onereason_0.8b_sft / trainer_log.jsonl
lldois's picture
Upload onereason_0.8b_sft model without checkpoints
9f001a6 verified
Raw
History Blame Contribute Delete
16.6 kB
{"current_steps": 5, "total_steps": 400, "loss": 3.0092775344848635, "lr": 6.666666666666667e-06, "epoch": 0.012523481527864746, "percentage": 1.25, "elapsed_time": "0:00:41", "remaining_time": "0:54:28"}
{"current_steps": 10, "total_steps": 400, "loss": 2.547764778137207, "lr": 1.5000000000000002e-05, "epoch": 0.025046963055729492, "percentage": 2.5, "elapsed_time": "0:01:21", "remaining_time": "0:52:42"}
{"current_steps": 15, "total_steps": 400, "loss": 2.233675956726074, "lr": 1.9998688836656322e-05, "epoch": 0.03757044458359424, "percentage": 3.75, "elapsed_time": "0:02:02", "remaining_time": "0:52:24"}
{"current_steps": 20, "total_steps": 400, "loss": 2.057873344421387, "lr": 1.9983942197426272e-05, "epoch": 0.050093926111458985, "percentage": 5.0, "elapsed_time": "0:02:42", "remaining_time": "0:51:29"}
{"current_steps": 25, "total_steps": 400, "loss": 1.851465606689453, "lr": 1.995283421166614e-05, "epoch": 0.06261740763932373, "percentage": 6.25, "elapsed_time": "0:03:24", "remaining_time": "0:51:14"}
{"current_steps": 30, "total_steps": 400, "loss": 1.855565071105957, "lr": 1.9905415858090036e-05, "epoch": 0.07514088916718847, "percentage": 7.5, "elapsed_time": "0:04:04", "remaining_time": "0:50:10"}
{"current_steps": 35, "total_steps": 400, "loss": 1.752499771118164, "lr": 1.9841764844290744e-05, "epoch": 0.08766437069505323, "percentage": 8.75, "elapsed_time": "0:04:45", "remaining_time": "0:49:38"}
{"current_steps": 40, "total_steps": 400, "loss": 1.8114988327026367, "lr": 1.976198547939518e-05, "epoch": 0.10018785222291797, "percentage": 10.0, "elapsed_time": "0:05:24", "remaining_time": "0:48:44"}
{"current_steps": 45, "total_steps": 400, "loss": 1.6981731414794923, "lr": 1.9666208503126115e-05, "epoch": 0.11271133375078271, "percentage": 11.25, "elapsed_time": "0:06:05", "remaining_time": "0:48:06"}
{"current_steps": 50, "total_steps": 400, "loss": 1.6682065963745116, "lr": 1.955459087155033e-05, "epoch": 0.12523481527864747, "percentage": 12.5, "elapsed_time": "0:06:45", "remaining_time": "0:47:21"}
{"current_steps": 55, "total_steps": 400, "loss": 1.654319953918457, "lr": 1.9427315499864345e-05, "epoch": 0.13775829680651222, "percentage": 13.75, "elapsed_time": "0:07:25", "remaining_time": "0:46:34"}
{"current_steps": 60, "total_steps": 400, "loss": 1.628897476196289, "lr": 1.928459096263918e-05, "epoch": 0.15028177833437695, "percentage": 15.0, "elapsed_time": "0:08:04", "remaining_time": "0:45:43"}
{"current_steps": 65, "total_steps": 400, "loss": 1.588959312438965, "lr": 1.9126651152015404e-05, "epoch": 0.1628052598622417, "percentage": 16.25, "elapsed_time": "0:08:45", "remaining_time": "0:45:10"}
{"current_steps": 70, "total_steps": 400, "loss": 1.643252182006836, "lr": 1.8953754894408617e-05, "epoch": 0.17532874139010646, "percentage": 17.5, "elapsed_time": "0:09:26", "remaining_time": "0:44:30"}
{"current_steps": 75, "total_steps": 400, "loss": 1.575343132019043, "lr": 1.876618552635348e-05, "epoch": 0.18785222291797118, "percentage": 18.75, "elapsed_time": "0:10:08", "remaining_time": "0:43:56"}
{"current_steps": 80, "total_steps": 400, "loss": 1.6070398330688476, "lr": 1.8564250430181387e-05, "epoch": 0.20037570444583594, "percentage": 20.0, "elapsed_time": "0:10:48", "remaining_time": "0:43:13"}
{"current_steps": 85, "total_steps": 400, "loss": 1.6005193710327148, "lr": 1.8348280530292712e-05, "epoch": 0.2128991859737007, "percentage": 21.25, "elapsed_time": "0:11:28", "remaining_time": "0:42:31"}
{"current_steps": 90, "total_steps": 400, "loss": 1.5561012268066405, "lr": 1.8118629750849106e-05, "epoch": 0.22542266750156542, "percentage": 22.5, "elapsed_time": "0:12:09", "remaining_time": "0:41:51"}
{"current_steps": 95, "total_steps": 400, "loss": 1.5994838714599608, "lr": 1.7875674435774546e-05, "epoch": 0.23794614902943018, "percentage": 23.75, "elapsed_time": "0:12:49", "remaining_time": "0:41:10"}
{"current_steps": 100, "total_steps": 400, "loss": 1.5856236457824706, "lr": 1.7619812732015664e-05, "epoch": 0.25046963055729493, "percentage": 25.0, "elapsed_time": "0:13:29", "remaining_time": "0:40:27"}
{"current_steps": 105, "total_steps": 400, "loss": 1.5562751770019532, "lr": 1.7351463937072008e-05, "epoch": 0.2629931120851597, "percentage": 26.25, "elapsed_time": "0:14:10", "remaining_time": "0:39:49"}
{"current_steps": 110, "total_steps": 400, "loss": 1.5253159523010253, "lr": 1.7071067811865477e-05, "epoch": 0.27551659361302444, "percentage": 27.5, "elapsed_time": "0:14:50", "remaining_time": "0:39:07"}
{"current_steps": 115, "total_steps": 400, "loss": 1.5002705574035644, "lr": 1.6779083860075032e-05, "epoch": 0.28804007514088914, "percentage": 28.75, "elapsed_time": "0:15:32", "remaining_time": "0:38:32"}
{"current_steps": 120, "total_steps": 400, "loss": 1.5255040168762206, "lr": 1.6475990575117603e-05, "epoch": 0.3005635566687539, "percentage": 30.0, "elapsed_time": "0:16:11", "remaining_time": "0:37:46"}
{"current_steps": 125, "total_steps": 400, "loss": 1.489553737640381, "lr": 1.6162284656009276e-05, "epoch": 0.31308703819661865, "percentage": 31.25, "elapsed_time": "0:16:54", "remaining_time": "0:37:10"}
{"current_steps": 130, "total_steps": 400, "loss": 1.4954115867614746, "lr": 1.5838480193391753e-05, "epoch": 0.3256105197244834, "percentage": 32.5, "elapsed_time": "0:17:34", "remaining_time": "0:36:29"}
{"current_steps": 135, "total_steps": 400, "loss": 1.504003143310547, "lr": 1.5505107827058038e-05, "epoch": 0.33813400125234816, "percentage": 33.75, "elapsed_time": "0:18:15", "remaining_time": "0:35:50"}
{"current_steps": 140, "total_steps": 400, "loss": 1.5397921562194825, "lr": 1.516271387635786e-05, "epoch": 0.3506574827802129, "percentage": 35.0, "elapsed_time": "0:18:54", "remaining_time": "0:35:07"}
{"current_steps": 145, "total_steps": 400, "loss": 1.5844552040100097, "lr": 1.4811859444908053e-05, "epoch": 0.36318096430807767, "percentage": 36.25, "elapsed_time": "0:19:36", "remaining_time": "0:34:28"}
{"current_steps": 150, "total_steps": 400, "loss": 1.4908522605895995, "lr": 1.4453119501074924e-05, "epoch": 0.37570444583594237, "percentage": 37.5, "elapsed_time": "0:20:17", "remaining_time": "0:33:49"}
{"current_steps": 155, "total_steps": 400, "loss": 1.4880791664123536, "lr": 1.4087081935735565e-05, "epoch": 0.3882279273638071, "percentage": 38.75, "elapsed_time": "0:20:58", "remaining_time": "0:33:09"}
{"current_steps": 160, "total_steps": 400, "loss": 1.4971721649169922, "lr": 1.3714346598862168e-05, "epoch": 0.4007514088916719, "percentage": 40.0, "elapsed_time": "0:21:39", "remaining_time": "0:32:29"}
{"current_steps": 165, "total_steps": 400, "loss": 1.4654574394226074, "lr": 1.3335524316508208e-05, "epoch": 0.41327489041953663, "percentage": 41.25, "elapsed_time": "0:22:20", "remaining_time": "0:31:49"}
{"current_steps": 170, "total_steps": 400, "loss": 1.450455379486084, "lr": 1.2951235889807386e-05, "epoch": 0.4257983719474014, "percentage": 42.5, "elapsed_time": "0:23:00", "remaining_time": "0:31:07"}
{"current_steps": 175, "total_steps": 400, "loss": 1.570608425140381, "lr": 1.2562111077625723e-05, "epoch": 0.43832185347526614, "percentage": 43.75, "elapsed_time": "0:23:41", "remaining_time": "0:30:27"}
{"current_steps": 180, "total_steps": 400, "loss": 1.4704577445983886, "lr": 1.2168787564534078e-05, "epoch": 0.45084533500313084, "percentage": 45.0, "elapsed_time": "0:24:22", "remaining_time": "0:29:47"}
{"current_steps": 185, "total_steps": 400, "loss": 1.5063845634460449, "lr": 1.177190991579223e-05, "epoch": 0.4633688165309956, "percentage": 46.25, "elapsed_time": "0:25:01", "remaining_time": "0:29:04"}
{"current_steps": 190, "total_steps": 400, "loss": 1.4744919776916503, "lr": 1.1372128521057155e-05, "epoch": 0.47589229805886035, "percentage": 47.5, "elapsed_time": "0:25:44", "remaining_time": "0:28:26"}
{"current_steps": 195, "total_steps": 400, "loss": 1.511544895172119, "lr": 1.0970098528546482e-05, "epoch": 0.4884157795867251, "percentage": 48.75, "elapsed_time": "0:26:23", "remaining_time": "0:27:44"}
{"current_steps": 200, "total_steps": 400, "loss": 1.4689907073974608, "lr": 1.0566478771403763e-05, "epoch": 0.5009392611145899, "percentage": 50.0, "elapsed_time": "0:27:04", "remaining_time": "0:27:04"}
{"current_steps": 205, "total_steps": 400, "loss": 1.4732332229614258, "lr": 1.0161930688025018e-05, "epoch": 0.5134627426424546, "percentage": 51.25, "elapsed_time": "0:27:45", "remaining_time": "0:26:24"}
{"current_steps": 210, "total_steps": 400, "loss": 1.4493576049804688, "lr": 9.757117238115871e-06, "epoch": 0.5259862241703194, "percentage": 52.5, "elapsed_time": "0:28:26", "remaining_time": "0:25:44"}
{"current_steps": 215, "total_steps": 400, "loss": 1.4741571426391602, "lr": 9.352701816255643e-06, "epoch": 0.5385097056981841, "percentage": 53.75, "elapsed_time": "0:29:07", "remaining_time": "0:25:03"}
{"current_steps": 220, "total_steps": 400, "loss": 1.4440049171447753, "lr": 8.949347164748761e-06, "epoch": 0.5510331872260489, "percentage": 55.0, "elapsed_time": "0:29:49", "remaining_time": "0:24:24"}
{"current_steps": 225, "total_steps": 400, "loss": 1.5042129516601563, "lr": 8.5477142875451e-06, "epoch": 0.5635566687539136, "percentage": 56.25, "elapsed_time": "0:30:30", "remaining_time": "0:23:43"}
{"current_steps": 230, "total_steps": 400, "loss": 1.479151153564453, "lr": 8.148461367009081e-06, "epoch": 0.5760801502817783, "percentage": 57.5, "elapsed_time": "0:31:10", "remaining_time": "0:23:02"}
{"current_steps": 235, "total_steps": 400, "loss": 1.5147887229919434, "lr": 7.752242685312709e-06, "epoch": 0.588603631809643, "percentage": 58.75, "elapsed_time": "0:31:50", "remaining_time": "0:22:21"}
{"current_steps": 240, "total_steps": 400, "loss": 1.4407625198364258, "lr": 7.35970755222007e-06, "epoch": 0.6011271133375078, "percentage": 60.0, "elapsed_time": "0:32:32", "remaining_time": "0:21:41"}
{"current_steps": 245, "total_steps": 400, "loss": 1.4036590576171875, "lr": 6.971499241020495e-06, "epoch": 0.6136505948653725, "percentage": 61.25, "elapsed_time": "0:33:14", "remaining_time": "0:21:02"}
{"current_steps": 250, "total_steps": 400, "loss": 1.4591806411743165, "lr": 6.588253934354039e-06, "epoch": 0.6261740763932373, "percentage": 62.5, "elapsed_time": "0:33:54", "remaining_time": "0:20:20"}
{"current_steps": 255, "total_steps": 400, "loss": 1.5027113914489747, "lr": 6.210599681656933e-06, "epoch": 0.638697557921102, "percentage": 63.75, "elapsed_time": "0:34:36", "remaining_time": "0:19:40"}
{"current_steps": 260, "total_steps": 400, "loss": 1.4685559272766113, "lr": 5.839155369935407e-06, "epoch": 0.6512210394489668, "percentage": 65.0, "elapsed_time": "0:35:17", "remaining_time": "0:19:00"}
{"current_steps": 265, "total_steps": 400, "loss": 1.5166523933410645, "lr": 5.4745297095546125e-06, "epoch": 0.6637445209768316, "percentage": 66.25, "elapsed_time": "0:35:58", "remaining_time": "0:18:19"}
{"current_steps": 270, "total_steps": 400, "loss": 1.4691507339477539, "lr": 5.117320236704697e-06, "epoch": 0.6762680025046963, "percentage": 67.5, "elapsed_time": "0:36:40", "remaining_time": "0:17:39"}
{"current_steps": 275, "total_steps": 400, "loss": 1.53342924118042, "lr": 4.7681123341787e-06, "epoch": 0.6887914840325611, "percentage": 68.75, "elapsed_time": "0:37:18", "remaining_time": "0:16:57"}
{"current_steps": 280, "total_steps": 400, "loss": 1.514073371887207, "lr": 4.427478272067066e-06, "epoch": 0.7013149655604258, "percentage": 70.0, "elapsed_time": "0:37:59", "remaining_time": "0:16:16"}
{"current_steps": 285, "total_steps": 400, "loss": 1.4454584121704102, "lr": 4.095976269940777e-06, "epoch": 0.7138384470882906, "percentage": 71.25, "elapsed_time": "0:38:39", "remaining_time": "0:15:35"}
{"current_steps": 290, "total_steps": 400, "loss": 1.4844335556030273, "lr": 3.7741495820600128e-06, "epoch": 0.7263619286161553, "percentage": 72.5, "elapsed_time": "0:39:20", "remaining_time": "0:14:55"}
{"current_steps": 295, "total_steps": 400, "loss": 1.4866701126098634, "lr": 3.4625256071074776e-06, "epoch": 0.73888541014402, "percentage": 73.75, "elapsed_time": "0:39:58", "remaining_time": "0:14:13"}
{"current_steps": 300, "total_steps": 400, "loss": 1.4392054557800293, "lr": 3.1616150239052647e-06, "epoch": 0.7514088916718847, "percentage": 75.0, "elapsed_time": "0:40:42", "remaining_time": "0:13:34"}
{"current_steps": 305, "total_steps": 400, "loss": 1.4637357711791992, "lr": 2.8719109545317102e-06, "epoch": 0.7639323731997495, "percentage": 76.25, "elapsed_time": "0:41:21", "remaining_time": "0:12:52"}
{"current_steps": 310, "total_steps": 400, "loss": 1.4387860298156738, "lr": 2.593888156209603e-06, "epoch": 0.7764558547276142, "percentage": 77.5, "elapsed_time": "0:42:04", "remaining_time": "0:12:13"}
{"current_steps": 315, "total_steps": 400, "loss": 1.4650882720947265, "lr": 2.328002243290138e-06, "epoch": 0.788979336255479, "percentage": 78.75, "elapsed_time": "0:42:46", "remaining_time": "0:11:32"}
{"current_steps": 320, "total_steps": 400, "loss": 1.5315435409545899, "lr": 2.074688940607529e-06, "epoch": 0.8015028177833438, "percentage": 80.0, "elapsed_time": "0:43:26", "remaining_time": "0:10:51"}
{"current_steps": 325, "total_steps": 400, "loss": 1.5125369071960448, "lr": 1.8343633694278895e-06, "epoch": 0.8140262993112085, "percentage": 81.25, "elapsed_time": "0:44:07", "remaining_time": "0:10:10"}
{"current_steps": 330, "total_steps": 400, "loss": 1.4377523422241212, "lr": 1.607419367162577e-06, "epoch": 0.8265497808390733, "percentage": 82.5, "elapsed_time": "0:44:48", "remaining_time": "0:09:30"}
{"current_steps": 335, "total_steps": 400, "loss": 1.4360872268676759, "lr": 1.3942288419607476e-06, "epoch": 0.839073262366938, "percentage": 83.75, "elapsed_time": "0:45:29", "remaining_time": "0:08:49"}
{"current_steps": 340, "total_steps": 400, "loss": 1.4957749366760253, "lr": 1.195141163238892e-06, "epoch": 0.8515967438948028, "percentage": 85.0, "elapsed_time": "0:46:10", "remaining_time": "0:08:08"}
{"current_steps": 345, "total_steps": 400, "loss": 1.4363853454589843, "lr": 1.010482589146048e-06, "epoch": 0.8641202254226675, "percentage": 86.25, "elapsed_time": "0:46:50", "remaining_time": "0:07:28"}
{"current_steps": 350, "total_steps": 400, "loss": 1.5025806427001953, "lr": 8.405557319029911e-07, "epoch": 0.8766437069505323, "percentage": 87.5, "elapsed_time": "0:47:31", "remaining_time": "0:06:47"}
{"current_steps": 355, "total_steps": 400, "loss": 1.4651078224182128, "lr": 6.856390618915775e-07, "epoch": 0.889167188478397, "percentage": 88.75, "elapsed_time": "0:48:12", "remaining_time": "0:06:06"}
{"current_steps": 360, "total_steps": 400, "loss": 1.464914894104004, "lr": 5.459864513068991e-07, "epoch": 0.9016906700062617, "percentage": 90.0, "elapsed_time": "0:48:52", "remaining_time": "0:05:25"}
{"current_steps": 365, "total_steps": 400, "loss": 1.44300537109375, "lr": 4.218267581201296e-07, "epoch": 0.9142141515341264, "percentage": 91.25, "elapsed_time": "0:49:32", "remaining_time": "0:04:45"}
{"current_steps": 370, "total_steps": 400, "loss": 1.4994802474975586, "lr": 3.133634510338235e-07, "epoch": 0.9267376330619912, "percentage": 92.5, "elapsed_time": "0:50:10", "remaining_time": "0:04:04"}
{"current_steps": 375, "total_steps": 400, "loss": 1.4373616218566894, "lr": 2.2077427604429435e-07, "epoch": 0.939261114589856, "percentage": 93.75, "elapsed_time": "0:50:52", "remaining_time": "0:03:23"}
{"current_steps": 380, "total_steps": 400, "loss": 1.4988561630249024, "lr": 1.4421096515749855e-07, "epoch": 0.9517845961177207, "percentage": 95.0, "elapsed_time": "0:51:33", "remaining_time": "0:02:42"}
{"current_steps": 385, "total_steps": 400, "loss": 1.5371465682983398, "lr": 8.379898773574924e-08, "epoch": 0.9643080776455855, "percentage": 96.25, "elapsed_time": "0:52:14", "remaining_time": "0:02:02"}
{"current_steps": 390, "total_steps": 400, "loss": 1.4375405311584473, "lr": 3.963734488278248e-08, "epoch": 0.9768315591734502, "percentage": 97.5, "elapsed_time": "0:52:54", "remaining_time": "0:01:21"}
{"current_steps": 395, "total_steps": 400, "loss": 1.4510549545288085, "lr": 1.179840720409331e-08, "epoch": 0.989355040701315, "percentage": 98.75, "elapsed_time": "0:53:35", "remaining_time": "0:00:40"}
{"current_steps": 400, "total_steps": 400, "loss": 1.4790672302246093, "lr": 3.277962084369257e-10, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:54:10", "remaining_time": "0:00:00"}
{"current_steps": 400, "total_steps": 400, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:54:13", "remaining_time": "0:00:00"}