{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 13527, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.011088933244621867, "grad_norm": 8.14461898803711, "learning_rate": 1.9927552302801804e-05, "loss": 0.902, "step": 50 }, { "epoch": 0.022177866489243733, "grad_norm": 6.75203800201416, "learning_rate": 1.9853626081170995e-05, "loss": 0.448, "step": 100 }, { "epoch": 0.0332667997338656, "grad_norm": 7.353200912475586, "learning_rate": 1.977969985954018e-05, "loss": 0.3174, "step": 150 }, { "epoch": 0.04435573297848747, "grad_norm": 2.7292733192443848, "learning_rate": 1.970577363790937e-05, "loss": 0.281, "step": 200 }, { "epoch": 0.05544466622310934, "grad_norm": 3.5009043216705322, "learning_rate": 1.9631847416278556e-05, "loss": 0.2798, "step": 250 }, { "epoch": 0.0665335994677312, "grad_norm": 5.440974712371826, "learning_rate": 1.9557921194647743e-05, "loss": 0.2409, "step": 300 }, { "epoch": 0.07762253271235307, "grad_norm": 4.327282905578613, "learning_rate": 1.948399497301693e-05, "loss": 0.203, "step": 350 }, { "epoch": 0.08871146595697493, "grad_norm": 1.8929752111434937, "learning_rate": 1.9410068751386117e-05, "loss": 0.2169, "step": 400 }, { "epoch": 0.0998003992015968, "grad_norm": 2.9351725578308105, "learning_rate": 1.9336142529755308e-05, "loss": 0.2197, "step": 450 }, { "epoch": 0.11088933244621868, "grad_norm": 5.145724296569824, "learning_rate": 1.926221630812449e-05, "loss": 0.2073, "step": 500 }, { "epoch": 0.12197826569084054, "grad_norm": 4.723082542419434, "learning_rate": 1.9188290086493682e-05, "loss": 0.2188, "step": 550 }, { "epoch": 0.1330671989354624, "grad_norm": 2.782973289489746, "learning_rate": 1.911436386486287e-05, "loss": 0.2062, "step": 600 }, { "epoch": 0.14415613218008427, "grad_norm": 3.5191564559936523, "learning_rate": 1.9040437643232056e-05, "loss": 0.213, "step": 650 }, { "epoch": 0.15524506542470615, "grad_norm": 1.734594702720642, "learning_rate": 1.8966511421601243e-05, "loss": 0.2064, "step": 700 }, { "epoch": 0.16633399866932802, "grad_norm": 3.7910728454589844, "learning_rate": 1.889258519997043e-05, "loss": 0.1943, "step": 750 }, { "epoch": 0.17742293191394987, "grad_norm": 3.688796281814575, "learning_rate": 1.881865897833962e-05, "loss": 0.1928, "step": 800 }, { "epoch": 0.18851186515857174, "grad_norm": 2.2231035232543945, "learning_rate": 1.8744732756708804e-05, "loss": 0.1825, "step": 850 }, { "epoch": 0.1996007984031936, "grad_norm": 4.24806022644043, "learning_rate": 1.8670806535077994e-05, "loss": 0.1578, "step": 900 }, { "epoch": 0.2106897316478155, "grad_norm": 3.1724870204925537, "learning_rate": 1.859688031344718e-05, "loss": 0.1645, "step": 950 }, { "epoch": 0.22177866489243736, "grad_norm": 2.4956796169281006, "learning_rate": 1.852295409181637e-05, "loss": 0.1796, "step": 1000 }, { "epoch": 0.2328675981370592, "grad_norm": 1.245104432106018, "learning_rate": 1.8449027870185556e-05, "loss": 0.1669, "step": 1050 }, { "epoch": 0.24395653138168108, "grad_norm": 2.2229013442993164, "learning_rate": 1.8375101648554743e-05, "loss": 0.1743, "step": 1100 }, { "epoch": 0.25504546462630295, "grad_norm": 3.6590652465820312, "learning_rate": 1.8301175426923933e-05, "loss": 0.1654, "step": 1150 }, { "epoch": 0.2661343978709248, "grad_norm": 2.119847297668457, "learning_rate": 1.8227249205293117e-05, "loss": 0.1603, "step": 1200 }, { "epoch": 0.2772233311155467, "grad_norm": 3.36673903465271, "learning_rate": 1.8153322983662307e-05, "loss": 0.1593, "step": 1250 }, { "epoch": 0.28831226436016855, "grad_norm": 2.931980609893799, "learning_rate": 1.8079396762031494e-05, "loss": 0.1585, "step": 1300 }, { "epoch": 0.2994011976047904, "grad_norm": 1.6280852556228638, "learning_rate": 1.800547054040068e-05, "loss": 0.1676, "step": 1350 }, { "epoch": 0.3104901308494123, "grad_norm": 5.353924751281738, "learning_rate": 1.793154431876987e-05, "loss": 0.155, "step": 1400 }, { "epoch": 0.32157906409403414, "grad_norm": 1.9066994190216064, "learning_rate": 1.7857618097139056e-05, "loss": 0.168, "step": 1450 }, { "epoch": 0.33266799733865604, "grad_norm": 3.3019158840179443, "learning_rate": 1.7783691875508246e-05, "loss": 0.144, "step": 1500 }, { "epoch": 0.3437569305832779, "grad_norm": 2.2679409980773926, "learning_rate": 1.770976565387743e-05, "loss": 0.1616, "step": 1550 }, { "epoch": 0.35484586382789973, "grad_norm": 3.734102964401245, "learning_rate": 1.763583943224662e-05, "loss": 0.1331, "step": 1600 }, { "epoch": 0.36593479707252163, "grad_norm": 2.348113775253296, "learning_rate": 1.7561913210615807e-05, "loss": 0.1477, "step": 1650 }, { "epoch": 0.3770237303171435, "grad_norm": 3.4904134273529053, "learning_rate": 1.7487986988984994e-05, "loss": 0.1448, "step": 1700 }, { "epoch": 0.3881126635617654, "grad_norm": 1.9997397661209106, "learning_rate": 1.741406076735418e-05, "loss": 0.1461, "step": 1750 }, { "epoch": 0.3992015968063872, "grad_norm": 2.7343485355377197, "learning_rate": 1.7340134545723372e-05, "loss": 0.149, "step": 1800 }, { "epoch": 0.4102905300510091, "grad_norm": 3.363621950149536, "learning_rate": 1.726620832409256e-05, "loss": 0.1601, "step": 1850 }, { "epoch": 0.421379463295631, "grad_norm": 1.4055149555206299, "learning_rate": 1.7192282102461742e-05, "loss": 0.1475, "step": 1900 }, { "epoch": 0.4324683965402528, "grad_norm": 4.3813066482543945, "learning_rate": 1.7118355880830933e-05, "loss": 0.1434, "step": 1950 }, { "epoch": 0.4435573297848747, "grad_norm": 2.2316620349884033, "learning_rate": 1.704442965920012e-05, "loss": 0.1452, "step": 2000 }, { "epoch": 0.45464626302949657, "grad_norm": 1.3528106212615967, "learning_rate": 1.6970503437569307e-05, "loss": 0.138, "step": 2050 }, { "epoch": 0.4657351962741184, "grad_norm": 2.043443441390991, "learning_rate": 1.6896577215938494e-05, "loss": 0.1586, "step": 2100 }, { "epoch": 0.4768241295187403, "grad_norm": 1.920172929763794, "learning_rate": 1.6822650994307685e-05, "loss": 0.1267, "step": 2150 }, { "epoch": 0.48791306276336216, "grad_norm": 2.8047444820404053, "learning_rate": 1.6748724772676868e-05, "loss": 0.1417, "step": 2200 }, { "epoch": 0.499001996007984, "grad_norm": 3.8060503005981445, "learning_rate": 1.6674798551046055e-05, "loss": 0.1345, "step": 2250 }, { "epoch": 0.5100909292526059, "grad_norm": 2.5561251640319824, "learning_rate": 1.6600872329415246e-05, "loss": 0.1266, "step": 2300 }, { "epoch": 0.5211798624972278, "grad_norm": 4.142666339874268, "learning_rate": 1.6526946107784433e-05, "loss": 0.1407, "step": 2350 }, { "epoch": 0.5322687957418496, "grad_norm": 1.7247148752212524, "learning_rate": 1.645301988615362e-05, "loss": 0.1339, "step": 2400 }, { "epoch": 0.5433577289864715, "grad_norm": 4.735507965087891, "learning_rate": 1.6379093664522807e-05, "loss": 0.1355, "step": 2450 }, { "epoch": 0.5544466622310934, "grad_norm": 4.915506362915039, "learning_rate": 1.6305167442891997e-05, "loss": 0.1373, "step": 2500 }, { "epoch": 0.5655355954757152, "grad_norm": 2.5551493167877197, "learning_rate": 1.623124122126118e-05, "loss": 0.1344, "step": 2550 }, { "epoch": 0.5766245287203371, "grad_norm": 1.054781436920166, "learning_rate": 1.615731499963037e-05, "loss": 0.126, "step": 2600 }, { "epoch": 0.587713461964959, "grad_norm": 2.835658311843872, "learning_rate": 1.608338877799956e-05, "loss": 0.1312, "step": 2650 }, { "epoch": 0.5988023952095808, "grad_norm": 3.4936070442199707, "learning_rate": 1.6009462556368746e-05, "loss": 0.1078, "step": 2700 }, { "epoch": 0.6098913284542027, "grad_norm": 2.4390571117401123, "learning_rate": 1.5935536334737933e-05, "loss": 0.1405, "step": 2750 }, { "epoch": 0.6209802616988246, "grad_norm": 2.4469242095947266, "learning_rate": 1.586161011310712e-05, "loss": 0.1246, "step": 2800 }, { "epoch": 0.6320691949434465, "grad_norm": 3.6933956146240234, "learning_rate": 1.578768389147631e-05, "loss": 0.1297, "step": 2850 }, { "epoch": 0.6431581281880683, "grad_norm": 2.2289130687713623, "learning_rate": 1.5713757669845494e-05, "loss": 0.1265, "step": 2900 }, { "epoch": 0.6542470614326902, "grad_norm": 1.5156584978103638, "learning_rate": 1.5639831448214684e-05, "loss": 0.1311, "step": 2950 }, { "epoch": 0.6653359946773121, "grad_norm": 1.9378397464752197, "learning_rate": 1.556590522658387e-05, "loss": 0.1275, "step": 3000 }, { "epoch": 0.6764249279219339, "grad_norm": 1.9141340255737305, "learning_rate": 1.549197900495306e-05, "loss": 0.1141, "step": 3050 }, { "epoch": 0.6875138611665558, "grad_norm": 1.9459818601608276, "learning_rate": 1.5418052783322245e-05, "loss": 0.1318, "step": 3100 }, { "epoch": 0.6986027944111777, "grad_norm": 7.391958236694336, "learning_rate": 1.5344126561691432e-05, "loss": 0.1203, "step": 3150 }, { "epoch": 0.7096917276557995, "grad_norm": 2.0345418453216553, "learning_rate": 1.5270200340060623e-05, "loss": 0.1273, "step": 3200 }, { "epoch": 0.7207806609004214, "grad_norm": 4.687112808227539, "learning_rate": 1.5196274118429808e-05, "loss": 0.1018, "step": 3250 }, { "epoch": 0.7318695941450433, "grad_norm": 2.794402837753296, "learning_rate": 1.5122347896798997e-05, "loss": 0.1164, "step": 3300 }, { "epoch": 0.7429585273896652, "grad_norm": 2.7743284702301025, "learning_rate": 1.5048421675168184e-05, "loss": 0.1164, "step": 3350 }, { "epoch": 0.754047460634287, "grad_norm": 3.1311397552490234, "learning_rate": 1.497449545353737e-05, "loss": 0.1245, "step": 3400 }, { "epoch": 0.7651363938789089, "grad_norm": 3.217726230621338, "learning_rate": 1.4900569231906558e-05, "loss": 0.1045, "step": 3450 }, { "epoch": 0.7762253271235308, "grad_norm": 1.691542387008667, "learning_rate": 1.4826643010275745e-05, "loss": 0.134, "step": 3500 }, { "epoch": 0.7873142603681526, "grad_norm": 3.6782033443450928, "learning_rate": 1.4752716788644934e-05, "loss": 0.1276, "step": 3550 }, { "epoch": 0.7984031936127745, "grad_norm": 1.4673993587493896, "learning_rate": 1.4678790567014121e-05, "loss": 0.1059, "step": 3600 }, { "epoch": 0.8094921268573964, "grad_norm": 2.9146125316619873, "learning_rate": 1.460486434538331e-05, "loss": 0.1165, "step": 3650 }, { "epoch": 0.8205810601020181, "grad_norm": 2.6374094486236572, "learning_rate": 1.4530938123752497e-05, "loss": 0.1245, "step": 3700 }, { "epoch": 0.83166999334664, "grad_norm": 0.7516615986824036, "learning_rate": 1.4457011902121686e-05, "loss": 0.1178, "step": 3750 }, { "epoch": 0.842758926591262, "grad_norm": 2.7078309059143066, "learning_rate": 1.4383085680490871e-05, "loss": 0.1216, "step": 3800 }, { "epoch": 0.8538478598358837, "grad_norm": 1.5147875547409058, "learning_rate": 1.4309159458860058e-05, "loss": 0.1178, "step": 3850 }, { "epoch": 0.8649367930805056, "grad_norm": 1.8173058032989502, "learning_rate": 1.4235233237229247e-05, "loss": 0.1177, "step": 3900 }, { "epoch": 0.8760257263251275, "grad_norm": 2.6974475383758545, "learning_rate": 1.4161307015598434e-05, "loss": 0.1093, "step": 3950 }, { "epoch": 0.8871146595697494, "grad_norm": 2.176143169403076, "learning_rate": 1.4087380793967623e-05, "loss": 0.1058, "step": 4000 }, { "epoch": 0.8982035928143712, "grad_norm": 2.174964427947998, "learning_rate": 1.4013454572336808e-05, "loss": 0.1164, "step": 4050 }, { "epoch": 0.9092925260589931, "grad_norm": 2.4584383964538574, "learning_rate": 1.3939528350705997e-05, "loss": 0.1188, "step": 4100 }, { "epoch": 0.920381459303615, "grad_norm": 1.6693115234375, "learning_rate": 1.3865602129075184e-05, "loss": 0.112, "step": 4150 }, { "epoch": 0.9314703925482368, "grad_norm": 2.2045669555664062, "learning_rate": 1.379167590744437e-05, "loss": 0.1234, "step": 4200 }, { "epoch": 0.9425593257928587, "grad_norm": 2.9538867473602295, "learning_rate": 1.371774968581356e-05, "loss": 0.1019, "step": 4250 }, { "epoch": 0.9536482590374806, "grad_norm": 1.7292181253433228, "learning_rate": 1.3643823464182747e-05, "loss": 0.118, "step": 4300 }, { "epoch": 0.9647371922821024, "grad_norm": 1.2080588340759277, "learning_rate": 1.3569897242551935e-05, "loss": 0.1096, "step": 4350 }, { "epoch": 0.9758261255267243, "grad_norm": 1.0146644115447998, "learning_rate": 1.349597102092112e-05, "loss": 0.1211, "step": 4400 }, { "epoch": 0.9869150587713462, "grad_norm": 3.40978741645813, "learning_rate": 1.342204479929031e-05, "loss": 0.114, "step": 4450 }, { "epoch": 0.998003992015968, "grad_norm": 2.2283411026000977, "learning_rate": 1.3348118577659497e-05, "loss": 0.1024, "step": 4500 }, { "epoch": 1.00909292526059, "grad_norm": 3.0386204719543457, "learning_rate": 1.3274192356028684e-05, "loss": 0.1037, "step": 4550 }, { "epoch": 1.0201818585052118, "grad_norm": 2.2395098209381104, "learning_rate": 1.3200266134397872e-05, "loss": 0.0962, "step": 4600 }, { "epoch": 1.0312707917498336, "grad_norm": 0.779739499092102, "learning_rate": 1.312633991276706e-05, "loss": 0.0897, "step": 4650 }, { "epoch": 1.0423597249944556, "grad_norm": 2.3607208728790283, "learning_rate": 1.3052413691136248e-05, "loss": 0.0913, "step": 4700 }, { "epoch": 1.0534486582390774, "grad_norm": 1.5109652280807495, "learning_rate": 1.2978487469505434e-05, "loss": 0.0987, "step": 4750 }, { "epoch": 1.0645375914836992, "grad_norm": 4.1896467208862305, "learning_rate": 1.2904561247874622e-05, "loss": 0.1044, "step": 4800 }, { "epoch": 1.0756265247283212, "grad_norm": 3.4481632709503174, "learning_rate": 1.283063502624381e-05, "loss": 0.1065, "step": 4850 }, { "epoch": 1.086715457972943, "grad_norm": 1.4650681018829346, "learning_rate": 1.2756708804612998e-05, "loss": 0.0854, "step": 4900 }, { "epoch": 1.0978043912175648, "grad_norm": 2.925077438354492, "learning_rate": 1.2682782582982185e-05, "loss": 0.1055, "step": 4950 }, { "epoch": 1.1088933244621868, "grad_norm": 1.6256483793258667, "learning_rate": 1.2608856361351372e-05, "loss": 0.1016, "step": 5000 }, { "epoch": 1.1199822577068086, "grad_norm": 2.7225170135498047, "learning_rate": 1.2534930139720561e-05, "loss": 0.0999, "step": 5050 }, { "epoch": 1.1310711909514304, "grad_norm": 2.22430419921875, "learning_rate": 1.2461003918089746e-05, "loss": 0.0886, "step": 5100 }, { "epoch": 1.1421601241960524, "grad_norm": 2.4130799770355225, "learning_rate": 1.2387077696458935e-05, "loss": 0.1012, "step": 5150 }, { "epoch": 1.1532490574406742, "grad_norm": 1.5306169986724854, "learning_rate": 1.2313151474828122e-05, "loss": 0.0988, "step": 5200 }, { "epoch": 1.1643379906852962, "grad_norm": 1.8464442491531372, "learning_rate": 1.2239225253197311e-05, "loss": 0.0928, "step": 5250 }, { "epoch": 1.175426923929918, "grad_norm": 2.2706775665283203, "learning_rate": 1.2165299031566498e-05, "loss": 0.094, "step": 5300 }, { "epoch": 1.1865158571745398, "grad_norm": 1.517385482788086, "learning_rate": 1.2091372809935685e-05, "loss": 0.1032, "step": 5350 }, { "epoch": 1.1976047904191618, "grad_norm": 1.9841318130493164, "learning_rate": 1.2017446588304874e-05, "loss": 0.0974, "step": 5400 }, { "epoch": 1.2086937236637836, "grad_norm": 3.8151936531066895, "learning_rate": 1.1943520366674059e-05, "loss": 0.0921, "step": 5450 }, { "epoch": 1.2197826569084054, "grad_norm": 1.1752043962478638, "learning_rate": 1.1869594145043248e-05, "loss": 0.0918, "step": 5500 }, { "epoch": 1.2308715901530274, "grad_norm": 3.7480061054229736, "learning_rate": 1.1795667923412435e-05, "loss": 0.0935, "step": 5550 }, { "epoch": 1.2419605233976492, "grad_norm": 2.0084166526794434, "learning_rate": 1.1721741701781624e-05, "loss": 0.1018, "step": 5600 }, { "epoch": 1.253049456642271, "grad_norm": 3.461491823196411, "learning_rate": 1.164781548015081e-05, "loss": 0.1044, "step": 5650 }, { "epoch": 1.264138389886893, "grad_norm": 1.8434693813323975, "learning_rate": 1.1573889258519996e-05, "loss": 0.0939, "step": 5700 }, { "epoch": 1.2752273231315148, "grad_norm": 2.570587158203125, "learning_rate": 1.1499963036889185e-05, "loss": 0.0984, "step": 5750 }, { "epoch": 1.2863162563761366, "grad_norm": 1.5073240995407104, "learning_rate": 1.1426036815258372e-05, "loss": 0.0889, "step": 5800 }, { "epoch": 1.2974051896207586, "grad_norm": 2.8674674034118652, "learning_rate": 1.135211059362756e-05, "loss": 0.1007, "step": 5850 }, { "epoch": 1.3084941228653804, "grad_norm": 5.509634971618652, "learning_rate": 1.1278184371996748e-05, "loss": 0.0916, "step": 5900 }, { "epoch": 1.3195830561100022, "grad_norm": 1.8779860734939575, "learning_rate": 1.1204258150365936e-05, "loss": 0.1009, "step": 5950 }, { "epoch": 1.3306719893546242, "grad_norm": 1.6348674297332764, "learning_rate": 1.1130331928735124e-05, "loss": 0.1009, "step": 6000 }, { "epoch": 1.341760922599246, "grad_norm": 2.8110697269439697, "learning_rate": 1.1056405707104312e-05, "loss": 0.11, "step": 6050 }, { "epoch": 1.3528498558438677, "grad_norm": 1.2461209297180176, "learning_rate": 1.0982479485473498e-05, "loss": 0.101, "step": 6100 }, { "epoch": 1.3639387890884898, "grad_norm": 3.5219790935516357, "learning_rate": 1.0908553263842685e-05, "loss": 0.0935, "step": 6150 }, { "epoch": 1.3750277223331115, "grad_norm": 1.9491550922393799, "learning_rate": 1.0834627042211873e-05, "loss": 0.0987, "step": 6200 }, { "epoch": 1.3861166555777333, "grad_norm": 1.0792142152786255, "learning_rate": 1.076070082058106e-05, "loss": 0.0887, "step": 6250 }, { "epoch": 1.3972055888223553, "grad_norm": 2.6937804222106934, "learning_rate": 1.068677459895025e-05, "loss": 0.0844, "step": 6300 }, { "epoch": 1.4082945220669771, "grad_norm": 1.8635441064834595, "learning_rate": 1.0612848377319436e-05, "loss": 0.0961, "step": 6350 }, { "epoch": 1.419383455311599, "grad_norm": 2.886840581893921, "learning_rate": 1.0538922155688625e-05, "loss": 0.1027, "step": 6400 }, { "epoch": 1.430472388556221, "grad_norm": 1.2699713706970215, "learning_rate": 1.046499593405781e-05, "loss": 0.084, "step": 6450 }, { "epoch": 1.4415613218008427, "grad_norm": 3.5690715312957764, "learning_rate": 1.0391069712426998e-05, "loss": 0.1007, "step": 6500 }, { "epoch": 1.4526502550454645, "grad_norm": 2.6432716846466064, "learning_rate": 1.0317143490796186e-05, "loss": 0.086, "step": 6550 }, { "epoch": 1.4637391882900865, "grad_norm": 1.3745814561843872, "learning_rate": 1.0243217269165373e-05, "loss": 0.1001, "step": 6600 }, { "epoch": 1.4748281215347083, "grad_norm": 2.1724355220794678, "learning_rate": 1.0169291047534562e-05, "loss": 0.0761, "step": 6650 }, { "epoch": 1.4859170547793301, "grad_norm": 2.703815460205078, "learning_rate": 1.0095364825903749e-05, "loss": 0.0921, "step": 6700 }, { "epoch": 1.4970059880239521, "grad_norm": 5.101301670074463, "learning_rate": 1.0021438604272938e-05, "loss": 0.1016, "step": 6750 }, { "epoch": 1.508094921268574, "grad_norm": 2.663522243499756, "learning_rate": 9.947512382642123e-06, "loss": 0.0872, "step": 6800 }, { "epoch": 1.5191838545131957, "grad_norm": 1.159928321838379, "learning_rate": 9.873586161011312e-06, "loss": 0.0897, "step": 6850 }, { "epoch": 1.5302727877578177, "grad_norm": 1.6328009366989136, "learning_rate": 9.799659939380499e-06, "loss": 0.0823, "step": 6900 }, { "epoch": 1.5413617210024395, "grad_norm": 2.2539258003234863, "learning_rate": 9.725733717749686e-06, "loss": 0.0974, "step": 6950 }, { "epoch": 1.5524506542470613, "grad_norm": 1.0964053869247437, "learning_rate": 9.651807496118875e-06, "loss": 0.0906, "step": 7000 }, { "epoch": 1.5635395874916833, "grad_norm": 1.5801488161087036, "learning_rate": 9.577881274488062e-06, "loss": 0.1, "step": 7050 }, { "epoch": 1.5746285207363053, "grad_norm": 1.7104038000106812, "learning_rate": 9.503955052857249e-06, "loss": 0.0935, "step": 7100 }, { "epoch": 1.585717453980927, "grad_norm": 2.5046310424804688, "learning_rate": 9.430028831226436e-06, "loss": 0.0908, "step": 7150 }, { "epoch": 1.596806387225549, "grad_norm": 1.518405795097351, "learning_rate": 9.356102609595625e-06, "loss": 0.092, "step": 7200 }, { "epoch": 1.607895320470171, "grad_norm": 1.8131279945373535, "learning_rate": 9.282176387964812e-06, "loss": 0.0837, "step": 7250 }, { "epoch": 1.6189842537147925, "grad_norm": 1.3197726011276245, "learning_rate": 9.208250166333999e-06, "loss": 0.0984, "step": 7300 }, { "epoch": 1.6300731869594145, "grad_norm": 2.3708226680755615, "learning_rate": 9.134323944703188e-06, "loss": 0.0861, "step": 7350 }, { "epoch": 1.6411621202040365, "grad_norm": 3.385481119155884, "learning_rate": 9.060397723072375e-06, "loss": 0.0889, "step": 7400 }, { "epoch": 1.652251053448658, "grad_norm": 1.1704720258712769, "learning_rate": 8.986471501441562e-06, "loss": 0.1005, "step": 7450 }, { "epoch": 1.66333998669328, "grad_norm": 2.1572084426879883, "learning_rate": 8.912545279810749e-06, "loss": 0.0884, "step": 7500 }, { "epoch": 1.674428919937902, "grad_norm": 3.3791210651397705, "learning_rate": 8.838619058179938e-06, "loss": 0.09, "step": 7550 }, { "epoch": 1.685517853182524, "grad_norm": 2.125641345977783, "learning_rate": 8.764692836549125e-06, "loss": 0.0856, "step": 7600 }, { "epoch": 1.6966067864271457, "grad_norm": 2.459035873413086, "learning_rate": 8.690766614918312e-06, "loss": 0.0845, "step": 7650 }, { "epoch": 1.7076957196717677, "grad_norm": 0.977972686290741, "learning_rate": 8.6168403932875e-06, "loss": 0.0973, "step": 7700 }, { "epoch": 1.7187846529163895, "grad_norm": 2.432441473007202, "learning_rate": 8.542914171656688e-06, "loss": 0.0984, "step": 7750 }, { "epoch": 1.7298735861610113, "grad_norm": 1.9185181856155396, "learning_rate": 8.468987950025875e-06, "loss": 0.0878, "step": 7800 }, { "epoch": 1.7409625194056333, "grad_norm": 1.8849973678588867, "learning_rate": 8.395061728395062e-06, "loss": 0.0822, "step": 7850 }, { "epoch": 1.752051452650255, "grad_norm": 3.4242374897003174, "learning_rate": 8.32113550676425e-06, "loss": 0.088, "step": 7900 }, { "epoch": 1.7631403858948769, "grad_norm": 3.122772216796875, "learning_rate": 8.247209285133437e-06, "loss": 0.0858, "step": 7950 }, { "epoch": 1.7742293191394989, "grad_norm": 2.070228338241577, "learning_rate": 8.173283063502625e-06, "loss": 0.0863, "step": 8000 }, { "epoch": 1.7853182523841207, "grad_norm": 1.955519199371338, "learning_rate": 8.099356841871813e-06, "loss": 0.0919, "step": 8050 }, { "epoch": 1.7964071856287425, "grad_norm": 3.2033774852752686, "learning_rate": 8.025430620241e-06, "loss": 0.0906, "step": 8100 }, { "epoch": 1.8074961188733645, "grad_norm": 2.1565141677856445, "learning_rate": 7.951504398610187e-06, "loss": 0.0989, "step": 8150 }, { "epoch": 1.8185850521179863, "grad_norm": 2.1477930545806885, "learning_rate": 7.877578176979376e-06, "loss": 0.0812, "step": 8200 }, { "epoch": 1.829673985362608, "grad_norm": 1.8666229248046875, "learning_rate": 7.803651955348563e-06, "loss": 0.088, "step": 8250 }, { "epoch": 1.84076291860723, "grad_norm": 1.3660918474197388, "learning_rate": 7.72972573371775e-06, "loss": 0.0936, "step": 8300 }, { "epoch": 1.8518518518518519, "grad_norm": 2.6135261058807373, "learning_rate": 7.655799512086937e-06, "loss": 0.0839, "step": 8350 }, { "epoch": 1.8629407850964737, "grad_norm": 3.5965628623962402, "learning_rate": 7.581873290456125e-06, "loss": 0.1014, "step": 8400 }, { "epoch": 1.8740297183410957, "grad_norm": 4.500585079193115, "learning_rate": 7.507947068825313e-06, "loss": 0.0819, "step": 8450 }, { "epoch": 1.8851186515857175, "grad_norm": 2.053957223892212, "learning_rate": 7.434020847194501e-06, "loss": 0.087, "step": 8500 }, { "epoch": 1.8962075848303392, "grad_norm": 1.6143734455108643, "learning_rate": 7.360094625563688e-06, "loss": 0.0908, "step": 8550 }, { "epoch": 1.9072965180749613, "grad_norm": 2.1243669986724854, "learning_rate": 7.286168403932875e-06, "loss": 0.095, "step": 8600 }, { "epoch": 1.918385451319583, "grad_norm": 1.8068082332611084, "learning_rate": 7.212242182302063e-06, "loss": 0.0853, "step": 8650 }, { "epoch": 1.9294743845642048, "grad_norm": 1.7410554885864258, "learning_rate": 7.13831596067125e-06, "loss": 0.0887, "step": 8700 }, { "epoch": 1.9405633178088268, "grad_norm": 3.2952396869659424, "learning_rate": 7.064389739040438e-06, "loss": 0.093, "step": 8750 }, { "epoch": 1.9516522510534486, "grad_norm": 1.382659673690796, "learning_rate": 6.990463517409626e-06, "loss": 0.0988, "step": 8800 }, { "epoch": 1.9627411842980704, "grad_norm": 1.8536710739135742, "learning_rate": 6.916537295778814e-06, "loss": 0.0855, "step": 8850 }, { "epoch": 1.9738301175426924, "grad_norm": 1.3422974348068237, "learning_rate": 6.842611074148001e-06, "loss": 0.0913, "step": 8900 }, { "epoch": 1.9849190507873142, "grad_norm": 0.9699559211730957, "learning_rate": 6.768684852517189e-06, "loss": 0.0827, "step": 8950 }, { "epoch": 1.996007984031936, "grad_norm": 2.4076015949249268, "learning_rate": 6.694758630886376e-06, "loss": 0.0738, "step": 9000 }, { "epoch": 2.007096917276558, "grad_norm": 2.115738868713379, "learning_rate": 6.620832409255563e-06, "loss": 0.0799, "step": 9050 }, { "epoch": 2.01818585052118, "grad_norm": 0.871468186378479, "learning_rate": 6.546906187624751e-06, "loss": 0.0636, "step": 9100 }, { "epoch": 2.0292747837658016, "grad_norm": 3.783653497695923, "learning_rate": 6.472979965993939e-06, "loss": 0.0689, "step": 9150 }, { "epoch": 2.0403637170104236, "grad_norm": 2.4445955753326416, "learning_rate": 6.399053744363127e-06, "loss": 0.0792, "step": 9200 }, { "epoch": 2.0514526502550456, "grad_norm": 1.8684531450271606, "learning_rate": 6.325127522732314e-06, "loss": 0.0661, "step": 9250 }, { "epoch": 2.062541583499667, "grad_norm": 1.0839345455169678, "learning_rate": 6.2512013011015016e-06, "loss": 0.0775, "step": 9300 }, { "epoch": 2.073630516744289, "grad_norm": 0.9116957187652588, "learning_rate": 6.1772750794706895e-06, "loss": 0.0772, "step": 9350 }, { "epoch": 2.0847194499889112, "grad_norm": 1.6374276876449585, "learning_rate": 6.103348857839876e-06, "loss": 0.0649, "step": 9400 }, { "epoch": 2.095808383233533, "grad_norm": 2.419456720352173, "learning_rate": 6.029422636209064e-06, "loss": 0.0688, "step": 9450 }, { "epoch": 2.106897316478155, "grad_norm": 3.2619240283966064, "learning_rate": 5.9554964145782515e-06, "loss": 0.0773, "step": 9500 }, { "epoch": 2.117986249722777, "grad_norm": 3.0861144065856934, "learning_rate": 5.8815701929474386e-06, "loss": 0.074, "step": 9550 }, { "epoch": 2.1290751829673984, "grad_norm": 1.3020782470703125, "learning_rate": 5.8076439713166265e-06, "loss": 0.0702, "step": 9600 }, { "epoch": 2.1401641162120204, "grad_norm": 2.4096367359161377, "learning_rate": 5.733717749685814e-06, "loss": 0.0713, "step": 9650 }, { "epoch": 2.1512530494566424, "grad_norm": 1.2149136066436768, "learning_rate": 5.659791528055002e-06, "loss": 0.0664, "step": 9700 }, { "epoch": 2.162341982701264, "grad_norm": 3.8028881549835205, "learning_rate": 5.585865306424189e-06, "loss": 0.0736, "step": 9750 }, { "epoch": 2.173430915945886, "grad_norm": 2.2303028106689453, "learning_rate": 5.511939084793376e-06, "loss": 0.0748, "step": 9800 }, { "epoch": 2.184519849190508, "grad_norm": 2.6183419227600098, "learning_rate": 5.438012863162564e-06, "loss": 0.0768, "step": 9850 }, { "epoch": 2.1956087824351296, "grad_norm": 1.402911901473999, "learning_rate": 5.364086641531751e-06, "loss": 0.0663, "step": 9900 }, { "epoch": 2.2066977156797516, "grad_norm": 2.14359450340271, "learning_rate": 5.290160419900939e-06, "loss": 0.0654, "step": 9950 }, { "epoch": 2.2177866489243736, "grad_norm": 1.4012452363967896, "learning_rate": 5.216234198270127e-06, "loss": 0.0803, "step": 10000 }, { "epoch": 2.228875582168995, "grad_norm": 0.9938985705375671, "learning_rate": 5.142307976639315e-06, "loss": 0.0743, "step": 10050 }, { "epoch": 2.239964515413617, "grad_norm": 1.9487541913986206, "learning_rate": 5.068381755008502e-06, "loss": 0.0748, "step": 10100 }, { "epoch": 2.251053448658239, "grad_norm": 6.113137245178223, "learning_rate": 4.994455533377689e-06, "loss": 0.0816, "step": 10150 }, { "epoch": 2.2621423819028608, "grad_norm": 1.868437647819519, "learning_rate": 4.920529311746877e-06, "loss": 0.0752, "step": 10200 }, { "epoch": 2.273231315147483, "grad_norm": 1.6830744743347168, "learning_rate": 4.846603090116064e-06, "loss": 0.0706, "step": 10250 }, { "epoch": 2.284320248392105, "grad_norm": 1.8964732885360718, "learning_rate": 4.772676868485252e-06, "loss": 0.0687, "step": 10300 }, { "epoch": 2.2954091816367264, "grad_norm": 2.1506104469299316, "learning_rate": 4.69875064685444e-06, "loss": 0.0838, "step": 10350 }, { "epoch": 2.3064981148813484, "grad_norm": 2.777594804763794, "learning_rate": 4.624824425223627e-06, "loss": 0.0684, "step": 10400 }, { "epoch": 2.3175870481259704, "grad_norm": 1.3911370038986206, "learning_rate": 4.550898203592815e-06, "loss": 0.0679, "step": 10450 }, { "epoch": 2.3286759813705924, "grad_norm": 1.7069896459579468, "learning_rate": 4.476971981962002e-06, "loss": 0.0683, "step": 10500 }, { "epoch": 2.339764914615214, "grad_norm": 3.0551908016204834, "learning_rate": 4.40304576033119e-06, "loss": 0.0719, "step": 10550 }, { "epoch": 2.350853847859836, "grad_norm": 1.223029375076294, "learning_rate": 4.329119538700378e-06, "loss": 0.0692, "step": 10600 }, { "epoch": 2.3619427811044575, "grad_norm": 3.9574992656707764, "learning_rate": 4.255193317069565e-06, "loss": 0.0716, "step": 10650 }, { "epoch": 2.3730317143490796, "grad_norm": 1.701469898223877, "learning_rate": 4.181267095438753e-06, "loss": 0.0857, "step": 10700 }, { "epoch": 2.3841206475937016, "grad_norm": 1.5294601917266846, "learning_rate": 4.10734087380794e-06, "loss": 0.0714, "step": 10750 }, { "epoch": 2.3952095808383236, "grad_norm": 2.6890389919281006, "learning_rate": 4.033414652177128e-06, "loss": 0.0649, "step": 10800 }, { "epoch": 2.406298514082945, "grad_norm": 1.7154722213745117, "learning_rate": 3.959488430546315e-06, "loss": 0.0736, "step": 10850 }, { "epoch": 2.417387447327567, "grad_norm": 1.9531513452529907, "learning_rate": 3.885562208915503e-06, "loss": 0.0764, "step": 10900 }, { "epoch": 2.4284763805721887, "grad_norm": 1.5990239381790161, "learning_rate": 3.81163598728469e-06, "loss": 0.0617, "step": 10950 }, { "epoch": 2.4395653138168107, "grad_norm": 1.2892380952835083, "learning_rate": 3.737709765653878e-06, "loss": 0.0644, "step": 11000 }, { "epoch": 2.4506542470614328, "grad_norm": 2.5764858722686768, "learning_rate": 3.663783544023065e-06, "loss": 0.0606, "step": 11050 }, { "epoch": 2.4617431803060548, "grad_norm": 2.1783535480499268, "learning_rate": 3.589857322392253e-06, "loss": 0.0816, "step": 11100 }, { "epoch": 2.4728321135506763, "grad_norm": 2.3354318141937256, "learning_rate": 3.5159311007614405e-06, "loss": 0.0817, "step": 11150 }, { "epoch": 2.4839210467952983, "grad_norm": 3.374755382537842, "learning_rate": 3.4420048791306276e-06, "loss": 0.0737, "step": 11200 }, { "epoch": 2.49500998003992, "grad_norm": 3.841001272201538, "learning_rate": 3.3680786574998155e-06, "loss": 0.068, "step": 11250 }, { "epoch": 2.506098913284542, "grad_norm": 1.0251437425613403, "learning_rate": 3.294152435869003e-06, "loss": 0.0776, "step": 11300 }, { "epoch": 2.517187846529164, "grad_norm": 2.3336868286132812, "learning_rate": 3.220226214238191e-06, "loss": 0.074, "step": 11350 }, { "epoch": 2.528276779773786, "grad_norm": 1.9687585830688477, "learning_rate": 3.146299992607378e-06, "loss": 0.0634, "step": 11400 }, { "epoch": 2.5393657130184075, "grad_norm": 3.6472342014312744, "learning_rate": 3.0723737709765654e-06, "loss": 0.0713, "step": 11450 }, { "epoch": 2.5504546462630295, "grad_norm": 1.97185218334198, "learning_rate": 2.9984475493457533e-06, "loss": 0.0692, "step": 11500 }, { "epoch": 2.561543579507651, "grad_norm": 8.52320671081543, "learning_rate": 2.9245213277149408e-06, "loss": 0.0679, "step": 11550 }, { "epoch": 2.572632512752273, "grad_norm": 4.320559501647949, "learning_rate": 2.850595106084128e-06, "loss": 0.0775, "step": 11600 }, { "epoch": 2.583721445996895, "grad_norm": 0.5261452794075012, "learning_rate": 2.7766688844533158e-06, "loss": 0.0577, "step": 11650 }, { "epoch": 2.594810379241517, "grad_norm": 1.5301717519760132, "learning_rate": 2.7027426628225032e-06, "loss": 0.0694, "step": 11700 }, { "epoch": 2.6058993124861387, "grad_norm": 1.3441177606582642, "learning_rate": 2.628816441191691e-06, "loss": 0.0733, "step": 11750 }, { "epoch": 2.6169882457307607, "grad_norm": 1.2103335857391357, "learning_rate": 2.554890219560878e-06, "loss": 0.0764, "step": 11800 }, { "epoch": 2.6280771789753827, "grad_norm": 2.5863022804260254, "learning_rate": 2.480963997930066e-06, "loss": 0.0764, "step": 11850 }, { "epoch": 2.6391661122200043, "grad_norm": 2.4411420822143555, "learning_rate": 2.4070377762992536e-06, "loss": 0.0763, "step": 11900 }, { "epoch": 2.6502550454646263, "grad_norm": 2.061426877975464, "learning_rate": 2.333111554668441e-06, "loss": 0.075, "step": 11950 }, { "epoch": 2.6613439787092483, "grad_norm": 0.7995760440826416, "learning_rate": 2.2591853330376285e-06, "loss": 0.0622, "step": 12000 }, { "epoch": 2.67243291195387, "grad_norm": 2.9890496730804443, "learning_rate": 2.185259111406816e-06, "loss": 0.0766, "step": 12050 }, { "epoch": 2.683521845198492, "grad_norm": 2.9018654823303223, "learning_rate": 2.111332889776004e-06, "loss": 0.0677, "step": 12100 }, { "epoch": 2.694610778443114, "grad_norm": 0.40557801723480225, "learning_rate": 2.0374066681451914e-06, "loss": 0.0647, "step": 12150 }, { "epoch": 2.7056997116877355, "grad_norm": 4.465837001800537, "learning_rate": 1.963480446514379e-06, "loss": 0.0649, "step": 12200 }, { "epoch": 2.7167886449323575, "grad_norm": 2.300358533859253, "learning_rate": 1.8895542248835664e-06, "loss": 0.0797, "step": 12250 }, { "epoch": 2.7278775781769795, "grad_norm": 1.4945405721664429, "learning_rate": 1.815628003252754e-06, "loss": 0.0651, "step": 12300 }, { "epoch": 2.738966511421601, "grad_norm": 1.3923050165176392, "learning_rate": 1.7417017816219413e-06, "loss": 0.0857, "step": 12350 }, { "epoch": 2.750055444666223, "grad_norm": 1.2946971654891968, "learning_rate": 1.667775559991129e-06, "loss": 0.0634, "step": 12400 }, { "epoch": 2.761144377910845, "grad_norm": 2.017392158508301, "learning_rate": 1.5938493383603165e-06, "loss": 0.0585, "step": 12450 }, { "epoch": 2.7722333111554667, "grad_norm": 2.730674982070923, "learning_rate": 1.5199231167295042e-06, "loss": 0.0647, "step": 12500 }, { "epoch": 2.7833222444000887, "grad_norm": 0.6496580243110657, "learning_rate": 1.4459968950986917e-06, "loss": 0.0611, "step": 12550 }, { "epoch": 2.7944111776447107, "grad_norm": 3.458625078201294, "learning_rate": 1.372070673467879e-06, "loss": 0.0784, "step": 12600 }, { "epoch": 2.8055001108893327, "grad_norm": 8.372861862182617, "learning_rate": 1.2981444518370667e-06, "loss": 0.0668, "step": 12650 }, { "epoch": 2.8165890441339543, "grad_norm": 3.9860599040985107, "learning_rate": 1.2242182302062543e-06, "loss": 0.067, "step": 12700 }, { "epoch": 2.8276779773785763, "grad_norm": 1.4425193071365356, "learning_rate": 1.1502920085754418e-06, "loss": 0.0706, "step": 12750 }, { "epoch": 2.838766910623198, "grad_norm": 2.859701156616211, "learning_rate": 1.0763657869446293e-06, "loss": 0.0679, "step": 12800 }, { "epoch": 2.84985584386782, "grad_norm": 2.2282726764678955, "learning_rate": 1.002439565313817e-06, "loss": 0.0724, "step": 12850 }, { "epoch": 2.860944777112442, "grad_norm": 2.407137870788574, "learning_rate": 9.285133436830045e-07, "loss": 0.0627, "step": 12900 }, { "epoch": 2.872033710357064, "grad_norm": 3.5280649662017822, "learning_rate": 8.54587122052192e-07, "loss": 0.0674, "step": 12950 }, { "epoch": 2.8831226436016855, "grad_norm": 1.6543505191802979, "learning_rate": 7.806609004213796e-07, "loss": 0.0765, "step": 13000 }, { "epoch": 2.8942115768463075, "grad_norm": 0.9745455384254456, "learning_rate": 7.067346787905671e-07, "loss": 0.0602, "step": 13050 }, { "epoch": 2.905300510090929, "grad_norm": 2.4250497817993164, "learning_rate": 6.328084571597546e-07, "loss": 0.0735, "step": 13100 }, { "epoch": 2.916389443335551, "grad_norm": 2.5135929584503174, "learning_rate": 5.588822355289421e-07, "loss": 0.0654, "step": 13150 }, { "epoch": 2.927478376580173, "grad_norm": 1.6418380737304688, "learning_rate": 4.849560138981297e-07, "loss": 0.0667, "step": 13200 }, { "epoch": 2.938567309824795, "grad_norm": 4.118490695953369, "learning_rate": 4.1102979226731723e-07, "loss": 0.0725, "step": 13250 }, { "epoch": 2.9496562430694167, "grad_norm": 0.931894063949585, "learning_rate": 3.371035706365048e-07, "loss": 0.0548, "step": 13300 }, { "epoch": 2.9607451763140387, "grad_norm": 0.6899275183677673, "learning_rate": 2.6317734900569235e-07, "loss": 0.0826, "step": 13350 }, { "epoch": 2.9718341095586602, "grad_norm": 1.263277292251587, "learning_rate": 1.892511273748799e-07, "loss": 0.0683, "step": 13400 }, { "epoch": 2.9829230428032822, "grad_norm": 2.3304920196533203, "learning_rate": 1.1532490574406743e-07, "loss": 0.0651, "step": 13450 }, { "epoch": 2.9940119760479043, "grad_norm": 1.8537914752960205, "learning_rate": 4.139868411325497e-08, "loss": 0.0648, "step": 13500 } ], "logging_steps": 50, "max_steps": 13527, "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": 1.414150781306112e+16, "train_batch_size": 16, "trial_name": null, "trial_params": null }