{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.999447004608295, "eval_steps": 500, "global_step": 5424, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.005529953917050691, "grad_norm": 6.0903776907776255, "learning_rate": 1.8416206261510132e-07, "loss": 0.8665, "step": 10 }, { "epoch": 0.011059907834101382, "grad_norm": 5.453075517812696, "learning_rate": 3.6832412523020263e-07, "loss": 0.8531, "step": 20 }, { "epoch": 0.016589861751152075, "grad_norm": 3.537343733022185, "learning_rate": 5.524861878453039e-07, "loss": 0.8281, "step": 30 }, { "epoch": 0.022119815668202765, "grad_norm": 1.7050757720044358, "learning_rate": 7.366482504604053e-07, "loss": 0.7589, "step": 40 }, { "epoch": 0.027649769585253458, "grad_norm": 1.4012843364617489, "learning_rate": 9.208103130755065e-07, "loss": 0.715, "step": 50 }, { "epoch": 0.03317972350230415, "grad_norm": 0.8011478929925271, "learning_rate": 1.1049723756906078e-06, "loss": 0.6922, "step": 60 }, { "epoch": 0.03870967741935484, "grad_norm": 0.5699780949895114, "learning_rate": 1.289134438305709e-06, "loss": 0.6497, "step": 70 }, { "epoch": 0.04423963133640553, "grad_norm": 0.4520674784173067, "learning_rate": 1.4732965009208105e-06, "loss": 0.6281, "step": 80 }, { "epoch": 0.04976958525345622, "grad_norm": 0.39365714402711754, "learning_rate": 1.6574585635359118e-06, "loss": 0.611, "step": 90 }, { "epoch": 0.055299539170506916, "grad_norm": 0.4304728776273806, "learning_rate": 1.841620626151013e-06, "loss": 0.594, "step": 100 }, { "epoch": 0.060829493087557605, "grad_norm": 0.36773866506240127, "learning_rate": 2.0257826887661147e-06, "loss": 0.5946, "step": 110 }, { "epoch": 0.0663594470046083, "grad_norm": 0.40144795349227336, "learning_rate": 2.2099447513812157e-06, "loss": 0.5758, "step": 120 }, { "epoch": 0.07188940092165899, "grad_norm": 0.3650630134248591, "learning_rate": 2.394106813996317e-06, "loss": 0.5774, "step": 130 }, { "epoch": 0.07741935483870968, "grad_norm": 0.40858596339929243, "learning_rate": 2.578268876611418e-06, "loss": 0.5811, "step": 140 }, { "epoch": 0.08294930875576037, "grad_norm": 0.3915180921441105, "learning_rate": 2.7624309392265196e-06, "loss": 0.5567, "step": 150 }, { "epoch": 0.08847926267281106, "grad_norm": 0.38045253569441917, "learning_rate": 2.946593001841621e-06, "loss": 0.5558, "step": 160 }, { "epoch": 0.09400921658986175, "grad_norm": 0.37413606476610706, "learning_rate": 3.130755064456722e-06, "loss": 0.5493, "step": 170 }, { "epoch": 0.09953917050691244, "grad_norm": 0.42201408210941044, "learning_rate": 3.3149171270718235e-06, "loss": 0.5517, "step": 180 }, { "epoch": 0.10506912442396313, "grad_norm": 0.4095688421864769, "learning_rate": 3.4990791896869245e-06, "loss": 0.5463, "step": 190 }, { "epoch": 0.11059907834101383, "grad_norm": 0.4463086469391698, "learning_rate": 3.683241252302026e-06, "loss": 0.547, "step": 200 }, { "epoch": 0.11612903225806452, "grad_norm": 0.3760139550501188, "learning_rate": 3.867403314917128e-06, "loss": 0.5393, "step": 210 }, { "epoch": 0.12165898617511521, "grad_norm": 0.4078492489838482, "learning_rate": 4.051565377532229e-06, "loss": 0.5329, "step": 220 }, { "epoch": 0.1271889400921659, "grad_norm": 0.3908887647799372, "learning_rate": 4.23572744014733e-06, "loss": 0.5431, "step": 230 }, { "epoch": 0.1327188940092166, "grad_norm": 0.3761589181214343, "learning_rate": 4.419889502762431e-06, "loss": 0.5381, "step": 240 }, { "epoch": 0.1382488479262673, "grad_norm": 0.41027742174158294, "learning_rate": 4.604051565377533e-06, "loss": 0.5339, "step": 250 }, { "epoch": 0.14377880184331798, "grad_norm": 0.3993047304895881, "learning_rate": 4.788213627992634e-06, "loss": 0.5337, "step": 260 }, { "epoch": 0.14930875576036867, "grad_norm": 0.4267384725056861, "learning_rate": 4.972375690607736e-06, "loss": 0.5325, "step": 270 }, { "epoch": 0.15483870967741936, "grad_norm": 0.3741112789490821, "learning_rate": 5.156537753222836e-06, "loss": 0.5347, "step": 280 }, { "epoch": 0.16036866359447005, "grad_norm": 0.5001650422449634, "learning_rate": 5.340699815837938e-06, "loss": 0.5264, "step": 290 }, { "epoch": 0.16589861751152074, "grad_norm": 0.40870225399677257, "learning_rate": 5.524861878453039e-06, "loss": 0.5295, "step": 300 }, { "epoch": 0.17142857142857143, "grad_norm": 0.4489579942156596, "learning_rate": 5.709023941068141e-06, "loss": 0.5267, "step": 310 }, { "epoch": 0.17695852534562212, "grad_norm": 0.4576001899146063, "learning_rate": 5.893186003683242e-06, "loss": 0.5208, "step": 320 }, { "epoch": 0.1824884792626728, "grad_norm": 0.42765306743716647, "learning_rate": 6.077348066298343e-06, "loss": 0.5188, "step": 330 }, { "epoch": 0.1880184331797235, "grad_norm": 0.43147440269952797, "learning_rate": 6.261510128913444e-06, "loss": 0.5154, "step": 340 }, { "epoch": 0.1935483870967742, "grad_norm": 0.4497751095330459, "learning_rate": 6.445672191528546e-06, "loss": 0.5048, "step": 350 }, { "epoch": 0.19907834101382488, "grad_norm": 0.5327826362213908, "learning_rate": 6.629834254143647e-06, "loss": 0.5128, "step": 360 }, { "epoch": 0.20460829493087557, "grad_norm": 0.4115996357259951, "learning_rate": 6.8139963167587485e-06, "loss": 0.5178, "step": 370 }, { "epoch": 0.21013824884792626, "grad_norm": 0.40196263236255503, "learning_rate": 6.998158379373849e-06, "loss": 0.514, "step": 380 }, { "epoch": 0.21566820276497695, "grad_norm": 0.42296446460219156, "learning_rate": 7.182320441988951e-06, "loss": 0.5085, "step": 390 }, { "epoch": 0.22119815668202766, "grad_norm": 0.45986207995548617, "learning_rate": 7.366482504604052e-06, "loss": 0.5139, "step": 400 }, { "epoch": 0.22672811059907835, "grad_norm": 0.44973185296884877, "learning_rate": 7.5506445672191534e-06, "loss": 0.5103, "step": 410 }, { "epoch": 0.23225806451612904, "grad_norm": 0.5306307382931725, "learning_rate": 7.734806629834256e-06, "loss": 0.506, "step": 420 }, { "epoch": 0.23778801843317973, "grad_norm": 0.42387585926266613, "learning_rate": 7.918968692449355e-06, "loss": 0.508, "step": 430 }, { "epoch": 0.24331797235023042, "grad_norm": 0.4600172141091088, "learning_rate": 8.103130755064459e-06, "loss": 0.5053, "step": 440 }, { "epoch": 0.2488479262672811, "grad_norm": 0.5063886096298784, "learning_rate": 8.287292817679558e-06, "loss": 0.505, "step": 450 }, { "epoch": 0.2543778801843318, "grad_norm": 0.45595110131670297, "learning_rate": 8.47145488029466e-06, "loss": 0.4994, "step": 460 }, { "epoch": 0.25990783410138246, "grad_norm": 0.3979219166043402, "learning_rate": 8.655616942909761e-06, "loss": 0.5003, "step": 470 }, { "epoch": 0.2654377880184332, "grad_norm": 0.47071002002813517, "learning_rate": 8.839779005524863e-06, "loss": 0.4971, "step": 480 }, { "epoch": 0.2709677419354839, "grad_norm": 0.4204629206638486, "learning_rate": 9.023941068139964e-06, "loss": 0.5032, "step": 490 }, { "epoch": 0.2764976958525346, "grad_norm": 0.4755494443427242, "learning_rate": 9.208103130755066e-06, "loss": 0.4999, "step": 500 }, { "epoch": 0.2820276497695853, "grad_norm": 0.41495435521999285, "learning_rate": 9.392265193370167e-06, "loss": 0.5035, "step": 510 }, { "epoch": 0.28755760368663597, "grad_norm": 0.405511787171205, "learning_rate": 9.576427255985269e-06, "loss": 0.4999, "step": 520 }, { "epoch": 0.29308755760368665, "grad_norm": 0.47131810224352805, "learning_rate": 9.760589318600368e-06, "loss": 0.5089, "step": 530 }, { "epoch": 0.29861751152073734, "grad_norm": 0.4504585902565694, "learning_rate": 9.944751381215471e-06, "loss": 0.499, "step": 540 }, { "epoch": 0.30414746543778803, "grad_norm": 0.5477004156365718, "learning_rate": 9.999949252169092e-06, "loss": 0.5006, "step": 550 }, { "epoch": 0.3096774193548387, "grad_norm": 0.5531038596543296, "learning_rate": 9.999700693844523e-06, "loss": 0.4882, "step": 560 }, { "epoch": 0.3152073732718894, "grad_norm": 0.5330112235228269, "learning_rate": 9.99924501428021e-06, "loss": 0.4916, "step": 570 }, { "epoch": 0.3207373271889401, "grad_norm": 0.4577766765611679, "learning_rate": 9.99858223235347e-06, "loss": 0.4924, "step": 580 }, { "epoch": 0.3262672811059908, "grad_norm": 0.40765286650009175, "learning_rate": 9.997712375521187e-06, "loss": 0.4895, "step": 590 }, { "epoch": 0.3317972350230415, "grad_norm": 0.47974015373170437, "learning_rate": 9.996635479818683e-06, "loss": 0.4933, "step": 600 }, { "epoch": 0.33732718894009217, "grad_norm": 0.44956075853602034, "learning_rate": 9.995351589858227e-06, "loss": 0.4954, "step": 610 }, { "epoch": 0.34285714285714286, "grad_norm": 0.4619350325798451, "learning_rate": 9.993860758827171e-06, "loss": 0.4918, "step": 620 }, { "epoch": 0.34838709677419355, "grad_norm": 0.49495275870753425, "learning_rate": 9.992163048485776e-06, "loss": 0.4928, "step": 630 }, { "epoch": 0.35391705069124424, "grad_norm": 0.3640423564274247, "learning_rate": 9.990258529164618e-06, "loss": 0.4838, "step": 640 }, { "epoch": 0.35944700460829493, "grad_norm": 0.4420987239801644, "learning_rate": 9.988147279761706e-06, "loss": 0.488, "step": 650 }, { "epoch": 0.3649769585253456, "grad_norm": 0.4511577371212687, "learning_rate": 9.985829387739192e-06, "loss": 0.4985, "step": 660 }, { "epoch": 0.3705069124423963, "grad_norm": 0.4396075419107915, "learning_rate": 9.98330494911976e-06, "loss": 0.4915, "step": 670 }, { "epoch": 0.376036866359447, "grad_norm": 0.4704848369571105, "learning_rate": 9.980574068482635e-06, "loss": 0.4878, "step": 680 }, { "epoch": 0.3815668202764977, "grad_norm": 0.4763102579576698, "learning_rate": 9.977636858959274e-06, "loss": 0.4957, "step": 690 }, { "epoch": 0.3870967741935484, "grad_norm": 0.45436384650049316, "learning_rate": 9.974493442228653e-06, "loss": 0.4871, "step": 700 }, { "epoch": 0.39262672811059907, "grad_norm": 0.4546113951664281, "learning_rate": 9.971143948512239e-06, "loss": 0.4839, "step": 710 }, { "epoch": 0.39815668202764976, "grad_norm": 0.3942291564886981, "learning_rate": 9.967588516568601e-06, "loss": 0.4817, "step": 720 }, { "epoch": 0.40368663594470044, "grad_norm": 0.42410341959833237, "learning_rate": 9.963827293687648e-06, "loss": 0.4926, "step": 730 }, { "epoch": 0.40921658986175113, "grad_norm": 0.5249360145309199, "learning_rate": 9.959860435684534e-06, "loss": 0.4855, "step": 740 }, { "epoch": 0.4147465437788018, "grad_norm": 0.44333787753063203, "learning_rate": 9.95568810689321e-06, "loss": 0.4909, "step": 750 }, { "epoch": 0.4202764976958525, "grad_norm": 0.4571044299213202, "learning_rate": 9.951310480159605e-06, "loss": 0.4808, "step": 760 }, { "epoch": 0.4258064516129032, "grad_norm": 0.404103839654976, "learning_rate": 9.946727736834467e-06, "loss": 0.4816, "step": 770 }, { "epoch": 0.4313364055299539, "grad_norm": 0.4725053041297357, "learning_rate": 9.94194006676586e-06, "loss": 0.4888, "step": 780 }, { "epoch": 0.4368663594470046, "grad_norm": 0.46985417927228335, "learning_rate": 9.936947668291284e-06, "loss": 0.4877, "step": 790 }, { "epoch": 0.4423963133640553, "grad_norm": 0.49996822002708025, "learning_rate": 9.931750748229475e-06, "loss": 0.4804, "step": 800 }, { "epoch": 0.447926267281106, "grad_norm": 0.4531834191607307, "learning_rate": 9.926349521871824e-06, "loss": 0.4795, "step": 810 }, { "epoch": 0.4534562211981567, "grad_norm": 0.37802138341323005, "learning_rate": 9.920744212973468e-06, "loss": 0.4756, "step": 820 }, { "epoch": 0.4589861751152074, "grad_norm": 0.4243052863598972, "learning_rate": 9.91493505374401e-06, "loss": 0.4852, "step": 830 }, { "epoch": 0.4645161290322581, "grad_norm": 0.38897153286113667, "learning_rate": 9.908922284837911e-06, "loss": 0.4816, "step": 840 }, { "epoch": 0.4700460829493088, "grad_norm": 0.39229328262545654, "learning_rate": 9.90270615534451e-06, "loss": 0.485, "step": 850 }, { "epoch": 0.47557603686635946, "grad_norm": 0.4195538643886297, "learning_rate": 9.89628692277771e-06, "loss": 0.4791, "step": 860 }, { "epoch": 0.48110599078341015, "grad_norm": 0.45215319555762606, "learning_rate": 9.889664853065315e-06, "loss": 0.4749, "step": 870 }, { "epoch": 0.48663594470046084, "grad_norm": 0.3934282464522341, "learning_rate": 9.882840220538002e-06, "loss": 0.4847, "step": 880 }, { "epoch": 0.49216589861751153, "grad_norm": 0.45882453815542523, "learning_rate": 9.875813307917966e-06, "loss": 0.4823, "step": 890 }, { "epoch": 0.4976958525345622, "grad_norm": 0.4171659335530635, "learning_rate": 9.8685844063072e-06, "loss": 0.4791, "step": 900 }, { "epoch": 0.5032258064516129, "grad_norm": 0.36877001843415697, "learning_rate": 9.86115381517545e-06, "loss": 0.48, "step": 910 }, { "epoch": 0.5087557603686635, "grad_norm": 0.4248437155717216, "learning_rate": 9.853521842347787e-06, "loss": 0.4821, "step": 920 }, { "epoch": 0.5142857142857142, "grad_norm": 0.3865550402068234, "learning_rate": 9.845688803991873e-06, "loss": 0.4778, "step": 930 }, { "epoch": 0.5198156682027649, "grad_norm": 0.4048712896727712, "learning_rate": 9.837655024604856e-06, "loss": 0.4771, "step": 940 }, { "epoch": 0.5253456221198156, "grad_norm": 0.3928080223641722, "learning_rate": 9.82942083699993e-06, "loss": 0.4711, "step": 950 }, { "epoch": 0.5308755760368664, "grad_norm": 0.4073506281198024, "learning_rate": 9.82098658229254e-06, "loss": 0.4773, "step": 960 }, { "epoch": 0.5364055299539171, "grad_norm": 0.3799265930738453, "learning_rate": 9.812352609886261e-06, "loss": 0.4633, "step": 970 }, { "epoch": 0.5419354838709678, "grad_norm": 0.3791754783762012, "learning_rate": 9.803519277458323e-06, "loss": 0.4786, "step": 980 }, { "epoch": 0.5474654377880185, "grad_norm": 0.3724177446979329, "learning_rate": 9.794486950944775e-06, "loss": 0.4706, "step": 990 }, { "epoch": 0.5529953917050692, "grad_norm": 0.39011612493597525, "learning_rate": 9.785256004525357e-06, "loss": 0.472, "step": 1000 }, { "epoch": 0.5585253456221199, "grad_norm": 0.4159910634501067, "learning_rate": 9.775826820607967e-06, "loss": 0.4684, "step": 1010 }, { "epoch": 0.5640552995391706, "grad_norm": 0.35305967243893827, "learning_rate": 9.766199789812845e-06, "loss": 0.4705, "step": 1020 }, { "epoch": 0.5695852534562212, "grad_norm": 0.3826755145391677, "learning_rate": 9.756375310956375e-06, "loss": 0.4759, "step": 1030 }, { "epoch": 0.5751152073732719, "grad_norm": 0.44126945362012004, "learning_rate": 9.746353791034566e-06, "loss": 0.468, "step": 1040 }, { "epoch": 0.5806451612903226, "grad_norm": 0.3594904638993689, "learning_rate": 9.736135645206198e-06, "loss": 0.4718, "step": 1050 }, { "epoch": 0.5861751152073733, "grad_norm": 0.3757559330794908, "learning_rate": 9.725721296775616e-06, "loss": 0.4727, "step": 1060 }, { "epoch": 0.591705069124424, "grad_norm": 0.39116446398772703, "learning_rate": 9.7151111771752e-06, "loss": 0.4697, "step": 1070 }, { "epoch": 0.5972350230414747, "grad_norm": 0.3968279194826454, "learning_rate": 9.704305725947483e-06, "loss": 0.4698, "step": 1080 }, { "epoch": 0.6027649769585254, "grad_norm": 0.40587146268322655, "learning_rate": 9.693305390726952e-06, "loss": 0.4685, "step": 1090 }, { "epoch": 0.6082949308755761, "grad_norm": 0.377035786368524, "learning_rate": 9.682110627221503e-06, "loss": 0.4654, "step": 1100 }, { "epoch": 0.6138248847926268, "grad_norm": 0.4003895929403935, "learning_rate": 9.670721899193556e-06, "loss": 0.4769, "step": 1110 }, { "epoch": 0.6193548387096774, "grad_norm": 0.45185844229175914, "learning_rate": 9.659139678440845e-06, "loss": 0.4684, "step": 1120 }, { "epoch": 0.6248847926267281, "grad_norm": 0.37936262857073433, "learning_rate": 9.647364444776877e-06, "loss": 0.478, "step": 1130 }, { "epoch": 0.6304147465437788, "grad_norm": 0.42159273587503454, "learning_rate": 9.635396686011052e-06, "loss": 0.4731, "step": 1140 }, { "epoch": 0.6359447004608295, "grad_norm": 0.43046479239329904, "learning_rate": 9.623236897928456e-06, "loss": 0.4685, "step": 1150 }, { "epoch": 0.6414746543778802, "grad_norm": 0.4148842353858753, "learning_rate": 9.61088558426932e-06, "loss": 0.4659, "step": 1160 }, { "epoch": 0.6470046082949309, "grad_norm": 0.39473737868525427, "learning_rate": 9.59834325670815e-06, "loss": 0.4709, "step": 1170 }, { "epoch": 0.6525345622119816, "grad_norm": 0.4015353344240955, "learning_rate": 9.58561043483254e-06, "loss": 0.4751, "step": 1180 }, { "epoch": 0.6580645161290323, "grad_norm": 0.42994188947795353, "learning_rate": 9.572687646121632e-06, "loss": 0.4732, "step": 1190 }, { "epoch": 0.663594470046083, "grad_norm": 0.42736852075339316, "learning_rate": 9.559575425924279e-06, "loss": 0.4665, "step": 1200 }, { "epoch": 0.6691244239631337, "grad_norm": 0.34722978632130697, "learning_rate": 9.546274317436858e-06, "loss": 0.4608, "step": 1210 }, { "epoch": 0.6746543778801843, "grad_norm": 0.37549780094613294, "learning_rate": 9.53278487168077e-06, "loss": 0.4759, "step": 1220 }, { "epoch": 0.680184331797235, "grad_norm": 0.5132407412202136, "learning_rate": 9.519107647479609e-06, "loss": 0.4662, "step": 1230 }, { "epoch": 0.6857142857142857, "grad_norm": 0.4174412166764788, "learning_rate": 9.505243211436023e-06, "loss": 0.4594, "step": 1240 }, { "epoch": 0.6912442396313364, "grad_norm": 0.3916564363860535, "learning_rate": 9.49119213790823e-06, "loss": 0.4715, "step": 1250 }, { "epoch": 0.6967741935483871, "grad_norm": 0.3997293166106522, "learning_rate": 9.476955008986228e-06, "loss": 0.4683, "step": 1260 }, { "epoch": 0.7023041474654378, "grad_norm": 0.3308300953282631, "learning_rate": 9.46253241446768e-06, "loss": 0.4633, "step": 1270 }, { "epoch": 0.7078341013824885, "grad_norm": 0.43602935959437467, "learning_rate": 9.447924951833483e-06, "loss": 0.4656, "step": 1280 }, { "epoch": 0.7133640552995392, "grad_norm": 0.36016668450990325, "learning_rate": 9.433133226223018e-06, "loss": 0.4768, "step": 1290 }, { "epoch": 0.7188940092165899, "grad_norm": 0.3965741821184055, "learning_rate": 9.418157850409075e-06, "loss": 0.4669, "step": 1300 }, { "epoch": 0.7244239631336405, "grad_norm": 0.38734403985392707, "learning_rate": 9.40299944477247e-06, "loss": 0.4765, "step": 1310 }, { "epoch": 0.7299539170506912, "grad_norm": 0.3563445657533695, "learning_rate": 9.387658637276348e-06, "loss": 0.4655, "step": 1320 }, { "epoch": 0.7354838709677419, "grad_norm": 0.3410984943251049, "learning_rate": 9.372136063440165e-06, "loss": 0.4669, "step": 1330 }, { "epoch": 0.7410138248847926, "grad_norm": 0.43850058902455336, "learning_rate": 9.356432366313362e-06, "loss": 0.4601, "step": 1340 }, { "epoch": 0.7465437788018433, "grad_norm": 0.39491440886088125, "learning_rate": 9.340548196448729e-06, "loss": 0.4762, "step": 1350 }, { "epoch": 0.752073732718894, "grad_norm": 0.3843586922714567, "learning_rate": 9.324484211875442e-06, "loss": 0.4639, "step": 1360 }, { "epoch": 0.7576036866359447, "grad_norm": 0.37491204324406624, "learning_rate": 9.30824107807182e-06, "loss": 0.4654, "step": 1370 }, { "epoch": 0.7631336405529954, "grad_norm": 0.4576626954126291, "learning_rate": 9.291819467937746e-06, "loss": 0.4611, "step": 1380 }, { "epoch": 0.7686635944700461, "grad_norm": 0.4394756523970031, "learning_rate": 9.275220061766793e-06, "loss": 0.4619, "step": 1390 }, { "epoch": 0.7741935483870968, "grad_norm": 0.3687712612876861, "learning_rate": 9.258443547218041e-06, "loss": 0.4601, "step": 1400 }, { "epoch": 0.7797235023041474, "grad_norm": 0.37939730644811315, "learning_rate": 9.241490619287593e-06, "loss": 0.4671, "step": 1410 }, { "epoch": 0.7852534562211981, "grad_norm": 0.4503285510527914, "learning_rate": 9.224361980279779e-06, "loss": 0.4631, "step": 1420 }, { "epoch": 0.7907834101382488, "grad_norm": 0.45715075255423665, "learning_rate": 9.207058339778065e-06, "loss": 0.4681, "step": 1430 }, { "epoch": 0.7963133640552995, "grad_norm": 0.3541259878976316, "learning_rate": 9.189580414615658e-06, "loss": 0.457, "step": 1440 }, { "epoch": 0.8018433179723502, "grad_norm": 0.4085052745840183, "learning_rate": 9.171928928845802e-06, "loss": 0.4541, "step": 1450 }, { "epoch": 0.8073732718894009, "grad_norm": 0.3616899823860361, "learning_rate": 9.154104613711798e-06, "loss": 0.4575, "step": 1460 }, { "epoch": 0.8129032258064516, "grad_norm": 0.39971875774962656, "learning_rate": 9.136108207616694e-06, "loss": 0.4695, "step": 1470 }, { "epoch": 0.8184331797235023, "grad_norm": 0.4179584638146379, "learning_rate": 9.117940456092706e-06, "loss": 0.4659, "step": 1480 }, { "epoch": 0.823963133640553, "grad_norm": 0.3835155006911313, "learning_rate": 9.099602111770336e-06, "loss": 0.458, "step": 1490 }, { "epoch": 0.8294930875576036, "grad_norm": 0.36547715603099723, "learning_rate": 9.081093934347178e-06, "loss": 0.4646, "step": 1500 }, { "epoch": 0.8350230414746543, "grad_norm": 0.3295307717464045, "learning_rate": 9.062416690556463e-06, "loss": 0.4602, "step": 1510 }, { "epoch": 0.840552995391705, "grad_norm": 0.34026406181637314, "learning_rate": 9.043571154135285e-06, "loss": 0.4543, "step": 1520 }, { "epoch": 0.8460829493087557, "grad_norm": 0.40280573682285203, "learning_rate": 9.02455810579255e-06, "loss": 0.4669, "step": 1530 }, { "epoch": 0.8516129032258064, "grad_norm": 0.34345937973887686, "learning_rate": 9.005378333176637e-06, "loss": 0.4616, "step": 1540 }, { "epoch": 0.8571428571428571, "grad_norm": 0.34245350990620255, "learning_rate": 8.986032630842767e-06, "loss": 0.4623, "step": 1550 }, { "epoch": 0.8626728110599078, "grad_norm": 0.3852027478756217, "learning_rate": 8.966521800220084e-06, "loss": 0.4629, "step": 1560 }, { "epoch": 0.8682027649769585, "grad_norm": 0.4686461690105208, "learning_rate": 8.946846649578457e-06, "loss": 0.4606, "step": 1570 }, { "epoch": 0.8737327188940092, "grad_norm": 0.3405054745038256, "learning_rate": 8.927007993994997e-06, "loss": 0.4562, "step": 1580 }, { "epoch": 0.8792626728110599, "grad_norm": 0.3692693675496781, "learning_rate": 8.907006655320287e-06, "loss": 0.4558, "step": 1590 }, { "epoch": 0.8847926267281107, "grad_norm": 0.3379877106135158, "learning_rate": 8.886843462144343e-06, "loss": 0.4605, "step": 1600 }, { "epoch": 0.8903225806451613, "grad_norm": 0.36146892614586007, "learning_rate": 8.866519249762275e-06, "loss": 0.464, "step": 1610 }, { "epoch": 0.895852534562212, "grad_norm": 0.3979151729935212, "learning_rate": 8.846034860139706e-06, "loss": 0.465, "step": 1620 }, { "epoch": 0.9013824884792627, "grad_norm": 0.3488713134537118, "learning_rate": 8.82539114187786e-06, "loss": 0.4545, "step": 1630 }, { "epoch": 0.9069124423963134, "grad_norm": 0.37006007621420706, "learning_rate": 8.804588950178439e-06, "loss": 0.4592, "step": 1640 }, { "epoch": 0.9124423963133641, "grad_norm": 0.4218977786755043, "learning_rate": 8.783629146808175e-06, "loss": 0.4623, "step": 1650 }, { "epoch": 0.9179723502304148, "grad_norm": 0.36142612348312186, "learning_rate": 8.762512600063136e-06, "loss": 0.4597, "step": 1660 }, { "epoch": 0.9235023041474655, "grad_norm": 0.37743894605389894, "learning_rate": 8.74124018473276e-06, "loss": 0.4538, "step": 1670 }, { "epoch": 0.9290322580645162, "grad_norm": 0.37370963533147783, "learning_rate": 8.719812782063603e-06, "loss": 0.4547, "step": 1680 }, { "epoch": 0.9345622119815669, "grad_norm": 0.40809993391643884, "learning_rate": 8.698231279722845e-06, "loss": 0.462, "step": 1690 }, { "epoch": 0.9400921658986175, "grad_norm": 0.3756284623011763, "learning_rate": 8.676496571761507e-06, "loss": 0.4513, "step": 1700 }, { "epoch": 0.9456221198156682, "grad_norm": 0.3390495467924666, "learning_rate": 8.65460955857742e-06, "loss": 0.4574, "step": 1710 }, { "epoch": 0.9511520737327189, "grad_norm": 0.3968064162366307, "learning_rate": 8.632571146877924e-06, "loss": 0.4587, "step": 1720 }, { "epoch": 0.9566820276497696, "grad_norm": 0.37489260177502365, "learning_rate": 8.6103822496423e-06, "loss": 0.4614, "step": 1730 }, { "epoch": 0.9622119815668203, "grad_norm": 0.3468923282438075, "learning_rate": 8.588043786083952e-06, "loss": 0.4561, "step": 1740 }, { "epoch": 0.967741935483871, "grad_norm": 0.3742022627413655, "learning_rate": 8.565556681612335e-06, "loss": 0.4521, "step": 1750 }, { "epoch": 0.9732718894009217, "grad_norm": 0.35327369319565305, "learning_rate": 8.542921867794597e-06, "loss": 0.4534, "step": 1760 }, { "epoch": 0.9788018433179724, "grad_norm": 0.39149761577819314, "learning_rate": 8.520140282317018e-06, "loss": 0.4561, "step": 1770 }, { "epoch": 0.9843317972350231, "grad_norm": 0.42419710853826387, "learning_rate": 8.497212868946132e-06, "loss": 0.4496, "step": 1780 }, { "epoch": 0.9898617511520738, "grad_norm": 0.370513055308333, "learning_rate": 8.474140577489652e-06, "loss": 0.4512, "step": 1790 }, { "epoch": 0.9953917050691244, "grad_norm": 0.46731006937418296, "learning_rate": 8.45092436375712e-06, "loss": 0.447, "step": 1800 }, { "epoch": 1.0009216589861751, "grad_norm": 0.43527476672720355, "learning_rate": 8.4275651895203e-06, "loss": 0.4858, "step": 1810 }, { "epoch": 1.0064516129032257, "grad_norm": 0.3927852344244657, "learning_rate": 8.404064022473344e-06, "loss": 0.433, "step": 1820 }, { "epoch": 1.0119815668202765, "grad_norm": 0.44790042998448304, "learning_rate": 8.380421836192705e-06, "loss": 0.4299, "step": 1830 }, { "epoch": 1.017511520737327, "grad_norm": 0.36665409180864517, "learning_rate": 8.356639610096799e-06, "loss": 0.4372, "step": 1840 }, { "epoch": 1.023041474654378, "grad_norm": 0.4154548719085105, "learning_rate": 8.33271832940543e-06, "loss": 0.4153, "step": 1850 }, { "epoch": 1.0285714285714285, "grad_norm": 0.3498424106524037, "learning_rate": 8.308658985098983e-06, "loss": 0.4365, "step": 1860 }, { "epoch": 1.0341013824884793, "grad_norm": 0.3527496476806808, "learning_rate": 8.284462573877367e-06, "loss": 0.4414, "step": 1870 }, { "epoch": 1.0396313364055298, "grad_norm": 0.34095264970889066, "learning_rate": 8.260130098118724e-06, "loss": 0.4373, "step": 1880 }, { "epoch": 1.0451612903225806, "grad_norm": 0.3525020261906649, "learning_rate": 8.235662565837901e-06, "loss": 0.446, "step": 1890 }, { "epoch": 1.0506912442396312, "grad_norm": 0.30559116702498945, "learning_rate": 8.211060990644699e-06, "loss": 0.4293, "step": 1900 }, { "epoch": 1.056221198156682, "grad_norm": 0.37541049203915616, "learning_rate": 8.18632639170188e-06, "loss": 0.4306, "step": 1910 }, { "epoch": 1.0617511520737328, "grad_norm": 0.3896683499442952, "learning_rate": 8.161459793682937e-06, "loss": 0.4338, "step": 1920 }, { "epoch": 1.0672811059907834, "grad_norm": 0.35556240560090524, "learning_rate": 8.136462226729663e-06, "loss": 0.4273, "step": 1930 }, { "epoch": 1.072811059907834, "grad_norm": 0.33870684965626063, "learning_rate": 8.111334726409453e-06, "loss": 0.4275, "step": 1940 }, { "epoch": 1.0783410138248848, "grad_norm": 0.32599049999370167, "learning_rate": 8.08607833367243e-06, "loss": 0.4344, "step": 1950 }, { "epoch": 1.0838709677419356, "grad_norm": 0.37446391533889434, "learning_rate": 8.060694094808295e-06, "loss": 0.4376, "step": 1960 }, { "epoch": 1.0894009216589862, "grad_norm": 0.33002930959463256, "learning_rate": 8.035183061403006e-06, "loss": 0.434, "step": 1970 }, { "epoch": 1.094930875576037, "grad_norm": 0.35423865601253207, "learning_rate": 8.0095462902952e-06, "loss": 0.4201, "step": 1980 }, { "epoch": 1.1004608294930875, "grad_norm": 0.3248427195938627, "learning_rate": 7.983784843532415e-06, "loss": 0.4253, "step": 1990 }, { "epoch": 1.1059907834101383, "grad_norm": 0.34623653882886374, "learning_rate": 7.957899788327092e-06, "loss": 0.4323, "step": 2000 }, { "epoch": 1.111520737327189, "grad_norm": 0.3599295805789168, "learning_rate": 7.93189219701237e-06, "loss": 0.4259, "step": 2010 }, { "epoch": 1.1170506912442397, "grad_norm": 0.38414283548649564, "learning_rate": 7.905763146997652e-06, "loss": 0.4335, "step": 2020 }, { "epoch": 1.1225806451612903, "grad_norm": 0.32382155481213737, "learning_rate": 7.879513720723984e-06, "loss": 0.4395, "step": 2030 }, { "epoch": 1.128110599078341, "grad_norm": 0.32042378851107606, "learning_rate": 7.853145005619199e-06, "loss": 0.426, "step": 2040 }, { "epoch": 1.1336405529953917, "grad_norm": 0.33755347609978986, "learning_rate": 7.826658094052884e-06, "loss": 0.4362, "step": 2050 }, { "epoch": 1.1391705069124425, "grad_norm": 0.39877451031067934, "learning_rate": 7.800054083291114e-06, "loss": 0.428, "step": 2060 }, { "epoch": 1.144700460829493, "grad_norm": 0.31738937325882993, "learning_rate": 7.773334075451e-06, "loss": 0.4413, "step": 2070 }, { "epoch": 1.1502304147465439, "grad_norm": 0.34047775678025793, "learning_rate": 7.746499177455036e-06, "loss": 0.4309, "step": 2080 }, { "epoch": 1.1557603686635944, "grad_norm": 0.324338242448013, "learning_rate": 7.719550500985234e-06, "loss": 0.4315, "step": 2090 }, { "epoch": 1.1612903225806452, "grad_norm": 0.33430643506460095, "learning_rate": 7.69248916243708e-06, "loss": 0.4329, "step": 2100 }, { "epoch": 1.1668202764976958, "grad_norm": 0.3641478085283545, "learning_rate": 7.665316282873281e-06, "loss": 0.4286, "step": 2110 }, { "epoch": 1.1723502304147466, "grad_norm": 0.43045384768424416, "learning_rate": 7.638032987977322e-06, "loss": 0.4247, "step": 2120 }, { "epoch": 1.1778801843317972, "grad_norm": 0.4742558814490241, "learning_rate": 7.610640408006832e-06, "loss": 0.4358, "step": 2130 }, { "epoch": 1.183410138248848, "grad_norm": 0.3728801367095553, "learning_rate": 7.583139677746769e-06, "loss": 0.4261, "step": 2140 }, { "epoch": 1.1889400921658986, "grad_norm": 0.3946467119158356, "learning_rate": 7.555531936462398e-06, "loss": 0.4215, "step": 2150 }, { "epoch": 1.1944700460829494, "grad_norm": 0.42194525138871064, "learning_rate": 7.527818327852101e-06, "loss": 0.4413, "step": 2160 }, { "epoch": 1.2, "grad_norm": 0.3362981808853216, "learning_rate": 7.500000000000001e-06, "loss": 0.4268, "step": 2170 }, { "epoch": 1.2055299539170508, "grad_norm": 0.3603451029762717, "learning_rate": 7.472078105328391e-06, "loss": 0.4264, "step": 2180 }, { "epoch": 1.2110599078341013, "grad_norm": 0.4138525995577666, "learning_rate": 7.444053800550004e-06, "loss": 0.4366, "step": 2190 }, { "epoch": 1.2165898617511521, "grad_norm": 0.39448869972439937, "learning_rate": 7.415928246620086e-06, "loss": 0.4294, "step": 2200 }, { "epoch": 1.2221198156682027, "grad_norm": 0.33343622855975236, "learning_rate": 7.387702608688302e-06, "loss": 0.42, "step": 2210 }, { "epoch": 1.2276497695852535, "grad_norm": 0.33564499515032403, "learning_rate": 7.359378056050472e-06, "loss": 0.4382, "step": 2220 }, { "epoch": 1.233179723502304, "grad_norm": 0.3305094552462621, "learning_rate": 7.3309557621001295e-06, "loss": 0.4362, "step": 2230 }, { "epoch": 1.238709677419355, "grad_norm": 0.3505064540471358, "learning_rate": 7.3024369042799094e-06, "loss": 0.4315, "step": 2240 }, { "epoch": 1.2442396313364055, "grad_norm": 0.4175232059230619, "learning_rate": 7.273822664032771e-06, "loss": 0.4333, "step": 2250 }, { "epoch": 1.2497695852534563, "grad_norm": 0.31440206686096517, "learning_rate": 7.245114226753055e-06, "loss": 0.4302, "step": 2260 }, { "epoch": 1.2552995391705069, "grad_norm": 0.3799967479589324, "learning_rate": 7.2163127817373815e-06, "loss": 0.4416, "step": 2270 }, { "epoch": 1.2608294930875577, "grad_norm": 0.34246345630017244, "learning_rate": 7.1874195221353706e-06, "loss": 0.4315, "step": 2280 }, { "epoch": 1.2663594470046082, "grad_norm": 0.2952208188222985, "learning_rate": 7.158435644900226e-06, "loss": 0.4308, "step": 2290 }, { "epoch": 1.271889400921659, "grad_norm": 0.3364601276348195, "learning_rate": 7.129362350739138e-06, "loss": 0.4271, "step": 2300 }, { "epoch": 1.2774193548387096, "grad_norm": 0.3474139278148847, "learning_rate": 7.1002008440635515e-06, "loss": 0.4305, "step": 2310 }, { "epoch": 1.2829493087557604, "grad_norm": 0.3280092320348997, "learning_rate": 7.070952332939266e-06, "loss": 0.4331, "step": 2320 }, { "epoch": 1.288479262672811, "grad_norm": 0.4223833613636633, "learning_rate": 7.04161802903639e-06, "loss": 0.4327, "step": 2330 }, { "epoch": 1.2940092165898618, "grad_norm": 0.3448536879815269, "learning_rate": 7.012199147579146e-06, "loss": 0.4246, "step": 2340 }, { "epoch": 1.2995391705069124, "grad_norm": 0.3207441765420925, "learning_rate": 6.98269690729553e-06, "loss": 0.4301, "step": 2350 }, { "epoch": 1.3050691244239632, "grad_norm": 0.3165222151173208, "learning_rate": 6.953112530366818e-06, "loss": 0.4261, "step": 2360 }, { "epoch": 1.3105990783410137, "grad_norm": 0.3876615485028844, "learning_rate": 6.923447242376942e-06, "loss": 0.4316, "step": 2370 }, { "epoch": 1.3161290322580645, "grad_norm": 0.37232768341887623, "learning_rate": 6.893702272261711e-06, "loss": 0.4212, "step": 2380 }, { "epoch": 1.3216589861751151, "grad_norm": 0.34637683615909776, "learning_rate": 6.863878852257908e-06, "loss": 0.4334, "step": 2390 }, { "epoch": 1.327188940092166, "grad_norm": 0.35731944832213297, "learning_rate": 6.833978217852233e-06, "loss": 0.4225, "step": 2400 }, { "epoch": 1.3327188940092167, "grad_norm": 0.31517156848331396, "learning_rate": 6.80400160773013e-06, "loss": 0.4254, "step": 2410 }, { "epoch": 1.3382488479262673, "grad_norm": 0.31675935891661117, "learning_rate": 6.773950263724467e-06, "loss": 0.4267, "step": 2420 }, { "epoch": 1.3437788018433179, "grad_norm": 0.35820405964245244, "learning_rate": 6.743825430764091e-06, "loss": 0.4369, "step": 2430 }, { "epoch": 1.3493087557603687, "grad_norm": 0.3198735130417677, "learning_rate": 6.713628356822259e-06, "loss": 0.4334, "step": 2440 }, { "epoch": 1.3548387096774195, "grad_norm": 0.35391376983158945, "learning_rate": 6.683360292864933e-06, "loss": 0.4298, "step": 2450 }, { "epoch": 1.36036866359447, "grad_norm": 0.3447181141751271, "learning_rate": 6.653022492798959e-06, "loss": 0.429, "step": 2460 }, { "epoch": 1.3658986175115206, "grad_norm": 0.32591032190478314, "learning_rate": 6.622616213420125e-06, "loss": 0.4242, "step": 2470 }, { "epoch": 1.3714285714285714, "grad_norm": 0.35079358158009544, "learning_rate": 6.592142714361085e-06, "loss": 0.4299, "step": 2480 }, { "epoch": 1.3769585253456222, "grad_norm": 0.3105061790757026, "learning_rate": 6.561603258039195e-06, "loss": 0.4315, "step": 2490 }, { "epoch": 1.3824884792626728, "grad_norm": 0.366393325245765, "learning_rate": 6.530999109604197e-06, "loss": 0.4244, "step": 2500 }, { "epoch": 1.3880184331797234, "grad_norm": 0.354855687477892, "learning_rate": 6.500331536885819e-06, "loss": 0.425, "step": 2510 }, { "epoch": 1.3935483870967742, "grad_norm": 0.29867754767506527, "learning_rate": 6.469601810341247e-06, "loss": 0.4314, "step": 2520 }, { "epoch": 1.399078341013825, "grad_norm": 0.3631093513648162, "learning_rate": 6.438811203002499e-06, "loss": 0.4246, "step": 2530 }, { "epoch": 1.4046082949308756, "grad_norm": 0.3467860388407693, "learning_rate": 6.407960990423683e-06, "loss": 0.4344, "step": 2540 }, { "epoch": 1.4101382488479262, "grad_norm": 0.31828964825920697, "learning_rate": 6.377052450628159e-06, "loss": 0.4158, "step": 2550 }, { "epoch": 1.415668202764977, "grad_norm": 0.31023813410711815, "learning_rate": 6.346086864055594e-06, "loss": 0.4356, "step": 2560 }, { "epoch": 1.4211981566820278, "grad_norm": 0.332473917922917, "learning_rate": 6.31506551350891e-06, "loss": 0.43, "step": 2570 }, { "epoch": 1.4267281105990783, "grad_norm": 0.3409141756767579, "learning_rate": 6.283989684101155e-06, "loss": 0.4296, "step": 2580 }, { "epoch": 1.432258064516129, "grad_norm": 0.3385052993526194, "learning_rate": 6.252860663202254e-06, "loss": 0.4297, "step": 2590 }, { "epoch": 1.4377880184331797, "grad_norm": 0.32236622569856693, "learning_rate": 6.221679740385684e-06, "loss": 0.4274, "step": 2600 }, { "epoch": 1.4433179723502305, "grad_norm": 0.315316876619347, "learning_rate": 6.190448207375046e-06, "loss": 0.4162, "step": 2610 }, { "epoch": 1.448847926267281, "grad_norm": 0.3376657547389814, "learning_rate": 6.159167357990555e-06, "loss": 0.433, "step": 2620 }, { "epoch": 1.4543778801843317, "grad_norm": 0.32358782865643143, "learning_rate": 6.127838488095448e-06, "loss": 0.4267, "step": 2630 }, { "epoch": 1.4599078341013825, "grad_norm": 0.3756530225009165, "learning_rate": 6.096462895542288e-06, "loss": 0.4373, "step": 2640 }, { "epoch": 1.4654377880184333, "grad_norm": 0.38682543540126985, "learning_rate": 6.065041880119209e-06, "loss": 0.4227, "step": 2650 }, { "epoch": 1.4709677419354839, "grad_norm": 0.38616555341944436, "learning_rate": 6.0335767434960625e-06, "loss": 0.4185, "step": 2660 }, { "epoch": 1.4764976958525344, "grad_norm": 0.3602473989547172, "learning_rate": 6.002068789170497e-06, "loss": 0.4229, "step": 2670 }, { "epoch": 1.4820276497695852, "grad_norm": 0.34024391453280106, "learning_rate": 5.970519322413965e-06, "loss": 0.4325, "step": 2680 }, { "epoch": 1.487557603686636, "grad_norm": 0.334874165318193, "learning_rate": 5.938929650217636e-06, "loss": 0.4325, "step": 2690 }, { "epoch": 1.4930875576036866, "grad_norm": 0.29562689064173814, "learning_rate": 5.9073010812382595e-06, "loss": 0.4171, "step": 2700 }, { "epoch": 1.4986175115207372, "grad_norm": 0.30805696197429483, "learning_rate": 5.875634925743955e-06, "loss": 0.428, "step": 2710 }, { "epoch": 1.504147465437788, "grad_norm": 0.32622309094002283, "learning_rate": 5.843932495559925e-06, "loss": 0.4181, "step": 2720 }, { "epoch": 1.5096774193548388, "grad_norm": 0.33140067437976467, "learning_rate": 5.812195104014119e-06, "loss": 0.4359, "step": 2730 }, { "epoch": 1.5152073732718894, "grad_norm": 0.3233776164901754, "learning_rate": 5.780424065882817e-06, "loss": 0.4241, "step": 2740 }, { "epoch": 1.52073732718894, "grad_norm": 0.3295175080953441, "learning_rate": 5.748620697336165e-06, "loss": 0.4276, "step": 2750 }, { "epoch": 1.5262672811059907, "grad_norm": 0.3051493556807249, "learning_rate": 5.716786315883657e-06, "loss": 0.4332, "step": 2760 }, { "epoch": 1.5317972350230415, "grad_norm": 0.32518469758621127, "learning_rate": 5.6849222403195455e-06, "loss": 0.427, "step": 2770 }, { "epoch": 1.5373271889400921, "grad_norm": 0.3502785279432566, "learning_rate": 5.653029790668221e-06, "loss": 0.4228, "step": 2780 }, { "epoch": 1.5428571428571427, "grad_norm": 0.328626841799296, "learning_rate": 5.621110288129509e-06, "loss": 0.4254, "step": 2790 }, { "epoch": 1.5483870967741935, "grad_norm": 0.34919486039336417, "learning_rate": 5.5891650550239555e-06, "loss": 0.4333, "step": 2800 }, { "epoch": 1.5539170506912443, "grad_norm": 0.31813515025326766, "learning_rate": 5.5571954147380355e-06, "loss": 0.4246, "step": 2810 }, { "epoch": 1.5594470046082949, "grad_norm": 0.33770710120288266, "learning_rate": 5.525202691669335e-06, "loss": 0.4289, "step": 2820 }, { "epoch": 1.5649769585253455, "grad_norm": 0.3169850413623026, "learning_rate": 5.493188211171688e-06, "loss": 0.4303, "step": 2830 }, { "epoch": 1.5705069124423963, "grad_norm": 0.3593536785787455, "learning_rate": 5.461153299500261e-06, "loss": 0.4286, "step": 2840 }, { "epoch": 1.576036866359447, "grad_norm": 0.30079605129375003, "learning_rate": 5.429099283756618e-06, "loss": 0.4299, "step": 2850 }, { "epoch": 1.5815668202764976, "grad_norm": 0.3239103063739578, "learning_rate": 5.3970274918337464e-06, "loss": 0.4162, "step": 2860 }, { "epoch": 1.5870967741935482, "grad_norm": 0.3255485670024084, "learning_rate": 5.364939252361041e-06, "loss": 0.4276, "step": 2870 }, { "epoch": 1.592626728110599, "grad_norm": 0.3301274211586159, "learning_rate": 5.3328358946492634e-06, "loss": 0.4192, "step": 2880 }, { "epoch": 1.5981566820276498, "grad_norm": 0.316100975989548, "learning_rate": 5.3007187486354735e-06, "loss": 0.4283, "step": 2890 }, { "epoch": 1.6036866359447006, "grad_norm": 0.3340521867756924, "learning_rate": 5.268589144827939e-06, "loss": 0.4387, "step": 2900 }, { "epoch": 1.6092165898617512, "grad_norm": 0.298422914640259, "learning_rate": 5.236448414251012e-06, "loss": 0.4332, "step": 2910 }, { "epoch": 1.6147465437788018, "grad_norm": 0.3397319884556222, "learning_rate": 5.204297888389988e-06, "loss": 0.4248, "step": 2920 }, { "epoch": 1.6202764976958526, "grad_norm": 0.30762817141809806, "learning_rate": 5.17213889913595e-06, "loss": 0.4207, "step": 2930 }, { "epoch": 1.6258064516129034, "grad_norm": 0.30525042043948947, "learning_rate": 5.139972778730593e-06, "loss": 0.4232, "step": 2940 }, { "epoch": 1.631336405529954, "grad_norm": 0.38997729074598075, "learning_rate": 5.107800859711032e-06, "loss": 0.4271, "step": 2950 }, { "epoch": 1.6368663594470045, "grad_norm": 0.36592419956378963, "learning_rate": 5.075624474854599e-06, "loss": 0.4247, "step": 2960 }, { "epoch": 1.6423963133640553, "grad_norm": 0.29950858149943177, "learning_rate": 5.0434449571236314e-06, "loss": 0.4168, "step": 2970 }, { "epoch": 1.6479262672811061, "grad_norm": 0.32408588211542844, "learning_rate": 5.01126363961025e-06, "loss": 0.4287, "step": 2980 }, { "epoch": 1.6534562211981567, "grad_norm": 0.3199409766199922, "learning_rate": 4.979081855481136e-06, "loss": 0.4223, "step": 2990 }, { "epoch": 1.6589861751152073, "grad_norm": 0.3308561884228066, "learning_rate": 4.946900937922302e-06, "loss": 0.4219, "step": 3000 }, { "epoch": 1.664516129032258, "grad_norm": 0.316626858385731, "learning_rate": 4.914722220083859e-06, "loss": 0.4331, "step": 3010 }, { "epoch": 1.670046082949309, "grad_norm": 0.40665900945253314, "learning_rate": 4.8825470350247925e-06, "loss": 0.4246, "step": 3020 }, { "epoch": 1.6755760368663595, "grad_norm": 0.3780339341762518, "learning_rate": 4.850376715657736e-06, "loss": 0.4295, "step": 3030 }, { "epoch": 1.68110599078341, "grad_norm": 0.33553921665146924, "learning_rate": 4.81821259469375e-06, "loss": 0.4298, "step": 3040 }, { "epoch": 1.6866359447004609, "grad_norm": 0.34374298733619857, "learning_rate": 4.786056004587125e-06, "loss": 0.423, "step": 3050 }, { "epoch": 1.6921658986175117, "grad_norm": 0.3151480951742569, "learning_rate": 4.753908277480162e-06, "loss": 0.413, "step": 3060 }, { "epoch": 1.6976958525345622, "grad_norm": 0.30161164918082994, "learning_rate": 4.721770745148003e-06, "loss": 0.4278, "step": 3070 }, { "epoch": 1.7032258064516128, "grad_norm": 0.31750652806344676, "learning_rate": 4.689644738943451e-06, "loss": 0.4245, "step": 3080 }, { "epoch": 1.7087557603686636, "grad_norm": 0.3494801701281207, "learning_rate": 4.657531589741822e-06, "loss": 0.4236, "step": 3090 }, { "epoch": 1.7142857142857144, "grad_norm": 0.3449639569803028, "learning_rate": 4.6254326278858056e-06, "loss": 0.4261, "step": 3100 }, { "epoch": 1.719815668202765, "grad_norm": 0.32166503784245665, "learning_rate": 4.593349183130359e-06, "loss": 0.4255, "step": 3110 }, { "epoch": 1.7253456221198156, "grad_norm": 0.3318579047371131, "learning_rate": 4.561282584587612e-06, "loss": 0.4319, "step": 3120 }, { "epoch": 1.7308755760368664, "grad_norm": 0.3194685879222433, "learning_rate": 4.529234160671814e-06, "loss": 0.4206, "step": 3130 }, { "epoch": 1.7364055299539172, "grad_norm": 0.2942895639419189, "learning_rate": 4.497205239044305e-06, "loss": 0.4228, "step": 3140 }, { "epoch": 1.7419354838709677, "grad_norm": 0.357982132475268, "learning_rate": 4.465197146558498e-06, "loss": 0.426, "step": 3150 }, { "epoch": 1.7474654377880183, "grad_norm": 0.3165760814177771, "learning_rate": 4.433211209204928e-06, "loss": 0.4259, "step": 3160 }, { "epoch": 1.7529953917050691, "grad_norm": 0.3275533345265724, "learning_rate": 4.401248752056317e-06, "loss": 0.419, "step": 3170 }, { "epoch": 1.75852534562212, "grad_norm": 0.35208363382480495, "learning_rate": 4.369311099212676e-06, "loss": 0.4285, "step": 3180 }, { "epoch": 1.7640552995391705, "grad_norm": 0.3322400582949709, "learning_rate": 4.337399573746457e-06, "loss": 0.4227, "step": 3190 }, { "epoch": 1.769585253456221, "grad_norm": 0.3318593706128403, "learning_rate": 4.305515497647739e-06, "loss": 0.4169, "step": 3200 }, { "epoch": 1.7751152073732719, "grad_norm": 0.3342118085075894, "learning_rate": 4.273660191769463e-06, "loss": 0.4156, "step": 3210 }, { "epoch": 1.7806451612903227, "grad_norm": 0.3243982851428786, "learning_rate": 4.241834975772715e-06, "loss": 0.4296, "step": 3220 }, { "epoch": 1.7861751152073733, "grad_norm": 0.30024745550956594, "learning_rate": 4.210041168072055e-06, "loss": 0.4155, "step": 3230 }, { "epoch": 1.7917050691244238, "grad_norm": 0.31137799931917143, "learning_rate": 4.1782800857809025e-06, "loss": 0.423, "step": 3240 }, { "epoch": 1.7972350230414746, "grad_norm": 0.34187401190050304, "learning_rate": 4.146553044656967e-06, "loss": 0.4222, "step": 3250 }, { "epoch": 1.8027649769585254, "grad_norm": 0.3233685519538971, "learning_rate": 4.114861359047744e-06, "loss": 0.411, "step": 3260 }, { "epoch": 1.808294930875576, "grad_norm": 0.31178793164096785, "learning_rate": 4.083206341836069e-06, "loss": 0.4244, "step": 3270 }, { "epoch": 1.8138248847926266, "grad_norm": 0.31269926393343633, "learning_rate": 4.051589304385723e-06, "loss": 0.4163, "step": 3280 }, { "epoch": 1.8193548387096774, "grad_norm": 0.3184909825619447, "learning_rate": 4.02001155648711e-06, "loss": 0.4292, "step": 3290 }, { "epoch": 1.8248847926267282, "grad_norm": 0.3028954525575807, "learning_rate": 3.988474406302995e-06, "loss": 0.4258, "step": 3300 }, { "epoch": 1.8304147465437788, "grad_norm": 0.3155454356334078, "learning_rate": 3.956979160314318e-06, "loss": 0.4131, "step": 3310 }, { "epoch": 1.8359447004608294, "grad_norm": 0.28622990953618355, "learning_rate": 3.925527123266059e-06, "loss": 0.4161, "step": 3320 }, { "epoch": 1.8414746543778802, "grad_norm": 0.2945156841734928, "learning_rate": 3.894119598113196e-06, "loss": 0.4298, "step": 3330 }, { "epoch": 1.847004608294931, "grad_norm": 0.33440108206239455, "learning_rate": 3.862757885966726e-06, "loss": 0.4281, "step": 3340 }, { "epoch": 1.8525345622119815, "grad_norm": 0.31936860050567883, "learning_rate": 3.83144328603976e-06, "loss": 0.4212, "step": 3350 }, { "epoch": 1.8580645161290321, "grad_norm": 0.35312174535698115, "learning_rate": 3.800177095593706e-06, "loss": 0.4227, "step": 3360 }, { "epoch": 1.863594470046083, "grad_norm": 0.34861457106320726, "learning_rate": 3.7689606098845264e-06, "loss": 0.431, "step": 3370 }, { "epoch": 1.8691244239631337, "grad_norm": 0.27435811268943505, "learning_rate": 3.737795122109075e-06, "loss": 0.408, "step": 3380 }, { "epoch": 1.8746543778801843, "grad_norm": 0.2838590192840328, "learning_rate": 3.706681923351533e-06, "loss": 0.4181, "step": 3390 }, { "epoch": 1.8801843317972349, "grad_norm": 0.2829660341227658, "learning_rate": 3.675622302529914e-06, "loss": 0.4221, "step": 3400 }, { "epoch": 1.8857142857142857, "grad_norm": 0.3274364986529272, "learning_rate": 3.644617546342678e-06, "loss": 0.4269, "step": 3410 }, { "epoch": 1.8912442396313365, "grad_norm": 0.30334659787980706, "learning_rate": 3.6136689392154186e-06, "loss": 0.4218, "step": 3420 }, { "epoch": 1.896774193548387, "grad_norm": 0.2997371229134624, "learning_rate": 3.582777763247659e-06, "loss": 0.4271, "step": 3430 }, { "epoch": 1.9023041474654376, "grad_norm": 0.2912936491731307, "learning_rate": 3.5519452981597386e-06, "loss": 0.4261, "step": 3440 }, { "epoch": 1.9078341013824884, "grad_norm": 0.31304519994194124, "learning_rate": 3.521172821239796e-06, "loss": 0.4237, "step": 3450 }, { "epoch": 1.9133640552995392, "grad_norm": 0.29223645004148463, "learning_rate": 3.490461607290857e-06, "loss": 0.4206, "step": 3460 }, { "epoch": 1.9188940092165898, "grad_norm": 0.2767982303480485, "learning_rate": 3.4598129285780214e-06, "loss": 0.4239, "step": 3470 }, { "epoch": 1.9244239631336404, "grad_norm": 0.2857900663137054, "learning_rate": 3.4292280547757586e-06, "loss": 0.4274, "step": 3480 }, { "epoch": 1.9299539170506912, "grad_norm": 0.30735872690033156, "learning_rate": 3.398708252915312e-06, "loss": 0.4249, "step": 3490 }, { "epoch": 1.935483870967742, "grad_norm": 0.35018152107887573, "learning_rate": 3.368254787332206e-06, "loss": 0.4224, "step": 3500 }, { "epoch": 1.9410138248847926, "grad_norm": 0.32130245581445155, "learning_rate": 3.337868919613869e-06, "loss": 0.4273, "step": 3510 }, { "epoch": 1.9465437788018434, "grad_norm": 0.3399875563122416, "learning_rate": 3.3075519085473746e-06, "loss": 0.416, "step": 3520 }, { "epoch": 1.952073732718894, "grad_norm": 0.2975964678653707, "learning_rate": 3.277305010067282e-06, "loss": 0.4161, "step": 3530 }, { "epoch": 1.9576036866359448, "grad_norm": 0.32352875000727493, "learning_rate": 3.2471294772036287e-06, "loss": 0.4338, "step": 3540 }, { "epoch": 1.9631336405529956, "grad_norm": 0.26327310896150496, "learning_rate": 3.2170265600299977e-06, "loss": 0.4231, "step": 3550 }, { "epoch": 1.9686635944700461, "grad_norm": 0.30483497487890593, "learning_rate": 3.186997505611745e-06, "loss": 0.4244, "step": 3560 }, { "epoch": 1.9741935483870967, "grad_norm": 0.33975972239987273, "learning_rate": 3.1570435579543333e-06, "loss": 0.4238, "step": 3570 }, { "epoch": 1.9797235023041475, "grad_norm": 0.3449206346574356, "learning_rate": 3.1271659579518e-06, "loss": 0.4251, "step": 3580 }, { "epoch": 1.9852534562211983, "grad_norm": 0.28831583716824516, "learning_rate": 3.097365943335347e-06, "loss": 0.4216, "step": 3590 }, { "epoch": 1.9907834101382489, "grad_norm": 0.3144096706683747, "learning_rate": 3.0676447486220705e-06, "loss": 0.4285, "step": 3600 }, { "epoch": 1.9963133640552995, "grad_norm": 0.290045183909965, "learning_rate": 3.0380036050638106e-06, "loss": 0.4197, "step": 3610 }, { "epoch": 2.0018433179723503, "grad_norm": 0.3238458773243826, "learning_rate": 3.008443740596153e-06, "loss": 0.4474, "step": 3620 }, { "epoch": 2.007373271889401, "grad_norm": 0.3287019922620765, "learning_rate": 2.9789663797875614e-06, "loss": 0.4023, "step": 3630 }, { "epoch": 2.0129032258064514, "grad_norm": 0.29141383184538444, "learning_rate": 2.9495727437886355e-06, "loss": 0.3943, "step": 3640 }, { "epoch": 2.0184331797235022, "grad_norm": 0.29646707994500565, "learning_rate": 2.920264050281533e-06, "loss": 0.4023, "step": 3650 }, { "epoch": 2.023963133640553, "grad_norm": 0.30655398704765174, "learning_rate": 2.8910415134295216e-06, "loss": 0.3968, "step": 3660 }, { "epoch": 2.029493087557604, "grad_norm": 0.2833005227781744, "learning_rate": 2.8619063438266846e-06, "loss": 0.4101, "step": 3670 }, { "epoch": 2.035023041474654, "grad_norm": 0.2968009733215101, "learning_rate": 2.8328597484477582e-06, "loss": 0.3935, "step": 3680 }, { "epoch": 2.040552995391705, "grad_norm": 0.2839483708587392, "learning_rate": 2.803902930598144e-06, "loss": 0.4034, "step": 3690 }, { "epoch": 2.046082949308756, "grad_norm": 0.2707519826472345, "learning_rate": 2.775037089864054e-06, "loss": 0.3941, "step": 3700 }, { "epoch": 2.0516129032258066, "grad_norm": 0.30059219330904746, "learning_rate": 2.7462634220628146e-06, "loss": 0.3981, "step": 3710 }, { "epoch": 2.057142857142857, "grad_norm": 0.29397070675360604, "learning_rate": 2.7175831191933275e-06, "loss": 0.4004, "step": 3720 }, { "epoch": 2.0626728110599077, "grad_norm": 0.3320584432373214, "learning_rate": 2.688997369386698e-06, "loss": 0.3934, "step": 3730 }, { "epoch": 2.0682027649769585, "grad_norm": 0.31494300922463103, "learning_rate": 2.6605073568569993e-06, "loss": 0.394, "step": 3740 }, { "epoch": 2.0737327188940093, "grad_norm": 0.29583460527636174, "learning_rate": 2.6321142618522288e-06, "loss": 0.3989, "step": 3750 }, { "epoch": 2.0792626728110597, "grad_norm": 0.32390817110689435, "learning_rate": 2.603819260605399e-06, "loss": 0.4019, "step": 3760 }, { "epoch": 2.0847926267281105, "grad_norm": 0.2672110867976394, "learning_rate": 2.5756235252858288e-06, "loss": 0.4003, "step": 3770 }, { "epoch": 2.0903225806451613, "grad_norm": 0.3123455250583991, "learning_rate": 2.5475282239505685e-06, "loss": 0.4018, "step": 3780 }, { "epoch": 2.095852534562212, "grad_norm": 0.27691159250970976, "learning_rate": 2.5195345204960196e-06, "loss": 0.4008, "step": 3790 }, { "epoch": 2.1013824884792625, "grad_norm": 0.26123816601956984, "learning_rate": 2.4916435746097166e-06, "loss": 0.3876, "step": 3800 }, { "epoch": 2.1069124423963133, "grad_norm": 0.30637053965231187, "learning_rate": 2.4638565417222816e-06, "loss": 0.3982, "step": 3810 }, { "epoch": 2.112442396313364, "grad_norm": 0.3315750567953371, "learning_rate": 2.436174572959561e-06, "loss": 0.4073, "step": 3820 }, { "epoch": 2.117972350230415, "grad_norm": 0.3105020636320244, "learning_rate": 2.408598815094944e-06, "loss": 0.399, "step": 3830 }, { "epoch": 2.1235023041474657, "grad_norm": 0.27435494573021874, "learning_rate": 2.381130410501845e-06, "loss": 0.4009, "step": 3840 }, { "epoch": 2.129032258064516, "grad_norm": 0.2663389329232196, "learning_rate": 2.353770497106381e-06, "loss": 0.3967, "step": 3850 }, { "epoch": 2.134562211981567, "grad_norm": 0.3194906899085194, "learning_rate": 2.3265202083402376e-06, "loss": 0.4001, "step": 3860 }, { "epoch": 2.1400921658986176, "grad_norm": 0.31197437534194744, "learning_rate": 2.299380673093712e-06, "loss": 0.4033, "step": 3870 }, { "epoch": 2.145622119815668, "grad_norm": 0.29924705453864847, "learning_rate": 2.272353015668942e-06, "loss": 0.3994, "step": 3880 }, { "epoch": 2.1511520737327188, "grad_norm": 0.29115026537537425, "learning_rate": 2.2454383557333358e-06, "loss": 0.4014, "step": 3890 }, { "epoch": 2.1566820276497696, "grad_norm": 0.2834889760546468, "learning_rate": 2.218637808273184e-06, "loss": 0.3998, "step": 3900 }, { "epoch": 2.1622119815668204, "grad_norm": 0.2910305450411384, "learning_rate": 2.1919524835474713e-06, "loss": 0.405, "step": 3910 }, { "epoch": 2.167741935483871, "grad_norm": 0.289932930612974, "learning_rate": 2.1653834870418807e-06, "loss": 0.3896, "step": 3920 }, { "epoch": 2.1732718894009215, "grad_norm": 0.2722298839273463, "learning_rate": 2.1389319194230017e-06, "loss": 0.4003, "step": 3930 }, { "epoch": 2.1788018433179723, "grad_norm": 0.28486359542042644, "learning_rate": 2.1125988764927225e-06, "loss": 0.4013, "step": 3940 }, { "epoch": 2.184331797235023, "grad_norm": 0.29750089176475963, "learning_rate": 2.0863854491428454e-06, "loss": 0.3989, "step": 3950 }, { "epoch": 2.189861751152074, "grad_norm": 0.2766502298353407, "learning_rate": 2.0602927233098908e-06, "loss": 0.3921, "step": 3960 }, { "epoch": 2.1953917050691243, "grad_norm": 0.2789326319161608, "learning_rate": 2.034321779930109e-06, "loss": 0.4001, "step": 3970 }, { "epoch": 2.200921658986175, "grad_norm": 0.3371618622489858, "learning_rate": 2.0084736948947027e-06, "loss": 0.4049, "step": 3980 }, { "epoch": 2.206451612903226, "grad_norm": 0.2783901912695157, "learning_rate": 1.982749539005254e-06, "loss": 0.4041, "step": 3990 }, { "epoch": 2.2119815668202767, "grad_norm": 0.279176756791974, "learning_rate": 1.9571503779293683e-06, "loss": 0.3978, "step": 4000 }, { "epoch": 2.217511520737327, "grad_norm": 0.30608460679313365, "learning_rate": 1.93167727215652e-06, "loss": 0.406, "step": 4010 }, { "epoch": 2.223041474654378, "grad_norm": 0.3151983208092032, "learning_rate": 1.9063312769541348e-06, "loss": 0.3956, "step": 4020 }, { "epoch": 2.2285714285714286, "grad_norm": 0.3005770395178785, "learning_rate": 1.8811134423238513e-06, "loss": 0.3966, "step": 4030 }, { "epoch": 2.2341013824884794, "grad_norm": 0.2940499233107073, "learning_rate": 1.8560248129580422e-06, "loss": 0.4043, "step": 4040 }, { "epoch": 2.23963133640553, "grad_norm": 0.28429612401283494, "learning_rate": 1.8310664281965268e-06, "loss": 0.4076, "step": 4050 }, { "epoch": 2.2451612903225806, "grad_norm": 0.3064049873744565, "learning_rate": 1.8062393219835173e-06, "loss": 0.3972, "step": 4060 }, { "epoch": 2.2506912442396314, "grad_norm": 0.29946204785644764, "learning_rate": 1.7815445228247851e-06, "loss": 0.3945, "step": 4070 }, { "epoch": 2.256221198156682, "grad_norm": 0.2715437304149103, "learning_rate": 1.7569830537450533e-06, "loss": 0.4033, "step": 4080 }, { "epoch": 2.2617511520737326, "grad_norm": 0.2854830351871705, "learning_rate": 1.732555932245616e-06, "loss": 0.3955, "step": 4090 }, { "epoch": 2.2672811059907834, "grad_norm": 0.3147639419603036, "learning_rate": 1.7082641702621856e-06, "loss": 0.3953, "step": 4100 }, { "epoch": 2.272811059907834, "grad_norm": 0.27518159279482673, "learning_rate": 1.6841087741229745e-06, "loss": 0.4021, "step": 4110 }, { "epoch": 2.278341013824885, "grad_norm": 0.3039597096572996, "learning_rate": 1.660090744507003e-06, "loss": 0.4013, "step": 4120 }, { "epoch": 2.2838709677419353, "grad_norm": 0.2998615031450226, "learning_rate": 1.6362110764026473e-06, "loss": 0.4112, "step": 4130 }, { "epoch": 2.289400921658986, "grad_norm": 0.3022483293545665, "learning_rate": 1.6124707590664168e-06, "loss": 0.3993, "step": 4140 }, { "epoch": 2.294930875576037, "grad_norm": 0.2724443752633973, "learning_rate": 1.5888707759819766e-06, "loss": 0.4078, "step": 4150 }, { "epoch": 2.3004608294930877, "grad_norm": 0.30699585205563196, "learning_rate": 1.5654121048194016e-06, "loss": 0.3966, "step": 4160 }, { "epoch": 2.305990783410138, "grad_norm": 0.2774026863139645, "learning_rate": 1.5420957173946772e-06, "loss": 0.3931, "step": 4170 }, { "epoch": 2.311520737327189, "grad_norm": 0.30520288048797833, "learning_rate": 1.5189225796294383e-06, "loss": 0.3963, "step": 4180 }, { "epoch": 2.3170506912442397, "grad_norm": 0.25456512857000035, "learning_rate": 1.4958936515109551e-06, "loss": 0.3937, "step": 4190 }, { "epoch": 2.3225806451612905, "grad_norm": 0.26955539407811574, "learning_rate": 1.4730098870523652e-06, "loss": 0.4004, "step": 4200 }, { "epoch": 2.328110599078341, "grad_norm": 0.2793395228272683, "learning_rate": 1.450272234253149e-06, "loss": 0.4014, "step": 4210 }, { "epoch": 2.3336405529953916, "grad_norm": 0.2670008731741953, "learning_rate": 1.427681635059861e-06, "loss": 0.399, "step": 4220 }, { "epoch": 2.3391705069124424, "grad_norm": 0.26366634919045073, "learning_rate": 1.4052390253271037e-06, "loss": 0.3967, "step": 4230 }, { "epoch": 2.3447004608294932, "grad_norm": 0.2736550342611439, "learning_rate": 1.3829453347787626e-06, "loss": 0.4053, "step": 4240 }, { "epoch": 2.3502304147465436, "grad_norm": 0.2658041185832838, "learning_rate": 1.3608014869694869e-06, "loss": 0.3965, "step": 4250 }, { "epoch": 2.3557603686635944, "grad_norm": 0.2663003739913603, "learning_rate": 1.3388083992464335e-06, "loss": 0.408, "step": 4260 }, { "epoch": 2.361290322580645, "grad_norm": 0.3046466052962007, "learning_rate": 1.3169669827112603e-06, "loss": 0.4036, "step": 4270 }, { "epoch": 2.366820276497696, "grad_norm": 0.2895481931800935, "learning_rate": 1.2952781421823846e-06, "loss": 0.3936, "step": 4280 }, { "epoch": 2.3723502304147464, "grad_norm": 0.2677071356544069, "learning_rate": 1.2737427761575006e-06, "loss": 0.4006, "step": 4290 }, { "epoch": 2.377880184331797, "grad_norm": 0.29306704953880125, "learning_rate": 1.2523617767763535e-06, "loss": 0.3994, "step": 4300 }, { "epoch": 2.383410138248848, "grad_norm": 0.2739530738988769, "learning_rate": 1.2311360297837849e-06, "loss": 0.4001, "step": 4310 }, { "epoch": 2.3889400921658988, "grad_norm": 0.27681408852313116, "learning_rate": 1.210066414493039e-06, "loss": 0.3924, "step": 4320 }, { "epoch": 2.394470046082949, "grad_norm": 0.30545245080294625, "learning_rate": 1.1891538037493322e-06, "loss": 0.4044, "step": 4330 }, { "epoch": 2.4, "grad_norm": 0.26864664635574714, "learning_rate": 1.1683990638936981e-06, "loss": 0.4017, "step": 4340 }, { "epoch": 2.4055299539170507, "grad_norm": 0.2944152586026279, "learning_rate": 1.147803054727095e-06, "loss": 0.401, "step": 4350 }, { "epoch": 2.4110599078341015, "grad_norm": 0.282595000728746, "learning_rate": 1.1273666294747886e-06, "loss": 0.4003, "step": 4360 }, { "epoch": 2.4165898617511523, "grad_norm": 0.28429008222935853, "learning_rate": 1.1070906347510051e-06, "loss": 0.3955, "step": 4370 }, { "epoch": 2.4221198156682027, "grad_norm": 0.2831830240980828, "learning_rate": 1.0869759105238592e-06, "loss": 0.3981, "step": 4380 }, { "epoch": 2.4276497695852535, "grad_norm": 0.30047729151565855, "learning_rate": 1.0670232900805561e-06, "loss": 0.3979, "step": 4390 }, { "epoch": 2.4331797235023043, "grad_norm": 0.27151153552568635, "learning_rate": 1.0472335999928712e-06, "loss": 0.398, "step": 4400 }, { "epoch": 2.4387096774193546, "grad_norm": 0.26079113997988657, "learning_rate": 1.0276076600829094e-06, "loss": 0.3928, "step": 4410 }, { "epoch": 2.4442396313364054, "grad_norm": 0.2943190568488448, "learning_rate": 1.008146283389142e-06, "loss": 0.4051, "step": 4420 }, { "epoch": 2.4497695852534562, "grad_norm": 0.29471175081496465, "learning_rate": 9.888502761327235e-07, "loss": 0.4016, "step": 4430 }, { "epoch": 2.455299539170507, "grad_norm": 0.2828161001369082, "learning_rate": 9.697204376840936e-07, "loss": 0.3955, "step": 4440 }, { "epoch": 2.460829493087558, "grad_norm": 0.2700457496469629, "learning_rate": 9.50757560529863e-07, "loss": 0.3999, "step": 4450 }, { "epoch": 2.466359447004608, "grad_norm": 0.28527113567956547, "learning_rate": 9.319624302399827e-07, "loss": 0.3976, "step": 4460 }, { "epoch": 2.471889400921659, "grad_norm": 0.2913598279022557, "learning_rate": 9.133358254351982e-07, "loss": 0.3959, "step": 4470 }, { "epoch": 2.47741935483871, "grad_norm": 0.2528128242967444, "learning_rate": 8.948785177547975e-07, "loss": 0.3999, "step": 4480 }, { "epoch": 2.48294930875576, "grad_norm": 0.28379973900510885, "learning_rate": 8.765912718246423e-07, "loss": 0.3943, "step": 4490 }, { "epoch": 2.488479262672811, "grad_norm": 0.3067123055839093, "learning_rate": 8.584748452254888e-07, "loss": 0.3979, "step": 4500 }, { "epoch": 2.4940092165898617, "grad_norm": 0.2753166288210943, "learning_rate": 8.405299884616142e-07, "loss": 0.3942, "step": 4510 }, { "epoch": 2.4995391705069125, "grad_norm": 0.28727455911235195, "learning_rate": 8.227574449297137e-07, "loss": 0.4003, "step": 4520 }, { "epoch": 2.5050691244239633, "grad_norm": 0.2743598195044324, "learning_rate": 8.051579508881107e-07, "loss": 0.3952, "step": 4530 }, { "epoch": 2.5105990783410137, "grad_norm": 0.2693576075557049, "learning_rate": 7.877322354262545e-07, "loss": 0.4033, "step": 4540 }, { "epoch": 2.5161290322580645, "grad_norm": 0.2896358229000151, "learning_rate": 7.704810204345154e-07, "loss": 0.4005, "step": 4550 }, { "epoch": 2.5216589861751153, "grad_norm": 0.28471183419181173, "learning_rate": 7.534050205742827e-07, "loss": 0.3914, "step": 4560 }, { "epoch": 2.5271889400921657, "grad_norm": 0.2594303056396339, "learning_rate": 7.365049432483529e-07, "loss": 0.4032, "step": 4570 }, { "epoch": 2.5327188940092165, "grad_norm": 0.29975502440359814, "learning_rate": 7.19781488571632e-07, "loss": 0.4039, "step": 4580 }, { "epoch": 2.5382488479262673, "grad_norm": 0.272206139015925, "learning_rate": 7.032353493421213e-07, "loss": 0.403, "step": 4590 }, { "epoch": 2.543778801843318, "grad_norm": 0.27442194973354395, "learning_rate": 6.868672110122271e-07, "loss": 0.4, "step": 4600 }, { "epoch": 2.549308755760369, "grad_norm": 0.26622819466668635, "learning_rate": 6.706777516603636e-07, "loss": 0.4064, "step": 4610 }, { "epoch": 2.554838709677419, "grad_norm": 0.2921603411199283, "learning_rate": 6.546676419628545e-07, "loss": 0.398, "step": 4620 }, { "epoch": 2.56036866359447, "grad_norm": 0.2634896902237433, "learning_rate": 6.388375451661578e-07, "loss": 0.3958, "step": 4630 }, { "epoch": 2.565898617511521, "grad_norm": 0.2578581966184642, "learning_rate": 6.231881170593828e-07, "loss": 0.3983, "step": 4640 }, { "epoch": 2.571428571428571, "grad_norm": 0.2816419136865501, "learning_rate": 6.077200059471289e-07, "loss": 0.3993, "step": 4650 }, { "epoch": 2.576958525345622, "grad_norm": 0.25487527822128436, "learning_rate": 5.924338526226259e-07, "loss": 0.3856, "step": 4660 }, { "epoch": 2.5824884792626728, "grad_norm": 0.25615420713688475, "learning_rate": 5.773302903411848e-07, "loss": 0.3943, "step": 4670 }, { "epoch": 2.5880184331797236, "grad_norm": 0.25869788749142564, "learning_rate": 5.624099447939696e-07, "loss": 0.3997, "step": 4680 }, { "epoch": 2.5935483870967744, "grad_norm": 0.27630938101238434, "learning_rate": 5.476734340820738e-07, "loss": 0.3914, "step": 4690 }, { "epoch": 2.5990783410138247, "grad_norm": 0.29080902856797114, "learning_rate": 5.331213686909159e-07, "loss": 0.4052, "step": 4700 }, { "epoch": 2.6046082949308755, "grad_norm": 0.27150428918656966, "learning_rate": 5.187543514649479e-07, "loss": 0.3987, "step": 4710 }, { "epoch": 2.6101382488479263, "grad_norm": 0.2814113138950482, "learning_rate": 5.045729775826818e-07, "loss": 0.4, "step": 4720 }, { "epoch": 2.6156682027649767, "grad_norm": 0.26628699037750947, "learning_rate": 4.905778345320339e-07, "loss": 0.4046, "step": 4730 }, { "epoch": 2.6211981566820275, "grad_norm": 0.2679284474349017, "learning_rate": 4.767695020859847e-07, "loss": 0.3989, "step": 4740 }, { "epoch": 2.6267281105990783, "grad_norm": 0.304861228416287, "learning_rate": 4.6314855227856505e-07, "loss": 0.3966, "step": 4750 }, { "epoch": 2.632258064516129, "grad_norm": 0.28378340208874464, "learning_rate": 4.497155493811539e-07, "loss": 0.3923, "step": 4760 }, { "epoch": 2.63778801843318, "grad_norm": 0.2720375532229136, "learning_rate": 4.3647104987910636e-07, "loss": 0.3983, "step": 4770 }, { "epoch": 2.6433179723502302, "grad_norm": 0.2648120126986214, "learning_rate": 4.2341560244869797e-07, "loss": 0.3925, "step": 4780 }, { "epoch": 2.648847926267281, "grad_norm": 0.30311062145568735, "learning_rate": 4.1054974793439504e-07, "loss": 0.3986, "step": 4790 }, { "epoch": 2.654377880184332, "grad_norm": 0.26568936508620244, "learning_rate": 3.978740193264524e-07, "loss": 0.3921, "step": 4800 }, { "epoch": 2.6599078341013827, "grad_norm": 0.2710800781363938, "learning_rate": 3.853889417388279e-07, "loss": 0.3984, "step": 4810 }, { "epoch": 2.6654377880184335, "grad_norm": 0.2676349044854644, "learning_rate": 3.730950323874322e-07, "loss": 0.3977, "step": 4820 }, { "epoch": 2.670967741935484, "grad_norm": 0.28364404186426295, "learning_rate": 3.6099280056870136e-07, "loss": 0.4008, "step": 4830 }, { "epoch": 2.6764976958525346, "grad_norm": 0.27479432043235197, "learning_rate": 3.490827476385006e-07, "loss": 0.4006, "step": 4840 }, { "epoch": 2.6820276497695854, "grad_norm": 0.2801115377310389, "learning_rate": 3.373653669913479e-07, "loss": 0.3973, "step": 4850 }, { "epoch": 2.6875576036866358, "grad_norm": 0.26687736410074, "learning_rate": 3.258411440399839e-07, "loss": 0.3921, "step": 4860 }, { "epoch": 2.6930875576036866, "grad_norm": 0.26749077132763405, "learning_rate": 3.1451055619525495e-07, "loss": 0.401, "step": 4870 }, { "epoch": 2.6986175115207374, "grad_norm": 0.2477585356057615, "learning_rate": 3.0337407284634023e-07, "loss": 0.4003, "step": 4880 }, { "epoch": 2.704147465437788, "grad_norm": 0.2577396288674699, "learning_rate": 2.924321553413029e-07, "loss": 0.4003, "step": 4890 }, { "epoch": 2.709677419354839, "grad_norm": 0.25584827001987803, "learning_rate": 2.8168525696798287e-07, "loss": 0.3932, "step": 4900 }, { "epoch": 2.7152073732718893, "grad_norm": 0.24937840132532715, "learning_rate": 2.7113382293521285e-07, "loss": 0.3935, "step": 4910 }, { "epoch": 2.72073732718894, "grad_norm": 0.27907536990926873, "learning_rate": 2.607782903543782e-07, "loss": 0.4059, "step": 4920 }, { "epoch": 2.726267281105991, "grad_norm": 0.2646543562986845, "learning_rate": 2.5061908822131e-07, "loss": 0.3842, "step": 4930 }, { "epoch": 2.7317972350230413, "grad_norm": 0.2471190703893049, "learning_rate": 2.406566373985075e-07, "loss": 0.3952, "step": 4940 }, { "epoch": 2.737327188940092, "grad_norm": 0.31897120592126615, "learning_rate": 2.3089135059771007e-07, "loss": 0.4097, "step": 4950 }, { "epoch": 2.742857142857143, "grad_norm": 0.2805170269928884, "learning_rate": 2.2132363236279654e-07, "loss": 0.402, "step": 4960 }, { "epoch": 2.7483870967741937, "grad_norm": 0.2653861937229007, "learning_rate": 2.1195387905302511e-07, "loss": 0.3986, "step": 4970 }, { "epoch": 2.7539170506912445, "grad_norm": 0.2730399737644054, "learning_rate": 2.0278247882661584e-07, "loss": 0.3925, "step": 4980 }, { "epoch": 2.759447004608295, "grad_norm": 0.26909939634669794, "learning_rate": 1.9380981162466895e-07, "loss": 0.3967, "step": 4990 }, { "epoch": 2.7649769585253456, "grad_norm": 0.25520919828788585, "learning_rate": 1.8503624915542805e-07, "loss": 0.3958, "step": 5000 }, { "epoch": 2.7705069124423964, "grad_norm": 0.2671702254098107, "learning_rate": 1.7646215487887587e-07, "loss": 0.3972, "step": 5010 }, { "epoch": 2.776036866359447, "grad_norm": 0.27339509483158747, "learning_rate": 1.680878839916833e-07, "loss": 0.3954, "step": 5020 }, { "epoch": 2.7815668202764976, "grad_norm": 0.26926037978444856, "learning_rate": 1.5991378341249032e-07, "loss": 0.3909, "step": 5030 }, { "epoch": 2.7870967741935484, "grad_norm": 0.2829092539377384, "learning_rate": 1.5194019176753615e-07, "loss": 0.3987, "step": 5040 }, { "epoch": 2.792626728110599, "grad_norm": 0.3050896133507036, "learning_rate": 1.441674393766318e-07, "loss": 0.4025, "step": 5050 }, { "epoch": 2.79815668202765, "grad_norm": 0.2856518392105625, "learning_rate": 1.3659584823947524e-07, "loss": 0.3959, "step": 5060 }, { "epoch": 2.8036866359447004, "grad_norm": 0.2687721431412885, "learning_rate": 1.2922573202231114e-07, "loss": 0.3981, "step": 5070 }, { "epoch": 2.809216589861751, "grad_norm": 0.26981891331331803, "learning_rate": 1.2205739604493838e-07, "loss": 0.4043, "step": 5080 }, { "epoch": 2.814746543778802, "grad_norm": 0.27405104128549934, "learning_rate": 1.1509113726805965e-07, "loss": 0.3903, "step": 5090 }, { "epoch": 2.8202764976958523, "grad_norm": 0.28208244890965906, "learning_rate": 1.0832724428098185e-07, "loss": 0.3964, "step": 5100 }, { "epoch": 2.825806451612903, "grad_norm": 0.2763730332681255, "learning_rate": 1.0176599728965842e-07, "loss": 0.3975, "step": 5110 }, { "epoch": 2.831336405529954, "grad_norm": 0.2678730622209392, "learning_rate": 9.540766810508196e-08, "loss": 0.3966, "step": 5120 }, { "epoch": 2.8368663594470047, "grad_norm": 0.2701400907907813, "learning_rate": 8.925252013202545e-08, "loss": 0.3974, "step": 5130 }, { "epoch": 2.8423963133640555, "grad_norm": 0.2585458146463293, "learning_rate": 8.330080835812826e-08, "loss": 0.3915, "step": 5140 }, { "epoch": 2.847926267281106, "grad_norm": 0.23930472824369428, "learning_rate": 7.75527793433345e-08, "loss": 0.3959, "step": 5150 }, { "epoch": 2.8534562211981567, "grad_norm": 0.27899399555881804, "learning_rate": 7.20086712096768e-08, "loss": 0.4048, "step": 5160 }, { "epoch": 2.8589861751152075, "grad_norm": 0.834759001453546, "learning_rate": 6.666871363141426e-08, "loss": 0.4008, "step": 5170 }, { "epoch": 2.864516129032258, "grad_norm": 0.26729552891819924, "learning_rate": 6.153312782551546e-08, "loss": 0.3943, "step": 5180 }, { "epoch": 2.8700460829493086, "grad_norm": 0.28300940951846, "learning_rate": 5.6602126542496525e-08, "loss": 0.4068, "step": 5190 }, { "epoch": 2.8755760368663594, "grad_norm": 0.2863970268789953, "learning_rate": 5.187591405760528e-08, "loss": 0.3978, "step": 5200 }, { "epoch": 2.8811059907834102, "grad_norm": 0.25831402266128894, "learning_rate": 4.7354686162359165e-08, "loss": 0.4013, "step": 5210 }, { "epoch": 2.886635944700461, "grad_norm": 0.28023244054969493, "learning_rate": 4.3038630156436166e-08, "loss": 0.3905, "step": 5220 }, { "epoch": 2.8921658986175114, "grad_norm": 0.2661529733653034, "learning_rate": 3.8927924839913257e-08, "loss": 0.393, "step": 5230 }, { "epoch": 2.897695852534562, "grad_norm": 0.25493956535145407, "learning_rate": 3.502274050586063e-08, "loss": 0.4006, "step": 5240 }, { "epoch": 2.903225806451613, "grad_norm": 0.26543797268631775, "learning_rate": 3.1323238933286814e-08, "loss": 0.3978, "step": 5250 }, { "epoch": 2.9087557603686633, "grad_norm": 0.26274051264290293, "learning_rate": 2.7829573380436793e-08, "loss": 0.4029, "step": 5260 }, { "epoch": 2.914285714285714, "grad_norm": 0.281124942017121, "learning_rate": 2.4541888578442085e-08, "loss": 0.3915, "step": 5270 }, { "epoch": 2.919815668202765, "grad_norm": 0.2560745200044448, "learning_rate": 2.1460320725326113e-08, "loss": 0.392, "step": 5280 }, { "epoch": 2.9253456221198157, "grad_norm": 0.2679757306919012, "learning_rate": 1.8584997480361467e-08, "loss": 0.4023, "step": 5290 }, { "epoch": 2.9308755760368665, "grad_norm": 0.26744986991724706, "learning_rate": 1.5916037958781938e-08, "loss": 0.3966, "step": 5300 }, { "epoch": 2.936405529953917, "grad_norm": 0.25508086605530733, "learning_rate": 1.3453552726847008e-08, "loss": 0.4018, "step": 5310 }, { "epoch": 2.9419354838709677, "grad_norm": 0.27916128301046206, "learning_rate": 1.1197643797261626e-08, "loss": 0.4027, "step": 5320 }, { "epoch": 2.9474654377880185, "grad_norm": 0.2750137090266509, "learning_rate": 9.148404624951812e-09, "loss": 0.4033, "step": 5330 }, { "epoch": 2.952995391705069, "grad_norm": 0.2725446012014818, "learning_rate": 7.3059201031899786e-09, "loss": 0.3962, "step": 5340 }, { "epoch": 2.9585253456221197, "grad_norm": 0.2815517448254806, "learning_rate": 5.670266560081628e-09, "loss": 0.4014, "step": 5350 }, { "epoch": 2.9640552995391705, "grad_norm": 0.27490789785492287, "learning_rate": 4.241511755400662e-09, "loss": 0.4113, "step": 5360 }, { "epoch": 2.9695852534562213, "grad_norm": 0.2939191489301333, "learning_rate": 3.0197148777838524e-09, "loss": 0.3967, "step": 5370 }, { "epoch": 2.975115207373272, "grad_norm": 0.271422595495557, "learning_rate": 2.0049265422772414e-09, "loss": 0.3993, "step": 5380 }, { "epoch": 2.9806451612903224, "grad_norm": 0.26327553337631326, "learning_rate": 1.1971887882405997e-09, "loss": 0.4024, "step": 5390 }, { "epoch": 2.986175115207373, "grad_norm": 0.2805409873853394, "learning_rate": 5.965350776071521e-10, "loss": 0.4049, "step": 5400 }, { "epoch": 2.991705069124424, "grad_norm": 0.25201401300926546, "learning_rate": 2.029902934941319e-10, "loss": 0.3993, "step": 5410 }, { "epoch": 2.9972350230414744, "grad_norm": 0.2495374923869934, "learning_rate": 1.6570739174714967e-11, "loss": 0.3964, "step": 5420 }, { "epoch": 2.999447004608295, "step": 5424, "total_flos": 8192265561309184.0, "train_loss": 0.4416485577162388, "train_runtime": 91348.8221, "train_samples_per_second": 5.7, "train_steps_per_second": 0.059 } ], "logging_steps": 10, "max_steps": 5424, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 8192265561309184.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }