| {"current_steps": 5, "total_steps": 600, "loss": 3.6731, "lr": 0.2999671025212268, "epoch": 1.32, "percentage": 0.83, "elapsed_time": "0:00:11", "remaining_time": "0:22:00", "throughput": 2936.14, "total_tokens": 32576} |
| {"current_steps": 10, "total_steps": 600, "loss": 0.9267, "lr": 0.2998334812442955, "epoch": 2.64, "percentage": 1.67, "elapsed_time": "0:00:18", "remaining_time": "0:17:44", "throughput": 3516.0, "total_tokens": 63424} |
| {"current_steps": 15, "total_steps": 600, "loss": 0.4169, "lr": 0.29959717158366866, "epoch": 3.96, "percentage": 2.5, "elapsed_time": "0:00:24", "remaining_time": "0:16:11", "throughput": 3826.51, "total_tokens": 95360} |
| {"current_steps": 20, "total_steps": 600, "loss": 0.2866, "lr": 0.29925833549418396, "epoch": 5.0, "percentage": 3.33, "elapsed_time": "0:00:30", "remaining_time": "0:14:44", "throughput": 3947.76, "total_tokens": 120384} |
| {"current_steps": 25, "total_steps": 600, "loss": 0.2759, "lr": 0.2988172051971717, "epoch": 6.32, "percentage": 4.17, "elapsed_time": "0:00:37", "remaining_time": "0:14:30", "throughput": 4030.12, "total_tokens": 152512} |
| {"current_steps": 30, "total_steps": 600, "loss": 0.2554, "lr": 0.2982740830213025, "epoch": 7.64, "percentage": 5.0, "elapsed_time": "0:00:44", "remaining_time": "0:14:12", "throughput": 4108.1, "total_tokens": 184320} |
| {"current_steps": 35, "total_steps": 600, "loss": 0.2385, "lr": 0.29762934119538625, "epoch": 8.96, "percentage": 5.83, "elapsed_time": "0:00:51", "remaining_time": "0:13:50", "throughput": 4186.0, "total_tokens": 215296} |
| {"current_steps": 40, "total_steps": 600, "loss": 0.2027, "lr": 0.29688342159326486, "epoch": 10.0, "percentage": 6.67, "elapsed_time": "0:00:56", "remaining_time": "0:13:15", "throughput": 4223.99, "total_tokens": 239872} |
| {"current_steps": 45, "total_steps": 600, "loss": 0.2518, "lr": 0.29603683543097403, "epoch": 11.32, "percentage": 7.5, "elapsed_time": "0:01:03", "remaining_time": "0:13:05", "throughput": 4261.41, "total_tokens": 271424} |
| {"current_steps": 50, "total_steps": 600, "loss": 0.1676, "lr": 0.2950901629163815, "epoch": 12.64, "percentage": 8.33, "elapsed_time": "0:01:10", "remaining_time": "0:12:54", "throughput": 4304.34, "total_tokens": 302912} |
| {"current_steps": 55, "total_steps": 600, "loss": 0.1485, "lr": 0.29404405285154145, "epoch": 13.96, "percentage": 9.17, "elapsed_time": "0:01:17", "remaining_time": "0:12:43", "throughput": 4338.38, "total_tokens": 334464} |
| {"current_steps": 60, "total_steps": 600, "loss": 0.0873, "lr": 0.29289922218803793, "epoch": 15.0, "percentage": 10.0, "elapsed_time": "0:01:22", "remaining_time": "0:12:23", "throughput": 4357.2, "total_tokens": 359872} |
| {"current_steps": 65, "total_steps": 600, "loss": 0.0803, "lr": 0.29165645553562214, "epoch": 16.32, "percentage": 10.83, "elapsed_time": "0:01:29", "remaining_time": "0:12:17", "throughput": 4362.72, "total_tokens": 390784} |
| {"current_steps": 70, "total_steps": 600, "loss": 0.0995, "lr": 0.2903166046244801, "epoch": 17.64, "percentage": 11.67, "elapsed_time": "0:01:36", "remaining_time": "0:12:10", "throughput": 4380.55, "total_tokens": 422528} |
| {"current_steps": 75, "total_steps": 600, "loss": 0.1117, "lr": 0.2888805877214992, "epoch": 18.96, "percentage": 12.5, "elapsed_time": "0:01:43", "remaining_time": "0:12:02", "throughput": 4403.96, "total_tokens": 454400} |
| {"current_steps": 80, "total_steps": 600, "loss": 0.0746, "lr": 0.28734938900093415, "epoch": 20.0, "percentage": 13.33, "elapsed_time": "0:01:48", "remaining_time": "0:11:46", "throughput": 4415.08, "total_tokens": 479744} |
| {"current_steps": 85, "total_steps": 600, "loss": 0.1154, "lr": 0.2857240578699029, "epoch": 21.32, "percentage": 14.17, "elapsed_time": "0:01:55", "remaining_time": "0:11:42", "throughput": 4408.52, "total_tokens": 511168} |
| {"current_steps": 90, "total_steps": 600, "loss": 0.2176, "lr": 0.28400570824917565, "epoch": 22.64, "percentage": 15.0, "elapsed_time": "0:02:02", "remaining_time": "0:11:36", "throughput": 4423.21, "total_tokens": 543296} |
| {"current_steps": 95, "total_steps": 600, "loss": 0.133, "lr": 0.2821955178097488, "epoch": 23.96, "percentage": 15.83, "elapsed_time": "0:02:09", "remaining_time": "0:11:28", "throughput": 4438.27, "total_tokens": 574976} |
| {"current_steps": 100, "total_steps": 600, "loss": 0.139, "lr": 0.2802947271657287, "epoch": 25.0, "percentage": 16.67, "elapsed_time": "0:02:14", "remaining_time": "0:11:14", "throughput": 4445.9, "total_tokens": 600064} |
| {"current_steps": 105, "total_steps": 600, "loss": 0.0892, "lr": 0.278304639024076, "epoch": 26.32, "percentage": 17.5, "elapsed_time": "0:02:21", "remaining_time": "0:11:08", "throughput": 4450.3, "total_tokens": 631296} |
| {"current_steps": 110, "total_steps": 600, "loss": 0.0688, "lr": 0.27622661729179593, "epoch": 27.64, "percentage": 18.33, "elapsed_time": "0:02:28", "remaining_time": "0:11:01", "throughput": 4465.63, "total_tokens": 662976} |
| {"current_steps": 115, "total_steps": 600, "loss": 0.0574, "lr": 0.27406208614118427, "epoch": 28.96, "percentage": 19.17, "elapsed_time": "0:02:35", "remaining_time": "0:10:54", "throughput": 4475.41, "total_tokens": 694336} |
| {"current_steps": 120, "total_steps": 600, "loss": 0.0307, "lr": 0.27181252903377096, "epoch": 30.0, "percentage": 20.0, "elapsed_time": "0:02:40", "remaining_time": "0:10:42", "throughput": 4475.33, "total_tokens": 718976} |
| {"current_steps": 125, "total_steps": 600, "loss": 0.0062, "lr": 0.26947948770362945, "epoch": 31.32, "percentage": 20.83, "elapsed_time": "0:02:47", "remaining_time": "0:10:38", "throughput": 4470.82, "total_tokens": 750656} |
| {"current_steps": 130, "total_steps": 600, "loss": 0.0046, "lr": 0.26706456110074944, "epoch": 32.64, "percentage": 21.67, "elapsed_time": "0:02:54", "remaining_time": "0:10:31", "throughput": 4477.42, "total_tokens": 781952} |
| {"current_steps": 135, "total_steps": 600, "loss": 0.0017, "lr": 0.2645694042951963, "epoch": 33.96, "percentage": 22.5, "elapsed_time": "0:03:01", "remaining_time": "0:10:24", "throughput": 4480.95, "total_tokens": 812736} |
| {"current_steps": 140, "total_steps": 600, "loss": 0.0009, "lr": 0.2619957273428087, "epoch": 35.0, "percentage": 23.33, "elapsed_time": "0:03:06", "remaining_time": "0:10:14", "throughput": 4476.98, "total_tokens": 836992} |
| {"current_steps": 145, "total_steps": 600, "loss": 0.0004, "lr": 0.2593452941132117, "epoch": 36.32, "percentage": 24.17, "elapsed_time": "0:03:13", "remaining_time": "0:10:08", "throughput": 4475.65, "total_tokens": 868160} |
| {"current_steps": 150, "total_steps": 600, "loss": 0.0003, "lr": 0.2566199210809489, "epoch": 37.64, "percentage": 25.0, "elapsed_time": "0:03:20", "remaining_time": "0:10:02", "throughput": 4488.92, "total_tokens": 901568} |
| {"current_steps": 155, "total_steps": 600, "loss": 0.0002, "lr": 0.25382147608056105, "epoch": 38.96, "percentage": 25.83, "elapsed_time": "0:03:27", "remaining_time": "0:09:55", "throughput": 4490.78, "total_tokens": 931392} |
| {"current_steps": 160, "total_steps": 600, "loss": 0.0002, "lr": 0.250951877026466, "epoch": 40.0, "percentage": 26.67, "elapsed_time": "0:03:32", "remaining_time": "0:09:45", "throughput": 4494.95, "total_tokens": 957120} |
| {"current_steps": 165, "total_steps": 600, "loss": 0.0002, "lr": 0.24801309059851584, "epoch": 41.32, "percentage": 27.5, "elapsed_time": "0:03:40", "remaining_time": "0:09:40", "throughput": 4489.19, "total_tokens": 987648} |
| {"current_steps": 170, "total_steps": 600, "loss": 0.0001, "lr": 0.2450071308941325, "epoch": 42.64, "percentage": 28.33, "elapsed_time": "0:03:46", "remaining_time": "0:09:33", "throughput": 4497.51, "total_tokens": 1020544} |
| {"current_steps": 175, "total_steps": 600, "loss": 0.0001, "lr": 0.2419360580479465, "epoch": 43.96, "percentage": 29.17, "elapsed_time": "0:03:53", "remaining_time": "0:09:27", "throughput": 4504.7, "total_tokens": 1051776} |
| {"current_steps": 180, "total_steps": 600, "loss": 0.0001, "lr": 0.2388019768198829, "epoch": 45.0, "percentage": 30.0, "elapsed_time": "0:03:58", "remaining_time": "0:09:17", "throughput": 4506.58, "total_tokens": 1076864} |
| {"current_steps": 185, "total_steps": 600, "loss": 0.0001, "lr": 0.2356070351526648, "epoch": 46.32, "percentage": 30.83, "elapsed_time": "0:04:06", "remaining_time": "0:09:12", "throughput": 4504.43, "total_tokens": 1108608} |
| {"current_steps": 190, "total_steps": 600, "loss": 0.0001, "lr": 0.23235342269971976, "epoch": 47.64, "percentage": 31.67, "elapsed_time": "0:04:12", "remaining_time": "0:09:05", "throughput": 4514.6, "total_tokens": 1141888} |
| {"current_steps": 195, "total_steps": 600, "loss": 0.0001, "lr": 0.22904336932450164, "epoch": 48.96, "percentage": 32.5, "elapsed_time": "0:04:19", "remaining_time": "0:08:58", "throughput": 4518.79, "total_tokens": 1172352} |
| {"current_steps": 200, "total_steps": 600, "loss": 0.0001, "lr": 0.22567914357225285, "epoch": 50.0, "percentage": 33.33, "elapsed_time": "0:04:25", "remaining_time": "0:08:50", "throughput": 4516.43, "total_tokens": 1197376} |
| {"current_steps": 200, "total_steps": 600, "epoch": 50.0, "percentage": 33.33, "elapsed_time": "0:04:26", "remaining_time": "0:08:53", "throughput": 4484.69, "total_tokens": 1197376} |
| {"current_steps": 205, "total_steps": 600, "loss": 0.0001, "lr": 0.22226305111525727, "epoch": 51.32, "percentage": 34.17, "elapsed_time": "0:04:36", "remaining_time": "0:08:52", "throughput": 4448.83, "total_tokens": 1229248} |
| {"current_steps": 210, "total_steps": 600, "loss": 0.0001, "lr": 0.21879743317264727, "epoch": 52.64, "percentage": 35.0, "elapsed_time": "0:04:43", "remaining_time": "0:08:45", "throughput": 4456.45, "total_tokens": 1261888} |
| {"current_steps": 215, "total_steps": 600, "loss": 0.0001, "lr": 0.21528466490584913, "epoch": 53.96, "percentage": 35.83, "elapsed_time": "0:04:49", "remaining_time": "0:08:39", "throughput": 4460.33, "total_tokens": 1292992} |
| {"current_steps": 220, "total_steps": 600, "loss": 0.0001, "lr": 0.21172715379076631, "epoch": 55.0, "percentage": 36.67, "elapsed_time": "0:04:55", "remaining_time": "0:08:30", "throughput": 4461.63, "total_tokens": 1318016} |
| {"current_steps": 225, "total_steps": 600, "loss": 0.0001, "lr": 0.20812733796781543, "epoch": 56.32, "percentage": 37.5, "elapsed_time": "0:05:02", "remaining_time": "0:08:24", "throughput": 4464.12, "total_tokens": 1350080} |
| {"current_steps": 230, "total_steps": 600, "loss": 0.0001, "lr": 0.20448768457094676, "epoch": 57.64, "percentage": 38.33, "elapsed_time": "0:05:09", "remaining_time": "0:08:17", "throughput": 4469.94, "total_tokens": 1382272} |
| {"current_steps": 235, "total_steps": 600, "loss": 0.0001, "lr": 0.20081068803679372, "epoch": 58.96, "percentage": 39.17, "elapsed_time": "0:05:16", "remaining_time": "0:08:10", "throughput": 4472.18, "total_tokens": 1413632} |
| {"current_steps": 240, "total_steps": 600, "loss": 0.0001, "lr": 0.19709886839511073, "epoch": 60.0, "percentage": 40.0, "elapsed_time": "0:05:21", "remaining_time": "0:08:02", "throughput": 4470.48, "total_tokens": 1438336} |
| {"current_steps": 245, "total_steps": 600, "loss": 0.0001, "lr": 0.19335476954167072, "epoch": 61.32, "percentage": 40.83, "elapsed_time": "0:05:29", "remaining_time": "0:07:56", "throughput": 4467.0, "total_tokens": 1469824} |
| {"current_steps": 250, "total_steps": 600, "loss": 0.0001, "lr": 0.18958095749480594, "epoch": 62.64, "percentage": 41.67, "elapsed_time": "0:05:36", "remaining_time": "0:07:50", "throughput": 4467.76, "total_tokens": 1501568} |
| {"current_steps": 255, "total_steps": 600, "loss": 0.0001, "lr": 0.18578001863678714, "epoch": 63.96, "percentage": 42.5, "elapsed_time": "0:05:42", "remaining_time": "0:07:43", "throughput": 4472.79, "total_tokens": 1533824} |
| {"current_steps": 260, "total_steps": 600, "loss": 0.0, "lr": 0.18195455794124651, "epoch": 65.0, "percentage": 43.33, "elapsed_time": "0:05:48", "remaining_time": "0:07:35", "throughput": 4473.92, "total_tokens": 1558656} |
| {"current_steps": 265, "total_steps": 600, "loss": 0.0001, "lr": 0.17810719718785872, "epoch": 66.32, "percentage": 44.17, "elapsed_time": "0:05:55", "remaining_time": "0:07:29", "throughput": 4476.43, "total_tokens": 1590912} |
| {"current_steps": 270, "total_steps": 600, "loss": 0.0, "lr": 0.17424057316550418, "epoch": 67.64, "percentage": 45.0, "elapsed_time": "0:06:02", "remaining_time": "0:07:22", "throughput": 4480.57, "total_tokens": 1622656} |
| {"current_steps": 275, "total_steps": 600, "loss": 0.0001, "lr": 0.17035733586514565, "epoch": 68.96, "percentage": 45.83, "elapsed_time": "0:06:08", "remaining_time": "0:07:15", "throughput": 4483.86, "total_tokens": 1653696} |
| {"current_steps": 280, "total_steps": 600, "loss": 0.0001, "lr": 0.16646014666365677, "epoch": 70.0, "percentage": 46.67, "elapsed_time": "0:06:14", "remaining_time": "0:07:07", "throughput": 4482.47, "total_tokens": 1678144} |
| {"current_steps": 285, "total_steps": 600, "loss": 0.0, "lr": 0.16255167649984736, "epoch": 71.32, "percentage": 47.5, "elapsed_time": "0:06:21", "remaining_time": "0:07:01", "throughput": 4481.66, "total_tokens": 1709312} |
| {"current_steps": 290, "total_steps": 600, "loss": 0.0, "lr": 0.15863460404393512, "epoch": 72.64, "percentage": 48.33, "elapsed_time": "0:06:28", "remaining_time": "0:06:55", "throughput": 4486.4, "total_tokens": 1741952} |
| {"current_steps": 295, "total_steps": 600, "loss": 0.0001, "lr": 0.15471161386171925, "epoch": 73.96, "percentage": 49.17, "elapsed_time": "0:06:34", "remaining_time": "0:06:48", "throughput": 4489.06, "total_tokens": 1772992} |
| {"current_steps": 300, "total_steps": 600, "loss": 0.0, "lr": 0.1507853945747129, "epoch": 75.0, "percentage": 50.0, "elapsed_time": "0:06:40", "remaining_time": "0:06:40", "throughput": 4489.59, "total_tokens": 1797568} |
| {"current_steps": 305, "total_steps": 600, "loss": 0.0, "lr": 0.14685863701749646, "epoch": 76.32, "percentage": 50.83, "elapsed_time": "0:06:47", "remaining_time": "0:06:34", "throughput": 4490.22, "total_tokens": 1829120} |
| {"current_steps": 310, "total_steps": 600, "loss": 0.0, "lr": 0.1429340323935536, "epoch": 77.64, "percentage": 51.67, "elapsed_time": "0:06:53", "remaining_time": "0:06:27", "throughput": 4493.64, "total_tokens": 1860352} |
| {"current_steps": 315, "total_steps": 600, "loss": 0.0, "lr": 0.13901427043085526, "epoch": 78.96, "percentage": 52.5, "elapsed_time": "0:07:00", "remaining_time": "0:06:20", "throughput": 4497.97, "total_tokens": 1892736} |
| {"current_steps": 320, "total_steps": 600, "loss": 0.0, "lr": 0.13510203753845418, "epoch": 80.0, "percentage": 53.33, "elapsed_time": "0:07:06", "remaining_time": "0:06:12", "throughput": 4498.79, "total_tokens": 1917696} |
| {"current_steps": 325, "total_steps": 600, "loss": 0.0, "lr": 0.13120001496535433, "epoch": 81.32, "percentage": 54.17, "elapsed_time": "0:07:13", "remaining_time": "0:06:06", "throughput": 4499.33, "total_tokens": 1948736} |
| {"current_steps": 330, "total_steps": 600, "loss": 0.0, "lr": 0.12731087696291712, "epoch": 82.64, "percentage": 55.0, "elapsed_time": "0:07:19", "remaining_time": "0:05:59", "throughput": 4502.93, "total_tokens": 1980480} |
| {"current_steps": 335, "total_steps": 600, "loss": 0.0, "lr": 0.12343728895206252, "epoch": 83.96, "percentage": 55.83, "elapsed_time": "0:07:26", "remaining_time": "0:05:53", "throughput": 4505.58, "total_tokens": 2011776} |
| {"current_steps": 340, "total_steps": 600, "loss": 0.0, "lr": 0.11958190569652316, "epoch": 85.0, "percentage": 56.67, "elapsed_time": "0:07:31", "remaining_time": "0:05:45", "throughput": 4506.85, "total_tokens": 2036736} |
| {"current_steps": 345, "total_steps": 600, "loss": 0.0, "lr": 0.11574736948340163, "epoch": 86.32, "percentage": 57.5, "elapsed_time": "0:07:39", "remaining_time": "0:05:39", "throughput": 4507.22, "total_tokens": 2068928} |
| {"current_steps": 350, "total_steps": 600, "loss": 0.0, "lr": 0.11193630831227916, "epoch": 87.64, "percentage": 58.33, "elapsed_time": "0:07:45", "remaining_time": "0:05:32", "throughput": 4509.71, "total_tokens": 2099520} |
| {"current_steps": 355, "total_steps": 600, "loss": 0.0, "lr": 0.10815133409411562, "epoch": 88.96, "percentage": 59.17, "elapsed_time": "0:07:52", "remaining_time": "0:05:26", "throughput": 4512.69, "total_tokens": 2132480} |
| {"current_steps": 360, "total_steps": 600, "loss": 0.0, "lr": 0.10439504086117644, "epoch": 90.0, "percentage": 60.0, "elapsed_time": "0:07:57", "remaining_time": "0:05:18", "throughput": 4513.22, "total_tokens": 2157184} |
| {"current_steps": 365, "total_steps": 600, "loss": 0.0, "lr": 0.10067000298921251, "epoch": 91.32, "percentage": 60.83, "elapsed_time": "0:08:04", "remaining_time": "0:05:12", "throughput": 4512.21, "total_tokens": 2188032} |
| {"current_steps": 370, "total_steps": 600, "loss": 0.0, "lr": 0.09697877343311145, "epoch": 92.64, "percentage": 61.67, "elapsed_time": "0:08:11", "remaining_time": "0:05:05", "throughput": 4516.05, "total_tokens": 2220480} |
| {"current_steps": 375, "total_steps": 600, "loss": 0.0, "lr": 0.09332388197722995, "epoch": 93.96, "percentage": 62.5, "elapsed_time": "0:08:18", "remaining_time": "0:04:58", "throughput": 4518.74, "total_tokens": 2251008} |
| {"current_steps": 380, "total_steps": 600, "loss": 0.0, "lr": 0.089707833501606, "epoch": 95.0, "percentage": 63.33, "elapsed_time": "0:08:23", "remaining_time": "0:04:51", "throughput": 4518.86, "total_tokens": 2276736} |
| {"current_steps": 385, "total_steps": 600, "loss": 0.0, "lr": 0.0861331062652391, "epoch": 96.32, "percentage": 64.17, "elapsed_time": "0:08:31", "remaining_time": "0:04:45", "throughput": 4518.94, "total_tokens": 2309504} |
| {"current_steps": 390, "total_steps": 600, "loss": 0.0, "lr": 0.08260215020761554, "epoch": 97.64, "percentage": 65.0, "elapsed_time": "0:08:37", "remaining_time": "0:04:38", "throughput": 4517.94, "total_tokens": 2339776} |
| {"current_steps": 395, "total_steps": 600, "loss": 0.0, "lr": 0.07911738526964192, "epoch": 98.96, "percentage": 65.83, "elapsed_time": "0:08:44", "remaining_time": "0:04:32", "throughput": 4518.43, "total_tokens": 2371584} |
| {"current_steps": 400, "total_steps": 600, "loss": 0.0, "lr": 0.07568119973513886, "epoch": 100.0, "percentage": 66.67, "elapsed_time": "0:08:50", "remaining_time": "0:04:25", "throughput": 4518.89, "total_tokens": 2396736} |
| {"current_steps": 400, "total_steps": 600, "epoch": 100.0, "percentage": 66.67, "elapsed_time": "0:08:52", "remaining_time": "0:04:26", "throughput": 4503.51, "total_tokens": 2396736} |
| {"current_steps": 405, "total_steps": 600, "loss": 0.0, "lr": 0.07229594859403049, "epoch": 101.32, "percentage": 67.5, "elapsed_time": "0:09:01", "remaining_time": "0:04:20", "throughput": 4487.5, "total_tokens": 2428864} |
| {"current_steps": 410, "total_steps": 600, "loss": 0.0, "lr": 0.06896395192835174, "epoch": 102.64, "percentage": 68.33, "elapsed_time": "0:09:07", "remaining_time": "0:04:13", "throughput": 4488.49, "total_tokens": 2459328} |
| {"current_steps": 415, "total_steps": 600, "loss": 0.0, "lr": 0.06568749332218045, "epoch": 103.96, "percentage": 69.17, "elapsed_time": "0:09:14", "remaining_time": "0:04:07", "throughput": 4491.38, "total_tokens": 2491456} |
| {"current_steps": 420, "total_steps": 600, "loss": 0.0, "lr": 0.06246881829658239, "epoch": 105.0, "percentage": 70.0, "elapsed_time": "0:09:20", "remaining_time": "0:04:00", "throughput": 4493.59, "total_tokens": 2516800} |
| {"current_steps": 425, "total_steps": 600, "loss": 0.0, "lr": 0.05931013277064377, "epoch": 106.32, "percentage": 70.83, "elapsed_time": "0:09:27", "remaining_time": "0:03:53", "throughput": 4494.86, "total_tokens": 2548800} |
| {"current_steps": 430, "total_steps": 600, "loss": 0.0, "lr": 0.05621360154964427, "epoch": 107.64, "percentage": 71.67, "elapsed_time": "0:09:33", "remaining_time": "0:03:46", "throughput": 4497.52, "total_tokens": 2580160} |
| {"current_steps": 435, "total_steps": 600, "loss": 0.0, "lr": 0.053181346841407386, "epoch": 108.96, "percentage": 72.5, "elapsed_time": "0:09:40", "remaining_time": "0:03:40", "throughput": 4500.02, "total_tokens": 2611200} |
| {"current_steps": 440, "total_steps": 600, "loss": 0.0, "lr": 0.050215446801845885, "epoch": 110.0, "percentage": 73.33, "elapsed_time": "0:09:45", "remaining_time": "0:03:32", "throughput": 4501.05, "total_tokens": 2635968} |
| {"current_steps": 445, "total_steps": 600, "loss": 0.0, "lr": 0.04731793411069669, "epoch": 111.32, "percentage": 74.17, "elapsed_time": "0:09:52", "remaining_time": "0:03:26", "throughput": 4502.41, "total_tokens": 2668736} |
| {"current_steps": 450, "total_steps": 600, "loss": 0.0, "lr": 0.044490794578424434, "epoch": 112.64, "percentage": 75.0, "elapsed_time": "0:09:59", "remaining_time": "0:03:19", "throughput": 4505.18, "total_tokens": 2699520} |
| {"current_steps": 455, "total_steps": 600, "loss": 0.0, "lr": 0.041735965785245674, "epoch": 113.96, "percentage": 75.83, "elapsed_time": "0:10:05", "remaining_time": "0:03:13", "throughput": 4507.19, "total_tokens": 2730304} |
| {"current_steps": 460, "total_steps": 600, "loss": 0.0, "lr": 0.03905533575320853, "epoch": 115.0, "percentage": 76.67, "elapsed_time": "0:10:11", "remaining_time": "0:03:06", "throughput": 4507.79, "total_tokens": 2755776} |
| {"current_steps": 465, "total_steps": 600, "loss": 0.0, "lr": 0.03645074165223656, "epoch": 116.32, "percentage": 77.5, "elapsed_time": "0:10:18", "remaining_time": "0:02:59", "throughput": 4509.03, "total_tokens": 2787968} |
| {"current_steps": 470, "total_steps": 600, "loss": 0.0, "lr": 0.03392396854102408, "epoch": 117.64, "percentage": 78.33, "elapsed_time": "0:10:24", "remaining_time": "0:02:52", "throughput": 4511.61, "total_tokens": 2819584} |
| {"current_steps": 475, "total_steps": 600, "loss": 0.0, "lr": 0.031476748143646434, "epoch": 118.96, "percentage": 79.17, "elapsed_time": "0:10:31", "remaining_time": "0:02:46", "throughput": 4514.08, "total_tokens": 2851072} |
| {"current_steps": 480, "total_steps": 600, "loss": 0.0, "lr": 0.029110757662722652, "epoch": 120.0, "percentage": 80.0, "elapsed_time": "0:10:36", "remaining_time": "0:02:39", "throughput": 4514.58, "total_tokens": 2875328} |
| {"current_steps": 485, "total_steps": 600, "loss": 0.0, "lr": 0.026827618629944393, "epoch": 121.32, "percentage": 80.83, "elapsed_time": "0:10:43", "remaining_time": "0:02:32", "throughput": 4515.09, "total_tokens": 2906496} |
| {"current_steps": 490, "total_steps": 600, "loss": 0.0, "lr": 0.024628895794759492, "epoch": 122.64, "percentage": 81.67, "elapsed_time": "0:10:50", "remaining_time": "0:02:26", "throughput": 4518.52, "total_tokens": 2939584} |
| {"current_steps": 495, "total_steps": 600, "loss": 0.0, "lr": 0.022516096051970434, "epoch": 123.96, "percentage": 82.5, "elapsed_time": "0:10:57", "remaining_time": "0:02:19", "throughput": 4519.35, "total_tokens": 2971008} |
| {"current_steps": 500, "total_steps": 600, "loss": 0.0, "lr": 0.020490667408984253, "epoch": 125.0, "percentage": 83.33, "elapsed_time": "0:11:02", "remaining_time": "0:02:12", "throughput": 4519.81, "total_tokens": 2995392} |
| {"current_steps": 505, "total_steps": 600, "loss": 0.0, "lr": 0.018553997993420494, "epoch": 126.32, "percentage": 84.17, "elapsed_time": "0:11:09", "remaining_time": "0:02:06", "throughput": 4519.94, "total_tokens": 3027904} |
| {"current_steps": 510, "total_steps": 600, "loss": 0.0, "lr": 0.016707415101757654, "epoch": 127.64, "percentage": 85.0, "elapsed_time": "0:11:16", "remaining_time": "0:01:59", "throughput": 4520.37, "total_tokens": 3057472} |
| {"current_steps": 515, "total_steps": 600, "loss": 0.0, "lr": 0.014952184289670972, "epoch": 128.96, "percentage": 85.83, "elapsed_time": "0:11:23", "remaining_time": "0:01:52", "throughput": 4521.73, "total_tokens": 3089216} |
| {"current_steps": 520, "total_steps": 600, "loss": 0.0, "lr": 0.013289508504683205, "epoch": 130.0, "percentage": 86.67, "elapsed_time": "0:11:28", "remaining_time": "0:01:45", "throughput": 4522.21, "total_tokens": 3114240} |
| {"current_steps": 525, "total_steps": 600, "loss": 0.0, "lr": 0.011720527261724938, "epoch": 131.32, "percentage": 87.5, "elapsed_time": "0:11:35", "remaining_time": "0:01:39", "throughput": 4522.21, "total_tokens": 3145600} |
| {"current_steps": 530, "total_steps": 600, "loss": 0.0, "lr": 0.010246315862167664, "epoch": 132.64, "percentage": 88.33, "elapsed_time": "0:11:42", "remaining_time": "0:01:32", "throughput": 4525.04, "total_tokens": 3178176} |
| {"current_steps": 535, "total_steps": 600, "loss": 0.0, "lr": 0.00886788465686618, "epoch": 133.96, "percentage": 89.17, "elapsed_time": "0:11:48", "remaining_time": "0:01:26", "throughput": 4527.01, "total_tokens": 3209344} |
| {"current_steps": 540, "total_steps": 600, "loss": 0.0, "lr": 0.007586178353714434, "epoch": 135.0, "percentage": 90.0, "elapsed_time": "0:11:54", "remaining_time": "0:01:19", "throughput": 4527.44, "total_tokens": 3234688} |
| {"current_steps": 545, "total_steps": 600, "loss": 0.0, "lr": 0.006402075370189914, "epoch": 136.32, "percentage": 90.83, "elapsed_time": "0:12:01", "remaining_time": "0:01:12", "throughput": 4526.39, "total_tokens": 3265344} |
| {"current_steps": 550, "total_steps": 600, "loss": 0.0, "lr": 0.005316387231330288, "epoch": 137.64, "percentage": 91.67, "elapsed_time": "0:12:08", "remaining_time": "0:01:06", "throughput": 4528.35, "total_tokens": 3297216} |
| {"current_steps": 555, "total_steps": 600, "loss": 0.0, "lr": 0.004329858013554605, "epoch": 138.96, "percentage": 92.5, "elapsed_time": "0:12:14", "remaining_time": "0:00:59", "throughput": 4530.31, "total_tokens": 3328832} |
| {"current_steps": 560, "total_steps": 600, "loss": 0.0, "lr": 0.0034431638347104552, "epoch": 140.0, "percentage": 93.33, "elapsed_time": "0:12:20", "remaining_time": "0:00:52", "throughput": 4530.68, "total_tokens": 3353856} |
| {"current_steps": 565, "total_steps": 600, "loss": 0.0, "lr": 0.0026569123906967085, "epoch": 141.32, "percentage": 94.17, "elapsed_time": "0:12:26", "remaining_time": "0:00:46", "throughput": 4531.16, "total_tokens": 3384640} |
| {"current_steps": 570, "total_steps": 600, "loss": 0.0, "lr": 0.0019716425389789127, "epoch": 142.64, "percentage": 95.0, "elapsed_time": "0:12:33", "remaining_time": "0:00:39", "throughput": 4533.1, "total_tokens": 3417280} |
| {"current_steps": 575, "total_steps": 600, "loss": 0.0, "lr": 0.0013878239292834603, "epoch": 143.96, "percentage": 95.83, "elapsed_time": "0:12:40", "remaining_time": "0:00:33", "throughput": 4533.22, "total_tokens": 3447808} |
| {"current_steps": 580, "total_steps": 600, "loss": 0.0, "lr": 0.0009058566817230606, "epoch": 145.0, "percentage": 96.67, "elapsed_time": "0:12:46", "remaining_time": "0:00:26", "throughput": 4532.52, "total_tokens": 3472192} |
| {"current_steps": 585, "total_steps": 600, "loss": 0.0, "lr": 0.0005260711125743444, "epoch": 146.32, "percentage": 97.5, "elapsed_time": "0:12:52", "remaining_time": "0:00:19", "throughput": 4533.34, "total_tokens": 3503616} |
| {"current_steps": 590, "total_steps": 600, "loss": 0.0, "lr": 0.0002487275078957518, "epoch": 147.64, "percentage": 98.33, "elapsed_time": "0:12:59", "remaining_time": "0:00:13", "throughput": 4535.92, "total_tokens": 3536128} |
| {"current_steps": 595, "total_steps": 600, "loss": 0.0, "lr": 7.401594514025999e-05, "epoch": 148.96, "percentage": 99.17, "elapsed_time": "0:13:06", "remaining_time": "0:00:06", "throughput": 4537.96, "total_tokens": 3567872} |
| {"current_steps": 600, "total_steps": 600, "loss": 0.0, "lr": 2.0561628859883107e-06, "epoch": 150.0, "percentage": 100.0, "elapsed_time": "0:13:11", "remaining_time": "0:00:00", "throughput": 4538.02, "total_tokens": 3592960} |
| {"current_steps": 600, "total_steps": 600, "epoch": 150.0, "percentage": 100.0, "elapsed_time": "0:13:13", "remaining_time": "0:00:00", "throughput": 4527.48, "total_tokens": 3592960} |
| {"current_steps": 600, "total_steps": 600, "epoch": 150.0, "percentage": 100.0, "elapsed_time": "0:13:15", "remaining_time": "0:00:00", "throughput": 4515.85, "total_tokens": 3592960} |
|
|