{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 4179, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0023933464967390654, "grad_norm": 7.753860950469971, "learning_rate": 4.761064671776892e-06, "loss": 2.1283, "step": 10 }, { "epoch": 0.004786692993478131, "grad_norm": 3.498722791671753, "learning_rate": 6.194287949277823e-06, "loss": 1.1551, "step": 20 }, { "epoch": 0.007180039490217196, "grad_norm": 4.094305515289307, "learning_rate": 7.032669821776541e-06, "loss": 0.9528, "step": 30 }, { "epoch": 0.009573385986956262, "grad_norm": 7.770979881286621, "learning_rate": 7.627511226778755e-06, "loss": 0.829, "step": 40 }, { "epoch": 0.011966732483695328, "grad_norm": 7.127616882324219, "learning_rate": 8.088906066052852e-06, "loss": 0.7821, "step": 50 }, { "epoch": 0.014360078980434392, "grad_norm": 7.3015289306640625, "learning_rate": 8.465893099277471e-06, "loss": 0.6785, "step": 60 }, { "epoch": 0.01675342547717346, "grad_norm": 5.450230121612549, "learning_rate": 8.784631094276665e-06, "loss": 0.6297, "step": 70 }, { "epoch": 0.019146771973912523, "grad_norm": 4.430941581726074, "learning_rate": 9.060734504279687e-06, "loss": 0.6126, "step": 80 }, { "epoch": 0.021540118470651588, "grad_norm": 3.1959335803985596, "learning_rate": 9.304274971776188e-06, "loss": 0.568, "step": 90 }, { "epoch": 0.023933464967390655, "grad_norm": 2.2006144523620605, "learning_rate": 9.522129343553784e-06, "loss": 0.5229, "step": 100 }, { "epoch": 0.02632681146412972, "grad_norm": 2.263533592224121, "learning_rate": 9.719202594530593e-06, "loss": 0.5512, "step": 110 }, { "epoch": 0.028720157960868783, "grad_norm": 1.8305617570877075, "learning_rate": 9.899116376778404e-06, "loss": 0.5437, "step": 120 }, { "epoch": 0.03111350445760785, "grad_norm": 2.038649320602417, "learning_rate": 9.99259807549963e-06, "loss": 0.5128, "step": 130 }, { "epoch": 0.03350685095434692, "grad_norm": 1.7406952381134033, "learning_rate": 9.96792499383173e-06, "loss": 0.529, "step": 140 }, { "epoch": 0.03590019745108598, "grad_norm": 1.9308490753173828, "learning_rate": 9.94325191216383e-06, "loss": 0.5036, "step": 150 }, { "epoch": 0.03829354394782505, "grad_norm": 2.4779229164123535, "learning_rate": 9.91857883049593e-06, "loss": 0.5245, "step": 160 }, { "epoch": 0.04068689044456411, "grad_norm": 1.8702728748321533, "learning_rate": 9.89390574882803e-06, "loss": 0.4861, "step": 170 }, { "epoch": 0.043080236941303175, "grad_norm": 1.7144496440887451, "learning_rate": 9.869232667160129e-06, "loss": 0.5342, "step": 180 }, { "epoch": 0.04547358343804224, "grad_norm": 1.6926618814468384, "learning_rate": 9.844559585492228e-06, "loss": 0.4843, "step": 190 }, { "epoch": 0.04786692993478131, "grad_norm": 1.597118616104126, "learning_rate": 9.819886503824329e-06, "loss": 0.4648, "step": 200 }, { "epoch": 0.050260276431520375, "grad_norm": 1.7021759748458862, "learning_rate": 9.795213422156428e-06, "loss": 0.4706, "step": 210 }, { "epoch": 0.05265362292825944, "grad_norm": 1.6933318376541138, "learning_rate": 9.770540340488527e-06, "loss": 0.5085, "step": 220 }, { "epoch": 0.0550469694249985, "grad_norm": 1.7552145719528198, "learning_rate": 9.745867258820626e-06, "loss": 0.4284, "step": 230 }, { "epoch": 0.05744031592173757, "grad_norm": 1.4576905965805054, "learning_rate": 9.721194177152727e-06, "loss": 0.4546, "step": 240 }, { "epoch": 0.05983366241847664, "grad_norm": 1.6415495872497559, "learning_rate": 9.696521095484827e-06, "loss": 0.5003, "step": 250 }, { "epoch": 0.0622270089152157, "grad_norm": 2.341928720474243, "learning_rate": 9.671848013816928e-06, "loss": 0.4583, "step": 260 }, { "epoch": 0.06462035541195477, "grad_norm": 1.8057796955108643, "learning_rate": 9.647174932149027e-06, "loss": 0.4628, "step": 270 }, { "epoch": 0.06701370190869384, "grad_norm": 1.578305959701538, "learning_rate": 9.622501850481126e-06, "loss": 0.4446, "step": 280 }, { "epoch": 0.0694070484054329, "grad_norm": 1.426010012626648, "learning_rate": 9.597828768813225e-06, "loss": 0.4734, "step": 290 }, { "epoch": 0.07180039490217197, "grad_norm": 1.4295073747634888, "learning_rate": 9.573155687145326e-06, "loss": 0.4119, "step": 300 }, { "epoch": 0.07419374139891102, "grad_norm": 1.4099984169006348, "learning_rate": 9.548482605477426e-06, "loss": 0.4242, "step": 310 }, { "epoch": 0.0765870878956501, "grad_norm": 1.5255640745162964, "learning_rate": 9.523809523809525e-06, "loss": 0.4447, "step": 320 }, { "epoch": 0.07898043439238916, "grad_norm": 1.5205039978027344, "learning_rate": 9.499136442141624e-06, "loss": 0.3884, "step": 330 }, { "epoch": 0.08137378088912822, "grad_norm": 1.6005034446716309, "learning_rate": 9.474463360473723e-06, "loss": 0.4152, "step": 340 }, { "epoch": 0.0837671273858673, "grad_norm": 1.4102376699447632, "learning_rate": 9.449790278805824e-06, "loss": 0.4037, "step": 350 }, { "epoch": 0.08616047388260635, "grad_norm": 1.417392611503601, "learning_rate": 9.425117197137923e-06, "loss": 0.4502, "step": 360 }, { "epoch": 0.08855382037934542, "grad_norm": 1.512369155883789, "learning_rate": 9.400444115470023e-06, "loss": 0.3847, "step": 370 }, { "epoch": 0.09094716687608448, "grad_norm": 1.4647409915924072, "learning_rate": 9.375771033802122e-06, "loss": 0.4553, "step": 380 }, { "epoch": 0.09334051337282355, "grad_norm": 1.4595036506652832, "learning_rate": 9.351097952134223e-06, "loss": 0.4156, "step": 390 }, { "epoch": 0.09573385986956262, "grad_norm": 1.383710265159607, "learning_rate": 9.326424870466322e-06, "loss": 0.4098, "step": 400 }, { "epoch": 0.09812720636630168, "grad_norm": 1.6963629722595215, "learning_rate": 9.301751788798421e-06, "loss": 0.3902, "step": 410 }, { "epoch": 0.10052055286304075, "grad_norm": 1.4952212572097778, "learning_rate": 9.27707870713052e-06, "loss": 0.3965, "step": 420 }, { "epoch": 0.1029138993597798, "grad_norm": 2.1313915252685547, "learning_rate": 9.252405625462622e-06, "loss": 0.4293, "step": 430 }, { "epoch": 0.10530724585651888, "grad_norm": 1.3771822452545166, "learning_rate": 9.22773254379472e-06, "loss": 0.3626, "step": 440 }, { "epoch": 0.10770059235325795, "grad_norm": 1.5717588663101196, "learning_rate": 9.20305946212682e-06, "loss": 0.3767, "step": 450 }, { "epoch": 0.110093938849997, "grad_norm": 1.3924773931503296, "learning_rate": 9.178386380458921e-06, "loss": 0.4452, "step": 460 }, { "epoch": 0.11248728534673608, "grad_norm": 1.3925224542617798, "learning_rate": 9.153713298791019e-06, "loss": 0.4038, "step": 470 }, { "epoch": 0.11488063184347513, "grad_norm": 1.9098495244979858, "learning_rate": 9.12904021712312e-06, "loss": 0.4009, "step": 480 }, { "epoch": 0.1172739783402142, "grad_norm": 1.3831137418746948, "learning_rate": 9.104367135455219e-06, "loss": 0.3885, "step": 490 }, { "epoch": 0.11966732483695328, "grad_norm": 1.42930269241333, "learning_rate": 9.07969405378732e-06, "loss": 0.3748, "step": 500 }, { "epoch": 0.12206067133369233, "grad_norm": 1.7836018800735474, "learning_rate": 9.055020972119419e-06, "loss": 0.3877, "step": 510 }, { "epoch": 0.1244540178304314, "grad_norm": 1.2974871397018433, "learning_rate": 9.030347890451518e-06, "loss": 0.3802, "step": 520 }, { "epoch": 0.12684736432717048, "grad_norm": 1.4758553504943848, "learning_rate": 9.005674808783617e-06, "loss": 0.3412, "step": 530 }, { "epoch": 0.12924071082390953, "grad_norm": 1.6040432453155518, "learning_rate": 8.981001727115718e-06, "loss": 0.4111, "step": 540 }, { "epoch": 0.1316340573206486, "grad_norm": 1.4365266561508179, "learning_rate": 8.956328645447818e-06, "loss": 0.3592, "step": 550 }, { "epoch": 0.13402740381738767, "grad_norm": 1.3663755655288696, "learning_rate": 8.931655563779917e-06, "loss": 0.3978, "step": 560 }, { "epoch": 0.13642075031412673, "grad_norm": 1.33884596824646, "learning_rate": 8.906982482112016e-06, "loss": 0.3598, "step": 570 }, { "epoch": 0.1388140968108658, "grad_norm": 1.425356149673462, "learning_rate": 8.882309400444115e-06, "loss": 0.3762, "step": 580 }, { "epoch": 0.14120744330760485, "grad_norm": 1.6644937992095947, "learning_rate": 8.857636318776216e-06, "loss": 0.3752, "step": 590 }, { "epoch": 0.14360078980434393, "grad_norm": 1.3323246240615845, "learning_rate": 8.832963237108316e-06, "loss": 0.3501, "step": 600 }, { "epoch": 0.145994136301083, "grad_norm": 1.4648693799972534, "learning_rate": 8.808290155440415e-06, "loss": 0.3671, "step": 610 }, { "epoch": 0.14838748279782205, "grad_norm": 1.4320498704910278, "learning_rate": 8.783617073772514e-06, "loss": 0.3755, "step": 620 }, { "epoch": 0.15078082929456113, "grad_norm": 1.3594764471054077, "learning_rate": 8.758943992104615e-06, "loss": 0.3611, "step": 630 }, { "epoch": 0.1531741757913002, "grad_norm": 1.2988762855529785, "learning_rate": 8.734270910436714e-06, "loss": 0.4019, "step": 640 }, { "epoch": 0.15556752228803924, "grad_norm": 1.3275034427642822, "learning_rate": 8.709597828768815e-06, "loss": 0.3706, "step": 650 }, { "epoch": 0.15796086878477833, "grad_norm": 1.4416245222091675, "learning_rate": 8.684924747100913e-06, "loss": 0.3398, "step": 660 }, { "epoch": 0.1603542152815174, "grad_norm": 1.310385823249817, "learning_rate": 8.660251665433014e-06, "loss": 0.3511, "step": 670 }, { "epoch": 0.16274756177825644, "grad_norm": 1.4238604307174683, "learning_rate": 8.635578583765113e-06, "loss": 0.3662, "step": 680 }, { "epoch": 0.1651409082749955, "grad_norm": 1.3813670873641968, "learning_rate": 8.610905502097212e-06, "loss": 0.3567, "step": 690 }, { "epoch": 0.1675342547717346, "grad_norm": 1.3047897815704346, "learning_rate": 8.586232420429313e-06, "loss": 0.3549, "step": 700 }, { "epoch": 0.16992760126847364, "grad_norm": 1.58772873878479, "learning_rate": 8.561559338761412e-06, "loss": 0.3671, "step": 710 }, { "epoch": 0.1723209477652127, "grad_norm": 1.5185716152191162, "learning_rate": 8.536886257093512e-06, "loss": 0.3749, "step": 720 }, { "epoch": 0.17471429426195179, "grad_norm": 1.7793872356414795, "learning_rate": 8.51221317542561e-06, "loss": 0.3519, "step": 730 }, { "epoch": 0.17710764075869084, "grad_norm": 1.3881484270095825, "learning_rate": 8.487540093757712e-06, "loss": 0.369, "step": 740 }, { "epoch": 0.1795009872554299, "grad_norm": 1.4998046159744263, "learning_rate": 8.462867012089811e-06, "loss": 0.3476, "step": 750 }, { "epoch": 0.18189433375216896, "grad_norm": 1.4328734874725342, "learning_rate": 8.43819393042191e-06, "loss": 0.3456, "step": 760 }, { "epoch": 0.18428768024890804, "grad_norm": 1.5154374837875366, "learning_rate": 8.41352084875401e-06, "loss": 0.3508, "step": 770 }, { "epoch": 0.1866810267456471, "grad_norm": 1.2864036560058594, "learning_rate": 8.38884776708611e-06, "loss": 0.3711, "step": 780 }, { "epoch": 0.18907437324238616, "grad_norm": 1.4054689407348633, "learning_rate": 8.36417468541821e-06, "loss": 0.3367, "step": 790 }, { "epoch": 0.19146771973912524, "grad_norm": 1.3985927104949951, "learning_rate": 8.339501603750309e-06, "loss": 0.3512, "step": 800 }, { "epoch": 0.1938610662358643, "grad_norm": 1.5572525262832642, "learning_rate": 8.314828522082408e-06, "loss": 0.3262, "step": 810 }, { "epoch": 0.19625441273260336, "grad_norm": 1.3198823928833008, "learning_rate": 8.290155440414507e-06, "loss": 0.3135, "step": 820 }, { "epoch": 0.19864775922934244, "grad_norm": 1.3439698219299316, "learning_rate": 8.265482358746608e-06, "loss": 0.365, "step": 830 }, { "epoch": 0.2010411057260815, "grad_norm": 1.216245412826538, "learning_rate": 8.240809277078708e-06, "loss": 0.3556, "step": 840 }, { "epoch": 0.20343445222282056, "grad_norm": 1.33769690990448, "learning_rate": 8.216136195410807e-06, "loss": 0.3426, "step": 850 }, { "epoch": 0.2058277987195596, "grad_norm": 1.4364330768585205, "learning_rate": 8.191463113742906e-06, "loss": 0.3475, "step": 860 }, { "epoch": 0.2082211452162987, "grad_norm": 1.3421498537063599, "learning_rate": 8.166790032075007e-06, "loss": 0.3546, "step": 870 }, { "epoch": 0.21061449171303775, "grad_norm": 1.5308326482772827, "learning_rate": 8.142116950407106e-06, "loss": 0.335, "step": 880 }, { "epoch": 0.2130078382097768, "grad_norm": 1.6924855709075928, "learning_rate": 8.117443868739207e-06, "loss": 0.3811, "step": 890 }, { "epoch": 0.2154011847065159, "grad_norm": 1.4369523525238037, "learning_rate": 8.092770787071306e-06, "loss": 0.3116, "step": 900 }, { "epoch": 0.21779453120325495, "grad_norm": 1.2049809694290161, "learning_rate": 8.068097705403406e-06, "loss": 0.367, "step": 910 }, { "epoch": 0.220187877699994, "grad_norm": 1.4389671087265015, "learning_rate": 8.043424623735505e-06, "loss": 0.3291, "step": 920 }, { "epoch": 0.22258122419673307, "grad_norm": 1.2352498769760132, "learning_rate": 8.018751542067606e-06, "loss": 0.3459, "step": 930 }, { "epoch": 0.22497457069347215, "grad_norm": 1.7172787189483643, "learning_rate": 7.994078460399705e-06, "loss": 0.3251, "step": 940 }, { "epoch": 0.2273679171902112, "grad_norm": 1.2729766368865967, "learning_rate": 7.969405378731804e-06, "loss": 0.2964, "step": 950 }, { "epoch": 0.22976126368695027, "grad_norm": 1.4884804487228394, "learning_rate": 7.944732297063904e-06, "loss": 0.3043, "step": 960 }, { "epoch": 0.23215461018368935, "grad_norm": 1.7863214015960693, "learning_rate": 7.920059215396003e-06, "loss": 0.3522, "step": 970 }, { "epoch": 0.2345479566804284, "grad_norm": 1.4292254447937012, "learning_rate": 7.895386133728104e-06, "loss": 0.3481, "step": 980 }, { "epoch": 0.23694130317716747, "grad_norm": 1.251381278038025, "learning_rate": 7.870713052060203e-06, "loss": 0.3092, "step": 990 }, { "epoch": 0.23933464967390655, "grad_norm": 1.236761212348938, "learning_rate": 7.846039970392302e-06, "loss": 0.3183, "step": 1000 }, { "epoch": 0.2417279961706456, "grad_norm": 1.38023042678833, "learning_rate": 7.821366888724402e-06, "loss": 0.3327, "step": 1010 }, { "epoch": 0.24412134266738467, "grad_norm": 1.3220731019973755, "learning_rate": 7.796693807056503e-06, "loss": 0.3098, "step": 1020 }, { "epoch": 0.24651468916412372, "grad_norm": 1.5054066181182861, "learning_rate": 7.772020725388602e-06, "loss": 0.3766, "step": 1030 }, { "epoch": 0.2489080356608628, "grad_norm": 1.525158166885376, "learning_rate": 7.747347643720701e-06, "loss": 0.3222, "step": 1040 }, { "epoch": 0.2513013821576019, "grad_norm": 1.6636648178100586, "learning_rate": 7.7226745620528e-06, "loss": 0.3072, "step": 1050 }, { "epoch": 0.25369472865434095, "grad_norm": 1.279959797859192, "learning_rate": 7.698001480384901e-06, "loss": 0.3437, "step": 1060 }, { "epoch": 0.25608807515108, "grad_norm": 1.5092816352844238, "learning_rate": 7.673328398717e-06, "loss": 0.3541, "step": 1070 }, { "epoch": 0.25848142164781907, "grad_norm": 1.2588694095611572, "learning_rate": 7.6486553170491e-06, "loss": 0.3111, "step": 1080 }, { "epoch": 0.2608747681445581, "grad_norm": 1.4029079675674438, "learning_rate": 7.6239822353812e-06, "loss": 0.3596, "step": 1090 }, { "epoch": 0.2632681146412972, "grad_norm": 1.1977208852767944, "learning_rate": 7.599309153713299e-06, "loss": 0.3323, "step": 1100 }, { "epoch": 0.26566146113803624, "grad_norm": 1.3156075477600098, "learning_rate": 7.574636072045399e-06, "loss": 0.3074, "step": 1110 }, { "epoch": 0.26805480763477535, "grad_norm": 1.2822346687316895, "learning_rate": 7.549962990377498e-06, "loss": 0.3054, "step": 1120 }, { "epoch": 0.2704481541315144, "grad_norm": 1.1119033098220825, "learning_rate": 7.5252899087095985e-06, "loss": 0.3314, "step": 1130 }, { "epoch": 0.27284150062825346, "grad_norm": 1.1619426012039185, "learning_rate": 7.500616827041698e-06, "loss": 0.3193, "step": 1140 }, { "epoch": 0.2752348471249925, "grad_norm": 1.0465056896209717, "learning_rate": 7.475943745373798e-06, "loss": 0.321, "step": 1150 }, { "epoch": 0.2776281936217316, "grad_norm": 1.2400563955307007, "learning_rate": 7.451270663705897e-06, "loss": 0.3158, "step": 1160 }, { "epoch": 0.28002154011847064, "grad_norm": 2.0701723098754883, "learning_rate": 7.426597582037998e-06, "loss": 0.3207, "step": 1170 }, { "epoch": 0.2824148866152097, "grad_norm": 1.1048980951309204, "learning_rate": 7.401924500370096e-06, "loss": 0.3478, "step": 1180 }, { "epoch": 0.2848082331119488, "grad_norm": 1.3041422367095947, "learning_rate": 7.377251418702196e-06, "loss": 0.3174, "step": 1190 }, { "epoch": 0.28720157960868786, "grad_norm": 1.2175705432891846, "learning_rate": 7.352578337034297e-06, "loss": 0.3037, "step": 1200 }, { "epoch": 0.2895949261054269, "grad_norm": 1.3585985898971558, "learning_rate": 7.327905255366396e-06, "loss": 0.3388, "step": 1210 }, { "epoch": 0.291988272602166, "grad_norm": 1.4350008964538574, "learning_rate": 7.303232173698496e-06, "loss": 0.3088, "step": 1220 }, { "epoch": 0.29438161909890503, "grad_norm": 1.3344910144805908, "learning_rate": 7.278559092030595e-06, "loss": 0.3445, "step": 1230 }, { "epoch": 0.2967749655956441, "grad_norm": 1.1793681383132935, "learning_rate": 7.253886010362695e-06, "loss": 0.3246, "step": 1240 }, { "epoch": 0.29916831209238315, "grad_norm": 1.3544061183929443, "learning_rate": 7.2292129286947945e-06, "loss": 0.3141, "step": 1250 }, { "epoch": 0.30156165858912226, "grad_norm": 1.1560149192810059, "learning_rate": 7.204539847026895e-06, "loss": 0.3144, "step": 1260 }, { "epoch": 0.3039550050858613, "grad_norm": 1.2720812559127808, "learning_rate": 7.179866765358994e-06, "loss": 0.3163, "step": 1270 }, { "epoch": 0.3063483515826004, "grad_norm": 1.2398178577423096, "learning_rate": 7.155193683691094e-06, "loss": 0.3071, "step": 1280 }, { "epoch": 0.30874169807933943, "grad_norm": 1.369046926498413, "learning_rate": 7.130520602023193e-06, "loss": 0.3015, "step": 1290 }, { "epoch": 0.3111350445760785, "grad_norm": 1.6074063777923584, "learning_rate": 7.105847520355293e-06, "loss": 0.2872, "step": 1300 }, { "epoch": 0.31352839107281755, "grad_norm": 1.5829745531082153, "learning_rate": 7.0811744386873925e-06, "loss": 0.2759, "step": 1310 }, { "epoch": 0.31592173756955666, "grad_norm": 1.3352031707763672, "learning_rate": 7.056501357019492e-06, "loss": 0.3207, "step": 1320 }, { "epoch": 0.3183150840662957, "grad_norm": 1.0942381620407104, "learning_rate": 7.031828275351592e-06, "loss": 0.3184, "step": 1330 }, { "epoch": 0.3207084305630348, "grad_norm": 2.5868372917175293, "learning_rate": 7.007155193683691e-06, "loss": 0.2916, "step": 1340 }, { "epoch": 0.32310177705977383, "grad_norm": 1.0892747640609741, "learning_rate": 6.982482112015791e-06, "loss": 0.2934, "step": 1350 }, { "epoch": 0.3254951235565129, "grad_norm": 1.5752267837524414, "learning_rate": 6.9578090303478905e-06, "loss": 0.2984, "step": 1360 }, { "epoch": 0.32788847005325195, "grad_norm": 1.1799938678741455, "learning_rate": 6.9331359486799905e-06, "loss": 0.3151, "step": 1370 }, { "epoch": 0.330281816549991, "grad_norm": 1.2661657333374023, "learning_rate": 6.90846286701209e-06, "loss": 0.3259, "step": 1380 }, { "epoch": 0.3326751630467301, "grad_norm": 1.2282803058624268, "learning_rate": 6.883789785344191e-06, "loss": 0.309, "step": 1390 }, { "epoch": 0.3350685095434692, "grad_norm": 1.2133527994155884, "learning_rate": 6.85911670367629e-06, "loss": 0.3294, "step": 1400 }, { "epoch": 0.33746185604020823, "grad_norm": 1.7509887218475342, "learning_rate": 6.83444362200839e-06, "loss": 0.3082, "step": 1410 }, { "epoch": 0.3398552025369473, "grad_norm": 1.5616363286972046, "learning_rate": 6.809770540340489e-06, "loss": 0.2961, "step": 1420 }, { "epoch": 0.34224854903368634, "grad_norm": 1.3655364513397217, "learning_rate": 6.785097458672589e-06, "loss": 0.2735, "step": 1430 }, { "epoch": 0.3446418955304254, "grad_norm": 1.342238187789917, "learning_rate": 6.760424377004689e-06, "loss": 0.3248, "step": 1440 }, { "epoch": 0.34703524202716446, "grad_norm": 1.6433281898498535, "learning_rate": 6.735751295336788e-06, "loss": 0.3113, "step": 1450 }, { "epoch": 0.34942858852390357, "grad_norm": 1.2697690725326538, "learning_rate": 6.711078213668888e-06, "loss": 0.2617, "step": 1460 }, { "epoch": 0.35182193502064263, "grad_norm": 1.3193742036819458, "learning_rate": 6.686405132000987e-06, "loss": 0.2944, "step": 1470 }, { "epoch": 0.3542152815173817, "grad_norm": 1.238776445388794, "learning_rate": 6.661732050333087e-06, "loss": 0.2966, "step": 1480 }, { "epoch": 0.35660862801412074, "grad_norm": 1.2613089084625244, "learning_rate": 6.637058968665187e-06, "loss": 0.2709, "step": 1490 }, { "epoch": 0.3590019745108598, "grad_norm": 1.3654500246047974, "learning_rate": 6.612385886997287e-06, "loss": 0.3028, "step": 1500 }, { "epoch": 0.36139532100759886, "grad_norm": 1.256969928741455, "learning_rate": 6.587712805329386e-06, "loss": 0.3064, "step": 1510 }, { "epoch": 0.3637886675043379, "grad_norm": 1.439937949180603, "learning_rate": 6.563039723661486e-06, "loss": 0.3186, "step": 1520 }, { "epoch": 0.366182014001077, "grad_norm": 2.1648526191711426, "learning_rate": 6.538366641993585e-06, "loss": 0.286, "step": 1530 }, { "epoch": 0.3685753604978161, "grad_norm": 1.224603295326233, "learning_rate": 6.513693560325685e-06, "loss": 0.3126, "step": 1540 }, { "epoch": 0.37096870699455514, "grad_norm": 0.9492302536964417, "learning_rate": 6.489020478657785e-06, "loss": 0.2755, "step": 1550 }, { "epoch": 0.3733620534912942, "grad_norm": 1.257680058479309, "learning_rate": 6.464347396989885e-06, "loss": 0.2957, "step": 1560 }, { "epoch": 0.37575539998803326, "grad_norm": 1.300041675567627, "learning_rate": 6.439674315321984e-06, "loss": 0.3136, "step": 1570 }, { "epoch": 0.3781487464847723, "grad_norm": 1.2073733806610107, "learning_rate": 6.415001233654083e-06, "loss": 0.2817, "step": 1580 }, { "epoch": 0.38054209298151137, "grad_norm": 1.4004383087158203, "learning_rate": 6.390328151986184e-06, "loss": 0.2941, "step": 1590 }, { "epoch": 0.3829354394782505, "grad_norm": 1.6713262796401978, "learning_rate": 6.3656550703182825e-06, "loss": 0.2793, "step": 1600 }, { "epoch": 0.38532878597498954, "grad_norm": 1.1650950908660889, "learning_rate": 6.3409819886503835e-06, "loss": 0.3059, "step": 1610 }, { "epoch": 0.3877221324717286, "grad_norm": 1.2947584390640259, "learning_rate": 6.316308906982483e-06, "loss": 0.3024, "step": 1620 }, { "epoch": 0.39011547896846765, "grad_norm": 1.241655707359314, "learning_rate": 6.291635825314583e-06, "loss": 0.2875, "step": 1630 }, { "epoch": 0.3925088254652067, "grad_norm": 1.3550646305084229, "learning_rate": 6.266962743646682e-06, "loss": 0.262, "step": 1640 }, { "epoch": 0.39490217196194577, "grad_norm": 1.3829166889190674, "learning_rate": 6.242289661978782e-06, "loss": 0.3143, "step": 1650 }, { "epoch": 0.3972955184586849, "grad_norm": 1.3596593141555786, "learning_rate": 6.217616580310881e-06, "loss": 0.2879, "step": 1660 }, { "epoch": 0.39968886495542394, "grad_norm": 1.1706678867340088, "learning_rate": 6.1929434986429815e-06, "loss": 0.3319, "step": 1670 }, { "epoch": 0.402082211452163, "grad_norm": 1.5138920545578003, "learning_rate": 6.168270416975081e-06, "loss": 0.2828, "step": 1680 }, { "epoch": 0.40447555794890205, "grad_norm": 1.0524377822875977, "learning_rate": 6.14359733530718e-06, "loss": 0.2819, "step": 1690 }, { "epoch": 0.4068689044456411, "grad_norm": 2.1307592391967773, "learning_rate": 6.11892425363928e-06, "loss": 0.3198, "step": 1700 }, { "epoch": 0.40926225094238017, "grad_norm": 1.233102560043335, "learning_rate": 6.094251171971379e-06, "loss": 0.2802, "step": 1710 }, { "epoch": 0.4116555974391192, "grad_norm": 1.3827565908432007, "learning_rate": 6.0695780903034794e-06, "loss": 0.3014, "step": 1720 }, { "epoch": 0.41404894393585834, "grad_norm": 1.295032262802124, "learning_rate": 6.044905008635579e-06, "loss": 0.2702, "step": 1730 }, { "epoch": 0.4164422904325974, "grad_norm": 1.15171480178833, "learning_rate": 6.020231926967679e-06, "loss": 0.2634, "step": 1740 }, { "epoch": 0.41883563692933645, "grad_norm": 1.178030014038086, "learning_rate": 5.995558845299778e-06, "loss": 0.2947, "step": 1750 }, { "epoch": 0.4212289834260755, "grad_norm": 1.3594707250595093, "learning_rate": 5.970885763631878e-06, "loss": 0.2756, "step": 1760 }, { "epoch": 0.42362232992281457, "grad_norm": 1.1697347164154053, "learning_rate": 5.946212681963977e-06, "loss": 0.293, "step": 1770 }, { "epoch": 0.4260156764195536, "grad_norm": 1.226468801498413, "learning_rate": 5.921539600296078e-06, "loss": 0.2845, "step": 1780 }, { "epoch": 0.4284090229162927, "grad_norm": 1.067568063735962, "learning_rate": 5.896866518628177e-06, "loss": 0.2471, "step": 1790 }, { "epoch": 0.4308023694130318, "grad_norm": 1.205642580986023, "learning_rate": 5.872193436960278e-06, "loss": 0.2854, "step": 1800 }, { "epoch": 0.43319571590977085, "grad_norm": 1.0213494300842285, "learning_rate": 5.847520355292377e-06, "loss": 0.2987, "step": 1810 }, { "epoch": 0.4355890624065099, "grad_norm": 1.1673740148544312, "learning_rate": 5.822847273624475e-06, "loss": 0.2763, "step": 1820 }, { "epoch": 0.43798240890324897, "grad_norm": 1.2611061334609985, "learning_rate": 5.798174191956576e-06, "loss": 0.2587, "step": 1830 }, { "epoch": 0.440375755399988, "grad_norm": 1.051138162612915, "learning_rate": 5.7735011102886755e-06, "loss": 0.2873, "step": 1840 }, { "epoch": 0.4427691018967271, "grad_norm": 1.43403959274292, "learning_rate": 5.7488280286207756e-06, "loss": 0.2834, "step": 1850 }, { "epoch": 0.44516244839346614, "grad_norm": 1.0932261943817139, "learning_rate": 5.724154946952875e-06, "loss": 0.2798, "step": 1860 }, { "epoch": 0.44755579489020525, "grad_norm": 1.1541988849639893, "learning_rate": 5.699481865284975e-06, "loss": 0.2989, "step": 1870 }, { "epoch": 0.4499491413869443, "grad_norm": 1.197100043296814, "learning_rate": 5.674808783617074e-06, "loss": 0.2974, "step": 1880 }, { "epoch": 0.45234248788368336, "grad_norm": 1.1600849628448486, "learning_rate": 5.650135701949174e-06, "loss": 0.2945, "step": 1890 }, { "epoch": 0.4547358343804224, "grad_norm": 1.2405140399932861, "learning_rate": 5.6254626202812735e-06, "loss": 0.2798, "step": 1900 }, { "epoch": 0.4571291808771615, "grad_norm": 1.7206183671951294, "learning_rate": 5.600789538613374e-06, "loss": 0.2734, "step": 1910 }, { "epoch": 0.45952252737390054, "grad_norm": 1.9992940425872803, "learning_rate": 5.576116456945473e-06, "loss": 0.2676, "step": 1920 }, { "epoch": 0.46191587387063965, "grad_norm": 1.4115267992019653, "learning_rate": 5.551443375277573e-06, "loss": 0.3109, "step": 1930 }, { "epoch": 0.4643092203673787, "grad_norm": 1.2589079141616821, "learning_rate": 5.526770293609672e-06, "loss": 0.289, "step": 1940 }, { "epoch": 0.46670256686411776, "grad_norm": 1.241364598274231, "learning_rate": 5.502097211941771e-06, "loss": 0.302, "step": 1950 }, { "epoch": 0.4690959133608568, "grad_norm": 1.1608467102050781, "learning_rate": 5.4774241302738715e-06, "loss": 0.2831, "step": 1960 }, { "epoch": 0.4714892598575959, "grad_norm": 1.3736741542816162, "learning_rate": 5.452751048605971e-06, "loss": 0.2744, "step": 1970 }, { "epoch": 0.47388260635433493, "grad_norm": 1.1915043592453003, "learning_rate": 5.428077966938071e-06, "loss": 0.3024, "step": 1980 }, { "epoch": 0.476275952851074, "grad_norm": 1.2503719329833984, "learning_rate": 5.40340488527017e-06, "loss": 0.2694, "step": 1990 }, { "epoch": 0.4786692993478131, "grad_norm": 1.4188085794448853, "learning_rate": 5.378731803602271e-06, "loss": 0.27, "step": 2000 }, { "epoch": 0.48106264584455216, "grad_norm": 2.0826566219329834, "learning_rate": 5.3540587219343694e-06, "loss": 0.2537, "step": 2010 }, { "epoch": 0.4834559923412912, "grad_norm": 1.3236483335494995, "learning_rate": 5.32938564026647e-06, "loss": 0.3033, "step": 2020 }, { "epoch": 0.4858493388380303, "grad_norm": 1.2629801034927368, "learning_rate": 5.30471255859857e-06, "loss": 0.2706, "step": 2030 }, { "epoch": 0.48824268533476933, "grad_norm": 1.1761820316314697, "learning_rate": 5.28003947693067e-06, "loss": 0.2491, "step": 2040 }, { "epoch": 0.4906360318315084, "grad_norm": 1.4131414890289307, "learning_rate": 5.255366395262769e-06, "loss": 0.2798, "step": 2050 }, { "epoch": 0.49302937832824745, "grad_norm": 1.3679251670837402, "learning_rate": 5.230693313594868e-06, "loss": 0.2768, "step": 2060 }, { "epoch": 0.49542272482498656, "grad_norm": 1.2811331748962402, "learning_rate": 5.206020231926968e-06, "loss": 0.2547, "step": 2070 }, { "epoch": 0.4978160713217256, "grad_norm": 1.1285456418991089, "learning_rate": 5.1813471502590676e-06, "loss": 0.2694, "step": 2080 }, { "epoch": 0.5002094178184646, "grad_norm": 1.163135290145874, "learning_rate": 5.156674068591168e-06, "loss": 0.2664, "step": 2090 }, { "epoch": 0.5026027643152038, "grad_norm": 1.1090058088302612, "learning_rate": 5.132000986923267e-06, "loss": 0.2688, "step": 2100 }, { "epoch": 0.5049961108119428, "grad_norm": 1.157850980758667, "learning_rate": 5.107327905255367e-06, "loss": 0.2382, "step": 2110 }, { "epoch": 0.5073894573086819, "grad_norm": 1.0816707611083984, "learning_rate": 5.082654823587466e-06, "loss": 0.2453, "step": 2120 }, { "epoch": 0.509782803805421, "grad_norm": 1.1246033906936646, "learning_rate": 5.057981741919566e-06, "loss": 0.2782, "step": 2130 }, { "epoch": 0.51217615030216, "grad_norm": 1.5075746774673462, "learning_rate": 5.033308660251666e-06, "loss": 0.273, "step": 2140 }, { "epoch": 0.5145694967988991, "grad_norm": 1.589673399925232, "learning_rate": 5.008635578583766e-06, "loss": 0.3086, "step": 2150 }, { "epoch": 0.5169628432956381, "grad_norm": 1.167447805404663, "learning_rate": 4.983962496915865e-06, "loss": 0.2458, "step": 2160 }, { "epoch": 0.5193561897923772, "grad_norm": 1.5839897394180298, "learning_rate": 4.959289415247965e-06, "loss": 0.293, "step": 2170 }, { "epoch": 0.5217495362891162, "grad_norm": 1.2031172513961792, "learning_rate": 4.934616333580064e-06, "loss": 0.2592, "step": 2180 }, { "epoch": 0.5241428827858553, "grad_norm": 1.4997600317001343, "learning_rate": 4.909943251912164e-06, "loss": 0.2688, "step": 2190 }, { "epoch": 0.5265362292825944, "grad_norm": 0.9731311798095703, "learning_rate": 4.885270170244264e-06, "loss": 0.2835, "step": 2200 }, { "epoch": 0.5289295757793334, "grad_norm": 1.3232722282409668, "learning_rate": 4.860597088576364e-06, "loss": 0.2743, "step": 2210 }, { "epoch": 0.5313229222760725, "grad_norm": 1.2348476648330688, "learning_rate": 4.835924006908464e-06, "loss": 0.2588, "step": 2220 }, { "epoch": 0.5337162687728115, "grad_norm": 1.381761074066162, "learning_rate": 4.811250925240563e-06, "loss": 0.2491, "step": 2230 }, { "epoch": 0.5361096152695507, "grad_norm": 1.202336072921753, "learning_rate": 4.786577843572663e-06, "loss": 0.28, "step": 2240 }, { "epoch": 0.5385029617662898, "grad_norm": 1.0882714986801147, "learning_rate": 4.761904761904762e-06, "loss": 0.2649, "step": 2250 }, { "epoch": 0.5408963082630288, "grad_norm": 1.1813145875930786, "learning_rate": 4.737231680236862e-06, "loss": 0.2343, "step": 2260 }, { "epoch": 0.5432896547597679, "grad_norm": 1.1721665859222412, "learning_rate": 4.712558598568962e-06, "loss": 0.2403, "step": 2270 }, { "epoch": 0.5456830012565069, "grad_norm": 1.1786693334579468, "learning_rate": 4.687885516901061e-06, "loss": 0.2878, "step": 2280 }, { "epoch": 0.548076347753246, "grad_norm": 1.813693642616272, "learning_rate": 4.663212435233161e-06, "loss": 0.2419, "step": 2290 }, { "epoch": 0.550469694249985, "grad_norm": 1.6151432991027832, "learning_rate": 4.63853935356526e-06, "loss": 0.2722, "step": 2300 }, { "epoch": 0.5528630407467241, "grad_norm": 1.3817476034164429, "learning_rate": 4.61386627189736e-06, "loss": 0.2413, "step": 2310 }, { "epoch": 0.5552563872434632, "grad_norm": 1.7355929613113403, "learning_rate": 4.5891931902294605e-06, "loss": 0.2757, "step": 2320 }, { "epoch": 0.5576497337402022, "grad_norm": 1.050182580947876, "learning_rate": 4.56452010856156e-06, "loss": 0.2843, "step": 2330 }, { "epoch": 0.5600430802369413, "grad_norm": 1.7144726514816284, "learning_rate": 4.53984702689366e-06, "loss": 0.2768, "step": 2340 }, { "epoch": 0.5624364267336803, "grad_norm": 1.2476091384887695, "learning_rate": 4.515173945225759e-06, "loss": 0.238, "step": 2350 }, { "epoch": 0.5648297732304194, "grad_norm": 1.2352614402770996, "learning_rate": 4.490500863557859e-06, "loss": 0.2485, "step": 2360 }, { "epoch": 0.5672231197271586, "grad_norm": 1.2621803283691406, "learning_rate": 4.465827781889958e-06, "loss": 0.2643, "step": 2370 }, { "epoch": 0.5696164662238976, "grad_norm": 1.86287522315979, "learning_rate": 4.441154700222058e-06, "loss": 0.2525, "step": 2380 }, { "epoch": 0.5720098127206367, "grad_norm": 2.1014795303344727, "learning_rate": 4.416481618554158e-06, "loss": 0.258, "step": 2390 }, { "epoch": 0.5744031592173757, "grad_norm": 1.1729822158813477, "learning_rate": 4.391808536886257e-06, "loss": 0.271, "step": 2400 }, { "epoch": 0.5767965057141148, "grad_norm": 1.177506446838379, "learning_rate": 4.367135455218357e-06, "loss": 0.2692, "step": 2410 }, { "epoch": 0.5791898522108538, "grad_norm": 1.422754168510437, "learning_rate": 4.342462373550456e-06, "loss": 0.2706, "step": 2420 }, { "epoch": 0.5815831987075929, "grad_norm": 1.1413453817367554, "learning_rate": 4.3177892918825564e-06, "loss": 0.2556, "step": 2430 }, { "epoch": 0.583976545204332, "grad_norm": 1.624819040298462, "learning_rate": 4.2931162102146565e-06, "loss": 0.2675, "step": 2440 }, { "epoch": 0.586369891701071, "grad_norm": 1.3075209856033325, "learning_rate": 4.268443128546756e-06, "loss": 0.2618, "step": 2450 }, { "epoch": 0.5887632381978101, "grad_norm": 1.3485337495803833, "learning_rate": 4.243770046878856e-06, "loss": 0.2847, "step": 2460 }, { "epoch": 0.5911565846945491, "grad_norm": 1.2586491107940674, "learning_rate": 4.219096965210955e-06, "loss": 0.2529, "step": 2470 }, { "epoch": 0.5935499311912882, "grad_norm": 1.1659890413284302, "learning_rate": 4.194423883543055e-06, "loss": 0.2602, "step": 2480 }, { "epoch": 0.5959432776880272, "grad_norm": 1.186527967453003, "learning_rate": 4.1697508018751545e-06, "loss": 0.2444, "step": 2490 }, { "epoch": 0.5983366241847663, "grad_norm": 1.8560987710952759, "learning_rate": 4.145077720207254e-06, "loss": 0.2514, "step": 2500 }, { "epoch": 0.6007299706815055, "grad_norm": 1.676529884338379, "learning_rate": 4.120404638539354e-06, "loss": 0.2615, "step": 2510 }, { "epoch": 0.6031233171782445, "grad_norm": 1.8776030540466309, "learning_rate": 4.095731556871453e-06, "loss": 0.235, "step": 2520 }, { "epoch": 0.6055166636749836, "grad_norm": 1.1904994249343872, "learning_rate": 4.071058475203553e-06, "loss": 0.2647, "step": 2530 }, { "epoch": 0.6079100101717226, "grad_norm": 1.3398947715759277, "learning_rate": 4.046385393535653e-06, "loss": 0.2507, "step": 2540 }, { "epoch": 0.6103033566684617, "grad_norm": 1.180635929107666, "learning_rate": 4.0217123118677525e-06, "loss": 0.2353, "step": 2550 }, { "epoch": 0.6126967031652008, "grad_norm": 1.9972810745239258, "learning_rate": 3.9970392301998526e-06, "loss": 0.2435, "step": 2560 }, { "epoch": 0.6150900496619398, "grad_norm": 1.0863275527954102, "learning_rate": 3.972366148531952e-06, "loss": 0.2818, "step": 2570 }, { "epoch": 0.6174833961586789, "grad_norm": 1.178846001625061, "learning_rate": 3.947693066864052e-06, "loss": 0.2535, "step": 2580 }, { "epoch": 0.6198767426554179, "grad_norm": 2.1343159675598145, "learning_rate": 3.923019985196151e-06, "loss": 0.2393, "step": 2590 }, { "epoch": 0.622270089152157, "grad_norm": 1.3942614793777466, "learning_rate": 3.898346903528251e-06, "loss": 0.2694, "step": 2600 }, { "epoch": 0.624663435648896, "grad_norm": 1.549784779548645, "learning_rate": 3.8736738218603505e-06, "loss": 0.2726, "step": 2610 }, { "epoch": 0.6270567821456351, "grad_norm": 1.165950059890747, "learning_rate": 3.849000740192451e-06, "loss": 0.2367, "step": 2620 }, { "epoch": 0.6294501286423742, "grad_norm": 1.1804895401000977, "learning_rate": 3.82432765852455e-06, "loss": 0.2403, "step": 2630 }, { "epoch": 0.6318434751391133, "grad_norm": 1.3002017736434937, "learning_rate": 3.7996545768566495e-06, "loss": 0.3035, "step": 2640 }, { "epoch": 0.6342368216358524, "grad_norm": 1.3624404668807983, "learning_rate": 3.774981495188749e-06, "loss": 0.2328, "step": 2650 }, { "epoch": 0.6366301681325914, "grad_norm": 1.2703642845153809, "learning_rate": 3.750308413520849e-06, "loss": 0.2473, "step": 2660 }, { "epoch": 0.6390235146293305, "grad_norm": 1.204581379890442, "learning_rate": 3.7256353318529485e-06, "loss": 0.2602, "step": 2670 }, { "epoch": 0.6414168611260695, "grad_norm": 1.5052433013916016, "learning_rate": 3.700962250185048e-06, "loss": 0.278, "step": 2680 }, { "epoch": 0.6438102076228086, "grad_norm": 1.1291722059249878, "learning_rate": 3.6762891685171483e-06, "loss": 0.2343, "step": 2690 }, { "epoch": 0.6462035541195477, "grad_norm": 1.1545064449310303, "learning_rate": 3.651616086849248e-06, "loss": 0.2652, "step": 2700 }, { "epoch": 0.6485969006162867, "grad_norm": 1.409798264503479, "learning_rate": 3.6269430051813476e-06, "loss": 0.2714, "step": 2710 }, { "epoch": 0.6509902471130258, "grad_norm": 1.3719264268875122, "learning_rate": 3.6022699235134473e-06, "loss": 0.2485, "step": 2720 }, { "epoch": 0.6533835936097648, "grad_norm": 1.2027322053909302, "learning_rate": 3.577596841845547e-06, "loss": 0.2712, "step": 2730 }, { "epoch": 0.6557769401065039, "grad_norm": 1.1790002584457397, "learning_rate": 3.5529237601776466e-06, "loss": 0.2762, "step": 2740 }, { "epoch": 0.658170286603243, "grad_norm": 1.5962635278701782, "learning_rate": 3.528250678509746e-06, "loss": 0.2474, "step": 2750 }, { "epoch": 0.660563633099982, "grad_norm": 1.4343008995056152, "learning_rate": 3.5035775968418456e-06, "loss": 0.2377, "step": 2760 }, { "epoch": 0.6629569795967211, "grad_norm": 1.305679440498352, "learning_rate": 3.4789045151739452e-06, "loss": 0.2507, "step": 2770 }, { "epoch": 0.6653503260934602, "grad_norm": 1.5006093978881836, "learning_rate": 3.454231433506045e-06, "loss": 0.2697, "step": 2780 }, { "epoch": 0.6677436725901993, "grad_norm": 1.3560587167739868, "learning_rate": 3.429558351838145e-06, "loss": 0.2658, "step": 2790 }, { "epoch": 0.6701370190869383, "grad_norm": 1.3980733156204224, "learning_rate": 3.4048852701702447e-06, "loss": 0.2338, "step": 2800 }, { "epoch": 0.6725303655836774, "grad_norm": 1.1750844717025757, "learning_rate": 3.3802121885023443e-06, "loss": 0.2189, "step": 2810 }, { "epoch": 0.6749237120804165, "grad_norm": 1.0422217845916748, "learning_rate": 3.355539106834444e-06, "loss": 0.2391, "step": 2820 }, { "epoch": 0.6773170585771555, "grad_norm": 1.449839472770691, "learning_rate": 3.3308660251665437e-06, "loss": 0.2396, "step": 2830 }, { "epoch": 0.6797104050738946, "grad_norm": 1.219713568687439, "learning_rate": 3.3061929434986433e-06, "loss": 0.2516, "step": 2840 }, { "epoch": 0.6821037515706336, "grad_norm": 1.708020567893982, "learning_rate": 3.281519861830743e-06, "loss": 0.2339, "step": 2850 }, { "epoch": 0.6844970980673727, "grad_norm": 1.1863124370574951, "learning_rate": 3.2568467801628427e-06, "loss": 0.2188, "step": 2860 }, { "epoch": 0.6868904445641117, "grad_norm": 1.074019432067871, "learning_rate": 3.2321736984949424e-06, "loss": 0.2625, "step": 2870 }, { "epoch": 0.6892837910608508, "grad_norm": 1.1517128944396973, "learning_rate": 3.2075006168270416e-06, "loss": 0.2401, "step": 2880 }, { "epoch": 0.6916771375575899, "grad_norm": 1.157779335975647, "learning_rate": 3.1828275351591413e-06, "loss": 0.218, "step": 2890 }, { "epoch": 0.6940704840543289, "grad_norm": 1.0749232769012451, "learning_rate": 3.1581544534912414e-06, "loss": 0.2437, "step": 2900 }, { "epoch": 0.6964638305510681, "grad_norm": 3.3054139614105225, "learning_rate": 3.133481371823341e-06, "loss": 0.2314, "step": 2910 }, { "epoch": 0.6988571770478071, "grad_norm": 1.705291509628296, "learning_rate": 3.1088082901554407e-06, "loss": 0.2233, "step": 2920 }, { "epoch": 0.7012505235445462, "grad_norm": 1.1587389707565308, "learning_rate": 3.0841352084875404e-06, "loss": 0.2589, "step": 2930 }, { "epoch": 0.7036438700412853, "grad_norm": 1.4903759956359863, "learning_rate": 3.05946212681964e-06, "loss": 0.2844, "step": 2940 }, { "epoch": 0.7060372165380243, "grad_norm": 1.2323542833328247, "learning_rate": 3.0347890451517397e-06, "loss": 0.2047, "step": 2950 }, { "epoch": 0.7084305630347634, "grad_norm": 1.2094900608062744, "learning_rate": 3.0101159634838394e-06, "loss": 0.2378, "step": 2960 }, { "epoch": 0.7108239095315024, "grad_norm": 1.1978344917297363, "learning_rate": 2.985442881815939e-06, "loss": 0.2924, "step": 2970 }, { "epoch": 0.7132172560282415, "grad_norm": 1.2418081760406494, "learning_rate": 2.960769800148039e-06, "loss": 0.2638, "step": 2980 }, { "epoch": 0.7156106025249805, "grad_norm": 1.3295044898986816, "learning_rate": 2.936096718480139e-06, "loss": 0.2514, "step": 2990 }, { "epoch": 0.7180039490217196, "grad_norm": 1.1605592966079712, "learning_rate": 2.9114236368122376e-06, "loss": 0.2317, "step": 3000 }, { "epoch": 0.7203972955184587, "grad_norm": 1.4259930849075317, "learning_rate": 2.8867505551443377e-06, "loss": 0.2555, "step": 3010 }, { "epoch": 0.7227906420151977, "grad_norm": 1.298928141593933, "learning_rate": 2.8620774734764374e-06, "loss": 0.2571, "step": 3020 }, { "epoch": 0.7251839885119368, "grad_norm": 1.3968210220336914, "learning_rate": 2.837404391808537e-06, "loss": 0.247, "step": 3030 }, { "epoch": 0.7275773350086758, "grad_norm": 1.107237458229065, "learning_rate": 2.8127313101406367e-06, "loss": 0.2548, "step": 3040 }, { "epoch": 0.729970681505415, "grad_norm": 1.414443850517273, "learning_rate": 2.7880582284727364e-06, "loss": 0.2222, "step": 3050 }, { "epoch": 0.732364028002154, "grad_norm": 1.1926815509796143, "learning_rate": 2.763385146804836e-06, "loss": 0.2397, "step": 3060 }, { "epoch": 0.7347573744988931, "grad_norm": 1.126175045967102, "learning_rate": 2.7387120651369358e-06, "loss": 0.2592, "step": 3070 }, { "epoch": 0.7371507209956322, "grad_norm": 1.2841236591339111, "learning_rate": 2.7140389834690354e-06, "loss": 0.231, "step": 3080 }, { "epoch": 0.7395440674923712, "grad_norm": 1.2670103311538696, "learning_rate": 2.6893659018011355e-06, "loss": 0.2467, "step": 3090 }, { "epoch": 0.7419374139891103, "grad_norm": 1.1250816583633423, "learning_rate": 2.664692820133235e-06, "loss": 0.2526, "step": 3100 }, { "epoch": 0.7443307604858493, "grad_norm": 1.145416259765625, "learning_rate": 2.640019738465335e-06, "loss": 0.2512, "step": 3110 }, { "epoch": 0.7467241069825884, "grad_norm": 1.8776533603668213, "learning_rate": 2.615346656797434e-06, "loss": 0.2457, "step": 3120 }, { "epoch": 0.7491174534793275, "grad_norm": 1.261007308959961, "learning_rate": 2.5906735751295338e-06, "loss": 0.2941, "step": 3130 }, { "epoch": 0.7515107999760665, "grad_norm": 1.5598303079605103, "learning_rate": 2.5660004934616334e-06, "loss": 0.2474, "step": 3140 }, { "epoch": 0.7539041464728056, "grad_norm": 1.3169031143188477, "learning_rate": 2.541327411793733e-06, "loss": 0.2453, "step": 3150 }, { "epoch": 0.7562974929695446, "grad_norm": 1.2108057737350464, "learning_rate": 2.516654330125833e-06, "loss": 0.2622, "step": 3160 }, { "epoch": 0.7586908394662837, "grad_norm": 1.1165136098861694, "learning_rate": 2.4919812484579325e-06, "loss": 0.2315, "step": 3170 }, { "epoch": 0.7610841859630227, "grad_norm": 1.053459644317627, "learning_rate": 2.467308166790032e-06, "loss": 0.2477, "step": 3180 }, { "epoch": 0.7634775324597619, "grad_norm": 1.4853384494781494, "learning_rate": 2.442635085122132e-06, "loss": 0.2303, "step": 3190 }, { "epoch": 0.765870878956501, "grad_norm": 0.9642342925071716, "learning_rate": 2.417962003454232e-06, "loss": 0.2485, "step": 3200 }, { "epoch": 0.76826422545324, "grad_norm": 1.04854416847229, "learning_rate": 2.3932889217863316e-06, "loss": 0.2314, "step": 3210 }, { "epoch": 0.7706575719499791, "grad_norm": 1.3037827014923096, "learning_rate": 2.368615840118431e-06, "loss": 0.2396, "step": 3220 }, { "epoch": 0.7730509184467181, "grad_norm": 1.288132905960083, "learning_rate": 2.3439427584505305e-06, "loss": 0.2297, "step": 3230 }, { "epoch": 0.7754442649434572, "grad_norm": 1.1785624027252197, "learning_rate": 2.31926967678263e-06, "loss": 0.2277, "step": 3240 }, { "epoch": 0.7778376114401963, "grad_norm": 1.2337340116500854, "learning_rate": 2.2945965951147302e-06, "loss": 0.2206, "step": 3250 }, { "epoch": 0.7802309579369353, "grad_norm": 1.4937660694122314, "learning_rate": 2.26992351344683e-06, "loss": 0.2401, "step": 3260 }, { "epoch": 0.7826243044336744, "grad_norm": 1.4390426874160767, "learning_rate": 2.2452504317789296e-06, "loss": 0.2248, "step": 3270 }, { "epoch": 0.7850176509304134, "grad_norm": 1.084153413772583, "learning_rate": 2.220577350111029e-06, "loss": 0.2623, "step": 3280 }, { "epoch": 0.7874109974271525, "grad_norm": 1.198421835899353, "learning_rate": 2.1959042684431285e-06, "loss": 0.2411, "step": 3290 }, { "epoch": 0.7898043439238915, "grad_norm": 1.3425636291503906, "learning_rate": 2.171231186775228e-06, "loss": 0.2098, "step": 3300 }, { "epoch": 0.7921976904206306, "grad_norm": 1.2199220657348633, "learning_rate": 2.1465581051073283e-06, "loss": 0.2487, "step": 3310 }, { "epoch": 0.7945910369173698, "grad_norm": 1.3166937828063965, "learning_rate": 2.121885023439428e-06, "loss": 0.2238, "step": 3320 }, { "epoch": 0.7969843834141088, "grad_norm": 1.8201621770858765, "learning_rate": 2.0972119417715276e-06, "loss": 0.206, "step": 3330 }, { "epoch": 0.7993777299108479, "grad_norm": 1.142264485359192, "learning_rate": 2.072538860103627e-06, "loss": 0.2289, "step": 3340 }, { "epoch": 0.8017710764075869, "grad_norm": 1.559877872467041, "learning_rate": 2.0478657784357265e-06, "loss": 0.228, "step": 3350 }, { "epoch": 0.804164422904326, "grad_norm": 1.1096370220184326, "learning_rate": 2.0231926967678266e-06, "loss": 0.2119, "step": 3360 }, { "epoch": 0.806557769401065, "grad_norm": 1.409487247467041, "learning_rate": 1.9985196150999263e-06, "loss": 0.2389, "step": 3370 }, { "epoch": 0.8089511158978041, "grad_norm": 1.1949121952056885, "learning_rate": 1.973846533432026e-06, "loss": 0.2184, "step": 3380 }, { "epoch": 0.8113444623945432, "grad_norm": 1.2593088150024414, "learning_rate": 1.9491734517641256e-06, "loss": 0.2413, "step": 3390 }, { "epoch": 0.8137378088912822, "grad_norm": 1.3473296165466309, "learning_rate": 1.9245003700962253e-06, "loss": 0.2276, "step": 3400 }, { "epoch": 0.8161311553880213, "grad_norm": 1.269108533859253, "learning_rate": 1.8998272884283248e-06, "loss": 0.2099, "step": 3410 }, { "epoch": 0.8185245018847603, "grad_norm": 1.2058231830596924, "learning_rate": 1.8751542067604244e-06, "loss": 0.2536, "step": 3420 }, { "epoch": 0.8209178483814994, "grad_norm": 1.2022275924682617, "learning_rate": 1.850481125092524e-06, "loss": 0.2125, "step": 3430 }, { "epoch": 0.8233111948782385, "grad_norm": 1.2434262037277222, "learning_rate": 1.825808043424624e-06, "loss": 0.2583, "step": 3440 }, { "epoch": 0.8257045413749775, "grad_norm": 1.2136218547821045, "learning_rate": 1.8011349617567236e-06, "loss": 0.2303, "step": 3450 }, { "epoch": 0.8280978878717167, "grad_norm": 1.146084189414978, "learning_rate": 1.7764618800888233e-06, "loss": 0.2277, "step": 3460 }, { "epoch": 0.8304912343684557, "grad_norm": 0.8964742422103882, "learning_rate": 1.7517887984209228e-06, "loss": 0.2113, "step": 3470 }, { "epoch": 0.8328845808651948, "grad_norm": 1.0792003870010376, "learning_rate": 1.7271157167530224e-06, "loss": 0.2492, "step": 3480 }, { "epoch": 0.8352779273619338, "grad_norm": 1.4260661602020264, "learning_rate": 1.7024426350851223e-06, "loss": 0.2094, "step": 3490 }, { "epoch": 0.8376712738586729, "grad_norm": 1.4723421335220337, "learning_rate": 1.677769553417222e-06, "loss": 0.2143, "step": 3500 }, { "epoch": 0.840064620355412, "grad_norm": 1.1710749864578247, "learning_rate": 1.6530964717493217e-06, "loss": 0.2375, "step": 3510 }, { "epoch": 0.842457966852151, "grad_norm": 1.237210988998413, "learning_rate": 1.6284233900814213e-06, "loss": 0.2038, "step": 3520 }, { "epoch": 0.8448513133488901, "grad_norm": 1.4809659719467163, "learning_rate": 1.6037503084135208e-06, "loss": 0.2451, "step": 3530 }, { "epoch": 0.8472446598456291, "grad_norm": 1.3218790292739868, "learning_rate": 1.5790772267456207e-06, "loss": 0.237, "step": 3540 }, { "epoch": 0.8496380063423682, "grad_norm": 1.0716545581817627, "learning_rate": 1.5544041450777204e-06, "loss": 0.237, "step": 3550 }, { "epoch": 0.8520313528391072, "grad_norm": 1.1333329677581787, "learning_rate": 1.52973106340982e-06, "loss": 0.1905, "step": 3560 }, { "epoch": 0.8544246993358463, "grad_norm": 1.8725478649139404, "learning_rate": 1.5050579817419197e-06, "loss": 0.2312, "step": 3570 }, { "epoch": 0.8568180458325854, "grad_norm": 1.3748364448547363, "learning_rate": 1.4803849000740196e-06, "loss": 0.2193, "step": 3580 }, { "epoch": 0.8592113923293245, "grad_norm": 1.2401251792907715, "learning_rate": 1.4557118184061188e-06, "loss": 0.2129, "step": 3590 }, { "epoch": 0.8616047388260636, "grad_norm": 1.1358551979064941, "learning_rate": 1.4310387367382187e-06, "loss": 0.2409, "step": 3600 }, { "epoch": 0.8639980853228026, "grad_norm": 0.9937493801116943, "learning_rate": 1.4063656550703184e-06, "loss": 0.2185, "step": 3610 }, { "epoch": 0.8663914318195417, "grad_norm": 1.1215769052505493, "learning_rate": 1.381692573402418e-06, "loss": 0.2048, "step": 3620 }, { "epoch": 0.8687847783162808, "grad_norm": 1.2018488645553589, "learning_rate": 1.3570194917345177e-06, "loss": 0.2472, "step": 3630 }, { "epoch": 0.8711781248130198, "grad_norm": 1.207561731338501, "learning_rate": 1.3323464100666176e-06, "loss": 0.2184, "step": 3640 }, { "epoch": 0.8735714713097589, "grad_norm": 1.2512346506118774, "learning_rate": 1.307673328398717e-06, "loss": 0.2773, "step": 3650 }, { "epoch": 0.8759648178064979, "grad_norm": 1.5677765607833862, "learning_rate": 1.2830002467308167e-06, "loss": 0.2331, "step": 3660 }, { "epoch": 0.878358164303237, "grad_norm": 1.02482271194458, "learning_rate": 1.2583271650629164e-06, "loss": 0.2112, "step": 3670 }, { "epoch": 0.880751510799976, "grad_norm": 1.1923754215240479, "learning_rate": 1.233654083395016e-06, "loss": 0.2296, "step": 3680 }, { "epoch": 0.8831448572967151, "grad_norm": 1.2726351022720337, "learning_rate": 1.208981001727116e-06, "loss": 0.2586, "step": 3690 }, { "epoch": 0.8855382037934542, "grad_norm": 1.2303539514541626, "learning_rate": 1.1843079200592154e-06, "loss": 0.2308, "step": 3700 }, { "epoch": 0.8879315502901932, "grad_norm": 2.0627002716064453, "learning_rate": 1.159634838391315e-06, "loss": 0.234, "step": 3710 }, { "epoch": 0.8903248967869323, "grad_norm": 1.1610201597213745, "learning_rate": 1.134961756723415e-06, "loss": 0.2299, "step": 3720 }, { "epoch": 0.8927182432836714, "grad_norm": 1.101236343383789, "learning_rate": 1.1102886750555144e-06, "loss": 0.2106, "step": 3730 }, { "epoch": 0.8951115897804105, "grad_norm": 1.2132625579833984, "learning_rate": 1.085615593387614e-06, "loss": 0.231, "step": 3740 }, { "epoch": 0.8975049362771496, "grad_norm": 1.30766761302948, "learning_rate": 1.060942511719714e-06, "loss": 0.2088, "step": 3750 }, { "epoch": 0.8998982827738886, "grad_norm": 1.2873889207839966, "learning_rate": 1.0362694300518134e-06, "loss": 0.231, "step": 3760 }, { "epoch": 0.9022916292706277, "grad_norm": 1.1280388832092285, "learning_rate": 1.0115963483839133e-06, "loss": 0.2413, "step": 3770 }, { "epoch": 0.9046849757673667, "grad_norm": 1.170089840888977, "learning_rate": 9.86923266716013e-07, "loss": 0.2552, "step": 3780 }, { "epoch": 0.9070783222641058, "grad_norm": 1.5289994478225708, "learning_rate": 9.622501850481126e-07, "loss": 0.203, "step": 3790 }, { "epoch": 0.9094716687608448, "grad_norm": 1.2764493227005005, "learning_rate": 9.375771033802122e-07, "loss": 0.2117, "step": 3800 }, { "epoch": 0.9118650152575839, "grad_norm": 1.294645071029663, "learning_rate": 9.12904021712312e-07, "loss": 0.2, "step": 3810 }, { "epoch": 0.914258361754323, "grad_norm": 0.9800574779510498, "learning_rate": 8.882309400444117e-07, "loss": 0.2049, "step": 3820 }, { "epoch": 0.916651708251062, "grad_norm": 1.2550008296966553, "learning_rate": 8.635578583765112e-07, "loss": 0.2326, "step": 3830 }, { "epoch": 0.9190450547478011, "grad_norm": 1.1507264375686646, "learning_rate": 8.38884776708611e-07, "loss": 0.2352, "step": 3840 }, { "epoch": 0.9214384012445401, "grad_norm": 1.2210705280303955, "learning_rate": 8.142116950407107e-07, "loss": 0.2207, "step": 3850 }, { "epoch": 0.9238317477412793, "grad_norm": 1.3780649900436401, "learning_rate": 7.895386133728103e-07, "loss": 0.2367, "step": 3860 }, { "epoch": 0.9262250942380184, "grad_norm": 1.2742125988006592, "learning_rate": 7.6486553170491e-07, "loss": 0.2088, "step": 3870 }, { "epoch": 0.9286184407347574, "grad_norm": 1.176216721534729, "learning_rate": 7.401924500370098e-07, "loss": 0.2264, "step": 3880 }, { "epoch": 0.9310117872314965, "grad_norm": 0.994560718536377, "learning_rate": 7.155193683691094e-07, "loss": 0.235, "step": 3890 }, { "epoch": 0.9334051337282355, "grad_norm": 1.1734304428100586, "learning_rate": 6.90846286701209e-07, "loss": 0.2432, "step": 3900 }, { "epoch": 0.9357984802249746, "grad_norm": 1.2303521633148193, "learning_rate": 6.661732050333088e-07, "loss": 0.2343, "step": 3910 }, { "epoch": 0.9381918267217136, "grad_norm": 1.1788909435272217, "learning_rate": 6.415001233654084e-07, "loss": 0.2293, "step": 3920 }, { "epoch": 0.9405851732184527, "grad_norm": 1.204946756362915, "learning_rate": 6.16827041697508e-07, "loss": 0.2143, "step": 3930 }, { "epoch": 0.9429785197151918, "grad_norm": 1.3866838216781616, "learning_rate": 5.921539600296077e-07, "loss": 0.2508, "step": 3940 }, { "epoch": 0.9453718662119308, "grad_norm": 1.2376493215560913, "learning_rate": 5.674808783617075e-07, "loss": 0.2238, "step": 3950 }, { "epoch": 0.9477652127086699, "grad_norm": 1.4622169733047485, "learning_rate": 5.42807796693807e-07, "loss": 0.2533, "step": 3960 }, { "epoch": 0.9501585592054089, "grad_norm": 1.1332287788391113, "learning_rate": 5.181347150259067e-07, "loss": 0.2101, "step": 3970 }, { "epoch": 0.952551905702148, "grad_norm": 1.3656179904937744, "learning_rate": 4.934616333580065e-07, "loss": 0.2263, "step": 3980 }, { "epoch": 0.954945252198887, "grad_norm": 1.2029988765716553, "learning_rate": 4.687885516901061e-07, "loss": 0.2341, "step": 3990 }, { "epoch": 0.9573385986956262, "grad_norm": 1.3618018627166748, "learning_rate": 4.4411547002220583e-07, "loss": 0.2227, "step": 4000 }, { "epoch": 0.9597319451923653, "grad_norm": 0.9501358866691589, "learning_rate": 4.194423883543055e-07, "loss": 0.2156, "step": 4010 }, { "epoch": 0.9621252916891043, "grad_norm": 1.2028504610061646, "learning_rate": 3.9476930668640517e-07, "loss": 0.2545, "step": 4020 }, { "epoch": 0.9645186381858434, "grad_norm": 1.2028127908706665, "learning_rate": 3.700962250185049e-07, "loss": 0.2481, "step": 4030 }, { "epoch": 0.9669119846825824, "grad_norm": 1.1799533367156982, "learning_rate": 3.454231433506045e-07, "loss": 0.1933, "step": 4040 }, { "epoch": 0.9693053311793215, "grad_norm": 2.7324931621551514, "learning_rate": 3.207500616827042e-07, "loss": 0.2403, "step": 4050 }, { "epoch": 0.9716986776760606, "grad_norm": 1.0572327375411987, "learning_rate": 2.9607698001480385e-07, "loss": 0.2381, "step": 4060 }, { "epoch": 0.9740920241727996, "grad_norm": 1.145850658416748, "learning_rate": 2.714038983469035e-07, "loss": 0.1958, "step": 4070 }, { "epoch": 0.9764853706695387, "grad_norm": 1.2220932245254517, "learning_rate": 2.4673081667900324e-07, "loss": 0.2066, "step": 4080 }, { "epoch": 0.9788787171662777, "grad_norm": 1.155151605606079, "learning_rate": 2.2205773501110291e-07, "loss": 0.2348, "step": 4090 }, { "epoch": 0.9812720636630168, "grad_norm": 1.1293679475784302, "learning_rate": 1.9738465334320259e-07, "loss": 0.2014, "step": 4100 }, { "epoch": 0.9836654101597558, "grad_norm": 1.3047446012496948, "learning_rate": 1.7271157167530226e-07, "loss": 0.2103, "step": 4110 }, { "epoch": 0.9860587566564949, "grad_norm": 1.258976936340332, "learning_rate": 1.4803849000740193e-07, "loss": 0.2117, "step": 4120 }, { "epoch": 0.9884521031532341, "grad_norm": 1.3765350580215454, "learning_rate": 1.2336540833950162e-07, "loss": 0.262, "step": 4130 }, { "epoch": 0.9908454496499731, "grad_norm": 1.0909656286239624, "learning_rate": 9.869232667160129e-08, "loss": 0.2057, "step": 4140 }, { "epoch": 0.9932387961467122, "grad_norm": 1.0856449604034424, "learning_rate": 7.401924500370096e-08, "loss": 0.2099, "step": 4150 }, { "epoch": 0.9956321426434512, "grad_norm": 1.2953740358352661, "learning_rate": 4.9346163335800646e-08, "loss": 0.2115, "step": 4160 }, { "epoch": 0.9980254891401903, "grad_norm": 1.191356897354126, "learning_rate": 2.4673081667900323e-08, "loss": 0.2508, "step": 4170 }, { "epoch": 1.0, "step": 4179, "total_flos": 307614199578624.0, "train_loss": 0.3053776310174252, "train_runtime": 40436.9863, "train_samples_per_second": 13.226, "train_steps_per_second": 0.103 } ], "logging_steps": 10, "max_steps": 4179, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 50000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 307614199578624.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }