{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 5824, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0017172541106770275, "grad_norm": 2.515625, "learning_rate": 1.5437392795883362e-07, "loss": 1.8191020965576172, "step": 10 }, { "epoch": 0.003434508221354055, "grad_norm": 2.515625, "learning_rate": 3.259005145797599e-07, "loss": 1.8383596420288086, "step": 20 }, { "epoch": 0.005151762332031082, "grad_norm": 2.484375, "learning_rate": 4.974271012006862e-07, "loss": 1.8086517333984375, "step": 30 }, { "epoch": 0.00686901644270811, "grad_norm": 2.40625, "learning_rate": 6.689536878216124e-07, "loss": 1.8471620559692383, "step": 40 }, { "epoch": 0.008586270553385136, "grad_norm": 2.5, "learning_rate": 8.404802744425386e-07, "loss": 1.8357393264770507, "step": 50 }, { "epoch": 0.010303524664062164, "grad_norm": 2.578125, "learning_rate": 1.012006861063465e-06, "loss": 1.8345760345458983, "step": 60 }, { "epoch": 0.012020778774739192, "grad_norm": 1.8984375, "learning_rate": 1.183533447684391e-06, "loss": 1.8340810775756835, "step": 70 }, { "epoch": 0.01373803288541622, "grad_norm": 2.359375, "learning_rate": 1.3550600343053175e-06, "loss": 1.8440494537353516, "step": 80 }, { "epoch": 0.015455286996093246, "grad_norm": 2.109375, "learning_rate": 1.5265866209262437e-06, "loss": 1.8132513046264649, "step": 90 }, { "epoch": 0.017172541106770273, "grad_norm": 2.234375, "learning_rate": 1.6981132075471698e-06, "loss": 1.8075799942016602, "step": 100 }, { "epoch": 0.0188897952174473, "grad_norm": 2.171875, "learning_rate": 1.8696397941680962e-06, "loss": 1.8131261825561524, "step": 110 }, { "epoch": 0.02060704932812433, "grad_norm": 2.25, "learning_rate": 2.0411663807890227e-06, "loss": 1.8113420486450196, "step": 120 }, { "epoch": 0.022324303438801357, "grad_norm": 2.34375, "learning_rate": 2.2126929674099487e-06, "loss": 1.8287776947021483, "step": 130 }, { "epoch": 0.024041557549478385, "grad_norm": 2.609375, "learning_rate": 2.3842195540308747e-06, "loss": 1.8301383972167968, "step": 140 }, { "epoch": 0.025758811660155412, "grad_norm": 2.515625, "learning_rate": 2.555746140651801e-06, "loss": 1.8248241424560547, "step": 150 }, { "epoch": 0.02747606577083244, "grad_norm": 2.046875, "learning_rate": 2.7272727272727272e-06, "loss": 1.8159824371337892, "step": 160 }, { "epoch": 0.029193319881509465, "grad_norm": 2.1875, "learning_rate": 2.8987993138936537e-06, "loss": 1.8324663162231445, "step": 170 }, { "epoch": 0.030910573992186493, "grad_norm": 2.390625, "learning_rate": 3.07032590051458e-06, "loss": 1.7960712432861328, "step": 180 }, { "epoch": 0.03262782810286352, "grad_norm": 2.25, "learning_rate": 3.241852487135506e-06, "loss": 1.7990116119384765, "step": 190 }, { "epoch": 0.034345082213540545, "grad_norm": 1.8984375, "learning_rate": 3.4133790737564326e-06, "loss": 1.8299552917480468, "step": 200 }, { "epoch": 0.03606233632421758, "grad_norm": 2.109375, "learning_rate": 3.5849056603773586e-06, "loss": 1.8229988098144532, "step": 210 }, { "epoch": 0.0377795904348946, "grad_norm": 2.0, "learning_rate": 3.756432246998285e-06, "loss": 1.7922859191894531, "step": 220 }, { "epoch": 0.03949684454557163, "grad_norm": 1.8671875, "learning_rate": 3.927958833619211e-06, "loss": 1.7932601928710938, "step": 230 }, { "epoch": 0.04121409865624866, "grad_norm": 2.015625, "learning_rate": 4.099485420240138e-06, "loss": 1.840469741821289, "step": 240 }, { "epoch": 0.04293135276692569, "grad_norm": 2.21875, "learning_rate": 4.271012006861064e-06, "loss": 1.8065391540527345, "step": 250 }, { "epoch": 0.04464860687760271, "grad_norm": 2.265625, "learning_rate": 4.4425385934819905e-06, "loss": 1.7606891632080077, "step": 260 }, { "epoch": 0.04636586098827974, "grad_norm": 1.9375, "learning_rate": 4.614065180102916e-06, "loss": 1.7855205535888672, "step": 270 }, { "epoch": 0.04808311509895677, "grad_norm": 2.109375, "learning_rate": 4.7855917667238426e-06, "loss": 1.7873542785644532, "step": 280 }, { "epoch": 0.049800369209633794, "grad_norm": 1.9765625, "learning_rate": 4.957118353344769e-06, "loss": 1.806468391418457, "step": 290 }, { "epoch": 0.051517623320310825, "grad_norm": 2.40625, "learning_rate": 5.128644939965695e-06, "loss": 1.7866912841796876, "step": 300 }, { "epoch": 0.05323487743098785, "grad_norm": 2.0, "learning_rate": 5.300171526586622e-06, "loss": 1.7934232711791993, "step": 310 }, { "epoch": 0.05495213154166488, "grad_norm": 2.078125, "learning_rate": 5.4716981132075475e-06, "loss": 1.8392288208007812, "step": 320 }, { "epoch": 0.056669385652341905, "grad_norm": 1.9765625, "learning_rate": 5.643224699828473e-06, "loss": 1.7854141235351562, "step": 330 }, { "epoch": 0.05838663976301893, "grad_norm": 2.34375, "learning_rate": 5.8147512864494004e-06, "loss": 1.8038337707519532, "step": 340 }, { "epoch": 0.06010389387369596, "grad_norm": 2.171875, "learning_rate": 5.986277873070326e-06, "loss": 1.78695068359375, "step": 350 }, { "epoch": 0.061821147984372986, "grad_norm": 2.125, "learning_rate": 6.1578044596912525e-06, "loss": 1.780914306640625, "step": 360 }, { "epoch": 0.06353840209505002, "grad_norm": 1.875, "learning_rate": 6.329331046312179e-06, "loss": 1.8001070022583008, "step": 370 }, { "epoch": 0.06525565620572704, "grad_norm": 2.125, "learning_rate": 6.500857632933105e-06, "loss": 1.763052749633789, "step": 380 }, { "epoch": 0.06697291031640407, "grad_norm": 2.21875, "learning_rate": 6.672384219554031e-06, "loss": 1.7724241256713866, "step": 390 }, { "epoch": 0.06869016442708109, "grad_norm": 2.09375, "learning_rate": 6.843910806174958e-06, "loss": 1.7973081588745117, "step": 400 }, { "epoch": 0.07040741853775813, "grad_norm": 2.125, "learning_rate": 7.015437392795884e-06, "loss": 1.760462760925293, "step": 410 }, { "epoch": 0.07212467264843515, "grad_norm": 2.140625, "learning_rate": 7.18696397941681e-06, "loss": 1.7786720275878907, "step": 420 }, { "epoch": 0.07384192675911218, "grad_norm": 1.890625, "learning_rate": 7.358490566037736e-06, "loss": 1.789870262145996, "step": 430 }, { "epoch": 0.0755591808697892, "grad_norm": 1.921875, "learning_rate": 7.530017152658663e-06, "loss": 1.7521888732910156, "step": 440 }, { "epoch": 0.07727643498046624, "grad_norm": 1.9375, "learning_rate": 7.701543739279589e-06, "loss": 1.7595624923706055, "step": 450 }, { "epoch": 0.07899368909114327, "grad_norm": 2.1875, "learning_rate": 7.873070325900514e-06, "loss": 1.7787664413452149, "step": 460 }, { "epoch": 0.08071094320182029, "grad_norm": 1.9453125, "learning_rate": 8.044596912521442e-06, "loss": 1.7752704620361328, "step": 470 }, { "epoch": 0.08242819731249731, "grad_norm": 1.8359375, "learning_rate": 8.216123499142367e-06, "loss": 1.7766138076782227, "step": 480 }, { "epoch": 0.08414545142317434, "grad_norm": 2.203125, "learning_rate": 8.387650085763293e-06, "loss": 1.7754650115966797, "step": 490 }, { "epoch": 0.08586270553385138, "grad_norm": 2.015625, "learning_rate": 8.55917667238422e-06, "loss": 1.7739034652709962, "step": 500 }, { "epoch": 0.08586270553385138, "eval_loss": 1.76096510887146, "eval_runtime": 141.9794, "eval_samples_per_second": 33.477, "eval_steps_per_second": 4.191, "step": 500 }, { "epoch": 0.0875799596445284, "grad_norm": 1.8203125, "learning_rate": 8.730703259005146e-06, "loss": 1.7364377975463867, "step": 510 }, { "epoch": 0.08929721375520543, "grad_norm": 1.953125, "learning_rate": 8.902229845626073e-06, "loss": 1.7708450317382813, "step": 520 }, { "epoch": 0.09101446786588245, "grad_norm": 2.171875, "learning_rate": 9.073756432246999e-06, "loss": 1.741303062438965, "step": 530 }, { "epoch": 0.09273172197655948, "grad_norm": 1.9296875, "learning_rate": 9.245283018867926e-06, "loss": 1.7539249420166017, "step": 540 }, { "epoch": 0.09444897608723651, "grad_norm": 1.9296875, "learning_rate": 9.416809605488852e-06, "loss": 1.774032211303711, "step": 550 }, { "epoch": 0.09616623019791354, "grad_norm": 1.921875, "learning_rate": 9.588336192109777e-06, "loss": 1.739206314086914, "step": 560 }, { "epoch": 0.09788348430859056, "grad_norm": 1.953125, "learning_rate": 9.759862778730705e-06, "loss": 1.7598821640014648, "step": 570 }, { "epoch": 0.09960073841926759, "grad_norm": 2.3125, "learning_rate": 9.93138936535163e-06, "loss": 1.7059608459472657, "step": 580 }, { "epoch": 0.10131799252994463, "grad_norm": 1.9375, "learning_rate": 9.999967661976874e-06, "loss": 1.7766645431518555, "step": 590 }, { "epoch": 0.10303524664062165, "grad_norm": 2.140625, "learning_rate": 9.999770042239263e-06, "loss": 1.7646825790405274, "step": 600 }, { "epoch": 0.10475250075129867, "grad_norm": 1.984375, "learning_rate": 9.999392775424525e-06, "loss": 1.7517282485961914, "step": 610 }, { "epoch": 0.1064697548619757, "grad_norm": 2.109375, "learning_rate": 9.998835875088261e-06, "loss": 1.7577917098999023, "step": 620 }, { "epoch": 0.10818700897265272, "grad_norm": 2.09375, "learning_rate": 9.998099361240493e-06, "loss": 1.744452667236328, "step": 630 }, { "epoch": 0.10990426308332976, "grad_norm": 2.09375, "learning_rate": 9.997183260344951e-06, "loss": 1.764775276184082, "step": 640 }, { "epoch": 0.11162151719400679, "grad_norm": 2.03125, "learning_rate": 9.996087605318118e-06, "loss": 1.7428857803344726, "step": 650 }, { "epoch": 0.11333877130468381, "grad_norm": 2.109375, "learning_rate": 9.99481243552805e-06, "loss": 1.7467594146728516, "step": 660 }, { "epoch": 0.11505602541536084, "grad_norm": 2.0625, "learning_rate": 9.993357796792959e-06, "loss": 1.7692676544189454, "step": 670 }, { "epoch": 0.11677327952603786, "grad_norm": 1.9375, "learning_rate": 9.991723741379569e-06, "loss": 1.7462827682495117, "step": 680 }, { "epoch": 0.1184905336367149, "grad_norm": 1.8828125, "learning_rate": 9.989910328001235e-06, "loss": 1.7484481811523438, "step": 690 }, { "epoch": 0.12020778774739192, "grad_norm": 1.71875, "learning_rate": 9.987917621815838e-06, "loss": 1.7265098571777344, "step": 700 }, { "epoch": 0.12192504185806895, "grad_norm": 1.84375, "learning_rate": 9.985745694423436e-06, "loss": 1.7403778076171874, "step": 710 }, { "epoch": 0.12364229596874597, "grad_norm": 1.8984375, "learning_rate": 9.983394623863703e-06, "loss": 1.7482641220092774, "step": 720 }, { "epoch": 0.125359550079423, "grad_norm": 1.7578125, "learning_rate": 9.980864494613114e-06, "loss": 1.719842529296875, "step": 730 }, { "epoch": 0.12707680419010003, "grad_norm": 2.046875, "learning_rate": 9.978155397581913e-06, "loss": 1.7162540435791016, "step": 740 }, { "epoch": 0.12879405830077706, "grad_norm": 2.109375, "learning_rate": 9.975267430110853e-06, "loss": 1.72626953125, "step": 750 }, { "epoch": 0.13051131241145408, "grad_norm": 1.8359375, "learning_rate": 9.972200695967687e-06, "loss": 1.7553569793701171, "step": 760 }, { "epoch": 0.1322285665221311, "grad_norm": 2.078125, "learning_rate": 9.968955305343449e-06, "loss": 1.7669294357299805, "step": 770 }, { "epoch": 0.13394582063280813, "grad_norm": 1.9140625, "learning_rate": 9.96553137484849e-06, "loss": 1.7363698959350586, "step": 780 }, { "epoch": 0.13566307474348516, "grad_norm": 2.078125, "learning_rate": 9.961929027508287e-06, "loss": 1.7368303298950196, "step": 790 }, { "epoch": 0.13738032885416218, "grad_norm": 1.8671875, "learning_rate": 9.958148392759032e-06, "loss": 1.7271577835083007, "step": 800 }, { "epoch": 0.13909758296483923, "grad_norm": 1.8203125, "learning_rate": 9.954189606442964e-06, "loss": 1.7537052154541015, "step": 810 }, { "epoch": 0.14081483707551626, "grad_norm": 1.9921875, "learning_rate": 9.950052810803507e-06, "loss": 1.7164833068847656, "step": 820 }, { "epoch": 0.14253209118619328, "grad_norm": 1.8671875, "learning_rate": 9.945738154480144e-06, "loss": 1.7115219116210938, "step": 830 }, { "epoch": 0.1442493452968703, "grad_norm": 1.9609375, "learning_rate": 9.941245792503084e-06, "loss": 1.7425621032714844, "step": 840 }, { "epoch": 0.14596659940754733, "grad_norm": 2.15625, "learning_rate": 9.936575886287692e-06, "loss": 1.7231435775756836, "step": 850 }, { "epoch": 0.14768385351822436, "grad_norm": 2.109375, "learning_rate": 9.931728603628685e-06, "loss": 1.727653694152832, "step": 860 }, { "epoch": 0.14940110762890138, "grad_norm": 1.6484375, "learning_rate": 9.926704118694105e-06, "loss": 1.7384393692016602, "step": 870 }, { "epoch": 0.1511183617395784, "grad_norm": 2.046875, "learning_rate": 9.921502612019065e-06, "loss": 1.7027233123779297, "step": 880 }, { "epoch": 0.15283561585025543, "grad_norm": 2.03125, "learning_rate": 9.91612427049925e-06, "loss": 1.7272832870483399, "step": 890 }, { "epoch": 0.15455286996093248, "grad_norm": 1.8984375, "learning_rate": 9.910569287384218e-06, "loss": 1.724130630493164, "step": 900 }, { "epoch": 0.1562701240716095, "grad_norm": 2.03125, "learning_rate": 9.904837862270441e-06, "loss": 1.7301189422607421, "step": 910 }, { "epoch": 0.15798737818228653, "grad_norm": 2.109375, "learning_rate": 9.898930201094148e-06, "loss": 1.7268779754638672, "step": 920 }, { "epoch": 0.15970463229296356, "grad_norm": 1.890625, "learning_rate": 9.892846516123913e-06, "loss": 1.7030744552612305, "step": 930 }, { "epoch": 0.16142188640364058, "grad_norm": 2.046875, "learning_rate": 9.886587025953033e-06, "loss": 1.7468671798706055, "step": 940 }, { "epoch": 0.1631391405143176, "grad_norm": 2.015625, "learning_rate": 9.880151955491676e-06, "loss": 1.7273527145385743, "step": 950 }, { "epoch": 0.16485639462499463, "grad_norm": 1.9921875, "learning_rate": 9.873541535958795e-06, "loss": 1.7256607055664062, "step": 960 }, { "epoch": 0.16657364873567165, "grad_norm": 1.8984375, "learning_rate": 9.866756004873826e-06, "loss": 1.7481857299804688, "step": 970 }, { "epoch": 0.16829090284634868, "grad_norm": 1.921875, "learning_rate": 9.859795606048143e-06, "loss": 1.7159637451171874, "step": 980 }, { "epoch": 0.1700081569570257, "grad_norm": 2.21875, "learning_rate": 9.852660589576313e-06, "loss": 1.7166841506958008, "step": 990 }, { "epoch": 0.17172541106770275, "grad_norm": 2.09375, "learning_rate": 9.845351211827094e-06, "loss": 1.7375505447387696, "step": 1000 }, { "epoch": 0.17172541106770275, "eval_loss": 1.7176287174224854, "eval_runtime": 132.4335, "eval_samples_per_second": 35.89, "eval_steps_per_second": 4.493, "step": 1000 }, { "epoch": 0.17344266517837978, "grad_norm": 2.234375, "learning_rate": 9.83786773543424e-06, "loss": 1.732332992553711, "step": 1010 }, { "epoch": 0.1751599192890568, "grad_norm": 2.34375, "learning_rate": 9.830210429287045e-06, "loss": 1.7011711120605468, "step": 1020 }, { "epoch": 0.17687717339973383, "grad_norm": 1.8359375, "learning_rate": 9.8223795685207e-06, "loss": 1.7169408798217773, "step": 1030 }, { "epoch": 0.17859442751041085, "grad_norm": 1.671875, "learning_rate": 9.81437543450639e-06, "loss": 1.7173925399780274, "step": 1040 }, { "epoch": 0.18031168162108788, "grad_norm": 2.0, "learning_rate": 9.806198314841204e-06, "loss": 1.7173860549926758, "step": 1050 }, { "epoch": 0.1820289357317649, "grad_norm": 1.984375, "learning_rate": 9.797848503337781e-06, "loss": 1.7255718231201171, "step": 1060 }, { "epoch": 0.18374618984244193, "grad_norm": 2.046875, "learning_rate": 9.789326300013767e-06, "loss": 1.7371936798095704, "step": 1070 }, { "epoch": 0.18546344395311895, "grad_norm": 2.09375, "learning_rate": 9.780632011081029e-06, "loss": 1.6944318771362306, "step": 1080 }, { "epoch": 0.187180698063796, "grad_norm": 1.9453125, "learning_rate": 9.77176594893465e-06, "loss": 1.7311203002929687, "step": 1090 }, { "epoch": 0.18889795217447303, "grad_norm": 1.9609375, "learning_rate": 9.762728432141717e-06, "loss": 1.7183172225952148, "step": 1100 }, { "epoch": 0.19061520628515005, "grad_norm": 2.21875, "learning_rate": 9.753519785429856e-06, "loss": 1.7383792877197266, "step": 1110 }, { "epoch": 0.19233246039582708, "grad_norm": 2.0, "learning_rate": 9.744140339675579e-06, "loss": 1.7086549758911134, "step": 1120 }, { "epoch": 0.1940497145065041, "grad_norm": 2.15625, "learning_rate": 9.734590431892389e-06, "loss": 1.7353195190429687, "step": 1130 }, { "epoch": 0.19576696861718113, "grad_norm": 1.8671875, "learning_rate": 9.72487040521867e-06, "loss": 1.7314397811889648, "step": 1140 }, { "epoch": 0.19748422272785815, "grad_norm": 1.8515625, "learning_rate": 9.714980608905361e-06, "loss": 1.720893669128418, "step": 1150 }, { "epoch": 0.19920147683853517, "grad_norm": 1.96875, "learning_rate": 9.704921398303408e-06, "loss": 1.691641616821289, "step": 1160 }, { "epoch": 0.2009187309492122, "grad_norm": 2.203125, "learning_rate": 9.694693134850987e-06, "loss": 1.707383918762207, "step": 1170 }, { "epoch": 0.20263598505988925, "grad_norm": 1.84375, "learning_rate": 9.684296186060532e-06, "loss": 1.7150285720825196, "step": 1180 }, { "epoch": 0.20435323917056628, "grad_norm": 1.7578125, "learning_rate": 9.67373092550551e-06, "loss": 1.730926513671875, "step": 1190 }, { "epoch": 0.2060704932812433, "grad_norm": 2.25, "learning_rate": 9.662997732807023e-06, "loss": 1.7099994659423827, "step": 1200 }, { "epoch": 0.20778774739192032, "grad_norm": 1.8828125, "learning_rate": 9.652096993620141e-06, "loss": 1.717348289489746, "step": 1210 }, { "epoch": 0.20950500150259735, "grad_norm": 1.84375, "learning_rate": 9.641029099620069e-06, "loss": 1.718988800048828, "step": 1220 }, { "epoch": 0.21122225561327437, "grad_norm": 1.9375, "learning_rate": 9.629794448488054e-06, "loss": 1.711029624938965, "step": 1230 }, { "epoch": 0.2129395097239514, "grad_norm": 2.03125, "learning_rate": 9.618393443897113e-06, "loss": 1.7028345108032226, "step": 1240 }, { "epoch": 0.21465676383462842, "grad_norm": 1.84375, "learning_rate": 9.606826495497517e-06, "loss": 1.7267234802246094, "step": 1250 }, { "epoch": 0.21637401794530545, "grad_norm": 2.203125, "learning_rate": 9.595094018902071e-06, "loss": 1.7090307235717774, "step": 1260 }, { "epoch": 0.21809127205598247, "grad_norm": 2.140625, "learning_rate": 9.583196435671192e-06, "loss": 1.717936897277832, "step": 1270 }, { "epoch": 0.21980852616665952, "grad_norm": 2.03125, "learning_rate": 9.57113417329775e-06, "loss": 1.6932069778442382, "step": 1280 }, { "epoch": 0.22152578027733655, "grad_norm": 1.8203125, "learning_rate": 9.558907665191716e-06, "loss": 1.7166713714599608, "step": 1290 }, { "epoch": 0.22324303438801357, "grad_norm": 1.9296875, "learning_rate": 9.546517350664582e-06, "loss": 1.6913949966430664, "step": 1300 }, { "epoch": 0.2249602884986906, "grad_norm": 2.015625, "learning_rate": 9.53396367491358e-06, "loss": 1.6907821655273438, "step": 1310 }, { "epoch": 0.22667754260936762, "grad_norm": 2.234375, "learning_rate": 9.521247089005688e-06, "loss": 1.722113037109375, "step": 1320 }, { "epoch": 0.22839479672004465, "grad_norm": 1.84375, "learning_rate": 9.508368049861419e-06, "loss": 1.700862503051758, "step": 1330 }, { "epoch": 0.23011205083072167, "grad_norm": 1.7578125, "learning_rate": 9.495327020238403e-06, "loss": 1.7247949600219727, "step": 1340 }, { "epoch": 0.2318293049413987, "grad_norm": 2.078125, "learning_rate": 9.482124468714759e-06, "loss": 1.7145797729492187, "step": 1350 }, { "epoch": 0.23354655905207572, "grad_norm": 2.21875, "learning_rate": 9.468760869672268e-06, "loss": 1.7040904998779296, "step": 1360 }, { "epoch": 0.23526381316275277, "grad_norm": 1.859375, "learning_rate": 9.455236703279312e-06, "loss": 1.7360145568847656, "step": 1370 }, { "epoch": 0.2369810672734298, "grad_norm": 2.015625, "learning_rate": 9.44155245547363e-06, "loss": 1.6907886505126952, "step": 1380 }, { "epoch": 0.23869832138410682, "grad_norm": 2.015625, "learning_rate": 9.427708617944867e-06, "loss": 1.7014581680297851, "step": 1390 }, { "epoch": 0.24041557549478385, "grad_norm": 2.125, "learning_rate": 9.413705688116883e-06, "loss": 1.7179489135742188, "step": 1400 }, { "epoch": 0.24213282960546087, "grad_norm": 1.8828125, "learning_rate": 9.399544169129907e-06, "loss": 1.675210189819336, "step": 1410 }, { "epoch": 0.2438500837161379, "grad_norm": 2.15625, "learning_rate": 9.385224569822433e-06, "loss": 1.7012422561645508, "step": 1420 }, { "epoch": 0.24556733782681492, "grad_norm": 1.671875, "learning_rate": 9.370747404712964e-06, "loss": 1.7253131866455078, "step": 1430 }, { "epoch": 0.24728459193749194, "grad_norm": 1.9453125, "learning_rate": 9.3561131939815e-06, "loss": 1.7034761428833007, "step": 1440 }, { "epoch": 0.24900184604816897, "grad_norm": 1.828125, "learning_rate": 9.34132246345086e-06, "loss": 1.696240234375, "step": 1450 }, { "epoch": 0.250719100158846, "grad_norm": 2.0625, "learning_rate": 9.326375744567788e-06, "loss": 1.687434768676758, "step": 1460 }, { "epoch": 0.25243635426952304, "grad_norm": 2.0625, "learning_rate": 9.31127357438386e-06, "loss": 1.7171453475952148, "step": 1470 }, { "epoch": 0.25415360838020007, "grad_norm": 2.09375, "learning_rate": 9.296016495536173e-06, "loss": 1.6642601013183593, "step": 1480 }, { "epoch": 0.2558708624908771, "grad_norm": 2.28125, "learning_rate": 9.280605056227867e-06, "loss": 1.7005868911743165, "step": 1490 }, { "epoch": 0.2575881166015541, "grad_norm": 1.96875, "learning_rate": 9.265039810208415e-06, "loss": 1.7188047409057616, "step": 1500 }, { "epoch": 0.2575881166015541, "eval_loss": 1.6991082429885864, "eval_runtime": 131.4609, "eval_samples_per_second": 36.155, "eval_steps_per_second": 4.526, "step": 1500 }, { "epoch": 0.25930537071223114, "grad_norm": 1.8984375, "learning_rate": 9.24932131675373e-06, "loss": 1.7226228713989258, "step": 1510 }, { "epoch": 0.26102262482290817, "grad_norm": 1.9765625, "learning_rate": 9.233450140646067e-06, "loss": 1.6944751739501953, "step": 1520 }, { "epoch": 0.2627398789335852, "grad_norm": 1.8828125, "learning_rate": 9.217426852153734e-06, "loss": 1.6786415100097656, "step": 1530 }, { "epoch": 0.2644571330442622, "grad_norm": 1.984375, "learning_rate": 9.201252027010598e-06, "loss": 1.7314750671386718, "step": 1540 }, { "epoch": 0.26617438715493924, "grad_norm": 2.140625, "learning_rate": 9.184926246395401e-06, "loss": 1.6889457702636719, "step": 1550 }, { "epoch": 0.26789164126561626, "grad_norm": 2.203125, "learning_rate": 9.168450096910876e-06, "loss": 1.7198213577270507, "step": 1560 }, { "epoch": 0.2696088953762933, "grad_norm": 2.0625, "learning_rate": 9.151824170562667e-06, "loss": 1.6850738525390625, "step": 1570 }, { "epoch": 0.2713261494869703, "grad_norm": 1.9765625, "learning_rate": 9.135049064738068e-06, "loss": 1.6993120193481446, "step": 1580 }, { "epoch": 0.27304340359764734, "grad_norm": 2.015625, "learning_rate": 9.118125382184542e-06, "loss": 1.7165555953979492, "step": 1590 }, { "epoch": 0.27476065770832436, "grad_norm": 1.8359375, "learning_rate": 9.101053730988078e-06, "loss": 1.700321578979492, "step": 1600 }, { "epoch": 0.27647791181900144, "grad_norm": 1.8515625, "learning_rate": 9.083834724551335e-06, "loss": 1.6941600799560548, "step": 1610 }, { "epoch": 0.27819516592967847, "grad_norm": 1.8515625, "learning_rate": 9.066468981571606e-06, "loss": 1.6965486526489257, "step": 1620 }, { "epoch": 0.2799124200403555, "grad_norm": 1.6953125, "learning_rate": 9.048957126018579e-06, "loss": 1.7205291748046876, "step": 1630 }, { "epoch": 0.2816296741510325, "grad_norm": 2.03125, "learning_rate": 9.031299787111926e-06, "loss": 1.7206954956054688, "step": 1640 }, { "epoch": 0.28334692826170954, "grad_norm": 1.796875, "learning_rate": 9.013497599298693e-06, "loss": 1.7027090072631836, "step": 1650 }, { "epoch": 0.28506418237238657, "grad_norm": 1.9765625, "learning_rate": 8.995551202230497e-06, "loss": 1.701325035095215, "step": 1660 }, { "epoch": 0.2867814364830636, "grad_norm": 1.984375, "learning_rate": 8.977461240740555e-06, "loss": 1.7265708923339844, "step": 1670 }, { "epoch": 0.2884986905937406, "grad_norm": 1.7265625, "learning_rate": 8.959228364820498e-06, "loss": 1.6997587203979492, "step": 1680 }, { "epoch": 0.29021594470441764, "grad_norm": 2.0625, "learning_rate": 8.940853229597031e-06, "loss": 1.728235626220703, "step": 1690 }, { "epoch": 0.29193319881509466, "grad_norm": 1.6484375, "learning_rate": 8.922336495308389e-06, "loss": 1.7140905380249023, "step": 1700 }, { "epoch": 0.2936504529257717, "grad_norm": 1.7578125, "learning_rate": 8.903678827280607e-06, "loss": 1.6867521286010743, "step": 1710 }, { "epoch": 0.2953677070364487, "grad_norm": 1.921875, "learning_rate": 8.884880895903623e-06, "loss": 1.6819787979125977, "step": 1720 }, { "epoch": 0.29708496114712574, "grad_norm": 1.890625, "learning_rate": 8.865943376607186e-06, "loss": 1.7118709564208985, "step": 1730 }, { "epoch": 0.29880221525780276, "grad_norm": 1.890625, "learning_rate": 8.846866949836593e-06, "loss": 1.6928745269775392, "step": 1740 }, { "epoch": 0.3005194693684798, "grad_norm": 1.9140625, "learning_rate": 8.827652301028224e-06, "loss": 1.7110282897949218, "step": 1750 }, { "epoch": 0.3022367234791568, "grad_norm": 2.296875, "learning_rate": 8.808300120584937e-06, "loss": 1.706978988647461, "step": 1760 }, { "epoch": 0.30395397758983383, "grad_norm": 1.8515625, "learning_rate": 8.788811103851238e-06, "loss": 1.7176849365234375, "step": 1770 }, { "epoch": 0.30567123170051086, "grad_norm": 2.015625, "learning_rate": 8.769185951088314e-06, "loss": 1.6671594619750976, "step": 1780 }, { "epoch": 0.3073884858111879, "grad_norm": 1.859375, "learning_rate": 8.749425367448862e-06, "loss": 1.6910730361938477, "step": 1790 }, { "epoch": 0.30910573992186496, "grad_norm": 1.671875, "learning_rate": 8.729530062951755e-06, "loss": 1.6639533996582032, "step": 1800 }, { "epoch": 0.310822994032542, "grad_norm": 1.9296875, "learning_rate": 8.709500752456532e-06, "loss": 1.7049299240112306, "step": 1810 }, { "epoch": 0.312540248143219, "grad_norm": 2.015625, "learning_rate": 8.689338155637707e-06, "loss": 1.7183841705322265, "step": 1820 }, { "epoch": 0.31425750225389604, "grad_norm": 2.140625, "learning_rate": 8.66904299695892e-06, "loss": 1.7136545181274414, "step": 1830 }, { "epoch": 0.31597475636457306, "grad_norm": 2.046875, "learning_rate": 8.648616005646893e-06, "loss": 1.713533592224121, "step": 1840 }, { "epoch": 0.3176920104752501, "grad_norm": 2.015625, "learning_rate": 8.62805791566524e-06, "loss": 1.7070768356323243, "step": 1850 }, { "epoch": 0.3194092645859271, "grad_norm": 1.9375, "learning_rate": 8.607369465688091e-06, "loss": 1.6905519485473632, "step": 1860 }, { "epoch": 0.32112651869660414, "grad_norm": 2.390625, "learning_rate": 8.586551399073547e-06, "loss": 1.6916780471801758, "step": 1870 }, { "epoch": 0.32284377280728116, "grad_norm": 1.875, "learning_rate": 8.565604463836972e-06, "loss": 1.7060581207275392, "step": 1880 }, { "epoch": 0.3245610269179582, "grad_norm": 1.9140625, "learning_rate": 8.544529412624121e-06, "loss": 1.689253807067871, "step": 1890 }, { "epoch": 0.3262782810286352, "grad_norm": 1.9765625, "learning_rate": 8.523327002684092e-06, "loss": 1.6860944747924804, "step": 1900 }, { "epoch": 0.32799553513931223, "grad_norm": 2.0625, "learning_rate": 8.501997995842116e-06, "loss": 1.6716680526733398, "step": 1910 }, { "epoch": 0.32971278924998926, "grad_norm": 2.171875, "learning_rate": 8.480543158472186e-06, "loss": 1.6954851150512695, "step": 1920 }, { "epoch": 0.3314300433606663, "grad_norm": 2.078125, "learning_rate": 8.458963261469523e-06, "loss": 1.6969093322753905, "step": 1930 }, { "epoch": 0.3331472974713433, "grad_norm": 2.046875, "learning_rate": 8.437259080222874e-06, "loss": 1.6771305084228516, "step": 1940 }, { "epoch": 0.33486455158202033, "grad_norm": 2.0625, "learning_rate": 8.415431394586648e-06, "loss": 1.6757757186889648, "step": 1950 }, { "epoch": 0.33658180569269736, "grad_norm": 2.359375, "learning_rate": 8.3934809888529e-06, "loss": 1.6645269393920898, "step": 1960 }, { "epoch": 0.3382990598033744, "grad_norm": 1.9765625, "learning_rate": 8.371408651723155e-06, "loss": 1.6717287063598634, "step": 1970 }, { "epoch": 0.3400163139140514, "grad_norm": 1.9609375, "learning_rate": 8.349215176280052e-06, "loss": 1.7127954483032226, "step": 1980 }, { "epoch": 0.3417335680247285, "grad_norm": 2.046875, "learning_rate": 8.32690135995887e-06, "loss": 1.688150978088379, "step": 1990 }, { "epoch": 0.3434508221354055, "grad_norm": 1.8125, "learning_rate": 8.304468004518855e-06, "loss": 1.684065055847168, "step": 2000 }, { "epoch": 0.3434508221354055, "eval_loss": 1.6886166334152222, "eval_runtime": 131.9148, "eval_samples_per_second": 36.031, "eval_steps_per_second": 4.51, "step": 2000 }, { "epoch": 0.34516807624608253, "grad_norm": 2.28125, "learning_rate": 8.281915916014428e-06, "loss": 1.702587890625, "step": 2010 }, { "epoch": 0.34688533035675956, "grad_norm": 1.9453125, "learning_rate": 8.259245904766215e-06, "loss": 1.6986043930053711, "step": 2020 }, { "epoch": 0.3486025844674366, "grad_norm": 1.875, "learning_rate": 8.236458785331928e-06, "loss": 1.6774551391601562, "step": 2030 }, { "epoch": 0.3503198385781136, "grad_norm": 1.7890625, "learning_rate": 8.213555376477108e-06, "loss": 1.6879871368408204, "step": 2040 }, { "epoch": 0.35203709268879063, "grad_norm": 1.796875, "learning_rate": 8.190536501145687e-06, "loss": 1.6949779510498046, "step": 2050 }, { "epoch": 0.35375434679946766, "grad_norm": 1.953125, "learning_rate": 8.167402986430446e-06, "loss": 1.6962162017822267, "step": 2060 }, { "epoch": 0.3554716009101447, "grad_norm": 1.7421875, "learning_rate": 8.144155663543272e-06, "loss": 1.662078285217285, "step": 2070 }, { "epoch": 0.3571888550208217, "grad_norm": 1.9375, "learning_rate": 8.120795367785304e-06, "loss": 1.6930509567260743, "step": 2080 }, { "epoch": 0.35890610913149873, "grad_norm": 1.9609375, "learning_rate": 8.097322938516913e-06, "loss": 1.6991004943847656, "step": 2090 }, { "epoch": 0.36062336324217575, "grad_norm": 2.25, "learning_rate": 8.073739219127554e-06, "loss": 1.6764997482299804, "step": 2100 }, { "epoch": 0.3623406173528528, "grad_norm": 2.578125, "learning_rate": 8.050045057005448e-06, "loss": 1.7155282974243165, "step": 2110 }, { "epoch": 0.3640578714635298, "grad_norm": 2.046875, "learning_rate": 8.026241303507148e-06, "loss": 1.714227294921875, "step": 2120 }, { "epoch": 0.3657751255742068, "grad_norm": 2.09375, "learning_rate": 8.002328813926932e-06, "loss": 1.7099868774414062, "step": 2130 }, { "epoch": 0.36749237968488385, "grad_norm": 2.140625, "learning_rate": 7.978308447466094e-06, "loss": 1.6800619125366212, "step": 2140 }, { "epoch": 0.3692096337955609, "grad_norm": 2.09375, "learning_rate": 7.954181067202051e-06, "loss": 1.6670686721801757, "step": 2150 }, { "epoch": 0.3709268879062379, "grad_norm": 1.9140625, "learning_rate": 7.929947540057343e-06, "loss": 1.7205642700195312, "step": 2160 }, { "epoch": 0.3726441420169149, "grad_norm": 2.140625, "learning_rate": 7.905608736768481e-06, "loss": 1.6482656478881836, "step": 2170 }, { "epoch": 0.374361396127592, "grad_norm": 1.9765625, "learning_rate": 7.88116553185466e-06, "loss": 1.7352182388305664, "step": 2180 }, { "epoch": 0.37607865023826903, "grad_norm": 1.9296875, "learning_rate": 7.856618803586335e-06, "loss": 1.667134666442871, "step": 2190 }, { "epoch": 0.37779590434894605, "grad_norm": 1.640625, "learning_rate": 7.831969433953669e-06, "loss": 1.6808473587036132, "step": 2200 }, { "epoch": 0.3795131584596231, "grad_norm": 2.125, "learning_rate": 7.807218308634836e-06, "loss": 1.6947784423828125, "step": 2210 }, { "epoch": 0.3812304125703001, "grad_norm": 1.9453125, "learning_rate": 7.782366316964203e-06, "loss": 1.683536911010742, "step": 2220 }, { "epoch": 0.38294766668097713, "grad_norm": 1.9921875, "learning_rate": 7.757414351900371e-06, "loss": 1.6778770446777345, "step": 2230 }, { "epoch": 0.38466492079165415, "grad_norm": 1.9375, "learning_rate": 7.732363309994092e-06, "loss": 1.6829193115234375, "step": 2240 }, { "epoch": 0.3863821749023312, "grad_norm": 2.109375, "learning_rate": 7.707214091356054e-06, "loss": 1.681058692932129, "step": 2250 }, { "epoch": 0.3880994290130082, "grad_norm": 1.9921875, "learning_rate": 7.681967599624544e-06, "loss": 1.6540367126464843, "step": 2260 }, { "epoch": 0.3898166831236852, "grad_norm": 1.6796875, "learning_rate": 7.656624741932968e-06, "loss": 1.678452491760254, "step": 2270 }, { "epoch": 0.39153393723436225, "grad_norm": 2.0, "learning_rate": 7.631186428877271e-06, "loss": 1.6885982513427735, "step": 2280 }, { "epoch": 0.3932511913450393, "grad_norm": 1.8359375, "learning_rate": 7.605653574483207e-06, "loss": 1.6559461593627929, "step": 2290 }, { "epoch": 0.3949684454557163, "grad_norm": 1.8515625, "learning_rate": 7.580027096173499e-06, "loss": 1.70489444732666, "step": 2300 }, { "epoch": 0.3966856995663933, "grad_norm": 1.90625, "learning_rate": 7.554307914734886e-06, "loss": 1.6976411819458008, "step": 2310 }, { "epoch": 0.39840295367707035, "grad_norm": 2.03125, "learning_rate": 7.52849695428502e-06, "loss": 1.6676952362060546, "step": 2320 }, { "epoch": 0.4001202077877474, "grad_norm": 2.15625, "learning_rate": 7.502595142239275e-06, "loss": 1.684074592590332, "step": 2330 }, { "epoch": 0.4018374618984244, "grad_norm": 2.140625, "learning_rate": 7.476603409277422e-06, "loss": 1.6669532775878906, "step": 2340 }, { "epoch": 0.4035547160091014, "grad_norm": 2.125, "learning_rate": 7.450522689310182e-06, "loss": 1.6743785858154296, "step": 2350 }, { "epoch": 0.4052719701197785, "grad_norm": 1.9921875, "learning_rate": 7.424353919445679e-06, "loss": 1.6569658279418946, "step": 2360 }, { "epoch": 0.4069892242304555, "grad_norm": 1.921875, "learning_rate": 7.398098039955758e-06, "loss": 1.708488655090332, "step": 2370 }, { "epoch": 0.40870647834113255, "grad_norm": 2.0, "learning_rate": 7.371755994242209e-06, "loss": 1.6728775024414062, "step": 2380 }, { "epoch": 0.4104237324518096, "grad_norm": 1.8671875, "learning_rate": 7.345328728802869e-06, "loss": 1.6840057373046875, "step": 2390 }, { "epoch": 0.4121409865624866, "grad_norm": 1.8359375, "learning_rate": 7.3188171931976095e-06, "loss": 1.6793525695800782, "step": 2400 }, { "epoch": 0.4138582406731636, "grad_norm": 2.140625, "learning_rate": 7.292222340014212e-06, "loss": 1.668372917175293, "step": 2410 }, { "epoch": 0.41557549478384065, "grad_norm": 1.9296875, "learning_rate": 7.265545124834159e-06, "loss": 1.682711410522461, "step": 2420 }, { "epoch": 0.4172927488945177, "grad_norm": 2.265625, "learning_rate": 7.238786506198279e-06, "loss": 1.6730918884277344, "step": 2430 }, { "epoch": 0.4190100030051947, "grad_norm": 1.90625, "learning_rate": 7.2119474455723185e-06, "loss": 1.7171833038330078, "step": 2440 }, { "epoch": 0.4207272571158717, "grad_norm": 1.7734375, "learning_rate": 7.1850289073123855e-06, "loss": 1.657244873046875, "step": 2450 }, { "epoch": 0.42244451122654875, "grad_norm": 1.828125, "learning_rate": 7.15803185863031e-06, "loss": 1.7172735214233399, "step": 2460 }, { "epoch": 0.42416176533722577, "grad_norm": 2.109375, "learning_rate": 7.1309572695588815e-06, "loss": 1.6909856796264648, "step": 2470 }, { "epoch": 0.4258790194479028, "grad_norm": 1.9375, "learning_rate": 7.103806112917e-06, "loss": 1.6823898315429688, "step": 2480 }, { "epoch": 0.4275962735585798, "grad_norm": 2.15625, "learning_rate": 7.07657936427472e-06, "loss": 1.7273609161376953, "step": 2490 }, { "epoch": 0.42931352766925684, "grad_norm": 1.734375, "learning_rate": 7.049278001918197e-06, "loss": 1.6918079376220703, "step": 2500 }, { "epoch": 0.42931352766925684, "eval_loss": 1.682664394378662, "eval_runtime": 132.0379, "eval_samples_per_second": 35.997, "eval_steps_per_second": 4.506, "step": 2500 }, { "epoch": 0.43103078177993387, "grad_norm": 2.078125, "learning_rate": 7.021903006814538e-06, "loss": 1.683829116821289, "step": 2510 }, { "epoch": 0.4327480358906109, "grad_norm": 1.9296875, "learning_rate": 6.994455362576548e-06, "loss": 1.6695667266845704, "step": 2520 }, { "epoch": 0.4344652900012879, "grad_norm": 2.046875, "learning_rate": 6.966936055427404e-06, "loss": 1.7198301315307618, "step": 2530 }, { "epoch": 0.43618254411196494, "grad_norm": 1.7578125, "learning_rate": 6.939346074165194e-06, "loss": 1.6716541290283202, "step": 2540 }, { "epoch": 0.437899798222642, "grad_norm": 2.1875, "learning_rate": 6.911686410127414e-06, "loss": 1.6903951644897461, "step": 2550 }, { "epoch": 0.43961705233331905, "grad_norm": 2.078125, "learning_rate": 6.883958057155331e-06, "loss": 1.6649398803710938, "step": 2560 }, { "epoch": 0.44133430644399607, "grad_norm": 1.90625, "learning_rate": 6.8561620115582795e-06, "loss": 1.6970430374145509, "step": 2570 }, { "epoch": 0.4430515605546731, "grad_norm": 1.984375, "learning_rate": 6.828299272077864e-06, "loss": 1.6921920776367188, "step": 2580 }, { "epoch": 0.4447688146653501, "grad_norm": 2.09375, "learning_rate": 6.800370839852068e-06, "loss": 1.6477432250976562, "step": 2590 }, { "epoch": 0.44648606877602715, "grad_norm": 2.109375, "learning_rate": 6.772377718379288e-06, "loss": 1.6775671005249024, "step": 2600 }, { "epoch": 0.44820332288670417, "grad_norm": 2.109375, "learning_rate": 6.744320913482275e-06, "loss": 1.6973007202148438, "step": 2610 }, { "epoch": 0.4499205769973812, "grad_norm": 1.953125, "learning_rate": 6.7162014332719905e-06, "loss": 1.6901512145996094, "step": 2620 }, { "epoch": 0.4516378311080582, "grad_norm": 2.203125, "learning_rate": 6.688020288111392e-06, "loss": 1.6537458419799804, "step": 2630 }, { "epoch": 0.45335508521873524, "grad_norm": 2.046875, "learning_rate": 6.659778490579116e-06, "loss": 1.6901357650756836, "step": 2640 }, { "epoch": 0.45507233932941227, "grad_norm": 1.6953125, "learning_rate": 6.631477055433113e-06, "loss": 1.685549545288086, "step": 2650 }, { "epoch": 0.4567895934400893, "grad_norm": 2.0625, "learning_rate": 6.6031169995741705e-06, "loss": 1.7412605285644531, "step": 2660 }, { "epoch": 0.4585068475507663, "grad_norm": 1.7890625, "learning_rate": 6.574699342009384e-06, "loss": 1.6907888412475587, "step": 2670 }, { "epoch": 0.46022410166144334, "grad_norm": 2.234375, "learning_rate": 6.546225103815538e-06, "loss": 1.7110357284545898, "step": 2680 }, { "epoch": 0.46194135577212037, "grad_norm": 2.109375, "learning_rate": 6.517695308102417e-06, "loss": 1.6935695648193358, "step": 2690 }, { "epoch": 0.4636586098827974, "grad_norm": 2.0625, "learning_rate": 6.489110979976053e-06, "loss": 1.6636667251586914, "step": 2700 }, { "epoch": 0.4653758639934744, "grad_norm": 1.9765625, "learning_rate": 6.4604731465018814e-06, "loss": 1.6972545623779296, "step": 2710 }, { "epoch": 0.46709311810415144, "grad_norm": 1.765625, "learning_rate": 6.431782836667841e-06, "loss": 1.6882843017578124, "step": 2720 }, { "epoch": 0.46881037221482846, "grad_norm": 1.90625, "learning_rate": 6.403041081347408e-06, "loss": 1.686298942565918, "step": 2730 }, { "epoch": 0.47052762632550554, "grad_norm": 2.203125, "learning_rate": 6.374248913262541e-06, "loss": 1.6878038406372071, "step": 2740 }, { "epoch": 0.47224488043618257, "grad_norm": 1.6875, "learning_rate": 6.345407366946591e-06, "loss": 1.6685100555419923, "step": 2750 }, { "epoch": 0.4739621345468596, "grad_norm": 1.921875, "learning_rate": 6.316517478707118e-06, "loss": 1.6747262954711915, "step": 2760 }, { "epoch": 0.4756793886575366, "grad_norm": 1.9921875, "learning_rate": 6.287580286588658e-06, "loss": 1.6812864303588868, "step": 2770 }, { "epoch": 0.47739664276821364, "grad_norm": 2.0625, "learning_rate": 6.258596830335429e-06, "loss": 1.6670236587524414, "step": 2780 }, { "epoch": 0.47911389687889067, "grad_norm": 2.71875, "learning_rate": 6.2295681513539656e-06, "loss": 1.6908716201782226, "step": 2790 }, { "epoch": 0.4808311509895677, "grad_norm": 2.0, "learning_rate": 6.200495292675706e-06, "loss": 1.6669652938842774, "step": 2800 }, { "epoch": 0.4825484051002447, "grad_norm": 2.015625, "learning_rate": 6.171379298919511e-06, "loss": 1.6927835464477539, "step": 2810 }, { "epoch": 0.48426565921092174, "grad_norm": 2.234375, "learning_rate": 6.1422212162541295e-06, "loss": 1.6797420501708984, "step": 2820 }, { "epoch": 0.48598291332159876, "grad_norm": 1.8359375, "learning_rate": 6.113022092360613e-06, "loss": 1.6955087661743165, "step": 2830 }, { "epoch": 0.4877001674322758, "grad_norm": 2.171875, "learning_rate": 6.083782976394664e-06, "loss": 1.6834836959838868, "step": 2840 }, { "epoch": 0.4894174215429528, "grad_norm": 2.015625, "learning_rate": 6.054504918948948e-06, "loss": 1.659806251525879, "step": 2850 }, { "epoch": 0.49113467565362984, "grad_norm": 2.21875, "learning_rate": 6.025188972015332e-06, "loss": 1.7039405822753906, "step": 2860 }, { "epoch": 0.49285192976430686, "grad_norm": 2.203125, "learning_rate": 5.995836188947102e-06, "loss": 1.6875274658203125, "step": 2870 }, { "epoch": 0.4945691838749839, "grad_norm": 1.9453125, "learning_rate": 5.9664476244210975e-06, "loss": 1.697869110107422, "step": 2880 }, { "epoch": 0.4962864379856609, "grad_norm": 2.0625, "learning_rate": 5.937024334399829e-06, "loss": 1.6917144775390625, "step": 2890 }, { "epoch": 0.49800369209633794, "grad_norm": 1.9140625, "learning_rate": 5.907567376093531e-06, "loss": 1.7006925582885741, "step": 2900 }, { "epoch": 0.49972094620701496, "grad_norm": 1.953125, "learning_rate": 5.8780778079221726e-06, "loss": 1.6975530624389648, "step": 2910 }, { "epoch": 0.501438200317692, "grad_norm": 1.890625, "learning_rate": 5.84855668947743e-06, "loss": 1.6771890640258789, "step": 2920 }, { "epoch": 0.5031554544283691, "grad_norm": 1.9921875, "learning_rate": 5.819005081484619e-06, "loss": 1.6866941452026367, "step": 2930 }, { "epoch": 0.5048727085390461, "grad_norm": 1.765625, "learning_rate": 5.789424045764571e-06, "loss": 1.7066801071166993, "step": 2940 }, { "epoch": 0.5065899626497231, "grad_norm": 1.796875, "learning_rate": 5.759814645195495e-06, "loss": 1.6855461120605468, "step": 2950 }, { "epoch": 0.5083072167604001, "grad_norm": 2.5, "learning_rate": 5.730177943674771e-06, "loss": 1.6749443054199218, "step": 2960 }, { "epoch": 0.5100244708710772, "grad_norm": 1.9453125, "learning_rate": 5.700515006080737e-06, "loss": 1.6849287033081055, "step": 2970 }, { "epoch": 0.5117417249817542, "grad_norm": 2.109375, "learning_rate": 5.67082689823442e-06, "loss": 1.6899866104125976, "step": 2980 }, { "epoch": 0.5134589790924312, "grad_norm": 1.90625, "learning_rate": 5.641114686861238e-06, "loss": 1.6824975967407227, "step": 2990 }, { "epoch": 0.5151762332031082, "grad_norm": 2.078125, "learning_rate": 5.611379439552678e-06, "loss": 1.6941234588623046, "step": 3000 }, { "epoch": 0.5151762332031082, "eval_loss": 1.6793590784072876, "eval_runtime": 131.8596, "eval_samples_per_second": 36.046, "eval_steps_per_second": 4.512, "step": 3000 }, { "epoch": 0.5168934873137853, "grad_norm": 1.8828125, "learning_rate": 5.581622224727931e-06, "loss": 1.6599224090576172, "step": 3010 }, { "epoch": 0.5186107414244623, "grad_norm": 2.078125, "learning_rate": 5.551844111595506e-06, "loss": 1.7043123245239258, "step": 3020 }, { "epoch": 0.5203279955351393, "grad_norm": 1.984375, "learning_rate": 5.522046170114809e-06, "loss": 1.6758649826049805, "step": 3030 }, { "epoch": 0.5220452496458163, "grad_norm": 1.84375, "learning_rate": 5.4922294709577004e-06, "loss": 1.6937856674194336, "step": 3040 }, { "epoch": 0.5237625037564934, "grad_norm": 2.28125, "learning_rate": 5.462395085470024e-06, "loss": 1.6940069198608398, "step": 3050 }, { "epoch": 0.5254797578671704, "grad_norm": 2.125, "learning_rate": 5.432544085633111e-06, "loss": 1.6672548294067382, "step": 3060 }, { "epoch": 0.5271970119778474, "grad_norm": 2.03125, "learning_rate": 5.402677544025264e-06, "loss": 1.6675827026367187, "step": 3070 }, { "epoch": 0.5289142660885244, "grad_norm": 1.9296875, "learning_rate": 5.372796533783223e-06, "loss": 1.6944459915161132, "step": 3080 }, { "epoch": 0.5306315201992015, "grad_norm": 2.171875, "learning_rate": 5.342902128563593e-06, "loss": 1.6960567474365233, "step": 3090 }, { "epoch": 0.5323487743098785, "grad_norm": 2.46875, "learning_rate": 5.312995402504281e-06, "loss": 1.6805280685424804, "step": 3100 }, { "epoch": 0.5340660284205555, "grad_norm": 2.015625, "learning_rate": 5.283077430185893e-06, "loss": 1.7026758193969727, "step": 3110 }, { "epoch": 0.5357832825312325, "grad_norm": 1.7890625, "learning_rate": 5.2531492865931255e-06, "loss": 1.6845787048339844, "step": 3120 }, { "epoch": 0.5375005366419096, "grad_norm": 2.046875, "learning_rate": 5.223212047076142e-06, "loss": 1.7107906341552734, "step": 3130 }, { "epoch": 0.5392177907525866, "grad_norm": 2.03125, "learning_rate": 5.193266787311926e-06, "loss": 1.6671693801879883, "step": 3140 }, { "epoch": 0.5409350448632636, "grad_norm": 1.8984375, "learning_rate": 5.1633145832656425e-06, "loss": 1.6554080963134765, "step": 3150 }, { "epoch": 0.5426522989739406, "grad_norm": 2.078125, "learning_rate": 5.13335651115197e-06, "loss": 1.6992469787597657, "step": 3160 }, { "epoch": 0.5443695530846177, "grad_norm": 2.140625, "learning_rate": 5.103393647396433e-06, "loss": 1.6707094192504883, "step": 3170 }, { "epoch": 0.5460868071952947, "grad_norm": 1.9453125, "learning_rate": 5.073427068596728e-06, "loss": 1.6498741149902343, "step": 3180 }, { "epoch": 0.5478040613059717, "grad_norm": 1.7265625, "learning_rate": 5.043457851484029e-06, "loss": 1.7025842666625977, "step": 3190 }, { "epoch": 0.5495213154166487, "grad_norm": 1.984375, "learning_rate": 5.013487072884317e-06, "loss": 1.683099365234375, "step": 3200 }, { "epoch": 0.5512385695273259, "grad_norm": 2.03125, "learning_rate": 4.9835158096796735e-06, "loss": 1.7064334869384765, "step": 3210 }, { "epoch": 0.5529558236380029, "grad_norm": 2.0625, "learning_rate": 4.953545138769591e-06, "loss": 1.6625755310058594, "step": 3220 }, { "epoch": 0.5546730777486799, "grad_norm": 1.9609375, "learning_rate": 4.923576137032284e-06, "loss": 1.6901166915893555, "step": 3230 }, { "epoch": 0.5563903318593569, "grad_norm": 1.9296875, "learning_rate": 4.893609881285991e-06, "loss": 1.6619853973388672, "step": 3240 }, { "epoch": 0.558107585970034, "grad_norm": 1.921875, "learning_rate": 4.8636474482502835e-06, "loss": 1.6862195968627929, "step": 3250 }, { "epoch": 0.559824840080711, "grad_norm": 2.125, "learning_rate": 4.833689914507376e-06, "loss": 1.6763399124145508, "step": 3260 }, { "epoch": 0.561542094191388, "grad_norm": 1.765625, "learning_rate": 4.803738356463453e-06, "loss": 1.6811893463134766, "step": 3270 }, { "epoch": 0.563259348302065, "grad_norm": 1.984375, "learning_rate": 4.77379385030998e-06, "loss": 1.6773794174194336, "step": 3280 }, { "epoch": 0.5649766024127421, "grad_norm": 1.8984375, "learning_rate": 4.7438574719850426e-06, "loss": 1.7063253402709961, "step": 3290 }, { "epoch": 0.5666938565234191, "grad_norm": 1.9765625, "learning_rate": 4.713930297134683e-06, "loss": 1.6958925247192382, "step": 3300 }, { "epoch": 0.5684111106340961, "grad_norm": 1.8125, "learning_rate": 4.684013401074257e-06, "loss": 1.6969947814941406, "step": 3310 }, { "epoch": 0.5701283647447731, "grad_norm": 2.125, "learning_rate": 4.654107858749788e-06, "loss": 1.6974805831909179, "step": 3320 }, { "epoch": 0.5718456188554502, "grad_norm": 2.28125, "learning_rate": 4.624214744699349e-06, "loss": 1.671217918395996, "step": 3330 }, { "epoch": 0.5735628729661272, "grad_norm": 2.0625, "learning_rate": 4.594335133014455e-06, "loss": 1.6807682037353515, "step": 3340 }, { "epoch": 0.5752801270768042, "grad_norm": 2.0, "learning_rate": 4.564470097301462e-06, "loss": 1.6612432479858399, "step": 3350 }, { "epoch": 0.5769973811874812, "grad_norm": 2.078125, "learning_rate": 4.534620710642997e-06, "loss": 1.687340545654297, "step": 3360 }, { "epoch": 0.5787146352981583, "grad_norm": 1.8203125, "learning_rate": 4.5047880455594e-06, "loss": 1.7067007064819335, "step": 3370 }, { "epoch": 0.5804318894088353, "grad_norm": 1.953125, "learning_rate": 4.474973173970189e-06, "loss": 1.6687971115112306, "step": 3380 }, { "epoch": 0.5821491435195123, "grad_norm": 2.140625, "learning_rate": 4.44517716715554e-06, "loss": 1.6910263061523438, "step": 3390 }, { "epoch": 0.5838663976301893, "grad_norm": 1.9453125, "learning_rate": 4.415401095717799e-06, "loss": 1.6940975189208984, "step": 3400 }, { "epoch": 0.5855836517408664, "grad_norm": 1.8828125, "learning_rate": 4.38564602954301e-06, "loss": 1.6746652603149415, "step": 3410 }, { "epoch": 0.5873009058515434, "grad_norm": 2.140625, "learning_rate": 4.355913037762481e-06, "loss": 1.694173240661621, "step": 3420 }, { "epoch": 0.5890181599622204, "grad_norm": 2.046875, "learning_rate": 4.326203188714359e-06, "loss": 1.668067741394043, "step": 3430 }, { "epoch": 0.5907354140728974, "grad_norm": 2.34375, "learning_rate": 4.296517549905247e-06, "loss": 1.672216796875, "step": 3440 }, { "epoch": 0.5924526681835744, "grad_norm": 1.9609375, "learning_rate": 4.266857187971852e-06, "loss": 1.6901241302490235, "step": 3450 }, { "epoch": 0.5941699222942515, "grad_norm": 2.109375, "learning_rate": 4.237223168642653e-06, "loss": 1.6794466018676757, "step": 3460 }, { "epoch": 0.5958871764049285, "grad_norm": 1.8671875, "learning_rate": 4.207616556699615e-06, "loss": 1.7052120208740233, "step": 3470 }, { "epoch": 0.5976044305156055, "grad_norm": 2.046875, "learning_rate": 4.178038415939921e-06, "loss": 1.696548080444336, "step": 3480 }, { "epoch": 0.5993216846262825, "grad_norm": 2.125, "learning_rate": 4.148489809137754e-06, "loss": 1.6758693695068358, "step": 3490 }, { "epoch": 0.6010389387369596, "grad_norm": 1.9765625, "learning_rate": 4.118971798006118e-06, "loss": 1.6623727798461914, "step": 3500 }, { "epoch": 0.6010389387369596, "eval_loss": 1.6777236461639404, "eval_runtime": 132.0772, "eval_samples_per_second": 35.987, "eval_steps_per_second": 4.505, "step": 3500 }, { "epoch": 0.6027561928476366, "grad_norm": 1.953125, "learning_rate": 4.089485443158674e-06, "loss": 1.690532112121582, "step": 3510 }, { "epoch": 0.6044734469583136, "grad_norm": 1.84375, "learning_rate": 4.060031804071643e-06, "loss": 1.6979921340942383, "step": 3520 }, { "epoch": 0.6061907010689906, "grad_norm": 1.84375, "learning_rate": 4.030611939045731e-06, "loss": 1.6842302322387694, "step": 3530 }, { "epoch": 0.6079079551796677, "grad_norm": 2.015625, "learning_rate": 4.001226905168108e-06, "loss": 1.6710676193237304, "step": 3540 }, { "epoch": 0.6096252092903447, "grad_norm": 2.078125, "learning_rate": 3.971877758274423e-06, "loss": 1.7161846160888672, "step": 3550 }, { "epoch": 0.6113424634010217, "grad_norm": 2.0625, "learning_rate": 3.9425655529108685e-06, "loss": 1.6849218368530274, "step": 3560 }, { "epoch": 0.6130597175116987, "grad_norm": 2.0625, "learning_rate": 3.913291342296282e-06, "loss": 1.6851036071777343, "step": 3570 }, { "epoch": 0.6147769716223758, "grad_norm": 1.9296875, "learning_rate": 3.8840561782843226e-06, "loss": 1.6484107971191406, "step": 3580 }, { "epoch": 0.6164942257330529, "grad_norm": 1.8203125, "learning_rate": 3.854861111325647e-06, "loss": 1.669612503051758, "step": 3590 }, { "epoch": 0.6182114798437299, "grad_norm": 1.8125, "learning_rate": 3.825707190430196e-06, "loss": 1.7332313537597657, "step": 3600 }, { "epoch": 0.619928733954407, "grad_norm": 2.03125, "learning_rate": 3.79659546312948e-06, "loss": 1.719141387939453, "step": 3610 }, { "epoch": 0.621645988065084, "grad_norm": 1.84375, "learning_rate": 3.76752697543895e-06, "loss": 1.6692520141601563, "step": 3620 }, { "epoch": 0.623363242175761, "grad_norm": 1.8359375, "learning_rate": 3.7385027718204135e-06, "loss": 1.6629404067993163, "step": 3630 }, { "epoch": 0.625080496286438, "grad_norm": 1.96875, "learning_rate": 3.709523895144501e-06, "loss": 1.6516199111938477, "step": 3640 }, { "epoch": 0.626797750397115, "grad_norm": 1.8125, "learning_rate": 3.6805913866532033e-06, "loss": 1.6700164794921875, "step": 3650 }, { "epoch": 0.6285150045077921, "grad_norm": 1.890625, "learning_rate": 3.651706285922446e-06, "loss": 1.6376646041870118, "step": 3660 }, { "epoch": 0.6302322586184691, "grad_norm": 1.8671875, "learning_rate": 3.6228696308247456e-06, "loss": 1.7027305603027343, "step": 3670 }, { "epoch": 0.6319495127291461, "grad_norm": 2.109375, "learning_rate": 3.5940824574919197e-06, "loss": 1.686671829223633, "step": 3680 }, { "epoch": 0.6336667668398231, "grad_norm": 1.890625, "learning_rate": 3.565345800277845e-06, "loss": 1.662599754333496, "step": 3690 }, { "epoch": 0.6353840209505002, "grad_norm": 2.078125, "learning_rate": 3.5366606917213085e-06, "loss": 1.6606752395629882, "step": 3700 }, { "epoch": 0.6371012750611772, "grad_norm": 1.84375, "learning_rate": 3.5080281625088923e-06, "loss": 1.6924787521362306, "step": 3710 }, { "epoch": 0.6388185291718542, "grad_norm": 2.140625, "learning_rate": 3.479449241437948e-06, "loss": 1.662969207763672, "step": 3720 }, { "epoch": 0.6405357832825312, "grad_norm": 2.03125, "learning_rate": 3.450924955379635e-06, "loss": 1.6973854064941407, "step": 3730 }, { "epoch": 0.6422530373932083, "grad_norm": 2.078125, "learning_rate": 3.422456329242008e-06, "loss": 1.6661312103271484, "step": 3740 }, { "epoch": 0.6439702915038853, "grad_norm": 1.875, "learning_rate": 3.394044385933214e-06, "loss": 1.7091020584106444, "step": 3750 }, { "epoch": 0.6456875456145623, "grad_norm": 1.7734375, "learning_rate": 3.3656901463247137e-06, "loss": 1.6703121185302734, "step": 3760 }, { "epoch": 0.6474047997252393, "grad_norm": 1.890625, "learning_rate": 3.3373946292146186e-06, "loss": 1.6886062622070312, "step": 3770 }, { "epoch": 0.6491220538359164, "grad_norm": 2.390625, "learning_rate": 3.3091588512910777e-06, "loss": 1.6881946563720702, "step": 3780 }, { "epoch": 0.6508393079465934, "grad_norm": 1.9609375, "learning_rate": 3.280983827095745e-06, "loss": 1.703047752380371, "step": 3790 }, { "epoch": 0.6525565620572704, "grad_norm": 1.96875, "learning_rate": 3.2528705689873276e-06, "loss": 1.6761011123657226, "step": 3800 }, { "epoch": 0.6542738161679474, "grad_norm": 2.171875, "learning_rate": 3.224820087105217e-06, "loss": 1.690154457092285, "step": 3810 }, { "epoch": 0.6559910702786245, "grad_norm": 1.8046875, "learning_rate": 3.1968333893331795e-06, "loss": 1.6464597702026367, "step": 3820 }, { "epoch": 0.6577083243893015, "grad_norm": 2.109375, "learning_rate": 3.168911481263158e-06, "loss": 1.6696916580200196, "step": 3830 }, { "epoch": 0.6594255784999785, "grad_norm": 1.9375, "learning_rate": 3.1410553661591287e-06, "loss": 1.6890186309814452, "step": 3840 }, { "epoch": 0.6611428326106555, "grad_norm": 2.046875, "learning_rate": 3.1132660449210534e-06, "loss": 1.6701330184936523, "step": 3850 }, { "epoch": 0.6628600867213326, "grad_norm": 1.984375, "learning_rate": 3.085544516048924e-06, "loss": 1.6930913925170898, "step": 3860 }, { "epoch": 0.6645773408320096, "grad_norm": 2.1875, "learning_rate": 3.057891775606876e-06, "loss": 1.6896722793579102, "step": 3870 }, { "epoch": 0.6662945949426866, "grad_norm": 2.03125, "learning_rate": 3.030308817187408e-06, "loss": 1.6645723342895509, "step": 3880 }, { "epoch": 0.6680118490533636, "grad_norm": 1.8125, "learning_rate": 3.002796631875672e-06, "loss": 1.6646038055419923, "step": 3890 }, { "epoch": 0.6697291031640407, "grad_norm": 2.15625, "learning_rate": 2.9753562082138664e-06, "loss": 1.6508953094482421, "step": 3900 }, { "epoch": 0.6714463572747177, "grad_norm": 2.234375, "learning_rate": 2.947988532165721e-06, "loss": 1.6465852737426758, "step": 3910 }, { "epoch": 0.6731636113853947, "grad_norm": 2.359375, "learning_rate": 2.920694587081062e-06, "loss": 1.6760234832763672, "step": 3920 }, { "epoch": 0.6748808654960717, "grad_norm": 1.9921875, "learning_rate": 2.8934753536604864e-06, "loss": 1.6782474517822266, "step": 3930 }, { "epoch": 0.6765981196067488, "grad_norm": 1.984375, "learning_rate": 2.866331809920118e-06, "loss": 1.6897722244262696, "step": 3940 }, { "epoch": 0.6783153737174258, "grad_norm": 1.953125, "learning_rate": 2.8392649311564703e-06, "loss": 1.6710281372070312, "step": 3950 }, { "epoch": 0.6800326278281028, "grad_norm": 2.125, "learning_rate": 2.8122756899114074e-06, "loss": 1.673974609375, "step": 3960 }, { "epoch": 0.68174988193878, "grad_norm": 2.28125, "learning_rate": 2.785365055937186e-06, "loss": 1.67663631439209, "step": 3970 }, { "epoch": 0.683467136049457, "grad_norm": 1.9453125, "learning_rate": 2.7585339961616283e-06, "loss": 1.6704132080078125, "step": 3980 }, { "epoch": 0.685184390160134, "grad_norm": 2.125, "learning_rate": 2.7317834746533633e-06, "loss": 1.698836898803711, "step": 3990 }, { "epoch": 0.686901644270811, "grad_norm": 1.7890625, "learning_rate": 2.7051144525871968e-06, "loss": 1.6748104095458984, "step": 4000 }, { "epoch": 0.686901644270811, "eval_loss": 1.6769758462905884, "eval_runtime": 132.398, "eval_samples_per_second": 35.899, "eval_steps_per_second": 4.494, "step": 4000 }, { "epoch": 0.688618898381488, "grad_norm": 2.109375, "learning_rate": 2.6785278882095757e-06, "loss": 1.6461915969848633, "step": 4010 }, { "epoch": 0.6903361524921651, "grad_norm": 2.265625, "learning_rate": 2.6520247368041495e-06, "loss": 1.691582489013672, "step": 4020 }, { "epoch": 0.6920534066028421, "grad_norm": 1.78125, "learning_rate": 2.6256059506574514e-06, "loss": 1.6998956680297852, "step": 4030 }, { "epoch": 0.6937706607135191, "grad_norm": 1.921875, "learning_rate": 2.599272479024684e-06, "loss": 1.6911392211914062, "step": 4040 }, { "epoch": 0.6954879148241961, "grad_norm": 2.078125, "learning_rate": 2.5730252680956016e-06, "loss": 1.7022567749023438, "step": 4050 }, { "epoch": 0.6972051689348732, "grad_norm": 2.265625, "learning_rate": 2.5468652609605276e-06, "loss": 1.6842691421508789, "step": 4060 }, { "epoch": 0.6989224230455502, "grad_norm": 2.171875, "learning_rate": 2.520793397576455e-06, "loss": 1.6831863403320313, "step": 4070 }, { "epoch": 0.7006396771562272, "grad_norm": 1.9140625, "learning_rate": 2.4948106147332773e-06, "loss": 1.7208206176757812, "step": 4080 }, { "epoch": 0.7023569312669042, "grad_norm": 2.109375, "learning_rate": 2.468917846020133e-06, "loss": 1.7231781005859375, "step": 4090 }, { "epoch": 0.7040741853775813, "grad_norm": 2.296875, "learning_rate": 2.4431160217918504e-06, "loss": 1.6582822799682617, "step": 4100 }, { "epoch": 0.7057914394882583, "grad_norm": 1.953125, "learning_rate": 2.417406069135533e-06, "loss": 1.676438331604004, "step": 4110 }, { "epoch": 0.7075086935989353, "grad_norm": 1.9296875, "learning_rate": 2.391788911837236e-06, "loss": 1.6759963989257813, "step": 4120 }, { "epoch": 0.7092259477096123, "grad_norm": 2.28125, "learning_rate": 2.366265470348776e-06, "loss": 1.678311538696289, "step": 4130 }, { "epoch": 0.7109432018202894, "grad_norm": 1.8671875, "learning_rate": 2.340836661754667e-06, "loss": 1.689300537109375, "step": 4140 }, { "epoch": 0.7126604559309664, "grad_norm": 1.78125, "learning_rate": 2.315503399739155e-06, "loss": 1.693415641784668, "step": 4150 }, { "epoch": 0.7143777100416434, "grad_norm": 2.34375, "learning_rate": 2.2902665945534035e-06, "loss": 1.6509347915649415, "step": 4160 }, { "epoch": 0.7160949641523204, "grad_norm": 2.03125, "learning_rate": 2.265127152982771e-06, "loss": 1.7090904235839843, "step": 4170 }, { "epoch": 0.7178122182629975, "grad_norm": 2.0, "learning_rate": 2.2400859783142426e-06, "loss": 1.6681434631347656, "step": 4180 }, { "epoch": 0.7195294723736745, "grad_norm": 1.9765625, "learning_rate": 2.215143970303964e-06, "loss": 1.724860954284668, "step": 4190 }, { "epoch": 0.7212467264843515, "grad_norm": 1.828125, "learning_rate": 2.1903020251449236e-06, "loss": 1.697939109802246, "step": 4200 }, { "epoch": 0.7229639805950285, "grad_norm": 1.9375, "learning_rate": 2.165561035434739e-06, "loss": 1.6634525299072265, "step": 4210 }, { "epoch": 0.7246812347057056, "grad_norm": 1.9921875, "learning_rate": 2.140921890143593e-06, "loss": 1.662712287902832, "step": 4220 }, { "epoch": 0.7263984888163826, "grad_norm": 1.828125, "learning_rate": 2.1163854745822875e-06, "loss": 1.7017059326171875, "step": 4230 }, { "epoch": 0.7281157429270596, "grad_norm": 1.890625, "learning_rate": 2.0919526703704406e-06, "loss": 1.696014404296875, "step": 4240 }, { "epoch": 0.7298329970377366, "grad_norm": 2.03125, "learning_rate": 2.0676243554047994e-06, "loss": 1.6816932678222656, "step": 4250 }, { "epoch": 0.7315502511484137, "grad_norm": 2.390625, "learning_rate": 2.0434014038276993e-06, "loss": 1.6980966567993163, "step": 4260 }, { "epoch": 0.7332675052590907, "grad_norm": 2.09375, "learning_rate": 2.019284685995664e-06, "loss": 1.7112930297851563, "step": 4270 }, { "epoch": 0.7349847593697677, "grad_norm": 2.09375, "learning_rate": 1.9952750684481164e-06, "loss": 1.6958806991577149, "step": 4280 }, { "epoch": 0.7367020134804447, "grad_norm": 2.03125, "learning_rate": 1.97137341387626e-06, "loss": 1.6823633193969727, "step": 4290 }, { "epoch": 0.7384192675911218, "grad_norm": 2.0625, "learning_rate": 1.9475805810920678e-06, "loss": 1.658501434326172, "step": 4300 }, { "epoch": 0.7401365217017988, "grad_norm": 2.21875, "learning_rate": 1.923897424997429e-06, "loss": 1.6810495376586914, "step": 4310 }, { "epoch": 0.7418537758124758, "grad_norm": 1.8203125, "learning_rate": 1.9003247965534382e-06, "loss": 1.6920576095581055, "step": 4320 }, { "epoch": 0.7435710299231528, "grad_norm": 1.7890625, "learning_rate": 1.8768635427498083e-06, "loss": 1.6910625457763673, "step": 4330 }, { "epoch": 0.7452882840338299, "grad_norm": 2.0625, "learning_rate": 1.8535145065744425e-06, "loss": 1.6947786331176757, "step": 4340 }, { "epoch": 0.747005538144507, "grad_norm": 2.046875, "learning_rate": 1.8302785269831485e-06, "loss": 1.6586076736450195, "step": 4350 }, { "epoch": 0.748722792255184, "grad_norm": 1.890625, "learning_rate": 1.8071564388694874e-06, "loss": 1.667344856262207, "step": 4360 }, { "epoch": 0.750440046365861, "grad_norm": 2.078125, "learning_rate": 1.7841490730347777e-06, "loss": 1.6827234268188476, "step": 4370 }, { "epoch": 0.7521573004765381, "grad_norm": 1.96875, "learning_rate": 1.7612572561582424e-06, "loss": 1.676734733581543, "step": 4380 }, { "epoch": 0.7538745545872151, "grad_norm": 1.9296875, "learning_rate": 1.738481810767314e-06, "loss": 1.702406883239746, "step": 4390 }, { "epoch": 0.7555918086978921, "grad_norm": 2.015625, "learning_rate": 1.715823555208066e-06, "loss": 1.705453872680664, "step": 4400 }, { "epoch": 0.7573090628085691, "grad_norm": 1.921875, "learning_rate": 1.6932833036158163e-06, "loss": 1.6881147384643556, "step": 4410 }, { "epoch": 0.7590263169192462, "grad_norm": 2.140625, "learning_rate": 1.670861865885881e-06, "loss": 1.698809814453125, "step": 4420 }, { "epoch": 0.7607435710299232, "grad_norm": 2.125, "learning_rate": 1.6485600476444601e-06, "loss": 1.6559257507324219, "step": 4430 }, { "epoch": 0.7624608251406002, "grad_norm": 1.8828125, "learning_rate": 1.6263786502196992e-06, "loss": 1.6994630813598632, "step": 4440 }, { "epoch": 0.7641780792512772, "grad_norm": 2.03125, "learning_rate": 1.6043184706128994e-06, "loss": 1.7314516067504884, "step": 4450 }, { "epoch": 0.7658953333619543, "grad_norm": 1.9921875, "learning_rate": 1.5823803014698702e-06, "loss": 1.6673833847045898, "step": 4460 }, { "epoch": 0.7676125874726313, "grad_norm": 1.8671875, "learning_rate": 1.5605649310524607e-06, "loss": 1.6619630813598634, "step": 4470 }, { "epoch": 0.7693298415833083, "grad_norm": 1.6796875, "learning_rate": 1.5388731432102267e-06, "loss": 1.674607276916504, "step": 4480 }, { "epoch": 0.7710470956939853, "grad_norm": 1.8828125, "learning_rate": 1.5173057173522682e-06, "loss": 1.6886301040649414, "step": 4490 }, { "epoch": 0.7727643498046624, "grad_norm": 2.109375, "learning_rate": 1.4958634284192335e-06, "loss": 1.6885858535766602, "step": 4500 }, { "epoch": 0.7727643498046624, "eval_loss": 1.6767653226852417, "eval_runtime": 131.9708, "eval_samples_per_second": 36.016, "eval_steps_per_second": 4.509, "step": 4500 }, { "epoch": 0.7744816039153394, "grad_norm": 2.0, "learning_rate": 1.4745470468554618e-06, "loss": 1.684710693359375, "step": 4510 }, { "epoch": 0.7761988580260164, "grad_norm": 2.234375, "learning_rate": 1.453357338581307e-06, "loss": 1.705989456176758, "step": 4520 }, { "epoch": 0.7779161121366934, "grad_norm": 1.90625, "learning_rate": 1.4322950649656175e-06, "loss": 1.696319580078125, "step": 4530 }, { "epoch": 0.7796333662473705, "grad_norm": 1.9765625, "learning_rate": 1.411360982798376e-06, "loss": 1.6634998321533203, "step": 4540 }, { "epoch": 0.7813506203580475, "grad_norm": 2.125, "learning_rate": 1.3905558442635143e-06, "loss": 1.664762306213379, "step": 4550 }, { "epoch": 0.7830678744687245, "grad_norm": 1.859375, "learning_rate": 1.369880396911875e-06, "loss": 1.6650190353393555, "step": 4560 }, { "epoch": 0.7847851285794015, "grad_norm": 2.125, "learning_rate": 1.3493353836343666e-06, "loss": 1.6930984497070312, "step": 4570 }, { "epoch": 0.7865023826900785, "grad_norm": 1.921875, "learning_rate": 1.3289215426352543e-06, "loss": 1.7059337615966796, "step": 4580 }, { "epoch": 0.7882196368007556, "grad_norm": 1.84375, "learning_rate": 1.3086396074056452e-06, "loss": 1.7067310333251953, "step": 4590 }, { "epoch": 0.7899368909114326, "grad_norm": 1.921875, "learning_rate": 1.2884903066971354e-06, "loss": 1.6961929321289062, "step": 4600 }, { "epoch": 0.7916541450221096, "grad_norm": 2.0625, "learning_rate": 1.2684743644956144e-06, "loss": 1.6727468490600585, "step": 4610 }, { "epoch": 0.7933713991327866, "grad_norm": 1.8203125, "learning_rate": 1.2485924999952648e-06, "loss": 1.670815658569336, "step": 4620 }, { "epoch": 0.7950886532434637, "grad_norm": 2.21875, "learning_rate": 1.2288454275727092e-06, "loss": 1.705885887145996, "step": 4630 }, { "epoch": 0.7968059073541407, "grad_norm": 1.9375, "learning_rate": 1.2092338567613477e-06, "loss": 1.6970123291015624, "step": 4640 }, { "epoch": 0.7985231614648177, "grad_norm": 2.140625, "learning_rate": 1.189758492225866e-06, "loss": 1.6802467346191405, "step": 4650 }, { "epoch": 0.8002404155754947, "grad_norm": 2.046875, "learning_rate": 1.1704200337369093e-06, "loss": 1.6864849090576173, "step": 4660 }, { "epoch": 0.8019576696861718, "grad_norm": 2.109375, "learning_rate": 1.151219176145944e-06, "loss": 1.679457664489746, "step": 4670 }, { "epoch": 0.8036749237968488, "grad_norm": 2.078125, "learning_rate": 1.1321566093602886e-06, "loss": 1.6878799438476562, "step": 4680 }, { "epoch": 0.8053921779075258, "grad_norm": 2.3125, "learning_rate": 1.1132330183183248e-06, "loss": 1.6713159561157227, "step": 4690 }, { "epoch": 0.8071094320182028, "grad_norm": 2.25, "learning_rate": 1.0944490829648902e-06, "loss": 1.6758745193481446, "step": 4700 }, { "epoch": 0.8088266861288799, "grad_norm": 1.984375, "learning_rate": 1.0758054782268413e-06, "loss": 1.6936321258544922, "step": 4710 }, { "epoch": 0.810543940239557, "grad_norm": 1.796875, "learning_rate": 1.0573028739888046e-06, "loss": 1.6641183853149415, "step": 4720 }, { "epoch": 0.812261194350234, "grad_norm": 2.171875, "learning_rate": 1.0389419350691148e-06, "loss": 1.6812414169311523, "step": 4730 }, { "epoch": 0.813978448460911, "grad_norm": 2.046875, "learning_rate": 1.0207233211959118e-06, "loss": 1.6878366470336914, "step": 4740 }, { "epoch": 0.8156957025715881, "grad_norm": 1.8515625, "learning_rate": 1.0026476869834518e-06, "loss": 1.6963472366333008, "step": 4750 }, { "epoch": 0.8174129566822651, "grad_norm": 2.0625, "learning_rate": 9.84715681908574e-07, "loss": 1.692417526245117, "step": 4760 }, { "epoch": 0.8191302107929421, "grad_norm": 1.9453125, "learning_rate": 9.669279502873714e-07, "loss": 1.6806459426879883, "step": 4770 }, { "epoch": 0.8208474649036192, "grad_norm": 2.015625, "learning_rate": 9.49285131252038e-07, "loss": 1.7256832122802734, "step": 4780 }, { "epoch": 0.8225647190142962, "grad_norm": 1.9921875, "learning_rate": 9.317878587279028e-07, "loss": 1.693280029296875, "step": 4790 }, { "epoch": 0.8242819731249732, "grad_norm": 1.9375, "learning_rate": 9.144367614106553e-07, "loss": 1.673685646057129, "step": 4800 }, { "epoch": 0.8259992272356502, "grad_norm": 1.9609375, "learning_rate": 8.972324627437512e-07, "loss": 1.7132776260375977, "step": 4810 }, { "epoch": 0.8277164813463272, "grad_norm": 1.90625, "learning_rate": 8.80175580896015e-07, "loss": 1.6752429962158204, "step": 4820 }, { "epoch": 0.8294337354570043, "grad_norm": 1.9921875, "learning_rate": 8.632667287394275e-07, "loss": 1.6770788192749024, "step": 4830 }, { "epoch": 0.8311509895676813, "grad_norm": 1.9609375, "learning_rate": 8.465065138271034e-07, "loss": 1.7141851425170898, "step": 4840 }, { "epoch": 0.8328682436783583, "grad_norm": 1.859375, "learning_rate": 8.298955383714652e-07, "loss": 1.6812074661254883, "step": 4850 }, { "epoch": 0.8345854977890353, "grad_norm": 1.9921875, "learning_rate": 8.134343992226007e-07, "loss": 1.6711181640625, "step": 4860 }, { "epoch": 0.8363027518997124, "grad_norm": 2.03125, "learning_rate": 7.97123687846817e-07, "loss": 1.6912593841552734, "step": 4870 }, { "epoch": 0.8380200060103894, "grad_norm": 1.8984375, "learning_rate": 7.809639903053956e-07, "loss": 1.7027881622314454, "step": 4880 }, { "epoch": 0.8397372601210664, "grad_norm": 2.09375, "learning_rate": 7.649558872335261e-07, "loss": 1.694002342224121, "step": 4890 }, { "epoch": 0.8414545142317434, "grad_norm": 2.125, "learning_rate": 7.490999538194466e-07, "loss": 1.6670547485351563, "step": 4900 }, { "epoch": 0.8431717683424205, "grad_norm": 2.015625, "learning_rate": 7.333967597837793e-07, "loss": 1.6602981567382813, "step": 4910 }, { "epoch": 0.8448890224530975, "grad_norm": 1.9296875, "learning_rate": 7.178468693590552e-07, "loss": 1.6768507003784179, "step": 4920 }, { "epoch": 0.8466062765637745, "grad_norm": 1.984375, "learning_rate": 7.024508412694453e-07, "loss": 1.6982421875, "step": 4930 }, { "epoch": 0.8483235306744515, "grad_norm": 2.265625, "learning_rate": 6.872092287106797e-07, "loss": 1.6842584609985352, "step": 4940 }, { "epoch": 0.8500407847851286, "grad_norm": 1.8203125, "learning_rate": 6.721225793301744e-07, "loss": 1.6600732803344727, "step": 4950 }, { "epoch": 0.8517580388958056, "grad_norm": 1.984375, "learning_rate": 6.571914352073556e-07, "loss": 1.6617712020874023, "step": 4960 }, { "epoch": 0.8534752930064826, "grad_norm": 2.25, "learning_rate": 6.424163328341759e-07, "loss": 1.6836875915527343, "step": 4970 }, { "epoch": 0.8551925471171596, "grad_norm": 2.0625, "learning_rate": 6.277978030958432e-07, "loss": 1.6771120071411132, "step": 4980 }, { "epoch": 0.8569098012278367, "grad_norm": 1.9921875, "learning_rate": 6.13336371251742e-07, "loss": 1.6524078369140625, "step": 4990 }, { "epoch": 0.8586270553385137, "grad_norm": 2.046875, "learning_rate": 5.990325569165622e-07, "loss": 1.6842248916625977, "step": 5000 }, { "epoch": 0.8586270553385137, "eval_loss": 1.676727056503296, "eval_runtime": 131.9091, "eval_samples_per_second": 36.032, "eval_steps_per_second": 4.511, "step": 5000 }, { "epoch": 0.8603443094491907, "grad_norm": 2.03125, "learning_rate": 5.848868740416308e-07, "loss": 1.68514404296875, "step": 5010 }, { "epoch": 0.8620615635598677, "grad_norm": 1.8203125, "learning_rate": 5.708998308964381e-07, "loss": 1.6773714065551757, "step": 5020 }, { "epoch": 0.8637788176705448, "grad_norm": 1.96875, "learning_rate": 5.570719300503835e-07, "loss": 1.6834987640380858, "step": 5030 }, { "epoch": 0.8654960717812218, "grad_norm": 2.0625, "learning_rate": 5.434036683547117e-07, "loss": 1.6962696075439454, "step": 5040 }, { "epoch": 0.8672133258918988, "grad_norm": 1.671875, "learning_rate": 5.298955369246606e-07, "loss": 1.6798547744750976, "step": 5050 }, { "epoch": 0.8689305800025758, "grad_norm": 2.0, "learning_rate": 5.165480211218205e-07, "loss": 1.6901210784912108, "step": 5060 }, { "epoch": 0.8706478341132529, "grad_norm": 2.0, "learning_rate": 5.033616005366887e-07, "loss": 1.681991195678711, "step": 5070 }, { "epoch": 0.8723650882239299, "grad_norm": 1.921875, "learning_rate": 4.903367489714372e-07, "loss": 1.6555261611938477, "step": 5080 }, { "epoch": 0.8740823423346069, "grad_norm": 1.9453125, "learning_rate": 4.774739344228952e-07, "loss": 1.6676856994628906, "step": 5090 }, { "epoch": 0.875799596445284, "grad_norm": 1.984375, "learning_rate": 4.6477361906572425e-07, "loss": 1.6820755004882812, "step": 5100 }, { "epoch": 0.8775168505559611, "grad_norm": 1.8203125, "learning_rate": 4.522362592358204e-07, "loss": 1.6808874130249023, "step": 5110 }, { "epoch": 0.8792341046666381, "grad_norm": 2.0625, "learning_rate": 4.398623054139106e-07, "loss": 1.6864171981811524, "step": 5120 }, { "epoch": 0.8809513587773151, "grad_norm": 2.1875, "learning_rate": 4.2765220220936986e-07, "loss": 1.6654550552368164, "step": 5130 }, { "epoch": 0.8826686128879921, "grad_norm": 1.9609375, "learning_rate": 4.156063883442474e-07, "loss": 1.6699941635131836, "step": 5140 }, { "epoch": 0.8843858669986692, "grad_norm": 1.8046875, "learning_rate": 4.037252966374977e-07, "loss": 1.6848541259765626, "step": 5150 }, { "epoch": 0.8861031211093462, "grad_norm": 1.9375, "learning_rate": 3.920093539894365e-07, "loss": 1.676061248779297, "step": 5160 }, { "epoch": 0.8878203752200232, "grad_norm": 1.8515625, "learning_rate": 3.804589813663939e-07, "loss": 1.682215690612793, "step": 5170 }, { "epoch": 0.8895376293307002, "grad_norm": 2.078125, "learning_rate": 3.690745937855933e-07, "loss": 1.6449657440185548, "step": 5180 }, { "epoch": 0.8912548834413773, "grad_norm": 1.7421875, "learning_rate": 3.5785660030023983e-07, "loss": 1.6863983154296875, "step": 5190 }, { "epoch": 0.8929721375520543, "grad_norm": 2.171875, "learning_rate": 3.4680540398481733e-07, "loss": 1.687844467163086, "step": 5200 }, { "epoch": 0.8946893916627313, "grad_norm": 2.1875, "learning_rate": 3.359214019206147e-07, "loss": 1.688450241088867, "step": 5210 }, { "epoch": 0.8964066457734083, "grad_norm": 1.8515625, "learning_rate": 3.2520498518144706e-07, "loss": 1.6574895858764649, "step": 5220 }, { "epoch": 0.8981238998840854, "grad_norm": 2.09375, "learning_rate": 3.1465653881961325e-07, "loss": 1.6859638214111328, "step": 5230 }, { "epoch": 0.8998411539947624, "grad_norm": 2.0625, "learning_rate": 3.042764418520572e-07, "loss": 1.698681640625, "step": 5240 }, { "epoch": 0.9015584081054394, "grad_norm": 1.984375, "learning_rate": 2.9406506724674656e-07, "loss": 1.6472530364990234, "step": 5250 }, { "epoch": 0.9032756622161164, "grad_norm": 1.9375, "learning_rate": 2.840227819092778e-07, "loss": 1.7000297546386718, "step": 5260 }, { "epoch": 0.9049929163267935, "grad_norm": 2.046875, "learning_rate": 2.741499466696873e-07, "loss": 1.6824630737304687, "step": 5270 }, { "epoch": 0.9067101704374705, "grad_norm": 2.328125, "learning_rate": 2.6444691626948904e-07, "loss": 1.6929946899414063, "step": 5280 }, { "epoch": 0.9084274245481475, "grad_norm": 1.9296875, "learning_rate": 2.549140393489269e-07, "loss": 1.683822250366211, "step": 5290 }, { "epoch": 0.9101446786588245, "grad_norm": 2.0, "learning_rate": 2.455516584344503e-07, "loss": 1.6882390975952148, "step": 5300 }, { "epoch": 0.9118619327695016, "grad_norm": 1.96875, "learning_rate": 2.3636010992640235e-07, "loss": 1.676593017578125, "step": 5310 }, { "epoch": 0.9135791868801786, "grad_norm": 1.9765625, "learning_rate": 2.2733972408693904e-07, "loss": 1.6814647674560548, "step": 5320 }, { "epoch": 0.9152964409908556, "grad_norm": 1.90625, "learning_rate": 2.1849082502815532e-07, "loss": 1.700049591064453, "step": 5330 }, { "epoch": 0.9170136951015326, "grad_norm": 2.03125, "learning_rate": 2.0981373070044664e-07, "loss": 1.6850770950317382, "step": 5340 }, { "epoch": 0.9187309492122097, "grad_norm": 1.84375, "learning_rate": 2.01308752881077e-07, "loss": 1.6972654342651368, "step": 5350 }, { "epoch": 0.9204482033228867, "grad_norm": 1.890625, "learning_rate": 1.9297619716298231e-07, "loss": 1.688237190246582, "step": 5360 }, { "epoch": 0.9221654574335637, "grad_norm": 1.84375, "learning_rate": 1.848163629437899e-07, "loss": 1.6823043823242188, "step": 5370 }, { "epoch": 0.9238827115442407, "grad_norm": 2.203125, "learning_rate": 1.7682954341505577e-07, "loss": 1.7168113708496093, "step": 5380 }, { "epoch": 0.9255999656549178, "grad_norm": 1.734375, "learning_rate": 1.6901602555173645e-07, "loss": 1.7165647506713868, "step": 5390 }, { "epoch": 0.9273172197655948, "grad_norm": 2.046875, "learning_rate": 1.6137609010187293e-07, "loss": 1.6996660232543945, "step": 5400 }, { "epoch": 0.9290344738762718, "grad_norm": 2.21875, "learning_rate": 1.539100115765041e-07, "loss": 1.6905323028564454, "step": 5410 }, { "epoch": 0.9307517279869488, "grad_norm": 1.9765625, "learning_rate": 1.4661805823980635e-07, "loss": 1.6977949142456055, "step": 5420 }, { "epoch": 0.9324689820976259, "grad_norm": 1.8984375, "learning_rate": 1.3950049209944917e-07, "loss": 1.6839534759521484, "step": 5430 }, { "epoch": 0.9341862362083029, "grad_norm": 2.03125, "learning_rate": 1.3255756889718586e-07, "loss": 1.6930166244506837, "step": 5440 }, { "epoch": 0.9359034903189799, "grad_norm": 2.03125, "learning_rate": 1.257895380996621e-07, "loss": 1.7076713562011718, "step": 5450 }, { "epoch": 0.9376207444296569, "grad_norm": 1.71875, "learning_rate": 1.1919664288945088e-07, "loss": 1.6950756072998048, "step": 5460 }, { "epoch": 0.939337998540334, "grad_norm": 1.875, "learning_rate": 1.1277912015631942e-07, "loss": 1.7016971588134766, "step": 5470 }, { "epoch": 0.9410552526510111, "grad_norm": 1.7734375, "learning_rate": 1.0653720048871218e-07, "loss": 1.6829399108886718, "step": 5480 }, { "epoch": 0.9427725067616881, "grad_norm": 2.15625, "learning_rate": 1.0047110816546968e-07, "loss": 1.6759597778320312, "step": 5490 }, { "epoch": 0.9444897608723651, "grad_norm": 2.1875, "learning_rate": 9.458106114776711e-08, "loss": 1.7130905151367188, "step": 5500 }, { "epoch": 0.9444897608723651, "eval_loss": 1.6766955852508545, "eval_runtime": 131.481, "eval_samples_per_second": 36.15, "eval_steps_per_second": 4.525, "step": 5500 }, { "epoch": 0.9462070149830422, "grad_norm": 1.875, "learning_rate": 8.886727107128402e-08, "loss": 1.6850292205810546, "step": 5510 }, { "epoch": 0.9479242690937192, "grad_norm": 2.015625, "learning_rate": 8.332994323859978e-08, "loss": 1.702094841003418, "step": 5520 }, { "epoch": 0.9496415232043962, "grad_norm": 1.921875, "learning_rate": 7.796927661181785e-08, "loss": 1.6940507888793945, "step": 5530 }, { "epoch": 0.9513587773150732, "grad_norm": 2.140625, "learning_rate": 7.278546380541319e-08, "loss": 1.6953474044799806, "step": 5540 }, { "epoch": 0.9530760314257503, "grad_norm": 1.8203125, "learning_rate": 6.777869107931822e-08, "loss": 1.6881795883178712, "step": 5550 }, { "epoch": 0.9547932855364273, "grad_norm": 1.8671875, "learning_rate": 6.294913833222227e-08, "loss": 1.6704019546508788, "step": 5560 }, { "epoch": 0.9565105396471043, "grad_norm": 1.8359375, "learning_rate": 5.8296979095114335e-08, "loss": 1.6975568771362304, "step": 5570 }, { "epoch": 0.9582277937577813, "grad_norm": 2.0625, "learning_rate": 5.382238052504374e-08, "loss": 1.6895214080810548, "step": 5580 }, { "epoch": 0.9599450478684584, "grad_norm": 2.015625, "learning_rate": 4.9525503399115995e-08, "loss": 1.6707267761230469, "step": 5590 }, { "epoch": 0.9616623019791354, "grad_norm": 2.25, "learning_rate": 4.5406502108714665e-08, "loss": 1.6803543090820312, "step": 5600 }, { "epoch": 0.9633795560898124, "grad_norm": 1.796875, "learning_rate": 4.14655246539547e-08, "loss": 1.676511001586914, "step": 5610 }, { "epoch": 0.9650968102004894, "grad_norm": 2.09375, "learning_rate": 3.7702712638365e-08, "loss": 1.6697118759155274, "step": 5620 }, { "epoch": 0.9668140643111665, "grad_norm": 2.09375, "learning_rate": 3.411820126380083e-08, "loss": 1.66761474609375, "step": 5630 }, { "epoch": 0.9685313184218435, "grad_norm": 2.0, "learning_rate": 3.0712119325582715e-08, "loss": 1.7185823440551757, "step": 5640 }, { "epoch": 0.9702485725325205, "grad_norm": 2.046875, "learning_rate": 2.7484589207872892e-08, "loss": 1.6960851669311523, "step": 5650 }, { "epoch": 0.9719658266431975, "grad_norm": 2.125, "learning_rate": 2.443572687927498e-08, "loss": 1.6741943359375, "step": 5660 }, { "epoch": 0.9736830807538746, "grad_norm": 1.8515625, "learning_rate": 2.1565641888668386e-08, "loss": 1.6793323516845704, "step": 5670 }, { "epoch": 0.9754003348645516, "grad_norm": 1.921875, "learning_rate": 1.887443736127259e-08, "loss": 1.6985464096069336, "step": 5680 }, { "epoch": 0.9771175889752286, "grad_norm": 2.203125, "learning_rate": 1.6362209994939536e-08, "loss": 1.656944465637207, "step": 5690 }, { "epoch": 0.9788348430859056, "grad_norm": 1.90625, "learning_rate": 1.4029050056681981e-08, "loss": 1.6778036117553712, "step": 5700 }, { "epoch": 0.9805520971965827, "grad_norm": 2.015625, "learning_rate": 1.1875041379428298e-08, "loss": 1.6694595336914062, "step": 5710 }, { "epoch": 0.9822693513072597, "grad_norm": 2.0625, "learning_rate": 9.900261359010454e-09, "loss": 1.6779298782348633, "step": 5720 }, { "epoch": 0.9839866054179367, "grad_norm": 1.984375, "learning_rate": 8.104780951382896e-09, "loss": 1.700521469116211, "step": 5730 }, { "epoch": 0.9857038595286137, "grad_norm": 1.9765625, "learning_rate": 6.48866467007514e-09, "loss": 1.663212776184082, "step": 5740 }, { "epoch": 0.9874211136392907, "grad_norm": 2.109375, "learning_rate": 5.0519705838708574e-09, "loss": 1.6871564865112305, "step": 5750 }, { "epoch": 0.9891383677499678, "grad_norm": 2.125, "learning_rate": 3.794750314722318e-09, "loss": 1.6940940856933593, "step": 5760 }, { "epoch": 0.9908556218606448, "grad_norm": 1.96875, "learning_rate": 2.7170490358968683e-09, "loss": 1.6699420928955078, "step": 5770 }, { "epoch": 0.9925728759713218, "grad_norm": 1.8984375, "learning_rate": 1.818905470352683e-09, "loss": 1.6656627655029297, "step": 5780 }, { "epoch": 0.9942901300819988, "grad_norm": 2.296875, "learning_rate": 1.1003518893465403e-09, "loss": 1.6492998123168945, "step": 5790 }, { "epoch": 0.9960073841926759, "grad_norm": 1.9765625, "learning_rate": 5.614141112764149e-10, "loss": 1.678446388244629, "step": 5800 }, { "epoch": 0.9977246383033529, "grad_norm": 1.796875, "learning_rate": 2.0211150075277742e-10, "loss": 1.6793657302856446, "step": 5810 }, { "epoch": 0.9994418924140299, "grad_norm": 1.8671875, "learning_rate": 2.2456967900819083e-11, "loss": 1.6982393264770508, "step": 5820 }, { "epoch": 1.0, "eval_loss": 1.676680088043213, "eval_runtime": 131.2606, "eval_samples_per_second": 36.21, "eval_steps_per_second": 4.533, "step": 5824 }, { "epoch": 1.0, "step": 5824, "total_flos": 5.457426983499405e+18, "train_loss": 1.7026834567333315, "train_runtime": 26688.0587, "train_samples_per_second": 8.728, "train_steps_per_second": 0.218 } ], "logging_steps": 10, "max_steps": 5824, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 200, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 5.457426983499405e+18, "train_batch_size": 10, "trial_name": null, "trial_params": null }