web_qwen_sft_behavior_correct / trainer_log.jsonl
zizi-0123's picture
Add files using upload-large-folder tool
c15b306 verified
{"current_steps": 10, "total_steps": 915, "loss": 2.2481, "lr": 9.782608695652175e-07, "epoch": 0.03281378178835111, "percentage": 1.09, "elapsed_time": "0:01:11", "remaining_time": "1:48:19"}
{"current_steps": 20, "total_steps": 915, "loss": 1.9777, "lr": 2.065217391304348e-06, "epoch": 0.06562756357670221, "percentage": 2.19, "elapsed_time": "0:02:15", "remaining_time": "1:41:14"}
{"current_steps": 30, "total_steps": 915, "loss": 1.5908, "lr": 3.152173913043479e-06, "epoch": 0.09844134536505332, "percentage": 3.28, "elapsed_time": "0:03:23", "remaining_time": "1:39:49"}
{"current_steps": 40, "total_steps": 915, "loss": 1.4181, "lr": 4.239130434782609e-06, "epoch": 0.13125512715340443, "percentage": 4.37, "elapsed_time": "0:04:42", "remaining_time": "1:42:50"}
{"current_steps": 50, "total_steps": 915, "loss": 1.3642, "lr": 5.3260869565217395e-06, "epoch": 0.16406890894175555, "percentage": 5.46, "elapsed_time": "0:06:04", "remaining_time": "1:45:12"}
{"current_steps": 60, "total_steps": 915, "loss": 1.3139, "lr": 6.41304347826087e-06, "epoch": 0.19688269073010664, "percentage": 6.56, "elapsed_time": "0:07:15", "remaining_time": "1:43:29"}
{"current_steps": 70, "total_steps": 915, "loss": 1.2641, "lr": 7.500000000000001e-06, "epoch": 0.22969647251845776, "percentage": 7.65, "elapsed_time": "0:08:31", "remaining_time": "1:42:56"}
{"current_steps": 80, "total_steps": 915, "loss": 1.2517, "lr": 8.586956521739131e-06, "epoch": 0.26251025430680885, "percentage": 8.74, "elapsed_time": "0:09:43", "remaining_time": "1:41:26"}
{"current_steps": 90, "total_steps": 915, "loss": 1.2245, "lr": 9.673913043478262e-06, "epoch": 0.29532403609515995, "percentage": 9.84, "elapsed_time": "0:10:57", "remaining_time": "1:40:30"}
{"current_steps": 100, "total_steps": 915, "loss": 1.2013, "lr": 9.998215114657564e-06, "epoch": 0.3281378178835111, "percentage": 10.93, "elapsed_time": "0:12:11", "remaining_time": "1:39:24"}
{"current_steps": 110, "total_steps": 915, "loss": 1.2011, "lr": 9.98947588668843e-06, "epoch": 0.3609515996718622, "percentage": 12.02, "elapsed_time": "0:13:29", "remaining_time": "1:38:43"}
{"current_steps": 120, "total_steps": 915, "loss": 1.189, "lr": 9.973467196782484e-06, "epoch": 0.3937653814602133, "percentage": 13.11, "elapsed_time": "0:14:42", "remaining_time": "1:37:27"}
{"current_steps": 130, "total_steps": 915, "loss": 1.1834, "lr": 9.950212368945013e-06, "epoch": 0.4265791632485644, "percentage": 14.21, "elapsed_time": "0:15:58", "remaining_time": "1:36:24"}
{"current_steps": 140, "total_steps": 915, "loss": 1.1579, "lr": 9.91974528450737e-06, "epoch": 0.4593929450369155, "percentage": 15.3, "elapsed_time": "0:17:19", "remaining_time": "1:35:52"}
{"current_steps": 150, "total_steps": 915, "loss": 1.1714, "lr": 9.882110332763275e-06, "epoch": 0.4922067268252666, "percentage": 16.39, "elapsed_time": "0:18:50", "remaining_time": "1:36:07"}
{"current_steps": 160, "total_steps": 915, "loss": 1.1613, "lr": 9.83736234629543e-06, "epoch": 0.5250205086136177, "percentage": 17.49, "elapsed_time": "0:20:16", "remaining_time": "1:35:42"}
{"current_steps": 170, "total_steps": 915, "loss": 1.159, "lr": 9.785566521086695e-06, "epoch": 0.5578342904019689, "percentage": 18.58, "elapsed_time": "0:21:39", "remaining_time": "1:34:56"}
{"current_steps": 180, "total_steps": 915, "loss": 1.1349, "lr": 9.726798321532205e-06, "epoch": 0.5906480721903199, "percentage": 19.67, "elapsed_time": "0:22:56", "remaining_time": "1:33:38"}
{"current_steps": 190, "total_steps": 915, "loss": 1.1539, "lr": 9.661143370490846e-06, "epoch": 0.623461853978671, "percentage": 20.77, "elapsed_time": "0:24:16", "remaining_time": "1:32:38"}
{"current_steps": 200, "total_steps": 915, "loss": 1.1622, "lr": 9.588697324536254e-06, "epoch": 0.6562756357670222, "percentage": 21.86, "elapsed_time": "0:25:36", "remaining_time": "1:31:32"}
{"current_steps": 210, "total_steps": 915, "loss": 1.1318, "lr": 9.509565734589105e-06, "epoch": 0.6890894175553732, "percentage": 22.95, "elapsed_time": "0:27:31", "remaining_time": "1:32:23"}
{"current_steps": 220, "total_steps": 915, "loss": 1.0885, "lr": 9.423863892133754e-06, "epoch": 0.7219031993437244, "percentage": 24.04, "elapsed_time": "0:28:48", "remaining_time": "1:30:59"}
{"current_steps": 230, "total_steps": 915, "loss": 1.1129, "lr": 9.33171666124326e-06, "epoch": 0.7547169811320755, "percentage": 25.14, "elapsed_time": "0:30:19", "remaining_time": "1:30:18"}
{"current_steps": 240, "total_steps": 915, "loss": 1.1325, "lr": 9.233258296657547e-06, "epoch": 0.7875307629204266, "percentage": 26.23, "elapsed_time": "0:31:33", "remaining_time": "1:28:45"}
{"current_steps": 250, "total_steps": 915, "loss": 1.1133, "lr": 9.128632248179761e-06, "epoch": 0.8203445447087777, "percentage": 27.32, "elapsed_time": "0:32:55", "remaining_time": "1:27:35"}
{"current_steps": 260, "total_steps": 915, "loss": 1.1289, "lr": 9.017990951675764e-06, "epoch": 0.8531583264971287, "percentage": 28.42, "elapsed_time": "0:34:15", "remaining_time": "1:26:17"}
{"current_steps": 270, "total_steps": 915, "loss": 1.1303, "lr": 8.901495606981339e-06, "epoch": 0.8859721082854799, "percentage": 29.51, "elapsed_time": "0:35:26", "remaining_time": "1:24:39"}
{"current_steps": 280, "total_steps": 915, "loss": 1.1177, "lr": 8.779315943040629e-06, "epoch": 0.918785890073831, "percentage": 30.6, "elapsed_time": "0:36:47", "remaining_time": "1:23:26"}
{"current_steps": 290, "total_steps": 915, "loss": 1.1254, "lr": 8.65162997061802e-06, "epoch": 0.9515996718621821, "percentage": 31.69, "elapsed_time": "0:38:24", "remaining_time": "1:22:46"}
{"current_steps": 300, "total_steps": 915, "loss": 1.1169, "lr": 8.518623722943747e-06, "epoch": 0.9844134536505332, "percentage": 32.79, "elapsed_time": "0:39:45", "remaining_time": "1:21:30"}
{"current_steps": 310, "total_steps": 915, "loss": 1.0874, "lr": 8.380490984671105e-06, "epoch": 1.0164068908941755, "percentage": 33.88, "elapsed_time": "0:41:07", "remaining_time": "1:20:15"}
{"current_steps": 320, "total_steps": 915, "loss": 1.0118, "lr": 8.23743300954015e-06, "epoch": 1.0492206726825266, "percentage": 34.97, "elapsed_time": "0:42:22", "remaining_time": "1:18:48"}
{"current_steps": 330, "total_steps": 915, "loss": 1.0411, "lr": 8.089658227159239e-06, "epoch": 1.0820344544708778, "percentage": 36.07, "elapsed_time": "0:43:42", "remaining_time": "1:17:28"}
{"current_steps": 340, "total_steps": 915, "loss": 1.0222, "lr": 7.937381939331628e-06, "epoch": 1.114848236259229, "percentage": 37.16, "elapsed_time": "0:44:58", "remaining_time": "1:16:03"}
{"current_steps": 350, "total_steps": 915, "loss": 1.046, "lr": 7.780826006369586e-06, "epoch": 1.14766201804758, "percentage": 38.25, "elapsed_time": "0:46:27", "remaining_time": "1:15:00"}
{"current_steps": 360, "total_steps": 915, "loss": 1.0483, "lr": 7.620218523852987e-06, "epoch": 1.1804757998359312, "percentage": 39.34, "elapsed_time": "0:47:41", "remaining_time": "1:13:31"}
{"current_steps": 370, "total_steps": 915, "loss": 1.0435, "lr": 7.4557934903034035e-06, "epoch": 1.2132895816242821, "percentage": 40.44, "elapsed_time": "0:49:10", "remaining_time": "1:12:25"}
{"current_steps": 380, "total_steps": 915, "loss": 1.028, "lr": 7.287790466257854e-06, "epoch": 1.2461033634126333, "percentage": 41.53, "elapsed_time": "0:50:20", "remaining_time": "1:10:53"}
{"current_steps": 390, "total_steps": 915, "loss": 1.03, "lr": 7.116454225238909e-06, "epoch": 1.2789171452009844, "percentage": 42.62, "elapsed_time": "0:51:42", "remaining_time": "1:09:36"}
{"current_steps": 400, "total_steps": 915, "loss": 1.0192, "lr": 6.942034397129702e-06, "epoch": 1.3117309269893356, "percentage": 43.72, "elapsed_time": "0:52:47", "remaining_time": "1:07:58"}
{"current_steps": 410, "total_steps": 915, "loss": 1.0175, "lr": 6.764785104473411e-06, "epoch": 1.3445447087776867, "percentage": 44.81, "elapsed_time": "0:54:49", "remaining_time": "1:07:31"}
{"current_steps": 420, "total_steps": 915, "loss": 1.0607, "lr": 6.584964592227135e-06, "epoch": 1.3773584905660377, "percentage": 45.9, "elapsed_time": "0:56:01", "remaining_time": "1:06:01"}
{"current_steps": 430, "total_steps": 915, "loss": 1.021, "lr": 6.402834851509564e-06, "epoch": 1.4101722723543888, "percentage": 46.99, "elapsed_time": "0:57:17", "remaining_time": "1:04:37"}
{"current_steps": 440, "total_steps": 915, "loss": 1.0269, "lr": 6.2186612378906545e-06, "epoch": 1.44298605414274, "percentage": 48.09, "elapsed_time": "0:58:48", "remaining_time": "1:03:29"}
{"current_steps": 450, "total_steps": 915, "loss": 1.0066, "lr": 6.0327120847794415e-06, "epoch": 1.475799835931091, "percentage": 49.18, "elapsed_time": "1:00:03", "remaining_time": "1:02:03"}
{"current_steps": 460, "total_steps": 915, "loss": 1.0516, "lr": 5.845258312473252e-06, "epoch": 1.5086136177194422, "percentage": 50.27, "elapsed_time": "1:01:17", "remaining_time": "1:00:37"}
{"current_steps": 470, "total_steps": 915, "loss": 1.0027, "lr": 5.656573033437932e-06, "epoch": 1.5414273995077932, "percentage": 51.37, "elapsed_time": "1:02:40", "remaining_time": "0:59:20"}
{"current_steps": 480, "total_steps": 915, "loss": 1.0135, "lr": 5.466931154394171e-06, "epoch": 1.5742411812961445, "percentage": 52.46, "elapsed_time": "1:03:54", "remaining_time": "0:57:55"}
{"current_steps": 490, "total_steps": 915, "loss": 1.0147, "lr": 5.276608975789683e-06, "epoch": 1.6070549630844955, "percentage": 53.55, "elapsed_time": "1:05:20", "remaining_time": "0:56:40"}
{"current_steps": 500, "total_steps": 915, "loss": 1.0174, "lr": 5.085883789240764e-06, "epoch": 1.6398687448728466, "percentage": 54.64, "elapsed_time": "1:06:50", "remaining_time": "0:55:28"}
{"current_steps": 510, "total_steps": 915, "loss": 0.9969, "lr": 4.8950334735297746e-06, "epoch": 1.6726825266611978, "percentage": 55.74, "elapsed_time": "1:08:10", "remaining_time": "0:54:08"}
{"current_steps": 520, "total_steps": 915, "loss": 1.0161, "lr": 4.704336089747135e-06, "epoch": 1.7054963084495487, "percentage": 56.83, "elapsed_time": "1:09:28", "remaining_time": "0:52:46"}
{"current_steps": 530, "total_steps": 915, "loss": 1.0112, "lr": 4.514069476167716e-06, "epoch": 1.7383100902379, "percentage": 57.92, "elapsed_time": "1:10:39", "remaining_time": "0:51:19"}
{"current_steps": 540, "total_steps": 915, "loss": 1.0389, "lr": 4.324510843451851e-06, "epoch": 1.771123872026251, "percentage": 59.02, "elapsed_time": "1:12:09", "remaining_time": "0:50:06"}
{"current_steps": 550, "total_steps": 915, "loss": 1.0123, "lr": 4.135936370760759e-06, "epoch": 1.8039376538146021, "percentage": 60.11, "elapsed_time": "1:13:17", "remaining_time": "0:48:38"}
{"current_steps": 560, "total_steps": 915, "loss": 1.0228, "lr": 3.9486208033748315e-06, "epoch": 1.8367514356029533, "percentage": 61.2, "elapsed_time": "1:14:54", "remaining_time": "0:47:29"}
{"current_steps": 570, "total_steps": 915, "loss": 1.012, "lr": 3.762837052401004e-06, "epoch": 1.8695652173913042, "percentage": 62.3, "elapsed_time": "1:16:10", "remaining_time": "0:46:06"}
{"current_steps": 580, "total_steps": 915, "loss": 1.0164, "lr": 3.5788557971524695e-06, "epoch": 1.9023789991796556, "percentage": 63.39, "elapsed_time": "1:17:25", "remaining_time": "0:44:42"}
{"current_steps": 590, "total_steps": 915, "loss": 1.0279, "lr": 3.3969450907799966e-06, "epoch": 1.9351927809680065, "percentage": 64.48, "elapsed_time": "1:18:30", "remaining_time": "0:43:14"}
{"current_steps": 600, "total_steps": 915, "loss": 1.0159, "lr": 3.217369969729476e-06, "epoch": 1.9680065627563577, "percentage": 65.57, "elapsed_time": "1:19:50", "remaining_time": "0:41:54"}
{"current_steps": 610, "total_steps": 915, "loss": 1.0203, "lr": 3.0403920675946826e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:21:53", "remaining_time": "0:40:56"}
{"current_steps": 620, "total_steps": 915, "loss": 0.9542, "lr": 2.8662692339278387e-06, "epoch": 2.032813781788351, "percentage": 67.76, "elapsed_time": "1:23:07", "remaining_time": "0:39:33"}
{"current_steps": 630, "total_steps": 915, "loss": 0.957, "lr": 2.6952551585633947e-06, "epoch": 2.0656275635767023, "percentage": 68.85, "elapsed_time": "1:24:24", "remaining_time": "0:38:11"}
{"current_steps": 640, "total_steps": 915, "loss": 0.9479, "lr": 2.52759900200232e-06, "epoch": 2.0984413453650532, "percentage": 69.95, "elapsed_time": "1:25:51", "remaining_time": "0:36:53"}
{"current_steps": 650, "total_steps": 915, "loss": 0.9242, "lr": 2.3635450323954773e-06, "epoch": 2.1312551271534046, "percentage": 71.04, "elapsed_time": "1:27:27", "remaining_time": "0:35:39"}
{"current_steps": 660, "total_steps": 915, "loss": 0.925, "lr": 2.2033322696549197e-06, "epoch": 2.1640689089417555, "percentage": 72.13, "elapsed_time": "1:28:42", "remaining_time": "0:34:16"}
{"current_steps": 670, "total_steps": 915, "loss": 0.9249, "lr": 2.0471941372116793e-06, "epoch": 2.1968826907301064, "percentage": 73.22, "elapsed_time": "1:29:54", "remaining_time": "0:32:52"}
{"current_steps": 680, "total_steps": 915, "loss": 0.9725, "lr": 1.8953581219273987e-06, "epoch": 2.229696472518458, "percentage": 74.32, "elapsed_time": "1:31:09", "remaining_time": "0:31:30"}
{"current_steps": 690, "total_steps": 915, "loss": 0.9498, "lr": 1.7480454426552773e-06, "epoch": 2.2625102543068087, "percentage": 75.41, "elapsed_time": "1:32:24", "remaining_time": "0:30:08"}
{"current_steps": 700, "total_steps": 915, "loss": 0.9304, "lr": 1.6054707279332865e-06, "epoch": 2.29532403609516, "percentage": 76.5, "elapsed_time": "1:33:42", "remaining_time": "0:28:46"}
{"current_steps": 710, "total_steps": 915, "loss": 0.9443, "lr": 1.4678417032791653e-06, "epoch": 2.328137817883511, "percentage": 77.6, "elapsed_time": "1:34:58", "remaining_time": "0:27:25"}
{"current_steps": 720, "total_steps": 915, "loss": 0.9515, "lr": 1.335358888542862e-06, "epoch": 2.3609515996718624, "percentage": 78.69, "elapsed_time": "1:36:17", "remaining_time": "0:26:04"}
{"current_steps": 730, "total_steps": 915, "loss": 0.9601, "lr": 1.20821530575733e-06, "epoch": 2.3937653814602133, "percentage": 79.78, "elapsed_time": "1:37:43", "remaining_time": "0:24:45"}
{"current_steps": 740, "total_steps": 915, "loss": 0.928, "lr": 1.0865961979133245e-06, "epoch": 2.4265791632485643, "percentage": 80.87, "elapsed_time": "1:39:00", "remaining_time": "0:23:24"}
{"current_steps": 750, "total_steps": 915, "loss": 0.9493, "lr": 9.706787590679685e-07, "epoch": 2.4593929450369156, "percentage": 81.97, "elapsed_time": "1:40:17", "remaining_time": "0:22:03"}
{"current_steps": 760, "total_steps": 915, "loss": 0.9413, "lr": 8.606318761802584e-07, "epoch": 2.4922067268252666, "percentage": 83.06, "elapsed_time": "1:41:32", "remaining_time": "0:20:42"}
{"current_steps": 770, "total_steps": 915, "loss": 0.9436, "lr": 7.566158830496917e-07, "epoch": 2.5250205086136175, "percentage": 84.15, "elapsed_time": "1:42:48", "remaining_time": "0:19:21"}
{"current_steps": 780, "total_steps": 915, "loss": 0.9485, "lr": 6.587823267164911e-07, "epoch": 2.557834290401969, "percentage": 85.25, "elapsed_time": "1:44:04", "remaining_time": "0:18:00"}
{"current_steps": 790, "total_steps": 915, "loss": 0.9382, "lr": 5.672737466637701e-07, "epoch": 2.59064807219032, "percentage": 86.34, "elapsed_time": "1:45:14", "remaining_time": "0:16:39"}
{"current_steps": 800, "total_steps": 915, "loss": 0.94, "lr": 4.822234671433552e-07, "epoch": 2.623461853978671, "percentage": 87.43, "elapsed_time": "1:46:23", "remaining_time": "0:15:17"}
{"current_steps": 810, "total_steps": 915, "loss": 0.9456, "lr": 4.03755402927804e-07, "epoch": 2.656275635767022, "percentage": 88.52, "elapsed_time": "1:48:34", "remaining_time": "0:14:04"}
{"current_steps": 820, "total_steps": 915, "loss": 0.9454, "lr": 3.319838787716634e-07, "epoch": 2.6890894175553735, "percentage": 89.62, "elapsed_time": "1:49:46", "remaining_time": "0:12:43"}
{"current_steps": 830, "total_steps": 915, "loss": 0.947, "lr": 2.6701346284499e-07, "epoch": 2.7219031993437244, "percentage": 90.71, "elapsed_time": "1:50:57", "remaining_time": "0:11:21"}
{"current_steps": 840, "total_steps": 915, "loss": 0.9476, "lr": 2.0893881438180275e-07, "epoch": 2.7547169811320753, "percentage": 91.8, "elapsed_time": "1:52:13", "remaining_time": "0:10:01"}
{"current_steps": 850, "total_steps": 915, "loss": 0.9455, "lr": 1.578445457654637e-07, "epoch": 2.7875307629204267, "percentage": 92.9, "elapsed_time": "1:53:41", "remaining_time": "0:08:41"}
{"current_steps": 860, "total_steps": 915, "loss": 0.9604, "lr": 1.1380509925189853e-07, "epoch": 2.8203445447087776, "percentage": 93.99, "elapsed_time": "1:55:01", "remaining_time": "0:07:21"}
{"current_steps": 870, "total_steps": 915, "loss": 0.9678, "lr": 7.688463851028227e-08, "epoch": 2.8531583264971285, "percentage": 95.08, "elapsed_time": "1:56:18", "remaining_time": "0:06:00"}
{"current_steps": 880, "total_steps": 915, "loss": 0.9369, "lr": 4.713695513920147e-08, "epoch": 2.88597210828548, "percentage": 96.17, "elapsed_time": "1:57:39", "remaining_time": "0:04:40"}
{"current_steps": 890, "total_steps": 915, "loss": 0.9766, "lr": 2.4605390294497043e-08, "epoch": 2.9187858900738313, "percentage": 97.27, "elapsed_time": "1:58:57", "remaining_time": "0:03:20"}
{"current_steps": 900, "total_steps": 915, "loss": 0.9369, "lr": 9.322771542978892e-09, "epoch": 2.951599671862182, "percentage": 98.36, "elapsed_time": "2:00:05", "remaining_time": "0:02:00"}
{"current_steps": 910, "total_steps": 915, "loss": 0.931, "lr": 1.3113650340046413e-09, "epoch": 2.984413453650533, "percentage": 99.45, "elapsed_time": "2:01:31", "remaining_time": "0:00:40"}
{"current_steps": 915, "total_steps": 915, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:03:06", "remaining_time": "0:00:00"}