{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.977587343441002, "eval_steps": 500, "global_step": 3000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 4.98901340364755e-05, "loss": 1.7796, "step": 10 }, { "epoch": 0.01, "learning_rate": 4.9780268072951005e-05, "loss": 1.7713, "step": 20 }, { "epoch": 0.02, "learning_rate": 4.96704021094265e-05, "loss": 1.7176, "step": 30 }, { "epoch": 0.03, "learning_rate": 4.9560536145902e-05, "loss": 1.6604, "step": 40 }, { "epoch": 0.03, "learning_rate": 4.94506701823775e-05, "loss": 1.6656, "step": 50 }, { "epoch": 0.04, "learning_rate": 4.9340804218853e-05, "loss": 1.6062, "step": 60 }, { "epoch": 0.05, "learning_rate": 4.92309382553285e-05, "loss": 1.5675, "step": 70 }, { "epoch": 0.05, "learning_rate": 4.9121072291804e-05, "loss": 1.5991, "step": 80 }, { "epoch": 0.06, "learning_rate": 4.90112063282795e-05, "loss": 1.5755, "step": 90 }, { "epoch": 0.07, "learning_rate": 4.8901340364755e-05, "loss": 1.5343, "step": 100 }, { "epoch": 0.07, "learning_rate": 4.8791474401230506e-05, "loss": 1.5777, "step": 110 }, { "epoch": 0.08, "learning_rate": 4.8681608437706e-05, "loss": 1.5148, "step": 120 }, { "epoch": 0.09, "learning_rate": 4.85717424741815e-05, "loss": 1.514, "step": 130 }, { "epoch": 0.09, "learning_rate": 4.8461876510657e-05, "loss": 1.5594, "step": 140 }, { "epoch": 0.1, "learning_rate": 4.83520105471325e-05, "loss": 1.5238, "step": 150 }, { "epoch": 0.11, "learning_rate": 4.8242144583608e-05, "loss": 1.5445, "step": 160 }, { "epoch": 0.11, "learning_rate": 4.81322786200835e-05, "loss": 1.4958, "step": 170 }, { "epoch": 0.12, "learning_rate": 4.8022412656559004e-05, "loss": 1.531, "step": 180 }, { "epoch": 0.13, "learning_rate": 4.79125466930345e-05, "loss": 1.4877, "step": 190 }, { "epoch": 0.13, "learning_rate": 4.780268072951e-05, "loss": 1.5099, "step": 200 }, { "epoch": 0.14, "learning_rate": 4.76928147659855e-05, "loss": 1.5628, "step": 210 }, { "epoch": 0.15, "learning_rate": 4.7582948802461e-05, "loss": 1.5843, "step": 220 }, { "epoch": 0.15, "learning_rate": 4.74730828389365e-05, "loss": 1.4917, "step": 230 }, { "epoch": 0.16, "learning_rate": 4.7363216875412e-05, "loss": 1.5552, "step": 240 }, { "epoch": 0.16, "learning_rate": 4.72533509118875e-05, "loss": 1.5284, "step": 250 }, { "epoch": 0.17, "learning_rate": 4.7143484948363e-05, "loss": 1.5283, "step": 260 }, { "epoch": 0.18, "learning_rate": 4.70336189848385e-05, "loss": 1.5425, "step": 270 }, { "epoch": 0.18, "learning_rate": 4.6923753021313996e-05, "loss": 1.5408, "step": 280 }, { "epoch": 0.19, "learning_rate": 4.68138870577895e-05, "loss": 1.5508, "step": 290 }, { "epoch": 0.2, "learning_rate": 4.6704021094265e-05, "loss": 1.5359, "step": 300 }, { "epoch": 0.2, "learning_rate": 4.6594155130740496e-05, "loss": 1.5042, "step": 310 }, { "epoch": 0.21, "learning_rate": 4.6484289167216e-05, "loss": 1.5511, "step": 320 }, { "epoch": 0.22, "learning_rate": 4.63744232036915e-05, "loss": 1.5468, "step": 330 }, { "epoch": 0.22, "learning_rate": 4.6264557240167003e-05, "loss": 1.4891, "step": 340 }, { "epoch": 0.23, "learning_rate": 4.6154691276642495e-05, "loss": 1.5386, "step": 350 }, { "epoch": 0.24, "learning_rate": 4.6044825313118e-05, "loss": 1.525, "step": 360 }, { "epoch": 0.24, "learning_rate": 4.59349593495935e-05, "loss": 1.5367, "step": 370 }, { "epoch": 0.25, "learning_rate": 4.5825093386068995e-05, "loss": 1.5011, "step": 380 }, { "epoch": 0.26, "learning_rate": 4.57152274225445e-05, "loss": 1.5259, "step": 390 }, { "epoch": 0.26, "learning_rate": 4.560536145902e-05, "loss": 1.4764, "step": 400 }, { "epoch": 0.27, "learning_rate": 4.54954954954955e-05, "loss": 1.5166, "step": 410 }, { "epoch": 0.28, "learning_rate": 4.5385629531971e-05, "loss": 1.5049, "step": 420 }, { "epoch": 0.28, "learning_rate": 4.52757635684465e-05, "loss": 1.5383, "step": 430 }, { "epoch": 0.29, "learning_rate": 4.5165897604921995e-05, "loss": 1.5166, "step": 440 }, { "epoch": 0.3, "learning_rate": 4.505603164139749e-05, "loss": 1.5898, "step": 450 }, { "epoch": 0.3, "learning_rate": 4.4946165677873e-05, "loss": 1.5512, "step": 460 }, { "epoch": 0.31, "learning_rate": 4.4836299714348496e-05, "loss": 1.5215, "step": 470 }, { "epoch": 0.32, "learning_rate": 4.4726433750824e-05, "loss": 1.5372, "step": 480 }, { "epoch": 0.32, "learning_rate": 4.46165677872995e-05, "loss": 1.4994, "step": 490 }, { "epoch": 0.33, "learning_rate": 4.4506701823774996e-05, "loss": 1.5261, "step": 500 }, { "epoch": 0.34, "learning_rate": 4.4396835860250494e-05, "loss": 1.523, "step": 510 }, { "epoch": 0.34, "learning_rate": 4.428696989672599e-05, "loss": 1.5369, "step": 520 }, { "epoch": 0.35, "learning_rate": 4.4177103933201496e-05, "loss": 1.5606, "step": 530 }, { "epoch": 0.36, "learning_rate": 4.4067237969676994e-05, "loss": 1.5142, "step": 540 }, { "epoch": 0.36, "learning_rate": 4.39573720061525e-05, "loss": 1.4941, "step": 550 }, { "epoch": 0.37, "learning_rate": 4.3847506042627997e-05, "loss": 1.5467, "step": 560 }, { "epoch": 0.38, "learning_rate": 4.37376400791035e-05, "loss": 1.5277, "step": 570 }, { "epoch": 0.38, "learning_rate": 4.362777411557899e-05, "loss": 1.5358, "step": 580 }, { "epoch": 0.39, "learning_rate": 4.351790815205449e-05, "loss": 1.5611, "step": 590 }, { "epoch": 0.4, "learning_rate": 4.3408042188529995e-05, "loss": 1.4959, "step": 600 }, { "epoch": 0.4, "learning_rate": 4.329817622500549e-05, "loss": 1.5214, "step": 610 }, { "epoch": 0.41, "learning_rate": 4.3188310261481e-05, "loss": 1.4937, "step": 620 }, { "epoch": 0.42, "learning_rate": 4.3078444297956495e-05, "loss": 1.5066, "step": 630 }, { "epoch": 0.42, "learning_rate": 4.2968578334432e-05, "loss": 1.5101, "step": 640 }, { "epoch": 0.43, "learning_rate": 4.28587123709075e-05, "loss": 1.5346, "step": 650 }, { "epoch": 0.44, "learning_rate": 4.2748846407382995e-05, "loss": 1.5236, "step": 660 }, { "epoch": 0.44, "learning_rate": 4.263898044385849e-05, "loss": 1.5401, "step": 670 }, { "epoch": 0.45, "learning_rate": 4.252911448033399e-05, "loss": 1.5027, "step": 680 }, { "epoch": 0.45, "learning_rate": 4.2419248516809496e-05, "loss": 1.5197, "step": 690 }, { "epoch": 0.46, "learning_rate": 4.2309382553284993e-05, "loss": 1.5357, "step": 700 }, { "epoch": 0.47, "learning_rate": 4.21995165897605e-05, "loss": 1.5042, "step": 710 }, { "epoch": 0.47, "learning_rate": 4.2089650626235996e-05, "loss": 1.534, "step": 720 }, { "epoch": 0.48, "learning_rate": 4.1979784662711494e-05, "loss": 1.4954, "step": 730 }, { "epoch": 0.49, "learning_rate": 4.186991869918699e-05, "loss": 1.5142, "step": 740 }, { "epoch": 0.49, "learning_rate": 4.176005273566249e-05, "loss": 1.4959, "step": 750 }, { "epoch": 0.5, "learning_rate": 4.1650186772137994e-05, "loss": 1.529, "step": 760 }, { "epoch": 0.51, "learning_rate": 4.154032080861349e-05, "loss": 1.5751, "step": 770 }, { "epoch": 0.51, "learning_rate": 4.1430454845088996e-05, "loss": 1.4828, "step": 780 }, { "epoch": 0.52, "learning_rate": 4.1320588881564494e-05, "loss": 1.5057, "step": 790 }, { "epoch": 0.53, "learning_rate": 4.121072291804e-05, "loss": 1.5223, "step": 800 }, { "epoch": 0.53, "learning_rate": 4.110085695451549e-05, "loss": 1.526, "step": 810 }, { "epoch": 0.54, "learning_rate": 4.099099099099099e-05, "loss": 1.5107, "step": 820 }, { "epoch": 0.55, "learning_rate": 4.088112502746649e-05, "loss": 1.5018, "step": 830 }, { "epoch": 0.55, "learning_rate": 4.077125906394199e-05, "loss": 1.51, "step": 840 }, { "epoch": 0.56, "learning_rate": 4.0661393100417495e-05, "loss": 1.5105, "step": 850 }, { "epoch": 0.57, "learning_rate": 4.055152713689299e-05, "loss": 1.5267, "step": 860 }, { "epoch": 0.57, "learning_rate": 4.04416611733685e-05, "loss": 1.5797, "step": 870 }, { "epoch": 0.58, "learning_rate": 4.0331795209843995e-05, "loss": 1.476, "step": 880 }, { "epoch": 0.59, "learning_rate": 4.022192924631949e-05, "loss": 1.5339, "step": 890 }, { "epoch": 0.59, "learning_rate": 4.011206328279499e-05, "loss": 1.527, "step": 900 }, { "epoch": 0.6, "learning_rate": 4.000219731927049e-05, "loss": 1.5095, "step": 910 }, { "epoch": 0.61, "learning_rate": 3.989233135574599e-05, "loss": 1.5169, "step": 920 }, { "epoch": 0.61, "learning_rate": 3.978246539222149e-05, "loss": 1.4762, "step": 930 }, { "epoch": 0.62, "learning_rate": 3.9672599428696996e-05, "loss": 1.5396, "step": 940 }, { "epoch": 0.63, "learning_rate": 3.9562733465172494e-05, "loss": 1.5001, "step": 950 }, { "epoch": 0.63, "learning_rate": 3.945286750164799e-05, "loss": 1.491, "step": 960 }, { "epoch": 0.64, "learning_rate": 3.934300153812349e-05, "loss": 1.5115, "step": 970 }, { "epoch": 0.65, "learning_rate": 3.923313557459899e-05, "loss": 1.5134, "step": 980 }, { "epoch": 0.65, "learning_rate": 3.912326961107449e-05, "loss": 1.5099, "step": 990 }, { "epoch": 0.66, "learning_rate": 3.901340364754999e-05, "loss": 1.4916, "step": 1000 }, { "epoch": 0.67, "learning_rate": 3.8903537684025494e-05, "loss": 1.5408, "step": 1010 }, { "epoch": 0.67, "learning_rate": 3.879367172050099e-05, "loss": 1.5136, "step": 1020 }, { "epoch": 0.68, "learning_rate": 3.868380575697649e-05, "loss": 1.4436, "step": 1030 }, { "epoch": 0.69, "learning_rate": 3.857393979345199e-05, "loss": 1.5159, "step": 1040 }, { "epoch": 0.69, "learning_rate": 3.8464073829927486e-05, "loss": 1.5099, "step": 1050 }, { "epoch": 0.7, "learning_rate": 3.835420786640299e-05, "loss": 1.4799, "step": 1060 }, { "epoch": 0.71, "learning_rate": 3.824434190287849e-05, "loss": 1.5627, "step": 1070 }, { "epoch": 0.71, "learning_rate": 3.813447593935399e-05, "loss": 1.5385, "step": 1080 }, { "epoch": 0.72, "learning_rate": 3.802460997582949e-05, "loss": 1.5316, "step": 1090 }, { "epoch": 0.73, "learning_rate": 3.7914744012304995e-05, "loss": 1.5288, "step": 1100 }, { "epoch": 0.73, "learning_rate": 3.780487804878049e-05, "loss": 1.5161, "step": 1110 }, { "epoch": 0.74, "learning_rate": 3.769501208525599e-05, "loss": 1.5441, "step": 1120 }, { "epoch": 0.74, "learning_rate": 3.758514612173149e-05, "loss": 1.5228, "step": 1130 }, { "epoch": 0.75, "learning_rate": 3.7475280158206986e-05, "loss": 1.5138, "step": 1140 }, { "epoch": 0.76, "learning_rate": 3.736541419468249e-05, "loss": 1.5264, "step": 1150 }, { "epoch": 0.76, "learning_rate": 3.725554823115799e-05, "loss": 1.5054, "step": 1160 }, { "epoch": 0.77, "learning_rate": 3.7145682267633494e-05, "loss": 1.5449, "step": 1170 }, { "epoch": 0.78, "learning_rate": 3.703581630410899e-05, "loss": 1.5117, "step": 1180 }, { "epoch": 0.78, "learning_rate": 3.692595034058449e-05, "loss": 1.5085, "step": 1190 }, { "epoch": 0.79, "learning_rate": 3.681608437705999e-05, "loss": 1.555, "step": 1200 }, { "epoch": 0.8, "learning_rate": 3.6706218413535485e-05, "loss": 1.5582, "step": 1210 }, { "epoch": 0.8, "learning_rate": 3.659635245001099e-05, "loss": 1.5092, "step": 1220 }, { "epoch": 0.81, "learning_rate": 3.648648648648649e-05, "loss": 1.4987, "step": 1230 }, { "epoch": 0.82, "learning_rate": 3.637662052296199e-05, "loss": 1.5117, "step": 1240 }, { "epoch": 0.82, "learning_rate": 3.626675455943749e-05, "loss": 1.528, "step": 1250 }, { "epoch": 0.83, "learning_rate": 3.615688859591299e-05, "loss": 1.4907, "step": 1260 }, { "epoch": 0.84, "learning_rate": 3.6047022632388485e-05, "loss": 1.4761, "step": 1270 }, { "epoch": 0.84, "learning_rate": 3.593715666886398e-05, "loss": 1.5295, "step": 1280 }, { "epoch": 0.85, "learning_rate": 3.582729070533949e-05, "loss": 1.5091, "step": 1290 }, { "epoch": 0.86, "learning_rate": 3.5717424741814986e-05, "loss": 1.5224, "step": 1300 }, { "epoch": 0.86, "learning_rate": 3.560755877829049e-05, "loss": 1.5155, "step": 1310 }, { "epoch": 0.87, "learning_rate": 3.549769281476599e-05, "loss": 1.5345, "step": 1320 }, { "epoch": 0.88, "learning_rate": 3.5387826851241486e-05, "loss": 1.5193, "step": 1330 }, { "epoch": 0.88, "learning_rate": 3.527796088771699e-05, "loss": 1.5366, "step": 1340 }, { "epoch": 0.89, "learning_rate": 3.516809492419248e-05, "loss": 1.4594, "step": 1350 }, { "epoch": 0.9, "learning_rate": 3.5058228960667986e-05, "loss": 1.518, "step": 1360 }, { "epoch": 0.9, "learning_rate": 3.4948362997143484e-05, "loss": 1.5273, "step": 1370 }, { "epoch": 0.91, "learning_rate": 3.483849703361899e-05, "loss": 1.5005, "step": 1380 }, { "epoch": 0.92, "learning_rate": 3.472863107009449e-05, "loss": 1.4857, "step": 1390 }, { "epoch": 0.92, "learning_rate": 3.4618765106569984e-05, "loss": 1.519, "step": 1400 }, { "epoch": 0.93, "learning_rate": 3.450889914304549e-05, "loss": 1.5566, "step": 1410 }, { "epoch": 0.94, "learning_rate": 3.439903317952099e-05, "loss": 1.543, "step": 1420 }, { "epoch": 0.94, "learning_rate": 3.4289167215996485e-05, "loss": 1.5184, "step": 1430 }, { "epoch": 0.95, "learning_rate": 3.417930125247198e-05, "loss": 1.5114, "step": 1440 }, { "epoch": 0.96, "learning_rate": 3.406943528894749e-05, "loss": 1.5024, "step": 1450 }, { "epoch": 0.96, "learning_rate": 3.3959569325422985e-05, "loss": 1.518, "step": 1460 }, { "epoch": 0.97, "learning_rate": 3.384970336189849e-05, "loss": 1.5261, "step": 1470 }, { "epoch": 0.98, "learning_rate": 3.373983739837399e-05, "loss": 1.5171, "step": 1480 }, { "epoch": 0.98, "learning_rate": 3.3629971434849485e-05, "loss": 1.5435, "step": 1490 }, { "epoch": 0.99, "learning_rate": 3.352010547132498e-05, "loss": 1.5156, "step": 1500 }, { "epoch": 1.0, "learning_rate": 3.341023950780048e-05, "loss": 1.512, "step": 1510 }, { "epoch": 1.0, "learning_rate": 3.3300373544275986e-05, "loss": 1.4642, "step": 1520 }, { "epoch": 1.01, "learning_rate": 3.3190507580751483e-05, "loss": 1.4732, "step": 1530 }, { "epoch": 1.02, "learning_rate": 3.308064161722699e-05, "loss": 1.5265, "step": 1540 }, { "epoch": 1.02, "learning_rate": 3.2970775653702486e-05, "loss": 1.5021, "step": 1550 }, { "epoch": 1.03, "learning_rate": 3.2860909690177984e-05, "loss": 1.467, "step": 1560 }, { "epoch": 1.03, "learning_rate": 3.275104372665349e-05, "loss": 1.5358, "step": 1570 }, { "epoch": 1.04, "learning_rate": 3.264117776312898e-05, "loss": 1.5134, "step": 1580 }, { "epoch": 1.05, "learning_rate": 3.2531311799604484e-05, "loss": 1.5223, "step": 1590 }, { "epoch": 1.05, "learning_rate": 3.242144583607998e-05, "loss": 1.5, "step": 1600 }, { "epoch": 1.06, "learning_rate": 3.2311579872555487e-05, "loss": 1.5264, "step": 1610 }, { "epoch": 1.07, "learning_rate": 3.2201713909030984e-05, "loss": 1.5443, "step": 1620 }, { "epoch": 1.07, "learning_rate": 3.209184794550648e-05, "loss": 1.505, "step": 1630 }, { "epoch": 1.08, "learning_rate": 3.198198198198199e-05, "loss": 1.5006, "step": 1640 }, { "epoch": 1.09, "learning_rate": 3.1872116018457485e-05, "loss": 1.4926, "step": 1650 }, { "epoch": 1.09, "learning_rate": 3.176225005493298e-05, "loss": 1.4822, "step": 1660 }, { "epoch": 1.1, "learning_rate": 3.165238409140848e-05, "loss": 1.4926, "step": 1670 }, { "epoch": 1.11, "learning_rate": 3.1542518127883985e-05, "loss": 1.518, "step": 1680 }, { "epoch": 1.11, "learning_rate": 3.143265216435948e-05, "loss": 1.48, "step": 1690 }, { "epoch": 1.12, "learning_rate": 3.132278620083498e-05, "loss": 1.4855, "step": 1700 }, { "epoch": 1.13, "learning_rate": 3.1212920237310485e-05, "loss": 1.5082, "step": 1710 }, { "epoch": 1.13, "learning_rate": 3.110305427378598e-05, "loss": 1.5386, "step": 1720 }, { "epoch": 1.14, "learning_rate": 3.099318831026148e-05, "loss": 1.5127, "step": 1730 }, { "epoch": 1.15, "learning_rate": 3.088332234673698e-05, "loss": 1.5055, "step": 1740 }, { "epoch": 1.15, "learning_rate": 3.077345638321248e-05, "loss": 1.4899, "step": 1750 }, { "epoch": 1.16, "learning_rate": 3.066359041968798e-05, "loss": 1.4672, "step": 1760 }, { "epoch": 1.17, "learning_rate": 3.055372445616348e-05, "loss": 1.4608, "step": 1770 }, { "epoch": 1.17, "learning_rate": 3.0443858492638984e-05, "loss": 1.5024, "step": 1780 }, { "epoch": 1.18, "learning_rate": 3.033399252911448e-05, "loss": 1.5399, "step": 1790 }, { "epoch": 1.19, "learning_rate": 3.0224126565589983e-05, "loss": 1.5202, "step": 1800 }, { "epoch": 1.19, "learning_rate": 3.011426060206548e-05, "loss": 1.5153, "step": 1810 }, { "epoch": 1.2, "learning_rate": 3.0004394638540985e-05, "loss": 1.49, "step": 1820 }, { "epoch": 1.21, "learning_rate": 2.989452867501648e-05, "loss": 1.5247, "step": 1830 }, { "epoch": 1.21, "learning_rate": 2.9784662711491977e-05, "loss": 1.5244, "step": 1840 }, { "epoch": 1.22, "learning_rate": 2.9674796747967482e-05, "loss": 1.5037, "step": 1850 }, { "epoch": 1.23, "learning_rate": 2.956493078444298e-05, "loss": 1.5281, "step": 1860 }, { "epoch": 1.23, "learning_rate": 2.945506482091848e-05, "loss": 1.5172, "step": 1870 }, { "epoch": 1.24, "learning_rate": 2.934519885739398e-05, "loss": 1.5056, "step": 1880 }, { "epoch": 1.25, "learning_rate": 2.9235332893869484e-05, "loss": 1.4896, "step": 1890 }, { "epoch": 1.25, "learning_rate": 2.912546693034498e-05, "loss": 1.5634, "step": 1900 }, { "epoch": 1.26, "learning_rate": 2.9015600966820483e-05, "loss": 1.5211, "step": 1910 }, { "epoch": 1.27, "learning_rate": 2.890573500329598e-05, "loss": 1.5346, "step": 1920 }, { "epoch": 1.27, "learning_rate": 2.879586903977148e-05, "loss": 1.5723, "step": 1930 }, { "epoch": 1.28, "learning_rate": 2.868600307624698e-05, "loss": 1.4715, "step": 1940 }, { "epoch": 1.29, "learning_rate": 2.8576137112722477e-05, "loss": 1.5107, "step": 1950 }, { "epoch": 1.29, "learning_rate": 2.8466271149197982e-05, "loss": 1.5052, "step": 1960 }, { "epoch": 1.3, "learning_rate": 2.835640518567348e-05, "loss": 1.5363, "step": 1970 }, { "epoch": 1.31, "learning_rate": 2.824653922214898e-05, "loss": 1.4704, "step": 1980 }, { "epoch": 1.31, "learning_rate": 2.813667325862448e-05, "loss": 1.5256, "step": 1990 }, { "epoch": 1.32, "learning_rate": 2.8026807295099977e-05, "loss": 1.5022, "step": 2000 }, { "epoch": 1.32, "learning_rate": 2.791694133157548e-05, "loss": 1.5098, "step": 2010 }, { "epoch": 1.33, "learning_rate": 2.780707536805098e-05, "loss": 1.5184, "step": 2020 }, { "epoch": 1.34, "learning_rate": 2.769720940452648e-05, "loss": 1.5153, "step": 2030 }, { "epoch": 1.34, "learning_rate": 2.7587343441001978e-05, "loss": 1.4908, "step": 2040 }, { "epoch": 1.35, "learning_rate": 2.7477477477477483e-05, "loss": 1.5063, "step": 2050 }, { "epoch": 1.36, "learning_rate": 2.7367611513952977e-05, "loss": 1.5283, "step": 2060 }, { "epoch": 1.36, "learning_rate": 2.7257745550428475e-05, "loss": 1.5117, "step": 2070 }, { "epoch": 1.37, "learning_rate": 2.714787958690398e-05, "loss": 1.5171, "step": 2080 }, { "epoch": 1.38, "learning_rate": 2.7038013623379478e-05, "loss": 1.5178, "step": 2090 }, { "epoch": 1.38, "learning_rate": 2.692814765985498e-05, "loss": 1.544, "step": 2100 }, { "epoch": 1.39, "learning_rate": 2.6818281696330477e-05, "loss": 1.554, "step": 2110 }, { "epoch": 1.4, "learning_rate": 2.670841573280598e-05, "loss": 1.5475, "step": 2120 }, { "epoch": 1.4, "learning_rate": 2.659854976928148e-05, "loss": 1.5047, "step": 2130 }, { "epoch": 1.41, "learning_rate": 2.6488683805756974e-05, "loss": 1.5467, "step": 2140 }, { "epoch": 1.42, "learning_rate": 2.6378817842232478e-05, "loss": 1.5198, "step": 2150 }, { "epoch": 1.42, "learning_rate": 2.6268951878707976e-05, "loss": 1.5535, "step": 2160 }, { "epoch": 1.43, "learning_rate": 2.6159085915183477e-05, "loss": 1.4805, "step": 2170 }, { "epoch": 1.44, "learning_rate": 2.6049219951658975e-05, "loss": 1.5443, "step": 2180 }, { "epoch": 1.44, "learning_rate": 2.593935398813448e-05, "loss": 1.5291, "step": 2190 }, { "epoch": 1.45, "learning_rate": 2.5829488024609978e-05, "loss": 1.4886, "step": 2200 }, { "epoch": 1.46, "learning_rate": 2.5719622061085475e-05, "loss": 1.5348, "step": 2210 }, { "epoch": 1.46, "learning_rate": 2.5609756097560977e-05, "loss": 1.5393, "step": 2220 }, { "epoch": 1.47, "learning_rate": 2.5499890134036475e-05, "loss": 1.5525, "step": 2230 }, { "epoch": 1.48, "learning_rate": 2.539002417051198e-05, "loss": 1.5496, "step": 2240 }, { "epoch": 1.48, "learning_rate": 2.5280158206987477e-05, "loss": 1.4784, "step": 2250 }, { "epoch": 1.49, "learning_rate": 2.5170292243462978e-05, "loss": 1.4567, "step": 2260 }, { "epoch": 1.5, "learning_rate": 2.5060426279938476e-05, "loss": 1.4958, "step": 2270 }, { "epoch": 1.5, "learning_rate": 2.4950560316413977e-05, "loss": 1.5037, "step": 2280 }, { "epoch": 1.51, "learning_rate": 2.4840694352889475e-05, "loss": 1.5023, "step": 2290 }, { "epoch": 1.52, "learning_rate": 2.4730828389364976e-05, "loss": 1.5096, "step": 2300 }, { "epoch": 1.52, "learning_rate": 2.4620962425840478e-05, "loss": 1.5476, "step": 2310 }, { "epoch": 1.53, "learning_rate": 2.4511096462315975e-05, "loss": 1.4844, "step": 2320 }, { "epoch": 1.54, "learning_rate": 2.4401230498791473e-05, "loss": 1.4702, "step": 2330 }, { "epoch": 1.54, "learning_rate": 2.4291364535266974e-05, "loss": 1.5297, "step": 2340 }, { "epoch": 1.55, "learning_rate": 2.4181498571742476e-05, "loss": 1.4954, "step": 2350 }, { "epoch": 1.56, "learning_rate": 2.4071632608217977e-05, "loss": 1.5016, "step": 2360 }, { "epoch": 1.56, "learning_rate": 2.3961766644693475e-05, "loss": 1.5038, "step": 2370 }, { "epoch": 1.57, "learning_rate": 2.3851900681168976e-05, "loss": 1.4758, "step": 2380 }, { "epoch": 1.58, "learning_rate": 2.3742034717644474e-05, "loss": 1.4669, "step": 2390 }, { "epoch": 1.58, "learning_rate": 2.3632168754119975e-05, "loss": 1.5204, "step": 2400 }, { "epoch": 1.59, "learning_rate": 2.3522302790595473e-05, "loss": 1.5103, "step": 2410 }, { "epoch": 1.6, "learning_rate": 2.3412436827070974e-05, "loss": 1.5083, "step": 2420 }, { "epoch": 1.6, "learning_rate": 2.3302570863546475e-05, "loss": 1.5019, "step": 2430 }, { "epoch": 1.61, "learning_rate": 2.3192704900021973e-05, "loss": 1.4884, "step": 2440 }, { "epoch": 1.62, "learning_rate": 2.3082838936497474e-05, "loss": 1.457, "step": 2450 }, { "epoch": 1.62, "learning_rate": 2.2972972972972976e-05, "loss": 1.5291, "step": 2460 }, { "epoch": 1.63, "learning_rate": 2.2863107009448473e-05, "loss": 1.4711, "step": 2470 }, { "epoch": 1.63, "learning_rate": 2.2753241045923975e-05, "loss": 1.4642, "step": 2480 }, { "epoch": 1.64, "learning_rate": 2.2643375082399473e-05, "loss": 1.5143, "step": 2490 }, { "epoch": 1.65, "learning_rate": 2.2533509118874974e-05, "loss": 1.522, "step": 2500 }, { "epoch": 1.65, "learning_rate": 2.2423643155350475e-05, "loss": 1.5441, "step": 2510 }, { "epoch": 1.66, "learning_rate": 2.2313777191825973e-05, "loss": 1.5014, "step": 2520 }, { "epoch": 1.67, "learning_rate": 2.2203911228301474e-05, "loss": 1.4878, "step": 2530 }, { "epoch": 1.67, "learning_rate": 2.2094045264776972e-05, "loss": 1.5278, "step": 2540 }, { "epoch": 1.68, "learning_rate": 2.1984179301252473e-05, "loss": 1.4931, "step": 2550 }, { "epoch": 1.69, "learning_rate": 2.187431333772797e-05, "loss": 1.5347, "step": 2560 }, { "epoch": 1.69, "learning_rate": 2.1764447374203472e-05, "loss": 1.5179, "step": 2570 }, { "epoch": 1.7, "learning_rate": 2.1654581410678973e-05, "loss": 1.4976, "step": 2580 }, { "epoch": 1.71, "learning_rate": 2.1544715447154475e-05, "loss": 1.4873, "step": 2590 }, { "epoch": 1.71, "learning_rate": 2.1434849483629972e-05, "loss": 1.5061, "step": 2600 }, { "epoch": 1.72, "learning_rate": 2.1324983520105474e-05, "loss": 1.4761, "step": 2610 }, { "epoch": 1.73, "learning_rate": 2.121511755658097e-05, "loss": 1.4965, "step": 2620 }, { "epoch": 1.73, "learning_rate": 2.1105251593056473e-05, "loss": 1.4988, "step": 2630 }, { "epoch": 1.74, "learning_rate": 2.099538562953197e-05, "loss": 1.5104, "step": 2640 }, { "epoch": 1.75, "learning_rate": 2.0885519666007472e-05, "loss": 1.5326, "step": 2650 }, { "epoch": 1.75, "learning_rate": 2.0775653702482973e-05, "loss": 1.5127, "step": 2660 }, { "epoch": 1.76, "learning_rate": 2.066578773895847e-05, "loss": 1.5219, "step": 2670 }, { "epoch": 1.77, "learning_rate": 2.0555921775433972e-05, "loss": 1.5296, "step": 2680 }, { "epoch": 1.77, "learning_rate": 2.044605581190947e-05, "loss": 1.5155, "step": 2690 }, { "epoch": 1.78, "learning_rate": 2.033618984838497e-05, "loss": 1.5104, "step": 2700 }, { "epoch": 1.79, "learning_rate": 2.0226323884860472e-05, "loss": 1.5286, "step": 2710 }, { "epoch": 1.79, "learning_rate": 2.011645792133597e-05, "loss": 1.488, "step": 2720 }, { "epoch": 1.8, "learning_rate": 2.000659195781147e-05, "loss": 1.5372, "step": 2730 }, { "epoch": 1.81, "learning_rate": 1.9896725994286973e-05, "loss": 1.5224, "step": 2740 }, { "epoch": 1.81, "learning_rate": 1.978686003076247e-05, "loss": 1.5292, "step": 2750 }, { "epoch": 1.82, "learning_rate": 1.967699406723797e-05, "loss": 1.5251, "step": 2760 }, { "epoch": 1.83, "learning_rate": 1.956712810371347e-05, "loss": 1.4906, "step": 2770 }, { "epoch": 1.83, "learning_rate": 1.945726214018897e-05, "loss": 1.5173, "step": 2780 }, { "epoch": 1.84, "learning_rate": 1.934739617666447e-05, "loss": 1.4758, "step": 2790 }, { "epoch": 1.85, "learning_rate": 1.923753021313997e-05, "loss": 1.5156, "step": 2800 }, { "epoch": 1.85, "learning_rate": 1.912766424961547e-05, "loss": 1.5072, "step": 2810 }, { "epoch": 1.86, "learning_rate": 1.9017798286090972e-05, "loss": 1.4955, "step": 2820 }, { "epoch": 1.87, "learning_rate": 1.890793232256647e-05, "loss": 1.5252, "step": 2830 }, { "epoch": 1.87, "learning_rate": 1.8798066359041968e-05, "loss": 1.4833, "step": 2840 }, { "epoch": 1.88, "learning_rate": 1.868820039551747e-05, "loss": 1.5287, "step": 2850 }, { "epoch": 1.89, "learning_rate": 1.857833443199297e-05, "loss": 1.4767, "step": 2860 }, { "epoch": 1.89, "learning_rate": 1.846846846846847e-05, "loss": 1.4979, "step": 2870 }, { "epoch": 1.9, "learning_rate": 1.835860250494397e-05, "loss": 1.5249, "step": 2880 }, { "epoch": 1.91, "learning_rate": 1.824873654141947e-05, "loss": 1.5127, "step": 2890 }, { "epoch": 1.91, "learning_rate": 1.813887057789497e-05, "loss": 1.5252, "step": 2900 }, { "epoch": 1.92, "learning_rate": 1.8029004614370466e-05, "loss": 1.499, "step": 2910 }, { "epoch": 1.92, "learning_rate": 1.7919138650845968e-05, "loss": 1.5672, "step": 2920 }, { "epoch": 1.93, "learning_rate": 1.780927268732147e-05, "loss": 1.485, "step": 2930 }, { "epoch": 1.94, "learning_rate": 1.769940672379697e-05, "loss": 1.5526, "step": 2940 }, { "epoch": 1.94, "learning_rate": 1.7589540760272468e-05, "loss": 1.551, "step": 2950 }, { "epoch": 1.95, "learning_rate": 1.747967479674797e-05, "loss": 1.518, "step": 2960 }, { "epoch": 1.96, "learning_rate": 1.736980883322347e-05, "loss": 1.5185, "step": 2970 }, { "epoch": 1.96, "learning_rate": 1.7259942869698968e-05, "loss": 1.4947, "step": 2980 }, { "epoch": 1.97, "learning_rate": 1.7150076906174466e-05, "loss": 1.503, "step": 2990 }, { "epoch": 1.98, "learning_rate": 1.7040210942649967e-05, "loss": 1.4985, "step": 3000 } ], "logging_steps": 10, "max_steps": 4551, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "total_flos": 1.89607446577152e+18, "train_batch_size": 4, "trial_name": null, "trial_params": null }