{"current_steps": 1, "total_steps": 1200, "loss": 0.5487, "lr": 4.999991432639962e-05, "epoch": 0.016614745586708203, "percentage": 0.08, "elapsed_time": "0:00:31", "remaining_time": "10:32:35", "throughput": 2224.17, "total_tokens": 70408} {"current_steps": 2, "total_steps": 1200, "loss": 0.4981, "lr": 4.999965730618567e-05, "epoch": 0.033229491173416406, "percentage": 0.17, "elapsed_time": "0:01:02", "remaining_time": "10:26:41", "throughput": 2224.49, "total_tokens": 139640} {"current_steps": 3, "total_steps": 1200, "loss": 0.5505, "lr": 4.9999228941119745e-05, "epoch": 0.04984423676012461, "percentage": 0.25, "elapsed_time": "0:01:44", "remaining_time": "11:32:18", "throughput": 2148.36, "total_tokens": 223656} {"current_steps": 4, "total_steps": 1200, "loss": 0.504, "lr": 4.999862923413781e-05, "epoch": 0.06645898234683281, "percentage": 0.33, "elapsed_time": "0:02:21", "remaining_time": "11:42:45", "throughput": 2132.22, "total_tokens": 300688} {"current_steps": 5, "total_steps": 1200, "loss": 0.4925, "lr": 4.999785818935018e-05, "epoch": 0.08307372793354102, "percentage": 0.42, "elapsed_time": "0:02:48", "remaining_time": "11:13:01", "throughput": 2168.36, "total_tokens": 366368} {"current_steps": 6, "total_steps": 1200, "loss": 0.4771, "lr": 4.999691581204152e-05, "epoch": 0.09968847352024922, "percentage": 0.5, "elapsed_time": "0:03:25", "remaining_time": "11:22:12", "throughput": 2167.39, "total_tokens": 445808} {"current_steps": 7, "total_steps": 1200, "loss": 0.4986, "lr": 4.9995802108670775e-05, "epoch": 0.11630321910695743, "percentage": 0.58, "elapsed_time": "0:04:03", "remaining_time": "11:31:48", "throughput": 2146.55, "total_tokens": 522800} {"current_steps": 8, "total_steps": 1200, "loss": 0.5171, "lr": 4.999451708687114e-05, "epoch": 0.13291796469366562, "percentage": 0.67, "elapsed_time": "0:04:38", "remaining_time": "11:32:35", "throughput": 2149.95, "total_tokens": 599608} {"current_steps": 9, "total_steps": 1200, "loss": 0.5669, "lr": 4.9993060755450015e-05, "epoch": 0.14953271028037382, "percentage": 0.75, "elapsed_time": "0:05:19", "remaining_time": "11:43:35", "throughput": 2136.09, "total_tokens": 681424} {"current_steps": 10, "total_steps": 1200, "loss": 0.4218, "lr": 4.999143312438893e-05, "epoch": 0.16614745586708204, "percentage": 0.83, "elapsed_time": "0:05:53", "remaining_time": "11:41:53", "throughput": 2138.31, "total_tokens": 756744} {"current_steps": 11, "total_steps": 1200, "loss": 0.434, "lr": 4.998963420484349e-05, "epoch": 0.18276220145379024, "percentage": 0.92, "elapsed_time": "0:06:36", "remaining_time": "11:54:22", "throughput": 2124.8, "total_tokens": 842576} {"current_steps": 12, "total_steps": 1200, "loss": 0.4287, "lr": 4.998766400914329e-05, "epoch": 0.19937694704049844, "percentage": 1.0, "elapsed_time": "0:07:11", "remaining_time": "11:52:25", "throughput": 2124.32, "total_tokens": 917232} {"current_steps": 13, "total_steps": 1200, "loss": 0.3454, "lr": 4.9985522550791825e-05, "epoch": 0.21599169262720663, "percentage": 1.08, "elapsed_time": "0:07:57", "remaining_time": "12:06:27", "throughput": 2109.07, "total_tokens": 1006800} {"current_steps": 14, "total_steps": 1200, "loss": 0.436, "lr": 4.998320984446641e-05, "epoch": 0.23260643821391486, "percentage": 1.17, "elapsed_time": "0:08:35", "remaining_time": "12:08:04", "throughput": 2105.66, "total_tokens": 1085824} {"current_steps": 15, "total_steps": 1200, "loss": 0.4625, "lr": 4.9980725906018074e-05, "epoch": 0.24922118380062305, "percentage": 1.25, "elapsed_time": "0:09:08", "remaining_time": "12:02:04", "throughput": 2122.77, "total_tokens": 1164160} {"current_steps": 16, "total_steps": 1200, "loss": 0.5035, "lr": 4.997807075247146e-05, "epoch": 0.26583592938733125, "percentage": 1.33, "elapsed_time": "0:09:47", "remaining_time": "12:04:19", "throughput": 2115.25, "total_tokens": 1242264} {"current_steps": 17, "total_steps": 1200, "loss": 0.4354, "lr": 4.997524440202469e-05, "epoch": 0.2824506749740395, "percentage": 1.42, "elapsed_time": "0:10:24", "remaining_time": "12:04:47", "throughput": 2121.7, "total_tokens": 1325904} {"current_steps": 18, "total_steps": 1200, "loss": 0.5439, "lr": 4.9972246874049254e-05, "epoch": 0.29906542056074764, "percentage": 1.5, "elapsed_time": "0:10:52", "remaining_time": "11:53:36", "throughput": 2125.1, "total_tokens": 1385632} {"current_steps": 19, "total_steps": 1200, "loss": 0.3727, "lr": 4.996907818908987e-05, "epoch": 0.31568016614745587, "percentage": 1.58, "elapsed_time": "0:11:32", "remaining_time": "11:57:29", "throughput": 2123.4, "total_tokens": 1470632} {"current_steps": 20, "total_steps": 1200, "loss": 0.4894, "lr": 4.996573836886435e-05, "epoch": 0.3322949117341641, "percentage": 1.67, "elapsed_time": "0:12:10", "remaining_time": "11:58:11", "throughput": 2118.84, "total_tokens": 1547536} {"current_steps": 21, "total_steps": 1200, "loss": 0.3846, "lr": 4.9962227436263453e-05, "epoch": 0.34890965732087226, "percentage": 1.75, "elapsed_time": "0:12:44", "remaining_time": "11:55:02", "throughput": 2114.09, "total_tokens": 1615528} {"current_steps": 22, "total_steps": 1200, "loss": 0.4362, "lr": 4.995854541535071e-05, "epoch": 0.3655244029075805, "percentage": 1.83, "elapsed_time": "0:13:21", "remaining_time": "11:55:39", "throughput": 2112.84, "total_tokens": 1694352} {"current_steps": 23, "total_steps": 1200, "loss": 0.4438, "lr": 4.9954692331362294e-05, "epoch": 0.3821391484942887, "percentage": 1.92, "elapsed_time": "0:13:49", "remaining_time": "11:47:34", "throughput": 2113.97, "total_tokens": 1753776} {"current_steps": 24, "total_steps": 1200, "loss": 0.4496, "lr": 4.995066821070679e-05, "epoch": 0.3987538940809969, "percentage": 2.0, "elapsed_time": "0:14:15", "remaining_time": "11:38:37", "throughput": 2114.72, "total_tokens": 1809048} {"current_steps": 25, "total_steps": 1200, "loss": 0.5096, "lr": 4.994647308096509e-05, "epoch": 0.4153686396677051, "percentage": 2.08, "elapsed_time": "0:14:48", "remaining_time": "11:35:54", "throughput": 2120.99, "total_tokens": 1884264} {"current_steps": 26, "total_steps": 1200, "loss": 0.3722, "lr": 4.994210697089014e-05, "epoch": 0.43198338525441327, "percentage": 2.17, "elapsed_time": "0:15:38", "remaining_time": "11:46:28", "throughput": 2110.98, "total_tokens": 1981704} {"current_steps": 27, "total_steps": 1200, "loss": 0.4103, "lr": 4.9937569910406756e-05, "epoch": 0.4485981308411215, "percentage": 2.25, "elapsed_time": "0:16:07", "remaining_time": "11:40:28", "throughput": 2113.0, "total_tokens": 2044144} {"current_steps": 28, "total_steps": 1200, "loss": 0.357, "lr": 4.9932861930611454e-05, "epoch": 0.4652128764278297, "percentage": 2.33, "elapsed_time": "0:16:33", "remaining_time": "11:33:14", "throughput": 2120.89, "total_tokens": 2107584} {"current_steps": 29, "total_steps": 1200, "loss": 0.3889, "lr": 4.9927983063772196e-05, "epoch": 0.4818276220145379, "percentage": 2.42, "elapsed_time": "0:17:00", "remaining_time": "11:27:04", "throughput": 2124.8, "total_tokens": 2169248} {"current_steps": 30, "total_steps": 1200, "loss": 0.3543, "lr": 4.99229333433282e-05, "epoch": 0.4984423676012461, "percentage": 2.5, "elapsed_time": "0:17:31", "remaining_time": "11:23:09", "throughput": 2122.1, "total_tokens": 2230344} {"current_steps": 31, "total_steps": 1200, "loss": 0.3453, "lr": 4.9917712803889674e-05, "epoch": 0.5150571131879543, "percentage": 2.58, "elapsed_time": "0:18:05", "remaining_time": "11:22:02", "throughput": 2121.62, "total_tokens": 2302368} {"current_steps": 32, "total_steps": 1200, "loss": 0.435, "lr": 4.991232148123761e-05, "epoch": 0.5316718587746625, "percentage": 2.67, "elapsed_time": "0:18:34", "remaining_time": "11:18:09", "throughput": 2125.95, "total_tokens": 2369984} {"current_steps": 33, "total_steps": 1200, "loss": 0.3981, "lr": 4.990675941232353e-05, "epoch": 0.5482866043613707, "percentage": 2.75, "elapsed_time": "0:19:12", "remaining_time": "11:19:02", "throughput": 2129.17, "total_tokens": 2453032} {"current_steps": 34, "total_steps": 1200, "loss": 0.3755, "lr": 4.990102663526924e-05, "epoch": 0.564901349948079, "percentage": 2.83, "elapsed_time": "0:19:48", "remaining_time": "11:19:17", "throughput": 2126.67, "total_tokens": 2527464} {"current_steps": 35, "total_steps": 1200, "loss": 0.3699, "lr": 4.989512318936655e-05, "epoch": 0.5815160955347871, "percentage": 2.92, "elapsed_time": "0:20:22", "remaining_time": "11:18:02", "throughput": 2124.83, "total_tokens": 2597032} {"current_steps": 36, "total_steps": 1200, "loss": 0.3705, "lr": 4.9889049115077005e-05, "epoch": 0.5981308411214953, "percentage": 3.0, "elapsed_time": "0:20:57", "remaining_time": "11:17:29", "throughput": 2125.14, "total_tokens": 2671704} {"current_steps": 37, "total_steps": 1200, "loss": 0.3797, "lr": 4.988280445403164e-05, "epoch": 0.6147455867082036, "percentage": 3.08, "elapsed_time": "0:21:42", "remaining_time": "11:22:31", "throughput": 2124.29, "total_tokens": 2767640} {"current_steps": 38, "total_steps": 1200, "loss": 0.3799, "lr": 4.987638924903067e-05, "epoch": 0.6313603322949117, "percentage": 3.17, "elapsed_time": "0:22:16", "remaining_time": "11:21:02", "throughput": 2128.08, "total_tokens": 2843720} {"current_steps": 39, "total_steps": 1200, "loss": 0.2866, "lr": 4.9869803544043166e-05, "epoch": 0.6479750778816199, "percentage": 3.25, "elapsed_time": "0:22:55", "remaining_time": "11:22:20", "throughput": 2124.3, "total_tokens": 2921472} {"current_steps": 40, "total_steps": 1200, "loss": 0.4115, "lr": 4.9863047384206835e-05, "epoch": 0.6645898234683282, "percentage": 3.33, "elapsed_time": "0:23:30", "remaining_time": "11:21:58", "throughput": 2125.06, "total_tokens": 2998400} {"current_steps": 41, "total_steps": 1200, "loss": 0.3804, "lr": 4.985612081582764e-05, "epoch": 0.6812045690550363, "percentage": 3.42, "elapsed_time": "0:23:58", "remaining_time": "11:17:52", "throughput": 2126.5, "total_tokens": 3059648} {"current_steps": 42, "total_steps": 1200, "loss": 0.3121, "lr": 4.98490238863795e-05, "epoch": 0.6978193146417445, "percentage": 3.5, "elapsed_time": "0:24:32", "remaining_time": "11:16:26", "throughput": 2133.19, "total_tokens": 3140184} {"current_steps": 43, "total_steps": 1200, "loss": 0.3271, "lr": 4.984175664450397e-05, "epoch": 0.7144340602284528, "percentage": 3.58, "elapsed_time": "0:25:04", "remaining_time": "11:14:37", "throughput": 2131.93, "total_tokens": 3207184} {"current_steps": 44, "total_steps": 1200, "loss": 0.364, "lr": 4.983431914000991e-05, "epoch": 0.731048805815161, "percentage": 3.67, "elapsed_time": "0:25:43", "remaining_time": "11:16:01", "throughput": 2132.55, "total_tokens": 3292344} {"current_steps": 45, "total_steps": 1200, "loss": 0.3894, "lr": 4.982671142387316e-05, "epoch": 0.7476635514018691, "percentage": 3.75, "elapsed_time": "0:26:17", "remaining_time": "11:14:59", "throughput": 2132.81, "total_tokens": 3365384} {"current_steps": 46, "total_steps": 1200, "loss": 0.3354, "lr": 4.981893354823614e-05, "epoch": 0.7642782969885774, "percentage": 3.83, "elapsed_time": "0:26:52", "remaining_time": "11:14:14", "throughput": 2133.69, "total_tokens": 3440720} {"current_steps": 47, "total_steps": 1200, "loss": 0.3058, "lr": 4.9810985566407544e-05, "epoch": 0.7808930425752856, "percentage": 3.92, "elapsed_time": "0:27:36", "remaining_time": "11:17:25", "throughput": 2132.72, "total_tokens": 3533576} {"current_steps": 48, "total_steps": 1200, "loss": 0.4658, "lr": 4.980286753286195e-05, "epoch": 0.7975077881619937, "percentage": 4.0, "elapsed_time": "0:28:06", "remaining_time": "11:14:43", "throughput": 2134.06, "total_tokens": 3599744} {"current_steps": 49, "total_steps": 1200, "loss": 0.3647, "lr": 4.979457950323945e-05, "epoch": 0.814122533748702, "percentage": 4.08, "elapsed_time": "0:28:53", "remaining_time": "11:18:34", "throughput": 2128.65, "total_tokens": 3689520} {"current_steps": 50, "total_steps": 1200, "loss": 0.343, "lr": 4.9786121534345265e-05, "epoch": 0.8307372793354102, "percentage": 4.17, "elapsed_time": "0:29:20", "remaining_time": "11:14:54", "throughput": 2130.94, "total_tokens": 3751808} {"current_steps": 51, "total_steps": 1200, "loss": 0.3317, "lr": 4.9777493684149375e-05, "epoch": 0.8473520249221184, "percentage": 4.25, "elapsed_time": "0:30:01", "remaining_time": "11:16:29", "throughput": 2130.92, "total_tokens": 3839096} {"current_steps": 52, "total_steps": 1200, "loss": 0.38, "lr": 4.976869601178609e-05, "epoch": 0.8639667705088265, "percentage": 4.33, "elapsed_time": "0:30:39", "remaining_time": "11:16:53", "throughput": 2130.75, "total_tokens": 3919824} {"current_steps": 53, "total_steps": 1200, "loss": 0.2676, "lr": 4.975972857755369e-05, "epoch": 0.8805815160955348, "percentage": 4.42, "elapsed_time": "0:31:11", "remaining_time": "11:15:04", "throughput": 2131.48, "total_tokens": 3989312} {"current_steps": 54, "total_steps": 1200, "loss": 0.3516, "lr": 4.975059144291394e-05, "epoch": 0.897196261682243, "percentage": 4.5, "elapsed_time": "0:31:41", "remaining_time": "11:12:38", "throughput": 2135.19, "total_tokens": 4060528} {"current_steps": 55, "total_steps": 1200, "loss": 0.3004, "lr": 4.974128467049176e-05, "epoch": 0.9138110072689511, "percentage": 4.58, "elapsed_time": "0:32:12", "remaining_time": "11:10:38", "throughput": 2136.4, "total_tokens": 4129368} {"current_steps": 56, "total_steps": 1200, "loss": 0.3009, "lr": 4.9731808324074717e-05, "epoch": 0.9304257528556594, "percentage": 4.67, "elapsed_time": "0:32:34", "remaining_time": "11:05:24", "throughput": 2136.38, "total_tokens": 4175208} {"current_steps": 57, "total_steps": 1200, "loss": 0.2814, "lr": 4.972216246861262e-05, "epoch": 0.9470404984423676, "percentage": 4.75, "elapsed_time": "0:32:54", "remaining_time": "10:59:50", "throughput": 2136.47, "total_tokens": 4218096} {"current_steps": 58, "total_steps": 1200, "loss": 0.3321, "lr": 4.971234717021709e-05, "epoch": 0.9636552440290758, "percentage": 4.83, "elapsed_time": "0:33:20", "remaining_time": "10:56:24", "throughput": 2137.69, "total_tokens": 4275968} {"current_steps": 59, "total_steps": 1200, "loss": 0.2881, "lr": 4.9702362496161085e-05, "epoch": 0.980269989615784, "percentage": 4.92, "elapsed_time": "0:33:51", "remaining_time": "10:54:48", "throughput": 2139.53, "total_tokens": 4346616} {"current_steps": 60, "total_steps": 1200, "loss": 0.2993, "lr": 4.9692208514878444e-05, "epoch": 0.9968847352024922, "percentage": 5.0, "elapsed_time": "0:34:29", "remaining_time": "10:55:24", "throughput": 2137.99, "total_tokens": 4425064} {"current_steps": 61, "total_steps": 1200, "loss": 0.2511, "lr": 4.968188529596342e-05, "epoch": 1.0, "percentage": 5.08, "elapsed_time": "0:34:36", "remaining_time": "10:46:21", "throughput": 2135.49, "total_tokens": 4435328} {"current_steps": 62, "total_steps": 1200, "loss": 0.3127, "lr": 4.9671392910170185e-05, "epoch": 1.0166147455867083, "percentage": 5.17, "elapsed_time": "0:35:09", "remaining_time": "10:45:15", "throughput": 2133.46, "total_tokens": 4500104} {"current_steps": 63, "total_steps": 1200, "loss": 0.3601, "lr": 4.966073142941239e-05, "epoch": 1.0332294911734163, "percentage": 5.25, "elapsed_time": "0:35:46", "remaining_time": "10:45:41", "throughput": 2134.48, "total_tokens": 4581976} {"current_steps": 64, "total_steps": 1200, "loss": 0.3049, "lr": 4.964990092676263e-05, "epoch": 1.0498442367601246, "percentage": 5.33, "elapsed_time": "0:36:17", "remaining_time": "10:44:14", "throughput": 2136.24, "total_tokens": 4652160} {"current_steps": 65, "total_steps": 1200, "loss": 0.3099, "lr": 4.9638901476451946e-05, "epoch": 1.066458982346833, "percentage": 5.42, "elapsed_time": "0:36:43", "remaining_time": "10:41:17", "throughput": 2137.19, "total_tokens": 4709368} {"current_steps": 66, "total_steps": 1200, "loss": 0.3273, "lr": 4.962773315386935e-05, "epoch": 1.083073727933541, "percentage": 5.5, "elapsed_time": "0:37:28", "remaining_time": "10:43:45", "throughput": 2134.44, "total_tokens": 4798256} {"current_steps": 67, "total_steps": 1200, "loss": 0.282, "lr": 4.961639603556127e-05, "epoch": 1.0996884735202492, "percentage": 5.58, "elapsed_time": "0:37:54", "remaining_time": "10:40:59", "throughput": 2136.58, "total_tokens": 4859200} {"current_steps": 68, "total_steps": 1200, "loss": 0.3642, "lr": 4.960489019923105e-05, "epoch": 1.1163032191069575, "percentage": 5.67, "elapsed_time": "0:38:23", "remaining_time": "10:38:58", "throughput": 2138.91, "total_tokens": 4925992} {"current_steps": 69, "total_steps": 1200, "loss": 0.2896, "lr": 4.9593215723738404e-05, "epoch": 1.1329179646936656, "percentage": 5.75, "elapsed_time": "0:38:56", "remaining_time": "10:38:25", "throughput": 2139.04, "total_tokens": 4998808} {"current_steps": 70, "total_steps": 1200, "loss": 0.2578, "lr": 4.958137268909887e-05, "epoch": 1.1495327102803738, "percentage": 5.83, "elapsed_time": "0:39:41", "remaining_time": "10:40:48", "throughput": 2136.93, "total_tokens": 5089672} {"current_steps": 71, "total_steps": 1200, "loss": 0.3243, "lr": 4.9569361176483286e-05, "epoch": 1.1661474558670821, "percentage": 5.92, "elapsed_time": "0:40:19", "remaining_time": "10:41:21", "throughput": 2135.03, "total_tokens": 5166744} {"current_steps": 72, "total_steps": 1200, "loss": 0.3949, "lr": 4.9557181268217227e-05, "epoch": 1.1827622014537902, "percentage": 6.0, "elapsed_time": "0:40:48", "remaining_time": "10:39:14", "throughput": 2135.58, "total_tokens": 5228264} {"current_steps": 73, "total_steps": 1200, "loss": 0.2877, "lr": 4.9544833047780394e-05, "epoch": 1.1993769470404985, "percentage": 6.08, "elapsed_time": "0:41:39", "remaining_time": "10:43:09", "throughput": 2135.65, "total_tokens": 5338224} {"current_steps": 74, "total_steps": 1200, "loss": 0.3152, "lr": 4.9532316599806124e-05, "epoch": 1.2159916926272065, "percentage": 6.17, "elapsed_time": "0:42:08", "remaining_time": "10:41:07", "throughput": 2135.95, "total_tokens": 5399848} {"current_steps": 75, "total_steps": 1200, "loss": 0.2976, "lr": 4.951963201008076e-05, "epoch": 1.2326064382139148, "percentage": 6.25, "elapsed_time": "0:42:39", "remaining_time": "10:39:47", "throughput": 2136.85, "total_tokens": 5468624} {"current_steps": 76, "total_steps": 1200, "loss": 0.2982, "lr": 4.9506779365543046e-05, "epoch": 1.249221183800623, "percentage": 6.33, "elapsed_time": "0:43:11", "remaining_time": "10:38:43", "throughput": 2136.71, "total_tokens": 5536776} {"current_steps": 77, "total_steps": 1200, "loss": 0.3272, "lr": 4.949375875428357e-05, "epoch": 1.2658359293873311, "percentage": 6.42, "elapsed_time": "0:43:41", "remaining_time": "10:37:11", "throughput": 2139.83, "total_tokens": 5609296} {"current_steps": 78, "total_steps": 1200, "loss": 0.2768, "lr": 4.9480570265544144e-05, "epoch": 1.2824506749740394, "percentage": 6.5, "elapsed_time": "0:44:07", "remaining_time": "10:34:41", "throughput": 2139.43, "total_tokens": 5663824} {"current_steps": 79, "total_steps": 1200, "loss": 0.318, "lr": 4.94672139897172e-05, "epoch": 1.2990654205607477, "percentage": 6.58, "elapsed_time": "0:44:41", "remaining_time": "10:34:05", "throughput": 2141.6, "total_tokens": 5742032} {"current_steps": 80, "total_steps": 1200, "loss": 0.3007, "lr": 4.9453690018345144e-05, "epoch": 1.3156801661474558, "percentage": 6.67, "elapsed_time": "0:45:16", "remaining_time": "10:33:50", "throughput": 2141.33, "total_tokens": 5816864} {"current_steps": 81, "total_steps": 1200, "loss": 0.2797, "lr": 4.943999844411977e-05, "epoch": 1.332294911734164, "percentage": 6.75, "elapsed_time": "0:45:45", "remaining_time": "10:32:07", "throughput": 2142.34, "total_tokens": 5881624} {"current_steps": 82, "total_steps": 1200, "loss": 0.2591, "lr": 4.94261393608816e-05, "epoch": 1.3489096573208723, "percentage": 6.83, "elapsed_time": "0:46:30", "remaining_time": "10:34:02", "throughput": 2139.68, "total_tokens": 5970272} {"current_steps": 83, "total_steps": 1200, "loss": 0.2687, "lr": 4.941211286361922e-05, "epoch": 1.3655244029075804, "percentage": 6.92, "elapsed_time": "0:47:11", "remaining_time": "10:35:02", "throughput": 2139.96, "total_tokens": 6058752} {"current_steps": 84, "total_steps": 1200, "loss": 0.2979, "lr": 4.939791904846869e-05, "epoch": 1.3821391484942886, "percentage": 7.0, "elapsed_time": "0:47:37", "remaining_time": "10:32:44", "throughput": 2141.71, "total_tokens": 6120064} {"current_steps": 85, "total_steps": 1200, "loss": 0.2927, "lr": 4.938355801271282e-05, "epoch": 1.398753894080997, "percentage": 7.08, "elapsed_time": "0:48:06", "remaining_time": "10:31:00", "throughput": 2141.93, "total_tokens": 6182072} {"current_steps": 86, "total_steps": 1200, "loss": 0.295, "lr": 4.936902985478055e-05, "epoch": 1.415368639667705, "percentage": 7.17, "elapsed_time": "0:48:48", "remaining_time": "10:32:09", "throughput": 2141.17, "total_tokens": 6269680} {"current_steps": 87, "total_steps": 1200, "loss": 0.2925, "lr": 4.935433467424624e-05, "epoch": 1.4319833852544133, "percentage": 7.25, "elapsed_time": "0:49:24", "remaining_time": "10:32:06", "throughput": 2141.05, "total_tokens": 6347424} {"current_steps": 88, "total_steps": 1200, "loss": 0.3153, "lr": 4.933947257182901e-05, "epoch": 1.4485981308411215, "percentage": 7.33, "elapsed_time": "0:49:57", "remaining_time": "10:31:17", "throughput": 2139.31, "total_tokens": 6412584} {"current_steps": 89, "total_steps": 1200, "loss": 0.292, "lr": 4.932444364939205e-05, "epoch": 1.4652128764278296, "percentage": 7.42, "elapsed_time": "0:50:27", "remaining_time": "10:29:47", "throughput": 2141.59, "total_tokens": 6482728} {"current_steps": 90, "total_steps": 1200, "loss": 0.3472, "lr": 4.9309248009941914e-05, "epoch": 1.4818276220145379, "percentage": 7.5, "elapsed_time": "0:51:03", "remaining_time": "10:29:40", "throughput": 2142.17, "total_tokens": 6562104} {"current_steps": 91, "total_steps": 1200, "loss": 0.2995, "lr": 4.929388575762782e-05, "epoch": 1.4984423676012462, "percentage": 7.58, "elapsed_time": "0:51:42", "remaining_time": "10:30:11", "throughput": 2145.44, "total_tokens": 6656552} {"current_steps": 92, "total_steps": 1200, "loss": 0.2549, "lr": 4.9278356997740904e-05, "epoch": 1.5150571131879542, "percentage": 7.67, "elapsed_time": "0:52:07", "remaining_time": "10:27:47", "throughput": 2146.75, "total_tokens": 6714184} {"current_steps": 93, "total_steps": 1200, "loss": 0.2814, "lr": 4.9262661836713564e-05, "epoch": 1.5316718587746625, "percentage": 7.75, "elapsed_time": "0:52:44", "remaining_time": "10:27:52", "throughput": 2146.52, "total_tokens": 6793552} {"current_steps": 94, "total_steps": 1200, "loss": 0.2876, "lr": 4.924680038211867e-05, "epoch": 1.5482866043613708, "percentage": 7.83, "elapsed_time": "0:53:18", "remaining_time": "10:27:13", "throughput": 2146.39, "total_tokens": 6865256} {"current_steps": 95, "total_steps": 1200, "loss": 0.2846, "lr": 4.9230772742668866e-05, "epoch": 1.5649013499480788, "percentage": 7.92, "elapsed_time": "0:53:49", "remaining_time": "10:26:01", "throughput": 2146.33, "total_tokens": 6931152} {"current_steps": 96, "total_steps": 1200, "loss": 0.2944, "lr": 4.9214579028215776e-05, "epoch": 1.5815160955347871, "percentage": 8.0, "elapsed_time": "0:54:20", "remaining_time": "10:25:00", "throughput": 2146.17, "total_tokens": 6998408} {"current_steps": 97, "total_steps": 1200, "loss": 0.251, "lr": 4.919821934974933e-05, "epoch": 1.5981308411214954, "percentage": 8.08, "elapsed_time": "0:54:45", "remaining_time": "10:22:37", "throughput": 2146.87, "total_tokens": 7053008} {"current_steps": 98, "total_steps": 1200, "loss": 0.2851, "lr": 4.918169381939692e-05, "epoch": 1.6147455867082035, "percentage": 8.17, "elapsed_time": "0:55:08", "remaining_time": "10:20:03", "throughput": 2147.94, "total_tokens": 7106440} {"current_steps": 99, "total_steps": 1200, "loss": 0.2959, "lr": 4.916500255042268e-05, "epoch": 1.6313603322949117, "percentage": 8.25, "elapsed_time": "0:55:36", "remaining_time": "10:18:25", "throughput": 2148.08, "total_tokens": 7167032} {"current_steps": 100, "total_steps": 1200, "loss": 0.2481, "lr": 4.914814565722671e-05, "epoch": 1.64797507788162, "percentage": 8.33, "elapsed_time": "0:56:14", "remaining_time": "10:18:36", "throughput": 2147.39, "total_tokens": 7245720} {"current_steps": 101, "total_steps": 1200, "loss": 0.3168, "lr": 4.913112325534426e-05, "epoch": 1.664589823468328, "percentage": 8.42, "elapsed_time": "0:56:49", "remaining_time": "10:18:23", "throughput": 2148.56, "total_tokens": 7326320} {"current_steps": 102, "total_steps": 1200, "loss": 0.2805, "lr": 4.9113935461444955e-05, "epoch": 1.6812045690550363, "percentage": 8.5, "elapsed_time": "0:57:45", "remaining_time": "10:21:48", "throughput": 2147.32, "total_tokens": 7442232} {"current_steps": 103, "total_steps": 1200, "loss": 0.2675, "lr": 4.9096582393332025e-05, "epoch": 1.6978193146417446, "percentage": 8.58, "elapsed_time": "0:58:12", "remaining_time": "10:19:59", "throughput": 2148.03, "total_tokens": 7502496} {"current_steps": 104, "total_steps": 1200, "loss": 0.3038, "lr": 4.907906416994146e-05, "epoch": 1.7144340602284527, "percentage": 8.67, "elapsed_time": "0:58:41", "remaining_time": "10:18:34", "throughput": 2148.48, "total_tokens": 7566496} {"current_steps": 105, "total_steps": 1200, "loss": 0.3639, "lr": 4.906138091134118e-05, "epoch": 1.731048805815161, "percentage": 8.75, "elapsed_time": "0:59:09", "remaining_time": "10:16:53", "throughput": 2149.49, "total_tokens": 7629056} {"current_steps": 106, "total_steps": 1200, "loss": 0.2944, "lr": 4.9043532738730284e-05, "epoch": 1.7476635514018692, "percentage": 8.83, "elapsed_time": "0:59:44", "remaining_time": "10:16:38", "throughput": 2149.64, "total_tokens": 7706096} {"current_steps": 107, "total_steps": 1200, "loss": 0.2392, "lr": 4.9025519774438136e-05, "epoch": 1.7642782969885773, "percentage": 8.92, "elapsed_time": "1:00:18", "remaining_time": "10:16:06", "throughput": 2149.89, "total_tokens": 7780072} {"current_steps": 108, "total_steps": 1200, "loss": 0.2685, "lr": 4.900734214192358e-05, "epoch": 1.7808930425752856, "percentage": 9.0, "elapsed_time": "1:00:52", "remaining_time": "10:15:33", "throughput": 2151.17, "total_tokens": 7857712} {"current_steps": 109, "total_steps": 1200, "loss": 0.2513, "lr": 4.898899996577407e-05, "epoch": 1.7975077881619939, "percentage": 9.08, "elapsed_time": "1:01:19", "remaining_time": "10:13:53", "throughput": 2151.34, "total_tokens": 7916832} {"current_steps": 110, "total_steps": 1200, "loss": 0.2974, "lr": 4.8970493371704826e-05, "epoch": 1.814122533748702, "percentage": 9.17, "elapsed_time": "1:01:49", "remaining_time": "10:12:40", "throughput": 2154.58, "total_tokens": 7993056} {"current_steps": 111, "total_steps": 1200, "loss": 0.3096, "lr": 4.8951822486557986e-05, "epoch": 1.8307372793354102, "percentage": 9.25, "elapsed_time": "1:02:36", "remaining_time": "10:14:13", "throughput": 2153.67, "total_tokens": 8090056} {"current_steps": 112, "total_steps": 1200, "loss": 0.2633, "lr": 4.893298743830168e-05, "epoch": 1.8473520249221185, "percentage": 9.33, "elapsed_time": "1:03:11", "remaining_time": "10:13:48", "throughput": 2153.61, "total_tokens": 8164808} {"current_steps": 113, "total_steps": 1200, "loss": 0.2584, "lr": 4.891398835602925e-05, "epoch": 1.8639667705088265, "percentage": 9.42, "elapsed_time": "1:03:38", "remaining_time": "10:12:07", "throughput": 2153.87, "total_tokens": 8223568} {"current_steps": 114, "total_steps": 1200, "loss": 0.2619, "lr": 4.8894825369958255e-05, "epoch": 1.8805815160955348, "percentage": 9.5, "elapsed_time": "1:04:02", "remaining_time": "10:10:02", "throughput": 2153.96, "total_tokens": 8276160} {"current_steps": 115, "total_steps": 1200, "loss": 0.2762, "lr": 4.8875498611429674e-05, "epoch": 1.897196261682243, "percentage": 9.58, "elapsed_time": "1:04:36", "remaining_time": "10:09:38", "throughput": 2155.02, "total_tokens": 8354904} {"current_steps": 116, "total_steps": 1200, "loss": 0.3152, "lr": 4.8856008212906925e-05, "epoch": 1.9138110072689511, "percentage": 9.67, "elapsed_time": "1:05:13", "remaining_time": "10:09:29", "throughput": 2157.41, "total_tokens": 8442584} {"current_steps": 117, "total_steps": 1200, "loss": 0.2759, "lr": 4.8836354307975026e-05, "epoch": 1.9304257528556594, "percentage": 9.75, "elapsed_time": "1:05:41", "remaining_time": "10:08:04", "throughput": 2158.24, "total_tokens": 8506688} {"current_steps": 118, "total_steps": 1200, "loss": 0.2192, "lr": 4.881653703133966e-05, "epoch": 1.9470404984423677, "percentage": 9.83, "elapsed_time": "1:06:32", "remaining_time": "10:10:07", "throughput": 2156.82, "total_tokens": 8610712} {"current_steps": 119, "total_steps": 1200, "loss": 0.2618, "lr": 4.87965565188262e-05, "epoch": 1.9636552440290758, "percentage": 9.92, "elapsed_time": "1:07:12", "remaining_time": "10:10:28", "throughput": 2155.81, "total_tokens": 8692624} {"current_steps": 120, "total_steps": 1200, "loss": 0.2666, "lr": 4.877641290737884e-05, "epoch": 1.980269989615784, "percentage": 10.0, "elapsed_time": "1:07:49", "remaining_time": "10:10:21", "throughput": 2155.83, "total_tokens": 8772208} {"current_steps": 121, "total_steps": 1200, "loss": 0.253, "lr": 4.8756106335059646e-05, "epoch": 1.9968847352024923, "percentage": 10.08, "elapsed_time": "1:08:25", "remaining_time": "10:10:14", "throughput": 2156.58, "total_tokens": 8854904} {"current_steps": 122, "total_steps": 1200, "loss": 0.235, "lr": 4.87356369410476e-05, "epoch": 2.0, "percentage": 10.17, "elapsed_time": "1:08:35", "remaining_time": "10:06:04", "throughput": 2155.95, "total_tokens": 8872656} {"current_steps": 123, "total_steps": 1200, "loss": 0.266, "lr": 4.8715004865637614e-05, "epoch": 2.016614745586708, "percentage": 10.25, "elapsed_time": "1:09:08", "remaining_time": "10:05:26", "throughput": 2156.43, "total_tokens": 8946480} {"current_steps": 124, "total_steps": 1200, "loss": 0.2696, "lr": 4.869421025023965e-05, "epoch": 2.0332294911734166, "percentage": 10.33, "elapsed_time": "1:09:41", "remaining_time": "10:04:45", "throughput": 2157.85, "total_tokens": 9023328} {"current_steps": 125, "total_steps": 1200, "loss": 0.2552, "lr": 4.867325323737765e-05, "epoch": 2.0498442367601246, "percentage": 10.42, "elapsed_time": "1:10:04", "remaining_time": "10:02:39", "throughput": 2158.17, "total_tokens": 9074320} {"current_steps": 126, "total_steps": 1200, "loss": 0.2486, "lr": 4.8652133970688636e-05, "epoch": 2.0664589823468327, "percentage": 10.5, "elapsed_time": "1:10:40", "remaining_time": "10:02:22", "throughput": 2157.66, "total_tokens": 9148784} {"current_steps": 127, "total_steps": 1200, "loss": 0.2814, "lr": 4.8630852594921706e-05, "epoch": 2.083073727933541, "percentage": 10.58, "elapsed_time": "1:11:24", "remaining_time": "10:03:23", "throughput": 2157.91, "total_tokens": 9246624} {"current_steps": 128, "total_steps": 1200, "loss": 0.304, "lr": 4.860940925593703e-05, "epoch": 2.0996884735202492, "percentage": 10.67, "elapsed_time": "1:12:01", "remaining_time": "10:03:09", "throughput": 2158.72, "total_tokens": 9328176} {"current_steps": 129, "total_steps": 1200, "loss": 0.2427, "lr": 4.8587804100704845e-05, "epoch": 2.1163032191069573, "percentage": 10.75, "elapsed_time": "1:12:26", "remaining_time": "10:01:23", "throughput": 2160.27, "total_tokens": 9388936} {"current_steps": 130, "total_steps": 1200, "loss": 0.2485, "lr": 4.856603727730447e-05, "epoch": 2.132917964693666, "percentage": 10.83, "elapsed_time": "1:13:00", "remaining_time": "10:00:51", "throughput": 2160.15, "total_tokens": 9461664} {"current_steps": 131, "total_steps": 1200, "loss": 0.2628, "lr": 4.854410893492326e-05, "epoch": 2.149532710280374, "percentage": 10.92, "elapsed_time": "1:13:32", "remaining_time": "10:00:08", "throughput": 2160.86, "total_tokens": 9535000} {"current_steps": 132, "total_steps": 1200, "loss": 0.2518, "lr": 4.852201922385564e-05, "epoch": 2.166147455867082, "percentage": 11.0, "elapsed_time": "1:14:01", "remaining_time": "9:58:52", "throughput": 2161.72, "total_tokens": 9600296} {"current_steps": 133, "total_steps": 1200, "loss": 0.2429, "lr": 4.8499768295502004e-05, "epoch": 2.1827622014537904, "percentage": 11.08, "elapsed_time": "1:14:42", "remaining_time": "9:59:17", "throughput": 2161.22, "total_tokens": 9686784} {"current_steps": 134, "total_steps": 1200, "loss": 0.2775, "lr": 4.847735630236773e-05, "epoch": 2.1993769470404985, "percentage": 11.17, "elapsed_time": "1:15:27", "remaining_time": "10:00:14", "throughput": 2160.55, "total_tokens": 9781112} {"current_steps": 135, "total_steps": 1200, "loss": 0.2439, "lr": 4.8454783398062106e-05, "epoch": 2.2159916926272065, "percentage": 11.25, "elapsed_time": "1:15:59", "remaining_time": "9:59:26", "throughput": 2160.42, "total_tokens": 9849528} {"current_steps": 136, "total_steps": 1200, "loss": 0.2538, "lr": 4.843204973729729e-05, "epoch": 2.232606438213915, "percentage": 11.33, "elapsed_time": "1:16:36", "remaining_time": "9:59:20", "throughput": 2160.58, "total_tokens": 9931080} {"current_steps": 137, "total_steps": 1200, "loss": 0.2782, "lr": 4.840915547588725e-05, "epoch": 2.249221183800623, "percentage": 11.42, "elapsed_time": "1:17:15", "remaining_time": "9:59:26", "throughput": 2159.75, "total_tokens": 10011176} {"current_steps": 138, "total_steps": 1200, "loss": 0.248, "lr": 4.838610077074669e-05, "epoch": 2.265835929387331, "percentage": 11.5, "elapsed_time": "1:17:49", "remaining_time": "9:58:52", "throughput": 2159.73, "total_tokens": 10084128} {"current_steps": 139, "total_steps": 1200, "loss": 0.2582, "lr": 4.836288577988996e-05, "epoch": 2.2824506749740396, "percentage": 11.58, "elapsed_time": "1:18:21", "remaining_time": "9:58:08", "throughput": 2159.98, "total_tokens": 10155536} {"current_steps": 140, "total_steps": 1200, "loss": 0.2199, "lr": 4.8339510662430046e-05, "epoch": 2.2990654205607477, "percentage": 11.67, "elapsed_time": "1:19:06", "remaining_time": "9:58:54", "throughput": 2159.93, "total_tokens": 10251160} {"current_steps": 141, "total_steps": 1200, "loss": 0.2324, "lr": 4.8315975578577355e-05, "epoch": 2.3156801661474558, "percentage": 11.75, "elapsed_time": "1:19:51", "remaining_time": "9:59:49", "throughput": 2159.09, "total_tokens": 10345864} {"current_steps": 142, "total_steps": 1200, "loss": 0.4072, "lr": 4.8292280689638725e-05, "epoch": 2.3322949117341643, "percentage": 11.83, "elapsed_time": "1:20:22", "remaining_time": "9:58:53", "throughput": 2160.04, "total_tokens": 10417616} {"current_steps": 143, "total_steps": 1200, "loss": 0.2607, "lr": 4.826842615801628e-05, "epoch": 2.3489096573208723, "percentage": 11.92, "elapsed_time": "1:20:52", "remaining_time": "9:57:48", "throughput": 2160.05, "total_tokens": 10481816} {"current_steps": 144, "total_steps": 1200, "loss": 0.3094, "lr": 4.8244412147206284e-05, "epoch": 2.3655244029075804, "percentage": 12.0, "elapsed_time": "1:21:31", "remaining_time": "9:57:52", "throughput": 2159.15, "total_tokens": 10562056} {"current_steps": 145, "total_steps": 1200, "loss": 0.2407, "lr": 4.822023882179811e-05, "epoch": 2.382139148494289, "percentage": 12.08, "elapsed_time": "1:21:56", "remaining_time": "9:56:09", "throughput": 2158.76, "total_tokens": 10612808} {"current_steps": 146, "total_steps": 1200, "loss": 0.2481, "lr": 4.8195906347473e-05, "epoch": 2.398753894080997, "percentage": 12.17, "elapsed_time": "1:22:26", "remaining_time": "9:55:08", "throughput": 2159.66, "total_tokens": 10682328} {"current_steps": 147, "total_steps": 1200, "loss": 0.2528, "lr": 4.817141489100302e-05, "epoch": 2.415368639667705, "percentage": 12.25, "elapsed_time": "1:23:06", "remaining_time": "9:55:18", "throughput": 2160.29, "total_tokens": 10771912} {"current_steps": 148, "total_steps": 1200, "loss": 0.2739, "lr": 4.814676462024988e-05, "epoch": 2.431983385254413, "percentage": 12.33, "elapsed_time": "1:23:39", "remaining_time": "9:54:37", "throughput": 2160.1, "total_tokens": 10842232} {"current_steps": 149, "total_steps": 1200, "loss": 0.2407, "lr": 4.8121955704163745e-05, "epoch": 2.4485981308411215, "percentage": 12.42, "elapsed_time": "1:24:05", "remaining_time": "9:53:07", "throughput": 2160.89, "total_tokens": 10902264} {"current_steps": 150, "total_steps": 1200, "loss": 0.2142, "lr": 4.8096988312782174e-05, "epoch": 2.4652128764278296, "percentage": 12.5, "elapsed_time": "1:24:51", "remaining_time": "9:54:03", "throughput": 2158.83, "total_tokens": 10992744} {"current_steps": 151, "total_steps": 1200, "loss": 0.1428, "lr": 4.8071862617228855e-05, "epoch": 2.4818276220145377, "percentage": 12.58, "elapsed_time": "1:25:40", "remaining_time": "9:55:08", "throughput": 2157.58, "total_tokens": 11090064} {"current_steps": 152, "total_steps": 1200, "loss": 0.2268, "lr": 4.8046578789712515e-05, "epoch": 2.498442367601246, "percentage": 12.67, "elapsed_time": "1:26:14", "remaining_time": "9:54:34", "throughput": 2157.4, "total_tokens": 11162864} {"current_steps": 153, "total_steps": 1200, "loss": 0.2388, "lr": 4.8021137003525664e-05, "epoch": 2.515057113187954, "percentage": 12.75, "elapsed_time": "1:26:41", "remaining_time": "9:53:17", "throughput": 2157.74, "total_tokens": 11224368} {"current_steps": 154, "total_steps": 1200, "loss": 0.2588, "lr": 4.7995537433043446e-05, "epoch": 2.5316718587746623, "percentage": 12.83, "elapsed_time": "1:27:12", "remaining_time": "9:52:18", "throughput": 2157.97, "total_tokens": 11291056} {"current_steps": 155, "total_steps": 1200, "loss": 0.2225, "lr": 4.796978025372246e-05, "epoch": 2.5482866043613708, "percentage": 12.92, "elapsed_time": "1:27:35", "remaining_time": "9:50:34", "throughput": 2158.63, "total_tokens": 11345464} {"current_steps": 156, "total_steps": 1200, "loss": 0.275, "lr": 4.794386564209953e-05, "epoch": 2.564901349948079, "percentage": 13.0, "elapsed_time": "1:28:08", "remaining_time": "9:49:51", "throughput": 2159.26, "total_tokens": 11418912} {"current_steps": 157, "total_steps": 1200, "loss": 0.2407, "lr": 4.79177937757905e-05, "epoch": 2.581516095534787, "percentage": 13.08, "elapsed_time": "1:28:40", "remaining_time": "9:49:05", "throughput": 2159.82, "total_tokens": 11491216} {"current_steps": 158, "total_steps": 1200, "loss": 0.1971, "lr": 4.7891564833489035e-05, "epoch": 2.5981308411214954, "percentage": 13.17, "elapsed_time": "1:29:10", "remaining_time": "9:48:05", "throughput": 2160.19, "total_tokens": 11558016} {"current_steps": 159, "total_steps": 1200, "loss": 0.2362, "lr": 4.7865178994965344e-05, "epoch": 2.6147455867082035, "percentage": 13.25, "elapsed_time": "1:29:41", "remaining_time": "9:47:13", "throughput": 2161.19, "total_tokens": 11630432} {"current_steps": 160, "total_steps": 1200, "loss": 0.2252, "lr": 4.783863644106502e-05, "epoch": 2.6313603322949115, "percentage": 13.33, "elapsed_time": "1:30:06", "remaining_time": "9:45:40", "throughput": 2161.34, "total_tokens": 11684624} {"current_steps": 161, "total_steps": 1200, "loss": 0.2506, "lr": 4.781193735370777e-05, "epoch": 2.64797507788162, "percentage": 13.42, "elapsed_time": "1:30:45", "remaining_time": "9:45:45", "throughput": 2161.27, "total_tokens": 11770232} {"current_steps": 162, "total_steps": 1200, "loss": 0.2352, "lr": 4.7785081915886134e-05, "epoch": 2.664589823468328, "percentage": 13.5, "elapsed_time": "1:31:11", "remaining_time": "9:44:20", "throughput": 2161.64, "total_tokens": 11828360} {"current_steps": 163, "total_steps": 1200, "loss": 0.2308, "lr": 4.775807031166428e-05, "epoch": 2.681204569055036, "percentage": 13.58, "elapsed_time": "1:31:52", "remaining_time": "9:44:31", "throughput": 2161.56, "total_tokens": 11915944} {"current_steps": 164, "total_steps": 1200, "loss": 0.2238, "lr": 4.773090272617672e-05, "epoch": 2.6978193146417446, "percentage": 13.67, "elapsed_time": "1:32:22", "remaining_time": "9:43:31", "throughput": 2161.85, "total_tokens": 11981792} {"current_steps": 165, "total_steps": 1200, "loss": 0.3196, "lr": 4.7703579345627035e-05, "epoch": 2.7144340602284527, "percentage": 13.75, "elapsed_time": "1:32:51", "remaining_time": "9:42:29", "throughput": 2161.65, "total_tokens": 12044024} {"current_steps": 166, "total_steps": 1200, "loss": 0.2745, "lr": 4.7676100357286624e-05, "epoch": 2.7310488058151607, "percentage": 13.83, "elapsed_time": "1:33:15", "remaining_time": "9:40:52", "throughput": 2161.37, "total_tokens": 12093424} {"current_steps": 167, "total_steps": 1200, "loss": 0.2285, "lr": 4.76484659494934e-05, "epoch": 2.7476635514018692, "percentage": 13.92, "elapsed_time": "1:33:49", "remaining_time": "9:40:19", "throughput": 2161.6, "total_tokens": 12167792} {"current_steps": 168, "total_steps": 1200, "loss": 0.2506, "lr": 4.762067631165049e-05, "epoch": 2.7642782969885773, "percentage": 14.0, "elapsed_time": "1:34:16", "remaining_time": "9:39:08", "throughput": 2162.69, "total_tokens": 12233712} {"current_steps": 169, "total_steps": 1200, "loss": 0.2052, "lr": 4.7592731634224966e-05, "epoch": 2.7808930425752854, "percentage": 14.08, "elapsed_time": "1:34:55", "remaining_time": "9:39:07", "throughput": 2161.38, "total_tokens": 12310544} {"current_steps": 170, "total_steps": 1200, "loss": 0.2309, "lr": 4.756463210874652e-05, "epoch": 2.797507788161994, "percentage": 14.17, "elapsed_time": "1:35:38", "remaining_time": "9:39:31", "throughput": 2160.69, "total_tokens": 12400160} {"current_steps": 171, "total_steps": 1200, "loss": 0.2544, "lr": 4.753637792780614e-05, "epoch": 2.814122533748702, "percentage": 14.25, "elapsed_time": "1:36:15", "remaining_time": "9:39:11", "throughput": 2161.08, "total_tokens": 12480432} {"current_steps": 172, "total_steps": 1200, "loss": 0.2434, "lr": 4.7507969285054845e-05, "epoch": 2.83073727933541, "percentage": 14.33, "elapsed_time": "1:36:53", "remaining_time": "9:39:08", "throughput": 2161.73, "total_tokens": 12568064} {"current_steps": 173, "total_steps": 1200, "loss": 0.2417, "lr": 4.7479406375202264e-05, "epoch": 2.8473520249221185, "percentage": 14.42, "elapsed_time": "1:37:29", "remaining_time": "9:38:47", "throughput": 2161.98, "total_tokens": 12647400} {"current_steps": 174, "total_steps": 1200, "loss": 0.2121, "lr": 4.745068939401539e-05, "epoch": 2.8639667705088265, "percentage": 14.5, "elapsed_time": "1:37:51", "remaining_time": "9:37:02", "throughput": 2162.63, "total_tokens": 12698208} {"current_steps": 175, "total_steps": 1200, "loss": 0.2238, "lr": 4.742181853831721e-05, "epoch": 2.8805815160955346, "percentage": 14.58, "elapsed_time": "1:38:16", "remaining_time": "9:35:37", "throughput": 2163.72, "total_tokens": 12758528} {"current_steps": 176, "total_steps": 1200, "loss": 0.2333, "lr": 4.7392794005985326e-05, "epoch": 2.897196261682243, "percentage": 14.67, "elapsed_time": "1:38:54", "remaining_time": "9:35:26", "throughput": 2163.27, "total_tokens": 12837264} {"current_steps": 177, "total_steps": 1200, "loss": 0.2179, "lr": 4.7363615995950626e-05, "epoch": 2.913811007268951, "percentage": 14.75, "elapsed_time": "1:39:25", "remaining_time": "9:34:35", "throughput": 2162.99, "total_tokens": 12902368} {"current_steps": 178, "total_steps": 1200, "loss": 0.2144, "lr": 4.733428470819594e-05, "epoch": 2.930425752855659, "percentage": 14.83, "elapsed_time": "1:40:01", "remaining_time": "9:34:15", "throughput": 2162.0, "total_tokens": 12974296} {"current_steps": 179, "total_steps": 1200, "loss": 0.2413, "lr": 4.730480034375462e-05, "epoch": 2.9470404984423677, "percentage": 14.92, "elapsed_time": "1:40:40", "remaining_time": "9:34:12", "throughput": 2161.74, "total_tokens": 13057280} {"current_steps": 180, "total_steps": 1200, "loss": 0.294, "lr": 4.72751631047092e-05, "epoch": 2.9636552440290758, "percentage": 15.0, "elapsed_time": "1:41:23", "remaining_time": "9:34:35", "throughput": 2162.76, "total_tokens": 13158232} {"current_steps": 181, "total_steps": 1200, "loss": 0.216, "lr": 4.7245373194189994e-05, "epoch": 2.980269989615784, "percentage": 15.08, "elapsed_time": "1:41:57", "remaining_time": "9:34:00", "throughput": 2162.59, "total_tokens": 13229840} {"current_steps": 182, "total_steps": 1200, "loss": 0.2384, "lr": 4.7215430816373726e-05, "epoch": 2.9968847352024923, "percentage": 15.17, "elapsed_time": "1:42:28", "remaining_time": "9:33:10", "throughput": 2162.59, "total_tokens": 13296520} {"current_steps": 183, "total_steps": 1200, "loss": 0.1459, "lr": 4.718533617648209e-05, "epoch": 3.0, "percentage": 15.25, "elapsed_time": "1:42:34", "remaining_time": "9:30:03", "throughput": 2162.57, "total_tokens": 13309672} {"current_steps": 184, "total_steps": 1200, "loss": 0.1985, "lr": 4.715508948078037e-05, "epoch": 3.016614745586708, "percentage": 15.33, "elapsed_time": "1:43:01", "remaining_time": "9:28:50", "throughput": 2163.29, "total_tokens": 13371544} {"current_steps": 185, "total_steps": 1200, "loss": 0.1856, "lr": 4.712469093657605e-05, "epoch": 3.0332294911734166, "percentage": 15.42, "elapsed_time": "1:43:28", "remaining_time": "9:27:42", "throughput": 2163.68, "total_tokens": 13432984} {"current_steps": 186, "total_steps": 1200, "loss": 0.2385, "lr": 4.709414075221734e-05, "epoch": 3.0498442367601246, "percentage": 15.5, "elapsed_time": "1:43:59", "remaining_time": "9:26:54", "throughput": 2163.68, "total_tokens": 13500016} {"current_steps": 187, "total_steps": 1200, "loss": 0.2227, "lr": 4.706343913709178e-05, "epoch": 3.0664589823468327, "percentage": 15.58, "elapsed_time": "1:44:35", "remaining_time": "9:26:32", "throughput": 2164.07, "total_tokens": 13579672} {"current_steps": 188, "total_steps": 1200, "loss": 0.2045, "lr": 4.70325863016248e-05, "epoch": 3.083073727933541, "percentage": 15.67, "elapsed_time": "1:44:59", "remaining_time": "9:25:09", "throughput": 2163.82, "total_tokens": 13630704} {"current_steps": 189, "total_steps": 1200, "loss": 0.2648, "lr": 4.7001582457278304e-05, "epoch": 3.0996884735202492, "percentage": 15.75, "elapsed_time": "1:45:30", "remaining_time": "9:24:21", "throughput": 2163.52, "total_tokens": 13695472} {"current_steps": 190, "total_steps": 1200, "loss": 0.22, "lr": 4.697042781654913e-05, "epoch": 3.1163032191069573, "percentage": 15.83, "elapsed_time": "1:46:04", "remaining_time": "9:23:50", "throughput": 2163.32, "total_tokens": 13767792} {"current_steps": 191, "total_steps": 1200, "loss": 0.2667, "lr": 4.693912259296773e-05, "epoch": 3.132917964693666, "percentage": 15.92, "elapsed_time": "1:46:42", "remaining_time": "9:23:40", "throughput": 2164.52, "total_tokens": 13857352} {"current_steps": 192, "total_steps": 1200, "loss": 0.2154, "lr": 4.690766700109659e-05, "epoch": 3.149532710280374, "percentage": 16.0, "elapsed_time": "1:47:19", "remaining_time": "9:23:26", "throughput": 2164.82, "total_tokens": 13939928} {"current_steps": 193, "total_steps": 1200, "loss": 0.1963, "lr": 4.687606125652882e-05, "epoch": 3.166147455867082, "percentage": 16.08, "elapsed_time": "1:47:58", "remaining_time": "9:23:23", "throughput": 2163.69, "total_tokens": 14017936} {"current_steps": 194, "total_steps": 1200, "loss": 0.1862, "lr": 4.684430557588664e-05, "epoch": 3.1827622014537904, "percentage": 16.17, "elapsed_time": "1:48:24", "remaining_time": "9:22:10", "throughput": 2163.67, "total_tokens": 14074176} {"current_steps": 195, "total_steps": 1200, "loss": 0.2576, "lr": 4.681240017681993e-05, "epoch": 3.1993769470404985, "percentage": 16.25, "elapsed_time": "1:49:05", "remaining_time": "9:22:16", "throughput": 2164.35, "total_tokens": 14167656} {"current_steps": 196, "total_steps": 1200, "loss": 0.1813, "lr": 4.678034527800474e-05, "epoch": 3.2159916926272065, "percentage": 16.33, "elapsed_time": "1:49:39", "remaining_time": "9:21:45", "throughput": 2163.52, "total_tokens": 14235800} {"current_steps": 197, "total_steps": 1200, "loss": 0.1741, "lr": 4.674814109914174e-05, "epoch": 3.232606438213915, "percentage": 16.42, "elapsed_time": "1:50:10", "remaining_time": "9:20:54", "throughput": 2163.55, "total_tokens": 14301272} {"current_steps": 198, "total_steps": 1200, "loss": 0.2186, "lr": 4.671578786095478e-05, "epoch": 3.249221183800623, "percentage": 16.5, "elapsed_time": "1:50:30", "remaining_time": "9:19:15", "throughput": 2163.74, "total_tokens": 14347352} {"current_steps": 199, "total_steps": 1200, "loss": 0.2892, "lr": 4.668328578518933e-05, "epoch": 3.265835929387331, "percentage": 16.58, "elapsed_time": "1:51:11", "remaining_time": "9:19:18", "throughput": 2163.65, "total_tokens": 14434600} {"current_steps": 200, "total_steps": 1200, "loss": 0.2014, "lr": 4.665063509461097e-05, "epoch": 3.2824506749740396, "percentage": 16.67, "elapsed_time": "1:51:33", "remaining_time": "9:17:46", "throughput": 2163.99, "total_tokens": 14484104} {"current_steps": 201, "total_steps": 1200, "loss": 0.2158, "lr": 4.661783601300388e-05, "epoch": 3.2990654205607477, "percentage": 16.75, "elapsed_time": "1:52:12", "remaining_time": "9:17:43", "throughput": 2163.58, "total_tokens": 14567152} {"current_steps": 202, "total_steps": 1200, "loss": 0.2578, "lr": 4.6584888765169296e-05, "epoch": 3.3156801661474558, "percentage": 16.83, "elapsed_time": "1:52:50", "remaining_time": "9:17:30", "throughput": 2163.34, "total_tokens": 14647040} {"current_steps": 203, "total_steps": 1200, "loss": 0.2213, "lr": 4.6551793576923964e-05, "epoch": 3.3322949117341643, "percentage": 16.92, "elapsed_time": "1:53:30", "remaining_time": "9:17:26", "throughput": 2164.15, "total_tokens": 14738216} {"current_steps": 204, "total_steps": 1200, "loss": 0.1828, "lr": 4.65185506750986e-05, "epoch": 3.3489096573208723, "percentage": 17.0, "elapsed_time": "1:54:02", "remaining_time": "9:16:46", "throughput": 2164.64, "total_tokens": 14811216} {"current_steps": 205, "total_steps": 1200, "loss": 0.1619, "lr": 4.648516028753632e-05, "epoch": 3.3655244029075804, "percentage": 17.08, "elapsed_time": "1:54:37", "remaining_time": "9:16:21", "throughput": 2164.44, "total_tokens": 14885992} {"current_steps": 206, "total_steps": 1200, "loss": 0.2438, "lr": 4.645162264309112e-05, "epoch": 3.382139148494289, "percentage": 17.17, "elapsed_time": "1:55:12", "remaining_time": "9:15:55", "throughput": 2164.4, "total_tokens": 14961984} {"current_steps": 207, "total_steps": 1200, "loss": 0.1771, "lr": 4.6417937971626245e-05, "epoch": 3.398753894080997, "percentage": 17.25, "elapsed_time": "1:55:39", "remaining_time": "9:14:49", "throughput": 2164.59, "total_tokens": 15021240} {"current_steps": 208, "total_steps": 1200, "loss": 0.1742, "lr": 4.638410650401267e-05, "epoch": 3.415368639667705, "percentage": 17.33, "elapsed_time": "1:56:11", "remaining_time": "9:14:07", "throughput": 2164.92, "total_tokens": 15092016} {"current_steps": 209, "total_steps": 1200, "loss": 0.1725, "lr": 4.635012847212748e-05, "epoch": 3.431983385254413, "percentage": 17.42, "elapsed_time": "1:56:58", "remaining_time": "9:14:37", "throughput": 2165.55, "total_tokens": 15198192} {"current_steps": 210, "total_steps": 1200, "loss": 0.186, "lr": 4.6316004108852305e-05, "epoch": 3.4485981308411215, "percentage": 17.5, "elapsed_time": "1:57:25", "remaining_time": "9:13:34", "throughput": 2165.68, "total_tokens": 15258432} {"current_steps": 211, "total_steps": 1200, "loss": 0.2166, "lr": 4.628173364807171e-05, "epoch": 3.4652128764278296, "percentage": 17.58, "elapsed_time": "1:57:56", "remaining_time": "9:12:48", "throughput": 2166.29, "total_tokens": 15329600} {"current_steps": 212, "total_steps": 1200, "loss": 0.2038, "lr": 4.6247317324671605e-05, "epoch": 3.4818276220145377, "percentage": 17.67, "elapsed_time": "1:58:32", "remaining_time": "9:12:26", "throughput": 2166.36, "total_tokens": 15407920} {"current_steps": 213, "total_steps": 1200, "loss": 0.2017, "lr": 4.6212755374537596e-05, "epoch": 3.498442367601246, "percentage": 17.75, "elapsed_time": "1:59:05", "remaining_time": "9:11:49", "throughput": 2166.43, "total_tokens": 15479640} {"current_steps": 214, "total_steps": 1200, "loss": 0.2048, "lr": 4.617804803455344e-05, "epoch": 3.515057113187954, "percentage": 17.83, "elapsed_time": "1:59:46", "remaining_time": "9:11:49", "throughput": 2165.56, "total_tokens": 15561960} {"current_steps": 215, "total_steps": 1200, "loss": 0.2358, "lr": 4.614319554259934e-05, "epoch": 3.5316718587746623, "percentage": 17.92, "elapsed_time": "2:00:19", "remaining_time": "9:11:14", "throughput": 2166.63, "total_tokens": 15641440} {"current_steps": 216, "total_steps": 1200, "loss": 0.2374, "lr": 4.610819813755038e-05, "epoch": 3.5482866043613708, "percentage": 18.0, "elapsed_time": "2:01:00", "remaining_time": "9:11:16", "throughput": 2166.32, "total_tokens": 15728872} {"current_steps": 217, "total_steps": 1200, "loss": 0.1919, "lr": 4.607305605927487e-05, "epoch": 3.564901349948079, "percentage": 18.08, "elapsed_time": "2:01:32", "remaining_time": "9:10:32", "throughput": 2166.48, "total_tokens": 15798112} {"current_steps": 218, "total_steps": 1200, "loss": 0.2583, "lr": 4.6037769548632656e-05, "epoch": 3.581516095534787, "percentage": 18.17, "elapsed_time": "2:02:05", "remaining_time": "9:09:56", "throughput": 2165.99, "total_tokens": 15865936} {"current_steps": 219, "total_steps": 1200, "loss": 0.2337, "lr": 4.600233884747355e-05, "epoch": 3.5981308411214954, "percentage": 18.25, "elapsed_time": "2:02:37", "remaining_time": "9:09:17", "throughput": 2166.72, "total_tokens": 15941368} {"current_steps": 220, "total_steps": 1200, "loss": 0.1818, "lr": 4.5966764198635606e-05, "epoch": 3.6147455867082035, "percentage": 18.33, "elapsed_time": "2:03:19", "remaining_time": "9:09:19", "throughput": 2166.25, "total_tokens": 16028208} {"current_steps": 221, "total_steps": 1200, "loss": 0.1646, "lr": 4.5931045845943474e-05, "epoch": 3.6313603322949115, "percentage": 18.42, "elapsed_time": "2:03:54", "remaining_time": "9:08:53", "throughput": 2166.17, "total_tokens": 16104408} {"current_steps": 222, "total_steps": 1200, "loss": 0.3263, "lr": 4.5895184034206765e-05, "epoch": 3.64797507788162, "percentage": 18.5, "elapsed_time": "2:04:17", "remaining_time": "9:07:31", "throughput": 2166.62, "total_tokens": 16156800} {"current_steps": 223, "total_steps": 1200, "loss": 0.2636, "lr": 4.585917900921829e-05, "epoch": 3.664589823468328, "percentage": 18.58, "elapsed_time": "2:05:03", "remaining_time": "9:07:53", "throughput": 2166.58, "total_tokens": 16256712} {"current_steps": 224, "total_steps": 1200, "loss": 0.1759, "lr": 4.5823031017752485e-05, "epoch": 3.681204569055036, "percentage": 18.67, "elapsed_time": "2:05:38", "remaining_time": "9:07:25", "throughput": 2166.29, "total_tokens": 16330344} {"current_steps": 225, "total_steps": 1200, "loss": 0.196, "lr": 4.5786740307563636e-05, "epoch": 3.6978193146417446, "percentage": 18.75, "elapsed_time": "2:06:10", "remaining_time": "9:06:43", "throughput": 2166.38, "total_tokens": 16399792} {"current_steps": 226, "total_steps": 1200, "loss": 0.186, "lr": 4.575030712738419e-05, "epoch": 3.7144340602284527, "percentage": 18.83, "elapsed_time": "2:06:39", "remaining_time": "9:05:53", "throughput": 2166.68, "total_tokens": 16466368} {"current_steps": 227, "total_steps": 1200, "loss": 0.1789, "lr": 4.571373172692309e-05, "epoch": 3.7310488058151607, "percentage": 18.92, "elapsed_time": "2:07:07", "remaining_time": "9:04:53", "throughput": 2167.35, "total_tokens": 16530976} {"current_steps": 228, "total_steps": 1200, "loss": 0.1929, "lr": 4.567701435686404e-05, "epoch": 3.7476635514018692, "percentage": 19.0, "elapsed_time": "2:07:40", "remaining_time": "9:04:16", "throughput": 2167.1, "total_tokens": 16600216} {"current_steps": 229, "total_steps": 1200, "loss": 0.2268, "lr": 4.5640155268863796e-05, "epoch": 3.7642782969885773, "percentage": 19.08, "elapsed_time": "2:08:13", "remaining_time": "9:03:41", "throughput": 2167.22, "total_tokens": 16673192} {"current_steps": 230, "total_steps": 1200, "loss": 0.1716, "lr": 4.5603154715550386e-05, "epoch": 3.7808930425752854, "percentage": 19.17, "elapsed_time": "2:08:47", "remaining_time": "9:03:08", "throughput": 2166.4, "total_tokens": 16739912} {"current_steps": 231, "total_steps": 1200, "loss": 0.1844, "lr": 4.55660129505215e-05, "epoch": 3.797507788161994, "percentage": 19.25, "elapsed_time": "2:09:28", "remaining_time": "9:03:08", "throughput": 2166.94, "total_tokens": 16834632} {"current_steps": 232, "total_steps": 1200, "loss": 0.1899, "lr": 4.5528730228342605e-05, "epoch": 3.814122533748702, "percentage": 19.33, "elapsed_time": "2:10:03", "remaining_time": "9:02:37", "throughput": 2167.7, "total_tokens": 16914728} {"current_steps": 233, "total_steps": 1200, "loss": 0.2214, "lr": 4.549130680454532e-05, "epoch": 3.83073727933541, "percentage": 19.42, "elapsed_time": "2:10:51", "remaining_time": "9:03:06", "throughput": 2166.96, "total_tokens": 17014304} {"current_steps": 234, "total_steps": 1200, "loss": 0.2062, "lr": 4.545374293562559e-05, "epoch": 3.8473520249221185, "percentage": 19.5, "elapsed_time": "2:11:32", "remaining_time": "9:03:03", "throughput": 2167.32, "total_tokens": 17106664} {"current_steps": 235, "total_steps": 1200, "loss": 0.2016, "lr": 4.541603887904198e-05, "epoch": 3.8639667705088265, "percentage": 19.58, "elapsed_time": "2:12:13", "remaining_time": "9:02:58", "throughput": 2167.22, "total_tokens": 17193744} {"current_steps": 236, "total_steps": 1200, "loss": 0.1992, "lr": 4.537819489321386e-05, "epoch": 3.8805815160955346, "percentage": 19.67, "elapsed_time": "2:12:40", "remaining_time": "9:01:58", "throughput": 2167.44, "total_tokens": 17254656} {"current_steps": 237, "total_steps": 1200, "loss": 0.1961, "lr": 4.534021123751968e-05, "epoch": 3.897196261682243, "percentage": 19.75, "elapsed_time": "2:13:11", "remaining_time": "9:01:11", "throughput": 2168.07, "total_tokens": 17325896} {"current_steps": 238, "total_steps": 1200, "loss": 0.2302, "lr": 4.5302088172295156e-05, "epoch": 3.913811007268951, "percentage": 19.83, "elapsed_time": "2:13:44", "remaining_time": "9:00:33", "throughput": 2167.75, "total_tokens": 17394424} {"current_steps": 239, "total_steps": 1200, "loss": 0.1846, "lr": 4.526382595883152e-05, "epoch": 3.930425752855659, "percentage": 19.92, "elapsed_time": "2:14:10", "remaining_time": "8:59:31", "throughput": 2168.3, "total_tokens": 17456352} {"current_steps": 240, "total_steps": 1200, "loss": 0.1879, "lr": 4.522542485937369e-05, "epoch": 3.9470404984423677, "percentage": 20.0, "elapsed_time": "2:14:43", "remaining_time": "8:58:53", "throughput": 2167.28, "total_tokens": 17519168} {"current_steps": 241, "total_steps": 1200, "loss": 0.206, "lr": 4.51868851371185e-05, "epoch": 3.9636552440290758, "percentage": 20.08, "elapsed_time": "2:15:14", "remaining_time": "8:58:08", "throughput": 2167.2, "total_tokens": 17585144} {"current_steps": 242, "total_steps": 1200, "loss": 0.1676, "lr": 4.5148207056212896e-05, "epoch": 3.980269989615784, "percentage": 20.17, "elapsed_time": "2:15:46", "remaining_time": "8:57:29", "throughput": 2168.05, "total_tokens": 17662024} {"current_steps": 243, "total_steps": 1200, "loss": 0.1961, "lr": 4.5109390881752114e-05, "epoch": 3.9968847352024923, "percentage": 20.25, "elapsed_time": "2:16:14", "remaining_time": "8:56:33", "throughput": 2168.25, "total_tokens": 17724360} {"current_steps": 244, "total_steps": 1200, "loss": 0.185, "lr": 4.5070436879777865e-05, "epoch": 4.0, "percentage": 20.33, "elapsed_time": "2:16:25", "remaining_time": "8:54:30", "throughput": 2168.02, "total_tokens": 17746200} {"current_steps": 245, "total_steps": 1200, "loss": 0.1674, "lr": 4.503134531727652e-05, "epoch": 4.0166147455867085, "percentage": 20.42, "elapsed_time": "2:17:01", "remaining_time": "8:54:08", "throughput": 2168.69, "total_tokens": 17830760} {"current_steps": 246, "total_steps": 1200, "loss": 0.1739, "lr": 4.499211646217727e-05, "epoch": 4.033229491173416, "percentage": 20.5, "elapsed_time": "2:17:33", "remaining_time": "8:53:29", "throughput": 2169.11, "total_tokens": 17903840} {"current_steps": 247, "total_steps": 1200, "loss": 0.1753, "lr": 4.495275058335029e-05, "epoch": 4.049844236760125, "percentage": 20.58, "elapsed_time": "2:18:14", "remaining_time": "8:53:23", "throughput": 2168.94, "total_tokens": 17990448} {"current_steps": 248, "total_steps": 1200, "loss": 0.1896, "lr": 4.491324795060491e-05, "epoch": 4.066458982346833, "percentage": 20.67, "elapsed_time": "2:18:49", "remaining_time": "8:52:54", "throughput": 2169.35, "total_tokens": 18069520} {"current_steps": 249, "total_steps": 1200, "loss": 0.1688, "lr": 4.487360883468775e-05, "epoch": 4.083073727933541, "percentage": 20.75, "elapsed_time": "2:19:17", "remaining_time": "8:51:58", "throughput": 2169.31, "total_tokens": 18129128} {"current_steps": 250, "total_steps": 1200, "loss": 0.1928, "lr": 4.4833833507280884e-05, "epoch": 4.099688473520249, "percentage": 20.83, "elapsed_time": "2:19:49", "remaining_time": "8:51:20", "throughput": 2169.64, "total_tokens": 18202472} {"current_steps": 251, "total_steps": 1200, "loss": 0.1737, "lr": 4.4793922240999933e-05, "epoch": 4.116303219106958, "percentage": 20.92, "elapsed_time": "2:20:19", "remaining_time": "8:50:33", "throughput": 2169.63, "total_tokens": 18267232} {"current_steps": 252, "total_steps": 1200, "loss": 0.1883, "lr": 4.4753875309392266e-05, "epoch": 4.132917964693665, "percentage": 21.0, "elapsed_time": "2:20:47", "remaining_time": "8:49:36", "throughput": 2169.42, "total_tokens": 18325216} {"current_steps": 253, "total_steps": 1200, "loss": 0.2042, "lr": 4.471369298693505e-05, "epoch": 4.149532710280374, "percentage": 21.08, "elapsed_time": "2:21:25", "remaining_time": "8:49:20", "throughput": 2169.2, "total_tokens": 18406184} {"current_steps": 254, "total_steps": 1200, "loss": 0.1656, "lr": 4.467337554903344e-05, "epoch": 4.166147455867082, "percentage": 21.17, "elapsed_time": "2:21:57", "remaining_time": "8:48:43", "throughput": 2169.68, "total_tokens": 18481056} {"current_steps": 255, "total_steps": 1200, "loss": 0.1454, "lr": 4.463292327201862e-05, "epoch": 4.18276220145379, "percentage": 21.25, "elapsed_time": "2:22:31", "remaining_time": "8:48:11", "throughput": 2169.73, "total_tokens": 18554864} {"current_steps": 256, "total_steps": 1200, "loss": 0.2039, "lr": 4.4592336433146e-05, "epoch": 4.1993769470404985, "percentage": 21.33, "elapsed_time": "2:22:58", "remaining_time": "8:47:13", "throughput": 2169.63, "total_tokens": 18612120} {"current_steps": 257, "total_steps": 1200, "loss": 0.2112, "lr": 4.4551615310593195e-05, "epoch": 4.215991692627207, "percentage": 21.42, "elapsed_time": "2:23:45", "remaining_time": "8:47:29", "throughput": 2169.21, "total_tokens": 18710408} {"current_steps": 258, "total_steps": 1200, "loss": 0.1831, "lr": 4.451076018345825e-05, "epoch": 4.232606438213915, "percentage": 21.5, "elapsed_time": "2:24:12", "remaining_time": "8:46:31", "throughput": 2169.25, "total_tokens": 18769400} {"current_steps": 259, "total_steps": 1200, "loss": 0.1722, "lr": 4.4469771331757604e-05, "epoch": 4.249221183800623, "percentage": 21.58, "elapsed_time": "2:24:48", "remaining_time": "8:46:05", "throughput": 2169.58, "total_tokens": 18849704} {"current_steps": 260, "total_steps": 1200, "loss": 0.1981, "lr": 4.442864903642428e-05, "epoch": 4.265835929387332, "percentage": 21.67, "elapsed_time": "2:25:33", "remaining_time": "8:46:13", "throughput": 2169.13, "total_tokens": 18943328} {"current_steps": 261, "total_steps": 1200, "loss": 0.2014, "lr": 4.4387393579305865e-05, "epoch": 4.282450674974039, "percentage": 21.75, "elapsed_time": "2:26:09", "remaining_time": "8:45:51", "throughput": 2169.08, "total_tokens": 19022536} {"current_steps": 262, "total_steps": 1200, "loss": 0.167, "lr": 4.434600524316266e-05, "epoch": 4.299065420560748, "percentage": 21.83, "elapsed_time": "2:26:42", "remaining_time": "8:45:13", "throughput": 2168.63, "total_tokens": 19089200} {"current_steps": 263, "total_steps": 1200, "loss": 0.2747, "lr": 4.430448431166567e-05, "epoch": 4.315680166147456, "percentage": 21.92, "elapsed_time": "2:27:19", "remaining_time": "8:44:52", "throughput": 2168.81, "total_tokens": 19171216} {"current_steps": 264, "total_steps": 1200, "loss": 0.1508, "lr": 4.426283106939474e-05, "epoch": 4.332294911734164, "percentage": 22.0, "elapsed_time": "2:28:07", "remaining_time": "8:45:11", "throughput": 2168.35, "total_tokens": 19271872} {"current_steps": 265, "total_steps": 1200, "loss": 0.2585, "lr": 4.4221045801836494e-05, "epoch": 4.348909657320872, "percentage": 22.08, "elapsed_time": "2:28:38", "remaining_time": "8:44:28", "throughput": 2168.79, "total_tokens": 19342984} {"current_steps": 266, "total_steps": 1200, "loss": 0.1789, "lr": 4.41791287953825e-05, "epoch": 4.365524402907581, "percentage": 22.17, "elapsed_time": "2:28:59", "remaining_time": "8:43:10", "throughput": 2169.14, "total_tokens": 19391640} {"current_steps": 267, "total_steps": 1200, "loss": 0.1953, "lr": 4.4137080337327205e-05, "epoch": 4.382139148494288, "percentage": 22.25, "elapsed_time": "2:29:34", "remaining_time": "8:42:39", "throughput": 2168.78, "total_tokens": 19463232} {"current_steps": 268, "total_steps": 1200, "loss": 0.1752, "lr": 4.4094900715866064e-05, "epoch": 4.398753894080997, "percentage": 22.33, "elapsed_time": "2:30:00", "remaining_time": "8:41:41", "throughput": 2169.1, "total_tokens": 19523728} {"current_steps": 269, "total_steps": 1200, "loss": 0.1904, "lr": 4.4052590220093446e-05, "epoch": 4.415368639667705, "percentage": 22.42, "elapsed_time": "2:30:34", "remaining_time": "8:41:06", "throughput": 2169.43, "total_tokens": 19598960} {"current_steps": 270, "total_steps": 1200, "loss": 0.1801, "lr": 4.401014914000078e-05, "epoch": 4.431983385254413, "percentage": 22.5, "elapsed_time": "2:31:05", "remaining_time": "8:40:26", "throughput": 2169.26, "total_tokens": 19666136} {"current_steps": 271, "total_steps": 1200, "loss": 0.1798, "lr": 4.3967577766474455e-05, "epoch": 4.4485981308411215, "percentage": 22.58, "elapsed_time": "2:31:33", "remaining_time": "8:39:31", "throughput": 2169.63, "total_tokens": 19728600} {"current_steps": 272, "total_steps": 1200, "loss": 0.2221, "lr": 4.3924876391293915e-05, "epoch": 4.46521287642783, "percentage": 22.67, "elapsed_time": "2:32:07", "remaining_time": "8:39:02", "throughput": 2169.26, "total_tokens": 19801032} {"current_steps": 273, "total_steps": 1200, "loss": 0.1906, "lr": 4.3882045307129594e-05, "epoch": 4.481827622014538, "percentage": 22.75, "elapsed_time": "2:32:44", "remaining_time": "8:38:37", "throughput": 2169.95, "total_tokens": 19885496} {"current_steps": 274, "total_steps": 1200, "loss": 0.1775, "lr": 4.383908480754095e-05, "epoch": 4.498442367601246, "percentage": 22.83, "elapsed_time": "2:33:14", "remaining_time": "8:37:51", "throughput": 2170.11, "total_tokens": 19952072} {"current_steps": 275, "total_steps": 1200, "loss": 0.1593, "lr": 4.379599518697444e-05, "epoch": 4.515057113187955, "percentage": 22.92, "elapsed_time": "2:33:48", "remaining_time": "8:37:20", "throughput": 2170.12, "total_tokens": 20026536} {"current_steps": 276, "total_steps": 1200, "loss": 0.1409, "lr": 4.375277674076149e-05, "epoch": 4.531671858774662, "percentage": 23.0, "elapsed_time": "2:34:12", "remaining_time": "8:36:16", "throughput": 2170.05, "total_tokens": 20079112} {"current_steps": 277, "total_steps": 1200, "loss": 0.2701, "lr": 4.3709429765116504e-05, "epoch": 4.548286604361371, "percentage": 23.08, "elapsed_time": "2:34:41", "remaining_time": "8:35:27", "throughput": 2170.33, "total_tokens": 20144264} {"current_steps": 278, "total_steps": 1200, "loss": 0.1856, "lr": 4.366595455713479e-05, "epoch": 4.564901349948079, "percentage": 23.17, "elapsed_time": "2:35:09", "remaining_time": "8:34:36", "throughput": 2170.59, "total_tokens": 20207568} {"current_steps": 279, "total_steps": 1200, "loss": 0.2204, "lr": 4.3622351414790554e-05, "epoch": 4.581516095534787, "percentage": 23.25, "elapsed_time": "2:35:49", "remaining_time": "8:34:23", "throughput": 2170.45, "total_tokens": 20292376} {"current_steps": 280, "total_steps": 1200, "loss": 0.1397, "lr": 4.357862063693486e-05, "epoch": 4.598130841121495, "percentage": 23.33, "elapsed_time": "2:36:35", "remaining_time": "8:34:31", "throughput": 2169.41, "total_tokens": 20383048} {"current_steps": 281, "total_steps": 1200, "loss": 0.1655, "lr": 4.353476252329356e-05, "epoch": 4.614745586708204, "percentage": 23.42, "elapsed_time": "2:37:12", "remaining_time": "8:34:09", "throughput": 2169.42, "total_tokens": 20463376} {"current_steps": 282, "total_steps": 1200, "loss": 0.1511, "lr": 4.349077737446525e-05, "epoch": 4.6313603322949115, "percentage": 23.5, "elapsed_time": "2:37:45", "remaining_time": "8:33:32", "throughput": 2169.81, "total_tokens": 20537808} {"current_steps": 283, "total_steps": 1200, "loss": 0.1783, "lr": 4.344666549191921e-05, "epoch": 4.64797507788162, "percentage": 23.58, "elapsed_time": "2:38:14", "remaining_time": "8:32:45", "throughput": 2170.24, "total_tokens": 20605496} {"current_steps": 284, "total_steps": 1200, "loss": 0.2135, "lr": 4.3402427177993366e-05, "epoch": 4.6645898234683285, "percentage": 23.67, "elapsed_time": "2:38:57", "remaining_time": "8:32:40", "throughput": 2169.61, "total_tokens": 20692096} {"current_steps": 285, "total_steps": 1200, "loss": 0.1919, "lr": 4.335806273589214e-05, "epoch": 4.681204569055036, "percentage": 23.75, "elapsed_time": "2:39:30", "remaining_time": "8:32:06", "throughput": 2169.48, "total_tokens": 20762800} {"current_steps": 286, "total_steps": 1200, "loss": 0.1546, "lr": 4.3313572469684474e-05, "epoch": 4.697819314641745, "percentage": 23.83, "elapsed_time": "2:40:01", "remaining_time": "8:31:25", "throughput": 2169.56, "total_tokens": 20831584} {"current_steps": 287, "total_steps": 1200, "loss": 0.124, "lr": 4.326895668430166e-05, "epoch": 4.714434060228453, "percentage": 23.92, "elapsed_time": "2:40:34", "remaining_time": "8:30:49", "throughput": 2168.97, "total_tokens": 20897320} {"current_steps": 288, "total_steps": 1200, "loss": 0.1639, "lr": 4.3224215685535294e-05, "epoch": 4.731048805815161, "percentage": 24.0, "elapsed_time": "2:41:05", "remaining_time": "8:30:06", "throughput": 2169.23, "total_tokens": 20966136} {"current_steps": 289, "total_steps": 1200, "loss": 0.1584, "lr": 4.317934978003517e-05, "epoch": 4.747663551401869, "percentage": 24.08, "elapsed_time": "2:41:39", "remaining_time": "8:29:33", "throughput": 2168.75, "total_tokens": 21034800} {"current_steps": 290, "total_steps": 1200, "loss": 0.1918, "lr": 4.313435927530719e-05, "epoch": 4.764278296988578, "percentage": 24.17, "elapsed_time": "2:42:09", "remaining_time": "8:28:49", "throughput": 2168.58, "total_tokens": 21098672} {"current_steps": 291, "total_steps": 1200, "loss": 0.1597, "lr": 4.3089244479711236e-05, "epoch": 4.780893042575285, "percentage": 24.25, "elapsed_time": "2:42:47", "remaining_time": "8:28:30", "throughput": 2168.23, "total_tokens": 21177632} {"current_steps": 292, "total_steps": 1200, "loss": 0.1847, "lr": 4.304400570245906e-05, "epoch": 4.797507788161994, "percentage": 24.33, "elapsed_time": "2:43:14", "remaining_time": "8:27:36", "throughput": 2168.69, "total_tokens": 21240896} {"current_steps": 293, "total_steps": 1200, "loss": 0.1472, "lr": 4.299864325361217e-05, "epoch": 4.814122533748702, "percentage": 24.42, "elapsed_time": "2:43:53", "remaining_time": "8:27:21", "throughput": 2168.31, "total_tokens": 21322984} {"current_steps": 294, "total_steps": 1200, "loss": 0.1607, "lr": 4.295315744407972e-05, "epoch": 4.83073727933541, "percentage": 24.5, "elapsed_time": "2:44:24", "remaining_time": "8:26:38", "throughput": 2168.33, "total_tokens": 21389128} {"current_steps": 295, "total_steps": 1200, "loss": 0.1851, "lr": 4.290754858561637e-05, "epoch": 4.8473520249221185, "percentage": 24.58, "elapsed_time": "2:45:01", "remaining_time": "8:26:17", "throughput": 2168.26, "total_tokens": 21469912} {"current_steps": 296, "total_steps": 1200, "loss": 0.1531, "lr": 4.2861816990820084e-05, "epoch": 4.863966770508826, "percentage": 24.67, "elapsed_time": "2:45:31", "remaining_time": "8:25:32", "throughput": 2168.8, "total_tokens": 21540320} {"current_steps": 297, "total_steps": 1200, "loss": 0.1815, "lr": 4.281596297313013e-05, "epoch": 4.880581516095535, "percentage": 24.75, "elapsed_time": "2:46:08", "remaining_time": "8:25:09", "throughput": 2169.36, "total_tokens": 21626312} {"current_steps": 298, "total_steps": 1200, "loss": 0.1667, "lr": 4.2769986846824815e-05, "epoch": 4.897196261682243, "percentage": 24.83, "elapsed_time": "2:46:43", "remaining_time": "8:24:38", "throughput": 2169.53, "total_tokens": 21702792} {"current_steps": 299, "total_steps": 1200, "loss": 0.1805, "lr": 4.272388892701934e-05, "epoch": 4.913811007268951, "percentage": 24.92, "elapsed_time": "2:47:12", "remaining_time": "8:23:51", "throughput": 2170.16, "total_tokens": 21771880} {"current_steps": 300, "total_steps": 1200, "loss": 0.1653, "lr": 4.267766952966369e-05, "epoch": 4.930425752855659, "percentage": 25.0, "elapsed_time": "2:47:44", "remaining_time": "8:23:14", "throughput": 2170.36, "total_tokens": 21844024} {"current_steps": 301, "total_steps": 1200, "loss": 0.1654, "lr": 4.2631328971540444e-05, "epoch": 4.947040498442368, "percentage": 25.08, "elapsed_time": "2:48:26", "remaining_time": "8:23:04", "throughput": 2169.49, "total_tokens": 21925632} {"current_steps": 302, "total_steps": 1200, "loss": 0.1774, "lr": 4.2584867570262597e-05, "epoch": 4.963655244029075, "percentage": 25.17, "elapsed_time": "2:48:50", "remaining_time": "8:22:03", "throughput": 2169.84, "total_tokens": 21981952} {"current_steps": 303, "total_steps": 1200, "loss": 0.1452, "lr": 4.25382856442714e-05, "epoch": 4.980269989615784, "percentage": 25.25, "elapsed_time": "2:49:32", "remaining_time": "8:21:55", "throughput": 2169.56, "total_tokens": 22070440} {"current_steps": 304, "total_steps": 1200, "loss": 0.1806, "lr": 4.249158351283414e-05, "epoch": 4.996884735202492, "percentage": 25.33, "elapsed_time": "2:50:18", "remaining_time": "8:21:57", "throughput": 2169.65, "total_tokens": 22170184} {"current_steps": 305, "total_steps": 1200, "loss": 0.2115, "lr": 4.244476149604201e-05, "epoch": 5.0, "percentage": 25.42, "elapsed_time": "2:50:23", "remaining_time": "8:19:59", "throughput": 2169.7, "total_tokens": 22181856} {"current_steps": 306, "total_steps": 1200, "loss": 0.1614, "lr": 4.2397819914807856e-05, "epoch": 5.0166147455867085, "percentage": 25.5, "elapsed_time": "2:50:58", "remaining_time": "8:19:30", "throughput": 2169.62, "total_tokens": 22256808} {"current_steps": 307, "total_steps": 1200, "loss": 0.1838, "lr": 4.2350759090864046e-05, "epoch": 5.033229491173416, "percentage": 25.58, "elapsed_time": "2:51:30", "remaining_time": "8:18:52", "throughput": 2169.56, "total_tokens": 22325224} {"current_steps": 308, "total_steps": 1200, "loss": 0.1421, "lr": 4.230357934676017e-05, "epoch": 5.049844236760125, "percentage": 25.67, "elapsed_time": "2:51:59", "remaining_time": "8:18:06", "throughput": 2169.62, "total_tokens": 22389624} {"current_steps": 309, "total_steps": 1200, "loss": 0.1852, "lr": 4.225628100586093e-05, "epoch": 5.066458982346833, "percentage": 25.75, "elapsed_time": "2:52:37", "remaining_time": "8:17:45", "throughput": 2168.84, "total_tokens": 22463872} {"current_steps": 310, "total_steps": 1200, "loss": 0.1526, "lr": 4.220886439234385e-05, "epoch": 5.083073727933541, "percentage": 25.83, "elapsed_time": "2:53:00", "remaining_time": "8:16:41", "throughput": 2169.08, "total_tokens": 22515824} {"current_steps": 311, "total_steps": 1200, "loss": 0.151, "lr": 4.2161329831197095e-05, "epoch": 5.099688473520249, "percentage": 25.92, "elapsed_time": "2:53:43", "remaining_time": "8:16:36", "throughput": 2168.38, "total_tokens": 22602336} {"current_steps": 312, "total_steps": 1200, "loss": 0.142, "lr": 4.211367764821722e-05, "epoch": 5.116303219106958, "percentage": 26.0, "elapsed_time": "2:54:06", "remaining_time": "8:15:32", "throughput": 2168.65, "total_tokens": 22655176} {"current_steps": 313, "total_steps": 1200, "loss": 0.1589, "lr": 4.2065908170006955e-05, "epoch": 5.132917964693665, "percentage": 26.08, "elapsed_time": "2:54:39", "remaining_time": "8:14:56", "throughput": 2168.97, "total_tokens": 22728680} {"current_steps": 314, "total_steps": 1200, "loss": 0.1435, "lr": 4.201802172397295e-05, "epoch": 5.149532710280374, "percentage": 26.17, "elapsed_time": "2:55:13", "remaining_time": "8:14:26", "throughput": 2169.2, "total_tokens": 22806784} {"current_steps": 315, "total_steps": 1200, "loss": 0.1447, "lr": 4.197001863832355e-05, "epoch": 5.166147455867082, "percentage": 26.25, "elapsed_time": "2:55:45", "remaining_time": "8:13:48", "throughput": 2169.69, "total_tokens": 22880648} {"current_steps": 316, "total_steps": 1200, "loss": 0.1418, "lr": 4.192189924206652e-05, "epoch": 5.18276220145379, "percentage": 26.33, "elapsed_time": "2:56:15", "remaining_time": "8:13:04", "throughput": 2170.44, "total_tokens": 22953184} {"current_steps": 317, "total_steps": 1200, "loss": 0.1845, "lr": 4.187366386500683e-05, "epoch": 5.1993769470404985, "percentage": 26.42, "elapsed_time": "2:56:51", "remaining_time": "8:12:37", "throughput": 2171.06, "total_tokens": 23037392} {"current_steps": 318, "total_steps": 1200, "loss": 0.2668, "lr": 4.182531283774434e-05, "epoch": 5.215991692627207, "percentage": 26.5, "elapsed_time": "2:57:13", "remaining_time": "8:11:33", "throughput": 2171.06, "total_tokens": 23086552} {"current_steps": 319, "total_steps": 1200, "loss": 0.1567, "lr": 4.177684649167158e-05, "epoch": 5.232606438213915, "percentage": 26.58, "elapsed_time": "2:57:41", "remaining_time": "8:10:44", "throughput": 2171.66, "total_tokens": 23153152} {"current_steps": 320, "total_steps": 1200, "loss": 0.1617, "lr": 4.172826515897146e-05, "epoch": 5.249221183800623, "percentage": 26.67, "elapsed_time": "2:58:20", "remaining_time": "8:10:27", "throughput": 2171.88, "total_tokens": 23240928} {"current_steps": 321, "total_steps": 1200, "loss": 0.1573, "lr": 4.1679569172614996e-05, "epoch": 5.265835929387332, "percentage": 26.75, "elapsed_time": "2:58:59", "remaining_time": "8:10:07", "throughput": 2171.99, "total_tokens": 23325912} {"current_steps": 322, "total_steps": 1200, "loss": 0.1738, "lr": 4.163075886635902e-05, "epoch": 5.282450674974039, "percentage": 26.83, "elapsed_time": "2:59:32", "remaining_time": "8:09:33", "throughput": 2172.41, "total_tokens": 23401952} {"current_steps": 323, "total_steps": 1200, "loss": 0.1433, "lr": 4.1581834574743915e-05, "epoch": 5.299065420560748, "percentage": 26.92, "elapsed_time": "2:59:58", "remaining_time": "8:08:40", "throughput": 2172.83, "total_tokens": 23463760} {"current_steps": 324, "total_steps": 1200, "loss": 0.1511, "lr": 4.1532796633091296e-05, "epoch": 5.315680166147456, "percentage": 27.0, "elapsed_time": "3:00:31", "remaining_time": "8:08:04", "throughput": 2172.9, "total_tokens": 23535272} {"current_steps": 325, "total_steps": 1200, "loss": 0.1296, "lr": 4.148364537750172e-05, "epoch": 5.332294911734164, "percentage": 27.08, "elapsed_time": "3:01:05", "remaining_time": "8:07:33", "throughput": 2172.68, "total_tokens": 23607752} {"current_steps": 326, "total_steps": 1200, "loss": 0.142, "lr": 4.14343811448524e-05, "epoch": 5.348909657320872, "percentage": 27.17, "elapsed_time": "3:01:32", "remaining_time": "8:06:42", "throughput": 2173.51, "total_tokens": 23674872} {"current_steps": 327, "total_steps": 1200, "loss": 0.1679, "lr": 4.138500427279485e-05, "epoch": 5.365524402907581, "percentage": 27.25, "elapsed_time": "3:01:58", "remaining_time": "8:05:50", "throughput": 2173.91, "total_tokens": 23736384} {"current_steps": 328, "total_steps": 1200, "loss": 0.1346, "lr": 4.133551509975264e-05, "epoch": 5.382139148494288, "percentage": 27.33, "elapsed_time": "3:02:47", "remaining_time": "8:05:57", "throughput": 2173.27, "total_tokens": 23835000} {"current_steps": 329, "total_steps": 1200, "loss": 0.1364, "lr": 4.128591396491901e-05, "epoch": 5.398753894080997, "percentage": 27.42, "elapsed_time": "3:03:23", "remaining_time": "8:05:31", "throughput": 2173.12, "total_tokens": 23912552} {"current_steps": 330, "total_steps": 1200, "loss": 0.1719, "lr": 4.123620120825459e-05, "epoch": 5.415368639667705, "percentage": 27.5, "elapsed_time": "3:03:58", "remaining_time": "8:05:01", "throughput": 2173.07, "total_tokens": 23987368} {"current_steps": 331, "total_steps": 1200, "loss": 0.1468, "lr": 4.118637717048506e-05, "epoch": 5.431983385254413, "percentage": 27.58, "elapsed_time": "3:04:24", "remaining_time": "8:04:09", "throughput": 2173.62, "total_tokens": 24050848} {"current_steps": 332, "total_steps": 1200, "loss": 0.1418, "lr": 4.113644219309877e-05, "epoch": 5.4485981308411215, "percentage": 27.67, "elapsed_time": "3:05:10", "remaining_time": "8:04:08", "throughput": 2173.24, "total_tokens": 24146104} {"current_steps": 333, "total_steps": 1200, "loss": 0.1502, "lr": 4.1086396618344476e-05, "epoch": 5.46521287642783, "percentage": 27.75, "elapsed_time": "3:05:31", "remaining_time": "8:03:02", "throughput": 2173.43, "total_tokens": 24194184} {"current_steps": 334, "total_steps": 1200, "loss": 0.1571, "lr": 4.1036240789228954e-05, "epoch": 5.481827622014538, "percentage": 27.83, "elapsed_time": "3:06:09", "remaining_time": "8:02:41", "throughput": 2173.27, "total_tokens": 24275368} {"current_steps": 335, "total_steps": 1200, "loss": 0.1607, "lr": 4.098597504951462e-05, "epoch": 5.498442367601246, "percentage": 27.92, "elapsed_time": "3:06:32", "remaining_time": "8:01:39", "throughput": 2173.73, "total_tokens": 24329192} {"current_steps": 336, "total_steps": 1200, "loss": 0.1453, "lr": 4.093559974371725e-05, "epoch": 5.515057113187955, "percentage": 28.0, "elapsed_time": "3:07:13", "remaining_time": "8:01:26", "throughput": 2174.46, "total_tokens": 24426696} {"current_steps": 337, "total_steps": 1200, "loss": 0.1411, "lr": 4.088511521710352e-05, "epoch": 5.531671858774662, "percentage": 28.08, "elapsed_time": "3:07:55", "remaining_time": "8:01:14", "throughput": 2174.12, "total_tokens": 24514344} {"current_steps": 338, "total_steps": 1200, "loss": 0.1467, "lr": 4.083452181568875e-05, "epoch": 5.548286604361371, "percentage": 28.17, "elapsed_time": "3:08:24", "remaining_time": "8:00:30", "throughput": 2174.7, "total_tokens": 24584464} {"current_steps": 339, "total_steps": 1200, "loss": 0.1304, "lr": 4.0783819886234445e-05, "epoch": 5.564901349948079, "percentage": 28.25, "elapsed_time": "3:08:59", "remaining_time": "8:00:01", "throughput": 2174.7, "total_tokens": 24660600} {"current_steps": 340, "total_steps": 1200, "loss": 0.1374, "lr": 4.073300977624594e-05, "epoch": 5.581516095534787, "percentage": 28.33, "elapsed_time": "3:09:24", "remaining_time": "7:59:06", "throughput": 2174.85, "total_tokens": 24717088} {"current_steps": 341, "total_steps": 1200, "loss": 0.1519, "lr": 4.068209183397004e-05, "epoch": 5.598130841121495, "percentage": 28.42, "elapsed_time": "3:09:49", "remaining_time": "7:58:10", "throughput": 2175.28, "total_tokens": 24775352} {"current_steps": 342, "total_steps": 1200, "loss": 0.1409, "lr": 4.063106640839264e-05, "epoch": 5.614745586708204, "percentage": 28.5, "elapsed_time": "3:10:32", "remaining_time": "7:58:00", "throughput": 2174.6, "total_tokens": 24860072} {"current_steps": 343, "total_steps": 1200, "loss": 0.1393, "lr": 4.057993384923626e-05, "epoch": 5.6313603322949115, "percentage": 28.58, "elapsed_time": "3:11:14", "remaining_time": "7:57:50", "throughput": 2174.13, "total_tokens": 24947856} {"current_steps": 344, "total_steps": 1200, "loss": 0.1539, "lr": 4.052869450695776e-05, "epoch": 5.64797507788162, "percentage": 28.67, "elapsed_time": "3:11:51", "remaining_time": "7:57:24", "throughput": 2173.98, "total_tokens": 25024992} {"current_steps": 345, "total_steps": 1200, "loss": 0.1522, "lr": 4.047734873274586e-05, "epoch": 5.6645898234683285, "percentage": 28.75, "elapsed_time": "3:12:22", "remaining_time": "7:56:45", "throughput": 2173.86, "total_tokens": 25092248} {"current_steps": 346, "total_steps": 1200, "loss": 0.1493, "lr": 4.042589687851872e-05, "epoch": 5.681204569055036, "percentage": 28.83, "elapsed_time": "3:12:58", "remaining_time": "7:56:18", "throughput": 2173.91, "total_tokens": 25170496} {"current_steps": 347, "total_steps": 1200, "loss": 0.1529, "lr": 4.037433929692161e-05, "epoch": 5.697819314641745, "percentage": 28.92, "elapsed_time": "3:13:41", "remaining_time": "7:56:08", "throughput": 2174.27, "total_tokens": 25268720} {"current_steps": 348, "total_steps": 1200, "loss": 0.1499, "lr": 4.0322676341324415e-05, "epoch": 5.714434060228453, "percentage": 29.0, "elapsed_time": "3:14:09", "remaining_time": "7:55:21", "throughput": 2174.52, "total_tokens": 25332688} {"current_steps": 349, "total_steps": 1200, "loss": 0.173, "lr": 4.027090836581925e-05, "epoch": 5.731048805815161, "percentage": 29.08, "elapsed_time": "3:14:45", "remaining_time": "7:54:55", "throughput": 2174.73, "total_tokens": 25413904} {"current_steps": 350, "total_steps": 1200, "loss": 0.1531, "lr": 4.021903572521802e-05, "epoch": 5.747663551401869, "percentage": 29.17, "elapsed_time": "3:15:28", "remaining_time": "7:54:43", "throughput": 2174.48, "total_tokens": 25503720} {"current_steps": 351, "total_steps": 1200, "loss": 0.1615, "lr": 4.0167058775049996e-05, "epoch": 5.764278296988578, "percentage": 29.25, "elapsed_time": "3:15:55", "remaining_time": "7:53:53", "throughput": 2175.09, "total_tokens": 25568560} {"current_steps": 352, "total_steps": 1200, "loss": 0.1452, "lr": 4.011497787155938e-05, "epoch": 5.780893042575285, "percentage": 29.33, "elapsed_time": "3:16:25", "remaining_time": "7:53:12", "throughput": 2175.14, "total_tokens": 25635184} {"current_steps": 353, "total_steps": 1200, "loss": 0.148, "lr": 4.006279337170283e-05, "epoch": 5.797507788161994, "percentage": 29.42, "elapsed_time": "3:17:04", "remaining_time": "7:52:51", "throughput": 2175.14, "total_tokens": 25719768} {"current_steps": 354, "total_steps": 1200, "loss": 0.1446, "lr": 4.0010505633147106e-05, "epoch": 5.814122533748702, "percentage": 29.5, "elapsed_time": "3:17:37", "remaining_time": "7:52:17", "throughput": 2175.45, "total_tokens": 25795016} {"current_steps": 355, "total_steps": 1200, "loss": 0.1297, "lr": 3.995811501426648e-05, "epoch": 5.83073727933541, "percentage": 29.58, "elapsed_time": "3:18:10", "remaining_time": "7:51:41", "throughput": 2175.18, "total_tokens": 25863184} {"current_steps": 356, "total_steps": 1200, "loss": 0.1479, "lr": 3.99056218741404e-05, "epoch": 5.8473520249221185, "percentage": 29.67, "elapsed_time": "3:18:41", "remaining_time": "7:51:03", "throughput": 2175.55, "total_tokens": 25935752} {"current_steps": 357, "total_steps": 1200, "loss": 0.1466, "lr": 3.985302657255097e-05, "epoch": 5.863966770508826, "percentage": 29.75, "elapsed_time": "3:19:07", "remaining_time": "7:50:11", "throughput": 2175.9, "total_tokens": 25995760} {"current_steps": 358, "total_steps": 1200, "loss": 0.1297, "lr": 3.980032946998049e-05, "epoch": 5.880581516095535, "percentage": 29.83, "elapsed_time": "3:19:37", "remaining_time": "7:49:29", "throughput": 2175.93, "total_tokens": 26061240} {"current_steps": 359, "total_steps": 1200, "loss": 0.1421, "lr": 3.974753092760901e-05, "epoch": 5.897196261682243, "percentage": 29.92, "elapsed_time": "3:20:08", "remaining_time": "7:48:51", "throughput": 2176.04, "total_tokens": 26131024} {"current_steps": 360, "total_steps": 1200, "loss": 0.1737, "lr": 3.969463130731183e-05, "epoch": 5.913811007268951, "percentage": 30.0, "elapsed_time": "3:20:53", "remaining_time": "7:48:45", "throughput": 2176.38, "total_tokens": 26233672} {"current_steps": 361, "total_steps": 1200, "loss": 0.1153, "lr": 3.964163097165702e-05, "epoch": 5.930425752855659, "percentage": 30.08, "elapsed_time": "3:21:27", "remaining_time": "7:48:13", "throughput": 2176.01, "total_tokens": 26303488} {"current_steps": 362, "total_steps": 1200, "loss": 0.1347, "lr": 3.958853028390294e-05, "epoch": 5.947040498442368, "percentage": 30.17, "elapsed_time": "3:22:03", "remaining_time": "7:47:44", "throughput": 2175.81, "total_tokens": 26377768} {"current_steps": 363, "total_steps": 1200, "loss": 0.2736, "lr": 3.953532960799577e-05, "epoch": 5.963655244029075, "percentage": 30.25, "elapsed_time": "3:22:28", "remaining_time": "7:46:52", "throughput": 2176.01, "total_tokens": 26435984} {"current_steps": 364, "total_steps": 1200, "loss": 0.1563, "lr": 3.948202930856697e-05, "epoch": 5.980269989615784, "percentage": 30.33, "elapsed_time": "3:23:03", "remaining_time": "7:46:21", "throughput": 2176.22, "total_tokens": 26513960} {"current_steps": 365, "total_steps": 1200, "loss": 0.1361, "lr": 3.942862975093085e-05, "epoch": 5.996884735202492, "percentage": 30.42, "elapsed_time": "3:23:43", "remaining_time": "7:46:02", "throughput": 2176.11, "total_tokens": 26599064} {"current_steps": 366, "total_steps": 1200, "loss": 0.1849, "lr": 3.937513130108197e-05, "epoch": 6.0, "percentage": 30.5, "elapsed_time": "3:23:51", "remaining_time": "7:44:32", "throughput": 2176.07, "total_tokens": 26617264} {"current_steps": 367, "total_steps": 1200, "loss": 0.1452, "lr": 3.9321534325692726e-05, "epoch": 6.0166147455867085, "percentage": 30.58, "elapsed_time": "3:24:36", "remaining_time": "7:44:24", "throughput": 2176.27, "total_tokens": 26717024} {"current_steps": 368, "total_steps": 1200, "loss": 0.1361, "lr": 3.92678391921108e-05, "epoch": 6.033229491173416, "percentage": 30.67, "elapsed_time": "3:25:10", "remaining_time": "7:43:51", "throughput": 2176.1, "total_tokens": 26788120} {"current_steps": 369, "total_steps": 1200, "loss": 0.1537, "lr": 3.92140462683566e-05, "epoch": 6.049844236760125, "percentage": 30.75, "elapsed_time": "3:25:40", "remaining_time": "7:43:10", "throughput": 2176.09, "total_tokens": 26853760} {"current_steps": 370, "total_steps": 1200, "loss": 0.1354, "lr": 3.916015592312082e-05, "epoch": 6.066458982346833, "percentage": 30.83, "elapsed_time": "3:26:12", "remaining_time": "7:42:33", "throughput": 2176.18, "total_tokens": 26923848} {"current_steps": 371, "total_steps": 1200, "loss": 0.1233, "lr": 3.9106168525761855e-05, "epoch": 6.083073727933541, "percentage": 30.92, "elapsed_time": "3:26:35", "remaining_time": "7:41:38", "throughput": 2176.24, "total_tokens": 26976184} {"current_steps": 372, "total_steps": 1200, "loss": 0.125, "lr": 3.905208444630327e-05, "epoch": 6.099688473520249, "percentage": 31.0, "elapsed_time": "3:27:15", "remaining_time": "7:41:19", "throughput": 2176.46, "total_tokens": 27065712} {"current_steps": 373, "total_steps": 1200, "loss": 0.1475, "lr": 3.899790405543129e-05, "epoch": 6.116303219106958, "percentage": 31.08, "elapsed_time": "3:27:56", "remaining_time": "7:41:01", "throughput": 2175.8, "total_tokens": 27145472} {"current_steps": 374, "total_steps": 1200, "loss": 0.1235, "lr": 3.894362772449226e-05, "epoch": 6.132917964693665, "percentage": 31.17, "elapsed_time": "3:28:38", "remaining_time": "7:40:47", "throughput": 2175.52, "total_tokens": 27233904} {"current_steps": 375, "total_steps": 1200, "loss": 0.1117, "lr": 3.888925582549006e-05, "epoch": 6.149532710280374, "percentage": 31.25, "elapsed_time": "3:29:13", "remaining_time": "7:40:18", "throughput": 2175.53, "total_tokens": 27311512} {"current_steps": 376, "total_steps": 1200, "loss": 0.1226, "lr": 3.883478873108361e-05, "epoch": 6.166147455867082, "percentage": 31.33, "elapsed_time": "3:29:45", "remaining_time": "7:39:41", "throughput": 2176.07, "total_tokens": 27387400} {"current_steps": 377, "total_steps": 1200, "loss": 0.1295, "lr": 3.878022681458426e-05, "epoch": 6.18276220145379, "percentage": 31.42, "elapsed_time": "3:30:18", "remaining_time": "7:39:05", "throughput": 2176.35, "total_tokens": 27461280} {"current_steps": 378, "total_steps": 1200, "loss": 0.1197, "lr": 3.87255704499533e-05, "epoch": 6.1993769470404985, "percentage": 31.5, "elapsed_time": "3:31:06", "remaining_time": "7:39:04", "throughput": 2175.52, "total_tokens": 27556400} {"current_steps": 379, "total_steps": 1200, "loss": 0.1417, "lr": 3.8670820011799315e-05, "epoch": 6.215991692627207, "percentage": 31.58, "elapsed_time": "3:31:33", "remaining_time": "7:38:15", "throughput": 2175.5, "total_tokens": 27613664} {"current_steps": 380, "total_steps": 1200, "loss": 0.1565, "lr": 3.861597587537568e-05, "epoch": 6.232606438213915, "percentage": 31.67, "elapsed_time": "3:32:04", "remaining_time": "7:37:38", "throughput": 2175.35, "total_tokens": 27681024} {"current_steps": 381, "total_steps": 1200, "loss": 0.1293, "lr": 3.856103841657797e-05, "epoch": 6.249221183800623, "percentage": 31.75, "elapsed_time": "3:32:41", "remaining_time": "7:37:11", "throughput": 2175.29, "total_tokens": 27759536} {"current_steps": 382, "total_steps": 1200, "loss": 0.0967, "lr": 3.850600801194138e-05, "epoch": 6.265835929387332, "percentage": 31.83, "elapsed_time": "3:33:25", "remaining_time": "7:37:00", "throughput": 2175.43, "total_tokens": 27857288} {"current_steps": 383, "total_steps": 1200, "loss": 0.1395, "lr": 3.8450885038638127e-05, "epoch": 6.282450674974039, "percentage": 31.92, "elapsed_time": "3:34:04", "remaining_time": "7:36:38", "throughput": 2175.32, "total_tokens": 27940528} {"current_steps": 384, "total_steps": 1200, "loss": 0.1402, "lr": 3.8395669874474915e-05, "epoch": 6.299065420560748, "percentage": 32.0, "elapsed_time": "3:34:49", "remaining_time": "7:36:30", "throughput": 2174.89, "total_tokens": 28033824} {"current_steps": 385, "total_steps": 1200, "loss": 0.1137, "lr": 3.834036289789029e-05, "epoch": 6.315680166147456, "percentage": 32.08, "elapsed_time": "3:35:19", "remaining_time": "7:35:48", "throughput": 2174.79, "total_tokens": 28096192} {"current_steps": 386, "total_steps": 1200, "loss": 0.1143, "lr": 3.828496448795207e-05, "epoch": 6.332294911734164, "percentage": 32.17, "elapsed_time": "3:36:00", "remaining_time": "7:35:30", "throughput": 2174.46, "total_tokens": 28181256} {"current_steps": 387, "total_steps": 1200, "loss": 0.121, "lr": 3.822947502435477e-05, "epoch": 6.348909657320872, "percentage": 32.25, "elapsed_time": "3:36:29", "remaining_time": "7:34:47", "throughput": 2174.56, "total_tokens": 28245480} {"current_steps": 388, "total_steps": 1200, "loss": 0.1183, "lr": 3.8173894887416945e-05, "epoch": 6.365524402907581, "percentage": 32.33, "elapsed_time": "3:36:56", "remaining_time": "7:34:00", "throughput": 2174.72, "total_tokens": 28307200} {"current_steps": 389, "total_steps": 1200, "loss": 0.1423, "lr": 3.811822445807863e-05, "epoch": 6.382139148494288, "percentage": 32.42, "elapsed_time": "3:37:31", "remaining_time": "7:33:31", "throughput": 2174.75, "total_tokens": 28384640} {"current_steps": 390, "total_steps": 1200, "loss": 0.1068, "lr": 3.8062464117898724e-05, "epoch": 6.398753894080997, "percentage": 32.5, "elapsed_time": "3:37:59", "remaining_time": "7:32:44", "throughput": 2175.02, "total_tokens": 28447992} {"current_steps": 391, "total_steps": 1200, "loss": 0.1233, "lr": 3.800661424905235e-05, "epoch": 6.415368639667705, "percentage": 32.58, "elapsed_time": "3:38:27", "remaining_time": "7:32:00", "throughput": 2175.34, "total_tokens": 28513856} {"current_steps": 392, "total_steps": 1200, "loss": 0.1354, "lr": 3.795067523432826e-05, "epoch": 6.431983385254413, "percentage": 32.67, "elapsed_time": "3:39:08", "remaining_time": "7:31:41", "throughput": 2174.93, "total_tokens": 28596584} {"current_steps": 393, "total_steps": 1200, "loss": 0.1483, "lr": 3.789464745712619e-05, "epoch": 6.4485981308411215, "percentage": 32.75, "elapsed_time": "3:39:40", "remaining_time": "7:31:04", "throughput": 2174.84, "total_tokens": 28664560} {"current_steps": 394, "total_steps": 1200, "loss": 0.1225, "lr": 3.7838531301454254e-05, "epoch": 6.46521287642783, "percentage": 32.83, "elapsed_time": "3:40:13", "remaining_time": "7:30:29", "throughput": 2175.08, "total_tokens": 28739512} {"current_steps": 395, "total_steps": 1200, "loss": 0.1318, "lr": 3.77823271519263e-05, "epoch": 6.481827622014538, "percentage": 32.92, "elapsed_time": "3:40:57", "remaining_time": "7:30:18", "throughput": 2174.77, "total_tokens": 28831848} {"current_steps": 396, "total_steps": 1200, "loss": 0.1337, "lr": 3.7726035393759285e-05, "epoch": 6.498442367601246, "percentage": 33.0, "elapsed_time": "3:41:25", "remaining_time": "7:29:34", "throughput": 2175.11, "total_tokens": 28898408} {"current_steps": 397, "total_steps": 1200, "loss": 0.1283, "lr": 3.76696564127706e-05, "epoch": 6.515057113187955, "percentage": 33.08, "elapsed_time": "3:41:55", "remaining_time": "7:28:52", "throughput": 2174.94, "total_tokens": 28960224} {"current_steps": 398, "total_steps": 1200, "loss": 0.1548, "lr": 3.761319059537548e-05, "epoch": 6.531671858774662, "percentage": 33.17, "elapsed_time": "3:42:22", "remaining_time": "7:28:05", "throughput": 2175.09, "total_tokens": 29020568} {"current_steps": 399, "total_steps": 1200, "loss": 0.1154, "lr": 3.755663832858432e-05, "epoch": 6.548286604361371, "percentage": 33.25, "elapsed_time": "3:42:57", "remaining_time": "7:27:34", "throughput": 2175.03, "total_tokens": 29095448} {"current_steps": 400, "total_steps": 1200, "loss": 0.1276, "lr": 3.7500000000000003e-05, "epoch": 6.564901349948079, "percentage": 33.33, "elapsed_time": "3:43:34", "remaining_time": "7:27:09", "throughput": 2175.72, "total_tokens": 29186600} {"current_steps": 401, "total_steps": 1200, "loss": 0.2184, "lr": 3.744327599781531e-05, "epoch": 6.581516095534787, "percentage": 33.42, "elapsed_time": "3:44:09", "remaining_time": "7:26:38", "throughput": 2175.46, "total_tokens": 29258552} {"current_steps": 402, "total_steps": 1200, "loss": 0.1508, "lr": 3.7386466710810194e-05, "epoch": 6.598130841121495, "percentage": 33.5, "elapsed_time": "3:44:51", "remaining_time": "7:26:22", "throughput": 2174.99, "total_tokens": 29344848} {"current_steps": 403, "total_steps": 1200, "loss": 0.2035, "lr": 3.7329572528349146e-05, "epoch": 6.614745586708204, "percentage": 33.58, "elapsed_time": "3:45:22", "remaining_time": "7:25:42", "throughput": 2174.96, "total_tokens": 29410184} {"current_steps": 404, "total_steps": 1200, "loss": 0.1308, "lr": 3.727259384037852e-05, "epoch": 6.6313603322949115, "percentage": 33.67, "elapsed_time": "3:45:58", "remaining_time": "7:25:13", "throughput": 2174.68, "total_tokens": 29484928} {"current_steps": 405, "total_steps": 1200, "loss": 0.1349, "lr": 3.721553103742388e-05, "epoch": 6.64797507788162, "percentage": 33.75, "elapsed_time": "3:46:36", "remaining_time": "7:24:48", "throughput": 2174.61, "total_tokens": 29566432} {"current_steps": 406, "total_steps": 1200, "loss": 0.1246, "lr": 3.715838451058726e-05, "epoch": 6.6645898234683285, "percentage": 33.83, "elapsed_time": "3:47:07", "remaining_time": "7:24:11", "throughput": 2174.55, "total_tokens": 29634032} {"current_steps": 407, "total_steps": 1200, "loss": 0.142, "lr": 3.7101154651544584e-05, "epoch": 6.681204569055036, "percentage": 33.92, "elapsed_time": "3:47:29", "remaining_time": "7:23:14", "throughput": 2174.56, "total_tokens": 29681424} {"current_steps": 408, "total_steps": 1200, "loss": 0.118, "lr": 3.704384185254288e-05, "epoch": 6.697819314641745, "percentage": 34.0, "elapsed_time": "3:48:04", "remaining_time": "7:22:44", "throughput": 2174.81, "total_tokens": 29762208} {"current_steps": 409, "total_steps": 1200, "loss": 0.1286, "lr": 3.6986446506397666e-05, "epoch": 6.714434060228453, "percentage": 34.08, "elapsed_time": "3:48:29", "remaining_time": "7:21:53", "throughput": 2174.88, "total_tokens": 29816280} {"current_steps": 410, "total_steps": 1200, "loss": 0.1211, "lr": 3.692896900649021e-05, "epoch": 6.731048805815161, "percentage": 34.17, "elapsed_time": "3:49:02", "remaining_time": "7:21:19", "throughput": 2175.22, "total_tokens": 29893040} {"current_steps": 411, "total_steps": 1200, "loss": 0.1324, "lr": 3.6871409746764865e-05, "epoch": 6.747663551401869, "percentage": 34.25, "elapsed_time": "3:49:38", "remaining_time": "7:20:51", "throughput": 2175.18, "total_tokens": 29971688} {"current_steps": 412, "total_steps": 1200, "loss": 0.1175, "lr": 3.681376912172636e-05, "epoch": 6.764278296988578, "percentage": 34.33, "elapsed_time": "3:50:15", "remaining_time": "7:20:24", "throughput": 2175.17, "total_tokens": 30051784} {"current_steps": 413, "total_steps": 1200, "loss": 0.1279, "lr": 3.675604752643706e-05, "epoch": 6.780893042575285, "percentage": 34.42, "elapsed_time": "3:51:01", "remaining_time": "7:20:13", "throughput": 2174.84, "total_tokens": 30146048} {"current_steps": 414, "total_steps": 1200, "loss": 0.1204, "lr": 3.6698245356514335e-05, "epoch": 6.797507788161994, "percentage": 34.5, "elapsed_time": "3:51:35", "remaining_time": "7:19:41", "throughput": 2174.91, "total_tokens": 30221296} {"current_steps": 415, "total_steps": 1200, "loss": 0.1311, "lr": 3.6640363008127784e-05, "epoch": 6.814122533748702, "percentage": 34.58, "elapsed_time": "3:52:07", "remaining_time": "7:19:04", "throughput": 2174.72, "total_tokens": 30287664} {"current_steps": 416, "total_steps": 1200, "loss": 0.1417, "lr": 3.6582400877996546e-05, "epoch": 6.83073727933541, "percentage": 34.67, "elapsed_time": "3:52:37", "remaining_time": "7:18:23", "throughput": 2174.73, "total_tokens": 30352816} {"current_steps": 417, "total_steps": 1200, "loss": 0.1316, "lr": 3.652435936338656e-05, "epoch": 6.8473520249221185, "percentage": 34.75, "elapsed_time": "3:53:17", "remaining_time": "7:18:03", "throughput": 2174.66, "total_tokens": 30439688} {"current_steps": 418, "total_steps": 1200, "loss": 0.1422, "lr": 3.646623886210788e-05, "epoch": 6.863966770508826, "percentage": 34.83, "elapsed_time": "3:53:47", "remaining_time": "7:17:22", "throughput": 2174.78, "total_tokens": 30506856} {"current_steps": 419, "total_steps": 1200, "loss": 0.1148, "lr": 3.64080397725119e-05, "epoch": 6.880581516095535, "percentage": 34.92, "elapsed_time": "3:54:13", "remaining_time": "7:16:34", "throughput": 2175.0, "total_tokens": 30565848} {"current_steps": 420, "total_steps": 1200, "loss": 0.1472, "lr": 3.634976249348867e-05, "epoch": 6.897196261682243, "percentage": 35.0, "elapsed_time": "3:54:44", "remaining_time": "7:15:57", "throughput": 2174.95, "total_tokens": 30633944} {"current_steps": 421, "total_steps": 1200, "loss": 0.1281, "lr": 3.629140742446414e-05, "epoch": 6.913811007268951, "percentage": 35.08, "elapsed_time": "3:55:20", "remaining_time": "7:15:27", "throughput": 2174.51, "total_tokens": 30704760} {"current_steps": 422, "total_steps": 1200, "loss": 0.1207, "lr": 3.623297496539741e-05, "epoch": 6.930425752855659, "percentage": 35.17, "elapsed_time": "3:55:49", "remaining_time": "7:14:46", "throughput": 2174.84, "total_tokens": 30773792} {"current_steps": 423, "total_steps": 1200, "loss": 0.1274, "lr": 3.6174465516778035e-05, "epoch": 6.947040498442368, "percentage": 35.25, "elapsed_time": "3:56:22", "remaining_time": "7:14:11", "throughput": 2175.12, "total_tokens": 30848672} {"current_steps": 424, "total_steps": 1200, "loss": 0.1234, "lr": 3.611587947962319e-05, "epoch": 6.963655244029075, "percentage": 35.33, "elapsed_time": "3:56:48", "remaining_time": "7:13:24", "throughput": 2175.16, "total_tokens": 30906064} {"current_steps": 425, "total_steps": 1200, "loss": 0.1465, "lr": 3.6057217255475034e-05, "epoch": 6.980269989615784, "percentage": 35.42, "elapsed_time": "3:57:15", "remaining_time": "7:12:38", "throughput": 2175.23, "total_tokens": 30964720} {"current_steps": 426, "total_steps": 1200, "loss": 0.133, "lr": 3.599847924639788e-05, "epoch": 6.996884735202492, "percentage": 35.5, "elapsed_time": "3:57:51", "remaining_time": "7:12:10", "throughput": 2175.14, "total_tokens": 31043152} {"current_steps": 427, "total_steps": 1200, "loss": 0.106, "lr": 3.593966585497547e-05, "epoch": 7.0, "percentage": 35.58, "elapsed_time": "3:57:57", "remaining_time": "7:10:46", "throughput": 2175.2, "total_tokens": 31056056} {"current_steps": 428, "total_steps": 1200, "loss": 0.1082, "lr": 3.588077748430819e-05, "epoch": 7.0166147455867085, "percentage": 35.67, "elapsed_time": "3:58:33", "remaining_time": "7:10:18", "throughput": 2175.19, "total_tokens": 31135304} {"current_steps": 429, "total_steps": 1200, "loss": 0.1217, "lr": 3.582181453801036e-05, "epoch": 7.033229491173416, "percentage": 35.75, "elapsed_time": "3:58:57", "remaining_time": "7:09:27", "throughput": 2175.07, "total_tokens": 31185600} {"current_steps": 430, "total_steps": 1200, "loss": 0.119, "lr": 3.576277742020738e-05, "epoch": 7.049844236760125, "percentage": 35.83, "elapsed_time": "3:59:28", "remaining_time": "7:08:49", "throughput": 2175.18, "total_tokens": 31254312} {"current_steps": 431, "total_steps": 1200, "loss": 0.1131, "lr": 3.570366653553307e-05, "epoch": 7.066458982346833, "percentage": 35.92, "elapsed_time": "4:00:10", "remaining_time": "7:08:31", "throughput": 2174.75, "total_tokens": 31339112} {"current_steps": 432, "total_steps": 1200, "loss": 0.0967, "lr": 3.564448228912682e-05, "epoch": 7.083073727933541, "percentage": 36.0, "elapsed_time": "4:00:49", "remaining_time": "7:08:08", "throughput": 2174.71, "total_tokens": 31424024} {"current_steps": 433, "total_steps": 1200, "loss": 0.124, "lr": 3.558522508663081e-05, "epoch": 7.099688473520249, "percentage": 36.08, "elapsed_time": "4:01:20", "remaining_time": "7:07:29", "throughput": 2175.0, "total_tokens": 31494656} {"current_steps": 434, "total_steps": 1200, "loss": 0.1102, "lr": 3.552589533418728e-05, "epoch": 7.116303219106958, "percentage": 36.17, "elapsed_time": "4:02:00", "remaining_time": "7:07:09", "throughput": 2175.38, "total_tokens": 31588536} {"current_steps": 435, "total_steps": 1200, "loss": 0.2184, "lr": 3.54664934384357e-05, "epoch": 7.132917964693665, "percentage": 36.25, "elapsed_time": "4:02:32", "remaining_time": "7:06:31", "throughput": 2175.44, "total_tokens": 31657560} {"current_steps": 436, "total_steps": 1200, "loss": 0.1208, "lr": 3.540701980651003e-05, "epoch": 7.149532710280374, "percentage": 36.33, "elapsed_time": "4:03:11", "remaining_time": "7:06:08", "throughput": 2175.48, "total_tokens": 31743992} {"current_steps": 437, "total_steps": 1200, "loss": 0.108, "lr": 3.534747484603587e-05, "epoch": 7.166147455867082, "percentage": 36.42, "elapsed_time": "4:03:38", "remaining_time": "7:05:23", "throughput": 2175.76, "total_tokens": 31806520} {"current_steps": 438, "total_steps": 1200, "loss": 0.1154, "lr": 3.528785896512772e-05, "epoch": 7.18276220145379, "percentage": 36.5, "elapsed_time": "4:04:05", "remaining_time": "7:04:38", "throughput": 2175.51, "total_tokens": 31860464} {"current_steps": 439, "total_steps": 1200, "loss": 0.2637, "lr": 3.5228172572386146e-05, "epoch": 7.1993769470404985, "percentage": 36.58, "elapsed_time": "4:04:33", "remaining_time": "7:03:56", "throughput": 2175.43, "total_tokens": 31921424} {"current_steps": 440, "total_steps": 1200, "loss": 0.1164, "lr": 3.516841607689501e-05, "epoch": 7.215991692627207, "percentage": 36.67, "elapsed_time": "4:04:57", "remaining_time": "7:03:06", "throughput": 2175.94, "total_tokens": 31981064} {"current_steps": 441, "total_steps": 1200, "loss": 0.1085, "lr": 3.510858988821863e-05, "epoch": 7.232606438213915, "percentage": 36.75, "elapsed_time": "4:05:26", "remaining_time": "7:02:26", "throughput": 2176.34, "total_tokens": 32050648} {"current_steps": 442, "total_steps": 1200, "loss": 0.1026, "lr": 3.504869441639901e-05, "epoch": 7.249221183800623, "percentage": 36.83, "elapsed_time": "4:05:58", "remaining_time": "7:01:49", "throughput": 2176.31, "total_tokens": 32118584} {"current_steps": 443, "total_steps": 1200, "loss": 0.1035, "lr": 3.4988730071953004e-05, "epoch": 7.265835929387332, "percentage": 36.92, "elapsed_time": "4:06:37", "remaining_time": "7:01:25", "throughput": 2176.5, "total_tokens": 32206384} {"current_steps": 444, "total_steps": 1200, "loss": 0.0904, "lr": 3.4928697265869515e-05, "epoch": 7.282450674974039, "percentage": 37.0, "elapsed_time": "4:07:23", "remaining_time": "7:01:13", "throughput": 2175.98, "total_tokens": 32299040} {"current_steps": 445, "total_steps": 1200, "loss": 0.1053, "lr": 3.486859640960668e-05, "epoch": 7.299065420560748, "percentage": 37.08, "elapsed_time": "4:07:47", "remaining_time": "7:00:25", "throughput": 2176.2, "total_tokens": 32355624} {"current_steps": 446, "total_steps": 1200, "loss": 0.1227, "lr": 3.480842791508904e-05, "epoch": 7.315680166147456, "percentage": 37.17, "elapsed_time": "4:08:20", "remaining_time": "6:59:51", "throughput": 2176.23, "total_tokens": 32427792} {"current_steps": 447, "total_steps": 1200, "loss": 0.1104, "lr": 3.474819219470471e-05, "epoch": 7.332294911734164, "percentage": 37.25, "elapsed_time": "4:08:59", "remaining_time": "6:59:27", "throughput": 2175.96, "total_tokens": 32508696} {"current_steps": 448, "total_steps": 1200, "loss": 0.1099, "lr": 3.4687889661302576e-05, "epoch": 7.348909657320872, "percentage": 37.33, "elapsed_time": "4:09:43", "remaining_time": "6:59:10", "throughput": 2175.85, "total_tokens": 32601312} {"current_steps": 449, "total_steps": 1200, "loss": 0.0966, "lr": 3.4627520728189456e-05, "epoch": 7.365524402907581, "percentage": 37.42, "elapsed_time": "4:10:17", "remaining_time": "6:58:38", "throughput": 2176.09, "total_tokens": 32680256} {"current_steps": 450, "total_steps": 1200, "loss": 0.1138, "lr": 3.456708580912725e-05, "epoch": 7.382139148494288, "percentage": 37.5, "elapsed_time": "4:10:46", "remaining_time": "6:57:57", "throughput": 2175.81, "total_tokens": 32738816} {"current_steps": 451, "total_steps": 1200, "loss": 0.1026, "lr": 3.4506585318330125e-05, "epoch": 7.398753894080997, "percentage": 37.58, "elapsed_time": "4:11:24", "remaining_time": "6:57:32", "throughput": 2175.26, "total_tokens": 32813240} {"current_steps": 452, "total_steps": 1200, "loss": 0.1183, "lr": 3.444601967046168e-05, "epoch": 7.415368639667705, "percentage": 37.67, "elapsed_time": "4:11:57", "remaining_time": "6:56:58", "throughput": 2175.54, "total_tokens": 32889680} {"current_steps": 453, "total_steps": 1200, "loss": 0.1218, "lr": 3.438538928063208e-05, "epoch": 7.431983385254413, "percentage": 37.75, "elapsed_time": "4:12:32", "remaining_time": "6:56:26", "throughput": 2175.5, "total_tokens": 32964760} {"current_steps": 454, "total_steps": 1200, "loss": 0.1226, "lr": 3.432469456439523e-05, "epoch": 7.4485981308411215, "percentage": 37.83, "elapsed_time": "4:13:08", "remaining_time": "6:55:56", "throughput": 2175.95, "total_tokens": 33048992} {"current_steps": 455, "total_steps": 1200, "loss": 0.1127, "lr": 3.426393593774591e-05, "epoch": 7.46521287642783, "percentage": 37.92, "elapsed_time": "4:13:47", "remaining_time": "6:55:33", "throughput": 2175.66, "total_tokens": 33130200} {"current_steps": 456, "total_steps": 1200, "loss": 0.1057, "lr": 3.4203113817116957e-05, "epoch": 7.481827622014538, "percentage": 38.0, "elapsed_time": "4:14:29", "remaining_time": "6:55:13", "throughput": 2175.77, "total_tokens": 33223024} {"current_steps": 457, "total_steps": 1200, "loss": 0.1127, "lr": 3.414222861937636e-05, "epoch": 7.498442367601246, "percentage": 38.08, "elapsed_time": "4:15:06", "remaining_time": "6:54:45", "throughput": 2175.79, "total_tokens": 33303120} {"current_steps": 458, "total_steps": 1200, "loss": 0.1201, "lr": 3.408128076182446e-05, "epoch": 7.515057113187955, "percentage": 38.17, "elapsed_time": "4:15:33", "remaining_time": "6:54:02", "throughput": 2175.92, "total_tokens": 33364984} {"current_steps": 459, "total_steps": 1200, "loss": 0.1318, "lr": 3.402027066219105e-05, "epoch": 7.531671858774662, "percentage": 38.25, "elapsed_time": "4:16:00", "remaining_time": "6:53:16", "throughput": 2176.26, "total_tokens": 33427352} {"current_steps": 460, "total_steps": 1200, "loss": 0.1045, "lr": 3.39591987386325e-05, "epoch": 7.548286604361371, "percentage": 38.33, "elapsed_time": "4:16:25", "remaining_time": "6:52:30", "throughput": 2176.17, "total_tokens": 33481272} {"current_steps": 461, "total_steps": 1200, "loss": 0.1, "lr": 3.389806540972898e-05, "epoch": 7.564901349948079, "percentage": 38.42, "elapsed_time": "4:16:49", "remaining_time": "6:51:42", "throughput": 2176.45, "total_tokens": 33538904} {"current_steps": 462, "total_steps": 1200, "loss": 0.1111, "lr": 3.383687109448143e-05, "epoch": 7.581516095534787, "percentage": 38.5, "elapsed_time": "4:17:32", "remaining_time": "6:51:24", "throughput": 2176.69, "total_tokens": 33635976} {"current_steps": 463, "total_steps": 1200, "loss": 0.1123, "lr": 3.377561621230887e-05, "epoch": 7.598130841121495, "percentage": 38.58, "elapsed_time": "4:18:05", "remaining_time": "6:50:50", "throughput": 2176.89, "total_tokens": 33711184} {"current_steps": 464, "total_steps": 1200, "loss": 0.0937, "lr": 3.3714301183045385e-05, "epoch": 7.614745586708204, "percentage": 38.67, "elapsed_time": "4:18:39", "remaining_time": "6:50:16", "throughput": 2176.56, "total_tokens": 33778848} {"current_steps": 465, "total_steps": 1200, "loss": 0.1023, "lr": 3.365292642693732e-05, "epoch": 7.6313603322949115, "percentage": 38.75, "elapsed_time": "4:19:19", "remaining_time": "6:49:54", "throughput": 2176.49, "total_tokens": 33866024} {"current_steps": 466, "total_steps": 1200, "loss": 0.1179, "lr": 3.359149236464041e-05, "epoch": 7.64797507788162, "percentage": 38.83, "elapsed_time": "4:20:10", "remaining_time": "6:49:48", "throughput": 2176.58, "total_tokens": 33978144} {"current_steps": 467, "total_steps": 1200, "loss": 0.1326, "lr": 3.35299994172168e-05, "epoch": 7.6645898234683285, "percentage": 38.92, "elapsed_time": "4:20:41", "remaining_time": "6:49:10", "throughput": 2176.73, "total_tokens": 34047480} {"current_steps": 468, "total_steps": 1200, "loss": 0.1058, "lr": 3.346844800613229e-05, "epoch": 7.681204569055036, "percentage": 39.0, "elapsed_time": "4:21:23", "remaining_time": "6:48:49", "throughput": 2176.52, "total_tokens": 34134480} {"current_steps": 469, "total_steps": 1200, "loss": 0.1077, "lr": 3.340683855325335e-05, "epoch": 7.697819314641745, "percentage": 39.08, "elapsed_time": "4:21:47", "remaining_time": "6:48:01", "throughput": 2176.74, "total_tokens": 34190176} {"current_steps": 470, "total_steps": 1200, "loss": 0.1224, "lr": 3.3345171480844275e-05, "epoch": 7.714434060228453, "percentage": 39.17, "elapsed_time": "4:22:24", "remaining_time": "6:47:34", "throughput": 2176.45, "total_tokens": 34267336} {"current_steps": 471, "total_steps": 1200, "loss": 0.116, "lr": 3.3283447211564276e-05, "epoch": 7.731048805815161, "percentage": 39.25, "elapsed_time": "4:22:51", "remaining_time": "6:46:50", "throughput": 2176.93, "total_tokens": 34333616} {"current_steps": 472, "total_steps": 1200, "loss": 0.1153, "lr": 3.322166616846458e-05, "epoch": 7.747663551401869, "percentage": 39.33, "elapsed_time": "4:23:23", "remaining_time": "6:46:14", "throughput": 2176.99, "total_tokens": 34404000} {"current_steps": 473, "total_steps": 1200, "loss": 0.111, "lr": 3.315982877498555e-05, "epoch": 7.764278296988578, "percentage": 39.42, "elapsed_time": "4:23:49", "remaining_time": "6:45:29", "throughput": 2177.37, "total_tokens": 34466048} {"current_steps": 474, "total_steps": 1200, "loss": 0.1099, "lr": 3.309793545495374e-05, "epoch": 7.780893042575285, "percentage": 39.5, "elapsed_time": "4:24:24", "remaining_time": "6:44:58", "throughput": 2177.63, "total_tokens": 34547312} {"current_steps": 475, "total_steps": 1200, "loss": 0.1029, "lr": 3.303598663257904e-05, "epoch": 7.797507788161994, "percentage": 39.58, "elapsed_time": "4:24:48", "remaining_time": "6:44:10", "throughput": 2177.71, "total_tokens": 34600544} {"current_steps": 476, "total_steps": 1200, "loss": 0.1111, "lr": 3.2973982732451755e-05, "epoch": 7.814122533748702, "percentage": 39.67, "elapsed_time": "4:25:15", "remaining_time": "6:43:28", "throughput": 2177.73, "total_tokens": 34660792} {"current_steps": 477, "total_steps": 1200, "loss": 0.162, "lr": 3.2911924179539656e-05, "epoch": 7.83073727933541, "percentage": 39.75, "elapsed_time": "4:26:06", "remaining_time": "6:43:21", "throughput": 2178.17, "total_tokens": 34778440} {"current_steps": 478, "total_steps": 1200, "loss": 0.1161, "lr": 3.284981139918513e-05, "epoch": 7.8473520249221185, "percentage": 39.83, "elapsed_time": "4:26:38", "remaining_time": "6:42:44", "throughput": 2178.38, "total_tokens": 34849760} {"current_steps": 479, "total_steps": 1200, "loss": 0.0973, "lr": 3.278764481710221e-05, "epoch": 7.863966770508826, "percentage": 39.92, "elapsed_time": "4:27:18", "remaining_time": "6:42:22", "throughput": 2178.49, "total_tokens": 34940776} {"current_steps": 480, "total_steps": 1200, "loss": 0.1131, "lr": 3.272542485937369e-05, "epoch": 7.880581516095535, "percentage": 40.0, "elapsed_time": "4:27:54", "remaining_time": "6:41:51", "throughput": 2178.52, "total_tokens": 35018104} {"current_steps": 481, "total_steps": 1200, "loss": 0.1012, "lr": 3.26631519524482e-05, "epoch": 7.897196261682243, "percentage": 40.08, "elapsed_time": "4:28:24", "remaining_time": "6:41:13", "throughput": 2178.23, "total_tokens": 35079744} {"current_steps": 482, "total_steps": 1200, "loss": 0.1, "lr": 3.260082652313726e-05, "epoch": 7.913811007268951, "percentage": 40.17, "elapsed_time": "4:28:49", "remaining_time": "6:40:26", "throughput": 2178.17, "total_tokens": 35132808} {"current_steps": 483, "total_steps": 1200, "loss": 0.1005, "lr": 3.253844899861239e-05, "epoch": 7.930425752855659, "percentage": 40.25, "elapsed_time": "4:29:18", "remaining_time": "6:39:46", "throughput": 2178.3, "total_tokens": 35197816} {"current_steps": 484, "total_steps": 1200, "loss": 0.0914, "lr": 3.247601980640217e-05, "epoch": 7.947040498442368, "percentage": 40.33, "elapsed_time": "4:29:54", "remaining_time": "6:39:17", "throughput": 2178.23, "total_tokens": 35275528} {"current_steps": 485, "total_steps": 1200, "loss": 0.119, "lr": 3.241353937438927e-05, "epoch": 7.963655244029075, "percentage": 40.42, "elapsed_time": "4:30:19", "remaining_time": "6:38:31", "throughput": 2178.39, "total_tokens": 35333280} {"current_steps": 486, "total_steps": 1200, "loss": 0.1156, "lr": 3.23510081308076e-05, "epoch": 7.980269989615784, "percentage": 40.5, "elapsed_time": "4:30:58", "remaining_time": "6:38:06", "throughput": 2178.08, "total_tokens": 35412944} {"current_steps": 487, "total_steps": 1200, "loss": 0.1217, "lr": 3.228842650423929e-05, "epoch": 7.996884735202492, "percentage": 40.58, "elapsed_time": "4:31:29", "remaining_time": "6:37:29", "throughput": 2178.34, "total_tokens": 35485056} {"current_steps": 488, "total_steps": 1200, "loss": 0.1188, "lr": 3.222579492361179e-05, "epoch": 8.0, "percentage": 40.67, "elapsed_time": "4:31:34", "remaining_time": "6:36:14", "throughput": 2178.33, "total_tokens": 35494824} {"current_steps": 489, "total_steps": 1200, "loss": 0.0967, "lr": 3.2163113818194964e-05, "epoch": 8.016614745586708, "percentage": 40.75, "elapsed_time": "4:32:01", "remaining_time": "6:35:30", "throughput": 2178.63, "total_tokens": 35557768} {"current_steps": 490, "total_steps": 1200, "loss": 0.0989, "lr": 3.210038361759807e-05, "epoch": 8.033229491173417, "percentage": 40.83, "elapsed_time": "4:32:24", "remaining_time": "6:34:42", "throughput": 2178.9, "total_tokens": 35613120} {"current_steps": 491, "total_steps": 1200, "loss": 0.096, "lr": 3.2037604751766885e-05, "epoch": 8.049844236760125, "percentage": 40.92, "elapsed_time": "4:32:53", "remaining_time": "6:34:03", "throughput": 2178.73, "total_tokens": 35674176} {"current_steps": 492, "total_steps": 1200, "loss": 0.1049, "lr": 3.1974777650980735e-05, "epoch": 8.066458982346832, "percentage": 41.0, "elapsed_time": "4:33:50", "remaining_time": "6:34:04", "throughput": 2178.0, "total_tokens": 35786664} {"current_steps": 493, "total_steps": 1200, "loss": 0.1102, "lr": 3.191190274584952e-05, "epoch": 8.083073727933542, "percentage": 41.08, "elapsed_time": "4:34:15", "remaining_time": "6:33:18", "throughput": 2178.02, "total_tokens": 35840720} {"current_steps": 494, "total_steps": 1200, "loss": 0.0864, "lr": 3.184898046731082e-05, "epoch": 8.09968847352025, "percentage": 41.17, "elapsed_time": "4:35:03", "remaining_time": "6:33:05", "throughput": 2177.53, "total_tokens": 35936736} {"current_steps": 495, "total_steps": 1200, "loss": 0.1, "lr": 3.178601124662686e-05, "epoch": 8.116303219106957, "percentage": 41.25, "elapsed_time": "4:35:37", "remaining_time": "6:32:33", "throughput": 2177.68, "total_tokens": 36013800} {"current_steps": 496, "total_steps": 1200, "loss": 0.0957, "lr": 3.172299551538164e-05, "epoch": 8.132917964693666, "percentage": 41.33, "elapsed_time": "4:36:16", "remaining_time": "6:32:07", "throughput": 2177.66, "total_tokens": 36097904} {"current_steps": 497, "total_steps": 1200, "loss": 0.077, "lr": 3.165993370547794e-05, "epoch": 8.149532710280374, "percentage": 41.42, "elapsed_time": "4:37:00", "remaining_time": "6:31:49", "throughput": 2177.78, "total_tokens": 36195544} {"current_steps": 498, "total_steps": 1200, "loss": 0.1195, "lr": 3.1596826249134324e-05, "epoch": 8.166147455867081, "percentage": 41.5, "elapsed_time": "4:37:31", "remaining_time": "6:31:12", "throughput": 2177.65, "total_tokens": 36261256} {"current_steps": 499, "total_steps": 1200, "loss": 0.1199, "lr": 3.153367357888224e-05, "epoch": 8.18276220145379, "percentage": 41.58, "elapsed_time": "4:37:58", "remaining_time": "6:30:29", "throughput": 2177.97, "total_tokens": 36325024} {"current_steps": 500, "total_steps": 1200, "loss": 0.1066, "lr": 3.147047612756302e-05, "epoch": 8.199376947040498, "percentage": 41.67, "elapsed_time": "4:38:22", "remaining_time": "6:29:42", "throughput": 2178.02, "total_tokens": 36377368} {"current_steps": 501, "total_steps": 1200, "loss": 0.0908, "lr": 3.140723432832492e-05, "epoch": 8.215991692627206, "percentage": 41.75, "elapsed_time": "4:38:58", "remaining_time": "6:29:13", "throughput": 2178.15, "total_tokens": 36459240} {"current_steps": 502, "total_steps": 1200, "loss": 0.1022, "lr": 3.1343948614620145e-05, "epoch": 8.232606438213915, "percentage": 41.83, "elapsed_time": "4:39:41", "remaining_time": "6:28:54", "throughput": 2178.12, "total_tokens": 36553088} {"current_steps": 503, "total_steps": 1200, "loss": 0.2542, "lr": 3.128061942020189e-05, "epoch": 8.249221183800623, "percentage": 41.92, "elapsed_time": "4:40:07", "remaining_time": "6:28:10", "throughput": 2178.25, "total_tokens": 36611464} {"current_steps": 504, "total_steps": 1200, "loss": 0.0817, "lr": 3.121724717912138e-05, "epoch": 8.26583592938733, "percentage": 42.0, "elapsed_time": "4:40:54", "remaining_time": "6:27:55", "throughput": 2177.79, "total_tokens": 36705696} {"current_steps": 505, "total_steps": 1200, "loss": 0.0879, "lr": 3.115383232572483e-05, "epoch": 8.28245067497404, "percentage": 42.08, "elapsed_time": "4:41:20", "remaining_time": "6:27:11", "throughput": 2177.84, "total_tokens": 36762744} {"current_steps": 506, "total_steps": 1200, "loss": 0.1057, "lr": 3.109037529465056e-05, "epoch": 8.299065420560748, "percentage": 42.17, "elapsed_time": "4:41:50", "remaining_time": "6:26:34", "throughput": 2177.74, "total_tokens": 36827816} {"current_steps": 507, "total_steps": 1200, "loss": 0.0924, "lr": 3.102687652082597e-05, "epoch": 8.315680166147455, "percentage": 42.25, "elapsed_time": "4:42:34", "remaining_time": "6:26:14", "throughput": 2178.24, "total_tokens": 36931424} {"current_steps": 508, "total_steps": 1200, "loss": 0.093, "lr": 3.0963336439464526e-05, "epoch": 8.332294911734165, "percentage": 42.33, "elapsed_time": "4:43:02", "remaining_time": "6:25:34", "throughput": 2178.15, "total_tokens": 36991464} {"current_steps": 509, "total_steps": 1200, "loss": 0.0784, "lr": 3.089975548606283e-05, "epoch": 8.348909657320872, "percentage": 42.42, "elapsed_time": "4:43:51", "remaining_time": "6:25:20", "throughput": 2177.95, "total_tokens": 37092928} {"current_steps": 510, "total_steps": 1200, "loss": 0.0953, "lr": 3.083613409639764e-05, "epoch": 8.36552440290758, "percentage": 42.5, "elapsed_time": "4:44:23", "remaining_time": "6:24:46", "throughput": 2178.25, "total_tokens": 37168792} {"current_steps": 511, "total_steps": 1200, "loss": 0.0964, "lr": 3.0772472706522806e-05, "epoch": 8.38213914849429, "percentage": 42.58, "elapsed_time": "4:45:10", "remaining_time": "6:24:30", "throughput": 2177.58, "total_tokens": 37258864} {"current_steps": 512, "total_steps": 1200, "loss": 0.1084, "lr": 3.0708771752766394e-05, "epoch": 8.398753894080997, "percentage": 42.67, "elapsed_time": "4:45:44", "remaining_time": "6:23:57", "throughput": 2178.2, "total_tokens": 37343224} {"current_steps": 513, "total_steps": 1200, "loss": 0.1068, "lr": 3.06450316717276e-05, "epoch": 8.415368639667705, "percentage": 42.75, "elapsed_time": "4:46:07", "remaining_time": "6:23:10", "throughput": 2178.23, "total_tokens": 37395488} {"current_steps": 514, "total_steps": 1200, "loss": 0.0849, "lr": 3.0581252900273786e-05, "epoch": 8.431983385254414, "percentage": 42.83, "elapsed_time": "4:46:42", "remaining_time": "6:22:38", "throughput": 2178.39, "total_tokens": 37473248} {"current_steps": 515, "total_steps": 1200, "loss": 0.0883, "lr": 3.0517435875537536e-05, "epoch": 8.448598130841122, "percentage": 42.92, "elapsed_time": "4:47:06", "remaining_time": "6:21:52", "throughput": 2178.78, "total_tokens": 37532096} {"current_steps": 516, "total_steps": 1200, "loss": 0.0839, "lr": 3.045358103491357e-05, "epoch": 8.46521287642783, "percentage": 43.0, "elapsed_time": "4:47:47", "remaining_time": "6:21:30", "throughput": 2178.73, "total_tokens": 37622328} {"current_steps": 517, "total_steps": 1200, "loss": 0.0999, "lr": 3.038968881605583e-05, "epoch": 8.481827622014539, "percentage": 43.08, "elapsed_time": "4:48:16", "remaining_time": "6:20:50", "throughput": 2178.82, "total_tokens": 37686304} {"current_steps": 518, "total_steps": 1200, "loss": 0.1023, "lr": 3.0325759656874418e-05, "epoch": 8.498442367601246, "percentage": 43.17, "elapsed_time": "4:48:58", "remaining_time": "6:20:27", "throughput": 2178.48, "total_tokens": 37770856} {"current_steps": 519, "total_steps": 1200, "loss": 0.0907, "lr": 3.026179399553264e-05, "epoch": 8.515057113187954, "percentage": 43.25, "elapsed_time": "4:49:28", "remaining_time": "6:19:49", "throughput": 2178.35, "total_tokens": 37834072} {"current_steps": 520, "total_steps": 1200, "loss": 0.0899, "lr": 3.0197792270443982e-05, "epoch": 8.531671858774663, "percentage": 43.33, "elapsed_time": "4:49:53", "remaining_time": "6:19:05", "throughput": 2178.4, "total_tokens": 37889928} {"current_steps": 521, "total_steps": 1200, "loss": 0.2102, "lr": 3.0133754920269103e-05, "epoch": 8.54828660436137, "percentage": 43.42, "elapsed_time": "4:50:31", "remaining_time": "6:18:37", "throughput": 2178.3, "total_tokens": 37971296} {"current_steps": 522, "total_steps": 1200, "loss": 0.0978, "lr": 3.0069682383912813e-05, "epoch": 8.564901349948078, "percentage": 43.5, "elapsed_time": "4:51:06", "remaining_time": "6:18:06", "throughput": 2178.42, "total_tokens": 38049288} {"current_steps": 523, "total_steps": 1200, "loss": 0.1069, "lr": 3.0005575100521118e-05, "epoch": 8.581516095534788, "percentage": 43.58, "elapsed_time": "4:51:41", "remaining_time": "6:17:35", "throughput": 2178.28, "total_tokens": 38123392} {"current_steps": 524, "total_steps": 1200, "loss": 0.0973, "lr": 2.9941433509478156e-05, "epoch": 8.598130841121495, "percentage": 43.67, "elapsed_time": "4:52:18", "remaining_time": "6:17:06", "throughput": 2178.51, "total_tokens": 38208264} {"current_steps": 525, "total_steps": 1200, "loss": 0.1045, "lr": 2.9877258050403212e-05, "epoch": 8.614745586708203, "percentage": 43.75, "elapsed_time": "4:52:42", "remaining_time": "6:16:20", "throughput": 2178.38, "total_tokens": 38258192} {"current_steps": 526, "total_steps": 1200, "loss": 0.1014, "lr": 2.9813049163147688e-05, "epoch": 8.631360332294912, "percentage": 43.83, "elapsed_time": "4:53:15", "remaining_time": "6:15:46", "throughput": 2178.52, "total_tokens": 38332408} {"current_steps": 527, "total_steps": 1200, "loss": 0.0816, "lr": 2.974880728779212e-05, "epoch": 8.64797507788162, "percentage": 43.92, "elapsed_time": "4:53:52", "remaining_time": "6:15:16", "throughput": 2178.13, "total_tokens": 38404960} {"current_steps": 528, "total_steps": 1200, "loss": 0.1103, "lr": 2.9684532864643122e-05, "epoch": 8.664589823468328, "percentage": 44.0, "elapsed_time": "4:54:22", "remaining_time": "6:14:39", "throughput": 2178.72, "total_tokens": 38481704} {"current_steps": 529, "total_steps": 1200, "loss": 0.0833, "lr": 2.9620226334230388e-05, "epoch": 8.681204569055037, "percentage": 44.08, "elapsed_time": "4:54:50", "remaining_time": "6:13:59", "throughput": 2178.92, "total_tokens": 38546304} {"current_steps": 530, "total_steps": 1200, "loss": 0.1225, "lr": 2.9555888137303695e-05, "epoch": 8.697819314641745, "percentage": 44.17, "elapsed_time": "4:55:24", "remaining_time": "6:13:26", "throughput": 2178.92, "total_tokens": 38621024} {"current_steps": 531, "total_steps": 1200, "loss": 0.0874, "lr": 2.949151871482982e-05, "epoch": 8.714434060228452, "percentage": 44.25, "elapsed_time": "4:55:49", "remaining_time": "6:12:42", "throughput": 2179.15, "total_tokens": 38679368} {"current_steps": 532, "total_steps": 1200, "loss": 0.1045, "lr": 2.9427118507989586e-05, "epoch": 8.731048805815162, "percentage": 44.33, "elapsed_time": "4:56:23", "remaining_time": "6:12:09", "throughput": 2179.21, "total_tokens": 38753984} {"current_steps": 533, "total_steps": 1200, "loss": 0.0939, "lr": 2.93626879581748e-05, "epoch": 8.74766355140187, "percentage": 44.42, "elapsed_time": "4:56:48", "remaining_time": "6:11:25", "throughput": 2179.23, "total_tokens": 38808336} {"current_steps": 534, "total_steps": 1200, "loss": 0.2031, "lr": 2.929822750698524e-05, "epoch": 8.764278296988577, "percentage": 44.5, "elapsed_time": "4:57:21", "remaining_time": "6:10:51", "throughput": 2178.99, "total_tokens": 38876624} {"current_steps": 535, "total_steps": 1200, "loss": 0.0906, "lr": 2.9233737596225613e-05, "epoch": 8.780893042575286, "percentage": 44.58, "elapsed_time": "4:57:47", "remaining_time": "6:10:08", "throughput": 2179.05, "total_tokens": 38933576} {"current_steps": 536, "total_steps": 1200, "loss": 0.0876, "lr": 2.916921866790256e-05, "epoch": 8.797507788161994, "percentage": 44.67, "elapsed_time": "4:58:38", "remaining_time": "6:09:57", "throughput": 2179.41, "total_tokens": 39050816} {"current_steps": 537, "total_steps": 1200, "loss": 0.0899, "lr": 2.9104671164221576e-05, "epoch": 8.814122533748701, "percentage": 44.75, "elapsed_time": "4:59:01", "remaining_time": "6:09:11", "throughput": 2179.39, "total_tokens": 39101856} {"current_steps": 538, "total_steps": 1200, "loss": 0.094, "lr": 2.9040095527584032e-05, "epoch": 8.83073727933541, "percentage": 44.83, "elapsed_time": "4:59:26", "remaining_time": "6:08:27", "throughput": 2179.72, "total_tokens": 39161928} {"current_steps": 539, "total_steps": 1200, "loss": 0.1077, "lr": 2.897549220058411e-05, "epoch": 8.847352024922118, "percentage": 44.92, "elapsed_time": "4:59:50", "remaining_time": "6:07:42", "throughput": 2179.79, "total_tokens": 39216048} {"current_steps": 540, "total_steps": 1200, "loss": 0.0857, "lr": 2.8910861626005776e-05, "epoch": 8.863966770508826, "percentage": 45.0, "elapsed_time": "5:00:36", "remaining_time": "6:07:24", "throughput": 2179.9, "total_tokens": 39317320} {"current_steps": 541, "total_steps": 1200, "loss": 0.0981, "lr": 2.884620424681976e-05, "epoch": 8.880581516095535, "percentage": 45.08, "elapsed_time": "5:01:08", "remaining_time": "6:06:49", "throughput": 2179.7, "total_tokens": 39383120} {"current_steps": 542, "total_steps": 1200, "loss": 0.0969, "lr": 2.8781520506180486e-05, "epoch": 8.897196261682243, "percentage": 45.17, "elapsed_time": "5:01:43", "remaining_time": "6:06:18", "throughput": 2179.56, "total_tokens": 39458584} {"current_steps": 543, "total_steps": 1200, "loss": 0.0809, "lr": 2.871681084742308e-05, "epoch": 8.91381100726895, "percentage": 45.25, "elapsed_time": "5:02:17", "remaining_time": "6:05:44", "throughput": 2179.79, "total_tokens": 39535152} {"current_steps": 544, "total_steps": 1200, "loss": 0.1064, "lr": 2.8652075714060295e-05, "epoch": 8.93042575285566, "percentage": 45.33, "elapsed_time": "5:02:41", "remaining_time": "6:05:00", "throughput": 2179.95, "total_tokens": 39590360} {"current_steps": 545, "total_steps": 1200, "loss": 0.0897, "lr": 2.858731554977948e-05, "epoch": 8.947040498442368, "percentage": 45.42, "elapsed_time": "5:03:17", "remaining_time": "6:04:29", "throughput": 2180.01, "total_tokens": 39669984} {"current_steps": 546, "total_steps": 1200, "loss": 0.0883, "lr": 2.8522530798439567e-05, "epoch": 8.963655244029075, "percentage": 45.5, "elapsed_time": "5:03:57", "remaining_time": "6:04:04", "throughput": 2179.98, "total_tokens": 39757392} {"current_steps": 547, "total_steps": 1200, "loss": 0.1024, "lr": 2.845772190406798e-05, "epoch": 8.980269989615785, "percentage": 45.58, "elapsed_time": "5:04:40", "remaining_time": "6:03:43", "throughput": 2179.75, "total_tokens": 39848064} {"current_steps": 548, "total_steps": 1200, "loss": 0.093, "lr": 2.8392889310857612e-05, "epoch": 8.996884735202492, "percentage": 45.67, "elapsed_time": "5:05:14", "remaining_time": "6:03:10", "throughput": 2179.77, "total_tokens": 39922288} {"current_steps": 549, "total_steps": 1200, "loss": 0.0997, "lr": 2.832803346316381e-05, "epoch": 9.0, "percentage": 45.75, "elapsed_time": "5:05:19", "remaining_time": "6:02:03", "throughput": 2179.75, "total_tokens": 39932640} {"current_steps": 550, "total_steps": 1200, "loss": 0.0756, "lr": 2.8263154805501297e-05, "epoch": 9.016614745586708, "percentage": 45.83, "elapsed_time": "5:05:51", "remaining_time": "6:01:27", "throughput": 2179.98, "total_tokens": 40005688} {"current_steps": 551, "total_steps": 1200, "loss": 0.0851, "lr": 2.819825378254111e-05, "epoch": 9.033229491173417, "percentage": 45.92, "elapsed_time": "5:06:15", "remaining_time": "6:00:43", "throughput": 2179.98, "total_tokens": 40057120} {"current_steps": 552, "total_steps": 1200, "loss": 0.0841, "lr": 2.8133330839107608e-05, "epoch": 9.049844236760125, "percentage": 46.0, "elapsed_time": "5:06:52", "remaining_time": "6:00:14", "throughput": 2179.82, "total_tokens": 40135992} {"current_steps": 553, "total_steps": 1200, "loss": 0.1069, "lr": 2.8068386420175375e-05, "epoch": 9.066458982346832, "percentage": 46.08, "elapsed_time": "5:07:16", "remaining_time": "5:59:30", "throughput": 2180.32, "total_tokens": 40196928} {"current_steps": 554, "total_steps": 1200, "loss": 0.0851, "lr": 2.8003420970866177e-05, "epoch": 9.083073727933542, "percentage": 46.17, "elapsed_time": "5:07:50", "remaining_time": "5:58:57", "throughput": 2180.23, "total_tokens": 40269392} {"current_steps": 555, "total_steps": 1200, "loss": 0.0899, "lr": 2.7938434936445945e-05, "epoch": 9.09968847352025, "percentage": 46.25, "elapsed_time": "5:08:25", "remaining_time": "5:58:26", "throughput": 2180.48, "total_tokens": 40350080} {"current_steps": 556, "total_steps": 1200, "loss": 0.0991, "lr": 2.787342876232167e-05, "epoch": 9.116303219106957, "percentage": 46.33, "elapsed_time": "5:08:54", "remaining_time": "5:57:47", "throughput": 2180.62, "total_tokens": 40416360} {"current_steps": 557, "total_steps": 1200, "loss": 0.0733, "lr": 2.780840289403839e-05, "epoch": 9.132917964693666, "percentage": 46.42, "elapsed_time": "5:09:25", "remaining_time": "5:57:12", "throughput": 2180.91, "total_tokens": 40490432} {"current_steps": 558, "total_steps": 1200, "loss": 0.0927, "lr": 2.774335777727613e-05, "epoch": 9.149532710280374, "percentage": 46.5, "elapsed_time": "5:09:57", "remaining_time": "5:56:36", "throughput": 2181.07, "total_tokens": 40561784} {"current_steps": 559, "total_steps": 1200, "loss": 0.083, "lr": 2.7678293857846844e-05, "epoch": 9.166147455867081, "percentage": 46.58, "elapsed_time": "5:10:30", "remaining_time": "5:56:02", "throughput": 2181.51, "total_tokens": 40641728} {"current_steps": 560, "total_steps": 1200, "loss": 0.0975, "lr": 2.761321158169134e-05, "epoch": 9.18276220145379, "percentage": 46.67, "elapsed_time": "5:10:54", "remaining_time": "5:55:19", "throughput": 2181.8, "total_tokens": 40700744} {"current_steps": 561, "total_steps": 1200, "loss": 0.0995, "lr": 2.754811139487625e-05, "epoch": 9.199376947040498, "percentage": 46.75, "elapsed_time": "5:11:15", "remaining_time": "5:54:32", "throughput": 2181.85, "total_tokens": 40748048} {"current_steps": 562, "total_steps": 1200, "loss": 0.073, "lr": 2.7482993743590978e-05, "epoch": 9.215991692627206, "percentage": 46.83, "elapsed_time": "5:11:43", "remaining_time": "5:53:52", "throughput": 2181.93, "total_tokens": 40810104} {"current_steps": 563, "total_steps": 1200, "loss": 0.0952, "lr": 2.7417859074144604e-05, "epoch": 9.232606438213915, "percentage": 46.92, "elapsed_time": "5:12:25", "remaining_time": "5:53:29", "throughput": 2181.79, "total_tokens": 40899480} {"current_steps": 564, "total_steps": 1200, "loss": 0.0808, "lr": 2.7352707832962865e-05, "epoch": 9.249221183800623, "percentage": 47.0, "elapsed_time": "5:13:07", "remaining_time": "5:53:06", "throughput": 2181.95, "total_tokens": 40993536} {"current_steps": 565, "total_steps": 1200, "loss": 0.0698, "lr": 2.7287540466585065e-05, "epoch": 9.26583592938733, "percentage": 47.08, "elapsed_time": "5:13:36", "remaining_time": "5:52:28", "throughput": 2182.13, "total_tokens": 41060848} {"current_steps": 566, "total_steps": 1200, "loss": 0.0931, "lr": 2.7222357421661042e-05, "epoch": 9.28245067497404, "percentage": 47.17, "elapsed_time": "5:14:10", "remaining_time": "5:51:55", "throughput": 2182.31, "total_tokens": 41138352} {"current_steps": 567, "total_steps": 1200, "loss": 0.0996, "lr": 2.7157159144948092e-05, "epoch": 9.299065420560748, "percentage": 47.25, "elapsed_time": "5:14:44", "remaining_time": "5:51:22", "throughput": 2182.39, "total_tokens": 41212624} {"current_steps": 568, "total_steps": 1200, "loss": 0.0764, "lr": 2.7091946083307896e-05, "epoch": 9.315680166147455, "percentage": 47.33, "elapsed_time": "5:15:13", "remaining_time": "5:50:44", "throughput": 2182.53, "total_tokens": 41279472} {"current_steps": 569, "total_steps": 1200, "loss": 0.0942, "lr": 2.7026718683703473e-05, "epoch": 9.332294911734165, "percentage": 47.42, "elapsed_time": "5:15:50", "remaining_time": "5:50:15", "throughput": 2182.21, "total_tokens": 41353544} {"current_steps": 570, "total_steps": 1200, "loss": 0.0718, "lr": 2.6961477393196126e-05, "epoch": 9.348909657320872, "percentage": 47.5, "elapsed_time": "5:16:32", "remaining_time": "5:49:51", "throughput": 2182.2, "total_tokens": 41444896} {"current_steps": 571, "total_steps": 1200, "loss": 0.0906, "lr": 2.6896222658942348e-05, "epoch": 9.36552440290758, "percentage": 47.58, "elapsed_time": "5:16:59", "remaining_time": "5:49:11", "throughput": 2182.27, "total_tokens": 41505152} {"current_steps": 572, "total_steps": 1200, "loss": 0.1081, "lr": 2.6830954928190794e-05, "epoch": 9.38213914849429, "percentage": 47.67, "elapsed_time": "5:17:29", "remaining_time": "5:48:33", "throughput": 2182.09, "total_tokens": 41566696} {"current_steps": 573, "total_steps": 1200, "loss": 0.0922, "lr": 2.6765674648279172e-05, "epoch": 9.398753894080997, "percentage": 47.75, "elapsed_time": "5:18:03", "remaining_time": "5:48:01", "throughput": 2182.12, "total_tokens": 41641736} {"current_steps": 574, "total_steps": 1200, "loss": 0.0748, "lr": 2.6700382266631206e-05, "epoch": 9.415368639667705, "percentage": 47.83, "elapsed_time": "5:18:51", "remaining_time": "5:47:44", "throughput": 2181.76, "total_tokens": 41740008} {"current_steps": 575, "total_steps": 1200, "loss": 0.0813, "lr": 2.663507823075358e-05, "epoch": 9.431983385254414, "percentage": 47.92, "elapsed_time": "5:19:35", "remaining_time": "5:47:23", "throughput": 2182.07, "total_tokens": 41842808} {"current_steps": 576, "total_steps": 1200, "loss": 0.0779, "lr": 2.656976298823284e-05, "epoch": 9.448598130841122, "percentage": 48.0, "elapsed_time": "5:20:04", "remaining_time": "5:46:45", "throughput": 2182.62, "total_tokens": 41917128} {"current_steps": 577, "total_steps": 1200, "loss": 0.0882, "lr": 2.6504436986732338e-05, "epoch": 9.46521287642783, "percentage": 48.08, "elapsed_time": "5:20:38", "remaining_time": "5:46:12", "throughput": 2182.32, "total_tokens": 41984232} {"current_steps": 578, "total_steps": 1200, "loss": 0.0905, "lr": 2.6439100673989187e-05, "epoch": 9.481827622014539, "percentage": 48.17, "elapsed_time": "5:21:05", "remaining_time": "5:45:32", "throughput": 2182.52, "total_tokens": 42047216} {"current_steps": 579, "total_steps": 1200, "loss": 0.081, "lr": 2.637375449781115e-05, "epoch": 9.498442367601246, "percentage": 48.25, "elapsed_time": "5:21:38", "remaining_time": "5:44:57", "throughput": 2182.71, "total_tokens": 42122072} {"current_steps": 580, "total_steps": 1200, "loss": 0.0777, "lr": 2.63083989060736e-05, "epoch": 9.515057113187954, "percentage": 48.33, "elapsed_time": "5:22:10", "remaining_time": "5:44:23", "throughput": 2182.97, "total_tokens": 42198480} {"current_steps": 581, "total_steps": 1200, "loss": 0.0817, "lr": 2.624303434671645e-05, "epoch": 9.531671858774663, "percentage": 48.42, "elapsed_time": "5:22:53", "remaining_time": "5:44:00", "throughput": 2182.81, "total_tokens": 42289336} {"current_steps": 582, "total_steps": 1200, "loss": 0.0931, "lr": 2.6177661267741065e-05, "epoch": 9.54828660436137, "percentage": 48.5, "elapsed_time": "5:23:23", "remaining_time": "5:43:23", "throughput": 2182.73, "total_tokens": 42352288} {"current_steps": 583, "total_steps": 1200, "loss": 0.0852, "lr": 2.611228011720722e-05, "epoch": 9.564901349948078, "percentage": 48.58, "elapsed_time": "5:24:10", "remaining_time": "5:43:05", "throughput": 2182.63, "total_tokens": 42453832} {"current_steps": 584, "total_steps": 1200, "loss": 0.0917, "lr": 2.604689134322999e-05, "epoch": 9.581516095534788, "percentage": 48.67, "elapsed_time": "5:24:37", "remaining_time": "5:42:24", "throughput": 2182.77, "total_tokens": 42514704} {"current_steps": 585, "total_steps": 1200, "loss": 0.184, "lr": 2.598149539397672e-05, "epoch": 9.598130841121495, "percentage": 48.75, "elapsed_time": "5:25:05", "remaining_time": "5:41:46", "throughput": 2182.74, "total_tokens": 42576344} {"current_steps": 586, "total_steps": 1200, "loss": 0.0799, "lr": 2.591609271766391e-05, "epoch": 9.614745586708203, "percentage": 48.83, "elapsed_time": "5:25:48", "remaining_time": "5:41:22", "throughput": 2182.44, "total_tokens": 42662824} {"current_steps": 587, "total_steps": 1200, "loss": 0.0681, "lr": 2.5850683762554184e-05, "epoch": 9.631360332294912, "percentage": 48.92, "elapsed_time": "5:26:33", "remaining_time": "5:41:01", "throughput": 2181.95, "total_tokens": 42752496} {"current_steps": 588, "total_steps": 1200, "loss": 0.07, "lr": 2.578526897695321e-05, "epoch": 9.64797507788162, "percentage": 49.0, "elapsed_time": "5:27:07", "remaining_time": "5:40:28", "throughput": 2181.92, "total_tokens": 42826064} {"current_steps": 589, "total_steps": 1200, "loss": 0.1774, "lr": 2.5719848809206586e-05, "epoch": 9.664589823468328, "percentage": 49.08, "elapsed_time": "5:27:37", "remaining_time": "5:39:51", "throughput": 2182.18, "total_tokens": 42895808} {"current_steps": 590, "total_steps": 1200, "loss": 0.0925, "lr": 2.5654423707696833e-05, "epoch": 9.681204569055037, "percentage": 49.17, "elapsed_time": "5:28:02", "remaining_time": "5:39:09", "throughput": 2182.32, "total_tokens": 42952408} {"current_steps": 591, "total_steps": 1200, "loss": 0.0824, "lr": 2.558899412084026e-05, "epoch": 9.697819314641745, "percentage": 49.25, "elapsed_time": "5:28:35", "remaining_time": "5:38:36", "throughput": 2182.27, "total_tokens": 43025536} {"current_steps": 592, "total_steps": 1200, "loss": 0.0634, "lr": 2.5523560497083926e-05, "epoch": 9.714434060228452, "percentage": 49.33, "elapsed_time": "5:29:18", "remaining_time": "5:38:12", "throughput": 2182.26, "total_tokens": 43118024} {"current_steps": 593, "total_steps": 1200, "loss": 0.0796, "lr": 2.5458123284902573e-05, "epoch": 9.731048805815162, "percentage": 49.42, "elapsed_time": "5:29:56", "remaining_time": "5:37:44", "throughput": 2182.09, "total_tokens": 43198360} {"current_steps": 594, "total_steps": 1200, "loss": 0.0681, "lr": 2.539268293279552e-05, "epoch": 9.74766355140187, "percentage": 49.5, "elapsed_time": "5:30:29", "remaining_time": "5:37:10", "throughput": 2181.77, "total_tokens": 43264072} {"current_steps": 595, "total_steps": 1200, "loss": 0.098, "lr": 2.5327239889283612e-05, "epoch": 9.764278296988577, "percentage": 49.58, "elapsed_time": "5:31:07", "remaining_time": "5:36:41", "throughput": 2181.46, "total_tokens": 43339600} {"current_steps": 596, "total_steps": 1200, "loss": 0.0857, "lr": 2.5261794602906145e-05, "epoch": 9.780893042575286, "percentage": 49.67, "elapsed_time": "5:31:35", "remaining_time": "5:36:02", "throughput": 2181.49, "total_tokens": 43401136} {"current_steps": 597, "total_steps": 1200, "loss": 0.0853, "lr": 2.5196347522217784e-05, "epoch": 9.797507788161994, "percentage": 49.75, "elapsed_time": "5:32:12", "remaining_time": "5:35:33", "throughput": 2181.2, "total_tokens": 43477528} {"current_steps": 598, "total_steps": 1200, "loss": 0.0825, "lr": 2.513089909578549e-05, "epoch": 9.814122533748701, "percentage": 49.83, "elapsed_time": "5:32:49", "remaining_time": "5:35:03", "throughput": 2181.17, "total_tokens": 43557352} {"current_steps": 599, "total_steps": 1200, "loss": 0.0985, "lr": 2.5065449772185456e-05, "epoch": 9.83073727933541, "percentage": 49.92, "elapsed_time": "5:33:34", "remaining_time": "5:34:40", "throughput": 2180.63, "total_tokens": 43643104} {"current_steps": 600, "total_steps": 1200, "loss": 0.0859, "lr": 2.5e-05, "epoch": 9.847352024922118, "percentage": 50.0, "elapsed_time": "5:34:07", "remaining_time": "5:34:07", "throughput": 2180.86, "total_tokens": 43721408} {"current_steps": 601, "total_steps": 1200, "loss": 0.0745, "lr": 2.4934550227814553e-05, "epoch": 9.863966770508826, "percentage": 50.08, "elapsed_time": "5:34:47", "remaining_time": "5:33:40", "throughput": 2180.56, "total_tokens": 43802136} {"current_steps": 602, "total_steps": 1200, "loss": 0.0909, "lr": 2.486910090421451e-05, "epoch": 9.880581516095535, "percentage": 50.17, "elapsed_time": "5:35:14", "remaining_time": "5:33:01", "throughput": 2180.62, "total_tokens": 43862904} {"current_steps": 603, "total_steps": 1200, "loss": 0.0946, "lr": 2.480365247778223e-05, "epoch": 9.897196261682243, "percentage": 50.25, "elapsed_time": "5:35:53", "remaining_time": "5:32:32", "throughput": 2180.4, "total_tokens": 43942056} {"current_steps": 604, "total_steps": 1200, "loss": 0.163, "lr": 2.4738205397093864e-05, "epoch": 9.91381100726895, "percentage": 50.33, "elapsed_time": "5:36:28", "remaining_time": "5:32:01", "throughput": 2180.24, "total_tokens": 44016096} {"current_steps": 605, "total_steps": 1200, "loss": 0.1059, "lr": 2.4672760110716394e-05, "epoch": 9.93042575285566, "percentage": 50.42, "elapsed_time": "5:36:51", "remaining_time": "5:31:17", "throughput": 2180.26, "total_tokens": 44065504} {"current_steps": 606, "total_steps": 1200, "loss": 0.0852, "lr": 2.460731706720449e-05, "epoch": 9.947040498442368, "percentage": 50.5, "elapsed_time": "5:37:11", "remaining_time": "5:30:31", "throughput": 2180.45, "total_tokens": 44114776} {"current_steps": 607, "total_steps": 1200, "loss": 0.1065, "lr": 2.4541876715097432e-05, "epoch": 9.963655244029075, "percentage": 50.58, "elapsed_time": "5:37:38", "remaining_time": "5:29:51", "throughput": 2180.52, "total_tokens": 44175184} {"current_steps": 608, "total_steps": 1200, "loss": 0.0708, "lr": 2.447643950291608e-05, "epoch": 9.980269989615785, "percentage": 50.67, "elapsed_time": "5:38:24", "remaining_time": "5:29:29", "throughput": 2180.1, "total_tokens": 44265024} {"current_steps": 609, "total_steps": 1200, "loss": 0.0803, "lr": 2.4411005879159753e-05, "epoch": 9.996884735202492, "percentage": 50.75, "elapsed_time": "5:39:06", "remaining_time": "5:29:05", "throughput": 2179.95, "total_tokens": 44355400} {"current_steps": 610, "total_steps": 1200, "loss": 0.0686, "lr": 2.4345576292303176e-05, "epoch": 10.0, "percentage": 50.83, "elapsed_time": "5:39:12", "remaining_time": "5:28:05", "throughput": 2180.1, "total_tokens": 44370360} {"current_steps": 611, "total_steps": 1200, "loss": 0.0685, "lr": 2.4280151190793417e-05, "epoch": 10.016614745586708, "percentage": 50.92, "elapsed_time": "5:39:50", "remaining_time": "5:27:36", "throughput": 2179.73, "total_tokens": 44446816} {"current_steps": 612, "total_steps": 1200, "loss": 0.0814, "lr": 2.4214731023046793e-05, "epoch": 10.033229491173417, "percentage": 51.0, "elapsed_time": "5:40:15", "remaining_time": "5:26:54", "throughput": 2179.89, "total_tokens": 44503632} {"current_steps": 613, "total_steps": 1200, "loss": 0.0782, "lr": 2.4149316237445812e-05, "epoch": 10.049844236760125, "percentage": 51.08, "elapsed_time": "5:40:54", "remaining_time": "5:26:27", "throughput": 2179.94, "total_tokens": 44590320} {"current_steps": 614, "total_steps": 1200, "loss": 0.0793, "lr": 2.408390728233609e-05, "epoch": 10.066458982346832, "percentage": 51.17, "elapsed_time": "5:41:21", "remaining_time": "5:25:47", "throughput": 2180.22, "total_tokens": 44655224} {"current_steps": 615, "total_steps": 1200, "loss": 0.1559, "lr": 2.4018504606023293e-05, "epoch": 10.083073727933542, "percentage": 51.25, "elapsed_time": "5:41:59", "remaining_time": "5:25:18", "throughput": 2180.15, "total_tokens": 44736200} {"current_steps": 616, "total_steps": 1200, "loss": 0.069, "lr": 2.3953108656770016e-05, "epoch": 10.09968847352025, "percentage": 51.33, "elapsed_time": "5:42:32", "remaining_time": "5:24:44", "throughput": 2180.05, "total_tokens": 44804416} {"current_steps": 617, "total_steps": 1200, "loss": 0.0694, "lr": 2.3887719882792785e-05, "epoch": 10.116303219106957, "percentage": 51.42, "elapsed_time": "5:43:03", "remaining_time": "5:24:08", "throughput": 2180.13, "total_tokens": 44873864} {"current_steps": 618, "total_steps": 1200, "loss": 0.081, "lr": 2.3822338732258937e-05, "epoch": 10.132917964693666, "percentage": 51.5, "elapsed_time": "5:43:31", "remaining_time": "5:23:30", "throughput": 2180.22, "total_tokens": 44936736} {"current_steps": 619, "total_steps": 1200, "loss": 0.0612, "lr": 2.3756965653283557e-05, "epoch": 10.149532710280374, "percentage": 51.58, "elapsed_time": "5:44:13", "remaining_time": "5:23:05", "throughput": 2180.13, "total_tokens": 45026952} {"current_steps": 620, "total_steps": 1200, "loss": 0.0776, "lr": 2.3691601093926404e-05, "epoch": 10.166147455867081, "percentage": 51.67, "elapsed_time": "5:44:50", "remaining_time": "5:22:35", "throughput": 2180.0, "total_tokens": 45104816} {"current_steps": 621, "total_steps": 1200, "loss": 0.0707, "lr": 2.3626245502188864e-05, "epoch": 10.18276220145379, "percentage": 51.75, "elapsed_time": "5:45:25", "remaining_time": "5:22:04", "throughput": 2179.75, "total_tokens": 45177392} {"current_steps": 622, "total_steps": 1200, "loss": 0.0849, "lr": 2.3560899326010822e-05, "epoch": 10.199376947040498, "percentage": 51.83, "elapsed_time": "5:45:55", "remaining_time": "5:21:27", "throughput": 2179.5, "total_tokens": 45237200} {"current_steps": 623, "total_steps": 1200, "loss": 0.0856, "lr": 2.3495563013267664e-05, "epoch": 10.215991692627206, "percentage": 51.92, "elapsed_time": "5:46:20", "remaining_time": "5:20:46", "throughput": 2179.57, "total_tokens": 45293376} {"current_steps": 624, "total_steps": 1200, "loss": 0.081, "lr": 2.3430237011767167e-05, "epoch": 10.232606438213915, "percentage": 52.0, "elapsed_time": "5:46:54", "remaining_time": "5:20:13", "throughput": 2179.67, "total_tokens": 45369376} {"current_steps": 625, "total_steps": 1200, "loss": 0.0707, "lr": 2.3364921769246423e-05, "epoch": 10.249221183800623, "percentage": 52.08, "elapsed_time": "5:47:29", "remaining_time": "5:19:41", "throughput": 2179.41, "total_tokens": 45439920} {"current_steps": 626, "total_steps": 1200, "loss": 0.0791, "lr": 2.3299617733368806e-05, "epoch": 10.26583592938733, "percentage": 52.17, "elapsed_time": "5:47:56", "remaining_time": "5:19:01", "throughput": 2179.44, "total_tokens": 45497992} {"current_steps": 627, "total_steps": 1200, "loss": 0.0649, "lr": 2.323432535172084e-05, "epoch": 10.28245067497404, "percentage": 52.25, "elapsed_time": "5:48:27", "remaining_time": "5:18:27", "throughput": 2179.24, "total_tokens": 45562832} {"current_steps": 628, "total_steps": 1200, "loss": 0.0835, "lr": 2.3169045071809215e-05, "epoch": 10.299065420560748, "percentage": 52.33, "elapsed_time": "5:49:04", "remaining_time": "5:17:57", "throughput": 2179.0, "total_tokens": 45638712} {"current_steps": 629, "total_steps": 1200, "loss": 0.0797, "lr": 2.3103777341057655e-05, "epoch": 10.315680166147455, "percentage": 52.42, "elapsed_time": "5:49:32", "remaining_time": "5:17:19", "throughput": 2178.87, "total_tokens": 45697336} {"current_steps": 630, "total_steps": 1200, "loss": 0.0892, "lr": 2.303852260680388e-05, "epoch": 10.332294911734165, "percentage": 52.5, "elapsed_time": "5:50:01", "remaining_time": "5:16:41", "throughput": 2179.14, "total_tokens": 45765680} {"current_steps": 631, "total_steps": 1200, "loss": 0.081, "lr": 2.2973281316296533e-05, "epoch": 10.348909657320872, "percentage": 52.58, "elapsed_time": "5:50:30", "remaining_time": "5:16:03", "throughput": 2179.23, "total_tokens": 45829592} {"current_steps": 632, "total_steps": 1200, "loss": 0.0816, "lr": 2.2908053916692117e-05, "epoch": 10.36552440290758, "percentage": 52.67, "elapsed_time": "5:51:04", "remaining_time": "5:15:30", "throughput": 2179.23, "total_tokens": 45903304} {"current_steps": 633, "total_steps": 1200, "loss": 0.0773, "lr": 2.284284085505192e-05, "epoch": 10.38213914849429, "percentage": 52.75, "elapsed_time": "5:51:49", "remaining_time": "5:15:08", "throughput": 2179.14, "total_tokens": 45999840} {"current_steps": 634, "total_steps": 1200, "loss": 0.0773, "lr": 2.2777642578338963e-05, "epoch": 10.398753894080997, "percentage": 52.83, "elapsed_time": "5:52:38", "remaining_time": "5:14:48", "throughput": 2179.17, "total_tokens": 46107264} {"current_steps": 635, "total_steps": 1200, "loss": 0.0696, "lr": 2.2712459533414944e-05, "epoch": 10.415368639667705, "percentage": 52.92, "elapsed_time": "5:53:09", "remaining_time": "5:14:13", "throughput": 2179.11, "total_tokens": 46174720} {"current_steps": 636, "total_steps": 1200, "loss": 0.063, "lr": 2.2647292167037144e-05, "epoch": 10.431983385254414, "percentage": 53.0, "elapsed_time": "5:53:57", "remaining_time": "5:13:53", "throughput": 2178.71, "total_tokens": 46269984} {"current_steps": 637, "total_steps": 1200, "loss": 0.0672, "lr": 2.2582140925855395e-05, "epoch": 10.448598130841122, "percentage": 53.08, "elapsed_time": "5:54:35", "remaining_time": "5:13:24", "throughput": 2178.75, "total_tokens": 46354792} {"current_steps": 638, "total_steps": 1200, "loss": 0.0755, "lr": 2.251700625640903e-05, "epoch": 10.46521287642783, "percentage": 53.17, "elapsed_time": "5:55:04", "remaining_time": "5:12:46", "throughput": 2178.93, "total_tokens": 46420480} {"current_steps": 639, "total_steps": 1200, "loss": 0.0773, "lr": 2.2451888605123754e-05, "epoch": 10.481827622014539, "percentage": 53.25, "elapsed_time": "5:55:35", "remaining_time": "5:12:11", "throughput": 2178.88, "total_tokens": 46487288} {"current_steps": 640, "total_steps": 1200, "loss": 0.0769, "lr": 2.238678841830867e-05, "epoch": 10.498442367601246, "percentage": 53.33, "elapsed_time": "5:56:08", "remaining_time": "5:11:37", "throughput": 2178.9, "total_tokens": 46560016} {"current_steps": 641, "total_steps": 1200, "loss": 0.079, "lr": 2.2321706142153162e-05, "epoch": 10.515057113187954, "percentage": 53.42, "elapsed_time": "5:56:44", "remaining_time": "5:11:06", "throughput": 2179.03, "total_tokens": 46640864} {"current_steps": 642, "total_steps": 1200, "loss": 0.0798, "lr": 2.225664222272387e-05, "epoch": 10.531671858774663, "percentage": 53.5, "elapsed_time": "5:57:14", "remaining_time": "5:10:30", "throughput": 2179.26, "total_tokens": 46712072} {"current_steps": 643, "total_steps": 1200, "loss": 0.075, "lr": 2.219159710596161e-05, "epoch": 10.54828660436137, "percentage": 53.58, "elapsed_time": "5:57:48", "remaining_time": "5:09:56", "throughput": 2179.38, "total_tokens": 46787552} {"current_steps": 644, "total_steps": 1200, "loss": 0.0724, "lr": 2.212657123767834e-05, "epoch": 10.564901349948078, "percentage": 53.67, "elapsed_time": "5:58:22", "remaining_time": "5:09:24", "throughput": 2179.42, "total_tokens": 46862880} {"current_steps": 645, "total_steps": 1200, "loss": 0.0711, "lr": 2.2061565063554064e-05, "epoch": 10.581516095534788, "percentage": 53.75, "elapsed_time": "5:58:58", "remaining_time": "5:08:53", "throughput": 2179.54, "total_tokens": 46944632} {"current_steps": 646, "total_steps": 1200, "loss": 0.0699, "lr": 2.1996579029133825e-05, "epoch": 10.598130841121495, "percentage": 53.83, "elapsed_time": "5:59:35", "remaining_time": "5:08:22", "throughput": 2179.73, "total_tokens": 47029152} {"current_steps": 647, "total_steps": 1200, "loss": 0.0717, "lr": 2.1931613579824628e-05, "epoch": 10.614745586708203, "percentage": 53.92, "elapsed_time": "6:00:26", "remaining_time": "5:08:04", "throughput": 2179.46, "total_tokens": 47133448} {"current_steps": 648, "total_steps": 1200, "loss": 0.0698, "lr": 2.186666916089239e-05, "epoch": 10.631360332294912, "percentage": 54.0, "elapsed_time": "6:01:05", "remaining_time": "5:07:35", "throughput": 2179.48, "total_tokens": 47219888} {"current_steps": 649, "total_steps": 1200, "loss": 0.07, "lr": 2.180174621745889e-05, "epoch": 10.64797507788162, "percentage": 54.08, "elapsed_time": "6:01:37", "remaining_time": "5:07:00", "throughput": 2179.37, "total_tokens": 47286344} {"current_steps": 650, "total_steps": 1200, "loss": 0.0619, "lr": 2.173684519449872e-05, "epoch": 10.664589823468328, "percentage": 54.17, "elapsed_time": "6:02:27", "remaining_time": "5:06:41", "throughput": 2179.21, "total_tokens": 47392832} {"current_steps": 651, "total_steps": 1200, "loss": 0.0796, "lr": 2.1671966536836196e-05, "epoch": 10.681204569055037, "percentage": 54.25, "elapsed_time": "6:02:57", "remaining_time": "5:06:05", "throughput": 2179.16, "total_tokens": 47456448} {"current_steps": 652, "total_steps": 1200, "loss": 0.0696, "lr": 2.1607110689142393e-05, "epoch": 10.697819314641745, "percentage": 54.33, "elapsed_time": "6:03:34", "remaining_time": "5:05:34", "throughput": 2179.48, "total_tokens": 47544608} {"current_steps": 653, "total_steps": 1200, "loss": 0.0804, "lr": 2.154227809593203e-05, "epoch": 10.714434060228452, "percentage": 54.42, "elapsed_time": "6:04:01", "remaining_time": "5:04:56", "throughput": 2179.56, "total_tokens": 47605504} {"current_steps": 654, "total_steps": 1200, "loss": 0.0675, "lr": 2.1477469201560435e-05, "epoch": 10.731048805815162, "percentage": 54.5, "elapsed_time": "6:04:27", "remaining_time": "5:04:16", "throughput": 2179.87, "total_tokens": 47668856} {"current_steps": 655, "total_steps": 1200, "loss": 0.0779, "lr": 2.141268445022052e-05, "epoch": 10.74766355140187, "percentage": 54.58, "elapsed_time": "6:04:56", "remaining_time": "5:03:39", "throughput": 2179.88, "total_tokens": 47732072} {"current_steps": 656, "total_steps": 1200, "loss": 0.0645, "lr": 2.1347924285939714e-05, "epoch": 10.764278296988577, "percentage": 54.67, "elapsed_time": "6:05:35", "remaining_time": "5:03:10", "throughput": 2180.11, "total_tokens": 47821128} {"current_steps": 657, "total_steps": 1200, "loss": 0.0975, "lr": 2.1283189152576925e-05, "epoch": 10.780893042575286, "percentage": 54.75, "elapsed_time": "6:06:05", "remaining_time": "5:02:34", "throughput": 2180.13, "total_tokens": 47888432} {"current_steps": 658, "total_steps": 1200, "loss": 0.0789, "lr": 2.121847949381952e-05, "epoch": 10.797507788161994, "percentage": 54.83, "elapsed_time": "6:06:36", "remaining_time": "5:01:58", "throughput": 2180.46, "total_tokens": 47961872} {"current_steps": 659, "total_steps": 1200, "loss": 0.0607, "lr": 2.1153795753180247e-05, "epoch": 10.814122533748701, "percentage": 54.92, "elapsed_time": "6:07:16", "remaining_time": "5:01:30", "throughput": 2180.49, "total_tokens": 48049624} {"current_steps": 660, "total_steps": 1200, "loss": 0.0868, "lr": 2.1089138373994223e-05, "epoch": 10.83073727933541, "percentage": 55.0, "elapsed_time": "6:07:49", "remaining_time": "5:00:56", "throughput": 2180.38, "total_tokens": 48119288} {"current_steps": 661, "total_steps": 1200, "loss": 0.0888, "lr": 2.1024507799415903e-05, "epoch": 10.847352024922118, "percentage": 55.08, "elapsed_time": "6:08:17", "remaining_time": "5:00:18", "throughput": 2180.2, "total_tokens": 48176432} {"current_steps": 662, "total_steps": 1200, "loss": 0.1672, "lr": 2.0959904472415977e-05, "epoch": 10.863966770508826, "percentage": 55.17, "elapsed_time": "6:08:53", "remaining_time": "4:59:47", "throughput": 2180.09, "total_tokens": 48252000} {"current_steps": 663, "total_steps": 1200, "loss": 0.0815, "lr": 2.089532883577843e-05, "epoch": 10.880581516095535, "percentage": 55.25, "elapsed_time": "6:09:20", "remaining_time": "4:59:09", "throughput": 2180.29, "total_tokens": 48317320} {"current_steps": 664, "total_steps": 1200, "loss": 0.0764, "lr": 2.0830781332097446e-05, "epoch": 10.897196261682243, "percentage": 55.33, "elapsed_time": "6:09:49", "remaining_time": "4:58:32", "throughput": 2180.48, "total_tokens": 48384728} {"current_steps": 665, "total_steps": 1200, "loss": 0.181, "lr": 2.0766262403774386e-05, "epoch": 10.91381100726895, "percentage": 55.42, "elapsed_time": "6:10:18", "remaining_time": "4:57:55", "throughput": 2180.64, "total_tokens": 48451128} {"current_steps": 666, "total_steps": 1200, "loss": 0.0658, "lr": 2.070177249301476e-05, "epoch": 10.93042575285566, "percentage": 55.5, "elapsed_time": "6:10:56", "remaining_time": "4:57:25", "throughput": 2180.72, "total_tokens": 48535696} {"current_steps": 667, "total_steps": 1200, "loss": 0.0701, "lr": 2.0637312041825205e-05, "epoch": 10.947040498442368, "percentage": 55.58, "elapsed_time": "6:11:28", "remaining_time": "4:56:50", "throughput": 2180.76, "total_tokens": 48606496} {"current_steps": 668, "total_steps": 1200, "loss": 0.091, "lr": 2.057288149201042e-05, "epoch": 10.963655244029075, "percentage": 55.67, "elapsed_time": "6:11:59", "remaining_time": "4:56:15", "throughput": 2180.64, "total_tokens": 48671728} {"current_steps": 669, "total_steps": 1200, "loss": 0.0652, "lr": 2.0508481285170186e-05, "epoch": 10.980269989615785, "percentage": 55.75, "elapsed_time": "6:12:28", "remaining_time": "4:55:38", "throughput": 2180.66, "total_tokens": 48735408} {"current_steps": 670, "total_steps": 1200, "loss": 0.0916, "lr": 2.0444111862696314e-05, "epoch": 10.996884735202492, "percentage": 55.83, "elapsed_time": "6:12:56", "remaining_time": "4:55:00", "throughput": 2180.59, "total_tokens": 48794360} {"current_steps": 671, "total_steps": 1200, "loss": 0.1137, "lr": 2.037977366576961e-05, "epoch": 11.0, "percentage": 55.92, "elapsed_time": "6:13:02", "remaining_time": "4:54:05", "throughput": 2180.54, "total_tokens": 48806360} {"current_steps": 672, "total_steps": 1200, "loss": 0.0732, "lr": 2.031546713535688e-05, "epoch": 11.016614745586708, "percentage": 56.0, "elapsed_time": "6:13:32", "remaining_time": "4:53:29", "throughput": 2180.67, "total_tokens": 48873568} {"current_steps": 673, "total_steps": 1200, "loss": 0.0561, "lr": 2.025119271220789e-05, "epoch": 11.033229491173417, "percentage": 56.08, "elapsed_time": "6:14:11", "remaining_time": "4:53:01", "throughput": 2180.67, "total_tokens": 48959880} {"current_steps": 674, "total_steps": 1200, "loss": 0.0598, "lr": 2.018695083685232e-05, "epoch": 11.049844236760125, "percentage": 56.17, "elapsed_time": "6:14:54", "remaining_time": "4:52:35", "throughput": 2180.48, "total_tokens": 49048936} {"current_steps": 675, "total_steps": 1200, "loss": 0.0586, "lr": 2.0122741949596797e-05, "epoch": 11.066458982346832, "percentage": 56.25, "elapsed_time": "6:15:27", "remaining_time": "4:52:01", "throughput": 2180.43, "total_tokens": 49119216} {"current_steps": 676, "total_steps": 1200, "loss": 0.0718, "lr": 2.0058566490521847e-05, "epoch": 11.083073727933542, "percentage": 56.33, "elapsed_time": "6:15:56", "remaining_time": "4:51:24", "throughput": 2180.42, "total_tokens": 49183408} {"current_steps": 677, "total_steps": 1200, "loss": 0.062, "lr": 1.9994424899478885e-05, "epoch": 11.09968847352025, "percentage": 56.42, "elapsed_time": "6:16:39", "remaining_time": "4:50:58", "throughput": 2180.39, "total_tokens": 49275352} {"current_steps": 678, "total_steps": 1200, "loss": 0.0794, "lr": 1.9930317616087196e-05, "epoch": 11.116303219106957, "percentage": 56.5, "elapsed_time": "6:17:02", "remaining_time": "4:50:17", "throughput": 2180.38, "total_tokens": 49326536} {"current_steps": 679, "total_steps": 1200, "loss": 0.066, "lr": 1.986624507973091e-05, "epoch": 11.132917964693666, "percentage": 56.58, "elapsed_time": "6:17:30", "remaining_time": "4:49:39", "throughput": 2180.59, "total_tokens": 49390840} {"current_steps": 680, "total_steps": 1200, "loss": 0.0612, "lr": 1.980220772955602e-05, "epoch": 11.149532710280374, "percentage": 56.67, "elapsed_time": "6:18:09", "remaining_time": "4:49:10", "throughput": 2180.49, "total_tokens": 49474128} {"current_steps": 681, "total_steps": 1200, "loss": 0.0715, "lr": 1.9738206004467363e-05, "epoch": 11.166147455867081, "percentage": 56.75, "elapsed_time": "6:18:35", "remaining_time": "4:48:31", "throughput": 2180.62, "total_tokens": 49534248} {"current_steps": 682, "total_steps": 1200, "loss": 0.0535, "lr": 1.9674240343125588e-05, "epoch": 11.18276220145379, "percentage": 56.83, "elapsed_time": "6:19:17", "remaining_time": "4:48:04", "throughput": 2180.46, "total_tokens": 49621320} {"current_steps": 683, "total_steps": 1200, "loss": 0.0729, "lr": 1.961031118394418e-05, "epoch": 11.199376947040498, "percentage": 56.92, "elapsed_time": "6:19:51", "remaining_time": "4:47:31", "throughput": 2180.21, "total_tokens": 49689760} {"current_steps": 684, "total_steps": 1200, "loss": 0.0635, "lr": 1.9546418965086442e-05, "epoch": 11.215991692627206, "percentage": 57.0, "elapsed_time": "6:20:32", "remaining_time": "4:47:04", "throughput": 2179.88, "total_tokens": 49771640} {"current_steps": 685, "total_steps": 1200, "loss": 0.0644, "lr": 1.9482564124462476e-05, "epoch": 11.232606438213915, "percentage": 57.08, "elapsed_time": "6:21:01", "remaining_time": "4:46:28", "throughput": 2179.99, "total_tokens": 49838736} {"current_steps": 686, "total_steps": 1200, "loss": 0.079, "lr": 1.941874709972622e-05, "epoch": 11.249221183800623, "percentage": 57.17, "elapsed_time": "6:21:34", "remaining_time": "4:45:54", "throughput": 2179.91, "total_tokens": 49908376} {"current_steps": 687, "total_steps": 1200, "loss": 0.0518, "lr": 1.935496832827241e-05, "epoch": 11.26583592938733, "percentage": 57.25, "elapsed_time": "6:22:23", "remaining_time": "4:45:32", "throughput": 2179.59, "total_tokens": 50006464} {"current_steps": 688, "total_steps": 1200, "loss": 0.075, "lr": 1.9291228247233605e-05, "epoch": 11.28245067497404, "percentage": 57.33, "elapsed_time": "6:22:59", "remaining_time": "4:45:01", "throughput": 2179.37, "total_tokens": 50081920} {"current_steps": 689, "total_steps": 1200, "loss": 0.1651, "lr": 1.9227527293477186e-05, "epoch": 11.299065420560748, "percentage": 57.42, "elapsed_time": "6:23:26", "remaining_time": "4:44:23", "throughput": 2179.6, "total_tokens": 50145832} {"current_steps": 690, "total_steps": 1200, "loss": 0.0777, "lr": 1.9163865903602374e-05, "epoch": 11.315680166147455, "percentage": 57.5, "elapsed_time": "6:23:48", "remaining_time": "4:43:41", "throughput": 2179.6, "total_tokens": 50193752} {"current_steps": 691, "total_steps": 1200, "loss": 0.0765, "lr": 1.9100244513937174e-05, "epoch": 11.332294911734165, "percentage": 57.58, "elapsed_time": "6:24:13", "remaining_time": "4:43:01", "throughput": 2179.82, "total_tokens": 50252792} {"current_steps": 692, "total_steps": 1200, "loss": 0.0693, "lr": 1.9036663560535483e-05, "epoch": 11.348909657320872, "percentage": 57.67, "elapsed_time": "6:24:41", "remaining_time": "4:42:24", "throughput": 2179.87, "total_tokens": 50315264} {"current_steps": 693, "total_steps": 1200, "loss": 0.0658, "lr": 1.897312347917404e-05, "epoch": 11.36552440290758, "percentage": 57.75, "elapsed_time": "6:25:09", "remaining_time": "4:41:47", "throughput": 2180.0, "total_tokens": 50379280} {"current_steps": 694, "total_steps": 1200, "loss": 0.0709, "lr": 1.890962470534944e-05, "epoch": 11.38213914849429, "percentage": 57.83, "elapsed_time": "6:25:47", "remaining_time": "4:41:17", "throughput": 2179.87, "total_tokens": 50459248} {"current_steps": 695, "total_steps": 1200, "loss": 0.0649, "lr": 1.8846167674275176e-05, "epoch": 11.398753894080997, "percentage": 57.92, "elapsed_time": "6:26:33", "remaining_time": "4:40:52", "throughput": 2179.62, "total_tokens": 50552672} {"current_steps": 696, "total_steps": 1200, "loss": 0.062, "lr": 1.8782752820878634e-05, "epoch": 11.415368639667705, "percentage": 58.0, "elapsed_time": "6:27:01", "remaining_time": "4:40:15", "throughput": 2179.65, "total_tokens": 50613744} {"current_steps": 697, "total_steps": 1200, "loss": 0.0667, "lr": 1.8719380579798112e-05, "epoch": 11.431983385254414, "percentage": 58.08, "elapsed_time": "6:27:39", "remaining_time": "4:39:45", "throughput": 2179.38, "total_tokens": 50690248} {"current_steps": 698, "total_steps": 1200, "loss": 0.0638, "lr": 1.865605138537986e-05, "epoch": 11.448598130841122, "percentage": 58.17, "elapsed_time": "6:28:20", "remaining_time": "4:39:17", "throughput": 2179.45, "total_tokens": 50782136} {"current_steps": 699, "total_steps": 1200, "loss": 0.0806, "lr": 1.8592765671675084e-05, "epoch": 11.46521287642783, "percentage": 58.25, "elapsed_time": "6:28:47", "remaining_time": "4:38:39", "throughput": 2179.51, "total_tokens": 50843280} {"current_steps": 700, "total_steps": 1200, "loss": 0.0738, "lr": 1.852952387243698e-05, "epoch": 11.481827622014539, "percentage": 58.33, "elapsed_time": "6:29:17", "remaining_time": "4:38:03", "throughput": 2179.6, "total_tokens": 50909176} {"current_steps": 701, "total_steps": 1200, "loss": 0.0823, "lr": 1.846632642111777e-05, "epoch": 11.498442367601246, "percentage": 58.42, "elapsed_time": "6:29:47", "remaining_time": "4:37:27", "throughput": 2179.81, "total_tokens": 50979512} {"current_steps": 702, "total_steps": 1200, "loss": 0.0726, "lr": 1.8403173750865685e-05, "epoch": 11.515057113187954, "percentage": 58.5, "elapsed_time": "6:30:13", "remaining_time": "4:36:49", "throughput": 2180.07, "total_tokens": 51043064} {"current_steps": 703, "total_steps": 1200, "loss": 0.0812, "lr": 1.8340066294522068e-05, "epoch": 11.531671858774663, "percentage": 58.58, "elapsed_time": "6:30:47", "remaining_time": "4:36:16", "throughput": 2180.13, "total_tokens": 51117784} {"current_steps": 704, "total_steps": 1200, "loss": 0.0661, "lr": 1.827700448461836e-05, "epoch": 11.54828660436137, "percentage": 58.67, "elapsed_time": "6:31:18", "remaining_time": "4:35:41", "throughput": 2180.33, "total_tokens": 51190232} {"current_steps": 705, "total_steps": 1200, "loss": 0.0714, "lr": 1.8213988753373146e-05, "epoch": 11.564901349948078, "percentage": 58.75, "elapsed_time": "6:31:49", "remaining_time": "4:35:06", "throughput": 2180.48, "total_tokens": 51261080} {"current_steps": 706, "total_steps": 1200, "loss": 0.0573, "lr": 1.815101953268919e-05, "epoch": 11.581516095534788, "percentage": 58.83, "elapsed_time": "6:32:26", "remaining_time": "4:34:35", "throughput": 2180.48, "total_tokens": 51341592} {"current_steps": 707, "total_steps": 1200, "loss": 0.0625, "lr": 1.8088097254150486e-05, "epoch": 11.598130841121495, "percentage": 58.92, "elapsed_time": "6:32:57", "remaining_time": "4:34:00", "throughput": 2180.55, "total_tokens": 51411168} {"current_steps": 708, "total_steps": 1200, "loss": 0.0729, "lr": 1.802522234901927e-05, "epoch": 11.614745586708203, "percentage": 59.0, "elapsed_time": "6:33:21", "remaining_time": "4:33:21", "throughput": 2180.67, "total_tokens": 51467184} {"current_steps": 709, "total_steps": 1200, "loss": 0.1445, "lr": 1.7962395248233114e-05, "epoch": 11.631360332294912, "percentage": 59.08, "elapsed_time": "6:34:09", "remaining_time": "4:32:57", "throughput": 2180.52, "total_tokens": 51567896} {"current_steps": 710, "total_steps": 1200, "loss": 0.0814, "lr": 1.7899616382401936e-05, "epoch": 11.64797507788162, "percentage": 59.17, "elapsed_time": "6:34:37", "remaining_time": "4:32:20", "throughput": 2180.53, "total_tokens": 51629240} {"current_steps": 711, "total_steps": 1200, "loss": 0.087, "lr": 1.783688618180504e-05, "epoch": 11.664589823468328, "percentage": 59.25, "elapsed_time": "6:35:04", "remaining_time": "4:31:43", "throughput": 2180.45, "total_tokens": 51687552} {"current_steps": 712, "total_steps": 1200, "loss": 0.0658, "lr": 1.7774205076388206e-05, "epoch": 11.681204569055037, "percentage": 59.33, "elapsed_time": "6:35:51", "remaining_time": "4:31:19", "throughput": 2180.24, "total_tokens": 51784232} {"current_steps": 713, "total_steps": 1200, "loss": 0.0708, "lr": 1.7711573495760725e-05, "epoch": 11.697819314641745, "percentage": 59.42, "elapsed_time": "6:36:20", "remaining_time": "4:30:42", "throughput": 2180.49, "total_tokens": 51852288} {"current_steps": 714, "total_steps": 1200, "loss": 0.0526, "lr": 1.7648991869192405e-05, "epoch": 11.714434060228452, "percentage": 59.5, "elapsed_time": "6:37:03", "remaining_time": "4:30:16", "throughput": 2180.54, "total_tokens": 51948408} {"current_steps": 715, "total_steps": 1200, "loss": 0.0648, "lr": 1.7586460625610728e-05, "epoch": 11.731048805815162, "percentage": 59.58, "elapsed_time": "6:37:39", "remaining_time": "4:29:44", "throughput": 2180.66, "total_tokens": 52029512} {"current_steps": 716, "total_steps": 1200, "loss": 0.073, "lr": 1.7523980193597836e-05, "epoch": 11.74766355140187, "percentage": 59.67, "elapsed_time": "6:38:09", "remaining_time": "4:29:09", "throughput": 2180.67, "total_tokens": 52095864} {"current_steps": 717, "total_steps": 1200, "loss": 0.0764, "lr": 1.746155100138761e-05, "epoch": 11.764278296988577, "percentage": 59.75, "elapsed_time": "6:38:36", "remaining_time": "4:28:31", "throughput": 2180.67, "total_tokens": 52154880} {"current_steps": 718, "total_steps": 1200, "loss": 0.0807, "lr": 1.739917347686274e-05, "epoch": 11.780893042575286, "percentage": 59.83, "elapsed_time": "6:39:02", "remaining_time": "4:27:53", "throughput": 2180.59, "total_tokens": 52209696} {"current_steps": 719, "total_steps": 1200, "loss": 0.0552, "lr": 1.7336848047551814e-05, "epoch": 11.797507788161994, "percentage": 59.92, "elapsed_time": "6:39:40", "remaining_time": "4:27:22", "throughput": 2180.52, "total_tokens": 52290608} {"current_steps": 720, "total_steps": 1200, "loss": 0.0628, "lr": 1.7274575140626318e-05, "epoch": 11.814122533748701, "percentage": 60.0, "elapsed_time": "6:40:14", "remaining_time": "4:26:49", "throughput": 2180.58, "total_tokens": 52364616} {"current_steps": 721, "total_steps": 1200, "loss": 0.0687, "lr": 1.72123551828978e-05, "epoch": 11.83073727933541, "percentage": 60.08, "elapsed_time": "6:40:55", "remaining_time": "4:26:21", "throughput": 2180.21, "total_tokens": 52446432} {"current_steps": 722, "total_steps": 1200, "loss": 0.1985, "lr": 1.7150188600814877e-05, "epoch": 11.847352024922118, "percentage": 60.17, "elapsed_time": "6:41:19", "remaining_time": "4:25:41", "throughput": 2180.3, "total_tokens": 52500320} {"current_steps": 723, "total_steps": 1200, "loss": 0.0639, "lr": 1.7088075820460346e-05, "epoch": 11.863966770508826, "percentage": 60.25, "elapsed_time": "6:41:54", "remaining_time": "4:25:09", "throughput": 2180.18, "total_tokens": 52572888} {"current_steps": 724, "total_steps": 1200, "loss": 0.0715, "lr": 1.702601726754825e-05, "epoch": 11.880581516095535, "percentage": 60.33, "elapsed_time": "6:42:27", "remaining_time": "4:24:36", "throughput": 2180.28, "total_tokens": 52649240} {"current_steps": 725, "total_steps": 1200, "loss": 0.0638, "lr": 1.6964013367420966e-05, "epoch": 11.897196261682243, "percentage": 60.42, "elapsed_time": "6:43:04", "remaining_time": "4:24:05", "throughput": 2180.37, "total_tokens": 52731312} {"current_steps": 726, "total_steps": 1200, "loss": 0.0668, "lr": 1.690206454504627e-05, "epoch": 11.91381100726895, "percentage": 60.5, "elapsed_time": "6:43:46", "remaining_time": "4:23:37", "throughput": 2180.65, "total_tokens": 52829968} {"current_steps": 727, "total_steps": 1200, "loss": 0.0567, "lr": 1.6840171225014457e-05, "epoch": 11.93042575285566, "percentage": 60.58, "elapsed_time": "6:44:40", "remaining_time": "4:23:17", "throughput": 2180.32, "total_tokens": 52938304} {"current_steps": 728, "total_steps": 1200, "loss": 0.0798, "lr": 1.677833383153542e-05, "epoch": 11.947040498442368, "percentage": 60.67, "elapsed_time": "6:45:11", "remaining_time": "4:22:42", "throughput": 2180.2, "total_tokens": 53003736} {"current_steps": 729, "total_steps": 1200, "loss": 0.0621, "lr": 1.6716552788435724e-05, "epoch": 11.963655244029075, "percentage": 60.75, "elapsed_time": "6:45:41", "remaining_time": "4:22:06", "throughput": 2180.3, "total_tokens": 53071872} {"current_steps": 730, "total_steps": 1200, "loss": 0.06, "lr": 1.665482851915573e-05, "epoch": 11.980269989615785, "percentage": 60.83, "elapsed_time": "6:46:14", "remaining_time": "4:21:33", "throughput": 2180.35, "total_tokens": 53145192} {"current_steps": 731, "total_steps": 1200, "loss": 0.0551, "lr": 1.659316144674666e-05, "epoch": 11.996884735202492, "percentage": 60.92, "elapsed_time": "6:46:53", "remaining_time": "4:21:03", "throughput": 2180.34, "total_tokens": 53229240} {"current_steps": 732, "total_steps": 1200, "loss": 0.0551, "lr": 1.6531551993867717e-05, "epoch": 12.0, "percentage": 61.0, "elapsed_time": "6:46:59", "remaining_time": "4:20:12", "throughput": 2180.49, "total_tokens": 53245592} {"current_steps": 733, "total_steps": 1200, "loss": 0.0617, "lr": 1.6470000582783204e-05, "epoch": 12.016614745586708, "percentage": 61.08, "elapsed_time": "6:47:36", "remaining_time": "4:19:41", "throughput": 2180.46, "total_tokens": 53327016} {"current_steps": 734, "total_steps": 1200, "loss": 0.062, "lr": 1.64085076353596e-05, "epoch": 12.033229491173417, "percentage": 61.17, "elapsed_time": "6:48:08", "remaining_time": "4:19:07", "throughput": 2180.47, "total_tokens": 53396464} {"current_steps": 735, "total_steps": 1200, "loss": 0.0568, "lr": 1.6347073573062672e-05, "epoch": 12.049844236760125, "percentage": 61.25, "elapsed_time": "6:48:52", "remaining_time": "4:18:40", "throughput": 2180.15, "total_tokens": 53485056} {"current_steps": 736, "total_steps": 1200, "loss": 0.0666, "lr": 1.6285698816954624e-05, "epoch": 12.066458982346832, "percentage": 61.33, "elapsed_time": "6:49:20", "remaining_time": "4:18:04", "throughput": 2180.44, "total_tokens": 53553376} {"current_steps": 737, "total_steps": 1200, "loss": 0.0675, "lr": 1.622438378769114e-05, "epoch": 12.083073727933542, "percentage": 61.42, "elapsed_time": "6:49:48", "remaining_time": "4:17:27", "throughput": 2180.51, "total_tokens": 53615616} {"current_steps": 738, "total_steps": 1200, "loss": 0.0631, "lr": 1.6163128905518578e-05, "epoch": 12.09968847352025, "percentage": 61.5, "elapsed_time": "6:50:23", "remaining_time": "4:16:55", "throughput": 2180.37, "total_tokens": 53689512} {"current_steps": 739, "total_steps": 1200, "loss": 0.0775, "lr": 1.6101934590271032e-05, "epoch": 12.116303219106957, "percentage": 61.58, "elapsed_time": "6:50:47", "remaining_time": "4:16:15", "throughput": 2180.49, "total_tokens": 53743080} {"current_steps": 740, "total_steps": 1200, "loss": 0.0568, "lr": 1.6040801261367493e-05, "epoch": 12.132917964693666, "percentage": 61.67, "elapsed_time": "6:51:29", "remaining_time": "4:15:47", "throughput": 2180.31, "total_tokens": 53830432} {"current_steps": 741, "total_steps": 1200, "loss": 0.0545, "lr": 1.5979729337808955e-05, "epoch": 12.149532710280374, "percentage": 61.75, "elapsed_time": "6:52:04", "remaining_time": "4:15:15", "throughput": 2180.61, "total_tokens": 53914536} {"current_steps": 742, "total_steps": 1200, "loss": 0.0553, "lr": 1.5918719238175544e-05, "epoch": 12.166147455867081, "percentage": 61.83, "elapsed_time": "6:52:31", "remaining_time": "4:14:38", "throughput": 2180.72, "total_tokens": 53977072} {"current_steps": 743, "total_steps": 1200, "loss": 0.0609, "lr": 1.5857771380623643e-05, "epoch": 12.18276220145379, "percentage": 61.92, "elapsed_time": "6:53:04", "remaining_time": "4:14:04", "throughput": 2180.82, "total_tokens": 54051576} {"current_steps": 744, "total_steps": 1200, "loss": 0.0629, "lr": 1.5796886182883053e-05, "epoch": 12.199376947040498, "percentage": 62.0, "elapsed_time": "6:53:40", "remaining_time": "4:13:32", "throughput": 2180.73, "total_tokens": 54126832} {"current_steps": 745, "total_steps": 1200, "loss": 0.0579, "lr": 1.5736064062254094e-05, "epoch": 12.215991692627206, "percentage": 62.08, "elapsed_time": "6:54:18", "remaining_time": "4:13:02", "throughput": 2180.49, "total_tokens": 54203832} {"current_steps": 746, "total_steps": 1200, "loss": 0.0652, "lr": 1.5675305435604775e-05, "epoch": 12.232606438213915, "percentage": 62.17, "elapsed_time": "6:54:49", "remaining_time": "4:12:27", "throughput": 2180.42, "total_tokens": 54268712} {"current_steps": 747, "total_steps": 1200, "loss": 0.1332, "lr": 1.561461071936792e-05, "epoch": 12.249221183800623, "percentage": 62.25, "elapsed_time": "6:55:22", "remaining_time": "4:11:53", "throughput": 2180.45, "total_tokens": 54342024} {"current_steps": 748, "total_steps": 1200, "loss": 0.0549, "lr": 1.5553980329538326e-05, "epoch": 12.26583592938733, "percentage": 62.33, "elapsed_time": "6:55:51", "remaining_time": "4:11:17", "throughput": 2180.52, "total_tokens": 54407352} {"current_steps": 749, "total_steps": 1200, "loss": 0.0639, "lr": 1.549341468166988e-05, "epoch": 12.28245067497404, "percentage": 62.42, "elapsed_time": "6:56:17", "remaining_time": "4:10:40", "throughput": 2180.58, "total_tokens": 54466560} {"current_steps": 750, "total_steps": 1200, "loss": 0.0611, "lr": 1.5432914190872757e-05, "epoch": 12.299065420560748, "percentage": 62.5, "elapsed_time": "6:57:00", "remaining_time": "4:10:12", "throughput": 2180.6, "total_tokens": 54559704} {"current_steps": 751, "total_steps": 1200, "loss": 0.0735, "lr": 1.537247927181055e-05, "epoch": 12.315680166147455, "percentage": 62.58, "elapsed_time": "6:57:32", "remaining_time": "4:09:38", "throughput": 2180.37, "total_tokens": 54623736} {"current_steps": 752, "total_steps": 1200, "loss": 0.0655, "lr": 1.5312110338697426e-05, "epoch": 12.332294911734165, "percentage": 62.67, "elapsed_time": "6:58:09", "remaining_time": "4:09:06", "throughput": 2180.2, "total_tokens": 54699928} {"current_steps": 753, "total_steps": 1200, "loss": 0.0529, "lr": 1.5251807805295302e-05, "epoch": 12.348909657320872, "percentage": 62.75, "elapsed_time": "6:58:49", "remaining_time": "4:08:37", "throughput": 2180.06, "total_tokens": 54782808} {"current_steps": 754, "total_steps": 1200, "loss": 0.0607, "lr": 1.519157208491097e-05, "epoch": 12.36552440290758, "percentage": 62.83, "elapsed_time": "6:59:30", "remaining_time": "4:08:08", "throughput": 2179.9, "total_tokens": 54868720} {"current_steps": 755, "total_steps": 1200, "loss": 0.0496, "lr": 1.5131403590393323e-05, "epoch": 12.38213914849429, "percentage": 62.92, "elapsed_time": "7:00:14", "remaining_time": "4:07:41", "throughput": 2179.7, "total_tokens": 54960384} {"current_steps": 756, "total_steps": 1200, "loss": 0.0553, "lr": 1.5071302734130489e-05, "epoch": 12.398753894080997, "percentage": 63.0, "elapsed_time": "7:00:49", "remaining_time": "4:07:09", "throughput": 2180.01, "total_tokens": 55044232} {"current_steps": 757, "total_steps": 1200, "loss": 0.1655, "lr": 1.5011269928047003e-05, "epoch": 12.415368639667705, "percentage": 63.08, "elapsed_time": "7:01:26", "remaining_time": "4:06:37", "throughput": 2180.02, "total_tokens": 55125632} {"current_steps": 758, "total_steps": 1200, "loss": 0.0588, "lr": 1.4951305583601e-05, "epoch": 12.431983385254414, "percentage": 63.17, "elapsed_time": "7:02:02", "remaining_time": "4:06:05", "throughput": 2179.93, "total_tokens": 55201720} {"current_steps": 759, "total_steps": 1200, "loss": 0.0522, "lr": 1.4891410111781378e-05, "epoch": 12.448598130841122, "percentage": 63.25, "elapsed_time": "7:02:30", "remaining_time": "4:05:29", "throughput": 2180.08, "total_tokens": 55265832} {"current_steps": 760, "total_steps": 1200, "loss": 0.0776, "lr": 1.4831583923104999e-05, "epoch": 12.46521287642783, "percentage": 63.33, "elapsed_time": "7:02:53", "remaining_time": "4:04:49", "throughput": 2180.1, "total_tokens": 55316928} {"current_steps": 761, "total_steps": 1200, "loss": 0.059, "lr": 1.4771827427613855e-05, "epoch": 12.481827622014539, "percentage": 63.42, "elapsed_time": "7:03:26", "remaining_time": "4:04:16", "throughput": 2180.18, "total_tokens": 55391232} {"current_steps": 762, "total_steps": 1200, "loss": 0.0604, "lr": 1.4712141034872282e-05, "epoch": 12.498442367601246, "percentage": 63.5, "elapsed_time": "7:03:57", "remaining_time": "4:03:41", "throughput": 2180.28, "total_tokens": 55460984} {"current_steps": 763, "total_steps": 1200, "loss": 0.0556, "lr": 1.4652525153964131e-05, "epoch": 12.515057113187954, "percentage": 63.58, "elapsed_time": "7:04:34", "remaining_time": "4:03:10", "throughput": 2180.12, "total_tokens": 55537056} {"current_steps": 764, "total_steps": 1200, "loss": 0.0598, "lr": 1.4592980193489975e-05, "epoch": 12.531671858774663, "percentage": 63.67, "elapsed_time": "7:05:16", "remaining_time": "4:02:41", "throughput": 2179.98, "total_tokens": 55625272} {"current_steps": 765, "total_steps": 1200, "loss": 0.05, "lr": 1.4533506561564306e-05, "epoch": 12.54828660436137, "percentage": 63.75, "elapsed_time": "7:05:53", "remaining_time": "4:02:10", "throughput": 2179.79, "total_tokens": 55701992} {"current_steps": 766, "total_steps": 1200, "loss": 0.066, "lr": 1.4474104665812727e-05, "epoch": 12.564901349948078, "percentage": 63.83, "elapsed_time": "7:06:19", "remaining_time": "4:01:32", "throughput": 2179.84, "total_tokens": 55759312} {"current_steps": 767, "total_steps": 1200, "loss": 0.0541, "lr": 1.44147749133692e-05, "epoch": 12.581516095534788, "percentage": 63.92, "elapsed_time": "7:06:57", "remaining_time": "4:01:01", "throughput": 2179.79, "total_tokens": 55840400} {"current_steps": 768, "total_steps": 1200, "loss": 0.0623, "lr": 1.4355517710873184e-05, "epoch": 12.598130841121495, "percentage": 64.0, "elapsed_time": "7:07:28", "remaining_time": "4:00:27", "throughput": 2179.91, "total_tokens": 55912176} {"current_steps": 769, "total_steps": 1200, "loss": 0.0542, "lr": 1.429633346446693e-05, "epoch": 12.614745586708203, "percentage": 64.08, "elapsed_time": "7:08:05", "remaining_time": "3:59:55", "throughput": 2179.8, "total_tokens": 55989272} {"current_steps": 770, "total_steps": 1200, "loss": 0.0719, "lr": 1.4237222579792618e-05, "epoch": 12.631360332294912, "percentage": 64.17, "elapsed_time": "7:08:30", "remaining_time": "3:59:17", "throughput": 2179.95, "total_tokens": 56046720} {"current_steps": 771, "total_steps": 1200, "loss": 0.0572, "lr": 1.4178185461989662e-05, "epoch": 12.64797507788162, "percentage": 64.25, "elapsed_time": "7:09:11", "remaining_time": "3:58:48", "throughput": 2179.78, "total_tokens": 56132720} {"current_steps": 772, "total_steps": 1200, "loss": 0.0648, "lr": 1.4119222515691816e-05, "epoch": 12.664589823468328, "percentage": 64.33, "elapsed_time": "7:09:36", "remaining_time": "3:58:10", "throughput": 2179.83, "total_tokens": 56187824} {"current_steps": 773, "total_steps": 1200, "loss": 0.0576, "lr": 1.4060334145024542e-05, "epoch": 12.681204569055037, "percentage": 64.42, "elapsed_time": "7:10:07", "remaining_time": "3:57:35", "throughput": 2180.0, "total_tokens": 56259248} {"current_steps": 774, "total_steps": 1200, "loss": 0.0637, "lr": 1.4001520753602121e-05, "epoch": 12.697819314641745, "percentage": 64.5, "elapsed_time": "7:10:52", "remaining_time": "3:57:08", "throughput": 2179.59, "total_tokens": 56347584} {"current_steps": 775, "total_steps": 1200, "loss": 0.0584, "lr": 1.3942782744524973e-05, "epoch": 12.714434060228452, "percentage": 64.58, "elapsed_time": "7:11:31", "remaining_time": "3:56:38", "throughput": 2179.58, "total_tokens": 56433184} {"current_steps": 776, "total_steps": 1200, "loss": 0.0866, "lr": 1.388412052037682e-05, "epoch": 12.731048805815162, "percentage": 64.67, "elapsed_time": "7:11:58", "remaining_time": "3:56:01", "throughput": 2179.61, "total_tokens": 56491176} {"current_steps": 777, "total_steps": 1200, "loss": 0.0536, "lr": 1.3825534483221974e-05, "epoch": 12.74766355140187, "percentage": 64.75, "elapsed_time": "7:12:28", "remaining_time": "3:55:26", "throughput": 2179.7, "total_tokens": 56560952} {"current_steps": 778, "total_steps": 1200, "loss": 0.0638, "lr": 1.376702503460259e-05, "epoch": 12.764278296988577, "percentage": 64.83, "elapsed_time": "7:12:56", "remaining_time": "3:54:50", "throughput": 2179.74, "total_tokens": 56622384} {"current_steps": 779, "total_steps": 1200, "loss": 0.0606, "lr": 1.3708592575535858e-05, "epoch": 12.780893042575286, "percentage": 64.92, "elapsed_time": "7:13:33", "remaining_time": "3:54:18", "throughput": 2179.98, "total_tokens": 56709344} {"current_steps": 780, "total_steps": 1200, "loss": 0.0752, "lr": 1.3650237506511331e-05, "epoch": 12.797507788161994, "percentage": 65.0, "elapsed_time": "7:14:06", "remaining_time": "3:53:44", "throughput": 2179.98, "total_tokens": 56780664} {"current_steps": 781, "total_steps": 1200, "loss": 0.0537, "lr": 1.3591960227488098e-05, "epoch": 12.814122533748701, "percentage": 65.08, "elapsed_time": "7:14:47", "remaining_time": "3:53:15", "throughput": 2179.69, "total_tokens": 56862528} {"current_steps": 782, "total_steps": 1200, "loss": 0.0575, "lr": 1.3533761137892136e-05, "epoch": 12.83073727933541, "percentage": 65.17, "elapsed_time": "7:15:21", "remaining_time": "3:52:42", "throughput": 2179.58, "total_tokens": 56933384} {"current_steps": 783, "total_steps": 1200, "loss": 0.0555, "lr": 1.3475640636613446e-05, "epoch": 12.847352024922118, "percentage": 65.25, "elapsed_time": "7:16:01", "remaining_time": "3:52:12", "throughput": 2179.62, "total_tokens": 57023008} {"current_steps": 784, "total_steps": 1200, "loss": 0.0743, "lr": 1.3417599122003464e-05, "epoch": 12.863966770508826, "percentage": 65.33, "elapsed_time": "7:16:36", "remaining_time": "3:51:39", "throughput": 2179.53, "total_tokens": 57095032} {"current_steps": 785, "total_steps": 1200, "loss": 0.1914, "lr": 1.3359636991872215e-05, "epoch": 12.880581516095535, "percentage": 65.42, "elapsed_time": "7:17:06", "remaining_time": "3:51:05", "throughput": 2179.55, "total_tokens": 57162840} {"current_steps": 786, "total_steps": 1200, "loss": 0.0483, "lr": 1.330175464348567e-05, "epoch": 12.897196261682243, "percentage": 65.5, "elapsed_time": "7:17:47", "remaining_time": "3:50:35", "throughput": 2179.41, "total_tokens": 57247992} {"current_steps": 787, "total_steps": 1200, "loss": 0.0709, "lr": 1.3243952473562942e-05, "epoch": 12.91381100726895, "percentage": 65.58, "elapsed_time": "7:18:16", "remaining_time": "3:50:00", "throughput": 2179.43, "total_tokens": 57312216} {"current_steps": 788, "total_steps": 1200, "loss": 0.0697, "lr": 1.3186230878273653e-05, "epoch": 12.93042575285566, "percentage": 65.67, "elapsed_time": "7:18:42", "remaining_time": "3:49:22", "throughput": 2179.43, "total_tokens": 57367104} {"current_steps": 789, "total_steps": 1200, "loss": 0.0562, "lr": 1.312859025323514e-05, "epoch": 12.947040498442368, "percentage": 65.75, "elapsed_time": "7:19:14", "remaining_time": "3:48:48", "throughput": 2179.42, "total_tokens": 57437176} {"current_steps": 790, "total_steps": 1200, "loss": 0.0653, "lr": 1.3071030993509788e-05, "epoch": 12.963655244029075, "percentage": 65.83, "elapsed_time": "7:19:37", "remaining_time": "3:48:09", "throughput": 2179.69, "total_tokens": 57495304} {"current_steps": 791, "total_steps": 1200, "loss": 0.0566, "lr": 1.3013553493602338e-05, "epoch": 12.980269989615785, "percentage": 65.92, "elapsed_time": "7:20:18", "remaining_time": "3:47:40", "throughput": 2179.62, "total_tokens": 57582400} {"current_steps": 792, "total_steps": 1200, "loss": 0.0577, "lr": 1.2956158147457115e-05, "epoch": 12.996884735202492, "percentage": 66.0, "elapsed_time": "7:20:57", "remaining_time": "3:47:09", "throughput": 2179.58, "total_tokens": 57666136} {"current_steps": 793, "total_steps": 1200, "loss": 0.0425, "lr": 1.2898845348455418e-05, "epoch": 13.0, "percentage": 66.08, "elapsed_time": "7:21:04", "remaining_time": "3:46:22", "throughput": 2179.64, "total_tokens": 57682352} {"current_steps": 794, "total_steps": 1200, "loss": 0.0538, "lr": 1.2841615489412739e-05, "epoch": 13.016614745586708, "percentage": 66.17, "elapsed_time": "7:21:31", "remaining_time": "3:45:46", "throughput": 2179.74, "total_tokens": 57745080} {"current_steps": 795, "total_steps": 1200, "loss": 0.0569, "lr": 1.2784468962576136e-05, "epoch": 13.033229491173417, "percentage": 66.25, "elapsed_time": "7:22:02", "remaining_time": "3:45:11", "throughput": 2179.57, "total_tokens": 57808680} {"current_steps": 796, "total_steps": 1200, "loss": 0.067, "lr": 1.272740615962148e-05, "epoch": 13.049844236760125, "percentage": 66.33, "elapsed_time": "7:22:35", "remaining_time": "3:44:37", "throughput": 2179.53, "total_tokens": 57878016} {"current_steps": 797, "total_steps": 1200, "loss": 0.0593, "lr": 1.2670427471650864e-05, "epoch": 13.066458982346832, "percentage": 66.42, "elapsed_time": "7:23:01", "remaining_time": "3:44:01", "throughput": 2179.59, "total_tokens": 57937640} {"current_steps": 798, "total_steps": 1200, "loss": 0.0554, "lr": 1.261353328918981e-05, "epoch": 13.083073727933542, "percentage": 66.5, "elapsed_time": "7:23:33", "remaining_time": "3:43:26", "throughput": 2179.68, "total_tokens": 58009448} {"current_steps": 799, "total_steps": 1200, "loss": 0.2005, "lr": 1.2556724002184696e-05, "epoch": 13.09968847352025, "percentage": 66.58, "elapsed_time": "7:23:59", "remaining_time": "3:42:49", "throughput": 2179.84, "total_tokens": 58068936} {"current_steps": 800, "total_steps": 1200, "loss": 0.0501, "lr": 1.2500000000000006e-05, "epoch": 13.116303219106957, "percentage": 66.67, "elapsed_time": "7:24:34", "remaining_time": "3:42:17", "throughput": 2179.95, "total_tokens": 58148824} {"current_steps": 801, "total_steps": 1200, "loss": 0.048, "lr": 1.2443361671415687e-05, "epoch": 13.132917964693666, "percentage": 66.75, "elapsed_time": "7:25:06", "remaining_time": "3:41:43", "throughput": 2180.0, "total_tokens": 58220720} {"current_steps": 802, "total_steps": 1200, "loss": 0.05, "lr": 1.2386809404624521e-05, "epoch": 13.149532710280374, "percentage": 66.83, "elapsed_time": "7:25:40", "remaining_time": "3:41:10", "throughput": 2179.87, "total_tokens": 58290944} {"current_steps": 803, "total_steps": 1200, "loss": 0.0517, "lr": 1.2330343587229396e-05, "epoch": 13.166147455867081, "percentage": 66.92, "elapsed_time": "7:26:25", "remaining_time": "3:40:42", "throughput": 2179.6, "total_tokens": 58382480} {"current_steps": 804, "total_steps": 1200, "loss": 0.0558, "lr": 1.2273964606240718e-05, "epoch": 13.18276220145379, "percentage": 67.0, "elapsed_time": "7:26:54", "remaining_time": "3:40:07", "throughput": 2179.5, "total_tokens": 58443424} {"current_steps": 805, "total_steps": 1200, "loss": 0.0602, "lr": 1.2217672848073702e-05, "epoch": 13.199376947040498, "percentage": 67.08, "elapsed_time": "7:27:39", "remaining_time": "3:39:39", "throughput": 2179.27, "total_tokens": 58534424} {"current_steps": 806, "total_steps": 1200, "loss": 0.0585, "lr": 1.2161468698545755e-05, "epoch": 13.215991692627206, "percentage": 67.17, "elapsed_time": "7:28:07", "remaining_time": "3:39:03", "throughput": 2179.37, "total_tokens": 58597336} {"current_steps": 807, "total_steps": 1200, "loss": 0.0642, "lr": 1.2105352542873815e-05, "epoch": 13.232606438213915, "percentage": 67.25, "elapsed_time": "7:28:30", "remaining_time": "3:38:25", "throughput": 2179.33, "total_tokens": 58647872} {"current_steps": 808, "total_steps": 1200, "loss": 0.0544, "lr": 1.2049324765671749e-05, "epoch": 13.249221183800623, "percentage": 67.33, "elapsed_time": "7:29:13", "remaining_time": "3:37:56", "throughput": 2178.99, "total_tokens": 58731544} {"current_steps": 809, "total_steps": 1200, "loss": 0.0639, "lr": 1.199338575094765e-05, "epoch": 13.26583592938733, "percentage": 67.42, "elapsed_time": "7:29:39", "remaining_time": "3:37:19", "throughput": 2179.02, "total_tokens": 58788488} {"current_steps": 810, "total_steps": 1200, "loss": 0.0392, "lr": 1.1937535882101281e-05, "epoch": 13.28245067497404, "percentage": 67.5, "elapsed_time": "7:30:29", "remaining_time": "3:36:54", "throughput": 2178.59, "total_tokens": 58886640} {"current_steps": 811, "total_steps": 1200, "loss": 0.0644, "lr": 1.1881775541921378e-05, "epoch": 13.299065420560748, "percentage": 67.58, "elapsed_time": "7:30:55", "remaining_time": "3:36:17", "throughput": 2178.58, "total_tokens": 58943304} {"current_steps": 812, "total_steps": 1200, "loss": 0.0632, "lr": 1.1826105112583061e-05, "epoch": 13.315680166147455, "percentage": 67.67, "elapsed_time": "7:31:30", "remaining_time": "3:35:44", "throughput": 2178.65, "total_tokens": 59020992} {"current_steps": 813, "total_steps": 1200, "loss": 0.0424, "lr": 1.1770524975645238e-05, "epoch": 13.332294911734165, "percentage": 67.75, "elapsed_time": "7:32:12", "remaining_time": "3:35:15", "throughput": 2178.62, "total_tokens": 59111368} {"current_steps": 814, "total_steps": 1200, "loss": 0.0574, "lr": 1.1715035512047925e-05, "epoch": 13.348909657320872, "percentage": 67.83, "elapsed_time": "7:32:54", "remaining_time": "3:34:46", "throughput": 2178.34, "total_tokens": 59194880} {"current_steps": 815, "total_steps": 1200, "loss": 0.0521, "lr": 1.1659637102109714e-05, "epoch": 13.36552440290758, "percentage": 67.92, "elapsed_time": "7:33:20", "remaining_time": "3:34:09", "throughput": 2178.3, "total_tokens": 59250648} {"current_steps": 816, "total_steps": 1200, "loss": 0.0515, "lr": 1.1604330125525079e-05, "epoch": 13.38213914849429, "percentage": 68.0, "elapsed_time": "7:33:54", "remaining_time": "3:33:36", "throughput": 2178.33, "total_tokens": 59324888} {"current_steps": 817, "total_steps": 1200, "loss": 0.0585, "lr": 1.154911496136188e-05, "epoch": 13.398753894080997, "percentage": 68.08, "elapsed_time": "7:34:28", "remaining_time": "3:33:03", "throughput": 2178.18, "total_tokens": 59395120} {"current_steps": 818, "total_steps": 1200, "loss": 0.0526, "lr": 1.1493991988058625e-05, "epoch": 13.415368639667705, "percentage": 68.17, "elapsed_time": "7:35:06", "remaining_time": "3:32:31", "throughput": 2178.09, "total_tokens": 59475152} {"current_steps": 819, "total_steps": 1200, "loss": 0.0484, "lr": 1.1438961583422037e-05, "epoch": 13.431983385254414, "percentage": 68.25, "elapsed_time": "7:35:33", "remaining_time": "3:31:55", "throughput": 2178.24, "total_tokens": 59538328} {"current_steps": 820, "total_steps": 1200, "loss": 0.0599, "lr": 1.1384024124624324e-05, "epoch": 13.448598130841122, "percentage": 68.33, "elapsed_time": "7:36:05", "remaining_time": "3:31:21", "throughput": 2178.18, "total_tokens": 59606280} {"current_steps": 821, "total_steps": 1200, "loss": 0.0585, "lr": 1.1329179988200694e-05, "epoch": 13.46521287642783, "percentage": 68.42, "elapsed_time": "7:36:45", "remaining_time": "3:30:51", "throughput": 2178.15, "total_tokens": 59694032} {"current_steps": 822, "total_steps": 1200, "loss": 0.0534, "lr": 1.1274429550046704e-05, "epoch": 13.481827622014539, "percentage": 68.5, "elapsed_time": "7:37:18", "remaining_time": "3:30:17", "throughput": 2178.11, "total_tokens": 59764904} {"current_steps": 823, "total_steps": 1200, "loss": 0.0486, "lr": 1.121977318541575e-05, "epoch": 13.498442367601246, "percentage": 68.58, "elapsed_time": "7:37:52", "remaining_time": "3:29:44", "throughput": 2178.12, "total_tokens": 59839232} {"current_steps": 824, "total_steps": 1200, "loss": 0.0608, "lr": 1.11652112689164e-05, "epoch": 13.515057113187954, "percentage": 68.67, "elapsed_time": "7:38:26", "remaining_time": "3:29:11", "throughput": 2177.96, "total_tokens": 59907248} {"current_steps": 825, "total_steps": 1200, "loss": 0.062, "lr": 1.1110744174509952e-05, "epoch": 13.531671858774663, "percentage": 68.75, "elapsed_time": "7:38:54", "remaining_time": "3:28:35", "throughput": 2178.06, "total_tokens": 59971912} {"current_steps": 826, "total_steps": 1200, "loss": 0.0495, "lr": 1.1056372275507749e-05, "epoch": 13.54828660436137, "percentage": 68.83, "elapsed_time": "7:39:32", "remaining_time": "3:28:04", "throughput": 2178.06, "total_tokens": 60054728} {"current_steps": 827, "total_steps": 1200, "loss": 0.0506, "lr": 1.1002095944568707e-05, "epoch": 13.564901349948078, "percentage": 68.92, "elapsed_time": "7:40:08", "remaining_time": "3:27:32", "throughput": 2178.07, "total_tokens": 60133824} {"current_steps": 828, "total_steps": 1200, "loss": 0.058, "lr": 1.0947915553696742e-05, "epoch": 13.581516095534788, "percentage": 69.0, "elapsed_time": "7:40:36", "remaining_time": "3:26:56", "throughput": 2178.11, "total_tokens": 60194832} {"current_steps": 829, "total_steps": 1200, "loss": 0.0592, "lr": 1.089383147423815e-05, "epoch": 13.598130841121495, "percentage": 69.08, "elapsed_time": "7:41:13", "remaining_time": "3:26:24", "throughput": 2178.27, "total_tokens": 60280224} {"current_steps": 830, "total_steps": 1200, "loss": 0.0658, "lr": 1.0839844076879185e-05, "epoch": 13.614745586708203, "percentage": 69.17, "elapsed_time": "7:41:42", "remaining_time": "3:25:49", "throughput": 2178.18, "total_tokens": 60341144} {"current_steps": 831, "total_steps": 1200, "loss": 0.0504, "lr": 1.07859537316434e-05, "epoch": 13.631360332294912, "percentage": 69.25, "elapsed_time": "7:42:21", "remaining_time": "3:25:18", "throughput": 2178.12, "total_tokens": 60425128} {"current_steps": 832, "total_steps": 1200, "loss": 0.0523, "lr": 1.0732160807889211e-05, "epoch": 13.64797507788162, "percentage": 69.33, "elapsed_time": "7:43:05", "remaining_time": "3:24:49", "throughput": 2178.1, "total_tokens": 60520456} {"current_steps": 833, "total_steps": 1200, "loss": 0.0495, "lr": 1.0678465674307273e-05, "epoch": 13.664589823468328, "percentage": 69.42, "elapsed_time": "7:43:49", "remaining_time": "3:24:21", "throughput": 2178.16, "total_tokens": 60617640} {"current_steps": 834, "total_steps": 1200, "loss": 0.0632, "lr": 1.0624868698918045e-05, "epoch": 13.681204569055037, "percentage": 69.5, "elapsed_time": "7:44:16", "remaining_time": "3:23:44", "throughput": 2178.19, "total_tokens": 60676584} {"current_steps": 835, "total_steps": 1200, "loss": 0.1454, "lr": 1.0571370249069162e-05, "epoch": 13.697819314641745, "percentage": 69.58, "elapsed_time": "7:44:50", "remaining_time": "3:23:11", "throughput": 2178.15, "total_tokens": 60750760} {"current_steps": 836, "total_steps": 1200, "loss": 0.0637, "lr": 1.0517970691433035e-05, "epoch": 13.714434060228452, "percentage": 69.67, "elapsed_time": "7:45:24", "remaining_time": "3:22:38", "throughput": 2178.11, "total_tokens": 60823520} {"current_steps": 837, "total_steps": 1200, "loss": 0.0587, "lr": 1.0464670392004235e-05, "epoch": 13.731048805815162, "percentage": 69.75, "elapsed_time": "7:46:07", "remaining_time": "3:22:09", "throughput": 2178.12, "total_tokens": 60917712} {"current_steps": 838, "total_steps": 1200, "loss": 0.0646, "lr": 1.0411469716097067e-05, "epoch": 13.74766355140187, "percentage": 69.83, "elapsed_time": "7:46:35", "remaining_time": "3:21:33", "throughput": 2178.23, "total_tokens": 60979928} {"current_steps": 839, "total_steps": 1200, "loss": 0.0609, "lr": 1.0358369028342985e-05, "epoch": 13.764278296988577, "percentage": 69.92, "elapsed_time": "7:47:07", "remaining_time": "3:20:59", "throughput": 2178.24, "total_tokens": 61050592} {"current_steps": 840, "total_steps": 1200, "loss": 0.0457, "lr": 1.0305368692688174e-05, "epoch": 13.780893042575286, "percentage": 70.0, "elapsed_time": "7:47:42", "remaining_time": "3:20:26", "throughput": 2178.25, "total_tokens": 61126704} {"current_steps": 841, "total_steps": 1200, "loss": 0.0592, "lr": 1.0252469072390994e-05, "epoch": 13.797507788161994, "percentage": 70.08, "elapsed_time": "7:48:12", "remaining_time": "3:19:51", "throughput": 2178.26, "total_tokens": 61192016} {"current_steps": 842, "total_steps": 1200, "loss": 0.0687, "lr": 1.0199670530019511e-05, "epoch": 13.814122533748701, "percentage": 70.17, "elapsed_time": "7:48:44", "remaining_time": "3:19:17", "throughput": 2178.35, "total_tokens": 61264256} {"current_steps": 843, "total_steps": 1200, "loss": 0.0559, "lr": 1.0146973427449038e-05, "epoch": 13.83073727933541, "percentage": 70.25, "elapsed_time": "7:49:13", "remaining_time": "3:18:42", "throughput": 2178.43, "total_tokens": 61330712} {"current_steps": 844, "total_steps": 1200, "loss": 0.0539, "lr": 1.0094378125859602e-05, "epoch": 13.847352024922118, "percentage": 70.33, "elapsed_time": "7:49:44", "remaining_time": "3:18:08", "throughput": 2178.64, "total_tokens": 61403992} {"current_steps": 845, "total_steps": 1200, "loss": 0.0551, "lr": 1.0041884985733524e-05, "epoch": 13.863966770508826, "percentage": 70.42, "elapsed_time": "7:50:36", "remaining_time": "3:17:42", "throughput": 2178.23, "total_tokens": 61505072} {"current_steps": 846, "total_steps": 1200, "loss": 0.058, "lr": 9.989494366852904e-06, "epoch": 13.880581516095535, "percentage": 70.5, "elapsed_time": "7:51:08", "remaining_time": "3:17:08", "throughput": 2178.2, "total_tokens": 61574704} {"current_steps": 847, "total_steps": 1200, "loss": 0.0584, "lr": 9.937206628297172e-06, "epoch": 13.897196261682243, "percentage": 70.58, "elapsed_time": "7:51:41", "remaining_time": "3:16:34", "throughput": 2178.26, "total_tokens": 61647640} {"current_steps": 848, "total_steps": 1200, "loss": 0.0682, "lr": 9.88502212844063e-06, "epoch": 13.91381100726895, "percentage": 70.67, "elapsed_time": "7:52:09", "remaining_time": "3:15:59", "throughput": 2178.28, "total_tokens": 61708696} {"current_steps": 849, "total_steps": 1200, "loss": 0.0436, "lr": 9.832941224950012e-06, "epoch": 13.93042575285566, "percentage": 70.75, "elapsed_time": "7:52:50", "remaining_time": "3:15:29", "throughput": 2178.34, "total_tokens": 61801464} {"current_steps": 850, "total_steps": 1200, "loss": 0.0593, "lr": 9.780964274781984e-06, "epoch": 13.947040498442368, "percentage": 70.83, "elapsed_time": "7:53:28", "remaining_time": "3:14:57", "throughput": 2178.1, "total_tokens": 61876376} {"current_steps": 851, "total_steps": 1200, "loss": 0.0562, "lr": 9.729091634180756e-06, "epoch": 13.963655244029075, "percentage": 70.92, "elapsed_time": "7:54:01", "remaining_time": "3:14:23", "throughput": 2178.09, "total_tokens": 61947232} {"current_steps": 852, "total_steps": 1200, "loss": 0.0485, "lr": 9.677323658675594e-06, "epoch": 13.980269989615785, "percentage": 71.0, "elapsed_time": "7:54:39", "remaining_time": "3:13:52", "throughput": 2177.95, "total_tokens": 62026520} {"current_steps": 853, "total_steps": 1200, "loss": 0.1437, "lr": 9.625660703078392e-06, "epoch": 13.996884735202492, "percentage": 71.08, "elapsed_time": "7:55:16", "remaining_time": "3:13:20", "throughput": 2177.93, "total_tokens": 62107152} {"current_steps": 854, "total_steps": 1200, "loss": 0.054, "lr": 9.574103121481288e-06, "epoch": 14.0, "percentage": 71.17, "elapsed_time": "7:55:20", "remaining_time": "3:12:35", "throughput": 2177.99, "total_tokens": 62117944} {"current_steps": 855, "total_steps": 1200, "loss": 0.0527, "lr": 9.522651267254149e-06, "epoch": 14.016614745586708, "percentage": 71.25, "elapsed_time": "7:55:53", "remaining_time": "3:12:01", "throughput": 2178.08, "total_tokens": 62192136} {"current_steps": 856, "total_steps": 1200, "loss": 0.0479, "lr": 9.471305493042243e-06, "epoch": 14.033229491173417, "percentage": 71.33, "elapsed_time": "7:56:36", "remaining_time": "3:11:31", "throughput": 2178.26, "total_tokens": 62290128} {"current_steps": 857, "total_steps": 1200, "loss": 0.0542, "lr": 9.420066150763748e-06, "epoch": 14.049844236760125, "percentage": 71.42, "elapsed_time": "7:57:02", "remaining_time": "3:10:55", "throughput": 2178.26, "total_tokens": 62346640} {"current_steps": 858, "total_steps": 1200, "loss": 0.0412, "lr": 9.368933591607378e-06, "epoch": 14.066458982346832, "percentage": 71.5, "elapsed_time": "7:57:38", "remaining_time": "3:10:23", "throughput": 2178.39, "total_tokens": 62430464} {"current_steps": 859, "total_steps": 1200, "loss": 0.055, "lr": 9.317908166029962e-06, "epoch": 14.083073727933542, "percentage": 71.58, "elapsed_time": "7:58:05", "remaining_time": "3:09:47", "throughput": 2178.38, "total_tokens": 62487224} {"current_steps": 860, "total_steps": 1200, "loss": 0.0644, "lr": 9.266990223754069e-06, "epoch": 14.09968847352025, "percentage": 71.67, "elapsed_time": "7:58:45", "remaining_time": "3:09:16", "throughput": 2178.24, "total_tokens": 62570352} {"current_steps": 861, "total_steps": 1200, "loss": 0.0509, "lr": 9.216180113765558e-06, "epoch": 14.116303219106957, "percentage": 71.75, "elapsed_time": "7:59:30", "remaining_time": "3:08:47", "throughput": 2178.56, "total_tokens": 62677432} {"current_steps": 862, "total_steps": 1200, "loss": 0.0538, "lr": 9.16547818431125e-06, "epoch": 14.132917964693666, "percentage": 71.83, "elapsed_time": "8:00:01", "remaining_time": "3:08:13", "throughput": 2178.71, "total_tokens": 62750304} {"current_steps": 863, "total_steps": 1200, "loss": 0.0495, "lr": 9.114884782896483e-06, "epoch": 14.149532710280374, "percentage": 71.92, "elapsed_time": "8:00:30", "remaining_time": "3:07:38", "throughput": 2178.83, "total_tokens": 62817736} {"current_steps": 864, "total_steps": 1200, "loss": 0.0521, "lr": 9.064400256282757e-06, "epoch": 14.166147455867081, "percentage": 72.0, "elapsed_time": "8:01:07", "remaining_time": "3:07:06", "throughput": 2178.8, "total_tokens": 62896016} {"current_steps": 865, "total_steps": 1200, "loss": 0.0483, "lr": 9.014024950485383e-06, "epoch": 14.18276220145379, "percentage": 72.08, "elapsed_time": "8:01:36", "remaining_time": "3:06:31", "throughput": 2178.72, "total_tokens": 62957488} {"current_steps": 866, "total_steps": 1200, "loss": 0.0526, "lr": 8.963759210771052e-06, "epoch": 14.199376947040498, "percentage": 72.17, "elapsed_time": "8:02:02", "remaining_time": "3:05:54", "throughput": 2178.71, "total_tokens": 63013344} {"current_steps": 867, "total_steps": 1200, "loss": 0.0543, "lr": 8.913603381655528e-06, "epoch": 14.215991692627206, "percentage": 72.25, "elapsed_time": "8:02:29", "remaining_time": "3:05:19", "throughput": 2178.73, "total_tokens": 63073504} {"current_steps": 868, "total_steps": 1200, "loss": 0.0438, "lr": 8.863557806901233e-06, "epoch": 14.232606438213915, "percentage": 72.33, "elapsed_time": "8:03:01", "remaining_time": "3:04:44", "throughput": 2178.77, "total_tokens": 63143344} {"current_steps": 869, "total_steps": 1200, "loss": 0.041, "lr": 8.813622829514956e-06, "epoch": 14.249221183800623, "percentage": 72.42, "elapsed_time": "8:03:44", "remaining_time": "3:04:15", "throughput": 2179.07, "total_tokens": 63245488} {"current_steps": 870, "total_steps": 1200, "loss": 0.0523, "lr": 8.763798791745411e-06, "epoch": 14.26583592938733, "percentage": 72.5, "elapsed_time": "8:04:06", "remaining_time": "3:03:37", "throughput": 2179.16, "total_tokens": 63297208} {"current_steps": 871, "total_steps": 1200, "loss": 0.055, "lr": 8.714086035080996e-06, "epoch": 14.28245067497404, "percentage": 72.58, "elapsed_time": "8:04:35", "remaining_time": "3:03:02", "throughput": 2179.08, "total_tokens": 63357392} {"current_steps": 872, "total_steps": 1200, "loss": 0.0499, "lr": 8.664484900247363e-06, "epoch": 14.299065420560748, "percentage": 72.67, "elapsed_time": "8:05:08", "remaining_time": "3:02:29", "throughput": 2179.05, "total_tokens": 63429064} {"current_steps": 873, "total_steps": 1200, "loss": 0.0698, "lr": 8.614995727205156e-06, "epoch": 14.315680166147455, "percentage": 72.75, "elapsed_time": "8:05:32", "remaining_time": "3:01:52", "throughput": 2178.96, "total_tokens": 63478112} {"current_steps": 874, "total_steps": 1200, "loss": 0.0464, "lr": 8.565618855147603e-06, "epoch": 14.332294911734165, "percentage": 72.83, "elapsed_time": "8:06:09", "remaining_time": "3:01:20", "throughput": 2178.96, "total_tokens": 63558472} {"current_steps": 875, "total_steps": 1200, "loss": 0.0474, "lr": 8.51635462249828e-06, "epoch": 14.348909657320872, "percentage": 72.92, "elapsed_time": "8:06:49", "remaining_time": "3:00:49", "throughput": 2178.82, "total_tokens": 63641776} {"current_steps": 876, "total_steps": 1200, "loss": 0.0458, "lr": 8.467203366908707e-06, "epoch": 14.36552440290758, "percentage": 73.0, "elapsed_time": "8:07:44", "remaining_time": "3:00:23", "throughput": 2178.31, "total_tokens": 63746080} {"current_steps": 877, "total_steps": 1200, "loss": 0.1133, "lr": 8.41816542525608e-06, "epoch": 14.38213914849429, "percentage": 73.08, "elapsed_time": "8:08:35", "remaining_time": "2:59:56", "throughput": 2177.93, "total_tokens": 63846320} {"current_steps": 878, "total_steps": 1200, "loss": 0.0462, "lr": 8.369241133640982e-06, "epoch": 14.398753894080997, "percentage": 73.17, "elapsed_time": "8:09:06", "remaining_time": "2:59:22", "throughput": 2178.05, "total_tokens": 63917736} {"current_steps": 879, "total_steps": 1200, "loss": 0.133, "lr": 8.320430827385003e-06, "epoch": 14.415368639667705, "percentage": 73.25, "elapsed_time": "8:09:33", "remaining_time": "2:58:46", "throughput": 2178.18, "total_tokens": 63981576} {"current_steps": 880, "total_steps": 1200, "loss": 0.0649, "lr": 8.271734841028553e-06, "epoch": 14.431983385254414, "percentage": 73.33, "elapsed_time": "8:09:57", "remaining_time": "2:58:10", "throughput": 2178.14, "total_tokens": 64032848} {"current_steps": 881, "total_steps": 1200, "loss": 0.0533, "lr": 8.22315350832843e-06, "epoch": 14.448598130841122, "percentage": 73.42, "elapsed_time": "8:10:25", "remaining_time": "2:57:34", "throughput": 2178.35, "total_tokens": 64098072} {"current_steps": 882, "total_steps": 1200, "loss": 0.0484, "lr": 8.174687162255672e-06, "epoch": 14.46521287642783, "percentage": 73.5, "elapsed_time": "8:11:02", "remaining_time": "2:57:02", "throughput": 2178.6, "total_tokens": 64186088} {"current_steps": 883, "total_steps": 1200, "loss": 0.05, "lr": 8.126336134993176e-06, "epoch": 14.481827622014539, "percentage": 73.58, "elapsed_time": "8:11:47", "remaining_time": "2:56:33", "throughput": 2178.38, "total_tokens": 64277520} {"current_steps": 884, "total_steps": 1200, "loss": 0.0603, "lr": 8.078100757933485e-06, "epoch": 14.498442367601246, "percentage": 73.67, "elapsed_time": "8:12:17", "remaining_time": "2:55:58", "throughput": 2178.25, "total_tokens": 64340728} {"current_steps": 885, "total_steps": 1200, "loss": 0.0497, "lr": 8.029981361676456e-06, "epoch": 14.515057113187954, "percentage": 73.75, "elapsed_time": "8:12:54", "remaining_time": "2:55:26", "throughput": 2178.15, "total_tokens": 64417080} {"current_steps": 886, "total_steps": 1200, "loss": 0.0396, "lr": 7.981978276027055e-06, "epoch": 14.531671858774663, "percentage": 73.83, "elapsed_time": "8:13:34", "remaining_time": "2:54:55", "throughput": 2178.14, "total_tokens": 64503560} {"current_steps": 887, "total_steps": 1200, "loss": 0.0505, "lr": 7.934091829993055e-06, "epoch": 14.54828660436137, "percentage": 73.92, "elapsed_time": "8:14:05", "remaining_time": "2:54:21", "throughput": 2178.26, "total_tokens": 64575432} {"current_steps": 888, "total_steps": 1200, "loss": 0.0455, "lr": 7.886322351782783e-06, "epoch": 14.564901349948078, "percentage": 74.0, "elapsed_time": "8:14:49", "remaining_time": "2:53:51", "throughput": 2178.21, "total_tokens": 64669216} {"current_steps": 889, "total_steps": 1200, "loss": 0.0633, "lr": 7.838670168802909e-06, "epoch": 14.581516095534788, "percentage": 74.08, "elapsed_time": "8:15:14", "remaining_time": "2:53:15", "throughput": 2178.34, "total_tokens": 64728640} {"current_steps": 890, "total_steps": 1200, "loss": 0.0598, "lr": 7.791135607656147e-06, "epoch": 14.598130841121495, "percentage": 74.17, "elapsed_time": "8:15:36", "remaining_time": "2:52:37", "throughput": 2178.44, "total_tokens": 64780032} {"current_steps": 891, "total_steps": 1200, "loss": 0.0536, "lr": 7.743718994139071e-06, "epoch": 14.614745586708203, "percentage": 74.25, "elapsed_time": "8:16:16", "remaining_time": "2:52:06", "throughput": 2178.33, "total_tokens": 64863760} {"current_steps": 892, "total_steps": 1200, "loss": 0.0515, "lr": 7.696420653239833e-06, "epoch": 14.631360332294912, "percentage": 74.33, "elapsed_time": "8:16:45", "remaining_time": "2:51:31", "throughput": 2178.41, "total_tokens": 64928808} {"current_steps": 893, "total_steps": 1200, "loss": 0.0579, "lr": 7.649240909135965e-06, "epoch": 14.64797507788162, "percentage": 74.42, "elapsed_time": "8:17:19", "remaining_time": "2:50:58", "throughput": 2178.26, "total_tokens": 64999256} {"current_steps": 894, "total_steps": 1200, "loss": 0.0462, "lr": 7.602180085192143e-06, "epoch": 14.664589823468328, "percentage": 74.5, "elapsed_time": "8:17:57", "remaining_time": "2:50:26", "throughput": 2178.28, "total_tokens": 65081544} {"current_steps": 895, "total_steps": 1200, "loss": 0.0545, "lr": 7.555238503958001e-06, "epoch": 14.681204569055037, "percentage": 74.58, "elapsed_time": "8:18:25", "remaining_time": "2:49:51", "throughput": 2178.36, "total_tokens": 65145096} {"current_steps": 896, "total_steps": 1200, "loss": 0.0446, "lr": 7.508416487165862e-06, "epoch": 14.697819314641745, "percentage": 74.67, "elapsed_time": "8:19:01", "remaining_time": "2:49:18", "throughput": 2178.54, "total_tokens": 65229504} {"current_steps": 897, "total_steps": 1200, "loss": 0.0511, "lr": 7.461714355728608e-06, "epoch": 14.714434060228452, "percentage": 74.75, "elapsed_time": "8:19:32", "remaining_time": "2:48:44", "throughput": 2178.61, "total_tokens": 65299408} {"current_steps": 898, "total_steps": 1200, "loss": 0.061, "lr": 7.415132429737407e-06, "epoch": 14.731048805815162, "percentage": 74.83, "elapsed_time": "8:20:07", "remaining_time": "2:48:11", "throughput": 2178.65, "total_tokens": 65376216} {"current_steps": 899, "total_steps": 1200, "loss": 0.0453, "lr": 7.368671028459564e-06, "epoch": 14.74766355140187, "percentage": 74.92, "elapsed_time": "8:20:45", "remaining_time": "2:47:39", "throughput": 2178.59, "total_tokens": 65457240} {"current_steps": 900, "total_steps": 1200, "loss": 0.0585, "lr": 7.3223304703363135e-06, "epoch": 14.764278296988577, "percentage": 75.0, "elapsed_time": "8:21:18", "remaining_time": "2:47:06", "throughput": 2178.69, "total_tokens": 65531064} {"current_steps": 901, "total_steps": 1200, "loss": 0.1328, "lr": 7.276111072980663e-06, "epoch": 14.780893042575286, "percentage": 75.08, "elapsed_time": "8:21:52", "remaining_time": "2:46:32", "throughput": 2178.52, "total_tokens": 65600688} {"current_steps": 902, "total_steps": 1200, "loss": 0.0515, "lr": 7.230013153175188e-06, "epoch": 14.797507788161994, "percentage": 75.17, "elapsed_time": "8:22:30", "remaining_time": "2:46:00", "throughput": 2178.39, "total_tokens": 65678640} {"current_steps": 903, "total_steps": 1200, "loss": 0.0496, "lr": 7.184037026869867e-06, "epoch": 14.814122533748701, "percentage": 75.25, "elapsed_time": "8:23:05", "remaining_time": "2:45:28", "throughput": 2178.36, "total_tokens": 65755816} {"current_steps": 904, "total_steps": 1200, "loss": 0.0499, "lr": 7.138183009179922e-06, "epoch": 14.83073727933541, "percentage": 75.33, "elapsed_time": "8:23:43", "remaining_time": "2:44:56", "throughput": 2178.35, "total_tokens": 65837696} {"current_steps": 905, "total_steps": 1200, "loss": 0.0545, "lr": 7.092451414383644e-06, "epoch": 14.847352024922118, "percentage": 75.42, "elapsed_time": "8:24:14", "remaining_time": "2:44:22", "throughput": 2178.23, "total_tokens": 65901792} {"current_steps": 906, "total_steps": 1200, "loss": 0.0614, "lr": 7.046842555920283e-06, "epoch": 14.863966770508826, "percentage": 75.5, "elapsed_time": "8:24:48", "remaining_time": "2:43:48", "throughput": 2178.02, "total_tokens": 65969960} {"current_steps": 907, "total_steps": 1200, "loss": 0.053, "lr": 7.00135674638783e-06, "epoch": 14.880581516095535, "percentage": 75.58, "elapsed_time": "8:25:18", "remaining_time": "2:43:14", "throughput": 2178.34, "total_tokens": 66043752} {"current_steps": 908, "total_steps": 1200, "loss": 0.0562, "lr": 6.9559942975409465e-06, "epoch": 14.897196261682243, "percentage": 75.67, "elapsed_time": "8:25:44", "remaining_time": "2:42:38", "throughput": 2178.37, "total_tokens": 66100456} {"current_steps": 909, "total_steps": 1200, "loss": 0.0582, "lr": 6.91075552028877e-06, "epoch": 14.91381100726895, "percentage": 75.75, "elapsed_time": "8:26:17", "remaining_time": "2:42:04", "throughput": 2178.52, "total_tokens": 66177320} {"current_steps": 910, "total_steps": 1200, "loss": 0.0582, "lr": 6.865640724692815e-06, "epoch": 14.93042575285566, "percentage": 75.83, "elapsed_time": "8:26:41", "remaining_time": "2:41:28", "throughput": 2178.57, "total_tokens": 66231656} {"current_steps": 911, "total_steps": 1200, "loss": 0.0477, "lr": 6.820650219964833e-06, "epoch": 14.947040498442368, "percentage": 75.92, "elapsed_time": "8:27:24", "remaining_time": "2:40:57", "throughput": 2178.29, "total_tokens": 66315768} {"current_steps": 912, "total_steps": 1200, "loss": 0.0522, "lr": 6.775784314464717e-06, "epoch": 14.963655244029075, "percentage": 76.0, "elapsed_time": "8:28:01", "remaining_time": "2:40:25", "throughput": 2178.05, "total_tokens": 66391256} {"current_steps": 913, "total_steps": 1200, "loss": 0.0617, "lr": 6.731043315698346e-06, "epoch": 14.980269989615785, "percentage": 76.08, "elapsed_time": "8:28:39", "remaining_time": "2:39:53", "throughput": 2177.93, "total_tokens": 66469184} {"current_steps": 914, "total_steps": 1200, "loss": 0.0553, "lr": 6.686427530315534e-06, "epoch": 14.996884735202492, "percentage": 76.17, "elapsed_time": "8:29:08", "remaining_time": "2:39:18", "throughput": 2178.19, "total_tokens": 66540392} {"current_steps": 915, "total_steps": 1200, "loss": 0.038, "lr": 6.641937264107867e-06, "epoch": 15.0, "percentage": 76.25, "elapsed_time": "8:29:17", "remaining_time": "2:38:37", "throughput": 2178.26, "total_tokens": 66561792} {"current_steps": 916, "total_steps": 1200, "loss": 0.0557, "lr": 6.5975728220066425e-06, "epoch": 15.016614745586708, "percentage": 76.33, "elapsed_time": "8:29:49", "remaining_time": "2:38:04", "throughput": 2178.37, "total_tokens": 66635072} {"current_steps": 917, "total_steps": 1200, "loss": 0.0475, "lr": 6.553334508080794e-06, "epoch": 15.033229491173417, "percentage": 76.42, "elapsed_time": "8:30:24", "remaining_time": "2:37:31", "throughput": 2178.29, "total_tokens": 66708200} {"current_steps": 918, "total_steps": 1200, "loss": 0.0401, "lr": 6.509222625534755e-06, "epoch": 15.049844236760125, "percentage": 76.5, "elapsed_time": "8:31:04", "remaining_time": "2:36:59", "throughput": 2178.32, "total_tokens": 66796600} {"current_steps": 919, "total_steps": 1200, "loss": 0.0624, "lr": 6.465237476706449e-06, "epoch": 15.066458982346832, "percentage": 76.58, "elapsed_time": "8:31:43", "remaining_time": "2:36:28", "throughput": 2178.23, "total_tokens": 66878560} {"current_steps": 920, "total_steps": 1200, "loss": 0.0502, "lr": 6.421379363065142e-06, "epoch": 15.083073727933542, "percentage": 76.67, "elapsed_time": "8:32:15", "remaining_time": "2:35:54", "throughput": 2178.09, "total_tokens": 66944600} {"current_steps": 921, "total_steps": 1200, "loss": 0.0384, "lr": 6.377648585209456e-06, "epoch": 15.09968847352025, "percentage": 76.75, "elapsed_time": "8:32:55", "remaining_time": "2:35:22", "throughput": 2177.91, "total_tokens": 67026488} {"current_steps": 922, "total_steps": 1200, "loss": 0.0525, "lr": 6.334045442865219e-06, "epoch": 15.116303219106957, "percentage": 76.83, "elapsed_time": "8:33:27", "remaining_time": "2:34:48", "throughput": 2177.92, "total_tokens": 67095344} {"current_steps": 923, "total_steps": 1200, "loss": 0.0567, "lr": 6.290570234883505e-06, "epoch": 15.132917964693666, "percentage": 76.92, "elapsed_time": "8:34:00", "remaining_time": "2:34:15", "throughput": 2178.06, "total_tokens": 67171352} {"current_steps": 924, "total_steps": 1200, "loss": 0.0611, "lr": 6.247223259238511e-06, "epoch": 15.149532710280374, "percentage": 77.0, "elapsed_time": "8:34:29", "remaining_time": "2:33:40", "throughput": 2177.97, "total_tokens": 67232288} {"current_steps": 925, "total_steps": 1200, "loss": 0.0583, "lr": 6.204004813025568e-06, "epoch": 15.166147455867081, "percentage": 77.08, "elapsed_time": "8:34:51", "remaining_time": "2:33:03", "throughput": 2178.17, "total_tokens": 67287128} {"current_steps": 926, "total_steps": 1200, "loss": 0.0419, "lr": 6.160915192459058e-06, "epoch": 15.18276220145379, "percentage": 77.17, "elapsed_time": "8:35:27", "remaining_time": "2:32:31", "throughput": 2178.04, "total_tokens": 67362248} {"current_steps": 927, "total_steps": 1200, "loss": 0.0484, "lr": 6.117954692870412e-06, "epoch": 15.199376947040498, "percentage": 77.25, "elapsed_time": "8:35:56", "remaining_time": "2:31:56", "throughput": 2178.16, "total_tokens": 67427448} {"current_steps": 928, "total_steps": 1200, "loss": 0.0477, "lr": 6.075123608706093e-06, "epoch": 15.215991692627206, "percentage": 77.33, "elapsed_time": "8:36:34", "remaining_time": "2:31:24", "throughput": 2177.99, "total_tokens": 67506648} {"current_steps": 929, "total_steps": 1200, "loss": 0.0411, "lr": 6.032422233525545e-06, "epoch": 15.232606438213915, "percentage": 77.42, "elapsed_time": "8:37:14", "remaining_time": "2:30:53", "throughput": 2177.88, "total_tokens": 67589024} {"current_steps": 930, "total_steps": 1200, "loss": 0.0511, "lr": 5.989850859999227e-06, "epoch": 15.249221183800623, "percentage": 77.5, "elapsed_time": "8:37:43", "remaining_time": "2:30:18", "throughput": 2177.79, "total_tokens": 67649592} {"current_steps": 931, "total_steps": 1200, "loss": 0.048, "lr": 5.947409779906554e-06, "epoch": 15.26583592938733, "percentage": 77.58, "elapsed_time": "8:38:14", "remaining_time": "2:29:44", "throughput": 2177.78, "total_tokens": 67717080} {"current_steps": 932, "total_steps": 1200, "loss": 0.0511, "lr": 5.905099284133952e-06, "epoch": 15.28245067497404, "percentage": 77.67, "elapsed_time": "8:38:48", "remaining_time": "2:29:11", "throughput": 2177.77, "total_tokens": 67791560} {"current_steps": 933, "total_steps": 1200, "loss": 0.0452, "lr": 5.8629196626728e-06, "epoch": 15.299065420560748, "percentage": 77.75, "elapsed_time": "8:39:14", "remaining_time": "2:28:35", "throughput": 2177.95, "total_tokens": 67852376} {"current_steps": 934, "total_steps": 1200, "loss": 0.0384, "lr": 5.820871204617515e-06, "epoch": 15.315680166147455, "percentage": 77.83, "elapsed_time": "8:39:59", "remaining_time": "2:28:05", "throughput": 2177.82, "total_tokens": 67946192} {"current_steps": 935, "total_steps": 1200, "loss": 0.0404, "lr": 5.778954198163514e-06, "epoch": 15.332294911734165, "percentage": 77.92, "elapsed_time": "8:40:33", "remaining_time": "2:27:32", "throughput": 2177.97, "total_tokens": 68025248} {"current_steps": 936, "total_steps": 1200, "loss": 0.0517, "lr": 5.737168930605272e-06, "epoch": 15.348909657320872, "percentage": 78.0, "elapsed_time": "8:41:12", "remaining_time": "2:27:00", "throughput": 2177.94, "total_tokens": 68109776} {"current_steps": 937, "total_steps": 1200, "loss": 0.0481, "lr": 5.6955156883343265e-06, "epoch": 15.36552440290758, "percentage": 78.08, "elapsed_time": "8:41:47", "remaining_time": "2:26:27", "throughput": 2178.01, "total_tokens": 68187496} {"current_steps": 938, "total_steps": 1200, "loss": 0.0429, "lr": 5.653994756837347e-06, "epoch": 15.38213914849429, "percentage": 78.17, "elapsed_time": "8:42:24", "remaining_time": "2:25:55", "throughput": 2177.98, "total_tokens": 68268560} {"current_steps": 939, "total_steps": 1200, "loss": 0.058, "lr": 5.612606420694141e-06, "epoch": 15.398753894080997, "percentage": 78.25, "elapsed_time": "8:42:53", "remaining_time": "2:25:20", "throughput": 2178.01, "total_tokens": 68331208} {"current_steps": 940, "total_steps": 1200, "loss": 0.0561, "lr": 5.571350963575728e-06, "epoch": 15.415368639667705, "percentage": 78.33, "elapsed_time": "8:43:23", "remaining_time": "2:24:46", "throughput": 2178.13, "total_tokens": 68401712} {"current_steps": 941, "total_steps": 1200, "loss": 0.0411, "lr": 5.530228668242402e-06, "epoch": 15.431983385254414, "percentage": 78.42, "elapsed_time": "8:44:03", "remaining_time": "2:24:14", "throughput": 2178.13, "total_tokens": 68487824} {"current_steps": 942, "total_steps": 1200, "loss": 0.05, "lr": 5.489239816541755e-06, "epoch": 15.448598130841122, "percentage": 78.5, "elapsed_time": "8:44:40", "remaining_time": "2:23:41", "throughput": 2177.82, "total_tokens": 68558256} {"current_steps": 943, "total_steps": 1200, "loss": 0.0493, "lr": 5.4483846894068046e-06, "epoch": 15.46521287642783, "percentage": 78.58, "elapsed_time": "8:45:27", "remaining_time": "2:23:12", "throughput": 2177.57, "total_tokens": 68652768} {"current_steps": 944, "total_steps": 1200, "loss": 0.0433, "lr": 5.4076635668540075e-06, "epoch": 15.481827622014539, "percentage": 78.67, "elapsed_time": "8:46:10", "remaining_time": "2:22:41", "throughput": 2177.54, "total_tokens": 68745352} {"current_steps": 945, "total_steps": 1200, "loss": 0.0411, "lr": 5.367076727981382e-06, "epoch": 15.498442367601246, "percentage": 78.75, "elapsed_time": "8:46:54", "remaining_time": "2:22:10", "throughput": 2177.21, "total_tokens": 68830520} {"current_steps": 946, "total_steps": 1200, "loss": 0.2515, "lr": 5.326624450966569e-06, "epoch": 15.515057113187954, "percentage": 78.83, "elapsed_time": "8:47:20", "remaining_time": "2:21:35", "throughput": 2177.37, "total_tokens": 68894064} {"current_steps": 947, "total_steps": 1200, "loss": 0.0441, "lr": 5.286307013064956e-06, "epoch": 15.531671858774663, "percentage": 78.92, "elapsed_time": "8:47:53", "remaining_time": "2:21:01", "throughput": 2177.34, "total_tokens": 68963888} {"current_steps": 948, "total_steps": 1200, "loss": 0.048, "lr": 5.24612469060774e-06, "epoch": 15.54828660436137, "percentage": 79.0, "elapsed_time": "8:48:18", "remaining_time": "2:20:26", "throughput": 2177.55, "total_tokens": 69025032} {"current_steps": 949, "total_steps": 1200, "loss": 0.0477, "lr": 5.206077759000069e-06, "epoch": 15.564901349948078, "percentage": 79.08, "elapsed_time": "8:48:46", "remaining_time": "2:19:51", "throughput": 2177.61, "total_tokens": 69087736} {"current_steps": 950, "total_steps": 1200, "loss": 0.0533, "lr": 5.166166492719124e-06, "epoch": 15.581516095534788, "percentage": 79.17, "elapsed_time": "8:49:23", "remaining_time": "2:19:18", "throughput": 2177.58, "total_tokens": 69168720} {"current_steps": 951, "total_steps": 1200, "loss": 0.0589, "lr": 5.12639116531225e-06, "epoch": 15.598130841121495, "percentage": 79.25, "elapsed_time": "8:49:55", "remaining_time": "2:18:45", "throughput": 2177.48, "total_tokens": 69234496} {"current_steps": 952, "total_steps": 1200, "loss": 0.0476, "lr": 5.086752049395094e-06, "epoch": 15.614745586708203, "percentage": 79.33, "elapsed_time": "8:50:26", "remaining_time": "2:18:10", "throughput": 2177.56, "total_tokens": 69303200} {"current_steps": 953, "total_steps": 1200, "loss": 0.0486, "lr": 5.0472494166497135e-06, "epoch": 15.631360332294912, "percentage": 79.42, "elapsed_time": "8:51:05", "remaining_time": "2:17:38", "throughput": 2177.55, "total_tokens": 69387968} {"current_steps": 954, "total_steps": 1200, "loss": 0.0428, "lr": 5.007883537822736e-06, "epoch": 15.64797507788162, "percentage": 79.5, "elapsed_time": "8:51:41", "remaining_time": "2:17:06", "throughput": 2177.61, "total_tokens": 69468496} {"current_steps": 955, "total_steps": 1200, "loss": 0.0485, "lr": 4.9686546827234865e-06, "epoch": 15.664589823468328, "percentage": 79.58, "elapsed_time": "8:52:14", "remaining_time": "2:16:32", "throughput": 2177.73, "total_tokens": 69545408} {"current_steps": 956, "total_steps": 1200, "loss": 0.0468, "lr": 4.929563120222141e-06, "epoch": 15.681204569055037, "percentage": 79.67, "elapsed_time": "8:52:41", "remaining_time": "2:15:57", "throughput": 2177.75, "total_tokens": 69604664} {"current_steps": 957, "total_steps": 1200, "loss": 0.061, "lr": 4.890609118247888e-06, "epoch": 15.697819314641745, "percentage": 79.75, "elapsed_time": "8:53:08", "remaining_time": "2:15:22", "throughput": 2177.76, "total_tokens": 69663456} {"current_steps": 958, "total_steps": 1200, "loss": 0.0588, "lr": 4.851792943787109e-06, "epoch": 15.714434060228452, "percentage": 79.83, "elapsed_time": "8:53:37", "remaining_time": "2:14:47", "throughput": 2177.75, "total_tokens": 69726392} {"current_steps": 959, "total_steps": 1200, "loss": 0.0527, "lr": 4.813114862881502e-06, "epoch": 15.731048805815162, "percentage": 79.92, "elapsed_time": "8:53:59", "remaining_time": "2:14:11", "throughput": 2177.79, "total_tokens": 69774792} {"current_steps": 960, "total_steps": 1200, "loss": 0.0377, "lr": 4.7745751406263165e-06, "epoch": 15.74766355140187, "percentage": 80.0, "elapsed_time": "8:54:42", "remaining_time": "2:13:40", "throughput": 2177.66, "total_tokens": 69864152} {"current_steps": 961, "total_steps": 1200, "loss": 0.0498, "lr": 4.7361740411684865e-06, "epoch": 15.764278296988577, "percentage": 80.08, "elapsed_time": "8:55:12", "remaining_time": "2:13:06", "throughput": 2177.71, "total_tokens": 69932112} {"current_steps": 962, "total_steps": 1200, "loss": 0.0467, "lr": 4.6979118277048426e-06, "epoch": 15.780893042575286, "percentage": 80.17, "elapsed_time": "8:55:43", "remaining_time": "2:12:32", "throughput": 2177.64, "total_tokens": 69997512} {"current_steps": 963, "total_steps": 1200, "loss": 0.047, "lr": 4.659788762480327e-06, "epoch": 15.797507788161994, "percentage": 80.25, "elapsed_time": "8:56:11", "remaining_time": "2:11:57", "throughput": 2177.8, "total_tokens": 70063808} {"current_steps": 964, "total_steps": 1200, "loss": 0.0486, "lr": 4.621805106786142e-06, "epoch": 15.814122533748701, "percentage": 80.33, "elapsed_time": "8:56:49", "remaining_time": "2:11:25", "throughput": 2177.64, "total_tokens": 70140760} {"current_steps": 965, "total_steps": 1200, "loss": 0.0468, "lr": 4.583961120958027e-06, "epoch": 15.83073727933541, "percentage": 80.42, "elapsed_time": "8:57:26", "remaining_time": "2:10:52", "throughput": 2177.57, "total_tokens": 70218960} {"current_steps": 966, "total_steps": 1200, "loss": 0.0467, "lr": 4.54625706437441e-06, "epoch": 15.847352024922118, "percentage": 80.5, "elapsed_time": "8:57:58", "remaining_time": "2:10:19", "throughput": 2177.71, "total_tokens": 70293824} {"current_steps": 967, "total_steps": 1200, "loss": 0.0515, "lr": 4.508693195454694e-06, "epoch": 15.863966770508826, "percentage": 80.58, "elapsed_time": "8:58:39", "remaining_time": "2:09:47", "throughput": 2177.79, "total_tokens": 70384464} {"current_steps": 968, "total_steps": 1200, "loss": 0.042, "lr": 4.4712697716574e-06, "epoch": 15.880581516095535, "percentage": 80.67, "elapsed_time": "8:59:09", "remaining_time": "2:09:13", "throughput": 2177.93, "total_tokens": 70455440} {"current_steps": 969, "total_steps": 1200, "loss": 0.0487, "lr": 4.433987049478508e-06, "epoch": 15.897196261682243, "percentage": 80.75, "elapsed_time": "8:59:35", "remaining_time": "2:08:38", "throughput": 2177.98, "total_tokens": 70513984} {"current_steps": 970, "total_steps": 1200, "loss": 0.0435, "lr": 4.396845284449608e-06, "epoch": 15.91381100726895, "percentage": 80.83, "elapsed_time": "9:00:10", "remaining_time": "2:08:05", "throughput": 2177.94, "total_tokens": 70588896} {"current_steps": 971, "total_steps": 1200, "loss": 0.1434, "lr": 4.359844731136209e-06, "epoch": 15.93042575285566, "percentage": 80.92, "elapsed_time": "9:00:50", "remaining_time": "2:07:33", "throughput": 2177.89, "total_tokens": 70673296} {"current_steps": 972, "total_steps": 1200, "loss": 0.0477, "lr": 4.322985643135952e-06, "epoch": 15.947040498442368, "percentage": 81.0, "elapsed_time": "9:01:19", "remaining_time": "2:06:58", "throughput": 2178.07, "total_tokens": 70742760} {"current_steps": 973, "total_steps": 1200, "loss": 0.0543, "lr": 4.286268273076915e-06, "epoch": 15.963655244029075, "percentage": 81.08, "elapsed_time": "9:01:47", "remaining_time": "2:06:23", "throughput": 2178.16, "total_tokens": 70806728} {"current_steps": 974, "total_steps": 1200, "loss": 0.0496, "lr": 4.2496928726158155e-06, "epoch": 15.980269989615785, "percentage": 81.17, "elapsed_time": "9:02:34", "remaining_time": "2:05:53", "throughput": 2178.15, "total_tokens": 70909320} {"current_steps": 975, "total_steps": 1200, "loss": 0.0566, "lr": 4.213259692436367e-06, "epoch": 15.996884735202492, "percentage": 81.25, "elapsed_time": "9:03:09", "remaining_time": "2:05:20", "throughput": 2178.3, "total_tokens": 70989640} {"current_steps": 976, "total_steps": 1200, "loss": 0.049, "lr": 4.176968982247514e-06, "epoch": 16.0, "percentage": 81.33, "elapsed_time": "9:03:13", "remaining_time": "2:04:40", "throughput": 2178.31, "total_tokens": 70997848} {"current_steps": 977, "total_steps": 1200, "loss": 0.0534, "lr": 4.140820990781705e-06, "epoch": 16.016614745586708, "percentage": 81.42, "elapsed_time": "9:03:39", "remaining_time": "2:04:05", "throughput": 2178.19, "total_tokens": 71051960} {"current_steps": 978, "total_steps": 1200, "loss": 0.0468, "lr": 4.104815965793249e-06, "epoch": 16.033229491173415, "percentage": 81.5, "elapsed_time": "9:04:21", "remaining_time": "2:03:33", "throughput": 2177.9, "total_tokens": 71132536} {"current_steps": 979, "total_steps": 1200, "loss": 0.0448, "lr": 4.068954154056528e-06, "epoch": 16.049844236760123, "percentage": 81.58, "elapsed_time": "9:04:53", "remaining_time": "2:03:00", "throughput": 2177.9, "total_tokens": 71202432} {"current_steps": 980, "total_steps": 1200, "loss": 0.0415, "lr": 4.0332358013644016e-06, "epoch": 16.066458982346834, "percentage": 81.67, "elapsed_time": "9:05:32", "remaining_time": "2:02:28", "throughput": 2177.86, "total_tokens": 71287576} {"current_steps": 981, "total_steps": 1200, "loss": 0.1111, "lr": 3.9976611525264525e-06, "epoch": 16.08307372793354, "percentage": 81.75, "elapsed_time": "9:06:09", "remaining_time": "2:01:55", "throughput": 2177.83, "total_tokens": 71367248} {"current_steps": 982, "total_steps": 1200, "loss": 0.0432, "lr": 3.962230451367349e-06, "epoch": 16.09968847352025, "percentage": 81.83, "elapsed_time": "9:06:48", "remaining_time": "2:01:23", "throughput": 2177.71, "total_tokens": 71447928} {"current_steps": 983, "total_steps": 1200, "loss": 0.0499, "lr": 3.926943940725137e-06, "epoch": 16.116303219106957, "percentage": 81.92, "elapsed_time": "9:07:11", "remaining_time": "2:00:47", "throughput": 2177.8, "total_tokens": 71501472} {"current_steps": 984, "total_steps": 1200, "loss": 0.0511, "lr": 3.891801862449629e-06, "epoch": 16.132917964693664, "percentage": 82.0, "elapsed_time": "9:07:40", "remaining_time": "2:00:13", "throughput": 2177.91, "total_tokens": 71568048} {"current_steps": 985, "total_steps": 1200, "loss": 0.0476, "lr": 3.85680445740067e-06, "epoch": 16.149532710280372, "percentage": 82.08, "elapsed_time": "9:08:12", "remaining_time": "1:59:39", "throughput": 2178.03, "total_tokens": 71641112} {"current_steps": 986, "total_steps": 1200, "loss": 0.0456, "lr": 3.821951965446577e-06, "epoch": 16.166147455867083, "percentage": 82.17, "elapsed_time": "9:08:47", "remaining_time": "1:59:06", "throughput": 2178.01, "total_tokens": 71716800} {"current_steps": 987, "total_steps": 1200, "loss": 0.0341, "lr": 3.7872446254624104e-06, "epoch": 16.18276220145379, "percentage": 82.25, "elapsed_time": "9:09:30", "remaining_time": "1:58:35", "throughput": 2177.69, "total_tokens": 71799616} {"current_steps": 988, "total_steps": 1200, "loss": 0.0496, "lr": 3.752682675328406e-06, "epoch": 16.1993769470405, "percentage": 82.33, "elapsed_time": "9:09:59", "remaining_time": "1:58:00", "throughput": 2177.71, "total_tokens": 71863392} {"current_steps": 989, "total_steps": 1200, "loss": 0.0458, "lr": 3.718266351928287e-06, "epoch": 16.215991692627206, "percentage": 82.42, "elapsed_time": "9:10:27", "remaining_time": "1:57:26", "throughput": 2177.83, "total_tokens": 71927704} {"current_steps": 990, "total_steps": 1200, "loss": 0.0473, "lr": 3.6839958911476957e-06, "epoch": 16.232606438213914, "percentage": 82.5, "elapsed_time": "9:10:53", "remaining_time": "1:56:51", "throughput": 2177.81, "total_tokens": 71984208} {"current_steps": 991, "total_steps": 1200, "loss": 0.0378, "lr": 3.6498715278725254e-06, "epoch": 16.24922118380062, "percentage": 82.58, "elapsed_time": "9:11:21", "remaining_time": "1:56:16", "throughput": 2178.04, "total_tokens": 72053448} {"current_steps": 992, "total_steps": 1200, "loss": 0.0422, "lr": 3.6158934959873353e-06, "epoch": 16.265835929387332, "percentage": 82.67, "elapsed_time": "9:11:54", "remaining_time": "1:55:43", "throughput": 2178.03, "total_tokens": 72123464} {"current_steps": 993, "total_steps": 1200, "loss": 0.1494, "lr": 3.5820620283737616e-06, "epoch": 16.28245067497404, "percentage": 82.75, "elapsed_time": "9:12:26", "remaining_time": "1:55:09", "throughput": 2178.16, "total_tokens": 72197920} {"current_steps": 994, "total_steps": 1200, "loss": 0.044, "lr": 3.5483773569088856e-06, "epoch": 16.299065420560748, "percentage": 82.83, "elapsed_time": "9:13:12", "remaining_time": "1:54:38", "throughput": 2178.1, "total_tokens": 72295824} {"current_steps": 995, "total_steps": 1200, "loss": 0.0428, "lr": 3.5148397124636826e-06, "epoch": 16.315680166147455, "percentage": 82.92, "elapsed_time": "9:13:56", "remaining_time": "1:54:07", "throughput": 2177.98, "total_tokens": 72389296} {"current_steps": 996, "total_steps": 1200, "loss": 0.0546, "lr": 3.4814493249014116e-06, "epoch": 16.332294911734163, "percentage": 83.0, "elapsed_time": "9:14:24", "remaining_time": "1:53:33", "throughput": 2178.01, "total_tokens": 72451080} {"current_steps": 997, "total_steps": 1200, "loss": 0.0457, "lr": 3.4482064230760474e-06, "epoch": 16.34890965732087, "percentage": 83.08, "elapsed_time": "9:14:55", "remaining_time": "1:52:59", "throughput": 2178.15, "total_tokens": 72523168} {"current_steps": 998, "total_steps": 1200, "loss": 0.0573, "lr": 3.415111234830709e-06, "epoch": 16.36552440290758, "percentage": 83.17, "elapsed_time": "9:15:25", "remaining_time": "1:52:25", "throughput": 2178.06, "total_tokens": 72585384} {"current_steps": 999, "total_steps": 1200, "loss": 0.0484, "lr": 3.382163986996126e-06, "epoch": 16.38213914849429, "percentage": 83.25, "elapsed_time": "9:15:53", "remaining_time": "1:51:50", "throughput": 2178.07, "total_tokens": 72645544} {"current_steps": 1000, "total_steps": 1200, "loss": 0.0412, "lr": 3.3493649053890326e-06, "epoch": 16.398753894080997, "percentage": 83.33, "elapsed_time": "9:16:26", "remaining_time": "1:51:17", "throughput": 2178.19, "total_tokens": 72722408} {"current_steps": 1001, "total_steps": 1200, "loss": 0.0498, "lr": 3.3167142148106762e-06, "epoch": 16.415368639667705, "percentage": 83.42, "elapsed_time": "9:16:58", "remaining_time": "1:50:43", "throughput": 2178.41, "total_tokens": 72798192} {"current_steps": 1002, "total_steps": 1200, "loss": 0.0492, "lr": 3.284212139045223e-06, "epoch": 16.431983385254412, "percentage": 83.5, "elapsed_time": "9:17:25", "remaining_time": "1:50:08", "throughput": 2178.57, "total_tokens": 72862440} {"current_steps": 1003, "total_steps": 1200, "loss": 0.0507, "lr": 3.2518589008582597e-06, "epoch": 16.44859813084112, "percentage": 83.58, "elapsed_time": "9:17:48", "remaining_time": "1:49:33", "throughput": 2178.54, "total_tokens": 72911448} {"current_steps": 1004, "total_steps": 1200, "loss": 0.0501, "lr": 3.219654721995266e-06, "epoch": 16.46521287642783, "percentage": 83.67, "elapsed_time": "9:18:16", "remaining_time": "1:48:59", "throughput": 2178.74, "total_tokens": 72980368} {"current_steps": 1005, "total_steps": 1200, "loss": 0.0548, "lr": 3.187599823180071e-06, "epoch": 16.48182762201454, "percentage": 83.75, "elapsed_time": "9:18:45", "remaining_time": "1:48:24", "throughput": 2178.79, "total_tokens": 73044888} {"current_steps": 1006, "total_steps": 1200, "loss": 0.0427, "lr": 3.15569442411337e-06, "epoch": 16.498442367601246, "percentage": 83.83, "elapsed_time": "9:19:18", "remaining_time": "1:47:51", "throughput": 2178.89, "total_tokens": 73119968} {"current_steps": 1007, "total_steps": 1200, "loss": 0.0475, "lr": 3.1239387434711916e-06, "epoch": 16.515057113187954, "percentage": 83.92, "elapsed_time": "9:19:49", "remaining_time": "1:47:17", "throughput": 2178.79, "total_tokens": 73184104} {"current_steps": 1008, "total_steps": 1200, "loss": 0.0517, "lr": 3.092332998903416e-06, "epoch": 16.53167185877466, "percentage": 84.0, "elapsed_time": "9:20:16", "remaining_time": "1:46:43", "throughput": 2178.68, "total_tokens": 73239464} {"current_steps": 1009, "total_steps": 1200, "loss": 0.0548, "lr": 3.06087740703227e-06, "epoch": 16.54828660436137, "percentage": 84.08, "elapsed_time": "9:20:49", "remaining_time": "1:46:09", "throughput": 2178.7, "total_tokens": 73312808} {"current_steps": 1010, "total_steps": 1200, "loss": 0.1552, "lr": 3.029572183450868e-06, "epoch": 16.56490134994808, "percentage": 84.17, "elapsed_time": "9:21:21", "remaining_time": "1:45:36", "throughput": 2178.7, "total_tokens": 73381528} {"current_steps": 1011, "total_steps": 1200, "loss": 0.0461, "lr": 2.9984175427217016e-06, "epoch": 16.581516095534788, "percentage": 84.25, "elapsed_time": "9:22:02", "remaining_time": "1:45:04", "throughput": 2178.22, "total_tokens": 73455200}