token_skip-0.6b / trainer_log.jsonl
mingiJ's picture
Initial upload
58a1b61 verified
Raw
History Blame Contribute Delete
18.9 kB
{"current_steps": 10, "total_steps": 977, "loss": 1.3341, "lr": 9.183673469387756e-06, "epoch": 0.01023541453428864, "percentage": 1.02, "elapsed_time": "0:02:04", "remaining_time": "3:20:09"}
{"current_steps": 20, "total_steps": 977, "loss": 0.9581, "lr": 1.9387755102040817e-05, "epoch": 0.02047082906857728, "percentage": 2.05, "elapsed_time": "0:03:23", "remaining_time": "2:42:06"}
{"current_steps": 30, "total_steps": 977, "loss": 0.8198, "lr": 2.959183673469388e-05, "epoch": 0.030706243602865915, "percentage": 3.07, "elapsed_time": "0:04:33", "remaining_time": "2:23:42"}
{"current_steps": 40, "total_steps": 977, "loss": 0.8068, "lr": 3.979591836734694e-05, "epoch": 0.04094165813715456, "percentage": 4.09, "elapsed_time": "0:05:35", "remaining_time": "2:11:09"}
{"current_steps": 50, "total_steps": 977, "loss": 0.7806, "lr": 5e-05, "epoch": 0.0511770726714432, "percentage": 5.12, "elapsed_time": "0:06:45", "remaining_time": "2:05:18"}
{"current_steps": 60, "total_steps": 977, "loss": 0.7813, "lr": 6.0204081632653065e-05, "epoch": 0.06141248720573183, "percentage": 6.14, "elapsed_time": "0:07:53", "remaining_time": "2:00:34"}
{"current_steps": 70, "total_steps": 977, "loss": 0.7638, "lr": 7.040816326530612e-05, "epoch": 0.07164790174002048, "percentage": 7.16, "elapsed_time": "0:08:59", "remaining_time": "1:56:36"}
{"current_steps": 80, "total_steps": 977, "loss": 0.7851, "lr": 8.061224489795919e-05, "epoch": 0.08188331627430911, "percentage": 8.19, "elapsed_time": "0:10:02", "remaining_time": "1:52:38"}
{"current_steps": 90, "total_steps": 977, "loss": 0.8118, "lr": 9.081632653061225e-05, "epoch": 0.09211873080859775, "percentage": 9.21, "elapsed_time": "0:11:06", "remaining_time": "1:49:31"}
{"current_steps": 100, "total_steps": 977, "loss": 0.7849, "lr": 9.999968065395524e-05, "epoch": 0.1023541453428864, "percentage": 10.24, "elapsed_time": "0:12:09", "remaining_time": "1:46:35"}
{"current_steps": 110, "total_steps": 977, "loss": 0.7867, "lr": 9.996136406426098e-05, "epoch": 0.11258955987717502, "percentage": 11.26, "elapsed_time": "0:13:05", "remaining_time": "1:43:12"}
{"current_steps": 120, "total_steps": 977, "loss": 0.7762, "lr": 9.985923434387545e-05, "epoch": 0.12282497441146366, "percentage": 12.28, "elapsed_time": "0:14:01", "remaining_time": "1:40:12"}
{"current_steps": 130, "total_steps": 977, "loss": 0.7805, "lr": 9.969342193793992e-05, "epoch": 0.1330603889457523, "percentage": 13.31, "elapsed_time": "0:15:05", "remaining_time": "1:38:17"}
{"current_steps": 140, "total_steps": 977, "loss": 0.767, "lr": 9.94641386302783e-05, "epoch": 0.14329580348004095, "percentage": 14.33, "elapsed_time": "0:16:23", "remaining_time": "1:37:57"}
{"current_steps": 150, "total_steps": 977, "loss": 0.7929, "lr": 9.91716772728964e-05, "epoch": 0.1535312180143296, "percentage": 15.35, "elapsed_time": "0:17:36", "remaining_time": "1:37:07"}
{"current_steps": 160, "total_steps": 977, "loss": 0.7922, "lr": 9.881641141193671e-05, "epoch": 0.16376663254861823, "percentage": 16.38, "elapsed_time": "0:18:57", "remaining_time": "1:36:46"}
{"current_steps": 170, "total_steps": 977, "loss": 0.7732, "lr": 9.839879481056682e-05, "epoch": 0.17400204708290687, "percentage": 17.4, "elapsed_time": "0:20:11", "remaining_time": "1:35:51"}
{"current_steps": 180, "total_steps": 977, "loss": 0.7811, "lr": 9.791936086941064e-05, "epoch": 0.1842374616171955, "percentage": 18.42, "elapsed_time": "0:21:18", "remaining_time": "1:34:21"}
{"current_steps": 190, "total_steps": 977, "loss": 0.7861, "lr": 9.737872194526263e-05, "epoch": 0.19447287615148415, "percentage": 19.45, "elapsed_time": "0:22:25", "remaining_time": "1:32:52"}
{"current_steps": 200, "total_steps": 977, "loss": 0.7815, "lr": 9.677756856895532e-05, "epoch": 0.2047082906857728, "percentage": 20.47, "elapsed_time": "0:23:32", "remaining_time": "1:31:27"}
{"current_steps": 210, "total_steps": 977, "loss": 0.7712, "lr": 9.611666856337919e-05, "epoch": 0.21494370522006143, "percentage": 21.49, "elapsed_time": "0:35:03", "remaining_time": "2:08:02"}
{"current_steps": 220, "total_steps": 977, "loss": 0.7562, "lr": 9.53968660627812e-05, "epoch": 0.22517911975435004, "percentage": 22.52, "elapsed_time": "0:36:23", "remaining_time": "2:05:13"}
{"current_steps": 230, "total_steps": 977, "loss": 0.7546, "lr": 9.461908043459458e-05, "epoch": 0.23541453428863868, "percentage": 23.54, "elapsed_time": "0:37:36", "remaining_time": "2:02:08"}
{"current_steps": 240, "total_steps": 977, "loss": 0.7593, "lr": 9.378430510517731e-05, "epoch": 0.24564994882292732, "percentage": 24.56, "elapsed_time": "0:38:47", "remaining_time": "1:59:05"}
{"current_steps": 250, "total_steps": 977, "loss": 0.7567, "lr": 9.289360629095867e-05, "epoch": 0.25588536335721596, "percentage": 25.59, "elapsed_time": "0:39:56", "remaining_time": "1:56:09"}
{"current_steps": 260, "total_steps": 977, "loss": 0.7519, "lr": 9.194812163661474e-05, "epoch": 0.2661207778915046, "percentage": 26.61, "elapsed_time": "0:41:13", "remaining_time": "1:53:40"}
{"current_steps": 270, "total_steps": 977, "loss": 0.7487, "lr": 9.094905876201229e-05, "epoch": 0.27635619242579323, "percentage": 27.64, "elapsed_time": "0:42:25", "remaining_time": "1:51:05"}
{"current_steps": 280, "total_steps": 977, "loss": 0.7522, "lr": 8.989769371977678e-05, "epoch": 0.2865916069600819, "percentage": 28.66, "elapsed_time": "0:43:34", "remaining_time": "1:48:28"}
{"current_steps": 290, "total_steps": 977, "loss": 0.7628, "lr": 8.879536936545472e-05, "epoch": 0.2968270214943705, "percentage": 29.68, "elapsed_time": "0:44:41", "remaining_time": "1:45:51"}
{"current_steps": 300, "total_steps": 977, "loss": 0.7513, "lr": 8.764349364235196e-05, "epoch": 0.3070624360286592, "percentage": 30.71, "elapsed_time": "0:45:49", "remaining_time": "1:43:24"}
{"current_steps": 310, "total_steps": 977, "loss": 0.7545, "lr": 8.644353778323877e-05, "epoch": 0.3172978505629478, "percentage": 31.73, "elapsed_time": "0:46:51", "remaining_time": "1:40:48"}
{"current_steps": 320, "total_steps": 977, "loss": 0.7206, "lr": 8.519703443121839e-05, "epoch": 0.32753326509723646, "percentage": 32.75, "elapsed_time": "0:47:58", "remaining_time": "1:38:29"}
{"current_steps": 330, "total_steps": 977, "loss": 0.7379, "lr": 8.390557568215928e-05, "epoch": 0.33776867963152507, "percentage": 33.78, "elapsed_time": "0:49:02", "remaining_time": "1:36:09"}
{"current_steps": 340, "total_steps": 977, "loss": 0.7279, "lr": 8.25708110511914e-05, "epoch": 0.34800409416581374, "percentage": 34.8, "elapsed_time": "0:50:05", "remaining_time": "1:33:51"}
{"current_steps": 350, "total_steps": 977, "loss": 0.7239, "lr": 8.119444536586362e-05, "epoch": 0.35823950870010235, "percentage": 35.82, "elapsed_time": "0:51:09", "remaining_time": "1:31:39"}
{"current_steps": 360, "total_steps": 977, "loss": 0.7244, "lr": 7.977823658865364e-05, "epoch": 0.368474923234391, "percentage": 36.85, "elapsed_time": "0:52:14", "remaining_time": "1:29:31"}
{"current_steps": 370, "total_steps": 977, "loss": 0.7138, "lr": 7.832399357161096e-05, "epoch": 0.37871033776867963, "percentage": 37.87, "elapsed_time": "0:53:16", "remaining_time": "1:27:24"}
{"current_steps": 380, "total_steps": 977, "loss": 0.7253, "lr": 7.683357374600157e-05, "epoch": 0.3889457523029683, "percentage": 38.89, "elapsed_time": "0:54:17", "remaining_time": "1:25:18"}
{"current_steps": 390, "total_steps": 977, "loss": 0.7041, "lr": 7.530888074990457e-05, "epoch": 0.3991811668372569, "percentage": 39.92, "elapsed_time": "0:55:18", "remaining_time": "1:23:14"}
{"current_steps": 400, "total_steps": 977, "loss": 0.7156, "lr": 7.375186199679128e-05, "epoch": 0.4094165813715456, "percentage": 40.94, "elapsed_time": "0:56:11", "remaining_time": "1:21:02"}
{"current_steps": 410, "total_steps": 977, "loss": 0.7321, "lr": 7.216450618819221e-05, "epoch": 0.4196519959058342, "percentage": 41.97, "elapsed_time": "1:08:02", "remaining_time": "1:34:05"}
{"current_steps": 420, "total_steps": 977, "loss": 0.7205, "lr": 7.054884077362892e-05, "epoch": 0.42988741044012285, "percentage": 42.99, "elapsed_time": "1:08:50", "remaining_time": "1:31:17"}
{"current_steps": 430, "total_steps": 977, "loss": 0.7184, "lr": 6.890692936105493e-05, "epoch": 0.44012282497441146, "percentage": 44.01, "elapsed_time": "1:09:38", "remaining_time": "1:28:35"}
{"current_steps": 440, "total_steps": 977, "loss": 0.7043, "lr": 6.724086908111342e-05, "epoch": 0.4503582395087001, "percentage": 45.04, "elapsed_time": "1:10:28", "remaining_time": "1:26:00"}
{"current_steps": 450, "total_steps": 977, "loss": 0.7141, "lr": 6.5552787908578e-05, "epoch": 0.46059365404298874, "percentage": 46.06, "elapsed_time": "1:11:21", "remaining_time": "1:23:33"}
{"current_steps": 460, "total_steps": 977, "loss": 0.7277, "lr": 6.384484194439783e-05, "epoch": 0.47082906857727735, "percentage": 47.08, "elapsed_time": "1:12:10", "remaining_time": "1:21:07"}
{"current_steps": 470, "total_steps": 977, "loss": 0.6942, "lr": 6.211921266181862e-05, "epoch": 0.481064483111566, "percentage": 48.11, "elapsed_time": "1:12:59", "remaining_time": "1:18:44"}
{"current_steps": 480, "total_steps": 977, "loss": 0.7105, "lr": 6.037810412009692e-05, "epoch": 0.49129989764585463, "percentage": 49.13, "elapsed_time": "1:13:51", "remaining_time": "1:16:28"}
{"current_steps": 490, "total_steps": 977, "loss": 0.6919, "lr": 5.8623740149366266e-05, "epoch": 0.5015353121801432, "percentage": 50.15, "elapsed_time": "1:14:43", "remaining_time": "1:14:16"}
{"current_steps": 500, "total_steps": 977, "loss": 0.7004, "lr": 5.685836151025124e-05, "epoch": 0.5117707267144319, "percentage": 51.18, "elapsed_time": "1:15:31", "remaining_time": "1:12:03"}
{"current_steps": 510, "total_steps": 977, "loss": 0.6809, "lr": 5.508422303185682e-05, "epoch": 0.5220061412487206, "percentage": 52.2, "elapsed_time": "1:16:21", "remaining_time": "1:09:55"}
{"current_steps": 520, "total_steps": 977, "loss": 0.676, "lr": 5.3303590731788967e-05, "epoch": 0.5322415557830092, "percentage": 53.22, "elapsed_time": "1:17:10", "remaining_time": "1:07:49"}
{"current_steps": 530, "total_steps": 977, "loss": 0.7019, "lr": 5.1518738921884526e-05, "epoch": 0.5424769703172978, "percentage": 54.25, "elapsed_time": "1:18:00", "remaining_time": "1:05:47"}
{"current_steps": 540, "total_steps": 977, "loss": 0.652, "lr": 4.973194730334748e-05, "epoch": 0.5527123848515865, "percentage": 55.27, "elapsed_time": "1:18:50", "remaining_time": "1:03:48"}
{"current_steps": 550, "total_steps": 977, "loss": 0.6727, "lr": 4.794549805500157e-05, "epoch": 0.5629477993858751, "percentage": 56.29, "elapsed_time": "1:19:41", "remaining_time": "1:01:52"}
{"current_steps": 560, "total_steps": 977, "loss": 0.6787, "lr": 4.616167291837833e-05, "epoch": 0.5731832139201638, "percentage": 57.32, "elapsed_time": "1:20:28", "remaining_time": "0:59:55"}
{"current_steps": 570, "total_steps": 977, "loss": 0.678, "lr": 4.4382750283363734e-05, "epoch": 0.5834186284544524, "percentage": 58.34, "elapsed_time": "1:21:19", "remaining_time": "0:58:03"}
{"current_steps": 580, "total_steps": 977, "loss": 0.6702, "lr": 4.2611002278125716e-05, "epoch": 0.593654042988741, "percentage": 59.37, "elapsed_time": "1:22:06", "remaining_time": "0:56:12"}
{"current_steps": 590, "total_steps": 977, "loss": 0.6837, "lr": 4.084869186703939e-05, "epoch": 0.6038894575230297, "percentage": 60.39, "elapsed_time": "1:22:55", "remaining_time": "0:54:23"}
{"current_steps": 600, "total_steps": 977, "loss": 0.6803, "lr": 3.909806996031681e-05, "epoch": 0.6141248720573184, "percentage": 61.41, "elapsed_time": "1:23:43", "remaining_time": "0:52:36"}
{"current_steps": 610, "total_steps": 977, "loss": 0.6571, "lr": 3.736137253903294e-05, "epoch": 0.6243602865916069, "percentage": 62.44, "elapsed_time": "1:34:01", "remaining_time": "0:56:33"}
{"current_steps": 620, "total_steps": 977, "loss": 0.6733, "lr": 3.564081779921964e-05, "epoch": 0.6345957011258956, "percentage": 63.46, "elapsed_time": "1:34:50", "remaining_time": "0:54:36"}
{"current_steps": 630, "total_steps": 977, "loss": 0.679, "lr": 3.393860331867589e-05, "epoch": 0.6448311156601843, "percentage": 64.48, "elapsed_time": "1:35:34", "remaining_time": "0:52:38"}
{"current_steps": 640, "total_steps": 977, "loss": 0.6679, "lr": 3.2256903250112384e-05, "epoch": 0.6550665301944729, "percentage": 65.51, "elapsed_time": "1:36:23", "remaining_time": "0:50:45"}
{"current_steps": 650, "total_steps": 977, "loss": 0.6579, "lr": 3.0597865544216024e-05, "epoch": 0.6653019447287615, "percentage": 66.53, "elapsed_time": "1:37:10", "remaining_time": "0:48:53"}
{"current_steps": 660, "total_steps": 977, "loss": 0.6534, "lr": 2.8963609206180714e-05, "epoch": 0.6755373592630501, "percentage": 67.55, "elapsed_time": "1:37:57", "remaining_time": "0:47:03"}
{"current_steps": 670, "total_steps": 977, "loss": 0.653, "lr": 2.735622158920898e-05, "epoch": 0.6857727737973388, "percentage": 68.58, "elapsed_time": "1:38:48", "remaining_time": "0:45:16"}
{"current_steps": 680, "total_steps": 977, "loss": 0.6504, "lr": 2.5777755728441e-05, "epoch": 0.6960081883316275, "percentage": 69.6, "elapsed_time": "1:39:38", "remaining_time": "0:43:31"}
{"current_steps": 690, "total_steps": 977, "loss": 0.6441, "lr": 2.4230227718716235e-05, "epoch": 0.706243602865916, "percentage": 70.62, "elapsed_time": "1:40:25", "remaining_time": "0:41:46"}
{"current_steps": 700, "total_steps": 977, "loss": 0.6461, "lr": 2.271561413951735e-05, "epoch": 0.7164790174002047, "percentage": 71.65, "elapsed_time": "1:41:12", "remaining_time": "0:40:03"}
{"current_steps": 710, "total_steps": 977, "loss": 0.6451, "lr": 2.1235849530384762e-05, "epoch": 0.7267144319344934, "percentage": 72.67, "elapsed_time": "1:42:00", "remaining_time": "0:38:21"}
{"current_steps": 720, "total_steps": 977, "loss": 0.6384, "lr": 1.979282392002691e-05, "epoch": 0.736949846468782, "percentage": 73.69, "elapsed_time": "1:42:51", "remaining_time": "0:36:42"}
{"current_steps": 730, "total_steps": 977, "loss": 0.6449, "lr": 1.8388380412281907e-05, "epoch": 0.7471852610030706, "percentage": 74.72, "elapsed_time": "1:43:37", "remaining_time": "0:35:03"}
{"current_steps": 740, "total_steps": 977, "loss": 0.6326, "lr": 1.7024312832013977e-05, "epoch": 0.7574206755373593, "percentage": 75.74, "elapsed_time": "1:44:24", "remaining_time": "0:33:26"}
{"current_steps": 750, "total_steps": 977, "loss": 0.631, "lr": 1.5702363433951407e-05, "epoch": 0.7676560900716479, "percentage": 76.77, "elapsed_time": "1:45:11", "remaining_time": "0:31:50"}
{"current_steps": 760, "total_steps": 977, "loss": 0.642, "lr": 1.4424220677392387e-05, "epoch": 0.7778915046059366, "percentage": 77.79, "elapsed_time": "1:46:00", "remaining_time": "0:30:16"}
{"current_steps": 770, "total_steps": 977, "loss": 0.6063, "lr": 1.3191517069621157e-05, "epoch": 0.7881269191402251, "percentage": 78.81, "elapsed_time": "1:46:48", "remaining_time": "0:28:42"}
{"current_steps": 780, "total_steps": 977, "loss": 0.6267, "lr": 1.2005827080788834e-05, "epoch": 0.7983623336745138, "percentage": 79.84, "elapsed_time": "1:47:37", "remaining_time": "0:27:10"}
{"current_steps": 790, "total_steps": 977, "loss": 0.626, "lr": 1.086866513292198e-05, "epoch": 0.8085977482088025, "percentage": 80.86, "elapsed_time": "1:48:23", "remaining_time": "0:25:39"}
{"current_steps": 800, "total_steps": 977, "loss": 0.6379, "lr": 9.781483665627778e-06, "epoch": 0.8188331627430911, "percentage": 81.88, "elapsed_time": "1:49:10", "remaining_time": "0:24:09"}
{"current_steps": 810, "total_steps": 977, "loss": 0.6166, "lr": 8.745671280966177e-06, "epoch": 0.8290685772773797, "percentage": 82.91, "elapsed_time": "1:58:29", "remaining_time": "0:24:25"}
{"current_steps": 820, "total_steps": 977, "loss": 0.6283, "lr": 7.762550969858512e-06, "epoch": 0.8393039918116684, "percentage": 83.93, "elapsed_time": "1:59:16", "remaining_time": "0:22:50"}
{"current_steps": 830, "total_steps": 977, "loss": 0.6188, "lr": 6.8333784222979146e-06, "epoch": 0.849539406345957, "percentage": 84.95, "elapsed_time": "2:00:04", "remaining_time": "0:21:16"}
{"current_steps": 840, "total_steps": 977, "loss": 0.6118, "lr": 5.959340423519777e-06, "epoch": 0.8597748208802457, "percentage": 85.98, "elapsed_time": "2:00:52", "remaining_time": "0:19:42"}
{"current_steps": 850, "total_steps": 977, "loss": 0.6171, "lr": 5.14155333818086e-06, "epoch": 0.8700102354145343, "percentage": 87.0, "elapsed_time": "2:01:41", "remaining_time": "0:18:10"}
{"current_steps": 860, "total_steps": 977, "loss": 0.6275, "lr": 4.381061684483018e-06, "epoch": 0.8802456499488229, "percentage": 88.02, "elapsed_time": "2:02:30", "remaining_time": "0:16:40"}
{"current_steps": 870, "total_steps": 977, "loss": 0.6346, "lr": 3.6788368000627625e-06, "epoch": 0.8904810644831116, "percentage": 89.05, "elapsed_time": "2:03:17", "remaining_time": "0:15:09"}
{"current_steps": 880, "total_steps": 977, "loss": 0.6223, "lr": 3.035775601350688e-06, "epoch": 0.9007164790174002, "percentage": 90.07, "elapsed_time": "2:04:03", "remaining_time": "0:13:40"}
{"current_steps": 890, "total_steps": 977, "loss": 0.6219, "lr": 2.4526994379853617e-06, "epoch": 0.9109518935516888, "percentage": 91.1, "elapsed_time": "2:04:48", "remaining_time": "0:12:12"}
{"current_steps": 900, "total_steps": 977, "loss": 0.6008, "lr": 1.9303530437448035e-06, "epoch": 0.9211873080859775, "percentage": 92.12, "elapsed_time": "2:05:36", "remaining_time": "0:10:44"}
{"current_steps": 910, "total_steps": 977, "loss": 0.6169, "lr": 1.4694035853356769e-06, "epoch": 0.9314227226202662, "percentage": 93.14, "elapsed_time": "2:06:24", "remaining_time": "0:09:18"}
{"current_steps": 920, "total_steps": 977, "loss": 0.619, "lr": 1.070439810254803e-06, "epoch": 0.9416581371545547, "percentage": 94.17, "elapsed_time": "2:07:11", "remaining_time": "0:07:52"}
{"current_steps": 930, "total_steps": 977, "loss": 0.5986, "lr": 7.339712948117417e-07, "epoch": 0.9518935516888434, "percentage": 95.19, "elapsed_time": "2:07:57", "remaining_time": "0:06:27"}
{"current_steps": 940, "total_steps": 977, "loss": 0.6225, "lr": 4.6042779327264973e-07, "epoch": 0.962128966223132, "percentage": 96.21, "elapsed_time": "2:08:44", "remaining_time": "0:05:04"}
{"current_steps": 950, "total_steps": 977, "loss": 0.616, "lr": 2.5015868895682527e-07, "epoch": 0.9723643807574207, "percentage": 97.24, "elapsed_time": "2:09:30", "remaining_time": "0:03:40"}
{"current_steps": 960, "total_steps": 977, "loss": 0.6218, "lr": 1.0343254798702018e-07, "epoch": 0.9825997952917093, "percentage": 98.26, "elapsed_time": "2:10:17", "remaining_time": "0:02:18"}
{"current_steps": 970, "total_steps": 977, "loss": 0.6047, "lr": 2.0436776263471624e-08, "epoch": 0.9928352098259979, "percentage": 99.28, "elapsed_time": "2:11:03", "remaining_time": "0:00:56"}
{"current_steps": 977, "total_steps": 977, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "2:20:55", "remaining_time": "0:00:00"}