train_mnli_1744891318 / trainer_log.jsonl
rbelanec's picture
Training in progress, step 1000
11cb5d9 verified
{"current_steps": 5, "total_steps": 20000, "loss": 8.4796, "lr": 0.29999997039118775, "epoch": 0.0009054075465719007, "percentage": 0.03, "elapsed_time": "0:00:15", "remaining_time": "17:02:34", "throughput": 2423.6, "total_tokens": 37184}
{"current_steps": 10, "total_steps": 20000, "loss": 5.9943, "lr": 0.29999985010540814, "epoch": 0.0018108150931438014, "percentage": 0.05, "elapsed_time": "0:00:28", "remaining_time": "15:41:22", "throughput": 2500.61, "total_tokens": 70656}
{"current_steps": 15, "total_steps": 20000, "loss": 3.1346, "lr": 0.29999963729218443, "epoch": 0.002716222639715702, "percentage": 0.07, "elapsed_time": "0:00:41", "remaining_time": "15:13:23", "throughput": 2522.11, "total_tokens": 103744}
{"current_steps": 20, "total_steps": 20000, "loss": 2.173, "lr": 0.29999933195164796, "epoch": 0.0036216301862876028, "percentage": 0.1, "elapsed_time": "0:00:53", "remaining_time": "14:56:50", "throughput": 2531.98, "total_tokens": 136384}
{"current_steps": 25, "total_steps": 20000, "loss": 1.875, "lr": 0.2999989340839871, "epoch": 0.004527037732859503, "percentage": 0.12, "elapsed_time": "0:01:07", "remaining_time": "14:53:37", "throughput": 2556.93, "total_tokens": 171584}
{"current_steps": 30, "total_steps": 20000, "loss": 1.3949, "lr": 0.2999984436894472, "epoch": 0.005432445279431404, "percentage": 0.15, "elapsed_time": "0:01:20", "remaining_time": "14:48:09", "throughput": 2563.07, "total_tokens": 205184}
{"current_steps": 35, "total_steps": 20000, "loss": 0.9359, "lr": 0.29999786076833085, "epoch": 0.0063378528260033045, "percentage": 0.18, "elapsed_time": "0:01:32", "remaining_time": "14:43:22", "throughput": 2567.81, "total_tokens": 238592}
{"current_steps": 40, "total_steps": 20000, "loss": 0.5998, "lr": 0.29999718532099756, "epoch": 0.0072432603725752056, "percentage": 0.2, "elapsed_time": "0:01:46", "remaining_time": "14:46:07", "throughput": 2581.65, "total_tokens": 275072}
{"current_steps": 45, "total_steps": 20000, "loss": 0.4296, "lr": 0.29999641734786403, "epoch": 0.008148667919147106, "percentage": 0.22, "elapsed_time": "0:02:00", "remaining_time": "14:46:53", "throughput": 2589.86, "total_tokens": 310784}
{"current_steps": 50, "total_steps": 20000, "loss": 0.3741, "lr": 0.29999555684940393, "epoch": 0.009054075465719007, "percentage": 0.25, "elapsed_time": "0:02:12", "remaining_time": "14:43:53", "throughput": 2594.83, "total_tokens": 344896}
{"current_steps": 55, "total_steps": 20000, "loss": 0.3577, "lr": 0.2999946038261481, "epoch": 0.009959483012290908, "percentage": 0.27, "elapsed_time": "0:02:26", "remaining_time": "14:48:21", "throughput": 2609.05, "total_tokens": 383488}
{"current_steps": 60, "total_steps": 20000, "loss": 0.3565, "lr": 0.2999935582786844, "epoch": 0.010864890558862809, "percentage": 0.3, "elapsed_time": "0:02:39", "remaining_time": "14:44:48", "throughput": 2604.97, "total_tokens": 416128}
{"current_steps": 65, "total_steps": 20000, "loss": 0.396, "lr": 0.29999242020765776, "epoch": 0.011770298105434708, "percentage": 0.33, "elapsed_time": "0:02:53", "remaining_time": "14:44:23", "throughput": 2607.83, "total_tokens": 451200}
{"current_steps": 70, "total_steps": 20000, "loss": 0.3657, "lr": 0.2999911896137702, "epoch": 0.012675705652006609, "percentage": 0.35, "elapsed_time": "0:03:06", "remaining_time": "14:42:43", "throughput": 2607.14, "total_tokens": 484992}
{"current_steps": 75, "total_steps": 20000, "loss": 0.3487, "lr": 0.29998986649778087, "epoch": 0.01358111319857851, "percentage": 0.38, "elapsed_time": "0:03:19", "remaining_time": "14:41:59", "throughput": 2608.89, "total_tokens": 519680}
{"current_steps": 80, "total_steps": 20000, "loss": 0.3356, "lr": 0.29998845086050585, "epoch": 0.014486520745150411, "percentage": 0.4, "elapsed_time": "0:03:31", "remaining_time": "14:39:29", "throughput": 2605.91, "total_tokens": 552256}
{"current_steps": 85, "total_steps": 20000, "loss": 0.3435, "lr": 0.29998694270281845, "epoch": 0.015391928291722312, "percentage": 0.43, "elapsed_time": "0:03:44", "remaining_time": "14:37:32", "throughput": 2604.66, "total_tokens": 585344}
{"current_steps": 90, "total_steps": 20000, "loss": 0.3476, "lr": 0.2999853420256489, "epoch": 0.01629733583829421, "percentage": 0.45, "elapsed_time": "0:03:57", "remaining_time": "14:36:53", "throughput": 2604.33, "total_tokens": 619392}
{"current_steps": 95, "total_steps": 20000, "loss": 0.3515, "lr": 0.29998364882998463, "epoch": 0.017202743384866114, "percentage": 0.47, "elapsed_time": "0:04:11", "remaining_time": "14:37:14", "throughput": 2607.3, "total_tokens": 654976}
{"current_steps": 100, "total_steps": 20000, "loss": 0.3391, "lr": 0.2999818631168701, "epoch": 0.018108150931438013, "percentage": 0.5, "elapsed_time": "0:04:24", "remaining_time": "14:36:45", "throughput": 2607.71, "total_tokens": 689344}
{"current_steps": 105, "total_steps": 20000, "loss": 0.3621, "lr": 0.2999799848874068, "epoch": 0.019013558478009913, "percentage": 0.53, "elapsed_time": "0:04:37", "remaining_time": "14:37:09", "throughput": 2609.42, "total_tokens": 724800}
{"current_steps": 110, "total_steps": 20000, "loss": 0.346, "lr": 0.2999780141427533, "epoch": 0.019918966024581816, "percentage": 0.55, "elapsed_time": "0:04:50", "remaining_time": "14:36:21", "throughput": 2609.08, "total_tokens": 758720}
{"current_steps": 115, "total_steps": 20000, "loss": 0.3376, "lr": 0.2999759508841253, "epoch": 0.020824373571153715, "percentage": 0.57, "elapsed_time": "0:05:04", "remaining_time": "14:37:07", "throughput": 2613.14, "total_tokens": 795328}
{"current_steps": 120, "total_steps": 20000, "loss": 0.3354, "lr": 0.2999737951127955, "epoch": 0.021729781117725618, "percentage": 0.6, "elapsed_time": "0:05:17", "remaining_time": "14:36:49", "throughput": 2613.29, "total_tokens": 829888}
{"current_steps": 125, "total_steps": 20000, "loss": 0.3423, "lr": 0.2999715468300937, "epoch": 0.022635188664297517, "percentage": 0.62, "elapsed_time": "0:05:30", "remaining_time": "14:36:41", "throughput": 2614.95, "total_tokens": 865088}
{"current_steps": 130, "total_steps": 20000, "loss": 0.3411, "lr": 0.29996920603740673, "epoch": 0.023540596210869416, "percentage": 0.65, "elapsed_time": "0:05:44", "remaining_time": "14:36:44", "throughput": 2616.4, "total_tokens": 900480}
{"current_steps": 135, "total_steps": 20000, "loss": 0.3489, "lr": 0.2999667727361785, "epoch": 0.02444600375744132, "percentage": 0.68, "elapsed_time": "0:05:57", "remaining_time": "14:36:14", "throughput": 2618.66, "total_tokens": 935616}
{"current_steps": 140, "total_steps": 20000, "loss": 0.357, "lr": 0.29996424692791, "epoch": 0.025351411304013218, "percentage": 0.7, "elapsed_time": "0:06:10", "remaining_time": "14:36:00", "throughput": 2618.41, "total_tokens": 970176}
{"current_steps": 145, "total_steps": 20000, "loss": 0.3315, "lr": 0.2999616286141593, "epoch": 0.02625681885058512, "percentage": 0.73, "elapsed_time": "0:06:23", "remaining_time": "14:35:35", "throughput": 2619.47, "total_tokens": 1004992}
{"current_steps": 150, "total_steps": 20000, "loss": 0.3579, "lr": 0.29995891779654155, "epoch": 0.02716222639715702, "percentage": 0.75, "elapsed_time": "0:06:36", "remaining_time": "14:35:00", "throughput": 2619.18, "total_tokens": 1039104}
{"current_steps": 155, "total_steps": 20000, "loss": 0.355, "lr": 0.2999561144767288, "epoch": 0.02806763394372892, "percentage": 0.78, "elapsed_time": "0:06:49", "remaining_time": "14:34:20", "throughput": 2617.49, "total_tokens": 1072512}
{"current_steps": 160, "total_steps": 20000, "loss": 0.3572, "lr": 0.29995321865645036, "epoch": 0.028973041490300822, "percentage": 0.8, "elapsed_time": "0:07:02", "remaining_time": "14:33:50", "throughput": 2617.21, "total_tokens": 1106624}
{"current_steps": 165, "total_steps": 20000, "loss": 0.3397, "lr": 0.2999502303374925, "epoch": 0.02987844903687272, "percentage": 0.83, "elapsed_time": "0:07:16", "remaining_time": "14:33:42", "throughput": 2618.23, "total_tokens": 1141760}
{"current_steps": 170, "total_steps": 20000, "loss": 0.3573, "lr": 0.2999471495216986, "epoch": 0.030783856583444624, "percentage": 0.85, "elapsed_time": "0:07:29", "remaining_time": "14:33:46", "throughput": 2619.1, "total_tokens": 1177152}
{"current_steps": 175, "total_steps": 20000, "loss": 0.3641, "lr": 0.29994397621096897, "epoch": 0.03168926413001653, "percentage": 0.88, "elapsed_time": "0:07:42", "remaining_time": "14:33:21", "throughput": 2618.76, "total_tokens": 1211328}
{"current_steps": 180, "total_steps": 20000, "loss": 0.3529, "lr": 0.29994071040726117, "epoch": 0.03259467167658842, "percentage": 0.9, "elapsed_time": "0:07:55", "remaining_time": "14:32:27", "throughput": 2617.97, "total_tokens": 1244608}
{"current_steps": 185, "total_steps": 20000, "loss": 0.3404, "lr": 0.29993735211258965, "epoch": 0.033500079223160326, "percentage": 0.92, "elapsed_time": "0:08:08", "remaining_time": "14:32:28", "throughput": 2618.68, "total_tokens": 1279872}
{"current_steps": 190, "total_steps": 20000, "loss": 0.34, "lr": 0.299933901329026, "epoch": 0.03440548676973223, "percentage": 0.95, "elapsed_time": "0:08:21", "remaining_time": "14:32:20", "throughput": 2618.01, "total_tokens": 1314240}
{"current_steps": 195, "total_steps": 20000, "loss": 0.3413, "lr": 0.2999303580586988, "epoch": 0.035310894316304124, "percentage": 0.97, "elapsed_time": "0:08:35", "remaining_time": "14:32:23", "throughput": 2618.72, "total_tokens": 1349632}
{"current_steps": 200, "total_steps": 20000, "loss": 0.3442, "lr": 0.2999267223037937, "epoch": 0.03621630186287603, "percentage": 1.0, "elapsed_time": "0:08:48", "remaining_time": "14:32:30", "throughput": 2620.44, "total_tokens": 1385664}
{"current_steps": 200, "total_steps": 20000, "eval_loss": 0.3349427282810211, "epoch": 0.03621630186287603, "percentage": 1.0, "elapsed_time": "0:21:08", "remaining_time": "1 day, 10:53:45", "throughput": 1091.98, "total_tokens": 1385664}
{"current_steps": 205, "total_steps": 20000, "loss": 0.3333, "lr": 0.29992299406655354, "epoch": 0.03712170940944793, "percentage": 1.03, "elapsed_time": "0:21:22", "remaining_time": "1 day, 10:24:45", "throughput": 1106.97, "total_tokens": 1420224}
{"current_steps": 210, "total_steps": 20000, "loss": 0.3449, "lr": 0.299919173349278, "epoch": 0.038027116956019825, "percentage": 1.05, "elapsed_time": "0:21:36", "remaining_time": "1 day, 9:56:17", "throughput": 1122.85, "total_tokens": 1455744}
{"current_steps": 215, "total_steps": 20000, "loss": 0.3406, "lr": 0.29991526015432385, "epoch": 0.03893252450259173, "percentage": 1.07, "elapsed_time": "0:21:49", "remaining_time": "1 day, 9:28:33", "throughput": 1138.13, "total_tokens": 1490496}
{"current_steps": 220, "total_steps": 20000, "loss": 0.3196, "lr": 0.299911254484105, "epoch": 0.03983793204916363, "percentage": 1.1, "elapsed_time": "0:22:02", "remaining_time": "1 day, 9:02:26", "throughput": 1153.49, "total_tokens": 1526016}
{"current_steps": 225, "total_steps": 20000, "loss": 0.3317, "lr": 0.2999071563410924, "epoch": 0.040743339595735534, "percentage": 1.12, "elapsed_time": "0:22:16", "remaining_time": "1 day, 8:37:01", "throughput": 1168.13, "total_tokens": 1560640}
{"current_steps": 230, "total_steps": 20000, "loss": 0.349, "lr": 0.2999029657278139, "epoch": 0.04164874714230743, "percentage": 1.15, "elapsed_time": "0:22:29", "remaining_time": "1 day, 8:13:08", "throughput": 1183.16, "total_tokens": 1596544}
{"current_steps": 235, "total_steps": 20000, "loss": 0.3319, "lr": 0.2998986826468545, "epoch": 0.04255415468887933, "percentage": 1.18, "elapsed_time": "0:22:42", "remaining_time": "1 day, 7:49:47", "throughput": 1196.37, "total_tokens": 1629952}
{"current_steps": 240, "total_steps": 20000, "loss": 0.3645, "lr": 0.2998943071008562, "epoch": 0.043459562235451235, "percentage": 1.2, "elapsed_time": "0:22:55", "remaining_time": "1 day, 7:27:33", "throughput": 1209.89, "total_tokens": 1664256}
{"current_steps": 245, "total_steps": 20000, "loss": 0.3547, "lr": 0.2998898390925181, "epoch": 0.04436496978202313, "percentage": 1.23, "elapsed_time": "0:23:09", "remaining_time": "1 day, 7:06:46", "throughput": 1224.21, "total_tokens": 1700544}
{"current_steps": 250, "total_steps": 20000, "loss": 0.3551, "lr": 0.2998852786245963, "epoch": 0.045270377328595034, "percentage": 1.25, "elapsed_time": "0:23:22", "remaining_time": "1 day, 6:46:09", "throughput": 1236.96, "total_tokens": 1734400}
{"current_steps": 255, "total_steps": 20000, "loss": 0.3446, "lr": 0.29988062569990387, "epoch": 0.046175784875166936, "percentage": 1.27, "elapsed_time": "0:23:35", "remaining_time": "1 day, 6:26:35", "throughput": 1250.17, "total_tokens": 1769472}
{"current_steps": 260, "total_steps": 20000, "loss": 0.3815, "lr": 0.299875880321311, "epoch": 0.04708119242173883, "percentage": 1.3, "elapsed_time": "0:23:48", "remaining_time": "1 day, 6:07:38", "throughput": 1263.03, "total_tokens": 1804288}
{"current_steps": 265, "total_steps": 20000, "loss": 0.3563, "lr": 0.29987104249174495, "epoch": 0.047986599968310735, "percentage": 1.32, "elapsed_time": "0:24:01", "remaining_time": "1 day, 5:49:20", "throughput": 1275.09, "total_tokens": 1838208}
{"current_steps": 270, "total_steps": 20000, "loss": 0.3417, "lr": 0.2998661122141898, "epoch": 0.04889200751488264, "percentage": 1.35, "elapsed_time": "0:24:14", "remaining_time": "1 day, 5:31:42", "throughput": 1287.37, "total_tokens": 1872768}
{"current_steps": 275, "total_steps": 20000, "loss": 0.3418, "lr": 0.2998610894916869, "epoch": 0.04979741506145454, "percentage": 1.38, "elapsed_time": "0:24:27", "remaining_time": "1 day, 5:14:22", "throughput": 1298.63, "total_tokens": 1905792}
{"current_steps": 280, "total_steps": 20000, "loss": 0.3385, "lr": 0.29985597432733446, "epoch": 0.050702822608026436, "percentage": 1.4, "elapsed_time": "0:24:41", "remaining_time": "1 day, 4:59:02", "throughput": 1312.19, "total_tokens": 1944064}
{"current_steps": 285, "total_steps": 20000, "loss": 0.3418, "lr": 0.2998507667242878, "epoch": 0.05160823015459834, "percentage": 1.43, "elapsed_time": "0:24:54", "remaining_time": "1 day, 4:43:30", "throughput": 1324.44, "total_tokens": 1979904}
{"current_steps": 290, "total_steps": 20000, "loss": 0.342, "lr": 0.29984546668575923, "epoch": 0.05251363770117024, "percentage": 1.45, "elapsed_time": "0:25:07", "remaining_time": "1 day, 4:28:10", "throughput": 1335.79, "total_tokens": 2014336}
{"current_steps": 295, "total_steps": 20000, "loss": 0.3343, "lr": 0.299840074215018, "epoch": 0.05341904524774214, "percentage": 1.47, "elapsed_time": "0:25:20", "remaining_time": "1 day, 4:13:17", "throughput": 1346.61, "total_tokens": 2048192}
{"current_steps": 300, "total_steps": 20000, "loss": 0.347, "lr": 0.2998345893153906, "epoch": 0.05432445279431404, "percentage": 1.5, "elapsed_time": "0:25:34", "remaining_time": "1 day, 3:59:07", "throughput": 1358.02, "total_tokens": 2083520}
{"current_steps": 305, "total_steps": 20000, "loss": 0.3471, "lr": 0.29982901199026024, "epoch": 0.05522986034088594, "percentage": 1.52, "elapsed_time": "0:25:47", "remaining_time": "1 day, 3:45:14", "throughput": 1368.53, "total_tokens": 2117504}
{"current_steps": 310, "total_steps": 20000, "loss": 0.3302, "lr": 0.29982334224306745, "epoch": 0.05613526788745784, "percentage": 1.55, "elapsed_time": "0:26:00", "remaining_time": "1 day, 3:31:58", "throughput": 1379.35, "total_tokens": 2152512}
{"current_steps": 315, "total_steps": 20000, "loss": 0.3325, "lr": 0.2998175800773095, "epoch": 0.05704067543402974, "percentage": 1.57, "elapsed_time": "0:26:13", "remaining_time": "1 day, 3:19:08", "throughput": 1389.9, "total_tokens": 2187392}
{"current_steps": 320, "total_steps": 20000, "loss": 0.3271, "lr": 0.29981172549654084, "epoch": 0.057946082980601644, "percentage": 1.6, "elapsed_time": "0:26:27", "remaining_time": "1 day, 3:06:50", "throughput": 1400.31, "total_tokens": 2222528}
{"current_steps": 325, "total_steps": 20000, "loss": 0.3373, "lr": 0.2998057785043728, "epoch": 0.05885149052717355, "percentage": 1.62, "elapsed_time": "0:26:40", "remaining_time": "1 day, 2:54:52", "throughput": 1410.75, "total_tokens": 2257920}
{"current_steps": 330, "total_steps": 20000, "loss": 0.3443, "lr": 0.2997997391044739, "epoch": 0.05975689807374544, "percentage": 1.65, "elapsed_time": "0:26:53", "remaining_time": "1 day, 2:42:59", "throughput": 1420.5, "total_tokens": 2292096}
{"current_steps": 335, "total_steps": 20000, "loss": 0.3461, "lr": 0.2997936073005695, "epoch": 0.060662305620317346, "percentage": 1.68, "elapsed_time": "0:27:06", "remaining_time": "1 day, 2:31:19", "throughput": 1429.74, "total_tokens": 2325504}
{"current_steps": 340, "total_steps": 20000, "loss": 0.3647, "lr": 0.2997873830964419, "epoch": 0.06156771316688925, "percentage": 1.7, "elapsed_time": "0:27:19", "remaining_time": "1 day, 2:20:01", "throughput": 1439.16, "total_tokens": 2359488}
{"current_steps": 345, "total_steps": 20000, "loss": 0.3661, "lr": 0.29978106649593056, "epoch": 0.062473120713461144, "percentage": 1.73, "elapsed_time": "0:27:32", "remaining_time": "1 day, 2:09:10", "throughput": 1448.69, "total_tokens": 2394112}
{"current_steps": 350, "total_steps": 20000, "loss": 0.3476, "lr": 0.29977465750293203, "epoch": 0.06337852826003305, "percentage": 1.75, "elapsed_time": "0:27:45", "remaining_time": "1 day, 1:58:35", "throughput": 1457.76, "total_tokens": 2428160}
{"current_steps": 355, "total_steps": 20000, "loss": 0.3373, "lr": 0.29976815612139945, "epoch": 0.06428393580660495, "percentage": 1.77, "elapsed_time": "0:27:59", "remaining_time": "1 day, 1:49:11", "throughput": 1468.42, "total_tokens": 2466496}
{"current_steps": 360, "total_steps": 20000, "loss": 0.3408, "lr": 0.2997615623553434, "epoch": 0.06518934335317685, "percentage": 1.8, "elapsed_time": "0:28:13", "remaining_time": "1 day, 1:39:33", "throughput": 1478.25, "total_tokens": 2502976}
{"current_steps": 365, "total_steps": 20000, "loss": 0.3374, "lr": 0.2997548762088311, "epoch": 0.06609475089974876, "percentage": 1.82, "elapsed_time": "0:28:26", "remaining_time": "1 day, 1:29:58", "throughput": 1487.42, "total_tokens": 2538240}
{"current_steps": 370, "total_steps": 20000, "loss": 0.3445, "lr": 0.299748097685987, "epoch": 0.06700015844632065, "percentage": 1.85, "elapsed_time": "0:28:39", "remaining_time": "1 day, 1:20:19", "throughput": 1495.66, "total_tokens": 2571584}
{"current_steps": 375, "total_steps": 20000, "loss": 0.345, "lr": 0.29974122679099235, "epoch": 0.06790556599289255, "percentage": 1.88, "elapsed_time": "0:28:52", "remaining_time": "1 day, 1:11:18", "throughput": 1504.94, "total_tokens": 2607616}
{"current_steps": 380, "total_steps": 20000, "loss": 0.3322, "lr": 0.2997342635280856, "epoch": 0.06881097353946446, "percentage": 1.9, "elapsed_time": "0:29:06", "remaining_time": "1 day, 1:02:30", "throughput": 1513.38, "total_tokens": 2642432}
{"current_steps": 385, "total_steps": 20000, "loss": 0.328, "lr": 0.2997272079015619, "epoch": 0.06971638108603635, "percentage": 1.93, "elapsed_time": "0:29:19", "remaining_time": "1 day, 0:53:40", "throughput": 1521.72, "total_tokens": 2676800}
{"current_steps": 390, "total_steps": 20000, "loss": 0.3372, "lr": 0.29972005991577355, "epoch": 0.07062178863260825, "percentage": 1.95, "elapsed_time": "0:29:32", "remaining_time": "1 day, 0:45:12", "throughput": 1530.04, "total_tokens": 2711616}
{"current_steps": 395, "total_steps": 20000, "loss": 0.3347, "lr": 0.29971281957512985, "epoch": 0.07152719617918016, "percentage": 1.98, "elapsed_time": "0:29:45", "remaining_time": "1 day, 0:37:00", "throughput": 1538.21, "total_tokens": 2746496}
{"current_steps": 400, "total_steps": 20000, "loss": 0.3347, "lr": 0.299705486884097, "epoch": 0.07243260372575205, "percentage": 2.0, "elapsed_time": "0:29:59", "remaining_time": "1 day, 0:29:17", "throughput": 1547.35, "total_tokens": 2783872}
{"current_steps": 400, "total_steps": 20000, "eval_loss": 0.3339003622531891, "epoch": 0.07243260372575205, "percentage": 2.0, "elapsed_time": "0:42:19", "remaining_time": "1 day, 10:33:49", "throughput": 1096.28, "total_tokens": 2783872}
{"current_steps": 405, "total_steps": 20000, "loss": 0.3361, "lr": 0.29969806184719805, "epoch": 0.07333801127232395, "percentage": 2.02, "elapsed_time": "0:42:33", "remaining_time": "1 day, 10:19:04", "throughput": 1103.84, "total_tokens": 2818624}
{"current_steps": 410, "total_steps": 20000, "loss": 0.3245, "lr": 0.2996905444690132, "epoch": 0.07424341881889586, "percentage": 2.05, "elapsed_time": "0:42:46", "remaining_time": "1 day, 10:03:57", "throughput": 1111.77, "total_tokens": 2853568}
{"current_steps": 415, "total_steps": 20000, "loss": 0.3289, "lr": 0.2996829347541797, "epoch": 0.07514882636546776, "percentage": 2.08, "elapsed_time": "0:42:59", "remaining_time": "1 day, 9:49:10", "throughput": 1119.44, "total_tokens": 2888000}
{"current_steps": 420, "total_steps": 20000, "loss": 0.3311, "lr": 0.2996752327073913, "epoch": 0.07605423391203965, "percentage": 2.1, "elapsed_time": "0:43:12", "remaining_time": "1 day, 9:34:42", "throughput": 1127.0, "total_tokens": 2922304}
{"current_steps": 425, "total_steps": 20000, "loss": 0.3352, "lr": 0.2996674383333993, "epoch": 0.07695964145861156, "percentage": 2.12, "elapsed_time": "0:43:26", "remaining_time": "1 day, 9:20:45", "throughput": 1134.8, "total_tokens": 2957696}
{"current_steps": 430, "total_steps": 20000, "loss": 0.3344, "lr": 0.2996595516370115, "epoch": 0.07786504900518346, "percentage": 2.15, "elapsed_time": "0:43:39", "remaining_time": "1 day, 9:06:57", "throughput": 1142.45, "total_tokens": 2992640}
{"current_steps": 435, "total_steps": 20000, "loss": 0.3349, "lr": 0.2996515726230929, "epoch": 0.07877045655175535, "percentage": 2.17, "elapsed_time": "0:43:52", "remaining_time": "1 day, 8:53:18", "throughput": 1149.6, "total_tokens": 3026240}
{"current_steps": 440, "total_steps": 20000, "loss": 0.3597, "lr": 0.29964350129656525, "epoch": 0.07967586409832726, "percentage": 2.2, "elapsed_time": "0:44:05", "remaining_time": "1 day, 8:40:06", "throughput": 1156.72, "total_tokens": 3060160}
{"current_steps": 445, "total_steps": 20000, "loss": 0.3379, "lr": 0.2996353376624074, "epoch": 0.08058127164489916, "percentage": 2.23, "elapsed_time": "0:44:18", "remaining_time": "1 day, 8:27:13", "throughput": 1163.97, "total_tokens": 3094656}
{"current_steps": 450, "total_steps": 20000, "loss": 0.339, "lr": 0.2996270817256551, "epoch": 0.08148667919147107, "percentage": 2.25, "elapsed_time": "0:44:31", "remaining_time": "1 day, 8:14:35", "throughput": 1170.98, "total_tokens": 3128640}
{"current_steps": 455, "total_steps": 20000, "loss": 0.3485, "lr": 0.2996187334914011, "epoch": 0.08239208673804296, "percentage": 2.27, "elapsed_time": "0:44:44", "remaining_time": "1 day, 8:02:14", "throughput": 1178.1, "total_tokens": 3163136}
{"current_steps": 460, "total_steps": 20000, "loss": 0.3445, "lr": 0.29961029296479486, "epoch": 0.08329749428461486, "percentage": 2.3, "elapsed_time": "0:44:58", "remaining_time": "1 day, 7:50:19", "throughput": 1185.55, "total_tokens": 3198976}
{"current_steps": 465, "total_steps": 20000, "loss": 0.3469, "lr": 0.299601760151043, "epoch": 0.08420290183118677, "percentage": 2.33, "elapsed_time": "0:45:11", "remaining_time": "1 day, 7:38:27", "throughput": 1192.45, "total_tokens": 3233216}
{"current_steps": 470, "total_steps": 20000, "loss": 0.3409, "lr": 0.299593135055409, "epoch": 0.08510830937775866, "percentage": 2.35, "elapsed_time": "0:45:24", "remaining_time": "1 day, 7:26:52", "throughput": 1199.33, "total_tokens": 3267584}
{"current_steps": 475, "total_steps": 20000, "loss": 0.3362, "lr": 0.29958441768321326, "epoch": 0.08601371692433056, "percentage": 2.38, "elapsed_time": "0:45:38", "remaining_time": "1 day, 7:15:47", "throughput": 1206.47, "total_tokens": 3303360}
{"current_steps": 480, "total_steps": 20000, "loss": 0.3434, "lr": 0.2995756080398331, "epoch": 0.08691912447090247, "percentage": 2.4, "elapsed_time": "0:45:51", "remaining_time": "1 day, 7:04:38", "throughput": 1213.11, "total_tokens": 3337408}
{"current_steps": 485, "total_steps": 20000, "loss": 0.3419, "lr": 0.2995667061307026, "epoch": 0.08782453201747437, "percentage": 2.43, "elapsed_time": "0:46:04", "remaining_time": "1 day, 6:53:42", "throughput": 1219.83, "total_tokens": 3371840}
{"current_steps": 490, "total_steps": 20000, "loss": 0.3326, "lr": 0.29955771196131314, "epoch": 0.08872993956404626, "percentage": 2.45, "elapsed_time": "0:46:17", "remaining_time": "1 day, 6:43:11", "throughput": 1226.69, "total_tokens": 3407168}
{"current_steps": 495, "total_steps": 20000, "loss": 0.3462, "lr": 0.29954862553721257, "epoch": 0.08963534711061817, "percentage": 2.48, "elapsed_time": "0:46:31", "remaining_time": "1 day, 6:32:58", "throughput": 1233.64, "total_tokens": 3443136}
{"current_steps": 500, "total_steps": 20000, "loss": 0.3446, "lr": 0.29953944686400596, "epoch": 0.09054075465719007, "percentage": 2.5, "elapsed_time": "0:46:43", "remaining_time": "1 day, 6:22:27", "throughput": 1239.71, "total_tokens": 3475904}
{"current_steps": 505, "total_steps": 20000, "loss": 0.3365, "lr": 0.2995301759473552, "epoch": 0.09144616220376196, "percentage": 2.53, "elapsed_time": "0:46:56", "remaining_time": "1 day, 6:12:18", "throughput": 1246.09, "total_tokens": 3509952}
{"current_steps": 510, "total_steps": 20000, "loss": 0.3381, "lr": 0.29952081279297904, "epoch": 0.09235156975033387, "percentage": 2.55, "elapsed_time": "0:47:09", "remaining_time": "1 day, 6:02:21", "throughput": 1252.31, "total_tokens": 3543744}
{"current_steps": 515, "total_steps": 20000, "loss": 0.3292, "lr": 0.2995113574066531, "epoch": 0.09325697729690577, "percentage": 2.57, "elapsed_time": "0:47:23", "remaining_time": "1 day, 5:52:52", "throughput": 1258.88, "total_tokens": 3579264}
{"current_steps": 520, "total_steps": 20000, "loss": 0.3362, "lr": 0.2995018097942099, "epoch": 0.09416238484347766, "percentage": 2.6, "elapsed_time": "0:47:36", "remaining_time": "1 day, 5:43:24", "throughput": 1264.97, "total_tokens": 3613248}
{"current_steps": 525, "total_steps": 20000, "loss": 0.3286, "lr": 0.299492169961539, "epoch": 0.09506779239004957, "percentage": 2.62, "elapsed_time": "0:47:49", "remaining_time": "1 day, 5:33:54", "throughput": 1271.0, "total_tokens": 3646784}
{"current_steps": 530, "total_steps": 20000, "loss": 0.3317, "lr": 0.2994824379145867, "epoch": 0.09597319993662147, "percentage": 2.65, "elapsed_time": "0:48:02", "remaining_time": "1 day, 5:24:36", "throughput": 1276.93, "total_tokens": 3680256}
{"current_steps": 535, "total_steps": 20000, "loss": 0.3402, "lr": 0.2994726136593561, "epoch": 0.09687860748319337, "percentage": 2.67, "elapsed_time": "0:48:15", "remaining_time": "1 day, 5:15:55", "throughput": 1283.62, "total_tokens": 3716992}
{"current_steps": 540, "total_steps": 20000, "loss": 0.3405, "lr": 0.2994626972019075, "epoch": 0.09778401502976528, "percentage": 2.7, "elapsed_time": "0:48:28", "remaining_time": "1 day, 5:07:06", "throughput": 1289.61, "total_tokens": 3751296}
{"current_steps": 545, "total_steps": 20000, "loss": 0.3484, "lr": 0.29945268854835766, "epoch": 0.09868942257633717, "percentage": 2.73, "elapsed_time": "0:48:41", "remaining_time": "1 day, 4:58:25", "throughput": 1295.46, "total_tokens": 3785280}
{"current_steps": 550, "total_steps": 20000, "loss": 0.3352, "lr": 0.2994425877048806, "epoch": 0.09959483012290908, "percentage": 2.75, "elapsed_time": "0:48:55", "remaining_time": "1 day, 4:50:03", "throughput": 1301.67, "total_tokens": 3820800}
{"current_steps": 555, "total_steps": 20000, "loss": 0.3316, "lr": 0.2994323946777069, "epoch": 0.10050023766948098, "percentage": 2.77, "elapsed_time": "0:49:08", "remaining_time": "1 day, 4:41:38", "throughput": 1307.44, "total_tokens": 3854784}
{"current_steps": 560, "total_steps": 20000, "loss": 0.3366, "lr": 0.29942210947312414, "epoch": 0.10140564521605287, "percentage": 2.8, "elapsed_time": "0:49:21", "remaining_time": "1 day, 4:33:29", "throughput": 1313.33, "total_tokens": 3889536}
{"current_steps": 565, "total_steps": 20000, "loss": 0.3411, "lr": 0.29941173209747685, "epoch": 0.10231105276262478, "percentage": 2.83, "elapsed_time": "0:49:34", "remaining_time": "1 day, 4:25:32", "throughput": 1319.23, "total_tokens": 3924608}
{"current_steps": 570, "total_steps": 20000, "loss": 0.3367, "lr": 0.29940126255716626, "epoch": 0.10321646030919668, "percentage": 2.85, "elapsed_time": "0:49:48", "remaining_time": "1 day, 4:17:37", "throughput": 1324.89, "total_tokens": 3958912}
{"current_steps": 575, "total_steps": 20000, "loss": 0.3369, "lr": 0.2993907008586505, "epoch": 0.10412186785576857, "percentage": 2.88, "elapsed_time": "0:50:01", "remaining_time": "1 day, 4:10:13", "throughput": 1331.38, "total_tokens": 3996736}
{"current_steps": 580, "total_steps": 20000, "loss": 0.3363, "lr": 0.2993800470084445, "epoch": 0.10502727540234048, "percentage": 2.9, "elapsed_time": "0:50:14", "remaining_time": "1 day, 4:02:26", "throughput": 1336.77, "total_tokens": 4030208}
{"current_steps": 585, "total_steps": 20000, "loss": 0.3434, "lr": 0.2993693010131202, "epoch": 0.10593268294891238, "percentage": 2.93, "elapsed_time": "0:50:27", "remaining_time": "1 day, 3:54:42", "throughput": 1341.91, "total_tokens": 4062848}
{"current_steps": 590, "total_steps": 20000, "loss": 0.3334, "lr": 0.2993584628793063, "epoch": 0.10683809049548428, "percentage": 2.95, "elapsed_time": "0:50:41", "remaining_time": "1 day, 3:47:25", "throughput": 1347.64, "total_tokens": 4098240}
{"current_steps": 595, "total_steps": 20000, "loss": 0.3344, "lr": 0.29934753261368807, "epoch": 0.10774349804205618, "percentage": 2.97, "elapsed_time": "0:50:54", "remaining_time": "1 day, 3:40:07", "throughput": 1353.05, "total_tokens": 4132480}
{"current_steps": 600, "total_steps": 20000, "loss": 0.3392, "lr": 0.29933651022300806, "epoch": 0.10864890558862808, "percentage": 3.0, "elapsed_time": "0:51:07", "remaining_time": "1 day, 3:33:06", "throughput": 1358.85, "total_tokens": 4168448}
{"current_steps": 600, "total_steps": 20000, "eval_loss": 0.33281853795051575, "epoch": 0.10864890558862808, "percentage": 3.0, "elapsed_time": "1:03:28", "remaining_time": "1 day, 10:12:12", "throughput": 1094.59, "total_tokens": 4168448}
{"current_steps": 605, "total_steps": 20000, "loss": 0.3378, "lr": 0.2993253957140654, "epoch": 0.10955431313519998, "percentage": 3.02, "elapsed_time": "1:03:42", "remaining_time": "1 day, 10:02:10", "throughput": 1099.64, "total_tokens": 4203008}
{"current_steps": 610, "total_steps": 20000, "loss": 0.3353, "lr": 0.29931418909371604, "epoch": 0.11045972068177189, "percentage": 3.05, "elapsed_time": "1:03:55", "remaining_time": "1 day, 9:51:50", "throughput": 1104.7, "total_tokens": 4236800}
{"current_steps": 615, "total_steps": 20000, "loss": 0.324, "lr": 0.29930289036887286, "epoch": 0.11136512822834378, "percentage": 3.08, "elapsed_time": "1:04:08", "remaining_time": "1 day, 9:41:44", "throughput": 1110.02, "total_tokens": 4271872}
{"current_steps": 620, "total_steps": 20000, "loss": 0.3457, "lr": 0.2992914995465053, "epoch": 0.11227053577491568, "percentage": 3.1, "elapsed_time": "1:04:21", "remaining_time": "1 day, 9:31:53", "throughput": 1115.34, "total_tokens": 4307264}
{"current_steps": 625, "total_steps": 20000, "loss": 0.3378, "lr": 0.29928001663364, "epoch": 0.11317594332148759, "percentage": 3.12, "elapsed_time": "1:04:35", "remaining_time": "1 day, 9:22:17", "throughput": 1120.85, "total_tokens": 4343744}
{"current_steps": 630, "total_steps": 20000, "loss": 0.3353, "lr": 0.29926844163736005, "epoch": 0.11408135086805948, "percentage": 3.15, "elapsed_time": "1:04:48", "remaining_time": "1 day, 9:12:47", "throughput": 1126.26, "total_tokens": 4379904}
{"current_steps": 635, "total_steps": 20000, "loss": 0.3303, "lr": 0.2992567745648056, "epoch": 0.11498675841463138, "percentage": 3.17, "elapsed_time": "1:05:01", "remaining_time": "1 day, 9:03:05", "throughput": 1130.99, "total_tokens": 4412736}
{"current_steps": 640, "total_steps": 20000, "loss": 0.3329, "lr": 0.29924501542317344, "epoch": 0.11589216596120329, "percentage": 3.2, "elapsed_time": "1:05:14", "remaining_time": "1 day, 8:53:38", "throughput": 1135.86, "total_tokens": 4446528}
{"current_steps": 645, "total_steps": 20000, "loss": 0.3302, "lr": 0.2992331642197172, "epoch": 0.11679757350777518, "percentage": 3.23, "elapsed_time": "1:05:28", "remaining_time": "1 day, 8:44:34", "throughput": 1141.19, "total_tokens": 4482752}
{"current_steps": 650, "total_steps": 20000, "loss": 0.323, "lr": 0.29922122096174725, "epoch": 0.1177029810543471, "percentage": 3.25, "elapsed_time": "1:05:41", "remaining_time": "1 day, 8:35:26", "throughput": 1146.11, "total_tokens": 4517056}
{"current_steps": 655, "total_steps": 20000, "loss": 0.3314, "lr": 0.29920918565663085, "epoch": 0.11860838860091899, "percentage": 3.28, "elapsed_time": "1:05:54", "remaining_time": "1 day, 8:26:27", "throughput": 1151.04, "total_tokens": 4551552}
{"current_steps": 660, "total_steps": 20000, "loss": 0.3357, "lr": 0.299197058311792, "epoch": 0.11951379614749089, "percentage": 3.3, "elapsed_time": "1:06:07", "remaining_time": "1 day, 8:17:37", "throughput": 1155.85, "total_tokens": 4585728}
{"current_steps": 665, "total_steps": 20000, "loss": 0.3411, "lr": 0.29918483893471143, "epoch": 0.1204192036940628, "percentage": 3.33, "elapsed_time": "1:06:20", "remaining_time": "1 day, 8:09:00", "throughput": 1160.81, "total_tokens": 4620864}
{"current_steps": 670, "total_steps": 20000, "loss": 0.3276, "lr": 0.2991725275329266, "epoch": 0.12132461124063469, "percentage": 3.35, "elapsed_time": "1:06:34", "remaining_time": "1 day, 8:00:39", "throughput": 1166.11, "total_tokens": 4657856}
{"current_steps": 675, "total_steps": 20000, "loss": 0.3399, "lr": 0.29916012411403187, "epoch": 0.12223001878720659, "percentage": 3.38, "elapsed_time": "1:06:47", "remaining_time": "1 day, 7:52:04", "throughput": 1170.71, "total_tokens": 4691264}
{"current_steps": 680, "total_steps": 20000, "loss": 0.3355, "lr": 0.2991476286856783, "epoch": 0.1231354263337785, "percentage": 3.4, "elapsed_time": "1:07:00", "remaining_time": "1 day, 7:43:48", "throughput": 1175.51, "total_tokens": 4726080}
{"current_steps": 685, "total_steps": 20000, "loss": 0.3416, "lr": 0.29913504125557366, "epoch": 0.12404083388035039, "percentage": 3.43, "elapsed_time": "1:07:13", "remaining_time": "1 day, 7:35:41", "throughput": 1180.36, "total_tokens": 4761344}
{"current_steps": 690, "total_steps": 20000, "loss": 0.343, "lr": 0.29912236183148255, "epoch": 0.12494624142692229, "percentage": 3.45, "elapsed_time": "1:07:27", "remaining_time": "1 day, 7:27:39", "throughput": 1185.18, "total_tokens": 4796544}
{"current_steps": 695, "total_steps": 20000, "loss": 0.3295, "lr": 0.29910959042122626, "epoch": 0.12585164897349418, "percentage": 3.48, "elapsed_time": "1:07:40", "remaining_time": "1 day, 7:19:41", "throughput": 1189.81, "total_tokens": 4830912}
{"current_steps": 700, "total_steps": 20000, "loss": 0.3341, "lr": 0.2990967270326828, "epoch": 0.1267570565200661, "percentage": 3.5, "elapsed_time": "1:07:53", "remaining_time": "1 day, 7:11:49", "throughput": 1194.34, "total_tokens": 4865024}
{"current_steps": 705, "total_steps": 20000, "loss": 0.3343, "lr": 0.299083771673787, "epoch": 0.127662464066638, "percentage": 3.52, "elapsed_time": "1:08:06", "remaining_time": "1 day, 7:03:57", "throughput": 1198.64, "total_tokens": 4897984}
{"current_steps": 710, "total_steps": 20000, "loss": 0.3392, "lr": 0.2990707243525304, "epoch": 0.1285678716132099, "percentage": 3.55, "elapsed_time": "1:08:19", "remaining_time": "1 day, 6:56:23", "throughput": 1203.22, "total_tokens": 4932800}
{"current_steps": 715, "total_steps": 20000, "loss": 0.3433, "lr": 0.2990575850769612, "epoch": 0.1294732791597818, "percentage": 3.57, "elapsed_time": "1:08:32", "remaining_time": "1 day, 6:48:54", "throughput": 1207.84, "total_tokens": 4967744}
{"current_steps": 720, "total_steps": 20000, "loss": 0.3321, "lr": 0.2990443538551843, "epoch": 0.1303786867063537, "percentage": 3.6, "elapsed_time": "1:08:46", "remaining_time": "1 day, 6:41:25", "throughput": 1212.26, "total_tokens": 5001792}
{"current_steps": 725, "total_steps": 20000, "loss": 0.3431, "lr": 0.29903103069536147, "epoch": 0.1312840942529256, "percentage": 3.62, "elapsed_time": "1:08:59", "remaining_time": "1 day, 6:34:04", "throughput": 1216.71, "total_tokens": 5036160}
{"current_steps": 730, "total_steps": 20000, "loss": 0.3392, "lr": 0.29901761560571116, "epoch": 0.1321895017994975, "percentage": 3.65, "elapsed_time": "1:09:12", "remaining_time": "1 day, 6:26:50", "throughput": 1221.12, "total_tokens": 5070528}
{"current_steps": 735, "total_steps": 20000, "loss": 0.3366, "lr": 0.2990041085945083, "epoch": 0.1330949093460694, "percentage": 3.67, "elapsed_time": "1:09:25", "remaining_time": "1 day, 6:19:43", "throughput": 1225.57, "total_tokens": 5105216}
{"current_steps": 740, "total_steps": 20000, "loss": 0.3346, "lr": 0.2989905096700849, "epoch": 0.1340003168926413, "percentage": 3.7, "elapsed_time": "1:09:38", "remaining_time": "1 day, 6:12:44", "throughput": 1230.16, "total_tokens": 5140736}
{"current_steps": 745, "total_steps": 20000, "loss": 0.3398, "lr": 0.2989768188408293, "epoch": 0.1349057244392132, "percentage": 3.72, "elapsed_time": "1:09:51", "remaining_time": "1 day, 6:05:44", "throughput": 1234.61, "total_tokens": 5175488}
{"current_steps": 750, "total_steps": 20000, "loss": 0.338, "lr": 0.2989630361151867, "epoch": 0.1358111319857851, "percentage": 3.75, "elapsed_time": "1:10:04", "remaining_time": "1 day, 5:58:45", "throughput": 1238.85, "total_tokens": 5209216}
{"current_steps": 755, "total_steps": 20000, "loss": 0.3314, "lr": 0.29894916150165907, "epoch": 0.136716539532357, "percentage": 3.77, "elapsed_time": "1:10:18", "remaining_time": "1 day, 5:52:10", "throughput": 1243.54, "total_tokens": 5245888}
{"current_steps": 760, "total_steps": 20000, "loss": 0.3389, "lr": 0.2989351950088049, "epoch": 0.1376219470789289, "percentage": 3.8, "elapsed_time": "1:10:32", "remaining_time": "1 day, 5:45:42", "throughput": 1248.35, "total_tokens": 5283328}
{"current_steps": 765, "total_steps": 20000, "loss": 0.3442, "lr": 0.29892113664523945, "epoch": 0.1385273546255008, "percentage": 3.82, "elapsed_time": "1:10:45", "remaining_time": "1 day, 5:39:11", "throughput": 1252.82, "total_tokens": 5319040}
{"current_steps": 770, "total_steps": 20000, "loss": 0.3315, "lr": 0.29890698641963465, "epoch": 0.1394327621720727, "percentage": 3.85, "elapsed_time": "1:10:59", "remaining_time": "1 day, 5:32:45", "throughput": 1257.21, "total_tokens": 5354496}
{"current_steps": 775, "total_steps": 20000, "loss": 0.3504, "lr": 0.298892744340719, "epoch": 0.1403381697186446, "percentage": 3.88, "elapsed_time": "1:11:12", "remaining_time": "1 day, 5:26:17", "throughput": 1261.31, "total_tokens": 5388544}
{"current_steps": 780, "total_steps": 20000, "loss": 0.3425, "lr": 0.2988784104172778, "epoch": 0.1412435772652165, "percentage": 3.9, "elapsed_time": "1:11:24", "remaining_time": "1 day, 5:19:46", "throughput": 1265.23, "total_tokens": 5421504}
{"current_steps": 785, "total_steps": 20000, "loss": 0.3366, "lr": 0.2988639846581529, "epoch": 0.1421489848117884, "percentage": 3.92, "elapsed_time": "1:11:38", "remaining_time": "1 day, 5:13:32", "throughput": 1269.43, "total_tokens": 5456384}
{"current_steps": 790, "total_steps": 20000, "loss": 0.3346, "lr": 0.2988494670722428, "epoch": 0.14305439235836032, "percentage": 3.95, "elapsed_time": "1:11:51", "remaining_time": "1 day, 5:07:18", "throughput": 1273.43, "total_tokens": 5490304}
{"current_steps": 795, "total_steps": 20000, "loss": 0.3474, "lr": 0.2988348576685027, "epoch": 0.1439597999049322, "percentage": 3.98, "elapsed_time": "1:12:04", "remaining_time": "1 day, 5:01:11", "throughput": 1277.62, "total_tokens": 5525248}
{"current_steps": 800, "total_steps": 20000, "loss": 0.3417, "lr": 0.29882015645594445, "epoch": 0.1448652074515041, "percentage": 4.0, "elapsed_time": "1:12:17", "remaining_time": "1 day, 4:55:06", "throughput": 1281.63, "total_tokens": 5559424}
{"current_steps": 800, "total_steps": 20000, "eval_loss": 0.3351232707500458, "epoch": 0.1448652074515041, "percentage": 4.0, "elapsed_time": "1:24:39", "remaining_time": "1 day, 9:51:42", "throughput": 1094.53, "total_tokens": 5559424}
{"current_steps": 805, "total_steps": 20000, "loss": 0.3489, "lr": 0.29880536344363645, "epoch": 0.145770614998076, "percentage": 4.03, "elapsed_time": "1:24:53", "remaining_time": "1 day, 9:44:11", "throughput": 1098.33, "total_tokens": 5594240}
{"current_steps": 810, "total_steps": 20000, "loss": 0.3407, "lr": 0.29879047864070385, "epoch": 0.1466760225446479, "percentage": 4.05, "elapsed_time": "1:25:06", "remaining_time": "1 day, 9:36:17", "throughput": 1102.09, "total_tokens": 5627712}
{"current_steps": 815, "total_steps": 20000, "loss": 0.3289, "lr": 0.2987755020563283, "epoch": 0.14758143009121982, "percentage": 4.08, "elapsed_time": "1:25:19", "remaining_time": "1 day, 9:28:40", "throughput": 1106.28, "total_tokens": 5664000}
{"current_steps": 820, "total_steps": 20000, "loss": 0.3387, "lr": 0.29876043369974803, "epoch": 0.14848683763779172, "percentage": 4.1, "elapsed_time": "1:25:33", "remaining_time": "1 day, 9:21:08", "throughput": 1110.25, "total_tokens": 5699200}
{"current_steps": 825, "total_steps": 20000, "loss": 0.3334, "lr": 0.2987452735802581, "epoch": 0.14939224518436361, "percentage": 4.12, "elapsed_time": "1:25:46", "remaining_time": "1 day, 9:13:40", "throughput": 1114.22, "total_tokens": 5734528}
{"current_steps": 830, "total_steps": 20000, "loss": 0.3356, "lr": 0.29873002170720997, "epoch": 0.1502976527309355, "percentage": 4.15, "elapsed_time": "1:25:59", "remaining_time": "1 day, 9:06:15", "throughput": 1118.12, "total_tokens": 5769408}
{"current_steps": 835, "total_steps": 20000, "loss": 0.3288, "lr": 0.2987146780900117, "epoch": 0.1512030602775074, "percentage": 4.17, "elapsed_time": "1:26:12", "remaining_time": "1 day, 8:58:49", "throughput": 1121.88, "total_tokens": 5803392}
{"current_steps": 840, "total_steps": 20000, "loss": 0.3235, "lr": 0.29869924273812803, "epoch": 0.1521084678240793, "percentage": 4.2, "elapsed_time": "1:26:25", "remaining_time": "1 day, 8:51:20", "throughput": 1125.37, "total_tokens": 5835712}
{"current_steps": 845, "total_steps": 20000, "loss": 0.3314, "lr": 0.2986837156610804, "epoch": 0.15301387537065123, "percentage": 4.23, "elapsed_time": "1:26:38", "remaining_time": "1 day, 8:44:11", "throughput": 1129.11, "total_tokens": 5870080}
{"current_steps": 850, "total_steps": 20000, "loss": 0.3345, "lr": 0.2986680968684465, "epoch": 0.15391928291722312, "percentage": 4.25, "elapsed_time": "1:26:52", "remaining_time": "1 day, 8:37:10", "throughput": 1133.02, "total_tokens": 5905664}
{"current_steps": 855, "total_steps": 20000, "loss": 0.34, "lr": 0.29865238636986086, "epoch": 0.15482469046379502, "percentage": 4.28, "elapsed_time": "1:27:05", "remaining_time": "1 day, 8:30:03", "throughput": 1136.59, "total_tokens": 5939008}
{"current_steps": 860, "total_steps": 20000, "loss": 0.3313, "lr": 0.29863658417501454, "epoch": 0.1557300980103669, "percentage": 4.3, "elapsed_time": "1:27:18", "remaining_time": "1 day, 8:23:12", "throughput": 1140.59, "total_tokens": 5975232}
{"current_steps": 865, "total_steps": 20000, "loss": 0.3319, "lr": 0.2986206902936551, "epoch": 0.1566355055569388, "percentage": 4.32, "elapsed_time": "1:27:32", "remaining_time": "1 day, 8:16:23", "throughput": 1144.42, "total_tokens": 6010624}
{"current_steps": 870, "total_steps": 20000, "loss": 0.3162, "lr": 0.2986047047355867, "epoch": 0.1575409131035107, "percentage": 4.35, "elapsed_time": "1:27:45", "remaining_time": "1 day, 8:09:31", "throughput": 1148.05, "total_tokens": 6044608}
{"current_steps": 875, "total_steps": 20000, "loss": 0.3201, "lr": 0.29858862751067, "epoch": 0.15844632065008263, "percentage": 4.38, "elapsed_time": "1:27:58", "remaining_time": "1 day, 8:02:53", "throughput": 1151.85, "total_tokens": 6080064}
{"current_steps": 880, "total_steps": 20000, "loss": 0.3223, "lr": 0.29857245862882226, "epoch": 0.15935172819665452, "percentage": 4.4, "elapsed_time": "1:28:11", "remaining_time": "1 day, 7:56:16", "throughput": 1155.72, "total_tokens": 6115840}
{"current_steps": 885, "total_steps": 20000, "loss": 0.315, "lr": 0.29855619810001727, "epoch": 0.16025713574322642, "percentage": 4.42, "elapsed_time": "1:28:25", "remaining_time": "1 day, 7:49:47", "throughput": 1159.55, "total_tokens": 6151744}
{"current_steps": 890, "total_steps": 20000, "loss": 0.3098, "lr": 0.2985398459342853, "epoch": 0.16116254328979832, "percentage": 4.45, "elapsed_time": "1:28:38", "remaining_time": "1 day, 7:43:26", "throughput": 1163.41, "total_tokens": 6188032}
{"current_steps": 895, "total_steps": 20000, "loss": 0.3145, "lr": 0.29852340214171325, "epoch": 0.1620679508363702, "percentage": 4.47, "elapsed_time": "1:28:52", "remaining_time": "1 day, 7:37:07", "throughput": 1167.31, "total_tokens": 6224576}
{"current_steps": 900, "total_steps": 20000, "loss": 0.3224, "lr": 0.2985068667324444, "epoch": 0.16297335838294214, "percentage": 4.5, "elapsed_time": "1:29:05", "remaining_time": "1 day, 7:30:51", "throughput": 1171.16, "total_tokens": 6260864}
{"current_steps": 905, "total_steps": 20000, "loss": 0.3317, "lr": 0.2984902397166787, "epoch": 0.16387876592951403, "percentage": 4.52, "elapsed_time": "1:29:19", "remaining_time": "1 day, 7:24:37", "throughput": 1174.81, "total_tokens": 6296128}
{"current_steps": 910, "total_steps": 20000, "loss": 0.3142, "lr": 0.2984735211046725, "epoch": 0.16478417347608593, "percentage": 4.55, "elapsed_time": "1:29:32", "remaining_time": "1 day, 7:18:22", "throughput": 1178.23, "total_tokens": 6329920}
{"current_steps": 915, "total_steps": 20000, "loss": 0.3451, "lr": 0.29845671090673864, "epoch": 0.16568958102265782, "percentage": 4.58, "elapsed_time": "1:29:45", "remaining_time": "1 day, 7:12:06", "throughput": 1181.56, "total_tokens": 6363072}
{"current_steps": 920, "total_steps": 20000, "loss": 0.3904, "lr": 0.2984398091332466, "epoch": 0.16659498856922972, "percentage": 4.6, "elapsed_time": "1:29:58", "remaining_time": "1 day, 7:05:52", "throughput": 1184.82, "total_tokens": 6395840}
{"current_steps": 925, "total_steps": 20000, "loss": 2.5884, "lr": 0.2984228157946221, "epoch": 0.16750039611580161, "percentage": 4.62, "elapsed_time": "1:30:11", "remaining_time": "1 day, 6:59:49", "throughput": 1188.31, "total_tokens": 6430272}
{"current_steps": 930, "total_steps": 20000, "loss": 1.0429, "lr": 0.2984057309013476, "epoch": 0.16840580366237354, "percentage": 4.65, "elapsed_time": "1:30:24", "remaining_time": "1 day, 6:53:54", "throughput": 1191.98, "total_tokens": 6466112}
{"current_steps": 935, "total_steps": 20000, "loss": 0.5225, "lr": 0.29838855446396184, "epoch": 0.16931121120894543, "percentage": 4.67, "elapsed_time": "1:30:37", "remaining_time": "1 day, 6:47:58", "throughput": 1195.43, "total_tokens": 6500480}
{"current_steps": 940, "total_steps": 20000, "loss": 0.3775, "lr": 0.29837128649306016, "epoch": 0.17021661875551733, "percentage": 4.7, "elapsed_time": "1:30:51", "remaining_time": "1 day, 6:42:09", "throughput": 1198.98, "total_tokens": 6535744}
{"current_steps": 945, "total_steps": 20000, "loss": 0.3523, "lr": 0.2983539269992943, "epoch": 0.17112202630208923, "percentage": 4.72, "elapsed_time": "1:31:04", "remaining_time": "1 day, 6:36:23", "throughput": 1202.46, "total_tokens": 6570688}
{"current_steps": 950, "total_steps": 20000, "loss": 0.3351, "lr": 0.2983364759933725, "epoch": 0.17202743384866112, "percentage": 4.75, "elapsed_time": "1:31:17", "remaining_time": "1 day, 6:30:48", "throughput": 1206.08, "total_tokens": 6606912}
{"current_steps": 955, "total_steps": 20000, "loss": 0.3402, "lr": 0.2983189334860593, "epoch": 0.17293284139523302, "percentage": 4.78, "elapsed_time": "1:31:30", "remaining_time": "1 day, 6:25:03", "throughput": 1209.27, "total_tokens": 6640064}
{"current_steps": 960, "total_steps": 20000, "loss": 0.3722, "lr": 0.29830129948817596, "epoch": 0.17383824894180494, "percentage": 4.8, "elapsed_time": "1:31:44", "remaining_time": "1 day, 6:19:23", "throughput": 1212.46, "total_tokens": 6673408}
{"current_steps": 965, "total_steps": 20000, "loss": 0.3689, "lr": 0.2982835740105999, "epoch": 0.17474365648837684, "percentage": 4.83, "elapsed_time": "1:31:57", "remaining_time": "1 day, 6:13:51", "throughput": 1215.83, "total_tokens": 6708160}
{"current_steps": 970, "total_steps": 20000, "loss": 0.3638, "lr": 0.29826575706426517, "epoch": 0.17564906403494873, "percentage": 4.85, "elapsed_time": "1:32:10", "remaining_time": "1 day, 6:08:18", "throughput": 1219.11, "total_tokens": 6742144}
{"current_steps": 975, "total_steps": 20000, "loss": 0.3562, "lr": 0.29824784866016213, "epoch": 0.17655447158152063, "percentage": 4.88, "elapsed_time": "1:32:23", "remaining_time": "1 day, 6:02:49", "throughput": 1222.33, "total_tokens": 6776000}
{"current_steps": 980, "total_steps": 20000, "loss": 0.3465, "lr": 0.29822984880933745, "epoch": 0.17745987912809252, "percentage": 4.9, "elapsed_time": "1:32:36", "remaining_time": "1 day, 5:57:28", "throughput": 1225.68, "total_tokens": 6810944}
{"current_steps": 985, "total_steps": 20000, "loss": 0.3617, "lr": 0.2982117575228945, "epoch": 0.17836528667466445, "percentage": 4.92, "elapsed_time": "1:32:50", "remaining_time": "1 day, 5:52:10", "throughput": 1229.08, "total_tokens": 6846272}
{"current_steps": 990, "total_steps": 20000, "loss": 0.3686, "lr": 0.29819357481199293, "epoch": 0.17927069422123634, "percentage": 4.95, "elapsed_time": "1:33:03", "remaining_time": "1 day, 5:46:52", "throughput": 1232.39, "total_tokens": 6880960}
{"current_steps": 995, "total_steps": 20000, "loss": 0.3399, "lr": 0.29817530068784864, "epoch": 0.18017610176780824, "percentage": 4.98, "elapsed_time": "1:33:16", "remaining_time": "1 day, 5:41:35", "throughput": 1235.53, "total_tokens": 6914624}
{"current_steps": 1000, "total_steps": 20000, "loss": 0.3449, "lr": 0.2981569351617341, "epoch": 0.18108150931438013, "percentage": 5.0, "elapsed_time": "1:33:30", "remaining_time": "1 day, 5:36:31", "throughput": 1239.13, "total_tokens": 6951616}
{"current_steps": 1000, "total_steps": 20000, "eval_loss": 0.3443968594074249, "epoch": 0.18108150931438013, "percentage": 5.0, "elapsed_time": "1:45:51", "remaining_time": "1 day, 9:31:27", "throughput": 1094.4, "total_tokens": 6951616}