初始化项目,由ModelHub XC社区提供模型

Model: shubhamrgandhi/qwen3-4b-instruct-2507-full-sft-prm-r2egym-swebench-instructions-k5-qwen-only
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-29 07:44:13 +08:00
commit 6d79867f72
14 changed files with 919 additions and 0 deletions

77
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,77 @@
{"current_steps": 10, "total_steps": 720, "loss": 1.3478851318359375, "lr": 6.25e-07, "epoch": 0.041666666666666664, "percentage": 1.39, "elapsed_time": "0:06:44", "remaining_time": "7:58:59"}
{"current_steps": 20, "total_steps": 720, "loss": 1.1414000511169433, "lr": 1.3194444444444446e-06, "epoch": 0.08333333333333333, "percentage": 2.78, "elapsed_time": "0:14:36", "remaining_time": "8:31:10"}
{"current_steps": 30, "total_steps": 720, "loss": 0.8360883712768554, "lr": 2.0138888888888893e-06, "epoch": 0.125, "percentage": 4.17, "elapsed_time": "0:22:48", "remaining_time": "8:44:34"}
{"current_steps": 40, "total_steps": 720, "loss": 0.7460173606872559, "lr": 2.7083333333333334e-06, "epoch": 0.16666666666666666, "percentage": 5.56, "elapsed_time": "0:29:47", "remaining_time": "8:26:29"}
{"current_steps": 50, "total_steps": 720, "loss": 0.7003425598144531, "lr": 3.4027777777777783e-06, "epoch": 0.20833333333333334, "percentage": 6.94, "elapsed_time": "0:37:14", "remaining_time": "8:19:02"}
{"current_steps": 60, "total_steps": 720, "loss": 0.6781439304351806, "lr": 4.097222222222222e-06, "epoch": 0.25, "percentage": 8.33, "elapsed_time": "0:44:22", "remaining_time": "8:08:07"}
{"current_steps": 70, "total_steps": 720, "loss": 0.6273435592651367, "lr": 4.791666666666668e-06, "epoch": 0.2916666666666667, "percentage": 9.72, "elapsed_time": "0:51:44", "remaining_time": "8:00:29"}
{"current_steps": 80, "total_steps": 720, "loss": 0.6232743263244629, "lr": 4.998560491796288e-06, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "0:59:17", "remaining_time": "7:54:21"}
{"current_steps": 90, "total_steps": 720, "loss": 0.5979775428771973, "lr": 4.991513829823945e-06, "epoch": 0.375, "percentage": 12.5, "elapsed_time": "1:07:01", "remaining_time": "7:49:07"}
{"current_steps": 100, "total_steps": 720, "loss": 0.5922712326049805, "lr": 4.978612153434527e-06, "epoch": 0.4166666666666667, "percentage": 13.89, "elapsed_time": "1:13:20", "remaining_time": "7:34:40"}
{"current_steps": 110, "total_steps": 720, "loss": 0.602515983581543, "lr": 4.9598857813444524e-06, "epoch": 0.4583333333333333, "percentage": 15.28, "elapsed_time": "1:20:50", "remaining_time": "7:28:17"}
{"current_steps": 120, "total_steps": 720, "loss": 0.5727059364318847, "lr": 4.935378720204319e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "1:28:22", "remaining_time": "7:21:52"}
{"current_steps": 130, "total_steps": 720, "loss": 0.5602549552917481, "lr": 4.905148561184033e-06, "epoch": 0.5416666666666666, "percentage": 18.06, "elapsed_time": "1:36:28", "remaining_time": "7:17:48"}
{"current_steps": 140, "total_steps": 720, "loss": 0.5857479095458984, "lr": 4.869266344634556e-06, "epoch": 0.5833333333333334, "percentage": 19.44, "elapsed_time": "1:43:54", "remaining_time": "7:10:29"}
{"current_steps": 150, "total_steps": 720, "loss": 0.5755341529846192, "lr": 4.827816393144305e-06, "epoch": 0.625, "percentage": 20.83, "elapsed_time": "1:51:14", "remaining_time": "7:02:44"}
{"current_steps": 160, "total_steps": 720, "loss": 0.5534672737121582, "lr": 4.780896113382536e-06, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "1:58:59", "remaining_time": "6:56:29"}
{"current_steps": 170, "total_steps": 720, "loss": 0.553608751296997, "lr": 4.728615767195347e-06, "epoch": 0.7083333333333334, "percentage": 23.61, "elapsed_time": "2:06:32", "remaining_time": "6:49:25"}
{"current_steps": 180, "total_steps": 720, "loss": 0.5626870155334472, "lr": 4.671098212492251e-06, "epoch": 0.75, "percentage": 25.0, "elapsed_time": "2:14:28", "remaining_time": "6:43:24"}
{"current_steps": 190, "total_steps": 720, "loss": 0.5459296226501464, "lr": 4.608478614532215e-06, "epoch": 0.7916666666666666, "percentage": 26.39, "elapsed_time": "2:22:07", "remaining_time": "6:36:25"}
{"current_steps": 200, "total_steps": 720, "loss": 0.5788500785827637, "lr": 4.54090412828763e-06, "epoch": 0.8333333333333334, "percentage": 27.78, "elapsed_time": "2:29:27", "remaining_time": "6:28:35"}
{"current_steps": 210, "total_steps": 720, "loss": 0.5325177192687989, "lr": 4.468533552632681e-06, "epoch": 0.875, "percentage": 29.17, "elapsed_time": "2:39:25", "remaining_time": "6:27:09"}
{"current_steps": 220, "total_steps": 720, "loss": 0.5544806003570557, "lr": 4.391536957168733e-06, "epoch": 0.9166666666666666, "percentage": 30.56, "elapsed_time": "2:47:28", "remaining_time": "6:20:36"}
{"current_steps": 230, "total_steps": 720, "loss": 0.5456794261932373, "lr": 4.3100952825637064e-06, "epoch": 0.9583333333333334, "percentage": 31.94, "elapsed_time": "2:55:36", "remaining_time": "6:14:06"}
{"current_steps": 240, "total_steps": 720, "loss": 0.5358950138092041, "lr": 4.2243999153446445e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "3:03:01", "remaining_time": "6:06:02"}
{"current_steps": 210, "total_steps": 720, "loss": 0.5325778007507325, "lr": 4.468533552632681e-06, "epoch": 0.875, "percentage": 29.17, "elapsed_time": "0:08:16", "remaining_time": "0:20:06"}
{"current_steps": 220, "total_steps": 720, "loss": 0.5544434547424316, "lr": 4.391536957168733e-06, "epoch": 0.9166666666666666, "percentage": 30.56, "elapsed_time": "0:16:19", "remaining_time": "0:37:07"}
{"current_steps": 230, "total_steps": 720, "loss": 0.5456916332244873, "lr": 4.3100952825637064e-06, "epoch": 0.9583333333333334, "percentage": 31.94, "elapsed_time": "0:24:28", "remaining_time": "0:52:08"}
{"current_steps": 240, "total_steps": 720, "loss": 0.535283899307251, "lr": 4.2243999153446445e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:31:53", "remaining_time": "1:03:46"}
{"current_steps": 250, "total_steps": 720, "loss": 0.4393170356750488, "lr": 4.134652238142674e-06, "epoch": 1.0416666666666667, "percentage": 34.72, "elapsed_time": "0:39:59", "remaining_time": "1:15:11"}
{"current_steps": 260, "total_steps": 720, "loss": 0.4061892032623291, "lr": 4.041063156447314e-06, "epoch": 1.0833333333333333, "percentage": 36.11, "elapsed_time": "0:47:07", "remaining_time": "1:23:22"}
{"current_steps": 270, "total_steps": 720, "loss": 0.413454532623291, "lr": 3.943852602982213e-06, "epoch": 1.125, "percentage": 37.5, "elapsed_time": "0:55:06", "remaining_time": "1:31:50"}
{"current_steps": 280, "total_steps": 720, "loss": 0.41506023406982423, "lr": 3.8432490208670605e-06, "epoch": 1.1666666666666667, "percentage": 38.89, "elapsed_time": "1:02:31", "remaining_time": "1:38:15"}
{"current_steps": 290, "total_steps": 720, "loss": 0.3757039785385132, "lr": 3.739488826780199e-06, "epoch": 1.2083333333333333, "percentage": 40.28, "elapsed_time": "1:10:27", "remaining_time": "1:44:29"}
{"current_steps": 300, "total_steps": 720, "loss": 0.38776512145996095, "lr": 3.6328158553835206e-06, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "1:17:30", "remaining_time": "1:48:31"}
{"current_steps": 310, "total_steps": 720, "loss": 0.3929452896118164, "lr": 3.5234807863152316e-06, "epoch": 1.2916666666666667, "percentage": 43.06, "elapsed_time": "1:25:43", "remaining_time": "1:53:23"}
{"current_steps": 320, "total_steps": 720, "loss": 0.41544904708862307, "lr": 3.41174055509703e-06, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "1:33:38", "remaining_time": "1:57:03"}
{"current_steps": 330, "total_steps": 720, "loss": 0.4201189517974854, "lr": 3.2978577493400775e-06, "epoch": 1.375, "percentage": 45.83, "elapsed_time": "1:41:33", "remaining_time": "2:00:01"}
{"current_steps": 340, "total_steps": 720, "loss": 0.3872462272644043, "lr": 3.182099991668653e-06, "epoch": 1.4166666666666667, "percentage": 47.22, "elapsed_time": "1:48:51", "remaining_time": "2:01:40"}
{"current_steps": 350, "total_steps": 720, "loss": 0.3856550931930542, "lr": 3.064739310811612e-06, "epoch": 1.4583333333333333, "percentage": 48.61, "elapsed_time": "1:56:03", "remaining_time": "2:02:41"}
{"current_steps": 360, "total_steps": 720, "loss": 0.4167680263519287, "lr": 2.9460515023395807e-06, "epoch": 1.5, "percentage": 50.0, "elapsed_time": "2:04:12", "remaining_time": "2:04:12"}
{"current_steps": 370, "total_steps": 720, "loss": 0.40921745300292967, "lr": 2.82631548055013e-06, "epoch": 1.5416666666666665, "percentage": 51.39, "elapsed_time": "2:10:18", "remaining_time": "2:03:15"}
{"current_steps": 380, "total_steps": 720, "loss": 0.39605083465576174, "lr": 2.705812623024e-06, "epoch": 1.5833333333333335, "percentage": 52.78, "elapsed_time": "2:17:49", "remaining_time": "2:03:18"}
{"current_steps": 390, "total_steps": 720, "loss": 0.4075204372406006, "lr": 2.5848261093926565e-06, "epoch": 1.625, "percentage": 54.17, "elapsed_time": "2:25:45", "remaining_time": "2:03:19"}
{"current_steps": 400, "total_steps": 720, "loss": 0.40534563064575196, "lr": 2.4636402558710434e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "2:33:40", "remaining_time": "2:02:56"}
{"current_steps": 410, "total_steps": 720, "loss": 0.39900033473968505, "lr": 2.3425398471194056e-06, "epoch": 1.7083333333333335, "percentage": 56.94, "elapsed_time": "2:44:10", "remaining_time": "2:04:08"}
{"current_steps": 420, "total_steps": 720, "loss": 0.40346851348876955, "lr": 2.221809467004251e-06, "epoch": 1.75, "percentage": 58.33, "elapsed_time": "2:51:16", "remaining_time": "2:02:20"}
{"current_steps": 430, "total_steps": 720, "loss": 0.4041299819946289, "lr": 2.101732829831194e-06, "epoch": 1.7916666666666665, "percentage": 59.72, "elapsed_time": "2:58:58", "remaining_time": "2:00:41"}
{"current_steps": 440, "total_steps": 720, "loss": 0.3829362392425537, "lr": 1.9825921136212372e-06, "epoch": 1.8333333333333335, "percentage": 61.11, "elapsed_time": "3:07:14", "remaining_time": "1:59:09"}
{"current_steps": 450, "total_steps": 720, "loss": 0.41110787391662595, "lr": 1.8646672969973034e-06, "epoch": 1.875, "percentage": 62.5, "elapsed_time": "3:15:22", "remaining_time": "1:57:13"}
{"current_steps": 460, "total_steps": 720, "loss": 0.376175594329834, "lr": 1.7482355012393177e-06, "epoch": 1.9166666666666665, "percentage": 63.89, "elapsed_time": "3:22:44", "remaining_time": "1:54:35"}
{"current_steps": 470, "total_steps": 720, "loss": 0.3938215017318726, "lr": 1.633570339053982e-06, "epoch": 1.9583333333333335, "percentage": 65.28, "elapsed_time": "3:30:17", "remaining_time": "1:51:51"}
{"current_steps": 480, "total_steps": 720, "loss": 0.41222400665283204, "lr": 1.5209412715896527e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "3:38:21", "remaining_time": "1:49:10"}
{"current_steps": 490, "total_steps": 720, "loss": 0.2820391893386841, "lr": 1.4106129752073023e-06, "epoch": 2.0416666666666665, "percentage": 68.06, "elapsed_time": "3:44:41", "remaining_time": "1:45:27"}
{"current_steps": 500, "total_steps": 720, "loss": 0.2755776882171631, "lr": 1.3028447194956413e-06, "epoch": 2.0833333333333335, "percentage": 69.44, "elapsed_time": "3:51:56", "remaining_time": "1:42:03"}
{"current_steps": 510, "total_steps": 720, "loss": 0.26791958808898925, "lr": 1.197889757992076e-06, "epoch": 2.125, "percentage": 70.83, "elapsed_time": "3:59:26", "remaining_time": "1:38:35"}
{"current_steps": 520, "total_steps": 720, "loss": 0.27331366539001467, "lr": 1.0959947330412681e-06, "epoch": 2.1666666666666665, "percentage": 72.22, "elapsed_time": "4:07:09", "remaining_time": "1:35:03"}
{"current_steps": 530, "total_steps": 720, "loss": 0.27553110122680663, "lr": 9.973990961898928e-07, "epoch": 2.2083333333333335, "percentage": 73.61, "elapsed_time": "4:15:22", "remaining_time": "1:31:32"}
{"current_steps": 540, "total_steps": 720, "loss": 0.2681769132614136, "lr": 9.023345454796459e-07, "epoch": 2.25, "percentage": 75.0, "elapsed_time": "4:22:50", "remaining_time": "1:27:36"}
{"current_steps": 550, "total_steps": 720, "loss": 0.25668916702270506, "lr": 8.110244809608494e-07, "epoch": 2.2916666666666665, "percentage": 76.39, "elapsed_time": "4:30:01", "remaining_time": "1:23:27"}
{"current_steps": 560, "total_steps": 720, "loss": 0.27220232486724855, "lr": 7.236834797061979e-07, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "4:37:28", "remaining_time": "1:19:16"}
{"current_steps": 570, "total_steps": 720, "loss": 0.28708949089050295, "lr": 6.405167915583477e-07, "epoch": 2.375, "percentage": 79.17, "elapsed_time": "4:45:13", "remaining_time": "1:15:03"}
{"current_steps": 580, "total_steps": 720, "loss": 0.2636965274810791, "lr": 5.617198567963353e-07, "epoch": 2.4166666666666665, "percentage": 80.56, "elapsed_time": "4:52:33", "remaining_time": "1:10:37"}
{"current_steps": 590, "total_steps": 720, "loss": 0.2697884559631348, "lr": 4.874778468543043e-07, "epoch": 2.4583333333333335, "percentage": 81.94, "elapsed_time": "5:00:38", "remaining_time": "1:06:14"}
{"current_steps": 600, "total_steps": 720, "loss": 0.2729990005493164, "lr": 4.1796522917183226e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "5:08:34", "remaining_time": "1:01:42"}
{"current_steps": 610, "total_steps": 720, "loss": 0.2704613208770752, "lr": 3.5334535719846767e-07, "epoch": 2.5416666666666665, "percentage": 84.72, "elapsed_time": "5:19:12", "remaining_time": "0:57:33"}
{"current_steps": 620, "total_steps": 720, "loss": 0.26971731185913084, "lr": 2.9377008651594737e-07, "epoch": 2.5833333333333335, "percentage": 86.11, "elapsed_time": "5:26:26", "remaining_time": "0:52:39"}
{"current_steps": 630, "total_steps": 720, "loss": 0.266050910949707, "lr": 2.393794179802053e-07, "epoch": 2.625, "percentage": 87.5, "elapsed_time": "5:33:27", "remaining_time": "0:47:38"}
{"current_steps": 640, "total_steps": 720, "loss": 0.27685208320617677, "lr": 1.9030116872178317e-07, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "5:40:03", "remaining_time": "0:42:30"}
{"current_steps": 650, "total_steps": 720, "loss": 0.2522747993469238, "lr": 1.4665067177778187e-07, "epoch": 2.7083333333333335, "percentage": 90.28, "elapsed_time": "5:47:50", "remaining_time": "0:37:27"}
{"current_steps": 660, "total_steps": 720, "loss": 0.25966610908508303, "lr": 1.0853050506121927e-07, "epoch": 2.75, "percentage": 91.67, "elapsed_time": "5:55:01", "remaining_time": "0:32:16"}
{"current_steps": 670, "total_steps": 720, "loss": 0.27193603515625, "lr": 7.603025030471001e-08, "epoch": 2.7916666666666665, "percentage": 93.06, "elapsed_time": "6:02:51", "remaining_time": "0:27:04"}
{"current_steps": 680, "total_steps": 720, "loss": 0.27923831939697263, "lr": 4.922628254493994e-08, "epoch": 2.8333333333333335, "percentage": 94.44, "elapsed_time": "6:10:16", "remaining_time": "0:21:46"}
{"current_steps": 690, "total_steps": 720, "loss": 0.26351704597473147, "lr": 2.81815906426533e-08, "epoch": 2.875, "percentage": 95.83, "elapsed_time": "6:18:03", "remaining_time": "0:16:26"}
{"current_steps": 700, "total_steps": 720, "loss": 0.25306267738342286, "lr": 1.2945629259917547e-08, "epoch": 2.9166666666666665, "percentage": 97.22, "elapsed_time": "6:25:46", "remaining_time": "0:11:01"}
{"current_steps": 710, "total_steps": 720, "loss": 0.26765923500061034, "lr": 3.5542026425233746e-09, "epoch": 2.9583333333333335, "percentage": 98.61, "elapsed_time": "6:33:28", "remaining_time": "0:05:32"}
{"current_steps": 720, "total_steps": 720, "loss": 0.26591691970825193, "lr": 2.938048062617327e-11, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "6:40:39", "remaining_time": "0:00:00"}
{"current_steps": 720, "total_steps": 720, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "6:43:12", "remaining_time": "0:00:00"}