KKHYA/qwen3-1.7b-fft-math
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: KKHYA/qwen3-1.7b-fft-math
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-16 05:05:17 +08:00
commit 634c2e8d57
15 changed files with 3954 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

94
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,94 @@
{"current_steps": 10, "total_steps": 938, "loss": 0.6841894149780273, "lr": 9.574468085106384e-07, "epoch": 0.021333333333333333, "percentage": 1.07, "elapsed_time": "0:00:43", "remaining_time": "1:07:39"}
{"current_steps": 20, "total_steps": 938, "loss": 0.6096980094909668, "lr": 2.021276595744681e-06, "epoch": 0.042666666666666665, "percentage": 2.13, "elapsed_time": "0:01:23", "remaining_time": "1:04:01"}
{"current_steps": 30, "total_steps": 938, "loss": 0.46523351669311525, "lr": 3.0851063829787237e-06, "epoch": 0.064, "percentage": 3.2, "elapsed_time": "0:02:03", "remaining_time": "1:02:05"}
{"current_steps": 40, "total_steps": 938, "loss": 0.38690838813781736, "lr": 4.148936170212766e-06, "epoch": 0.08533333333333333, "percentage": 4.26, "elapsed_time": "0:02:43", "remaining_time": "1:01:20"}
{"current_steps": 50, "total_steps": 938, "loss": 0.3463115692138672, "lr": 5.212765957446809e-06, "epoch": 0.10666666666666667, "percentage": 5.33, "elapsed_time": "0:03:26", "remaining_time": "1:01:14"}
{"current_steps": 60, "total_steps": 938, "loss": 0.3305189609527588, "lr": 6.276595744680851e-06, "epoch": 0.128, "percentage": 6.4, "elapsed_time": "0:04:07", "remaining_time": "1:00:18"}
{"current_steps": 70, "total_steps": 938, "loss": 0.33223772048950195, "lr": 7.340425531914894e-06, "epoch": 0.14933333333333335, "percentage": 7.46, "elapsed_time": "0:04:49", "remaining_time": "0:59:44"}
{"current_steps": 80, "total_steps": 938, "loss": 0.31659588813781736, "lr": 8.404255319148937e-06, "epoch": 0.17066666666666666, "percentage": 8.53, "elapsed_time": "0:05:31", "remaining_time": "0:59:11"}
{"current_steps": 90, "total_steps": 938, "loss": 0.31022181510925295, "lr": 9.46808510638298e-06, "epoch": 0.192, "percentage": 9.59, "elapsed_time": "0:06:11", "remaining_time": "0:58:21"}
{"current_steps": 100, "total_steps": 938, "loss": 0.3155974388122559, "lr": 9.999134070902206e-06, "epoch": 0.21333333333333335, "percentage": 10.66, "elapsed_time": "0:06:52", "remaining_time": "0:57:34"}
{"current_steps": 110, "total_steps": 938, "loss": 0.31209163665771483, "lr": 9.992208437615651e-06, "epoch": 0.23466666666666666, "percentage": 11.73, "elapsed_time": "0:07:33", "remaining_time": "0:56:57"}
{"current_steps": 120, "total_steps": 938, "loss": 0.30946059226989747, "lr": 9.97836676558346e-06, "epoch": 0.256, "percentage": 12.79, "elapsed_time": "0:08:14", "remaining_time": "0:56:12"}
{"current_steps": 130, "total_steps": 938, "loss": 0.3128779888153076, "lr": 9.957628230595527e-06, "epoch": 0.2773333333333333, "percentage": 13.86, "elapsed_time": "0:08:54", "remaining_time": "0:55:20"}
{"current_steps": 140, "total_steps": 938, "loss": 0.3062174320220947, "lr": 9.930021563125204e-06, "epoch": 0.2986666666666667, "percentage": 14.93, "elapsed_time": "0:09:35", "remaining_time": "0:54:39"}
{"current_steps": 150, "total_steps": 938, "loss": 0.30686254501342775, "lr": 9.895585008527075e-06, "epoch": 0.32, "percentage": 15.99, "elapsed_time": "0:10:15", "remaining_time": "0:53:53"}
{"current_steps": 160, "total_steps": 938, "loss": 0.3146007299423218, "lr": 9.854366274053125e-06, "epoch": 0.3413333333333333, "percentage": 17.06, "elapsed_time": "0:10:56", "remaining_time": "0:53:11"}
{"current_steps": 170, "total_steps": 938, "loss": 0.30956292152404785, "lr": 9.806422462760687e-06, "epoch": 0.3626666666666667, "percentage": 18.12, "elapsed_time": "0:11:36", "remaining_time": "0:52:27"}
{"current_steps": 180, "total_steps": 938, "loss": 0.30700514316558836, "lr": 9.751819994403802e-06, "epoch": 0.384, "percentage": 19.19, "elapsed_time": "0:12:19", "remaining_time": "0:51:54"}
{"current_steps": 190, "total_steps": 938, "loss": 0.31289896965026853, "lr": 9.690634513417487e-06, "epoch": 0.4053333333333333, "percentage": 20.26, "elapsed_time": "0:12:59", "remaining_time": "0:51:09"}
{"current_steps": 200, "total_steps": 938, "loss": 0.3092350959777832, "lr": 9.622950784122473e-06, "epoch": 0.4266666666666667, "percentage": 21.32, "elapsed_time": "0:13:40", "remaining_time": "0:50:26"}
{"current_steps": 210, "total_steps": 938, "loss": 0.3032077312469482, "lr": 9.548862573295552e-06, "epoch": 0.448, "percentage": 22.39, "elapsed_time": "0:14:22", "remaining_time": "0:49:50"}
{"current_steps": 220, "total_steps": 938, "loss": 0.30856895446777344, "lr": 9.468472520268207e-06, "epoch": 0.4693333333333333, "percentage": 23.45, "elapsed_time": "0:15:04", "remaining_time": "0:49:13"}
{"current_steps": 230, "total_steps": 938, "loss": 0.3001561641693115, "lr": 9.38189199473352e-06, "epoch": 0.49066666666666664, "percentage": 24.52, "elapsed_time": "0:15:45", "remaining_time": "0:48:31"}
{"current_steps": 240, "total_steps": 938, "loss": 0.2990098476409912, "lr": 9.289240942458322e-06, "epoch": 0.512, "percentage": 25.59, "elapsed_time": "0:16:25", "remaining_time": "0:47:45"}
{"current_steps": 250, "total_steps": 938, "loss": 0.2924530029296875, "lr": 9.190647719114328e-06, "epoch": 0.5333333333333333, "percentage": 26.65, "elapsed_time": "0:17:08", "remaining_time": "0:47:09"}
{"current_steps": 260, "total_steps": 938, "loss": 0.3162691116333008, "lr": 9.086248912458484e-06, "epoch": 0.5546666666666666, "percentage": 27.72, "elapsed_time": "0:17:48", "remaining_time": "0:46:25"}
{"current_steps": 270, "total_steps": 938, "loss": 0.30709133148193357, "lr": 8.976189153108853e-06, "epoch": 0.576, "percentage": 28.78, "elapsed_time": "0:18:28", "remaining_time": "0:45:42"}
{"current_steps": 280, "total_steps": 938, "loss": 0.3032949924468994, "lr": 8.860620914178188e-06, "epoch": 0.5973333333333334, "percentage": 29.85, "elapsed_time": "0:19:08", "remaining_time": "0:44:59"}
{"current_steps": 290, "total_steps": 938, "loss": 0.29636149406433104, "lr": 8.73970430004278e-06, "epoch": 0.6186666666666667, "percentage": 30.92, "elapsed_time": "0:19:49", "remaining_time": "0:44:18"}
{"current_steps": 300, "total_steps": 938, "loss": 0.3070181369781494, "lr": 8.613606824539198e-06, "epoch": 0.64, "percentage": 31.98, "elapsed_time": "0:20:32", "remaining_time": "0:43:41"}
{"current_steps": 310, "total_steps": 938, "loss": 0.3074164867401123, "lr": 8.482503178896227e-06, "epoch": 0.6613333333333333, "percentage": 33.05, "elapsed_time": "0:21:12", "remaining_time": "0:42:57"}
{"current_steps": 320, "total_steps": 938, "loss": 0.2806987762451172, "lr": 8.34657498972347e-06, "epoch": 0.6826666666666666, "percentage": 34.12, "elapsed_time": "0:21:55", "remaining_time": "0:42:20"}
{"current_steps": 330, "total_steps": 938, "loss": 0.28669133186340334, "lr": 8.206010567391918e-06, "epoch": 0.704, "percentage": 35.18, "elapsed_time": "0:22:37", "remaining_time": "0:41:41"}
{"current_steps": 340, "total_steps": 938, "loss": 0.30783905982971194, "lr": 8.061004645155049e-06, "epoch": 0.7253333333333334, "percentage": 36.25, "elapsed_time": "0:23:23", "remaining_time": "0:41:08"}
{"current_steps": 350, "total_steps": 938, "loss": 0.29372529983520507, "lr": 7.91175810937189e-06, "epoch": 0.7466666666666667, "percentage": 37.31, "elapsed_time": "0:24:06", "remaining_time": "0:40:30"}
{"current_steps": 360, "total_steps": 938, "loss": 0.2857055187225342, "lr": 7.758477721205767e-06, "epoch": 0.768, "percentage": 38.38, "elapsed_time": "0:24:50", "remaining_time": "0:39:52"}
{"current_steps": 370, "total_steps": 938, "loss": 0.2911552429199219, "lr": 7.601375830184297e-06, "epoch": 0.7893333333333333, "percentage": 39.45, "elapsed_time": "0:25:32", "remaining_time": "0:39:12"}
{"current_steps": 380, "total_steps": 938, "loss": 0.28858585357666017, "lr": 7.4406700800174545e-06, "epoch": 0.8106666666666666, "percentage": 40.51, "elapsed_time": "0:26:18", "remaining_time": "0:38:37"}
{"current_steps": 390, "total_steps": 938, "loss": 0.2948747158050537, "lr": 7.276583107081243e-06, "epoch": 0.832, "percentage": 41.58, "elapsed_time": "0:26:59", "remaining_time": "0:37:56"}
{"current_steps": 400, "total_steps": 938, "loss": 0.28877460956573486, "lr": 7.109342231984698e-06, "epoch": 0.8533333333333334, "percentage": 42.64, "elapsed_time": "0:27:43", "remaining_time": "0:37:16"}
{"current_steps": 410, "total_steps": 938, "loss": 0.3021462202072144, "lr": 6.939179144647516e-06, "epoch": 0.8746666666666667, "percentage": 43.71, "elapsed_time": "0:28:23", "remaining_time": "0:36:34"}
{"current_steps": 420, "total_steps": 938, "loss": 0.2928939342498779, "lr": 6.766329583324582e-06, "epoch": 0.896, "percentage": 44.78, "elapsed_time": "0:29:06", "remaining_time": "0:35:53"}
{"current_steps": 430, "total_steps": 938, "loss": 0.28879172801971437, "lr": 6.591033008022067e-06, "epoch": 0.9173333333333333, "percentage": 45.84, "elapsed_time": "0:29:46", "remaining_time": "0:35:10"}
{"current_steps": 440, "total_steps": 938, "loss": 0.2961143493652344, "lr": 6.413532268757537e-06, "epoch": 0.9386666666666666, "percentage": 46.91, "elapsed_time": "0:30:28", "remaining_time": "0:34:29"}
{"current_steps": 450, "total_steps": 938, "loss": 0.2954572200775146, "lr": 6.234073269123654e-06, "epoch": 0.96, "percentage": 47.97, "elapsed_time": "0:31:09", "remaining_time": "0:33:47"}
{"current_steps": 460, "total_steps": 938, "loss": 0.2948294162750244, "lr": 6.052904625621556e-06, "epoch": 0.9813333333333333, "percentage": 49.04, "elapsed_time": "0:31:54", "remaining_time": "0:33:09"}
{"current_steps": 470, "total_steps": 938, "loss": 0.2971747875213623, "lr": 5.870277323235871e-06, "epoch": 1.0021333333333333, "percentage": 50.11, "elapsed_time": "0:32:34", "remaining_time": "0:32:26"}
{"current_steps": 480, "total_steps": 938, "loss": 0.26477513313293455, "lr": 5.686444367728494e-06, "epoch": 1.0234666666666667, "percentage": 51.17, "elapsed_time": "0:33:15", "remaining_time": "0:31:44"}
{"current_steps": 490, "total_steps": 938, "loss": 0.2709561824798584, "lr": 5.501660435132871e-06, "epoch": 1.0448, "percentage": 52.24, "elapsed_time": "0:33:57", "remaining_time": "0:31:02"}
{"current_steps": 500, "total_steps": 938, "loss": 0.27056255340576174, "lr": 5.316181518934319e-06, "epoch": 1.0661333333333334, "percentage": 53.3, "elapsed_time": "0:34:38", "remaining_time": "0:30:20"}
{"current_steps": 510, "total_steps": 938, "loss": 0.27835679054260254, "lr": 5.130264575425225e-06, "epoch": 1.0874666666666666, "percentage": 54.37, "elapsed_time": "0:35:30", "remaining_time": "0:29:48"}
{"current_steps": 520, "total_steps": 938, "loss": 0.26178646087646484, "lr": 4.944167167726367e-06, "epoch": 1.1088, "percentage": 55.44, "elapsed_time": "0:36:13", "remaining_time": "0:29:07"}
{"current_steps": 530, "total_steps": 938, "loss": 0.2711505889892578, "lr": 4.758147108967585e-06, "epoch": 1.1301333333333332, "percentage": 56.5, "elapsed_time": "0:36:54", "remaining_time": "0:28:24"}
{"current_steps": 540, "total_steps": 938, "loss": 0.262709903717041, "lr": 4.572462105122078e-06, "epoch": 1.1514666666666666, "percentage": 57.57, "elapsed_time": "0:37:37", "remaining_time": "0:27:43"}
{"current_steps": 550, "total_steps": 938, "loss": 0.2738328218460083, "lr": 4.3873693979891705e-06, "epoch": 1.1728, "percentage": 58.64, "elapsed_time": "0:38:18", "remaining_time": "0:27:01"}
{"current_steps": 560, "total_steps": 938, "loss": 0.26540517807006836, "lr": 4.203125408820106e-06, "epoch": 1.1941333333333333, "percentage": 59.7, "elapsed_time": "0:38:58", "remaining_time": "0:26:18"}
{"current_steps": 570, "total_steps": 938, "loss": 0.26726350784301756, "lr": 4.019985383080632e-06, "epoch": 1.2154666666666667, "percentage": 60.77, "elapsed_time": "0:39:40", "remaining_time": "0:25:37"}
{"current_steps": 580, "total_steps": 938, "loss": 0.2629551887512207, "lr": 3.838203036842446e-06, "epoch": 1.2368000000000001, "percentage": 61.83, "elapsed_time": "0:40:20", "remaining_time": "0:24:53"}
{"current_steps": 590, "total_steps": 938, "loss": 0.2717682600021362, "lr": 3.65803020529343e-06, "epoch": 1.2581333333333333, "percentage": 62.9, "elapsed_time": "0:41:04", "remaining_time": "0:24:13"}
{"current_steps": 600, "total_steps": 938, "loss": 0.2709221601486206, "lr": 3.4797164938536113e-06, "epoch": 1.2794666666666665, "percentage": 63.97, "elapsed_time": "0:41:46", "remaining_time": "0:23:32"}
{"current_steps": 610, "total_steps": 938, "loss": 0.26828670501708984, "lr": 3.3035089323801323e-06, "epoch": 1.3008, "percentage": 65.03, "elapsed_time": "0:42:29", "remaining_time": "0:22:50"}
{"current_steps": 620, "total_steps": 938, "loss": 0.27147223949432375, "lr": 3.1296516329403626e-06, "epoch": 1.3221333333333334, "percentage": 66.1, "elapsed_time": "0:43:10", "remaining_time": "0:22:08"}
{"current_steps": 630, "total_steps": 938, "loss": 0.272589111328125, "lr": 2.9583854516271815e-06, "epoch": 1.3434666666666666, "percentage": 67.16, "elapsed_time": "0:43:51", "remaining_time": "0:21:26"}
{"current_steps": 640, "total_steps": 938, "loss": 0.2664657115936279, "lr": 2.7899476548850046e-06, "epoch": 1.3648, "percentage": 68.23, "elapsed_time": "0:44:32", "remaining_time": "0:20:44"}
{"current_steps": 650, "total_steps": 938, "loss": 0.2647489786148071, "lr": 2.624571590808781e-06, "epoch": 1.3861333333333334, "percentage": 69.3, "elapsed_time": "0:45:12", "remaining_time": "0:20:01"}
{"current_steps": 660, "total_steps": 938, "loss": 0.2691283941268921, "lr": 2.4624863658713383e-06, "epoch": 1.4074666666666666, "percentage": 70.36, "elapsed_time": "0:45:53", "remaining_time": "0:19:19"}
{"current_steps": 670, "total_steps": 938, "loss": 0.2635840892791748, "lr": 2.3039165275269214e-06, "epoch": 1.4288, "percentage": 71.43, "elapsed_time": "0:46:34", "remaining_time": "0:18:37"}
{"current_steps": 680, "total_steps": 938, "loss": 0.2607363224029541, "lr": 2.1490817531306778e-06, "epoch": 1.4501333333333333, "percentage": 72.49, "elapsed_time": "0:47:15", "remaining_time": "0:17:55"}
{"current_steps": 690, "total_steps": 938, "loss": 0.27231812477111816, "lr": 1.99819654560496e-06, "epoch": 1.4714666666666667, "percentage": 73.56, "elapsed_time": "0:47:54", "remaining_time": "0:17:13"}
{"current_steps": 700, "total_steps": 938, "loss": 0.2777836561203003, "lr": 1.851469936274174e-06, "epoch": 1.4928, "percentage": 74.63, "elapsed_time": "0:48:35", "remaining_time": "0:16:31"}
{"current_steps": 710, "total_steps": 938, "loss": 0.2632488965988159, "lr": 1.7091051952797404e-06, "epoch": 1.5141333333333333, "percentage": 75.69, "elapsed_time": "0:49:18", "remaining_time": "0:15:50"}
{"current_steps": 720, "total_steps": 938, "loss": 0.2699136257171631, "lr": 1.571299549976456e-06, "epoch": 1.5354666666666668, "percentage": 76.76, "elapsed_time": "0:49:58", "remaining_time": "0:15:07"}
{"current_steps": 730, "total_steps": 938, "loss": 0.25556948184967043, "lr": 1.4382439117002938e-06, "epoch": 1.5568, "percentage": 77.83, "elapsed_time": "0:50:41", "remaining_time": "0:14:26"}
{"current_steps": 740, "total_steps": 938, "loss": 0.26279048919677733, "lr": 1.3101226112862232e-06, "epoch": 1.5781333333333334, "percentage": 78.89, "elapsed_time": "0:51:22", "remaining_time": "0:13:44"}
{"current_steps": 750, "total_steps": 938, "loss": 0.2726590633392334, "lr": 1.1871131437024291e-06, "epoch": 1.5994666666666668, "percentage": 79.96, "elapsed_time": "0:52:02", "remaining_time": "0:13:02"}
{"current_steps": 760, "total_steps": 938, "loss": 0.2752861499786377, "lr": 1.0693859221547115e-06, "epoch": 1.6208, "percentage": 81.02, "elapsed_time": "0:52:45", "remaining_time": "0:12:21"}
{"current_steps": 770, "total_steps": 938, "loss": 0.2579826354980469, "lr": 9.571040420017324e-07, "epoch": 1.6421333333333332, "percentage": 82.09, "elapsed_time": "0:53:28", "remaining_time": "0:11:39"}
{"current_steps": 780, "total_steps": 938, "loss": 0.26852080821990965, "lr": 8.504230548081499e-07, "epoch": 1.6634666666666666, "percentage": 83.16, "elapsed_time": "0:54:10", "remaining_time": "0:10:58"}
{"current_steps": 790, "total_steps": 938, "loss": 0.26603677272796633, "lr": 7.4949075284868e-07, "epoch": 1.6848, "percentage": 84.22, "elapsed_time": "0:54:52", "remaining_time": "0:10:16"}
{"current_steps": 800, "total_steps": 938, "loss": 0.25719456672668456, "lr": 6.544469643616192e-07, "epoch": 1.7061333333333333, "percentage": 85.29, "elapsed_time": "0:55:34", "remaining_time": "0:09:35"}
{"current_steps": 810, "total_steps": 938, "loss": 0.2663470506668091, "lr": 5.654233598354752e-07, "epoch": 1.7274666666666667, "percentage": 86.35, "elapsed_time": "0:56:15", "remaining_time": "0:08:53"}
{"current_steps": 820, "total_steps": 938, "loss": 0.26163082122802733, "lr": 4.825432695970673e-07, "epoch": 1.7488000000000001, "percentage": 87.42, "elapsed_time": "0:57:00", "remaining_time": "0:08:12"}
{"current_steps": 830, "total_steps": 938, "loss": 0.26932682991027834, "lr": 4.0592151295382464e-07, "epoch": 1.7701333333333333, "percentage": 88.49, "elapsed_time": "0:57:40", "remaining_time": "0:07:30"}
{"current_steps": 840, "total_steps": 938, "loss": 0.27272663116455076, "lr": 3.356642391269405e-07, "epoch": 1.7914666666666665, "percentage": 89.55, "elapsed_time": "0:58:21", "remaining_time": "0:06:48"}
{"current_steps": 850, "total_steps": 938, "loss": 0.2759810447692871, "lr": 2.7186878019580197e-07, "epoch": 1.8128, "percentage": 90.62, "elapsed_time": "0:59:02", "remaining_time": "0:06:06"}
{"current_steps": 860, "total_steps": 938, "loss": 0.2736822128295898, "lr": 2.1462351625736677e-07, "epoch": 1.8341333333333334, "percentage": 91.68, "elapsed_time": "0:59:43", "remaining_time": "0:05:24"}
{"current_steps": 870, "total_steps": 938, "loss": 0.2506378173828125, "lr": 1.6400775298734017e-07, "epoch": 1.8554666666666666, "percentage": 92.75, "elapsed_time": "1:00:28", "remaining_time": "0:04:43"}
{"current_steps": 880, "total_steps": 938, "loss": 0.2735074520111084, "lr": 1.2009161177273742e-07, "epoch": 1.8768, "percentage": 93.82, "elapsed_time": "1:01:08", "remaining_time": "0:04:01"}
{"current_steps": 890, "total_steps": 938, "loss": 0.26666769981384275, "lr": 8.293593256805842e-08, "epoch": 1.8981333333333335, "percentage": 94.88, "elapsed_time": "1:01:49", "remaining_time": "0:03:20"}
{"current_steps": 900, "total_steps": 938, "loss": 0.2759205102920532, "lr": 5.259218960964874e-08, "epoch": 1.9194666666666667, "percentage": 95.95, "elapsed_time": "1:02:31", "remaining_time": "0:02:38"}
{"current_steps": 910, "total_steps": 938, "loss": 0.27174739837646483, "lr": 2.9102420105009966e-08, "epoch": 1.9407999999999999, "percentage": 97.01, "elapsed_time": "1:03:12", "remaining_time": "0:01:56"}
{"current_steps": 920, "total_steps": 938, "loss": 0.26730976104736326, "lr": 1.249916599585954e-08, "epoch": 1.9621333333333333, "percentage": 98.08, "elapsed_time": "1:03:50", "remaining_time": "0:01:14"}
{"current_steps": 930, "total_steps": 938, "loss": 0.2772205352783203, "lr": 2.80542887561297e-09, "epoch": 1.9834666666666667, "percentage": 99.15, "elapsed_time": "1:04:31", "remaining_time": "0:00:33"}
{"current_steps": 938, "total_steps": 938, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "1:05:13", "remaining_time": "0:00:00"}