "loss": 0.007, |
| "step": 6380 |
| }, |
| { |
| "epoch": 3.664228866422887, |
| "grad_norm": 0.020889578387141228, |
| "learning_rate": 2.016051848714758e-06, |
| "loss": 0.0012, |
| "step": 6390 |
| }, |
| { |
| "epoch": 3.669964866996487, |
| "grad_norm": 0.09611943364143372, |
| "learning_rate": 2.000005405216931e-06, |
| "loss": 0.0011, |
| "step": 6400 |
| }, |
| { |
| "epoch": 3.669964866996487, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08481152355670929, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2176, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.776, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.412, |
| "step": 6400 |
| }, |
| { |
| "epoch": 3.675700867570087, |
| "grad_norm": 0.004153054673224688, |
| "learning_rate": 1.984007096079676e-06, |
| "loss": 0.0175, |
| "step": 6410 |
| }, |
| { |
| "epoch": 3.681436868143687, |
| "grad_norm": 0.0063193319365382195, |
| "learning_rate": 1.968057177992915e-06, |
| "loss": 0.0018, |
| "step": 6420 |
| }, |
| { |
| "epoch": 3.687172868717287, |
| "grad_norm": 0.05629734694957733, |
| "learning_rate": 1.9521559068701447e-06, |
| "loss": 0.0005, |
| "step": 6430 |
| }, |
| { |
| "epoch": 3.692908869290887, |
| "grad_norm": 0.042965829372406006, |
| "learning_rate": 1.9363035378443313e-06, |
| "loss": 0.0017, |
| "step": 6440 |
| }, |
| { |
| "epoch": 3.698644869864487, |
| "grad_norm": 0.029728276655077934, |
| "learning_rate": 1.9205003252638176e-06, |
| "loss": 0.0041, |
| "step": 6450 |
| }, |
| { |
| "epoch": 3.698644869864487, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08883155882358551, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1133, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.928, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.488, |
| "step": 6450 |
| }, |
| { |
| "epoch": 3.704380870438087, |
| "grad_norm": 0.014888194389641285, |
| "learning_rate": 1.904746522688236e-06, |
| "loss": 0.0018, |
| "step": 6460 |
| }, |
| { |
| "epoch": 3.710116871011687, |
| "grad_norm": 4.221490859985352, |
| "learning_rate": 1.8890423828844462e-06, |
| "loss": 0.0047, |
| "step": 6470 |
| }, |
| { |
| "epoch": 3.7158528715852874, |
| "grad_norm": 2.9691474437713623, |
| "learning_rate": 1.873388157822477e-06, |
| "loss": 0.0087, |
| "step": 6480 |
| }, |
| { |
| "epoch": 3.721588872158887, |
| "grad_norm": 0.1171032041311264, |
| "learning_rate": 1.8577840986714868e-06, |
| "loss": 0.0019, |
| "step": 6490 |
| }, |
| { |
| "epoch": 3.7273248727324875, |
| "grad_norm": 0.006826687604188919, |
| "learning_rate": 1.8422304557957315e-06, |
| "loss": 0.0123, |
| "step": 6500 |
| }, |
| { |
| "epoch": 3.7273248727324875, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08897148817777634, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2955, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.664, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.355, |
| "step": 6500 |
| }, |
| { |
| "epoch": 3.7330608733060875, |
| "grad_norm": 0.022587748244404793, |
| "learning_rate": 1.8267274787505446e-06, |
| "loss": 0.0087, |
| "step": 6510 |
| }, |
| { |
| "epoch": 3.7387968738796875, |
| "grad_norm": 0.5572834014892578, |
| "learning_rate": 1.8112754162783336e-06, |
| "loss": 0.0084, |
| "step": 6520 |
| }, |
| { |
| "epoch": 3.7445328744532875, |
| "grad_norm": 0.015338007360696793, |
| "learning_rate": 1.7958745163045987e-06, |
| "loss": 0.0085, |
| "step": 6530 |
| }, |
| { |
| "epoch": 3.7502688750268875, |
| "grad_norm": 0.004370348062366247, |
| "learning_rate": 1.7805250259339379e-06, |
| "loss": 0.0075, |
| "step": 6540 |
| }, |
| { |
| "epoch": 3.7560048756004876, |
| "grad_norm": 0.006390043999999762, |
| "learning_rate": 1.765227191446101e-06, |
| "loss": 0.0074, |
| "step": 6550 |
| }, |
| { |
| "epoch": 3.7560048756004876, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08355527371168137, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1302, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.904, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.475, |
| "step": 6550 |
| }, |
| { |
| "epoch": 3.7617408761740876, |
| "grad_norm": 0.09934690594673157, |
| "learning_rate": 1.7499812582920222e-06, |
| "loss": 0.0038, |
| "step": 6560 |
| }, |
| { |
| "epoch": 3.7674768767476876, |
| "grad_norm": 0.0005312475841492414, |
| "learning_rate": 1.734787471089887e-06, |
| "loss": 0.005, |
| "step": 6570 |
| }, |
| { |
| "epoch": 3.7732128773212876, |
| "grad_norm": 0.5943177938461304, |
| "learning_rate": 1.7196460736212167e-06, |
| "loss": 0.0111, |
| "step": 6580 |
| }, |
| { |
| "epoch": 3.7789488778948876, |
| "grad_norm": 0.03382878378033638, |
| "learning_rate": 1.7045573088269408e-06, |
| "loss": 0.0022, |
| "step": 6590 |
| }, |
| { |
| "epoch": 3.7846848784684877, |
| "grad_norm": 0.018695516511797905, |
| "learning_rate": 1.6895214188035125e-06, |
| "loss": 0.0038, |
| "step": 6600 |
| }, |
| { |
| "epoch": 3.7846848784684877, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.0897902175784111, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2015, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.8, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.423, |
| "step": 6600 |
| }, |
| { |
| "epoch": 3.790420879042088, |
| "grad_norm": 0.03567569702863693, |
| "learning_rate": 1.6745386447990153e-06, |
| "loss": 0.0149, |
| "step": 6610 |
| }, |
| { |
| "epoch": 3.7961568796156877, |
| "grad_norm": 0.005937593523412943, |
| "learning_rate": 1.6596092272093e-06, |
| "loss": 0.0057, |
| "step": 6620 |
| }, |
| { |
| "epoch": 3.801892880189288, |
| "grad_norm": 0.001366928219795227, |
| "learning_rate": 1.6447334055741198e-06, |
| "loss": 0.0019, |
| "step": 6630 |
| }, |
| { |
| "epoch": 3.807628880762888, |
| "grad_norm": 0.017239965498447418, |
| "learning_rate": 1.6299114185732918e-06, |
| "loss": 0.0068, |
| "step": 6640 |
| }, |
| { |
| "epoch": 3.813364881336488, |
| "grad_norm": 0.09475360810756683, |
| "learning_rate": 1.6151435040228663e-06, |
| "loss": 0.0084, |
| "step": 6650 |
| }, |
| { |
| "epoch": 3.813364881336488, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09376490861177444, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2936, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.667, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.357, |
| "step": 6650 |
| }, |
| { |
| "epoch": 3.8191008819100882, |
| "grad_norm": 0.004428621847182512, |
| "learning_rate": 1.6004298988713153e-06, |
| "loss": 0.0003, |
| "step": 6660 |
| }, |
| { |
| "epoch": 3.8248368824836882, |
| "grad_norm": 0.0019930372945964336, |
| "learning_rate": 1.5857708391957194e-06, |
| "loss": 0.0012, |
| "step": 6670 |
| }, |
| { |
| "epoch": 3.8305728830572883, |
| "grad_norm": 0.24852816760540009, |
| "learning_rate": 1.571166560197991e-06, |
| "loss": 0.0018, |
| "step": 6680 |
| }, |
| { |
| "epoch": 3.8363088836308883, |
| "grad_norm": 0.05106634274125099, |
| "learning_rate": 1.5566172962010944e-06, |
| "loss": 0.0088, |
| "step": 6690 |
| }, |
| { |
| "epoch": 3.8420448842044883, |
| "grad_norm": 0.957535982131958, |
| "learning_rate": 1.542123280645292e-06, |
| "loss": 0.0013, |
| "step": 6700 |
| }, |
| { |
| "epoch": 3.8420448842044883, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09245079010725021, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1154, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.925, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.486, |
| "step": 6700 |
| }, |
| { |
| "epoch": 3.8477808847780883, |
| "grad_norm": 0.022298647090792656, |
| "learning_rate": 1.527684746084394e-06, |
| "loss": 0.0103, |
| "step": 6710 |
| }, |
| { |
| "epoch": 3.853516885351689, |
| "grad_norm": 0.21422079205513, |
| "learning_rate": 1.5133019241820257e-06, |
| "loss": 0.0341, |
| "step": 6720 |
| }, |
| { |
| "epoch": 3.8592528859252884, |
| "grad_norm": 0.08396855741739273, |
| "learning_rate": 1.4989750457079156e-06, |
| "loss": 0.0033, |
| "step": 6730 |
| }, |
| { |
| "epoch": 3.864988886498889, |
| "grad_norm": 0.12731043994426727, |
| "learning_rate": 1.484704340534187e-06, |
| "loss": 0.0028, |
| "step": 6740 |
| }, |
| { |
| "epoch": 3.870724887072489, |
| "grad_norm": 0.4012109637260437, |
| "learning_rate": 1.4704900376316773e-06, |
| "loss": 0.0008, |
| "step": 6750 |
| }, |
| { |
| "epoch": 3.870724887072489, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09105575829744339, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2863, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.677, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.362, |
| "step": 6750 |
| }, |
| { |
| "epoch": 3.876460887646089, |
| "grad_norm": 0.4341152012348175, |
| "learning_rate": 1.4563323650662586e-06, |
| "loss": 0.0013, |
| "step": 6760 |
| }, |
| { |
| "epoch": 3.882196888219689, |
| "grad_norm": 0.14372624456882477, |
| "learning_rate": 1.4422315499951783e-06, |
| "loss": 0.0059, |
| "step": 6770 |
| }, |
| { |
| "epoch": 3.887932888793289, |
| "grad_norm": 0.010315956547856331, |
| "learning_rate": 1.4281878186634157e-06, |
| "loss": 0.01, |
| "step": 6780 |
| }, |
| { |
| "epoch": 3.893668889366889, |
| "grad_norm": 0.1287292093038559, |
| "learning_rate": 1.4142013964000513e-06, |
| "loss": 0.01, |
| "step": 6790 |
| }, |
| { |
| "epoch": 3.899404889940489, |
| "grad_norm": 0.4034357964992523, |
| "learning_rate": 1.400272507614655e-06, |
| "loss": 0.0012, |
| "step": 6800 |
| }, |
| { |
| "epoch": 3.899404889940489, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09034840762615204, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1486, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.877, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.462, |
| "step": 6800 |
| }, |
| { |
| "epoch": 3.905140890514089, |
| "grad_norm": 0.15965530276298523, |
| "learning_rate": 1.3864013757936828e-06, |
| "loss": 0.0009, |
| "step": 6810 |
| }, |
| { |
| "epoch": 3.910876891087689, |
| "grad_norm": 0.07124567031860352, |
| "learning_rate": 1.3725882234968879e-06, |
| "loss": 0.0118, |
| "step": 6820 |
| }, |
| { |
| "epoch": 3.916612891661289, |
| "grad_norm": 0.022812863811850548, |
| "learning_rate": 1.3588332723537523e-06, |
| "loss": 0.0133, |
| "step": 6830 |
| }, |
| { |
| "epoch": 3.922348892234889, |
| "grad_norm": 0.0023223236203193665, |
| "learning_rate": 1.345136743059936e-06, |
| "loss": 0.013, |
| "step": 6840 |
| }, |
| { |
| "epoch": 3.9280848928084895, |
| "grad_norm": 0.08886972069740295, |
| "learning_rate": 1.3314988553737256e-06, |
| "loss": 0.0028, |
| "step": 6850 |
| }, |
| { |
| "epoch": 3.9280848928084895, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.0912175104022026, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2896, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.672, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.36, |
| "step": 6850 |
| }, |
| { |
| "epoch": 3.933820893382089, |
| "grad_norm": 0.022729717195034027, |
| "learning_rate": 1.3179198281125188e-06, |
| "loss": 0.0069, |
| "step": 6860 |
| }, |
| { |
| "epoch": 3.9395568939556895, |
| "grad_norm": 2.09700083732605, |
| "learning_rate": 1.3043998791493034e-06, |
| "loss": 0.006, |
| "step": 6870 |
| }, |
| { |
| "epoch": 3.9452928945292896, |
| "grad_norm": 0.026967119425535202, |
| "learning_rate": 1.290939225409173e-06, |
| "loss": 0.0018, |
| "step": 6880 |
| }, |
| { |
| "epoch": 3.9510288951028896, |
| "grad_norm": 0.010416003875434399, |
| "learning_rate": 1.277538082865835e-06, |
| "loss": 0.012, |
| "step": 6890 |
| }, |
| { |
| "epoch": 3.9567648956764896, |
| "grad_norm": 0.04778837040066719, |
| "learning_rate": 1.2641966665381517e-06, |
| "loss": 0.0117, |
| "step": 6900 |
| }, |
| { |
| "epoch": 3.9567648956764896, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09045156091451645, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1714, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.844, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.445, |
| "step": 6900 |
| }, |
| { |
| "epoch": 3.9625008962500896, |
| "grad_norm": 0.0013466872042044997, |
| "learning_rate": 1.2509151904866922e-06, |
| "loss": 0.0012, |
| "step": 6910 |
| }, |
| { |
| "epoch": 3.9682368968236896, |
| "grad_norm": 0.057207245379686356, |
| "learning_rate": 1.2376938678102913e-06, |
| "loss": 0.0172, |
| "step": 6920 |
| }, |
| { |
| "epoch": 3.9739728973972896, |
| "grad_norm": 2.2670977115631104, |
| "learning_rate": 1.2245329106426367e-06, |
| "loss": 0.013, |
| "step": 6930 |
| }, |
| { |
| "epoch": 3.9797088979708897, |
| "grad_norm": 0.0011907550506293774, |
| "learning_rate": 1.2114325301488616e-06, |
| "loss": 0.0117, |
| "step": 6940 |
| }, |
| { |
| "epoch": 3.9854448985444897, |
| "grad_norm": 0.023963019251823425, |
| "learning_rate": 1.1983929365221548e-06, |
| "loss": 0.0096, |
| "step": 6950 |
| }, |
| { |
| "epoch": 3.9854448985444897, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08352689445018768, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2306, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.757, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.402, |
| "step": 6950 |
| }, |
| { |
| "epoch": 3.99118089911809, |
| "grad_norm": 0.02613544650375843, |
| "learning_rate": 1.1854143389803962e-06, |
| "loss": 0.0104, |
| "step": 6960 |
| }, |
| { |
| "epoch": 3.9969168996916897, |
| "grad_norm": 0.004353563766926527, |
| "learning_rate": 1.1724969457627928e-06, |
| "loss": 0.0004, |
| "step": 6970 |
| }, |
| { |
| "epoch": 4.00229440022944, |
| "grad_norm": 0.013296003453433514, |
| "learning_rate": 1.1596409641265376e-06, |
| "loss": 0.0053, |
| "step": 6980 |
| }, |
| { |
| "epoch": 4.00803040080304, |
| "grad_norm": 0.01596342958509922, |
| "learning_rate": 1.146846600343488e-06, |
| "loss": 0.0013, |
| "step": 6990 |
| }, |
| { |
| "epoch": 4.01376640137664, |
| "grad_norm": 0.003088761121034622, |
| "learning_rate": 1.1341140596968525e-06, |
| "loss": 0.0005, |
| "step": 7000 |
| }, |
| { |
| "epoch": 4.01376640137664, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08817622810602188, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2983, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.66, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.353, |
| "step": 7000 |
| }, |
| { |
| "epoch": 4.01950240195024, |
| "grad_norm": 0.0804172232747078, |
| "learning_rate": 1.1214435464779006e-06, |
| "loss": 0.0003, |
| "step": 7010 |
| }, |
| { |
| "epoch": 4.02523840252384, |
| "grad_norm": 0.13886569440364838, |
| "learning_rate": 1.1088352639826844e-06, |
| "loss": 0.0006, |
| "step": 7020 |
| }, |
| { |
| "epoch": 4.03097440309744, |
| "grad_norm": 0.029498988762497902, |
| "learning_rate": 1.0962894145087715e-06, |
| "loss": 0.0058, |
| "step": 7030 |
| }, |
| { |
| "epoch": 4.03671040367104, |
| "grad_norm": 3.7734415531158447, |
| "learning_rate": 1.0838061993520072e-06, |
| "loss": 0.0125, |
| "step": 7040 |
| }, |
| { |
| "epoch": 4.04244640424464, |
| "grad_norm": 0.12142331153154373, |
| "learning_rate": 1.0713858188032755e-06, |
| "loss": 0.0161, |
| "step": 7050 |
| }, |
| { |
| "epoch": 4.04244640424464, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09039638936519623, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2759, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.692, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.369, |
| "step": 7050 |
| }, |
| { |
| "epoch": 4.048182404818241, |
| "grad_norm": 0.003838218515738845, |
| "learning_rate": 1.0590284721452965e-06, |
| "loss": 0.0076, |
| "step": 7060 |
| }, |
| { |
| "epoch": 4.0539184053918405, |
| "grad_norm": 0.0031382606830447912, |
| "learning_rate": 1.0467343576494215e-06, |
| "loss": 0.0007, |
| "step": 7070 |
| }, |
| { |
| "epoch": 4.059654405965441, |
| "grad_norm": 0.0018334095366299152, |
| "learning_rate": 1.0345036725724517e-06, |
| "loss": 0.0206, |
| "step": 7080 |
| }, |
| { |
| "epoch": 4.0653904065390405, |
| "grad_norm": 0.06359425187110901, |
| "learning_rate": 1.0223366131534746e-06, |
| "loss": 0.0004, |
| "step": 7090 |
| }, |
| { |
| "epoch": 4.071126407112641, |
| "grad_norm": 0.08629762381315231, |
| "learning_rate": 1.010233374610719e-06, |
| "loss": 0.0003, |
| "step": 7100 |
| }, |
| { |
| "epoch": 4.071126407112641, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09012720733880997, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2717, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.698, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.373, |
| "step": 7100 |
| }, |
| { |
| "epoch": 4.0768624076862405, |
| "grad_norm": 0.16138513386249542, |
| "learning_rate": 9.981941511384152e-07, |
| "loss": 0.0042, |
| "step": 7110 |
| }, |
| { |
| "epoch": 4.082598408259841, |
| "grad_norm": 2.28838849067688, |
| "learning_rate": 9.862191359036883e-07, |
| "loss": 0.0019, |
| "step": 7120 |
| }, |
| { |
| "epoch": 4.088334408833441, |
| "grad_norm": 0.003568111453205347, |
| "learning_rate": 9.743085210434505e-07, |
| "loss": 0.0136, |
| "step": 7130 |
| }, |
| { |
| "epoch": 4.094070409407041, |
| "grad_norm": 2.805901050567627, |
| "learning_rate": 9.624624976613217e-07, |
| "loss": 0.0083, |
| "step": 7140 |
| }, |
| { |
| "epoch": 4.099806409980641, |
| "grad_norm": 0.009448690339922905, |
| "learning_rate": 9.506812558245665e-07, |
| "loss": 0.0004, |
| "step": 7150 |
| }, |
| { |
| "epoch": 4.099806409980641, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09947969764471054, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2914, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.67, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.358, |
| "step": 7150 |
| }, |
| { |
| "epoch": 4.105542410554241, |
| "grad_norm": 0.007924864068627357, |
| "learning_rate": 9.389649845610376e-07, |
| "loss": 0.0083, |
| "step": 7160 |
| }, |
| { |
| "epoch": 4.1112784111278415, |
| "grad_norm": 0.03764890506863594, |
| "learning_rate": 9.273138718561519e-07, |
| "loss": 0.0003, |
| "step": 7170 |
| }, |
| { |
| "epoch": 4.117014411701441, |
| "grad_norm": 0.015703987330198288, |
| "learning_rate": 9.157281046498628e-07, |
| "loss": 0.0141, |
| "step": 7180 |
| }, |
| { |
| "epoch": 4.122750412275042, |
| "grad_norm": 0.04593523591756821, |
| "learning_rate": 9.042078688336737e-07, |
| "loss": 0.0005, |
| "step": 7190 |
| }, |
| { |
| "epoch": 4.128486412848641, |
| "grad_norm": 0.08672873675823212, |
| "learning_rate": 8.927533492476437e-07, |
| "loss": 0.0088, |
| "step": 7200 |
| }, |
| { |
| "epoch": 4.128486412848641, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09371308237314224, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2865, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.677, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.362, |
| "step": 7200 |
| }, |
| { |
| "epoch": 4.134222413422242, |
| "grad_norm": 0.0006487391074188054, |
| "learning_rate": 8.813647296774291e-07, |
| "loss": 0.0033, |
| "step": 7210 |
| }, |
| { |
| "epoch": 4.139958413995841, |
| "grad_norm": 2.7435028553009033, |
| "learning_rate": 8.700421928513353e-07, |
| "loss": 0.0104, |
| "step": 7220 |
| }, |
| { |
| "epoch": 4.145694414569442, |
| "grad_norm": 0.12825919687747955, |
| "learning_rate": 8.58785920437376e-07, |
| "loss": 0.0131, |
| "step": 7230 |
| }, |
| { |
| "epoch": 4.151430415143041, |
| "grad_norm": 0.019473344087600708, |
| "learning_rate": 8.475960930403721e-07, |
| "loss": 0.0123, |
| "step": 7240 |
| }, |
| { |
| "epoch": 4.157166415716642, |
| "grad_norm": 0.019103556871414185, |
| "learning_rate": 8.364728901990404e-07, |
| "loss": 0.0161, |
| "step": 7250 |
| }, |
| { |
| "epoch": 4.157166415716642, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08745884150266647, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.3788, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.544, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.296, |
| "step": 7250 |
| }, |
| { |
| "epoch": 4.162902416290241, |
| "grad_norm": 0.001977517269551754, |
| "learning_rate": 8.254164903831203e-07, |
| "loss": 0.009, |
| "step": 7260 |
| }, |
| { |
| "epoch": 4.168638416863842, |
| "grad_norm": 0.00919981300830841, |
| "learning_rate": 8.144270709905117e-07, |
| "loss": 0.0185, |
| "step": 7270 |
| }, |
| { |
| "epoch": 4.174374417437441, |
| "grad_norm": 0.007627399172633886, |
| "learning_rate": 8.035048083444241e-07, |
| "loss": 0.0013, |
| "step": 7280 |
| }, |
| { |
| "epoch": 4.180110418011042, |
| "grad_norm": 0.006586376577615738, |
| "learning_rate": 7.926498776905495e-07, |
| "loss": 0.0013, |
| "step": 7290 |
| }, |
| { |
| "epoch": 4.185846418584642, |
| "grad_norm": 0.0025622497778385878, |
| "learning_rate": 7.818624531942493e-07, |
| "loss": 0.0003, |
| "step": 7300 |
| }, |
| { |
| "epoch": 4.185846418584642, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08901920914649963, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2083, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.79, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.419, |
| "step": 7300 |
| }, |
| { |
| "epoch": 4.191582419158242, |
| "grad_norm": 0.07510726898908615, |
| "learning_rate": 7.711427079377614e-07, |
| "loss": 0.0055, |
| "step": 7310 |
| }, |
| { |
| "epoch": 4.197318419731842, |
| "grad_norm": 0.002239730441942811, |
| "learning_rate": 7.604908139174255e-07, |
| "loss": 0.0007, |
| "step": 7320 |
| }, |
| { |
| "epoch": 4.203054420305442, |
| "grad_norm": 0.0018331691389903426, |
| "learning_rate": 7.499069420409183e-07, |
| "loss": 0.0104, |
| "step": 7330 |
| }, |
| { |
| "epoch": 4.208790420879042, |
| "grad_norm": 0.06228185445070267, |
| "learning_rate": 7.393912621245142e-07, |
| "loss": 0.015, |
| "step": 7340 |
| }, |
| { |
| "epoch": 4.214526421452642, |
| "grad_norm": 0.0020015144255012274, |
| "learning_rate": 7.289439428903599e-07, |
| "loss": 0.0015, |
| "step": 7350 |
| }, |
| { |
| "epoch": 4.214526421452642, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08976524323225021, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.3011, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.656, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.351, |
| "step": 7350 |
| }, |
| { |
| "epoch": 4.220262422026242, |
| "grad_norm": 3.2421772480010986, |
| "learning_rate": 7.185651519637659e-07, |
| "loss": 0.0083, |
| "step": 7360 |
| }, |
| { |
| "epoch": 4.225998422599842, |
| "grad_norm": 0.0900789201259613, |
| "learning_rate": 7.082550558705225e-07, |
| "loss": 0.0084, |
| "step": 7370 |
| }, |
| { |
| "epoch": 4.231734423173442, |
| "grad_norm": 0.0065153795294463634, |
| "learning_rate": 6.980138200342229e-07, |
| "loss": 0.0003, |
| "step": 7380 |
| }, |
| { |
| "epoch": 4.237470423747042, |
| "grad_norm": 0.041670165956020355, |
| "learning_rate": 6.878416087736079e-07, |
| "loss": 0.0006, |
| "step": 7390 |
| }, |
| { |
| "epoch": 4.243206424320642, |
| "grad_norm": 0.005517491605132818, |
| "learning_rate": 6.777385852999319e-07, |
| "loss": 0.0005, |
| "step": 7400 |
| }, |
| { |
| "epoch": 4.243206424320642, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08851981908082962, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2967, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.662, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.355, |
| "step": 7400 |
| }, |
| { |
| "epoch": 4.248942424894243, |
| "grad_norm": 0.007675142493098974, |
| "learning_rate": 6.67704911714348e-07, |
| "loss": 0.0127, |
| "step": 7410 |
| }, |
| { |
| "epoch": 4.2546784254678425, |
| "grad_norm": 2.6328227519989014, |
| "learning_rate": 6.577407490052978e-07, |
| "loss": 0.0152, |
| "step": 7420 |
| }, |
| { |
| "epoch": 4.260414426041443, |
| "grad_norm": 0.14412537217140198, |
| "learning_rate": 6.478462570459388e-07, |
| "loss": 0.0012, |
| "step": 7430 |
| }, |
| { |
| "epoch": 4.2661504266150425, |
| "grad_norm": 3.322977066040039, |
| "learning_rate": 6.380215945915702e-07, |
| "loss": 0.0065, |
| "step": 7440 |
| }, |
| { |
| "epoch": 4.271886427188643, |
| "grad_norm": 0.0006975011201575398, |
| "learning_rate": 6.282669192770896e-07, |
| "loss": 0.0008, |
| "step": 7450 |
| }, |
| { |
| "epoch": 4.271886427188643, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09144297242164612, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2868, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.676, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.362, |
| "step": 7450 |
| }, |
| { |
| "epoch": 4.2776224277622426, |
| "grad_norm": 0.04776507988572121, |
| "learning_rate": 6.185823876144675e-07, |
| "loss": 0.0052, |
| "step": 7460 |
| }, |
| { |
| "epoch": 4.283358428335843, |
| "grad_norm": 4.260890483856201, |
| "learning_rate": 6.089681549902287e-07, |
| "loss": 0.0172, |
| "step": 7470 |
| }, |
| { |
| "epoch": 4.289094428909443, |
| "grad_norm": 0.0017789709381759167, |
| "learning_rate": 5.994243756629664e-07, |
| "loss": 0.0045, |
| "step": 7480 |
| }, |
| { |
| "epoch": 4.294830429483043, |
| "grad_norm": 0.020361248403787613, |
| "learning_rate": 5.89951202760859e-07, |
| "loss": 0.0013, |
| "step": 7490 |
| }, |
| { |
| "epoch": 4.300566430056643, |
| "grad_norm": 0.01590687222778797, |
| "learning_rate": 5.805487882792227e-07, |
| "loss": 0.0079, |
| "step": 7500 |
| }, |
| { |
| "epoch": 4.300566430056643, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08803683519363403, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2002, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.802, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.424, |
| "step": 7500 |
| }, |
| { |
| "epoch": 4.306302430630243, |
| "grad_norm": 0.016193749383091927, |
| "learning_rate": 5.712172830780649e-07, |
| "loss": 0.0032, |
| "step": 7510 |
| }, |
| { |
| "epoch": 4.312038431203844, |
| "grad_norm": 0.2794877588748932, |
| "learning_rate": 5.619568368796657e-07, |
| "loss": 0.0046, |
| "step": 7520 |
| }, |
| { |
| "epoch": 4.317774431777443, |
| "grad_norm": 0.3345611095428467, |
| "learning_rate": 5.527675982661801e-07, |
| "loss": 0.0028, |
| "step": 7530 |
| }, |
| { |
| "epoch": 4.323510432351044, |
| "grad_norm": 0.10426267981529236, |
| "learning_rate": 5.43649714677249e-07, |
| "loss": 0.0013, |
| "step": 7540 |
| }, |
| { |
| "epoch": 4.329246432924643, |
| "grad_norm": 0.0005553574301302433, |
| "learning_rate": 5.346033324076338e-07, |
| "loss": 0.006, |
| "step": 7550 |
| }, |
| { |
| "epoch": 4.329246432924643, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.087630994617939, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2554, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.722, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.384, |
| "step": 7550 |
| }, |
| { |
| "epoch": 4.334982433498244, |
| "grad_norm": 0.08077429980039597, |
| "learning_rate": 5.256285966048719e-07, |
| "loss": 0.0067, |
| "step": 7560 |
| }, |
| { |
| "epoch": 4.340718434071843, |
| "grad_norm": 0.004632384981960058, |
| "learning_rate": 5.167256512669444e-07, |
| "loss": 0.0084, |
| "step": 7570 |
| }, |
| { |
| "epoch": 4.346454434645444, |
| "grad_norm": 0.0067880041897296906, |
| "learning_rate": 5.078946392399703e-07, |
| "loss": 0.0021, |
| "step": 7580 |
| }, |
| { |
| "epoch": 4.352190435219043, |
| "grad_norm": 0.001848329440690577, |
| "learning_rate": 4.991357022159111e-07, |
| "loss": 0.0007, |
| "step": 7590 |
| }, |
| { |
| "epoch": 4.357926435792644, |
| "grad_norm": 0.09323499351739883, |
| "learning_rate": 4.90448980730297e-07, |
| "loss": 0.0024, |
| "step": 7600 |
| }, |
| { |
| "epoch": 4.357926435792644, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08750669658184052, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2509, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.728, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.388, |
| "step": 7600 |
| }, |
| { |
| "epoch": 4.363662436366243, |
| "grad_norm": 0.0019721076823771, |
| "learning_rate": 4.818346141599739e-07, |
| "loss": 0.0037, |
| "step": 7610 |
| }, |
| { |
| "epoch": 4.369398436939844, |
| "grad_norm": 0.26007330417633057, |
| "learning_rate": 4.732927407208654e-07, |
| "loss": 0.0011, |
| "step": 7620 |
| }, |
| { |
| "epoch": 4.375134437513443, |
| "grad_norm": 3.1276211738586426, |
| "learning_rate": 4.6482349746575783e-07, |
| "loss": 0.0274, |
| "step": 7630 |
| }, |
| { |
| "epoch": 4.380870438087044, |
| "grad_norm": 0.004567150957882404, |
| "learning_rate": 4.564270202820997e-07, |
| "loss": 0.0004, |
| "step": 7640 |
| }, |
| { |
| "epoch": 4.386606438660644, |
| "grad_norm": 0.033358391374349594, |
| "learning_rate": 4.4810344388982017e-07, |
| "loss": 0.0078, |
| "step": 7650 |
| }, |
| { |
| "epoch": 4.386606438660644, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08857561647891998, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2607, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.714, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.381, |
| "step": 7650 |
| }, |
| { |
| "epoch": 4.392342439234244, |
| "grad_norm": 0.3984158933162689, |
| "learning_rate": 4.3985290183916893e-07, |
| "loss": 0.003, |
| "step": 7660 |
| }, |
| { |
| "epoch": 4.398078439807844, |
| "grad_norm": 0.09813853353261948, |
| "learning_rate": 4.316755265085715e-07, |
| "loss": 0.002, |
| "step": 7670 |
| }, |
| { |
| "epoch": 4.403814440381444, |
| "grad_norm": 0.013608184643089771, |
| "learning_rate": 4.2357144910251003e-07, |
| "loss": 0.0007, |
| "step": 7680 |
| }, |
| { |
| "epoch": 4.409550440955044, |
| "grad_norm": 0.012810665182769299, |
| "learning_rate": 4.155407996494143e-07, |
| "loss": 0.0003, |
| "step": 7690 |
| }, |
| { |
| "epoch": 4.415286441528644, |
| "grad_norm": 0.5154911279678345, |
| "learning_rate": 4.0758370699957416e-07, |
| "loss": 0.0135, |
| "step": 7700 |
| }, |
| { |
| "epoch": 4.415286441528644, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08959878236055374, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2846, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.679, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.363, |
| "step": 7700 |
| }, |
| { |
| "epoch": 4.421022442102244, |
| "grad_norm": 0.0007974316249601543, |
| "learning_rate": 3.997002988230747e-07, |
| "loss": 0.0026, |
| "step": 7710 |
| }, |
| { |
| "epoch": 4.426758442675844, |
| "grad_norm": 0.032501526176929474, |
| "learning_rate": 3.918907016077489e-07, |
| "loss": 0.0051, |
| "step": 7720 |
| }, |
| { |
| "epoch": 4.432494443249444, |
| "grad_norm": 0.2708737552165985, |
| "learning_rate": 3.841550406571443e-07, |
| "loss": 0.0009, |
| "step": 7730 |
| }, |
| { |
| "epoch": 4.438230443823044, |
| "grad_norm": 0.6233472228050232, |
| "learning_rate": 3.764934400885162e-07, |
| "loss": 0.0012, |
| "step": 7740 |
| }, |
| { |
| "epoch": 4.4439664443966445, |
| "grad_norm": 0.00045903949649073184, |
| "learning_rate": 3.689060228308339e-07, |
| "loss": 0.0016, |
| "step": 7750 |
| }, |
| { |
| "epoch": 4.4439664443966445, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08894706517457962, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.3241, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.623, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.335, |
| "step": 7750 |
| }, |
| { |
| "epoch": 4.449702444970244, |
| "grad_norm": 0.02216159924864769, |
| "learning_rate": 3.6139291062281036e-07, |
| "loss": 0.0112, |
| "step": 7760 |
| }, |
| { |
| "epoch": 4.4554384455438445, |
| "grad_norm": 0.028067264705896378, |
| "learning_rate": 3.539542240109456e-07, |
| "loss": 0.0044, |
| "step": 7770 |
| }, |
| { |
| "epoch": 4.461174446117445, |
| "grad_norm": 3.8059170246124268, |
| "learning_rate": 3.4659008234759597e-07, |
| "loss": 0.0063, |
| "step": 7780 |
| }, |
| { |
| "epoch": 4.4669104466910445, |
| "grad_norm": 0.0011888346634805202, |
| "learning_rate": 3.3930060378905893e-07, |
| "loss": 0.0003, |
| "step": 7790 |
| }, |
| { |
| "epoch": 4.472646447264645, |
| "grad_norm": 0.0015550279058516026, |
| "learning_rate": 3.320859052936731e-07, |
| "loss": 0.0009, |
| "step": 7800 |
| }, |
| { |
| "epoch": 4.472646447264645, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09025800973176956, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1333, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.899, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.473, |
| "step": 7800 |
| }, |
| { |
| "epoch": 4.478382447838245, |
| "grad_norm": 0.039686888456344604, |
| "learning_rate": 3.249461026199485e-07, |
| "loss": 0.0003, |
| "step": 7810 |
| }, |
| { |
| "epoch": 4.484118448411845, |
| "grad_norm": 3.7747395038604736, |
| "learning_rate": 3.1788131032470306e-07, |
| "loss": 0.0124, |
| "step": 7820 |
| }, |
| { |
| "epoch": 4.489854448985445, |
| "grad_norm": 0.000805154733825475, |
| "learning_rate": 3.108916417612262e-07, |
| "loss": 0.0031, |
| "step": 7830 |
| }, |
| { |
| "epoch": 4.495590449559045, |
| "grad_norm": 0.0011434925254434347, |
| "learning_rate": 3.039772090774634e-07, |
| "loss": 0.0009, |
| "step": 7840 |
| }, |
| { |
| "epoch": 4.501326450132645, |
| "grad_norm": 0.019072147086262703, |
| "learning_rate": 2.97138123214214e-07, |
| "loss": 0.0003, |
| "step": 7850 |
| }, |
| { |
| "epoch": 4.501326450132645, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09056304395198822, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.169, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.847, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.447, |
| "step": 7850 |
| }, |
| { |
| "epoch": 4.507062450706245, |
| "grad_norm": 0.005647636018693447, |
| "learning_rate": 2.903744939033504e-07, |
| "loss": 0.0001, |
| "step": 7860 |
| }, |
| { |
| "epoch": 4.512798451279846, |
| "grad_norm": 2.6264231204986572, |
| "learning_rate": 2.836864296660574e-07, |
| "loss": 0.0132, |
| "step": 7870 |
| }, |
| { |
| "epoch": 4.518534451853445, |
| "grad_norm": 0.010306664742529392, |
| "learning_rate": 2.770740378110942e-07, |
| "loss": 0.0145, |
| "step": 7880 |
| }, |
| { |
| "epoch": 4.524270452427046, |
| "grad_norm": 0.18294845521450043, |
| "learning_rate": 2.7053742443307054e-07, |
| "loss": 0.0041, |
| "step": 7890 |
| }, |
| { |
| "epoch": 4.530006453000645, |
| "grad_norm": 0.017165735363960266, |
| "learning_rate": 2.640766944107431e-07, |
| "loss": 0.0007, |
| "step": 7900 |
| }, |
| { |
| "epoch": 4.530006453000645, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08944171667098999, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2567, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.72, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.383, |
| "step": 7900 |
| }, |
| { |
| "epoch": 4.535742453574246, |
| "grad_norm": 0.04896865785121918, |
| "learning_rate": 2.5769195140533556e-07, |
| "loss": 0.0125, |
| "step": 7910 |
| }, |
| { |
| "epoch": 4.541478454147845, |
| "grad_norm": 0.022854099050164223, |
| "learning_rate": 2.5138329785887263e-07, |
| "loss": 0.0005, |
| "step": 7920 |
| }, |
| { |
| "epoch": 4.547214454721446, |
| "grad_norm": 0.0018585673533380032, |
| "learning_rate": 2.4515083499253743e-07, |
| "loss": 0.0016, |
| "step": 7930 |
| }, |
| { |
| "epoch": 4.552950455295045, |
| "grad_norm": 0.003768256865441799, |
| "learning_rate": 2.3899466280504936e-07, |
| "loss": 0.0217, |
| "step": 7940 |
| }, |
| { |
| "epoch": 4.558686455868646, |
| "grad_norm": 0.05598225072026253, |
| "learning_rate": 2.3291488007105734e-07, |
| "loss": 0.009, |
| "step": 7950 |
| }, |
| { |
| "epoch": 4.558686455868646, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09063292294740677, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1171, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.923, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.485, |
| "step": 7950 |
| }, |
| { |
| "epoch": 4.564422456442245, |
| "grad_norm": 3.3265416622161865, |
| "learning_rate": 2.269115843395553e-07, |
| "loss": 0.0151, |
| "step": 7960 |
| }, |
| { |
| "epoch": 4.570158457015846, |
| "grad_norm": 0.0049064746126532555, |
| "learning_rate": 2.2098487193231543e-07, |
| "loss": 0.0208, |
| "step": 7970 |
| }, |
| { |
| "epoch": 4.575894457589445, |
| "grad_norm": 0.0036308506969362497, |
| "learning_rate": 2.1513483794234847e-07, |
| "loss": 0.0068, |
| "step": 7980 |
| }, |
| { |
| "epoch": 4.581630458163046, |
| "grad_norm": 0.0013542186934500933, |
| "learning_rate": 2.093615762323703e-07, |
| "loss": 0.0022, |
| "step": 7990 |
| }, |
| { |
| "epoch": 4.587366458736646, |
| "grad_norm": 2.7696778774261475, |
| "learning_rate": 2.0366517943330278e-07, |
| "loss": 0.0014, |
| "step": 8000 |
| }, |
| { |
| "epoch": 4.587366458736646, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.08961217105388641, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.3584, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.574, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.31, |
| "step": 8000 |
| }, |
| { |
| "epoch": 4.593102459310246, |
| "grad_norm": 0.0006430260837078094, |
| "learning_rate": 1.9804573894278311e-07, |
| "loss": 0.0137, |
| "step": 8010 |
| }, |
| { |
| "epoch": 4.598838459883846, |
| "grad_norm": 0.49191415309906006, |
| "learning_rate": 1.925033449236974e-07, |
| "loss": 0.0127, |
| "step": 8020 |
| }, |
| { |
| "epoch": 4.604574460457446, |
| "grad_norm": 0.4231385886669159, |
| "learning_rate": 1.8703808630273768e-07, |
| "loss": 0.0108, |
| "step": 8030 |
| }, |
| { |
| "epoch": 4.610310461031046, |
| "grad_norm": 5.982341289520264, |
| "learning_rate": 1.8165005076897114e-07, |
| "loss": 0.0034, |
| "step": 8040 |
| }, |
| { |
| "epoch": 4.616046461604646, |
| "grad_norm": 0.01885843276977539, |
| "learning_rate": 1.7633932477243599e-07, |
| "loss": 0.0227, |
| "step": 8050 |
| }, |
| { |
| "epoch": 4.616046461604646, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09145788848400116, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2115, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.785, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.416, |
| "step": 8050 |
| }, |
| { |
| "epoch": 4.621782462178246, |
| "grad_norm": 0.004457383882254362, |
| "learning_rate": 1.7110599352275104e-07, |
| "loss": 0.0066, |
| "step": 8060 |
| }, |
| { |
| "epoch": 4.627518462751846, |
| "grad_norm": 0.005887819454073906, |
| "learning_rate": 1.6595014098775342e-07, |
| "loss": 0.004, |
| "step": 8070 |
| }, |
| { |
| "epoch": 4.633254463325446, |
| "grad_norm": 0.023113150149583817, |
| "learning_rate": 1.6087184989214687e-07, |
| "loss": 0.0258, |
| "step": 8080 |
| }, |
| { |
| "epoch": 4.638990463899046, |
| "grad_norm": 0.020028818398714066, |
| "learning_rate": 1.5587120171617509e-07, |
| "loss": 0.0005, |
| "step": 8090 |
| }, |
| { |
| "epoch": 4.6447264644726465, |
| "grad_norm": 0.01912406086921692, |
| "learning_rate": 1.509482766943182e-07, |
| "loss": 0.0006, |
| "step": 8100 |
| }, |
| { |
| "epoch": 4.6447264644726465, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09051110595464706, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.4316, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.469, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.258, |
| "step": 8100 |
| }, |
| { |
| "epoch": 4.650462465046246, |
| "grad_norm": 3.4732401371002197, |
| "learning_rate": 1.4610315381400175e-07, |
| "loss": 0.0149, |
| "step": 8110 |
| }, |
| { |
| "epoch": 4.6561984656198465, |
| "grad_norm": 0.0006817178218625486, |
| "learning_rate": 1.4133591081432806e-07, |
| "loss": 0.0008, |
| "step": 8120 |
| }, |
| { |
| "epoch": 4.661934466193447, |
| "grad_norm": 0.0062561482191085815, |
| "learning_rate": 1.366466241848341e-07, |
| "loss": 0.0004, |
| "step": 8130 |
| }, |
| { |
| "epoch": 4.6676704667670466, |
| "grad_norm": 0.022234557196497917, |
| "learning_rate": 1.3203536916425842e-07, |
| "loss": 0.001, |
| "step": 8140 |
| }, |
| { |
| "epoch": 4.673406467340647, |
| "grad_norm": 4.0328369140625, |
| "learning_rate": 1.275022197393394e-07, |
| "loss": 0.0047, |
| "step": 8150 |
| }, |
| { |
| "epoch": 4.673406467340647, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09013617783784866, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1698, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.846, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.447, |
| "step": 8150 |
| }, |
| { |
| "epoch": 4.679142467914247, |
| "grad_norm": 0.15110693871974945, |
| "learning_rate": 1.230472486436246e-07, |
| "loss": 0.0004, |
| "step": 8160 |
| }, |
| { |
| "epoch": 4.684878468487847, |
| "grad_norm": 0.009227008558809757, |
| "learning_rate": 1.1867052735630435e-07, |
| "loss": 0.0014, |
| "step": 8170 |
| }, |
| { |
| "epoch": 4.690614469061447, |
| "grad_norm": 0.2895458936691284, |
| "learning_rate": 1.1437212610106496e-07, |
| "loss": 0.0013, |
| "step": 8180 |
| }, |
| { |
| "epoch": 4.696350469635047, |
| "grad_norm": 0.541077733039856, |
| "learning_rate": 1.1015211384496238e-07, |
| "loss": 0.0102, |
| "step": 8190 |
| }, |
| { |
| "epoch": 4.702086470208647, |
| "grad_norm": 2.9748380184173584, |
| "learning_rate": 1.0601055829731588e-07, |
| "loss": 0.023, |
| "step": 8200 |
| }, |
| { |
| "epoch": 4.702086470208647, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09088833630084991, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2127, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.783, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.415, |
| "step": 8200 |
| }, |
| { |
| "epoch": 4.707822470782247, |
| "grad_norm": 5.7777838706970215, |
| "learning_rate": 1.0194752590862223e-07, |
| "loss": 0.0119, |
| "step": 8210 |
| }, |
| { |
| "epoch": 4.713558471355848, |
| "grad_norm": 0.06003111973404884, |
| "learning_rate": 9.796308186948711e-08, |
| "loss": 0.0007, |
| "step": 8220 |
| }, |
| { |
| "epoch": 4.719294471929447, |
| "grad_norm": 0.005556735210120678, |
| "learning_rate": 9.405729010958043e-08, |
| "loss": 0.001, |
| "step": 8230 |
| }, |
| { |
| "epoch": 4.725030472503047, |
| "grad_norm": 2.6498606204986572, |
| "learning_rate": 9.023021329661152e-08, |
| "loss": 0.0095, |
| "step": 8240 |
| }, |
| { |
| "epoch": 4.730766473076647, |
| "grad_norm": 0.03512834012508392, |
| "learning_rate": 8.648191283532337e-08, |
| "loss": 0.0081, |
| "step": 8250 |
| }, |
| { |
| "epoch": 4.730766473076647, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.0907173827290535, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.316, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.634, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.341, |
| "step": 8250 |
| }, |
| { |
| "epoch": 4.736502473650248, |
| "grad_norm": 0.009284062311053276, |
| "learning_rate": 8.281244886650607e-08, |
| "loss": 0.0051, |
| "step": 8260 |
| }, |
| { |
| "epoch": 4.742238474223847, |
| "grad_norm": 0.02183857187628746, |
| "learning_rate": 7.922188026603273e-08, |
| "loss": 0.0022, |
| "step": 8270 |
| }, |
| { |
| "epoch": 4.747974474797448, |
| "grad_norm": 0.0035564859863370657, |
| "learning_rate": 7.571026464391451e-08, |
| "loss": 0.0025, |
| "step": 8280 |
| }, |
| { |
| "epoch": 4.753710475371047, |
| "grad_norm": 0.04188934341073036, |
| "learning_rate": 7.227765834337874e-08, |
| "loss": 0.0004, |
| "step": 8290 |
| }, |
| { |
| "epoch": 4.759446475944648, |
| "grad_norm": 0.6253750324249268, |
| "learning_rate": 6.892411643995955e-08, |
| "loss": 0.0006, |
| "step": 8300 |
| }, |
| { |
| "epoch": 4.759446475944648, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.090791717171669, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.3622, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.568, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.307, |
| "step": 8300 |
| }, |
| { |
| "epoch": 4.765182476518247, |
| "grad_norm": 0.3705517053604126, |
| "learning_rate": 6.564969274061972e-08, |
| "loss": 0.0042, |
| "step": 8310 |
| }, |
| { |
| "epoch": 4.770918477091848, |
| "grad_norm": 0.0012910285731777549, |
| "learning_rate": 6.245443978288413e-08, |
| "loss": 0.0023, |
| "step": 8320 |
| }, |
| { |
| "epoch": 4.776654477665447, |
| "grad_norm": 0.5175131559371948, |
| "learning_rate": 5.933840883399766e-08, |
| "loss": 0.0011, |
| "step": 8330 |
| }, |
| { |
| "epoch": 4.782390478239048, |
| "grad_norm": 3.527125358581543, |
| "learning_rate": 5.630164989010312e-08, |
| "loss": 0.0023, |
| "step": 8340 |
| }, |
| { |
| "epoch": 4.788126478812648, |
| "grad_norm": 0.3973446190357208, |
| "learning_rate": 5.334421167543735e-08, |
| "loss": 0.0026, |
| "step": 8350 |
| }, |
| { |
| "epoch": 4.788126478812648, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09068261086940765, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1697, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.846, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.447, |
| "step": 8350 |
| }, |
| { |
| "epoch": 4.793862479386248, |
| "grad_norm": 0.003769023111090064, |
| "learning_rate": 5.0466141641553056e-08, |
| "loss": 0.0001, |
| "step": 8360 |
| }, |
| { |
| "epoch": 4.799598479959848, |
| "grad_norm": 0.08687523007392883, |
| "learning_rate": 4.766748596655268e-08, |
| "loss": 0.0061, |
| "step": 8370 |
| }, |
| { |
| "epoch": 4.805334480533448, |
| "grad_norm": 5.824708461761475, |
| "learning_rate": 4.494828955435126e-08, |
| "loss": 0.0047, |
| "step": 8380 |
| }, |
| { |
| "epoch": 4.811070481107048, |
| "grad_norm": 2.9158382415771484, |
| "learning_rate": 4.230859603395421e-08, |
| "loss": 0.011, |
| "step": 8390 |
| }, |
| { |
| "epoch": 4.816806481680648, |
| "grad_norm": 0.04298550263047218, |
| "learning_rate": 3.974844775875786e-08, |
| "loss": 0.0016, |
| "step": 8400 |
| }, |
| { |
| "epoch": 4.816806481680648, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09151580929756165, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2757, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.692, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.37, |
| "step": 8400 |
| }, |
| { |
| "epoch": 4.822542482254248, |
| "grad_norm": 0.005364727228879929, |
| "learning_rate": 3.726788580586893e-08, |
| "loss": 0.0099, |
| "step": 8410 |
| }, |
| { |
| "epoch": 4.828278482827848, |
| "grad_norm": 0.0018757123034447432, |
| "learning_rate": 3.4866949975448374e-08, |
| "loss": 0.0009, |
| "step": 8420 |
| }, |
| { |
| "epoch": 4.8340144834014485, |
| "grad_norm": 0.008776834234595299, |
| "learning_rate": 3.254567879006798e-08, |
| "loss": 0.0068, |
| "step": 8430 |
| }, |
| { |
| "epoch": 4.839750483975048, |
| "grad_norm": 0.009764501824975014, |
| "learning_rate": 3.030410949409701e-08, |
| "loss": 0.0088, |
| "step": 8440 |
| }, |
| { |
| "epoch": 4.8454864845486485, |
| "grad_norm": 4.281154632568359, |
| "learning_rate": 2.8142278053101545e-08, |
| "loss": 0.0135, |
| "step": 8450 |
| }, |
| { |
| "epoch": 4.8454864845486485, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.0919208973646164, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1321, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.901, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.474, |
| "step": 8450 |
| }, |
| { |
| "epoch": 4.851222485122248, |
| "grad_norm": 0.09912008792161942, |
| "learning_rate": 2.6060219153268286e-08, |
| "loss": 0.0005, |
| "step": 8460 |
| }, |
| { |
| "epoch": 4.8569584856958485, |
| "grad_norm": 0.019211160019040108, |
| "learning_rate": 2.4057966200849437e-08, |
| "loss": 0.0005, |
| "step": 8470 |
| }, |
| { |
| "epoch": 4.862694486269449, |
| "grad_norm": 0.05037353187799454, |
| "learning_rate": 2.213555132162426e-08, |
| "loss": 0.0012, |
| "step": 8480 |
| }, |
| { |
| "epoch": 4.868430486843049, |
| "grad_norm": 0.00411713682115078, |
| "learning_rate": 2.0293005360386142e-08, |
| "loss": 0.0003, |
| "step": 8490 |
| }, |
| { |
| "epoch": 4.874166487416649, |
| "grad_norm": 0.0006664736429229379, |
| "learning_rate": 1.8530357880444105e-08, |
| "loss": 0.0202, |
| "step": 8500 |
| }, |
| { |
| "epoch": 4.874166487416649, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09091775864362717, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2769, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.69, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.369, |
| "step": 8500 |
| }, |
| { |
| "epoch": 4.879902487990249, |
| "grad_norm": 1.6142276525497437, |
| "learning_rate": 1.684763716315374e-08, |
| "loss": 0.0011, |
| "step": 8510 |
| }, |
| { |
| "epoch": 4.885638488563849, |
| "grad_norm": 0.000510135549120605, |
| "learning_rate": 1.524487020745813e-08, |
| "loss": 0.0011, |
| "step": 8520 |
| }, |
| { |
| "epoch": 4.891374489137449, |
| "grad_norm": 0.001830592635087669, |
| "learning_rate": 1.372208272945763e-08, |
| "loss": 0.0187, |
| "step": 8530 |
| }, |
| { |
| "epoch": 4.897110489711049, |
| "grad_norm": 0.2799864709377289, |
| "learning_rate": 1.2279299161997438e-08, |
| "loss": 0.0157, |
| "step": 8540 |
| }, |
| { |
| "epoch": 4.902846490284649, |
| "grad_norm": 0.009001590311527252, |
| "learning_rate": 1.0916542654273443e-08, |
| "loss": 0.0272, |
| "step": 8550 |
| }, |
| { |
| "epoch": 4.902846490284649, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09087590873241425, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.3382, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.602, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.325, |
| "step": 8550 |
| }, |
| { |
| "epoch": 4.908582490858249, |
| "grad_norm": 0.17294363677501678, |
| "learning_rate": 9.633835071463094e-09, |
| "loss": 0.0052, |
| "step": 8560 |
| }, |
| { |
| "epoch": 4.91431849143185, |
| "grad_norm": 0.008691389113664627, |
| "learning_rate": 8.431196994373447e-09, |
| "loss": 0.0065, |
| "step": 8570 |
| }, |
| { |
| "epoch": 4.920054492005449, |
| "grad_norm": 0.010057262144982815, |
| "learning_rate": 7.3086477191103285e-09, |
| "loss": 0.02, |
| "step": 8580 |
| }, |
| { |
| "epoch": 4.925790492579049, |
| "grad_norm": 0.19418714940547943, |
| "learning_rate": 6.2662052567702414e-09, |
| "loss": 0.0003, |
| "step": 8590 |
| }, |
| { |
| "epoch": 4.931526493152649, |
| "grad_norm": 0.033849816769361496, |
| "learning_rate": 5.303886333151154e-09, |
| "loss": 0.0126, |
| "step": 8600 |
| }, |
| { |
| "epoch": 4.931526493152649, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09129200130701065, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2495, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.73, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.389, |
| "step": 8600 |
| }, |
| { |
| "epoch": 4.93726249372625, |
| "grad_norm": 0.024734610691666603, |
| "learning_rate": 4.421706388481606e-09, |
| "loss": 0.0171, |
| "step": 8610 |
| }, |
| { |
| "epoch": 4.942998494299849, |
| "grad_norm": 0.0016847607912495732, |
| "learning_rate": 3.6196795771770156e-09, |
| "loss": 0.0126, |
| "step": 8620 |
| }, |
| { |
| "epoch": 4.94873449487345, |
| "grad_norm": 0.004256678279489279, |
| "learning_rate": 2.897818767609861e-09, |
| "loss": 0.0161, |
| "step": 8630 |
| }, |
| { |
| "epoch": 4.954470495447049, |
| "grad_norm": 4.404531002044678, |
| "learning_rate": 2.2561355419037368e-09, |
| "loss": 0.0087, |
| "step": 8640 |
| }, |
| { |
| "epoch": 4.96020649602065, |
| "grad_norm": 3.0091116428375244, |
| "learning_rate": 1.6946401957479431e-09, |
| "loss": 0.0145, |
| "step": 8650 |
| }, |
| { |
| "epoch": 4.96020649602065, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09181646257638931, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.2421, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.741, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.394, |
| "step": 8650 |
| }, |
| { |
| "epoch": 4.965942496594249, |
| "grad_norm": 0.04898509010672569, |
| "learning_rate": 1.2133417382320656e-09, |
| "loss": 0.0032, |
| "step": 8660 |
| }, |
| { |
| "epoch": 4.97167849716785, |
| "grad_norm": 0.002836048137396574, |
| "learning_rate": 8.122478916999799e-10, |
| "loss": 0.0074, |
| "step": 8670 |
| }, |
| { |
| "epoch": 4.977414497741449, |
| "grad_norm": 0.02022160217165947, |
| "learning_rate": 4.913650916299473e-10, |
| "loss": 0.0098, |
| "step": 8680 |
| }, |
| { |
| "epoch": 4.98315049831505, |
| "grad_norm": 0.007077803369611502, |
| "learning_rate": 2.506984865263684e-10, |
| "loss": 0.0016, |
| "step": 8690 |
| }, |
| { |
| "epoch": 4.98888649888865, |
| "grad_norm": 0.1649414747953415, |
| "learning_rate": 9.025193784151232e-11, |
| "loss": 0.0041, |
| "step": 8700 |
| }, |
| { |
| "epoch": 4.98888649888865, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_loss": 0.09170719236135483, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_runtime": 21.1606, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_samples_per_second": 30.859, |
| "eval_thought_eval_raw_data_english_72b_clean_1117_steps_per_second": 15.453, |
| "step": 8700 |
| }, |
| { |
| "epoch": 4.99462249946225, |
| "grad_norm": 0.00366253312677145, |
| "learning_rate": 1.0028019910013342e-11, |
| "loss": 0.0032, |
| "step": 8710 |
| }, |
| { |
| "epoch": 4.99749049974905, |
| "step": 8715, |
| "total_flos": 6.758260289254195e+17, |
| "train_loss": 0.02162364056710329, |
| "train_runtime": 21813.1277, |
| "train_samples_per_second": 6.394, |
| "train_steps_per_second": 0.4 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 8715, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 250, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.758260289254195e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
