|
{"current_steps": 5, "total_steps": 3672, "loss": 0.7652, "learning_rate": 5.000000000000001e-07, "epoch": 0.0027221995372260785, "percentage": 0.14, "elapsed_time": "0:01:30", "remaining_time": "18:31:09", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 10, "total_steps": 3672, "loss": 0.7798, "learning_rate": 1.0000000000000002e-06, "epoch": 0.005444399074452157, "percentage": 0.27, "elapsed_time": "0:03:02", "remaining_time": "18:35:18", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 15, "total_steps": 3672, "loss": 0.7635, "learning_rate": 1.5e-06, "epoch": 0.008166598611678236, "percentage": 0.41, "elapsed_time": "0:04:38", "remaining_time": "18:49:57", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 20, "total_steps": 3672, "loss": 0.7475, "learning_rate": 2.0000000000000003e-06, "epoch": 0.010888798148904314, "percentage": 0.54, "elapsed_time": "0:06:23", "remaining_time": "19:28:20", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 25, "total_steps": 3672, "loss": 0.7827, "learning_rate": 2.5e-06, "epoch": 0.013610997686130393, "percentage": 0.68, "elapsed_time": "0:08:33", "remaining_time": "20:48:59", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 30, "total_steps": 3672, "loss": 0.7985, "learning_rate": 3e-06, "epoch": 0.016333197223356473, "percentage": 0.82, "elapsed_time": "0:10:32", "remaining_time": "21:18:56", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 35, "total_steps": 3672, "loss": 0.7608, "learning_rate": 3.5000000000000004e-06, "epoch": 0.01905539676058255, "percentage": 0.95, "elapsed_time": "0:12:29", "remaining_time": "21:38:18", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 40, "total_steps": 3672, "loss": 0.7566, "learning_rate": 4.000000000000001e-06, "epoch": 0.021777596297808628, "percentage": 1.09, "elapsed_time": "0:14:28", "remaining_time": "21:54:34", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 45, "total_steps": 3672, "loss": 0.75, "learning_rate": 4.5e-06, "epoch": 0.02449979583503471, "percentage": 1.23, "elapsed_time": "0:16:34", "remaining_time": "22:16:19", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 50, "total_steps": 3672, "loss": 0.7492, "learning_rate": 5e-06, "epoch": 0.027221995372260787, "percentage": 1.36, "elapsed_time": "0:18:40", "remaining_time": "22:32:34", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 55, "total_steps": 3672, "loss": 0.7208, "learning_rate": 5.500000000000001e-06, "epoch": 0.029944194909486865, "percentage": 1.5, "elapsed_time": "0:20:31", "remaining_time": "22:29:30", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 60, "total_steps": 3672, "loss": 0.6911, "learning_rate": 6e-06, "epoch": 0.032666394446712946, "percentage": 1.63, "elapsed_time": "0:22:26", "remaining_time": "22:31:21", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 65, "total_steps": 3672, "loss": 0.6624, "learning_rate": 6.5000000000000004e-06, "epoch": 0.03538859398393902, "percentage": 1.77, "elapsed_time": "0:24:24", "remaining_time": "22:34:21", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 70, "total_steps": 3672, "loss": 0.6326, "learning_rate": 7.000000000000001e-06, "epoch": 0.0381107935211651, "percentage": 1.91, "elapsed_time": "0:26:21", "remaining_time": "22:36:18", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 75, "total_steps": 3672, "loss": 0.6135, "learning_rate": 7.5e-06, "epoch": 0.04083299305839118, "percentage": 2.04, "elapsed_time": "0:28:29", "remaining_time": "22:46:21", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 80, "total_steps": 3672, "loss": 0.5585, "learning_rate": 8.000000000000001e-06, "epoch": 0.043555192595617256, "percentage": 2.18, "elapsed_time": "0:30:27", "remaining_time": "22:47:54", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 85, "total_steps": 3672, "loss": 0.5482, "learning_rate": 8.500000000000002e-06, "epoch": 0.046277392132843334, "percentage": 2.31, "elapsed_time": "0:32:31", "remaining_time": "22:52:36", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 90, "total_steps": 3672, "loss": 0.5488, "learning_rate": 9e-06, "epoch": 0.04899959167006942, "percentage": 2.45, "elapsed_time": "0:34:30", "remaining_time": "22:53:22", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 95, "total_steps": 3672, "loss": 0.4816, "learning_rate": 9.5e-06, "epoch": 0.051721791207295496, "percentage": 2.59, "elapsed_time": "0:36:11", "remaining_time": "22:42:48", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 100, "total_steps": 3672, "loss": 0.4686, "learning_rate": 1e-05, "epoch": 0.054443990744521574, "percentage": 2.72, "elapsed_time": "0:38:04", "remaining_time": "22:40:19", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 105, "total_steps": 3672, "loss": 0.4426, "learning_rate": 1.05e-05, "epoch": 0.05716619028174765, "percentage": 2.86, "elapsed_time": "0:39:48", "remaining_time": "22:32:05", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 110, "total_steps": 3672, "loss": 0.4131, "learning_rate": 1.1000000000000001e-05, "epoch": 0.05988838981897373, "percentage": 3.0, "elapsed_time": "0:41:30", "remaining_time": "22:24:05", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 115, "total_steps": 3672, "loss": 0.394, "learning_rate": 1.1500000000000002e-05, "epoch": 0.06261058935619981, "percentage": 3.13, "elapsed_time": "0:43:20", "remaining_time": "22:20:19", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 120, "total_steps": 3672, "loss": 0.3621, "learning_rate": 1.2e-05, "epoch": 0.06533278889342589, "percentage": 3.27, "elapsed_time": "0:45:00", "remaining_time": "22:12:07", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 125, "total_steps": 3672, "loss": 0.3436, "learning_rate": 1.25e-05, "epoch": 0.06805498843065197, "percentage": 3.4, "elapsed_time": "0:46:49", "remaining_time": "22:08:29", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 130, "total_steps": 3672, "loss": 0.3235, "learning_rate": 1.3000000000000001e-05, "epoch": 0.07077718796787805, "percentage": 3.54, "elapsed_time": "0:48:29", "remaining_time": "22:01:10", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 135, "total_steps": 3672, "loss": 0.3093, "learning_rate": 1.3500000000000001e-05, "epoch": 0.07349938750510412, "percentage": 3.68, "elapsed_time": "0:50:16", "remaining_time": "21:57:20", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 140, "total_steps": 3672, "loss": 0.281, "learning_rate": 1.4000000000000001e-05, "epoch": 0.0762215870423302, "percentage": 3.81, "elapsed_time": "0:51:58", "remaining_time": "21:51:14", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 145, "total_steps": 3672, "loss": 0.2645, "learning_rate": 1.45e-05, "epoch": 0.07894378657955628, "percentage": 3.95, "elapsed_time": "0:53:47", "remaining_time": "21:48:32", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 150, "total_steps": 3672, "loss": 0.2399, "learning_rate": 1.5e-05, "epoch": 0.08166598611678236, "percentage": 4.08, "elapsed_time": "0:55:30", "remaining_time": "21:43:31", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 155, "total_steps": 3672, "loss": 0.2381, "learning_rate": 1.55e-05, "epoch": 0.08438818565400844, "percentage": 4.22, "elapsed_time": "0:57:17", "remaining_time": "21:39:55", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 160, "total_steps": 3672, "loss": 0.2139, "learning_rate": 1.6000000000000003e-05, "epoch": 0.08711038519123451, "percentage": 4.36, "elapsed_time": "0:59:05", "remaining_time": "21:37:05", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 165, "total_steps": 3672, "loss": 0.1956, "learning_rate": 1.65e-05, "epoch": 0.08983258472846059, "percentage": 4.49, "elapsed_time": "1:00:54", "remaining_time": "21:34:36", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 170, "total_steps": 3672, "loss": 0.1906, "learning_rate": 1.7000000000000003e-05, "epoch": 0.09255478426568667, "percentage": 4.63, "elapsed_time": "1:02:41", "remaining_time": "21:31:27", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 175, "total_steps": 3672, "loss": 0.1811, "learning_rate": 1.75e-05, "epoch": 0.09527698380291276, "percentage": 4.77, "elapsed_time": "1:04:42", "remaining_time": "21:33:04", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 180, "total_steps": 3672, "loss": 0.1756, "learning_rate": 1.8e-05, "epoch": 0.09799918334013884, "percentage": 4.9, "elapsed_time": "1:06:31", "remaining_time": "21:30:43", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 185, "total_steps": 3672, "loss": 0.1745, "learning_rate": 1.85e-05, "epoch": 0.10072138287736492, "percentage": 5.04, "elapsed_time": "1:08:36", "remaining_time": "21:33:07", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 190, "total_steps": 3672, "loss": 0.1641, "learning_rate": 1.9e-05, "epoch": 0.10344358241459099, "percentage": 5.17, "elapsed_time": "1:10:36", "remaining_time": "21:33:53", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 195, "total_steps": 3672, "loss": 0.1478, "learning_rate": 1.9500000000000003e-05, "epoch": 0.10616578195181707, "percentage": 5.31, "elapsed_time": "1:12:32", "remaining_time": "21:33:24", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 200, "total_steps": 3672, "loss": 0.1621, "learning_rate": 2e-05, "epoch": 0.10888798148904315, "percentage": 5.45, "elapsed_time": "1:14:31", "remaining_time": "21:33:51", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 205, "total_steps": 3672, "loss": 0.1416, "learning_rate": 2.05e-05, "epoch": 0.11161018102626923, "percentage": 5.58, "elapsed_time": "1:16:27", "remaining_time": "21:33:10", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 210, "total_steps": 3672, "loss": 0.1418, "learning_rate": 2.1e-05, "epoch": 0.1143323805634953, "percentage": 5.72, "elapsed_time": "1:18:19", "remaining_time": "21:31:19", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 215, "total_steps": 3672, "loss": 0.137, "learning_rate": 2.15e-05, "epoch": 0.11705458010072138, "percentage": 5.86, "elapsed_time": "1:20:15", "remaining_time": "21:30:36", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 220, "total_steps": 3672, "loss": 0.1186, "learning_rate": 2.2000000000000003e-05, "epoch": 0.11977677963794746, "percentage": 5.99, "elapsed_time": "1:22:07", "remaining_time": "21:28:37", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 225, "total_steps": 3672, "loss": 0.1243, "learning_rate": 2.25e-05, "epoch": 0.12249897917517354, "percentage": 6.13, "elapsed_time": "1:24:07", "remaining_time": "21:28:50", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 230, "total_steps": 3672, "loss": 0.1472, "learning_rate": 2.3000000000000003e-05, "epoch": 0.12522117871239963, "percentage": 6.26, "elapsed_time": "1:26:00", "remaining_time": "21:27:02", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 235, "total_steps": 3672, "loss": 0.1258, "learning_rate": 2.35e-05, "epoch": 0.1279433782496257, "percentage": 6.4, "elapsed_time": "1:27:59", "remaining_time": "21:26:58", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 240, "total_steps": 3672, "loss": 0.1407, "learning_rate": 2.4e-05, "epoch": 0.13066557778685178, "percentage": 6.54, "elapsed_time": "1:29:52", "remaining_time": "21:25:11", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 245, "total_steps": 3672, "loss": 0.1355, "learning_rate": 2.45e-05, "epoch": 0.13338777732407786, "percentage": 6.67, "elapsed_time": "1:31:48", "remaining_time": "21:24:08", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 250, "total_steps": 3672, "loss": 0.1298, "learning_rate": 2.5e-05, "epoch": 0.13610997686130394, "percentage": 6.81, "elapsed_time": "1:33:46", "remaining_time": "21:23:29", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 255, "total_steps": 3672, "loss": 0.1256, "learning_rate": 2.5500000000000003e-05, "epoch": 0.13883217639853002, "percentage": 6.94, "elapsed_time": "1:35:38", "remaining_time": "21:21:41", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 260, "total_steps": 3672, "loss": 0.1435, "learning_rate": 2.6000000000000002e-05, "epoch": 0.1415543759357561, "percentage": 7.08, "elapsed_time": "1:37:33", "remaining_time": "21:20:10", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 265, "total_steps": 3672, "loss": 0.1353, "learning_rate": 2.6500000000000004e-05, "epoch": 0.14427657547298217, "percentage": 7.22, "elapsed_time": "1:39:22", "remaining_time": "21:17:39", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 270, "total_steps": 3672, "loss": 0.1187, "learning_rate": 2.7000000000000002e-05, "epoch": 0.14699877501020825, "percentage": 7.35, "elapsed_time": "1:41:11", "remaining_time": "21:15:06", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 275, "total_steps": 3672, "loss": 0.1697, "learning_rate": 2.7500000000000004e-05, "epoch": 0.14972097454743433, "percentage": 7.49, "elapsed_time": "1:43:07", "remaining_time": "21:13:55", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 280, "total_steps": 3672, "loss": 0.1229, "learning_rate": 2.8000000000000003e-05, "epoch": 0.1524431740846604, "percentage": 7.63, "elapsed_time": "1:44:55", "remaining_time": "21:11:05", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 285, "total_steps": 3672, "loss": 0.1086, "learning_rate": 2.8499999999999998e-05, "epoch": 0.15516537362188648, "percentage": 7.76, "elapsed_time": "1:46:40", "remaining_time": "21:07:48", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 290, "total_steps": 3672, "loss": 0.1064, "learning_rate": 2.9e-05, "epoch": 0.15788757315911256, "percentage": 7.9, "elapsed_time": "1:48:26", "remaining_time": "21:04:37", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 295, "total_steps": 3672, "loss": 0.1145, "learning_rate": 2.95e-05, "epoch": 0.16060977269633864, "percentage": 8.03, "elapsed_time": "1:50:17", "remaining_time": "21:02:29", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 300, "total_steps": 3672, "loss": 0.1181, "learning_rate": 3e-05, "epoch": 0.16333197223356472, "percentage": 8.17, "elapsed_time": "1:51:59", "remaining_time": "20:58:45", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 305, "total_steps": 3672, "loss": 0.1093, "learning_rate": 3.05e-05, "epoch": 0.1660541717707908, "percentage": 8.31, "elapsed_time": "1:53:47", "remaining_time": "20:56:13", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 310, "total_steps": 3672, "loss": 0.1119, "learning_rate": 3.1e-05, "epoch": 0.16877637130801687, "percentage": 8.44, "elapsed_time": "1:55:31", "remaining_time": "20:52:48", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 315, "total_steps": 3672, "loss": 0.1079, "learning_rate": 3.15e-05, "epoch": 0.17149857084524295, "percentage": 8.58, "elapsed_time": "1:57:25", "remaining_time": "20:51:25", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 320, "total_steps": 3672, "loss": 0.1035, "learning_rate": 3.2000000000000005e-05, "epoch": 0.17422077038246903, "percentage": 8.71, "elapsed_time": "1:59:12", "remaining_time": "20:48:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 325, "total_steps": 3672, "loss": 0.1208, "learning_rate": 3.2500000000000004e-05, "epoch": 0.1769429699196951, "percentage": 8.85, "elapsed_time": "2:01:08", "remaining_time": "20:47:30", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 330, "total_steps": 3672, "loss": 0.113, "learning_rate": 3.3e-05, "epoch": 0.17966516945692118, "percentage": 8.99, "elapsed_time": "2:02:54", "remaining_time": "20:44:42", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 335, "total_steps": 3672, "loss": 0.1082, "learning_rate": 3.35e-05, "epoch": 0.18238736899414726, "percentage": 9.12, "elapsed_time": "2:04:51", "remaining_time": "20:43:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 340, "total_steps": 3672, "loss": 0.103, "learning_rate": 3.4000000000000007e-05, "epoch": 0.18510956853137334, "percentage": 9.26, "elapsed_time": "2:06:43", "remaining_time": "20:41:50", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 345, "total_steps": 3672, "loss": 0.1084, "learning_rate": 3.45e-05, "epoch": 0.18783176806859944, "percentage": 9.4, "elapsed_time": "2:08:45", "remaining_time": "20:41:38", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 350, "total_steps": 3672, "loss": 0.1021, "learning_rate": 3.5e-05, "epoch": 0.19055396760582552, "percentage": 9.53, "elapsed_time": "2:10:45", "remaining_time": "20:41:05", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 355, "total_steps": 3672, "loss": 0.1088, "learning_rate": 3.55e-05, "epoch": 0.1932761671430516, "percentage": 9.67, "elapsed_time": "2:12:43", "remaining_time": "20:40:07", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 360, "total_steps": 3672, "loss": 0.1104, "learning_rate": 3.6e-05, "epoch": 0.19599836668027767, "percentage": 9.8, "elapsed_time": "2:14:45", "remaining_time": "20:39:42", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 365, "total_steps": 3672, "loss": 0.1073, "learning_rate": 3.65e-05, "epoch": 0.19872056621750375, "percentage": 9.94, "elapsed_time": "2:16:51", "remaining_time": "20:39:54", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 370, "total_steps": 3672, "loss": 0.1365, "learning_rate": 3.7e-05, "epoch": 0.20144276575472983, "percentage": 10.08, "elapsed_time": "2:18:51", "remaining_time": "20:39:09", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 375, "total_steps": 3672, "loss": 0.0984, "learning_rate": 3.7500000000000003e-05, "epoch": 0.2041649652919559, "percentage": 10.21, "elapsed_time": "2:21:01", "remaining_time": "20:39:52", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 380, "total_steps": 3672, "loss": 0.1289, "learning_rate": 3.8e-05, "epoch": 0.20688716482918199, "percentage": 10.35, "elapsed_time": "2:23:05", "remaining_time": "20:39:34", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 385, "total_steps": 3672, "loss": 0.1055, "learning_rate": 3.85e-05, "epoch": 0.20960936436640806, "percentage": 10.48, "elapsed_time": "2:25:11", "remaining_time": "20:39:35", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 390, "total_steps": 3672, "loss": 0.1203, "learning_rate": 3.9000000000000006e-05, "epoch": 0.21233156390363414, "percentage": 10.62, "elapsed_time": "2:27:11", "remaining_time": "20:38:38", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 395, "total_steps": 3672, "loss": 0.0965, "learning_rate": 3.9500000000000005e-05, "epoch": 0.21505376344086022, "percentage": 10.76, "elapsed_time": "2:29:15", "remaining_time": "20:38:16", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 400, "total_steps": 3672, "loss": 0.0961, "learning_rate": 4e-05, "epoch": 0.2177759629780863, "percentage": 10.89, "elapsed_time": "2:31:20", "remaining_time": "20:37:54", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 405, "total_steps": 3672, "loss": 0.0945, "learning_rate": 4.05e-05, "epoch": 0.22049816251531237, "percentage": 11.03, "elapsed_time": "2:33:24", "remaining_time": "20:37:29", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 410, "total_steps": 3672, "loss": 0.0991, "learning_rate": 4.1e-05, "epoch": 0.22322036205253845, "percentage": 11.17, "elapsed_time": "2:35:20", "remaining_time": "20:35:52", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 415, "total_steps": 3672, "loss": 0.1069, "learning_rate": 4.15e-05, "epoch": 0.22594256158976453, "percentage": 11.3, "elapsed_time": "2:37:11", "remaining_time": "20:33:37", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 420, "total_steps": 3672, "loss": 0.1037, "learning_rate": 4.2e-05, "epoch": 0.2286647611269906, "percentage": 11.44, "elapsed_time": "2:39:01", "remaining_time": "20:31:18", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 425, "total_steps": 3672, "loss": 0.0952, "learning_rate": 4.25e-05, "epoch": 0.23138696066421668, "percentage": 11.57, "elapsed_time": "2:40:46", "remaining_time": "20:28:17", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 430, "total_steps": 3672, "loss": 0.0962, "learning_rate": 4.3e-05, "epoch": 0.23410916020144276, "percentage": 11.71, "elapsed_time": "2:42:27", "remaining_time": "20:24:48", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 435, "total_steps": 3672, "loss": 0.1075, "learning_rate": 4.35e-05, "epoch": 0.23683135973866884, "percentage": 11.85, "elapsed_time": "2:44:15", "remaining_time": "20:22:22", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 440, "total_steps": 3672, "loss": 0.104, "learning_rate": 4.4000000000000006e-05, "epoch": 0.23955355927589492, "percentage": 11.98, "elapsed_time": "2:46:00", "remaining_time": "20:19:21", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 445, "total_steps": 3672, "loss": 0.1012, "learning_rate": 4.4500000000000004e-05, "epoch": 0.242275758813121, "percentage": 12.12, "elapsed_time": "2:47:47", "remaining_time": "20:16:45", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 450, "total_steps": 3672, "loss": 0.1115, "learning_rate": 4.5e-05, "epoch": 0.24499795835034707, "percentage": 12.25, "elapsed_time": "2:49:32", "remaining_time": "20:13:55", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 455, "total_steps": 3672, "loss": 0.1006, "learning_rate": 4.55e-05, "epoch": 0.24772015788757315, "percentage": 12.39, "elapsed_time": "2:51:20", "remaining_time": "20:11:23", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 460, "total_steps": 3672, "loss": 0.0902, "learning_rate": 4.600000000000001e-05, "epoch": 0.25044235742479926, "percentage": 12.53, "elapsed_time": "2:53:02", "remaining_time": "20:08:18", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 465, "total_steps": 3672, "loss": 0.0937, "learning_rate": 4.6500000000000005e-05, "epoch": 0.25316455696202533, "percentage": 12.66, "elapsed_time": "2:54:46", "remaining_time": "20:05:24", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 470, "total_steps": 3672, "loss": 0.0944, "learning_rate": 4.7e-05, "epoch": 0.2558867564992514, "percentage": 12.8, "elapsed_time": "2:56:37", "remaining_time": "20:03:17", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 475, "total_steps": 3672, "loss": 0.104, "learning_rate": 4.75e-05, "epoch": 0.2586089560364775, "percentage": 12.94, "elapsed_time": "2:58:22", "remaining_time": "20:00:35", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 480, "total_steps": 3672, "loss": 0.0889, "learning_rate": 4.8e-05, "epoch": 0.26133115557370357, "percentage": 13.07, "elapsed_time": "3:00:12", "remaining_time": "19:58:20", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 485, "total_steps": 3672, "loss": 0.0964, "learning_rate": 4.85e-05, "epoch": 0.26405335511092964, "percentage": 13.21, "elapsed_time": "3:02:04", "remaining_time": "19:56:24", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 490, "total_steps": 3672, "loss": 0.1038, "learning_rate": 4.9e-05, "epoch": 0.2667755546481557, "percentage": 13.34, "elapsed_time": "3:03:58", "remaining_time": "19:54:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 495, "total_steps": 3672, "loss": 0.0941, "learning_rate": 4.9500000000000004e-05, "epoch": 0.2694977541853818, "percentage": 13.48, "elapsed_time": "3:05:56", "remaining_time": "19:53:21", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 500, "total_steps": 3672, "loss": 0.1013, "learning_rate": 5e-05, "epoch": 0.2722199537226079, "percentage": 13.62, "elapsed_time": "3:07:48", "remaining_time": "19:51:30", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 500, "total_steps": 3672, "eval_loss": 0.09772992134094238, "epoch": 0.2722199537226079, "percentage": 13.62, "elapsed_time": "3:12:19", "remaining_time": "20:20:09", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 505, "total_steps": 3672, "loss": 0.098, "learning_rate": 4.999969346326857e-05, "epoch": 0.27494215325983395, "percentage": 13.75, "elapsed_time": "3:14:21", "remaining_time": "20:18:53", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 510, "total_steps": 3672, "loss": 0.0912, "learning_rate": 4.9998773860591444e-05, "epoch": 0.27766435279706003, "percentage": 13.89, "elapsed_time": "3:16:32", "remaining_time": "20:18:34", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 515, "total_steps": 3672, "loss": 0.0885, "learning_rate": 4.9997241214519986e-05, "epoch": 0.2803865523342861, "percentage": 14.03, "elapsed_time": "3:18:35", "remaining_time": "20:17:20", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 520, "total_steps": 3672, "loss": 0.1013, "learning_rate": 4.999509556263919e-05, "epoch": 0.2831087518715122, "percentage": 14.16, "elapsed_time": "3:20:46", "remaining_time": "20:17:03", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 525, "total_steps": 3672, "loss": 0.1005, "learning_rate": 4.999233695756673e-05, "epoch": 0.28583095140873827, "percentage": 14.3, "elapsed_time": "3:22:51", "remaining_time": "20:15:58", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 530, "total_steps": 3672, "loss": 0.0958, "learning_rate": 4.998896546695172e-05, "epoch": 0.28855315094596434, "percentage": 14.43, "elapsed_time": "3:24:47", "remaining_time": "20:14:01", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 535, "total_steps": 3672, "loss": 0.0971, "learning_rate": 4.998498117347302e-05, "epoch": 0.2912753504831904, "percentage": 14.57, "elapsed_time": "3:26:51", "remaining_time": "20:12:52", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 540, "total_steps": 3672, "loss": 0.1057, "learning_rate": 4.998038417483721e-05, "epoch": 0.2939975500204165, "percentage": 14.71, "elapsed_time": "3:28:49", "remaining_time": "20:11:09", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 545, "total_steps": 3672, "loss": 0.0943, "learning_rate": 4.9975174583776196e-05, "epoch": 0.2967197495576426, "percentage": 14.84, "elapsed_time": "3:30:43", "remaining_time": "20:09:05", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 550, "total_steps": 3672, "loss": 0.0968, "learning_rate": 4.996935252804448e-05, "epoch": 0.29944194909486865, "percentage": 14.98, "elapsed_time": "3:32:40", "remaining_time": "20:07:13", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 555, "total_steps": 3672, "loss": 0.0975, "learning_rate": 4.9962918150415946e-05, "epoch": 0.30216414863209473, "percentage": 15.11, "elapsed_time": "3:34:35", "remaining_time": "20:05:10", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 560, "total_steps": 3672, "loss": 0.0925, "learning_rate": 4.995587160868047e-05, "epoch": 0.3048863481693208, "percentage": 15.25, "elapsed_time": "3:36:34", "remaining_time": "20:03:32", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 565, "total_steps": 3672, "loss": 0.097, "learning_rate": 4.994821307563995e-05, "epoch": 0.3076085477065469, "percentage": 15.39, "elapsed_time": "3:38:32", "remaining_time": "20:01:48", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 570, "total_steps": 3672, "loss": 0.0996, "learning_rate": 4.9939942739104105e-05, "epoch": 0.31033074724377296, "percentage": 15.52, "elapsed_time": "3:40:24", "remaining_time": "19:59:31", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 575, "total_steps": 3672, "loss": 0.0888, "learning_rate": 4.993106080188592e-05, "epoch": 0.31305294678099904, "percentage": 15.66, "elapsed_time": "3:42:20", "remaining_time": "19:57:34", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 580, "total_steps": 3672, "loss": 0.0994, "learning_rate": 4.9921567481796585e-05, "epoch": 0.3157751463182251, "percentage": 15.8, "elapsed_time": "3:44:07", "remaining_time": "19:54:48", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 585, "total_steps": 3672, "loss": 0.0976, "learning_rate": 4.9911463011640195e-05, "epoch": 0.3184973458554512, "percentage": 15.93, "elapsed_time": "3:46:02", "remaining_time": "19:52:48", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 590, "total_steps": 3672, "loss": 0.0947, "learning_rate": 4.9900747639208044e-05, "epoch": 0.3212195453926773, "percentage": 16.07, "elapsed_time": "3:47:57", "remaining_time": "19:50:48", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 595, "total_steps": 3672, "loss": 0.1039, "learning_rate": 4.9889421627272575e-05, "epoch": 0.32394174492990335, "percentage": 16.2, "elapsed_time": "3:49:45", "remaining_time": "19:48:10", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 600, "total_steps": 3672, "loss": 0.1005, "learning_rate": 4.987748525358087e-05, "epoch": 0.32666394446712943, "percentage": 16.34, "elapsed_time": "3:51:23", "remaining_time": "19:44:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 605, "total_steps": 3672, "loss": 0.0941, "learning_rate": 4.9864938810847884e-05, "epoch": 0.3293861440043555, "percentage": 16.48, "elapsed_time": "3:53:18", "remaining_time": "19:42:43", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 610, "total_steps": 3672, "loss": 0.1055, "learning_rate": 4.985178260674927e-05, "epoch": 0.3321083435415816, "percentage": 16.61, "elapsed_time": "3:55:07", "remaining_time": "19:40:17", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 615, "total_steps": 3672, "loss": 0.0941, "learning_rate": 4.98380169639138e-05, "epoch": 0.33483054307880766, "percentage": 16.75, "elapsed_time": "3:56:54", "remaining_time": "19:37:34", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 620, "total_steps": 3672, "loss": 0.0991, "learning_rate": 4.98236422199155e-05, "epoch": 0.33755274261603374, "percentage": 16.88, "elapsed_time": "3:58:48", "remaining_time": "19:35:33", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 625, "total_steps": 3672, "loss": 0.0979, "learning_rate": 4.980865872726532e-05, "epoch": 0.3402749421532598, "percentage": 17.02, "elapsed_time": "4:00:32", "remaining_time": "19:32:43", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 630, "total_steps": 3672, "loss": 0.0957, "learning_rate": 4.9793066853402536e-05, "epoch": 0.3429971416904859, "percentage": 17.16, "elapsed_time": "4:02:18", "remaining_time": "19:29:59", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 635, "total_steps": 3672, "loss": 0.0889, "learning_rate": 4.977686698068572e-05, "epoch": 0.345719341227712, "percentage": 17.29, "elapsed_time": "4:04:15", "remaining_time": "19:28:10", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 640, "total_steps": 3672, "loss": 0.0928, "learning_rate": 4.976005950638334e-05, "epoch": 0.34844154076493805, "percentage": 17.43, "elapsed_time": "4:05:56", "remaining_time": "19:25:10", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 645, "total_steps": 3672, "loss": 0.0927, "learning_rate": 4.974264484266406e-05, "epoch": 0.35116374030216413, "percentage": 17.57, "elapsed_time": "4:07:51", "remaining_time": "19:23:10", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 650, "total_steps": 3672, "loss": 0.0944, "learning_rate": 4.972462341658661e-05, "epoch": 0.3538859398393902, "percentage": 17.7, "elapsed_time": "4:09:37", "remaining_time": "19:20:35", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 655, "total_steps": 3672, "loss": 0.0998, "learning_rate": 4.970599567008931e-05, "epoch": 0.3566081393766163, "percentage": 17.84, "elapsed_time": "4:11:31", "remaining_time": "19:18:34", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 660, "total_steps": 3672, "loss": 0.0981, "learning_rate": 4.968676205997925e-05, "epoch": 0.35933033891384236, "percentage": 17.97, "elapsed_time": "4:13:24", "remaining_time": "19:16:30", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 665, "total_steps": 3672, "loss": 0.0932, "learning_rate": 4.966692305792106e-05, "epoch": 0.36205253845106844, "percentage": 18.11, "elapsed_time": "4:15:15", "remaining_time": "19:14:11", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 670, "total_steps": 3672, "loss": 0.0866, "learning_rate": 4.9646479150425376e-05, "epoch": 0.3647747379882945, "percentage": 18.25, "elapsed_time": "4:17:09", "remaining_time": "19:12:15", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 675, "total_steps": 3672, "loss": 0.0837, "learning_rate": 4.962543083883687e-05, "epoch": 0.3674969375255206, "percentage": 18.38, "elapsed_time": "4:19:08", "remaining_time": "19:10:33", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 680, "total_steps": 3672, "loss": 0.0906, "learning_rate": 4.9603778639322004e-05, "epoch": 0.3702191370627467, "percentage": 18.52, "elapsed_time": "4:20:58", "remaining_time": "19:08:17", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 685, "total_steps": 3672, "loss": 0.0949, "learning_rate": 4.958152308285633e-05, "epoch": 0.37294133659997275, "percentage": 18.65, "elapsed_time": "4:22:59", "remaining_time": "19:06:46", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 690, "total_steps": 3672, "loss": 0.0931, "learning_rate": 4.95586647152115e-05, "epoch": 0.3756635361371989, "percentage": 18.79, "elapsed_time": "4:24:56", "remaining_time": "19:05:00", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 695, "total_steps": 3672, "loss": 0.087, "learning_rate": 4.9535204096941854e-05, "epoch": 0.37838573567442496, "percentage": 18.93, "elapsed_time": "4:26:46", "remaining_time": "19:02:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 700, "total_steps": 3672, "loss": 0.0965, "learning_rate": 4.951114180337069e-05, "epoch": 0.38110793521165104, "percentage": 19.06, "elapsed_time": "4:28:28", "remaining_time": "18:59:53", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 705, "total_steps": 3672, "loss": 0.0862, "learning_rate": 4.948647842457615e-05, "epoch": 0.3838301347488771, "percentage": 19.2, "elapsed_time": "4:30:25", "remaining_time": "18:58:03", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 710, "total_steps": 3672, "loss": 0.0911, "learning_rate": 4.946121456537676e-05, "epoch": 0.3865523342861032, "percentage": 19.34, "elapsed_time": "4:32:14", "remaining_time": "18:55:46", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 715, "total_steps": 3672, "loss": 0.0851, "learning_rate": 4.9435350845316575e-05, "epoch": 0.38927453382332927, "percentage": 19.47, "elapsed_time": "4:34:08", "remaining_time": "18:53:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 720, "total_steps": 3672, "loss": 0.0836, "learning_rate": 4.9408887898650036e-05, "epoch": 0.39199673336055535, "percentage": 19.61, "elapsed_time": "4:36:08", "remaining_time": "18:52:08", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 725, "total_steps": 3672, "loss": 0.1033, "learning_rate": 4.9381826374326336e-05, "epoch": 0.3947189328977814, "percentage": 19.74, "elapsed_time": "4:38:04", "remaining_time": "18:50:21", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 730, "total_steps": 3672, "loss": 0.0862, "learning_rate": 4.935416693597358e-05, "epoch": 0.3974411324350075, "percentage": 19.88, "elapsed_time": "4:39:50", "remaining_time": "18:47:46", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 735, "total_steps": 3672, "loss": 0.0946, "learning_rate": 4.932591026188247e-05, "epoch": 0.4001633319722336, "percentage": 20.02, "elapsed_time": "4:41:50", "remaining_time": "18:46:11", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 740, "total_steps": 3672, "loss": 0.0913, "learning_rate": 4.929705704498969e-05, "epoch": 0.40288553150945966, "percentage": 20.15, "elapsed_time": "4:43:33", "remaining_time": "18:43:29", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 745, "total_steps": 3672, "loss": 0.0888, "learning_rate": 4.9267607992860906e-05, "epoch": 0.40560773104668574, "percentage": 20.29, "elapsed_time": "4:45:33", "remaining_time": "18:41:54", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 750, "total_steps": 3672, "loss": 0.0845, "learning_rate": 4.9237563827673416e-05, "epoch": 0.4083299305839118, "percentage": 20.42, "elapsed_time": "4:47:29", "remaining_time": "18:40:03", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 755, "total_steps": 3672, "loss": 0.09, "learning_rate": 4.9206925286198426e-05, "epoch": 0.4110521301211379, "percentage": 20.56, "elapsed_time": "4:49:27", "remaining_time": "18:38:21", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 760, "total_steps": 3672, "loss": 0.0855, "learning_rate": 4.9175693119783013e-05, "epoch": 0.41377432965836397, "percentage": 20.7, "elapsed_time": "4:51:19", "remaining_time": "18:36:14", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 765, "total_steps": 3672, "loss": 0.0946, "learning_rate": 4.914386809433167e-05, "epoch": 0.41649652919559005, "percentage": 20.83, "elapsed_time": "4:53:15", "remaining_time": "18:34:22", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 770, "total_steps": 3672, "loss": 0.0861, "learning_rate": 4.911145099028753e-05, "epoch": 0.4192187287328161, "percentage": 20.97, "elapsed_time": "4:55:12", "remaining_time": "18:32:36", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 775, "total_steps": 3672, "loss": 0.088, "learning_rate": 4.9078442602613265e-05, "epoch": 0.4219409282700422, "percentage": 21.11, "elapsed_time": "4:57:02", "remaining_time": "18:30:20", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 780, "total_steps": 3672, "loss": 0.0882, "learning_rate": 4.9044843740771505e-05, "epoch": 0.4246631278072683, "percentage": 21.24, "elapsed_time": "4:59:02", "remaining_time": "18:28:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 785, "total_steps": 3672, "loss": 0.0978, "learning_rate": 4.901065522870511e-05, "epoch": 0.42738532734449436, "percentage": 21.38, "elapsed_time": "5:00:54", "remaining_time": "18:26:38", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 790, "total_steps": 3672, "loss": 0.0833, "learning_rate": 4.897587790481683e-05, "epoch": 0.43010752688172044, "percentage": 21.51, "elapsed_time": "5:02:51", "remaining_time": "18:24:52", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 795, "total_steps": 3672, "loss": 0.0944, "learning_rate": 4.894051262194885e-05, "epoch": 0.4328297264189465, "percentage": 21.65, "elapsed_time": "5:04:49", "remaining_time": "18:23:08", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 800, "total_steps": 3672, "loss": 0.1036, "learning_rate": 4.8904560247361833e-05, "epoch": 0.4355519259561726, "percentage": 21.79, "elapsed_time": "5:06:31", "remaining_time": "18:20:26", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 805, "total_steps": 3672, "loss": 0.1042, "learning_rate": 4.886802166271364e-05, "epoch": 0.43827412549339867, "percentage": 21.92, "elapsed_time": "5:08:29", "remaining_time": "18:18:41", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 810, "total_steps": 3672, "loss": 0.0771, "learning_rate": 4.8830897764037744e-05, "epoch": 0.44099632503062475, "percentage": 22.06, "elapsed_time": "5:10:27", "remaining_time": "18:16:56", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 815, "total_steps": 3672, "loss": 0.0992, "learning_rate": 4.879318946172123e-05, "epoch": 0.4437185245678508, "percentage": 22.19, "elapsed_time": "5:12:25", "remaining_time": "18:15:14", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 820, "total_steps": 3672, "loss": 0.0959, "learning_rate": 4.875489768048247e-05, "epoch": 0.4464407241050769, "percentage": 22.33, "elapsed_time": "5:14:15", "remaining_time": "18:13:01", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 825, "total_steps": 3672, "loss": 0.0817, "learning_rate": 4.871602335934847e-05, "epoch": 0.449162923642303, "percentage": 22.47, "elapsed_time": "5:16:11", "remaining_time": "18:11:09", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 830, "total_steps": 3672, "loss": 0.0763, "learning_rate": 4.867656745163182e-05, "epoch": 0.45188512317952906, "percentage": 22.6, "elapsed_time": "5:18:01", "remaining_time": "18:08:57", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 835, "total_steps": 3672, "loss": 0.1026, "learning_rate": 4.8636530924907296e-05, "epoch": 0.45460732271675514, "percentage": 22.74, "elapsed_time": "5:19:57", "remaining_time": "18:07:06", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 840, "total_steps": 3672, "loss": 0.0986, "learning_rate": 4.85959147609882e-05, "epoch": 0.4573295222539812, "percentage": 22.88, "elapsed_time": "5:21:48", "remaining_time": "18:04:55", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 845, "total_steps": 3672, "loss": 0.1099, "learning_rate": 4.855471995590222e-05, "epoch": 0.4600517217912073, "percentage": 23.01, "elapsed_time": "5:23:31", "remaining_time": "18:02:21", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 850, "total_steps": 3672, "loss": 0.0839, "learning_rate": 4.851294751986702e-05, "epoch": 0.46277392132843337, "percentage": 23.15, "elapsed_time": "5:25:21", "remaining_time": "18:00:12", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 855, "total_steps": 3672, "loss": 0.097, "learning_rate": 4.84705984772655e-05, "epoch": 0.46549612086565945, "percentage": 23.28, "elapsed_time": "5:27:17", "remaining_time": "17:58:19", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 860, "total_steps": 3672, "loss": 0.0837, "learning_rate": 4.8427673866620615e-05, "epoch": 0.4682183204028855, "percentage": 23.42, "elapsed_time": "5:29:08", "remaining_time": "17:56:12", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 865, "total_steps": 3672, "loss": 0.0871, "learning_rate": 4.8384174740569944e-05, "epoch": 0.4709405199401116, "percentage": 23.56, "elapsed_time": "5:30:49", "remaining_time": "17:53:32", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 870, "total_steps": 3672, "loss": 0.0905, "learning_rate": 4.83401021658399e-05, "epoch": 0.4736627194773377, "percentage": 23.69, "elapsed_time": "5:32:45", "remaining_time": "17:51:43", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 875, "total_steps": 3672, "loss": 0.1187, "learning_rate": 4.82954572232195e-05, "epoch": 0.47638491901456376, "percentage": 23.83, "elapsed_time": "5:34:33", "remaining_time": "17:49:25", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 880, "total_steps": 3672, "loss": 0.0892, "learning_rate": 4.825024100753395e-05, "epoch": 0.47910711855178983, "percentage": 23.97, "elapsed_time": "5:36:21", "remaining_time": "17:47:11", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 885, "total_steps": 3672, "loss": 0.0865, "learning_rate": 4.820445462761771e-05, "epoch": 0.4818293180890159, "percentage": 24.1, "elapsed_time": "5:38:17", "remaining_time": "17:45:21", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 890, "total_steps": 3672, "loss": 0.0899, "learning_rate": 4.815809920628738e-05, "epoch": 0.484551517626242, "percentage": 24.24, "elapsed_time": "5:39:57", "remaining_time": "17:42:40", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 895, "total_steps": 3672, "loss": 0.0767, "learning_rate": 4.8111175880314084e-05, "epoch": 0.48727371716346807, "percentage": 24.37, "elapsed_time": "5:41:53", "remaining_time": "17:40:49", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 900, "total_steps": 3672, "loss": 0.0832, "learning_rate": 4.806368580039566e-05, "epoch": 0.48999591670069415, "percentage": 24.51, "elapsed_time": "5:43:44", "remaining_time": "17:38:43", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 905, "total_steps": 3672, "loss": 0.0873, "learning_rate": 4.801563013112844e-05, "epoch": 0.4927181162379202, "percentage": 24.65, "elapsed_time": "5:45:34", "remaining_time": "17:36:33", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 910, "total_steps": 3672, "loss": 0.1083, "learning_rate": 4.7967010050978635e-05, "epoch": 0.4954403157751463, "percentage": 24.78, "elapsed_time": "5:47:21", "remaining_time": "17:34:18", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 915, "total_steps": 3672, "loss": 0.0853, "learning_rate": 4.791782675225348e-05, "epoch": 0.4981625153123724, "percentage": 24.92, "elapsed_time": "5:49:10", "remaining_time": "17:32:06", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 920, "total_steps": 3672, "loss": 0.0882, "learning_rate": 4.7868081441071975e-05, "epoch": 0.5008847148495985, "percentage": 25.05, "elapsed_time": "5:50:58", "remaining_time": "17:29:51", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 925, "total_steps": 3672, "loss": 0.0859, "learning_rate": 4.781777533733534e-05, "epoch": 0.5036069143868246, "percentage": 25.19, "elapsed_time": "5:52:49", "remaining_time": "17:27:48", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 930, "total_steps": 3672, "loss": 0.0788, "learning_rate": 4.776690967469708e-05, "epoch": 0.5063291139240507, "percentage": 25.33, "elapsed_time": "5:54:37", "remaining_time": "17:25:34", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 935, "total_steps": 3672, "loss": 0.075, "learning_rate": 4.771548570053268e-05, "epoch": 0.5090513134612767, "percentage": 25.46, "elapsed_time": "5:56:31", "remaining_time": "17:23:37", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 940, "total_steps": 3672, "loss": 0.0991, "learning_rate": 4.766350467590911e-05, "epoch": 0.5117735129985028, "percentage": 25.6, "elapsed_time": "5:58:21", "remaining_time": "17:21:32", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 945, "total_steps": 3672, "loss": 0.082, "learning_rate": 4.7610967875553846e-05, "epoch": 0.5144957125357289, "percentage": 25.74, "elapsed_time": "6:00:12", "remaining_time": "17:19:27", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 950, "total_steps": 3672, "loss": 0.0848, "learning_rate": 4.755787658782361e-05, "epoch": 0.517217912072955, "percentage": 25.87, "elapsed_time": "6:02:00", "remaining_time": "17:17:15", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 955, "total_steps": 3672, "loss": 0.083, "learning_rate": 4.750423211467278e-05, "epoch": 0.519940111610181, "percentage": 26.01, "elapsed_time": "6:03:51", "remaining_time": "17:15:12", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 960, "total_steps": 3672, "loss": 0.0856, "learning_rate": 4.745003577162148e-05, "epoch": 0.5226623111474071, "percentage": 26.14, "elapsed_time": "6:05:42", "remaining_time": "17:13:06", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 965, "total_steps": 3672, "loss": 0.0953, "learning_rate": 4.7395288887723296e-05, "epoch": 0.5253845106846332, "percentage": 26.28, "elapsed_time": "6:07:28", "remaining_time": "17:10:51", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 970, "total_steps": 3672, "loss": 0.0887, "learning_rate": 4.73399928055327e-05, "epoch": 0.5281067102218593, "percentage": 26.42, "elapsed_time": "6:09:22", "remaining_time": "17:08:55", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 975, "total_steps": 3672, "loss": 0.0908, "learning_rate": 4.728414888107211e-05, "epoch": 0.5308289097590854, "percentage": 26.55, "elapsed_time": "6:11:21", "remaining_time": "17:07:13", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 980, "total_steps": 3672, "loss": 0.0898, "learning_rate": 4.722775848379866e-05, "epoch": 0.5335511092963114, "percentage": 26.69, "elapsed_time": "6:13:13", "remaining_time": "17:05:13", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 985, "total_steps": 3672, "loss": 0.0985, "learning_rate": 4.717082299657058e-05, "epoch": 0.5362733088335375, "percentage": 26.82, "elapsed_time": "6:15:13", "remaining_time": "17:03:35", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 990, "total_steps": 3672, "loss": 0.0894, "learning_rate": 4.711334381561333e-05, "epoch": 0.5389955083707636, "percentage": 26.96, "elapsed_time": "6:17:12", "remaining_time": "17:01:52", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 995, "total_steps": 3672, "loss": 0.0823, "learning_rate": 4.7055322350485344e-05, "epoch": 0.5417177079079897, "percentage": 27.1, "elapsed_time": "6:19:06", "remaining_time": "16:59:58", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1000, "total_steps": 3672, "loss": 0.0851, "learning_rate": 4.699676002404342e-05, "epoch": 0.5444399074452158, "percentage": 27.23, "elapsed_time": "6:21:04", "remaining_time": "16:58:13", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1000, "total_steps": 3672, "eval_loss": 0.08648888021707535, "epoch": 0.5444399074452158, "percentage": 27.23, "elapsed_time": "6:25:19", "remaining_time": "17:09:34", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1005, "total_steps": 3672, "loss": 0.0827, "learning_rate": 4.6937658272407905e-05, "epoch": 0.5471621069824418, "percentage": 27.37, "elapsed_time": "6:27:13", "remaining_time": "17:07:35", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1010, "total_steps": 3672, "loss": 0.0986, "learning_rate": 4.6878018544927415e-05, "epoch": 0.5498843065196679, "percentage": 27.51, "elapsed_time": "6:29:03", "remaining_time": "17:05:25", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1015, "total_steps": 3672, "loss": 0.0883, "learning_rate": 4.681784230414332e-05, "epoch": 0.552606506056894, "percentage": 27.64, "elapsed_time": "6:30:51", "remaining_time": "17:03:10", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1020, "total_steps": 3672, "loss": 0.0881, "learning_rate": 4.6757131025753886e-05, "epoch": 0.5553287055941201, "percentage": 27.78, "elapsed_time": "6:32:51", "remaining_time": "17:01:25", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1025, "total_steps": 3672, "loss": 0.0825, "learning_rate": 4.6695886198578034e-05, "epoch": 0.5580509051313461, "percentage": 27.91, "elapsed_time": "6:34:48", "remaining_time": "16:59:35", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1030, "total_steps": 3672, "loss": 0.0978, "learning_rate": 4.6634109324518914e-05, "epoch": 0.5607731046685722, "percentage": 28.05, "elapsed_time": "6:36:51", "remaining_time": "16:57:58", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1035, "total_steps": 3672, "loss": 0.1565, "learning_rate": 4.657180191852701e-05, "epoch": 0.5634953042057983, "percentage": 28.19, "elapsed_time": "6:38:37", "remaining_time": "16:55:37", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1040, "total_steps": 3672, "loss": 0.0927, "learning_rate": 4.6508965508562995e-05, "epoch": 0.5662175037430244, "percentage": 28.32, "elapsed_time": "6:40:37", "remaining_time": "16:53:52", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1045, "total_steps": 3672, "loss": 0.0839, "learning_rate": 4.644560163556031e-05, "epoch": 0.5689397032802505, "percentage": 28.46, "elapsed_time": "6:42:32", "remaining_time": "16:51:55", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1050, "total_steps": 3672, "loss": 0.0812, "learning_rate": 4.638171185338729e-05, "epoch": 0.5716619028174765, "percentage": 28.59, "elapsed_time": "6:44:20", "remaining_time": "16:49:40", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1055, "total_steps": 3672, "loss": 0.0889, "learning_rate": 4.6317297728809147e-05, "epoch": 0.5743841023547026, "percentage": 28.73, "elapsed_time": "6:46:10", "remaining_time": "16:47:32", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1060, "total_steps": 3672, "loss": 0.0858, "learning_rate": 4.62523608414495e-05, "epoch": 0.5771063018919287, "percentage": 28.87, "elapsed_time": "6:47:58", "remaining_time": "16:45:17", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1065, "total_steps": 3672, "loss": 0.0856, "learning_rate": 4.618690278375164e-05, "epoch": 0.5798285014291548, "percentage": 29.0, "elapsed_time": "6:49:50", "remaining_time": "16:43:15", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1070, "total_steps": 3672, "loss": 0.082, "learning_rate": 4.61209251609395e-05, "epoch": 0.5825507009663808, "percentage": 29.14, "elapsed_time": "6:51:40", "remaining_time": "16:41:06", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1075, "total_steps": 3672, "loss": 0.0821, "learning_rate": 4.605442959097826e-05, "epoch": 0.5852729005036069, "percentage": 29.28, "elapsed_time": "6:53:28", "remaining_time": "16:38:51", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1080, "total_steps": 3672, "loss": 0.1273, "learning_rate": 4.5987417704534697e-05, "epoch": 0.587995100040833, "percentage": 29.41, "elapsed_time": "6:55:26", "remaining_time": "16:37:02", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1085, "total_steps": 3672, "loss": 0.0807, "learning_rate": 4.591989114493718e-05, "epoch": 0.5907172995780591, "percentage": 29.55, "elapsed_time": "6:57:25", "remaining_time": "16:35:17", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1090, "total_steps": 3672, "loss": 0.0737, "learning_rate": 4.5851851568135376e-05, "epoch": 0.5934394991152852, "percentage": 29.68, "elapsed_time": "6:59:19", "remaining_time": "16:33:17", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1095, "total_steps": 3672, "loss": 0.0904, "learning_rate": 4.5783300642659644e-05, "epoch": 0.5961616986525112, "percentage": 29.82, "elapsed_time": "7:01:17", "remaining_time": "16:31:28", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1100, "total_steps": 3672, "loss": 0.0863, "learning_rate": 4.571424004958012e-05, "epoch": 0.5988838981897373, "percentage": 29.96, "elapsed_time": "7:03:09", "remaining_time": "16:29:25", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1105, "total_steps": 3672, "loss": 0.0839, "learning_rate": 4.564467148246548e-05, "epoch": 0.6016060977269634, "percentage": 30.09, "elapsed_time": "7:04:58", "remaining_time": "16:27:14", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1110, "total_steps": 3672, "loss": 0.0862, "learning_rate": 4.557459664734141e-05, "epoch": 0.6043282972641895, "percentage": 30.23, "elapsed_time": "7:06:50", "remaining_time": "16:25:11", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1115, "total_steps": 3672, "loss": 0.0733, "learning_rate": 4.550401726264879e-05, "epoch": 0.6070504968014155, "percentage": 30.36, "elapsed_time": "7:08:43", "remaining_time": "16:23:10", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1120, "total_steps": 3672, "loss": 0.0712, "learning_rate": 4.5432935059201544e-05, "epoch": 0.6097726963386416, "percentage": 30.5, "elapsed_time": "7:10:35", "remaining_time": "16:21:07", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1125, "total_steps": 3672, "loss": 0.0808, "learning_rate": 4.536135178014415e-05, "epoch": 0.6124948958758677, "percentage": 30.64, "elapsed_time": "7:12:19", "remaining_time": "16:18:48", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1130, "total_steps": 3672, "loss": 0.0863, "learning_rate": 4.528926918090898e-05, "epoch": 0.6152170954130938, "percentage": 30.77, "elapsed_time": "7:14:12", "remaining_time": "16:16:45", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1135, "total_steps": 3672, "loss": 0.0848, "learning_rate": 4.521668902917317e-05, "epoch": 0.6179392949503199, "percentage": 30.91, "elapsed_time": "7:16:02", "remaining_time": "16:14:40", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1140, "total_steps": 3672, "loss": 0.0929, "learning_rate": 4.514361310481533e-05, "epoch": 0.6206614944875459, "percentage": 31.05, "elapsed_time": "7:18:00", "remaining_time": "16:12:51", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1145, "total_steps": 3672, "loss": 0.0914, "learning_rate": 4.507004319987185e-05, "epoch": 0.623383694024772, "percentage": 31.18, "elapsed_time": "7:19:58", "remaining_time": "16:11:01", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1150, "total_steps": 3672, "loss": 0.0885, "learning_rate": 4.499598111849299e-05, "epoch": 0.6261058935619981, "percentage": 31.32, "elapsed_time": "7:21:58", "remaining_time": "16:09:15", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1155, "total_steps": 3672, "loss": 0.083, "learning_rate": 4.492142867689861e-05, "epoch": 0.6288280930992242, "percentage": 31.45, "elapsed_time": "7:23:52", "remaining_time": "16:07:18", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1160, "total_steps": 3672, "loss": 0.0866, "learning_rate": 4.484638770333367e-05, "epoch": 0.6315502926364502, "percentage": 31.59, "elapsed_time": "7:25:30", "remaining_time": "16:04:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1165, "total_steps": 3672, "loss": 0.0991, "learning_rate": 4.4770860038023335e-05, "epoch": 0.6342724921736763, "percentage": 31.73, "elapsed_time": "7:27:34", "remaining_time": "16:03:08", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1170, "total_steps": 3672, "loss": 0.079, "learning_rate": 4.4694847533127903e-05, "epoch": 0.6369946917109024, "percentage": 31.86, "elapsed_time": "7:29:16", "remaining_time": "16:00:45", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1175, "total_steps": 3672, "loss": 0.0842, "learning_rate": 4.461835205269736e-05, "epoch": 0.6397168912481285, "percentage": 32.0, "elapsed_time": "7:31:11", "remaining_time": "15:58:49", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1180, "total_steps": 3672, "loss": 0.0771, "learning_rate": 4.454137547262566e-05, "epoch": 0.6424390907853545, "percentage": 32.14, "elapsed_time": "7:32:55", "remaining_time": "15:56:31", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1185, "total_steps": 3672, "loss": 0.0831, "learning_rate": 4.446391968060475e-05, "epoch": 0.6451612903225806, "percentage": 32.27, "elapsed_time": "7:34:52", "remaining_time": "15:54:39", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1190, "total_steps": 3672, "loss": 0.0918, "learning_rate": 4.4385986576078254e-05, "epoch": 0.6478834898598067, "percentage": 32.41, "elapsed_time": "7:36:41", "remaining_time": "15:52:31", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1195, "total_steps": 3672, "loss": 0.0897, "learning_rate": 4.43075780701949e-05, "epoch": 0.6506056893970328, "percentage": 32.54, "elapsed_time": "7:38:40", "remaining_time": "15:50:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1200, "total_steps": 3672, "loss": 0.1353, "learning_rate": 4.422869608576167e-05, "epoch": 0.6533278889342589, "percentage": 32.68, "elapsed_time": "7:40:36", "remaining_time": "15:48:51", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1205, "total_steps": 3672, "loss": 0.2083, "learning_rate": 4.4149342557196605e-05, "epoch": 0.6560500884714849, "percentage": 32.82, "elapsed_time": "7:42:31", "remaining_time": "15:46:56", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1210, "total_steps": 3672, "loss": 0.0824, "learning_rate": 4.406951943048141e-05, "epoch": 0.658772288008711, "percentage": 32.95, "elapsed_time": "7:44:28", "remaining_time": "15:45:04", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1215, "total_steps": 3672, "loss": 0.0774, "learning_rate": 4.3989228663113714e-05, "epoch": 0.6614944875459371, "percentage": 33.09, "elapsed_time": "7:46:17", "remaining_time": "15:42:55", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1220, "total_steps": 3672, "loss": 0.0788, "learning_rate": 4.3908472224059064e-05, "epoch": 0.6642166870831632, "percentage": 33.22, "elapsed_time": "7:48:06", "remaining_time": "15:40:50", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1225, "total_steps": 3672, "loss": 0.0882, "learning_rate": 4.3827252093702656e-05, "epoch": 0.6669388866203892, "percentage": 33.36, "elapsed_time": "7:49:53", "remaining_time": "15:38:36", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1230, "total_steps": 3672, "loss": 0.0783, "learning_rate": 4.374557026380075e-05, "epoch": 0.6696610861576153, "percentage": 33.5, "elapsed_time": "7:51:31", "remaining_time": "15:36:09", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1235, "total_steps": 3672, "loss": 0.0874, "learning_rate": 4.366342873743185e-05, "epoch": 0.6723832856948414, "percentage": 33.63, "elapsed_time": "7:53:14", "remaining_time": "15:33:49", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1240, "total_steps": 3672, "loss": 0.0863, "learning_rate": 4.358082952894753e-05, "epoch": 0.6751054852320675, "percentage": 33.77, "elapsed_time": "7:54:55", "remaining_time": "15:31:27", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1245, "total_steps": 3672, "loss": 0.0784, "learning_rate": 4.349777466392313e-05, "epoch": 0.6778276847692936, "percentage": 33.91, "elapsed_time": "7:56:41", "remaining_time": "15:29:14", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1250, "total_steps": 3672, "loss": 0.0823, "learning_rate": 4.341426617910798e-05, "epoch": 0.6805498843065196, "percentage": 34.04, "elapsed_time": "7:58:16", "remaining_time": "15:26:41", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1255, "total_steps": 3672, "loss": 0.0787, "learning_rate": 4.3330306122375516e-05, "epoch": 0.6832720838437457, "percentage": 34.18, "elapsed_time": "8:00:11", "remaining_time": "15:24:48", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1260, "total_steps": 3672, "loss": 0.0812, "learning_rate": 4.324589655267306e-05, "epoch": 0.6859942833809718, "percentage": 34.31, "elapsed_time": "8:01:53", "remaining_time": "15:22:28", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1265, "total_steps": 3672, "loss": 0.0917, "learning_rate": 4.3161039539971295e-05, "epoch": 0.6887164829181979, "percentage": 34.45, "elapsed_time": "8:03:46", "remaining_time": "15:20:29", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1270, "total_steps": 3672, "loss": 0.0866, "learning_rate": 4.307573716521353e-05, "epoch": 0.691438682455424, "percentage": 34.59, "elapsed_time": "8:05:27", "remaining_time": "15:18:09", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1275, "total_steps": 3672, "loss": 0.0822, "learning_rate": 4.298999152026465e-05, "epoch": 0.69416088199265, "percentage": 34.72, "elapsed_time": "8:07:13", "remaining_time": "15:15:59", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1280, "total_steps": 3672, "loss": 0.1482, "learning_rate": 4.2903804707859835e-05, "epoch": 0.6968830815298761, "percentage": 34.86, "elapsed_time": "8:08:57", "remaining_time": "15:13:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1285, "total_steps": 3672, "loss": 0.0792, "learning_rate": 4.281717884155298e-05, "epoch": 0.6996052810671022, "percentage": 34.99, "elapsed_time": "8:10:37", "remaining_time": "15:11:22", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1290, "total_steps": 3672, "loss": 0.0909, "learning_rate": 4.2730116045664905e-05, "epoch": 0.7023274806043283, "percentage": 35.13, "elapsed_time": "8:12:24", "remaining_time": "15:09:14", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1295, "total_steps": 3672, "loss": 0.0902, "learning_rate": 4.264261845523116e-05, "epoch": 0.7050496801415543, "percentage": 35.27, "elapsed_time": "8:13:59", "remaining_time": "15:06:43", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1300, "total_steps": 3672, "loss": 0.0796, "learning_rate": 4.255468821594981e-05, "epoch": 0.7077718796787804, "percentage": 35.4, "elapsed_time": "8:15:46", "remaining_time": "15:04:35", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1305, "total_steps": 3672, "loss": 0.0929, "learning_rate": 4.2466327484128685e-05, "epoch": 0.7104940792160065, "percentage": 35.54, "elapsed_time": "8:17:23", "remaining_time": "15:02:09", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1310, "total_steps": 3672, "loss": 0.0997, "learning_rate": 4.2377538426632595e-05, "epoch": 0.7132162787532326, "percentage": 35.68, "elapsed_time": "8:19:07", "remaining_time": "14:59:57", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1315, "total_steps": 3672, "loss": 0.0806, "learning_rate": 4.228832322083013e-05, "epoch": 0.7159384782904586, "percentage": 35.81, "elapsed_time": "8:20:50", "remaining_time": "14:57:43", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1320, "total_steps": 3672, "loss": 0.0877, "learning_rate": 4.2198684054540285e-05, "epoch": 0.7186606778276847, "percentage": 35.95, "elapsed_time": "8:22:34", "remaining_time": "14:55:30", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1325, "total_steps": 3672, "loss": 0.0802, "learning_rate": 4.210862312597884e-05, "epoch": 0.7213828773649108, "percentage": 36.08, "elapsed_time": "8:24:27", "remaining_time": "14:53:32", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1330, "total_steps": 3672, "loss": 0.0816, "learning_rate": 4.201814264370441e-05, "epoch": 0.7241050769021369, "percentage": 36.22, "elapsed_time": "8:26:06", "remaining_time": "14:51:12", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1335, "total_steps": 3672, "loss": 0.0812, "learning_rate": 4.192724482656428e-05, "epoch": 0.726827276439363, "percentage": 36.36, "elapsed_time": "8:27:57", "remaining_time": "14:49:12", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1340, "total_steps": 3672, "loss": 0.0926, "learning_rate": 4.1835931903640046e-05, "epoch": 0.729549475976589, "percentage": 36.49, "elapsed_time": "8:29:40", "remaining_time": "14:46:59", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1345, "total_steps": 3672, "loss": 0.078, "learning_rate": 4.17442061141929e-05, "epoch": 0.7322716755138151, "percentage": 36.63, "elapsed_time": "8:31:23", "remaining_time": "14:44:46", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1350, "total_steps": 3672, "loss": 0.0805, "learning_rate": 4.165206970760874e-05, "epoch": 0.7349938750510412, "percentage": 36.76, "elapsed_time": "8:33:06", "remaining_time": "14:42:33", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1355, "total_steps": 3672, "loss": 0.0837, "learning_rate": 4.1559524943342985e-05, "epoch": 0.7377160745882673, "percentage": 36.9, "elapsed_time": "8:34:48", "remaining_time": "14:40:17", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1360, "total_steps": 3672, "loss": 0.0857, "learning_rate": 4.1466574090865225e-05, "epoch": 0.7404382741254933, "percentage": 37.04, "elapsed_time": "8:36:24", "remaining_time": "14:37:54", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1365, "total_steps": 3672, "loss": 0.0814, "learning_rate": 4.1373219429603473e-05, "epoch": 0.7431604736627194, "percentage": 37.17, "elapsed_time": "8:38:11", "remaining_time": "14:35:47", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1370, "total_steps": 3672, "loss": 0.0743, "learning_rate": 4.127946324888836e-05, "epoch": 0.7458826731999455, "percentage": 37.31, "elapsed_time": "8:39:46", "remaining_time": "14:33:22", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1375, "total_steps": 3672, "loss": 0.0768, "learning_rate": 4.118530784789694e-05, "epoch": 0.7486048727371717, "percentage": 37.45, "elapsed_time": "8:41:32", "remaining_time": "14:31:15", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1380, "total_steps": 3672, "loss": 0.0806, "learning_rate": 4.109075553559633e-05, "epoch": 0.7513270722743978, "percentage": 37.58, "elapsed_time": "8:43:19", "remaining_time": "14:29:10", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1385, "total_steps": 3672, "loss": 0.0915, "learning_rate": 4.099580863068706e-05, "epoch": 0.7540492718116238, "percentage": 37.72, "elapsed_time": "8:45:03", "remaining_time": "14:27:00", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1390, "total_steps": 3672, "loss": 0.0799, "learning_rate": 4.0900469461546235e-05, "epoch": 0.7567714713488499, "percentage": 37.85, "elapsed_time": "8:46:49", "remaining_time": "14:24:54", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1395, "total_steps": 3672, "loss": 0.0899, "learning_rate": 4.0804740366170454e-05, "epoch": 0.759493670886076, "percentage": 37.99, "elapsed_time": "8:48:35", "remaining_time": "14:22:47", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1400, "total_steps": 3672, "loss": 0.0827, "learning_rate": 4.070862369211843e-05, "epoch": 0.7622158704233021, "percentage": 38.13, "elapsed_time": "8:50:19", "remaining_time": "14:20:38", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1405, "total_steps": 3672, "loss": 0.0856, "learning_rate": 4.061212179645345e-05, "epoch": 0.7649380699605282, "percentage": 38.26, "elapsed_time": "8:52:01", "remaining_time": "14:18:26", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1410, "total_steps": 3672, "loss": 0.1416, "learning_rate": 4.051523704568557e-05, "epoch": 0.7676602694977542, "percentage": 38.4, "elapsed_time": "8:53:44", "remaining_time": "14:16:15", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1415, "total_steps": 3672, "loss": 0.0827, "learning_rate": 4.0417971815713584e-05, "epoch": 0.7703824690349803, "percentage": 38.53, "elapsed_time": "8:55:25", "remaining_time": "14:14:01", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1420, "total_steps": 3672, "loss": 0.0808, "learning_rate": 4.032032849176673e-05, "epoch": 0.7731046685722064, "percentage": 38.67, "elapsed_time": "8:57:04", "remaining_time": "14:11:45", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1425, "total_steps": 3672, "loss": 0.08, "learning_rate": 4.022230946834624e-05, "epoch": 0.7758268681094325, "percentage": 38.81, "elapsed_time": "8:58:46", "remaining_time": "14:09:33", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1430, "total_steps": 3672, "loss": 0.0867, "learning_rate": 4.012391714916661e-05, "epoch": 0.7785490676466585, "percentage": 38.94, "elapsed_time": "9:00:27", "remaining_time": "14:07:21", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1435, "total_steps": 3672, "loss": 0.0865, "learning_rate": 4.0025153947096624e-05, "epoch": 0.7812712671838846, "percentage": 39.08, "elapsed_time": "9:02:09", "remaining_time": "14:05:09", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1440, "total_steps": 3672, "loss": 0.0983, "learning_rate": 3.992602228410023e-05, "epoch": 0.7839934667211107, "percentage": 39.22, "elapsed_time": "9:03:49", "remaining_time": "14:02:55", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1445, "total_steps": 3672, "loss": 0.0829, "learning_rate": 3.982652459117707e-05, "epoch": 0.7867156662583368, "percentage": 39.35, "elapsed_time": "9:05:35", "remaining_time": "14:00:51", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1450, "total_steps": 3672, "loss": 0.0903, "learning_rate": 3.972666330830299e-05, "epoch": 0.7894378657955629, "percentage": 39.49, "elapsed_time": "9:07:08", "remaining_time": "13:58:27", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1455, "total_steps": 3672, "loss": 0.0748, "learning_rate": 3.9626440884370065e-05, "epoch": 0.7921600653327889, "percentage": 39.62, "elapsed_time": "9:08:47", "remaining_time": "13:56:12", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1460, "total_steps": 3672, "loss": 0.083, "learning_rate": 3.952585977712664e-05, "epoch": 0.794882264870015, "percentage": 39.76, "elapsed_time": "9:10:48", "remaining_time": "13:54:30", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1465, "total_steps": 3672, "loss": 0.0926, "learning_rate": 3.942492245311703e-05, "epoch": 0.7976044644072411, "percentage": 39.9, "elapsed_time": "9:12:30", "remaining_time": "13:52:20", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1470, "total_steps": 3672, "loss": 0.0841, "learning_rate": 3.9323631387621015e-05, "epoch": 0.8003266639444672, "percentage": 40.03, "elapsed_time": "9:14:09", "remaining_time": "13:50:05", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1475, "total_steps": 3672, "loss": 0.076, "learning_rate": 3.9221989064593175e-05, "epoch": 0.8030488634816932, "percentage": 40.17, "elapsed_time": "9:15:57", "remaining_time": "13:48:05", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1480, "total_steps": 3672, "loss": 0.097, "learning_rate": 3.9119997976601954e-05, "epoch": 0.8057710630189193, "percentage": 40.31, "elapsed_time": "9:17:37", "remaining_time": "13:45:53", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1485, "total_steps": 3672, "loss": 0.0834, "learning_rate": 3.9017660624768515e-05, "epoch": 0.8084932625561454, "percentage": 40.44, "elapsed_time": "9:19:21", "remaining_time": "13:43:46", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1490, "total_steps": 3672, "loss": 0.0765, "learning_rate": 3.891497951870545e-05, "epoch": 0.8112154620933715, "percentage": 40.58, "elapsed_time": "9:21:03", "remaining_time": "13:41:38", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1495, "total_steps": 3672, "loss": 0.0832, "learning_rate": 3.8811957176455214e-05, "epoch": 0.8139376616305976, "percentage": 40.71, "elapsed_time": "9:22:47", "remaining_time": "13:39:31", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1500, "total_steps": 3672, "loss": 0.0819, "learning_rate": 3.870859612442837e-05, "epoch": 0.8166598611678236, "percentage": 40.85, "elapsed_time": "9:24:35", "remaining_time": "13:37:31", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1500, "total_steps": 3672, "eval_loss": 0.08255165070295334, "epoch": 0.8166598611678236, "percentage": 40.85, "elapsed_time": "9:28:33", "remaining_time": "13:43:16", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1505, "total_steps": 3672, "loss": 0.1878, "learning_rate": 3.8604898897341644e-05, "epoch": 0.8193820607050497, "percentage": 40.99, "elapsed_time": "9:30:27", "remaining_time": "13:41:23", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1510, "total_steps": 3672, "loss": 0.0879, "learning_rate": 3.850086803815576e-05, "epoch": 0.8221042602422758, "percentage": 41.12, "elapsed_time": "9:32:14", "remaining_time": "13:39:20", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1515, "total_steps": 3672, "loss": 0.0767, "learning_rate": 3.8396506098013076e-05, "epoch": 0.8248264597795019, "percentage": 41.26, "elapsed_time": "9:34:07", "remaining_time": "13:37:24", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1520, "total_steps": 3672, "loss": 0.0972, "learning_rate": 3.829181563617503e-05, "epoch": 0.8275486593167279, "percentage": 41.39, "elapsed_time": "9:35:54", "remaining_time": "13:35:22", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1525, "total_steps": 3672, "loss": 0.0839, "learning_rate": 3.81867992199594e-05, "epoch": 0.830270858853954, "percentage": 41.53, "elapsed_time": "9:37:50", "remaining_time": "13:33:30", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1530, "total_steps": 3672, "loss": 0.0923, "learning_rate": 3.808145942467729e-05, "epoch": 0.8329930583911801, "percentage": 41.67, "elapsed_time": "9:39:34", "remaining_time": "13:31:24", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1535, "total_steps": 3672, "loss": 0.0872, "learning_rate": 3.797579883357002e-05, "epoch": 0.8357152579284062, "percentage": 41.8, "elapsed_time": "9:41:11", "remaining_time": "13:29:07", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1540, "total_steps": 3672, "loss": 0.1243, "learning_rate": 3.7869820037745776e-05, "epoch": 0.8384374574656323, "percentage": 41.94, "elapsed_time": "9:43:04", "remaining_time": "13:27:13", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1545, "total_steps": 3672, "loss": 0.0839, "learning_rate": 3.776352563611604e-05, "epoch": 0.8411596570028583, "percentage": 42.08, "elapsed_time": "9:44:53", "remaining_time": "13:25:12", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1550, "total_steps": 3672, "loss": 0.0873, "learning_rate": 3.765691823533191e-05, "epoch": 0.8438818565400844, "percentage": 42.21, "elapsed_time": "9:46:41", "remaining_time": "13:23:11", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1555, "total_steps": 3672, "loss": 0.0771, "learning_rate": 3.75500004497201e-05, "epoch": 0.8466040560773105, "percentage": 42.35, "elapsed_time": "9:48:37", "remaining_time": "13:21:22", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1560, "total_steps": 3672, "loss": 0.0816, "learning_rate": 3.74427749012189e-05, "epoch": 0.8493262556145366, "percentage": 42.48, "elapsed_time": "9:50:27", "remaining_time": "13:19:23", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1565, "total_steps": 3672, "loss": 0.0859, "learning_rate": 3.733524421931385e-05, "epoch": 0.8520484551517626, "percentage": 42.62, "elapsed_time": "9:52:18", "remaining_time": "13:17:25", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1570, "total_steps": 3672, "loss": 0.0806, "learning_rate": 3.722741104097323e-05, "epoch": 0.8547706546889887, "percentage": 42.76, "elapsed_time": "9:54:16", "remaining_time": "13:15:38", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1575, "total_steps": 3672, "loss": 0.0792, "learning_rate": 3.711927801058347e-05, "epoch": 0.8574928542262148, "percentage": 42.89, "elapsed_time": "9:56:12", "remaining_time": "13:13:48", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1580, "total_steps": 3672, "loss": 0.0763, "learning_rate": 3.7010847779884204e-05, "epoch": 0.8602150537634409, "percentage": 43.03, "elapsed_time": "9:58:01", "remaining_time": "13:11:48", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1585, "total_steps": 3672, "loss": 0.0871, "learning_rate": 3.690212300790333e-05, "epoch": 0.862937253300667, "percentage": 43.16, "elapsed_time": "9:59:59", "remaining_time": "13:10:01", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1590, "total_steps": 3672, "loss": 0.1189, "learning_rate": 3.679310636089174e-05, "epoch": 0.865659452837893, "percentage": 43.3, "elapsed_time": "10:01:54", "remaining_time": "13:08:09", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1595, "total_steps": 3672, "loss": 0.0811, "learning_rate": 3.668380051225794e-05, "epoch": 0.8683816523751191, "percentage": 43.44, "elapsed_time": "10:03:48", "remaining_time": "13:06:16", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1600, "total_steps": 3672, "loss": 0.086, "learning_rate": 3.657420814250258e-05, "epoch": 0.8711038519123452, "percentage": 43.57, "elapsed_time": "10:05:39", "remaining_time": "13:04:19", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1605, "total_steps": 3672, "loss": 0.0885, "learning_rate": 3.646433193915257e-05, "epoch": 0.8738260514495713, "percentage": 43.71, "elapsed_time": "10:07:36", "remaining_time": "13:02:30", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1610, "total_steps": 3672, "loss": 0.0738, "learning_rate": 3.635417459669532e-05, "epoch": 0.8765482509867973, "percentage": 43.85, "elapsed_time": "10:09:30", "remaining_time": "13:00:37", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1615, "total_steps": 3672, "loss": 0.0883, "learning_rate": 3.624373881651254e-05, "epoch": 0.8792704505240234, "percentage": 43.98, "elapsed_time": "10:11:28", "remaining_time": "12:58:49", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1620, "total_steps": 3672, "loss": 0.0869, "learning_rate": 3.6133027306814085e-05, "epoch": 0.8819926500612495, "percentage": 44.12, "elapsed_time": "10:13:20", "remaining_time": "12:56:54", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1625, "total_steps": 3672, "loss": 0.0868, "learning_rate": 3.6022042782571494e-05, "epoch": 0.8847148495984756, "percentage": 44.25, "elapsed_time": "10:15:27", "remaining_time": "12:55:17", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1630, "total_steps": 3672, "loss": 0.0829, "learning_rate": 3.591078796545144e-05, "epoch": 0.8874370491357016, "percentage": 44.39, "elapsed_time": "10:17:39", "remaining_time": "12:53:46", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1635, "total_steps": 3672, "loss": 0.0888, "learning_rate": 3.579926558374897e-05, "epoch": 0.8901592486729277, "percentage": 44.53, "elapsed_time": "10:19:35", "remaining_time": "12:51:55", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1640, "total_steps": 3672, "loss": 0.0853, "learning_rate": 3.5687478372320576e-05, "epoch": 0.8928814482101538, "percentage": 44.66, "elapsed_time": "10:21:26", "remaining_time": "12:49:58", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1645, "total_steps": 3672, "loss": 0.0763, "learning_rate": 3.557542907251718e-05, "epoch": 0.8956036477473799, "percentage": 44.8, "elapsed_time": "10:23:24", "remaining_time": "12:48:10", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1650, "total_steps": 3672, "loss": 0.0835, "learning_rate": 3.546312043211687e-05, "epoch": 0.898325847284606, "percentage": 44.93, "elapsed_time": "10:25:24", "remaining_time": "12:46:24", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1655, "total_steps": 3672, "loss": 0.0795, "learning_rate": 3.535055520525753e-05, "epoch": 0.901048046821832, "percentage": 45.07, "elapsed_time": "10:27:17", "remaining_time": "12:44:29", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1660, "total_steps": 3672, "loss": 0.0838, "learning_rate": 3.52377361523693e-05, "epoch": 0.9037702463590581, "percentage": 45.21, "elapsed_time": "10:29:15", "remaining_time": "12:42:41", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1665, "total_steps": 3672, "loss": 0.0834, "learning_rate": 3.512466604010688e-05, "epoch": 0.9064924458962842, "percentage": 45.34, "elapsed_time": "10:31:10", "remaining_time": "12:40:49", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1670, "total_steps": 3672, "loss": 0.0933, "learning_rate": 3.501134764128167e-05, "epoch": 0.9092146454335103, "percentage": 45.48, "elapsed_time": "10:33:00", "remaining_time": "12:38:51", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1675, "total_steps": 3672, "loss": 0.0829, "learning_rate": 3.4897783734793794e-05, "epoch": 0.9119368449707363, "percentage": 45.62, "elapsed_time": "10:34:58", "remaining_time": "12:37:01", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1680, "total_steps": 3672, "loss": 0.0775, "learning_rate": 3.478397710556397e-05, "epoch": 0.9146590445079624, "percentage": 45.75, "elapsed_time": "10:36:51", "remaining_time": "12:35:07", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1685, "total_steps": 3672, "loss": 0.0762, "learning_rate": 3.466993054446515e-05, "epoch": 0.9173812440451885, "percentage": 45.89, "elapsed_time": "10:38:45", "remaining_time": "12:33:13", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1690, "total_steps": 3672, "loss": 0.094, "learning_rate": 3.4555646848254136e-05, "epoch": 0.9201034435824146, "percentage": 46.02, "elapsed_time": "10:40:35", "remaining_time": "12:31:16", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1695, "total_steps": 3672, "loss": 0.0839, "learning_rate": 3.4441128819503e-05, "epoch": 0.9228256431196407, "percentage": 46.16, "elapsed_time": "10:42:28", "remaining_time": "12:29:22", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1700, "total_steps": 3672, "loss": 0.0831, "learning_rate": 3.4326379266530314e-05, "epoch": 0.9255478426568667, "percentage": 46.3, "elapsed_time": "10:44:22", "remaining_time": "12:27:28", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1705, "total_steps": 3672, "loss": 0.0842, "learning_rate": 3.421140100333231e-05, "epoch": 0.9282700421940928, "percentage": 46.43, "elapsed_time": "10:46:11", "remaining_time": "12:25:29", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1710, "total_steps": 3672, "loss": 0.1127, "learning_rate": 3.409619684951386e-05, "epoch": 0.9309922417313189, "percentage": 46.57, "elapsed_time": "10:48:07", "remaining_time": "12:23:38", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1715, "total_steps": 3672, "loss": 0.0781, "learning_rate": 3.3980769630219354e-05, "epoch": 0.933714441268545, "percentage": 46.7, "elapsed_time": "10:50:00", "remaining_time": "12:21:43", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1720, "total_steps": 3672, "loss": 0.071, "learning_rate": 3.386512217606339e-05, "epoch": 0.936436640805771, "percentage": 46.84, "elapsed_time": "10:51:51", "remaining_time": "12:19:47", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1725, "total_steps": 3672, "loss": 0.0852, "learning_rate": 3.3749257323061376e-05, "epoch": 0.9391588403429971, "percentage": 46.98, "elapsed_time": "10:53:47", "remaining_time": "12:17:55", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1730, "total_steps": 3672, "loss": 0.0793, "learning_rate": 3.3633177912559984e-05, "epoch": 0.9418810398802232, "percentage": 47.11, "elapsed_time": "10:55:44", "remaining_time": "12:16:05", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1735, "total_steps": 3672, "loss": 0.0804, "learning_rate": 3.3516886791167444e-05, "epoch": 0.9446032394174493, "percentage": 47.25, "elapsed_time": "10:57:38", "remaining_time": "12:14:12", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1740, "total_steps": 3672, "loss": 0.0865, "learning_rate": 3.34003868106838e-05, "epoch": 0.9473254389546754, "percentage": 47.39, "elapsed_time": "10:59:28", "remaining_time": "12:12:14", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1745, "total_steps": 3672, "loss": 0.0793, "learning_rate": 3.328368082803088e-05, "epoch": 0.9500476384919014, "percentage": 47.52, "elapsed_time": "11:01:21", "remaining_time": "12:10:20", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1750, "total_steps": 3672, "loss": 0.0769, "learning_rate": 3.316677170518235e-05, "epoch": 0.9527698380291275, "percentage": 47.66, "elapsed_time": "11:03:18", "remaining_time": "12:08:30", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1755, "total_steps": 3672, "loss": 0.0931, "learning_rate": 3.304966230909342e-05, "epoch": 0.9554920375663536, "percentage": 47.79, "elapsed_time": "11:05:15", "remaining_time": "12:06:40", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1760, "total_steps": 3672, "loss": 0.0835, "learning_rate": 3.293235551163063e-05, "epoch": 0.9582142371035797, "percentage": 47.93, "elapsed_time": "11:07:00", "remaining_time": "12:04:36", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1765, "total_steps": 3672, "loss": 0.0866, "learning_rate": 3.2814854189501346e-05, "epoch": 0.9609364366408057, "percentage": 48.07, "elapsed_time": "11:09:02", "remaining_time": "12:02:52", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1770, "total_steps": 3672, "loss": 0.0851, "learning_rate": 3.269716122418326e-05, "epoch": 0.9636586361780318, "percentage": 48.2, "elapsed_time": "11:10:59", "remaining_time": "12:01:01", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1775, "total_steps": 3672, "loss": 0.0834, "learning_rate": 3.2579279501853744e-05, "epoch": 0.9663808357152579, "percentage": 48.34, "elapsed_time": "11:12:41", "remaining_time": "11:58:55", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1780, "total_steps": 3672, "loss": 0.0868, "learning_rate": 3.246121191331902e-05, "epoch": 0.969103035252484, "percentage": 48.47, "elapsed_time": "11:14:40", "remaining_time": "11:57:07", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1785, "total_steps": 3672, "loss": 0.081, "learning_rate": 3.234296135394329e-05, "epoch": 0.9718252347897101, "percentage": 48.61, "elapsed_time": "11:16:36", "remaining_time": "11:55:16", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1790, "total_steps": 3672, "loss": 0.0758, "learning_rate": 3.222453072357777e-05, "epoch": 0.9745474343269361, "percentage": 48.75, "elapsed_time": "11:18:34", "remaining_time": "11:53:26", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1795, "total_steps": 3672, "loss": 0.1002, "learning_rate": 3.2105922926489504e-05, "epoch": 0.9772696338641622, "percentage": 48.88, "elapsed_time": "11:20:31", "remaining_time": "11:51:36", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1800, "total_steps": 3672, "loss": 0.0736, "learning_rate": 3.1987140871290236e-05, "epoch": 0.9799918334013883, "percentage": 49.02, "elapsed_time": "11:22:27", "remaining_time": "11:49:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1805, "total_steps": 3672, "loss": 0.0779, "learning_rate": 3.1868187470864984e-05, "epoch": 0.9827140329386144, "percentage": 49.16, "elapsed_time": "11:24:13", "remaining_time": "11:47:43", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1810, "total_steps": 3672, "loss": 0.0833, "learning_rate": 3.1749065642300674e-05, "epoch": 0.9854362324758404, "percentage": 49.29, "elapsed_time": "11:26:14", "remaining_time": "11:45:57", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1815, "total_steps": 3672, "loss": 0.0859, "learning_rate": 3.1629778306814585e-05, "epoch": 0.9881584320130665, "percentage": 49.43, "elapsed_time": "11:28:16", "remaining_time": "11:44:11", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1820, "total_steps": 3672, "loss": 0.0845, "learning_rate": 3.151032838968271e-05, "epoch": 0.9908806315502926, "percentage": 49.56, "elapsed_time": "11:30:08", "remaining_time": "11:42:16", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1825, "total_steps": 3672, "loss": 0.0935, "learning_rate": 3.139071882016802e-05, "epoch": 0.9936028310875187, "percentage": 49.7, "elapsed_time": "11:32:07", "remaining_time": "11:40:28", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1830, "total_steps": 3672, "loss": 0.077, "learning_rate": 3.127095253144864e-05, "epoch": 0.9963250306247448, "percentage": 49.84, "elapsed_time": "11:34:01", "remaining_time": "11:38:34", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1835, "total_steps": 3672, "loss": 0.0795, "learning_rate": 3.11510324605459e-05, "epoch": 0.9990472301619708, "percentage": 49.97, "elapsed_time": "11:35:58", "remaining_time": "11:36:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1840, "total_steps": 3672, "loss": 0.1021, "learning_rate": 3.103096154825233e-05, "epoch": 1.001769429699197, "percentage": 50.11, "elapsed_time": "11:38:01", "remaining_time": "11:34:59", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1845, "total_steps": 3672, "loss": 0.0833, "learning_rate": 3.0910742739059527e-05, "epoch": 1.004491629236423, "percentage": 50.25, "elapsed_time": "11:40:03", "remaining_time": "11:33:13", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1850, "total_steps": 3672, "loss": 0.076, "learning_rate": 3.0790378981085956e-05, "epoch": 1.0072138287736492, "percentage": 50.38, "elapsed_time": "11:41:58", "remaining_time": "11:31:21", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1855, "total_steps": 3672, "loss": 0.0769, "learning_rate": 3.0669873226004655e-05, "epoch": 1.0099360283108751, "percentage": 50.52, "elapsed_time": "11:43:58", "remaining_time": "11:29:33", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1860, "total_steps": 3672, "loss": 0.0729, "learning_rate": 3.054922842897084e-05, "epoch": 1.0126582278481013, "percentage": 50.65, "elapsed_time": "11:45:55", "remaining_time": "11:27:42", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1865, "total_steps": 3672, "loss": 0.0772, "learning_rate": 3.0428447548549467e-05, "epoch": 1.0153804273853273, "percentage": 50.79, "elapsed_time": "11:48:00", "remaining_time": "11:25:59", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1870, "total_steps": 3672, "loss": 0.1681, "learning_rate": 3.030753354664262e-05, "epoch": 1.0181026269225535, "percentage": 50.93, "elapsed_time": "11:50:00", "remaining_time": "11:24:10", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1875, "total_steps": 3672, "loss": 0.0753, "learning_rate": 3.018648938841695e-05, "epoch": 1.0208248264597795, "percentage": 51.06, "elapsed_time": "11:52:03", "remaining_time": "11:22:26", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1880, "total_steps": 3672, "loss": 0.0746, "learning_rate": 3.00653180422309e-05, "epoch": 1.0235470259970056, "percentage": 51.2, "elapsed_time": "11:54:02", "remaining_time": "11:20:37", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1885, "total_steps": 3672, "loss": 0.0733, "learning_rate": 2.994402247956194e-05, "epoch": 1.0262692255342316, "percentage": 51.33, "elapsed_time": "11:56:09", "remaining_time": "11:18:55", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1890, "total_steps": 3672, "loss": 0.076, "learning_rate": 2.9822605674933696e-05, "epoch": 1.0289914250714578, "percentage": 51.47, "elapsed_time": "11:58:12", "remaining_time": "11:17:09", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1895, "total_steps": 3672, "loss": 0.0756, "learning_rate": 2.9701070605843e-05, "epoch": 1.0317136246086838, "percentage": 51.61, "elapsed_time": "12:00:08", "remaining_time": "11:15:18", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1900, "total_steps": 3672, "loss": 0.0733, "learning_rate": 2.957942025268689e-05, "epoch": 1.03443582414591, "percentage": 51.74, "elapsed_time": "12:02:15", "remaining_time": "11:13:36", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1905, "total_steps": 3672, "loss": 0.0837, "learning_rate": 2.945765759868949e-05, "epoch": 1.037158023683136, "percentage": 51.88, "elapsed_time": "12:04:11", "remaining_time": "11:11:43", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1910, "total_steps": 3672, "loss": 0.0814, "learning_rate": 2.933578562982888e-05, "epoch": 1.039880223220362, "percentage": 52.02, "elapsed_time": "12:06:10", "remaining_time": "11:09:54", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1915, "total_steps": 3672, "loss": 0.0748, "learning_rate": 2.9213807334763854e-05, "epoch": 1.042602422757588, "percentage": 52.15, "elapsed_time": "12:07:56", "remaining_time": "11:07:52", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1920, "total_steps": 3672, "loss": 0.0668, "learning_rate": 2.9091725704760638e-05, "epoch": 1.0453246222948143, "percentage": 52.29, "elapsed_time": "12:09:49", "remaining_time": "11:05:57", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1925, "total_steps": 3672, "loss": 0.0742, "learning_rate": 2.8969543733619554e-05, "epoch": 1.0480468218320402, "percentage": 52.42, "elapsed_time": "12:11:26", "remaining_time": "11:03:48", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1930, "total_steps": 3672, "loss": 0.0716, "learning_rate": 2.884726441760155e-05, "epoch": 1.0507690213692664, "percentage": 52.56, "elapsed_time": "12:13:17", "remaining_time": "11:01:51", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1935, "total_steps": 3672, "loss": 0.0882, "learning_rate": 2.8724890755354783e-05, "epoch": 1.0534912209064924, "percentage": 52.7, "elapsed_time": "12:14:56", "remaining_time": "10:59:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1940, "total_steps": 3672, "loss": 0.0715, "learning_rate": 2.8602425747841057e-05, "epoch": 1.0562134204437186, "percentage": 52.83, "elapsed_time": "12:16:39", "remaining_time": "10:57:40", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1945, "total_steps": 3672, "loss": 0.0805, "learning_rate": 2.8479872398262198e-05, "epoch": 1.0589356199809445, "percentage": 52.97, "elapsed_time": "12:18:19", "remaining_time": "10:55:33", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1950, "total_steps": 3672, "loss": 0.0764, "learning_rate": 2.8357233711986487e-05, "epoch": 1.0616578195181707, "percentage": 53.1, "elapsed_time": "12:19:58", "remaining_time": "10:53:26", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1955, "total_steps": 3672, "loss": 0.0733, "learning_rate": 2.8234512696474875e-05, "epoch": 1.0643800190553967, "percentage": 53.24, "elapsed_time": "12:21:37", "remaining_time": "10:51:19", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1960, "total_steps": 3672, "loss": 0.0751, "learning_rate": 2.8111712361207283e-05, "epoch": 1.0671022185926229, "percentage": 53.38, "elapsed_time": "12:23:15", "remaining_time": "10:49:12", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1965, "total_steps": 3672, "loss": 0.0776, "learning_rate": 2.7988835717608784e-05, "epoch": 1.0698244181298489, "percentage": 53.51, "elapsed_time": "12:24:59", "remaining_time": "10:47:10", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1970, "total_steps": 3672, "loss": 0.0764, "learning_rate": 2.7865885778975743e-05, "epoch": 1.072546617667075, "percentage": 53.65, "elapsed_time": "12:26:37", "remaining_time": "10:45:03", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1975, "total_steps": 3672, "loss": 0.0792, "learning_rate": 2.774286556040196e-05, "epoch": 1.075268817204301, "percentage": 53.79, "elapsed_time": "12:28:17", "remaining_time": "10:42:58", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1980, "total_steps": 3672, "loss": 0.0706, "learning_rate": 2.7619778078704685e-05, "epoch": 1.0779910167415272, "percentage": 53.92, "elapsed_time": "12:29:57", "remaining_time": "10:40:52", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1985, "total_steps": 3672, "loss": 0.0826, "learning_rate": 2.7496626352350664e-05, "epoch": 1.0807132162787532, "percentage": 54.06, "elapsed_time": "12:31:34", "remaining_time": "10:38:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1990, "total_steps": 3672, "loss": 0.076, "learning_rate": 2.7373413401382104e-05, "epoch": 1.0834354158159794, "percentage": 54.19, "elapsed_time": "12:33:12", "remaining_time": "10:36:37", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 1995, "total_steps": 3672, "loss": 0.1298, "learning_rate": 2.7250142247342637e-05, "epoch": 1.0861576153532053, "percentage": 54.33, "elapsed_time": "12:34:54", "remaining_time": "10:34:34", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2000, "total_steps": 3672, "loss": 0.0753, "learning_rate": 2.7126815913203178e-05, "epoch": 1.0888798148904315, "percentage": 54.47, "elapsed_time": "12:36:29", "remaining_time": "10:32:25", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2000, "total_steps": 3672, "eval_loss": 0.08035612851381302, "epoch": 1.0888798148904315, "percentage": 54.47, "elapsed_time": "12:40:18", "remaining_time": "10:35:36", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2005, "total_steps": 3672, "loss": 0.1036, "learning_rate": 2.7003437423287857e-05, "epoch": 1.0916020144276575, "percentage": 54.6, "elapsed_time": "12:41:55", "remaining_time": "10:33:28", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2010, "total_steps": 3672, "loss": 0.0744, "learning_rate": 2.688000980319979e-05, "epoch": 1.0943242139648837, "percentage": 54.74, "elapsed_time": "12:43:31", "remaining_time": "10:31:19", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2015, "total_steps": 3672, "loss": 0.0738, "learning_rate": 2.6756536079746907e-05, "epoch": 1.0970464135021096, "percentage": 54.87, "elapsed_time": "12:45:06", "remaining_time": "10:29:10", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2020, "total_steps": 3672, "loss": 0.0701, "learning_rate": 2.663301928086774e-05, "epoch": 1.0997686130393358, "percentage": 55.01, "elapsed_time": "12:46:45", "remaining_time": "10:27:04", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2025, "total_steps": 3672, "loss": 0.0707, "learning_rate": 2.6509462435557152e-05, "epoch": 1.1024908125765618, "percentage": 55.15, "elapsed_time": "12:48:23", "remaining_time": "10:24:57", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2030, "total_steps": 3672, "loss": 0.07, "learning_rate": 2.6385868573792072e-05, "epoch": 1.105213012113788, "percentage": 55.28, "elapsed_time": "12:50:00", "remaining_time": "10:22:50", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2035, "total_steps": 3672, "loss": 0.0815, "learning_rate": 2.6262240726457167e-05, "epoch": 1.107935211651014, "percentage": 55.42, "elapsed_time": "12:51:38", "remaining_time": "10:20:43", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2040, "total_steps": 3672, "loss": 0.0802, "learning_rate": 2.6138581925270533e-05, "epoch": 1.1106574111882401, "percentage": 55.56, "elapsed_time": "12:53:16", "remaining_time": "10:18:36", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2045, "total_steps": 3672, "loss": 0.0777, "learning_rate": 2.6014895202709354e-05, "epoch": 1.113379610725466, "percentage": 55.69, "elapsed_time": "12:54:59", "remaining_time": "10:16:35", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2050, "total_steps": 3672, "loss": 0.0798, "learning_rate": 2.5891183591935515e-05, "epoch": 1.1161018102626923, "percentage": 55.83, "elapsed_time": "12:56:38", "remaining_time": "10:14:29", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2055, "total_steps": 3672, "loss": 0.0679, "learning_rate": 2.5767450126721255e-05, "epoch": 1.1188240097999183, "percentage": 55.96, "elapsed_time": "12:58:17", "remaining_time": "10:12:24", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2060, "total_steps": 3672, "loss": 0.0742, "learning_rate": 2.564369784137472e-05, "epoch": 1.1215462093371444, "percentage": 56.1, "elapsed_time": "12:59:58", "remaining_time": "10:10:21", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2065, "total_steps": 3672, "loss": 0.0885, "learning_rate": 2.5519929770665597e-05, "epoch": 1.1242684088743704, "percentage": 56.24, "elapsed_time": "13:01:37", "remaining_time": "10:08:16", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2070, "total_steps": 3672, "loss": 0.0672, "learning_rate": 2.539614894975067e-05, "epoch": 1.1269906084115966, "percentage": 56.37, "elapsed_time": "13:03:19", "remaining_time": "10:06:13", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2075, "total_steps": 3672, "loss": 0.0765, "learning_rate": 2.5272358414099413e-05, "epoch": 1.1297128079488226, "percentage": 56.51, "elapsed_time": "13:04:56", "remaining_time": "10:04:07", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2080, "total_steps": 3672, "loss": 0.0728, "learning_rate": 2.5148561199419516e-05, "epoch": 1.1324350074860488, "percentage": 56.64, "elapsed_time": "13:06:32", "remaining_time": "10:02:00", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2085, "total_steps": 3672, "loss": 0.0785, "learning_rate": 2.5024760341582453e-05, "epoch": 1.1351572070232747, "percentage": 56.78, "elapsed_time": "13:08:15", "remaining_time": "9:59:58", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2090, "total_steps": 3672, "loss": 0.0971, "learning_rate": 2.490095887654906e-05, "epoch": 1.137879406560501, "percentage": 56.92, "elapsed_time": "13:09:53", "remaining_time": "9:57:53", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2095, "total_steps": 3672, "loss": 0.0669, "learning_rate": 2.4777159840295046e-05, "epoch": 1.1406016060977269, "percentage": 57.05, "elapsed_time": "13:11:33", "remaining_time": "9:55:50", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2100, "total_steps": 3672, "loss": 0.0776, "learning_rate": 2.4653366268736565e-05, "epoch": 1.143323805634953, "percentage": 57.19, "elapsed_time": "13:13:15", "remaining_time": "9:53:48", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2105, "total_steps": 3672, "loss": 0.0782, "learning_rate": 2.452958119765577e-05, "epoch": 1.146046005172179, "percentage": 57.33, "elapsed_time": "13:14:52", "remaining_time": "9:51:43", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2110, "total_steps": 3672, "loss": 0.0792, "learning_rate": 2.4405807662626338e-05, "epoch": 1.1487682047094052, "percentage": 57.46, "elapsed_time": "13:16:35", "remaining_time": "9:49:42", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2115, "total_steps": 3672, "loss": 0.0729, "learning_rate": 2.4282048698939062e-05, "epoch": 1.1514904042466312, "percentage": 57.6, "elapsed_time": "13:18:16", "remaining_time": "9:47:39", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2120, "total_steps": 3672, "loss": 0.0842, "learning_rate": 2.41583073415274e-05, "epoch": 1.1542126037838574, "percentage": 57.73, "elapsed_time": "13:20:01", "remaining_time": "9:45:40", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2125, "total_steps": 3672, "loss": 0.0903, "learning_rate": 2.403458662489304e-05, "epoch": 1.1569348033210836, "percentage": 57.87, "elapsed_time": "13:21:40", "remaining_time": "9:43:36", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2130, "total_steps": 3672, "loss": 0.0793, "learning_rate": 2.3910889583031533e-05, "epoch": 1.1596570028583095, "percentage": 58.01, "elapsed_time": "13:23:25", "remaining_time": "9:41:37", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2135, "total_steps": 3672, "loss": 0.0759, "learning_rate": 2.3787219249357803e-05, "epoch": 1.1623792023955355, "percentage": 58.14, "elapsed_time": "13:25:16", "remaining_time": "9:39:43", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2140, "total_steps": 3672, "loss": 0.0783, "learning_rate": 2.3663578656631858e-05, "epoch": 1.1651014019327617, "percentage": 58.28, "elapsed_time": "13:27:01", "remaining_time": "9:37:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2145, "total_steps": 3672, "loss": 0.0816, "learning_rate": 2.3539970836884347e-05, "epoch": 1.1678236014699879, "percentage": 58.42, "elapsed_time": "13:28:50", "remaining_time": "9:35:48", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2150, "total_steps": 3672, "loss": 0.0739, "learning_rate": 2.3416398821342238e-05, "epoch": 1.1705458010072138, "percentage": 58.55, "elapsed_time": "13:30:43", "remaining_time": "9:33:55", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2155, "total_steps": 3672, "loss": 0.0764, "learning_rate": 2.329286564035446e-05, "epoch": 1.1732680005444398, "percentage": 58.69, "elapsed_time": "13:32:34", "remaining_time": "9:32:00", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2160, "total_steps": 3672, "loss": 0.0716, "learning_rate": 2.3169374323317624e-05, "epoch": 1.175990200081666, "percentage": 58.82, "elapsed_time": "13:34:30", "remaining_time": "9:30:09", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2165, "total_steps": 3672, "loss": 0.0737, "learning_rate": 2.3045927898601702e-05, "epoch": 1.1787123996188922, "percentage": 58.96, "elapsed_time": "13:36:20", "remaining_time": "9:28:14", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2170, "total_steps": 3672, "loss": 0.0674, "learning_rate": 2.292252939347577e-05, "epoch": 1.1814345991561181, "percentage": 59.1, "elapsed_time": "13:38:18", "remaining_time": "9:26:24", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2175, "total_steps": 3672, "loss": 0.0872, "learning_rate": 2.27991818340338e-05, "epoch": 1.1841567986933441, "percentage": 59.23, "elapsed_time": "13:40:12", "remaining_time": "9:24:31", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2180, "total_steps": 3672, "loss": 0.1069, "learning_rate": 2.2675888245120382e-05, "epoch": 1.1868789982305703, "percentage": 59.37, "elapsed_time": "13:42:15", "remaining_time": "9:22:45", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2185, "total_steps": 3672, "loss": 0.0753, "learning_rate": 2.255265165025663e-05, "epoch": 1.1896011977677965, "percentage": 59.5, "elapsed_time": "13:44:16", "remaining_time": "9:20:57", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2190, "total_steps": 3672, "loss": 0.0704, "learning_rate": 2.2429475071565987e-05, "epoch": 1.1923233973050225, "percentage": 59.64, "elapsed_time": "13:46:13", "remaining_time": "9:19:07", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2195, "total_steps": 3672, "loss": 0.081, "learning_rate": 2.2306361529700125e-05, "epoch": 1.1950455968422484, "percentage": 59.78, "elapsed_time": "13:48:11", "remaining_time": "9:17:17", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2200, "total_steps": 3672, "loss": 0.0813, "learning_rate": 2.218331404376484e-05, "epoch": 1.1977677963794746, "percentage": 59.91, "elapsed_time": "13:50:12", "remaining_time": "9:15:29", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2205, "total_steps": 3672, "loss": 0.0793, "learning_rate": 2.2060335631246075e-05, "epoch": 1.2004899959167008, "percentage": 60.05, "elapsed_time": "13:52:10", "remaining_time": "9:13:39", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2210, "total_steps": 3672, "loss": 0.0763, "learning_rate": 2.1937429307935887e-05, "epoch": 1.2032121954539268, "percentage": 60.19, "elapsed_time": "13:54:10", "remaining_time": "9:11:50", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2215, "total_steps": 3672, "loss": 0.0882, "learning_rate": 2.1814598087858476e-05, "epoch": 1.2059343949911527, "percentage": 60.32, "elapsed_time": "13:56:06", "remaining_time": "9:09:58", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2220, "total_steps": 3672, "loss": 0.0762, "learning_rate": 2.16918449831963e-05, "epoch": 1.208656594528379, "percentage": 60.46, "elapsed_time": "13:58:06", "remaining_time": "9:08:10", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2225, "total_steps": 3672, "loss": 0.0802, "learning_rate": 2.15691730042162e-05, "epoch": 1.2113787940656051, "percentage": 60.59, "elapsed_time": "14:00:05", "remaining_time": "9:06:20", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2230, "total_steps": 3672, "loss": 0.071, "learning_rate": 2.144658515919557e-05, "epoch": 1.214100993602831, "percentage": 60.73, "elapsed_time": "14:02:03", "remaining_time": "9:04:30", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2235, "total_steps": 3672, "loss": 0.069, "learning_rate": 2.1324084454348592e-05, "epoch": 1.216823193140057, "percentage": 60.87, "elapsed_time": "14:04:06", "remaining_time": "9:02:43", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2240, "total_steps": 3672, "loss": 0.0793, "learning_rate": 2.1201673893752534e-05, "epoch": 1.2195453926772832, "percentage": 61.0, "elapsed_time": "14:06:03", "remaining_time": "9:00:52", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2245, "total_steps": 3672, "loss": 0.0653, "learning_rate": 2.107935647927404e-05, "epoch": 1.2222675922145094, "percentage": 61.14, "elapsed_time": "14:07:56", "remaining_time": "8:58:58", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2250, "total_steps": 3672, "loss": 0.0726, "learning_rate": 2.095713521049554e-05, "epoch": 1.2249897917517354, "percentage": 61.27, "elapsed_time": "14:10:00", "remaining_time": "8:57:12", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2255, "total_steps": 3672, "loss": 0.0781, "learning_rate": 2.0835013084641704e-05, "epoch": 1.2277119912889614, "percentage": 61.41, "elapsed_time": "14:11:59", "remaining_time": "8:55:22", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2260, "total_steps": 3672, "loss": 0.0754, "learning_rate": 2.07129930965059e-05, "epoch": 1.2304341908261875, "percentage": 61.55, "elapsed_time": "14:13:52", "remaining_time": "8:53:29", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2265, "total_steps": 3672, "loss": 0.1275, "learning_rate": 2.0591078238376803e-05, "epoch": 1.2331563903634137, "percentage": 61.68, "elapsed_time": "14:15:50", "remaining_time": "8:51:38", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2270, "total_steps": 3672, "loss": 0.0738, "learning_rate": 2.0469271499964993e-05, "epoch": 1.2358785899006397, "percentage": 61.82, "elapsed_time": "14:17:47", "remaining_time": "8:49:47", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2275, "total_steps": 3672, "loss": 0.0719, "learning_rate": 2.034757586832961e-05, "epoch": 1.238600789437866, "percentage": 61.96, "elapsed_time": "14:19:42", "remaining_time": "8:47:55", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2280, "total_steps": 3672, "loss": 0.0793, "learning_rate": 2.022599432780515e-05, "epoch": 1.2413229889750919, "percentage": 62.09, "elapsed_time": "14:21:38", "remaining_time": "8:46:03", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2285, "total_steps": 3672, "loss": 0.0754, "learning_rate": 2.0104529859928254e-05, "epoch": 1.244045188512318, "percentage": 62.23, "elapsed_time": "14:23:34", "remaining_time": "8:44:11", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2290, "total_steps": 3672, "loss": 0.0679, "learning_rate": 1.9983185443364615e-05, "epoch": 1.246767388049544, "percentage": 62.36, "elapsed_time": "14:25:32", "remaining_time": "8:42:20", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2295, "total_steps": 3672, "loss": 0.0778, "learning_rate": 1.9861964053835885e-05, "epoch": 1.2494895875867702, "percentage": 62.5, "elapsed_time": "14:27:30", "remaining_time": "8:40:30", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2300, "total_steps": 3672, "loss": 0.0874, "learning_rate": 1.974086866404675e-05, "epoch": 1.2522117871239962, "percentage": 62.64, "elapsed_time": "14:29:26", "remaining_time": "8:38:38", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2305, "total_steps": 3672, "loss": 0.0708, "learning_rate": 1.961990224361201e-05, "epoch": 1.2549339866612224, "percentage": 62.77, "elapsed_time": "14:31:21", "remaining_time": "8:36:46", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2310, "total_steps": 3672, "loss": 0.0841, "learning_rate": 1.949906775898375e-05, "epoch": 1.2576561861984483, "percentage": 62.91, "elapsed_time": "14:33:20", "remaining_time": "8:34:55", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2315, "total_steps": 3672, "loss": 0.0802, "learning_rate": 1.9378368173378618e-05, "epoch": 1.2603783857356743, "percentage": 63.04, "elapsed_time": "14:35:19", "remaining_time": "8:33:05", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2320, "total_steps": 3672, "loss": 0.0675, "learning_rate": 1.9257806446705116e-05, "epoch": 1.2631005852729005, "percentage": 63.18, "elapsed_time": "14:37:12", "remaining_time": "8:31:12", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2325, "total_steps": 3672, "loss": 0.0848, "learning_rate": 1.913738553549106e-05, "epoch": 1.2658227848101267, "percentage": 63.32, "elapsed_time": "14:39:07", "remaining_time": "8:29:19", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2330, "total_steps": 3672, "loss": 0.0687, "learning_rate": 1.9017108392811065e-05, "epoch": 1.2685449843473526, "percentage": 63.45, "elapsed_time": "14:41:03", "remaining_time": "8:27:27", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2335, "total_steps": 3672, "loss": 0.113, "learning_rate": 1.8896977968214078e-05, "epoch": 1.2712671838845788, "percentage": 63.59, "elapsed_time": "14:42:55", "remaining_time": "8:25:33", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2340, "total_steps": 3672, "loss": 0.0771, "learning_rate": 1.877699720765114e-05, "epoch": 1.2739893834218048, "percentage": 63.73, "elapsed_time": "14:44:42", "remaining_time": "8:23:36", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2345, "total_steps": 3672, "loss": 0.0771, "learning_rate": 1.8657169053403052e-05, "epoch": 1.276711582959031, "percentage": 63.86, "elapsed_time": "14:46:39", "remaining_time": "8:21:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2350, "total_steps": 3672, "loss": 0.07, "learning_rate": 1.8537496444008283e-05, "epoch": 1.279433782496257, "percentage": 64.0, "elapsed_time": "14:48:33", "remaining_time": "8:19:51", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2355, "total_steps": 3672, "loss": 0.0815, "learning_rate": 1.841798231419087e-05, "epoch": 1.2821559820334831, "percentage": 64.13, "elapsed_time": "14:50:26", "remaining_time": "8:17:57", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2360, "total_steps": 3672, "loss": 0.0689, "learning_rate": 1.8298629594788467e-05, "epoch": 1.284878181570709, "percentage": 64.27, "elapsed_time": "14:52:14", "remaining_time": "8:16:01", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2365, "total_steps": 3672, "loss": 0.0728, "learning_rate": 1.817944121268048e-05, "epoch": 1.2876003811079353, "percentage": 64.41, "elapsed_time": "14:54:00", "remaining_time": "8:14:03", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2370, "total_steps": 3672, "loss": 0.0789, "learning_rate": 1.8060420090716265e-05, "epoch": 1.2903225806451613, "percentage": 64.54, "elapsed_time": "14:55:40", "remaining_time": "8:12:03", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2375, "total_steps": 3672, "loss": 0.0702, "learning_rate": 1.794156914764349e-05, "epoch": 1.2930447801823874, "percentage": 64.68, "elapsed_time": "14:57:19", "remaining_time": "8:10:02", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2380, "total_steps": 3672, "loss": 0.0781, "learning_rate": 1.7822891298036515e-05, "epoch": 1.2957669797196134, "percentage": 64.81, "elapsed_time": "14:58:57", "remaining_time": "8:08:00", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2385, "total_steps": 3672, "loss": 0.0805, "learning_rate": 1.7704389452224944e-05, "epoch": 1.2984891792568396, "percentage": 64.95, "elapsed_time": "15:00:33", "remaining_time": "8:05:57", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2390, "total_steps": 3672, "loss": 0.0768, "learning_rate": 1.7586066516222276e-05, "epoch": 1.3012113787940656, "percentage": 65.09, "elapsed_time": "15:02:10", "remaining_time": "8:03:55", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2395, "total_steps": 3672, "loss": 0.0825, "learning_rate": 1.7467925391654585e-05, "epoch": 1.3039335783312918, "percentage": 65.22, "elapsed_time": "15:03:46", "remaining_time": "8:01:53", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2400, "total_steps": 3672, "loss": 0.0823, "learning_rate": 1.73499689756894e-05, "epoch": 1.3066557778685177, "percentage": 65.36, "elapsed_time": "15:05:24", "remaining_time": "7:59:51", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2405, "total_steps": 3672, "loss": 0.0832, "learning_rate": 1.7232200160964657e-05, "epoch": 1.309377977405744, "percentage": 65.5, "elapsed_time": "15:07:05", "remaining_time": "7:57:52", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2410, "total_steps": 3672, "loss": 0.0791, "learning_rate": 1.7114621835517773e-05, "epoch": 1.3121001769429699, "percentage": 65.63, "elapsed_time": "15:08:40", "remaining_time": "7:55:49", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2415, "total_steps": 3672, "loss": 0.0703, "learning_rate": 1.699723688271477e-05, "epoch": 1.314822376480196, "percentage": 65.77, "elapsed_time": "15:10:21", "remaining_time": "7:53:50", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2420, "total_steps": 3672, "loss": 0.0797, "learning_rate": 1.6880048181179652e-05, "epoch": 1.317544576017422, "percentage": 65.9, "elapsed_time": "15:11:55", "remaining_time": "7:51:47", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2425, "total_steps": 3672, "loss": 0.0727, "learning_rate": 1.6763058604723723e-05, "epoch": 1.3202667755546482, "percentage": 66.04, "elapsed_time": "15:13:35", "remaining_time": "7:49:47", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2430, "total_steps": 3672, "loss": 0.066, "learning_rate": 1.6646271022275185e-05, "epoch": 1.3229889750918742, "percentage": 66.18, "elapsed_time": "15:15:11", "remaining_time": "7:47:45", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2435, "total_steps": 3672, "loss": 0.078, "learning_rate": 1.6529688297808726e-05, "epoch": 1.3257111746291004, "percentage": 66.31, "elapsed_time": "15:16:46", "remaining_time": "7:45:43", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2440, "total_steps": 3672, "loss": 0.0779, "learning_rate": 1.6413313290275355e-05, "epoch": 1.3284333741663263, "percentage": 66.45, "elapsed_time": "15:18:21", "remaining_time": "7:43:41", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2445, "total_steps": 3672, "loss": 0.0835, "learning_rate": 1.629714885353221e-05, "epoch": 1.3311555737035525, "percentage": 66.58, "elapsed_time": "15:19:56", "remaining_time": "7:41:40", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2450, "total_steps": 3672, "loss": 0.0759, "learning_rate": 1.618119783627263e-05, "epoch": 1.3338777732407785, "percentage": 66.72, "elapsed_time": "15:21:32", "remaining_time": "7:39:38", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2455, "total_steps": 3672, "loss": 0.0745, "learning_rate": 1.6065463081956292e-05, "epoch": 1.3365999727780047, "percentage": 66.86, "elapsed_time": "15:23:07", "remaining_time": "7:37:37", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2460, "total_steps": 3672, "loss": 0.084, "learning_rate": 1.5949947428739448e-05, "epoch": 1.3393221723152307, "percentage": 66.99, "elapsed_time": "15:24:44", "remaining_time": "7:35:36", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2465, "total_steps": 3672, "loss": 0.0707, "learning_rate": 1.5834653709405368e-05, "epoch": 1.3420443718524568, "percentage": 67.13, "elapsed_time": "15:26:30", "remaining_time": "7:33:40", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2470, "total_steps": 3672, "loss": 0.0701, "learning_rate": 1.571958475129484e-05, "epoch": 1.3447665713896828, "percentage": 67.27, "elapsed_time": "15:28:08", "remaining_time": "7:31:40", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2475, "total_steps": 3672, "loss": 0.0708, "learning_rate": 1.5604743376236847e-05, "epoch": 1.347488770926909, "percentage": 67.4, "elapsed_time": "15:29:50", "remaining_time": "7:29:42", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2480, "total_steps": 3672, "loss": 0.0731, "learning_rate": 1.549013240047937e-05, "epoch": 1.350210970464135, "percentage": 67.54, "elapsed_time": "15:31:24", "remaining_time": "7:27:40", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2485, "total_steps": 3672, "loss": 0.0712, "learning_rate": 1.537575463462031e-05, "epoch": 1.3529331700013612, "percentage": 67.67, "elapsed_time": "15:33:07", "remaining_time": "7:25:43", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2490, "total_steps": 3672, "loss": 0.0825, "learning_rate": 1.526161288353861e-05, "epoch": 1.3556553695385871, "percentage": 67.81, "elapsed_time": "15:34:48", "remaining_time": "7:23:45", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2495, "total_steps": 3672, "loss": 0.0769, "learning_rate": 1.5147709946325395e-05, "epoch": 1.3583775690758133, "percentage": 67.95, "elapsed_time": "15:36:37", "remaining_time": "7:21:50", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2500, "total_steps": 3672, "loss": 0.0737, "learning_rate": 1.5034048616215402e-05, "epoch": 1.3610997686130393, "percentage": 68.08, "elapsed_time": "15:38:22", "remaining_time": "7:19:54", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2500, "total_steps": 3672, "eval_loss": 0.07860012352466583, "epoch": 1.3610997686130393, "percentage": 68.08, "elapsed_time": "15:42:30", "remaining_time": "7:21:51", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2505, "total_steps": 3672, "loss": 0.0695, "learning_rate": 1.4920631680518432e-05, "epoch": 1.3638219681502655, "percentage": 68.22, "elapsed_time": "15:44:13", "remaining_time": "7:19:53", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2510, "total_steps": 3672, "loss": 0.0752, "learning_rate": 1.4807461920551028e-05, "epoch": 1.3665441676874914, "percentage": 68.36, "elapsed_time": "15:46:10", "remaining_time": "7:18:01", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2515, "total_steps": 3672, "loss": 0.0698, "learning_rate": 1.469454211156826e-05, "epoch": 1.3692663672247176, "percentage": 68.49, "elapsed_time": "15:48:06", "remaining_time": "7:16:09", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2520, "total_steps": 3672, "loss": 0.0897, "learning_rate": 1.4581875022695653e-05, "epoch": 1.3719885667619436, "percentage": 68.63, "elapsed_time": "15:49:59", "remaining_time": "7:14:16", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2525, "total_steps": 3672, "loss": 0.0751, "learning_rate": 1.4469463416861307e-05, "epoch": 1.3747107662991698, "percentage": 68.76, "elapsed_time": "15:51:58", "remaining_time": "7:12:26", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2530, "total_steps": 3672, "loss": 0.0807, "learning_rate": 1.4357310050728115e-05, "epoch": 1.3774329658363957, "percentage": 68.9, "elapsed_time": "15:53:49", "remaining_time": "7:10:32", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2535, "total_steps": 3672, "loss": 0.0693, "learning_rate": 1.4245417674626183e-05, "epoch": 1.380155165373622, "percentage": 69.04, "elapsed_time": "15:55:43", "remaining_time": "7:08:39", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2540, "total_steps": 3672, "loss": 0.0739, "learning_rate": 1.4133789032485367e-05, "epoch": 1.382877364910848, "percentage": 69.17, "elapsed_time": "15:57:38", "remaining_time": "7:06:47", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2545, "total_steps": 3672, "loss": 0.0806, "learning_rate": 1.4022426861767998e-05, "epoch": 1.385599564448074, "percentage": 69.31, "elapsed_time": "15:59:27", "remaining_time": "7:04:52", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2550, "total_steps": 3672, "loss": 0.0737, "learning_rate": 1.391133389340174e-05, "epoch": 1.3883217639853, "percentage": 69.44, "elapsed_time": "16:01:27", "remaining_time": "7:03:02", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2555, "total_steps": 3672, "loss": 0.0746, "learning_rate": 1.3800512851712635e-05, "epoch": 1.3910439635225262, "percentage": 69.58, "elapsed_time": "16:03:17", "remaining_time": "7:01:08", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2560, "total_steps": 3672, "loss": 0.0768, "learning_rate": 1.3689966454358256e-05, "epoch": 1.3937661630597522, "percentage": 69.72, "elapsed_time": "16:05:11", "remaining_time": "6:59:15", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2565, "total_steps": 3672, "loss": 0.0724, "learning_rate": 1.3579697412261117e-05, "epoch": 1.3964883625969784, "percentage": 69.85, "elapsed_time": "16:07:00", "remaining_time": "6:57:20", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2570, "total_steps": 3672, "loss": 0.0738, "learning_rate": 1.3469708429542157e-05, "epoch": 1.3992105621342044, "percentage": 69.99, "elapsed_time": "16:08:55", "remaining_time": "6:55:27", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2575, "total_steps": 3672, "loss": 0.0739, "learning_rate": 1.3360002203454442e-05, "epoch": 1.4019327616714305, "percentage": 70.13, "elapsed_time": "16:10:44", "remaining_time": "6:53:33", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2580, "total_steps": 3672, "loss": 0.0732, "learning_rate": 1.325058142431701e-05, "epoch": 1.4046549612086565, "percentage": 70.26, "elapsed_time": "16:12:34", "remaining_time": "6:51:39", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2585, "total_steps": 3672, "loss": 0.0781, "learning_rate": 1.3141448775448875e-05, "epoch": 1.4073771607458827, "percentage": 70.4, "elapsed_time": "16:14:28", "remaining_time": "6:49:46", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2590, "total_steps": 3672, "loss": 0.0742, "learning_rate": 1.3032606933103305e-05, "epoch": 1.4100993602831087, "percentage": 70.53, "elapsed_time": "16:16:15", "remaining_time": "6:47:50", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2595, "total_steps": 3672, "loss": 0.0761, "learning_rate": 1.2924058566402098e-05, "epoch": 1.4128215598203349, "percentage": 70.67, "elapsed_time": "16:18:08", "remaining_time": "6:45:57", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2600, "total_steps": 3672, "loss": 0.0693, "learning_rate": 1.2815806337270186e-05, "epoch": 1.4155437593575608, "percentage": 70.81, "elapsed_time": "16:19:58", "remaining_time": "6:44:02", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2605, "total_steps": 3672, "loss": 0.0771, "learning_rate": 1.270785290037031e-05, "epoch": 1.418265958894787, "percentage": 70.94, "elapsed_time": "16:21:48", "remaining_time": "6:42:08", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2610, "total_steps": 3672, "loss": 0.1018, "learning_rate": 1.260020090303797e-05, "epoch": 1.4209881584320132, "percentage": 71.08, "elapsed_time": "16:23:37", "remaining_time": "6:40:14", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2615, "total_steps": 3672, "loss": 0.0708, "learning_rate": 1.2492852985216483e-05, "epoch": 1.4237103579692392, "percentage": 71.21, "elapsed_time": "16:25:28", "remaining_time": "6:38:20", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2620, "total_steps": 3672, "loss": 0.0795, "learning_rate": 1.2385811779392236e-05, "epoch": 1.4264325575064651, "percentage": 71.35, "elapsed_time": "16:27:18", "remaining_time": "6:36:25", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2625, "total_steps": 3672, "loss": 0.0811, "learning_rate": 1.2279079910530147e-05, "epoch": 1.4291547570436913, "percentage": 71.49, "elapsed_time": "16:29:11", "remaining_time": "6:34:32", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2630, "total_steps": 3672, "loss": 0.0762, "learning_rate": 1.2172659996009254e-05, "epoch": 1.4318769565809175, "percentage": 71.62, "elapsed_time": "16:30:57", "remaining_time": "6:32:37", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2635, "total_steps": 3672, "loss": 0.0739, "learning_rate": 1.2066554645558578e-05, "epoch": 1.4345991561181435, "percentage": 71.76, "elapsed_time": "16:32:51", "remaining_time": "6:30:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2640, "total_steps": 3672, "loss": 0.0663, "learning_rate": 1.1960766461193124e-05, "epoch": 1.4373213556553694, "percentage": 71.9, "elapsed_time": "16:34:41", "remaining_time": "6:28:50", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2645, "total_steps": 3672, "loss": 0.073, "learning_rate": 1.1855298037150022e-05, "epoch": 1.4400435551925956, "percentage": 72.03, "elapsed_time": "16:36:37", "remaining_time": "6:26:57", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2650, "total_steps": 3672, "loss": 0.0746, "learning_rate": 1.1750151959824961e-05, "epoch": 1.4427657547298218, "percentage": 72.17, "elapsed_time": "16:38:27", "remaining_time": "6:25:03", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2655, "total_steps": 3672, "loss": 0.0687, "learning_rate": 1.1645330807708713e-05, "epoch": 1.4454879542670478, "percentage": 72.3, "elapsed_time": "16:40:22", "remaining_time": "6:23:11", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2660, "total_steps": 3672, "loss": 0.0814, "learning_rate": 1.1540837151323951e-05, "epoch": 1.4482101538042738, "percentage": 72.44, "elapsed_time": "16:42:13", "remaining_time": "6:21:17", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2665, "total_steps": 3672, "loss": 0.0768, "learning_rate": 1.143667355316219e-05, "epoch": 1.4509323533415, "percentage": 72.58, "elapsed_time": "16:44:08", "remaining_time": "6:19:25", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2670, "total_steps": 3672, "loss": 0.0731, "learning_rate": 1.1332842567620941e-05, "epoch": 1.4536545528787261, "percentage": 72.71, "elapsed_time": "16:45:59", "remaining_time": "6:17:31", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2675, "total_steps": 3672, "loss": 0.0893, "learning_rate": 1.1229346740941088e-05, "epoch": 1.456376752415952, "percentage": 72.85, "elapsed_time": "16:47:54", "remaining_time": "6:15:39", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2680, "total_steps": 3672, "loss": 0.0981, "learning_rate": 1.1126188611144406e-05, "epoch": 1.459098951953178, "percentage": 72.98, "elapsed_time": "16:49:42", "remaining_time": "6:13:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2685, "total_steps": 3672, "loss": 0.0775, "learning_rate": 1.102337070797137e-05, "epoch": 1.4618211514904043, "percentage": 73.12, "elapsed_time": "16:51:29", "remaining_time": "6:11:49", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2690, "total_steps": 3672, "loss": 0.0828, "learning_rate": 1.0920895552819118e-05, "epoch": 1.4645433510276304, "percentage": 73.26, "elapsed_time": "16:53:18", "remaining_time": "6:09:54", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2695, "total_steps": 3672, "loss": 0.0766, "learning_rate": 1.0818765658679576e-05, "epoch": 1.4672655505648564, "percentage": 73.39, "elapsed_time": "16:55:03", "remaining_time": "6:07:58", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2700, "total_steps": 3672, "loss": 0.0776, "learning_rate": 1.0716983530077843e-05, "epoch": 1.4699877501020824, "percentage": 73.53, "elapsed_time": "16:56:52", "remaining_time": "6:06:04", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2705, "total_steps": 3672, "loss": 0.0689, "learning_rate": 1.0615551663010806e-05, "epoch": 1.4727099496393086, "percentage": 73.67, "elapsed_time": "16:58:36", "remaining_time": "6:04:08", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2710, "total_steps": 3672, "loss": 0.0634, "learning_rate": 1.051447254488591e-05, "epoch": 1.4754321491765348, "percentage": 73.8, "elapsed_time": "17:00:14", "remaining_time": "6:02:10", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2715, "total_steps": 3672, "loss": 0.0796, "learning_rate": 1.0413748654460149e-05, "epoch": 1.4781543487137607, "percentage": 73.94, "elapsed_time": "17:01:51", "remaining_time": "6:00:11", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2720, "total_steps": 3672, "loss": 0.0755, "learning_rate": 1.0313382461779306e-05, "epoch": 1.4808765482509867, "percentage": 74.07, "elapsed_time": "17:03:27", "remaining_time": "5:58:12", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2725, "total_steps": 3672, "loss": 0.0658, "learning_rate": 1.0213376428117333e-05, "epoch": 1.4835987477882129, "percentage": 74.21, "elapsed_time": "17:05:03", "remaining_time": "5:56:13", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2730, "total_steps": 3672, "loss": 0.075, "learning_rate": 1.0113733005916057e-05, "epoch": 1.486320947325439, "percentage": 74.35, "elapsed_time": "17:06:39", "remaining_time": "5:54:15", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2735, "total_steps": 3672, "loss": 0.0774, "learning_rate": 1.0014454638724982e-05, "epoch": 1.489043146862665, "percentage": 74.48, "elapsed_time": "17:08:15", "remaining_time": "5:52:16", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2740, "total_steps": 3672, "loss": 0.074, "learning_rate": 9.915543761141432e-06, "epoch": 1.491765346399891, "percentage": 74.62, "elapsed_time": "17:09:50", "remaining_time": "5:50:17", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2745, "total_steps": 3672, "loss": 0.0796, "learning_rate": 9.81700279875075e-06, "epoch": 1.4944875459371172, "percentage": 74.75, "elapsed_time": "17:11:26", "remaining_time": "5:48:19", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2750, "total_steps": 3672, "loss": 0.0713, "learning_rate": 9.718834168066904e-06, "epoch": 1.4972097454743434, "percentage": 74.89, "elapsed_time": "17:13:01", "remaining_time": "5:46:20", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2755, "total_steps": 3672, "loss": 0.077, "learning_rate": 9.62104027647319e-06, "epoch": 1.4999319450115693, "percentage": 75.03, "elapsed_time": "17:14:37", "remaining_time": "5:44:22", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2760, "total_steps": 3672, "loss": 0.0719, "learning_rate": 9.523623522163197e-06, "epoch": 1.5026541445487953, "percentage": 75.16, "elapsed_time": "17:16:12", "remaining_time": "5:42:23", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2765, "total_steps": 3672, "loss": 0.0776, "learning_rate": 9.426586294082013e-06, "epoch": 1.5053763440860215, "percentage": 75.3, "elapsed_time": "17:17:47", "remaining_time": "5:40:25", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2770, "total_steps": 3672, "loss": 0.0771, "learning_rate": 9.329930971867595e-06, "epoch": 1.5080985436232477, "percentage": 75.44, "elapsed_time": "17:19:22", "remaining_time": "5:38:27", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2775, "total_steps": 3672, "loss": 0.072, "learning_rate": 9.233659925792477e-06, "epoch": 1.5108207431604737, "percentage": 75.57, "elapsed_time": "17:20:58", "remaining_time": "5:36:29", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2780, "total_steps": 3672, "loss": 0.0758, "learning_rate": 9.137775516705604e-06, "epoch": 1.5135429426976996, "percentage": 75.71, "elapsed_time": "17:22:33", "remaining_time": "5:34:31", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2785, "total_steps": 3672, "loss": 0.0844, "learning_rate": 9.042280095974434e-06, "epoch": 1.5162651422349258, "percentage": 75.84, "elapsed_time": "17:24:08", "remaining_time": "5:32:33", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2790, "total_steps": 3672, "loss": 0.0798, "learning_rate": 8.947176005427324e-06, "epoch": 1.518987341772152, "percentage": 75.98, "elapsed_time": "17:25:43", "remaining_time": "5:30:35", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2795, "total_steps": 3672, "loss": 0.0761, "learning_rate": 8.852465577296015e-06, "epoch": 1.521709541309378, "percentage": 76.12, "elapsed_time": "17:27:18", "remaining_time": "5:28:37", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2800, "total_steps": 3672, "loss": 0.0753, "learning_rate": 8.75815113415852e-06, "epoch": 1.524431740846604, "percentage": 76.25, "elapsed_time": "17:28:54", "remaining_time": "5:26:39", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2805, "total_steps": 3672, "loss": 0.0764, "learning_rate": 8.66423498888213e-06, "epoch": 1.5271539403838301, "percentage": 76.39, "elapsed_time": "17:30:29", "remaining_time": "5:24:41", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2810, "total_steps": 3672, "loss": 0.0733, "learning_rate": 8.570719444566702e-06, "epoch": 1.5298761399210563, "percentage": 76.53, "elapsed_time": "17:32:04", "remaining_time": "5:22:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2815, "total_steps": 3672, "loss": 0.0839, "learning_rate": 8.477606794488183e-06, "epoch": 1.5325983394582823, "percentage": 76.66, "elapsed_time": "17:33:39", "remaining_time": "5:20:46", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2820, "total_steps": 3672, "loss": 0.0837, "learning_rate": 8.384899322042356e-06, "epoch": 1.5353205389955082, "percentage": 76.8, "elapsed_time": "17:35:15", "remaining_time": "5:18:49", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2825, "total_steps": 3672, "loss": 0.0775, "learning_rate": 8.29259930068887e-06, "epoch": 1.5380427385327344, "percentage": 76.93, "elapsed_time": "17:36:50", "remaining_time": "5:16:51", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2830, "total_steps": 3672, "loss": 0.0744, "learning_rate": 8.200708993895476e-06, "epoch": 1.5407649380699606, "percentage": 77.07, "elapsed_time": "17:38:25", "remaining_time": "5:14:54", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2835, "total_steps": 3672, "loss": 0.0795, "learning_rate": 8.109230655082517e-06, "epoch": 1.5434871376071866, "percentage": 77.21, "elapsed_time": "17:40:00", "remaining_time": "5:12:57", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2840, "total_steps": 3672, "loss": 0.0675, "learning_rate": 8.018166527567672e-06, "epoch": 1.5462093371444126, "percentage": 77.34, "elapsed_time": "17:41:35", "remaining_time": "5:11:00", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2845, "total_steps": 3672, "loss": 0.0703, "learning_rate": 7.927518844510941e-06, "epoch": 1.5489315366816387, "percentage": 77.48, "elapsed_time": "17:43:11", "remaining_time": "5:09:03", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2850, "total_steps": 3672, "loss": 0.0742, "learning_rate": 7.837289828859884e-06, "epoch": 1.551653736218865, "percentage": 77.61, "elapsed_time": "17:44:46", "remaining_time": "5:07:06", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2855, "total_steps": 3672, "loss": 0.0699, "learning_rate": 7.7474816932951e-06, "epoch": 1.554375935756091, "percentage": 77.75, "elapsed_time": "17:46:25", "remaining_time": "5:05:10", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2860, "total_steps": 3672, "loss": 0.0777, "learning_rate": 7.658096640175985e-06, "epoch": 1.5570981352933169, "percentage": 77.89, "elapsed_time": "17:48:01", "remaining_time": "5:03:13", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2865, "total_steps": 3672, "loss": 0.0648, "learning_rate": 7.569136861486686e-06, "epoch": 1.559820334830543, "percentage": 78.02, "elapsed_time": "17:49:38", "remaining_time": "5:01:17", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2870, "total_steps": 3672, "loss": 0.0713, "learning_rate": 7.4806045387823935e-06, "epoch": 1.5625425343677692, "percentage": 78.16, "elapsed_time": "17:51:21", "remaining_time": "4:59:22", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2875, "total_steps": 3672, "loss": 0.0649, "learning_rate": 7.392501843135816e-06, "epoch": 1.5652647339049952, "percentage": 78.3, "elapsed_time": "17:52:56", "remaining_time": "4:57:26", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2880, "total_steps": 3672, "loss": 0.0724, "learning_rate": 7.304830935083934e-06, "epoch": 1.5679869334422212, "percentage": 78.43, "elapsed_time": "17:54:43", "remaining_time": "4:55:32", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2885, "total_steps": 3672, "loss": 0.0695, "learning_rate": 7.2175939645750454e-06, "epoch": 1.5707091329794474, "percentage": 78.57, "elapsed_time": "17:56:22", "remaining_time": "4:53:37", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2890, "total_steps": 3672, "loss": 0.0762, "learning_rate": 7.130793070916006e-06, "epoch": 1.5734313325166736, "percentage": 78.7, "elapsed_time": "17:58:02", "remaining_time": "4:51:42", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2895, "total_steps": 3672, "loss": 0.0698, "learning_rate": 7.0444303827197994e-06, "epoch": 1.5761535320538995, "percentage": 78.84, "elapsed_time": "17:59:51", "remaining_time": "4:49:49", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2900, "total_steps": 3672, "loss": 0.0729, "learning_rate": 6.9585080178533155e-06, "epoch": 1.5788757315911255, "percentage": 78.98, "elapsed_time": "18:01:36", "remaining_time": "4:47:55", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2905, "total_steps": 3672, "loss": 0.0681, "learning_rate": 6.873028083385435e-06, "epoch": 1.5815979311283517, "percentage": 79.11, "elapsed_time": "18:03:24", "remaining_time": "4:46:02", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2910, "total_steps": 3672, "loss": 0.0803, "learning_rate": 6.787992675535318e-06, "epoch": 1.5843201306655779, "percentage": 79.25, "elapsed_time": "18:05:14", "remaining_time": "4:44:10", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2915, "total_steps": 3672, "loss": 0.0719, "learning_rate": 6.703403879621048e-06, "epoch": 1.5870423302028038, "percentage": 79.38, "elapsed_time": "18:07:05", "remaining_time": "4:42:18", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2920, "total_steps": 3672, "loss": 0.0764, "learning_rate": 6.619263770008471e-06, "epoch": 1.5897645297400298, "percentage": 79.52, "elapsed_time": "18:08:53", "remaining_time": "4:40:25", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2925, "total_steps": 3672, "loss": 0.0777, "learning_rate": 6.535574410060321e-06, "epoch": 1.592486729277256, "percentage": 79.66, "elapsed_time": "18:10:42", "remaining_time": "4:38:32", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2930, "total_steps": 3672, "loss": 0.077, "learning_rate": 6.452337852085621e-06, "epoch": 1.5952089288144822, "percentage": 79.79, "elapsed_time": "18:12:38", "remaining_time": "4:36:42", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2935, "total_steps": 3672, "loss": 0.0678, "learning_rate": 6.369556137289373e-06, "epoch": 1.5979311283517081, "percentage": 79.93, "elapsed_time": "18:14:25", "remaining_time": "4:34:49", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2940, "total_steps": 3672, "loss": 0.077, "learning_rate": 6.28723129572247e-06, "epoch": 1.600653327888934, "percentage": 80.07, "elapsed_time": "18:16:26", "remaining_time": "4:32:59", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2945, "total_steps": 3672, "loss": 0.0651, "learning_rate": 6.2053653462319475e-06, "epoch": 1.6033755274261603, "percentage": 80.2, "elapsed_time": "18:18:18", "remaining_time": "4:31:07", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2950, "total_steps": 3672, "loss": 0.0726, "learning_rate": 6.123960296411449e-06, "epoch": 1.6060977269633865, "percentage": 80.34, "elapsed_time": "18:20:08", "remaining_time": "4:29:15", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2955, "total_steps": 3672, "loss": 0.0747, "learning_rate": 6.043018142552009e-06, "epoch": 1.6088199265006125, "percentage": 80.47, "elapsed_time": "18:22:07", "remaining_time": "4:27:25", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2960, "total_steps": 3672, "loss": 0.0818, "learning_rate": 5.962540869593081e-06, "epoch": 1.6115421260378384, "percentage": 80.61, "elapsed_time": "18:24:22", "remaining_time": "4:25:38", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2965, "total_steps": 3672, "loss": 0.0724, "learning_rate": 5.882530451073886e-06, "epoch": 1.6142643255750646, "percentage": 80.75, "elapsed_time": "18:26:17", "remaining_time": "4:23:47", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2970, "total_steps": 3672, "loss": 0.0769, "learning_rate": 5.8029888490850005e-06, "epoch": 1.6169865251122908, "percentage": 80.88, "elapsed_time": "18:28:17", "remaining_time": "4:21:57", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2975, "total_steps": 3672, "loss": 0.0662, "learning_rate": 5.723918014220236e-06, "epoch": 1.6197087246495168, "percentage": 81.02, "elapsed_time": "18:30:21", "remaining_time": "4:20:08", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2980, "total_steps": 3672, "loss": 0.0938, "learning_rate": 5.645319885528824e-06, "epoch": 1.6224309241867427, "percentage": 81.15, "elapsed_time": "18:32:19", "remaining_time": "4:18:17", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2985, "total_steps": 3672, "loss": 0.0752, "learning_rate": 5.5671963904678185e-06, "epoch": 1.625153123723969, "percentage": 81.29, "elapsed_time": "18:34:14", "remaining_time": "4:16:26", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2990, "total_steps": 3672, "loss": 0.0875, "learning_rate": 5.489549444854908e-06, "epoch": 1.627875323261195, "percentage": 81.43, "elapsed_time": "18:36:14", "remaining_time": "4:14:36", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 2995, "total_steps": 3672, "loss": 0.0778, "learning_rate": 5.412380952821358e-06, "epoch": 1.630597522798421, "percentage": 81.56, "elapsed_time": "18:38:16", "remaining_time": "4:12:46", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3000, "total_steps": 3672, "loss": 0.0692, "learning_rate": 5.33569280676536e-06, "epoch": 1.633319722335647, "percentage": 81.7, "elapsed_time": "18:40:09", "remaining_time": "4:10:54", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3000, "total_steps": 3672, "eval_loss": 0.07731131464242935, "epoch": 1.633319722335647, "percentage": 81.7, "elapsed_time": "18:44:32", "remaining_time": "4:11:53", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3005, "total_steps": 3672, "loss": 0.068, "learning_rate": 5.259486887305592e-06, "epoch": 1.6360419218728732, "percentage": 81.84, "elapsed_time": "18:46:27", "remaining_time": "4:10:01", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3010, "total_steps": 3672, "loss": 0.0727, "learning_rate": 5.183765063235138e-06, "epoch": 1.6387641214100994, "percentage": 81.97, "elapsed_time": "18:48:22", "remaining_time": "4:08:10", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3015, "total_steps": 3672, "loss": 0.0794, "learning_rate": 5.108529191475636e-06, "epoch": 1.6414863209473254, "percentage": 82.11, "elapsed_time": "18:50:32", "remaining_time": "4:06:21", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3020, "total_steps": 3672, "loss": 0.072, "learning_rate": 5.033781117031738e-06, "epoch": 1.6442085204845516, "percentage": 82.24, "elapsed_time": "18:52:29", "remaining_time": "4:04:29", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3025, "total_steps": 3672, "loss": 0.0763, "learning_rate": 4.959522672945891e-06, "epoch": 1.6469307200217775, "percentage": 82.38, "elapsed_time": "18:54:28", "remaining_time": "4:02:38", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3030, "total_steps": 3672, "loss": 0.1175, "learning_rate": 4.885755680253334e-06, "epoch": 1.6496529195590037, "percentage": 82.52, "elapsed_time": "18:56:27", "remaining_time": "4:00:47", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3035, "total_steps": 3672, "loss": 0.0837, "learning_rate": 4.812481947937497e-06, "epoch": 1.65237511909623, "percentage": 82.65, "elapsed_time": "18:58:22", "remaining_time": "3:58:55", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3040, "total_steps": 3672, "loss": 0.0738, "learning_rate": 4.739703272885626e-06, "epoch": 1.6550973186334559, "percentage": 82.79, "elapsed_time": "19:00:16", "remaining_time": "3:57:03", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3045, "total_steps": 3672, "loss": 0.0708, "learning_rate": 4.667421439844691e-06, "epoch": 1.6578195181706818, "percentage": 82.92, "elapsed_time": "19:02:11", "remaining_time": "3:55:11", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3050, "total_steps": 3672, "loss": 0.1151, "learning_rate": 4.5956382213776295e-06, "epoch": 1.660541717707908, "percentage": 83.06, "elapsed_time": "19:04:04", "remaining_time": "3:53:19", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3055, "total_steps": 3672, "loss": 0.0831, "learning_rate": 4.524355377819897e-06, "epoch": 1.6632639172451342, "percentage": 83.2, "elapsed_time": "19:05:58", "remaining_time": "3:51:26", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3060, "total_steps": 3672, "loss": 0.0714, "learning_rate": 4.45357465723629e-06, "epoch": 1.6659861167823602, "percentage": 83.33, "elapsed_time": "19:07:54", "remaining_time": "3:49:34", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3065, "total_steps": 3672, "loss": 0.0675, "learning_rate": 4.383297795378061e-06, "epoch": 1.6687083163195862, "percentage": 83.47, "elapsed_time": "19:09:51", "remaining_time": "3:47:43", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3070, "total_steps": 3672, "loss": 0.0791, "learning_rate": 4.3135265156403756e-06, "epoch": 1.6714305158568123, "percentage": 83.61, "elapsed_time": "19:11:46", "remaining_time": "3:45:51", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3075, "total_steps": 3672, "loss": 0.0757, "learning_rate": 4.244262529020041e-06, "epoch": 1.6741527153940385, "percentage": 83.74, "elapsed_time": "19:13:45", "remaining_time": "3:43:59", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3080, "total_steps": 3672, "loss": 0.0732, "learning_rate": 4.175507534073533e-06, "epoch": 1.6768749149312645, "percentage": 83.88, "elapsed_time": "19:15:42", "remaining_time": "3:42:08", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3085, "total_steps": 3672, "loss": 0.0751, "learning_rate": 4.107263216875362e-06, "epoch": 1.6795971144684905, "percentage": 84.01, "elapsed_time": "19:17:38", "remaining_time": "3:40:16", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3090, "total_steps": 3672, "loss": 0.069, "learning_rate": 4.039531250976735e-06, "epoch": 1.6823193140057167, "percentage": 84.15, "elapsed_time": "19:19:38", "remaining_time": "3:38:25", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3095, "total_steps": 3672, "loss": 0.0708, "learning_rate": 3.972313297364494e-06, "epoch": 1.6850415135429428, "percentage": 84.29, "elapsed_time": "19:21:32", "remaining_time": "3:36:32", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3100, "total_steps": 3672, "loss": 0.0655, "learning_rate": 3.90561100442036e-06, "epoch": 1.6877637130801688, "percentage": 84.42, "elapsed_time": "19:23:33", "remaining_time": "3:34:41", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3105, "total_steps": 3672, "loss": 0.0736, "learning_rate": 3.8394260078805755e-06, "epoch": 1.6904859126173948, "percentage": 84.56, "elapsed_time": "19:25:33", "remaining_time": "3:32:50", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3110, "total_steps": 3672, "loss": 0.0669, "learning_rate": 3.7737599307957365e-06, "epoch": 1.693208112154621, "percentage": 84.69, "elapsed_time": "19:27:17", "remaining_time": "3:30:56", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3115, "total_steps": 3672, "loss": 0.0737, "learning_rate": 3.708614383491016e-06, "epoch": 1.6959303116918472, "percentage": 84.83, "elapsed_time": "19:29:10", "remaining_time": "3:29:03", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3120, "total_steps": 3672, "loss": 0.0627, "learning_rate": 3.643990963526672e-06, "epoch": 1.6986525112290731, "percentage": 84.97, "elapsed_time": "19:30:58", "remaining_time": "3:27:10", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3125, "total_steps": 3672, "loss": 0.0757, "learning_rate": 3.579891255658846e-06, "epoch": 1.701374710766299, "percentage": 85.1, "elapsed_time": "19:32:47", "remaining_time": "3:25:17", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3130, "total_steps": 3672, "loss": 0.1398, "learning_rate": 3.5163168318007365e-06, "epoch": 1.7040969103035253, "percentage": 85.24, "elapsed_time": "19:34:40", "remaining_time": "3:23:24", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3135, "total_steps": 3672, "loss": 0.0723, "learning_rate": 3.4532692509840313e-06, "epoch": 1.7068191098407515, "percentage": 85.38, "elapsed_time": "19:36:34", "remaining_time": "3:21:32", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3140, "total_steps": 3672, "loss": 0.0789, "learning_rate": 3.390750059320688e-06, "epoch": 1.7095413093779774, "percentage": 85.51, "elapsed_time": "19:38:24", "remaining_time": "3:19:39", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3145, "total_steps": 3672, "loss": 0.0728, "learning_rate": 3.328760789964988e-06, "epoch": 1.7122635089152034, "percentage": 85.65, "elapsed_time": "19:40:25", "remaining_time": "3:17:48", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3150, "total_steps": 3672, "loss": 0.0694, "learning_rate": 3.2673029630759745e-06, "epoch": 1.7149857084524296, "percentage": 85.78, "elapsed_time": "19:42:20", "remaining_time": "3:15:55", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3155, "total_steps": 3672, "loss": 0.0726, "learning_rate": 3.2063780857801596e-06, "epoch": 1.7177079079896558, "percentage": 85.92, "elapsed_time": "19:44:13", "remaining_time": "3:14:03", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3160, "total_steps": 3672, "loss": 0.0666, "learning_rate": 3.145987652134563e-06, "epoch": 1.7204301075268817, "percentage": 86.06, "elapsed_time": "19:46:14", "remaining_time": "3:12:12", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3165, "total_steps": 3672, "loss": 0.0788, "learning_rate": 3.0861331430900807e-06, "epoch": 1.7231523070641077, "percentage": 86.19, "elapsed_time": "19:48:05", "remaining_time": "3:10:19", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3170, "total_steps": 3672, "loss": 0.0701, "learning_rate": 3.0268160264551484e-06, "epoch": 1.725874506601334, "percentage": 86.33, "elapsed_time": "19:49:57", "remaining_time": "3:08:26", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3175, "total_steps": 3672, "loss": 0.0745, "learning_rate": 2.968037756859776e-06, "epoch": 1.72859670613856, "percentage": 86.47, "elapsed_time": "19:51:41", "remaining_time": "3:06:32", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3180, "total_steps": 3672, "loss": 0.0717, "learning_rate": 2.9097997757198516e-06, "epoch": 1.731318905675786, "percentage": 86.6, "elapsed_time": "19:53:26", "remaining_time": "3:04:38", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3185, "total_steps": 3672, "loss": 0.0644, "learning_rate": 2.8521035112018063e-06, "epoch": 1.734041105213012, "percentage": 86.74, "elapsed_time": "19:55:06", "remaining_time": "3:02:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3190, "total_steps": 3672, "loss": 0.0768, "learning_rate": 2.7949503781875912e-06, "epoch": 1.7367633047502382, "percentage": 86.87, "elapsed_time": "19:56:42", "remaining_time": "3:00:49", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3195, "total_steps": 3672, "loss": 0.0709, "learning_rate": 2.7383417782399693e-06, "epoch": 1.7394855042874644, "percentage": 87.01, "elapsed_time": "19:58:18", "remaining_time": "2:58:54", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3200, "total_steps": 3672, "loss": 0.0814, "learning_rate": 2.6822790995681577e-06, "epoch": 1.7422077038246904, "percentage": 87.15, "elapsed_time": "19:59:53", "remaining_time": "2:56:59", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3205, "total_steps": 3672, "loss": 0.0701, "learning_rate": 2.62676371699378e-06, "epoch": 1.7449299033619163, "percentage": 87.28, "elapsed_time": "20:01:28", "remaining_time": "2:55:03", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3210, "total_steps": 3672, "loss": 0.076, "learning_rate": 2.5717969919171553e-06, "epoch": 1.7476521028991425, "percentage": 87.42, "elapsed_time": "20:03:03", "remaining_time": "2:53:08", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3215, "total_steps": 3672, "loss": 0.0711, "learning_rate": 2.5173802722838867e-06, "epoch": 1.7503743024363687, "percentage": 87.55, "elapsed_time": "20:04:38", "remaining_time": "2:51:14", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3220, "total_steps": 3672, "loss": 0.0675, "learning_rate": 2.4635148925518577e-06, "epoch": 1.7530965019735947, "percentage": 87.69, "elapsed_time": "20:06:13", "remaining_time": "2:49:19", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3225, "total_steps": 3672, "loss": 0.0659, "learning_rate": 2.4102021736584575e-06, "epoch": 1.7558187015108206, "percentage": 87.83, "elapsed_time": "20:07:47", "remaining_time": "2:47:24", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3230, "total_steps": 3672, "loss": 0.0836, "learning_rate": 2.3574434229882145e-06, "epoch": 1.7585409010480468, "percentage": 87.96, "elapsed_time": "20:09:22", "remaining_time": "2:45:29", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3235, "total_steps": 3672, "loss": 0.079, "learning_rate": 2.3052399343407277e-06, "epoch": 1.761263100585273, "percentage": 88.1, "elapsed_time": "20:10:57", "remaining_time": "2:43:34", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3240, "total_steps": 3672, "loss": 0.075, "learning_rate": 2.253592987898942e-06, "epoch": 1.763985300122499, "percentage": 88.24, "elapsed_time": "20:12:32", "remaining_time": "2:41:40", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3245, "total_steps": 3672, "loss": 0.075, "learning_rate": 2.2025038501977486e-06, "epoch": 1.766707499659725, "percentage": 88.37, "elapsed_time": "20:14:07", "remaining_time": "2:39:45", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3250, "total_steps": 3672, "loss": 0.0847, "learning_rate": 2.1519737740929274e-06, "epoch": 1.7694296991969511, "percentage": 88.51, "elapsed_time": "20:15:42", "remaining_time": "2:37:51", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3255, "total_steps": 3672, "loss": 0.0852, "learning_rate": 2.1020039987304285e-06, "epoch": 1.7721518987341773, "percentage": 88.64, "elapsed_time": "20:17:17", "remaining_time": "2:35:56", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3260, "total_steps": 3672, "loss": 0.0726, "learning_rate": 2.05259574951599e-06, "epoch": 1.7748740982714033, "percentage": 88.78, "elapsed_time": "20:18:51", "remaining_time": "2:34:02", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3265, "total_steps": 3672, "loss": 0.076, "learning_rate": 2.003750238085053e-06, "epoch": 1.7775962978086293, "percentage": 88.92, "elapsed_time": "20:20:26", "remaining_time": "2:32:08", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3270, "total_steps": 3672, "loss": 0.0992, "learning_rate": 1.9554686622730993e-06, "epoch": 1.7803184973458555, "percentage": 89.05, "elapsed_time": "20:22:01", "remaining_time": "2:30:13", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3275, "total_steps": 3672, "loss": 0.0819, "learning_rate": 1.907752206086247e-06, "epoch": 1.7830406968830816, "percentage": 89.19, "elapsed_time": "20:23:36", "remaining_time": "2:28:19", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3280, "total_steps": 3672, "loss": 0.0726, "learning_rate": 1.8606020396722129e-06, "epoch": 1.7857628964203076, "percentage": 89.32, "elapsed_time": "20:25:10", "remaining_time": "2:26:25", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3285, "total_steps": 3672, "loss": 0.0754, "learning_rate": 1.814019319291635e-06, "epoch": 1.7884850959575336, "percentage": 89.46, "elapsed_time": "20:26:45", "remaining_time": "2:24:31", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3290, "total_steps": 3672, "loss": 0.0658, "learning_rate": 1.7680051872896869e-06, "epoch": 1.7912072954947598, "percentage": 89.6, "elapsed_time": "20:28:19", "remaining_time": "2:22:37", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3295, "total_steps": 3672, "loss": 0.0732, "learning_rate": 1.7225607720681131e-06, "epoch": 1.793929495031986, "percentage": 89.73, "elapsed_time": "20:29:54", "remaining_time": "2:20:43", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3300, "total_steps": 3672, "loss": 0.0833, "learning_rate": 1.6776871880575084e-06, "epoch": 1.796651694569212, "percentage": 89.87, "elapsed_time": "20:31:28", "remaining_time": "2:18:49", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3305, "total_steps": 3672, "loss": 0.1652, "learning_rate": 1.6333855356900185e-06, "epoch": 1.7993738941064379, "percentage": 90.01, "elapsed_time": "20:33:01", "remaining_time": "2:16:55", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3310, "total_steps": 3672, "loss": 0.0797, "learning_rate": 1.5896569013723329e-06, "epoch": 1.802096093643664, "percentage": 90.14, "elapsed_time": "20:34:35", "remaining_time": "2:15:01", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3315, "total_steps": 3672, "loss": 0.0757, "learning_rate": 1.5465023574590676e-06, "epoch": 1.8048182931808903, "percentage": 90.28, "elapsed_time": "20:36:10", "remaining_time": "2:13:07", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3320, "total_steps": 3672, "loss": 0.0781, "learning_rate": 1.5039229622264479e-06, "epoch": 1.8075404927181162, "percentage": 90.41, "elapsed_time": "20:37:45", "remaining_time": "2:11:13", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3325, "total_steps": 3672, "loss": 0.0764, "learning_rate": 1.4619197598463641e-06, "epoch": 1.8102626922553422, "percentage": 90.55, "elapsed_time": "20:39:20", "remaining_time": "2:09:20", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3330, "total_steps": 3672, "loss": 0.0708, "learning_rate": 1.420493780360771e-06, "epoch": 1.8129848917925684, "percentage": 90.69, "elapsed_time": "20:40:55", "remaining_time": "2:07:26", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3335, "total_steps": 3672, "loss": 0.0711, "learning_rate": 1.3796460396564098e-06, "epoch": 1.8157070913297946, "percentage": 90.82, "elapsed_time": "20:42:30", "remaining_time": "2:05:33", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3340, "total_steps": 3672, "loss": 0.0797, "learning_rate": 1.3393775394399123e-06, "epoch": 1.8184292908670205, "percentage": 90.96, "elapsed_time": "20:44:05", "remaining_time": "2:03:39", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3345, "total_steps": 3672, "loss": 0.0845, "learning_rate": 1.2996892672132416e-06, "epoch": 1.8211514904042465, "percentage": 91.09, "elapsed_time": "20:45:40", "remaining_time": "2:01:46", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3350, "total_steps": 3672, "loss": 0.1118, "learning_rate": 1.2605821962494574e-06, "epoch": 1.8238736899414727, "percentage": 91.23, "elapsed_time": "20:47:15", "remaining_time": "1:59:53", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3355, "total_steps": 3672, "loss": 0.0782, "learning_rate": 1.2220572855688507e-06, "epoch": 1.8265958894786989, "percentage": 91.37, "elapsed_time": "20:48:50", "remaining_time": "1:57:59", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3360, "total_steps": 3672, "loss": 0.0737, "learning_rate": 1.1841154799154374e-06, "epoch": 1.8293180890159249, "percentage": 91.5, "elapsed_time": "20:50:25", "remaining_time": "1:56:06", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3365, "total_steps": 3672, "loss": 0.0939, "learning_rate": 1.1467577097337867e-06, "epoch": 1.8320402885531508, "percentage": 91.64, "elapsed_time": "20:52:00", "remaining_time": "1:54:13", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3370, "total_steps": 3672, "loss": 0.0752, "learning_rate": 1.1099848911462014e-06, "epoch": 1.834762488090377, "percentage": 91.78, "elapsed_time": "20:53:34", "remaining_time": "1:52:20", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3375, "total_steps": 3672, "loss": 0.0688, "learning_rate": 1.0737979259302478e-06, "epoch": 1.8374846876276032, "percentage": 91.91, "elapsed_time": "20:55:09", "remaining_time": "1:50:27", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3380, "total_steps": 3672, "loss": 0.0996, "learning_rate": 1.0381977014966543e-06, "epoch": 1.8402068871648292, "percentage": 92.05, "elapsed_time": "20:56:44", "remaining_time": "1:48:34", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3385, "total_steps": 3672, "loss": 0.1217, "learning_rate": 1.0031850908675283e-06, "epoch": 1.8429290867020551, "percentage": 92.18, "elapsed_time": "20:58:19", "remaining_time": "1:46:41", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3390, "total_steps": 3672, "loss": 0.0653, "learning_rate": 9.68760952654968e-07, "epoch": 1.8456512862392813, "percentage": 92.32, "elapsed_time": "20:59:53", "remaining_time": "1:44:48", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3395, "total_steps": 3672, "loss": 0.0735, "learning_rate": 9.349261310400037e-07, "epoch": 1.8483734857765075, "percentage": 92.46, "elapsed_time": "21:01:28", "remaining_time": "1:42:55", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3400, "total_steps": 3672, "loss": 0.0683, "learning_rate": 9.016814557518849e-07, "epoch": 1.8510956853137335, "percentage": 92.59, "elapsed_time": "21:03:03", "remaining_time": "1:41:02", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3405, "total_steps": 3672, "loss": 0.079, "learning_rate": 8.690277420477372e-07, "epoch": 1.8538178848509594, "percentage": 92.73, "elapsed_time": "21:04:38", "remaining_time": "1:39:09", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3410, "total_steps": 3672, "loss": 0.0753, "learning_rate": 8.369657906925732e-07, "epoch": 1.8565400843881856, "percentage": 92.86, "elapsed_time": "21:06:13", "remaining_time": "1:37:17", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3415, "total_steps": 3672, "loss": 0.0646, "learning_rate": 8.054963879396554e-07, "epoch": 1.8592622839254118, "percentage": 93.0, "elapsed_time": "21:07:48", "remaining_time": "1:35:24", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3420, "total_steps": 3672, "loss": 0.1086, "learning_rate": 7.746203055112145e-07, "epoch": 1.8619844834626378, "percentage": 93.14, "elapsed_time": "21:09:23", "remaining_time": "1:33:32", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3425, "total_steps": 3672, "loss": 0.0946, "learning_rate": 7.443383005795224e-07, "epoch": 1.8647066829998638, "percentage": 93.27, "elapsed_time": "21:10:58", "remaining_time": "1:31:39", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3430, "total_steps": 3672, "loss": 0.0829, "learning_rate": 7.146511157483216e-07, "epoch": 1.86742888253709, "percentage": 93.41, "elapsed_time": "21:12:33", "remaining_time": "1:29:47", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3435, "total_steps": 3672, "loss": 0.0679, "learning_rate": 6.85559479034617e-07, "epoch": 1.8701510820743161, "percentage": 93.55, "elapsed_time": "21:14:08", "remaining_time": "1:27:54", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3440, "total_steps": 3672, "loss": 0.0762, "learning_rate": 6.570641038508296e-07, "epoch": 1.872873281611542, "percentage": 93.68, "elapsed_time": "21:15:44", "remaining_time": "1:26:02", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3445, "total_steps": 3672, "loss": 0.0803, "learning_rate": 6.291656889873016e-07, "epoch": 1.875595481148768, "percentage": 93.82, "elapsed_time": "21:17:19", "remaining_time": "1:24:09", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3450, "total_steps": 3672, "loss": 0.0707, "learning_rate": 6.018649185951325e-07, "epoch": 1.8783176806859943, "percentage": 93.95, "elapsed_time": "21:18:54", "remaining_time": "1:22:17", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3455, "total_steps": 3672, "loss": 0.0636, "learning_rate": 5.751624621694429e-07, "epoch": 1.8810398802232204, "percentage": 94.09, "elapsed_time": "21:20:29", "remaining_time": "1:20:25", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3460, "total_steps": 3672, "loss": 0.0774, "learning_rate": 5.490589745329261e-07, "epoch": 1.8837620797604464, "percentage": 94.23, "elapsed_time": "21:22:04", "remaining_time": "1:18:33", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3465, "total_steps": 3672, "loss": 0.073, "learning_rate": 5.235550958198083e-07, "epoch": 1.8864842792976724, "percentage": 94.36, "elapsed_time": "21:23:39", "remaining_time": "1:16:41", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3470, "total_steps": 3672, "loss": 0.0742, "learning_rate": 4.986514514601415e-07, "epoch": 1.8892064788348986, "percentage": 94.5, "elapsed_time": "21:25:14", "remaining_time": "1:14:49", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3475, "total_steps": 3672, "loss": 0.083, "learning_rate": 4.74348652164458e-07, "epoch": 1.8919286783721248, "percentage": 94.64, "elapsed_time": "21:26:49", "remaining_time": "1:12:57", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3480, "total_steps": 3672, "loss": 0.0755, "learning_rate": 4.5064729390881246e-07, "epoch": 1.8946508779093507, "percentage": 94.77, "elapsed_time": "21:28:24", "remaining_time": "1:11:05", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3485, "total_steps": 3672, "loss": 0.0703, "learning_rate": 4.275479579201602e-07, "epoch": 1.8973730774465767, "percentage": 94.91, "elapsed_time": "21:29:59", "remaining_time": "1:09:13", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3490, "total_steps": 3672, "loss": 0.0692, "learning_rate": 4.050512106620913e-07, "epoch": 1.9000952769838029, "percentage": 95.04, "elapsed_time": "21:31:33", "remaining_time": "1:07:21", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3495, "total_steps": 3672, "loss": 0.0794, "learning_rate": 3.8315760382096057e-07, "epoch": 1.902817476521029, "percentage": 95.18, "elapsed_time": "21:33:08", "remaining_time": "1:05:29", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3500, "total_steps": 3672, "loss": 0.0671, "learning_rate": 3.6186767429234323e-07, "epoch": 1.905539676058255, "percentage": 95.32, "elapsed_time": "21:34:43", "remaining_time": "1:03:37", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3500, "total_steps": 3672, "eval_loss": 0.07686587423086166, "epoch": 1.905539676058255, "percentage": 95.32, "elapsed_time": "21:38:22", "remaining_time": "1:03:48", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3505, "total_steps": 3672, "loss": 0.076, "learning_rate": 3.4118194416786764e-07, "epoch": 1.908261875595481, "percentage": 95.45, "elapsed_time": "21:39:57", "remaining_time": "1:01:56", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3510, "total_steps": 3672, "loss": 0.0723, "learning_rate": 3.211009207224225e-07, "epoch": 1.9109840751327072, "percentage": 95.59, "elapsed_time": "21:41:32", "remaining_time": "1:00:04", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3515, "total_steps": 3672, "loss": 0.0727, "learning_rate": 3.016250964017142e-07, "epoch": 1.9137062746699334, "percentage": 95.72, "elapsed_time": "21:43:07", "remaining_time": "0:58:12", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3520, "total_steps": 3672, "loss": 0.0699, "learning_rate": 2.827549488101849e-07, "epoch": 1.9164284742071593, "percentage": 95.86, "elapsed_time": "21:44:41", "remaining_time": "0:56:20", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3525, "total_steps": 3672, "loss": 0.0674, "learning_rate": 2.644909406992996e-07, "epoch": 1.9191506737443853, "percentage": 96.0, "elapsed_time": "21:46:16", "remaining_time": "0:54:28", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3530, "total_steps": 3672, "loss": 0.0779, "learning_rate": 2.468335199562105e-07, "epoch": 1.9218728732816115, "percentage": 96.13, "elapsed_time": "21:47:51", "remaining_time": "0:52:36", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3535, "total_steps": 3672, "loss": 0.0697, "learning_rate": 2.29783119592758e-07, "epoch": 1.9245950728188377, "percentage": 96.27, "elapsed_time": "21:49:25", "remaining_time": "0:50:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3540, "total_steps": 3672, "loss": 0.0682, "learning_rate": 2.1334015773486203e-07, "epoch": 1.9273172723560636, "percentage": 96.41, "elapsed_time": "21:50:59", "remaining_time": "0:48:53", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3545, "total_steps": 3672, "loss": 0.0787, "learning_rate": 1.975050376122667e-07, "epoch": 1.9300394718932896, "percentage": 96.54, "elapsed_time": "21:52:33", "remaining_time": "0:47:01", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3550, "total_steps": 3672, "loss": 0.0735, "learning_rate": 1.8227814754865068e-07, "epoch": 1.9327616714305158, "percentage": 96.68, "elapsed_time": "21:54:07", "remaining_time": "0:45:09", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3555, "total_steps": 3672, "loss": 0.0684, "learning_rate": 1.6765986095209908e-07, "epoch": 1.935483870967742, "percentage": 96.81, "elapsed_time": "21:55:40", "remaining_time": "0:43:18", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3560, "total_steps": 3672, "loss": 0.0738, "learning_rate": 1.536505363059576e-07, "epoch": 1.938206070504968, "percentage": 96.95, "elapsed_time": "21:57:13", "remaining_time": "0:41:26", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3565, "total_steps": 3672, "loss": 0.083, "learning_rate": 1.4025051716003157e-07, "epoch": 1.9409282700421941, "percentage": 97.09, "elapsed_time": "21:58:48", "remaining_time": "0:39:34", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3570, "total_steps": 3672, "loss": 0.0758, "learning_rate": 1.2746013212217022e-07, "epoch": 1.9436504695794201, "percentage": 97.22, "elapsed_time": "22:00:23", "remaining_time": "0:37:43", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3575, "total_steps": 3672, "loss": 0.0755, "learning_rate": 1.1527969485019275e-07, "epoch": 1.9463726691166463, "percentage": 97.36, "elapsed_time": "22:01:58", "remaining_time": "0:35:52", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3580, "total_steps": 3672, "loss": 0.0651, "learning_rate": 1.0370950404421931e-07, "epoch": 1.9490948686538725, "percentage": 97.49, "elapsed_time": "22:03:33", "remaining_time": "0:34:00", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3585, "total_steps": 3672, "loss": 0.0785, "learning_rate": 9.274984343932702e-08, "epoch": 1.9518170681910985, "percentage": 97.63, "elapsed_time": "22:05:07", "remaining_time": "0:32:09", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3590, "total_steps": 3672, "loss": 0.0826, "learning_rate": 8.240098179859712e-08, "epoch": 1.9545392677283244, "percentage": 97.77, "elapsed_time": "22:06:42", "remaining_time": "0:30:18", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3595, "total_steps": 3672, "loss": 0.0816, "learning_rate": 7.26631729065258e-08, "epoch": 1.9572614672655506, "percentage": 97.9, "elapsed_time": "22:08:17", "remaining_time": "0:28:27", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3600, "total_steps": 3672, "loss": 0.0699, "learning_rate": 6.353665556280697e-08, "epoch": 1.9599836668027768, "percentage": 98.04, "elapsed_time": "22:09:52", "remaining_time": "0:26:35", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3605, "total_steps": 3672, "loss": 0.062, "learning_rate": 5.5021653576459164e-08, "epoch": 1.9627058663400028, "percentage": 98.18, "elapsed_time": "22:11:26", "remaining_time": "0:24:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3610, "total_steps": 3672, "loss": 0.0804, "learning_rate": 4.7118375760357716e-08, "epoch": 1.9654280658772287, "percentage": 98.31, "elapsed_time": "22:13:01", "remaining_time": "0:22:53", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3615, "total_steps": 3672, "loss": 0.1359, "learning_rate": 3.982701592609439e-08, "epoch": 1.968150265414455, "percentage": 98.45, "elapsed_time": "22:14:36", "remaining_time": "0:21:02", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3620, "total_steps": 3672, "loss": 0.071, "learning_rate": 3.314775287923677e-08, "epoch": 1.9708724649516811, "percentage": 98.58, "elapsed_time": "22:16:10", "remaining_time": "0:19:11", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3625, "total_steps": 3672, "loss": 0.0784, "learning_rate": 2.708075041494562e-08, "epoch": 1.973594664488907, "percentage": 98.72, "elapsed_time": "22:17:45", "remaining_time": "0:17:20", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3630, "total_steps": 3672, "loss": 0.097, "learning_rate": 2.1626157313950345e-08, "epoch": 1.976316864026133, "percentage": 98.86, "elapsed_time": "22:19:20", "remaining_time": "0:15:29", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3635, "total_steps": 3672, "loss": 0.0775, "learning_rate": 1.6784107338899124e-08, "epoch": 1.9790390635633592, "percentage": 98.99, "elapsed_time": "22:20:55", "remaining_time": "0:13:38", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3640, "total_steps": 3672, "loss": 0.0696, "learning_rate": 1.2554719231083755e-08, "epoch": 1.9817612631005854, "percentage": 99.13, "elapsed_time": "22:22:30", "remaining_time": "0:11:48", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3645, "total_steps": 3672, "loss": 0.0674, "learning_rate": 8.93809670753365e-09, "epoch": 1.9844834626378114, "percentage": 99.26, "elapsed_time": "22:24:05", "remaining_time": "0:09:57", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3650, "total_steps": 3672, "loss": 0.0712, "learning_rate": 5.934328458459537e-09, "epoch": 1.9872056621750374, "percentage": 99.4, "elapsed_time": "22:25:39", "remaining_time": "0:08:06", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3655, "total_steps": 3672, "loss": 0.0614, "learning_rate": 3.543488145082985e-09, "epoch": 1.9899278617122635, "percentage": 99.54, "elapsed_time": "22:27:14", "remaining_time": "0:06:15", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3660, "total_steps": 3672, "loss": 0.0762, "learning_rate": 1.7656343978378342e-09, "epoch": 1.9926500612494897, "percentage": 99.67, "elapsed_time": "22:28:49", "remaining_time": "0:04:25", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3665, "total_steps": 3672, "loss": 0.0841, "learning_rate": 6.008108149185843e-10, "epoch": 1.9953722607867157, "percentage": 99.81, "elapsed_time": "22:30:23", "remaining_time": "0:02:34", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3670, "total_steps": 3672, "loss": 0.0805, "learning_rate": 4.904596122290439e-11, "epoch": 1.9980944603239417, "percentage": 99.95, "elapsed_time": "22:31:58", "remaining_time": "0:00:44", "throughput": "0.00", "total_tokens": 0} |
|
{"current_steps": 3672, "total_steps": 3672, "epoch": 1.9991833401388321, "percentage": 100.0, "elapsed_time": "22:32:37", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} |
|
|