| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 18.73536299765808, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1873536299765808, | |
| "grad_norm": 5.991908550262451, | |
| "learning_rate": 4.9999313759953484e-05, | |
| "loss": 6.4768, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3747072599531616, | |
| "grad_norm": 8.760614395141602, | |
| "learning_rate": 4.999725507748798e-05, | |
| "loss": 5.0186, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5620608899297423, | |
| "grad_norm": 4.322343826293945, | |
| "learning_rate": 4.999382406562349e-05, | |
| "loss": 3.1088, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7494145199063232, | |
| "grad_norm": 1.4796526432037354, | |
| "learning_rate": 4.9989020912719864e-05, | |
| "loss": 2.2997, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.936768149882904, | |
| "grad_norm": 0.8381783962249756, | |
| "learning_rate": 4.998284588246634e-05, | |
| "loss": 1.9748, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1241217798594847, | |
| "grad_norm": 0.6073408722877502, | |
| "learning_rate": 4.99752993138672e-05, | |
| "loss": 1.8716, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.3114754098360657, | |
| "grad_norm": 0.5777516961097717, | |
| "learning_rate": 4.996638162122302e-05, | |
| "loss": 1.7803, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.4988290398126463, | |
| "grad_norm": 0.5658383369445801, | |
| "learning_rate": 4.995609329410804e-05, | |
| "loss": 1.7585, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.6861826697892273, | |
| "grad_norm": 0.6109507083892822, | |
| "learning_rate": 4.994443489734322e-05, | |
| "loss": 1.6902, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.8735362997658078, | |
| "grad_norm": 0.6710304021835327, | |
| "learning_rate": 4.9931407070965254e-05, | |
| "loss": 1.675, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.060889929742389, | |
| "grad_norm": 0.6605099439620972, | |
| "learning_rate": 4.9917010530191455e-05, | |
| "loss": 1.5914, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.2482435597189694, | |
| "grad_norm": 0.8813541531562805, | |
| "learning_rate": 4.990124606538042e-05, | |
| "loss": 1.5681, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.4355971896955504, | |
| "grad_norm": 0.9561053514480591, | |
| "learning_rate": 4.9884114541988747e-05, | |
| "loss": 1.4891, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.6229508196721314, | |
| "grad_norm": 1.0302178859710693, | |
| "learning_rate": 4.9865616900523406e-05, | |
| "loss": 1.4524, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.810304449648712, | |
| "grad_norm": 1.114527940750122, | |
| "learning_rate": 4.984575415649019e-05, | |
| "loss": 1.3666, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.9976580796252925, | |
| "grad_norm": 1.1488112211227417, | |
| "learning_rate": 4.982452740033793e-05, | |
| "loss": 1.3581, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.1850117096018735, | |
| "grad_norm": 1.3187187910079956, | |
| "learning_rate": 4.9801937797398636e-05, | |
| "loss": 1.2926, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.3723653395784545, | |
| "grad_norm": 1.4319546222686768, | |
| "learning_rate": 4.9777986587823523e-05, | |
| "loss": 1.2463, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.559718969555035, | |
| "grad_norm": 1.4622282981872559, | |
| "learning_rate": 4.975267508651492e-05, | |
| "loss": 1.2304, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.747072599531616, | |
| "grad_norm": 2.000797748565674, | |
| "learning_rate": 4.97260046830541e-05, | |
| "loss": 1.2252, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.9344262295081966, | |
| "grad_norm": 1.6277581453323364, | |
| "learning_rate": 4.969797684162498e-05, | |
| "loss": 1.1649, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 4.121779859484778, | |
| "grad_norm": 2.1771910190582275, | |
| "learning_rate": 4.966859310093372e-05, | |
| "loss": 1.1471, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.309133489461359, | |
| "grad_norm": 1.9214098453521729, | |
| "learning_rate": 4.9637855074124305e-05, | |
| "loss": 1.1064, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 4.496487119437939, | |
| "grad_norm": 2.057615041732788, | |
| "learning_rate": 4.960576444868992e-05, | |
| "loss": 1.1061, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.68384074941452, | |
| "grad_norm": 1.851131796836853, | |
| "learning_rate": 4.957232298638036e-05, | |
| "loss": 1.0318, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.871194379391101, | |
| "grad_norm": 2.1048285961151123, | |
| "learning_rate": 4.953753252310526e-05, | |
| "loss": 1.0444, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 5.058548009367682, | |
| "grad_norm": 2.0235438346862793, | |
| "learning_rate": 4.950139496883335e-05, | |
| "loss": 1.0303, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 5.245901639344262, | |
| "grad_norm": 2.574484348297119, | |
| "learning_rate": 4.94639123074876e-05, | |
| "loss": 0.9954, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 5.433255269320843, | |
| "grad_norm": 2.1624159812927246, | |
| "learning_rate": 4.9425086596836264e-05, | |
| "loss": 0.9686, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 5.620608899297424, | |
| "grad_norm": 2.923964023590088, | |
| "learning_rate": 4.9384919968379945e-05, | |
| "loss": 0.961, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.807962529274005, | |
| "grad_norm": 3.605888843536377, | |
| "learning_rate": 4.934341462723455e-05, | |
| "loss": 0.9713, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 5.995316159250585, | |
| "grad_norm": 2.6934282779693604, | |
| "learning_rate": 4.930057285201027e-05, | |
| "loss": 0.9327, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 6.182669789227166, | |
| "grad_norm": 2.723066568374634, | |
| "learning_rate": 4.925639699468645e-05, | |
| "loss": 0.8974, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 6.370023419203747, | |
| "grad_norm": 2.7989768981933594, | |
| "learning_rate": 4.921088948048247e-05, | |
| "loss": 0.8912, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 6.557377049180328, | |
| "grad_norm": 2.685530424118042, | |
| "learning_rate": 4.916405280772462e-05, | |
| "loss": 0.8809, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 6.744730679156909, | |
| "grad_norm": 2.441941738128662, | |
| "learning_rate": 4.911588954770897e-05, | |
| "loss": 0.8984, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 6.932084309133489, | |
| "grad_norm": 2.7177064418792725, | |
| "learning_rate": 4.9066402344560115e-05, | |
| "loss": 0.855, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 7.11943793911007, | |
| "grad_norm": 3.2908644676208496, | |
| "learning_rate": 4.901559391508611e-05, | |
| "loss": 0.8785, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 7.306791569086651, | |
| "grad_norm": 3.195590019226074, | |
| "learning_rate": 4.896346704862927e-05, | |
| "loss": 0.8542, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 7.494145199063232, | |
| "grad_norm": 3.4960882663726807, | |
| "learning_rate": 4.891002460691306e-05, | |
| "loss": 0.7881, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.681498829039812, | |
| "grad_norm": 2.852773666381836, | |
| "learning_rate": 4.885526952388498e-05, | |
| "loss": 0.7957, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 7.868852459016393, | |
| "grad_norm": 2.8862316608428955, | |
| "learning_rate": 4.879920480555549e-05, | |
| "loss": 0.8022, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 8.056206088992974, | |
| "grad_norm": 2.706434488296509, | |
| "learning_rate": 4.874183352983297e-05, | |
| "loss": 0.7811, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 8.243559718969555, | |
| "grad_norm": 3.107057809829712, | |
| "learning_rate": 4.8683158846354786e-05, | |
| "loss": 0.7786, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 8.430913348946136, | |
| "grad_norm": 3.327939033508301, | |
| "learning_rate": 4.862318397631434e-05, | |
| "loss": 0.7431, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 8.618266978922717, | |
| "grad_norm": 3.249922513961792, | |
| "learning_rate": 4.8561912212284223e-05, | |
| "loss": 0.7477, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 8.805620608899297, | |
| "grad_norm": 3.709353446960449, | |
| "learning_rate": 4.84993469180355e-05, | |
| "loss": 0.7973, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 8.992974238875878, | |
| "grad_norm": 2.777991533279419, | |
| "learning_rate": 4.8435491528353026e-05, | |
| "loss": 0.7699, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 9.180327868852459, | |
| "grad_norm": 2.6447904109954834, | |
| "learning_rate": 4.8370349548846823e-05, | |
| "loss": 0.692, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 9.36768149882904, | |
| "grad_norm": 3.150733232498169, | |
| "learning_rate": 4.83039245557597e-05, | |
| "loss": 0.7435, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 9.55503512880562, | |
| "grad_norm": 3.316145420074463, | |
| "learning_rate": 4.823622019577089e-05, | |
| "loss": 0.7589, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 9.742388758782202, | |
| "grad_norm": 3.4923229217529297, | |
| "learning_rate": 4.8167240185795835e-05, | |
| "loss": 0.7262, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 9.929742388758783, | |
| "grad_norm": 3.1557626724243164, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 0.6824, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 10.117096018735364, | |
| "grad_norm": 3.2009847164154053, | |
| "learning_rate": 4.8025468433501774e-05, | |
| "loss": 0.7238, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 10.304449648711945, | |
| "grad_norm": 3.149319887161255, | |
| "learning_rate": 4.795268447433907e-05, | |
| "loss": 0.7002, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 10.491803278688524, | |
| "grad_norm": 3.1471166610717773, | |
| "learning_rate": 4.787864043107546e-05, | |
| "loss": 0.6933, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 10.679156908665105, | |
| "grad_norm": 2.9310121536254883, | |
| "learning_rate": 4.780334036866997e-05, | |
| "loss": 0.7152, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 10.866510538641686, | |
| "grad_norm": 3.6723790168762207, | |
| "learning_rate": 4.772678842103605e-05, | |
| "loss": 0.679, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 11.053864168618267, | |
| "grad_norm": 3.633692502975464, | |
| "learning_rate": 4.764898879081468e-05, | |
| "loss": 0.6489, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 11.241217798594848, | |
| "grad_norm": 3.9104480743408203, | |
| "learning_rate": 4.756994574914359e-05, | |
| "loss": 0.6116, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 11.428571428571429, | |
| "grad_norm": 3.8203835487365723, | |
| "learning_rate": 4.748966363542285e-05, | |
| "loss": 0.6549, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 11.61592505854801, | |
| "grad_norm": 3.5407750606536865, | |
| "learning_rate": 4.7408146857076566e-05, | |
| "loss": 0.6532, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 11.80327868852459, | |
| "grad_norm": 4.155674457550049, | |
| "learning_rate": 4.732539988931097e-05, | |
| "loss": 0.6684, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 11.99063231850117, | |
| "grad_norm": 4.21943473815918, | |
| "learning_rate": 4.724142727486869e-05, | |
| "loss": 0.683, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 12.177985948477751, | |
| "grad_norm": 3.3667685985565186, | |
| "learning_rate": 4.715623362377939e-05, | |
| "loss": 0.6127, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 12.365339578454332, | |
| "grad_norm": 3.7362210750579834, | |
| "learning_rate": 4.706982361310669e-05, | |
| "loss": 0.606, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 12.552693208430913, | |
| "grad_norm": 3.549915313720703, | |
| "learning_rate": 4.698220198669136e-05, | |
| "loss": 0.6349, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 12.740046838407494, | |
| "grad_norm": 3.360044002532959, | |
| "learning_rate": 4.6893373554890925e-05, | |
| "loss": 0.6335, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 12.927400468384075, | |
| "grad_norm": 3.676515817642212, | |
| "learning_rate": 4.680334319431555e-05, | |
| "loss": 0.6283, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 13.114754098360656, | |
| "grad_norm": 4.325002193450928, | |
| "learning_rate": 4.6712115847560355e-05, | |
| "loss": 0.6248, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 13.302107728337237, | |
| "grad_norm": 4.889411449432373, | |
| "learning_rate": 4.6619696522934024e-05, | |
| "loss": 0.5959, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 13.489461358313818, | |
| "grad_norm": 4.090158939361572, | |
| "learning_rate": 4.652609029418389e-05, | |
| "loss": 0.6068, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 13.676814988290397, | |
| "grad_norm": 3.8901116847991943, | |
| "learning_rate": 4.643130230021737e-05, | |
| "loss": 0.6042, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 13.864168618266978, | |
| "grad_norm": 4.178182125091553, | |
| "learning_rate": 4.6335337744819873e-05, | |
| "loss": 0.6253, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 14.05152224824356, | |
| "grad_norm": 3.4572255611419678, | |
| "learning_rate": 4.6238201896369055e-05, | |
| "loss": 0.6136, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 14.23887587822014, | |
| "grad_norm": 4.382098197937012, | |
| "learning_rate": 4.613990008754565e-05, | |
| "loss": 0.5499, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 14.426229508196721, | |
| "grad_norm": 4.183515548706055, | |
| "learning_rate": 4.6040437715040706e-05, | |
| "loss": 0.5845, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 14.613583138173302, | |
| "grad_norm": 3.2976605892181396, | |
| "learning_rate": 4.593982023925926e-05, | |
| "loss": 0.6097, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 14.800936768149883, | |
| "grad_norm": 4.0663347244262695, | |
| "learning_rate": 4.58380531840206e-05, | |
| "loss": 0.6161, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 14.988290398126464, | |
| "grad_norm": 4.074985980987549, | |
| "learning_rate": 4.573514213625505e-05, | |
| "loss": 0.5597, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 15.175644028103045, | |
| "grad_norm": 4.086116790771484, | |
| "learning_rate": 4.563109274569717e-05, | |
| "loss": 0.5484, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 15.362997658079625, | |
| "grad_norm": 3.6355836391448975, | |
| "learning_rate": 4.552591072457565e-05, | |
| "loss": 0.5561, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 15.550351288056206, | |
| "grad_norm": 4.557271480560303, | |
| "learning_rate": 4.5419601847299706e-05, | |
| "loss": 0.5729, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 15.737704918032787, | |
| "grad_norm": 3.3405730724334717, | |
| "learning_rate": 4.5312171950142034e-05, | |
| "loss": 0.5654, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 15.925058548009368, | |
| "grad_norm": 5.102325439453125, | |
| "learning_rate": 4.5203626930918455e-05, | |
| "loss": 0.5766, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 16.11241217798595, | |
| "grad_norm": 4.394238471984863, | |
| "learning_rate": 4.509397274866409e-05, | |
| "loss": 0.5617, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 16.29976580796253, | |
| "grad_norm": 4.780090808868408, | |
| "learning_rate": 4.498321542330623e-05, | |
| "loss": 0.5363, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 16.48711943793911, | |
| "grad_norm": 3.9079573154449463, | |
| "learning_rate": 4.4871361035333836e-05, | |
| "loss": 0.5387, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 16.67447306791569, | |
| "grad_norm": 4.230076789855957, | |
| "learning_rate": 4.4758415725463746e-05, | |
| "loss": 0.5594, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 16.861826697892273, | |
| "grad_norm": 3.655414581298828, | |
| "learning_rate": 4.464438569430354e-05, | |
| "loss": 0.5556, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 17.049180327868854, | |
| "grad_norm": 3.818207025527954, | |
| "learning_rate": 4.452927720201112e-05, | |
| "loss": 0.5367, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 17.236533957845435, | |
| "grad_norm": 3.827942371368408, | |
| "learning_rate": 4.441309656795106e-05, | |
| "loss": 0.5108, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 17.423887587822016, | |
| "grad_norm": 3.933605194091797, | |
| "learning_rate": 4.4295850170347664e-05, | |
| "loss": 0.5258, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 17.611241217798593, | |
| "grad_norm": 4.577270030975342, | |
| "learning_rate": 4.417754444593478e-05, | |
| "loss": 0.5313, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 17.798594847775174, | |
| "grad_norm": 5.285182476043701, | |
| "learning_rate": 4.40581858896025e-05, | |
| "loss": 0.5421, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 17.985948477751755, | |
| "grad_norm": 4.50776481628418, | |
| "learning_rate": 4.3937781054040505e-05, | |
| "loss": 0.5428, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 18.173302107728336, | |
| "grad_norm": 3.9270503520965576, | |
| "learning_rate": 4.38163365493784e-05, | |
| "loss": 0.4744, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 18.360655737704917, | |
| "grad_norm": 4.346292018890381, | |
| "learning_rate": 4.3693859042822774e-05, | |
| "loss": 0.5177, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 18.548009367681498, | |
| "grad_norm": 3.9130234718322754, | |
| "learning_rate": 4.357035525829123e-05, | |
| "loss": 0.5387, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 18.73536299765808, | |
| "grad_norm": 3.995023250579834, | |
| "learning_rate": 4.344583197604318e-05, | |
| "loss": 0.5071, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 4240, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 80, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.7866540300790006e+18, | |
| "train_batch_size": 10, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |