diff --git "a/checkpoint-600/trainer_state.json" "b/checkpoint-600/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-600/trainer_state.json" @@ -0,0 +1,4233 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 4.337349397590361, + "eval_steps": 50, + "global_step": 600, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.007228915662650603, + "grad_norm": 3.171796668248988, + "learning_rate": 1.3333333333333334e-06, + "loss": 11.2137, + "step": 1 + }, + { + "epoch": 0.014457831325301205, + "grad_norm": 3.1707739710439076, + "learning_rate": 2.666666666666667e-06, + "loss": 11.2137, + "step": 2 + }, + { + "epoch": 0.021686746987951807, + "grad_norm": 3.2027941867217407, + "learning_rate": 4.000000000000001e-06, + "loss": 11.2128, + "step": 3 + }, + { + "epoch": 0.02891566265060241, + "grad_norm": 3.165506125068552, + "learning_rate": 5.333333333333334e-06, + "loss": 11.1895, + "step": 4 + }, + { + "epoch": 0.03614457831325301, + "grad_norm": 3.193452742356146, + "learning_rate": 6.666666666666667e-06, + "loss": 11.1119, + "step": 5 + }, + { + "epoch": 0.043373493975903614, + "grad_norm": 3.225997111904869, + "learning_rate": 8.000000000000001e-06, + "loss": 11.0683, + "step": 6 + }, + { + "epoch": 0.05060240963855422, + "grad_norm": 3.730074542647314, + "learning_rate": 9.333333333333334e-06, + "loss": 10.74, + "step": 7 + }, + { + "epoch": 0.05783132530120482, + "grad_norm": 4.035219081617531, + "learning_rate": 1.0666666666666667e-05, + "loss": 10.6055, + "step": 8 + }, + { + "epoch": 0.06506024096385542, + "grad_norm": 9.65258338136702, + "learning_rate": 1.2e-05, + "loss": 10.0028, + "step": 9 + }, + { + "epoch": 0.07228915662650602, + "grad_norm": 8.31667671170884, + "learning_rate": 1.3333333333333333e-05, + "loss": 9.8408, + "step": 10 + }, + { + "epoch": 0.07951807228915662, + "grad_norm": 4.991403421247793, + "learning_rate": 1.4666666666666666e-05, + "loss": 9.5849, + "step": 11 + }, + { + "epoch": 0.08674698795180723, + "grad_norm": 22.736881861641823, + "learning_rate": 1.6000000000000003e-05, + "loss": 10.3364, + "step": 12 + }, + { + "epoch": 0.09397590361445783, + "grad_norm": 6.702516595093613, + "learning_rate": 1.7333333333333336e-05, + "loss": 9.9409, + "step": 13 + }, + { + "epoch": 0.10120481927710843, + "grad_norm": 6.489246651194166, + "learning_rate": 1.866666666666667e-05, + "loss": 9.541, + "step": 14 + }, + { + "epoch": 0.10843373493975904, + "grad_norm": 6.0911333019039, + "learning_rate": 2e-05, + "loss": 8.9292, + "step": 15 + }, + { + "epoch": 0.11566265060240964, + "grad_norm": 19.10698802756055, + "learning_rate": 1.9999994461641828e-05, + "loss": 8.8768, + "step": 16 + }, + { + "epoch": 0.12289156626506025, + "grad_norm": 23.248522636875954, + "learning_rate": 1.9999977846573447e-05, + "loss": 9.075, + "step": 17 + }, + { + "epoch": 0.13012048192771083, + "grad_norm": 16.744432299141884, + "learning_rate": 1.9999950154813253e-05, + "loss": 8.8426, + "step": 18 + }, + { + "epoch": 0.13734939759036144, + "grad_norm": 8.068279939163723, + "learning_rate": 1.999991138639193e-05, + "loss": 8.464, + "step": 19 + }, + { + "epoch": 0.14457831325301204, + "grad_norm": 5.015885612913215, + "learning_rate": 1.9999861541352416e-05, + "loss": 8.3351, + "step": 20 + }, + { + "epoch": 0.15180722891566265, + "grad_norm": 8.22497767561685, + "learning_rate": 1.9999800619749922e-05, + "loss": 8.2269, + "step": 21 + }, + { + "epoch": 0.15903614457831325, + "grad_norm": 6.117420631713467, + "learning_rate": 1.9999728621651928e-05, + "loss": 8.0756, + "step": 22 + }, + { + "epoch": 0.16626506024096385, + "grad_norm": 12.16982281732316, + "learning_rate": 1.999964554713819e-05, + "loss": 8.1024, + "step": 23 + }, + { + "epoch": 0.17349397590361446, + "grad_norm": 7.456329076047914, + "learning_rate": 1.9999551396300722e-05, + "loss": 8.0019, + "step": 24 + }, + { + "epoch": 0.18072289156626506, + "grad_norm": 4.440613166100985, + "learning_rate": 1.9999446169243816e-05, + "loss": 7.8293, + "step": 25 + }, + { + "epoch": 0.18795180722891566, + "grad_norm": 6.566054149827827, + "learning_rate": 1.9999329866084025e-05, + "loss": 7.8169, + "step": 26 + }, + { + "epoch": 0.19518072289156627, + "grad_norm": 5.278515612282176, + "learning_rate": 1.9999202486950177e-05, + "loss": 7.7384, + "step": 27 + }, + { + "epoch": 0.20240963855421687, + "grad_norm": 3.95795043459971, + "learning_rate": 1.9999064031983366e-05, + "loss": 7.6547, + "step": 28 + }, + { + "epoch": 0.20963855421686747, + "grad_norm": 3.127753435885174, + "learning_rate": 1.9998914501336956e-05, + "loss": 7.5462, + "step": 29 + }, + { + "epoch": 0.21686746987951808, + "grad_norm": 4.438751294210153, + "learning_rate": 1.9998753895176576e-05, + "loss": 7.49, + "step": 30 + }, + { + "epoch": 0.22409638554216868, + "grad_norm": 4.273352272968494, + "learning_rate": 1.9998582213680123e-05, + "loss": 7.4468, + "step": 31 + }, + { + "epoch": 0.23132530120481928, + "grad_norm": 4.039956440849618, + "learning_rate": 1.999839945703777e-05, + "loss": 7.3883, + "step": 32 + }, + { + "epoch": 0.2385542168674699, + "grad_norm": 3.46365331288089, + "learning_rate": 1.9998205625451942e-05, + "loss": 7.3413, + "step": 33 + }, + { + "epoch": 0.2457831325301205, + "grad_norm": 3.761224558374574, + "learning_rate": 1.9998000719137353e-05, + "loss": 7.2896, + "step": 34 + }, + { + "epoch": 0.25301204819277107, + "grad_norm": 2.186432630643423, + "learning_rate": 1.999778473832096e-05, + "loss": 7.2291, + "step": 35 + }, + { + "epoch": 0.26024096385542167, + "grad_norm": 2.362614951337317, + "learning_rate": 1.9997557683242002e-05, + "loss": 7.2061, + "step": 36 + }, + { + "epoch": 0.2674698795180723, + "grad_norm": 2.98365102790646, + "learning_rate": 1.9997319554151988e-05, + "loss": 7.1366, + "step": 37 + }, + { + "epoch": 0.2746987951807229, + "grad_norm": 2.4721645367609306, + "learning_rate": 1.999707035131468e-05, + "loss": 7.1196, + "step": 38 + }, + { + "epoch": 0.2819277108433735, + "grad_norm": 2.5862742956183595, + "learning_rate": 1.9996810075006118e-05, + "loss": 7.078, + "step": 39 + }, + { + "epoch": 0.2891566265060241, + "grad_norm": 1.761307023407293, + "learning_rate": 1.9996538725514597e-05, + "loss": 7.0406, + "step": 40 + }, + { + "epoch": 0.2963855421686747, + "grad_norm": 2.000320378345402, + "learning_rate": 1.9996256303140688e-05, + "loss": 6.994, + "step": 41 + }, + { + "epoch": 0.3036144578313253, + "grad_norm": 1.746136060053765, + "learning_rate": 1.9995962808197217e-05, + "loss": 6.9823, + "step": 42 + }, + { + "epoch": 0.3108433734939759, + "grad_norm": 2.221450310426094, + "learning_rate": 1.9995658241009287e-05, + "loss": 6.9416, + "step": 43 + }, + { + "epoch": 0.3180722891566265, + "grad_norm": 2.1286116939303565, + "learning_rate": 1.9995342601914253e-05, + "loss": 6.8975, + "step": 44 + }, + { + "epoch": 0.3253012048192771, + "grad_norm": 3.9934233459602155, + "learning_rate": 1.999501589126174e-05, + "loss": 6.8784, + "step": 45 + }, + { + "epoch": 0.3325301204819277, + "grad_norm": 2.3348260466914788, + "learning_rate": 1.9994678109413638e-05, + "loss": 6.8568, + "step": 46 + }, + { + "epoch": 0.3397590361445783, + "grad_norm": 2.354485208468061, + "learning_rate": 1.9994329256744098e-05, + "loss": 6.8399, + "step": 47 + }, + { + "epoch": 0.3469879518072289, + "grad_norm": 2.1060678792501606, + "learning_rate": 1.9993969333639533e-05, + "loss": 6.8025, + "step": 48 + }, + { + "epoch": 0.3542168674698795, + "grad_norm": 1.968952895510157, + "learning_rate": 1.999359834049862e-05, + "loss": 6.7626, + "step": 49 + }, + { + "epoch": 0.3614457831325301, + "grad_norm": 3.1844501997779573, + "learning_rate": 1.9993216277732302e-05, + "loss": 6.7535, + "step": 50 + }, + { + "epoch": 0.3686746987951807, + "grad_norm": 1.4004142529003338, + "learning_rate": 1.999282314576377e-05, + "loss": 6.7236, + "step": 51 + }, + { + "epoch": 0.3759036144578313, + "grad_norm": 2.2511518742674075, + "learning_rate": 1.9992418945028494e-05, + "loss": 6.7025, + "step": 52 + }, + { + "epoch": 0.38313253012048193, + "grad_norm": 2.017984757576541, + "learning_rate": 1.999200367597419e-05, + "loss": 6.6952, + "step": 53 + }, + { + "epoch": 0.39036144578313253, + "grad_norm": 2.693725440825055, + "learning_rate": 1.9991577339060842e-05, + "loss": 6.6671, + "step": 54 + }, + { + "epoch": 0.39759036144578314, + "grad_norm": 2.336687191513332, + "learning_rate": 1.999113993476069e-05, + "loss": 6.6279, + "step": 55 + }, + { + "epoch": 0.40481927710843374, + "grad_norm": 1.626156137507855, + "learning_rate": 1.9990691463558235e-05, + "loss": 6.6054, + "step": 56 + }, + { + "epoch": 0.41204819277108434, + "grad_norm": 4.710443054060896, + "learning_rate": 1.999023192595024e-05, + "loss": 6.6323, + "step": 57 + }, + { + "epoch": 0.41927710843373495, + "grad_norm": 3.1631374303832787, + "learning_rate": 1.9989761322445714e-05, + "loss": 6.6045, + "step": 58 + }, + { + "epoch": 0.42650602409638555, + "grad_norm": 2.705558784445874, + "learning_rate": 1.9989279653565937e-05, + "loss": 6.5761, + "step": 59 + }, + { + "epoch": 0.43373493975903615, + "grad_norm": 2.4029383370840343, + "learning_rate": 1.9988786919844437e-05, + "loss": 6.5353, + "step": 60 + }, + { + "epoch": 0.44096385542168676, + "grad_norm": 4.839935196054632, + "learning_rate": 1.9988283121827004e-05, + "loss": 6.5426, + "step": 61 + }, + { + "epoch": 0.44819277108433736, + "grad_norm": 2.756332508287445, + "learning_rate": 1.9987768260071676e-05, + "loss": 6.5024, + "step": 62 + }, + { + "epoch": 0.45542168674698796, + "grad_norm": 3.1831689088661688, + "learning_rate": 1.9987242335148757e-05, + "loss": 6.4839, + "step": 63 + }, + { + "epoch": 0.46265060240963857, + "grad_norm": 2.4835416495638625, + "learning_rate": 1.9986705347640797e-05, + "loss": 6.4779, + "step": 64 + }, + { + "epoch": 0.46987951807228917, + "grad_norm": 3.5329316160565254, + "learning_rate": 1.9986157298142595e-05, + "loss": 6.4812, + "step": 65 + }, + { + "epoch": 0.4771084337349398, + "grad_norm": 5.2048663013264616, + "learning_rate": 1.998559818726122e-05, + "loss": 6.4407, + "step": 66 + }, + { + "epoch": 0.4843373493975904, + "grad_norm": 3.354789297443166, + "learning_rate": 1.9985028015615977e-05, + "loss": 6.403, + "step": 67 + }, + { + "epoch": 0.491566265060241, + "grad_norm": 2.157900918992127, + "learning_rate": 1.9984446783838432e-05, + "loss": 6.3751, + "step": 68 + }, + { + "epoch": 0.4987951807228916, + "grad_norm": 4.357115916572051, + "learning_rate": 1.9983854492572394e-05, + "loss": 6.4063, + "step": 69 + }, + { + "epoch": 0.5060240963855421, + "grad_norm": 2.201495820105759, + "learning_rate": 1.9983251142473935e-05, + "loss": 6.3544, + "step": 70 + }, + { + "epoch": 0.5132530120481927, + "grad_norm": 3.560124480900461, + "learning_rate": 1.9982636734211363e-05, + "loss": 6.3406, + "step": 71 + }, + { + "epoch": 0.5204819277108433, + "grad_norm": 3.566386015017448, + "learning_rate": 1.9982011268465246e-05, + "loss": 6.3305, + "step": 72 + }, + { + "epoch": 0.5277108433734939, + "grad_norm": 3.1131013450231375, + "learning_rate": 1.9981374745928388e-05, + "loss": 6.3004, + "step": 73 + }, + { + "epoch": 0.5349397590361445, + "grad_norm": 2.233793810037388, + "learning_rate": 1.998072716730585e-05, + "loss": 6.2761, + "step": 74 + }, + { + "epoch": 0.5421686746987951, + "grad_norm": 2.092535316219654, + "learning_rate": 1.9980068533314937e-05, + "loss": 6.2389, + "step": 75 + }, + { + "epoch": 0.5493975903614458, + "grad_norm": 2.45842268354128, + "learning_rate": 1.9979398844685197e-05, + "loss": 6.2151, + "step": 76 + }, + { + "epoch": 0.5566265060240964, + "grad_norm": 2.434137746198376, + "learning_rate": 1.9978718102158426e-05, + "loss": 6.2081, + "step": 77 + }, + { + "epoch": 0.563855421686747, + "grad_norm": 1.9402942665250358, + "learning_rate": 1.9978026306488665e-05, + "loss": 6.1746, + "step": 78 + }, + { + "epoch": 0.5710843373493976, + "grad_norm": 2.212680204205858, + "learning_rate": 1.99773234584422e-05, + "loss": 6.1698, + "step": 79 + }, + { + "epoch": 0.5783132530120482, + "grad_norm": 2.867414145507553, + "learning_rate": 1.9976609558797545e-05, + "loss": 6.1731, + "step": 80 + }, + { + "epoch": 0.5855421686746988, + "grad_norm": 1.6677690785418402, + "learning_rate": 1.9975884608345476e-05, + "loss": 6.131, + "step": 81 + }, + { + "epoch": 0.5927710843373494, + "grad_norm": 2.283628912711049, + "learning_rate": 1.9975148607888996e-05, + "loss": 6.0977, + "step": 82 + }, + { + "epoch": 0.6, + "grad_norm": 1.694395360167115, + "learning_rate": 1.9974401558243355e-05, + "loss": 6.0956, + "step": 83 + }, + { + "epoch": 0.6072289156626506, + "grad_norm": 2.1339705194766396, + "learning_rate": 1.9973643460236032e-05, + "loss": 6.108, + "step": 84 + }, + { + "epoch": 0.6144578313253012, + "grad_norm": 1.8551400305063734, + "learning_rate": 1.9972874314706755e-05, + "loss": 6.0656, + "step": 85 + }, + { + "epoch": 0.6216867469879518, + "grad_norm": 1.5313963607117285, + "learning_rate": 1.9972094122507485e-05, + "loss": 6.0186, + "step": 86 + }, + { + "epoch": 0.6289156626506024, + "grad_norm": 2.740724894685539, + "learning_rate": 1.997130288450242e-05, + "loss": 6.0288, + "step": 87 + }, + { + "epoch": 0.636144578313253, + "grad_norm": 2.0020638006423455, + "learning_rate": 1.997050060156799e-05, + "loss": 5.9922, + "step": 88 + }, + { + "epoch": 0.6433734939759036, + "grad_norm": 2.0686044074960948, + "learning_rate": 1.9969687274592863e-05, + "loss": 5.9676, + "step": 89 + }, + { + "epoch": 0.6506024096385542, + "grad_norm": 2.5446753330179055, + "learning_rate": 1.9968862904477936e-05, + "loss": 5.9557, + "step": 90 + }, + { + "epoch": 0.6578313253012048, + "grad_norm": 1.2820834374222696, + "learning_rate": 1.9968027492136337e-05, + "loss": 5.9011, + "step": 91 + }, + { + "epoch": 0.6650602409638554, + "grad_norm": 3.091054744667501, + "learning_rate": 1.9967181038493435e-05, + "loss": 5.9168, + "step": 92 + }, + { + "epoch": 0.672289156626506, + "grad_norm": 2.072802836305613, + "learning_rate": 1.9966323544486817e-05, + "loss": 5.8987, + "step": 93 + }, + { + "epoch": 0.6795180722891566, + "grad_norm": 1.946281703099331, + "learning_rate": 1.9965455011066313e-05, + "loss": 5.8606, + "step": 94 + }, + { + "epoch": 0.6867469879518072, + "grad_norm": 3.9574158066669143, + "learning_rate": 1.9964575439193966e-05, + "loss": 5.8466, + "step": 95 + }, + { + "epoch": 0.6939759036144578, + "grad_norm": 2.8374569157108525, + "learning_rate": 1.9963684829844053e-05, + "loss": 5.8101, + "step": 96 + }, + { + "epoch": 0.7012048192771084, + "grad_norm": 2.481663771923425, + "learning_rate": 1.996278318400308e-05, + "loss": 5.7891, + "step": 97 + }, + { + "epoch": 0.708433734939759, + "grad_norm": 2.628963140065436, + "learning_rate": 1.9961870502669772e-05, + "loss": 5.778, + "step": 98 + }, + { + "epoch": 0.7156626506024096, + "grad_norm": 1.7537754862303554, + "learning_rate": 1.996094678685508e-05, + "loss": 5.7059, + "step": 99 + }, + { + "epoch": 0.7228915662650602, + "grad_norm": 2.9054329151341802, + "learning_rate": 1.996001203758218e-05, + "loss": 5.7243, + "step": 100 + }, + { + "epoch": 0.7301204819277108, + "grad_norm": 2.335259221423995, + "learning_rate": 1.9959066255886465e-05, + "loss": 5.7074, + "step": 101 + }, + { + "epoch": 0.7373493975903614, + "grad_norm": 1.503090373097313, + "learning_rate": 1.9958109442815553e-05, + "loss": 5.6759, + "step": 102 + }, + { + "epoch": 0.744578313253012, + "grad_norm": 3.6022806083901573, + "learning_rate": 1.9957141599429277e-05, + "loss": 5.671, + "step": 103 + }, + { + "epoch": 0.7518072289156627, + "grad_norm": 2.0559454839399285, + "learning_rate": 1.995616272679969e-05, + "loss": 5.6682, + "step": 104 + }, + { + "epoch": 0.7590361445783133, + "grad_norm": 2.320827355274334, + "learning_rate": 1.995517282601106e-05, + "loss": 5.6525, + "step": 105 + }, + { + "epoch": 0.7662650602409639, + "grad_norm": 1.7559053764640538, + "learning_rate": 1.9954171898159876e-05, + "loss": 5.5938, + "step": 106 + }, + { + "epoch": 0.7734939759036145, + "grad_norm": 2.955031141899699, + "learning_rate": 1.9953159944354832e-05, + "loss": 5.5713, + "step": 107 + }, + { + "epoch": 0.7807228915662651, + "grad_norm": 1.6374927792829403, + "learning_rate": 1.9952136965716846e-05, + "loss": 5.5735, + "step": 108 + }, + { + "epoch": 0.7879518072289157, + "grad_norm": 2.291268667751327, + "learning_rate": 1.995110296337904e-05, + "loss": 5.5624, + "step": 109 + }, + { + "epoch": 0.7951807228915663, + "grad_norm": 1.889173374799646, + "learning_rate": 1.9950057938486745e-05, + "loss": 5.5267, + "step": 110 + }, + { + "epoch": 0.8024096385542169, + "grad_norm": 2.1937875261971054, + "learning_rate": 1.9949001892197514e-05, + "loss": 5.4858, + "step": 111 + }, + { + "epoch": 0.8096385542168675, + "grad_norm": 1.4888370843663468, + "learning_rate": 1.9947934825681092e-05, + "loss": 5.4787, + "step": 112 + }, + { + "epoch": 0.8168674698795181, + "grad_norm": 2.8633836455244195, + "learning_rate": 1.9946856740119442e-05, + "loss": 5.4862, + "step": 113 + }, + { + "epoch": 0.8240963855421687, + "grad_norm": 2.4482360353083337, + "learning_rate": 1.994576763670673e-05, + "loss": 5.4919, + "step": 114 + }, + { + "epoch": 0.8313253012048193, + "grad_norm": 1.7268002558296573, + "learning_rate": 1.994466751664932e-05, + "loss": 5.4446, + "step": 115 + }, + { + "epoch": 0.8385542168674699, + "grad_norm": 2.186838960349522, + "learning_rate": 1.9943556381165785e-05, + "loss": 5.4286, + "step": 116 + }, + { + "epoch": 0.8457831325301205, + "grad_norm": 1.7901714148433048, + "learning_rate": 1.99424342314869e-05, + "loss": 5.4139, + "step": 117 + }, + { + "epoch": 0.8530120481927711, + "grad_norm": 1.7585907215388294, + "learning_rate": 1.994130106885564e-05, + "loss": 5.3935, + "step": 118 + }, + { + "epoch": 0.8602409638554217, + "grad_norm": 1.8017706034631977, + "learning_rate": 1.9940156894527178e-05, + "loss": 5.3549, + "step": 119 + }, + { + "epoch": 0.8674698795180723, + "grad_norm": 1.851212819912402, + "learning_rate": 1.993900170976888e-05, + "loss": 5.3467, + "step": 120 + }, + { + "epoch": 0.8746987951807229, + "grad_norm": 1.5118926301562392, + "learning_rate": 1.993783551586031e-05, + "loss": 5.3375, + "step": 121 + }, + { + "epoch": 0.8819277108433735, + "grad_norm": 1.7153595550375194, + "learning_rate": 1.993665831409323e-05, + "loss": 5.2921, + "step": 122 + }, + { + "epoch": 0.8891566265060241, + "grad_norm": 2.074317448041623, + "learning_rate": 1.9935470105771596e-05, + "loss": 5.2889, + "step": 123 + }, + { + "epoch": 0.8963855421686747, + "grad_norm": 1.3244813318443867, + "learning_rate": 1.9934270892211548e-05, + "loss": 5.2638, + "step": 124 + }, + { + "epoch": 0.9036144578313253, + "grad_norm": 3.321959023030634, + "learning_rate": 1.9933060674741422e-05, + "loss": 5.3037, + "step": 125 + }, + { + "epoch": 0.9108433734939759, + "grad_norm": 2.0640131331656213, + "learning_rate": 1.9931839454701744e-05, + "loss": 5.289, + "step": 126 + }, + { + "epoch": 0.9180722891566265, + "grad_norm": 2.1456889879912757, + "learning_rate": 1.993060723344522e-05, + "loss": 5.2088, + "step": 127 + }, + { + "epoch": 0.9253012048192771, + "grad_norm": 2.0596746709249167, + "learning_rate": 1.992936401233675e-05, + "loss": 5.2139, + "step": 128 + }, + { + "epoch": 0.9325301204819277, + "grad_norm": 1.9248162588441524, + "learning_rate": 1.9928109792753417e-05, + "loss": 5.2246, + "step": 129 + }, + { + "epoch": 0.9397590361445783, + "grad_norm": 1.4891364526870876, + "learning_rate": 1.9926844576084483e-05, + "loss": 5.1677, + "step": 130 + }, + { + "epoch": 0.946987951807229, + "grad_norm": 1.5932598961826778, + "learning_rate": 1.9925568363731388e-05, + "loss": 5.1616, + "step": 131 + }, + { + "epoch": 0.9542168674698795, + "grad_norm": 1.7385768882199546, + "learning_rate": 1.9924281157107762e-05, + "loss": 5.1549, + "step": 132 + }, + { + "epoch": 0.9614457831325302, + "grad_norm": 1.6773180106543204, + "learning_rate": 1.99229829576394e-05, + "loss": 5.1407, + "step": 133 + }, + { + "epoch": 0.9686746987951808, + "grad_norm": 1.1426123121276215, + "learning_rate": 1.9921673766764292e-05, + "loss": 5.121, + "step": 134 + }, + { + "epoch": 0.9759036144578314, + "grad_norm": 2.474738495686583, + "learning_rate": 1.992035358593258e-05, + "loss": 5.1344, + "step": 135 + }, + { + "epoch": 0.983132530120482, + "grad_norm": 1.6451131370612986, + "learning_rate": 1.9919022416606596e-05, + "loss": 5.1402, + "step": 136 + }, + { + "epoch": 0.9903614457831326, + "grad_norm": 2.9204003742023374, + "learning_rate": 1.991768026026084e-05, + "loss": 5.1172, + "step": 137 + }, + { + "epoch": 0.9975903614457832, + "grad_norm": 2.1702223253759776, + "learning_rate": 1.991632711838198e-05, + "loss": 5.1175, + "step": 138 + }, + { + "epoch": 1.0048192771084337, + "grad_norm": 1.496695700102801, + "learning_rate": 1.9914962992468854e-05, + "loss": 5.0598, + "step": 139 + }, + { + "epoch": 1.0120481927710843, + "grad_norm": 3.3192304356055917, + "learning_rate": 1.991358788403246e-05, + "loss": 5.0917, + "step": 140 + }, + { + "epoch": 1.0192771084337349, + "grad_norm": 2.613171654160906, + "learning_rate": 1.991220179459597e-05, + "loss": 5.0876, + "step": 141 + }, + { + "epoch": 1.0265060240963855, + "grad_norm": 2.021270169187327, + "learning_rate": 1.991080472569472e-05, + "loss": 5.0376, + "step": 142 + }, + { + "epoch": 1.033734939759036, + "grad_norm": 1.7874754394384833, + "learning_rate": 1.9909396678876197e-05, + "loss": 5.0297, + "step": 143 + }, + { + "epoch": 1.0409638554216867, + "grad_norm": 2.1666942328948693, + "learning_rate": 1.9907977655700056e-05, + "loss": 5.021, + "step": 144 + }, + { + "epoch": 1.0481927710843373, + "grad_norm": 1.4974174294265452, + "learning_rate": 1.990654765773811e-05, + "loss": 4.9784, + "step": 145 + }, + { + "epoch": 1.0554216867469879, + "grad_norm": 2.4030846737304903, + "learning_rate": 1.990510668657433e-05, + "loss": 5.0143, + "step": 146 + }, + { + "epoch": 1.0626506024096385, + "grad_norm": 1.5847142291975158, + "learning_rate": 1.9903654743804833e-05, + "loss": 4.9717, + "step": 147 + }, + { + "epoch": 1.069879518072289, + "grad_norm": 2.2293042123928872, + "learning_rate": 1.9902191831037898e-05, + "loss": 4.975, + "step": 148 + }, + { + "epoch": 1.0771084337349397, + "grad_norm": 1.3107443058211161, + "learning_rate": 1.9900717949893952e-05, + "loss": 4.9554, + "step": 149 + }, + { + "epoch": 1.0843373493975903, + "grad_norm": 2.98633810723938, + "learning_rate": 1.9899233102005573e-05, + "loss": 4.9822, + "step": 150 + }, + { + "epoch": 1.091566265060241, + "grad_norm": 2.2485470075652567, + "learning_rate": 1.989773728901748e-05, + "loss": 4.9836, + "step": 151 + }, + { + "epoch": 1.0987951807228915, + "grad_norm": 1.6406575235273002, + "learning_rate": 1.9896230512586548e-05, + "loss": 4.9658, + "step": 152 + }, + { + "epoch": 1.106024096385542, + "grad_norm": 2.042584221681109, + "learning_rate": 1.9894712774381787e-05, + "loss": 4.9253, + "step": 153 + }, + { + "epoch": 1.1132530120481927, + "grad_norm": 2.027178425201193, + "learning_rate": 1.9893184076084356e-05, + "loss": 4.9186, + "step": 154 + }, + { + "epoch": 1.1204819277108433, + "grad_norm": 1.432938791816063, + "learning_rate": 1.9891644419387545e-05, + "loss": 4.915, + "step": 155 + }, + { + "epoch": 1.127710843373494, + "grad_norm": 1.8296615722980554, + "learning_rate": 1.989009380599679e-05, + "loss": 4.8821, + "step": 156 + }, + { + "epoch": 1.1349397590361445, + "grad_norm": 1.8064088509012493, + "learning_rate": 1.988853223762967e-05, + "loss": 4.9103, + "step": 157 + }, + { + "epoch": 1.1421686746987951, + "grad_norm": 1.6601625863719773, + "learning_rate": 1.988695971601588e-05, + "loss": 4.902, + "step": 158 + }, + { + "epoch": 1.1493975903614457, + "grad_norm": 1.4310915855021005, + "learning_rate": 1.9885376242897257e-05, + "loss": 4.8543, + "step": 159 + }, + { + "epoch": 1.1566265060240963, + "grad_norm": 1.6199867111977333, + "learning_rate": 1.9883781820027777e-05, + "loss": 4.8642, + "step": 160 + }, + { + "epoch": 1.163855421686747, + "grad_norm": 1.60087290545569, + "learning_rate": 1.988217644917353e-05, + "loss": 4.861, + "step": 161 + }, + { + "epoch": 1.1710843373493975, + "grad_norm": 1.4310791832649268, + "learning_rate": 1.9880560132112743e-05, + "loss": 4.8449, + "step": 162 + }, + { + "epoch": 1.1783132530120481, + "grad_norm": 1.5116431119020965, + "learning_rate": 1.9878932870635766e-05, + "loss": 4.8333, + "step": 163 + }, + { + "epoch": 1.1855421686746987, + "grad_norm": 1.3107772455570288, + "learning_rate": 1.9877294666545067e-05, + "loss": 4.8205, + "step": 164 + }, + { + "epoch": 1.1927710843373494, + "grad_norm": 1.590059839480383, + "learning_rate": 1.987564552165524e-05, + "loss": 4.7843, + "step": 165 + }, + { + "epoch": 1.2, + "grad_norm": 1.2940053194060677, + "learning_rate": 1.9873985437792992e-05, + "loss": 4.7775, + "step": 166 + }, + { + "epoch": 1.2072289156626506, + "grad_norm": 1.5649565551472995, + "learning_rate": 1.987231441679716e-05, + "loss": 4.7764, + "step": 167 + }, + { + "epoch": 1.2144578313253012, + "grad_norm": 1.364758540526031, + "learning_rate": 1.987063246051868e-05, + "loss": 4.7742, + "step": 168 + }, + { + "epoch": 1.2216867469879518, + "grad_norm": 1.9001350592348814, + "learning_rate": 1.9868939570820608e-05, + "loss": 4.7813, + "step": 169 + }, + { + "epoch": 1.2289156626506024, + "grad_norm": 1.4234469610031761, + "learning_rate": 1.9867235749578108e-05, + "loss": 4.7641, + "step": 170 + }, + { + "epoch": 1.236144578313253, + "grad_norm": 2.1776918892703225, + "learning_rate": 1.9865520998678458e-05, + "loss": 4.7818, + "step": 171 + }, + { + "epoch": 1.2433734939759036, + "grad_norm": 1.3890011845463408, + "learning_rate": 1.986379532002104e-05, + "loss": 4.7704, + "step": 172 + }, + { + "epoch": 1.2506024096385542, + "grad_norm": 2.0487165142274306, + "learning_rate": 1.9862058715517332e-05, + "loss": 4.7802, + "step": 173 + }, + { + "epoch": 1.2578313253012048, + "grad_norm": 1.2355025181764954, + "learning_rate": 1.9860311187090927e-05, + "loss": 4.7402, + "step": 174 + }, + { + "epoch": 1.2650602409638554, + "grad_norm": 1.9249359849876109, + "learning_rate": 1.9858552736677516e-05, + "loss": 4.7306, + "step": 175 + }, + { + "epoch": 1.272289156626506, + "grad_norm": 2.139696984414974, + "learning_rate": 1.985678336622488e-05, + "loss": 4.717, + "step": 176 + }, + { + "epoch": 1.2795180722891566, + "grad_norm": 1.0388000431735693, + "learning_rate": 1.9855003077692898e-05, + "loss": 4.6619, + "step": 177 + }, + { + "epoch": 1.2867469879518072, + "grad_norm": 1.5186233110203489, + "learning_rate": 1.9853211873053547e-05, + "loss": 4.6737, + "step": 178 + }, + { + "epoch": 1.2939759036144578, + "grad_norm": 0.9525342243672005, + "learning_rate": 1.98514097542909e-05, + "loss": 4.6861, + "step": 179 + }, + { + "epoch": 1.3012048192771084, + "grad_norm": 1.689627739569883, + "learning_rate": 1.984959672340111e-05, + "loss": 4.6936, + "step": 180 + }, + { + "epoch": 1.308433734939759, + "grad_norm": 1.7822859896216436, + "learning_rate": 1.984777278239241e-05, + "loss": 4.6881, + "step": 181 + }, + { + "epoch": 1.3156626506024096, + "grad_norm": 0.9953258914708404, + "learning_rate": 1.984593793328514e-05, + "loss": 4.6258, + "step": 182 + }, + { + "epoch": 1.3228915662650602, + "grad_norm": 2.5510924952211647, + "learning_rate": 1.9844092178111703e-05, + "loss": 4.6827, + "step": 183 + }, + { + "epoch": 1.3301204819277108, + "grad_norm": 1.4564971326104093, + "learning_rate": 1.9842235518916592e-05, + "loss": 4.675, + "step": 184 + }, + { + "epoch": 1.3373493975903614, + "grad_norm": 1.3183469685608156, + "learning_rate": 1.984036795775638e-05, + "loss": 4.6577, + "step": 185 + }, + { + "epoch": 1.344578313253012, + "grad_norm": 1.6076666014762455, + "learning_rate": 1.9838489496699703e-05, + "loss": 4.6344, + "step": 186 + }, + { + "epoch": 1.3518072289156626, + "grad_norm": 1.4334408175522528, + "learning_rate": 1.983660013782729e-05, + "loss": 4.6371, + "step": 187 + }, + { + "epoch": 1.3590361445783132, + "grad_norm": 1.0276575588288683, + "learning_rate": 1.983469988323192e-05, + "loss": 4.5858, + "step": 188 + }, + { + "epoch": 1.3662650602409638, + "grad_norm": 1.2524191668366011, + "learning_rate": 1.9832788735018452e-05, + "loss": 4.6238, + "step": 189 + }, + { + "epoch": 1.3734939759036144, + "grad_norm": 1.111924655995767, + "learning_rate": 1.9830866695303817e-05, + "loss": 4.6196, + "step": 190 + }, + { + "epoch": 1.380722891566265, + "grad_norm": 1.4587811465856404, + "learning_rate": 1.9828933766216998e-05, + "loss": 4.6152, + "step": 191 + }, + { + "epoch": 1.3879518072289156, + "grad_norm": 1.3517246312720717, + "learning_rate": 1.982698994989905e-05, + "loss": 4.5879, + "step": 192 + }, + { + "epoch": 1.3951807228915662, + "grad_norm": 1.0781361858523884, + "learning_rate": 1.982503524850308e-05, + "loss": 4.5935, + "step": 193 + }, + { + "epoch": 1.4024096385542169, + "grad_norm": 1.3983940494845462, + "learning_rate": 1.982306966419426e-05, + "loss": 4.567, + "step": 194 + }, + { + "epoch": 1.4096385542168675, + "grad_norm": 1.0951708644481744, + "learning_rate": 1.9821093199149806e-05, + "loss": 4.5285, + "step": 195 + }, + { + "epoch": 1.416867469879518, + "grad_norm": 1.5337453436245976, + "learning_rate": 1.9819105855558996e-05, + "loss": 4.5419, + "step": 196 + }, + { + "epoch": 1.4240963855421687, + "grad_norm": 1.0266826762343255, + "learning_rate": 1.981710763562315e-05, + "loss": 4.5681, + "step": 197 + }, + { + "epoch": 1.4313253012048193, + "grad_norm": 1.7564922932399614, + "learning_rate": 1.9815098541555645e-05, + "loss": 4.5582, + "step": 198 + }, + { + "epoch": 1.4385542168674699, + "grad_norm": 1.1072497618442172, + "learning_rate": 1.9813078575581898e-05, + "loss": 4.5167, + "step": 199 + }, + { + "epoch": 1.4457831325301205, + "grad_norm": 1.566828226827763, + "learning_rate": 1.981104773993936e-05, + "loss": 4.5037, + "step": 200 + }, + { + "epoch": 1.453012048192771, + "grad_norm": 1.2269950037429016, + "learning_rate": 1.9809006036877537e-05, + "loss": 4.5214, + "step": 201 + }, + { + "epoch": 1.4602409638554217, + "grad_norm": 1.2192495763855802, + "learning_rate": 1.9806953468657966e-05, + "loss": 4.5067, + "step": 202 + }, + { + "epoch": 1.4674698795180723, + "grad_norm": 1.0133073397884125, + "learning_rate": 1.9804890037554215e-05, + "loss": 4.5097, + "step": 203 + }, + { + "epoch": 1.4746987951807229, + "grad_norm": 1.1081042205578755, + "learning_rate": 1.9802815745851888e-05, + "loss": 4.4802, + "step": 204 + }, + { + "epoch": 1.4819277108433735, + "grad_norm": 1.052790913749799, + "learning_rate": 1.980073059584862e-05, + "loss": 4.4943, + "step": 205 + }, + { + "epoch": 1.489156626506024, + "grad_norm": 1.0752814528281058, + "learning_rate": 1.9798634589854073e-05, + "loss": 4.4714, + "step": 206 + }, + { + "epoch": 1.4963855421686747, + "grad_norm": 1.4338817481695876, + "learning_rate": 1.9796527730189936e-05, + "loss": 4.4653, + "step": 207 + }, + { + "epoch": 1.5036144578313253, + "grad_norm": 0.9863500898479299, + "learning_rate": 1.9794410019189913e-05, + "loss": 4.4539, + "step": 208 + }, + { + "epoch": 1.510843373493976, + "grad_norm": 1.2842052237396306, + "learning_rate": 1.9792281459199737e-05, + "loss": 4.4653, + "step": 209 + }, + { + "epoch": 1.5180722891566265, + "grad_norm": 1.4247627004514936, + "learning_rate": 1.9790142052577148e-05, + "loss": 4.4411, + "step": 210 + }, + { + "epoch": 1.5253012048192771, + "grad_norm": 1.2800317446823677, + "learning_rate": 1.9787991801691907e-05, + "loss": 4.43, + "step": 211 + }, + { + "epoch": 1.5325301204819277, + "grad_norm": 1.288596540985055, + "learning_rate": 1.9785830708925792e-05, + "loss": 4.4493, + "step": 212 + }, + { + "epoch": 1.5397590361445783, + "grad_norm": 1.2727314825477154, + "learning_rate": 1.978365877667258e-05, + "loss": 4.4233, + "step": 213 + }, + { + "epoch": 1.546987951807229, + "grad_norm": 1.0980274594078798, + "learning_rate": 1.9781476007338058e-05, + "loss": 4.3968, + "step": 214 + }, + { + "epoch": 1.5542168674698795, + "grad_norm": 1.2067021264618283, + "learning_rate": 1.977928240334002e-05, + "loss": 4.4214, + "step": 215 + }, + { + "epoch": 1.5614457831325301, + "grad_norm": 1.2126474757588954, + "learning_rate": 1.9777077967108254e-05, + "loss": 4.4098, + "step": 216 + }, + { + "epoch": 1.5686746987951807, + "grad_norm": 1.4690386666975572, + "learning_rate": 1.9774862701084555e-05, + "loss": 4.4268, + "step": 217 + }, + { + "epoch": 1.5759036144578313, + "grad_norm": 1.0488849882671147, + "learning_rate": 1.9772636607722714e-05, + "loss": 4.3894, + "step": 218 + }, + { + "epoch": 1.583132530120482, + "grad_norm": 1.630809721223867, + "learning_rate": 1.9770399689488506e-05, + "loss": 4.4133, + "step": 219 + }, + { + "epoch": 1.5903614457831325, + "grad_norm": 1.113109729713893, + "learning_rate": 1.9768151948859705e-05, + "loss": 4.3772, + "step": 220 + }, + { + "epoch": 1.5975903614457831, + "grad_norm": 1.5423275320082017, + "learning_rate": 1.9765893388326064e-05, + "loss": 4.3785, + "step": 221 + }, + { + "epoch": 1.6048192771084338, + "grad_norm": 1.0807052768227303, + "learning_rate": 1.9763624010389334e-05, + "loss": 4.3694, + "step": 222 + }, + { + "epoch": 1.6120481927710844, + "grad_norm": 1.235992463133922, + "learning_rate": 1.9761343817563235e-05, + "loss": 4.359, + "step": 223 + }, + { + "epoch": 1.619277108433735, + "grad_norm": 1.5186454860312188, + "learning_rate": 1.9759052812373478e-05, + "loss": 4.3792, + "step": 224 + }, + { + "epoch": 1.6265060240963856, + "grad_norm": 1.2019163259646208, + "learning_rate": 1.9756750997357738e-05, + "loss": 4.3688, + "step": 225 + }, + { + "epoch": 1.6337349397590362, + "grad_norm": 1.7333794728755505, + "learning_rate": 1.9754438375065673e-05, + "loss": 4.3512, + "step": 226 + }, + { + "epoch": 1.6409638554216868, + "grad_norm": 1.1407460567282055, + "learning_rate": 1.9752114948058908e-05, + "loss": 4.3802, + "step": 227 + }, + { + "epoch": 1.6481927710843374, + "grad_norm": 1.6157840392044631, + "learning_rate": 1.974978071891104e-05, + "loss": 4.3511, + "step": 228 + }, + { + "epoch": 1.655421686746988, + "grad_norm": 1.0476544634861773, + "learning_rate": 1.9747435690207625e-05, + "loss": 4.3221, + "step": 229 + }, + { + "epoch": 1.6626506024096386, + "grad_norm": 1.697500843790948, + "learning_rate": 1.9745079864546184e-05, + "loss": 4.3312, + "step": 230 + }, + { + "epoch": 1.6698795180722892, + "grad_norm": 1.3904195390686156, + "learning_rate": 1.9742713244536205e-05, + "loss": 4.2968, + "step": 231 + }, + { + "epoch": 1.6771084337349398, + "grad_norm": 1.5290382901012387, + "learning_rate": 1.9740335832799118e-05, + "loss": 4.319, + "step": 232 + }, + { + "epoch": 1.6843373493975904, + "grad_norm": 1.279841205474429, + "learning_rate": 1.973794763196832e-05, + "loss": 4.3077, + "step": 233 + }, + { + "epoch": 1.691566265060241, + "grad_norm": 1.3872098276085976, + "learning_rate": 1.973554864468915e-05, + "loss": 4.3165, + "step": 234 + }, + { + "epoch": 1.6987951807228916, + "grad_norm": 1.2522587215309555, + "learning_rate": 1.97331388736189e-05, + "loss": 4.2679, + "step": 235 + }, + { + "epoch": 1.7060240963855422, + "grad_norm": 1.3360665273295562, + "learning_rate": 1.9730718321426804e-05, + "loss": 4.306, + "step": 236 + }, + { + "epoch": 1.7132530120481928, + "grad_norm": 1.6653558400826634, + "learning_rate": 1.972828699079404e-05, + "loss": 4.2908, + "step": 237 + }, + { + "epoch": 1.7204819277108434, + "grad_norm": 1.057771248044181, + "learning_rate": 1.972584488441372e-05, + "loss": 4.2358, + "step": 238 + }, + { + "epoch": 1.727710843373494, + "grad_norm": 1.690770002741558, + "learning_rate": 1.9723392004990904e-05, + "loss": 4.2696, + "step": 239 + }, + { + "epoch": 1.7349397590361446, + "grad_norm": 1.3303504757518965, + "learning_rate": 1.972092835524257e-05, + "loss": 4.2581, + "step": 240 + }, + { + "epoch": 1.7421686746987952, + "grad_norm": 1.5896442171678875, + "learning_rate": 1.9718453937897637e-05, + "loss": 4.2744, + "step": 241 + }, + { + "epoch": 1.7493975903614458, + "grad_norm": 1.2953058262004782, + "learning_rate": 1.9715968755696946e-05, + "loss": 4.2906, + "step": 242 + }, + { + "epoch": 1.7566265060240964, + "grad_norm": 1.1295293666533506, + "learning_rate": 1.971347281139326e-05, + "loss": 4.2681, + "step": 243 + }, + { + "epoch": 1.763855421686747, + "grad_norm": 1.7488116684794741, + "learning_rate": 1.971096610775127e-05, + "loss": 4.2374, + "step": 244 + }, + { + "epoch": 1.7710843373493976, + "grad_norm": 0.9787269896385271, + "learning_rate": 1.9708448647547575e-05, + "loss": 4.2927, + "step": 245 + }, + { + "epoch": 1.7783132530120482, + "grad_norm": 1.9264724538555262, + "learning_rate": 1.9705920433570696e-05, + "loss": 4.2781, + "step": 246 + }, + { + "epoch": 1.7855421686746988, + "grad_norm": 1.1677065487324365, + "learning_rate": 1.970338146862107e-05, + "loss": 4.2401, + "step": 247 + }, + { + "epoch": 1.7927710843373494, + "grad_norm": 1.5709729392003717, + "learning_rate": 1.9700831755511028e-05, + "loss": 4.2468, + "step": 248 + }, + { + "epoch": 1.8, + "grad_norm": 0.971212117208314, + "learning_rate": 1.969827129706482e-05, + "loss": 4.2163, + "step": 249 + }, + { + "epoch": 1.8072289156626506, + "grad_norm": 1.4724427784286502, + "learning_rate": 1.9695700096118594e-05, + "loss": 4.2263, + "step": 250 + }, + { + "epoch": 1.8144578313253013, + "grad_norm": 1.2968473120262307, + "learning_rate": 1.9693118155520394e-05, + "loss": 4.2356, + "step": 251 + }, + { + "epoch": 1.8216867469879519, + "grad_norm": 1.3911380380341898, + "learning_rate": 1.9690525478130162e-05, + "loss": 4.2298, + "step": 252 + }, + { + "epoch": 1.8289156626506025, + "grad_norm": 0.8098318647581148, + "learning_rate": 1.9687922066819734e-05, + "loss": 4.1948, + "step": 253 + }, + { + "epoch": 1.836144578313253, + "grad_norm": 1.1659829550163594, + "learning_rate": 1.9685307924472835e-05, + "loss": 4.1959, + "step": 254 + }, + { + "epoch": 1.8433734939759037, + "grad_norm": 1.1602925584411976, + "learning_rate": 1.9682683053985073e-05, + "loss": 4.1684, + "step": 255 + }, + { + "epoch": 1.8506024096385543, + "grad_norm": 1.643102304487686, + "learning_rate": 1.968004745826395e-05, + "loss": 4.2193, + "step": 256 + }, + { + "epoch": 1.8578313253012049, + "grad_norm": 1.0061759340188303, + "learning_rate": 1.9677401140228834e-05, + "loss": 4.1585, + "step": 257 + }, + { + "epoch": 1.8650602409638555, + "grad_norm": 1.4204336218376243, + "learning_rate": 1.967474410281098e-05, + "loss": 4.2211, + "step": 258 + }, + { + "epoch": 1.872289156626506, + "grad_norm": 1.2381003435701177, + "learning_rate": 1.9672076348953507e-05, + "loss": 4.164, + "step": 259 + }, + { + "epoch": 1.8795180722891565, + "grad_norm": 1.3142604064597698, + "learning_rate": 1.966939788161142e-05, + "loss": 4.1279, + "step": 260 + }, + { + "epoch": 1.886746987951807, + "grad_norm": 1.5490808076132756, + "learning_rate": 1.9666708703751576e-05, + "loss": 4.1989, + "step": 261 + }, + { + "epoch": 1.8939759036144577, + "grad_norm": 1.6637523057931343, + "learning_rate": 1.96640088183527e-05, + "loss": 4.1386, + "step": 262 + }, + { + "epoch": 1.9012048192771083, + "grad_norm": 1.1845491376199697, + "learning_rate": 1.9661298228405377e-05, + "loss": 4.1487, + "step": 263 + }, + { + "epoch": 1.9084337349397589, + "grad_norm": 1.263908380935535, + "learning_rate": 1.9658576936912057e-05, + "loss": 4.1302, + "step": 264 + }, + { + "epoch": 1.9156626506024095, + "grad_norm": 1.289931147920118, + "learning_rate": 1.9655844946887035e-05, + "loss": 4.1303, + "step": 265 + }, + { + "epoch": 1.92289156626506, + "grad_norm": 1.0861244271331052, + "learning_rate": 1.9653102261356456e-05, + "loss": 4.1042, + "step": 266 + }, + { + "epoch": 1.9301204819277107, + "grad_norm": 1.4855987153795662, + "learning_rate": 1.9650348883358313e-05, + "loss": 4.1239, + "step": 267 + }, + { + "epoch": 1.9373493975903613, + "grad_norm": 1.1356728975830408, + "learning_rate": 1.9647584815942455e-05, + "loss": 4.1402, + "step": 268 + }, + { + "epoch": 1.944578313253012, + "grad_norm": 1.4987833232332588, + "learning_rate": 1.964481006217055e-05, + "loss": 4.1223, + "step": 269 + }, + { + "epoch": 1.9518072289156625, + "grad_norm": 1.3698683946332046, + "learning_rate": 1.9642024625116117e-05, + "loss": 4.0846, + "step": 270 + }, + { + "epoch": 1.959036144578313, + "grad_norm": 1.4713817649962406, + "learning_rate": 1.963922850786451e-05, + "loss": 4.0943, + "step": 271 + }, + { + "epoch": 1.9662650602409637, + "grad_norm": 1.6158687103746316, + "learning_rate": 1.963642171351291e-05, + "loss": 4.1092, + "step": 272 + }, + { + "epoch": 1.9734939759036143, + "grad_norm": 1.3112900282213475, + "learning_rate": 1.963360424517031e-05, + "loss": 4.1197, + "step": 273 + }, + { + "epoch": 1.980722891566265, + "grad_norm": 1.3165917322818186, + "learning_rate": 1.9630776105957553e-05, + "loss": 4.0985, + "step": 274 + }, + { + "epoch": 1.9879518072289155, + "grad_norm": 1.2679890312035356, + "learning_rate": 1.9627937299007286e-05, + "loss": 4.0918, + "step": 275 + }, + { + "epoch": 1.9951807228915661, + "grad_norm": 1.3006507811283787, + "learning_rate": 1.962508782746397e-05, + "loss": 4.1095, + "step": 276 + }, + { + "epoch": 2.0024096385542167, + "grad_norm": 1.4124431865354987, + "learning_rate": 1.9622227694483893e-05, + "loss": 4.0901, + "step": 277 + }, + { + "epoch": 2.0096385542168673, + "grad_norm": 1.2819799804016005, + "learning_rate": 1.9619356903235132e-05, + "loss": 4.047, + "step": 278 + }, + { + "epoch": 2.016867469879518, + "grad_norm": 1.5597905663515192, + "learning_rate": 1.961647545689759e-05, + "loss": 4.0477, + "step": 279 + }, + { + "epoch": 2.0240963855421685, + "grad_norm": 0.9423133582923033, + "learning_rate": 1.961358335866296e-05, + "loss": 4.0491, + "step": 280 + }, + { + "epoch": 2.031325301204819, + "grad_norm": 1.8743296089578012, + "learning_rate": 1.9610680611734737e-05, + "loss": 4.0293, + "step": 281 + }, + { + "epoch": 2.0385542168674697, + "grad_norm": 0.9891080430136323, + "learning_rate": 1.960776721932821e-05, + "loss": 4.0302, + "step": 282 + }, + { + "epoch": 2.0457831325301203, + "grad_norm": 2.1075583542099157, + "learning_rate": 1.9604843184670462e-05, + "loss": 4.0533, + "step": 283 + }, + { + "epoch": 2.053012048192771, + "grad_norm": 1.3836722891539663, + "learning_rate": 1.9601908511000362e-05, + "loss": 4.0804, + "step": 284 + }, + { + "epoch": 2.0602409638554215, + "grad_norm": 1.4934238633799322, + "learning_rate": 1.959896320156857e-05, + "loss": 4.0569, + "step": 285 + }, + { + "epoch": 2.067469879518072, + "grad_norm": 1.1757415076562812, + "learning_rate": 1.959600725963752e-05, + "loss": 3.9952, + "step": 286 + }, + { + "epoch": 2.0746987951807228, + "grad_norm": 1.5693536638143577, + "learning_rate": 1.959304068848142e-05, + "loss": 4.0489, + "step": 287 + }, + { + "epoch": 2.0819277108433734, + "grad_norm": 1.224291668036312, + "learning_rate": 1.9590063491386262e-05, + "loss": 4.0471, + "step": 288 + }, + { + "epoch": 2.089156626506024, + "grad_norm": 1.1290270781594147, + "learning_rate": 1.95870756716498e-05, + "loss": 4.0212, + "step": 289 + }, + { + "epoch": 2.0963855421686746, + "grad_norm": 1.894574752880013, + "learning_rate": 1.958407723258156e-05, + "loss": 4.0215, + "step": 290 + }, + { + "epoch": 2.103614457831325, + "grad_norm": 1.4980896883131283, + "learning_rate": 1.9581068177502826e-05, + "loss": 4.014, + "step": 291 + }, + { + "epoch": 2.1108433734939758, + "grad_norm": 1.4071538350431236, + "learning_rate": 1.9578048509746643e-05, + "loss": 3.9862, + "step": 292 + }, + { + "epoch": 2.1180722891566264, + "grad_norm": 1.3369928398838042, + "learning_rate": 1.9575018232657806e-05, + "loss": 4.0087, + "step": 293 + }, + { + "epoch": 2.125301204819277, + "grad_norm": 1.3725504314220875, + "learning_rate": 1.9571977349592878e-05, + "loss": 3.9819, + "step": 294 + }, + { + "epoch": 2.1325301204819276, + "grad_norm": 1.074883668514762, + "learning_rate": 1.9568925863920155e-05, + "loss": 3.9878, + "step": 295 + }, + { + "epoch": 2.139759036144578, + "grad_norm": 1.4617619796119823, + "learning_rate": 1.9565863779019675e-05, + "loss": 4.0011, + "step": 296 + }, + { + "epoch": 2.146987951807229, + "grad_norm": 1.295064754737287, + "learning_rate": 1.9562791098283226e-05, + "loss": 3.9857, + "step": 297 + }, + { + "epoch": 2.1542168674698794, + "grad_norm": 1.7198029396122985, + "learning_rate": 1.9559707825114334e-05, + "loss": 3.995, + "step": 298 + }, + { + "epoch": 2.16144578313253, + "grad_norm": 1.1877879145202288, + "learning_rate": 1.9556613962928244e-05, + "loss": 3.9518, + "step": 299 + }, + { + "epoch": 2.1686746987951806, + "grad_norm": 1.4041536368701515, + "learning_rate": 1.955350951515195e-05, + "loss": 3.9694, + "step": 300 + }, + { + "epoch": 2.175903614457831, + "grad_norm": 1.4632978460765673, + "learning_rate": 1.9550394485224154e-05, + "loss": 4.0008, + "step": 301 + }, + { + "epoch": 2.183132530120482, + "grad_norm": 1.179001588622081, + "learning_rate": 1.9547268876595286e-05, + "loss": 3.9742, + "step": 302 + }, + { + "epoch": 2.1903614457831324, + "grad_norm": 1.3424766923175933, + "learning_rate": 1.9544132692727497e-05, + "loss": 3.9582, + "step": 303 + }, + { + "epoch": 2.197590361445783, + "grad_norm": 1.44537054552251, + "learning_rate": 1.954098593709465e-05, + "loss": 3.9669, + "step": 304 + }, + { + "epoch": 2.2048192771084336, + "grad_norm": 1.2894995735637325, + "learning_rate": 1.9537828613182314e-05, + "loss": 3.9352, + "step": 305 + }, + { + "epoch": 2.212048192771084, + "grad_norm": 1.2191740632517898, + "learning_rate": 1.9534660724487766e-05, + "loss": 3.9462, + "step": 306 + }, + { + "epoch": 2.219277108433735, + "grad_norm": 1.2922608641871975, + "learning_rate": 1.953148227451999e-05, + "loss": 3.968, + "step": 307 + }, + { + "epoch": 2.2265060240963854, + "grad_norm": 1.4031391626334404, + "learning_rate": 1.952829326679966e-05, + "loss": 3.9203, + "step": 308 + }, + { + "epoch": 2.233734939759036, + "grad_norm": 1.3797106514946174, + "learning_rate": 1.9525093704859156e-05, + "loss": 3.9411, + "step": 309 + }, + { + "epoch": 2.2409638554216866, + "grad_norm": 1.2240686755095442, + "learning_rate": 1.9521883592242537e-05, + "loss": 3.8945, + "step": 310 + }, + { + "epoch": 2.2481927710843372, + "grad_norm": 1.359674903926122, + "learning_rate": 1.9518662932505554e-05, + "loss": 3.9592, + "step": 311 + }, + { + "epoch": 2.255421686746988, + "grad_norm": 0.8861545685501412, + "learning_rate": 1.9515431729215642e-05, + "loss": 3.9198, + "step": 312 + }, + { + "epoch": 2.2626506024096384, + "grad_norm": 1.486723607802486, + "learning_rate": 1.951218998595192e-05, + "loss": 3.9507, + "step": 313 + }, + { + "epoch": 2.269879518072289, + "grad_norm": 1.313871908419903, + "learning_rate": 1.950893770630516e-05, + "loss": 3.9217, + "step": 314 + }, + { + "epoch": 2.2771084337349397, + "grad_norm": 0.8836336304647858, + "learning_rate": 1.950567489387783e-05, + "loss": 3.9043, + "step": 315 + }, + { + "epoch": 2.2843373493975903, + "grad_norm": 1.1630419252591093, + "learning_rate": 1.9502401552284053e-05, + "loss": 3.9174, + "step": 316 + }, + { + "epoch": 2.291566265060241, + "grad_norm": 1.6191540917865768, + "learning_rate": 1.9499117685149617e-05, + "loss": 3.9032, + "step": 317 + }, + { + "epoch": 2.2987951807228915, + "grad_norm": 1.046430539809095, + "learning_rate": 1.9495823296111968e-05, + "loss": 3.9224, + "step": 318 + }, + { + "epoch": 2.306024096385542, + "grad_norm": 2.0316286942343846, + "learning_rate": 1.9492518388820204e-05, + "loss": 3.935, + "step": 319 + }, + { + "epoch": 2.3132530120481927, + "grad_norm": 0.7503307570466232, + "learning_rate": 1.9489202966935084e-05, + "loss": 3.8877, + "step": 320 + }, + { + "epoch": 2.3204819277108433, + "grad_norm": 2.195779504301335, + "learning_rate": 1.9485877034129e-05, + "loss": 3.9413, + "step": 321 + }, + { + "epoch": 2.327710843373494, + "grad_norm": 0.9316398409981106, + "learning_rate": 1.9482540594086e-05, + "loss": 3.8999, + "step": 322 + }, + { + "epoch": 2.3349397590361445, + "grad_norm": 1.869511574600292, + "learning_rate": 1.9479193650501756e-05, + "loss": 3.9171, + "step": 323 + }, + { + "epoch": 2.342168674698795, + "grad_norm": 1.1547734133448195, + "learning_rate": 1.947583620708359e-05, + "loss": 3.9078, + "step": 324 + }, + { + "epoch": 2.3493975903614457, + "grad_norm": 1.7976523987062796, + "learning_rate": 1.947246826755044e-05, + "loss": 3.9188, + "step": 325 + }, + { + "epoch": 2.3566265060240963, + "grad_norm": 1.3943533699571777, + "learning_rate": 1.9469089835632883e-05, + "loss": 3.8771, + "step": 326 + }, + { + "epoch": 2.363855421686747, + "grad_norm": 1.326917276516545, + "learning_rate": 1.946570091507311e-05, + "loss": 3.8827, + "step": 327 + }, + { + "epoch": 2.3710843373493975, + "grad_norm": 1.2430788981224146, + "learning_rate": 1.9462301509624933e-05, + "loss": 3.8734, + "step": 328 + }, + { + "epoch": 2.378313253012048, + "grad_norm": 1.5379553907088528, + "learning_rate": 1.9458891623053776e-05, + "loss": 3.9014, + "step": 329 + }, + { + "epoch": 2.3855421686746987, + "grad_norm": 1.2479691146217833, + "learning_rate": 1.945547125913667e-05, + "loss": 3.9109, + "step": 330 + }, + { + "epoch": 2.3927710843373493, + "grad_norm": 1.2398397651517286, + "learning_rate": 1.9452040421662263e-05, + "loss": 3.8697, + "step": 331 + }, + { + "epoch": 2.4, + "grad_norm": 1.1754621111943704, + "learning_rate": 1.9448599114430793e-05, + "loss": 3.8795, + "step": 332 + }, + { + "epoch": 2.4072289156626505, + "grad_norm": 1.3452310894880555, + "learning_rate": 1.9445147341254094e-05, + "loss": 3.8632, + "step": 333 + }, + { + "epoch": 2.414457831325301, + "grad_norm": 1.3656366008762484, + "learning_rate": 1.9441685105955605e-05, + "loss": 3.8541, + "step": 334 + }, + { + "epoch": 2.4216867469879517, + "grad_norm": 1.033093624385257, + "learning_rate": 1.943821241237034e-05, + "loss": 3.8198, + "step": 335 + }, + { + "epoch": 2.4289156626506023, + "grad_norm": 1.290188236529091, + "learning_rate": 1.94347292643449e-05, + "loss": 3.8341, + "step": 336 + }, + { + "epoch": 2.436144578313253, + "grad_norm": 1.2189948090841016, + "learning_rate": 1.943123566573748e-05, + "loss": 3.8599, + "step": 337 + }, + { + "epoch": 2.4433734939759035, + "grad_norm": 1.3522120356287177, + "learning_rate": 1.9427731620417832e-05, + "loss": 3.8676, + "step": 338 + }, + { + "epoch": 2.450602409638554, + "grad_norm": 1.293234164144659, + "learning_rate": 1.9424217132267287e-05, + "loss": 3.8229, + "step": 339 + }, + { + "epoch": 2.4578313253012047, + "grad_norm": 1.2407110746826315, + "learning_rate": 1.9420692205178753e-05, + "loss": 3.8536, + "step": 340 + }, + { + "epoch": 2.4650602409638553, + "grad_norm": 1.1831514740273819, + "learning_rate": 1.941715684305668e-05, + "loss": 3.8319, + "step": 341 + }, + { + "epoch": 2.472289156626506, + "grad_norm": 1.4909103135486783, + "learning_rate": 1.9413611049817098e-05, + "loss": 3.8408, + "step": 342 + }, + { + "epoch": 2.4795180722891565, + "grad_norm": 1.4697296716221555, + "learning_rate": 1.9410054829387577e-05, + "loss": 3.8168, + "step": 343 + }, + { + "epoch": 2.486746987951807, + "grad_norm": 1.3134233365354873, + "learning_rate": 1.940648818570724e-05, + "loss": 3.8229, + "step": 344 + }, + { + "epoch": 2.4939759036144578, + "grad_norm": 1.2481322084400526, + "learning_rate": 1.9402911122726756e-05, + "loss": 3.8271, + "step": 345 + }, + { + "epoch": 2.5012048192771084, + "grad_norm": 1.2353282699128232, + "learning_rate": 1.9399323644408343e-05, + "loss": 3.8442, + "step": 346 + }, + { + "epoch": 2.508433734939759, + "grad_norm": 1.3879510352014255, + "learning_rate": 1.9395725754725743e-05, + "loss": 3.8101, + "step": 347 + }, + { + "epoch": 2.5156626506024096, + "grad_norm": 1.2661019202378452, + "learning_rate": 1.939211745766424e-05, + "loss": 3.8343, + "step": 348 + }, + { + "epoch": 2.52289156626506, + "grad_norm": 1.4094304789617342, + "learning_rate": 1.938849875722064e-05, + "loss": 3.8225, + "step": 349 + }, + { + "epoch": 2.5301204819277108, + "grad_norm": 1.0676824726351448, + "learning_rate": 1.9384869657403277e-05, + "loss": 3.8148, + "step": 350 + }, + { + "epoch": 2.5373493975903614, + "grad_norm": 1.3083681717217666, + "learning_rate": 1.9381230162232e-05, + "loss": 3.8434, + "step": 351 + }, + { + "epoch": 2.544578313253012, + "grad_norm": 1.2325764419019432, + "learning_rate": 1.9377580275738173e-05, + "loss": 3.812, + "step": 352 + }, + { + "epoch": 2.5518072289156626, + "grad_norm": 1.3648434313844788, + "learning_rate": 1.9373920001964675e-05, + "loss": 3.8195, + "step": 353 + }, + { + "epoch": 2.559036144578313, + "grad_norm": 1.5083792667684395, + "learning_rate": 1.9370249344965884e-05, + "loss": 3.8391, + "step": 354 + }, + { + "epoch": 2.566265060240964, + "grad_norm": 1.0291949716161193, + "learning_rate": 1.9366568308807685e-05, + "loss": 3.8017, + "step": 355 + }, + { + "epoch": 2.5734939759036144, + "grad_norm": 1.5685196716178862, + "learning_rate": 1.9362876897567463e-05, + "loss": 3.8024, + "step": 356 + }, + { + "epoch": 2.580722891566265, + "grad_norm": 1.2942627306283834, + "learning_rate": 1.9359175115334077e-05, + "loss": 3.7885, + "step": 357 + }, + { + "epoch": 2.5879518072289156, + "grad_norm": 1.4645373990690937, + "learning_rate": 1.9355462966207895e-05, + "loss": 3.7797, + "step": 358 + }, + { + "epoch": 2.595180722891566, + "grad_norm": 1.2398186764780104, + "learning_rate": 1.9351740454300757e-05, + "loss": 3.7539, + "step": 359 + }, + { + "epoch": 2.602409638554217, + "grad_norm": 1.6059301916580724, + "learning_rate": 1.9348007583735985e-05, + "loss": 3.7835, + "step": 360 + }, + { + "epoch": 2.6096385542168674, + "grad_norm": 1.1561865019785784, + "learning_rate": 1.934426435864837e-05, + "loss": 3.777, + "step": 361 + }, + { + "epoch": 2.616867469879518, + "grad_norm": 1.6980059293390584, + "learning_rate": 1.9340510783184183e-05, + "loss": 3.7765, + "step": 362 + }, + { + "epoch": 2.6240963855421686, + "grad_norm": 1.0123067416195255, + "learning_rate": 1.9336746861501147e-05, + "loss": 3.7598, + "step": 363 + }, + { + "epoch": 2.6313253012048192, + "grad_norm": 1.673455267873693, + "learning_rate": 1.9332972597768457e-05, + "loss": 3.7805, + "step": 364 + }, + { + "epoch": 2.63855421686747, + "grad_norm": 1.0701597206020481, + "learning_rate": 1.9329187996166747e-05, + "loss": 3.7862, + "step": 365 + }, + { + "epoch": 2.6457831325301204, + "grad_norm": 1.7611784860019106, + "learning_rate": 1.9325393060888124e-05, + "loss": 3.7598, + "step": 366 + }, + { + "epoch": 2.653012048192771, + "grad_norm": 1.2398458219597617, + "learning_rate": 1.932158779613613e-05, + "loss": 3.768, + "step": 367 + }, + { + "epoch": 2.6602409638554216, + "grad_norm": 1.3462209809802463, + "learning_rate": 1.931777220612574e-05, + "loss": 3.7391, + "step": 368 + }, + { + "epoch": 2.6674698795180722, + "grad_norm": 1.3822586150711442, + "learning_rate": 1.9313946295083383e-05, + "loss": 3.7948, + "step": 369 + }, + { + "epoch": 2.674698795180723, + "grad_norm": 1.2896937317956254, + "learning_rate": 1.9310110067246905e-05, + "loss": 3.7446, + "step": 370 + }, + { + "epoch": 2.6819277108433734, + "grad_norm": 1.597748609201892, + "learning_rate": 1.9306263526865593e-05, + "loss": 3.7899, + "step": 371 + }, + { + "epoch": 2.689156626506024, + "grad_norm": 0.9887103404024649, + "learning_rate": 1.930240667820015e-05, + "loss": 3.7663, + "step": 372 + }, + { + "epoch": 2.6963855421686747, + "grad_norm": 1.479034639605643, + "learning_rate": 1.9298539525522698e-05, + "loss": 3.7601, + "step": 373 + }, + { + "epoch": 2.7036144578313253, + "grad_norm": 1.4800888826961993, + "learning_rate": 1.9294662073116768e-05, + "loss": 3.7695, + "step": 374 + }, + { + "epoch": 2.710843373493976, + "grad_norm": 1.2534099267746543, + "learning_rate": 1.9290774325277305e-05, + "loss": 3.747, + "step": 375 + }, + { + "epoch": 2.7180722891566265, + "grad_norm": 1.3056444769450586, + "learning_rate": 1.9286876286310663e-05, + "loss": 3.7368, + "step": 376 + }, + { + "epoch": 2.725301204819277, + "grad_norm": 1.1856236202724628, + "learning_rate": 1.9282967960534584e-05, + "loss": 3.7167, + "step": 377 + }, + { + "epoch": 2.7325301204819277, + "grad_norm": 1.151548092933736, + "learning_rate": 1.927904935227821e-05, + "loss": 3.7442, + "step": 378 + }, + { + "epoch": 2.7397590361445783, + "grad_norm": 1.8119770126998607, + "learning_rate": 1.927512046588207e-05, + "loss": 3.7437, + "step": 379 + }, + { + "epoch": 2.746987951807229, + "grad_norm": 1.2134322654005893, + "learning_rate": 1.9271181305698084e-05, + "loss": 3.7225, + "step": 380 + }, + { + "epoch": 2.7542168674698795, + "grad_norm": 1.6877025454737837, + "learning_rate": 1.926723187608955e-05, + "loss": 3.7445, + "step": 381 + }, + { + "epoch": 2.76144578313253, + "grad_norm": 1.1011325902712465, + "learning_rate": 1.9263272181431133e-05, + "loss": 3.7481, + "step": 382 + }, + { + "epoch": 2.7686746987951807, + "grad_norm": 1.5507791869887935, + "learning_rate": 1.9259302226108878e-05, + "loss": 3.7363, + "step": 383 + }, + { + "epoch": 2.7759036144578313, + "grad_norm": 1.1252933329680082, + "learning_rate": 1.9255322014520193e-05, + "loss": 3.7281, + "step": 384 + }, + { + "epoch": 2.783132530120482, + "grad_norm": 1.7448884917100538, + "learning_rate": 1.9251331551073843e-05, + "loss": 3.7347, + "step": 385 + }, + { + "epoch": 2.7903614457831325, + "grad_norm": 1.3167522856552092, + "learning_rate": 1.9247330840189948e-05, + "loss": 3.7262, + "step": 386 + }, + { + "epoch": 2.797590361445783, + "grad_norm": 1.2302348129154204, + "learning_rate": 1.924331988629999e-05, + "loss": 3.7248, + "step": 387 + }, + { + "epoch": 2.8048192771084337, + "grad_norm": 1.1716288708997376, + "learning_rate": 1.9239298693846783e-05, + "loss": 3.6978, + "step": 388 + }, + { + "epoch": 2.8120481927710843, + "grad_norm": 1.3724544034995316, + "learning_rate": 1.923526726728449e-05, + "loss": 3.7314, + "step": 389 + }, + { + "epoch": 2.819277108433735, + "grad_norm": 1.4480412852065119, + "learning_rate": 1.923122561107861e-05, + "loss": 3.7551, + "step": 390 + }, + { + "epoch": 2.8265060240963855, + "grad_norm": 1.004068176105684, + "learning_rate": 1.9227173729705962e-05, + "loss": 3.665, + "step": 391 + }, + { + "epoch": 2.833734939759036, + "grad_norm": 1.499032232612859, + "learning_rate": 1.9223111627654713e-05, + "loss": 3.7162, + "step": 392 + }, + { + "epoch": 2.8409638554216867, + "grad_norm": 1.3213003849841365, + "learning_rate": 1.921903930942433e-05, + "loss": 3.6653, + "step": 393 + }, + { + "epoch": 2.8481927710843373, + "grad_norm": 1.0692128354096737, + "learning_rate": 1.9214956779525605e-05, + "loss": 3.6982, + "step": 394 + }, + { + "epoch": 2.855421686746988, + "grad_norm": 1.6726385792325693, + "learning_rate": 1.9210864042480645e-05, + "loss": 3.6977, + "step": 395 + }, + { + "epoch": 2.8626506024096385, + "grad_norm": 1.2084768043267635, + "learning_rate": 1.920676110282285e-05, + "loss": 3.7059, + "step": 396 + }, + { + "epoch": 2.869879518072289, + "grad_norm": 1.1973676731876703, + "learning_rate": 1.9202647965096936e-05, + "loss": 3.6892, + "step": 397 + }, + { + "epoch": 2.8771084337349397, + "grad_norm": 1.7061815264302218, + "learning_rate": 1.919852463385891e-05, + "loss": 3.7393, + "step": 398 + }, + { + "epoch": 2.8843373493975903, + "grad_norm": 0.9603314248247711, + "learning_rate": 1.9194391113676066e-05, + "loss": 3.7312, + "step": 399 + }, + { + "epoch": 2.891566265060241, + "grad_norm": 1.2381539449289038, + "learning_rate": 1.9190247409126993e-05, + "loss": 3.6477, + "step": 400 + }, + { + "epoch": 2.8987951807228916, + "grad_norm": 1.4897933906972847, + "learning_rate": 1.9186093524801546e-05, + "loss": 3.6784, + "step": 401 + }, + { + "epoch": 2.906024096385542, + "grad_norm": 1.1132373553731765, + "learning_rate": 1.918192946530087e-05, + "loss": 3.6536, + "step": 402 + }, + { + "epoch": 2.9132530120481928, + "grad_norm": 1.3263129892692505, + "learning_rate": 1.917775523523737e-05, + "loss": 3.6956, + "step": 403 + }, + { + "epoch": 2.9204819277108434, + "grad_norm": 1.0680026924503008, + "learning_rate": 1.9173570839234735e-05, + "loss": 3.6553, + "step": 404 + }, + { + "epoch": 2.927710843373494, + "grad_norm": 1.4754538436442506, + "learning_rate": 1.916937628192789e-05, + "loss": 3.6432, + "step": 405 + }, + { + "epoch": 2.9349397590361446, + "grad_norm": 1.2479137486432985, + "learning_rate": 1.916517156796303e-05, + "loss": 3.6492, + "step": 406 + }, + { + "epoch": 2.942168674698795, + "grad_norm": 1.3365195210042529, + "learning_rate": 1.91609567019976e-05, + "loss": 3.6622, + "step": 407 + }, + { + "epoch": 2.9493975903614458, + "grad_norm": 1.2544818586873212, + "learning_rate": 1.9156731688700284e-05, + "loss": 3.6819, + "step": 408 + }, + { + "epoch": 2.9566265060240964, + "grad_norm": 1.2814859527796207, + "learning_rate": 1.9152496532751014e-05, + "loss": 3.6563, + "step": 409 + }, + { + "epoch": 2.963855421686747, + "grad_norm": 1.3272064954264093, + "learning_rate": 1.9148251238840947e-05, + "loss": 3.6581, + "step": 410 + }, + { + "epoch": 2.9710843373493976, + "grad_norm": 1.171014354368878, + "learning_rate": 1.9143995811672477e-05, + "loss": 3.637, + "step": 411 + }, + { + "epoch": 2.978313253012048, + "grad_norm": 1.7001876017529212, + "learning_rate": 1.913973025595922e-05, + "loss": 3.6431, + "step": 412 + }, + { + "epoch": 2.985542168674699, + "grad_norm": 1.0699675183248216, + "learning_rate": 1.913545457642601e-05, + "loss": 3.6085, + "step": 413 + }, + { + "epoch": 2.9927710843373494, + "grad_norm": 1.1416693812329064, + "learning_rate": 1.9131168777808898e-05, + "loss": 3.656, + "step": 414 + }, + { + "epoch": 3.0, + "grad_norm": 1.394313876963253, + "learning_rate": 1.9126872864855142e-05, + "loss": 3.625, + "step": 415 + }, + { + "epoch": 3.0072289156626506, + "grad_norm": 1.1937015014005639, + "learning_rate": 1.91225668423232e-05, + "loss": 3.6024, + "step": 416 + }, + { + "epoch": 3.014457831325301, + "grad_norm": 1.3445114911170963, + "learning_rate": 1.9118250714982733e-05, + "loss": 3.6236, + "step": 417 + }, + { + "epoch": 3.021686746987952, + "grad_norm": 1.7350644891144746, + "learning_rate": 1.911392448761459e-05, + "loss": 3.6218, + "step": 418 + }, + { + "epoch": 3.0289156626506024, + "grad_norm": 1.047365051789017, + "learning_rate": 1.910958816501081e-05, + "loss": 3.6287, + "step": 419 + }, + { + "epoch": 3.036144578313253, + "grad_norm": 1.7055691742758698, + "learning_rate": 1.9105241751974624e-05, + "loss": 3.5951, + "step": 420 + }, + { + "epoch": 3.0433734939759036, + "grad_norm": 1.0364220044160384, + "learning_rate": 1.910088525332042e-05, + "loss": 3.5828, + "step": 421 + }, + { + "epoch": 3.0506024096385542, + "grad_norm": 1.94317043809307, + "learning_rate": 1.9096518673873773e-05, + "loss": 3.6355, + "step": 422 + }, + { + "epoch": 3.057831325301205, + "grad_norm": 1.096628442648723, + "learning_rate": 1.9092142018471415e-05, + "loss": 3.5654, + "step": 423 + }, + { + "epoch": 3.0650602409638554, + "grad_norm": 1.8943159764104194, + "learning_rate": 1.9087755291961246e-05, + "loss": 3.5896, + "step": 424 + }, + { + "epoch": 3.072289156626506, + "grad_norm": 1.4605008938774497, + "learning_rate": 1.9083358499202323e-05, + "loss": 3.6443, + "step": 425 + }, + { + "epoch": 3.0795180722891566, + "grad_norm": 1.199002982548527, + "learning_rate": 1.9078951645064837e-05, + "loss": 3.6156, + "step": 426 + }, + { + "epoch": 3.0867469879518072, + "grad_norm": 1.3737048491463308, + "learning_rate": 1.9074534734430147e-05, + "loss": 3.5969, + "step": 427 + }, + { + "epoch": 3.093975903614458, + "grad_norm": 1.1507142428566965, + "learning_rate": 1.9070107772190734e-05, + "loss": 3.6112, + "step": 428 + }, + { + "epoch": 3.1012048192771084, + "grad_norm": 1.4622624757116582, + "learning_rate": 1.906567076325022e-05, + "loss": 3.6137, + "step": 429 + }, + { + "epoch": 3.108433734939759, + "grad_norm": 1.3627701895130038, + "learning_rate": 1.9061223712523352e-05, + "loss": 3.5957, + "step": 430 + }, + { + "epoch": 3.1156626506024097, + "grad_norm": 1.0700877019696842, + "learning_rate": 1.9056766624936003e-05, + "loss": 3.5863, + "step": 431 + }, + { + "epoch": 3.1228915662650603, + "grad_norm": 1.5955208448573346, + "learning_rate": 1.9052299505425164e-05, + "loss": 3.587, + "step": 432 + }, + { + "epoch": 3.130120481927711, + "grad_norm": 1.3565000081916603, + "learning_rate": 1.9047822358938933e-05, + "loss": 3.6409, + "step": 433 + }, + { + "epoch": 3.1373493975903615, + "grad_norm": 0.8840912550967165, + "learning_rate": 1.904333519043652e-05, + "loss": 3.5647, + "step": 434 + }, + { + "epoch": 3.144578313253012, + "grad_norm": 1.3572343135153577, + "learning_rate": 1.903883800488824e-05, + "loss": 3.6011, + "step": 435 + }, + { + "epoch": 3.1518072289156627, + "grad_norm": 1.2429040148925297, + "learning_rate": 1.9034330807275484e-05, + "loss": 3.5839, + "step": 436 + }, + { + "epoch": 3.1590361445783133, + "grad_norm": 1.4800542337109683, + "learning_rate": 1.9029813602590763e-05, + "loss": 3.5555, + "step": 437 + }, + { + "epoch": 3.166265060240964, + "grad_norm": 1.6482800246580644, + "learning_rate": 1.9025286395837647e-05, + "loss": 3.5884, + "step": 438 + }, + { + "epoch": 3.1734939759036145, + "grad_norm": 1.0501732415023106, + "learning_rate": 1.9020749192030795e-05, + "loss": 3.5781, + "step": 439 + }, + { + "epoch": 3.180722891566265, + "grad_norm": 1.5328073640134885, + "learning_rate": 1.9016201996195943e-05, + "loss": 3.5548, + "step": 440 + }, + { + "epoch": 3.1879518072289157, + "grad_norm": 1.118507184933988, + "learning_rate": 1.9011644813369886e-05, + "loss": 3.5596, + "step": 441 + }, + { + "epoch": 3.1951807228915663, + "grad_norm": 1.2284264310864856, + "learning_rate": 1.900707764860049e-05, + "loss": 3.5657, + "step": 442 + }, + { + "epoch": 3.202409638554217, + "grad_norm": 1.5003452370811305, + "learning_rate": 1.900250050694667e-05, + "loss": 3.5662, + "step": 443 + }, + { + "epoch": 3.2096385542168675, + "grad_norm": 1.2853868444977676, + "learning_rate": 1.8997913393478404e-05, + "loss": 3.5712, + "step": 444 + }, + { + "epoch": 3.216867469879518, + "grad_norm": 1.5925034895130508, + "learning_rate": 1.8993316313276694e-05, + "loss": 3.5776, + "step": 445 + }, + { + "epoch": 3.2240963855421687, + "grad_norm": 0.9811616125028083, + "learning_rate": 1.8988709271433607e-05, + "loss": 3.5428, + "step": 446 + }, + { + "epoch": 3.2313253012048193, + "grad_norm": 1.4478536151263606, + "learning_rate": 1.898409227305223e-05, + "loss": 3.5508, + "step": 447 + }, + { + "epoch": 3.23855421686747, + "grad_norm": 1.2477828448918005, + "learning_rate": 1.8979465323246676e-05, + "loss": 3.5611, + "step": 448 + }, + { + "epoch": 3.2457831325301205, + "grad_norm": 1.5858711129317897, + "learning_rate": 1.8974828427142093e-05, + "loss": 3.5629, + "step": 449 + }, + { + "epoch": 3.253012048192771, + "grad_norm": 1.0950035377608183, + "learning_rate": 1.8970181589874637e-05, + "loss": 3.5406, + "step": 450 + }, + { + "epoch": 3.2602409638554217, + "grad_norm": 1.5415115226682654, + "learning_rate": 1.8965524816591477e-05, + "loss": 3.5606, + "step": 451 + }, + { + "epoch": 3.2674698795180723, + "grad_norm": 1.1487484478951757, + "learning_rate": 1.8960858112450785e-05, + "loss": 3.5166, + "step": 452 + }, + { + "epoch": 3.274698795180723, + "grad_norm": 1.6420967703083962, + "learning_rate": 1.8956181482621746e-05, + "loss": 3.528, + "step": 453 + }, + { + "epoch": 3.2819277108433735, + "grad_norm": 0.8980303432743649, + "learning_rate": 1.895149493228452e-05, + "loss": 3.5287, + "step": 454 + }, + { + "epoch": 3.289156626506024, + "grad_norm": 1.3483910988264465, + "learning_rate": 1.894679846663027e-05, + "loss": 3.5731, + "step": 455 + }, + { + "epoch": 3.2963855421686747, + "grad_norm": 1.491314706003945, + "learning_rate": 1.894209209086114e-05, + "loss": 3.5231, + "step": 456 + }, + { + "epoch": 3.3036144578313253, + "grad_norm": 1.2270834009390768, + "learning_rate": 1.8937375810190247e-05, + "loss": 3.5386, + "step": 457 + }, + { + "epoch": 3.310843373493976, + "grad_norm": 1.1777132337252105, + "learning_rate": 1.8932649629841685e-05, + "loss": 3.5111, + "step": 458 + }, + { + "epoch": 3.3180722891566266, + "grad_norm": 1.3783327375707983, + "learning_rate": 1.8927913555050503e-05, + "loss": 3.5123, + "step": 459 + }, + { + "epoch": 3.325301204819277, + "grad_norm": 0.842194772816192, + "learning_rate": 1.8923167591062723e-05, + "loss": 3.5513, + "step": 460 + }, + { + "epoch": 3.3325301204819278, + "grad_norm": 1.3331154478098168, + "learning_rate": 1.891841174313531e-05, + "loss": 3.5017, + "step": 461 + }, + { + "epoch": 3.3397590361445784, + "grad_norm": 1.5139276628552356, + "learning_rate": 1.8913646016536184e-05, + "loss": 3.5145, + "step": 462 + }, + { + "epoch": 3.346987951807229, + "grad_norm": 1.1149277809499802, + "learning_rate": 1.8908870416544202e-05, + "loss": 3.5004, + "step": 463 + }, + { + "epoch": 3.3542168674698796, + "grad_norm": 1.4898157461888148, + "learning_rate": 1.890408494844917e-05, + "loss": 3.5329, + "step": 464 + }, + { + "epoch": 3.36144578313253, + "grad_norm": 0.9549742540395183, + "learning_rate": 1.8899289617551803e-05, + "loss": 3.5187, + "step": 465 + }, + { + "epoch": 3.3686746987951808, + "grad_norm": 1.7805688799594914, + "learning_rate": 1.8894484429163764e-05, + "loss": 3.5207, + "step": 466 + }, + { + "epoch": 3.3759036144578314, + "grad_norm": 1.2106962876906113, + "learning_rate": 1.8889669388607615e-05, + "loss": 3.514, + "step": 467 + }, + { + "epoch": 3.383132530120482, + "grad_norm": 1.6763747112024485, + "learning_rate": 1.8884844501216845e-05, + "loss": 3.5147, + "step": 468 + }, + { + "epoch": 3.3903614457831326, + "grad_norm": 1.031632991874722, + "learning_rate": 1.8880009772335843e-05, + "loss": 3.5116, + "step": 469 + }, + { + "epoch": 3.397590361445783, + "grad_norm": 1.8307621258883875, + "learning_rate": 1.8875165207319902e-05, + "loss": 3.5397, + "step": 470 + }, + { + "epoch": 3.404819277108434, + "grad_norm": 1.2852387998358652, + "learning_rate": 1.8870310811535208e-05, + "loss": 3.5036, + "step": 471 + }, + { + "epoch": 3.4120481927710844, + "grad_norm": 1.406175754082574, + "learning_rate": 1.886544659035884e-05, + "loss": 3.5133, + "step": 472 + }, + { + "epoch": 3.419277108433735, + "grad_norm": 1.4308043920793336, + "learning_rate": 1.8860572549178755e-05, + "loss": 3.5003, + "step": 473 + }, + { + "epoch": 3.4265060240963856, + "grad_norm": 1.161805161480239, + "learning_rate": 1.8855688693393788e-05, + "loss": 3.5061, + "step": 474 + }, + { + "epoch": 3.433734939759036, + "grad_norm": 1.3056601266916144, + "learning_rate": 1.8850795028413658e-05, + "loss": 3.4847, + "step": 475 + }, + { + "epoch": 3.440963855421687, + "grad_norm": 1.5521465688683451, + "learning_rate": 1.8845891559658925e-05, + "loss": 3.496, + "step": 476 + }, + { + "epoch": 3.4481927710843374, + "grad_norm": 1.1070668015919285, + "learning_rate": 1.884097829256103e-05, + "loss": 3.5009, + "step": 477 + }, + { + "epoch": 3.455421686746988, + "grad_norm": 1.3329315835553603, + "learning_rate": 1.883605523256226e-05, + "loss": 3.4943, + "step": 478 + }, + { + "epoch": 3.4626506024096386, + "grad_norm": 1.5538331615869527, + "learning_rate": 1.883112238511575e-05, + "loss": 3.4837, + "step": 479 + }, + { + "epoch": 3.4698795180722892, + "grad_norm": 1.092373343461448, + "learning_rate": 1.882617975568547e-05, + "loss": 3.4926, + "step": 480 + }, + { + "epoch": 3.47710843373494, + "grad_norm": 1.874379766491242, + "learning_rate": 1.8821227349746235e-05, + "loss": 3.4899, + "step": 481 + }, + { + "epoch": 3.4843373493975904, + "grad_norm": 0.9923448678530435, + "learning_rate": 1.881626517278368e-05, + "loss": 3.4728, + "step": 482 + }, + { + "epoch": 3.491566265060241, + "grad_norm": 1.2266774334839128, + "learning_rate": 1.881129323029427e-05, + "loss": 3.4892, + "step": 483 + }, + { + "epoch": 3.4987951807228916, + "grad_norm": 1.5096151923346919, + "learning_rate": 1.8806311527785287e-05, + "loss": 3.5182, + "step": 484 + }, + { + "epoch": 3.5060240963855422, + "grad_norm": 1.1571956260425034, + "learning_rate": 1.880132007077482e-05, + "loss": 3.4708, + "step": 485 + }, + { + "epoch": 3.513253012048193, + "grad_norm": 1.648444159789046, + "learning_rate": 1.8796318864791763e-05, + "loss": 3.4952, + "step": 486 + }, + { + "epoch": 3.5204819277108435, + "grad_norm": 1.093285229500888, + "learning_rate": 1.879130791537581e-05, + "loss": 3.4968, + "step": 487 + }, + { + "epoch": 3.527710843373494, + "grad_norm": 1.6721766885025302, + "learning_rate": 1.8786287228077453e-05, + "loss": 3.4886, + "step": 488 + }, + { + "epoch": 3.5349397590361447, + "grad_norm": 1.0756493747079099, + "learning_rate": 1.8781256808457954e-05, + "loss": 3.4859, + "step": 489 + }, + { + "epoch": 3.5421686746987953, + "grad_norm": 1.5147018364957974, + "learning_rate": 1.8776216662089373e-05, + "loss": 3.4958, + "step": 490 + }, + { + "epoch": 3.549397590361446, + "grad_norm": 1.3158687997204326, + "learning_rate": 1.8771166794554544e-05, + "loss": 3.5135, + "step": 491 + }, + { + "epoch": 3.5566265060240965, + "grad_norm": 1.519976844773512, + "learning_rate": 1.8766107211447046e-05, + "loss": 3.4772, + "step": 492 + }, + { + "epoch": 3.563855421686747, + "grad_norm": 1.1141857128087669, + "learning_rate": 1.8761037918371248e-05, + "loss": 3.4985, + "step": 493 + }, + { + "epoch": 3.5710843373493977, + "grad_norm": 1.4826112621775518, + "learning_rate": 1.875595892094226e-05, + "loss": 3.4615, + "step": 494 + }, + { + "epoch": 3.5783132530120483, + "grad_norm": 1.4123308003869872, + "learning_rate": 1.875087022478594e-05, + "loss": 3.464, + "step": 495 + }, + { + "epoch": 3.585542168674699, + "grad_norm": 1.290374316443633, + "learning_rate": 1.8745771835538893e-05, + "loss": 3.4795, + "step": 496 + }, + { + "epoch": 3.5927710843373495, + "grad_norm": 1.2931656378131897, + "learning_rate": 1.8740663758848463e-05, + "loss": 3.4812, + "step": 497 + }, + { + "epoch": 3.6, + "grad_norm": 1.023375443616966, + "learning_rate": 1.873554600037272e-05, + "loss": 3.471, + "step": 498 + }, + { + "epoch": 3.6072289156626507, + "grad_norm": 1.8081312761107482, + "learning_rate": 1.873041856578046e-05, + "loss": 3.4738, + "step": 499 + }, + { + "epoch": 3.6144578313253013, + "grad_norm": 1.0288627689254883, + "learning_rate": 1.8725281460751198e-05, + "loss": 3.4398, + "step": 500 + }, + { + "epoch": 3.621686746987952, + "grad_norm": 1.5832162058004138, + "learning_rate": 1.8720134690975157e-05, + "loss": 3.4424, + "step": 501 + }, + { + "epoch": 3.6289156626506025, + "grad_norm": 1.3177178077765743, + "learning_rate": 1.8714978262153268e-05, + "loss": 3.4589, + "step": 502 + }, + { + "epoch": 3.636144578313253, + "grad_norm": 1.0363297002224263, + "learning_rate": 1.8709812179997162e-05, + "loss": 3.4862, + "step": 503 + }, + { + "epoch": 3.6433734939759037, + "grad_norm": 1.4795903294105097, + "learning_rate": 1.8704636450229164e-05, + "loss": 3.4501, + "step": 504 + }, + { + "epoch": 3.6506024096385543, + "grad_norm": 1.3966788968436568, + "learning_rate": 1.869945107858228e-05, + "loss": 3.4638, + "step": 505 + }, + { + "epoch": 3.657831325301205, + "grad_norm": 1.1325789827684314, + "learning_rate": 1.8694256070800202e-05, + "loss": 3.4599, + "step": 506 + }, + { + "epoch": 3.6650602409638555, + "grad_norm": 1.5981674695873835, + "learning_rate": 1.868905143263729e-05, + "loss": 3.4762, + "step": 507 + }, + { + "epoch": 3.672289156626506, + "grad_norm": 1.1727596332947487, + "learning_rate": 1.8683837169858573e-05, + "loss": 3.4592, + "step": 508 + }, + { + "epoch": 3.6795180722891567, + "grad_norm": 1.3675155550509581, + "learning_rate": 1.8678613288239745e-05, + "loss": 3.4125, + "step": 509 + }, + { + "epoch": 3.6867469879518073, + "grad_norm": 1.4041957545233883, + "learning_rate": 1.867337979356715e-05, + "loss": 3.4293, + "step": 510 + }, + { + "epoch": 3.693975903614458, + "grad_norm": 1.3560113123509387, + "learning_rate": 1.866813669163778e-05, + "loss": 3.4508, + "step": 511 + }, + { + "epoch": 3.7012048192771085, + "grad_norm": 1.1545842984692207, + "learning_rate": 1.8662883988259276e-05, + "loss": 3.4248, + "step": 512 + }, + { + "epoch": 3.708433734939759, + "grad_norm": 1.2992676256754951, + "learning_rate": 1.86576216892499e-05, + "loss": 3.4531, + "step": 513 + }, + { + "epoch": 3.7156626506024097, + "grad_norm": 1.8499772386187696, + "learning_rate": 1.8652349800438558e-05, + "loss": 3.4513, + "step": 514 + }, + { + "epoch": 3.7228915662650603, + "grad_norm": 1.02374620550504, + "learning_rate": 1.8647068327664774e-05, + "loss": 3.4277, + "step": 515 + }, + { + "epoch": 3.730120481927711, + "grad_norm": 1.6630005224882898, + "learning_rate": 1.8641777276778677e-05, + "loss": 3.4379, + "step": 516 + }, + { + "epoch": 3.7373493975903616, + "grad_norm": 1.0239537219245924, + "learning_rate": 1.8636476653641015e-05, + "loss": 3.441, + "step": 517 + }, + { + "epoch": 3.744578313253012, + "grad_norm": 1.452754740516667, + "learning_rate": 1.8631166464123147e-05, + "loss": 3.4094, + "step": 518 + }, + { + "epoch": 3.7518072289156628, + "grad_norm": 1.1575160234867263, + "learning_rate": 1.8625846714107013e-05, + "loss": 3.4469, + "step": 519 + }, + { + "epoch": 3.7590361445783134, + "grad_norm": 1.8402168349048114, + "learning_rate": 1.8620517409485148e-05, + "loss": 3.4152, + "step": 520 + }, + { + "epoch": 3.766265060240964, + "grad_norm": 0.9286315933247561, + "learning_rate": 1.8615178556160675e-05, + "loss": 3.4106, + "step": 521 + }, + { + "epoch": 3.7734939759036146, + "grad_norm": 1.7068898144657225, + "learning_rate": 1.8609830160047283e-05, + "loss": 3.4277, + "step": 522 + }, + { + "epoch": 3.780722891566265, + "grad_norm": 1.3543309281771512, + "learning_rate": 1.8604472227069253e-05, + "loss": 3.4126, + "step": 523 + }, + { + "epoch": 3.787951807228916, + "grad_norm": 0.8836248770013484, + "learning_rate": 1.8599104763161402e-05, + "loss": 3.3996, + "step": 524 + }, + { + "epoch": 3.7951807228915664, + "grad_norm": 1.104673956712585, + "learning_rate": 1.8593727774269122e-05, + "loss": 3.4098, + "step": 525 + }, + { + "epoch": 3.802409638554217, + "grad_norm": 1.3914713972311137, + "learning_rate": 1.858834126634835e-05, + "loss": 3.4337, + "step": 526 + }, + { + "epoch": 3.8096385542168676, + "grad_norm": 1.4164106405394201, + "learning_rate": 1.8582945245365574e-05, + "loss": 3.4169, + "step": 527 + }, + { + "epoch": 3.816867469879518, + "grad_norm": 1.3207121109028854, + "learning_rate": 1.8577539717297806e-05, + "loss": 3.4247, + "step": 528 + }, + { + "epoch": 3.824096385542169, + "grad_norm": 1.4858975363520965, + "learning_rate": 1.85721246881326e-05, + "loss": 3.4251, + "step": 529 + }, + { + "epoch": 3.8313253012048194, + "grad_norm": 1.0773614825733793, + "learning_rate": 1.8566700163868027e-05, + "loss": 3.438, + "step": 530 + }, + { + "epoch": 3.83855421686747, + "grad_norm": 1.5240572802175603, + "learning_rate": 1.856126615051268e-05, + "loss": 3.3856, + "step": 531 + }, + { + "epoch": 3.8457831325301206, + "grad_norm": 1.212618647930279, + "learning_rate": 1.8555822654085665e-05, + "loss": 3.3794, + "step": 532 + }, + { + "epoch": 3.853012048192771, + "grad_norm": 1.3089580322466006, + "learning_rate": 1.8550369680616584e-05, + "loss": 3.3856, + "step": 533 + }, + { + "epoch": 3.860240963855422, + "grad_norm": 1.294624288123662, + "learning_rate": 1.854490723614554e-05, + "loss": 3.4072, + "step": 534 + }, + { + "epoch": 3.8674698795180724, + "grad_norm": 1.4162512393718127, + "learning_rate": 1.8539435326723135e-05, + "loss": 3.3985, + "step": 535 + }, + { + "epoch": 3.874698795180723, + "grad_norm": 1.5646417878212386, + "learning_rate": 1.853395395841044e-05, + "loss": 3.4295, + "step": 536 + }, + { + "epoch": 3.8819277108433736, + "grad_norm": 0.986716262091348, + "learning_rate": 1.852846313727902e-05, + "loss": 3.379, + "step": 537 + }, + { + "epoch": 3.8891566265060242, + "grad_norm": 1.4476864853119071, + "learning_rate": 1.852296286941089e-05, + "loss": 3.4318, + "step": 538 + }, + { + "epoch": 3.896385542168675, + "grad_norm": 1.336789866057074, + "learning_rate": 1.851745316089855e-05, + "loss": 3.3884, + "step": 539 + }, + { + "epoch": 3.9036144578313254, + "grad_norm": 1.5594590122697878, + "learning_rate": 1.851193401784495e-05, + "loss": 3.4078, + "step": 540 + }, + { + "epoch": 3.910843373493976, + "grad_norm": 1.217821216453777, + "learning_rate": 1.8506405446363476e-05, + "loss": 3.3646, + "step": 541 + }, + { + "epoch": 3.9180722891566266, + "grad_norm": 1.5654916960235976, + "learning_rate": 1.8500867452577978e-05, + "loss": 3.4169, + "step": 542 + }, + { + "epoch": 3.9253012048192772, + "grad_norm": 1.0290965394229443, + "learning_rate": 1.849532004262274e-05, + "loss": 3.4067, + "step": 543 + }, + { + "epoch": 3.932530120481928, + "grad_norm": 1.4367792614004797, + "learning_rate": 1.8489763222642457e-05, + "loss": 3.3943, + "step": 544 + }, + { + "epoch": 3.9397590361445785, + "grad_norm": 1.038088226531718, + "learning_rate": 1.848419699879227e-05, + "loss": 3.3621, + "step": 545 + }, + { + "epoch": 3.946987951807229, + "grad_norm": 1.6594075535521433, + "learning_rate": 1.8478621377237724e-05, + "loss": 3.3758, + "step": 546 + }, + { + "epoch": 3.9542168674698797, + "grad_norm": 1.100843923400257, + "learning_rate": 1.847303636415478e-05, + "loss": 3.4082, + "step": 547 + }, + { + "epoch": 3.9614457831325303, + "grad_norm": 1.30799271344962, + "learning_rate": 1.8467441965729796e-05, + "loss": 3.3983, + "step": 548 + }, + { + "epoch": 3.968674698795181, + "grad_norm": 1.0064869104717655, + "learning_rate": 1.846183818815953e-05, + "loss": 3.3768, + "step": 549 + }, + { + "epoch": 3.9759036144578315, + "grad_norm": 1.9019272157678964, + "learning_rate": 1.845622503765113e-05, + "loss": 3.3945, + "step": 550 + }, + { + "epoch": 3.983132530120482, + "grad_norm": 0.8834203829363729, + "learning_rate": 1.8450602520422113e-05, + "loss": 3.3691, + "step": 551 + }, + { + "epoch": 3.9903614457831327, + "grad_norm": 1.5879949736683259, + "learning_rate": 1.8444970642700396e-05, + "loss": 3.3763, + "step": 552 + }, + { + "epoch": 3.9975903614457833, + "grad_norm": 1.417799256266747, + "learning_rate": 1.843932941072424e-05, + "loss": 3.3897, + "step": 553 + }, + { + "epoch": 4.004819277108433, + "grad_norm": 1.268057538537551, + "learning_rate": 1.8433678830742284e-05, + "loss": 3.3272, + "step": 554 + }, + { + "epoch": 4.0120481927710845, + "grad_norm": 1.484719882690862, + "learning_rate": 1.842801890901351e-05, + "loss": 3.367, + "step": 555 + }, + { + "epoch": 4.019277108433735, + "grad_norm": 1.2643656531559433, + "learning_rate": 1.842234965180725e-05, + "loss": 3.3467, + "step": 556 + }, + { + "epoch": 4.026506024096386, + "grad_norm": 1.7452752799634084, + "learning_rate": 1.841667106540319e-05, + "loss": 3.3538, + "step": 557 + }, + { + "epoch": 4.033734939759036, + "grad_norm": 1.079426848592131, + "learning_rate": 1.8410983156091334e-05, + "loss": 3.3437, + "step": 558 + }, + { + "epoch": 4.040963855421687, + "grad_norm": 1.8083444736473766, + "learning_rate": 1.8405285930172016e-05, + "loss": 3.3492, + "step": 559 + }, + { + "epoch": 4.048192771084337, + "grad_norm": 1.2699753552523099, + "learning_rate": 1.8399579393955893e-05, + "loss": 3.3249, + "step": 560 + }, + { + "epoch": 4.055421686746988, + "grad_norm": 1.400246092211567, + "learning_rate": 1.839386355376393e-05, + "loss": 3.3767, + "step": 561 + }, + { + "epoch": 4.062650602409638, + "grad_norm": 1.244251569866778, + "learning_rate": 1.838813841592741e-05, + "loss": 3.2968, + "step": 562 + }, + { + "epoch": 4.069879518072289, + "grad_norm": 1.5584023465055492, + "learning_rate": 1.8382403986787895e-05, + "loss": 3.3499, + "step": 563 + }, + { + "epoch": 4.0771084337349395, + "grad_norm": 1.0765855271037599, + "learning_rate": 1.8376660272697257e-05, + "loss": 3.3528, + "step": 564 + }, + { + "epoch": 4.0843373493975905, + "grad_norm": 1.5570491879229293, + "learning_rate": 1.837090728001764e-05, + "loss": 3.3208, + "step": 565 + }, + { + "epoch": 4.091566265060241, + "grad_norm": 1.157602436803469, + "learning_rate": 1.8365145015121477e-05, + "loss": 3.3533, + "step": 566 + }, + { + "epoch": 4.098795180722892, + "grad_norm": 1.6099172851284775, + "learning_rate": 1.835937348439146e-05, + "loss": 3.3203, + "step": 567 + }, + { + "epoch": 4.106024096385542, + "grad_norm": 1.5490215318502463, + "learning_rate": 1.835359269422055e-05, + "loss": 3.3612, + "step": 568 + }, + { + "epoch": 4.113253012048193, + "grad_norm": 0.8911556352082233, + "learning_rate": 1.8347802651011965e-05, + "loss": 3.2801, + "step": 569 + }, + { + "epoch": 4.120481927710843, + "grad_norm": 1.6677145666770425, + "learning_rate": 1.834200336117918e-05, + "loss": 3.3293, + "step": 570 + }, + { + "epoch": 4.127710843373494, + "grad_norm": 1.3171442358917278, + "learning_rate": 1.8336194831145888e-05, + "loss": 3.3275, + "step": 571 + }, + { + "epoch": 4.134939759036144, + "grad_norm": 1.1299184058969571, + "learning_rate": 1.8330377067346045e-05, + "loss": 3.3105, + "step": 572 + }, + { + "epoch": 4.142168674698795, + "grad_norm": 1.2163200316102576, + "learning_rate": 1.8324550076223818e-05, + "loss": 3.3086, + "step": 573 + }, + { + "epoch": 4.1493975903614455, + "grad_norm": 1.4252511237340142, + "learning_rate": 1.83187138642336e-05, + "loss": 3.3388, + "step": 574 + }, + { + "epoch": 4.156626506024097, + "grad_norm": 1.3132028148730224, + "learning_rate": 1.8312868437840002e-05, + "loss": 3.3009, + "step": 575 + }, + { + "epoch": 4.163855421686747, + "grad_norm": 1.1629824196249723, + "learning_rate": 1.8307013803517834e-05, + "loss": 3.2775, + "step": 576 + }, + { + "epoch": 4.171084337349398, + "grad_norm": 1.5011239726999521, + "learning_rate": 1.8301149967752104e-05, + "loss": 3.3308, + "step": 577 + }, + { + "epoch": 4.178313253012048, + "grad_norm": 1.4397390142744335, + "learning_rate": 1.8295276937038023e-05, + "loss": 3.2927, + "step": 578 + }, + { + "epoch": 4.185542168674699, + "grad_norm": 1.2349876041301024, + "learning_rate": 1.8289394717880977e-05, + "loss": 3.3274, + "step": 579 + }, + { + "epoch": 4.192771084337349, + "grad_norm": 1.3027251020995771, + "learning_rate": 1.8283503316796536e-05, + "loss": 3.3363, + "step": 580 + }, + { + "epoch": 4.2, + "grad_norm": 1.2802765485296743, + "learning_rate": 1.8277602740310433e-05, + "loss": 3.3138, + "step": 581 + }, + { + "epoch": 4.20722891566265, + "grad_norm": 1.5672452547403777, + "learning_rate": 1.8271692994958576e-05, + "loss": 3.311, + "step": 582 + }, + { + "epoch": 4.214457831325301, + "grad_norm": 1.2976733074790296, + "learning_rate": 1.8265774087287016e-05, + "loss": 3.2846, + "step": 583 + }, + { + "epoch": 4.2216867469879515, + "grad_norm": 1.4144637634643196, + "learning_rate": 1.825984602385196e-05, + "loss": 3.3297, + "step": 584 + }, + { + "epoch": 4.228915662650603, + "grad_norm": 1.1749959337917693, + "learning_rate": 1.8253908811219764e-05, + "loss": 3.3001, + "step": 585 + }, + { + "epoch": 4.236144578313253, + "grad_norm": 1.4039885634229308, + "learning_rate": 1.82479624559669e-05, + "loss": 3.3219, + "step": 586 + }, + { + "epoch": 4.243373493975904, + "grad_norm": 1.212164693294027, + "learning_rate": 1.8242006964679978e-05, + "loss": 3.2915, + "step": 587 + }, + { + "epoch": 4.250602409638554, + "grad_norm": 1.2485625997266088, + "learning_rate": 1.8236042343955734e-05, + "loss": 3.2814, + "step": 588 + }, + { + "epoch": 4.257831325301205, + "grad_norm": 1.2830218516375618, + "learning_rate": 1.8230068600401e-05, + "loss": 3.2821, + "step": 589 + }, + { + "epoch": 4.265060240963855, + "grad_norm": 1.366157342834461, + "learning_rate": 1.822408574063273e-05, + "loss": 3.2994, + "step": 590 + }, + { + "epoch": 4.272289156626506, + "grad_norm": 1.3861702655842194, + "learning_rate": 1.8218093771277965e-05, + "loss": 3.292, + "step": 591 + }, + { + "epoch": 4.279518072289156, + "grad_norm": 1.2538740015004524, + "learning_rate": 1.8212092698973837e-05, + "loss": 3.3082, + "step": 592 + }, + { + "epoch": 4.286746987951807, + "grad_norm": 1.3134983549799732, + "learning_rate": 1.820608253036757e-05, + "loss": 3.2543, + "step": 593 + }, + { + "epoch": 4.293975903614458, + "grad_norm": 1.0874207166004457, + "learning_rate": 1.820006327211645e-05, + "loss": 3.2682, + "step": 594 + }, + { + "epoch": 4.301204819277109, + "grad_norm": 1.3562305588386105, + "learning_rate": 1.8194034930887842e-05, + "loss": 3.2865, + "step": 595 + }, + { + "epoch": 4.308433734939759, + "grad_norm": 1.1232485868536217, + "learning_rate": 1.818799751335917e-05, + "loss": 3.2844, + "step": 596 + }, + { + "epoch": 4.31566265060241, + "grad_norm": 1.4011009500618496, + "learning_rate": 1.8181951026217908e-05, + "loss": 3.3233, + "step": 597 + }, + { + "epoch": 4.32289156626506, + "grad_norm": 1.0020226275410233, + "learning_rate": 1.8175895476161577e-05, + "loss": 3.3181, + "step": 598 + }, + { + "epoch": 4.330120481927711, + "grad_norm": 1.3938263912157418, + "learning_rate": 1.8169830869897743e-05, + "loss": 3.2752, + "step": 599 + }, + { + "epoch": 4.337349397590361, + "grad_norm": 1.259453956832135, + "learning_rate": 1.8163757214143993e-05, + "loss": 3.3074, + "step": 600 + } + ], + "logging_steps": 1, + "max_steps": 3000, + "num_input_tokens_seen": 0, + "num_train_epochs": 22, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1816727679664128.0, + "train_batch_size": 19, + "trial_name": null, + "trial_params": null +}