IntroSVG-Qwen2.5-VL-7B / trainer_log.jsonl
gitcat404's picture
Upload 22 files
c2c1a57 verified
{"current_steps": 21, "total_steps": 6951, "loss": 1.431, "lr": 9.999774793715127e-05, "epoch": 0.009060022650056626, "percentage": 0.3, "elapsed_time": "0:09:04", "remaining_time": "2 days, 1:56:17", "throughput": 9395.55, "total_tokens": 5118512}
{"current_steps": 42, "total_steps": 6951, "loss": 0.5348, "lr": 9.99909919514765e-05, "epoch": 0.01812004530011325, "percentage": 0.6, "elapsed_time": "0:17:50", "remaining_time": "2 days, 0:56:01", "throughput": 9478.63, "total_tokens": 10150592}
{"current_steps": 63, "total_steps": 6951, "loss": 0.4599, "lr": 9.997973265157192e-05, "epoch": 0.027180067950169876, "percentage": 0.91, "elapsed_time": "0:26:30", "remaining_time": "2 days, 0:18:38", "throughput": 9537.12, "total_tokens": 15170896}
{"current_steps": 84, "total_steps": 6951, "loss": 0.4108, "lr": 9.996397105170353e-05, "epoch": 0.0362400906002265, "percentage": 1.21, "elapsed_time": "0:35:19", "remaining_time": "2 days, 0:08:22", "throughput": 9507.78, "total_tokens": 20155632}
{"current_steps": 105, "total_steps": 6951, "loss": 0.3947, "lr": 9.994370857171588e-05, "epoch": 0.045300113250283124, "percentage": 1.51, "elapsed_time": "0:44:14", "remaining_time": "2 days, 0:04:12", "throughput": 9470.14, "total_tokens": 25135440}
{"current_steps": 126, "total_steps": 6951, "loss": 0.3764, "lr": 9.991894703690414e-05, "epoch": 0.05436013590033975, "percentage": 1.81, "elapsed_time": "0:53:09", "remaining_time": "1 day, 23:58:59", "throughput": 9515.96, "total_tokens": 30346784}
{"current_steps": 147, "total_steps": 6951, "loss": 0.3751, "lr": 9.988968867784958e-05, "epoch": 0.06342015855039637, "percentage": 2.11, "elapsed_time": "1:01:42", "remaining_time": "1 day, 23:36:18", "throughput": 9525.58, "total_tokens": 35269664}
{"current_steps": 168, "total_steps": 6951, "loss": 0.3704, "lr": 9.985593613021872e-05, "epoch": 0.072480181200453, "percentage": 2.42, "elapsed_time": "1:10:20", "remaining_time": "1 day, 23:20:11", "throughput": 9513.01, "total_tokens": 40151792}
{"current_steps": 189, "total_steps": 6951, "loss": 0.3552, "lr": 9.981769243452595e-05, "epoch": 0.08154020385050963, "percentage": 2.72, "elapsed_time": "1:19:14", "remaining_time": "1 day, 23:14:54", "throughput": 9524.9, "total_tokens": 45283312}
{"current_steps": 210, "total_steps": 6951, "loss": 0.3576, "lr": 9.977496103585949e-05, "epoch": 0.09060022650056625, "percentage": 3.02, "elapsed_time": "1:28:00", "remaining_time": "1 day, 23:05:05", "throughput": 9525.35, "total_tokens": 50298912}
{"current_steps": 231, "total_steps": 6951, "loss": 0.3451, "lr": 9.972774578357117e-05, "epoch": 0.09966024915062288, "percentage": 3.32, "elapsed_time": "1:37:00", "remaining_time": "1 day, 23:02:12", "throughput": 9525.43, "total_tokens": 55445792}
{"current_steps": 252, "total_steps": 6951, "loss": 0.3506, "lr": 9.96760509309296e-05, "epoch": 0.1087202718006795, "percentage": 3.63, "elapsed_time": "1:45:52", "remaining_time": "1 day, 22:54:33", "throughput": 9524.66, "total_tokens": 60506496}
{"current_steps": 273, "total_steps": 6951, "loss": 0.3443, "lr": 9.961988113473708e-05, "epoch": 0.11778029445073612, "percentage": 3.93, "elapsed_time": "1:54:50", "remaining_time": "1 day, 22:49:19", "throughput": 9531.29, "total_tokens": 65678096}
{"current_steps": 294, "total_steps": 6951, "loss": 0.3446, "lr": 9.955924145491005e-05, "epoch": 0.12684031710079274, "percentage": 4.23, "elapsed_time": "2:03:13", "remaining_time": "1 day, 22:30:12", "throughput": 9532.39, "total_tokens": 70478688}
{"current_steps": 315, "total_steps": 6951, "loss": 0.3362, "lr": 9.94941373540233e-05, "epoch": 0.13590033975084936, "percentage": 4.53, "elapsed_time": "2:11:37", "remaining_time": "1 day, 22:13:01", "throughput": 9543.53, "total_tokens": 75373536}
{"current_steps": 336, "total_steps": 6951, "loss": 0.3384, "lr": 9.942457469681794e-05, "epoch": 0.144960362400906, "percentage": 4.83, "elapsed_time": "2:20:45", "remaining_time": "1 day, 22:11:15", "throughput": 9528.67, "total_tokens": 80476704}
{"current_steps": 357, "total_steps": 6951, "loss": 0.3315, "lr": 9.935055974967299e-05, "epoch": 0.15402038505096263, "percentage": 5.14, "elapsed_time": "2:29:44", "remaining_time": "1 day, 22:05:57", "throughput": 9534.93, "total_tokens": 85670800}
{"current_steps": 378, "total_steps": 6951, "loss": 0.33, "lr": 9.927209918004095e-05, "epoch": 0.16308040770101925, "percentage": 5.44, "elapsed_time": "2:38:25", "remaining_time": "1 day, 21:54:52", "throughput": 9542.47, "total_tokens": 90707040}
{"current_steps": 399, "total_steps": 6951, "loss": 0.3296, "lr": 9.918920005584719e-05, "epoch": 0.17214043035107587, "percentage": 5.74, "elapsed_time": "2:47:34", "remaining_time": "1 day, 21:51:41", "throughput": 9530.71, "total_tokens": 95824496}
{"current_steps": 420, "total_steps": 6951, "loss": 0.3315, "lr": 9.910186984485321e-05, "epoch": 0.1812004530011325, "percentage": 6.04, "elapsed_time": "2:56:23", "remaining_time": "1 day, 21:42:53", "throughput": 9530.11, "total_tokens": 100862224}
{"current_steps": 441, "total_steps": 6951, "loss": 0.353, "lr": 9.901011641398398e-05, "epoch": 0.19026047565118911, "percentage": 6.34, "elapsed_time": "3:05:16", "remaining_time": "1 day, 21:34:59", "throughput": 9524.36, "total_tokens": 105876656}
{"current_steps": 462, "total_steps": 6951, "loss": 0.3414, "lr": 9.89139480286192e-05, "epoch": 0.19932049830124576, "percentage": 6.65, "elapsed_time": "3:14:24", "remaining_time": "1 day, 21:30:34", "throughput": 9514.36, "total_tokens": 110980864}
{"current_steps": 483, "total_steps": 6951, "loss": 0.3224, "lr": 9.881337335184878e-05, "epoch": 0.20838052095130238, "percentage": 6.95, "elapsed_time": "3:23:22", "remaining_time": "1 day, 21:23:33", "throughput": 9515.3, "total_tokens": 116114800}
{"current_steps": 504, "total_steps": 6951, "loss": 0.3212, "lr": 9.870840144369246e-05, "epoch": 0.217440543601359, "percentage": 7.25, "elapsed_time": "3:32:28", "remaining_time": "1 day, 21:17:59", "throughput": 9511.06, "total_tokens": 121255744}
{"current_steps": 525, "total_steps": 6951, "loss": 0.3213, "lr": 9.859904176028362e-05, "epoch": 0.22650056625141562, "percentage": 7.55, "elapsed_time": "3:41:20", "remaining_time": "1 day, 21:09:18", "throughput": 9509.05, "total_tokens": 126288608}
{"current_steps": 546, "total_steps": 6951, "loss": 0.3198, "lr": 9.848530415301747e-05, "epoch": 0.23556058890147225, "percentage": 7.85, "elapsed_time": "3:49:53", "remaining_time": "1 day, 20:56:47", "throughput": 9514.22, "total_tokens": 131233488}
{"current_steps": 567, "total_steps": 6951, "loss": 0.3149, "lr": 9.836719886766356e-05, "epoch": 0.24462061155152887, "percentage": 8.16, "elapsed_time": "3:58:35", "remaining_time": "1 day, 20:46:18", "throughput": 9518.41, "total_tokens": 136257888}
{"current_steps": 588, "total_steps": 6951, "loss": 0.3169, "lr": 9.824473654344297e-05, "epoch": 0.2536806342015855, "percentage": 8.46, "elapsed_time": "4:07:48", "remaining_time": "1 day, 20:41:36", "throughput": 9510.51, "total_tokens": 141405120}
{"current_steps": 609, "total_steps": 6951, "loss": 0.3142, "lr": 9.811792821206969e-05, "epoch": 0.2627406568516421, "percentage": 8.76, "elapsed_time": "4:16:46", "remaining_time": "1 day, 20:33:56", "throughput": 9501.43, "total_tokens": 146380496}
{"current_steps": 630, "total_steps": 6951, "loss": 0.3097, "lr": 9.7986785296757e-05, "epoch": 0.2718006795016987, "percentage": 9.06, "elapsed_time": "4:25:32", "remaining_time": "1 day, 20:24:11", "throughput": 9499.35, "total_tokens": 151344048}
{"current_steps": 651, "total_steps": 6951, "loss": 0.3116, "lr": 9.785131961118844e-05, "epoch": 0.2808607021517554, "percentage": 9.37, "elapsed_time": "4:34:25", "remaining_time": "1 day, 20:15:47", "throughput": 9500.56, "total_tokens": 156435136}
{"current_steps": 672, "total_steps": 6951, "loss": 0.3086, "lr": 9.771154335845345e-05, "epoch": 0.289920724801812, "percentage": 9.67, "elapsed_time": "4:43:25", "remaining_time": "1 day, 20:08:13", "throughput": 9499.14, "total_tokens": 161536224}
{"current_steps": 693, "total_steps": 6951, "loss": 0.3057, "lr": 9.756746912994832e-05, "epoch": 0.29898074745186864, "percentage": 9.97, "elapsed_time": "4:52:30", "remaining_time": "1 day, 20:01:24", "throughput": 9491.21, "total_tokens": 166573984}
{"current_steps": 714, "total_steps": 6951, "loss": 0.3017, "lr": 9.741910990424174e-05, "epoch": 0.30804077010192527, "percentage": 10.27, "elapsed_time": "5:01:16", "remaining_time": "1 day, 19:51:46", "throughput": 9494.9, "total_tokens": 171638000}
{"current_steps": 735, "total_steps": 6951, "loss": 0.3066, "lr": 9.726647904590571e-05, "epoch": 0.3171007927519819, "percentage": 10.57, "elapsed_time": "5:10:26", "remaining_time": "1 day, 19:45:29", "throughput": 9489.84, "total_tokens": 176765648}
{"current_steps": 756, "total_steps": 6951, "loss": 0.2996, "lr": 9.710959030431167e-05, "epoch": 0.3261608154020385, "percentage": 10.88, "elapsed_time": "5:19:30", "remaining_time": "1 day, 19:38:14", "throughput": 9490.92, "total_tokens": 181949360}
{"current_steps": 777, "total_steps": 6951, "loss": 0.2972, "lr": 9.694845781239187e-05, "epoch": 0.3352208380520951, "percentage": 11.18, "elapsed_time": "5:28:25", "remaining_time": "1 day, 19:29:35", "throughput": 9489.46, "total_tokens": 186990096}
{"current_steps": 798, "total_steps": 6951, "loss": 0.2984, "lr": 9.678309608536626e-05, "epoch": 0.34428086070215175, "percentage": 11.48, "elapsed_time": "5:37:25", "remaining_time": "1 day, 19:21:44", "throughput": 9487.66, "total_tokens": 192083856}
{"current_steps": 819, "total_steps": 6951, "loss": 0.2957, "lr": 9.661352001943493e-05, "epoch": 0.35334088335220837, "percentage": 11.78, "elapsed_time": "5:46:05", "remaining_time": "1 day, 19:11:15", "throughput": 9493.32, "total_tokens": 197134448}
{"current_steps": 840, "total_steps": 6951, "loss": 0.2926, "lr": 9.64397448904362e-05, "epoch": 0.362400906002265, "percentage": 12.08, "elapsed_time": "5:55:14", "remaining_time": "1 day, 19:04:21", "throughput": 9491.78, "total_tokens": 202310368}
{"current_steps": 861, "total_steps": 6951, "loss": 0.2909, "lr": 9.626178635247054e-05, "epoch": 0.3714609286523216, "percentage": 12.39, "elapsed_time": "6:04:00", "remaining_time": "1 day, 18:54:38", "throughput": 9494.44, "total_tokens": 207359840}
{"current_steps": 882, "total_steps": 6951, "loss": 0.2954, "lr": 9.607966043649046e-05, "epoch": 0.38052095130237823, "percentage": 12.69, "elapsed_time": "6:12:54", "remaining_time": "1 day, 18:45:59", "throughput": 9492.66, "total_tokens": 212395664}
{"current_steps": 903, "total_steps": 6951, "loss": 0.2912, "lr": 9.589338354885629e-05, "epoch": 0.3895809739524349, "percentage": 12.99, "elapsed_time": "6:21:47", "remaining_time": "1 day, 18:37:06", "throughput": 9497.8, "total_tokens": 217570640}
{"current_steps": 924, "total_steps": 6951, "loss": 0.2928, "lr": 9.570297246985837e-05, "epoch": 0.3986409966024915, "percentage": 13.29, "elapsed_time": "6:30:38", "remaining_time": "1 day, 18:28:00", "throughput": 9498.61, "total_tokens": 222629712}
{"current_steps": 945, "total_steps": 6951, "loss": 0.292, "lr": 9.550844435220539e-05, "epoch": 0.40770101925254815, "percentage": 13.6, "elapsed_time": "6:38:57", "remaining_time": "1 day, 18:15:34", "throughput": 9506.77, "total_tokens": 227565744}
{"current_steps": 966, "total_steps": 6951, "loss": 0.292, "lr": 9.530981671947923e-05, "epoch": 0.41676104190260477, "percentage": 13.9, "elapsed_time": "6:48:04", "remaining_time": "1 day, 18:08:16", "throughput": 9502.21, "total_tokens": 232655712}
{"current_steps": 987, "total_steps": 6951, "loss": 0.2959, "lr": 9.510710746455636e-05, "epoch": 0.4258210645526614, "percentage": 14.2, "elapsed_time": "6:56:51", "remaining_time": "1 day, 17:58:52", "throughput": 9500.11, "total_tokens": 237611056}
{"current_steps": 1008, "total_steps": 6951, "loss": 0.2884, "lr": 9.490033484799608e-05, "epoch": 0.434881087202718, "percentage": 14.5, "elapsed_time": "7:05:54", "remaining_time": "1 day, 17:51:03", "throughput": 9497.19, "total_tokens": 242693136}
{"current_steps": 1029, "total_steps": 6951, "loss": 0.2878, "lr": 9.468951749639551e-05, "epoch": 0.44394110985277463, "percentage": 14.8, "elapsed_time": "7:14:46", "remaining_time": "1 day, 17:42:12", "throughput": 9494.35, "total_tokens": 247677488}
{"current_steps": 1050, "total_steps": 6951, "loss": 0.2908, "lr": 9.447467440071164e-05, "epoch": 0.45300113250283125, "percentage": 15.11, "elapsed_time": "7:23:55", "remaining_time": "1 day, 17:34:48", "throughput": 9490.15, "total_tokens": 252770384}
{"current_steps": 1071, "total_steps": 6951, "loss": 0.2796, "lr": 9.425582491455067e-05, "epoch": 0.46206115515288787, "percentage": 15.41, "elapsed_time": "7:33:19", "remaining_time": "1 day, 17:28:50", "throughput": 9485.8, "total_tokens": 258009696}
{"current_steps": 1092, "total_steps": 6951, "loss": 0.2858, "lr": 9.403298875242448e-05, "epoch": 0.4711211778029445, "percentage": 15.71, "elapsed_time": "7:42:23", "remaining_time": "1 day, 17:20:57", "throughput": 9484.86, "total_tokens": 263147728}
{"current_steps": 1113, "total_steps": 6951, "loss": 0.2876, "lr": 9.380618598797473e-05, "epoch": 0.4801812004530011, "percentage": 16.01, "elapsed_time": "7:51:09", "remaining_time": "1 day, 17:11:21", "throughput": 9486.71, "total_tokens": 268184080}
{"current_steps": 1134, "total_steps": 6951, "loss": 0.2814, "lr": 9.357543705216465e-05, "epoch": 0.48924122310305773, "percentage": 16.31, "elapsed_time": "8:00:24", "remaining_time": "1 day, 17:04:21", "throughput": 9486.33, "total_tokens": 273442768}
{"current_steps": 1155, "total_steps": 6951, "loss": 0.2804, "lr": 9.334076273143843e-05, "epoch": 0.4983012457531144, "percentage": 16.62, "elapsed_time": "8:09:16", "remaining_time": "1 day, 16:55:18", "throughput": 9491.48, "total_tokens": 278640624}
{"current_steps": 1176, "total_steps": 6951, "loss": 0.2863, "lr": 9.310218416584886e-05, "epoch": 0.507361268403171, "percentage": 16.92, "elapsed_time": "8:18:19", "remaining_time": "1 day, 16:47:09", "throughput": 9490.65, "total_tokens": 283769424}
{"current_steps": 1197, "total_steps": 6951, "loss": 0.2851, "lr": 9.28597228471529e-05, "epoch": 0.5164212910532276, "percentage": 17.22, "elapsed_time": "8:27:03", "remaining_time": "1 day, 16:37:28", "throughput": 9494.69, "total_tokens": 288866448}
{"current_steps": 1218, "total_steps": 6951, "loss": 0.2798, "lr": 9.26134006168757e-05, "epoch": 0.5254813137032842, "percentage": 17.52, "elapsed_time": "8:35:48", "remaining_time": "1 day, 16:27:52", "throughput": 9497.76, "total_tokens": 293944576}
{"current_steps": 1239, "total_steps": 6951, "loss": 0.2728, "lr": 9.236323966434295e-05, "epoch": 0.5345413363533409, "percentage": 17.82, "elapsed_time": "8:44:51", "remaining_time": "1 day, 16:19:39", "throughput": 9497.6, "total_tokens": 299090032}
{"current_steps": 1260, "total_steps": 6951, "loss": 0.2756, "lr": 9.210926252468219e-05, "epoch": 0.5436013590033975, "percentage": 18.13, "elapsed_time": "8:53:20", "remaining_time": "1 day, 16:08:56", "throughput": 9500.3, "total_tokens": 304016304}
{"current_steps": 1281, "total_steps": 6951, "loss": 0.2747, "lr": 9.185149207679263e-05, "epoch": 0.5526613816534541, "percentage": 18.43, "elapsed_time": "9:02:10", "remaining_time": "1 day, 15:59:46", "throughput": 9501.41, "total_tokens": 309084016}
{"current_steps": 1302, "total_steps": 6951, "loss": 0.2772, "lr": 9.158995154128425e-05, "epoch": 0.5617214043035108, "percentage": 18.73, "elapsed_time": "9:11:03", "remaining_time": "1 day, 15:50:52", "throughput": 9503.01, "total_tokens": 314201696}
{"current_steps": 1323, "total_steps": 6951, "loss": 0.2785, "lr": 9.132466447838597e-05, "epoch": 0.5707814269535674, "percentage": 19.03, "elapsed_time": "9:19:38", "remaining_time": "1 day, 15:40:41", "throughput": 9508.07, "total_tokens": 319266256}
{"current_steps": 1344, "total_steps": 6951, "loss": 0.2755, "lr": 9.105565478582334e-05, "epoch": 0.579841449603624, "percentage": 19.34, "elapsed_time": "9:28:38", "remaining_time": "1 day, 15:32:19", "throughput": 9509.96, "total_tokens": 324468352}
{"current_steps": 1365, "total_steps": 6951, "loss": 0.2708, "lr": 9.078294669666576e-05, "epoch": 0.5889014722536806, "percentage": 19.64, "elapsed_time": "9:37:46", "remaining_time": "1 day, 15:24:25", "throughput": 9506.81, "total_tokens": 329566736}
{"current_steps": 1386, "total_steps": 6951, "loss": 0.2729, "lr": 9.050656477714346e-05, "epoch": 0.5979614949037373, "percentage": 19.94, "elapsed_time": "9:46:49", "remaining_time": "1 day, 15:16:10", "throughput": 9504.96, "total_tokens": 334661888}
{"current_steps": 1407, "total_steps": 6951, "loss": 0.2754, "lr": 9.022653392443454e-05, "epoch": 0.6070215175537939, "percentage": 20.24, "elapsed_time": "9:55:45", "remaining_time": "1 day, 15:07:27", "throughput": 9505.7, "total_tokens": 339784976}
{"current_steps": 1428, "total_steps": 6951, "loss": 0.2742, "lr": 8.994287936442225e-05, "epoch": 0.6160815402038505, "percentage": 20.54, "elapsed_time": "10:04:49", "remaining_time": "1 day, 14:59:13", "throughput": 9500.81, "total_tokens": 344776544}
{"current_steps": 1449, "total_steps": 6951, "loss": 0.2703, "lr": 8.96556266494224e-05, "epoch": 0.6251415628539071, "percentage": 20.85, "elapsed_time": "10:13:22", "remaining_time": "1 day, 14:49:01", "throughput": 9503.01, "total_tokens": 349731168}
{"current_steps": 1470, "total_steps": 6951, "loss": 0.2756, "lr": 8.936480165588173e-05, "epoch": 0.6342015855039638, "percentage": 21.15, "elapsed_time": "10:22:04", "remaining_time": "1 day, 14:39:27", "throughput": 9502.95, "total_tokens": 354694544}
{"current_steps": 1491, "total_steps": 6951, "loss": 0.2698, "lr": 8.907043058204674e-05, "epoch": 0.6432616081540203, "percentage": 21.45, "elapsed_time": "10:31:13", "remaining_time": "1 day, 14:31:31", "throughput": 9501.97, "total_tokens": 359871984}
{"current_steps": 1512, "total_steps": 6951, "loss": 0.2716, "lr": 8.877253994560382e-05, "epoch": 0.652321630804077, "percentage": 21.75, "elapsed_time": "10:40:16", "remaining_time": "1 day, 14:23:14", "throughput": 9499.4, "total_tokens": 364937440}
{"current_steps": 1533, "total_steps": 6951, "loss": 0.2682, "lr": 8.847115658129039e-05, "epoch": 0.6613816534541337, "percentage": 22.05, "elapsed_time": "10:49:13", "remaining_time": "1 day, 14:14:29", "throughput": 9498.48, "total_tokens": 369994848}
{"current_steps": 1554, "total_steps": 6951, "loss": 0.2695, "lr": 8.816630763847755e-05, "epoch": 0.6704416761041903, "percentage": 22.36, "elapsed_time": "10:57:51", "remaining_time": "1 day, 14:04:43", "throughput": 9500.35, "total_tokens": 374992544}
{"current_steps": 1575, "total_steps": 6951, "loss": 0.2706, "lr": 8.785802057872446e-05, "epoch": 0.6795016987542469, "percentage": 22.66, "elapsed_time": "11:06:33", "remaining_time": "1 day, 13:55:11", "throughput": 9502.46, "total_tokens": 380038624}
{"current_steps": 1596, "total_steps": 6951, "loss": 0.2704, "lr": 8.754632317330447e-05, "epoch": 0.6885617214043035, "percentage": 22.96, "elapsed_time": "11:15:32", "remaining_time": "1 day, 13:46:38", "throughput": 9503.27, "total_tokens": 385195792}
{"current_steps": 1617, "total_steps": 6951, "loss": 0.2707, "lr": 8.723124350070347e-05, "epoch": 0.6976217440543602, "percentage": 23.26, "elapsed_time": "11:24:14", "remaining_time": "1 day, 13:37:05", "throughput": 9504.39, "total_tokens": 390195296}
{"current_steps": 1638, "total_steps": 6951, "loss": 0.2653, "lr": 8.691280994409043e-05, "epoch": 0.7066817667044167, "percentage": 23.56, "elapsed_time": "11:33:22", "remaining_time": "1 day, 13:28:59", "throughput": 9503.23, "total_tokens": 395353440}
{"current_steps": 1659, "total_steps": 6951, "loss": 0.2649, "lr": 8.659105118876068e-05, "epoch": 0.7157417893544734, "percentage": 23.87, "elapsed_time": "11:41:58", "remaining_time": "1 day, 13:19:14", "throughput": 9507.46, "total_tokens": 400444080}
{"current_steps": 1680, "total_steps": 6951, "loss": 0.2652, "lr": 8.626599621955179e-05, "epoch": 0.72480181200453, "percentage": 24.17, "elapsed_time": "11:50:50", "remaining_time": "1 day, 13:10:14", "throughput": 9507.43, "total_tokens": 405492112}
{"current_steps": 1701, "total_steps": 6951, "loss": 0.2638, "lr": 8.593767431823255e-05, "epoch": 0.7338618346545867, "percentage": 24.47, "elapsed_time": "11:59:34", "remaining_time": "1 day, 13:00:53", "throughput": 9507.28, "total_tokens": 410467584}
{"current_steps": 1722, "total_steps": 6951, "loss": 0.2685, "lr": 8.56061150608652e-05, "epoch": 0.7429218573046432, "percentage": 24.77, "elapsed_time": "12:08:13", "remaining_time": "1 day, 12:51:17", "throughput": 9510.67, "total_tokens": 415550320}
{"current_steps": 1743, "total_steps": 6951, "loss": 0.2584, "lr": 8.527134831514117e-05, "epoch": 0.7519818799546999, "percentage": 25.08, "elapsed_time": "12:16:49", "remaining_time": "1 day, 12:41:35", "throughput": 9511.61, "total_tokens": 420503712}
{"current_steps": 1764, "total_steps": 6951, "loss": 0.2607, "lr": 8.493340423769053e-05, "epoch": 0.7610419026047565, "percentage": 25.38, "elapsed_time": "12:25:46", "remaining_time": "1 day, 12:32:56", "throughput": 9511.41, "total_tokens": 425602800}
{"current_steps": 1785, "total_steps": 6951, "loss": 0.2652, "lr": 8.459231327136532e-05, "epoch": 0.7701019252548131, "percentage": 25.68, "elapsed_time": "12:34:23", "remaining_time": "1 day, 12:23:18", "throughput": 9511.99, "total_tokens": 430546320}
{"current_steps": 1806, "total_steps": 6951, "loss": 0.2604, "lr": 8.42481061424973e-05, "epoch": 0.7791619479048698, "percentage": 25.98, "elapsed_time": "12:43:09", "remaining_time": "1 day, 12:14:07", "throughput": 9513.64, "total_tokens": 435625600}
{"current_steps": 1827, "total_steps": 6951, "loss": 0.2603, "lr": 8.390081385812993e-05, "epoch": 0.7882219705549264, "percentage": 26.28, "elapsed_time": "12:51:51", "remaining_time": "1 day, 12:04:45", "throughput": 9515.83, "total_tokens": 440695024}
{"current_steps": 1848, "total_steps": 6951, "loss": 0.2576, "lr": 8.355046770322528e-05, "epoch": 0.797281993204983, "percentage": 26.59, "elapsed_time": "13:01:19", "remaining_time": "1 day, 11:57:30", "throughput": 9511.18, "total_tokens": 445877360}
{"current_steps": 1869, "total_steps": 6951, "loss": 0.2622, "lr": 8.319709923784573e-05, "epoch": 0.8063420158550396, "percentage": 26.89, "elapsed_time": "13:10:17", "remaining_time": "1 day, 11:48:52", "throughput": 9511.76, "total_tokens": 451021040}
{"current_steps": 1890, "total_steps": 6951, "loss": 0.2587, "lr": 8.284074029431099e-05, "epoch": 0.8154020385050963, "percentage": 27.19, "elapsed_time": "13:19:10", "remaining_time": "1 day, 11:39:59", "throughput": 9511.99, "total_tokens": 456101872}
{"current_steps": 1911, "total_steps": 6951, "loss": 0.2575, "lr": 8.248142297433057e-05, "epoch": 0.8244620611551529, "percentage": 27.49, "elapsed_time": "13:28:28", "remaining_time": "1 day, 11:32:13", "throughput": 9511.08, "total_tokens": 461365920}
{"current_steps": 1932, "total_steps": 6951, "loss": 0.2573, "lr": 8.211917964611196e-05, "epoch": 0.8335220838052095, "percentage": 27.79, "elapsed_time": "13:37:33", "remaining_time": "1 day, 11:23:52", "throughput": 9509.35, "total_tokens": 466466096}
{"current_steps": 1953, "total_steps": 6951, "loss": 0.26, "lr": 8.175404294144482e-05, "epoch": 0.8425821064552661, "percentage": 28.1, "elapsed_time": "13:46:33", "remaining_time": "1 day, 11:15:17", "throughput": 9508.08, "total_tokens": 471541104}
{"current_steps": 1974, "total_steps": 6951, "loss": 0.2571, "lr": 8.138604575276143e-05, "epoch": 0.8516421291053228, "percentage": 28.4, "elapsed_time": "13:55:43", "remaining_time": "1 day, 11:07:04", "throughput": 9505.71, "total_tokens": 476646096}
{"current_steps": 1995, "total_steps": 6951, "loss": 0.251, "lr": 8.10152212301737e-05, "epoch": 0.8607021517553793, "percentage": 28.7, "elapsed_time": "14:04:22", "remaining_time": "1 day, 10:57:36", "throughput": 9507.9, "total_tokens": 481695200}
{"current_steps": 2016, "total_steps": 6951, "loss": 0.2614, "lr": 8.064160277848682e-05, "epoch": 0.869762174405436, "percentage": 29.0, "elapsed_time": "14:13:13", "remaining_time": "1 day, 10:48:38", "throughput": 9507.12, "total_tokens": 486706656}
{"current_steps": 2037, "total_steps": 6951, "loss": 0.2528, "lr": 8.026522405419023e-05, "epoch": 0.8788221970554927, "percentage": 29.31, "elapsed_time": "14:22:37", "remaining_time": "1 day, 10:40:57", "throughput": 9504.87, "total_tokens": 491943424}
{"current_steps": 2058, "total_steps": 6951, "loss": 0.2571, "lr": 7.988611896242559e-05, "epoch": 0.8878822197055493, "percentage": 29.61, "elapsed_time": "14:31:02", "remaining_time": "1 day, 10:30:56", "throughput": 9508.31, "total_tokens": 496925888}
{"current_steps": 2079, "total_steps": 6951, "loss": 0.2547, "lr": 7.950432165393259e-05, "epoch": 0.8969422423556059, "percentage": 29.91, "elapsed_time": "14:40:01", "remaining_time": "1 day, 10:22:16", "throughput": 9508.57, "total_tokens": 502065216}
{"current_steps": 2100, "total_steps": 6951, "loss": 0.2538, "lr": 7.911986652197262e-05, "epoch": 0.9060022650056625, "percentage": 30.21, "elapsed_time": "14:48:55", "remaining_time": "1 day, 10:13:25", "throughput": 9507.51, "total_tokens": 507089616}
{"current_steps": 2121, "total_steps": 6951, "loss": 0.2551, "lr": 7.873278819923048e-05, "epoch": 0.9150622876557192, "percentage": 30.51, "elapsed_time": "14:57:43", "remaining_time": "1 day, 10:04:18", "throughput": 9506.69, "total_tokens": 512060336}
{"current_steps": 2142, "total_steps": 6951, "loss": 0.2515, "lr": 7.834312155469456e-05, "epoch": 0.9241223103057757, "percentage": 30.82, "elapsed_time": "15:06:55", "remaining_time": "1 day, 9:56:07", "throughput": 9503.49, "total_tokens": 517133680}
{"current_steps": 2163, "total_steps": 6951, "loss": 0.2526, "lr": 7.79509016905158e-05, "epoch": 0.9331823329558324, "percentage": 31.12, "elapsed_time": "15:15:49", "remaining_time": "1 day, 9:47:16", "throughput": 9503.75, "total_tokens": 522229616}
{"current_steps": 2184, "total_steps": 6951, "loss": 0.2482, "lr": 7.755616393884561e-05, "epoch": 0.942242355605889, "percentage": 31.42, "elapsed_time": "15:24:47", "remaining_time": "1 day, 9:38:31", "throughput": 9504.35, "total_tokens": 527368864}
{"current_steps": 2205, "total_steps": 6951, "loss": 0.2516, "lr": 7.715894385865299e-05, "epoch": 0.9513023782559457, "percentage": 31.72, "elapsed_time": "15:33:55", "remaining_time": "1 day, 9:30:09", "throughput": 9502.88, "total_tokens": 532499712}
{"current_steps": 2226, "total_steps": 6951, "loss": 0.2493, "lr": 7.675927723252134e-05, "epoch": 0.9603624009060022, "percentage": 32.02, "elapsed_time": "15:42:18", "remaining_time": "1 day, 9:20:10", "throughput": 9505.71, "total_tokens": 537438224}
{"current_steps": 2247, "total_steps": 6951, "loss": 0.2465, "lr": 7.635720006342512e-05, "epoch": 0.9694224235560589, "percentage": 32.33, "elapsed_time": "15:51:07", "remaining_time": "1 day, 9:11:07", "throughput": 9508.14, "total_tokens": 542603472}
{"current_steps": 2268, "total_steps": 6951, "loss": 0.2486, "lr": 7.595274857148652e-05, "epoch": 0.9784824462061155, "percentage": 32.63, "elapsed_time": "15:59:54", "remaining_time": "1 day, 9:02:01", "throughput": 9508.27, "total_tokens": 547622688}
{"current_steps": 2289, "total_steps": 6951, "loss": 0.2472, "lr": 7.554595919071268e-05, "epoch": 0.9875424688561721, "percentage": 32.93, "elapsed_time": "16:09:00", "remaining_time": "1 day, 8:53:35", "throughput": 9507.12, "total_tokens": 552751232}
{"current_steps": 2310, "total_steps": 6951, "loss": 0.2471, "lr": 7.513686856571368e-05, "epoch": 0.9966024915062288, "percentage": 33.23, "elapsed_time": "16:17:53", "remaining_time": "1 day, 8:44:39", "throughput": 9506.69, "total_tokens": 557786736}
{"current_steps": 2331, "total_steps": 6951, "loss": 0.2361, "lr": 7.472551354840145e-05, "epoch": 1.0060400151000377, "percentage": 33.53, "elapsed_time": "16:27:14", "remaining_time": "1 day, 8:36:40", "throughput": 9504.55, "total_tokens": 562993712}
{"current_steps": 2352, "total_steps": 6951, "loss": 0.217, "lr": 7.431193119467008e-05, "epoch": 1.0151000377500943, "percentage": 33.84, "elapsed_time": "16:36:00", "remaining_time": "1 day, 8:27:32", "throughput": 9504.99, "total_tokens": 568021744}
{"current_steps": 2373, "total_steps": 6951, "loss": 0.2145, "lr": 7.389615876105774e-05, "epoch": 1.024160060400151, "percentage": 34.14, "elapsed_time": "16:44:31", "remaining_time": "1 day, 8:17:55", "throughput": 9506.33, "total_tokens": 572956608}
{"current_steps": 2394, "total_steps": 6951, "loss": 0.2179, "lr": 7.347823370139042e-05, "epoch": 1.0332200830502076, "percentage": 34.44, "elapsed_time": "16:53:29", "remaining_time": "1 day, 8:09:11", "throughput": 9504.64, "total_tokens": 577973792}
{"current_steps": 2415, "total_steps": 6951, "loss": 0.2098, "lr": 7.30581936634082e-05, "epoch": 1.0422801057002642, "percentage": 34.74, "elapsed_time": "17:02:02", "remaining_time": "1 day, 7:59:40", "throughput": 9506.2, "total_tokens": 582948368}
{"current_steps": 2436, "total_steps": 6951, "loss": 0.2174, "lr": 7.263607648537364e-05, "epoch": 1.051340128350321, "percentage": 35.05, "elapsed_time": "17:10:54", "remaining_time": "1 day, 7:50:43", "throughput": 9505.78, "total_tokens": 587973936}
{"current_steps": 2457, "total_steps": 6951, "loss": 0.2187, "lr": 7.221192019266332e-05, "epoch": 1.0604001510003775, "percentage": 35.35, "elapsed_time": "17:19:42", "remaining_time": "1 day, 7:41:41", "throughput": 9506.65, "total_tokens": 593048624}
{"current_steps": 2478, "total_steps": 6951, "loss": 0.2162, "lr": 7.178576299434238e-05, "epoch": 1.069460173650434, "percentage": 35.65, "elapsed_time": "17:28:45", "remaining_time": "1 day, 7:33:05", "throughput": 9506.1, "total_tokens": 598171840}
{"current_steps": 2499, "total_steps": 6951, "loss": 0.2202, "lr": 7.135764327972261e-05, "epoch": 1.0785201963004907, "percentage": 35.95, "elapsed_time": "17:37:32", "remaining_time": "1 day, 7:24:02", "throughput": 9505.76, "total_tokens": 603168000}
{"current_steps": 2520, "total_steps": 6951, "loss": 0.2237, "lr": 7.092759961490415e-05, "epoch": 1.0875802189505475, "percentage": 36.25, "elapsed_time": "17:46:36", "remaining_time": "1 day, 7:15:26", "throughput": 9504.97, "total_tokens": 608280544}
{"current_steps": 2541, "total_steps": 6951, "loss": 0.2199, "lr": 7.049567073930143e-05, "epoch": 1.096640241600604, "percentage": 36.56, "elapsed_time": "17:55:12", "remaining_time": "1 day, 7:06:04", "throughput": 9505.35, "total_tokens": 613215280}
{"current_steps": 2562, "total_steps": 6951, "loss": 0.2189, "lr": 7.006189556215345e-05, "epoch": 1.1057002642506606, "percentage": 36.86, "elapsed_time": "18:04:29", "remaining_time": "1 day, 6:57:50", "throughput": 9501.61, "total_tokens": 618261984}
{"current_steps": 2583, "total_steps": 6951, "loss": 0.2163, "lr": 6.962631315901861e-05, "epoch": 1.1147602869007172, "percentage": 37.16, "elapsed_time": "18:13:39", "remaining_time": "1 day, 6:49:26", "throughput": 9501.64, "total_tokens": 623492320}
{"current_steps": 2604, "total_steps": 6951, "loss": 0.2157, "lr": 6.918896276825485e-05, "epoch": 1.123820309550774, "percentage": 37.46, "elapsed_time": "18:22:29", "remaining_time": "1 day, 6:40:26", "throughput": 9502.18, "total_tokens": 628563152}
{"current_steps": 2625, "total_steps": 6951, "loss": 0.2141, "lr": 6.874988378748483e-05, "epoch": 1.1328803322008305, "percentage": 37.76, "elapsed_time": "18:31:42", "remaining_time": "1 day, 6:32:05", "throughput": 9499.47, "total_tokens": 633639472}
{"current_steps": 2646, "total_steps": 6951, "loss": 0.2185, "lr": 6.830911577004698e-05, "epoch": 1.141940354850887, "percentage": 38.07, "elapsed_time": "18:40:08", "remaining_time": "1 day, 6:22:27", "throughput": 9502.37, "total_tokens": 638639648}
{"current_steps": 2667, "total_steps": 6951, "loss": 0.2125, "lr": 6.786669842143236e-05, "epoch": 1.1510003775009436, "percentage": 38.37, "elapsed_time": "18:49:04", "remaining_time": "1 day, 6:13:38", "throughput": 9502.47, "total_tokens": 643743632}
{"current_steps": 2688, "total_steps": 6951, "loss": 0.2138, "lr": 6.742267159570795e-05, "epoch": 1.1600604001510004, "percentage": 38.67, "elapsed_time": "18:58:03", "remaining_time": "1 day, 6:04:52", "throughput": 9501.96, "total_tokens": 648823584}
{"current_steps": 2709, "total_steps": 6951, "loss": 0.2152, "lr": 6.697707529192648e-05, "epoch": 1.169120422801057, "percentage": 38.97, "elapsed_time": "19:06:58", "remaining_time": "1 day, 5:56:01", "throughput": 9502.59, "total_tokens": 653949232}
{"current_steps": 2730, "total_steps": 6951, "loss": 0.2125, "lr": 6.652994965052319e-05, "epoch": 1.1781804454511136, "percentage": 39.27, "elapsed_time": "19:15:42", "remaining_time": "1 day, 5:46:54", "throughput": 9503.45, "total_tokens": 658996016}
{"current_steps": 2751, "total_steps": 6951, "loss": 0.2123, "lr": 6.608133494969994e-05, "epoch": 1.1872404681011703, "percentage": 39.58, "elapsed_time": "19:24:50", "remaining_time": "1 day, 5:38:23", "throughput": 9502.01, "total_tokens": 664102304}
{"current_steps": 2772, "total_steps": 6951, "loss": 0.2101, "lr": 6.563127160179671e-05, "epoch": 1.196300490751227, "percentage": 39.88, "elapsed_time": "19:33:50", "remaining_time": "1 day, 5:29:39", "throughput": 9500.47, "total_tokens": 669123584}
{"current_steps": 2793, "total_steps": 6951, "loss": 0.209, "lr": 6.517980014965139e-05, "epoch": 1.2053605134012835, "percentage": 40.18, "elapsed_time": "19:42:43", "remaining_time": "1 day, 5:20:44", "throughput": 9501.47, "total_tokens": 674256592}
{"current_steps": 2814, "total_steps": 6951, "loss": 0.2122, "lr": 6.472696126294732e-05, "epoch": 1.21442053605134, "percentage": 40.48, "elapsed_time": "19:51:25", "remaining_time": "1 day, 5:11:34", "throughput": 9501.91, "total_tokens": 679248208}
{"current_steps": 2835, "total_steps": 6951, "loss": 0.2093, "lr": 6.427279573454985e-05, "epoch": 1.2234805587013968, "percentage": 40.79, "elapsed_time": "20:00:27", "remaining_time": "1 day, 5:02:53", "throughput": 9500.84, "total_tokens": 684325632}
{"current_steps": 2856, "total_steps": 6951, "loss": 0.2114, "lr": 6.381734447683152e-05, "epoch": 1.2325405813514534, "percentage": 41.09, "elapsed_time": "20:09:08", "remaining_time": "1 day, 4:53:41", "throughput": 9501.8, "total_tokens": 689336736}
{"current_steps": 2877, "total_steps": 6951, "loss": 0.2111, "lr": 6.33606485179866e-05, "epoch": 1.24160060400151, "percentage": 41.39, "elapsed_time": "20:18:03", "remaining_time": "1 day, 4:44:51", "throughput": 9501.17, "total_tokens": 694382688}
{"current_steps": 2898, "total_steps": 6951, "loss": 0.2086, "lr": 6.290274899833517e-05, "epoch": 1.2506606266515665, "percentage": 41.69, "elapsed_time": "20:26:49", "remaining_time": "1 day, 4:35:46", "throughput": 9501.16, "total_tokens": 699371792}
{"current_steps": 2919, "total_steps": 6951, "loss": 0.2095, "lr": 6.244368716661713e-05, "epoch": 1.2597206493016233, "percentage": 41.99, "elapsed_time": "20:35:40", "remaining_time": "1 day, 4:26:49", "throughput": 9501.0, "total_tokens": 704404624}
{"current_steps": 2940, "total_steps": 6951, "loss": 0.2083, "lr": 6.198350437627632e-05, "epoch": 1.2687806719516799, "percentage": 42.3, "elapsed_time": "20:44:16", "remaining_time": "1 day, 4:17:33", "throughput": 9502.81, "total_tokens": 709451392}
{"current_steps": 2961, "total_steps": 6951, "loss": 0.2088, "lr": 6.152224208173533e-05, "epoch": 1.2778406946017364, "percentage": 42.6, "elapsed_time": "20:52:56", "remaining_time": "1 day, 4:08:22", "throughput": 9504.07, "total_tokens": 714486848}
{"current_steps": 2982, "total_steps": 6951, "loss": 0.2118, "lr": 6.10599418346613e-05, "epoch": 1.2869007172517932, "percentage": 42.9, "elapsed_time": "21:01:51", "remaining_time": "1 day, 3:59:30", "throughput": 9503.94, "total_tokens": 719556448}
{"current_steps": 3003, "total_steps": 6951, "loss": 0.2058, "lr": 6.059664528022266e-05, "epoch": 1.2959607399018498, "percentage": 43.2, "elapsed_time": "21:10:38", "remaining_time": "1 day, 3:50:29", "throughput": 9504.75, "total_tokens": 724625472}
{"current_steps": 3024, "total_steps": 6951, "loss": 0.2065, "lr": 6.0132394153337755e-05, "epoch": 1.3050207625519064, "percentage": 43.5, "elapsed_time": "21:19:41", "remaining_time": "1 day, 3:41:49", "throughput": 9504.8, "total_tokens": 729794320}
{"current_steps": 3045, "total_steps": 6951, "loss": 0.207, "lr": 5.9667230274915174e-05, "epoch": 1.3140807852019631, "percentage": 43.81, "elapsed_time": "21:28:27", "remaining_time": "1 day, 3:32:47", "throughput": 9504.25, "total_tokens": 734753392}
{"current_steps": 3066, "total_steps": 6951, "loss": 0.2049, "lr": 5.920119554808651e-05, "epoch": 1.3231408078520197, "percentage": 44.11, "elapsed_time": "21:37:32", "remaining_time": "1 day, 3:24:08", "throughput": 9502.94, "total_tokens": 739827088}
{"current_steps": 3087, "total_steps": 6951, "loss": 0.208, "lr": 5.873433195443152e-05, "epoch": 1.3322008305020763, "percentage": 44.41, "elapsed_time": "21:46:47", "remaining_time": "1 day, 3:15:42", "throughput": 9499.75, "total_tokens": 744847184}
{"current_steps": 3108, "total_steps": 6951, "loss": 0.2047, "lr": 5.82666815501964e-05, "epoch": 1.3412608531521328, "percentage": 44.71, "elapsed_time": "21:55:35", "remaining_time": "1 day, 3:06:42", "throughput": 9499.82, "total_tokens": 749874880}
{"current_steps": 3129, "total_steps": 6951, "loss": 0.2022, "lr": 5.779828646250521e-05, "epoch": 1.3503208758021894, "percentage": 45.02, "elapsed_time": "22:04:30", "remaining_time": "1 day, 2:57:51", "throughput": 9498.47, "total_tokens": 754848400}
{"current_steps": 3150, "total_steps": 6951, "loss": 0.2073, "lr": 5.7329188885565e-05, "epoch": 1.3593808984522462, "percentage": 45.32, "elapsed_time": "22:14:01", "remaining_time": "1 day, 2:49:43", "throughput": 9494.01, "total_tokens": 759913728}
{"current_steps": 3171, "total_steps": 6951, "loss": 0.2056, "lr": 5.6859431076864755e-05, "epoch": 1.3684409211023028, "percentage": 45.62, "elapsed_time": "22:23:11", "remaining_time": "1 day, 2:41:09", "throughput": 9492.45, "total_tokens": 765009632}
{"current_steps": 3192, "total_steps": 6951, "loss": 0.2056, "lr": 5.6389055353368826e-05, "epoch": 1.3775009437523593, "percentage": 45.92, "elapsed_time": "22:31:39", "remaining_time": "1 day, 2:31:44", "throughput": 9494.77, "total_tokens": 770016704}
{"current_steps": 3213, "total_steps": 6951, "loss": 0.2037, "lr": 5.591810408770493e-05, "epoch": 1.386560966402416, "percentage": 46.22, "elapsed_time": "22:40:44", "remaining_time": "1 day, 2:23:04", "throughput": 9494.81, "total_tokens": 775197264}
{"current_steps": 3234, "total_steps": 6951, "loss": 0.2042, "lr": 5.544661970434696e-05, "epoch": 1.3956209890524727, "percentage": 46.53, "elapsed_time": "22:49:16", "remaining_time": "1 day, 2:13:46", "throughput": 9496.67, "total_tokens": 780209328}
{"current_steps": 3255, "total_steps": 6951, "loss": 0.2011, "lr": 5.497464467579351e-05, "epoch": 1.4046810117025292, "percentage": 46.83, "elapsed_time": "22:58:20", "remaining_time": "1 day, 2:05:05", "throughput": 9496.92, "total_tokens": 785402112}
{"current_steps": 3276, "total_steps": 6951, "loss": 0.2015, "lr": 5.450222151874166e-05, "epoch": 1.4137410343525858, "percentage": 47.13, "elapsed_time": "23:07:23", "remaining_time": "1 day, 1:56:22", "throughput": 9495.35, "total_tokens": 790429216}
{"current_steps": 3297, "total_steps": 6951, "loss": 0.2005, "lr": 5.402939279025705e-05, "epoch": 1.4228010570026426, "percentage": 47.43, "elapsed_time": "23:16:41", "remaining_time": "1 day, 1:47:56", "throughput": 9493.13, "total_tokens": 795543264}
{"current_steps": 3318, "total_steps": 6951, "loss": 0.2052, "lr": 5.355620108394018e-05, "epoch": 1.4318610796526992, "percentage": 47.73, "elapsed_time": "23:25:21", "remaining_time": "1 day, 1:38:46", "throughput": 9493.86, "total_tokens": 800533200}
{"current_steps": 3339, "total_steps": 6951, "loss": 0.2042, "lr": 5.308268902608958e-05, "epoch": 1.4409211023027557, "percentage": 48.04, "elapsed_time": "23:33:57", "remaining_time": "1 day, 1:29:34", "throughput": 9495.07, "total_tokens": 805542720}
{"current_steps": 3360, "total_steps": 6951, "loss": 0.1984, "lr": 5.2608899271861765e-05, "epoch": 1.4499811249528123, "percentage": 48.34, "elapsed_time": "23:42:55", "remaining_time": "1 day, 1:20:44", "throughput": 9493.99, "total_tokens": 810549376}
{"current_steps": 3381, "total_steps": 6951, "loss": 0.2038, "lr": 5.213487450142892e-05, "epoch": 1.459041147602869, "percentage": 48.64, "elapsed_time": "23:52:03", "remaining_time": "1 day, 1:12:06", "throughput": 9492.2, "total_tokens": 815599232}
{"current_steps": 3402, "total_steps": 6951, "loss": 0.2012, "lr": 5.166065741613402e-05, "epoch": 1.4681011702529256, "percentage": 48.94, "elapsed_time": "1 day, 0:01:00", "remaining_time": "1 day, 1:03:16", "throughput": 9492.22, "total_tokens": 820700608}
{"current_steps": 3423, "total_steps": 6951, "loss": 0.1987, "lr": 5.118629073464424e-05, "epoch": 1.4771611929029822, "percentage": 49.24, "elapsed_time": "1 day, 0:09:40", "remaining_time": "1 day, 0:54:08", "throughput": 9492.76, "total_tokens": 825686176}
{"current_steps": 3444, "total_steps": 6951, "loss": 0.1986, "lr": 5.071181718910283e-05, "epoch": 1.486221215553039, "percentage": 49.55, "elapsed_time": "1 day, 0:18:43", "remaining_time": "1 day, 0:45:24", "throughput": 9491.54, "total_tokens": 830730000}
{"current_steps": 3465, "total_steps": 6951, "loss": 0.1987, "lr": 5.023727952127954e-05, "epoch": 1.4952812382030956, "percentage": 49.85, "elapsed_time": "1 day, 0:27:32", "remaining_time": "1 day, 0:36:26", "throughput": 9491.31, "total_tokens": 835738032}
{"current_steps": 3486, "total_steps": 6951, "loss": 0.1952, "lr": 4.976272047872046e-05, "epoch": 1.5043412608531521, "percentage": 50.15, "elapsed_time": "1 day, 0:36:07", "remaining_time": "1 day, 0:27:14", "throughput": 9493.38, "total_tokens": 840806528}
{"current_steps": 3507, "total_steps": 6951, "loss": 0.1957, "lr": 4.9288182810897184e-05, "epoch": 1.513401283503209, "percentage": 50.45, "elapsed_time": "1 day, 0:44:53", "remaining_time": "1 day, 0:18:12", "throughput": 9494.32, "total_tokens": 845877808}
{"current_steps": 3528, "total_steps": 6951, "loss": 0.1957, "lr": 4.8813709265355766e-05, "epoch": 1.5224613061532652, "percentage": 50.76, "elapsed_time": "1 day, 0:53:46", "remaining_time": "1 day, 0:09:18", "throughput": 9495.01, "total_tokens": 851002432}
{"current_steps": 3549, "total_steps": 6951, "loss": 0.197, "lr": 4.8339342583866005e-05, "epoch": 1.531521328803322, "percentage": 51.06, "elapsed_time": "1 day, 1:02:40", "remaining_time": "1 day, 0:00:26", "throughput": 9494.56, "total_tokens": 856037440}
{"current_steps": 3570, "total_steps": 6951, "loss": 0.1957, "lr": 4.7865125498571086e-05, "epoch": 1.5405813514533786, "percentage": 51.36, "elapsed_time": "1 day, 1:11:11", "remaining_time": "23:51:11", "throughput": 9495.47, "total_tokens": 860972624}
{"current_steps": 3591, "total_steps": 6951, "loss": 0.1926, "lr": 4.739110072813823e-05, "epoch": 1.5496413741034352, "percentage": 51.66, "elapsed_time": "1 day, 1:20:00", "remaining_time": "23:42:13", "throughput": 9496.47, "total_tokens": 866078128}
{"current_steps": 3612, "total_steps": 6951, "loss": 0.1934, "lr": 4.6917310973910425e-05, "epoch": 1.558701396753492, "percentage": 51.96, "elapsed_time": "1 day, 1:29:07", "remaining_time": "23:33:32", "throughput": 9496.66, "total_tokens": 871290720}
{"current_steps": 3633, "total_steps": 6951, "loss": 0.1961, "lr": 4.6443798916059836e-05, "epoch": 1.5677614194035485, "percentage": 52.27, "elapsed_time": "1 day, 1:38:01", "remaining_time": "23:24:40", "throughput": 9496.52, "total_tokens": 876353920}
{"current_steps": 3654, "total_steps": 6951, "loss": 0.1902, "lr": 4.597060720974298e-05, "epoch": 1.576821442053605, "percentage": 52.57, "elapsed_time": "1 day, 1:47:05", "remaining_time": "23:15:56", "throughput": 9496.01, "total_tokens": 881469536}
{"current_steps": 3675, "total_steps": 6951, "loss": 0.1971, "lr": 4.549777848125833e-05, "epoch": 1.5858814647036619, "percentage": 52.87, "elapsed_time": "1 day, 1:56:04", "remaining_time": "23:07:07", "throughput": 9495.37, "total_tokens": 886532048}
{"current_steps": 3696, "total_steps": 6951, "loss": 0.1952, "lr": 4.50253553242065e-05, "epoch": 1.5949414873537184, "percentage": 53.17, "elapsed_time": "1 day, 2:04:53", "remaining_time": "22:58:10", "throughput": 9495.5, "total_tokens": 891565152}
{"current_steps": 3717, "total_steps": 6951, "loss": 0.1908, "lr": 4.4553380295653053e-05, "epoch": 1.604001510003775, "percentage": 53.47, "elapsed_time": "1 day, 2:13:32", "remaining_time": "22:49:03", "throughput": 9496.69, "total_tokens": 896603568}
{"current_steps": 3738, "total_steps": 6951, "loss": 0.1945, "lr": 4.40818959122951e-05, "epoch": 1.6130615326538318, "percentage": 53.78, "elapsed_time": "1 day, 2:22:34", "remaining_time": "22:40:17", "throughput": 9496.2, "total_tokens": 901703264}
{"current_steps": 3759, "total_steps": 6951, "loss": 0.1911, "lr": 4.361094464663118e-05, "epoch": 1.6221215553038881, "percentage": 54.08, "elapsed_time": "1 day, 2:31:30", "remaining_time": "22:31:27", "throughput": 9496.7, "total_tokens": 906846256}
{"current_steps": 3780, "total_steps": 6951, "loss": 0.193, "lr": 4.3140568923135264e-05, "epoch": 1.631181577953945, "percentage": 54.38, "elapsed_time": "1 day, 2:40:27", "remaining_time": "22:22:36", "throughput": 9496.86, "total_tokens": 911964272}
{"current_steps": 3801, "total_steps": 6951, "loss": 0.1898, "lr": 4.267081111443501e-05, "epoch": 1.6402416006040015, "percentage": 54.68, "elapsed_time": "1 day, 2:49:16", "remaining_time": "22:13:39", "throughput": 9498.11, "total_tokens": 917101840}
{"current_steps": 3822, "total_steps": 6951, "loss": 0.1852, "lr": 4.22017135374948e-05, "epoch": 1.649301623254058, "percentage": 54.98, "elapsed_time": "1 day, 2:57:51", "remaining_time": "22:04:30", "throughput": 9500.27, "total_tokens": 922205664}
{"current_steps": 3843, "total_steps": 6951, "loss": 0.1863, "lr": 4.1733318449803624e-05, "epoch": 1.6583616459041148, "percentage": 55.29, "elapsed_time": "1 day, 3:06:51", "remaining_time": "21:55:42", "throughput": 9499.96, "total_tokens": 927302560}
{"current_steps": 3864, "total_steps": 6951, "loss": 0.1882, "lr": 4.1265668045568495e-05, "epoch": 1.6674216685541714, "percentage": 55.59, "elapsed_time": "1 day, 3:15:50", "remaining_time": "21:46:53", "throughput": 9498.96, "total_tokens": 932325424}
{"current_steps": 3885, "total_steps": 6951, "loss": 0.1893, "lr": 4.079880445191351e-05, "epoch": 1.676481691204228, "percentage": 55.89, "elapsed_time": "1 day, 3:24:37", "remaining_time": "21:37:54", "throughput": 9500.06, "total_tokens": 937438464}
{"current_steps": 3906, "total_steps": 6951, "loss": 0.1885, "lr": 4.033276972508484e-05, "epoch": 1.6855417138542848, "percentage": 56.19, "elapsed_time": "1 day, 3:33:46", "remaining_time": "21:29:13", "throughput": 9499.68, "total_tokens": 942617840}
{"current_steps": 3927, "total_steps": 6951, "loss": 0.1883, "lr": 3.9867605846662256e-05, "epoch": 1.6946017365043413, "percentage": 56.5, "elapsed_time": "1 day, 3:42:59", "remaining_time": "21:20:35", "throughput": 9499.21, "total_tokens": 947823200}
{"current_steps": 3948, "total_steps": 6951, "loss": 0.1871, "lr": 3.940335471977734e-05, "epoch": 1.7036617591543979, "percentage": 56.8, "elapsed_time": "1 day, 3:51:52", "remaining_time": "21:11:41", "throughput": 9499.01, "total_tokens": 952872784}
{"current_steps": 3969, "total_steps": 6951, "loss": 0.1853, "lr": 3.89400581653387e-05, "epoch": 1.7127217818044547, "percentage": 57.1, "elapsed_time": "1 day, 4:00:45", "remaining_time": "21:02:47", "throughput": 9498.79, "total_tokens": 957908608}
{"current_steps": 3990, "total_steps": 6951, "loss": 0.1862, "lr": 3.847775791826468e-05, "epoch": 1.721781804454511, "percentage": 57.4, "elapsed_time": "1 day, 4:09:30", "remaining_time": "20:53:47", "throughput": 9499.53, "total_tokens": 962972208}
{"current_steps": 4011, "total_steps": 6951, "loss": 0.1913, "lr": 3.801649562372371e-05, "epoch": 1.7308418271045678, "percentage": 57.7, "elapsed_time": "1 day, 4:18:34", "remaining_time": "20:45:01", "throughput": 9498.33, "total_tokens": 968020256}
{"current_steps": 4032, "total_steps": 6951, "loss": 0.1908, "lr": 3.755631283338287e-05, "epoch": 1.7399018497546244, "percentage": 58.01, "elapsed_time": "1 day, 4:27:34", "remaining_time": "20:36:12", "throughput": 9498.07, "total_tokens": 973116912}
{"current_steps": 4053, "total_steps": 6951, "loss": 0.1839, "lr": 3.709725100166482e-05, "epoch": 1.748961872404681, "percentage": 58.31, "elapsed_time": "1 day, 4:36:56", "remaining_time": "20:27:39", "throughput": 9496.29, "total_tokens": 978276224}
{"current_steps": 4074, "total_steps": 6951, "loss": 0.1869, "lr": 3.663935148201341e-05, "epoch": 1.7580218950547377, "percentage": 58.61, "elapsed_time": "1 day, 4:46:12", "remaining_time": "20:19:01", "throughput": 9495.72, "total_tokens": 983499184}
{"current_steps": 4095, "total_steps": 6951, "loss": 0.1884, "lr": 3.618265552316849e-05, "epoch": 1.7670819177047943, "percentage": 58.91, "elapsed_time": "1 day, 4:55:11", "remaining_time": "20:10:11", "throughput": 9494.7, "total_tokens": 988511216}
{"current_steps": 4116, "total_steps": 6951, "loss": 0.1863, "lr": 3.572720426545017e-05, "epoch": 1.7761419403548508, "percentage": 59.21, "elapsed_time": "1 day, 5:04:24", "remaining_time": "20:01:30", "throughput": 9492.68, "total_tokens": 993542272}
{"current_steps": 4137, "total_steps": 6951, "loss": 0.1884, "lr": 3.5273038737052675e-05, "epoch": 1.7852019630049076, "percentage": 59.52, "elapsed_time": "1 day, 5:13:02", "remaining_time": "19:52:25", "throughput": 9493.64, "total_tokens": 998561584}
{"current_steps": 4158, "total_steps": 6951, "loss": 0.1815, "lr": 3.482019985034861e-05, "epoch": 1.794261985654964, "percentage": 59.82, "elapsed_time": "1 day, 5:21:39", "remaining_time": "19:43:19", "throughput": 9494.28, "total_tokens": 1003535696}
{"current_steps": 4179, "total_steps": 6951, "loss": 0.1798, "lr": 3.43687283982033e-05, "epoch": 1.8033220083050208, "percentage": 60.12, "elapsed_time": "1 day, 5:30:37", "remaining_time": "19:34:29", "throughput": 9493.88, "total_tokens": 1008610432}
{"current_steps": 4200, "total_steps": 6951, "loss": 0.1797, "lr": 3.391866505030009e-05, "epoch": 1.8123820309550775, "percentage": 60.42, "elapsed_time": "1 day, 5:39:08", "remaining_time": "19:25:20", "throughput": 9495.04, "total_tokens": 1013577840}
{"current_steps": 4221, "total_steps": 6951, "loss": 0.1773, "lr": 3.347005034947681e-05, "epoch": 1.821442053605134, "percentage": 60.73, "elapsed_time": "1 day, 5:47:48", "remaining_time": "19:16:17", "throughput": 9495.33, "total_tokens": 1018549888}
{"current_steps": 4242, "total_steps": 6951, "loss": 0.1828, "lr": 3.3022924708073524e-05, "epoch": 1.8305020762551907, "percentage": 61.03, "elapsed_time": "1 day, 5:56:40", "remaining_time": "19:07:23", "throughput": 9494.34, "total_tokens": 1023498368}
{"current_steps": 4263, "total_steps": 6951, "loss": 0.18, "lr": 3.257732840429206e-05, "epoch": 1.8395620989052472, "percentage": 61.33, "elapsed_time": "1 day, 6:05:35", "remaining_time": "18:58:30", "throughput": 9494.06, "total_tokens": 1028542992}
{"current_steps": 4284, "total_steps": 6951, "loss": 0.1825, "lr": 3.2133301578567646e-05, "epoch": 1.8486221215553038, "percentage": 61.63, "elapsed_time": "1 day, 6:14:31", "remaining_time": "18:49:37", "throughput": 9493.51, "total_tokens": 1033574288}
{"current_steps": 4305, "total_steps": 6951, "loss": 0.1776, "lr": 3.169088422995304e-05, "epoch": 1.8576821442053606, "percentage": 61.93, "elapsed_time": "1 day, 6:23:27", "remaining_time": "18:40:45", "throughput": 9493.01, "total_tokens": 1038606208}
{"current_steps": 4326, "total_steps": 6951, "loss": 0.1768, "lr": 3.125011621251516e-05, "epoch": 1.8667421668554172, "percentage": 62.24, "elapsed_time": "1 day, 6:32:31", "remaining_time": "18:31:57", "throughput": 9493.04, "total_tokens": 1043770704}
{"current_steps": 4347, "total_steps": 6951, "loss": 0.1778, "lr": 3.081103723174515e-05, "epoch": 1.8758021895054737, "percentage": 62.54, "elapsed_time": "1 day, 6:41:34", "remaining_time": "18:23:09", "throughput": 9492.18, "total_tokens": 1048829664}
{"current_steps": 4368, "total_steps": 6951, "loss": 0.1788, "lr": 3.0373686840981397e-05, "epoch": 1.8848622121555305, "percentage": 62.84, "elapsed_time": "1 day, 6:50:45", "remaining_time": "18:14:26", "throughput": 9491.15, "total_tokens": 1053950224}
{"current_steps": 4389, "total_steps": 6951, "loss": 0.176, "lr": 2.9938104437846572e-05, "epoch": 1.8939222348055869, "percentage": 63.14, "elapsed_time": "1 day, 6:59:56", "remaining_time": "18:05:42", "throughput": 9490.66, "total_tokens": 1059119888}
{"current_steps": 4410, "total_steps": 6951, "loss": 0.1783, "lr": 2.950432926069857e-05, "epoch": 1.9029822574556436, "percentage": 63.44, "elapsed_time": "1 day, 7:08:56", "remaining_time": "17:56:52", "throughput": 9490.01, "total_tokens": 1064177088}
{"current_steps": 4431, "total_steps": 6951, "loss": 0.178, "lr": 2.9072400385095865e-05, "epoch": 1.9120422801057002, "percentage": 63.75, "elapsed_time": "1 day, 7:18:02", "remaining_time": "17:48:05", "throughput": 9488.58, "total_tokens": 1069200928}
{"current_steps": 4452, "total_steps": 6951, "loss": 0.1759, "lr": 2.864235672027741e-05, "epoch": 1.9211023027557568, "percentage": 64.05, "elapsed_time": "1 day, 7:27:05", "remaining_time": "17:39:15", "throughput": 9488.29, "total_tokens": 1074313840}
{"current_steps": 4473, "total_steps": 6951, "loss": 0.1769, "lr": 2.8214237005657627e-05, "epoch": 1.9301623254058136, "percentage": 64.35, "elapsed_time": "1 day, 7:36:04", "remaining_time": "17:30:24", "throughput": 9487.56, "total_tokens": 1079348080}
{"current_steps": 4494, "total_steps": 6951, "loss": 0.1761, "lr": 2.7788079807336692e-05, "epoch": 1.9392223480558701, "percentage": 64.65, "elapsed_time": "1 day, 7:44:52", "remaining_time": "17:21:26", "throughput": 9488.08, "total_tokens": 1084415072}
{"current_steps": 4515, "total_steps": 6951, "loss": 0.1762, "lr": 2.7363923514626367e-05, "epoch": 1.9482823707059267, "percentage": 64.95, "elapsed_time": "1 day, 7:53:50", "remaining_time": "17:12:35", "throughput": 9488.56, "total_tokens": 1089576528}
{"current_steps": 4536, "total_steps": 6951, "loss": 0.1715, "lr": 2.6941806336591808e-05, "epoch": 1.9573423933559835, "percentage": 65.26, "elapsed_time": "1 day, 8:02:49", "remaining_time": "17:03:43", "throughput": 9489.02, "total_tokens": 1094741664}
{"current_steps": 4557, "total_steps": 6951, "loss": 0.1728, "lr": 2.6521766298609584e-05, "epoch": 1.96640241600604, "percentage": 65.56, "elapsed_time": "1 day, 8:11:24", "remaining_time": "16:54:39", "throughput": 9489.67, "total_tokens": 1099708896}
{"current_steps": 4578, "total_steps": 6951, "loss": 0.175, "lr": 2.610384123894229e-05, "epoch": 1.9754624386560966, "percentage": 65.86, "elapsed_time": "1 day, 8:20:35", "remaining_time": "16:45:54", "throughput": 9488.69, "total_tokens": 1104824512}
{"current_steps": 4599, "total_steps": 6951, "loss": 0.1736, "lr": 2.568806880532991e-05, "epoch": 1.9845224613061534, "percentage": 66.16, "elapsed_time": "1 day, 8:29:26", "remaining_time": "16:36:58", "throughput": 9489.47, "total_tokens": 1109954160}
{"current_steps": 4620, "total_steps": 6951, "loss": 0.1704, "lr": 2.5274486451598565e-05, "epoch": 1.9935824839562097, "percentage": 66.47, "elapsed_time": "1 day, 8:38:34", "remaining_time": "16:28:11", "throughput": 9489.29, "total_tokens": 1115130992}
{"current_steps": 4641, "total_steps": 6951, "loss": 0.1548, "lr": 2.4863131434286342e-05, "epoch": 2.003020007550019, "percentage": 66.77, "elapsed_time": "1 day, 8:47:29", "remaining_time": "16:19:17", "throughput": 9490.07, "total_tokens": 1120294784}
{"current_steps": 4662, "total_steps": 6951, "loss": 0.1188, "lr": 2.4454040809287342e-05, "epoch": 2.0120800302000754, "percentage": 67.07, "elapsed_time": "1 day, 8:56:29", "remaining_time": "16:10:26", "throughput": 9489.7, "total_tokens": 1125375728}
{"current_steps": 4683, "total_steps": 6951, "loss": 0.1176, "lr": 2.4047251428513485e-05, "epoch": 2.021140052850132, "percentage": 67.37, "elapsed_time": "1 day, 9:05:40", "remaining_time": "16:01:40", "throughput": 9490.21, "total_tokens": 1130663488}
{"current_steps": 4704, "total_steps": 6951, "loss": 0.1166, "lr": 2.364279993657487e-05, "epoch": 2.0302000755001886, "percentage": 67.67, "elapsed_time": "1 day, 9:14:37", "remaining_time": "15:52:47", "throughput": 9489.93, "total_tokens": 1135729856}
{"current_steps": 4725, "total_steps": 6951, "loss": 0.1129, "lr": 2.3240722767478657e-05, "epoch": 2.0392600981502453, "percentage": 67.98, "elapsed_time": "1 day, 9:23:32", "remaining_time": "15:43:53", "throughput": 9489.27, "total_tokens": 1140728768}
{"current_steps": 4746, "total_steps": 6951, "loss": 0.1122, "lr": 2.2841056141347038e-05, "epoch": 2.048320120800302, "percentage": 68.28, "elapsed_time": "1 day, 9:32:17", "remaining_time": "15:34:54", "throughput": 9490.08, "total_tokens": 1145810672}
{"current_steps": 4767, "total_steps": 6951, "loss": 0.1145, "lr": 2.2443836061154415e-05, "epoch": 2.0573801434503585, "percentage": 68.58, "elapsed_time": "1 day, 9:41:09", "remaining_time": "15:25:59", "throughput": 9490.09, "total_tokens": 1150862064}
{"current_steps": 4788, "total_steps": 6951, "loss": 0.1153, "lr": 2.2049098309484195e-05, "epoch": 2.0664401661004153, "percentage": 68.88, "elapsed_time": "1 day, 9:50:04", "remaining_time": "15:17:05", "throughput": 9490.25, "total_tokens": 1155954544}
{"current_steps": 4809, "total_steps": 6951, "loss": 0.1152, "lr": 2.1656878445305447e-05, "epoch": 2.075500188750472, "percentage": 69.18, "elapsed_time": "1 day, 9:59:12", "remaining_time": "15:08:17", "throughput": 9489.42, "total_tokens": 1161054256}
{"current_steps": 4830, "total_steps": 6951, "loss": 0.1148, "lr": 2.1267211800769528e-05, "epoch": 2.0845602114005284, "percentage": 69.49, "elapsed_time": "1 day, 10:07:55", "remaining_time": "14:59:18", "throughput": 9489.77, "total_tokens": 1166056688}
{"current_steps": 4851, "total_steps": 6951, "loss": 0.1119, "lr": 2.088013347802738e-05, "epoch": 2.093620234050585, "percentage": 69.79, "elapsed_time": "1 day, 10:17:16", "remaining_time": "14:50:35", "throughput": 9488.55, "total_tokens": 1171231104}
{"current_steps": 4872, "total_steps": 6951, "loss": 0.1101, "lr": 2.0495678346067414e-05, "epoch": 2.102680256700642, "percentage": 70.09, "elapsed_time": "1 day, 10:26:21", "remaining_time": "14:41:45", "throughput": 9487.59, "total_tokens": 1176284976}
{"current_steps": 4893, "total_steps": 6951, "loss": 0.1139, "lr": 2.011388103757442e-05, "epoch": 2.1117402793506983, "percentage": 70.39, "elapsed_time": "1 day, 10:35:22", "remaining_time": "14:32:54", "throughput": 9487.45, "total_tokens": 1181400944}
{"current_steps": 4914, "total_steps": 6951, "loss": 0.1116, "lr": 1.973477594580977e-05, "epoch": 2.120800302000755, "percentage": 70.69, "elapsed_time": "1 day, 10:43:54", "remaining_time": "14:23:50", "throughput": 9489.64, "total_tokens": 1186527776}
{"current_steps": 4935, "total_steps": 6951, "loss": 0.112, "lr": 1.9358397221513176e-05, "epoch": 2.1298603246508114, "percentage": 71.0, "elapsed_time": "1 day, 10:53:02", "remaining_time": "14:15:01", "throughput": 9489.09, "total_tokens": 1191661680}
{"current_steps": 4956, "total_steps": 6951, "loss": 0.1106, "lr": 1.8984778769826316e-05, "epoch": 2.138920347300868, "percentage": 71.3, "elapsed_time": "1 day, 11:02:03", "remaining_time": "14:06:10", "throughput": 9488.78, "total_tokens": 1196759648}
{"current_steps": 4977, "total_steps": 6951, "loss": 0.1124, "lr": 1.8613954247238586e-05, "epoch": 2.147980369950925, "percentage": 71.6, "elapsed_time": "1 day, 11:11:03", "remaining_time": "13:57:17", "throughput": 9488.59, "total_tokens": 1201857104}
{"current_steps": 4998, "total_steps": 6951, "loss": 0.1136, "lr": 1.82459570585552e-05, "epoch": 2.1570403926009813, "percentage": 71.9, "elapsed_time": "1 day, 11:19:54", "remaining_time": "13:48:22", "throughput": 9488.83, "total_tokens": 1206927520}
{"current_steps": 5000, "total_steps": 6951, "eval_loss": 0.19485081732273102, "epoch": 2.157903251900987, "percentage": 71.93, "elapsed_time": "1 day, 11:29:30", "remaining_time": "13:50:56", "throughput": 9449.62, "total_tokens": 1207385424}
{"current_steps": 5019, "total_steps": 6951, "loss": 0.1102, "lr": 1.7880820353888056e-05, "epoch": 2.166100415251038, "percentage": 72.21, "elapsed_time": "1 day, 11:49:54", "remaining_time": "13:47:34", "throughput": 9394.81, "total_tokens": 1211875824}
{"current_steps": 5040, "total_steps": 6951, "loss": 0.113, "lr": 1.751857702566944e-05, "epoch": 2.175160437901095, "percentage": 72.51, "elapsed_time": "1 day, 11:58:57", "remaining_time": "13:38:36", "throughput": 9394.59, "total_tokens": 1216954688}
{"current_steps": 5061, "total_steps": 6951, "loss": 0.1104, "lr": 1.7159259705689e-05, "epoch": 2.1842204605511513, "percentage": 72.81, "elapsed_time": "1 day, 12:07:48", "remaining_time": "13:29:33", "throughput": 9394.84, "total_tokens": 1221976560}
{"current_steps": 5082, "total_steps": 6951, "loss": 0.1152, "lr": 1.6802900762154267e-05, "epoch": 2.193280483201208, "percentage": 73.11, "elapsed_time": "1 day, 12:16:35", "remaining_time": "13:20:29", "throughput": 9395.21, "total_tokens": 1226975776}
{"current_steps": 5103, "total_steps": 6951, "loss": 0.1097, "lr": 1.644953229677474e-05, "epoch": 2.2023405058512644, "percentage": 73.41, "elapsed_time": "1 day, 12:25:12", "remaining_time": "13:11:21", "throughput": 9396.5, "total_tokens": 1231998784}
{"current_steps": 5124, "total_steps": 6951, "loss": 0.1111, "lr": 1.609918614187009e-05, "epoch": 2.211400528501321, "percentage": 73.72, "elapsed_time": "1 day, 12:34:03", "remaining_time": "13:02:18", "throughput": 9396.54, "total_tokens": 1236990864}
{"current_steps": 5145, "total_steps": 6951, "loss": 0.1104, "lr": 1.575189385750271e-05, "epoch": 2.220460551151378, "percentage": 74.02, "elapsed_time": "1 day, 12:42:57", "remaining_time": "12:53:17", "throughput": 9396.81, "total_tokens": 1242051280}
{"current_steps": 5166, "total_steps": 6951, "loss": 0.1075, "lr": 1.540768672863468e-05, "epoch": 2.2295205738014343, "percentage": 74.32, "elapsed_time": "1 day, 12:51:51", "remaining_time": "12:44:15", "throughput": 9397.25, "total_tokens": 1247127040}
{"current_steps": 5187, "total_steps": 6951, "loss": 0.1093, "lr": 1.5066595762309477e-05, "epoch": 2.238580596451491, "percentage": 74.62, "elapsed_time": "1 day, 13:00:47", "remaining_time": "12:35:14", "throughput": 9397.23, "total_tokens": 1252158672}
{"current_steps": 5208, "total_steps": 6951, "loss": 0.1126, "lr": 1.4728651684858834e-05, "epoch": 2.247640619101548, "percentage": 74.92, "elapsed_time": "1 day, 13:09:50", "remaining_time": "12:26:16", "throughput": 9397.67, "total_tokens": 1257321184}
{"current_steps": 5229, "total_steps": 6951, "loss": 0.1064, "lr": 1.4393884939134833e-05, "epoch": 2.2567006417516042, "percentage": 75.23, "elapsed_time": "1 day, 13:18:33", "remaining_time": "12:17:11", "throughput": 9398.27, "total_tokens": 1262315984}
{"current_steps": 5250, "total_steps": 6951, "loss": 0.1096, "lr": 1.4062325681767469e-05, "epoch": 2.265760664401661, "percentage": 75.53, "elapsed_time": "1 day, 13:27:25", "remaining_time": "12:08:10", "throughput": 9398.52, "total_tokens": 1267351616}
{"current_steps": 5271, "total_steps": 6951, "loss": 0.1089, "lr": 1.3734003780448218e-05, "epoch": 2.274820687051718, "percentage": 75.83, "elapsed_time": "1 day, 13:36:22", "remaining_time": "11:59:09", "throughput": 9398.21, "total_tokens": 1272350592}
{"current_steps": 5292, "total_steps": 6951, "loss": 0.1093, "lr": 1.340894881123932e-05, "epoch": 2.283880709701774, "percentage": 76.13, "elapsed_time": "1 day, 13:44:45", "remaining_time": "11:49:58", "throughput": 9399.94, "total_tokens": 1277314160}
{"current_steps": 5313, "total_steps": 6951, "loss": 0.1064, "lr": 1.308719005590957e-05, "epoch": 2.292940732351831, "percentage": 76.44, "elapsed_time": "1 day, 13:53:34", "remaining_time": "11:40:56", "throughput": 9400.36, "total_tokens": 1282348896}
{"current_steps": 5334, "total_steps": 6951, "loss": 0.1103, "lr": 1.276875649929654e-05, "epoch": 2.3020007550018873, "percentage": 76.74, "elapsed_time": "1 day, 14:02:35", "remaining_time": "11:31:58", "throughput": 9400.86, "total_tokens": 1287503120}
{"current_steps": 5355, "total_steps": 6951, "loss": 0.1077, "lr": 1.2453676826695532e-05, "epoch": 2.311060777651944, "percentage": 77.04, "elapsed_time": "1 day, 14:11:17", "remaining_time": "11:22:53", "throughput": 9401.43, "total_tokens": 1292488224}
{"current_steps": 5376, "total_steps": 6951, "loss": 0.1051, "lr": 1.2141979421275545e-05, "epoch": 2.320120800302001, "percentage": 77.34, "elapsed_time": "1 day, 14:20:08", "remaining_time": "11:13:52", "throughput": 9402.42, "total_tokens": 1297613792}
{"current_steps": 5397, "total_steps": 6951, "loss": 0.1063, "lr": 1.1833692361522459e-05, "epoch": 2.329180822952057, "percentage": 77.64, "elapsed_time": "1 day, 14:29:19", "remaining_time": "11:04:56", "throughput": 9402.19, "total_tokens": 1302765200}
{"current_steps": 5418, "total_steps": 6951, "loss": 0.1073, "lr": 1.1528843418709622e-05, "epoch": 2.338240845602114, "percentage": 77.95, "elapsed_time": "1 day, 14:38:06", "remaining_time": "10:55:53", "throughput": 9402.65, "total_tokens": 1307780896}
{"current_steps": 5439, "total_steps": 6951, "loss": 0.1076, "lr": 1.1227460054396177e-05, "epoch": 2.3473008682521708, "percentage": 78.25, "elapsed_time": "1 day, 14:47:09", "remaining_time": "10:46:55", "throughput": 9402.88, "total_tokens": 1312916864}
{"current_steps": 5460, "total_steps": 6951, "loss": 0.1049, "lr": 1.0929569417953278e-05, "epoch": 2.356360890902227, "percentage": 78.55, "elapsed_time": "1 day, 14:55:45", "remaining_time": "10:37:50", "throughput": 9403.97, "total_tokens": 1317924528}
{"current_steps": 5481, "total_steps": 6951, "loss": 0.1038, "lr": 1.0635198344118296e-05, "epoch": 2.365420913552284, "percentage": 78.85, "elapsed_time": "1 day, 15:04:24", "remaining_time": "10:28:46", "throughput": 9404.57, "total_tokens": 1322892896}
{"current_steps": 5502, "total_steps": 6951, "loss": 0.1049, "lr": 1.034437335057762e-05, "epoch": 2.3744809362023407, "percentage": 79.15, "elapsed_time": "1 day, 15:13:27", "remaining_time": "10:19:48", "throughput": 9404.62, "total_tokens": 1328000960}
{"current_steps": 5523, "total_steps": 6951, "loss": 0.1026, "lr": 1.005712063557776e-05, "epoch": 2.383540958852397, "percentage": 79.46, "elapsed_time": "1 day, 15:22:31", "remaining_time": "10:10:50", "throughput": 9404.53, "total_tokens": 1333104928}
{"current_steps": 5544, "total_steps": 6951, "loss": 0.1061, "lr": 9.773466075565457e-06, "epoch": 2.392600981502454, "percentage": 79.76, "elapsed_time": "1 day, 15:31:14", "remaining_time": "10:01:47", "throughput": 9405.0, "total_tokens": 1338094928}
{"current_steps": 5565, "total_steps": 6951, "loss": 0.1078, "lr": 9.493435222856556e-06, "epoch": 2.40166100415251, "percentage": 80.06, "elapsed_time": "1 day, 15:39:56", "remaining_time": "9:52:44", "throughput": 9405.66, "total_tokens": 1343094352}
{"current_steps": 5586, "total_steps": 6951, "loss": 0.1021, "lr": 9.21705330333426e-06, "epoch": 2.410721026802567, "percentage": 80.36, "elapsed_time": "1 day, 15:49:17", "remaining_time": "9:43:50", "throughput": 9404.52, "total_tokens": 1348209008}
{"current_steps": 5607, "total_steps": 6951, "loss": 0.105, "lr": 8.944345214176675e-06, "epoch": 2.4197810494526237, "percentage": 80.66, "elapsed_time": "1 day, 15:58:21", "remaining_time": "9:34:53", "throughput": 9404.23, "total_tokens": 1353281712}
{"current_steps": 5628, "total_steps": 6951, "loss": 0.1039, "lr": 8.675335521614036e-06, "epoch": 2.42884107210268, "percentage": 80.97, "elapsed_time": "1 day, 16:07:19", "remaining_time": "9:25:54", "throughput": 9404.1, "total_tokens": 1358325728}
{"current_steps": 5649, "total_steps": 6951, "loss": 0.1026, "lr": 8.410048458715763e-06, "epoch": 2.437901094752737, "percentage": 81.27, "elapsed_time": "1 day, 16:16:00", "remaining_time": "9:16:50", "throughput": 9404.46, "total_tokens": 1363274864}
{"current_steps": 5670, "total_steps": 6951, "loss": 0.1046, "lr": 8.148507923207377e-06, "epoch": 2.4469611174027937, "percentage": 81.57, "elapsed_time": "1 day, 16:24:54", "remaining_time": "9:07:50", "throughput": 9405.18, "total_tokens": 1368398176}
{"current_steps": 5691, "total_steps": 6951, "loss": 0.1062, "lr": 7.890737475317817e-06, "epoch": 2.45602114005285, "percentage": 81.87, "elapsed_time": "1 day, 16:33:40", "remaining_time": "8:58:49", "throughput": 9405.68, "total_tokens": 1373421664}
{"current_steps": 5712, "total_steps": 6951, "loss": 0.1005, "lr": 7.636760335657056e-06, "epoch": 2.465081162702907, "percentage": 82.18, "elapsed_time": "1 day, 16:42:05", "remaining_time": "8:49:43", "throughput": 9407.14, "total_tokens": 1378386688}
{"current_steps": 5733, "total_steps": 6951, "loss": 0.1008, "lr": 7.38659938312432e-06, "epoch": 2.4741411853529636, "percentage": 82.48, "elapsed_time": "1 day, 16:51:02", "remaining_time": "8:40:43", "throughput": 9407.69, "total_tokens": 1383515360}
{"current_steps": 5754, "total_steps": 6951, "loss": 0.1012, "lr": 7.140277152847103e-06, "epoch": 2.48320120800302, "percentage": 82.78, "elapsed_time": "1 day, 17:00:07", "remaining_time": "8:31:46", "throughput": 9407.74, "total_tokens": 1388651712}
{"current_steps": 5775, "total_steps": 6951, "loss": 0.1004, "lr": 6.89781583415115e-06, "epoch": 2.4922612306530767, "percentage": 83.08, "elapsed_time": "1 day, 17:08:58", "remaining_time": "8:22:46", "throughput": 9408.87, "total_tokens": 1393819168}
{"current_steps": 5796, "total_steps": 6951, "loss": 0.1058, "lr": 6.659237268561569e-06, "epoch": 2.501321253303133, "percentage": 83.38, "elapsed_time": "1 day, 17:18:05", "remaining_time": "8:13:49", "throughput": 9409.14, "total_tokens": 1399005008}
{"current_steps": 5817, "total_steps": 6951, "loss": 0.0996, "lr": 6.424562947835367e-06, "epoch": 2.51038127595319, "percentage": 83.69, "elapsed_time": "1 day, 17:26:42", "remaining_time": "8:04:46", "throughput": 9410.56, "total_tokens": 1404075040}
{"current_steps": 5838, "total_steps": 6951, "loss": 0.098, "lr": 6.193814012025278e-06, "epoch": 2.5194412986032466, "percentage": 83.99, "elapsed_time": "1 day, 17:35:31", "remaining_time": "7:55:45", "throughput": 9411.15, "total_tokens": 1409145760}
{"current_steps": 5859, "total_steps": 6951, "loss": 0.1053, "lr": 5.967011247575532e-06, "epoch": 2.5285013212533034, "percentage": 84.29, "elapsed_time": "1 day, 17:44:21", "remaining_time": "7:46:45", "throughput": 9411.73, "total_tokens": 1414225568}
{"current_steps": 5880, "total_steps": 6951, "loss": 0.1021, "lr": 5.744175085449338e-06, "epoch": 2.5375613439033597, "percentage": 84.59, "elapsed_time": "1 day, 17:53:13", "remaining_time": "7:37:45", "throughput": 9412.46, "total_tokens": 1419339216}
{"current_steps": 5901, "total_steps": 6951, "loss": 0.1003, "lr": 5.525325599288356e-06, "epoch": 2.5466213665534165, "percentage": 84.89, "elapsed_time": "1 day, 18:01:57", "remaining_time": "7:28:44", "throughput": 9413.49, "total_tokens": 1424423024}
{"current_steps": 5922, "total_steps": 6951, "loss": 0.1039, "lr": 5.310482503604497e-06, "epoch": 2.555681389203473, "percentage": 85.2, "elapsed_time": "1 day, 18:10:34", "remaining_time": "7:19:42", "throughput": 9413.93, "total_tokens": 1429360512}
{"current_steps": 5943, "total_steps": 6951, "loss": 0.1034, "lr": 5.09966515200393e-06, "epoch": 2.5647414118535297, "percentage": 85.5, "elapsed_time": "1 day, 18:19:20", "remaining_time": "7:10:42", "throughput": 9414.81, "total_tokens": 1434443216}
{"current_steps": 5964, "total_steps": 6951, "loss": 0.1025, "lr": 4.892892535443655e-06, "epoch": 2.5738014345035864, "percentage": 85.8, "elapsed_time": "1 day, 18:28:29", "remaining_time": "7:01:45", "throughput": 9415.33, "total_tokens": 1439693152}
{"current_steps": 5985, "total_steps": 6951, "loss": 0.1041, "lr": 4.690183280520777e-06, "epoch": 2.582861457153643, "percentage": 86.1, "elapsed_time": "1 day, 18:37:21", "remaining_time": "6:52:45", "throughput": 9415.61, "total_tokens": 1444742640}
{"current_steps": 6006, "total_steps": 6951, "loss": 0.1035, "lr": 4.491555647794609e-06, "epoch": 2.5919214798036996, "percentage": 86.4, "elapsed_time": "1 day, 18:46:26", "remaining_time": "6:43:48", "throughput": 9415.24, "total_tokens": 1449817024}
{"current_steps": 6027, "total_steps": 6951, "loss": 0.102, "lr": 4.297027530141634e-06, "epoch": 2.600981502453756, "percentage": 86.71, "elapsed_time": "1 day, 18:55:28", "remaining_time": "6:34:50", "throughput": 9415.55, "total_tokens": 1454966656}
{"current_steps": 6048, "total_steps": 6951, "loss": 0.0968, "lr": 4.106616451143719e-06, "epoch": 2.6100415251038127, "percentage": 87.01, "elapsed_time": "1 day, 19:04:14", "remaining_time": "6:25:50", "throughput": 9416.74, "total_tokens": 1460107904}
{"current_steps": 6069, "total_steps": 6951, "loss": 0.1025, "lr": 3.9203395635095615e-06, "epoch": 2.6191015477538695, "percentage": 87.31, "elapsed_time": "1 day, 19:13:33", "remaining_time": "6:16:55", "throughput": 9416.5, "total_tokens": 1465329712}
{"current_steps": 6090, "total_steps": 6951, "loss": 0.0992, "lr": 3.7382136475294592e-06, "epoch": 2.6281615704039263, "percentage": 87.61, "elapsed_time": "1 day, 19:22:32", "remaining_time": "6:07:56", "throughput": 9417.01, "total_tokens": 1470486400}
{"current_steps": 6111, "total_steps": 6951, "loss": 0.1014, "lr": 3.5602551095638094e-06, "epoch": 2.6372215930539826, "percentage": 87.92, "elapsed_time": "1 day, 19:31:14", "remaining_time": "5:58:56", "throughput": 9417.49, "total_tokens": 1475481216}
{"current_steps": 6132, "total_steps": 6951, "loss": 0.097, "lr": 3.386479980565077e-06, "epoch": 2.6462816157040394, "percentage": 88.22, "elapsed_time": "1 day, 19:40:20", "remaining_time": "5:49:58", "throughput": 9416.8, "total_tokens": 1480509520}
{"current_steps": 6153, "total_steps": 6951, "loss": 0.1011, "lr": 3.2169039146337455e-06, "epoch": 2.6553416383540958, "percentage": 88.52, "elapsed_time": "1 day, 19:48:47", "remaining_time": "5:40:56", "throughput": 9417.61, "total_tokens": 1485415168}
{"current_steps": 6174, "total_steps": 6951, "loss": 0.1003, "lr": 3.0515421876081364e-06, "epoch": 2.6644016610041525, "percentage": 88.82, "elapsed_time": "1 day, 19:57:43", "remaining_time": "5:31:57", "throughput": 9418.35, "total_tokens": 1490580288}
{"current_steps": 6195, "total_steps": 6951, "loss": 0.1011, "lr": 2.8904096956883396e-06, "epoch": 2.6734616836542093, "percentage": 89.12, "elapsed_time": "1 day, 20:06:34", "remaining_time": "5:22:58", "throughput": 9419.24, "total_tokens": 1495724928}
{"current_steps": 6216, "total_steps": 6951, "loss": 0.0992, "lr": 2.733520954094304e-06, "epoch": 2.6825217063042657, "percentage": 89.43, "elapsed_time": "1 day, 20:15:26", "remaining_time": "5:13:59", "throughput": 9418.86, "total_tokens": 1500671568}
{"current_steps": 6237, "total_steps": 6951, "loss": 0.0985, "lr": 2.580890095758276e-06, "epoch": 2.6915817289543225, "percentage": 89.73, "elapsed_time": "1 day, 20:24:26", "remaining_time": "5:05:01", "throughput": 9418.72, "total_tokens": 1505736848}
{"current_steps": 6258, "total_steps": 6951, "loss": 0.0999, "lr": 2.4325308700516804e-06, "epoch": 2.700641751604379, "percentage": 90.03, "elapsed_time": "1 day, 20:33:16", "remaining_time": "4:56:01", "throughput": 9419.01, "total_tokens": 1510772384}
{"current_steps": 6279, "total_steps": 6951, "loss": 0.1015, "lr": 2.288456641546549e-06, "epoch": 2.7097017742544356, "percentage": 90.33, "elapsed_time": "1 day, 20:42:09", "remaining_time": "4:47:03", "throughput": 9419.26, "total_tokens": 1515840336}
{"current_steps": 6300, "total_steps": 6951, "loss": 0.0952, "lr": 2.1486803888115802e-06, "epoch": 2.7187617969044924, "percentage": 90.63, "elapsed_time": "1 day, 20:51:02", "remaining_time": "4:38:04", "throughput": 9418.88, "total_tokens": 1520795728}
{"current_steps": 6321, "total_steps": 6951, "loss": 0.1014, "lr": 2.013214703242994e-06, "epoch": 2.7278218195545487, "percentage": 90.94, "elapsed_time": "1 day, 21:00:04", "remaining_time": "4:29:06", "throughput": 9418.79, "total_tokens": 1525885232}
{"current_steps": 6342, "total_steps": 6951, "loss": 0.0962, "lr": 1.8820717879303175e-06, "epoch": 2.7368818422046055, "percentage": 91.24, "elapsed_time": "1 day, 21:09:18", "remaining_time": "4:20:09", "throughput": 9418.29, "total_tokens": 1531020736}
{"current_steps": 6363, "total_steps": 6951, "loss": 0.0984, "lr": 1.7552634565570325e-06, "epoch": 2.7459418648546623, "percentage": 91.54, "elapsed_time": "1 day, 21:18:27", "remaining_time": "4:11:12", "throughput": 9417.96, "total_tokens": 1536139280}
{"current_steps": 6384, "total_steps": 6951, "loss": 0.0996, "lr": 1.6328011323364313e-06, "epoch": 2.7550018875047186, "percentage": 91.84, "elapsed_time": "1 day, 21:26:59", "remaining_time": "4:02:12", "throughput": 9418.9, "total_tokens": 1541119392}
{"current_steps": 6405, "total_steps": 6951, "loss": 0.098, "lr": 1.5146958469825445e-06, "epoch": 2.7640619101547754, "percentage": 92.15, "elapsed_time": "1 day, 21:35:40", "remaining_time": "3:53:12", "throughput": 9419.8, "total_tokens": 1546172016}
{"current_steps": 6426, "total_steps": 6951, "loss": 0.0979, "lr": 1.4009582397163879e-06, "epoch": 2.773121932804832, "percentage": 92.45, "elapsed_time": "1 day, 21:45:02", "remaining_time": "3:44:16", "throughput": 9419.54, "total_tokens": 1551424800}
{"current_steps": 6447, "total_steps": 6951, "loss": 0.096, "lr": 1.2915985563075383e-06, "epoch": 2.7821819554548886, "percentage": 92.75, "elapsed_time": "1 day, 21:54:06", "remaining_time": "3:35:18", "throughput": 9419.3, "total_tokens": 1556510032}
{"current_steps": 6468, "total_steps": 6951, "loss": 0.0995, "lr": 1.1866266481512234e-06, "epoch": 2.7912419781049453, "percentage": 93.05, "elapsed_time": "1 day, 22:02:47", "remaining_time": "3:26:18", "throughput": 9419.37, "total_tokens": 1561425840}
{"current_steps": 6489, "total_steps": 6951, "loss": 0.0979, "lr": 1.0860519713808082e-06, "epoch": 2.8003020007550017, "percentage": 93.35, "elapsed_time": "1 day, 22:11:35", "remaining_time": "3:17:19", "throughput": 9419.58, "total_tokens": 1566437584}
{"current_steps": 6510, "total_steps": 6951, "loss": 0.0944, "lr": 9.898835860160271e-07, "epoch": 2.8093620234050585, "percentage": 93.66, "elapsed_time": "1 day, 22:20:25", "remaining_time": "3:08:21", "throughput": 9419.64, "total_tokens": 1571433728}
{"current_steps": 6531, "total_steps": 6951, "loss": 0.0949, "lr": 8.981301551467924e-07, "epoch": 2.8184220460551153, "percentage": 93.96, "elapsed_time": "1 day, 22:29:09", "remaining_time": "2:59:22", "throughput": 9420.47, "total_tokens": 1576510304}
{"current_steps": 6552, "total_steps": 6951, "loss": 0.0959, "lr": 8.10799944152818e-07, "epoch": 2.8274820687051716, "percentage": 94.26, "elapsed_time": "1 day, 22:38:19", "remaining_time": "2:50:24", "throughput": 9420.22, "total_tokens": 1581652480}
{"current_steps": 6573, "total_steps": 6951, "loss": 0.0995, "lr": 7.279008199590543e-07, "epoch": 2.8365420913552284, "percentage": 94.56, "elapsed_time": "1 day, 22:47:15", "remaining_time": "2:41:26", "throughput": 9420.29, "total_tokens": 1586710928}
{"current_steps": 6594, "total_steps": 6951, "loss": 0.0973, "lr": 6.494402503270158e-07, "epoch": 2.845602114005285, "percentage": 94.86, "elapsed_time": "1 day, 22:55:54", "remaining_time": "2:32:27", "throughput": 9421.16, "total_tokens": 1591751872}
{"current_steps": 6615, "total_steps": 6951, "loss": 0.0992, "lr": 5.754253031820588e-07, "epoch": 2.8546621366553415, "percentage": 95.17, "elapsed_time": "1 day, 23:04:46", "remaining_time": "2:23:28", "throughput": 9421.5, "total_tokens": 1596817344}
{"current_steps": 6636, "total_steps": 6951, "loss": 0.0978, "lr": 5.058626459766902e-07, "epoch": 2.8637221593053983, "percentage": 95.47, "elapsed_time": "1 day, 23:13:55", "remaining_time": "2:14:31", "throughput": 9421.29, "total_tokens": 1601955280}
{"current_steps": 6657, "total_steps": 6951, "loss": 0.0963, "lr": 4.407585450899587e-07, "epoch": 2.872782181955455, "percentage": 95.77, "elapsed_time": "1 day, 23:22:45", "remaining_time": "2:05:32", "throughput": 9421.46, "total_tokens": 1606977888}
{"current_steps": 6678, "total_steps": 6951, "loss": 0.0932, "lr": 3.8011886526292395e-07, "epoch": 2.8818422046055114, "percentage": 96.07, "elapsed_time": "1 day, 23:32:06", "remaining_time": "1:56:35", "throughput": 9420.75, "total_tokens": 1612137088}
{"current_steps": 6699, "total_steps": 6951, "loss": 0.098, "lr": 3.2394906907040056e-07, "epoch": 2.8909022272555682, "percentage": 96.37, "elapsed_time": "1 day, 23:40:48", "remaining_time": "1:47:36", "throughput": 9421.03, "total_tokens": 1617105760}
{"current_steps": 6720, "total_steps": 6951, "loss": 0.099, "lr": 2.7225421642883554e-07, "epoch": 2.8999622499056246, "percentage": 96.68, "elapsed_time": "1 day, 23:49:15", "remaining_time": "1:38:37", "throughput": 9422.17, "total_tokens": 1622079712}
{"current_steps": 6741, "total_steps": 6951, "loss": 0.0974, "lr": 2.250389641405115e-07, "epoch": 2.9090222725556814, "percentage": 96.98, "elapsed_time": "1 day, 23:58:31", "remaining_time": "1:29:40", "throughput": 9421.85, "total_tokens": 1627262208}
{"current_steps": 6762, "total_steps": 6951, "loss": 0.0995, "lr": 1.823075654740547e-07, "epoch": 2.918082295205738, "percentage": 97.28, "elapsed_time": "2 days, 0:07:09", "remaining_time": "1:20:41", "throughput": 9422.72, "total_tokens": 1632293744}
{"current_steps": 6783, "total_steps": 6951, "loss": 0.0955, "lr": 1.4406386978128018e-07, "epoch": 2.9271423178557945, "percentage": 97.58, "elapsed_time": "2 days, 0:16:23", "remaining_time": "1:11:44", "throughput": 9422.15, "total_tokens": 1637413856}
{"current_steps": 6804, "total_steps": 6951, "loss": 0.095, "lr": 1.1031132215043594e-07, "epoch": 2.9362023405058513, "percentage": 97.89, "elapsed_time": "2 days, 0:24:58", "remaining_time": "1:02:45", "throughput": 9422.79, "total_tokens": 1642376144}
{"current_steps": 6825, "total_steps": 6951, "loss": 0.0995, "lr": 8.105296309586785e-08, "epoch": 2.9452623631559076, "percentage": 98.19, "elapsed_time": "2 days, 0:33:56", "remaining_time": "0:53:47", "throughput": 9422.9, "total_tokens": 1647471008}
{"current_steps": 6846, "total_steps": 6951, "loss": 0.0976, "lr": 5.629142828411094e-08, "epoch": 2.9543223858059644, "percentage": 98.49, "elapsed_time": "2 days, 0:42:41", "remaining_time": "0:44:49", "throughput": 9423.33, "total_tokens": 1652489696}
{"current_steps": 6867, "total_steps": 6951, "loss": 0.0955, "lr": 3.602894829647374e-08, "epoch": 2.963382408456021, "percentage": 98.79, "elapsed_time": "2 days, 0:51:22", "remaining_time": "0:35:51", "throughput": 9423.84, "total_tokens": 1657488848}
{"current_steps": 6888, "total_steps": 6951, "loss": 0.0979, "lr": 2.0267348428087974e-08, "epoch": 2.972442431106078, "percentage": 99.09, "elapsed_time": "2 days, 1:00:06", "remaining_time": "0:26:53", "throughput": 9424.1, "total_tokens": 1662468816}
{"current_steps": 6909, "total_steps": 6951, "loss": 0.0999, "lr": 9.008048523501122e-09, "epoch": 2.9815024537561343, "percentage": 99.4, "elapsed_time": "2 days, 1:08:56", "remaining_time": "0:17:55", "throughput": 9425.0, "total_tokens": 1667627776}
{"current_steps": 6930, "total_steps": 6951, "loss": 0.099, "lr": 2.252062848745462e-09, "epoch": 2.990562476406191, "percentage": 99.7, "elapsed_time": "2 days, 1:18:09", "remaining_time": "0:08:57", "throughput": 9424.34, "total_tokens": 1672724048}
{"current_steps": 6951, "total_steps": 6951, "loss": 0.0971, "lr": 0.0, "epoch": 2.9996224990562474, "percentage": 100.0, "elapsed_time": "2 days, 1:27:28", "remaining_time": "0:00:00", "throughput": 9423.59, "total_tokens": 1677860944}
{"current_steps": 6951, "total_steps": 6951, "epoch": 2.9996224990562474, "percentage": 100.0, "elapsed_time": "2 days, 1:39:42", "remaining_time": "0:00:00", "throughput": 9384.94, "total_tokens": 1677860944}