{"current_steps": 2, "total_steps": 780, "loss": 0.7593, "learning_rate": 5.128205128205128e-07, "epoch": 0.0025622547842101048, "percentage": 0.26, "elapsed_time": "0:00:23", "remaining_time": "2:34:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 4, "total_steps": 780, "loss": 0.8076, "learning_rate": 1.0256410256410257e-06, "epoch": 0.0051245095684202095, "percentage": 0.51, "elapsed_time": "0:00:48", "remaining_time": "2:35:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 6, "total_steps": 780, "loss": 0.7059, "learning_rate": 1.5384615384615387e-06, "epoch": 0.007686764352630314, "percentage": 0.77, "elapsed_time": "0:01:15", "remaining_time": "2:43:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 8, "total_steps": 780, "loss": 0.715, "learning_rate": 2.0512820512820513e-06, "epoch": 0.010249019136840419, "percentage": 1.03, "elapsed_time": "0:01:47", "remaining_time": "2:52:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 10, "total_steps": 780, "loss": 0.7175, "learning_rate": 2.564102564102564e-06, "epoch": 0.012811273921050524, "percentage": 1.28, "elapsed_time": "0:02:12", "remaining_time": "2:50:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 12, "total_steps": 780, "loss": 0.6976, "learning_rate": 3.0769230769230774e-06, "epoch": 0.015373528705260629, "percentage": 1.54, "elapsed_time": "0:02:43", "remaining_time": "2:54:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 14, "total_steps": 780, "loss": 0.7615, "learning_rate": 3.58974358974359e-06, "epoch": 0.017935783489470735, "percentage": 1.79, "elapsed_time": "0:03:07", "remaining_time": "2:51:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 16, "total_steps": 780, "loss": 0.6735, "learning_rate": 4.102564102564103e-06, "epoch": 0.020498038273680838, "percentage": 2.05, "elapsed_time": "0:03:34", "remaining_time": "2:50:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 18, "total_steps": 780, "loss": 0.6885, "learning_rate": 4.615384615384616e-06, "epoch": 0.023060293057890945, "percentage": 2.31, "elapsed_time": "0:03:58", "remaining_time": "2:48:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 20, "total_steps": 780, "loss": 0.768, "learning_rate": 5.128205128205128e-06, "epoch": 0.025622547842101048, "percentage": 2.56, "elapsed_time": "0:04:22", "remaining_time": "2:46:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 22, "total_steps": 780, "loss": 0.7092, "learning_rate": 5.641025641025641e-06, "epoch": 0.028184802626311154, "percentage": 2.82, "elapsed_time": "0:04:48", "remaining_time": "2:45:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 24, "total_steps": 780, "loss": 0.6764, "learning_rate": 6.153846153846155e-06, "epoch": 0.030747057410521257, "percentage": 3.08, "elapsed_time": "0:05:13", "remaining_time": "2:44:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 26, "total_steps": 780, "loss": 0.6386, "learning_rate": 6.666666666666667e-06, "epoch": 0.033309312194731364, "percentage": 3.33, "elapsed_time": "0:05:41", "remaining_time": "2:44:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 28, "total_steps": 780, "loss": 0.6218, "learning_rate": 7.17948717948718e-06, "epoch": 0.03587156697894147, "percentage": 3.59, "elapsed_time": "0:06:05", "remaining_time": "2:43:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 30, "total_steps": 780, "loss": 0.5853, "learning_rate": 7.692307692307694e-06, "epoch": 0.03843382176315158, "percentage": 3.85, "elapsed_time": "0:06:34", "remaining_time": "2:44:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 32, "total_steps": 780, "loss": 0.5441, "learning_rate": 8.205128205128205e-06, "epoch": 0.040996076547361676, "percentage": 4.1, "elapsed_time": "0:07:01", "remaining_time": "2:44:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 34, "total_steps": 780, "loss": 0.5458, "learning_rate": 8.717948717948719e-06, "epoch": 0.04355833133157178, "percentage": 4.36, "elapsed_time": "0:07:26", "remaining_time": "2:43:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 36, "total_steps": 780, "loss": 0.4589, "learning_rate": 9.230769230769232e-06, "epoch": 0.04612058611578189, "percentage": 4.62, "elapsed_time": "0:07:50", "remaining_time": "2:41:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 38, "total_steps": 780, "loss": 0.4386, "learning_rate": 9.743589743589744e-06, "epoch": 0.048682840899991996, "percentage": 4.87, "elapsed_time": "0:08:13", "remaining_time": "2:40:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 40, "total_steps": 780, "loss": 0.4215, "learning_rate": 9.99995506314361e-06, "epoch": 0.051245095684202095, "percentage": 5.13, "elapsed_time": "0:08:38", "remaining_time": "2:39:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 42, "total_steps": 780, "loss": 0.3888, "learning_rate": 9.999595573138845e-06, "epoch": 0.0538073504684122, "percentage": 5.38, "elapsed_time": "0:09:06", "remaining_time": "2:39:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 44, "total_steps": 780, "loss": 0.3749, "learning_rate": 9.99887661897616e-06, "epoch": 0.05636960525262231, "percentage": 5.64, "elapsed_time": "0:09:31", "remaining_time": "2:39:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 46, "total_steps": 780, "loss": 0.3543, "learning_rate": 9.997798252347382e-06, "epoch": 0.058931860036832415, "percentage": 5.9, "elapsed_time": "0:09:59", "remaining_time": "2:39:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 48, "total_steps": 780, "loss": 0.3565, "learning_rate": 9.996360550785619e-06, "epoch": 0.061494114821042514, "percentage": 6.15, "elapsed_time": "0:10:27", "remaining_time": "2:39:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 50, "total_steps": 780, "loss": 0.3242, "learning_rate": 9.994563617659665e-06, "epoch": 0.06405636960525263, "percentage": 6.41, "elapsed_time": "0:10:54", "remaining_time": "2:39:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 52, "total_steps": 780, "loss": 0.3334, "learning_rate": 9.992407582166582e-06, "epoch": 0.06661862438946273, "percentage": 6.67, "elapsed_time": "0:11:23", "remaining_time": "2:39:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 54, "total_steps": 780, "loss": 0.3741, "learning_rate": 9.989892599322404e-06, "epoch": 0.06918087917367283, "percentage": 6.92, "elapsed_time": "0:11:52", "remaining_time": "2:39:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 56, "total_steps": 780, "loss": 0.3331, "learning_rate": 9.987018849950996e-06, "epoch": 0.07174313395788294, "percentage": 7.18, "elapsed_time": "0:12:17", "remaining_time": "2:38:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 58, "total_steps": 780, "loss": 0.3335, "learning_rate": 9.983786540671052e-06, "epoch": 0.07430538874209304, "percentage": 7.44, "elapsed_time": "0:12:44", "remaining_time": "2:38:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 60, "total_steps": 780, "loss": 0.3344, "learning_rate": 9.980195903881231e-06, "epoch": 0.07686764352630315, "percentage": 7.69, "elapsed_time": "0:13:09", "remaining_time": "2:37:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 62, "total_steps": 780, "loss": 0.3055, "learning_rate": 9.976247197743465e-06, "epoch": 0.07942989831051325, "percentage": 7.95, "elapsed_time": "0:13:31", "remaining_time": "2:36:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 64, "total_steps": 780, "loss": 0.3187, "learning_rate": 9.97194070616438e-06, "epoch": 0.08199215309472335, "percentage": 8.21, "elapsed_time": "0:13:55", "remaining_time": "2:35:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 66, "total_steps": 780, "loss": 0.2998, "learning_rate": 9.967276738774897e-06, "epoch": 0.08455440787893347, "percentage": 8.46, "elapsed_time": "0:14:23", "remaining_time": "2:35:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 68, "total_steps": 780, "loss": 0.3251, "learning_rate": 9.962255630907964e-06, "epoch": 0.08711666266314357, "percentage": 8.72, "elapsed_time": "0:14:48", "remaining_time": "2:35:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 70, "total_steps": 780, "loss": 0.317, "learning_rate": 9.956877743574437e-06, "epoch": 0.08967891744735366, "percentage": 8.97, "elapsed_time": "0:15:15", "remaining_time": "2:34:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 72, "total_steps": 780, "loss": 0.31, "learning_rate": 9.951143463437145e-06, "epoch": 0.09224117223156378, "percentage": 9.23, "elapsed_time": "0:15:41", "remaining_time": "2:34:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 74, "total_steps": 780, "loss": 0.3158, "learning_rate": 9.94505320278307e-06, "epoch": 0.09480342701577388, "percentage": 9.49, "elapsed_time": "0:16:05", "remaining_time": "2:33:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 76, "total_steps": 780, "loss": 0.3163, "learning_rate": 9.938607399493714e-06, "epoch": 0.09736568179998399, "percentage": 9.74, "elapsed_time": "0:16:30", "remaining_time": "2:32:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 78, "total_steps": 780, "loss": 0.3132, "learning_rate": 9.931806517013612e-06, "epoch": 0.09992793658419409, "percentage": 10.0, "elapsed_time": "0:16:56", "remaining_time": "2:32:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 80, "total_steps": 780, "loss": 0.315, "learning_rate": 9.924651044317017e-06, "epoch": 0.10249019136840419, "percentage": 10.26, "elapsed_time": "0:17:20", "remaining_time": "2:31:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 82, "total_steps": 780, "loss": 0.2851, "learning_rate": 9.917141495872733e-06, "epoch": 0.1050524461526143, "percentage": 10.51, "elapsed_time": "0:17:45", "remaining_time": "2:31:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 84, "total_steps": 780, "loss": 0.3036, "learning_rate": 9.909278411607134e-06, "epoch": 0.1076147009368244, "percentage": 10.77, "elapsed_time": "0:18:10", "remaining_time": "2:30:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 86, "total_steps": 780, "loss": 0.3374, "learning_rate": 9.90106235686534e-06, "epoch": 0.11017695572103452, "percentage": 11.03, "elapsed_time": "0:18:38", "remaining_time": "2:30:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 88, "total_steps": 780, "loss": 0.316, "learning_rate": 9.892493922370575e-06, "epoch": 0.11273921050524462, "percentage": 11.28, "elapsed_time": "0:19:02", "remaining_time": "2:29:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 90, "total_steps": 780, "loss": 0.3284, "learning_rate": 9.883573724181683e-06, "epoch": 0.11530146528945472, "percentage": 11.54, "elapsed_time": "0:19:25", "remaining_time": "2:28:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 92, "total_steps": 780, "loss": 0.3266, "learning_rate": 9.87430240364885e-06, "epoch": 0.11786372007366483, "percentage": 11.79, "elapsed_time": "0:19:51", "remaining_time": "2:28:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 94, "total_steps": 780, "loss": 0.3104, "learning_rate": 9.864680627367476e-06, "epoch": 0.12042597485787493, "percentage": 12.05, "elapsed_time": "0:20:16", "remaining_time": "2:28:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 96, "total_steps": 780, "loss": 0.3221, "learning_rate": 9.854709087130261e-06, "epoch": 0.12298822964208503, "percentage": 12.31, "elapsed_time": "0:20:43", "remaining_time": "2:27:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 98, "total_steps": 780, "loss": 0.2913, "learning_rate": 9.844388499877457e-06, "epoch": 0.12555048442629513, "percentage": 12.56, "elapsed_time": "0:21:11", "remaining_time": "2:27:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 100, "total_steps": 780, "loss": 0.2974, "learning_rate": 9.833719607645325e-06, "epoch": 0.12811273921050526, "percentage": 12.82, "elapsed_time": "0:21:37", "remaining_time": "2:27:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 102, "total_steps": 780, "loss": 0.3698, "learning_rate": 9.822703177512783e-06, "epoch": 0.13067499399471535, "percentage": 13.08, "elapsed_time": "0:22:06", "remaining_time": "2:26:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 104, "total_steps": 780, "loss": 0.2995, "learning_rate": 9.811340001546252e-06, "epoch": 0.13323724877892545, "percentage": 13.33, "elapsed_time": "0:22:30", "remaining_time": "2:26:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 106, "total_steps": 780, "loss": 0.304, "learning_rate": 9.799630896742716e-06, "epoch": 0.13579950356313555, "percentage": 13.59, "elapsed_time": "0:22:57", "remaining_time": "2:25:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 108, "total_steps": 780, "loss": 0.3032, "learning_rate": 9.787576704970965e-06, "epoch": 0.13836175834734565, "percentage": 13.85, "elapsed_time": "0:23:20", "remaining_time": "2:25:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 110, "total_steps": 780, "loss": 0.2915, "learning_rate": 9.77517829291108e-06, "epoch": 0.14092401313155578, "percentage": 14.1, "elapsed_time": "0:23:44", "remaining_time": "2:24:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 112, "total_steps": 780, "loss": 0.3192, "learning_rate": 9.762436551992117e-06, "epoch": 0.14348626791576588, "percentage": 14.36, "elapsed_time": "0:24:09", "remaining_time": "2:24:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 114, "total_steps": 780, "loss": 0.2999, "learning_rate": 9.74935239832801e-06, "epoch": 0.14604852269997598, "percentage": 14.62, "elapsed_time": "0:24:33", "remaining_time": "2:23:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 116, "total_steps": 780, "loss": 0.31, "learning_rate": 9.735926772651703e-06, "epoch": 0.14861077748418608, "percentage": 14.87, "elapsed_time": "0:24:59", "remaining_time": "2:23:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 118, "total_steps": 780, "loss": 0.292, "learning_rate": 9.722160640247523e-06, "epoch": 0.15117303226839618, "percentage": 15.13, "elapsed_time": "0:25:25", "remaining_time": "2:22:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 120, "total_steps": 780, "loss": 0.3077, "learning_rate": 9.708054990881763e-06, "epoch": 0.1537352870526063, "percentage": 15.38, "elapsed_time": "0:25:51", "remaining_time": "2:22:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 122, "total_steps": 780, "loss": 0.3132, "learning_rate": 9.693610838731532e-06, "epoch": 0.1562975418368164, "percentage": 15.64, "elapsed_time": "0:26:16", "remaining_time": "2:21:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 124, "total_steps": 780, "loss": 0.3139, "learning_rate": 9.678829222311827e-06, "epoch": 0.1588597966210265, "percentage": 15.9, "elapsed_time": "0:26:40", "remaining_time": "2:21:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 126, "total_steps": 780, "loss": 0.2992, "learning_rate": 9.663711204400872e-06, "epoch": 0.1614220514052366, "percentage": 16.15, "elapsed_time": "0:27:08", "remaining_time": "2:20:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 128, "total_steps": 780, "loss": 0.3066, "learning_rate": 9.6482578719637e-06, "epoch": 0.1639843061894467, "percentage": 16.41, "elapsed_time": "0:27:36", "remaining_time": "2:20:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 130, "total_steps": 780, "loss": 0.3121, "learning_rate": 9.632470336074009e-06, "epoch": 0.1665465609736568, "percentage": 16.67, "elapsed_time": "0:27:59", "remaining_time": "2:19:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 132, "total_steps": 780, "loss": 0.2991, "learning_rate": 9.616349731834271e-06, "epoch": 0.16910881575786693, "percentage": 16.92, "elapsed_time": "0:28:24", "remaining_time": "2:19:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 134, "total_steps": 780, "loss": 0.3227, "learning_rate": 9.599897218294122e-06, "epoch": 0.17167107054207703, "percentage": 17.18, "elapsed_time": "0:28:48", "remaining_time": "2:18:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 136, "total_steps": 780, "loss": 0.3025, "learning_rate": 9.583113978367026e-06, "epoch": 0.17423332532628713, "percentage": 17.44, "elapsed_time": "0:29:16", "remaining_time": "2:18:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 138, "total_steps": 780, "loss": 0.3179, "learning_rate": 9.56600121874523e-06, "epoch": 0.17679558011049723, "percentage": 17.69, "elapsed_time": "0:29:46", "remaining_time": "2:18:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 140, "total_steps": 780, "loss": 0.2906, "learning_rate": 9.548560169812997e-06, "epoch": 0.17935783489470733, "percentage": 17.95, "elapsed_time": "0:30:14", "remaining_time": "2:18:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 142, "total_steps": 780, "loss": 0.2968, "learning_rate": 9.530792085558151e-06, "epoch": 0.18192008967891746, "percentage": 18.21, "elapsed_time": "0:30:38", "remaining_time": "2:17:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 144, "total_steps": 780, "loss": 0.3076, "learning_rate": 9.512698243481914e-06, "epoch": 0.18448234446312756, "percentage": 18.46, "elapsed_time": "0:31:06", "remaining_time": "2:17:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 146, "total_steps": 780, "loss": 0.292, "learning_rate": 9.49427994450705e-06, "epoch": 0.18704459924733766, "percentage": 18.72, "elapsed_time": "0:31:32", "remaining_time": "2:16:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 148, "total_steps": 780, "loss": 0.3337, "learning_rate": 9.47553851288434e-06, "epoch": 0.18960685403154776, "percentage": 18.97, "elapsed_time": "0:32:00", "remaining_time": "2:16:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 150, "total_steps": 780, "loss": 0.2854, "learning_rate": 9.45647529609736e-06, "epoch": 0.19216910881575786, "percentage": 19.23, "elapsed_time": "0:32:23", "remaining_time": "2:16:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 152, "total_steps": 780, "loss": 0.328, "learning_rate": 9.437091664765611e-06, "epoch": 0.19473136359996798, "percentage": 19.49, "elapsed_time": "0:32:46", "remaining_time": "2:15:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 154, "total_steps": 780, "loss": 0.2831, "learning_rate": 9.41738901254596e-06, "epoch": 0.19729361838417808, "percentage": 19.74, "elapsed_time": "0:33:14", "remaining_time": "2:15:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 156, "total_steps": 780, "loss": 0.2899, "learning_rate": 9.397368756032445e-06, "epoch": 0.19985587316838818, "percentage": 20.0, "elapsed_time": "0:33:39", "remaining_time": "2:14:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 158, "total_steps": 780, "loss": 0.2796, "learning_rate": 9.37703233465443e-06, "epoch": 0.20241812795259828, "percentage": 20.26, "elapsed_time": "0:34:03", "remaining_time": "2:14:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 160, "total_steps": 780, "loss": 0.2965, "learning_rate": 9.356381210573092e-06, "epoch": 0.20498038273680838, "percentage": 20.51, "elapsed_time": "0:34:27", "remaining_time": "2:13:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 162, "total_steps": 780, "loss": 0.2884, "learning_rate": 9.33541686857632e-06, "epoch": 0.2075426375210185, "percentage": 20.77, "elapsed_time": "0:34:55", "remaining_time": "2:13:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 164, "total_steps": 780, "loss": 0.297, "learning_rate": 9.31414081597194e-06, "epoch": 0.2101048923052286, "percentage": 21.03, "elapsed_time": "0:35:22", "remaining_time": "2:12:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 166, "total_steps": 780, "loss": 0.2862, "learning_rate": 9.292554582479349e-06, "epoch": 0.2126671470894387, "percentage": 21.28, "elapsed_time": "0:35:46", "remaining_time": "2:12:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 168, "total_steps": 780, "loss": 0.2958, "learning_rate": 9.270659720119533e-06, "epoch": 0.2152294018736488, "percentage": 21.54, "elapsed_time": "0:36:15", "remaining_time": "2:12:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 170, "total_steps": 780, "loss": 0.2988, "learning_rate": 9.248457803103476e-06, "epoch": 0.2177916566578589, "percentage": 21.79, "elapsed_time": "0:36:42", "remaining_time": "2:11:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 172, "total_steps": 780, "loss": 0.2803, "learning_rate": 9.225950427718974e-06, "epoch": 0.22035391144206903, "percentage": 22.05, "elapsed_time": "0:37:10", "remaining_time": "2:11:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 174, "total_steps": 780, "loss": 0.2957, "learning_rate": 9.203139212215868e-06, "epoch": 0.22291616622627913, "percentage": 22.31, "elapsed_time": "0:37:35", "remaining_time": "2:10:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 176, "total_steps": 780, "loss": 0.2933, "learning_rate": 9.180025796689692e-06, "epoch": 0.22547842101048923, "percentage": 22.56, "elapsed_time": "0:38:01", "remaining_time": "2:10:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 178, "total_steps": 780, "loss": 0.2926, "learning_rate": 9.156611842963753e-06, "epoch": 0.22804067579469933, "percentage": 22.82, "elapsed_time": "0:38:24", "remaining_time": "2:09:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 180, "total_steps": 780, "loss": 0.3111, "learning_rate": 9.132899034469648e-06, "epoch": 0.23060293057890943, "percentage": 23.08, "elapsed_time": "0:38:47", "remaining_time": "2:09:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 182, "total_steps": 780, "loss": 0.2948, "learning_rate": 9.108889076126226e-06, "epoch": 0.23316518536311953, "percentage": 23.33, "elapsed_time": "0:39:11", "remaining_time": "2:08:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 184, "total_steps": 780, "loss": 0.2872, "learning_rate": 9.084583694217012e-06, "epoch": 0.23572744014732966, "percentage": 23.59, "elapsed_time": "0:39:36", "remaining_time": "2:08:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 186, "total_steps": 780, "loss": 0.3073, "learning_rate": 9.059984636266082e-06, "epoch": 0.23828969493153976, "percentage": 23.85, "elapsed_time": "0:40:04", "remaining_time": "2:08:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 188, "total_steps": 780, "loss": 0.2866, "learning_rate": 9.035093670912424e-06, "epoch": 0.24085194971574986, "percentage": 24.1, "elapsed_time": "0:40:30", "remaining_time": "2:07:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 190, "total_steps": 780, "loss": 0.298, "learning_rate": 9.009912587782772e-06, "epoch": 0.24341420449995996, "percentage": 24.36, "elapsed_time": "0:40:54", "remaining_time": "2:07:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 192, "total_steps": 780, "loss": 0.2644, "learning_rate": 8.984443197362938e-06, "epoch": 0.24597645928417006, "percentage": 24.62, "elapsed_time": "0:41:18", "remaining_time": "2:06:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 194, "total_steps": 780, "loss": 0.2986, "learning_rate": 8.958687330867634e-06, "epoch": 0.24853871406838018, "percentage": 24.87, "elapsed_time": "0:41:44", "remaining_time": "2:06:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 196, "total_steps": 780, "loss": 0.2826, "learning_rate": 8.932646840108818e-06, "epoch": 0.25110096885259026, "percentage": 25.13, "elapsed_time": "0:42:09", "remaining_time": "2:05:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 198, "total_steps": 780, "loss": 0.2824, "learning_rate": 8.906323597362547e-06, "epoch": 0.2536632236368004, "percentage": 25.38, "elapsed_time": "0:42:37", "remaining_time": "2:05:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 200, "total_steps": 780, "loss": 0.2836, "learning_rate": 8.879719495234363e-06, "epoch": 0.2562254784210105, "percentage": 25.64, "elapsed_time": "0:43:02", "remaining_time": "2:04:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 202, "total_steps": 780, "loss": 0.2799, "learning_rate": 8.852836446523213e-06, "epoch": 0.2587877332052206, "percentage": 25.9, "elapsed_time": "0:43:30", "remaining_time": "2:04:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 204, "total_steps": 780, "loss": 0.3027, "learning_rate": 8.825676384083936e-06, "epoch": 0.2613499879894307, "percentage": 26.15, "elapsed_time": "0:43:55", "remaining_time": "2:04:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 206, "total_steps": 780, "loss": 0.3032, "learning_rate": 8.798241260688273e-06, "epoch": 0.2639122427736408, "percentage": 26.41, "elapsed_time": "0:44:20", "remaining_time": "2:03:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 208, "total_steps": 780, "loss": 0.3044, "learning_rate": 8.770533048884483e-06, "epoch": 0.2664744975578509, "percentage": 26.67, "elapsed_time": "0:44:45", "remaining_time": "2:03:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 210, "total_steps": 780, "loss": 0.2784, "learning_rate": 8.742553740855507e-06, "epoch": 0.26903675234206104, "percentage": 26.92, "elapsed_time": "0:45:12", "remaining_time": "2:02:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 212, "total_steps": 780, "loss": 0.3142, "learning_rate": 8.71430534827574e-06, "epoch": 0.2715990071262711, "percentage": 27.18, "elapsed_time": "0:45:42", "remaining_time": "2:02:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 214, "total_steps": 780, "loss": 0.2592, "learning_rate": 8.685789902166395e-06, "epoch": 0.27416126191048124, "percentage": 27.44, "elapsed_time": "0:46:08", "remaining_time": "2:02:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 216, "total_steps": 780, "loss": 0.2881, "learning_rate": 8.657009452749466e-06, "epoch": 0.2767235166946913, "percentage": 27.69, "elapsed_time": "0:46:32", "remaining_time": "2:01:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 218, "total_steps": 780, "loss": 0.3017, "learning_rate": 8.627966069300332e-06, "epoch": 0.27928577147890143, "percentage": 27.95, "elapsed_time": "0:46:58", "remaining_time": "2:01:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 220, "total_steps": 780, "loss": 0.2781, "learning_rate": 8.598661839998972e-06, "epoch": 0.28184802626311156, "percentage": 28.21, "elapsed_time": "0:47:22", "remaining_time": "2:00:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 222, "total_steps": 780, "loss": 0.296, "learning_rate": 8.569098871779828e-06, "epoch": 0.28441028104732163, "percentage": 28.46, "elapsed_time": "0:47:51", "remaining_time": "2:00:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 224, "total_steps": 780, "loss": 0.3161, "learning_rate": 8.539279290180315e-06, "epoch": 0.28697253583153176, "percentage": 28.72, "elapsed_time": "0:48:18", "remaining_time": "1:59:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 226, "total_steps": 780, "loss": 0.2948, "learning_rate": 8.509205239188017e-06, "epoch": 0.28953479061574183, "percentage": 28.97, "elapsed_time": "0:48:45", "remaining_time": "1:59:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 228, "total_steps": 780, "loss": 0.2736, "learning_rate": 8.478878881086505e-06, "epoch": 0.29209704539995196, "percentage": 29.23, "elapsed_time": "0:49:08", "remaining_time": "1:58:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 230, "total_steps": 780, "loss": 0.2954, "learning_rate": 8.448302396299906e-06, "epoch": 0.2946593001841621, "percentage": 29.49, "elapsed_time": "0:49:32", "remaining_time": "1:58:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 232, "total_steps": 780, "loss": 0.3134, "learning_rate": 8.417477983236107e-06, "epoch": 0.29722155496837216, "percentage": 29.74, "elapsed_time": "0:49:57", "remaining_time": "1:58:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 234, "total_steps": 780, "loss": 0.2767, "learning_rate": 8.386407858128707e-06, "epoch": 0.2997838097525823, "percentage": 30.0, "elapsed_time": "0:50:21", "remaining_time": "1:57:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 236, "total_steps": 780, "loss": 0.2783, "learning_rate": 8.355094254877665e-06, "epoch": 0.30234606453679236, "percentage": 30.26, "elapsed_time": "0:50:46", "remaining_time": "1:57:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 238, "total_steps": 780, "loss": 0.2871, "learning_rate": 8.323539424888695e-06, "epoch": 0.3049083193210025, "percentage": 30.51, "elapsed_time": "0:51:10", "remaining_time": "1:56:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 240, "total_steps": 780, "loss": 0.2747, "learning_rate": 8.291745636911382e-06, "epoch": 0.3074705741052126, "percentage": 30.77, "elapsed_time": "0:51:40", "remaining_time": "1:56:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 242, "total_steps": 780, "loss": 0.2737, "learning_rate": 8.259715176876069e-06, "epoch": 0.3100328288894227, "percentage": 31.03, "elapsed_time": "0:52:08", "remaining_time": "1:55:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 244, "total_steps": 780, "loss": 0.2889, "learning_rate": 8.2274503477295e-06, "epoch": 0.3125950836736328, "percentage": 31.28, "elapsed_time": "0:52:37", "remaining_time": "1:55:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 246, "total_steps": 780, "loss": 0.2822, "learning_rate": 8.19495346926924e-06, "epoch": 0.3151573384578429, "percentage": 31.54, "elapsed_time": "0:53:00", "remaining_time": "1:55:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 248, "total_steps": 780, "loss": 0.284, "learning_rate": 8.162226877976886e-06, "epoch": 0.317719593242053, "percentage": 31.79, "elapsed_time": "0:53:28", "remaining_time": "1:54:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 250, "total_steps": 780, "loss": 0.2915, "learning_rate": 8.129272926850079e-06, "epoch": 0.32028184802626314, "percentage": 32.05, "elapsed_time": "0:53:52", "remaining_time": "1:54:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 252, "total_steps": 780, "loss": 0.2842, "learning_rate": 8.096093985233323e-06, "epoch": 0.3228441028104732, "percentage": 32.31, "elapsed_time": "0:54:18", "remaining_time": "1:53:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 254, "total_steps": 780, "loss": 0.3203, "learning_rate": 8.062692438647628e-06, "epoch": 0.32540635759468334, "percentage": 32.56, "elapsed_time": "0:54:44", "remaining_time": "1:53:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 256, "total_steps": 780, "loss": 0.2828, "learning_rate": 8.029070688619013e-06, "epoch": 0.3279686123788934, "percentage": 32.82, "elapsed_time": "0:55:10", "remaining_time": "1:52:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 258, "total_steps": 780, "loss": 0.2672, "learning_rate": 7.995231152505815e-06, "epoch": 0.33053086716310354, "percentage": 33.08, "elapsed_time": "0:55:36", "remaining_time": "1:52:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 260, "total_steps": 780, "loss": 0.292, "learning_rate": 7.961176263324902e-06, "epoch": 0.3330931219473136, "percentage": 33.33, "elapsed_time": "0:56:04", "remaining_time": "1:52:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 262, "total_steps": 780, "loss": 0.2987, "learning_rate": 7.92690846957673e-06, "epoch": 0.33565537673152374, "percentage": 33.59, "elapsed_time": "0:56:29", "remaining_time": "1:51:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 264, "total_steps": 780, "loss": 0.2881, "learning_rate": 7.892430235069317e-06, "epoch": 0.33821763151573386, "percentage": 33.85, "elapsed_time": "0:56:58", "remaining_time": "1:51:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 266, "total_steps": 780, "loss": 0.2912, "learning_rate": 7.857744038741076e-06, "epoch": 0.34077988629994393, "percentage": 34.1, "elapsed_time": "0:57:22", "remaining_time": "1:50:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 268, "total_steps": 780, "loss": 0.2672, "learning_rate": 7.822852374482597e-06, "epoch": 0.34334214108415406, "percentage": 34.36, "elapsed_time": "0:57:51", "remaining_time": "1:50:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 270, "total_steps": 780, "loss": 0.2921, "learning_rate": 7.787757750957335e-06, "epoch": 0.34590439586836413, "percentage": 34.62, "elapsed_time": "0:58:17", "remaining_time": "1:50:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 272, "total_steps": 780, "loss": 0.2676, "learning_rate": 7.752462691421245e-06, "epoch": 0.34846665065257426, "percentage": 34.87, "elapsed_time": "0:58:42", "remaining_time": "1:49:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 274, "total_steps": 780, "loss": 0.2576, "learning_rate": 7.716969733541357e-06, "epoch": 0.3510289054367844, "percentage": 35.13, "elapsed_time": "0:59:05", "remaining_time": "1:49:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 276, "total_steps": 780, "loss": 0.2686, "learning_rate": 7.681281429213328e-06, "epoch": 0.35359116022099446, "percentage": 35.38, "elapsed_time": "0:59:35", "remaining_time": "1:48:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 278, "total_steps": 780, "loss": 0.2678, "learning_rate": 7.645400344377953e-06, "epoch": 0.3561534150052046, "percentage": 35.64, "elapsed_time": "1:00:01", "remaining_time": "1:48:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 280, "total_steps": 780, "loss": 0.2907, "learning_rate": 7.609329058836694e-06, "epoch": 0.35871566978941466, "percentage": 35.9, "elapsed_time": "1:00:28", "remaining_time": "1:47:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 282, "total_steps": 780, "loss": 0.298, "learning_rate": 7.5730701660661795e-06, "epoch": 0.3612779245736248, "percentage": 36.15, "elapsed_time": "1:00:52", "remaining_time": "1:47:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 284, "total_steps": 780, "loss": 0.263, "learning_rate": 7.536626273031747e-06, "epoch": 0.3638401793578349, "percentage": 36.41, "elapsed_time": "1:01:20", "remaining_time": "1:47:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 286, "total_steps": 780, "loss": 0.2733, "learning_rate": 7.500000000000001e-06, "epoch": 0.366402434142045, "percentage": 36.67, "elapsed_time": "1:01:46", "remaining_time": "1:46:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 288, "total_steps": 780, "loss": 0.3159, "learning_rate": 7.4631939803504215e-06, "epoch": 0.3689646889262551, "percentage": 36.92, "elapsed_time": "1:02:13", "remaining_time": "1:46:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 290, "total_steps": 780, "loss": 0.2878, "learning_rate": 7.426210860386032e-06, "epoch": 0.3715269437104652, "percentage": 37.18, "elapsed_time": "1:02:39", "remaining_time": "1:45:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 292, "total_steps": 780, "loss": 0.2829, "learning_rate": 7.3890532991431174e-06, "epoch": 0.3740891984946753, "percentage": 37.44, "elapsed_time": "1:03:04", "remaining_time": "1:45:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 294, "total_steps": 780, "loss": 0.2646, "learning_rate": 7.3517239682000675e-06, "epoch": 0.37665145327888544, "percentage": 37.69, "elapsed_time": "1:03:28", "remaining_time": "1:44:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 296, "total_steps": 780, "loss": 0.301, "learning_rate": 7.314225551485273e-06, "epoch": 0.3792137080630955, "percentage": 37.95, "elapsed_time": "1:03:53", "remaining_time": "1:44:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 298, "total_steps": 780, "loss": 0.2622, "learning_rate": 7.276560745084167e-06, "epoch": 0.38177596284730564, "percentage": 38.21, "elapsed_time": "1:04:18", "remaining_time": "1:44:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 300, "total_steps": 780, "loss": 0.2901, "learning_rate": 7.2387322570453724e-06, "epoch": 0.3843382176315157, "percentage": 38.46, "elapsed_time": "1:04:45", "remaining_time": "1:43:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 302, "total_steps": 780, "loss": 0.2576, "learning_rate": 7.2007428071860045e-06, "epoch": 0.38690047241572584, "percentage": 38.72, "elapsed_time": "1:05:10", "remaining_time": "1:43:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 304, "total_steps": 780, "loss": 0.2716, "learning_rate": 7.162595126896111e-06, "epoch": 0.38946272719993597, "percentage": 38.97, "elapsed_time": "1:05:35", "remaining_time": "1:42:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 306, "total_steps": 780, "loss": 0.2716, "learning_rate": 7.1242919589422974e-06, "epoch": 0.39202498198414604, "percentage": 39.23, "elapsed_time": "1:06:02", "remaining_time": "1:42:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 308, "total_steps": 780, "loss": 0.2978, "learning_rate": 7.085836057270521e-06, "epoch": 0.39458723676835616, "percentage": 39.49, "elapsed_time": "1:06:27", "remaining_time": "1:41:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 310, "total_steps": 780, "loss": 0.2499, "learning_rate": 7.047230186808085e-06, "epoch": 0.39714949155256624, "percentage": 39.74, "elapsed_time": "1:06:54", "remaining_time": "1:41:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 312, "total_steps": 780, "loss": 0.3018, "learning_rate": 7.008477123264849e-06, "epoch": 0.39971174633677636, "percentage": 40.0, "elapsed_time": "1:07:18", "remaining_time": "1:40:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 314, "total_steps": 780, "loss": 0.2834, "learning_rate": 6.96957965293365e-06, "epoch": 0.4022740011209865, "percentage": 40.26, "elapsed_time": "1:07:47", "remaining_time": "1:40:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 316, "total_steps": 780, "loss": 0.3008, "learning_rate": 6.9305405724899876e-06, "epoch": 0.40483625590519656, "percentage": 40.51, "elapsed_time": "1:08:14", "remaining_time": "1:40:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 318, "total_steps": 780, "loss": 0.2753, "learning_rate": 6.891362688790925e-06, "epoch": 0.4073985106894067, "percentage": 40.77, "elapsed_time": "1:08:39", "remaining_time": "1:39:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 320, "total_steps": 780, "loss": 0.2943, "learning_rate": 6.8520488186733e-06, "epoch": 0.40996076547361676, "percentage": 41.03, "elapsed_time": "1:09:03", "remaining_time": "1:39:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 322, "total_steps": 780, "loss": 0.2692, "learning_rate": 6.812601788751192e-06, "epoch": 0.4125230202578269, "percentage": 41.28, "elapsed_time": "1:09:29", "remaining_time": "1:38:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 324, "total_steps": 780, "loss": 0.2961, "learning_rate": 6.773024435212678e-06, "epoch": 0.415085275042037, "percentage": 41.54, "elapsed_time": "1:09:53", "remaining_time": "1:38:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 326, "total_steps": 780, "loss": 0.2898, "learning_rate": 6.733319603615941e-06, "epoch": 0.4176475298262471, "percentage": 41.79, "elapsed_time": "1:10:20", "remaining_time": "1:37:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 328, "total_steps": 780, "loss": 0.2555, "learning_rate": 6.693490148684654e-06, "epoch": 0.4202097846104572, "percentage": 42.05, "elapsed_time": "1:10:44", "remaining_time": "1:37:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 330, "total_steps": 780, "loss": 0.3043, "learning_rate": 6.653538934102743e-06, "epoch": 0.4227720393946673, "percentage": 42.31, "elapsed_time": "1:11:08", "remaining_time": "1:37:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 332, "total_steps": 780, "loss": 0.3098, "learning_rate": 6.6134688323084884e-06, "epoch": 0.4253342941788774, "percentage": 42.56, "elapsed_time": "1:11:39", "remaining_time": "1:36:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 334, "total_steps": 780, "loss": 0.276, "learning_rate": 6.573282724288001e-06, "epoch": 0.42789654896308754, "percentage": 42.82, "elapsed_time": "1:12:02", "remaining_time": "1:36:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 336, "total_steps": 780, "loss": 0.2893, "learning_rate": 6.532983499368078e-06, "epoch": 0.4304588037472976, "percentage": 43.08, "elapsed_time": "1:12:30", "remaining_time": "1:35:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 338, "total_steps": 780, "loss": 0.2522, "learning_rate": 6.492574055008474e-06, "epoch": 0.43302105853150774, "percentage": 43.33, "elapsed_time": "1:12:55", "remaining_time": "1:35:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 340, "total_steps": 780, "loss": 0.2556, "learning_rate": 6.452057296593568e-06, "epoch": 0.4355833133157178, "percentage": 43.59, "elapsed_time": "1:13:26", "remaining_time": "1:35:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 342, "total_steps": 780, "loss": 0.2795, "learning_rate": 6.411436137223479e-06, "epoch": 0.43814556809992794, "percentage": 43.85, "elapsed_time": "1:13:53", "remaining_time": "1:34:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 344, "total_steps": 780, "loss": 0.2619, "learning_rate": 6.370713497504607e-06, "epoch": 0.44070782288413807, "percentage": 44.1, "elapsed_time": "1:14:19", "remaining_time": "1:34:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 346, "total_steps": 780, "loss": 0.2748, "learning_rate": 6.329892305339659e-06, "epoch": 0.44327007766834814, "percentage": 44.36, "elapsed_time": "1:14:43", "remaining_time": "1:33:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 348, "total_steps": 780, "loss": 0.2731, "learning_rate": 6.288975495717124e-06, "epoch": 0.44583233245255827, "percentage": 44.62, "elapsed_time": "1:15:10", "remaining_time": "1:33:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 350, "total_steps": 780, "loss": 0.2797, "learning_rate": 6.247966010500258e-06, "epoch": 0.44839458723676834, "percentage": 44.87, "elapsed_time": "1:15:35", "remaining_time": "1:32:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 352, "total_steps": 780, "loss": 0.2724, "learning_rate": 6.206866798215571e-06, "epoch": 0.45095684202097847, "percentage": 45.13, "elapsed_time": "1:16:00", "remaining_time": "1:32:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 354, "total_steps": 780, "loss": 0.2728, "learning_rate": 6.165680813840822e-06, "epoch": 0.4535190968051886, "percentage": 45.38, "elapsed_time": "1:16:26", "remaining_time": "1:31:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 356, "total_steps": 780, "loss": 0.2733, "learning_rate": 6.124411018592568e-06, "epoch": 0.45608135158939866, "percentage": 45.64, "elapsed_time": "1:16:52", "remaining_time": "1:31:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 358, "total_steps": 780, "loss": 0.2688, "learning_rate": 6.0830603797132574e-06, "epoch": 0.4586436063736088, "percentage": 45.9, "elapsed_time": "1:17:16", "remaining_time": "1:31:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 360, "total_steps": 780, "loss": 0.2505, "learning_rate": 6.041631870257882e-06, "epoch": 0.46120586115781886, "percentage": 46.15, "elapsed_time": "1:17:42", "remaining_time": "1:30:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 362, "total_steps": 780, "loss": 0.2749, "learning_rate": 6.000128468880223e-06, "epoch": 0.463768115942029, "percentage": 46.41, "elapsed_time": "1:18:10", "remaining_time": "1:30:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 364, "total_steps": 780, "loss": 0.2541, "learning_rate": 5.958553159618693e-06, "epoch": 0.46633037072623906, "percentage": 46.67, "elapsed_time": "1:18:37", "remaining_time": "1:29:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 366, "total_steps": 780, "loss": 0.2721, "learning_rate": 5.916908931681781e-06, "epoch": 0.4688926255104492, "percentage": 46.92, "elapsed_time": "1:19:08", "remaining_time": "1:29:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 368, "total_steps": 780, "loss": 0.2774, "learning_rate": 5.8751987792331365e-06, "epoch": 0.4714548802946593, "percentage": 47.18, "elapsed_time": "1:19:33", "remaining_time": "1:29:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 370, "total_steps": 780, "loss": 0.2497, "learning_rate": 5.833425701176294e-06, "epoch": 0.4740171350788694, "percentage": 47.44, "elapsed_time": "1:19:59", "remaining_time": "1:28:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 372, "total_steps": 780, "loss": 0.2686, "learning_rate": 5.79159270093905e-06, "epoch": 0.4765793898630795, "percentage": 47.69, "elapsed_time": "1:20:25", "remaining_time": "1:28:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 374, "total_steps": 780, "loss": 0.2797, "learning_rate": 5.749702786257529e-06, "epoch": 0.4791416446472896, "percentage": 47.95, "elapsed_time": "1:20:52", "remaining_time": "1:27:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 376, "total_steps": 780, "loss": 0.2665, "learning_rate": 5.707758968959923e-06, "epoch": 0.4817038994314997, "percentage": 48.21, "elapsed_time": "1:21:17", "remaining_time": "1:27:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 378, "total_steps": 780, "loss": 0.2753, "learning_rate": 5.6657642647499545e-06, "epoch": 0.48426615421570984, "percentage": 48.46, "elapsed_time": "1:21:44", "remaining_time": "1:26:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 380, "total_steps": 780, "loss": 0.2445, "learning_rate": 5.62372169299004e-06, "epoch": 0.4868284089999199, "percentage": 48.72, "elapsed_time": "1:22:08", "remaining_time": "1:26:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 382, "total_steps": 780, "loss": 0.2933, "learning_rate": 5.581634276484211e-06, "epoch": 0.48939066378413004, "percentage": 48.97, "elapsed_time": "1:22:34", "remaining_time": "1:26:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 384, "total_steps": 780, "loss": 0.2502, "learning_rate": 5.539505041260779e-06, "epoch": 0.4919529185683401, "percentage": 49.23, "elapsed_time": "1:22:56", "remaining_time": "1:25:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 386, "total_steps": 780, "loss": 0.263, "learning_rate": 5.497337016354757e-06, "epoch": 0.49451517335255024, "percentage": 49.49, "elapsed_time": "1:23:24", "remaining_time": "1:25:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 388, "total_steps": 780, "loss": 0.2494, "learning_rate": 5.45513323359009e-06, "epoch": 0.49707742813676037, "percentage": 49.74, "elapsed_time": "1:23:49", "remaining_time": "1:24:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 390, "total_steps": 780, "loss": 0.2431, "learning_rate": 5.412896727361663e-06, "epoch": 0.49963968292097044, "percentage": 50.0, "elapsed_time": "1:24:11", "remaining_time": "1:24:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 392, "total_steps": 780, "loss": 0.248, "learning_rate": 5.370630534417133e-06, "epoch": 0.5022019377051805, "percentage": 50.26, "elapsed_time": "1:24:40", "remaining_time": "1:23:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 394, "total_steps": 780, "loss": 0.2522, "learning_rate": 5.328337693638591e-06, "epoch": 0.5047641924893906, "percentage": 50.51, "elapsed_time": "1:25:02", "remaining_time": "1:23:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 396, "total_steps": 780, "loss": 0.2856, "learning_rate": 5.286021245824075e-06, "epoch": 0.5073264472736008, "percentage": 50.77, "elapsed_time": "1:25:28", "remaining_time": "1:22:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 398, "total_steps": 780, "loss": 0.2626, "learning_rate": 5.243684233468933e-06, "epoch": 0.5098887020578109, "percentage": 51.03, "elapsed_time": "1:25:54", "remaining_time": "1:22:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 400, "total_steps": 780, "loss": 0.2738, "learning_rate": 5.201329700547077e-06, "epoch": 0.512450956842021, "percentage": 51.28, "elapsed_time": "1:26:19", "remaining_time": "1:22:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 402, "total_steps": 780, "loss": 0.2511, "learning_rate": 5.158960692292122e-06, "epoch": 0.515013211626231, "percentage": 51.54, "elapsed_time": "1:26:48", "remaining_time": "1:21:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 404, "total_steps": 780, "loss": 0.2957, "learning_rate": 5.116580254978447e-06, "epoch": 0.5175754664104412, "percentage": 51.79, "elapsed_time": "1:27:14", "remaining_time": "1:21:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 406, "total_steps": 780, "loss": 0.2704, "learning_rate": 5.074191435702155e-06, "epoch": 0.5201377211946513, "percentage": 52.05, "elapsed_time": "1:27:39", "remaining_time": "1:20:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 408, "total_steps": 780, "loss": 0.3206, "learning_rate": 5.031797282162007e-06, "epoch": 0.5226999759788614, "percentage": 52.31, "elapsed_time": "1:28:05", "remaining_time": "1:20:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 410, "total_steps": 780, "loss": 0.2536, "learning_rate": 4.98940084244029e-06, "epoch": 0.5252622307630715, "percentage": 52.56, "elapsed_time": "1:28:27", "remaining_time": "1:19:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 412, "total_steps": 780, "loss": 0.2517, "learning_rate": 4.947005164783661e-06, "epoch": 0.5278244855472816, "percentage": 52.82, "elapsed_time": "1:28:52", "remaining_time": "1:19:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 414, "total_steps": 780, "loss": 0.2751, "learning_rate": 4.9046132973839895e-06, "epoch": 0.5303867403314917, "percentage": 53.08, "elapsed_time": "1:29:18", "remaining_time": "1:18:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 416, "total_steps": 780, "loss": 0.2583, "learning_rate": 4.862228288159191e-06, "epoch": 0.5329489951157018, "percentage": 53.33, "elapsed_time": "1:29:44", "remaining_time": "1:18:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 418, "total_steps": 780, "loss": 0.3033, "learning_rate": 4.819853184534085e-06, "epoch": 0.535511249899912, "percentage": 53.59, "elapsed_time": "1:30:11", "remaining_time": "1:18:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 420, "total_steps": 780, "loss": 0.2679, "learning_rate": 4.7774910332213005e-06, "epoch": 0.5380735046841221, "percentage": 53.85, "elapsed_time": "1:30:38", "remaining_time": "1:17:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 422, "total_steps": 780, "loss": 0.2765, "learning_rate": 4.735144880002199e-06, "epoch": 0.5406357594683321, "percentage": 54.1, "elapsed_time": "1:31:06", "remaining_time": "1:17:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 424, "total_steps": 780, "loss": 0.2629, "learning_rate": 4.692817769507912e-06, "epoch": 0.5431980142525422, "percentage": 54.36, "elapsed_time": "1:31:31", "remaining_time": "1:16:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 426, "total_steps": 780, "loss": 0.292, "learning_rate": 4.6505127450004216e-06, "epoch": 0.5457602690367523, "percentage": 54.62, "elapsed_time": "1:31:55", "remaining_time": "1:16:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 428, "total_steps": 780, "loss": 0.2388, "learning_rate": 4.608232848153757e-06, "epoch": 0.5483225238209625, "percentage": 54.87, "elapsed_time": "1:32:22", "remaining_time": "1:15:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 430, "total_steps": 780, "loss": 0.2683, "learning_rate": 4.565981118835299e-06, "epoch": 0.5508847786051726, "percentage": 55.13, "elapsed_time": "1:32:48", "remaining_time": "1:15:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 432, "total_steps": 780, "loss": 0.265, "learning_rate": 4.523760594887228e-06, "epoch": 0.5534470333893826, "percentage": 55.38, "elapsed_time": "1:33:11", "remaining_time": "1:15:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 434, "total_steps": 780, "loss": 0.2823, "learning_rate": 4.481574311908096e-06, "epoch": 0.5560092881735927, "percentage": 55.64, "elapsed_time": "1:33:40", "remaining_time": "1:14:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 436, "total_steps": 780, "loss": 0.2942, "learning_rate": 4.439425303034576e-06, "epoch": 0.5585715429578029, "percentage": 55.9, "elapsed_time": "1:34:06", "remaining_time": "1:14:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 438, "total_steps": 780, "loss": 0.2983, "learning_rate": 4.397316598723385e-06, "epoch": 0.561133797742013, "percentage": 56.15, "elapsed_time": "1:34:30", "remaining_time": "1:13:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 440, "total_steps": 780, "loss": 0.2435, "learning_rate": 4.355251226533396e-06, "epoch": 0.5636960525262231, "percentage": 56.41, "elapsed_time": "1:34:57", "remaining_time": "1:13:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 442, "total_steps": 780, "loss": 0.2615, "learning_rate": 4.313232210907959e-06, "epoch": 0.5662583073104331, "percentage": 56.67, "elapsed_time": "1:35:26", "remaining_time": "1:12:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 444, "total_steps": 780, "loss": 0.2603, "learning_rate": 4.271262572957453e-06, "epoch": 0.5688205620946433, "percentage": 56.92, "elapsed_time": "1:35:51", "remaining_time": "1:12:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 446, "total_steps": 780, "loss": 0.246, "learning_rate": 4.229345330242067e-06, "epoch": 0.5713828168788534, "percentage": 57.18, "elapsed_time": "1:36:16", "remaining_time": "1:12:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 448, "total_steps": 780, "loss": 0.2679, "learning_rate": 4.187483496554844e-06, "epoch": 0.5739450716630635, "percentage": 57.44, "elapsed_time": "1:36:41", "remaining_time": "1:11:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 450, "total_steps": 780, "loss": 0.2616, "learning_rate": 4.145680081704989e-06, "epoch": 0.5765073264472736, "percentage": 57.69, "elapsed_time": "1:37:07", "remaining_time": "1:11:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 452, "total_steps": 780, "loss": 0.2534, "learning_rate": 4.103938091301479e-06, "epoch": 0.5790695812314837, "percentage": 57.95, "elapsed_time": "1:37:34", "remaining_time": "1:10:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 454, "total_steps": 780, "loss": 0.2909, "learning_rate": 4.062260526536955e-06, "epoch": 0.5816318360156938, "percentage": 58.21, "elapsed_time": "1:37:59", "remaining_time": "1:10:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 456, "total_steps": 780, "loss": 0.261, "learning_rate": 4.0206503839719335e-06, "epoch": 0.5841940907999039, "percentage": 58.46, "elapsed_time": "1:38:21", "remaining_time": "1:09:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 458, "total_steps": 780, "loss": 0.2669, "learning_rate": 3.9791106553193746e-06, "epoch": 0.586756345584114, "percentage": 58.72, "elapsed_time": "1:38:48", "remaining_time": "1:09:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 460, "total_steps": 780, "loss": 0.251, "learning_rate": 3.937644327229572e-06, "epoch": 0.5893186003683242, "percentage": 58.97, "elapsed_time": "1:39:14", "remaining_time": "1:09:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 462, "total_steps": 780, "loss": 0.2595, "learning_rate": 3.896254381075416e-06, "epoch": 0.5918808551525342, "percentage": 59.23, "elapsed_time": "1:39:39", "remaining_time": "1:08:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 464, "total_steps": 780, "loss": 0.2866, "learning_rate": 3.854943792738037e-06, "epoch": 0.5944431099367443, "percentage": 59.49, "elapsed_time": "1:40:03", "remaining_time": "1:08:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 466, "total_steps": 780, "loss": 0.2832, "learning_rate": 3.8137155323928526e-06, "epoch": 0.5970053647209544, "percentage": 59.74, "elapsed_time": "1:40:31", "remaining_time": "1:07:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 468, "total_steps": 780, "loss": 0.2548, "learning_rate": 3.7725725642960047e-06, "epoch": 0.5995676195051646, "percentage": 60.0, "elapsed_time": "1:40:55", "remaining_time": "1:07:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 470, "total_steps": 780, "loss": 0.2603, "learning_rate": 3.7315178465712364e-06, "epoch": 0.6021298742893747, "percentage": 60.26, "elapsed_time": "1:41:19", "remaining_time": "1:06:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 472, "total_steps": 780, "loss": 0.2685, "learning_rate": 3.690554330997215e-06, "epoch": 0.6046921290735847, "percentage": 60.51, "elapsed_time": "1:41:44", "remaining_time": "1:06:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 474, "total_steps": 780, "loss": 0.2723, "learning_rate": 3.6496849627952875e-06, "epoch": 0.6072543838577948, "percentage": 60.77, "elapsed_time": "1:42:09", "remaining_time": "1:05:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 476, "total_steps": 780, "loss": 0.2691, "learning_rate": 3.6089126804177373e-06, "epoch": 0.609816638642005, "percentage": 61.03, "elapsed_time": "1:42:33", "remaining_time": "1:05:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 478, "total_steps": 780, "loss": 0.2838, "learning_rate": 3.568240415336509e-06, "epoch": 0.6123788934262151, "percentage": 61.28, "elapsed_time": "1:43:00", "remaining_time": "1:05:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 480, "total_steps": 780, "loss": 0.2847, "learning_rate": 3.52767109183244e-06, "epoch": 0.6149411482104252, "percentage": 61.54, "elapsed_time": "1:43:26", "remaining_time": "1:04:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 482, "total_steps": 780, "loss": 0.2488, "learning_rate": 3.4872076267850015e-06, "epoch": 0.6175034029946352, "percentage": 61.79, "elapsed_time": "1:43:52", "remaining_time": "1:04:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 484, "total_steps": 780, "loss": 0.2621, "learning_rate": 3.4468529294625895e-06, "epoch": 0.6200656577788454, "percentage": 62.05, "elapsed_time": "1:44:18", "remaining_time": "1:03:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 486, "total_steps": 780, "loss": 0.2543, "learning_rate": 3.406609901313349e-06, "epoch": 0.6226279125630555, "percentage": 62.31, "elapsed_time": "1:44:46", "remaining_time": "1:03:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 488, "total_steps": 780, "loss": 0.271, "learning_rate": 3.36648143575656e-06, "epoch": 0.6251901673472656, "percentage": 62.56, "elapsed_time": "1:45:14", "remaining_time": "1:02:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 490, "total_steps": 780, "loss": 0.2794, "learning_rate": 3.326470417974604e-06, "epoch": 0.6277524221314758, "percentage": 62.82, "elapsed_time": "1:45:40", "remaining_time": "1:02:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 492, "total_steps": 780, "loss": 0.2716, "learning_rate": 3.2865797247055354e-06, "epoch": 0.6303146769156858, "percentage": 63.08, "elapsed_time": "1:46:06", "remaining_time": "1:02:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 494, "total_steps": 780, "loss": 0.243, "learning_rate": 3.2468122240362287e-06, "epoch": 0.6328769316998959, "percentage": 63.33, "elapsed_time": "1:46:30", "remaining_time": "1:01:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 496, "total_steps": 780, "loss": 0.2808, "learning_rate": 3.2071707751961838e-06, "epoch": 0.635439186484106, "percentage": 63.59, "elapsed_time": "1:46:54", "remaining_time": "1:01:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 498, "total_steps": 780, "loss": 0.265, "learning_rate": 3.1676582283519454e-06, "epoch": 0.6380014412683161, "percentage": 63.85, "elapsed_time": "1:47:20", "remaining_time": "1:00:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 500, "total_steps": 780, "loss": 0.2858, "learning_rate": 3.1282774244021717e-06, "epoch": 0.6405636960525263, "percentage": 64.1, "elapsed_time": "1:47:50", "remaining_time": "1:00:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 500, "total_steps": 780, "eval_loss": 0.2639869451522827, "epoch": 0.6405636960525263, "percentage": 64.1, "elapsed_time": "1:52:20", "remaining_time": "1:02:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 502, "total_steps": 780, "loss": 0.2879, "learning_rate": 3.089031194773392e-06, "epoch": 0.6431259508367363, "percentage": 64.36, "elapsed_time": "1:52:45", "remaining_time": "1:02:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 504, "total_steps": 780, "loss": 0.2501, "learning_rate": 3.049922361216422e-06, "epoch": 0.6456882056209464, "percentage": 64.62, "elapsed_time": "1:53:13", "remaining_time": "1:02:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 506, "total_steps": 780, "loss": 0.2691, "learning_rate": 3.0109537356034856e-06, "epoch": 0.6482504604051565, "percentage": 64.87, "elapsed_time": "1:53:37", "remaining_time": "1:01:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 508, "total_steps": 780, "loss": 0.3519, "learning_rate": 2.9721281197260427e-06, "epoch": 0.6508127151893667, "percentage": 65.13, "elapsed_time": "1:54:02", "remaining_time": "1:01:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 510, "total_steps": 780, "loss": 0.281, "learning_rate": 2.9334483050933506e-06, "epoch": 0.6533749699735768, "percentage": 65.38, "elapsed_time": "1:54:27", "remaining_time": "1:00:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 512, "total_steps": 780, "loss": 0.2677, "learning_rate": 2.894917072731753e-06, "epoch": 0.6559372247577868, "percentage": 65.64, "elapsed_time": "1:54:53", "remaining_time": "1:00:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 514, "total_steps": 780, "loss": 0.2707, "learning_rate": 2.8565371929847286e-06, "epoch": 0.658499479541997, "percentage": 65.9, "elapsed_time": "1:55:15", "remaining_time": "0:59:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 516, "total_steps": 780, "loss": 0.2654, "learning_rate": 2.81831142531371e-06, "epoch": 0.6610617343262071, "percentage": 66.15, "elapsed_time": "1:55:39", "remaining_time": "0:59:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 518, "total_steps": 780, "loss": 0.2601, "learning_rate": 2.780242518099675e-06, "epoch": 0.6636239891104172, "percentage": 66.41, "elapsed_time": "1:56:03", "remaining_time": "0:58:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 520, "total_steps": 780, "loss": 0.2648, "learning_rate": 2.7423332084455543e-06, "epoch": 0.6661862438946272, "percentage": 66.67, "elapsed_time": "1:56:27", "remaining_time": "0:58:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 522, "total_steps": 780, "loss": 0.2744, "learning_rate": 2.704586221979422e-06, "epoch": 0.6687484986788373, "percentage": 66.92, "elapsed_time": "1:56:51", "remaining_time": "0:57:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 524, "total_steps": 780, "loss": 0.2499, "learning_rate": 2.667004272658541e-06, "epoch": 0.6713107534630475, "percentage": 67.18, "elapsed_time": "1:57:18", "remaining_time": "0:57:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 526, "total_steps": 780, "loss": 0.2716, "learning_rate": 2.629590062574221e-06, "epoch": 0.6738730082472576, "percentage": 67.44, "elapsed_time": "1:57:46", "remaining_time": "0:56:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 528, "total_steps": 780, "loss": 0.2361, "learning_rate": 2.592346281757552e-06, "epoch": 0.6764352630314677, "percentage": 67.69, "elapsed_time": "1:58:15", "remaining_time": "0:56:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 530, "total_steps": 780, "loss": 0.2476, "learning_rate": 2.5552756079859904e-06, "epoch": 0.6789975178156777, "percentage": 67.95, "elapsed_time": "1:58:38", "remaining_time": "0:55:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 532, "total_steps": 780, "loss": 0.2287, "learning_rate": 2.5183807065908296e-06, "epoch": 0.6815597725998879, "percentage": 68.21, "elapsed_time": "1:59:03", "remaining_time": "0:55:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 534, "total_steps": 780, "loss": 0.2644, "learning_rate": 2.4816642302655634e-06, "epoch": 0.684122027384098, "percentage": 68.46, "elapsed_time": "1:59:30", "remaining_time": "0:55:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 536, "total_steps": 780, "loss": 0.2354, "learning_rate": 2.445128818875166e-06, "epoch": 0.6866842821683081, "percentage": 68.72, "elapsed_time": "1:59:57", "remaining_time": "0:54:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 538, "total_steps": 780, "loss": 0.2779, "learning_rate": 2.408777099266291e-06, "epoch": 0.6892465369525183, "percentage": 68.97, "elapsed_time": "2:00:20", "remaining_time": "0:54:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 540, "total_steps": 780, "loss": 0.2742, "learning_rate": 2.3726116850783987e-06, "epoch": 0.6918087917367283, "percentage": 69.23, "elapsed_time": "2:00:44", "remaining_time": "0:53:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 542, "total_steps": 780, "loss": 0.2818, "learning_rate": 2.3366351765558437e-06, "epoch": 0.6943710465209384, "percentage": 69.49, "elapsed_time": "2:01:11", "remaining_time": "0:53:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 544, "total_steps": 780, "loss": 0.2542, "learning_rate": 2.3008501603609147e-06, "epoch": 0.6969333013051485, "percentage": 69.74, "elapsed_time": "2:01:33", "remaining_time": "0:52:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 546, "total_steps": 780, "loss": 0.2664, "learning_rate": 2.265259209387867e-06, "epoch": 0.6994955560893586, "percentage": 70.0, "elapsed_time": "2:02:00", "remaining_time": "0:52:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 548, "total_steps": 780, "loss": 0.2678, "learning_rate": 2.229864882577921e-06, "epoch": 0.7020578108735688, "percentage": 70.26, "elapsed_time": "2:02:24", "remaining_time": "0:51:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 550, "total_steps": 780, "loss": 0.2668, "learning_rate": 2.194669724735296e-06, "epoch": 0.7046200656577788, "percentage": 70.51, "elapsed_time": "2:02:49", "remaining_time": "0:51:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 552, "total_steps": 780, "loss": 0.2663, "learning_rate": 2.159676266344222e-06, "epoch": 0.7071823204419889, "percentage": 70.77, "elapsed_time": "2:03:16", "remaining_time": "0:50:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 554, "total_steps": 780, "loss": 0.2666, "learning_rate": 2.124887023387017e-06, "epoch": 0.709744575226199, "percentage": 71.03, "elapsed_time": "2:03:42", "remaining_time": "0:50:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 556, "total_steps": 780, "loss": 0.2292, "learning_rate": 2.0903044971631854e-06, "epoch": 0.7123068300104092, "percentage": 71.28, "elapsed_time": "2:04:09", "remaining_time": "0:50:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 558, "total_steps": 780, "loss": 0.2354, "learning_rate": 2.055931174109579e-06, "epoch": 0.7148690847946193, "percentage": 71.54, "elapsed_time": "2:04:32", "remaining_time": "0:49:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 560, "total_steps": 780, "loss": 0.2557, "learning_rate": 2.02176952562162e-06, "epoch": 0.7174313395788293, "percentage": 71.79, "elapsed_time": "2:04:54", "remaining_time": "0:49:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 562, "total_steps": 780, "loss": 0.2706, "learning_rate": 1.987822007875617e-06, "epoch": 0.7199935943630394, "percentage": 72.05, "elapsed_time": "2:05:21", "remaining_time": "0:48:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 564, "total_steps": 780, "loss": 0.2815, "learning_rate": 1.954091061652172e-06, "epoch": 0.7225558491472496, "percentage": 72.31, "elapsed_time": "2:05:48", "remaining_time": "0:48:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 566, "total_steps": 780, "loss": 0.2314, "learning_rate": 1.920579112160685e-06, "epoch": 0.7251181039314597, "percentage": 72.56, "elapsed_time": "2:06:14", "remaining_time": "0:47:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 568, "total_steps": 780, "loss": 0.2812, "learning_rate": 1.8872885688649879e-06, "epoch": 0.7276803587156698, "percentage": 72.82, "elapsed_time": "2:06:41", "remaining_time": "0:47:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 570, "total_steps": 780, "loss": 0.2656, "learning_rate": 1.854221825310103e-06, "epoch": 0.7302426134998798, "percentage": 73.08, "elapsed_time": "2:07:07", "remaining_time": "0:46:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 572, "total_steps": 780, "loss": 0.265, "learning_rate": 1.8213812589501611e-06, "epoch": 0.73280486828409, "percentage": 73.33, "elapsed_time": "2:07:33", "remaining_time": "0:46:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 574, "total_steps": 780, "loss": 0.2652, "learning_rate": 1.78876923097745e-06, "epoch": 0.7353671230683001, "percentage": 73.59, "elapsed_time": "2:07:58", "remaining_time": "0:45:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 576, "total_steps": 780, "loss": 0.2748, "learning_rate": 1.7563880861526656e-06, "epoch": 0.7379293778525102, "percentage": 73.85, "elapsed_time": "2:08:22", "remaining_time": "0:45:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 578, "total_steps": 780, "loss": 0.2847, "learning_rate": 1.7242401526363095e-06, "epoch": 0.7404916326367204, "percentage": 74.1, "elapsed_time": "2:08:48", "remaining_time": "0:45:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 580, "total_steps": 780, "loss": 0.2792, "learning_rate": 1.692327741821312e-06, "epoch": 0.7430538874209304, "percentage": 74.36, "elapsed_time": "2:09:14", "remaining_time": "0:44:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 582, "total_steps": 780, "loss": 0.2784, "learning_rate": 1.6606531481668364e-06, "epoch": 0.7456161422051405, "percentage": 74.62, "elapsed_time": "2:09:40", "remaining_time": "0:44:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 584, "total_steps": 780, "loss": 0.2862, "learning_rate": 1.6292186490333172e-06, "epoch": 0.7481783969893506, "percentage": 74.87, "elapsed_time": "2:10:07", "remaining_time": "0:43:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 586, "total_steps": 780, "loss": 0.2637, "learning_rate": 1.5980265045187139e-06, "epoch": 0.7507406517735608, "percentage": 75.13, "elapsed_time": "2:10:32", "remaining_time": "0:43:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 588, "total_steps": 780, "loss": 0.2617, "learning_rate": 1.567078957296016e-06, "epoch": 0.7533029065577709, "percentage": 75.38, "elapsed_time": "2:10:56", "remaining_time": "0:42:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 590, "total_steps": 780, "loss": 0.2569, "learning_rate": 1.5363782324520033e-06, "epoch": 0.7558651613419809, "percentage": 75.64, "elapsed_time": "2:11:20", "remaining_time": "0:42:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 592, "total_steps": 780, "loss": 0.2558, "learning_rate": 1.5059265373272574e-06, "epoch": 0.758427416126191, "percentage": 75.9, "elapsed_time": "2:11:45", "remaining_time": "0:41:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 594, "total_steps": 780, "loss": 0.2547, "learning_rate": 1.475726061357463e-06, "epoch": 0.7609896709104012, "percentage": 76.15, "elapsed_time": "2:12:11", "remaining_time": "0:41:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 596, "total_steps": 780, "loss": 0.2266, "learning_rate": 1.4457789759159813e-06, "epoch": 0.7635519256946113, "percentage": 76.41, "elapsed_time": "2:12:37", "remaining_time": "0:40:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 598, "total_steps": 780, "loss": 0.269, "learning_rate": 1.4160874341577447e-06, "epoch": 0.7661141804788214, "percentage": 76.67, "elapsed_time": "2:13:01", "remaining_time": "0:40:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 600, "total_steps": 780, "loss": 0.2536, "learning_rate": 1.3866535708644335e-06, "epoch": 0.7686764352630314, "percentage": 76.92, "elapsed_time": "2:13:26", "remaining_time": "0:40:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 602, "total_steps": 780, "loss": 0.3012, "learning_rate": 1.3574795022910014e-06, "epoch": 0.7712386900472415, "percentage": 77.18, "elapsed_time": "2:13:53", "remaining_time": "0:39:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 604, "total_steps": 780, "loss": 0.2453, "learning_rate": 1.3285673260135073e-06, "epoch": 0.7738009448314517, "percentage": 77.44, "elapsed_time": "2:14:20", "remaining_time": "0:39:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 606, "total_steps": 780, "loss": 0.2308, "learning_rate": 1.2999191207783129e-06, "epoch": 0.7763631996156618, "percentage": 77.69, "elapsed_time": "2:14:46", "remaining_time": "0:38:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 608, "total_steps": 780, "loss": 0.2534, "learning_rate": 1.2715369463526173e-06, "epoch": 0.7789254543998719, "percentage": 77.95, "elapsed_time": "2:15:12", "remaining_time": "0:38:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 610, "total_steps": 780, "loss": 0.2331, "learning_rate": 1.2434228433763657e-06, "epoch": 0.781487709184082, "percentage": 78.21, "elapsed_time": "2:15:37", "remaining_time": "0:37:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 612, "total_steps": 780, "loss": 0.2695, "learning_rate": 1.215578833215526e-06, "epoch": 0.7840499639682921, "percentage": 78.46, "elapsed_time": "2:16:09", "remaining_time": "0:37:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 614, "total_steps": 780, "loss": 0.2654, "learning_rate": 1.1880069178167586e-06, "epoch": 0.7866122187525022, "percentage": 78.72, "elapsed_time": "2:16:37", "remaining_time": "0:36:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 616, "total_steps": 780, "loss": 0.2597, "learning_rate": 1.1607090795634802e-06, "epoch": 0.7891744735367123, "percentage": 78.97, "elapsed_time": "2:17:03", "remaining_time": "0:36:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 618, "total_steps": 780, "loss": 0.2454, "learning_rate": 1.133687281133331e-06, "epoch": 0.7917367283209225, "percentage": 79.23, "elapsed_time": "2:17:30", "remaining_time": "0:36:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 620, "total_steps": 780, "loss": 0.2541, "learning_rate": 1.1069434653570633e-06, "epoch": 0.7942989831051325, "percentage": 79.49, "elapsed_time": "2:17:58", "remaining_time": "0:35:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 622, "total_steps": 780, "loss": 0.2743, "learning_rate": 1.0804795550788473e-06, "epoch": 0.7968612378893426, "percentage": 79.74, "elapsed_time": "2:18:24", "remaining_time": "0:35:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 624, "total_steps": 780, "loss": 0.2736, "learning_rate": 1.0542974530180327e-06, "epoch": 0.7994234926735527, "percentage": 80.0, "elapsed_time": "2:18:47", "remaining_time": "0:34:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 626, "total_steps": 780, "loss": 0.2503, "learning_rate": 1.0283990416323336e-06, "epoch": 0.8019857474577629, "percentage": 80.26, "elapsed_time": "2:19:12", "remaining_time": "0:34:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 628, "total_steps": 780, "loss": 0.232, "learning_rate": 1.0027861829824953e-06, "epoch": 0.804548002241973, "percentage": 80.51, "elapsed_time": "2:19:35", "remaining_time": "0:33:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 630, "total_steps": 780, "loss": 0.2549, "learning_rate": 9.774607185984004e-07, "epoch": 0.807110257026183, "percentage": 80.77, "elapsed_time": "2:20:02", "remaining_time": "0:33:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 632, "total_steps": 780, "loss": 0.2355, "learning_rate": 9.524244693466773e-07, "epoch": 0.8096725118103931, "percentage": 81.03, "elapsed_time": "2:20:27", "remaining_time": "0:32:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 634, "total_steps": 780, "loss": 0.2579, "learning_rate": 9.276792352997782e-07, "epoch": 0.8122347665946033, "percentage": 81.28, "elapsed_time": "2:20:53", "remaining_time": "0:32:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 636, "total_steps": 780, "loss": 0.2833, "learning_rate": 9.032267956065516e-07, "epoch": 0.8147970213788134, "percentage": 81.54, "elapsed_time": "2:21:19", "remaining_time": "0:31:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 638, "total_steps": 780, "loss": 0.2473, "learning_rate": 8.790689083643328e-07, "epoch": 0.8173592761630235, "percentage": 81.79, "elapsed_time": "2:21:43", "remaining_time": "0:31:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 640, "total_steps": 780, "loss": 0.2711, "learning_rate": 8.552073104925296e-07, "epoch": 0.8199215309472335, "percentage": 82.05, "elapsed_time": "2:22:06", "remaining_time": "0:31:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 642, "total_steps": 780, "loss": 0.2749, "learning_rate": 8.316437176077491e-07, "epoch": 0.8224837857314437, "percentage": 82.31, "elapsed_time": "2:22:31", "remaining_time": "0:30:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 644, "total_steps": 780, "loss": 0.259, "learning_rate": 8.083798239004408e-07, "epoch": 0.8250460405156538, "percentage": 82.56, "elapsed_time": "2:22:57", "remaining_time": "0:30:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 646, "total_steps": 780, "loss": 0.2946, "learning_rate": 7.854173020130906e-07, "epoch": 0.8276082952998639, "percentage": 82.82, "elapsed_time": "2:23:24", "remaining_time": "0:29:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 648, "total_steps": 780, "loss": 0.2573, "learning_rate": 7.627578029199562e-07, "epoch": 0.830170550084074, "percentage": 83.08, "elapsed_time": "2:23:49", "remaining_time": "0:29:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 650, "total_steps": 780, "loss": 0.2461, "learning_rate": 7.404029558083653e-07, "epoch": 0.832732804868284, "percentage": 83.33, "elapsed_time": "2:24:15", "remaining_time": "0:28:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 652, "total_steps": 780, "loss": 0.2578, "learning_rate": 7.183543679615834e-07, "epoch": 0.8352950596524942, "percentage": 83.59, "elapsed_time": "2:24:41", "remaining_time": "0:28:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 654, "total_steps": 780, "loss": 0.2412, "learning_rate": 6.966136246432492e-07, "epoch": 0.8378573144367043, "percentage": 83.85, "elapsed_time": "2:25:10", "remaining_time": "0:27:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 656, "total_steps": 780, "loss": 0.265, "learning_rate": 6.751822889833926e-07, "epoch": 0.8404195692209144, "percentage": 84.1, "elapsed_time": "2:25:34", "remaining_time": "0:27:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 658, "total_steps": 780, "loss": 0.226, "learning_rate": 6.540619018660555e-07, "epoch": 0.8429818240051246, "percentage": 84.36, "elapsed_time": "2:25:58", "remaining_time": "0:27:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 660, "total_steps": 780, "loss": 0.2501, "learning_rate": 6.332539818184985e-07, "epoch": 0.8455440787893346, "percentage": 84.62, "elapsed_time": "2:26:23", "remaining_time": "0:26:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 662, "total_steps": 780, "loss": 0.2747, "learning_rate": 6.127600249020216e-07, "epoch": 0.8481063335735447, "percentage": 84.87, "elapsed_time": "2:26:49", "remaining_time": "0:26:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 664, "total_steps": 780, "loss": 0.2612, "learning_rate": 5.925815046044026e-07, "epoch": 0.8506685883577548, "percentage": 85.13, "elapsed_time": "2:27:12", "remaining_time": "0:25:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 666, "total_steps": 780, "loss": 0.2574, "learning_rate": 5.727198717339511e-07, "epoch": 0.853230843141965, "percentage": 85.38, "elapsed_time": "2:27:37", "remaining_time": "0:25:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 668, "total_steps": 780, "loss": 0.2734, "learning_rate": 5.531765543152002e-07, "epoch": 0.8557930979261751, "percentage": 85.64, "elapsed_time": "2:28:01", "remaining_time": "0:24:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 670, "total_steps": 780, "loss": 0.2539, "learning_rate": 5.33952957486234e-07, "epoch": 0.8583553527103851, "percentage": 85.9, "elapsed_time": "2:28:28", "remaining_time": "0:24:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 672, "total_steps": 780, "loss": 0.3682, "learning_rate": 5.150504633976572e-07, "epoch": 0.8609176074945952, "percentage": 86.15, "elapsed_time": "2:29:00", "remaining_time": "0:23:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 674, "total_steps": 780, "loss": 0.2265, "learning_rate": 4.964704311132224e-07, "epoch": 0.8634798622788054, "percentage": 86.41, "elapsed_time": "2:29:26", "remaining_time": "0:23:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 676, "total_steps": 780, "loss": 0.2676, "learning_rate": 4.782141965121129e-07, "epoch": 0.8660421170630155, "percentage": 86.67, "elapsed_time": "2:29:50", "remaining_time": "0:23:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 678, "total_steps": 780, "loss": 0.2606, "learning_rate": 4.602830721928997e-07, "epoch": 0.8686043718472256, "percentage": 86.92, "elapsed_time": "2:30:17", "remaining_time": "0:22:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 680, "total_steps": 780, "loss": 0.2414, "learning_rate": 4.4267834737916295e-07, "epoch": 0.8711666266314356, "percentage": 87.18, "elapsed_time": "2:30:38", "remaining_time": "0:22:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 682, "total_steps": 780, "loss": 0.2287, "learning_rate": 4.2540128782679934e-07, "epoch": 0.8737288814156458, "percentage": 87.44, "elapsed_time": "2:31:04", "remaining_time": "0:21:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 684, "total_steps": 780, "loss": 0.2404, "learning_rate": 4.0845313573301736e-07, "epoch": 0.8762911361998559, "percentage": 87.69, "elapsed_time": "2:31:34", "remaining_time": "0:21:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 686, "total_steps": 780, "loss": 0.2719, "learning_rate": 3.9183510964702463e-07, "epoch": 0.878853390984066, "percentage": 87.95, "elapsed_time": "2:31:58", "remaining_time": "0:20:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 688, "total_steps": 780, "loss": 0.2608, "learning_rate": 3.755484043824131e-07, "epoch": 0.8814156457682761, "percentage": 88.21, "elapsed_time": "2:32:22", "remaining_time": "0:20:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 690, "total_steps": 780, "loss": 0.2852, "learning_rate": 3.595941909312595e-07, "epoch": 0.8839779005524862, "percentage": 88.46, "elapsed_time": "2:32:50", "remaining_time": "0:19:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 692, "total_steps": 780, "loss": 0.2693, "learning_rate": 3.439736163799251e-07, "epoch": 0.8865401553366963, "percentage": 88.72, "elapsed_time": "2:33:15", "remaining_time": "0:19:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 694, "total_steps": 780, "loss": 0.2443, "learning_rate": 3.2868780382658895e-07, "epoch": 0.8891024101209064, "percentage": 88.97, "elapsed_time": "2:33:40", "remaining_time": "0:19:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 696, "total_steps": 780, "loss": 0.2515, "learning_rate": 3.1373785230049356e-07, "epoch": 0.8916646649051165, "percentage": 89.23, "elapsed_time": "2:34:06", "remaining_time": "0:18:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 698, "total_steps": 780, "loss": 0.2757, "learning_rate": 2.991248366829291e-07, "epoch": 0.8942269196893267, "percentage": 89.49, "elapsed_time": "2:34:28", "remaining_time": "0:18:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 700, "total_steps": 780, "loss": 0.2963, "learning_rate": 2.848498076299483e-07, "epoch": 0.8967891744735367, "percentage": 89.74, "elapsed_time": "2:34:54", "remaining_time": "0:17:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 702, "total_steps": 780, "loss": 0.2361, "learning_rate": 2.7091379149682683e-07, "epoch": 0.8993514292577468, "percentage": 90.0, "elapsed_time": "2:35:18", "remaining_time": "0:17:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 704, "total_steps": 780, "loss": 0.2555, "learning_rate": 2.573177902642726e-07, "epoch": 0.9019136840419569, "percentage": 90.26, "elapsed_time": "2:35:44", "remaining_time": "0:16:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 706, "total_steps": 780, "loss": 0.2772, "learning_rate": 2.440627814663804e-07, "epoch": 0.9044759388261671, "percentage": 90.51, "elapsed_time": "2:36:10", "remaining_time": "0:16:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 708, "total_steps": 780, "loss": 0.2544, "learning_rate": 2.3114971812034981e-07, "epoch": 0.9070381936103772, "percentage": 90.77, "elapsed_time": "2:36:35", "remaining_time": "0:15:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 710, "total_steps": 780, "loss": 0.2424, "learning_rate": 2.1857952865796616e-07, "epoch": 0.9096004483945872, "percentage": 91.03, "elapsed_time": "2:37:00", "remaining_time": "0:15:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 712, "total_steps": 780, "loss": 0.2424, "learning_rate": 2.0635311685884675e-07, "epoch": 0.9121627031787973, "percentage": 91.28, "elapsed_time": "2:37:27", "remaining_time": "0:15:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 714, "total_steps": 780, "loss": 0.2475, "learning_rate": 1.9447136178545766e-07, "epoch": 0.9147249579630075, "percentage": 91.54, "elapsed_time": "2:37:52", "remaining_time": "0:14:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 716, "total_steps": 780, "loss": 0.2414, "learning_rate": 1.8293511771991624e-07, "epoch": 0.9172872127472176, "percentage": 91.79, "elapsed_time": "2:38:18", "remaining_time": "0:14:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 718, "total_steps": 780, "loss": 0.2733, "learning_rate": 1.7174521410256162e-07, "epoch": 0.9198494675314277, "percentage": 92.05, "elapsed_time": "2:38:42", "remaining_time": "0:13:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 720, "total_steps": 780, "loss": 0.2195, "learning_rate": 1.6090245547232707e-07, "epoch": 0.9224117223156377, "percentage": 92.31, "elapsed_time": "2:39:10", "remaining_time": "0:13:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 722, "total_steps": 780, "loss": 0.2496, "learning_rate": 1.5040762140888843e-07, "epoch": 0.9249739770998479, "percentage": 92.56, "elapsed_time": "2:39:35", "remaining_time": "0:12:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 724, "total_steps": 780, "loss": 0.2521, "learning_rate": 1.402614664766172e-07, "epoch": 0.927536231884058, "percentage": 92.82, "elapsed_time": "2:39:59", "remaining_time": "0:12:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 726, "total_steps": 780, "loss": 0.2742, "learning_rate": 1.3046472017032685e-07, "epoch": 0.9300984866682681, "percentage": 93.08, "elapsed_time": "2:40:23", "remaining_time": "0:11:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 728, "total_steps": 780, "loss": 0.2359, "learning_rate": 1.210180868628219e-07, "epoch": 0.9326607414524781, "percentage": 93.33, "elapsed_time": "2:40:49", "remaining_time": "0:11:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 730, "total_steps": 780, "loss": 0.2428, "learning_rate": 1.1192224575425848e-07, "epoch": 0.9352229962366883, "percentage": 93.59, "elapsed_time": "2:41:15", "remaining_time": "0:11:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 732, "total_steps": 780, "loss": 0.2982, "learning_rate": 1.0317785082330555e-07, "epoch": 0.9377852510208984, "percentage": 93.85, "elapsed_time": "2:41:40", "remaining_time": "0:10:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 734, "total_steps": 780, "loss": 0.2659, "learning_rate": 9.478553078013042e-08, "epoch": 0.9403475058051085, "percentage": 94.1, "elapsed_time": "2:42:03", "remaining_time": "0:10:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 736, "total_steps": 780, "loss": 0.2429, "learning_rate": 8.674588902118919e-08, "epoch": 0.9429097605893186, "percentage": 94.36, "elapsed_time": "2:42:33", "remaining_time": "0:09:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 738, "total_steps": 780, "loss": 0.2665, "learning_rate": 7.905950358584768e-08, "epoch": 0.9454720153735287, "percentage": 94.62, "elapsed_time": "2:43:03", "remaining_time": "0:09:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 740, "total_steps": 780, "loss": 0.2768, "learning_rate": 7.172692711482022e-08, "epoch": 0.9480342701577388, "percentage": 94.87, "elapsed_time": "2:43:30", "remaining_time": "0:08:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 742, "total_steps": 780, "loss": 0.264, "learning_rate": 6.474868681043578e-08, "epoch": 0.9505965249419489, "percentage": 95.13, "elapsed_time": "2:43:55", "remaining_time": "0:08:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 744, "total_steps": 780, "loss": 0.2686, "learning_rate": 5.8125284398730666e-08, "epoch": 0.953158779726159, "percentage": 95.38, "elapsed_time": "2:44:22", "remaining_time": "0:07:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 746, "total_steps": 780, "loss": 0.2709, "learning_rate": 5.185719609337836e-08, "epoch": 0.9557210345103692, "percentage": 95.64, "elapsed_time": "2:44:47", "remaining_time": "0:07:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 748, "total_steps": 780, "loss": 0.2542, "learning_rate": 4.5944872561448084e-08, "epoch": 0.9582832892945792, "percentage": 95.9, "elapsed_time": "2:45:14", "remaining_time": "0:07:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 750, "total_steps": 780, "loss": 0.2613, "learning_rate": 4.038873889100237e-08, "epoch": 0.9608455440787893, "percentage": 96.15, "elapsed_time": "2:45:39", "remaining_time": "0:06:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 752, "total_steps": 780, "loss": 0.2394, "learning_rate": 3.518919456053649e-08, "epoch": 0.9634077988629994, "percentage": 96.41, "elapsed_time": "2:46:03", "remaining_time": "0:06:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 754, "total_steps": 780, "loss": 0.2581, "learning_rate": 3.034661341025258e-08, "epoch": 0.9659700536472096, "percentage": 96.67, "elapsed_time": "2:46:31", "remaining_time": "0:05:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 756, "total_steps": 780, "loss": 0.2271, "learning_rate": 2.5861343615184997e-08, "epoch": 0.9685323084314197, "percentage": 96.92, "elapsed_time": "2:46:56", "remaining_time": "0:05:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 758, "total_steps": 780, "loss": 0.2569, "learning_rate": 2.173370766016314e-08, "epoch": 0.9710945632156297, "percentage": 97.18, "elapsed_time": "2:47:22", "remaining_time": "0:04:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 760, "total_steps": 780, "loss": 0.2569, "learning_rate": 1.7964002316628316e-08, "epoch": 0.9736568179998398, "percentage": 97.44, "elapsed_time": "2:47:49", "remaining_time": "0:04:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 762, "total_steps": 780, "loss": 0.2667, "learning_rate": 1.4552498621295264e-08, "epoch": 0.97621907278405, "percentage": 97.69, "elapsed_time": "2:48:13", "remaining_time": "0:03:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 764, "total_steps": 780, "loss": 0.2743, "learning_rate": 1.1499441856663296e-08, "epoch": 0.9787813275682601, "percentage": 97.95, "elapsed_time": "2:48:40", "remaining_time": "0:03:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 766, "total_steps": 780, "loss": 0.2321, "learning_rate": 8.805051533384846e-09, "epoch": 0.9813435823524702, "percentage": 98.21, "elapsed_time": "2:49:06", "remaining_time": "0:03:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 768, "total_steps": 780, "loss": 0.2375, "learning_rate": 6.469521374477539e-09, "epoch": 0.9839058371366802, "percentage": 98.46, "elapsed_time": "2:49:35", "remaining_time": "0:02:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 770, "total_steps": 780, "loss": 0.2373, "learning_rate": 4.493019301401447e-09, "epoch": 0.9864680919208904, "percentage": 98.72, "elapsed_time": "2:49:59", "remaining_time": "0:02:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 772, "total_steps": 780, "loss": 0.2703, "learning_rate": 2.875687421980966e-09, "epoch": 0.9890303467051005, "percentage": 98.97, "elapsed_time": "2:50:24", "remaining_time": "0:01:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 774, "total_steps": 780, "loss": 0.2426, "learning_rate": 1.6176420201902132e-09, "epoch": 0.9915926014893106, "percentage": 99.23, "elapsed_time": "2:50:49", "remaining_time": "0:01:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 776, "total_steps": 780, "loss": 0.2662, "learning_rate": 7.189735477913795e-10, "epoch": 0.9941548562735207, "percentage": 99.49, "elapsed_time": "2:51:15", "remaining_time": "0:00:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 778, "total_steps": 780, "loss": 0.242, "learning_rate": 1.797466178327101e-10, "epoch": 0.9967171110577308, "percentage": 99.74, "elapsed_time": "2:51:41", "remaining_time": "0:00:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 780, "total_steps": 780, "loss": 0.308, "learning_rate": 0.0, "epoch": 0.9992793658419409, "percentage": 100.0, "elapsed_time": "2:52:06", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 780, "total_steps": 780, "epoch": 0.9992793658419409, "percentage": 100.0, "elapsed_time": "2:52:07", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}