qwen3_14b_distill_32b_5e5 / trainer_log.jsonl
aaabiao's picture
Add files using upload-large-folder tool
056a0e4 verified
{"current_steps": 10, "total_steps": 879, "loss": 0.6914, "lr": 5.113636363636364e-06, "epoch": 0.034129692832764506, "percentage": 1.14, "elapsed_time": "0:15:23", "remaining_time": "22:18:06"}
{"current_steps": 20, "total_steps": 879, "loss": 0.5785, "lr": 1.0795454545454547e-05, "epoch": 0.06825938566552901, "percentage": 2.28, "elapsed_time": "0:29:06", "remaining_time": "20:50:19"}
{"current_steps": 30, "total_steps": 879, "loss": 0.5215, "lr": 1.6477272727272726e-05, "epoch": 0.10238907849829351, "percentage": 3.41, "elapsed_time": "0:42:37", "remaining_time": "20:06:25"}
{"current_steps": 40, "total_steps": 879, "loss": 0.4933, "lr": 2.215909090909091e-05, "epoch": 0.13651877133105803, "percentage": 4.55, "elapsed_time": "0:57:28", "remaining_time": "20:05:33"}
{"current_steps": 50, "total_steps": 879, "loss": 0.4751, "lr": 2.784090909090909e-05, "epoch": 0.17064846416382254, "percentage": 5.69, "elapsed_time": "1:11:44", "remaining_time": "19:49:33"}
{"current_steps": 60, "total_steps": 879, "loss": 0.4648, "lr": 3.352272727272727e-05, "epoch": 0.20477815699658702, "percentage": 6.83, "elapsed_time": "1:27:51", "remaining_time": "19:59:19"}
{"current_steps": 70, "total_steps": 879, "loss": 0.4589, "lr": 3.9204545454545456e-05, "epoch": 0.23890784982935154, "percentage": 7.96, "elapsed_time": "1:42:15", "remaining_time": "19:41:45"}
{"current_steps": 80, "total_steps": 879, "loss": 0.4492, "lr": 4.488636363636364e-05, "epoch": 0.27303754266211605, "percentage": 9.1, "elapsed_time": "1:56:00", "remaining_time": "19:18:40"}
{"current_steps": 90, "total_steps": 879, "loss": 0.4529, "lr": 4.99998028230155e-05, "epoch": 0.30716723549488056, "percentage": 10.24, "elapsed_time": "2:10:38", "remaining_time": "19:05:16"}
{"current_steps": 100, "total_steps": 879, "loss": 0.4483, "lr": 4.997614534810769e-05, "epoch": 0.3412969283276451, "percentage": 11.38, "elapsed_time": "2:24:36", "remaining_time": "18:46:26"}
{"current_steps": 110, "total_steps": 879, "loss": 0.4408, "lr": 4.991309523184661e-05, "epoch": 0.37542662116040953, "percentage": 12.51, "elapsed_time": "2:39:52", "remaining_time": "18:37:43"}
{"current_steps": 120, "total_steps": 879, "loss": 0.4361, "lr": 4.9810751917544375e-05, "epoch": 0.40955631399317405, "percentage": 13.65, "elapsed_time": "2:54:02", "remaining_time": "18:20:50"}
{"current_steps": 130, "total_steps": 879, "loss": 0.4375, "lr": 4.96692768221618e-05, "epoch": 0.44368600682593856, "percentage": 14.79, "elapsed_time": "3:08:22", "remaining_time": "18:05:17"}
{"current_steps": 140, "total_steps": 879, "loss": 0.4343, "lr": 4.948889308171989e-05, "epoch": 0.4778156996587031, "percentage": 15.93, "elapsed_time": "3:23:31", "remaining_time": "17:54:16"}
{"current_steps": 150, "total_steps": 879, "loss": 0.4322, "lr": 4.926988519936732e-05, "epoch": 0.5119453924914675, "percentage": 17.06, "elapsed_time": "3:37:48", "remaining_time": "17:38:34"}
{"current_steps": 160, "total_steps": 879, "loss": 0.4287, "lr": 4.9012598596659034e-05, "epoch": 0.5460750853242321, "percentage": 18.2, "elapsed_time": "3:53:36", "remaining_time": "17:29:48"}
{"current_steps": 170, "total_steps": 879, "loss": 0.4282, "lr": 4.8717439068753755e-05, "epoch": 0.5802047781569966, "percentage": 19.34, "elapsed_time": "4:07:52", "remaining_time": "17:13:45"}
{"current_steps": 180, "total_steps": 879, "loss": 0.4227, "lr": 4.838487214438951e-05, "epoch": 0.6143344709897611, "percentage": 20.48, "elapsed_time": "4:22:53", "remaining_time": "17:00:55"}
{"current_steps": 190, "total_steps": 879, "loss": 0.4286, "lr": 4.801542235164678e-05, "epoch": 0.6484641638225256, "percentage": 21.62, "elapsed_time": "4:37:21", "remaining_time": "16:45:47"}
{"current_steps": 200, "total_steps": 879, "loss": 0.4287, "lr": 4.7609672390657276e-05, "epoch": 0.6825938566552902, "percentage": 22.75, "elapsed_time": "4:51:32", "remaining_time": "16:29:45"}
{"current_steps": 210, "total_steps": 879, "loss": 0.4215, "lr": 4.716826221456305e-05, "epoch": 0.7167235494880546, "percentage": 23.89, "elapsed_time": "5:07:35", "remaining_time": "16:19:52"}
{"current_steps": 220, "total_steps": 879, "loss": 0.4197, "lr": 4.669188802017569e-05, "epoch": 0.7508532423208191, "percentage": 25.03, "elapsed_time": "5:22:42", "remaining_time": "16:06:40"}
{"current_steps": 230, "total_steps": 879, "loss": 0.425, "lr": 4.6181301149927245e-05, "epoch": 0.7849829351535836, "percentage": 26.17, "elapsed_time": "5:36:44", "remaining_time": "15:50:10"}
{"current_steps": 240, "total_steps": 879, "loss": 0.4232, "lr": 4.563730690684502e-05, "epoch": 0.8191126279863481, "percentage": 27.3, "elapsed_time": "5:50:47", "remaining_time": "15:33:58"}
{"current_steps": 250, "total_steps": 879, "loss": 0.4252, "lr": 4.5060763284419114e-05, "epoch": 0.8532423208191127, "percentage": 28.44, "elapsed_time": "6:05:16", "remaining_time": "15:19:01"}
{"current_steps": 260, "total_steps": 879, "loss": 0.4173, "lr": 4.445257961336594e-05, "epoch": 0.8873720136518771, "percentage": 29.58, "elapsed_time": "6:21:19", "remaining_time": "15:07:50"}
{"current_steps": 270, "total_steps": 879, "loss": 0.4205, "lr": 4.3813715127422186e-05, "epoch": 0.9215017064846417, "percentage": 30.72, "elapsed_time": "6:35:54", "remaining_time": "14:52:59"}
{"current_steps": 280, "total_steps": 879, "loss": 0.4185, "lr": 4.3145177450431235e-05, "epoch": 0.9556313993174061, "percentage": 31.85, "elapsed_time": "6:50:17", "remaining_time": "14:37:44"}
{"current_steps": 290, "total_steps": 879, "loss": 0.417, "lr": 4.244802100710809e-05, "epoch": 0.9897610921501706, "percentage": 32.99, "elapsed_time": "7:04:07", "remaining_time": "14:21:23"}
{"current_steps": 300, "total_steps": 879, "loss": 0.3911, "lr": 4.172334535998958e-05, "epoch": 1.023890784982935, "percentage": 34.13, "elapsed_time": "7:18:27", "remaining_time": "14:06:13"}
{"current_steps": 310, "total_steps": 879, "loss": 0.3733, "lr": 4.0972293475192634e-05, "epoch": 1.0580204778156996, "percentage": 35.27, "elapsed_time": "7:34:13", "remaining_time": "13:53:43"}
{"current_steps": 320, "total_steps": 879, "loss": 0.3778, "lr": 4.0196049919716004e-05, "epoch": 1.0921501706484642, "percentage": 36.41, "elapsed_time": "7:47:31", "remaining_time": "13:36:41"}
{"current_steps": 330, "total_steps": 879, "loss": 0.3778, "lr": 3.9395838993128645e-05, "epoch": 1.1262798634812285, "percentage": 37.54, "elapsed_time": "8:01:04", "remaining_time": "13:20:19"}
{"current_steps": 340, "total_steps": 879, "loss": 0.3751, "lr": 3.8572922796591415e-05, "epoch": 1.1604095563139931, "percentage": 38.68, "elapsed_time": "8:14:48", "remaining_time": "13:04:25"}
{"current_steps": 350, "total_steps": 879, "loss": 0.3755, "lr": 3.7728599242257786e-05, "epoch": 1.1945392491467577, "percentage": 39.82, "elapsed_time": "8:28:49", "remaining_time": "12:49:03"}
{"current_steps": 360, "total_steps": 879, "loss": 0.38, "lr": 3.686420000619301e-05, "epoch": 1.2286689419795223, "percentage": 40.96, "elapsed_time": "8:44:34", "remaining_time": "12:36:15"}
{"current_steps": 370, "total_steps": 879, "loss": 0.3802, "lr": 3.5981088428040464e-05, "epoch": 1.2627986348122868, "percentage": 42.09, "elapsed_time": "8:58:54", "remaining_time": "12:21:22"}
{"current_steps": 380, "total_steps": 879, "loss": 0.3739, "lr": 3.5080657360747985e-05, "epoch": 1.2969283276450512, "percentage": 43.23, "elapsed_time": "9:13:27", "remaining_time": "12:06:46"}
{"current_steps": 390, "total_steps": 879, "loss": 0.3791, "lr": 3.416432697374533e-05, "epoch": 1.3310580204778157, "percentage": 44.37, "elapsed_time": "9:27:28", "remaining_time": "11:51:30"}
{"current_steps": 400, "total_steps": 879, "loss": 0.3778, "lr": 3.323354251303797e-05, "epoch": 1.36518771331058, "percentage": 45.51, "elapsed_time": "9:41:38", "remaining_time": "11:36:30"}
{"current_steps": 410, "total_steps": 879, "loss": 0.3773, "lr": 3.228977202174973e-05, "epoch": 1.3993174061433447, "percentage": 46.64, "elapsed_time": "9:57:43", "remaining_time": "11:23:43"}
{"current_steps": 420, "total_steps": 879, "loss": 0.3774, "lr": 3.1334504024709605e-05, "epoch": 1.4334470989761092, "percentage": 47.78, "elapsed_time": "10:11:41", "remaining_time": "11:08:29"}
{"current_steps": 430, "total_steps": 879, "loss": 0.3754, "lr": 3.0369245180734605e-05, "epoch": 1.4675767918088738, "percentage": 48.92, "elapsed_time": "10:25:50", "remaining_time": "10:53:29"}
{"current_steps": 440, "total_steps": 879, "loss": 0.3769, "lr": 2.9395517906311494e-05, "epoch": 1.5017064846416384, "percentage": 50.06, "elapsed_time": "10:40:53", "remaining_time": "10:39:26"}
{"current_steps": 450, "total_steps": 879, "loss": 0.3736, "lr": 2.841485797442535e-05, "epoch": 1.5358361774744027, "percentage": 51.19, "elapsed_time": "10:55:14", "remaining_time": "10:24:40"}
{"current_steps": 460, "total_steps": 879, "loss": 0.3749, "lr": 2.742881209232215e-05, "epoch": 1.5699658703071673, "percentage": 52.33, "elapsed_time": "11:10:20", "remaining_time": "10:10:35"}
{"current_steps": 470, "total_steps": 879, "loss": 0.3725, "lr": 2.6438935462025672e-05, "epoch": 1.6040955631399316, "percentage": 53.47, "elapsed_time": "11:25:01", "remaining_time": "9:56:07"}
{"current_steps": 480, "total_steps": 879, "loss": 0.3736, "lr": 2.5446789327456373e-05, "epoch": 1.6382252559726962, "percentage": 54.61, "elapsed_time": "11:39:36", "remaining_time": "9:41:33"}
{"current_steps": 490, "total_steps": 879, "loss": 0.3757, "lr": 2.4453938512020927e-05, "epoch": 1.6723549488054608, "percentage": 55.75, "elapsed_time": "11:54:15", "remaining_time": "9:27:02"}
{"current_steps": 500, "total_steps": 879, "loss": 0.3718, "lr": 2.3461948950556133e-05, "epoch": 1.7064846416382253, "percentage": 56.88, "elapsed_time": "12:07:46", "remaining_time": "9:11:38"}
{"current_steps": 510, "total_steps": 879, "loss": 0.3766, "lr": 2.247238521951992e-05, "epoch": 1.74061433447099, "percentage": 58.02, "elapsed_time": "12:23:07", "remaining_time": "8:57:40"}
{"current_steps": 520, "total_steps": 879, "loss": 0.375, "lr": 2.1486808069324687e-05, "epoch": 1.7747440273037542, "percentage": 59.16, "elapsed_time": "12:37:33", "remaining_time": "8:43:00"}
{"current_steps": 530, "total_steps": 879, "loss": 0.3733, "lr": 2.0506771962705304e-05, "epoch": 1.8088737201365188, "percentage": 60.3, "elapsed_time": "12:51:39", "remaining_time": "8:28:07"}
{"current_steps": 540, "total_steps": 879, "loss": 0.3716, "lr": 1.953382262300389e-05, "epoch": 1.8430034129692832, "percentage": 61.43, "elapsed_time": "13:06:09", "remaining_time": "8:13:32"}
{"current_steps": 550, "total_steps": 879, "loss": 0.3722, "lr": 1.8569494596238658e-05, "epoch": 1.8771331058020477, "percentage": 62.57, "elapsed_time": "13:20:42", "remaining_time": "7:58:58"}
{"current_steps": 560, "total_steps": 879, "loss": 0.372, "lr": 1.7615308830801576e-05, "epoch": 1.9112627986348123, "percentage": 63.71, "elapsed_time": "13:37:11", "remaining_time": "7:45:30"}
{"current_steps": 570, "total_steps": 879, "loss": 0.3728, "lr": 1.6672770278602508e-05, "epoch": 1.9453924914675769, "percentage": 64.85, "elapsed_time": "13:51:30", "remaining_time": "7:30:45"}
{"current_steps": 580, "total_steps": 879, "loss": 0.3729, "lr": 1.5743365521443033e-05, "epoch": 1.9795221843003414, "percentage": 65.98, "elapsed_time": "14:06:24", "remaining_time": "7:16:20"}
{"current_steps": 590, "total_steps": 879, "loss": 0.3545, "lr": 1.4828560426363918e-05, "epoch": 2.013651877133106, "percentage": 67.12, "elapsed_time": "14:21:21", "remaining_time": "7:01:55"}
{"current_steps": 600, "total_steps": 879, "loss": 0.3297, "lr": 1.3929797833664013e-05, "epoch": 2.04778156996587, "percentage": 68.26, "elapsed_time": "14:35:11", "remaining_time": "6:46:58"}
{"current_steps": 610, "total_steps": 879, "loss": 0.3297, "lr": 1.30484952812373e-05, "epoch": 2.0819112627986347, "percentage": 69.4, "elapsed_time": "14:51:25", "remaining_time": "6:33:06"}
{"current_steps": 620, "total_steps": 879, "loss": 0.3304, "lr": 1.2186042768816988e-05, "epoch": 2.1160409556313993, "percentage": 70.53, "elapsed_time": "15:06:01", "remaining_time": "6:18:29"}
{"current_steps": 630, "total_steps": 879, "loss": 0.3265, "lr": 1.1343800565653332e-05, "epoch": 2.150170648464164, "percentage": 71.67, "elapsed_time": "15:20:41", "remaining_time": "6:03:53"}
{"current_steps": 640, "total_steps": 879, "loss": 0.329, "lr": 1.0523097065082413e-05, "epoch": 2.1843003412969284, "percentage": 72.81, "elapsed_time": "15:35:13", "remaining_time": "5:49:14"}
{"current_steps": 650, "total_steps": 879, "loss": 0.3276, "lr": 9.725226689370154e-06, "epoch": 2.218430034129693, "percentage": 73.95, "elapsed_time": "15:50:08", "remaining_time": "5:34:44"}
{"current_steps": 660, "total_steps": 879, "loss": 0.3287, "lr": 8.951447848135758e-06, "epoch": 2.252559726962457, "percentage": 75.09, "elapsed_time": "16:05:25", "remaining_time": "5:20:20"}
{"current_steps": 670, "total_steps": 879, "loss": 0.3298, "lr": 8.202980953574735e-06, "epoch": 2.2866894197952217, "percentage": 76.22, "elapsed_time": "16:19:57", "remaining_time": "5:05:41"}
{"current_steps": 680, "total_steps": 879, "loss": 0.3283, "lr": 7.481006495611817e-06, "epoch": 2.3208191126279862, "percentage": 77.36, "elapsed_time": "16:34:48", "remaining_time": "4:51:07"}
{"current_steps": 690, "total_steps": 879, "loss": 0.3274, "lr": 6.786663180019751e-06, "epoch": 2.354948805460751, "percentage": 78.5, "elapsed_time": "16:48:35", "remaining_time": "4:36:16"}
{"current_steps": 700, "total_steps": 879, "loss": 0.3255, "lr": 6.121046132440458e-06, "epoch": 2.3890784982935154, "percentage": 79.64, "elapsed_time": "17:03:46", "remaining_time": "4:21:47"}
{"current_steps": 710, "total_steps": 879, "loss": 0.3262, "lr": 5.485205171141272e-06, "epoch": 2.42320819112628, "percentage": 80.77, "elapsed_time": "17:19:24", "remaining_time": "4:07:24"}
{"current_steps": 720, "total_steps": 879, "loss": 0.325, "lr": 4.880143151230418e-06, "epoch": 2.4573378839590445, "percentage": 81.91, "elapsed_time": "17:33:46", "remaining_time": "3:52:42"}
{"current_steps": 730, "total_steps": 879, "loss": 0.3255, "lr": 4.306814382943306e-06, "epoch": 2.491467576791809, "percentage": 83.05, "elapsed_time": "17:48:11", "remaining_time": "3:38:01"}
{"current_steps": 740, "total_steps": 879, "loss": 0.3283, "lr": 3.7661231264943086e-06, "epoch": 2.5255972696245736, "percentage": 84.19, "elapsed_time": "18:02:58", "remaining_time": "3:23:25"}
{"current_steps": 750, "total_steps": 879, "loss": 0.3238, "lr": 3.2589221658679586e-06, "epoch": 2.5597269624573378, "percentage": 85.32, "elapsed_time": "18:17:09", "remaining_time": "3:08:42"}
{"current_steps": 760, "total_steps": 879, "loss": 0.3268, "lr": 2.7860114637989933e-06, "epoch": 2.5938566552901023, "percentage": 86.46, "elapsed_time": "18:32:25", "remaining_time": "2:54:11"}
{"current_steps": 770, "total_steps": 879, "loss": 0.3322, "lr": 2.3481369000626585e-06, "epoch": 2.627986348122867, "percentage": 87.6, "elapsed_time": "18:46:54", "remaining_time": "2:39:31"}
{"current_steps": 780, "total_steps": 879, "loss": 0.3229, "lr": 1.9459890950652093e-06, "epoch": 2.6621160409556315, "percentage": 88.74, "elapsed_time": "19:00:32", "remaining_time": "2:24:45"}
{"current_steps": 790, "total_steps": 879, "loss": 0.3243, "lr": 1.5802023205900797e-06, "epoch": 2.696245733788396, "percentage": 89.87, "elapsed_time": "19:15:20", "remaining_time": "2:10:09"}
{"current_steps": 800, "total_steps": 879, "loss": 0.3282, "lr": 1.251353499417704e-06, "epoch": 2.73037542662116, "percentage": 91.01, "elapsed_time": "19:30:38", "remaining_time": "1:55:36"}
{"current_steps": 810, "total_steps": 879, "loss": 0.3237, "lr": 9.599612953967746e-07, "epoch": 2.7645051194539247, "percentage": 92.15, "elapsed_time": "19:45:29", "remaining_time": "1:40:59"}
{"current_steps": 820, "total_steps": 879, "loss": 0.3309, "lr": 7.064852954021373e-07, "epoch": 2.7986348122866893, "percentage": 93.29, "elapsed_time": "19:59:18", "remaining_time": "1:26:17"}
{"current_steps": 830, "total_steps": 879, "loss": 0.3249, "lr": 4.913252844694821e-07, "epoch": 2.832764505119454, "percentage": 94.43, "elapsed_time": "20:13:29", "remaining_time": "1:11:38"}
{"current_steps": 840, "total_steps": 879, "loss": 0.3248, "lr": 3.1482061525015537e-07, "epoch": 2.8668941979522184, "percentage": 95.56, "elapsed_time": "20:27:01", "remaining_time": "0:56:58"}
{"current_steps": 850, "total_steps": 879, "loss": 0.3216, "lr": 1.772496727805495e-07, "epoch": 2.901023890784983, "percentage": 96.7, "elapsed_time": "20:41:06", "remaining_time": "0:42:20"}
{"current_steps": 860, "total_steps": 879, "loss": 0.3255, "lr": 7.882943541027976e-08, "epoch": 2.9351535836177476, "percentage": 97.84, "elapsed_time": "20:57:00", "remaining_time": "0:27:46"}
{"current_steps": 870, "total_steps": 879, "loss": 0.3277, "lr": 1.9715132581624164e-08, "epoch": 2.969283276450512, "percentage": 98.98, "elapsed_time": "21:11:10", "remaining_time": "0:13:09"}
{"current_steps": 879, "total_steps": 879, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "21:24:45", "remaining_time": "0:00:00"}