quip-4k-mistral / trainer_log.jsonl
Anis1123's picture
Initial model upload
76429c7 verified
{"current_steps": 5, "total_steps": 792, "loss": 2.995, "learning_rate": 4.9995083170283816e-05, "epoch": 0.03770028275212064, "percentage": 0.63, "elapsed_time": "0:00:35", "remaining_time": "1:33:42", "throughput": 1595.95, "total_tokens": 57008}
{"current_steps": 10, "total_steps": 792, "loss": 2.7127, "learning_rate": 4.998033461515242e-05, "epoch": 0.07540056550424128, "percentage": 1.26, "elapsed_time": "0:01:13", "remaining_time": "1:36:16", "throughput": 1596.52, "total_tokens": 117936}
{"current_steps": 15, "total_steps": 792, "loss": 2.6302, "learning_rate": 4.9955760135896534e-05, "epoch": 0.11310084825636192, "percentage": 1.89, "elapsed_time": "0:01:51", "remaining_time": "1:35:55", "throughput": 1586.63, "total_tokens": 176288}
{"current_steps": 20, "total_steps": 792, "loss": 2.5818, "learning_rate": 4.992136939879856e-05, "epoch": 0.15080113100848255, "percentage": 2.53, "elapsed_time": "0:02:25", "remaining_time": "1:33:35", "throughput": 1578.88, "total_tokens": 229712}
{"current_steps": 25, "total_steps": 792, "loss": 2.4913, "learning_rate": 4.9877175931330346e-05, "epoch": 0.1885014137606032, "percentage": 3.16, "elapsed_time": "0:03:04", "remaining_time": "1:34:15", "throughput": 1566.54, "total_tokens": 288784}
{"current_steps": 30, "total_steps": 792, "loss": 2.4694, "learning_rate": 4.982319711683221e-05, "epoch": 0.22620169651272384, "percentage": 3.79, "elapsed_time": "0:03:42", "remaining_time": "1:34:18", "throughput": 1560.85, "total_tokens": 347712}
{"current_steps": 35, "total_steps": 792, "loss": 2.4525, "learning_rate": 4.975945418767529e-05, "epoch": 0.2639019792648445, "percentage": 4.42, "elapsed_time": "0:04:17", "remaining_time": "1:32:52", "throughput": 1569.06, "total_tokens": 404272}
{"current_steps": 40, "total_steps": 792, "loss": 2.4745, "learning_rate": 4.968597221690986e-05, "epoch": 0.3016022620169651, "percentage": 5.05, "elapsed_time": "0:04:53", "remaining_time": "1:32:06", "throughput": 1570.31, "total_tokens": 461632}
{"current_steps": 45, "total_steps": 792, "loss": 2.4637, "learning_rate": 4.96027801084029e-05, "epoch": 0.3393025447690858, "percentage": 5.68, "elapsed_time": "0:05:28", "remaining_time": "1:30:58", "throughput": 1575.3, "total_tokens": 518016}
{"current_steps": 50, "total_steps": 792, "loss": 2.5011, "learning_rate": 4.950991058546893e-05, "epoch": 0.3770028275212064, "percentage": 6.31, "elapsed_time": "0:06:08", "remaining_time": "1:31:03", "throughput": 1573.44, "total_tokens": 579312}
{"current_steps": 55, "total_steps": 792, "loss": 2.4397, "learning_rate": 4.940740017799833e-05, "epoch": 0.41470311027332707, "percentage": 6.94, "elapsed_time": "0:06:44", "remaining_time": "1:30:22", "throughput": 1572.87, "total_tokens": 636448}
{"current_steps": 60, "total_steps": 792, "loss": 2.4109, "learning_rate": 4.929528920808854e-05, "epoch": 0.4524033930254477, "percentage": 7.58, "elapsed_time": "0:07:20", "remaining_time": "1:29:30", "throughput": 1575.4, "total_tokens": 693504}
{"current_steps": 65, "total_steps": 792, "loss": 2.4228, "learning_rate": 4.917362177418342e-05, "epoch": 0.49010367577756836, "percentage": 8.21, "elapsed_time": "0:07:57", "remaining_time": "1:29:01", "throughput": 1575.08, "total_tokens": 752160}
{"current_steps": 70, "total_steps": 792, "loss": 2.4391, "learning_rate": 4.904244573372733e-05, "epoch": 0.527803958529689, "percentage": 8.84, "elapsed_time": "0:08:34", "remaining_time": "1:28:27", "throughput": 1576.53, "total_tokens": 811296}
{"current_steps": 75, "total_steps": 792, "loss": 2.4552, "learning_rate": 4.8901812684340564e-05, "epoch": 0.5655042412818096, "percentage": 9.47, "elapsed_time": "0:09:08", "remaining_time": "1:27:28", "throughput": 1580.58, "total_tokens": 867696}
{"current_steps": 80, "total_steps": 792, "loss": 2.3658, "learning_rate": 4.8751777943523634e-05, "epoch": 0.6032045240339302, "percentage": 10.1, "elapsed_time": "0:09:45", "remaining_time": "1:26:51", "throughput": 1579.59, "total_tokens": 924944}
{"current_steps": 85, "total_steps": 792, "loss": 2.359, "learning_rate": 4.8592400526898314e-05, "epoch": 0.6409048067860509, "percentage": 10.73, "elapsed_time": "0:10:21", "remaining_time": "1:26:10", "throughput": 1574.53, "total_tokens": 978768}
{"current_steps": 90, "total_steps": 792, "loss": 2.4228, "learning_rate": 4.842374312499405e-05, "epoch": 0.6786050895381716, "percentage": 11.36, "elapsed_time": "0:10:56", "remaining_time": "1:25:20", "throughput": 1576.06, "total_tokens": 1034544}
{"current_steps": 95, "total_steps": 792, "loss": 2.32, "learning_rate": 4.824587207858888e-05, "epoch": 0.7163053722902922, "percentage": 11.99, "elapsed_time": "0:11:34", "remaining_time": "1:24:53", "throughput": 1572.77, "total_tokens": 1091776}
{"current_steps": 100, "total_steps": 792, "loss": 2.3393, "learning_rate": 4.805885735261454e-05, "epoch": 0.7540056550424128, "percentage": 12.63, "elapsed_time": "0:12:12", "remaining_time": "1:24:29", "throughput": 1573.96, "total_tokens": 1153056}
{"current_steps": 105, "total_steps": 792, "loss": 2.2595, "learning_rate": 4.786277250863599e-05, "epoch": 0.7917059377945335, "percentage": 13.26, "elapsed_time": "0:12:51", "remaining_time": "1:24:06", "throughput": 1571.22, "total_tokens": 1211808}
{"current_steps": 110, "total_steps": 792, "loss": 2.3171, "learning_rate": 4.765769467591625e-05, "epoch": 0.8294062205466541, "percentage": 13.89, "elapsed_time": "0:13:28", "remaining_time": "1:23:35", "throughput": 1574.36, "total_tokens": 1273600}
{"current_steps": 115, "total_steps": 792, "loss": 2.2949, "learning_rate": 4.744370452107789e-05, "epoch": 0.8671065032987747, "percentage": 14.52, "elapsed_time": "0:14:05", "remaining_time": "1:22:54", "throughput": 1575.54, "total_tokens": 1331392}
{"current_steps": 120, "total_steps": 792, "loss": 2.3818, "learning_rate": 4.722088621637309e-05, "epoch": 0.9048067860508954, "percentage": 15.15, "elapsed_time": "0:14:39", "remaining_time": "1:22:05", "throughput": 1577.57, "total_tokens": 1387664}
{"current_steps": 125, "total_steps": 792, "loss": 2.2494, "learning_rate": 4.698932740657479e-05, "epoch": 0.942507068803016, "percentage": 15.78, "elapsed_time": "0:15:18", "remaining_time": "1:21:41", "throughput": 1574.25, "total_tokens": 1445968}
{"current_steps": 130, "total_steps": 792, "loss": 2.3593, "learning_rate": 4.6749119174501975e-05, "epoch": 0.9802073515551367, "percentage": 16.41, "elapsed_time": "0:15:50", "remaining_time": "1:20:42", "throughput": 1574.99, "total_tokens": 1497744}
{"current_steps": 135, "total_steps": 792, "loss": 2.1892, "learning_rate": 4.6500356005192514e-05, "epoch": 1.0179076343072573, "percentage": 17.05, "elapsed_time": "0:16:25", "remaining_time": "1:19:56", "throughput": 1571.78, "total_tokens": 1549008}
{"current_steps": 140, "total_steps": 792, "loss": 2.1753, "learning_rate": 4.6243135748737864e-05, "epoch": 1.055607917059378, "percentage": 17.68, "elapsed_time": "0:17:00", "remaining_time": "1:19:10", "throughput": 1573.58, "total_tokens": 1605152}
{"current_steps": 145, "total_steps": 792, "loss": 2.1186, "learning_rate": 4.597755958179406e-05, "epoch": 1.0933081998114986, "percentage": 18.31, "elapsed_time": "0:17:35", "remaining_time": "1:18:31", "throughput": 1575.29, "total_tokens": 1663456}
{"current_steps": 150, "total_steps": 792, "loss": 2.0526, "learning_rate": 4.570373196778427e-05, "epoch": 1.1310084825636193, "percentage": 18.94, "elapsed_time": "0:18:14", "remaining_time": "1:18:03", "throughput": 1573.97, "total_tokens": 1722320}
{"current_steps": 155, "total_steps": 792, "loss": 2.1589, "learning_rate": 4.5421760615808474e-05, "epoch": 1.1687087653157398, "percentage": 19.57, "elapsed_time": "0:18:46", "remaining_time": "1:17:09", "throughput": 1572.77, "total_tokens": 1771664}
{"current_steps": 160, "total_steps": 792, "loss": 2.0505, "learning_rate": 4.513175643827647e-05, "epoch": 1.2064090480678604, "percentage": 20.2, "elapsed_time": "0:19:23", "remaining_time": "1:16:36", "throughput": 1572.57, "total_tokens": 1829824}
{"current_steps": 165, "total_steps": 792, "loss": 2.0924, "learning_rate": 4.4833833507280884e-05, "epoch": 1.244109330819981, "percentage": 20.83, "elapsed_time": "0:19:56", "remaining_time": "1:15:45", "throughput": 1573.65, "total_tokens": 1882384}
{"current_steps": 170, "total_steps": 792, "loss": 2.0184, "learning_rate": 4.4528109009727336e-05, "epoch": 1.2818096135721018, "percentage": 21.46, "elapsed_time": "0:20:31", "remaining_time": "1:15:07", "throughput": 1574.47, "total_tokens": 1939456}
{"current_steps": 175, "total_steps": 792, "loss": 2.1524, "learning_rate": 4.42147032012394e-05, "epoch": 1.3195098963242224, "percentage": 22.1, "elapsed_time": "0:21:06", "remaining_time": "1:14:26", "throughput": 1575.74, "total_tokens": 1996320}
{"current_steps": 180, "total_steps": 792, "loss": 2.1253, "learning_rate": 4.389373935885646e-05, "epoch": 1.3572101790763431, "percentage": 22.73, "elapsed_time": "0:21:46", "remaining_time": "1:14:00", "throughput": 1574.57, "total_tokens": 2056560}
{"current_steps": 185, "total_steps": 792, "loss": 2.0752, "learning_rate": 4.356534373254316e-05, "epoch": 1.3949104618284638, "percentage": 23.36, "elapsed_time": "0:22:27", "remaining_time": "1:13:39", "throughput": 1572.74, "total_tokens": 2118496}
{"current_steps": 190, "total_steps": 792, "loss": 2.0574, "learning_rate": 4.322964549552943e-05, "epoch": 1.4326107445805842, "percentage": 23.99, "elapsed_time": "0:23:04", "remaining_time": "1:13:07", "throughput": 1572.94, "total_tokens": 2178352}
{"current_steps": 195, "total_steps": 792, "loss": 2.0481, "learning_rate": 4.288677669350066e-05, "epoch": 1.4703110273327051, "percentage": 24.62, "elapsed_time": "0:23:40", "remaining_time": "1:12:27", "throughput": 1572.67, "total_tokens": 2233440}
{"current_steps": 200, "total_steps": 792, "loss": 2.0859, "learning_rate": 4.2536872192658036e-05, "epoch": 1.5080113100848256, "percentage": 25.25, "elapsed_time": "0:24:15", "remaining_time": "1:11:49", "throughput": 1572.76, "total_tokens": 2289648}
{"current_steps": 205, "total_steps": 792, "loss": 2.0877, "learning_rate": 4.218006962666934e-05, "epoch": 1.5457115928369463, "percentage": 25.88, "elapsed_time": "0:24:53", "remaining_time": "1:11:16", "throughput": 1570.86, "total_tokens": 2346224}
{"current_steps": 210, "total_steps": 792, "loss": 2.0488, "learning_rate": 4.181650934253132e-05, "epoch": 1.583411875589067, "percentage": 26.52, "elapsed_time": "0:25:30", "remaining_time": "1:10:42", "throughput": 1572.75, "total_tokens": 2407392}
{"current_steps": 215, "total_steps": 792, "loss": 2.0074, "learning_rate": 4.144633434536467e-05, "epoch": 1.6211121583411876, "percentage": 27.15, "elapsed_time": "0:26:05", "remaining_time": "1:10:02", "throughput": 1572.49, "total_tokens": 2462400}
{"current_steps": 220, "total_steps": 792, "loss": 2.0844, "learning_rate": 4.1069690242163484e-05, "epoch": 1.6588124410933083, "percentage": 27.78, "elapsed_time": "0:26:41", "remaining_time": "1:09:24", "throughput": 1572.27, "total_tokens": 2518304}
{"current_steps": 225, "total_steps": 792, "loss": 2.0943, "learning_rate": 4.06867251845213e-05, "epoch": 1.6965127238454287, "percentage": 28.41, "elapsed_time": "0:27:24", "remaining_time": "1:09:04", "throughput": 1570.54, "total_tokens": 2583168}
{"current_steps": 230, "total_steps": 792, "loss": 2.0858, "learning_rate": 4.0297589810356165e-05, "epoch": 1.7342130065975496, "percentage": 29.04, "elapsed_time": "0:28:03", "remaining_time": "1:08:34", "throughput": 1569.89, "total_tokens": 2643552}
{"current_steps": 235, "total_steps": 792, "loss": 2.044, "learning_rate": 3.9902437184657784e-05, "epoch": 1.77191328934967, "percentage": 29.67, "elapsed_time": "0:28:43", "remaining_time": "1:08:05", "throughput": 1569.73, "total_tokens": 2705600}
{"current_steps": 240, "total_steps": 792, "loss": 2.1083, "learning_rate": 3.9501422739279956e-05, "epoch": 1.8096135721017907, "percentage": 30.3, "elapsed_time": "0:29:22", "remaining_time": "1:07:33", "throughput": 1569.37, "total_tokens": 2765856}
{"current_steps": 245, "total_steps": 792, "loss": 2.0431, "learning_rate": 3.909470421180201e-05, "epoch": 1.8473138548539114, "percentage": 30.93, "elapsed_time": "0:29:58", "remaining_time": "1:06:54", "throughput": 1570.51, "total_tokens": 2824192}
{"current_steps": 250, "total_steps": 792, "loss": 2.0978, "learning_rate": 3.8682441583483314e-05, "epoch": 1.885014137606032, "percentage": 31.57, "elapsed_time": "0:30:32", "remaining_time": "1:06:13", "throughput": 1571.6, "total_tokens": 2880208}
{"current_steps": 255, "total_steps": 792, "loss": 2.096, "learning_rate": 3.8264797016335205e-05, "epoch": 1.9227144203581528, "percentage": 32.2, "elapsed_time": "0:31:09", "remaining_time": "1:05:36", "throughput": 1572.78, "total_tokens": 2939856}
{"current_steps": 260, "total_steps": 792, "loss": 1.9965, "learning_rate": 3.7841934789335164e-05, "epoch": 1.9604147031102732, "percentage": 32.83, "elapsed_time": "0:31:45", "remaining_time": "1:04:59", "throughput": 1571.97, "total_tokens": 2995552}
{"current_steps": 265, "total_steps": 792, "loss": 2.1569, "learning_rate": 3.741402123380828e-05, "epoch": 1.998114985862394, "percentage": 33.46, "elapsed_time": "0:32:22", "remaining_time": "1:04:23", "throughput": 1572.81, "total_tokens": 3055504}
{"current_steps": 270, "total_steps": 792, "loss": 1.7904, "learning_rate": 3.6981224668001424e-05, "epoch": 2.0358152686145146, "percentage": 34.09, "elapsed_time": "0:32:59", "remaining_time": "1:03:46", "throughput": 1571.65, "total_tokens": 3110576}
{"current_steps": 275, "total_steps": 792, "loss": 1.7416, "learning_rate": 3.654371533087586e-05, "epoch": 2.0735155513666355, "percentage": 34.72, "elapsed_time": "0:33:39", "remaining_time": "1:03:16", "throughput": 1570.53, "total_tokens": 3171440}
{"current_steps": 280, "total_steps": 792, "loss": 1.7513, "learning_rate": 3.610166531514436e-05, "epoch": 2.111215834118756, "percentage": 35.35, "elapsed_time": "0:34:09", "remaining_time": "1:02:27", "throughput": 1570.94, "total_tokens": 3219792}
{"current_steps": 285, "total_steps": 792, "loss": 1.7565, "learning_rate": 3.565524849957921e-05, "epoch": 2.1489161168708764, "percentage": 35.98, "elapsed_time": "0:34:45", "remaining_time": "1:01:50", "throughput": 1570.73, "total_tokens": 3275792}
{"current_steps": 290, "total_steps": 792, "loss": 1.7417, "learning_rate": 3.520464048061758e-05, "epoch": 2.1866163996229973, "percentage": 36.62, "elapsed_time": "0:35:20", "remaining_time": "1:01:10", "throughput": 1572.09, "total_tokens": 3333136}
{"current_steps": 295, "total_steps": 792, "loss": 1.7726, "learning_rate": 3.47500185032913e-05, "epoch": 2.2243166823751177, "percentage": 37.25, "elapsed_time": "0:35:54", "remaining_time": "1:00:29", "throughput": 1573.81, "total_tokens": 3390080}
{"current_steps": 300, "total_steps": 792, "loss": 1.7763, "learning_rate": 3.4291561391508185e-05, "epoch": 2.2620169651272386, "percentage": 37.88, "elapsed_time": "0:36:31", "remaining_time": "0:59:53", "throughput": 1572.76, "total_tokens": 3446208}
{"current_steps": 305, "total_steps": 792, "loss": 1.7327, "learning_rate": 3.3829449477712324e-05, "epoch": 2.299717247879359, "percentage": 38.51, "elapsed_time": "0:37:12", "remaining_time": "0:59:24", "throughput": 1571.43, "total_tokens": 3508240}
{"current_steps": 310, "total_steps": 792, "loss": 1.7441, "learning_rate": 3.336386453195088e-05, "epoch": 2.3374175306314795, "percentage": 39.14, "elapsed_time": "0:37:51", "remaining_time": "0:58:52", "throughput": 1571.49, "total_tokens": 3569856}
{"current_steps": 315, "total_steps": 792, "loss": 1.7355, "learning_rate": 3.2894989690375626e-05, "epoch": 2.3751178133836004, "percentage": 39.77, "elapsed_time": "0:38:29", "remaining_time": "0:58:17", "throughput": 1572.36, "total_tokens": 3631984}
{"current_steps": 320, "total_steps": 792, "loss": 1.7182, "learning_rate": 3.2423009383206876e-05, "epoch": 2.412818096135721, "percentage": 40.4, "elapsed_time": "0:39:05", "remaining_time": "0:57:39", "throughput": 1572.48, "total_tokens": 3688192}
{"current_steps": 325, "total_steps": 792, "loss": 1.7332, "learning_rate": 3.194810926218861e-05, "epoch": 2.4505183788878417, "percentage": 41.04, "elapsed_time": "0:39:42", "remaining_time": "0:57:03", "throughput": 1572.48, "total_tokens": 3746720}
{"current_steps": 330, "total_steps": 792, "loss": 1.6908, "learning_rate": 3.147047612756302e-05, "epoch": 2.488218661639962, "percentage": 41.67, "elapsed_time": "0:40:19", "remaining_time": "0:56:27", "throughput": 1571.67, "total_tokens": 3802432}
{"current_steps": 335, "total_steps": 792, "loss": 1.7756, "learning_rate": 3.099029785459328e-05, "epoch": 2.525918944392083, "percentage": 42.3, "elapsed_time": "0:40:55", "remaining_time": "0:55:49", "throughput": 1570.92, "total_tokens": 3856800}
{"current_steps": 340, "total_steps": 792, "loss": 1.7737, "learning_rate": 3.0507763319663517e-05, "epoch": 2.5636192271442035, "percentage": 42.93, "elapsed_time": "0:41:31", "remaining_time": "0:55:12", "throughput": 1571.62, "total_tokens": 3916320}
{"current_steps": 345, "total_steps": 792, "loss": 1.7446, "learning_rate": 3.002306232598497e-05, "epoch": 2.6013195098963244, "percentage": 43.56, "elapsed_time": "0:42:09", "remaining_time": "0:54:37", "throughput": 1571.34, "total_tokens": 3974864}
{"current_steps": 350, "total_steps": 792, "loss": 1.7283, "learning_rate": 2.9536385528937567e-05, "epoch": 2.639019792648445, "percentage": 44.19, "elapsed_time": "0:42:46", "remaining_time": "0:54:01", "throughput": 1571.16, "total_tokens": 4032656}
{"current_steps": 355, "total_steps": 792, "loss": 1.7573, "learning_rate": 2.9047924361076345e-05, "epoch": 2.6767200754005653, "percentage": 44.82, "elapsed_time": "0:43:25", "remaining_time": "0:53:27", "throughput": 1570.73, "total_tokens": 4092800}
{"current_steps": 360, "total_steps": 792, "loss": 1.6758, "learning_rate": 2.8557870956832132e-05, "epoch": 2.7144203581526862, "percentage": 45.45, "elapsed_time": "0:43:58", "remaining_time": "0:52:45", "throughput": 1571.05, "total_tokens": 4144592}
{"current_steps": 365, "total_steps": 792, "loss": 1.7087, "learning_rate": 2.8066418076936167e-05, "epoch": 2.7521206409048067, "percentage": 46.09, "elapsed_time": "0:44:34", "remaining_time": "0:52:09", "throughput": 1570.1, "total_tokens": 4200000}
{"current_steps": 370, "total_steps": 792, "loss": 1.7527, "learning_rate": 2.7573759032598366e-05, "epoch": 2.7898209236569276, "percentage": 46.72, "elapsed_time": "0:45:13", "remaining_time": "0:51:34", "throughput": 1570.7, "total_tokens": 4262288}
{"current_steps": 375, "total_steps": 792, "loss": 1.786, "learning_rate": 2.7080087609469062e-05, "epoch": 2.827521206409048, "percentage": 47.35, "elapsed_time": "0:45:49", "remaining_time": "0:50:57", "throughput": 1570.29, "total_tokens": 4317040}
{"current_steps": 380, "total_steps": 792, "loss": 1.677, "learning_rate": 2.6585597991414114e-05, "epoch": 2.8652214891611685, "percentage": 47.98, "elapsed_time": "0:46:26", "remaining_time": "0:50:21", "throughput": 1570.58, "total_tokens": 4376576}
{"current_steps": 385, "total_steps": 792, "loss": 1.7027, "learning_rate": 2.6090484684133404e-05, "epoch": 2.9029217719132894, "percentage": 48.61, "elapsed_time": "0:46:59", "remaining_time": "0:49:40", "throughput": 1571.04, "total_tokens": 4429024}
{"current_steps": 390, "total_steps": 792, "loss": 1.7717, "learning_rate": 2.5594942438652688e-05, "epoch": 2.9406220546654103, "percentage": 49.24, "elapsed_time": "0:47:39", "remaining_time": "0:49:07", "throughput": 1571.78, "total_tokens": 4494400}
{"current_steps": 395, "total_steps": 792, "loss": 1.8441, "learning_rate": 2.509916617471903e-05, "epoch": 2.9783223374175307, "percentage": 49.87, "elapsed_time": "0:48:20", "remaining_time": "0:48:34", "throughput": 1570.54, "total_tokens": 4554576}
{"current_steps": 400, "total_steps": 792, "loss": 1.604, "learning_rate": 2.46033509041298e-05, "epoch": 3.016022620169651, "percentage": 50.51, "elapsed_time": "0:48:56", "remaining_time": "0:47:58", "throughput": 1570.47, "total_tokens": 4612352}
{"current_steps": 405, "total_steps": 792, "loss": 1.4357, "learning_rate": 2.410769165402549e-05, "epoch": 3.053722902921772, "percentage": 51.14, "elapsed_time": "0:49:38", "remaining_time": "0:47:25", "throughput": 1569.67, "total_tokens": 4674960}
{"current_steps": 410, "total_steps": 792, "loss": 1.4401, "learning_rate": 2.3612383390176503e-05, "epoch": 3.0914231856738925, "percentage": 51.77, "elapsed_time": "0:50:13", "remaining_time": "0:46:47", "throughput": 1570.35, "total_tokens": 4732736}
{"current_steps": 415, "total_steps": 792, "loss": 1.4433, "learning_rate": 2.3117620940294048e-05, "epoch": 3.1291234684260134, "percentage": 52.4, "elapsed_time": "0:50:54", "remaining_time": "0:46:14", "throughput": 1570.11, "total_tokens": 4795856}
{"current_steps": 420, "total_steps": 792, "loss": 1.4739, "learning_rate": 2.2623598917395438e-05, "epoch": 3.166823751178134, "percentage": 53.03, "elapsed_time": "0:51:30", "remaining_time": "0:45:37", "throughput": 1570.77, "total_tokens": 4854976}
{"current_steps": 425, "total_steps": 792, "loss": 1.4327, "learning_rate": 2.213051164325366e-05, "epoch": 3.2045240339302543, "percentage": 53.66, "elapsed_time": "0:52:02", "remaining_time": "0:44:56", "throughput": 1571.13, "total_tokens": 4906032}
{"current_steps": 430, "total_steps": 792, "loss": 1.4281, "learning_rate": 2.1638553071961708e-05, "epoch": 3.242224316682375, "percentage": 54.29, "elapsed_time": "0:52:33", "remaining_time": "0:44:15", "throughput": 1570.83, "total_tokens": 4954352}
{"current_steps": 435, "total_steps": 792, "loss": 1.4006, "learning_rate": 2.1147916713641367e-05, "epoch": 3.2799245994344957, "percentage": 54.92, "elapsed_time": "0:53:11", "remaining_time": "0:43:39", "throughput": 1570.58, "total_tokens": 5012208}
{"current_steps": 440, "total_steps": 792, "loss": 1.4065, "learning_rate": 2.0658795558326743e-05, "epoch": 3.3176248821866166, "percentage": 55.56, "elapsed_time": "0:53:46", "remaining_time": "0:43:01", "throughput": 1570.74, "total_tokens": 5067616}
{"current_steps": 445, "total_steps": 792, "loss": 1.4158, "learning_rate": 2.017138200005236e-05, "epoch": 3.355325164938737, "percentage": 56.19, "elapsed_time": "0:54:26", "remaining_time": "0:42:27", "throughput": 1570.84, "total_tokens": 5131488}
{"current_steps": 450, "total_steps": 792, "loss": 1.5139, "learning_rate": 1.9685867761175584e-05, "epoch": 3.3930254476908575, "percentage": 56.82, "elapsed_time": "0:55:03", "remaining_time": "0:41:50", "throughput": 1570.89, "total_tokens": 5189216}
{"current_steps": 455, "total_steps": 792, "loss": 1.4692, "learning_rate": 1.9202443816963425e-05, "epoch": 3.4307257304429783, "percentage": 57.45, "elapsed_time": "0:55:40", "remaining_time": "0:41:14", "throughput": 1570.5, "total_tokens": 5246032}
{"current_steps": 460, "total_steps": 792, "loss": 1.3873, "learning_rate": 1.872130032047302e-05, "epoch": 3.468426013195099, "percentage": 58.08, "elapsed_time": "0:56:19", "remaining_time": "0:40:39", "throughput": 1570.9, "total_tokens": 5309648}
{"current_steps": 465, "total_steps": 792, "loss": 1.5167, "learning_rate": 1.824262652775568e-05, "epoch": 3.5061262959472197, "percentage": 58.71, "elapsed_time": "0:56:57", "remaining_time": "0:40:03", "throughput": 1571.89, "total_tokens": 5371392}
{"current_steps": 470, "total_steps": 792, "loss": 1.4093, "learning_rate": 1.7766610723413684e-05, "epoch": 3.54382657869934, "percentage": 59.34, "elapsed_time": "0:57:36", "remaining_time": "0:39:28", "throughput": 1571.11, "total_tokens": 5430528}
{"current_steps": 475, "total_steps": 792, "loss": 1.497, "learning_rate": 1.7293440146539196e-05, "epoch": 3.581526861451461, "percentage": 59.97, "elapsed_time": "0:58:11", "remaining_time": "0:38:50", "throughput": 1571.1, "total_tokens": 5486048}
{"current_steps": 480, "total_steps": 792, "loss": 1.5024, "learning_rate": 1.682330091706446e-05, "epoch": 3.6192271442035815, "percentage": 60.61, "elapsed_time": "0:58:54", "remaining_time": "0:38:17", "throughput": 1570.73, "total_tokens": 5551520}
{"current_steps": 485, "total_steps": 792, "loss": 1.3976, "learning_rate": 1.6356377962552238e-05, "epoch": 3.6569274269557024, "percentage": 61.24, "elapsed_time": "0:59:30", "remaining_time": "0:37:40", "throughput": 1570.59, "total_tokens": 5607968}
{"current_steps": 490, "total_steps": 792, "loss": 1.4343, "learning_rate": 1.589285494545514e-05, "epoch": 3.694627709707823, "percentage": 61.87, "elapsed_time": "1:00:08", "remaining_time": "0:37:04", "throughput": 1570.2, "total_tokens": 5666240}
{"current_steps": 495, "total_steps": 792, "loss": 1.4647, "learning_rate": 1.5432914190872757e-05, "epoch": 3.7323279924599433, "percentage": 62.5, "elapsed_time": "1:00:45", "remaining_time": "0:36:27", "throughput": 1570.37, "total_tokens": 5724272}
{"current_steps": 500, "total_steps": 792, "loss": 1.3874, "learning_rate": 1.4976736614834664e-05, "epoch": 3.770028275212064, "percentage": 63.13, "elapsed_time": "1:01:21", "remaining_time": "0:35:49", "throughput": 1570.68, "total_tokens": 5782144}
{"current_steps": 505, "total_steps": 792, "loss": 1.4405, "learning_rate": 1.4524501653137787e-05, "epoch": 3.8077285579641846, "percentage": 63.76, "elapsed_time": "1:01:55", "remaining_time": "0:35:11", "throughput": 1570.56, "total_tokens": 5835968}
{"current_steps": 510, "total_steps": 792, "loss": 1.4689, "learning_rate": 1.4076387190766017e-05, "epoch": 3.8454288407163055, "percentage": 64.39, "elapsed_time": "1:02:32", "remaining_time": "0:34:34", "throughput": 1570.81, "total_tokens": 5894032}
{"current_steps": 515, "total_steps": 792, "loss": 1.3515, "learning_rate": 1.363256949191972e-05, "epoch": 3.883129123468426, "percentage": 65.03, "elapsed_time": "1:03:09", "remaining_time": "0:33:57", "throughput": 1570.04, "total_tokens": 5948928}
{"current_steps": 520, "total_steps": 792, "loss": 1.4372, "learning_rate": 1.3193223130682936e-05, "epoch": 3.9208294062205464, "percentage": 65.66, "elapsed_time": "1:03:43", "remaining_time": "0:33:20", "throughput": 1570.1, "total_tokens": 6004016}
{"current_steps": 525, "total_steps": 792, "loss": 1.4051, "learning_rate": 1.2758520922355226e-05, "epoch": 3.9585296889726673, "percentage": 66.29, "elapsed_time": "1:04:16", "remaining_time": "0:32:41", "throughput": 1570.04, "total_tokens": 6054192}
{"current_steps": 530, "total_steps": 792, "loss": 1.4304, "learning_rate": 1.2328633855475429e-05, "epoch": 3.9962299717247878, "percentage": 66.92, "elapsed_time": "1:04:53", "remaining_time": "0:32:04", "throughput": 1569.78, "total_tokens": 6111840}
{"current_steps": 535, "total_steps": 792, "loss": 1.1746, "learning_rate": 1.1903731024563966e-05, "epoch": 4.033930254476909, "percentage": 67.55, "elapsed_time": "1:05:28", "remaining_time": "0:31:27", "throughput": 1570.3, "total_tokens": 6169584}
{"current_steps": 540, "total_steps": 792, "loss": 1.172, "learning_rate": 1.148397956361007e-05, "epoch": 4.071630537229029, "percentage": 68.18, "elapsed_time": "1:06:09", "remaining_time": "0:30:52", "throughput": 1570.29, "total_tokens": 6232800}
{"current_steps": 545, "total_steps": 792, "loss": 1.1709, "learning_rate": 1.106954458033026e-05, "epoch": 4.10933081998115, "percentage": 68.81, "elapsed_time": "1:06:49", "remaining_time": "0:30:16", "throughput": 1570.03, "total_tokens": 6294496}
{"current_steps": 550, "total_steps": 792, "loss": 1.247, "learning_rate": 1.0660589091223855e-05, "epoch": 4.147031102733271, "percentage": 69.44, "elapsed_time": "1:07:23", "remaining_time": "0:29:38", "throughput": 1570.31, "total_tokens": 6348976}
{"current_steps": 555, "total_steps": 792, "loss": 1.2236, "learning_rate": 1.025727395745095e-05, "epoch": 4.184731385485391, "percentage": 70.08, "elapsed_time": "1:07:56", "remaining_time": "0:29:00", "throughput": 1570.57, "total_tokens": 6402624}
{"current_steps": 560, "total_steps": 792, "loss": 1.1751, "learning_rate": 9.859757821558337e-06, "epoch": 4.222431668237512, "percentage": 70.71, "elapsed_time": "1:08:34", "remaining_time": "0:28:24", "throughput": 1570.69, "total_tokens": 6462992}
{"current_steps": 565, "total_steps": 792, "loss": 1.1056, "learning_rate": 9.468197045077976e-06, "epoch": 4.260131950989632, "percentage": 71.34, "elapsed_time": "1:09:08", "remaining_time": "0:27:46", "throughput": 1570.46, "total_tokens": 6514944}
{"current_steps": 570, "total_steps": 792, "loss": 1.1612, "learning_rate": 9.082745647022797e-06, "epoch": 4.297832233741753, "percentage": 71.97, "elapsed_time": "1:09:48", "remaining_time": "0:27:11", "throughput": 1570.41, "total_tokens": 6577440}
{"current_steps": 575, "total_steps": 792, "loss": 1.146, "learning_rate": 8.703555243303835e-06, "epoch": 4.335532516493874, "percentage": 72.6, "elapsed_time": "1:10:22", "remaining_time": "0:26:33", "throughput": 1570.59, "total_tokens": 6631296}
{"current_steps": 580, "total_steps": 792, "loss": 1.1462, "learning_rate": 8.330774987092712e-06, "epoch": 4.3732327992459945, "percentage": 73.23, "elapsed_time": "1:10:57", "remaining_time": "0:25:56", "throughput": 1570.71, "total_tokens": 6686784}
{"current_steps": 585, "total_steps": 792, "loss": 1.2129, "learning_rate": 7.96455151015272e-06, "epoch": 4.410933081998115, "percentage": 73.86, "elapsed_time": "1:11:34", "remaining_time": "0:25:19", "throughput": 1570.49, "total_tokens": 6743712}
{"current_steps": 590, "total_steps": 792, "loss": 1.2495, "learning_rate": 7.605028865161809e-06, "epoch": 4.448633364750235, "percentage": 74.49, "elapsed_time": "1:12:11", "remaining_time": "0:24:42", "throughput": 1570.46, "total_tokens": 6802416}
{"current_steps": 595, "total_steps": 792, "loss": 1.1615, "learning_rate": 7.25234846904993e-06, "epoch": 4.486333647502356, "percentage": 75.13, "elapsed_time": "1:12:48", "remaining_time": "0:24:06", "throughput": 1570.61, "total_tokens": 6860880}
{"current_steps": 600, "total_steps": 792, "loss": 1.2619, "learning_rate": 6.906649047373246e-06, "epoch": 4.524033930254477, "percentage": 75.76, "elapsed_time": "1:13:26", "remaining_time": "0:23:30", "throughput": 1570.75, "total_tokens": 6921424}
{"current_steps": 605, "total_steps": 792, "loss": 1.1949, "learning_rate": 6.568066579746901e-06, "epoch": 4.561734213006598, "percentage": 76.39, "elapsed_time": "1:13:59", "remaining_time": "0:22:52", "throughput": 1570.86, "total_tokens": 6973504}
{"current_steps": 610, "total_steps": 792, "loss": 1.1891, "learning_rate": 6.2367342463579475e-06, "epoch": 4.599434495758718, "percentage": 77.02, "elapsed_time": "1:14:35", "remaining_time": "0:22:15", "throughput": 1570.43, "total_tokens": 7027984}
{"current_steps": 615, "total_steps": 792, "loss": 1.1821, "learning_rate": 5.912782375579412e-06, "epoch": 4.6371347785108386, "percentage": 77.65, "elapsed_time": "1:15:11", "remaining_time": "0:21:38", "throughput": 1569.96, "total_tokens": 7082720}
{"current_steps": 620, "total_steps": 792, "loss": 1.2011, "learning_rate": 5.596338392706077e-06, "epoch": 4.674835061262959, "percentage": 78.28, "elapsed_time": "1:15:46", "remaining_time": "0:21:01", "throughput": 1570.34, "total_tokens": 7139760}
{"current_steps": 625, "total_steps": 792, "loss": 1.2479, "learning_rate": 5.2875267698322325e-06, "epoch": 4.71253534401508, "percentage": 78.91, "elapsed_time": "1:16:22", "remaining_time": "0:20:24", "throughput": 1570.47, "total_tokens": 7196832}
{"current_steps": 630, "total_steps": 792, "loss": 1.1982, "learning_rate": 4.986468976890993e-06, "epoch": 4.750235626767201, "percentage": 79.55, "elapsed_time": "1:16:58", "remaining_time": "0:19:47", "throughput": 1570.84, "total_tokens": 7255552}
{"current_steps": 635, "total_steps": 792, "loss": 1.1955, "learning_rate": 4.693283433874565e-06, "epoch": 4.787935909519321, "percentage": 80.18, "elapsed_time": "1:17:32", "remaining_time": "0:19:10", "throughput": 1571.08, "total_tokens": 7310144}
{"current_steps": 640, "total_steps": 792, "loss": 1.2429, "learning_rate": 4.408085464254183e-06, "epoch": 4.825636192271442, "percentage": 80.81, "elapsed_time": "1:18:07", "remaining_time": "0:18:33", "throughput": 1570.99, "total_tokens": 7363600}
{"current_steps": 645, "total_steps": 792, "loss": 1.2139, "learning_rate": 4.130987249617993e-06, "epoch": 4.863336475023563, "percentage": 81.44, "elapsed_time": "1:18:45", "remaining_time": "0:17:57", "throughput": 1571.2, "total_tokens": 7425056}
{"current_steps": 650, "total_steps": 792, "loss": 1.2122, "learning_rate": 3.8620977855448935e-06, "epoch": 4.9010367577756835, "percentage": 82.07, "elapsed_time": "1:19:25", "remaining_time": "0:17:21", "throughput": 1571.4, "total_tokens": 7488432}
{"current_steps": 655, "total_steps": 792, "loss": 1.1634, "learning_rate": 3.601522838731461e-06, "epoch": 4.938737040527804, "percentage": 82.7, "elapsed_time": "1:20:04", "remaining_time": "0:16:44", "throughput": 1571.39, "total_tokens": 7549248}
{"current_steps": 660, "total_steps": 792, "loss": 1.2289, "learning_rate": 3.3493649053890326e-06, "epoch": 4.976437323279924, "percentage": 83.33, "elapsed_time": "1:20:42", "remaining_time": "0:16:08", "throughput": 1570.84, "total_tokens": 7607168}
{"current_steps": 665, "total_steps": 792, "loss": 1.1895, "learning_rate": 3.1057231709272077e-06, "epoch": 5.014137606032045, "percentage": 83.96, "elapsed_time": "1:21:22", "remaining_time": "0:15:32", "throughput": 1570.22, "total_tokens": 7666560}
{"current_steps": 670, "total_steps": 792, "loss": 1.0644, "learning_rate": 2.8706934709395892e-06, "epoch": 5.051837888784166, "percentage": 84.6, "elapsed_time": "1:21:58", "remaining_time": "0:14:55", "throughput": 1570.06, "total_tokens": 7722432}
{"current_steps": 675, "total_steps": 792, "loss": 0.9969, "learning_rate": 2.6443682535072177e-06, "epoch": 5.089538171536287, "percentage": 85.23, "elapsed_time": "1:22:31", "remaining_time": "0:14:18", "throughput": 1570.16, "total_tokens": 7775296}
{"current_steps": 680, "total_steps": 792, "loss": 1.0552, "learning_rate": 2.4268365428344736e-06, "epoch": 5.127238454288407, "percentage": 85.86, "elapsed_time": "1:23:10", "remaining_time": "0:13:42", "throughput": 1569.78, "total_tokens": 7834752}
{"current_steps": 685, "total_steps": 792, "loss": 0.9982, "learning_rate": 2.21818390423168e-06, "epoch": 5.1649387370405275, "percentage": 86.49, "elapsed_time": "1:23:44", "remaining_time": "0:13:04", "throughput": 1569.42, "total_tokens": 7885680}
{"current_steps": 690, "total_steps": 792, "loss": 1.041, "learning_rate": 2.0184924104583613e-06, "epoch": 5.202639019792649, "percentage": 87.12, "elapsed_time": "1:24:17", "remaining_time": "0:12:27", "throughput": 1569.25, "total_tokens": 7936032}
{"current_steps": 695, "total_steps": 792, "loss": 1.0186, "learning_rate": 1.8278406094401623e-06, "epoch": 5.240339302544769, "percentage": 87.75, "elapsed_time": "1:24:50", "remaining_time": "0:11:50", "throughput": 1569.14, "total_tokens": 7988256}
{"current_steps": 700, "total_steps": 792, "loss": 1.0888, "learning_rate": 1.6463034933723337e-06, "epoch": 5.27803958529689, "percentage": 88.38, "elapsed_time": "1:25:25", "remaining_time": "0:11:13", "throughput": 1569.16, "total_tokens": 8043264}
{"current_steps": 705, "total_steps": 792, "loss": 1.0506, "learning_rate": 1.4739524692218314e-06, "epoch": 5.31573986804901, "percentage": 89.02, "elapsed_time": "1:26:01", "remaining_time": "0:10:36", "throughput": 1568.54, "total_tokens": 8096480}
{"current_steps": 710, "total_steps": 792, "loss": 1.1435, "learning_rate": 1.3108553306396265e-06, "epoch": 5.353440150801131, "percentage": 89.65, "elapsed_time": "1:26:38", "remaining_time": "0:10:00", "throughput": 1568.91, "total_tokens": 8156224}
{"current_steps": 715, "total_steps": 792, "loss": 1.0799, "learning_rate": 1.1570762312943295e-06, "epoch": 5.391140433553252, "percentage": 90.28, "elapsed_time": "1:27:17", "remaining_time": "0:09:24", "throughput": 1568.84, "total_tokens": 8216272}
{"current_steps": 720, "total_steps": 792, "loss": 1.0618, "learning_rate": 1.0126756596375686e-06, "epoch": 5.4288407163053725, "percentage": 90.91, "elapsed_time": "1:27:52", "remaining_time": "0:08:47", "throughput": 1568.6, "total_tokens": 8270896}
{"current_steps": 725, "total_steps": 792, "loss": 1.0932, "learning_rate": 8.777104151110826e-07, "epoch": 5.466540999057493, "percentage": 91.54, "elapsed_time": "1:28:34", "remaining_time": "0:08:11", "throughput": 1568.82, "total_tokens": 8337264}
{"current_steps": 730, "total_steps": 792, "loss": 1.064, "learning_rate": 7.522335858048707e-07, "epoch": 5.504241281809613, "percentage": 92.17, "elapsed_time": "1:29:15", "remaining_time": "0:07:34", "throughput": 1568.66, "total_tokens": 8401616}
{"current_steps": 735, "total_steps": 792, "loss": 1.0762, "learning_rate": 6.362945275751736e-07, "epoch": 5.541941564561734, "percentage": 92.8, "elapsed_time": "1:29:49", "remaining_time": "0:06:57", "throughput": 1569.15, "total_tokens": 8456976}
{"current_steps": 740, "total_steps": 792, "loss": 1.061, "learning_rate": 5.299388446305343e-07, "epoch": 5.579641847313855, "percentage": 93.43, "elapsed_time": "1:30:24", "remaining_time": "0:06:21", "throughput": 1569.47, "total_tokens": 8513616}
{"current_steps": 745, "total_steps": 792, "loss": 1.0795, "learning_rate": 4.3320837159353813e-07, "epoch": 5.617342130065976, "percentage": 94.07, "elapsed_time": "1:31:04", "remaining_time": "0:05:44", "throughput": 1569.32, "total_tokens": 8575136}
{"current_steps": 750, "total_steps": 792, "loss": 1.0228, "learning_rate": 3.4614115704533767e-07, "epoch": 5.655042412818096, "percentage": 94.7, "elapsed_time": "1:31:43", "remaining_time": "0:05:08", "throughput": 1569.61, "total_tokens": 8637744}
{"current_steps": 755, "total_steps": 792, "loss": 1.0506, "learning_rate": 2.687714485593462e-07, "epoch": 5.6927426955702165, "percentage": 95.33, "elapsed_time": "1:32:18", "remaining_time": "0:04:31", "throughput": 1569.84, "total_tokens": 8693904}
{"current_steps": 760, "total_steps": 792, "loss": 1.1141, "learning_rate": 2.011296792301165e-07, "epoch": 5.730442978322337, "percentage": 95.96, "elapsed_time": "1:32:57", "remaining_time": "0:03:54", "throughput": 1569.79, "total_tokens": 8756224}
{"current_steps": 765, "total_steps": 792, "loss": 1.1412, "learning_rate": 1.4324245570256633e-07, "epoch": 5.768143261074458, "percentage": 96.59, "elapsed_time": "1:33:32", "remaining_time": "0:03:18", "throughput": 1570.2, "total_tokens": 8813120}
{"current_steps": 770, "total_steps": 792, "loss": 1.0902, "learning_rate": 9.513254770636137e-08, "epoch": 5.805843543826579, "percentage": 97.22, "elapsed_time": "1:34:06", "remaining_time": "0:02:41", "throughput": 1570.1, "total_tokens": 8866160}
{"current_steps": 775, "total_steps": 792, "loss": 1.1053, "learning_rate": 5.681887909952388e-08, "epoch": 5.843543826578699, "percentage": 97.85, "elapsed_time": "1:34:45", "remaining_time": "0:02:04", "throughput": 1570.04, "total_tokens": 8925888}
{"current_steps": 780, "total_steps": 792, "loss": 1.0414, "learning_rate": 2.831652042480093e-08, "epoch": 5.88124410933082, "percentage": 98.48, "elapsed_time": "1:35:21", "remaining_time": "0:01:28", "throughput": 1570.25, "total_tokens": 8983424}
{"current_steps": 785, "total_steps": 792, "loss": 1.1207, "learning_rate": 9.636682981720158e-09, "epoch": 5.918944392082941, "percentage": 99.12, "elapsed_time": "1:35:57", "remaining_time": "0:00:51", "throughput": 1570.64, "total_tokens": 9042928}
{"current_steps": 790, "total_steps": 792, "loss": 1.0952, "learning_rate": 7.867144166728846e-10, "epoch": 5.956644674835061, "percentage": 99.75, "elapsed_time": "1:36:35", "remaining_time": "0:00:14", "throughput": 1570.67, "total_tokens": 9103184}
{"current_steps": 792, "total_steps": 792, "epoch": 5.971724787935909, "percentage": 100.0, "elapsed_time": "1:36:49", "remaining_time": "0:00:00", "throughput": 1570.7, "total_tokens": 9124912}